Compare commits

..
Author SHA1 Message Date
chatgpt-final-release-writer ffeaff69bc test(session-broker): replace channel smoke with shadow fixture 2026-07-26 01:35:16 +08:00
chatgpt-final-release-writer bc4d5c6a0a test(session): require task-bound adapter control auth 2026-07-26 01:34:23 +08:00
chatgpt-final-release-writer a62101340a security(codex): project adapter control credential 2026-07-26 01:34:22 +08:00
chatgpt-final-release-writer dc9157e679 security(openclaw): project adapter control credential 2026-07-26 01:34:21 +08:00
chatgpt-final-release-writer 6651753c7f feat(session-broker): bind native provider provisioning 2026-07-26 01:34:21 +08:00
chatgpt-final-release-writer 6494a666ec security(session): authenticate native adapter callers 2026-07-26 01:32:45 +08:00
chatgpt-final-release-writer 56ca465003 fix-gitops-validate-candidate-python-with-secret-scanner 2026-07-26 01:32:10 +08:00
chatgpt-final-release-writer 6a8f7c8668 test(session): keep native gates false until acceptance 2026-07-26 01:27:47 +08:00
chatgpt-final-release-writer 486e25d217 fix(codex): bind exact candidate credential reference 2026-07-26 01:27:46 +08:00
chatgpt-final-release-writer 88aa2f89d9 fix(openclaw): bind exact candidate credential reference 2026-07-26 01:27:46 +08:00
chatgpt-final-release-writer 8d9e8cba5d fix(session): defer gate truth until lifecycle acceptance 2026-07-26 01:27:45 +08:00
chatgpt-final-release-writer 12fca283c5 test(session-broker): verify native provider identity binding 2026-07-26 01:24:47 +08:00
chatgpt-final-release-writer 349f952be5 feat(codex): add isolated candidate app-server unit 2026-07-26 01:24:47 +08:00
chatgpt-final-release-writer 89bec6de6c feat(openclaw): add hardened candidate native adapter unit 2026-07-26 01:24:46 +08:00
chatgpt-final-release-writer 34d04a412a feat(codex): add candidate credential login projection 2026-07-26 01:24:45 +08:00
chatgpt-final-release-writer dbf0ccfdf7 feat(openclaw): add native task-bound session adapters 2026-07-26 01:24:44 +08:00
chatgpt-final-release-writer e08b5ee05f feat-gitops-add-exact-candidate-source-content-profile 2026-07-26 01:23:38 +08:00
chatgpt-final-release-writer 828ad998e6 docs(release): bind ChatGPT final release candidate 2026-07-26 01:09:57 +08:00
chatgpt-final-release-writer 1bc55343c8 Merge branch 'refs/heads/integration/openclaw-real-dispatch-session-broker-20260725' into patch/chatgpt-session-broker-final-release-20260726 2026-07-26 01:09:35 +08:00
chatgpt-final-release-writer 5fb2b08627 test: verify task-bound Stage A writer 2026-07-26 01:03:10 +08:00
AIOS Candidate Integration dcbcf93748 Merge Candidate caller authorization hardening 2026-07-26 00:24:55 +08:00
AIOS Candidate Integration 54e7dac80a security: authorize candidate owner signer callers 2026-07-26 00:23:48 +08:00
AIOS Candidate Integration 658ddbd3e9 Merge Candidate owner signer separation into dormant integration 2026-07-25 23:09:34 +08:00
AIOS Candidate Integration d31dd8a31b security: separate candidate owner approval signer 2026-07-25 23:07:22 +08:00
AIOS Candidate Integration f0a9b943ac merge: integrate session broker candidate security fixes
# Conflicts:
#	VERSION
#	versions/V2R1C1.json
2026-07-25 19:52:56 +08:00
chatgpt-gitops-bot e45a775af2 fix(candidate): harden broker approval and Gitea trust 2026-07-25 19:44:09 +08:00
AIOS Candidate Writer ebf33ba34a fix(task-plane): emit ISO session expiry 2026-07-25 18:49:00 +08:00
AIOS Candidate Writer 1c1aa1700b feat(gitops): add scoped Gitea grant lifecycle 2026-07-25 18:44:10 +08:00
AIOS Candidate Writer fd8bea6a23 feat(gitops): add revocable Gitea credential projection 2026-07-25 18:39:03 +08:00
AIOS Candidate Writer bd9cdd8daf feat(gitops): add revocable Gitea credential projection 2026-07-25 18:39:03 +08:00
AIOS Candidate Writer c48ea38711 feat(gitops): add revocable Gitea credential projection 2026-07-25 18:39:03 +08:00
AIOS Candidate Writer c4f2ac8903 test(candidate): verify test_candidate_runtime.py 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 47af809a8b feat(gitops): add candidate candidate_writer.py 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 77eb2aeda9 feat(task-plane): add candidate candidate_session_broker.py 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer d57772ad3e feat(task-plane): add candidate candidate_common.py 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 838a8ed69f feat(gitops): add candidate bootstrap_candidate_runtime.py 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 51b98041d9 feat(openclaw): add task-plane task-plane.js 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 4398caaedf feat(openclaw): add task-plane sandbox.js 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 0c0be7abc3 feat(openclaw): add task-plane mock.js 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer f96b712b26 test(candidate): verify dispatch.test.js 2026-07-25 18:35:21 +08:00
AIOS Candidate Writer 8f55eff11d feat(openclaw): add task-plane session-broker-client.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 56d675166a feat(openclaw): add task-plane package.json 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer d3b0307159 feat(openclaw): add task-plane openclaw.plugin.json 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 0e832bbe9a feat(openclaw): add task-plane index.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 04ab2db654 feat(openclaw): add task-plane task-plane.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer bc18ae4446 feat(openclaw): add task-plane sandbox.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer ea74af9751 feat(openclaw): add task-plane mock.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 57c3ce6e96 feat(openclaw): add task-plane session-broker-client.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 4b57a6268c feat(openclaw): add task-plane index.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 88dcebee78 feat(openclaw): add task-plane dispatch-errors.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 12a973c2cb feat(openclaw): add task-plane dispatch-contract.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 0babec654b feat(openclaw): add task-plane dispatch-audit.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer d787e98554 feat(openclaw): add task-plane dispatch-errors.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer c0450946e4 feat(openclaw): add task-plane dispatch-contract.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer b4c30e16e0 feat(openclaw): add task-plane dispatch-audit.js 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer f04473f657 docs(openclaw): document candidate session provisioning 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer dedef75f8c feat(gitops): add candidate aios-session-broker-bootstrap-writer-candidate.service 2026-07-25 18:35:20 +08:00
AIOS Candidate Writer 18c43e42a4 feat(gitops): add candidate aios-openclaw-session-broker-candidate.service 2026-07-25 18:35:20 +08:00
ChatGPT Release Governance 95b3728abd fix(wechat): pseudonymize owner provenance principal 2026-07-22 13:46:53 +08:00
ChatGPT Release Governance e1659069b1 fix(wechat): bind dispatch provider server-side 2026-07-22 13:34:40 +08:00
ChatGPT Release Governance 4b35eb52cb fix(wechat): bind protected dispatch provider schema 2026-07-22 13:21:47 +08:00
ChatGPT Release Governance 05835675b6 fix(wechat): enforce singleton Owner binding 2026-07-22 12:54:32 +08:00
ChatGPT Release Governance a1a3a021ef fix(wechat): bind protected Owner identity explicitly 2026-07-22 12:37:29 +08:00
ChatGPT Release Governance 40e21d3c07 fix(wechat): await inbound metadata before reply 2026-07-22 11:55:20 +08:00
ChatGPT Release Governance 46932c46ca fix(wechat): retry dispatch without re-recording inbound 2026-07-22 11:43:40 +08:00
ChatGPT Release Governance 9e0a40600b fix(wechat): retry transient reply session conflicts 2026-07-22 11:25:12 +08:00
ChatGPT Release Governance d54da54033 fix(wechat): propagate sender identity and isolate conversations 2026-07-22 10:40:56 +08:00
ChatGPT Release Governance 33152a7f52 fix(wechat): separate ordinary conversation from Owner provenance 2026-07-22 10:19:09 +08:00
ChatGPT Release Governance 3dd622b5a5 v2r1c2_guard_plan_oid_supersession 2026-07-22 04:24:27 +08:00
ChatGPT Release Governance f73052cd5c v2r1c2_audit_manifest_supersession 2026-07-22 04:19:55 +08:00
ChatGPT Release Governance 1b69e89718 v2r1c2_add_audited_not_started_retry 2026-07-22 04:17:53 +08:00
ChatGPT Release Governance f3c00d7294 v2r1c2_harden_provenance_caches 2026-07-22 03:53:22 +08:00
ChatGPT Release Governance 80e3f65cd6 v2r1c2_takeover_gate 2026-07-22 03:46:34 +08:00
ChatGPT Release Governance 0cf769ef67 fix(v2r1c2): auto-issue Owner provenance for protected dispatch 2026-07-22 03:33:41 +08:00
ChatGPT Release Governance 5e53203a61 feat(v2r1c2): add legal ChatGPT takeover provider 2026-07-22 03:25:49 +08:00
ChatGPT Release Governance cf5afdf4c0 docs(task): add concise OpenClaw online execution handoff 2026-07-22 02:46:26 +08:00
ChatGPT Release Governance b6e714e3fc docs(v2r1c2): add unified portal and portable executor contract 2026-07-22 02:36:31 +08:00
ChatGPT Release Governance 0022adf958 test(release): add V2R1C2 offline and online acceptance gate 2026-07-22 02:33:37 +08:00
ChatGPT Release Governance 22888c3d53 test(orchestration): cover portable executor release gates 2026-07-22 02:29:33 +08:00
ChatGPT Release Governance c2c9eb8d81 fix(orchestration): retry failed owner notifications idempotently 2026-07-22 02:26:12 +08:00
ChatGPT Release Governance 6df9c92020 fix(web): repair execution center script and truth projection 2026-07-22 02:23:56 +08:00
ChatGPT Release Governance 6bb8c530a4 feat(web): render portable executor execution center 2026-07-22 02:18:31 +08:00
ChatGPT Release Governance 024143efa5 feat(deploy): add V2R1C2 candidate environment template 2026-07-22 02:10:29 +08:00
ChatGPT Release Governance 06c6374126 feat(deploy): add isolated V2R1C2 portal candidate service 2026-07-22 02:07:44 +08:00
ChatGPT Release Governance 82177403f6 feat(orchestration): add portable execution plan lifecycle CLI 2026-07-22 02:04:52 +08:00
ChatGPT Release Governance ef074a0c97 feat(release): add V2R1C2 portable multi-provider execution plan 2026-07-22 02:00:00 +08:00
ChatGPT Release Governance 00fd375e4c feat(web): wire portable executor plans into V2R1C2 candidate 2026-07-22 01:54:45 +08:00
ChatGPT Release Governance 5b0c3eb404 feat(web): expose provider-neutral execution plan APIs 2026-07-22 01:51:12 +08:00
ChatGPT Release Governance 3161470bd2 fix(orchestration): activate dependent stages only after upstream gates pass 2026-07-22 01:46:28 +08:00
ChatGPT Release Governance 1852701236 feat(web): add execution-center capability and navigation 2026-07-22 01:39:46 +08:00
ChatGPT Release Governance 21fc8c60ed refactor(orchestration): authorize task API from dynamic Provider trust 2026-07-22 01:33:56 +08:00
ChatGPT Release Governance 77395fa9a0 feat(orchestration): add official portable executor providers 2026-07-22 01:29:46 +08:00
ChatGPT Release Governance 490ed4f65a feat(orchestration): add provider-neutral executor worker runtime 2026-07-22 01:26:54 +08:00
ChatGPT Release Governance d6d2407a0d feat(orchestration): add portable multi-provider execution plans 2026-07-22 01:22:48 +08:00
ChatGPT Release Governance db3fcb89a8 feat(orchestration): persist and migrate executor provider catalogs 2026-07-22 01:18:40 +08:00
ChatGPT Release Governance 20b7a41104 refactor(orchestration): make executor protocol provider-based and portable 2026-07-22 01:10:32 +08:00
ChatGPT Release Governance e739e67052 feat(orchestration): unify OpenClaw Hermes and Codex executor protocol 2026-07-22 01:05:56 +08:00
ChatGPT Release Governance 1e6c7b9ad8 feat(orchestration): add protected external task lifecycle API 2026-07-22 00:59:25 +08:00
ChatGPT Release Governance 1afbb11d3b feat(orchestration): add OpenClaw-compatible external task CLI 2026-07-22 00:54:49 +08:00
ChatGPT Release Governance 850beec8d7 feat(orchestration): add external task discovery read model 2026-07-22 00:49:45 +08:00
ChatGPT Release Governance fb11c71ec0 feat(orchestration): require owner notification receipts in external task gate 2026-07-22 00:42:50 +08:00
ChatGPT Release Governance 8acdd104bb feat(orchestration): add durable external task truth registry 2026-07-22 00:38:48 +08:00
ChatGPT Release Governance 43d77e520f feat(web): add tenant and Agent resource center to candidate portal 2026-07-22 00:34:16 +08:00
ChatGPT Release Governance a3f731d01c fix(web): bridge portal-only roles to domain read policy 2026-07-22 00:13:45 +08:00
ChatGPT Release Governance 8dba5b8c2e fix(web): provide unified portal HTML package boundary 2026-07-22 00:06:22 +08:00
ChatGPT Release Governance 74158908e8 feat(web): add V2R1C2 portal release entrypoint and resource aggregation 2026-07-22 00:04:12 +08:00
ChatGPT Release Governance ab36e36d5d feat(web): expose unified portal package 2026-07-22 00:00:17 +08:00
ChatGPT Release Governance c1b14753a3 feat(web): add tenant and Agent resource capabilities 2026-07-21 23:54:08 +08:00
ChatGPT Release Governance c62c8ee9f6 feat(web): replace read-only console with unified role-aware portal 2026-07-21 23:49:52 +08:00
ChatGPT Release Governance 9626e66e5b feat(web): add unified portal aggregation and protected action API 2026-07-21 23:44:06 +08:00
ChatGPT Release Governance b68e3c85a3 feat(web): add server-side role capability matrix 2026-07-21 23:39:20 +08:00
ChatGPT Release Governance 74014514da feat(web): create unified role-aware portal branch from V2R1C1 2026-07-21 23:17:54 +08:00
Codex 4e0e6dcb90 chore(release): close V2R1C1 companion validation metadata 2026-07-21 19:05:28 +08:00
Codex 0778a31ec0 chore(release): record OpenClaw v2 companion validation 2026-07-21 18:29:45 +08:00
Codex 80c4cbde03 release:prepare-V2R1C1-validation-metadata 2026-07-21 17:04:24 +08:00
Codex fb739f6e8f docs(hermes): preserve formal acceptance blocker 2026-07-21 13:59:01 +08:00
Codex e6da39a3cd docs(hermes): record final evidence and worktree blocker 2026-07-21 13:55:08 +08:00
Codex 95d2e52cb5 fix(hermes): reserve cancellation for control plane 2026-07-21 13:41:34 +08:00
Codex 283dec58ab fix(hermes): enforce minimum heartbeat lease duration 2026-07-21 13:21:09 +08:00
Codex 7de1fe80ac docs(hermes): retain key-id and rollback contracts 2026-07-21 13:19:21 +08:00
Codex 89a502b39b test(hermes): preserve validated ten-case release gate 2026-07-21 13:19:21 +08:00
Codex 61bec280e2 deploy(hermes): preserve bounded rollback readiness 2026-07-21 13:19:21 +08:00
Codex 1791c91c5b docs(hermes): define lifecycle contract and validation state 2026-07-21 13:13:15 +08:00
Codex e8c0f0250b test(hermes): cover live lifecycle and recovery matrix 2026-07-21 13:09:06 +08:00
Codex 94718308fc fix(hermes): normalize trusted runtime headers and conflicts 2026-07-21 13:09:06 +08:00
Codex a4cbed0f5f feat(hermes): persist and protect full runtime lifecycle 2026-07-21 13:09:06 +08:00
Codex 25c7740739 docs(hardening): refresh Gate A report with verified execution results 2026-07-21 12:39:53 +08:00
Codex 8bbb049c39 docs(hardening): index ADR-009 without inventing missing history 2026-07-21 12:36:22 +08:00
Codex 1707cc4953 docs(hardening): rebuild complete UR-001 to UR-022 traceability 2026-07-21 12:34:50 +08:00
Codex e397594200 docs(hardening): add Run Provenance and scoped Grant requirements 2026-07-21 12:31:58 +08:00
Codex 68b7f2c1d2 docs(hardening): align module contracts with hardened runtime and Grant model 2026-07-21 12:28:25 +08:00
Codex fda98e61f5 docs(hardening): record least-privilege Provenance decision 2026-07-21 12:16:22 +08:00
Codex ea9f599522 fix(hardening): scope CLI authorization to one Grant 2026-07-21 12:13:21 +08:00
Codex 1aabcd8b62 test(hardening): add least-privilege Grant isolation coverage 2026-07-21 12:04:02 +08:00
Codex 4d68af9524 test(hardening): upgrade runtime flows and add dispatch recovery coverage 2026-07-21 12:01:17 +08:00
Codex 467b127804 fix(hardening): give application a safe default Grant scope 2026-07-21 11:57:32 +08:00
Codex 50a73b211b fix(hardening): bind dispatch and runtime results to principal 2026-07-21 11:55:07 +08:00
Codex f14d4b6e14 feat(hardening): persist principal and runtime lookup in dispatch store 2026-07-21 11:51:01 +08:00
Codex fc8bd8c8d4 feat(hardening): build scoped Grant writers per service 2026-07-21 11:48:11 +08:00
Codex 382fe662a3 feat(hardening): add service-scoped least-privilege writer 2026-07-21 11:45:46 +08:00
Codex 4754e5762a fix(hardening): use constant-time fingerprint comparison 2026-07-21 11:42:08 +08:00
Codex ce7d35a811 config(hardening): add seven least-privilege Grant references 2026-07-21 11:37:58 +08:00
Codex 60ac7d9d0b refactor(hardening): make evidence tracking use least-privilege authorization interface 2026-07-21 11:34:43 +08:00
Codex 2a10d1cdd9 feat(hardening): add workflow and least-privilege Grant CLI 2026-07-21 11:31:51 +08:00
Codex 677ea738e7 fix(hardening): authorize Git content before modifying index 2026-07-21 11:27:28 +08:00
Codex 7154d62cca fix(hardening): export OpenClaw Ed25519 contract types 2026-07-21 11:24:35 +08:00
Codex 4e154c8baf feat(hardening): wire durable dispatch least-privilege grants and internal reconcile 2026-07-21 11:20:39 +08:00
Codex b848361079 feat(hardening): require least-privilege grants in production writer 2026-07-21 11:17:39 +08:00
Codex 74224cfbd5 feat(hardening): add least-privilege provenance child grants 2026-07-21 11:14:42 +08:00
Codex a7c09ba646 feat(hardening): upgrade OpenClaw command contract to Ed25519 v2 2026-07-21 11:10:21 +08:00
Codex f055cb74bb feat(hardening): persist dispatches and strictly bind runtime results 2026-07-21 11:04:59 +08:00
Codex 071a378de6 fix(hardening): close public runtime lifecycle bypass 2026-07-21 11:00:28 +08:00
Codex a492b15df6 feat(hardening): add durable dispatch repository 2026-07-21 10:53:32 +08:00
Codex a9f0a4359b patch(chatgpt): start full Gate A hardening 2026-07-21 10:46:59 +08:00
Codex 6a9fab894a docs(traceability): add run provenance implementation matrix 2026-07-21 10:30:54 +08:00
Codex e9111dea47 deploy(provenance): add mandatory operation authorization wrapper 2026-07-21 10:30:40 +08:00
Codex d25fbfa61e test(provenance): add signature lifecycle replay and seven-path gate coverage 2026-07-21 10:21:01 +08:00
Codex 6b03c47625 build(provenance): install Ed25519 runtime dependency 2026-07-21 10:16:28 +08:00
Codex 770fe1ef66 docs(aios-v2): add ADR-007 run provenance control 2026-07-21 10:12:03 +08:00
Codex 7a025430f9 config(provenance): add production environment references 2026-07-21 10:11:56 +08:00
Codex d079da4029 feat(provenance): export trusted provenance APIs 2026-07-21 10:11:49 +08:00
Codex b8f7dc4112 feat(provenance): wire production gate into API application 2026-07-21 10:07:19 +08:00
Codex 947cdaff42 feat(provenance): add issuer authorization revoke and status CLI 2026-07-21 10:00:02 +08:00
Codex 83b0c8bd74 feat(provenance): add deployment and rollback operation gate factory 2026-07-21 09:56:50 +08:00
Codex fbd880cf8c feat(provenance): add controlled Git writer with operation policy 2026-07-21 09:46:40 +08:00
Codex 819ac94c9f feat(provenance): enforce authorization before evidence writes 2026-07-21 09:42:25 +08:00
Codex b02401e60d feat(provenance): enforce signed provenance before runtime dispatch 2026-07-21 09:39:33 +08:00
Codex cbb2e232f5 feat(provenance): implement Ed25519 issuer persistent store and seven-path writer 2026-07-21 09:33:07 +08:00
Codex 9e46ac0504 patch(codex): start trusted run provenance issuer store and writer blocker resolution 2026-07-20 20:11:59 +08:00
Codex ba7669c3b4 docs(aios-v2): 更新监督状态与阻塞处置清单 2026-07-20 17:22:32 +08:00
Codex 634f6b164f docs(candidate): 新增完整中文生产候选报告 2026-07-20 12:06:55 +08:00
Codex c9ce12d102 deploy(candidate): 新增中文全量验收入口 2026-07-20 12:05:38 +08:00
Codex db50d2fa5a tasks(aios-v2): 完整中文化 Codex 生产监督任务 2026-07-20 12:04:43 +08:00
Codex 63fd23a464 tasks(aios-v2): 完整中文化 OpenClaw 生产部署任务 2026-07-20 12:04:11 +08:00
Codex 2e03ed74f6 feat(governance): 新增文档与代码匹配门禁 2026-07-20 12:03:36 +08:00
Codex b86f51c9ab docs(aios-v2): 新增 ADR-006 候选持久化策略 2026-07-20 12:01:49 +08:00
Codex 09448a5d3d docs(aios-v2): 完整中文化 ADR-005 2026-07-20 12:01:05 +08:00
Codex 18c719b2c6 docs(aios-v2): 完整中文化 ADR-004 2026-07-20 12:00:39 +08:00
Codex b0a78fa9a8 docs(aios-v2): 完整中文化 ADR-003 2026-07-20 12:00:07 +08:00
Codex 0aca7dbcfc docs(aios-v2): 完整中文化 ADR-002 2026-07-20 11:59:34 +08:00
Codex 3f84d8991e docs(aios-v2): 完整中文化 ADR-001 2026-07-20 11:59:10 +08:00
Codex 5ac8f3ea6f docs(aios-v2): 完整中文化 ADR 索引 2026-07-20 11:58:39 +08:00
Codex bfb1c2fd52 docs(aios-v2): 新增完整中文文档治理规范 2026-07-20 11:57:51 +08:00
Codex cbfe1211c1 docs(aios-v2): 将文档索引完整转换为中文 2026-07-20 11:56:30 +08:00
Codex efd99e620c docs(aios-v2): add ADR-004 tenant isolation decision 2026-07-20 11:53:04 +08:00
Codex f23b694ad3 tasks(aios-v2): add Codex production supervisor task 2026-07-20 11:46:43 +08:00
Codex f97dea55ac tasks(aios-v2): add OpenClaw production deployment task 2026-07-20 11:46:39 +08:00
Codex efd08d7771 docs(aios-v2): add ADR-003 GitOps-only flow 2026-07-20 11:46:31 +08:00
Codex ff6cb2e217 docs(aios-v2): add ADR-005 documentation sync gate 2026-07-20 11:45:16 +08:00
Codex d774620fea docs(aios-v2): add ADR-002 runtime decoupling decision 2026-07-20 11:45:12 +08:00
Codex b26ff010fc docs(aios-v2): add ADR-001 control plane decision 2026-07-20 11:45:09 +08:00
Codex 4b49f2ba4b docs(aios-v2): add ADR index 2026-07-20 11:45:04 +08:00
Codex b4b8fe8828 docs(aios-v2): add traceability matrix 2026-07-20 11:43:46 +08:00
Codex 4e8ab051a0 docs(aios-v2): add module contracts 2026-07-20 11:41:39 +08:00
Codex f61e35b218 docs(aios-v2): add migration and delivery strategy 2026-07-20 11:34:33 +08:00
Codex b2f90f24a3 docs(aios-v2): add target architecture 2026-07-20 11:32:16 +08:00
Codex 6721eb4752 docs(aios-v2): add user requirements baseline 2026-07-20 11:29:07 +08:00
Codex a9e4fd1e40 docs(aios-v2): establish architecture source of truth 2026-07-20 11:24:12 +08:00
Codex 621750976a deploy(candidate): add guarded release rollback 2026-07-20 11:22:04 +08:00
Codex 5359e88806 feat(candidate): expose sanitized GitOps status API 2026-07-20 11:19:37 +08:00
Codex 76636931ba feat(candidate): add sanitized GitOps status provider 2026-07-20 11:17:18 +08:00
Codex 180c1fc66e deploy(candidate): add end-to-end healthcheck 2026-07-20 11:14:53 +08:00
Codex c0ff052dab deploy(candidate): add Docker Compose runtime 2026-07-20 11:12:42 +08:00
Codex 94cffb6ba3 deploy(candidate): add hardened container image 2026-07-20 11:10:36 +08:00
Codex 9ad5628e69 deploy(candidate): add environment configuration template 2026-07-20 11:08:37 +08:00
Codex 6d397a7894 deploy(candidate): add hardened systemd service 2026-07-20 11:07:06 +08:00
Codex 165fea6ba9 fix(candidate): prevent Hermes completion heartbeat revision race 2026-07-20 11:05:45 +08:00
Codex d079e2087c test(candidate): add end-to-end runtime and persistence tests 2026-07-20 11:01:07 +08:00
Codex e3b36ebdcc feat(candidate): add production application entrypoint 2026-07-20 10:57:42 +08:00
Codex 5e791b11c0 feat(candidate): add tenant-safe web console 2026-07-20 10:54:43 +08:00
Codex 50be65b76e feat(candidate): add durable SQLite control-plane persistence 2026-07-20 10:50:31 +08:00
Codex 7bb86e30bf feat(candidate): export orchestration and execution tracking 2026-07-20 10:42:49 +08:00
Codex ea56b45b7e feat(candidate): add persistent agent execution tracking 2026-07-20 10:40:22 +08:00
Codex f53682da7a feat(candidate): add unified AIOS execution orchestrator 2026-07-20 10:38:06 +08:00
Codex 71884ac088 feat(candidate): add Hermes worker loop and lease heartbeat 2026-07-20 10:35:55 +08:00
Codex 969c278cb0 feat(candidate): implement Hermes queue and lease adapter 2026-07-20 10:34:25 +08:00
Codex 6fe2a1e036 feat(candidate): expose Hermes runtime package 2026-07-20 10:31:07 +08:00
Codex 9a60e0c68e feat(candidate): add Hermes runtime contracts 2026-07-20 10:27:47 +08:00
Codex 46f553ca11 feat(candidate): expose Hermes runtime boundary package 2026-07-20 10:17:02 +08:00
Codex 4f0a0c2184 feat(candidate): add OpenClaw audit callback sink 2026-07-20 10:07:54 +08:00
Codex c107b193d9 feat(candidate): add OpenClaw runtime health policy 2026-07-20 10:06:36 +08:00
Codex 2db7ced7a4 feat(candidate): add OpenClaw runtime transports 2026-07-20 10:01:59 +08:00
Codex 6361d9a334 feat(candidate): implement OpenClaw execution adapter 2026-07-20 09:59:53 +08:00
Codex 2cf54f04ef feat(candidate): expose OpenClaw adapter package 2026-07-20 09:56:06 +08:00
Codex f840ce5c94 feat(integration): add OpenClaw command contract 2026-07-20 09:49:15 +08:00
Codex 35e7b55490 integration(aios-v2): create CTO production candidate branch 2026-07-20 09:47:01 +08:00
Codex 1f8d1f23b3 feat(aios-v2): add tenant-aware HTTP control plane gateway 2026-07-20 02:24:19 +08:00
Codex e93011791e feat(aios-v2): add tenant-isolated control plane domain 2026-07-20 02:19:16 +08:00
Codex 4460564a48 feat(aios-v2): initialize control plane package 2026-07-20 01:11:11 +08:00
Codex 4d6658136e docs(task): add AIOS control plane gateway task contract 2026-07-20 01:06:11 +08:00
Codex 5767e665c2 task(codex): implement AIOS V2 control plane gateway v1 2026-07-20 01:06:04 +08:00
296 changed files with 31682 additions and 19219 deletions
@@ -0,0 +1,3 @@
d23bb1ec24a7f49359314e04cd2c04c8f38876e45f25a701506499d1b34f270f MANIFEST-AIOS-V2R1-HERMES-LIFECYCLE-20260721.json
5ce2894fdf8a22622954a1a10fb09fbab74af04f0260b249615c70236ff31731 RESULT-AIOS-V2R1-HERMES-LIFECYCLE-20260721.md
ca2ab3c22c2b2b33bbc03e59f1206b999ad1271de3e1938fd3a0b4234c613eef ../../../docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md
@@ -0,0 +1,44 @@
{
"schema_version": "aios.evidence.manifest.v1",
"generated_at": "2026-07-21T05:50:00Z",
"branch": "patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721",
"validated_oid": "95d2e52cb55c7b913e89bc6bed2bcdacf67512d4",
"evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z",
"evidence_hashes": {
"steps.tsv": "b2ad20585ba7f576e85657827a0b1db6f252887bbd73bcd718df38623e9d95cf",
"final-live-gate.log": "82040c674759dacf587658c5e936c313a1f50e8e2425be48ad891927befdf4fa",
"16R.log": "641246927a372ebaa9e6dde8b018b88275b2ba15a442473759b23fb1f215d9cf",
"15.log": "b0a474e2a74164f560c4f7572091911f32011c75faccd37a3c7315046275011e",
"13.log": "b9f637cca6e97ed893bf38530e05cd33b78e324c5e8865d4c602dfeac22a7710",
"12R2.log": "0c431f5f5f1c1b17acda160c917b08c7f4036485016c23e1236b9b6f4a78de67"
},
"validation": {
"candidate_tests": {"passed": 49, "failed": 0},
"hermes_lifecycle": {"passed": 17, "failed": 0},
"gate_b": {"passed": 10, "failed": 0},
"offline_acceptance": {"passed": 8, "failed": 0, "expected_warnings": 1},
"openclaw_real_http": "PASS",
"restart_recovery": "PASS",
"rollback_forward": "PASS",
"state_preservation": "PASS",
"final_health_corrected_16R": "PASS"
},
"git_gate": {
"oid_match": true,
"candidate_clean": true,
"active_controller_clean": true,
"locked": 0,
"prunable": 0,
"worktree_total": 88,
"worktree_dirty": 10,
"global_worktree_clean": false
},
"resolved_blockers": [],
"active_blockers": [
"BLK-LIVE-HERMES-FULL-LIFECYCLE-EVIDENCE-MISSING",
"BLK-GLOBAL-WORKTREE-CLEANLINESS"
],
"overall": "PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS",
"release_decision": "STOP_PREPRODUCTION",
"secrets_recorded": false
}
@@ -0,0 +1,16 @@
# AIOS V2R1 Hermes Lifecycle Result
- Branch: `patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721`
- Validated OID: `95d2e52cb55c7b913e89bc6bed2bcdacf67512d4`
- Evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z`
- Hermes blocker: `EVIDENCE_COMPLETE / FORMAL_CLOSURE_BLOCKED`
- Overall: `PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS`
- Release decision: `STOP_PREPRODUCTION`
Hermes lifecycle `17/17`, candidate `49/49`, Gate B `10/10`, offline acceptance `8/0/1`, OpenClaw real HTTP, restart recovery, rollback/forward, state preservation and corrected final health all passed at the validated OID. The Owner acceptance contract nevertheless forbids formally closing the Hermes blocker until every global gate also passes.
The candidate worktree and active Controller worktree are clean; local, worktree and Gitea OIDs match; locked/prunable are zero. The global authority currently has 10 dirty worktrees out of 88, so the Owner hard gate requiring every worktree to be clean fails.
No RC, Tag Approval Request, Tag, main mutation, force push, production traffic switch or secret disclosure was performed.
See `MANIFEST-AIOS-V2R1-HERMES-LIFECYCLE-20260721.json` and `docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md`.
@@ -0,0 +1,12 @@
# V2R1C1 Cleanup Closure
- `CLEANUP_REVIEW=PASS`
- `ARCHIVE_VALIDATION=PASS`
- `GLOBAL_WORKTREE_CLEAN=true`
- `global_dirty_count=0`
- `locked=0`
- `prunable=0`
- Portal Archive OID: `99671cc14d2631f989e0763dc882e4001c50a1ea`
- Spark Archive OID: `d97cd3642528bd3373fe4cf5161a5d99c0b9285f`
Closure evidence: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-blocker-clear-20260721T075647Z`.
@@ -0,0 +1,57 @@
{
"schema_version": "aios.v2r1c1.deployment-manifest.v1",
"vrc": "V2R1C1",
"release_branch": "release/AIOS-V2R1C1-20260721",
"old_release_oid": "80c4cbde03a82c30648a09b817bc2f03d5402936",
"validated_release_parent_oid": "0778a31ec073e7c90003ef091f1d093c16bf22e5",
"product_baseline_oid": "fb739f6e8ff9c031d319221ace68dce157694086",
"companion": {
"branch": "patch/openclaw/AIOS-V2R1C1-COMMAND-V2-COMPANION-20260721",
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
"oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
"plugin_version": "2.1.0-rc.4",
"contract_version": "aios.openclaw.command.v2",
"signature_algorithm": "Ed25519",
"verification_key_id": "openclaw-v2r1-candidate-ed25519",
"artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671"
},
"isolated_validation": {
"service": "aios-v2r1c1-openclaw-companion.service",
"account": "aios-v2r1c1-openclaw",
"listen": "127.0.0.1:28789",
"accept_v2": true,
"accept_v1": false,
"public_key_only": true,
"production_traffic_switched": false,
"result": "PASS"
},
"previous_plugin": {
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
"plugin_version": "2.1.0-rc.3",
"artifact_sha256": "d0fd11be4aec03eee9ca24bf1585d9ef3597254ad4b1db0d0137eab4456b5737"
},
"rollback": {
"production_plugin_unchanged": true,
"failed_isolated_attempts_rolled_back": true,
"previous_plugin_evidence": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z/00-baseline",
"previous_oid": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a",
"isolated_rollback_forward": "PASS",
"production_symlink_modified": false
},
"release_validation": {
"gate_a": "PASS",
"gate_b": "PASS",
"openclaw_v2_live": "PASS",
"openclaw_negative_live": "PASS",
"hermes_live": "PASS",
"restart_recovery": "PASS",
"rollback_forward": "PASS",
"final_health": "PASS",
"secret_violations": 0,
"global_dirty_count": 0,
"sync_status": "fully_synced"
},
"tag_status": "ABSENT",
"preproduction_status": "NOT_STARTED",
"production_status": "NOT_STARTED"
}
@@ -0,0 +1,55 @@
{
"schema_version": "aios.v2r1c1.release-evidence.v2",
"vrc": "V2R1C1",
"semver": "2.1.0-rc.1",
"product_baseline_oid": "fb739f6e8ff9c031d319221ace68dce157694086",
"old_release_oid": "80c4cbde03a82c30648a09b817bc2f03d5402936",
"validated_release_parent_oid": "0778a31ec073e7c90003ef091f1d093c16bf22e5",
"release_branch": "release/AIOS-V2R1C1-20260721",
"release_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-release-20260721",
"companion_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z",
"openclaw_companion": {
"branch": "patch/openclaw/AIOS-V2R1C1-COMMAND-V2-COMPANION-20260721",
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
"companion_oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
"plugin_version": "2.1.0-rc.4",
"contract_version": "aios.openclaw.command.v2",
"signature_algorithm": "Ed25519",
"verification_key_id": "openclaw-v2r1-candidate-ed25519",
"artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671"
},
"step13": {
"original_result": "FAIL_HTTP_401",
"original_diagnosis_manifest_sha256": "320017cbfc0f31392b4d0fb5996d0e32709982a967d102592ac45efdbdaad91f",
"remediated_result": "PASS",
"online_negative_evidence_sha256": "57ab8efd19d3bf659a65cbeda830785f6cea9172925a3cac9e027b9b842e644f",
"remediated_evidence_sha256": "5db59096c0586fcc0a51851d9a25d0a0b94f2bade45063fab16cc2a729f23130",
"task_state": "COMPLETED",
"dispatch_state": "COMPLETED",
"task_dispatch_audit_consistency": "PASS"
},
"release_validation": {
"static_revalidation": "PASS",
"static_evidence_sha256": "c33ffaf9a0f509d6e78bdfdc0848940c166b8a800940e259b7196adab04ec604",
"gate_a": "PASS",
"gate_b": "PASS",
"documentation_sync": "PASS",
"secret_scan_violations": 0,
"release_metadata": "PASS",
"hermes_live": "PASS",
"hermes_evidence_sha256": "e6553c99db55c3cdf9e16a4c1e6712064e00c41dc9965d0d179b6b1a2a1ad3ac",
"restart_recovery": "PASS",
"restart_evidence_sha256": "6031c92cd890dffd1de28ba75d81bed908e7da11a24aa129bcfde8efb23f0149",
"rollback_forward": "PASS",
"rollback_evidence_sha256": "f3d49c54e3f722facf68df2da3d82a9c82eb576f2c7c8dacb0f62c424d25737c",
"final_health": "PASS",
"final_health_evidence_sha256": "121cd52c0a4852b818e06be69211ae18b9fcccf976fa064e2a09c54eb8a01300",
"global_dirty_count": 0,
"sync_status": "fully_synced"
},
"validation_status": "PASS",
"tag_status": "ABSENT",
"preproduction_status": "NOT_STARTED",
"production_status": "NOT_STARTED",
"secrets_recorded": false
}
@@ -0,0 +1,52 @@
# V2R1C1 Validation Result
Status: `RELEASE_VALIDATION_PASS / FINAL_METADATA_COMMIT_REVALIDATION_REQUIRED`
Release decision: `STOP_PREPRODUCTION`
## OpenClaw Command v2 Companion
- Source OID: `83f8f878c7da5dd8263f2af2efa80750492e5cb3`
- Companion OID: `12d1c13170e0c5a691d67a9408e739e7a17064a3`
- Plugin version: `2.1.0-rc.4`
- Contract: `aios.openclaw.command.v2`
- Signature: `Ed25519`
- Artifact SHA256: `aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671`
- Companion unit/contract tests: `PASS`
- V1 fallback: `REJECTED`
- Isolated Gateway health: `PASS`
- Online positive/negative contract: `PASS`
- AIOS -> OpenClaw real HTTP: `PASS`
- Task state: `COMPLETED`
- Dispatch state: `COMPLETED`
- Task/Dispatch/Audit consistency: `PASS`
## Evidence linkage
- Original failed Release OID: `80c4cbde03a82c30648a09b817bc2f03d5402936`
- Original HTTP 401 diagnosis: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-release-20260721/pass1-80c4cbde/13-diagnosis`
- Original manifest SHA256: `320017cbfc0f31392b4d0fb5996d0e32709982a967d102592ac45efdbdaad91f`
- Companion evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z`
- Validated Release parent OID: `0778a31ec073e7c90003ef091f1d093c16bf22e5`
- Online negative evidence SHA256: `57ab8efd19d3bf659a65cbeda830785f6cea9172925a3cac9e027b9b842e644f`
- Remediated Step 13 evidence SHA256: `5db59096c0586fcc0a51851d9a25d0a0b94f2bade45063fab16cc2a729f23130`
## Release validation closure
- Gate A: `PASS`
- Gate B: `PASS`
- Documentation sync: `PASS`
- Secret violations: `0`
- Release Metadata: `PASS`
- Hermes live: `PASS`
- Restart recovery: `PASS`
- Previous ↔ V2R1C1 isolated rollback/forward: `PASS`
- Final health: `PASS`
- Global dirty / locked / prunable: `0 / 0 / 0`
- OID sync: `fully_synced`
- Production traffic switched: `false`
- Tag: `ABSENT`
## Remaining mandatory validation
本次最终元数据闭环提交将形成新的 Release OID。必须针对该最终 OID 再次复验 Gate A、Gate B、文档同步、Secret Scan、Release Metadata 和 OpenClaw 第 13 步正向/负向验证。复验通过前不得创建 Tag 或部署预生产/生产。
-486
View File
@@ -1,486 +0,0 @@
# Agent Production Deployment Requirements
## Status entering deployment
```yaml
code_development: COMPLETED
repository_commit: NOT_CREATED
production_deployment: NOT_STARTED
reason_repository_commit_missing:
current ChatGPT GitOps runtime has AIOS_GITOPS_WRITES_ENABLED=false
```
The code bundle is an input artifact. The Agent must place it on a non-main
integration branch, review it, run acceptance tests, merge it through protected
main and deploy the API adapter. The Agent must not regenerate or materially
rewrite the supplied implementation without recording the new diff and tests.
## Frozen production state
Before any change, verify:
```yaml
main_oid: 875d41c3101093149414292067fd700dc214d4d3
V2R1C5:
tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
peeled_target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
baseline_version: V2R1C5
baseline_status: PRODUCTION_DEPLOYED
target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
evidence_closure_oid: 5e2cf8276f5093f3352b9a3252c701a44c5ab807
```
If authoritative `main` no longer equals the approved base OID, stop with
`MANUAL_OWNER_REVIEW_REQUIRED / AUTHORIZED_BASE_OID_DRIFT`. Do not silently
rebase the bundle onto a different base.
## Bootstrap sequence — no additional Owner interaction
Use the following order so that the approved V2R1C6 base OID remains valid and
the bridge does not create its own authorization deadlock:
1. Verify the supplied archive/patch SHA-256.
2. Install the bundle into a temporary root-owned staging directory outside the
Git worktrees.
3. Start a localhost-only temporary instance of
`aios_authorized_task_writer_api.py` on a dedicated port or Unix socket.
4. Bind it to the existing authenticated Owner registry and the exact
`writer:provision` scope. Do not expose it through the public gateway.
5. Execute the live V2R1C6 provisioning request while `main` still equals
`875d41c3101093149414292067fd700dc214d4d3`.
6. Verify `READY_FOR_CODE_AUTHORING`, the exact branch OID, writer scope and
negative policy tests.
7. Use the newly created scoped writer to commit this reviewed bundle onto:
`agent/v2r1c6-mainline-reconciliation-20260805`.
8. Stop and remove the temporary bootstrap service and revoke its temporary
runtime credential. Preserve its signed grant receipt and audit logs.
9. Open a protected PR from the V2R1C6 branch. Deploy the permanent bridge only
from the reviewed merge commit.
The temporary service is a control-plane bootstrap, not a production release.
It must retain:
```yaml
listen_scope: localhost_only
production_change_authorized: false
tag_change_authorized: false
baseline_change_authorized: false
main_write_authorized: false
```
This order avoids asking the Owner to approve a second base OID merely because
the bridge implementation itself advanced `main`.
### Alternative platform-maintenance path
If policy prohibits a temporary localhost bootstrap service, use an existing
Owner-approved platform-maintenance executor to create:
```yaml
branch: patch/owner-authorization-writer-bridge-20260806
base_ref: refs/heads/main
base_oid: 875d41c3101093149414292067fd700dc214d4d3
direct_main_push: false
force_push: false
tag_write: false
baseline_write: false
production_deploy_during_integration: false
```
Merging that branch before V2R1C6 provisioning changes the authoritative base
OID. In that alternative only, a new exact Owner base-OID amendment is required.
The Agent must never substitute the newer `main` OID automatically.
## Files to install on the branch
Copy with the same relative paths:
```text
active-runtime/app/authorized_task_writer_provisioning.py
active-runtime/app/aios_authorized_task_writer_api.py
docs/gitops/authorized-task-writer-provisioning.md
docs/gitops/openapi-authorized-task-writer-fragment.yaml
deploy/systemd/aios-gitops-model-api-authorized-writer-bridge.conf.example
scripts/smoke_authorized_task_writer_provisioning.py
tests/test_authorized_task_writer_provisioning.py
```
Merge the OpenAPI fragment into:
```text
docs/gitops/openapi-chatgpt-actions.yaml
```
The final schema must expose:
```yaml
operationId: provisionAuthorizedTaskWriter
path: POST /api/task-writer/provision-authorized
x-openai-isConsequential: true
```
Do not deploy the fragment as a second standalone OpenAPI document.
## Required review of existing API integration
The adapter expects the existing API handler to provide:
```python
handler.need(scope)
handler.body()
handler.sendj(value, status=200)
api.H.do_POST
api.main()
```
Confirm these contracts against the branch before merge. If the live API has a
different authentication object shape, make the smallest adapter-only change
and rerun every test. The core provisioning policy must remain unchanged.
The API authorization registry must grant `writer:provision` only to the
authenticated Owner role. Agents and ordinary writer tokens must not receive
this scope.
## Privilege boundary
The API service must remain non-root.
Install a root-owned sudoers rule that allows the API service identity to run
only these exact commands with `sudo -n --`:
```text
/usr/local/libexec/aios-grant-signer-adapter
/usr/local/libexec/aios-grant-validator
/usr/local/libexec/aios-task-writer-provisioner
```
Do not allow:
```text
/bin/sh
/bin/bash
/usr/bin/env
/usr/bin/git
wildcard executable paths
SETENV
arbitrary environment preservation
```
The governed tools themselves must validate their `--grant-dir` and
`--result-json` paths. Their binaries must be root-owned, non-symlink, regular,
executable and not group/world writable.
The signer must access its private signing material only through a runtime
secret reference. No signing key or token may enter Git, API output, the
provisioning receipt or systemd environment text.
## Runtime paths and permissions
Create:
```text
/var/lib/aios-gitops/authorized-writer-bridge
/var/lib/aios-gitops/authorized-writer-bridge/receipts
/var/lib/aios-gitops/authorized-writer-bridge/locks
```
Required properties:
```yaml
owner: API service identity
mode: "0700"
symlink: false
persistent: true
```
The directory contains redacted receipts only. Temporary signed grant
directories are deleted after success or failure.
## Required staging environment
Configure the API service:
```text
AIOS_GITOPS_REPOSITORY_IDENTITY=aios/aios
AIOS_GITOPS_AUTHORITY_GIT_DIR=/data/aios-gitops/repo.git
AIOS_GITOPS_AUTHORIZED_WRITER_STATE_ROOT=/var/lib/aios-gitops/authorized-writer-bridge
AIOS_GITOPS_GRANT_SIGNER_ADAPTER=/usr/local/libexec/aios-grant-signer-adapter
AIOS_GITOPS_GRANT_VALIDATOR=/usr/local/libexec/aios-grant-validator
AIOS_GITOPS_TASK_WRITER_PROVISIONER=/usr/local/libexec/aios-task-writer-provisioner
AIOS_GITOPS_OWNER_PROVISION_SCOPE=writer:provision
AIOS_GITOPS_GOVERNED_USE_SUDO=true
AIOS_GITOPS_SUDO_PATH=/usr/bin/sudo
```
Use `aios_authorized_task_writer_api.py` as the API entrypoint. It delegates
all pre-existing routes and adds only the new endpoint.
## Pre-merge tests
Run from the repository root:
```bash
python3 -m unittest -v tests/test_authorized_task_writer_provisioning.py
python3 scripts/smoke_authorized_task_writer_provisioning.py
python3 -m py_compile \
active-runtime/app/authorized_task_writer_provisioning.py \
active-runtime/app/aios_authorized_task_writer_api.py
```
Required result:
```yaml
unit_tests:
total: 9
failures: 0
errors: 0
smoke: PASS
py_compile: PASS
```
Also run all existing GitOps API and isolated writer tests affected by:
```text
aios_chatgpt_actions_api
aios_isolated_writer_api
isolated_writer_authz
isolated_writer_token_registry
single_owner_governance
OpenAPI schema validation
```
Any regression blocks merge.
## Staging API acceptance
### Negative authentication
An Agent or non-Owner credential calling the endpoint must receive:
```yaml
http_status: 403
error: OWNER_AUTHORIZATION_REQUIRED
```
### Negative scope tests
Requests enabling any of the following must be denied before signer execution:
```text
production_change_authorized=true
tag_change_authorized=true
baseline_change_authorized=true
main_write_authorized=true
allowed_operations containing tag/main/baseline/admin operations
missing required denied operation
one_time_use=false
expiry over 1800 seconds
```
### Drift and conflict tests
Verify:
```yaml
wrong_base_oid:
http_status: 409
error: AUTHORIZED_BASE_OID_DRIFT
existing_unreceipted_target_branch:
http_status: 409
error: EXISTING_BRANCH_OID_CONFLICT
```
### Governed tool failures
Independently inject and verify fail-closed behavior for:
```text
signer unavailable
signer signature absent
validator signature_valid=false
validator signer_trusted=false
validator plan expired
provisioner grant_consumed=false
provisioner writer scope enables main/tag/baseline/force push
any required negative policy test false
```
None may create or modify a Git ref.
## Live V2R1C6 provisioning request
After protected merge and API deployment, authenticate as the Owner and submit
exactly:
```json
{
"task_id": "V2R1C6_TASK_SCOPED_WRITER_PROVISIONING",
"repository": "aios/aios",
"base_ref": "refs/heads/main",
"base_oid": "875d41c3101093149414292067fd700dc214d4d3",
"target_branch": "agent/v2r1c6-mainline-reconciliation-20260805",
"owner_authorization_reference": "chat-owner-authorization:v2r1c6:20260806",
"one_time_use": true,
"expires_in_seconds": 900,
"production_change_authorized": false,
"tag_change_authorized": false,
"baseline_change_authorized": false,
"main_write_authorized": false,
"allowed_operations": [
"create_worktree",
"create_target_branch_if_absent",
"commit_to_target_branch",
"push_target_branch"
],
"denied_operations": [
"direct_main_push",
"force_push",
"tag_create",
"tag_update",
"tag_delete",
"branch_delete",
"repository_admin",
"baseline_write",
"production_deploy",
"production_marker_write",
"history_rewrite"
]
}
```
This request must be executed by the localhost-only bootstrap instance before
the bridge code advances `main`. The endpoint must never infer “current main”.
If the Agent chooses the alternative merge-first path, it must stop after the
merge and obtain an exact Owner amendment for the new merge OID. It must not
silently replace the approved OID.
## Success response
Require:
```yaml
status: READY_FOR_CODE_AUTHORING
grant_consumed: true
branch: agent/v2r1c6-mainline-reconciliation-20260805
branch_oid: <exact amended authorized base OID>
base_oid: <same exact OID>
main_unchanged: true
writer_scope:
workspace_role: task-scoped-isolated-writer
writes_enabled: true
allowed_branch: agent/v2r1c6-mainline-reconciliation-20260805
allowed_base_oid: <exact amended authorized base OID>
allowed_routes:
- POST /api/commit-file
allow_main_write: false
allow_tag_write: false
allow_baseline_write: false
allow_force_push: false
```
All seven negative policy results must be true.
Submit the identical request a second time. It must return the same grant and
branch attestation with:
```yaml
idempotent: true
```
It must not run the provisioner again.
## Production postchecks
After API deployment and writer provisioning, independently verify:
```yaml
existing_routes_regression: PASS
new_endpoint: PASS
main_ref: expected reviewed merge commit
V2R1C5_tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
V2R1C5_peeled_target: aa60e891547abd7e215af7cf2bf3f21fd23541da
V2R1C5_baseline_unchanged: true
new_release_tag_created: false
production_baseline_changed: false
```
The deployment of this control-plane bridge does not authorize a V2R1C6
production release. It only enables scoped code authoring.
## Rollback
If the new API route fails:
1. Stop accepting new provisioning calls.
2. Restore the previous API entrypoint.
3. Restart and verify all existing routes.
4. Preserve receipts and logs.
5. Revoke any task writer capability already minted.
6. Do not delete a branch or rewrite a tag.
7. Revert the protected-main bridge commit through an ordinary reviewed revert
PR if source rollback is required.
## Required final Agent report
```yaml
STATUS: COMPLETED | PARTIALLY_COMPLETED | BLOCKED | FAILED
INTEGRATION:
branch:
commit:
protected_pr:
merge_commit:
files_changed:
TESTS:
unit:
smoke:
py_compile:
regression:
fault_injection:
DEPLOYMENT:
service:
entrypoint:
runtime_status:
endpoint_status:
rollback_verified:
PROVISIONING:
owner_authorization_reference:
approval_plan_id:
grant_id:
grant_digest_sha256:
signing_key_identity:
branch:
branch_oid:
workspace_path:
grant_consumed:
idempotent_replay:
CONSISTENCY:
main_oid:
V2R1C5_tag_oid:
V2R1C5_peeled_target_oid:
baseline_version:
baseline_changed:
tags_changed:
SECRETS:
runtime_secret_reference_used:
plaintext_secret_logged:
plaintext_secret_committed:
BLOCKERS:
GOVERNANCE:
force_push_used: false
tag_rewritten: false
direct_main_push: false
secrets_committed: false
owner_approval_respected: true
```
@@ -1,401 +0,0 @@
# Agent Deployment Requirements: Owner Authorization Broker V2
## Objective
Deploy the audited Owner Authorization Broker that closes the bootstrap gap
without issuing a new general-purpose Owner credential and without modifying
`/data/aios-gitops/runtime/secrets/gitops.tokens`.
The broker reuses one existing, non-wildcard Owner credential only to
authenticate the Owner identity through one pre-existing exact scope. It then
records an immutable task authorization event and directly invokes the
existing signed grant -> validator -> one-shot provisioner chain.
Production deployment of V2R1C6 is **not** authorized by this task.
## Fixed bindings
```yaml
task_id: V2R1C6_TASK_SCOPED_WRITER_PROVISIONING
repository: aios/aios
base_ref: refs/heads/main
base_oid: 875d41c3101093149414292067fd700dc214d4d3
target_branch: agent/v2r1c6-mainline-reconciliation-20260805
production_change_authorized: false
tag_change_authorized: false
baseline_change_authorized: false
main_write_authorized: false
```
The existing V2R1C5 objects are frozen:
```yaml
tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
peeled_target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
baseline_version: V2R1C5
baseline_status: PRODUCTION_DEPLOYED
```
## 1. Package verification
Verify `MANIFEST.sha256` before installation. Reject any mismatch.
Run:
```bash
python3 -m unittest -v \
tests/test_authorized_task_writer_provisioning.py \
tests/test_owner_authorization_broker.py
python3 scripts/smoke_authorized_task_writer_provisioning.py
python3 scripts/smoke_owner_authorization_broker.py
python3 -m py_compile \
active-runtime/app/authorized_task_writer_provisioning.py \
active-runtime/app/aios_authorized_task_writer_api.py \
active-runtime/app/owner_authorization_broker.py \
active-runtime/app/aios_owner_authorization_broker_api.py
```
All checks must pass.
## 2. Existing Owner credential selection
Read only the non-secret registry metadata. Select one existing credential
that satisfies all of the following:
```yaml
role: owner
wildcard_scope: false
account: exact known Owner identity
contains_exact_intake_scope: true
```
Use one existing exact scope such as `commit:create` or `file:write`. Prefer
the narrowest scope already assigned to the intended Owner.
Do not:
- use the historical wildcard Owner credential;
- add `writer:provision` to any bearer token;
- create or modify a bearer credential;
- print, copy or commit bearer-token material.
Record only:
```yaml
owner_account: <non-secret account>
credential_id: <non-secret ID, when available>
intake_scope: <one exact existing scope>
scope_readback_available: true|false
```
If `handler.need()` returns the exact scope set, configure the Owner account
allowlist and leave the credential ID allowlist empty.
If scope metadata is not returned, configure the exact non-secret credential
ID allowlist. If neither exact scope metadata nor a stable non-secret
credential ID can be proven, stop:
```yaml
STATUS: BLOCKED
REASON: OWNER_CREDENTIAL_SCOPE_NOT_PROVABLE
```
## 3. Staging installation
Install the four application modules in a root-owned staging directory:
```text
authorized_task_writer_provisioning.py
aios_authorized_task_writer_api.py
owner_authorization_broker.py
aios_owner_authorization_broker_api.py
```
The directory and files must not be group/world writable.
Prepare environment values:
```yaml
AIOS_GITOPS_OWNER_AUTHORIZATION_BROKER_ENABLED: "true"
AIOS_GITOPS_OWNER_AUTHORIZATION_INTAKE_SCOPES: <one exact existing scope>
AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_IDENTITIES: <exact owner account>
AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_CREDENTIAL_IDS: <exact ID or empty>
AIOS_GITOPS_OWNER_AUTHORIZATION_MAX_EXPIRY_SECONDS: "900"
AIOS_GITOPS_OWNER_AUTHORIZATION_STATE_ROOT:
/var/lib/aios-gitops/owner-authorization-broker
```
Use the existing signer, validator and provisioner paths. Do not change their
root governance configuration or disable signature checks.
Start a localhost-only staging instance on a temporary port. Do not replace
the production service yet.
## 4. Authentication fail-closed tests
The staging endpoint is:
```text
POST /api/governance/owner-authorizations
```
Required tests:
```yaml
unauthenticated:
expected: 401
wrong_role:
expected: 403
wrong_scope:
expected: 403
wildcard_owner:
expected: 403
error: WILDCARD_OWNER_CREDENTIAL_REJECTED
unallowlisted_owner:
expected: 403
error: OWNER_IDENTITY_NOT_ALLOWED
production_capability_true:
expected: 403
error: PRODUCTION_CAPABILITY_REJECTED
```
A connection failure, 404 or 500 is not an authorization-policy pass.
## 5. Formal provisioning request
Use the selected existing non-wildcard Owner credential through its runtime
secret reference. Never place the bearer token in the request body, command
line, shell history, output report or Git.
Request:
```json
{
"action": "AUTHORIZE_TASK_WRITER_PROVISIONING",
"task_id": "V2R1C6_TASK_SCOPED_WRITER_PROVISIONING",
"repository": "aios/aios",
"base_ref": "refs/heads/main",
"base_oid": "875d41c3101093149414292067fd700dc214d4d3",
"target_branch": "agent/v2r1c6-mainline-reconciliation-20260805",
"one_time_use": true,
"expires_in_seconds": 900,
"production_change_authorized": false,
"tag_change_authorized": false,
"baseline_change_authorized": false,
"main_write_authorized": false,
"allowed_operations": [
"create_worktree",
"create_target_branch_if_absent",
"commit_to_target_branch",
"push_target_branch"
],
"denied_operations": [
"direct_main_push",
"force_push",
"tag_create",
"tag_update",
"tag_delete",
"branch_delete",
"repository_admin",
"baseline_write",
"production_deploy",
"production_marker_write",
"history_rewrite"
]
}
```
The Owner authorization reference is generated by the broker. The caller must
not submit or invent one.
Expected result:
```yaml
status: READY_FOR_CODE_AUTHORING
owner_authorization_event_id: generated
owner_authorization_reference: generated
owner_authorization_digest_sha256: generated
owner_authorization_consumed: true
approval_plan_id: generated
grant_digest_sha256: generated
grant_consumed: true
branch_oid: 875d41c3101093149414292067fd700dc214d4d3
writer_scope:
workspace_role: task-scoped-isolated-writer
writes_enabled: true
allowed_branch: agent/v2r1c6-mainline-reconciliation-20260805
allowed_base_oid: 875d41c3101093149414292067fd700dc214d4d3
allow_main_write: false
allow_tag_write: false
allow_baseline_write: false
allow_force_push: false
```
## 6. Independent post-provisioning verification
Verify the Authority ref:
```bash
git --git-dir=/data/aios-gitops/repo.git rev-parse \
refs/heads/agent/v2r1c6-mainline-reconciliation-20260805
```
It must equal:
```text
875d41c3101093149414292067fd700dc214d4d3
```
Verify `main` remains unchanged, V2R1C5 tag object and peeled target remain
unchanged, and the Production Baseline remains V2R1C5.
Verify the broker audit event under:
```text
/var/lib/aios-gitops/owner-authorization-broker/events/
```
Requirements:
```yaml
status: CONSUMED
wildcard_scope_used: false
grant_consumed: true
permissions:
directory: "0700"
json_files: "0600"
```
Do not return bearer-token material in the report.
## 7. Commit the broker through the new writer
After `READY_FOR_CODE_AUTHORING`, use only the writer's
`POST /api/commit-file` route to put this code bundle on:
```text
agent/v2r1c6-mainline-reconciliation-20260805
```
Commit the bridge and broker as separate intentional commits when practical:
1. Owner-authorized task-writer bridge.
2. Audited Owner authorization broker and deployment docs.
Do not merge to `main` directly. Create a protected PR after branch commits
and tests are complete.
## 8. Permanent service deployment
Only after protected review and merge:
1. Install the reviewed files from the merge commit.
2. Apply a reviewed systemd drop-in based on the provided example.
3. Start the wrapper entrypoint:
`aios_owner_authorization_broker_api.py`.
4. Verify all existing API routes still work.
5. Verify the broker remains localhost/reverse-proxy constrained as intended.
6. Re-run authentication and policy tests.
7. Remove the temporary staging instance.
This permanent bridge deployment does not authorize a V2R1C6 production tag,
Baseline update or application deployment.
## 9. Fail-closed conditions
Stop with `BLOCKED` for any of the following:
- Authority `main` no longer equals the fixed base OID.
- Target branch exists at a different OID.
- Only a wildcard Owner credential can authenticate.
- Exact credential scope cannot be proven.
- Owner identity is not explicitly allow-listed.
- Signer, validator or provisioner self-test fails.
- Grant is not marked one-time and consumed.
- Writer allows main, tag, Baseline, force-push or branch-delete operations.
- Audit event contains sensitive material.
- V2R1C5 tag or Baseline changes.
## 10. Required Agent result
```yaml
STATUS: READY_FOR_CODE_AUTHORING | BLOCKED | FAILED
PACKAGE:
manifest_verified:
unit_tests:
smoke_tests:
py_compile:
OWNER_CREDENTIAL:
account:
credential_id:
intake_scope:
exact_scope_proven:
wildcard_used: false
token_logged: false
BROKER:
staging_listener:
endpoint_status:
event_id:
authorization_reference:
authorization_digest_sha256:
event_consumed:
audit_permissions_valid:
GRANT:
approval_plan_id:
grant_digest_sha256:
signer_identity:
signature_valid:
one_time_use:
consumed:
BRANCH:
name:
oid:
base_oid:
ref_exists:
worktree_path:
worktree_clean:
WRITER:
status:
writes_enabled:
allowed_branch:
allowed_base_oid:
allowed_routes:
main_write_denied:
tag_write_denied:
baseline_write_denied:
force_push_denied:
POSTCHECK:
main_unchanged:
V2R1C5_tag_unchanged:
baseline_unchanged:
REPOSITORY_INTEGRATION:
commit_oids:
protected_pr:
merged:
permanent_bridge_deployed:
BLOCKERS:
GOVERNANCE:
force_push_used: false
tag_rewritten: false
direct_main_push: false
secrets_committed: false
owner_approval_respected: true
```
-562
View File
@@ -1,562 +0,0 @@
# Agent execution requirements: V2R1C6 task identity overlay
## Required result
The Agent must return one of:
- `READY_FOR_CODE_AUTHORING`
- `BLOCKED`
- `FAILED`
The Agent may not report success until the task branch, isolated worktree and
task writer are independently verified.
This stage is **not** a production deployment. It must not modify `main`,
V2R1C5, tags, Registry, Production Baseline or production services.
## Fixed authority
```yaml
task_id: V2R1C6_TASK_SCOPED_WRITER_PROVISIONING
repository: aios/aios
base_ref: refs/heads/main
base_oid: 875d41c3101093149414292067fd700dc214d4d3
target_branch: agent/v2r1c6-mainline-reconciliation-20260805
owner_identity: aiman
one_time_use: true
maximum_ttl_seconds: 900
production_change_authorized: false
tag_change_authorized: false
baseline_change_authorized: false
main_write_authorized: false
```
## 1. Verify package
Verify the externally supplied package against the published SHA-256 values and
then verify every entry in `MANIFEST.sha256`.
Do not synthesize a missing archive. Use either the verified ZIP or TAR.GZ.
Required checks:
```yaml
package_hash_match: true
manifest_entries_match: true
unit_tests_pass: true
smoke_tests_pass: true
py_compile_pass: true
```
## 2. Create root-owned staging
Extract to a fresh directory such as:
```text
/var/lib/aios-gitops/staging/v2r1c6-task-identity-overlay-<nonce>
```
Requirements:
```yaml
owner: root
group: root
directory_mode: "0700"
files_not_world_writable: true
symlinks_rejected: true
```
Do not overwrite the active runtime tree.
## 3. Re-run target-host tests
From the staging root:
```bash
python3 -m unittest discover -s tests -v
python3 scripts/smoke_authorized_task_writer_provisioning.py
python3 scripts/smoke_owner_authorization_broker.py
python3 scripts/smoke_task_identity_overlay.py
python3 -m py_compile \
active-runtime/app/authorized_task_writer_provisioning.py \
active-runtime/app/owner_authorization_broker.py \
active-runtime/app/task_identity_overlay.py \
active-runtime/app/aios_authorized_task_writer_api.py \
active-runtime/app/aios_owner_authorization_broker_api.py \
active-runtime/app/aios_task_identity_overlay_api.py \
active-runtime/app/aios_task_identity_overlay_cli.py \
scripts/call_task_identity_overlay.py
```
Any failure is `BLOCKED`; do not proceed.
## 4. Prestart Git and production freeze checks
Read from the authority repository:
```bash
git --git-dir=/data/aios-gitops/repo.git rev-parse refs/heads/main
git --git-dir=/data/aios-gitops/repo.git \
show-ref --verify --quiet \
refs/heads/agent/v2r1c6-mainline-reconciliation-20260805
git --git-dir=/data/aios-gitops/repo.git rev-parse refs/tags/V2R1C5
git --git-dir=/data/aios-gitops/repo.git rev-parse 'refs/tags/V2R1C5^{}'
```
Expected:
```yaml
main_oid: 875d41c3101093149414292067fd700dc214d4d3
target_branch_exists: false
V2R1C5_tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
V2R1C5_peeled_target: aa60e891547abd7e215af7cf2bf3f21fd23541da
```
Read Baseline and require:
```yaml
version: V2R1C5
status: PRODUCTION_DEPLOYED
target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
evidence_closure_oid: 5e2cf8276f5093f3352b9a3252c701a44c5ab807
```
If `main` has drifted, return:
```yaml
STATUS: MANUAL_OWNER_REVIEW_REQUIRED
REASON: AUTHORIZED_BASE_OID_DRIFT
```
If the target branch already exists at another OID, return:
```yaml
STATUS: MANUAL_OWNER_REVIEW_REQUIRED
REASON: EXISTING_BRANCH_OID_CONFLICT
```
Do not delete, reset or force-push the branch.
## 5. Discover active secret references
The overlay does not read or modify `gitops.tokens`, but its issuer must compare
the new random secret against all active bearer secret references.
Discover references without printing secret contents. At minimum include the
currently active ChatGPT/GitOps bearer secret reference and any other bearer
files consumed by the active API.
Pass them as a comma-separated list in:
```text
AIOS_GITOPS_IDENTITY_OVERLAY_COLLISION_SECRET_REFS
```
Evidence must contain only paths and SHA-256 match counts, not token values.
If active secret references cannot be enumerated, return:
```yaml
STATUS: BLOCKED
REASON: ACTIVE_SECRET_REFERENCE_SET_UNRESOLVED
```
## 6. Install the transient systemd service
Use the provided template:
```text
deploy/systemd/aios-v2r1c6-task-identity-overlay.service.example
```
Substitute only:
- verified root-owned staging directory;
- verified active secret-ref path list.
Do not change task ID, repository, base OID, target branch or denied
capabilities.
The service must listen only on:
```text
127.0.0.1:19864
```
Before start, run:
```bash
systemd-analyze verify \
/etc/systemd/system/aios-v2r1c6-task-identity-overlay.service
```
Then:
```bash
sudo systemctl daemon-reload
sudo systemctl start aios-v2r1c6-task-identity-overlay.service
```
Confirm:
```bash
curl --fail --silent http://127.0.0.1:19864/healthz
```
Expected:
```yaml
service: aios-task-identity-overlay
status: active
global_token_registry_used: false
loopback_only: true
```
Do not expose the port externally.
## 7. Issue the one-time overlay
Use the root-only CLI. The authorization assertion is an audit label for this
already approved Owner task; it must not be described as an external signed
event.
Example:
```bash
sudo env \
PYTHONPATH=<staging>/active-runtime/app \
AIOS_GITOPS_IDENTITY_OVERLAY_STATE_ROOT=/var/lib/aios-gitops/task-identity-overlays \
AIOS_GITOPS_IDENTITY_OVERLAY_SECRET_ROOT=/run/aios-gitops/task-identity-overlays \
AIOS_GITOPS_IDENTITY_OVERLAY_TASK_ID=V2R1C6_TASK_SCOPED_WRITER_PROVISIONING \
AIOS_GITOPS_IDENTITY_OVERLAY_OWNER_IDENTITY=aiman \
AIOS_GITOPS_IDENTITY_OVERLAY_BASE_REF=refs/heads/main \
AIOS_GITOPS_IDENTITY_OVERLAY_BASE_OID=875d41c3101093149414292067fd700dc214d4d3 \
AIOS_GITOPS_IDENTITY_OVERLAY_TARGET_BRANCH=agent/v2r1c6-mainline-reconciliation-20260805 \
AIOS_GITOPS_IDENTITY_OVERLAY_COLLISION_SECRET_REFS=<verified-secret-ref-list> \
python3 <staging>/active-runtime/app/aios_task_identity_overlay_cli.py \
issue \
--ttl-seconds 900 \
--authorization-assertion-ref owner-session:V2R1C6:approved-20260806 \
--operator-identity <audited-agent-identity> \
--result-json /run/aios-gitops/v2r1c6-overlay-issued.json
```
The result must contain:
```yaml
status: OVERLAY_ACTIVE
idempotent: false
overlay_id: present
secret_ref: under /run/aios-gitops/task-identity-overlays
expires_at: within 900 seconds
```
It must not contain a token.
Verify:
```yaml
secret_file_mode: "0600"
metadata_contains_raw_token: false
token_hash_unique_across_configured_secret_refs: true
```
## 8. Negative tests
Before the valid request:
1. No Authorization header must return HTTP 401.
2. A random wrong bearer must return HTTP 401.
3. A request with `production_change_authorized=true` must be rejected.
4. A request with another base OID or branch must be rejected.
5. The valid overlay must remain `ACTIVE` after pre-auth request-validation
failures.
Do not use the global Owner or ChatGPT bearer credential for this endpoint.
## 9. Send the valid request
Use:
```text
deploy/v2r1c6-task-writer-authorization-request.json
```
Use the provided client so the bearer is not placed in argv, shell history or
logs:
```bash
sudo python3 <staging>/scripts/call_task_identity_overlay.py \
--secret-ref <secret_ref_from_issue_result> \
--request-json <staging>/deploy/v2r1c6-task-writer-authorization-request.json \
--url http://127.0.0.1:19864/api/governance/owner-authorizations \
--result-json /var/lib/aios-gitops/v2r1c6-overlay-provision-result.json
```
Required result:
```yaml
http_status: 200
status: READY_FOR_CODE_AUTHORING
owner_authorization_consumed: true
grant_consumed: true
identity_overlay_consumed: true
identity_overlay_secret_removed: true
branch: agent/v2r1c6-mainline-reconciliation-20260805
branch_oid: 875d41c3101093149414292067fd700dc214d4d3
```
The result must not include:
- bearer token;
- private key;
- signer secret;
- raw signature;
- credential value.
## 10. Independent acceptance
Verify the branch:
```bash
git --git-dir=/data/aios-gitops/repo.git \
rev-parse refs/heads/agent/v2r1c6-mainline-reconciliation-20260805
```
It must equal:
```text
875d41c3101093149414292067fd700dc214d4d3
```
Verify worktree evidence returned by the provisioner:
```yaml
branch: agent/v2r1c6-mainline-reconciliation-20260805
head_oid: 875d41c3101093149414292067fd700dc214d4d3
detached_head: false
worktree_clean: true
writer_status: active
writes_enabled: true
allowed_routes:
- POST /api/commit-file
allow_main_write: false
allow_tag_write: false
allow_baseline_write: false
allow_force_push: false
```
Run policy negative tests against the task writer and require explicit policy
denials for:
- main write;
- another branch;
- tag create/update;
- Baseline write;
- force push;
- branch delete.
Network errors, 404, 500 and stopped-service failures do not count as policy
denials.
## 11. Stop and clean up the overlay
After `READY_FOR_CODE_AUTHORING`:
```bash
sudo systemctl stop aios-v2r1c6-task-identity-overlay.service
sudo systemctl disable aios-v2r1c6-task-identity-overlay.service || true
sudo rm -f /etc/systemd/system/aios-v2r1c6-task-identity-overlay.service
sudo systemctl daemon-reload
```
Verify:
```yaml
overlay_listener_stopped: true
overlay_secret_removed: true
global_token_registry_unchanged: true
disabled_owner_record_unchanged: true
active_chatgpt_bot_record_unchanged: true
audit_metadata_retained: true
```
The root-owned staging directory may be retained until the code is committed,
then removed after checksum-confirmed repository integration.
## 12. Commit the developed code through the task writer
Only after writer acceptance, use `POST /api/commit-file` to commit the
verified package contents to:
```text
agent/v2r1c6-mainline-reconciliation-20260805
```
Commit in reviewable groups:
1. authorized task-writer bridge;
2. Owner authorization broker;
3. task identity overlay;
4. tests, docs, OpenAPI and deployment templates.
Do not include:
- package archives;
- runtime tokens;
- `/run` or `/var/lib` state;
- test result files containing host paths;
- secret references containing values;
- generated credentials.
Run the complete 40-test suite from the branch after commits.
## 13. Protected PR
Create a protected PR from:
```text
agent/v2r1c6-mainline-reconciliation-20260805
```
to:
```text
main
```
The PR must state:
- this change closes Owner authorization bootstrap gaps;
- the overlay is localhost-only and one-time;
- the global token registry is not modified;
- no production release is authorized;
- V2R1C5 tag and Baseline remain unchanged.
The Agent must not merge without the repository's normal protected review.
## 14. Required Agent report
```yaml
STATUS:
READY_FOR_CODE_AUTHORING | BLOCKED | FAILED
PACKAGE:
zip_sha256:
tar_gz_sha256:
manifest_entries:
manifest_matched:
TESTS:
unit_total:
unit_passed:
smoke_bridge:
smoke_broker:
smoke_overlay:
py_compile:
PRESTART:
main_oid:
target_branch_previously_absent:
V2R1C5_tag_oid:
V2R1C5_peeled_target:
baseline_unchanged:
OVERLAY:
overlay_id:
status:
secret_ref:
secret_file_mode:
token_hash_unique:
global_registry_used: false
listener:
expires_at:
consumed:
secret_removed:
NEGATIVE_TESTS:
unauthenticated_401:
wrong_token_401:
production_capability_denied:
wrong_base_denied:
wrong_branch_denied:
OWNER_AUTHORIZATION:
event_id:
reference:
consumed:
GRANT:
approval_plan_id:
grant_id:
grant_digest_sha256:
signature_valid:
consumed:
BRANCH:
name:
oid:
base_oid:
ref_exists:
worktree_path:
worktree_clean:
WRITER:
status:
writes_enabled:
allowed_branch:
allowed_base_oid:
allowed_routes:
main_write_denied:
tag_write_denied:
baseline_write_denied:
force_push_denied:
REPOSITORY_INTEGRATION:
commits:
tests_after_commit:
protected_pr:
merged: false
POSTCHECK:
main_unchanged:
V2R1C5_tag_unchanged:
baseline_unchanged:
global_token_registry_unchanged:
overlay_listener_stopped:
overlay_secret_removed:
SECRETS:
plaintext_logged: false
plaintext_committed: false
BLOCKERS:
GOVERNANCE:
force_push_used: false
tag_rewritten: false
direct_main_push: false
secrets_committed: false
owner_approval_respected: true
```
## Fail-closed conditions
Return `BLOCKED` and stop on any of:
- authoritative main OID drift;
- target branch conflict;
- inability to enumerate active secret references;
- secret hash collision;
- overlay not bound to the exact task/base/branch;
- non-loopback listener;
- raw secret in result or logs;
- Owner Authorization Broker event not created;
- signer/validator/provisioner failure;
- grant not consumed;
- branch OID mismatch;
- writer exposes main/tag/Baseline/force-push permissions;
- V2R1C5 tag or Baseline changes.
Never fall back to the shared `gitops-write-bot.token`, a wildcard credential,
manual `gitops.tokens` edits or a direct Git ref write.
+394
View File
@@ -0,0 +1,394 @@
# AIOS V2R1 生产候选报告
- 候选版本:`V2R1C0-candidate`
- 候选分支:`integration/aios-v2r1-cto-production-candidate-20260720`
- 报告语言:中文
- 架构负责人:AIOS V2 CTO
- 当前状态:代码与文档闭环已完成;精确 Commit 测试、真实 Runtime 联调和预发布验证待执行
## 1. 执行摘要
AIOS V2R1 Candidate 已完成以下核心建设:
- AIOS 唯一控制面;
- Tenant、Agent、Task、Policy、Approval 和 Audit 权威模型;
- SQLite WAL 候选持久化与重启恢复;
- Execution Orchestrator;
- OpenClaw 签名命令、Adapter、Transport、Health 和 Audit Callback;
- Hermes tenant/cell/profile 分区、Queue、Worker Lease、Heartbeat 和 Result;
- Agent Execution Evidence;
- Web Console;
- GitOps Status;
- systemd、Docker、Compose、Healthcheck 和 Rollback;
- 用户需求、目标架构、迁移策略、模块契约、追踪矩阵、文档治理和 ADR;
- 文档—代码匹配检查器;
- 全量验收入口;
- OpenClaw 预发布部署任务;
- Codex 架构监督和阻塞处理任务。
本报告不把“代码已提交”误报为“生产已验证”。以下状态仍需由无人值守任务执行并形成证据:
- 精确 Candidate Commit 的自动测试;
- 真实 OpenClaw Runtime 联调;
- Hermes 长任务、Worker 崩溃和 Lease Recovery 演练;
- systemd/Docker 预发布部署;
- 重启恢复与回滚演练;
- 本地仓库与 Gitea Candidate OID 一致验证;
- 身份代理、安全、性能和容量验证;
- Owner 对合并、Tag 和生产部署的批准。
## 2. 用户需求完成情况
| 需求 | 代码状态 | 测试状态 | 预发布状态 |
|---|---|---|---|
| AIOS 唯一控制面 | 已实现 | 已定义 | 待验证 |
| 复用 OpenClaw/Hermes/Agent Router | 已实现 | 已定义 | 待真实联调 |
| OpenClaw/Hermes 解耦 | 已实现 | 已定义 | 待旁路冻结验证 |
| 全面 Web 化 | 候选实现完成 | 冒烟测试待执行 | 待反向代理接入 |
| 多租户隔离 | 已实现 | Domain 负向测试已定义 | 待全链路安全验证 |
| 统一任务生命周期 | 已实现 | 已定义 | 待精确 Commit 执行 |
| 策略与审批 | 已实现 | 部分测试待补强 | 待身份代理验证 |
| 幂等与并发安全 | 已实现 | 基础测试已定义 | 待压力和并发验证 |
| 执行证据 | 已实现 | 已定义 | 待外部执行器持续回写 |
| GitOps 唯一流程 | 已实现并修复 Controller 冲突 | Runtime 部分验证 | 待双目标持续镜像证据 |
| 持久化与恢复 | 已实现 | 重启恢复测试已定义 | 待预发布演练 |
| 审计与合规 | 已实现候选 | 部分断言待补强 | 待不可变外部固化 |
| 密钥安全 | 引用模式已实现 | 基础扫描纳入验收 | 待 Secret Provider 联调 |
| 部署与回滚 | 资产完成 | 验收脚本已定义 | 待实际演练 |
| 文档与代码同步 | 已实现门禁 | 待精确 Commit 执行 | 待接入持续验收 |
## 3. 目标架构
```text
浏览器 / Web Console / Public API
|
v
AIOS 唯一控制面
Tenant | Agent | Task | Policy | Approval | Audit
|
v
Execution Orchestrator / Agent Router
/ \
v v
OpenClaw Adapter Hermes Boundary
| |
v v
OpenClaw Runtime Hermes Workers
\ /
v v
结果回写 + 审计 + 执行证据
```
权威边界:
- AIOS:租户、身份、Agent、任务、策略、审批、审计和执行证据;
- Agent Router:调度与路由;
- OpenClaw:签名命令执行、取消、状态、健康和回调;
- Hermes:队列、Worker、Lease、Heartbeat 和结果;
- Web:只调用 AIOS API;
- GitOps:所有代码、文档、部署和修复变更入口。
## 4. 实现清单
### 4.1 Control Plane
```text
active-runtime/app/aios_v2/control_plane.py
active-runtime/app/aios_v2/persistence.py
active-runtime/app/aios_v2/gateway.py
active-runtime/app/aios_v2/app.py
active-runtime/app/aios_v2/orchestrator.py
active-runtime/app/aios_v2/execution_tracking.py
active-runtime/app/aios_v2/gitops_status.py
active-runtime/app/aios_v2/console.py
```
### 4.2 OpenClaw
```text
active-runtime/app/aios_openclaw/contract.py
active-runtime/app/aios_openclaw/adapter.py
active-runtime/app/aios_openclaw/transport.py
active-runtime/app/aios_openclaw/health.py
active-runtime/app/aios_openclaw/callback.py
```
### 4.3 Hermes
```text
active-runtime/app/aios_hermes/contract.py
active-runtime/app/aios_hermes/adapter.py
active-runtime/app/aios_hermes/worker.py
```
### 4.4 测试与治理
```text
tests/aios_v2_candidate/test_candidate_flow.py
tools/aios_v2_docs_code_check.py
deploy/aios-v2/acceptance/run-all.sh
```
### 4.5 部署
```text
deploy/aios-v2/systemd/aios-v2.service
deploy/aios-v2/env/aios-v2.env.example
deploy/aios-v2/docker/Dockerfile
deploy/aios-v2/docker/compose.yaml
deploy/aios-v2/healthcheck/check.sh
deploy/aios-v2/rollback/rollback.sh
```
### 4.6 文档与任务
```text
docs/aios-v2/
tasks/openclaw-production-deploy-task.yaml
tasks/codex-production-supervisor-task.yaml
```
## 5. 多租户与安全设计
### 5.1 权威上下文
```text
tenant_id
principal_id
session_id
trace_id
task_id
policy_version
idempotency_key
```
### 5.2 OpenClaw
- HMAC-SHA256 规范化签名;
- 签名绑定 tenant/task/trace/action/payload/idempotency/time;
- Runtime Result 身份字段必须匹配;
- Secret 只通过受保护文件或引用解析。
### 5.3 Hermes
- tenant/cell/profile 分区;
- Worker Lease 与 Heartbeat;
- revision 乐观并发;
- Lease 过期自动回到 QUEUED;
- Worker 完成前停止 Heartbeat,避免 revision 竞态。
### 5.4 Web/API
- 可信代理注入 `X-AIOS-*`;
- 浏览器不选择租户;
- CSP、no-store、nosniff、DENY frame、no-referrer;
- 应用端口不得直接暴露公网。
### 5.5 GitOps
- Controller detached + clean;
- 禁止 fetch 到已检出本地分支;
- 所有修改进入分支、Commit、测试和统一审查;
- 明文 Secret 门禁;
- 文档变化与代码变化同步门禁。
## 6. 持久化策略
候选版:
- SQLite WAL;
- `synchronous=FULL`;
- `BEGIN IMMEDIATE`;
- 原子 Snapshot;
- schema version;
- 状态目录与代码版本分离;
- Execution Evidence 租户分区原子 JSON。
已知限制:
- 单进程候选优先;
- 尚无生产 RLS、多实例 HA、PITR 和容量证据;
- 后续必须通过新 ADR 迁移到生产数据层。
## 7. 测试与验收
### 7.1 文档—代码匹配
```bash
python3 tools/aios_v2_docs_code_check.py \
--base-ref integration/aios-v2r1-cto-production-candidate-20260720
```
### 7.2 候选测试
```bash
python3 -m unittest discover \
-s tests/aios_v2_candidate \
-p 'test_*.py' \
-v
```
覆盖:
- OpenClaw 完整执行;
- Hermes 完整执行;
- 跨租户拒绝;
- SQLite 重启恢复;
- Execution Evidence。
### 7.3 全量验收
```bash
bash deploy/aios-v2/acceptance/run-all.sh
```
可选在线健康检查:
```bash
AIOS_RUN_LIVE_HEALTHCHECK=1 \
bash deploy/aios-v2/acceptance/run-all.sh
```
### 7.4 健康检查
```bash
bash deploy/aios-v2/healthcheck/check.sh
```
检查:
- systemd;
- HTTP Health;
- 状态目录;
- SQLite quick_check;
- GitOps detached/clean;
- Evidence 文件。
## 8. 部署方式
### 8.1 systemd
```text
/etc/aios-v2/aios-v2.env
/opt/aios/current
/var/lib/aios-v2
```
运行用户:`aios`。
安全选项:NoNewPrivileges、ProtectSystem、ProtectHome、PrivateTmp、Capability 限制。
### 8.2 Docker/Compose
- 非 root UID/GID;
- Read-only root filesystem;
- Drop all capabilities;
- 独立 State Volume;
- HTTP Healthcheck;
- Secret 文件只读挂载。
## 9. 回滚
```bash
bash deploy/aios-v2/rollback/rollback.sh <previous-release>
```
原则:
- 回滚前自动备份状态;
- 默认只回滚代码;
- 状态恢复需显式 `AIOS_V2_RESTORE_STATE=1`;
- 回滚后必须执行健康检查;
- 目标版本失败时自动恢复 previous release。
## 10. 无人值守任务
### OpenClaw
任务:`tasks/openclaw-production-deploy-task.yaml`
职责:
- 预发布部署;
- 健康检查;
- Runtime 联调;
- 小型部署与 Runtime Bug 修复;
- 证据回写。
### Codex
任务:`tasks/codex-production-supervisor-task.yaml`
职责:
- 架构监督;
- 阻塞分析和跨模块修复;
- 文档、测试和安全审查;
- 发布建议。
所有修改和阻塞必须进入 Git 和 Execution Evidence,最终统一审视。
## 11. 当前已知风险
| 风险 | 级别 | 当前处理 |
|---|---|---|
| 精确 Candidate Commit 尚未执行全部测试 | 高 | OpenClaw 执行,Codex 监督 |
| 真实 OpenClaw Runtime 尚未联调 | 高 | 预发布任务必须完成 |
| 候选 SQLite 不支持生产多实例 HA | 高 | Candidate 单实例;后续 ADR 迁移 |
| 身份代理 Header 防伪尚未环境验证 | 高 | 预发布安全检查 |
| Web Console 为候选只读 MVP | 中 | 生产前补充 E2E 与安全验证 |
| 部分策略负向、并发和审计测试待补强 | 中 | Codex 登记 blocker 并补充 |
| 本地/Gitea 自动双写状态仍需持续证明 | 中 | 验收记录 OID |
| 性能、容量和 SLO 尚无实测 | 中 | 预发布基准测试 |
| 外部不可变审计固化尚未实现 | 中 | 生产数据层阶段完成 |
## 12. 发布 Gate
### 允许进入预发布
条件:
- Candidate 分支可见;
- 文档完整;
- 任务合同已生成;
- 部署资产存在;
- 无明文 Secret。
### 允许进入合并审查
条件:
- 全量验收通过;
- OpenClaw/Hermes 联调通过;
- 重启和回滚通过;
- 严重/高风险 blocker 已解决;
- Codex 输出正向监督结论;
- 本地/Gitea OID 一致。
### 允许生产发布
条件:
- Owner 明确批准;
- Merge 与 Tag 通过受控流程;
- 生产配置、Secret 和反向代理准备完成;
- 发布窗口、观察指标、回滚负责人明确。
## 13. 当前结论
**代码和正式中文文档已经达到候选闭环状态,但尚不能宣称生产已验证。**
下一阶段由 OpenClaw 执行预发布部署和低风险 Bug 修复,由 Codex 监督架构、文档、安全、测试和阻塞。所有过程证据统一进入系统,满足 Gate 后再请求 Owner 批准。
## 14. 更新规则
以下变化必须更新本报告:
- Candidate Commit;
- 测试结果;
- 部署和回滚结果;
- Blocker 和风险;
- OpenClaw/Codex 任务状态;
- 文档—代码匹配状态;
- Gitea OID;
- 发布建议和 Owner 决策。
+8
View File
@@ -0,0 +1,8 @@
# Changelog
## V2R1C1 - 2.1.0-rc.1
- 固定发布基线为 `fb739f6e8ff9c031d319221ace68dce157694086`。
- 收口 Hermes 生命周期、Grant 隔离、Dispatch 恢复、运行证据和回滚/前滚验证。
- Portal Adapter 与 Spark Provisioning 仅保留在 Archive,不属于产品发布图。
- Future Incubator 保持隔离,不属于 V2R1C1 发布输入。
-10
View File
@@ -1,10 +0,0 @@
bec7da1adb75bf5feaa63c60ec6d03adf15d7508742a486207033d000f72d4ff AGENT_DEPLOYMENT_REQUIREMENTS.md
251b46e51ce09aa2fd843bee48ef24a5608f31d24c599841f086ceb25c1a1715 README.md
783f68ec4f00a11d43ceed536196bfedccaf6614f6db9805f7b36d24e5fa7bc2 TEST_RESULTS.json
c4b24b65195077716983acdc8611f705324413a74453858994ba51541957afd4 active-runtime/app/aios_authorized_task_writer_api.py
8a1935fa098d47ac02ce51bbd9fd5fad7cf9ab9374ea3de5f630679b96681d84 active-runtime/app/authorized_task_writer_provisioning.py
a05d4e8038fdb866ce17d4fb8a54798a268a1e8d44ff2cbc559069fa6ab2a667 deploy/systemd/aios-gitops-model-api-authorized-writer-bridge.conf.example
a60dac51802bff67c2cfff61acdeb0a3a05d74a4f6cb47e3f78295ceb5c6acd9 docs/gitops/authorized-task-writer-provisioning.md
2690f76452bceddda90c728278c600bcebd533db24776e2966423c5a8655e4b5 docs/gitops/openapi-authorized-task-writer-fragment.yaml
54e2845d2c3c026323ad45515e082d661e3b461feb3bfefedf5adc52db2d7b78 scripts/smoke_authorized_task_writer_provisioning.py
3cce2b744326fe12b89bcad3cd352c77738950964bf8519e72cb5e9c7a5dfbfc tests/test_authorized_task_writer_provisioning.py
-25
View File
@@ -1,25 +0,0 @@
{
"git_branch_created": false,
"git_commit_created": false,
"production_mutation": false,
"py_compile": {
"files": [
"active-runtime/app/authorized_task_writer_provisioning.py",
"active-runtime/app/aios_authorized_task_writer_api.py"
],
"status": "PASS"
},
"schema": "aios.authorized-task-writer-bridge-test-report.v1",
"secrets_included": false,
"smoke": {
"command": "python3 scripts/smoke_authorized_task_writer_provisioning.py",
"status": "PASS"
},
"status": "PASS",
"unit_tests": {
"command": "python3 -m unittest -v tests/test_authorized_task_writer_provisioning.py",
"errors": 0,
"failures": 0,
"total": 9
}
}
+1 -1
View File
@@ -1 +1 @@
V2R1C6
V2R1C2
-201
View File
@@ -1,201 +0,0 @@
"""Fail-closed Agent Pull Runner primitives for AIOS autonomy v1.
The runner owns task discovery and reporting only. It never accepts shell
strings: executors receive argv, an allowlisted cwd and an allowlisted env.
Durable state is intentionally small so restart recovery and duplicate
suppression can be verified without coupling the runner to one database.
"""
from __future__ import annotations
import json
import os
import random
import shutil
import subprocess
import tempfile
import time
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, Callable, Mapping, Protocol, Sequence
class RunnerError(RuntimeError):
"""Raised when a runner contract would be violated."""
@dataclass(frozen=True)
class RunnerConfig:
worker_id: str
capabilities: tuple[str, ...] = ()
long_poll_seconds: int = 30
fallback_seconds: int = 60
jitter_seconds: int = 5
max_backoff_seconds: int = 300
executable_allowlist: tuple[str, ...] = ()
working_directory_allowlist: tuple[str, ...] = ()
environment_allowlist: tuple[str, ...] = ()
@dataclass
class RunnerState:
inflight: dict[str, dict[str, Any]] = field(default_factory=dict)
terminal: dict[str, dict[str, Any]] = field(default_factory=dict)
class RunnerTransport(Protocol):
def register_worker(self, worker_id: str, capabilities: Sequence[str]) -> Mapping[str, Any]: ...
def heartbeat(self, worker_id: str) -> Mapping[str, Any]: ...
def long_poll(self, worker_id: str, timeout_seconds: int) -> Mapping[str, Any] | None: ...
def poll(self, worker_id: str) -> Mapping[str, Any] | None: ...
def claim(self, worker_id: str, task: Mapping[str, Any]) -> Mapping[str, Any]: ...
def renew(self, worker_id: str, task_id: str) -> Mapping[str, Any]: ...
def report_progress(self, worker_id: str, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]: ...
def report_result(self, worker_id: str, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]: ...
def report_evidence(self, worker_id: str, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]: ...
class JsonStateStore:
"""Atomic JSON state store for restart recovery."""
def __init__(self, path: str | os.PathLike[str]) -> None:
self.path = Path(path)
def load(self) -> RunnerState:
if not self.path.exists():
return RunnerState()
value = json.loads(self.path.read_text(encoding="utf-8"))
if not isinstance(value, dict):
raise RunnerError("runner state must be an object")
return RunnerState(
inflight=dict(value.get("inflight", {})),
terminal=dict(value.get("terminal", {})),
)
def save(self, state: RunnerState) -> None:
self.path.parent.mkdir(parents=True, exist_ok=True)
fd, name = tempfile.mkstemp(prefix=self.path.name + ".", dir=self.path.parent)
try:
with os.fdopen(fd, "w", encoding="utf-8") as handle:
json.dump({"inflight": state.inflight, "terminal": state.terminal}, handle, sort_keys=True)
handle.write("\n")
os.chmod(name, 0o600)
os.replace(name, self.path)
finally:
if os.path.exists(name):
os.unlink(name)
class AgentPullRunner:
"""Pull, claim, execute and report one task at a time."""
def __init__(
self,
config: RunnerConfig,
transport: RunnerTransport,
state_store: JsonStateStore | None = None,
*,
random_fn: Callable[[], float] = random.random,
) -> None:
if not config.worker_id.strip():
raise RunnerError("worker_id is required")
self.config = config
self.transport = transport
self.state_store = state_store
self.random_fn = random_fn
self.state = state_store.load() if state_store else RunnerState()
def _save(self) -> None:
if self.state_store:
self.state_store.save(self.state)
def register(self) -> Mapping[str, Any]:
return self.transport.register_worker(self.config.worker_id, self.config.capabilities)
def heartbeat(self) -> Mapping[str, Any]:
return self.transport.heartbeat(self.config.worker_id)
def discovery_delay(self, failures: int) -> float:
failures = max(0, int(failures))
base = min(self.config.max_backoff_seconds, self.config.fallback_seconds * (2**failures))
jitter = self.random_fn() * max(0, self.config.jitter_seconds)
return min(self.config.max_backoff_seconds, base + jitter)
def discover_once(self) -> Mapping[str, Any] | None:
try:
task = self.transport.long_poll(self.config.worker_id, self.config.long_poll_seconds)
except Exception:
task = None
if task is None:
task = self.transport.poll(self.config.worker_id)
if not task:
return None
task_id = str(task.get("task_id", ""))
if not task_id:
raise RunnerError("task_id is required")
if task_id in self.state.terminal:
return {"status": "duplicate_suppressed", "task_id": task_id}
claimed = dict(self.transport.claim(self.config.worker_id, task))
self.state.inflight[task_id] = claimed
self._save()
return claimed
def renew(self, task_id: str) -> Mapping[str, Any]:
if task_id not in self.state.inflight:
raise RunnerError("task is not inflight")
return self.transport.renew(self.config.worker_id, task_id)
def report_progress(self, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]:
if task_id not in self.state.inflight:
raise RunnerError("task is not inflight")
return self.transport.report_progress(self.config.worker_id, task_id, payload)
def report_evidence(self, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]:
if task_id not in self.state.inflight:
raise RunnerError("task is not inflight")
return self.transport.report_evidence(self.config.worker_id, task_id, payload)
def report_result(self, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]:
if task_id in self.state.terminal:
return {"status": "duplicate_terminal_suppressed", "task_id": task_id}
if task_id not in self.state.inflight:
raise RunnerError("task is not inflight")
result = dict(self.transport.report_result(self.config.worker_id, task_id, payload))
self.state.terminal[task_id] = {"result": result, "reported_at": time.time()}
self.state.inflight.pop(task_id, None)
self._save()
return result
def recover_after_restart(self) -> list[Mapping[str, Any]]:
recovered: list[Mapping[str, Any]] = []
for task_id in tuple(self.state.inflight):
recovered.append(self.renew(task_id))
return recovered
def validate_execution(self, argv: Sequence[str], cwd: str | os.PathLike[str], env: Mapping[str, str]) -> None:
if not argv or any(not isinstance(item, str) or not item for item in argv):
raise RunnerError("argv_only_execution_required")
if any(ch in argv[0] for ch in (";", "|", "&", "`", "\n")):
raise RunnerError("shell_syntax_denied")
executable = shutil.which(argv[0])
if not executable:
raise RunnerError("executable_not_found")
if self.config.executable_allowlist and not any(
os.path.realpath(executable).startswith(os.path.realpath(prefix).rstrip(os.sep) + os.sep)
or os.path.realpath(executable) == os.path.realpath(prefix)
for prefix in self.config.executable_allowlist
):
raise RunnerError("executable_not_allowlisted")
real_cwd = os.path.realpath(os.fspath(cwd))
if self.config.working_directory_allowlist and not any(
real_cwd == os.path.realpath(prefix)
or real_cwd.startswith(os.path.realpath(prefix).rstrip(os.sep) + os.sep)
for prefix in self.config.working_directory_allowlist
):
raise RunnerError("working_directory_not_allowlisted")
if self.config.environment_allowlist and any(key not in self.config.environment_allowlist for key in env):
raise RunnerError("environment_key_not_allowlisted")
def execute_argv(self, argv: Sequence[str], cwd: str | os.PathLike[str], env: Mapping[str, str]) -> Mapping[str, Any]:
self.validate_execution(argv, cwd, env)
completed = subprocess.run(list(argv), cwd=os.fspath(cwd), env=dict(env), shell=False, text=True, capture_output=True, check=False)
return {"returncode": completed.returncode, "stdout": completed.stdout, "stderr": completed.stderr}
@@ -1,36 +0,0 @@
"""Small operational CLI for the Agent Pull Runner contract."""
from __future__ import annotations
import argparse
import json
from agent_pull_runner import AgentPullRunner, RunnerConfig
class _NoopTransport:
def register_worker(self, worker_id, capabilities): return {"status": "registered", "worker_id": worker_id, "capabilities": list(capabilities)}
def heartbeat(self, worker_id): return {"status": "alive", "worker_id": worker_id}
def long_poll(self, worker_id, timeout_seconds): return None
def poll(self, worker_id): return None
def claim(self, worker_id, task): return task
def renew(self, worker_id, task_id): return {"status": "renewed", "task_id": task_id}
def report_progress(self, worker_id, task_id, payload): return {"status": "progress_recorded", "task_id": task_id}
def report_result(self, worker_id, task_id, payload): return {"status": "result_recorded", "task_id": task_id}
def report_evidence(self, worker_id, task_id, payload): return {"status": "evidence_recorded", "task_id": task_id}
def main() -> int:
parser = argparse.ArgumentParser(description="AIOS Agent Pull Runner")
parser.add_argument("--worker-id", default="self-test-worker")
parser.add_argument("--self-test", action="store_true")
args = parser.parse_args()
runner = AgentPullRunner(RunnerConfig(worker_id=args.worker_id, fallback_seconds=60), _NoopTransport())
if args.self_test:
print(json.dumps({"status": "PASS", "registration": runner.register(), "fallback_seconds": runner.config.fallback_seconds}, sort_keys=True))
return 0
print(json.dumps({"status": "READY", "worker_id": args.worker_id}, sort_keys=True))
return 0
if __name__ == "__main__":
raise SystemExit(main())
@@ -1,73 +0,0 @@
"""HTTP adapter for Owner-authorized task writer provisioning.
Run this module instead of aios_chatgpt_actions_api.py. All existing routes are
delegated unchanged; only POST /api/task-writer/provision-authorized is added.
"""
from __future__ import annotations
import os
import urllib.parse
import aios_chatgpt_actions_api as api
from authorized_task_writer_provisioning import (
AuthorizedTaskWriterProvisioner,
OwnerContext,
ProvisioningError,
)
_original_do_post = api.H.do_POST
_ENDPOINT = "/api/task-writer/provision-authorized"
def _owner_authorization(handler):
scope = os.getenv(
"AIOS_GITOPS_OWNER_PROVISION_SCOPE", "writer:provision"
)
auth = handler.need(scope)
if not auth:
return None
if auth.get("role") != "owner":
handler.sendj({"error": "OWNER_AUTHORIZATION_REQUIRED"}, 403)
return None
identity = str(auth.get("account") or "").strip()
if not identity:
handler.sendj({"error": "OWNER_IDENTITY_REQUIRED"}, 403)
return None
return auth
def _authorized_do_post(self):
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if path != _ENDPOINT:
return _original_do_post(self)
auth = _owner_authorization(self)
if not auth:
return
data = self.body()
owner_reference = str(data.get("owner_authorization_reference") or "")
try:
result = AuthorizedTaskWriterProvisioner().provision(
data,
OwnerContext(
identity=str(auth["account"]),
role=str(auth["role"]),
authorization_reference=owner_reference,
),
)
return self.sendj(result)
except ProvisioningError as exc:
body = {"error": exc.code}
if exc.details:
body["details"] = exc.details
return self.sendj(body, exc.status)
except Exception:
# Do not expose tool output, paths containing credentials, or traceback data.
return self.sendj({"error": "AUTHORIZED_WRITER_BRIDGE_INTERNAL_ERROR"}, 500)
api.H.do_POST = _authorized_do_post
if __name__ == "__main__":
api.main()
@@ -1,89 +0,0 @@
"""Governed API facade for branch-bound repair leases.
The facade is transport-neutral so the permanent control plane can expose it
through its existing authenticated loopback/API seam without creating a second
Git writer or a global credential registry.
"""
from __future__ import annotations
from typing import Any, Mapping
from branch_repair_lease import LeaseError, RepairLease, RepairLeaseManager, sanitized_lease_view
class BranchRepairLeaseAPI:
"""Validate operation envelopes and return sanitized lease metadata."""
def __init__(self, manager: RepairLeaseManager) -> None:
self.manager = manager
@staticmethod
def _required(request: Mapping[str, Any], name: str) -> Any:
value = request.get(name)
if value is None or value == "":
raise LeaseError(f"missing required field: {name}")
return value
@staticmethod
def _view(lease: RepairLease) -> dict[str, Any]:
return {"status": "ok", "lease": sanitized_lease_view(lease)}
def handle(self, request: Mapping[str, Any]) -> dict[str, Any]:
try:
operation = self._required(request, "operation")
owner = str(self._required(request, "owner_identity"))
if operation == "issue":
lease = self.manager.issue(
task_id=str(self._required(request, "task_id")),
owner_identity=owner,
branch=str(self._required(request, "branch")),
description=str(self._required(request, "description")),
allowed_paths=tuple(self._required(request, "allowed_paths")),
ttl_seconds=int(request.get("ttl_seconds", 3600)),
)
elif operation == "attach_existing_branch":
lease = self.manager.attach_existing_branch(
str(self._required(request, "lease_id")),
owner_identity=owner,
expected_head_oid=str(self._required(request, "expected_head_oid")),
)
elif operation == "authorize_commit":
lease = self.manager.authorize_commit(
str(self._required(request, "lease_id")),
owner_identity=owner,
expected_head_oid=str(self._required(request, "expected_head_oid")),
paths=tuple(self._required(request, "paths")),
content=request.get("content"),
)
elif operation == "record_commit":
lease = self.manager.record_commit(
str(self._required(request, "lease_id")),
owner_identity=owner,
expected_head_oid=str(self._required(request, "expected_head_oid")),
new_head_oid=str(self._required(request, "new_head_oid")),
paths=tuple(self._required(request, "paths")),
)
elif operation == "recover":
lease = self.manager.recover(
str(self._required(request, "lease_id")), owner_identity=owner
)
elif operation == "renew":
lease = self.manager.renew(
str(self._required(request, "lease_id")),
owner_identity=owner,
ttl_seconds=int(self._required(request, "ttl_seconds")),
)
elif operation == "complete":
lease = self.manager.complete(
str(self._required(request, "lease_id")), owner_identity=owner
)
elif operation == "revoke":
lease = self.manager.revoke(
str(self._required(request, "lease_id")), owner_identity=owner
)
else:
raise LeaseError("unsupported lease operation")
return self._view(lease)
except (LeaseError, TypeError, ValueError):
return {"status": "blocked", "error": "lease_request_rejected"}
@@ -1,48 +0,0 @@
"""Root-only CLI for the branch-bound repair lease API."""
from __future__ import annotations
import argparse
import json
import os
import sys
from pathlib import Path
from aios_branch_repair_lease_api import BranchRepairLeaseAPI
from branch_repair_lease import GitProbe, LeaseStore
from branch_repair_lease import RepairLeaseManager
def main() -> int:
parser = argparse.ArgumentParser(description="AIOS branch repair lease CLI")
parser.add_argument("--store", required=True)
parser.add_argument("--bare-repo", required=True)
parser.add_argument("--request-file")
parser.add_argument("--request-json")
args = parser.parse_args()
if hasattr(os, "geteuid") and os.geteuid() != 0:
print(json.dumps({"status": "blocked", "error": "root_required"}))
return 2
if bool(args.request_file) == bool(args.request_json):
print(json.dumps({"status": "blocked", "error": "one_request_source_required"}))
return 2
try:
raw = (
Path(args.request_file).read_text(encoding="utf-8")
if args.request_file
else str(args.request_json)
)
request = json.loads(raw)
if not isinstance(request, dict):
raise ValueError("request must be an object")
api = BranchRepairLeaseAPI(RepairLeaseManager(LeaseStore(args.store), GitProbe(args.bare_repo)))
response = api.handle(request)
print(json.dumps(response, ensure_ascii=True, sort_keys=True, separators=(",", ":")))
return 0 if response.get("status") == "ok" else 1
except Exception:
print(json.dumps({"status": "blocked", "error": "lease_cli_failed"}))
return 1
if __name__ == "__main__":
raise SystemExit(main())
@@ -1,69 +0,0 @@
"""CLI client for the governed local writer service."""
from __future__ import annotations
import argparse
import json
import os
import socket
import sys
def _parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Send one governed-local-writer request")
parser.add_argument("--socket", required=True, help="AF_UNIX socket path")
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument("--request", help="Request JSON string")
group.add_argument("--request-file", help="Path to JSON request file")
return parser.parse_args()
def _load_request_text(args: argparse.Namespace) -> str:
if args.request is not None:
return args.request
request_path = os.fspath(args.request_file)
with open(request_path, "r", encoding="utf-8") as request_file:
return request_file.read()
def send_request(socket_path: str, request_text: str) -> dict[str, object]:
"""Open one Unix socket, send one NDJSON request, and parse one NDJSON response."""
payload = json.loads(request_text)
if not isinstance(payload, dict):
raise ValueError("request must be a JSON object")
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as client:
client.connect(socket_path)
client.sendall((json.dumps(payload) + "\n").encode("utf-8"))
response_chunks: list[str] = []
while True:
chunk = client.recv(1024 * 1024).decode("utf-8")
if not chunk:
break
response_chunks.append(chunk)
if "\n" in chunk:
break
response_text = "".join(response_chunks)
response_line = response_text.split("\n", 1)[0].strip()
if not response_line:
raise RuntimeError("empty response")
response = json.loads(response_line)
if not isinstance(response, dict):
raise RuntimeError("invalid response")
return response
def main() -> None:
args = _parse_args()
request_text = _load_request_text(args)
response = send_request(args.socket, request_text)
print(json.dumps(response, separators=(",", ":"), sort_keys=True))
if __name__ == "__main__":
try:
main()
except Exception as exc: # pragma: no cover - CLI entrypoint behavior
print(json.dumps({"status": "error", "error": str(exc)}), file=sys.stderr)
raise SystemExit(1)
@@ -1,931 +0,0 @@
"""Unix-socket service for governed local writer operations."""
from __future__ import annotations
import json
import hashlib
import argparse
import importlib.util
import os
import re
import socket
import subprocess
import sys
import tempfile
import uuid
from dataclasses import dataclass, field
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Callable, Mapping, Protocol
from governed_local_writer import (
AppendCommitRequest,
AuthorizationError,
BranchPolicy,
CreateBranchRequest,
GovernedAuthorization,
PeerIdentity,
PRINCIPAL,
TASK_ID,
extract_peer_identity,
contains_secret_like_content,
load_authorization_file,
validate_file_changes,
)
class ExistingGitOpsHandler:
"""Delegate repository mutations to the installed GitOps handler seam."""
def __init__(
self,
*,
workspace_by_branch: Mapping[str, str | os.PathLike[str]],
bare_repo: str | os.PathLike[str],
api_source: str | os.PathLike[str],
) -> None:
self.workspace_by_branch = {str(k): Path(v) for k, v in workspace_by_branch.items()}
self.bare_repo = Path(bare_repo)
self.api_source = Path(api_source)
@staticmethod
def _restore_env(previous: Mapping[str, str | None]) -> None:
for key, value in previous.items():
if value is None:
os.environ.pop(key, None)
else:
os.environ[key] = value
def _load_api(self, workspace: Path):
if not self.api_source.is_file() or self.api_source.is_symlink():
raise RuntimeError("installed GitOps handler source is unavailable")
keys = (
"AIOS_GITOPS_WORKSPACE",
"AIOS_GITOPS_BARE_REPO",
"AIOS_GITOPS_WRITES_ENABLED",
"PYTHONDONTWRITEBYTECODE",
"GIT_CONFIG_COUNT",
"GIT_CONFIG_KEY_0",
"GIT_CONFIG_VALUE_0",
"GIT_CONFIG_KEY_1",
"GIT_CONFIG_VALUE_1",
)
previous = {key: os.environ.get(key) for key in keys}
os.environ.update(
{
"AIOS_GITOPS_WORKSPACE": str(workspace),
"AIOS_GITOPS_BARE_REPO": str(self.bare_repo),
"AIOS_GITOPS_WRITES_ENABLED": "true",
"PYTHONDONTWRITEBYTECODE": "1",
"GIT_CONFIG_COUNT": "2",
"GIT_CONFIG_KEY_0": "safe.directory",
"GIT_CONFIG_VALUE_0": str(workspace),
"GIT_CONFIG_KEY_1": "safe.directory",
"GIT_CONFIG_VALUE_1": str(self.bare_repo),
}
)
module_name = f"_governed_gitops_api_{uuid.uuid4().hex}"
try:
spec = importlib.util.spec_from_file_location(module_name, self.api_source)
if spec is None or spec.loader is None:
raise RuntimeError("unable to load installed GitOps handler")
module = importlib.util.module_from_spec(spec)
sys.modules[module_name] = module
spec.loader.exec_module(module)
decision = module.evaluate_git_write(module.WS)
if not decision.allowed:
raise RuntimeError("existing GitOps write gate denied bootstrap")
return module, previous, module_name
except Exception:
sys.modules.pop(module_name, None)
self._restore_env(previous)
raise
def _workspace(self, branch: str) -> Path:
workspace = self.workspace_by_branch.get(branch)
if workspace is None or not workspace.is_dir():
raise RuntimeError("branch workspace is not authorized")
return workspace
@staticmethod
def _git(workspace: Path, args: list[str]) -> str:
result = subprocess.run(
["git", *args], cwd=workspace, text=True, capture_output=True, check=False
)
if result.returncode != 0:
raise RuntimeError("governed handler git probe failed")
return result.stdout.strip()
def create_branch(self, request: CreateBranchRequest) -> Mapping[str, object]:
workspace = self._workspace(request.branch)
# A prior handler call may have completed the fast-forward sync before
# the process observed a post-commit error. Reconcile only an exact,
# metadata-only result; never overwrite or move an existing ref here.
try:
existing = self._git(
workspace,
[
"--git-dir",
str(self.bare_repo),
"rev-parse",
f"refs/heads/{request.branch}",
],
)
except RuntimeError:
existing = ""
if existing:
parent = self._git(workspace, ["--git-dir", str(self.bare_repo), "rev-parse", f"{existing}^1"])
changed = self._git(
workspace,
[
"--git-dir",
str(self.bare_repo),
"diff-tree",
"--no-commit-id",
"--name-only",
"-r",
existing,
],
).splitlines()
safe_branch = re.sub(r"[^A-Za-z0-9_.-]+", "-", request.branch).strip("-")
if parent != request.base_oid or changed != [f"patches/{safe_branch}.branch.json"]:
raise RuntimeError("existing branch is not an exact metadata-only bootstrap")
return {"head_oid": existing, "parent_oid": parent, "handler_status": "reconciled"}
module, previous, module_name = self._load_api(workspace)
phase = "loaded"
try:
phase = "verify_base"
parent = self._git(
workspace,
["--git-dir", str(self.bare_repo), "rev-parse", "refs/heads/main"],
)
if parent != request.base_oid:
raise RuntimeError("authorized base OID drift")
phase = "checkout"
module.checkout(request.branch, base=request.base_oid, create=True)
phase = "write_metadata"
safe_branch = re.sub(r"[^A-Za-z0-9_.-]+", "-", request.branch).strip("-")
metadata_path = f"patches/{safe_branch}.branch.json"
module.write_json(
metadata_path,
{
"schema": "aios.governed-local-writer-bootstrap.v1",
"task_id": TASK_ID,
"principal": PRINCIPAL,
"branch": request.branch,
"parent_oid": request.base_oid,
"authorization_sha256": request.authorization_digest,
},
)
phase = "commit_and_sync"
result = module.commit(
[metadata_path], "chore(governance): bootstrap repair lease branch"
)
head_oid = self._git(workspace, ["rev-parse", "HEAD"])
first_parent = self._git(workspace, ["rev-parse", "HEAD^1"])
if first_parent != request.base_oid or (request.head_oid and head_oid != request.head_oid):
raise RuntimeError("bootstrap branch lineage check failed")
return {
"head_oid": head_oid,
"parent_oid": first_parent,
"handler_status": str(result.get("status")),
}
except Exception as exc:
raise RuntimeError(f"handler_phase={phase};error={exc.__class__.__name__}") from exc
finally:
sys.modules.pop(module_name, None)
self._restore_env(previous)
def append_commit(self, request: AppendCommitRequest) -> Mapping[str, object]:
workspace = self._workspace(request.branch)
module, previous, module_name = self._load_api(workspace)
phase = "loaded"
try:
phase = "verify_head"
current = self._git(workspace, ["rev-parse", "HEAD"])
if current != request.expected_head_oid:
raise RuntimeError("branch head advanced or is stale")
phase = "checkout"
module.checkout(request.branch, base=request.expected_head_oid, create=False)
phase = "write_files"
paths: list[str] = []
for change in request.changes:
paths.append(module.write_file(change.path, change.content))
phase = "commit_and_sync"
result = module.commit(paths, request.commit_message)
head_oid = self._git(workspace, ["rev-parse", "HEAD"])
first_parent = self._git(workspace, ["rev-parse", "HEAD^1"])
if first_parent != request.expected_head_oid or head_oid == first_parent:
raise RuntimeError("append commit lineage check failed")
return {
"head_oid": head_oid,
"parent_oid": first_parent,
"handler_status": str(result.get("status")),
}
except Exception as exc:
raise RuntimeError(f"handler_phase={phase};error={exc.__class__.__name__}") from exc
finally:
sys.modules.pop(module_name, None)
self._restore_env(previous)
class GovernedWriterHandler(Protocol):
"""Small adapter interface for real writer backend handlers."""
def create_branch(self, request: CreateBranchRequest) -> Mapping[str, object]:
"""Create a branch using internal repo services."""
def append_commit(self, request: AppendCommitRequest) -> Mapping[str, object]:
"""Append a commit using internal repo services."""
class AuditSink(Protocol):
"""Pluggable sink for sanitized audit records."""
def append(self, record: "AuditRecord") -> None:
"""Persist one audit record."""
@dataclass
class AuditRecord:
"""Sanitized audit log entry."""
authorization_digest: str
peer_pid: int
peer_uid: int
peer_gid: int
peer_executable: str | None
timestamp: datetime
operation: str
branch: str
result: str
class InMemoryAuditSink:
"""Simple in-memory audit log used by tests."""
def __init__(self) -> None:
self.records: list[AuditRecord] = []
def append(self, record: AuditRecord) -> None:
self.records.append(record)
@dataclass
class _AuthorizationState:
"""Tracks one-shot operation consumption."""
create_done: set[str] = field(default_factory=set)
append_done: set[str] = field(default_factory=set)
consumed: bool = False
class GovernedLocalWriterService:
"""Policy-aware AF_UNIX service that calls an injected handler."""
def __init__(
self,
socket_path: str | os.PathLike[str],
authorization: GovernedAuthorization,
handler: GovernedWriterHandler,
*,
audit_sink: AuditSink | None = None,
peer_identity_fn: Callable[[socket.socket], PeerIdentity] | None = None,
state_path: str | os.PathLike[str] | None = None,
) -> None:
self.socket_path = Path(socket_path)
self.authorization = authorization
self.handler = handler
self.peer_identity_fn = peer_identity_fn or extract_peer_identity
self.state = _AuthorizationState()
self.audit_sink = audit_sink or InMemoryAuditSink()
self.state_path = Path(state_path) if state_path is not None else None
self._load_state()
def _load_state(self) -> None:
"""Restore one-shot state without restoring request or secret material."""
if self.state_path is None or not self.state_path.exists():
return
try:
raw = json.loads(self.state_path.read_text(encoding="utf-8"))
if not isinstance(raw, dict):
raise ValueError("state must be an object")
if raw.get("authorization_sha256") != self.authorization.authorization_sha256:
raise ValueError("state authorization digest mismatch")
self.state.create_done = {str(v) for v in raw.get("create_done", [])}
self.state.append_done = {str(v) for v in raw.get("append_done", [])}
self.state.consumed = bool(raw.get("consumed", False))
except (OSError, ValueError, TypeError, json.JSONDecodeError) as exc:
raise AuthorizationError("authorization state is invalid") from exc
def _persist_state(self) -> None:
if self.state_path is None:
return
self.state_path.parent.mkdir(parents=True, exist_ok=True)
payload = {
"authorization_sha256": self.authorization.authorization_sha256,
"create_done": sorted(self.state.create_done),
"append_done": sorted(self.state.append_done),
"consumed": self.state.consumed,
}
fd, temp_name = tempfile.mkstemp(prefix=".writer-state-", dir=self.state_path.parent)
try:
os.fchmod(fd, 0o600)
with os.fdopen(fd, "w", encoding="utf-8") as stream:
json.dump(payload, stream, sort_keys=True, separators=(",", ":"))
stream.write("\n")
os.replace(temp_name, self.state_path)
os.chmod(self.state_path, 0o600)
finally:
if os.path.exists(temp_name):
os.unlink(temp_name)
def _new_audit(self, peer: PeerIdentity, operation: str, branch: str, result: str) -> None:
self.audit_sink.append(
AuditRecord(
authorization_digest=self.authorization.authorization_sha256,
peer_pid=peer.pid,
peer_uid=peer.uid,
peer_gid=peer.gid,
peer_executable=peer.executable,
timestamp=datetime.now(tz=timezone.utc),
operation=operation,
branch=branch,
result=result,
)
)
def _require_request_field(self, request: Mapping[str, Any], field_name: str) -> str:
value = request.get(field_name)
if not isinstance(value, str) or not value:
raise AuthorizationError(f"{field_name} must be a non-empty string")
return value
def _branch_policy(self, branch: str) -> BranchPolicy:
policy = self.authorization.branch_operations.get(branch)
if policy is None:
raise AuthorizationError("branch is not authorized")
return policy
def _ensure_not_consumed(self) -> None:
if self.state.consumed:
raise AuthorizationError("authorization consumed")
if datetime.now(tz=timezone.utc) >= self.authorization.expires_at:
raise AuthorizationError("authorization expired")
def _mark_success(self, op: str, branch: str) -> None:
if op == "create_branch":
self.state.create_done.add(branch)
elif op == "append_commit":
self.state.append_done.add(branch)
if self.state.create_done.issuperset(self.authorization.create_branches) and self.state.append_done.issuperset(
self.authorization.append_branches
):
self.state.consumed = True
self._persist_state()
def _validate_request(self, request: Mapping[str, Any]) -> dict[str, Any]:
task_id = self._require_request_field(request, "task_id")
if task_id != TASK_ID:
raise AuthorizationError("invalid task_id")
principal = self._require_request_field(request, "principal")
if principal != PRINCIPAL:
raise AuthorizationError("invalid principal")
operation = self._require_request_field(request, "op")
if operation not in {"create_branch", "append_commit"}:
raise AuthorizationError("unsupported operation")
if operation in self.authorization.denied_operations:
raise AuthorizationError("operation denied by policy")
branch = self._require_request_field(request, "branch")
self._ensure_not_consumed()
policy = self._branch_policy(branch)
if operation == "create_branch":
if policy.create_branch is None:
raise AuthorizationError("branch does not allow create_branch")
if branch in self.state.create_done:
raise AuthorizationError("create_branch already used for this branch")
base_oid = self._require_request_field(request, "base_oid")
raw_head_oid = request.get("head_oid")
if raw_head_oid is not None and (not isinstance(raw_head_oid, str) or not raw_head_oid):
raise AuthorizationError("head_oid must be a non-empty string when supplied")
head_oid = str(raw_head_oid) if raw_head_oid is not None else None
if base_oid != policy.create_branch.base_oid:
raise AuthorizationError("base_oid mismatch")
if policy.create_branch.head_oid is not None and head_oid != policy.create_branch.head_oid:
raise AuthorizationError("head_oid mismatch")
return {
"operation": operation,
"branch": branch,
"base_oid": base_oid,
"head_oid": head_oid,
}
if policy.append_commit is None:
raise AuthorizationError("branch does not allow append_commit")
if policy.create_branch is not None and branch not in self.state.create_done:
raise AuthorizationError("append_commit requires prior successful create_branch")
if branch in self.state.append_done:
raise AuthorizationError("append_commit already used for this branch")
expected_head = policy.append_commit.expected_head_oid
if "expected_head_oid" in request:
supplied_head = self._require_request_field(request, "expected_head_oid")
elif "current_head_oid" in request:
supplied_head = self._require_request_field(request, "current_head_oid")
else:
raise AuthorizationError("expected_head_oid or current_head_oid required")
if not re.fullmatch(r"[0-9a-fA-F]{40}", supplied_head):
raise AuthorizationError("head check must be a full commit OID")
if expected_head is not None and supplied_head != expected_head:
raise AuthorizationError("head check failed")
if request.get("force") is True or request.get("non_fast_forward") is True:
raise AuthorizationError("non-fast-forward operations are not allowed")
if request.get("history_rewrite") is True:
raise AuthorizationError("history rewrite is not allowed")
parent_oids = request.get("parent_oids")
if parent_oids is not None:
if not isinstance(parent_oids, list) or parent_oids != [supplied_head]:
raise AuthorizationError("parent_oids must contain exactly expected_head_oid")
changes = request.get("changes")
if not isinstance(changes, list):
raise AuthorizationError("changes must be a list")
validated_changes = validate_file_changes(changes, policy.append_commit.allowed_paths)
commit_message = request.get("commit_message", "chore(governance): append governed commit")
if not isinstance(commit_message, str) or not commit_message.strip() or len(commit_message) > 200:
raise AuthorizationError("commit_message must be a short non-empty string")
if "\n" in commit_message or "\r" in commit_message or contains_secret_like_content(commit_message):
raise AuthorizationError("commit_message failed policy")
return {
"operation": operation,
"branch": branch,
"expected_head_oid": supplied_head,
"changes": validated_changes,
"commit_message": commit_message.strip(),
}
def process_request(self, raw_request: Mapping[str, Any], peer: PeerIdentity) -> Mapping[str, Any]:
"""Run one request through policy checks and handler adapter."""
operation = raw_request.get("op") if isinstance(raw_request.get("op"), str) else "unknown"
branch = raw_request.get("branch") if isinstance(raw_request.get("branch"), str) else ""
try:
details = self._validate_request(raw_request)
operation = str(details["operation"])
branch = str(details["branch"])
if operation == "create_branch":
self.handler.create_branch(
CreateBranchRequest(
branch=branch,
base_oid=str(details["base_oid"]),
head_oid=(
str(details["head_oid"])
if details.get("head_oid") is not None
else None
),
authorization_digest=self.authorization.authorization_sha256,
)
)
self._mark_success("create_branch", branch)
self._new_audit(peer, operation, branch, "ok")
return {
"status": "ok",
"operation": operation,
"branch": branch,
"result": "applied",
}
self.handler.append_commit(
AppendCommitRequest(
branch=branch,
expected_head_oid=str(details["expected_head_oid"]),
changes=tuple(details["changes"]),
authorization_digest=self.authorization.authorization_sha256,
commit_message=str(details["commit_message"]),
)
)
self._mark_success("append_commit", branch)
self._new_audit(peer, operation, branch, "ok")
return {
"status": "ok",
"operation": operation,
"branch": branch,
"result": "applied",
}
except Exception as error:
self._new_audit(peer, operation or "unknown", branch, f"error:{error.__class__.__name__}")
if isinstance(error, PermissionError):
code = "permission_denied"
elif isinstance(error, AuthorizationError):
code = "request_denied"
else:
code = "handler_failed"
if code == "handler_failed" and str(error).startswith("handler_phase="):
code = str(error)
return {
"status": "error",
"operation": operation or "unknown",
"branch": branch,
"error": code,
}
def _write_json(self, connection: socket.socket, payload: Mapping[str, Any]) -> None:
connection.sendall((json.dumps(payload) + "\n").encode("utf-8"))
def _handle_client(self, connection: socket.socket) -> None:
with connection:
try:
peer = self.peer_identity_fn(connection)
except Exception:
self._write_json(
connection,
{
"status": "error",
"operation": "connection",
"branch": "",
"error": "peer identity validation failed",
},
)
return
with connection.makefile("r", encoding="utf-8") as stream:
for raw_line in stream:
line = raw_line.strip()
if not line:
continue
try:
request = json.loads(line)
except json.JSONDecodeError:
self._write_json(
connection,
{
"status": "error",
"operation": "request",
"branch": "",
"error": "invalid json",
},
)
continue
if not isinstance(request, Mapping):
self._write_json(
connection,
{
"status": "error",
"operation": "request",
"branch": "",
"error": "request must be a JSON object",
},
)
continue
self._write_json(connection, self.process_request(request, peer))
def _bind_socket(self) -> socket.socket:
if self.socket_path.exists():
raise RuntimeError("governed writer socket already exists")
parent = self.socket_path.parent
if not parent.is_dir():
raise RuntimeError("governed writer socket parent is missing")
if parent.is_symlink():
raise RuntimeError("governed writer socket parent must not be a symlink")
server = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
server.bind(str(self.socket_path))
os.chmod(self.socket_path, 0o600)
server.listen(16)
return server
def serve(self) -> None:
"""Serve newline-delimited JSON over a filesystem AF_UNIX socket."""
server = self._bind_socket()
try:
while True:
connection, _ = server.accept()
self._handle_client(connection)
finally:
server.close()
if self.socket_path.exists():
self.socket_path.unlink()
class JsonAuditSink:
"""Append-only root-owned audit sink containing no request payloads."""
def __init__(self, path: str | os.PathLike[str]) -> None:
self.path = Path(path)
self.path.parent.mkdir(parents=True, exist_ok=True)
def append(self, record: AuditRecord) -> None:
payload = {
"authorization_sha256": record.authorization_digest,
"peer_pid": record.peer_pid,
"peer_uid": record.peer_uid,
"peer_gid": record.peer_gid,
"peer_executable": record.peer_executable,
"timestamp": record.timestamp.isoformat(),
"operation": record.operation,
"branch": record.branch,
"result": record.result,
}
line = (json.dumps(payload, sort_keys=True, separators=(",", ":")) + "\n").encode("utf-8")
fd = os.open(self.path, os.O_WRONLY | os.O_CREAT | os.O_APPEND, 0o600)
try:
os.fchmod(fd, 0o600)
os.write(fd, line)
finally:
os.close(fd)
# V2R1C6 durable receipt overlay. This subclasses the original root-only
# writer in-place so the existing AF_UNIX/SO_PEERCRED and handler policy remain
# the only mutation path.
_LegacyGovernedLocalWriterService = GovernedLocalWriterService
class GovernedLocalWriterService(_LegacyGovernedLocalWriterService):
"""Existing writer with durable request receipts and safe recovery."""
def _load_state(self) -> None:
super()._load_state()
self.state.receipts = {}
if self.state_path is None or not self.state_path.exists():
return
raw = json.loads(self.state_path.read_text(encoding="utf-8"))
if not isinstance(raw, dict):
raise AuthorizationError("authorization state is invalid")
receipts = raw.get("receipts", {})
if not isinstance(receipts, dict):
raise AuthorizationError("authorization receipts are invalid")
self.state.receipts = {
str(key): dict(value)
for key, value in receipts.items()
if isinstance(value, dict)
}
def _persist_state(self) -> None:
if self.state_path is None:
return
self.state_path.parent.mkdir(parents=True, exist_ok=True)
payload = {
"authorization_sha256": self.authorization.authorization_sha256,
"create_done": sorted(self.state.create_done),
"append_done": sorted(self.state.append_done),
"consumed": bool(self.state.consumed),
"receipts": self.state.receipts,
}
fd, temp_name = tempfile.mkstemp(prefix=".writer-state-", dir=self.state_path.parent)
try:
os.fchmod(fd, 0o600)
with os.fdopen(fd, "w", encoding="utf-8") as stream:
json.dump(payload, stream, sort_keys=True, separators=(",", ":"))
stream.write("\n")
os.replace(temp_name, self.state_path)
os.chmod(self.state_path, 0o600)
finally:
if os.path.exists(temp_name):
os.unlink(temp_name)
def _request_identity(self, request: Mapping[str, Any]) -> dict[str, str]:
canonical = json.dumps(dict(request), sort_keys=True, separators=(",", ":"), ensure_ascii=True)
fallback = hashlib.sha256(canonical.encode("utf-8")).hexdigest()
request_id = request.get("request_id")
idempotency_key = request.get("idempotency_key")
request_id = request_id.strip() if isinstance(request_id, str) and request_id.strip() else "legacy-" + fallback
idempotency_key = idempotency_key.strip() if isinstance(idempotency_key, str) and idempotency_key.strip() else "legacy-" + fallback
for field_name, value in (("request_id", request_id), ("idempotency_key", idempotency_key)):
if len(value) > 200 or "\n" in value or "\r" in value:
raise AuthorizationError(field_name + " is invalid")
return {
"request_id": request_id,
"idempotency_key": idempotency_key,
"request_fingerprint": fallback,
}
def _find_receipt(self, details: Mapping[str, Any], compare_fingerprint: bool = True):
request_id = str(details["request_id"])
idempotency_key = str(details["idempotency_key"])
fingerprint = str(details.get("request_fingerprint", ""))
for receipt in self.state.receipts.values():
if receipt.get("request_id") == request_id or receipt.get("idempotency_key") == idempotency_key:
if compare_fingerprint and receipt.get("request_fingerprint") != fingerprint:
raise AuthorizationError("idempotency key reused with different request")
return receipt
return None
@staticmethod
def _receipt_response(receipt: Mapping[str, object], status: str = "receipt") -> dict[str, object]:
response = {
"status": status,
"request_id": receipt.get("request_id"),
"idempotency_key": receipt.get("idempotency_key"),
"operation": receipt.get("operation"),
"branch": receipt.get("branch", ""),
"receipt_status": receipt.get("status"),
}
for field_name in ("commit_oid", "final_head", "parent_oid", "audit_sha256", "error_code", "safe_to_retry"):
if field_name in receipt:
response[field_name] = receipt[field_name]
return response
def _new_receipt(self, details: Mapping[str, Any]) -> dict[str, object]:
return {
"request_id": str(details["request_id"]),
"idempotency_key": str(details["idempotency_key"]),
"request_fingerprint": str(details["request_fingerprint"]),
"operation": str(details["operation"]),
"branch": str(details.get("branch", "")),
"expected_head_oid": str(details.get("expected_head_oid", "")),
"status": "accepted",
"created_at": datetime.now(tz=timezone.utc).isoformat(),
"safe_to_retry": False,
}
def _new_audit(self, peer: PeerIdentity, operation: str, branch: str, result: str) -> str:
super()._new_audit(peer, operation, branch, result)
payload = {
"authorization_sha256": self.authorization.authorization_sha256,
"peer_pid": peer.pid,
"peer_uid": peer.uid,
"peer_gid": peer.gid,
"peer_executable": peer.executable,
"operation": operation,
"branch": branch,
"result": result,
}
return hashlib.sha256(json.dumps(payload, sort_keys=True, separators=(",", ":")).encode("utf-8")).hexdigest()
def _mark_success(self, op: str, branch: str) -> None:
if op == "create_branch":
self.state.create_done.add(branch)
elif op in {"append_commit", "append_files", "append_batch"}:
self.state.append_done.add(branch)
# The provisioning grant is one-shot; the task writer lease itself must
# support multiple append receipts for the exact authorized branches.
self.state.consumed = False
self._persist_state()
def _validate_durable(self, raw_request: Mapping[str, Any]) -> dict[str, Any]:
operation = self._require_request_field(raw_request, "op")
identity = self._request_identity(raw_request)
if operation == "query_receipt":
return {"operation": operation, **identity}
if operation == "recover_request":
branch = self._require_request_field(raw_request, "branch")
policy = self._branch_policy(branch)
if policy.append_commit is None:
raise AuthorizationError("branch does not allow recovery")
expected = raw_request.get("expected_head_oid") or policy.append_commit.expected_head_oid
if not isinstance(expected, str) or not re.fullmatch(r"[0-9a-fA-F]{40}", expected):
raise AuthorizationError("recovery requires expected_head_oid")
return {"operation": operation, "branch": branch, "expected_head_oid": expected.lower(), **identity}
if operation not in {"create_branch", "append_commit", "append_files", "append_batch"}:
raise AuthorizationError("unsupported operation")
request = dict(raw_request)
if operation in {"append_files", "append_batch"}:
request["op"] = "append_commit"
if operation in {"append_commit", "append_files", "append_batch"}:
self.state.consumed = False
branch = request.get("branch")
removed = False
dynamic_expected = False
if isinstance(branch, str) and branch in self.state.append_done:
self.state.append_done.remove(branch)
removed = True
policy = self.authorization.branch_operations.get(branch)
if policy is not None and policy.append_commit is not None and policy.append_commit.expected_head_oid is not None:
from governed_local_writer import BranchAppendPolicy, BranchPolicy
self.authorization.branch_operations[branch] = BranchPolicy(create_branch=policy.create_branch, append_commit=BranchAppendPolicy(branch=branch, expected_head_oid=None, allowed_paths=policy.append_commit.allowed_paths))
dynamic_expected = True
try:
details = super()._validate_request(request)
finally:
if dynamic_expected:
policy = self.authorization.branch_operations.get(str(branch))
if policy is not None and policy.append_commit is not None:
from governed_local_writer import BranchAppendPolicy, BranchPolicy
self.authorization.branch_operations[str(branch)] = BranchPolicy(create_branch=policy.create_branch, append_commit=BranchAppendPolicy(branch=str(branch), expected_head_oid=str(raw_request.get("expected_head_oid") or ""), allowed_paths=policy.append_commit.allowed_paths))
if removed:
self.state.append_done.add(str(branch))
details.update(identity)
details["operation"] = operation
return details
def _recover_backend(self, details: Mapping[str, Any]) -> dict[str, object]:
if not hasattr(self.handler, "_workspace") or not hasattr(self.handler, "_git"):
raise RuntimeError("recovery backend unavailable")
workspace = self.handler._workspace(str(details["branch"]))
expected = str(details["expected_head_oid"])
current = self.handler._git(workspace, ["rev-parse", "HEAD"])
if current == expected:
return {"status": "not_started", "final_head": current}
parent = self.handler._git(workspace, ["rev-parse", "HEAD^1"])
if parent != expected:
raise RuntimeError("external branch advance during recovery")
return {"status": "applied", "commit_oid": current, "final_head": current, "parent_oid": parent}
def process_request(self, raw_request: Mapping[str, Any], peer: PeerIdentity) -> Mapping[str, Any]:
operation = raw_request.get("op") if isinstance(raw_request.get("op"), str) else "unknown"
branch = raw_request.get("branch") if isinstance(raw_request.get("branch"), str) else ""
try:
details = self._validate_durable(raw_request)
operation = str(details["operation"])
branch = str(details.get("branch", ""))
if operation == "query_receipt":
receipt = self._find_receipt(details, compare_fingerprint=False)
return self._receipt_response(receipt) if receipt is not None else {"status": "not_found", "request_id": details["request_id"], "idempotency_key": details["idempotency_key"]}
if operation == "recover_request":
receipt = self._find_receipt(details, compare_fingerprint=False)
if receipt is None:
return {"status": "not_found", "request_id": details["request_id"], "idempotency_key": details["idempotency_key"], "safe_to_retry": True}
if receipt.get("status") == "applied":
return self._receipt_response(receipt)
recovered = self._recover_backend(details)
if recovered.get("status") == "applied":
receipt.update({"status": "applied", "commit_oid": recovered.get("commit_oid"), "final_head": recovered.get("final_head"), "parent_oid": recovered.get("parent_oid"), "safe_to_retry": False})
self._mark_success("append_commit", branch)
return self._receipt_response(receipt)
receipt["safe_to_retry"] = True
self._persist_state()
return self._receipt_response(receipt)
receipt = self._find_receipt(details)
if receipt is not None:
return self._receipt_response(receipt)
receipt = self._new_receipt(details)
self.state.receipts[str(details["request_id"])] = receipt
self._persist_state()
if operation == "create_branch":
result = self.handler.create_branch(CreateBranchRequest(branch=branch, base_oid=str(details["base_oid"]), head_oid=str(details["head_oid"]) if details.get("head_oid") is not None else None, authorization_digest=self.authorization.authorization_sha256))
commit_oid = str(result.get("head_oid", ""))
parent_oid = str(result.get("parent_oid", ""))
audit_sha = self._new_audit(peer, operation, branch, "ok")
receipt.update({"status": "applied", "commit_oid": commit_oid, "final_head": commit_oid, "parent_oid": parent_oid, "audit_sha256": audit_sha, "safe_to_retry": False})
self._mark_success("create_branch", branch)
return self._receipt_response(receipt, status="ok") | {"result": "applied"}
result = self.handler.append_commit(AppendCommitRequest(branch=branch, expected_head_oid=str(details["expected_head_oid"]), changes=tuple(details["changes"]), authorization_digest=self.authorization.authorization_sha256, commit_message=str(details["commit_message"])))
commit_oid = str(result.get("head_oid", ""))
parent_oid = str(result.get("parent_oid", ""))
audit_sha = self._new_audit(peer, operation, branch, "ok")
receipt.update({"status": "applied", "commit_oid": commit_oid, "final_head": commit_oid, "parent_oid": parent_oid, "audit_sha256": audit_sha, "safe_to_retry": False})
self._mark_success("append_commit", branch)
return self._receipt_response(receipt, status="ok") | {"result": "applied"}
except Exception as error:
try:
identity = self._request_identity(raw_request)
receipt = self.state.receipts.get(identity["request_id"])
if receipt is not None and receipt.get("status") == "accepted":
receipt.update({"status": "failed", "error_code": error.__class__.__name__, "safe_to_retry": False})
self._persist_state()
except Exception:
pass
self._new_audit(peer, operation, branch, "error:" + error.__class__.__name__)
return {"status": "error", "operation": operation, "branch": branch, "error": "request_denied" if isinstance(error, AuthorizationError) else "handler_failed"}
def _parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="AIOS governed local writer")
parser.add_argument("--socket", required=True)
parser.add_argument("--authorization", required=True)
parser.add_argument("--state", required=True)
parser.add_argument("--audit", required=True)
parser.add_argument("--repair-branch", required=True)
parser.add_argument("--repair-workspace", required=True)
parser.add_argument("--candidate-branch", required=True)
parser.add_argument("--candidate-workspace", required=True)
parser.add_argument("--bare-repo", required=True)
parser.add_argument("--api-source", required=True)
return parser.parse_args()
def main() -> int:
if hasattr(os, "geteuid") and os.geteuid() != 0:
print("governed local writer requires uid 0", file=sys.stderr)
return 2
args = _parse_args()
authorization = load_authorization_file(args.authorization)
handler = ExistingGitOpsHandler(
workspace_by_branch={
args.repair_branch: args.repair_workspace,
args.candidate_branch: args.candidate_workspace,
},
bare_repo=args.bare_repo,
api_source=args.api_source,
)
service = GovernedLocalWriterService(
args.socket,
authorization,
handler,
audit_sink=JsonAuditSink(args.audit),
state_path=args.state,
)
service.serve()
return 0
if __name__ == "__main__": # pragma: no cover - systemd entrypoint
raise SystemExit(main())
@@ -0,0 +1,27 @@
"""AIOS-managed Hermes runtime boundary."""
from .adapter import (
HermesAdapter,
HermesConflict,
HermesNotFound,
HermesRuntimeError,
InMemoryHermesStore,
SQLiteHermesStore,
)
from .contract import HermesHealth, HermesJob, HermesJobState, HermesResult
from .worker import HermesWorker, WorkerRunResult
__all__ = [
"HermesAdapter",
"HermesConflict",
"HermesHealth",
"HermesJob",
"HermesJobState",
"HermesNotFound",
"HermesResult",
"HermesRuntimeError",
"HermesWorker",
"InMemoryHermesStore",
"SQLiteHermesStore",
"WorkerRunResult",
]
+593
View File
@@ -0,0 +1,593 @@
"""Tenant-partitioned Hermes queue and worker lease boundary."""
from __future__ import annotations
import hashlib
import json
import sqlite3
import threading
from dataclasses import asdict, replace
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Iterable, Mapping
from .contract import (
ALLOWED_TRANSITIONS,
TERMINAL_STATES,
HermesHealth,
HermesJob,
HermesJobState,
HermesResult,
utc_now,
)
class HermesRuntimeError(RuntimeError):
"""Base Hermes runtime-boundary failure."""
class HermesNotFound(HermesRuntimeError):
"""A tenant-scoped job was not found."""
class HermesConflict(HermesRuntimeError):
"""A state, lease, idempotency, or revision conflict occurred."""
class InMemoryHermesStore:
"""Thread-safe reference store; production backends implement this contract."""
def __init__(self) -> None:
self.lock = threading.RLock()
self.jobs: dict[str, HermesJob] = {}
self.results: dict[str, HermesResult] = {}
self.idempotency: dict[tuple[str, str], tuple[str, str]] = {}
self.worker_heartbeats: dict[str, tuple[str, str | None]] = {}
def persist_locked(self) -> None:
"""Persist a mutation while ``lock`` is held; memory stores are a no-op."""
class SQLiteHermesStore(InMemoryHermesStore):
"""Durable snapshot for the existing Hermes queue state machine.
The adapter remains the sole owner of transitions and lease rules. This
store only makes its jobs, results, idempotency keys and worker heartbeats
survive a process restart.
"""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
super().__init__()
with self._connect() as connection:
connection.execute(
"""
CREATE TABLE IF NOT EXISTS hermes_state (
singleton INTEGER PRIMARY KEY CHECK (singleton = 1),
payload TEXT NOT NULL
)
"""
)
self._load()
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(str(self.path), timeout=30)
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
return connection
@staticmethod
def _record(value: HermesJob | HermesResult) -> dict[str, object]:
record = asdict(value)
record["state"] = value.state.value
return record
def _load(self) -> None:
with self.lock, self._connect() as connection:
row = connection.execute(
"SELECT payload FROM hermes_state WHERE singleton = 1"
).fetchone()
if row is None:
return
payload = json.loads(str(row[0]))
self.jobs = {
str(item["job_id"]): HermesJob(**item)
for item in payload.get("jobs", [])
}
self.results = {
str(item["job_id"]): HermesResult(**item)
for item in payload.get("results", [])
}
self.idempotency = {
(str(item["tenant_id"]), str(item["idempotency_key"])): (
str(item["job_id"]),
str(item["digest"]),
)
for item in payload.get("idempotency", [])
}
self.worker_heartbeats = {
str(item["worker_id"]): (
str(item["heartbeat_at"]),
str(item["job_id"]) if item.get("job_id") is not None else None,
)
for item in payload.get("worker_heartbeats", [])
}
def persist_locked(self) -> None:
payload = {
"version": 1,
"jobs": [self._record(item) for item in self.jobs.values()],
"results": [self._record(item) for item in self.results.values()],
"idempotency": [
{
"tenant_id": tenant_id,
"idempotency_key": idempotency_key,
"job_id": job_id,
"digest": digest,
}
for (tenant_id, idempotency_key), (job_id, digest)
in self.idempotency.items()
],
"worker_heartbeats": [
{
"worker_id": worker_id,
"heartbeat_at": heartbeat_at,
"job_id": job_id,
}
for worker_id, (heartbeat_at, job_id)
in self.worker_heartbeats.items()
],
}
encoded = json.dumps(
payload,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
)
with self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
connection.execute(
"""
INSERT INTO hermes_state(singleton, payload) VALUES(1, ?)
ON CONFLICT(singleton) DO UPDATE SET payload=excluded.payload
""",
(encoded,),
)
connection.commit()
class HermesAdapter:
"""Queue and reconcile Hermes jobs without owning AIOS policy."""
def __init__(
self,
store: InMemoryHermesStore | None = None,
*,
runtime_id: str = "hermes-runtime",
runtime_version: str = "v1",
default_lease_seconds: int = 60,
) -> None:
if default_lease_seconds < 5:
raise ValueError("default_lease_seconds must be >= 5")
self.store = store or InMemoryHermesStore()
self.runtime_id = runtime_id
self.runtime_version = runtime_version
self.default_lease_seconds = int(default_lease_seconds)
@staticmethod
def _digest(job: HermesJob) -> str:
raw = json.dumps(
{
"tenant_id": job.tenant_id,
"cell_id": job.cell_id,
"profile_id": job.profile_id,
"task_id": job.task_id,
"trace_id": job.trace_id,
"action": job.action,
"payload": dict(job.payload),
"priority": job.priority,
},
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
default=str,
).encode("utf-8")
return hashlib.sha256(raw).hexdigest()
@staticmethod
def _parse(value: str | None) -> datetime | None:
if value is None:
return None
normalized = value[:-1] + "+00:00" if value.endswith("Z") else value
parsed = datetime.fromisoformat(normalized)
if parsed.tzinfo is None:
raise ValueError("timestamp must include timezone")
return parsed.astimezone(timezone.utc)
@staticmethod
def _format(value: datetime) -> str:
return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
@staticmethod
def _assert_tenant(job: HermesJob, tenant_id: str) -> None:
if job.tenant_id != tenant_id:
raise HermesNotFound("job not found")
def enqueue(self, job: HermesJob) -> HermesJob:
if job.state != HermesJobState.QUEUED or job.revision != 1:
raise HermesConflict("new job must be QUEUED at revision 1")
digest = self._digest(job)
idem_ref = (job.tenant_id, job.idempotency_key)
with self.store.lock:
existing = self.store.jobs.get(job.job_id)
if existing is not None:
if self._digest(existing) != digest:
raise HermesConflict("job_id reused with different content")
return existing
prior = self.store.idempotency.get(idem_ref)
if prior is not None:
prior_id, prior_digest = prior
if prior_digest != digest:
raise HermesConflict("idempotency key reused with different content")
return self.store.jobs[prior_id]
self.store.jobs[job.job_id] = job
self.store.idempotency[idem_ref] = (job.job_id, digest)
self.store.persist_locked()
return job
def get(self, job_id: str, *, tenant_id: str) -> HermesJob:
with self.store.lock:
job = self.store.jobs.get(job_id)
if job is None:
raise HermesNotFound("job not found")
self._assert_tenant(job, tenant_id)
return job
def list_jobs(
self,
*,
tenant_id: str,
cell_id: str | None = None,
profile_id: str | None = None,
states: Iterable[HermesJobState | str] | None = None,
) -> list[HermesJob]:
state_filter = {HermesJobState(item) for item in states} if states else None
with self.store.lock:
if self._requeue_expired_locked():
self.store.persist_locked()
jobs = [
job
for job in self.store.jobs.values()
if job.tenant_id == tenant_id
and (cell_id is None or job.cell_id == cell_id)
and (profile_id is None or job.profile_id == profile_id)
and (state_filter is None or job.state in state_filter)
]
return sorted(jobs, key=lambda item: (item.priority, item.created_at, item.job_id))
def claim(
self,
*,
tenant_id: str,
cell_id: str,
profile_id: str,
worker_id: str,
lease_seconds: int | None = None,
job_id: str | None = None,
) -> HermesJob | None:
worker_id = str(worker_id or "").strip()
if not worker_id:
raise ValueError("worker_id is required")
duration = int(lease_seconds or self.default_lease_seconds)
if duration < 5:
raise ValueError("lease_seconds must be >= 5")
with self.store.lock:
self._requeue_expired_locked()
candidates = [
job
for job in self.store.jobs.values()
if job.tenant_id == tenant_id
and job.cell_id == cell_id
and job.profile_id == profile_id
and (job_id is None or job.job_id == job_id)
and job.state == HermesJobState.QUEUED
]
self.store.worker_heartbeats[worker_id] = (utc_now(), None)
if not candidates:
self.store.persist_locked()
return None
current = sorted(
candidates,
key=lambda item: (item.priority, item.created_at, item.job_id),
)[0]
claimed = self._transition_locked(
current,
HermesJobState.CLAIMED,
assigned_worker_id=worker_id,
lease_expires_at=self._format(
datetime.now(timezone.utc) + timedelta(seconds=duration)
),
)
self.store.worker_heartbeats[worker_id] = (utc_now(), claimed.job_id)
self.store.persist_locked()
return claimed
def start(
self,
job_id: str,
*,
tenant_id: str,
worker_id: str,
expected_revision: int | None = None,
) -> HermesJob:
with self.store.lock:
self._requeue_expired_locked()
current = self._owned_job_locked(job_id, tenant_id, worker_id)
self._assert_revision(current, expected_revision)
updated = self._transition_locked(current, HermesJobState.RUNNING)
self.store.persist_locked()
return updated
def heartbeat(
self,
job_id: str,
*,
tenant_id: str,
worker_id: str,
lease_seconds: int | None = None,
) -> HermesJob:
duration = int(lease_seconds or self.default_lease_seconds)
if duration < 5:
raise ValueError("lease_seconds must be >= 5")
with self.store.lock:
self._requeue_expired_locked()
current = self._owned_job_locked(job_id, tenant_id, worker_id)
if current.state not in {HermesJobState.CLAIMED, HermesJobState.RUNNING}:
raise HermesConflict("job does not accept heartbeat")
updated = replace(
current,
revision=current.revision + 1,
lease_expires_at=self._format(
datetime.now(timezone.utc) + timedelta(seconds=duration)
),
updated_at=utc_now(),
)
self.store.jobs[job_id] = updated
self.store.worker_heartbeats[worker_id] = (utc_now(), job_id)
self.store.persist_locked()
return updated
def complete(
self,
job_id: str,
*,
tenant_id: str,
worker_id: str,
output: Mapping[str, object],
expected_revision: int | None = None,
) -> HermesResult:
return self._finish(
job_id,
tenant_id=tenant_id,
worker_id=worker_id,
state=HermesJobState.COMPLETED,
output=output,
expected_revision=expected_revision,
)
def fail(
self,
job_id: str,
*,
tenant_id: str,
worker_id: str,
error: Mapping[str, object],
expected_revision: int | None = None,
) -> HermesResult:
return self._finish(
job_id,
tenant_id=tenant_id,
worker_id=worker_id,
state=HermesJobState.FAILED,
error=error,
expected_revision=expected_revision,
)
def cancel(
self,
job_id: str,
*,
tenant_id: str,
expected_revision: int | None = None,
) -> HermesResult:
with self.store.lock:
current = self.store.jobs.get(job_id)
if current is None:
raise HermesNotFound("job not found")
self._assert_tenant(current, tenant_id)
self._assert_revision(current, expected_revision)
if current.state in TERMINAL_STATES:
result = self.store.results.get(job_id)
if result is None:
raise HermesConflict("terminal result missing")
if result.state != HermesJobState.CANCELLED:
raise HermesConflict("job already has a different terminal result")
return result
updated = self._transition_locked(current, HermesJobState.CANCELLED)
result = HermesResult(
job_id=updated.job_id,
tenant_id=updated.tenant_id,
task_id=updated.task_id,
trace_id=updated.trace_id,
state=HermesJobState.CANCELLED,
worker_id=updated.assigned_worker_id,
error={"code": "cancelled", "message": "cancelled by AIOS"},
finished_at=utc_now(),
)
self.store.results[job_id] = result
self.store.persist_locked()
return result
def result(self, job_id: str, *, tenant_id: str) -> HermesResult:
with self.store.lock:
job = self.store.jobs.get(job_id)
if job is None:
raise HermesNotFound("job not found")
self._assert_tenant(job, tenant_id)
result = self.store.results.get(job_id)
if result is None:
raise HermesConflict("job has no terminal result")
return result
def requeue_expired(self) -> tuple[str, ...]:
"""Persistently release expired leases without changing policy state."""
with self.store.lock:
changed = self._requeue_expired_locked()
if changed:
self.store.persist_locked()
return tuple(sorted(changed))
def health(self) -> HermesHealth:
with self.store.lock:
if self._requeue_expired_locked():
self.store.persist_locked()
active_jobs = sum(
1 for job in self.store.jobs.values()
if job.state in {HermesJobState.CLAIMED, HermesJobState.RUNNING}
)
queued_jobs = sum(
1 for job in self.store.jobs.values()
if job.state == HermesJobState.QUEUED
)
partitions = {
(job.tenant_id, job.cell_id, job.profile_id)
for job in self.store.jobs.values()
}
active_workers = sum(
1 for heartbeat, _ in self.store.worker_heartbeats.values()
if self._parse(heartbeat)
and self._parse(heartbeat) >= datetime.now(timezone.utc) - timedelta(seconds=120)
)
return HermesHealth(
runtime_id=self.runtime_id,
status="healthy",
version=self.runtime_version,
heartbeat_at=utc_now(),
active_workers=active_workers,
active_jobs=active_jobs,
queued_jobs=queued_jobs,
tenant_partitions=len(partitions),
profile_isolation_enforced=True,
details={"store": type(self.store).__name__},
)
def _finish(
self,
job_id: str,
*,
tenant_id: str,
worker_id: str,
state: HermesJobState,
output: Mapping[str, object] | None = None,
error: Mapping[str, object] | None = None,
expected_revision: int | None,
) -> HermesResult:
with self.store.lock:
self._requeue_expired_locked()
current = self._owned_job_locked(job_id, tenant_id, worker_id)
if current.state in TERMINAL_STATES:
existing = self.store.results.get(job_id)
if existing is None:
raise HermesConflict("terminal result missing")
if (
existing.state == state
and existing.worker_id == worker_id
and existing.output == output
and existing.error == error
):
return existing
raise HermesConflict("job already has a different terminal result")
self._assert_revision(current, expected_revision)
updated = self._transition_locked(current, state)
result = HermesResult(
job_id=updated.job_id,
tenant_id=updated.tenant_id,
task_id=updated.task_id,
trace_id=updated.trace_id,
state=state,
worker_id=worker_id,
output=output,
error=error,
started_at=current.updated_at,
finished_at=utc_now(),
)
self.store.results[job_id] = result
self.store.worker_heartbeats[worker_id] = (utc_now(), None)
self.store.persist_locked()
return result
def _owned_job_locked(self, job_id: str, tenant_id: str, worker_id: str) -> HermesJob:
current = self.store.jobs.get(job_id)
if current is None:
raise HermesNotFound("job not found")
self._assert_tenant(current, tenant_id)
if current.assigned_worker_id != worker_id:
raise HermesConflict("worker does not own job lease")
return current
@staticmethod
def _assert_revision(job: HermesJob, expected: int | None) -> None:
if expected is not None and job.revision != expected:
raise HermesConflict("job revision changed")
def _transition_locked(
self,
current: HermesJob,
target: HermesJobState,
*,
assigned_worker_id: str | None = None,
lease_expires_at: str | None = None,
) -> HermesJob:
if target not in ALLOWED_TRANSITIONS[current.state]:
raise HermesConflict(
f"invalid transition {current.state.value} -> {target.value}"
)
updated = replace(
current,
state=target,
revision=current.revision + 1,
assigned_worker_id=(
assigned_worker_id
if assigned_worker_id is not None
else current.assigned_worker_id
),
lease_expires_at=(
lease_expires_at
if lease_expires_at is not None
else (None if target in TERMINAL_STATES else current.lease_expires_at)
),
updated_at=utc_now(),
)
self.store.jobs[current.job_id] = updated
return updated
def _requeue_expired_locked(self) -> set[str]:
now = datetime.now(timezone.utc)
changed: set[str] = set()
for current in list(self.store.jobs.values()):
expiry = self._parse(current.lease_expires_at)
if (
current.state in {HermesJobState.CLAIMED, HermesJobState.RUNNING}
and expiry is not None
and expiry <= now
):
self.store.jobs[current.job_id] = replace(
current,
state=HermesJobState.QUEUED,
revision=current.revision + 1,
assigned_worker_id=None,
lease_expires_at=None,
updated_at=utc_now(),
)
changed.add(current.job_id)
return changed
+153
View File
@@ -0,0 +1,153 @@
"""Tenant-scoped Hermes runtime contracts."""
from __future__ import annotations
import json
import uuid
from dataclasses import dataclass, field
from datetime import datetime, timezone
from enum import Enum
from typing import Any, Mapping
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def _required(value: str, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
def _safe_mapping(value: Mapping[str, Any] | None) -> dict[str, Any]:
return json.loads(json.dumps(dict(value or {}), ensure_ascii=False, sort_keys=True, default=str))
class HermesJobState(str, Enum):
QUEUED = "QUEUED"
CLAIMED = "CLAIMED"
RUNNING = "RUNNING"
COMPLETED = "COMPLETED"
FAILED = "FAILED"
CANCELLED = "CANCELLED"
ALLOWED_TRANSITIONS: Mapping[HermesJobState, frozenset[HermesJobState]] = {
HermesJobState.QUEUED: frozenset({HermesJobState.CLAIMED, HermesJobState.CANCELLED}),
HermesJobState.CLAIMED: frozenset({HermesJobState.RUNNING, HermesJobState.CANCELLED}),
HermesJobState.RUNNING: frozenset(
{HermesJobState.COMPLETED, HermesJobState.FAILED, HermesJobState.CANCELLED}
),
HermesJobState.COMPLETED: frozenset(),
HermesJobState.FAILED: frozenset(),
HermesJobState.CANCELLED: frozenset(),
}
TERMINAL_STATES = frozenset(
{HermesJobState.COMPLETED, HermesJobState.FAILED, HermesJobState.CANCELLED}
)
@dataclass(frozen=True)
class HermesJob:
job_id: str
tenant_id: str
cell_id: str
profile_id: str
task_id: str
trace_id: str
action: str
payload: Mapping[str, Any] = field(default_factory=dict)
idempotency_key: str = ""
priority: int = 100
state: HermesJobState = HermesJobState.QUEUED
revision: int = 1
assigned_worker_id: str | None = None
lease_expires_at: str | None = None
created_at: str = field(default_factory=utc_now)
updated_at: str = field(default_factory=utc_now)
def __post_init__(self) -> None:
for name in (
"job_id", "tenant_id", "cell_id", "profile_id", "task_id",
"trace_id", "action", "idempotency_key", "created_at", "updated_at",
):
object.__setattr__(self, name, _required(getattr(self, name), name))
object.__setattr__(self, "payload", _safe_mapping(self.payload))
object.__setattr__(self, "state", HermesJobState(self.state))
if not 0 <= int(self.priority) <= 1000:
raise ValueError("priority must be between 0 and 1000")
if self.revision < 1:
raise ValueError("revision must be >= 1")
@classmethod
def create(
cls,
*,
tenant_id: str,
cell_id: str,
profile_id: str,
task_id: str,
trace_id: str,
action: str,
payload: Mapping[str, Any] | None,
idempotency_key: str,
priority: int = 100,
) -> "HermesJob":
return cls(
job_id=f"hermes_{uuid.uuid4().hex}",
tenant_id=tenant_id,
cell_id=cell_id,
profile_id=profile_id,
task_id=task_id,
trace_id=trace_id,
action=action,
payload=_safe_mapping(payload),
idempotency_key=idempotency_key,
priority=priority,
)
@dataclass(frozen=True)
class HermesResult:
job_id: str
tenant_id: str
task_id: str
trace_id: str
state: HermesJobState
worker_id: str | None = None
output: Mapping[str, Any] | None = None
error: Mapping[str, Any] | None = None
started_at: str | None = None
finished_at: str | None = None
def __post_init__(self) -> None:
for name in ("job_id", "tenant_id", "task_id", "trace_id"):
object.__setattr__(self, name, _required(getattr(self, name), name))
object.__setattr__(self, "state", HermesJobState(self.state))
if self.output is not None:
object.__setattr__(self, "output", _safe_mapping(self.output))
if self.error is not None:
object.__setattr__(self, "error", _safe_mapping(self.error))
@dataclass(frozen=True)
class HermesHealth:
runtime_id: str
status: str
version: str
heartbeat_at: str
active_workers: int = 0
active_jobs: int = 0
queued_jobs: int = 0
tenant_partitions: int = 0
profile_isolation_enforced: bool = True
details: Mapping[str, Any] = field(default_factory=dict)
def __post_init__(self) -> None:
for name in ("runtime_id", "status", "version", "heartbeat_at"):
object.__setattr__(self, name, _required(getattr(self, name), name))
for name in ("active_workers", "active_jobs", "queued_jobs", "tenant_partitions"):
if int(getattr(self, name)) < 0:
raise ValueError(f"{name} must be >= 0")
object.__setattr__(self, "details", _safe_mapping(self.details))
+155
View File
@@ -0,0 +1,155 @@
"""Hermes worker loop with lease renewal and bounded recovery."""
from __future__ import annotations
import threading
from dataclasses import dataclass
from typing import Any, Callable, Mapping
from .adapter import HermesAdapter, HermesConflict
from .contract import HermesJob, HermesJobState
JobHandler = Callable[[HermesJob], Mapping[str, Any]]
@dataclass(frozen=True)
class WorkerRunResult:
claimed: bool
job_id: str | None = None
state: str | None = None
error: str | None = None
class HermesWorker:
"""Poll one tenant/cell/profile partition and execute jobs safely."""
def __init__(
self,
adapter: HermesAdapter,
handler: JobHandler,
*,
worker_id: str,
tenant_id: str,
cell_id: str,
profile_id: str,
poll_seconds: float = 1.0,
heartbeat_seconds: float = 10.0,
) -> None:
if poll_seconds <= 0 or heartbeat_seconds <= 0:
raise ValueError("poll_seconds and heartbeat_seconds must be positive")
for name, value in {
"worker_id": worker_id,
"tenant_id": tenant_id,
"cell_id": cell_id,
"profile_id": profile_id,
}.items():
if not str(value or "").strip():
raise ValueError(f"{name} is required")
self.adapter = adapter
self.handler = handler
self.worker_id = worker_id
self.tenant_id = tenant_id
self.cell_id = cell_id
self.profile_id = profile_id
self.poll_seconds = float(poll_seconds)
self.heartbeat_seconds = float(heartbeat_seconds)
self._stop = threading.Event()
def stop(self) -> None:
self._stop.set()
def run_once(self) -> WorkerRunResult:
job = self.adapter.claim(
tenant_id=self.tenant_id,
cell_id=self.cell_id,
profile_id=self.profile_id,
worker_id=self.worker_id,
)
if job is None:
return WorkerRunResult(claimed=False)
running = self.adapter.start(
job.job_id,
tenant_id=self.tenant_id,
worker_id=self.worker_id,
expected_revision=job.revision,
)
heartbeat_stop = threading.Event()
heartbeat_thread = threading.Thread(
target=self._heartbeat_loop,
args=(running.job_id, heartbeat_stop),
name=f"hermes-heartbeat-{self.worker_id}",
daemon=True,
)
heartbeat_thread.start()
output: Mapping[str, Any] | None = None
execution_error: Exception | None = None
try:
output = dict(self.handler(running))
except Exception as exc: # runtime boundary: normalize below
execution_error = exc
finally:
# Stop the lease heartbeat before reading the final revision. This
# prevents a revision increment racing with complete/fail.
heartbeat_stop.set()
heartbeat_thread.join(timeout=max(self.heartbeat_seconds * 2, 1.0))
try:
current = self.adapter.get(running.job_id, tenant_id=self.tenant_id)
if execution_error is None:
result = self.adapter.complete(
running.job_id,
tenant_id=self.tenant_id,
worker_id=self.worker_id,
output=dict(output or {}),
expected_revision=current.revision,
)
return WorkerRunResult(
claimed=True,
job_id=result.job_id,
state=result.state.value,
)
result = self.adapter.fail(
running.job_id,
tenant_id=self.tenant_id,
worker_id=self.worker_id,
error={
"code": "worker_error",
"message": str(execution_error),
},
expected_revision=current.revision,
)
return WorkerRunResult(
claimed=True,
job_id=result.job_id,
state=result.state.value,
error=str(execution_error),
)
except HermesConflict as exc:
return WorkerRunResult(
claimed=True,
job_id=running.job_id,
state=HermesJobState.FAILED.value,
error=f"reconciliation_conflict: {exc}",
)
def run_forever(self) -> None:
while not self._stop.is_set():
result = self.run_once()
if not result.claimed:
self._stop.wait(self.poll_seconds)
def _heartbeat_loop(self, job_id: str, stop_event: threading.Event) -> None:
while not stop_event.wait(self.heartbeat_seconds):
try:
self.adapter.heartbeat(
job_id,
tenant_id=self.tenant_id,
worker_id=self.worker_id,
)
except Exception:
stop_event.set()
return
@@ -0,0 +1,45 @@
"""AIOS-managed OpenClaw Ed25519 execution adapter."""
from .adapter import (
AdapterError,
CommandConflict,
CommandNotFound,
CommandRejected,
InMemoryCallbackSink,
OpenClawAdapter,
)
from .contract import (
CONTRACT_VERSION,
SIGNATURE_ALGORITHM,
CommandState,
Ed25519CommandSigner,
Ed25519CommandVerifier,
OpenClawCommand,
OpenClawResult,
RuntimeHealth,
sign_command,
verify_command_signature,
)
from .transport import HTTPRuntimeTransport, InProcessRuntimeTransport, RuntimeTransport
__all__ = [
"AdapterError",
"CONTRACT_VERSION",
"CommandConflict",
"CommandNotFound",
"CommandRejected",
"CommandState",
"Ed25519CommandSigner",
"Ed25519CommandVerifier",
"HTTPRuntimeTransport",
"InMemoryCallbackSink",
"InProcessRuntimeTransport",
"OpenClawAdapter",
"OpenClawCommand",
"OpenClawResult",
"RuntimeHealth",
"RuntimeTransport",
"SIGNATURE_ALGORITHM",
"sign_command",
"verify_command_signature",
]
+228
View File
@@ -0,0 +1,228 @@
"""Signed, tenant-isolated execution adapter for OpenClaw runtimes."""
from __future__ import annotations
import threading
from dataclasses import replace
from typing import Callable, Mapping, Protocol
from .contract import (
CommandState,
OpenClawCommand,
OpenClawResult,
RuntimeHealth,
utc_now,
verify_command_signature,
)
class AdapterError(RuntimeError):
"""Base adapter failure."""
class CommandRejected(AdapterError):
"""A command failed signature or contract validation."""
class CommandNotFound(AdapterError):
"""A tenant-scoped command is not visible."""
class CommandConflict(AdapterError):
"""A command or idempotency key conflicts with an existing execution."""
class RuntimeTransport(Protocol):
def execute(self, command: OpenClawCommand, timeout_seconds: float) -> OpenClawResult: ...
def cancel(self, command_id: str) -> bool: ...
def health(self) -> RuntimeHealth: ...
class CallbackSink(Protocol):
def on_started(self, result: OpenClawResult) -> None: ...
def on_completed(self, result: OpenClawResult) -> None: ...
def on_failed(self, result: OpenClawResult) -> None: ...
class InMemoryCallbackSink:
def __init__(self) -> None:
self._lock = threading.RLock()
self.started: list[OpenClawResult] = []
self.completed: list[OpenClawResult] = []
self.failed: list[OpenClawResult] = []
def on_started(self, result: OpenClawResult) -> None:
with self._lock:
self.started.append(result)
def on_completed(self, result: OpenClawResult) -> None:
with self._lock:
self.completed.append(result)
def on_failed(self, result: OpenClawResult) -> None:
with self._lock:
self.failed.append(result)
SigningMaterialResolver = Callable[[str, str], bytes | str]
class OpenClawAdapter:
"""Verify, de-duplicate, execute, cancel and reconcile commands."""
def __init__(
self,
transport: RuntimeTransport,
signing_material_resolver: SigningMaterialResolver,
*,
callback_sink: CallbackSink | None = None,
default_timeout_seconds: float = 300.0,
) -> None:
if default_timeout_seconds <= 0:
raise ValueError("default_timeout_seconds must be positive")
self.transport = transport
self.signing_material_resolver = signing_material_resolver
self.callback_sink = callback_sink or InMemoryCallbackSink()
self.default_timeout_seconds = float(default_timeout_seconds)
self._lock = threading.RLock()
self._commands: dict[str, OpenClawCommand] = {}
self._results: dict[str, OpenClawResult] = {}
self._idempotency: dict[tuple[str, str], tuple[str, str]] = {}
def _verify(self, command: OpenClawCommand) -> None:
try:
key_material = self.signing_material_resolver(command.tenant_id, command.key_id)
except Exception as exc:
raise CommandRejected("signing material unavailable") from exc
if not verify_command_signature(command, key_material):
raise CommandRejected("invalid or expired command signature")
@staticmethod
def _validate_result(command: OpenClawCommand, result: OpenClawResult) -> None:
if (
result.command_id != command.command_id
or result.tenant_id != command.tenant_id
or result.task_id != command.task_id
or result.trace_id != command.trace_id
):
raise AdapterError("runtime returned mismatched command identity")
if result.state not in {
CommandState.COMPLETED,
CommandState.FAILED,
CommandState.CANCELLED,
CommandState.TIMED_OUT,
}:
raise AdapterError("runtime returned a non-terminal result")
def execute(
self,
command: OpenClawCommand,
*,
timeout_seconds: float | None = None,
) -> OpenClawResult:
timeout = self.default_timeout_seconds if timeout_seconds is None else float(timeout_seconds)
if timeout <= 0:
raise ValueError("timeout_seconds must be positive")
self._verify(command)
digest = command.signature
idem_ref = (command.tenant_id, command.idempotency_key)
with self._lock:
prior_command = self._commands.get(command.command_id)
if prior_command is not None:
if prior_command.signature != command.signature:
raise CommandConflict("command_id reused with different content")
return self._results[command.command_id]
prior_idem = self._idempotency.get(idem_ref)
if prior_idem is not None:
prior_id, prior_digest = prior_idem
if prior_digest != digest:
raise CommandConflict("idempotency key reused with different content")
return self._results[prior_id]
running = OpenClawResult(
command_id=command.command_id,
tenant_id=command.tenant_id,
task_id=command.task_id,
trace_id=command.trace_id,
state=CommandState.RUNNING,
started_at=utc_now(),
)
self._commands[command.command_id] = command
self._results[command.command_id] = running
self._idempotency[idem_ref] = (command.command_id, digest)
self.callback_sink.on_started(running)
try:
result = self.transport.execute(command, timeout)
self._validate_result(command, result)
except TimeoutError as exc:
result = replace(
running,
state=CommandState.TIMED_OUT,
error={"code": "runtime_timeout", "message": str(exc) or "runtime timeout"},
finished_at=utc_now(),
)
except Exception as exc:
result = replace(
running,
state=CommandState.FAILED,
error={"code": "runtime_error", "message": str(exc)},
finished_at=utc_now(),
)
if result.started_at is None:
result = replace(result, started_at=running.started_at)
if result.finished_at is None:
result = replace(result, finished_at=utc_now())
with self._lock:
self._results[command.command_id] = result
if result.state == CommandState.COMPLETED:
self.callback_sink.on_completed(result)
else:
self.callback_sink.on_failed(result)
return result
def status(self, command_id: str, *, tenant_id: str) -> OpenClawResult:
with self._lock:
command = self._commands.get(command_id)
result = self._results.get(command_id)
if command is None or result is None or command.tenant_id != tenant_id:
raise CommandNotFound("command not found")
return result
def cancel(self, command_id: str, *, tenant_id: str) -> OpenClawResult:
with self._lock:
command = self._commands.get(command_id)
current = self._results.get(command_id)
if command is None or current is None or command.tenant_id != tenant_id:
raise CommandNotFound("command not found")
if current.state in {
CommandState.COMPLETED,
CommandState.FAILED,
CommandState.CANCELLED,
CommandState.TIMED_OUT,
CommandState.REJECTED,
}:
return current
if not self.transport.cancel(command_id):
raise AdapterError("runtime rejected cancellation")
cancelled = replace(
current,
state=CommandState.CANCELLED,
error={"code": "cancelled", "message": "cancelled by AIOS"},
finished_at=utc_now(),
)
with self._lock:
self._results[command_id] = cancelled
self.callback_sink.on_failed(cancelled)
return cancelled
def health(self) -> RuntimeHealth:
return self.transport.health()
def snapshot(self, *, tenant_id: str) -> Mapping[str, OpenClawResult]:
with self._lock:
return {
command_id: result
for command_id, result in self._results.items()
if self._commands[command_id].tenant_id == tenant_id
}
@@ -0,0 +1,97 @@
"""Audit-oriented lifecycle callbacks for OpenClaw execution."""
from __future__ import annotations
import json
import threading
from dataclasses import dataclass, field
from typing import Any, Mapping, Protocol
from .contract import OpenClawResult, utc_now
class EventPublisher(Protocol):
def publish(self, event: Mapping[str, Any]) -> None: ...
@dataclass(frozen=True)
class ExecutionEvent:
event_type: str
tenant_id: str
task_id: str
trace_id: str
command_id: str
state: str
created_at: str = field(default_factory=utc_now)
details: Mapping[str, Any] = field(default_factory=dict)
def as_dict(self) -> dict[str, Any]:
return {
"event_type": self.event_type,
"tenant_id": self.tenant_id,
"task_id": self.task_id,
"trace_id": self.trace_id,
"command_id": self.command_id,
"state": self.state,
"created_at": self.created_at,
"details": json.loads(
json.dumps(dict(self.details), ensure_ascii=False, default=str)
),
}
class InMemoryEventPublisher:
"""Thread-safe publisher used by tests and first integration slice."""
def __init__(self) -> None:
self._lock = threading.RLock()
self.events: list[dict[str, Any]] = []
def publish(self, event: Mapping[str, Any]) -> None:
with self._lock:
self.events.append(
json.loads(json.dumps(dict(event), ensure_ascii=False, default=str))
)
class AuditCallbackSink:
"""Convert runtime callbacks into tenant-scoped audit events."""
def __init__(self, publisher: EventPublisher) -> None:
self.publisher = publisher
@staticmethod
def _event(
event_type: str,
result: OpenClawResult,
) -> ExecutionEvent:
details: dict[str, Any] = {
"runtime_id": result.runtime_id,
"attempts": result.attempts,
}
if result.error:
details["error"] = dict(result.error)
if result.output:
details["output_present"] = True
return ExecutionEvent(
event_type=event_type,
tenant_id=result.tenant_id,
task_id=result.task_id,
trace_id=result.trace_id,
command_id=result.command_id,
state=result.state.value,
details=details,
)
def on_started(self, result: OpenClawResult) -> None:
self.publisher.publish(self._event("OPENCLAW_STARTED", result).as_dict())
def on_completed(self, result: OpenClawResult) -> None:
self.publisher.publish(self._event("OPENCLAW_COMPLETED", result).as_dict())
def on_failed(self, result: OpenClawResult) -> None:
event_type = {
"CANCELLED": "OPENCLAW_CANCELLED",
"TIMED_OUT": "OPENCLAW_TIMED_OUT",
"REJECTED": "OPENCLAW_REJECTED",
}.get(result.state.value, "OPENCLAW_FAILED")
self.publisher.publish(self._event(event_type, result).as_dict())
@@ -0,0 +1,383 @@
"""AIOS 到 OpenClaw 的 Ed25519 执行合同。"""
from __future__ import annotations
import base64
import hashlib
import hmac
import json
import uuid
from dataclasses import dataclass, field, replace
from datetime import datetime, timezone
from enum import Enum
from typing import Any, Mapping, Protocol
CONTRACT_VERSION = "aios.openclaw.command.v2"
SIGNATURE_ALGORITHM = "Ed25519"
DEFAULT_CLOCK_SKEW_SECONDS = 300
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def _parse_timestamp(value: str) -> datetime:
normalized = str(value or "").strip()
if not normalized:
raise ValueError("timestamp is required")
if normalized.endswith("Z"):
normalized = normalized[:-1] + "+00:00"
parsed = datetime.fromisoformat(normalized)
if parsed.tzinfo is None:
raise ValueError("timestamp must include a timezone")
return parsed.astimezone(timezone.utc)
def _required(value: str, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
def _safe_mapping(value: Mapping[str, Any] | None) -> dict[str, Any]:
return json.loads(
json.dumps(dict(value or {}), ensure_ascii=False, sort_keys=True, default=str)
)
def _load_crypto() -> tuple[Any, Any, Any]:
try:
from cryptography.hazmat.primitives import serialization
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
Ed25519PrivateKey,
Ed25519PublicKey,
)
except ImportError as exc: # pragma: no cover
raise RuntimeError("cryptography with Ed25519 support is required") from exc
return serialization, Ed25519PrivateKey, Ed25519PublicKey
class CommandSigner(Protocol):
key_id: str
fingerprint: str
def sign(self, payload: bytes) -> bytes: ...
class CommandVerifier(Protocol):
key_id: str
fingerprint: str
def verify(self, payload: bytes, signature: bytes) -> bool: ...
class Ed25519CommandSigner:
def __init__(self, private_key: Any, *, key_id: str) -> None:
serialization, private_cls, _ = _load_crypto()
if not isinstance(private_key, private_cls):
raise ValueError("private key is not Ed25519")
self.private_key = private_key
self.key_id = _required(key_id, "key_id")
raw = private_key.public_key().public_bytes(
encoding=serialization.Encoding.Raw,
format=serialization.PublicFormat.Raw,
)
self.fingerprint = hashlib.sha256(raw).hexdigest()
@classmethod
def from_bytes(cls, value: bytes | str, *, key_id: str) -> "Ed25519CommandSigner":
serialization, private_cls, _ = _load_crypto()
raw = value.encode("utf-8") if isinstance(value, str) else bytes(value)
if raw.startswith(b"-----BEGIN"):
key = serialization.load_pem_private_key(raw, password=None)
elif len(raw) == 32:
key = private_cls.from_private_bytes(raw)
else:
raise ValueError("Ed25519 private key must be PEM or a raw 32-byte seed")
return cls(key, key_id=key_id)
def sign(self, payload: bytes) -> bytes:
return self.private_key.sign(bytes(payload))
def verifier(self) -> "Ed25519CommandVerifier":
return Ed25519CommandVerifier(self.private_key.public_key(), key_id=self.key_id)
class Ed25519CommandVerifier:
def __init__(self, public_key: Any, *, key_id: str) -> None:
serialization, _, public_cls = _load_crypto()
if not isinstance(public_key, public_cls):
raise ValueError("public key is not Ed25519")
self.public_key = public_key
self.key_id = _required(key_id, "key_id")
raw = public_key.public_bytes(
encoding=serialization.Encoding.Raw,
format=serialization.PublicFormat.Raw,
)
self.fingerprint = hashlib.sha256(raw).hexdigest()
@classmethod
def from_bytes(cls, value: bytes | str, *, key_id: str) -> "Ed25519CommandVerifier":
serialization, private_cls, public_cls = _load_crypto()
raw = value.encode("utf-8") if isinstance(value, str) else bytes(value)
if raw.startswith(b"-----BEGIN"):
try:
key = serialization.load_pem_public_key(raw)
except ValueError:
private = serialization.load_pem_private_key(raw, password=None)
if not isinstance(private, private_cls):
raise ValueError("key is not Ed25519")
key = private.public_key()
elif len(raw) == 32:
key = public_cls.from_public_bytes(raw)
else:
raise ValueError("Ed25519 public key must be PEM or raw 32-byte key")
return cls(key, key_id=key_id)
def verify(self, payload: bytes, signature: bytes) -> bool:
try:
self.public_key.verify(bytes(signature), bytes(payload))
return True
except Exception:
return False
class CommandState(str, Enum):
ACCEPTED = "ACCEPTED"
RUNNING = "RUNNING"
COMPLETED = "COMPLETED"
FAILED = "FAILED"
CANCELLED = "CANCELLED"
TIMED_OUT = "TIMED_OUT"
REJECTED = "REJECTED"
@dataclass(frozen=True)
class OpenClawCommand:
command_id: str
tenant_id: str
task_id: str
trace_id: str
action: str
payload: Mapping[str, Any] = field(default_factory=dict)
idempotency_key: str = ""
created_at: str = field(default_factory=utc_now)
expires_at: str | None = None
contract_version: str = CONTRACT_VERSION
signature_algorithm: str = SIGNATURE_ALGORITHM
key_id: str = "default"
public_key_fingerprint: str = ""
signature: str = ""
def __post_init__(self) -> None:
for field_name in (
"command_id",
"tenant_id",
"task_id",
"trace_id",
"action",
"idempotency_key",
"created_at",
"contract_version",
"signature_algorithm",
"key_id",
):
object.__setattr__(
self, field_name, _required(getattr(self, field_name), field_name)
)
if self.contract_version != CONTRACT_VERSION:
raise ValueError(f"unsupported contract_version: {self.contract_version}")
if self.signature_algorithm != SIGNATURE_ALGORITHM:
raise ValueError(
f"unsupported signature_algorithm: {self.signature_algorithm}"
)
object.__setattr__(self, "payload", _safe_mapping(self.payload))
object.__setattr__(
self, "public_key_fingerprint", str(self.public_key_fingerprint or "").strip()
)
object.__setattr__(self, "signature", str(self.signature or "").strip())
_parse_timestamp(self.created_at)
if self.expires_at is not None:
object.__setattr__(self, "expires_at", _required(self.expires_at, "expires_at"))
if _parse_timestamp(self.expires_at) <= _parse_timestamp(self.created_at):
raise ValueError("expires_at must be later than created_at")
@classmethod
def create(
cls,
*,
tenant_id: str,
task_id: str,
trace_id: str,
action: str,
payload: Mapping[str, Any] | None,
idempotency_key: str,
expires_at: str | None = None,
key_id: str = "default",
command_id: str | None = None,
) -> "OpenClawCommand":
return cls(
command_id=command_id or f"cmd_{uuid.uuid4().hex}",
tenant_id=tenant_id,
task_id=task_id,
trace_id=trace_id,
action=action,
payload=_safe_mapping(payload),
idempotency_key=idempotency_key,
expires_at=expires_at,
key_id=key_id,
)
def unsigned_dict(self) -> dict[str, Any]:
return {
"command_id": self.command_id,
"tenant_id": self.tenant_id,
"task_id": self.task_id,
"trace_id": self.trace_id,
"action": self.action,
"payload": _safe_mapping(self.payload),
"idempotency_key": self.idempotency_key,
"created_at": self.created_at,
"expires_at": self.expires_at,
"contract_version": self.contract_version,
"signature_algorithm": self.signature_algorithm,
"key_id": self.key_id,
"public_key_fingerprint": self.public_key_fingerprint,
}
@dataclass(frozen=True)
class OpenClawResult:
command_id: str
tenant_id: str
task_id: str
trace_id: str
state: CommandState
output: Mapping[str, Any] | None = None
error: Mapping[str, Any] | None = None
started_at: str | None = None
finished_at: str | None = None
runtime_id: str | None = None
attempts: int = 1
def __post_init__(self) -> None:
for field_name in ("command_id", "tenant_id", "task_id", "trace_id"):
object.__setattr__(
self, field_name, _required(getattr(self, field_name), field_name)
)
object.__setattr__(self, "state", CommandState(self.state))
if self.output is not None:
object.__setattr__(self, "output", _safe_mapping(self.output))
if self.error is not None:
object.__setattr__(self, "error", _safe_mapping(self.error))
if self.started_at is not None:
_parse_timestamp(self.started_at)
if self.finished_at is not None:
_parse_timestamp(self.finished_at)
if self.attempts < 1:
raise ValueError("attempts must be >= 1")
@dataclass(frozen=True)
class RuntimeHealth:
runtime: str
runtime_id: str
status: str
version: str
heartbeat_at: str
active_tasks: int = 0
workspace_isolated: bool = False
credential_ref_configured: bool = False
details: Mapping[str, Any] = field(default_factory=dict)
def __post_init__(self) -> None:
for field_name in (
"runtime",
"runtime_id",
"status",
"version",
"heartbeat_at",
):
object.__setattr__(
self, field_name, _required(getattr(self, field_name), field_name)
)
_parse_timestamp(self.heartbeat_at)
if self.active_tasks < 0:
raise ValueError("active_tasks must be >= 0")
object.__setattr__(self, "details", _safe_mapping(self.details))
def canonical_command_bytes(command: OpenClawCommand) -> bytes:
return json.dumps(
command.unsigned_dict(),
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
).encode("utf-8")
def _as_signer(command: OpenClawCommand, value: Any) -> CommandSigner:
if hasattr(value, "sign") and hasattr(value, "fingerprint") and hasattr(value, "key_id"):
return value
return Ed25519CommandSigner.from_bytes(value, key_id=command.key_id)
def _as_verifier(command: OpenClawCommand, value: Any) -> CommandVerifier:
if isinstance(value, Ed25519CommandSigner):
return value.verifier()
if hasattr(value, "verify") and hasattr(value, "fingerprint") and hasattr(value, "key_id"):
return value
return Ed25519CommandVerifier.from_bytes(value, key_id=command.key_id)
def sign_command(command: OpenClawCommand, signing_key: Any) -> OpenClawCommand:
signer = _as_signer(command, signing_key)
if signer.key_id != command.key_id:
raise ValueError("command key_id does not match signer")
prepared = replace(
command,
signature_algorithm=SIGNATURE_ALGORITHM,
public_key_fingerprint=signer.fingerprint,
signature="",
)
signature = base64.b64encode(
signer.sign(canonical_command_bytes(prepared))
).decode("ascii")
return replace(prepared, signature=signature)
def verify_command_signature(
command: OpenClawCommand,
verification_key: Any,
*,
now: datetime | None = None,
clock_skew_seconds: int = DEFAULT_CLOCK_SKEW_SECONDS,
) -> bool:
if (
not command.signature
or command.contract_version != CONTRACT_VERSION
or command.signature_algorithm != SIGNATURE_ALGORITHM
):
return False
try:
verifier = _as_verifier(command, verification_key)
signature = base64.b64decode(command.signature, validate=True)
except Exception:
return False
if verifier.key_id != command.key_id:
return False
if not command.public_key_fingerprint or not hmac.compare_digest(
command.public_key_fingerprint, verifier.fingerprint
):
return False
if not verifier.verify(canonical_command_bytes(command), signature):
return False
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
created = _parse_timestamp(command.created_at)
if created.timestamp() - current.timestamp() > clock_skew_seconds:
return False
if command.expires_at is not None:
expires = _parse_timestamp(command.expires_at)
if current.timestamp() - expires.timestamp() > clock_skew_seconds:
return False
return True
+103
View File
@@ -0,0 +1,103 @@
"""Health policy and self-healing decisions for OpenClaw runtimes."""
from __future__ import annotations
from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Mapping
from .contract import RuntimeHealth
def _parse(value: str) -> datetime:
normalized = value[:-1] + "+00:00" if value.endswith("Z") else value
parsed = datetime.fromisoformat(normalized)
if parsed.tzinfo is None:
raise ValueError("heartbeat timestamp must include timezone")
return parsed.astimezone(timezone.utc)
@dataclass(frozen=True)
class HealthPolicy:
max_heartbeat_age_seconds: int = 90
require_workspace_isolation: bool = True
require_credential_ref: bool = True
accepted_statuses: frozenset[str] = field(
default_factory=lambda: frozenset({"healthy", "ready"})
)
def __post_init__(self) -> None:
if self.max_heartbeat_age_seconds < 5:
raise ValueError("max_heartbeat_age_seconds must be >= 5")
if not self.accepted_statuses:
raise ValueError("accepted_statuses must not be empty")
@dataclass(frozen=True)
class HealthAssessment:
healthy: bool
reasons: tuple[str, ...]
recoverable: bool
recommended_action: str
details: Mapping[str, object] = field(default_factory=dict)
class RuntimeHealthMonitor:
"""Evaluate runtime health and recommend bounded recovery actions."""
def __init__(self, policy: HealthPolicy | None = None) -> None:
self.policy = policy or HealthPolicy()
def assess(
self,
health: RuntimeHealth,
*,
now: datetime | None = None,
) -> HealthAssessment:
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
heartbeat = _parse(health.heartbeat_at)
age = max(0.0, current.timestamp() - heartbeat.timestamp())
reasons: list[str] = []
if health.status.lower() not in self.policy.accepted_statuses:
reasons.append("runtime_status_unhealthy")
if age > self.policy.max_heartbeat_age_seconds:
reasons.append("heartbeat_stale")
if self.policy.require_workspace_isolation and not health.workspace_isolated:
reasons.append("workspace_not_isolated")
if self.policy.require_credential_ref and not health.credential_ref_configured:
reasons.append("credential_reference_missing")
if not reasons:
return HealthAssessment(
healthy=True,
reasons=(),
recoverable=True,
recommended_action="none",
details={"heartbeat_age_seconds": age},
)
non_recoverable = {
"workspace_not_isolated",
"credential_reference_missing",
}.intersection(reasons)
if non_recoverable:
action = "quarantine_runtime"
recoverable = False
elif "heartbeat_stale" in reasons:
action = "restart_runtime"
recoverable = True
else:
action = "drain_and_restart"
recoverable = True
return HealthAssessment(
healthy=False,
reasons=tuple(reasons),
recoverable=recoverable,
recommended_action=action,
details={
"heartbeat_age_seconds": age,
"runtime_id": health.runtime_id,
"active_tasks": health.active_tasks,
},
)
@@ -0,0 +1,214 @@
"""Runtime transport implementations for the OpenClaw adapter."""
from __future__ import annotations
import json
import threading
import urllib.error
import urllib.parse
import urllib.request
from typing import Any, Callable, Mapping, Protocol
from .contract import (
CommandState,
OpenClawCommand,
OpenClawResult,
RuntimeHealth,
utc_now,
)
class RuntimeTransport(Protocol):
def execute(self, command: OpenClawCommand, timeout_seconds: float) -> OpenClawResult: ...
def cancel(self, command_id: str) -> bool: ...
def health(self) -> RuntimeHealth: ...
class TransportError(RuntimeError):
"""Runtime transport or protocol failure."""
RuntimeHandler = Callable[[OpenClawCommand], Mapping[str, Any] | OpenClawResult]
class InProcessRuntimeTransport:
"""Deterministic runtime used by tests and controlled local integrations."""
def __init__(
self,
handler: RuntimeHandler,
*,
runtime_id: str = "openclaw-in-process",
version: str = "v1",
workspace_isolated: bool = True,
credential_ref_configured: bool = True,
) -> None:
self.handler = handler
self.runtime_id = runtime_id
self.version = version
self.workspace_isolated = workspace_isolated
self.credential_ref_configured = credential_ref_configured
self._lock = threading.RLock()
self._running: set[str] = set()
self._cancelled: set[str] = set()
def execute(self, command: OpenClawCommand, timeout_seconds: float) -> OpenClawResult:
if timeout_seconds <= 0:
raise ValueError("timeout_seconds must be positive")
with self._lock:
if command.command_id in self._cancelled:
return OpenClawResult(
command_id=command.command_id,
tenant_id=command.tenant_id,
task_id=command.task_id,
trace_id=command.trace_id,
state=CommandState.CANCELLED,
error={"code": "cancelled", "message": "cancelled before execution"},
finished_at=utc_now(),
runtime_id=self.runtime_id,
)
self._running.add(command.command_id)
try:
raw = self.handler(command)
if isinstance(raw, OpenClawResult):
return raw
if not isinstance(raw, Mapping):
raise TransportError("runtime handler must return a mapping or OpenClawResult")
return OpenClawResult(
command_id=command.command_id,
tenant_id=command.tenant_id,
task_id=command.task_id,
trace_id=command.trace_id,
state=CommandState(str(raw.get("state", "COMPLETED"))),
output=raw.get("output"),
error=raw.get("error"),
started_at=str(raw.get("started_at") or utc_now()),
finished_at=str(raw.get("finished_at") or utc_now()),
runtime_id=str(raw.get("runtime_id") or self.runtime_id),
attempts=int(raw.get("attempts", 1)),
)
finally:
with self._lock:
self._running.discard(command.command_id)
def cancel(self, command_id: str) -> bool:
with self._lock:
self._cancelled.add(command_id)
return command_id in self._running
def health(self) -> RuntimeHealth:
with self._lock:
active = len(self._running)
return RuntimeHealth(
runtime="openclaw",
runtime_id=self.runtime_id,
status="healthy",
version=self.version,
heartbeat_at=utc_now(),
active_tasks=active,
workspace_isolated=self.workspace_isolated,
credential_ref_configured=self.credential_ref_configured,
details={"transport": "in_process"},
)
class HTTPRuntimeTransport:
"""Private HTTP transport for an OpenClaw runtime service."""
def __init__(
self,
base_url: str,
*,
runtime_id: str = "openclaw-http",
credential_ref: str | None = None,
max_response_bytes: int = 2_097_152,
) -> None:
normalized = str(base_url).rstrip("/")
if not normalized.startswith(("http://", "https://")):
raise ValueError("base_url must use http or https")
self.base_url = normalized
self.runtime_id = runtime_id
self.credential_ref = credential_ref
self.max_response_bytes = int(max_response_bytes)
def _request(
self,
method: str,
path: str,
*,
payload: Mapping[str, Any] | None,
timeout_seconds: float,
) -> Mapping[str, Any]:
body = None
headers = {"Accept": "application/json", "User-Agent": "AIOS-OpenClaw/1"}
if payload is not None:
body = json.dumps(dict(payload), separators=(",", ":")).encode("utf-8")
headers["Content-Type"] = "application/json"
if self.credential_ref:
headers["X-AIOS-Credential-Ref"] = self.credential_ref
request = urllib.request.Request(
f"{self.base_url}{path}",
data=body,
method=method,
headers=headers,
)
try:
with urllib.request.urlopen(request, timeout=timeout_seconds) as response:
raw = response.read(self.max_response_bytes + 1)
except urllib.error.HTTPError as exc:
raise TransportError(f"runtime returned HTTP {exc.code}") from exc
except urllib.error.URLError as exc:
raise TransportError(f"runtime unavailable: {exc.reason}") from exc
if len(raw) > self.max_response_bytes:
raise TransportError("runtime response exceeded size limit")
decoded = json.loads(raw.decode("utf-8"))
if not isinstance(decoded, Mapping):
raise TransportError("runtime response must be a JSON object")
return decoded
@staticmethod
def _command_payload(command: OpenClawCommand) -> dict[str, Any]:
return {**command.unsigned_dict(), "signature": command.signature}
def execute(self, command: OpenClawCommand, timeout_seconds: float) -> OpenClawResult:
value = self._request(
"POST",
"/v1/execute",
payload=self._command_payload(command),
timeout_seconds=timeout_seconds,
)
return OpenClawResult(
command_id=str(value["command_id"]),
tenant_id=str(value["tenant_id"]),
task_id=str(value["task_id"]),
trace_id=str(value["trace_id"]),
state=CommandState(str(value["state"])),
output=value.get("output"),
error=value.get("error"),
started_at=value.get("started_at"),
finished_at=value.get("finished_at"),
runtime_id=str(value.get("runtime_id") or self.runtime_id),
attempts=int(value.get("attempts", 1)),
)
def cancel(self, command_id: str) -> bool:
value = self._request(
"POST",
f"/v1/commands/{urllib.parse.quote(command_id, safe='')}/cancel",
payload={},
timeout_seconds=10.0,
)
return bool(value.get("accepted"))
def health(self) -> RuntimeHealth:
value = self._request("GET", "/v1/health", payload=None, timeout_seconds=5.0)
return RuntimeHealth(
runtime=str(value.get("runtime") or "openclaw"),
runtime_id=str(value.get("runtime_id") or self.runtime_id),
status=str(value.get("status") or "unknown"),
version=str(value.get("version") or "unknown"),
heartbeat_at=str(value.get("heartbeat_at") or utc_now()),
active_tasks=int(value.get("active_tasks", 0)),
workspace_isolated=bool(value.get("workspace_isolated", False)),
credential_ref_configured=bool(value.get("credential_ref_configured", False)),
details=value.get("details") if isinstance(value.get("details"), Mapping) else {},
)
@@ -1,144 +0,0 @@
"""HTTP adapter for audited Owner authorization and writer provisioning.
This module layers on top of ``aios_authorized_task_writer_api`` so existing
routes and the legacy exact ``writer:provision`` route remain available. The
new endpoint does not mint or modify bearer credentials. It authenticates an
existing, non-wildcard, explicitly allow-listed Owner credential and then
invokes the audited broker.
Endpoint:
POST /api/governance/owner-authorizations
"""
from __future__ import annotations
import os
import urllib.parse
from typing import Any, Mapping
import aios_authorized_task_writer_api as bridge_api
from authorized_task_writer_provisioning import ProvisioningError
from owner_authorization_broker import (
OwnerAuthorizationBroker,
OwnerAuthorizationError,
OwnerPrincipal,
)
api = bridge_api.api
_original_do_post = api.H.do_POST
_ENDPOINT = "/api/governance/owner-authorizations"
def _enabled() -> bool:
return os.getenv(
"AIOS_GITOPS_OWNER_AUTHORIZATION_BROKER_ENABLED", ""
).strip().lower() in {"1", "true", "yes", "on"}
def _configured_intake_scope() -> str:
scopes = [
item.strip()
for item in os.getenv(
"AIOS_GITOPS_OWNER_AUTHORIZATION_INTAKE_SCOPES", ""
).split(",")
if item.strip()
]
if len(scopes) != 1:
raise OwnerAuthorizationError(
"EXACTLY_ONE_HTTP_INTAKE_SCOPE_REQUIRED", 503
)
scope = scopes[0]
if scope == "writer:provision" or scope == "*" or scope.endswith(":*"):
raise OwnerAuthorizationError("HTTP_INTAKE_SCOPE_REJECTED", 503)
return scope
def _scope_set(auth: Mapping[str, Any]) -> frozenset[str]:
raw = auth.get("scopes")
if raw is None:
raw = auth.get("scope")
if raw is None:
return frozenset()
if isinstance(raw, str):
candidates = raw.replace(",", " ").split()
elif isinstance(raw, (list, tuple, set, frozenset)):
candidates = [str(item) for item in raw]
else:
raise OwnerAuthorizationError("OWNER_SCOPE_EVIDENCE_INVALID", 403)
return frozenset(item.strip() for item in candidates if item.strip())
def _credential_id(auth: Mapping[str, Any]) -> str:
for name in (
"credential_id",
"token_id",
"key_id",
"auth_id",
):
value = str(auth.get(name) or "").strip()
if value:
return value
return ""
def _authenticate_existing_owner(handler) -> OwnerPrincipal | None:
scope = _configured_intake_scope()
auth = handler.need(scope)
if not auth:
return None
if auth.get("role") != "owner":
handler.sendj({"error": "OWNER_ROLE_REQUIRED"}, 403)
return None
identity = str(auth.get("account") or auth.get("identity") or "").strip()
if not identity:
handler.sendj({"error": "OWNER_IDENTITY_REQUIRED"}, 403)
return None
scopes = _scope_set(auth)
if any(item == "*" or item.endswith(":*") for item in scopes):
handler.sendj(
{"error": "WILDCARD_OWNER_CREDENTIAL_REJECTED"}, 403
)
return None
return OwnerPrincipal(
identity=identity,
role="owner",
authenticated_scope=scope,
token_scopes=scopes,
credential_id=_credential_id(auth),
)
def _broker_do_post(self):
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if path != _ENDPOINT:
return _original_do_post(self)
if not _enabled():
return self.sendj(
{"error": "OWNER_AUTHORIZATION_BROKER_DISABLED"}, 503
)
try:
principal = _authenticate_existing_owner(self)
if principal is None:
return
data = self.body()
result = OwnerAuthorizationBroker().authorize_and_provision(
data, principal
)
return self.sendj(result)
except (OwnerAuthorizationError, ProvisioningError) as exc:
body = {"error": exc.code}
if exc.details:
body["details"] = exc.details
return self.sendj(body, exc.status)
except Exception:
# Never expose registry data, bearer tokens, signer output or traceback.
return self.sendj(
{"error": "OWNER_AUTHORIZATION_BROKER_INTERNAL_ERROR"}, 500
)
api.H.do_POST = _broker_do_post
if __name__ == "__main__":
api.main()
@@ -1,160 +0,0 @@
#!/usr/bin/env python3
"""Loopback-only HTTP API for the task identity overlay.
Endpoints:
GET /healthz
POST /api/governance/owner-authorizations
The API authenticates only the short-lived overlay credential. It does not read
or modify the global bearer-token registry.
"""
from __future__ import annotations
import json
import os
import urllib.parse
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from typing import Any
from authorized_task_writer_provisioning import ProvisioningError
from owner_authorization_broker import OwnerAuthorizationError
from task_identity_overlay import (
MAX_BODY_BYTES,
IdentityOverlayConfig,
IdentityOverlayError,
TaskIdentityOverlayService,
)
_ENDPOINT = "/api/governance/owner-authorizations"
def _enabled() -> bool:
return os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_ENABLED", ""
).strip().lower() in {"1", "true", "yes", "on"}
def _bearer(header: str) -> str:
prefix = "Bearer "
if not header.startswith(prefix):
raise IdentityOverlayError("OVERLAY_AUTHENTICATION_REQUIRED", 401)
token = header[len(prefix):].strip()
if not token or len(token) > 4096:
raise IdentityOverlayError("OVERLAY_AUTHENTICATION_REQUIRED", 401)
return token
class OverlayHandler(BaseHTTPRequestHandler):
server_version = "aios-task-identity-overlay/1"
sys_version = ""
@property
def overlay(self) -> TaskIdentityOverlayService:
return self.server.overlay # type: ignore[attr-defined]
def log_message(self, format: str, *args: Any) -> None:
# Never log Authorization or request bodies.
return
def _send(self, status: int, value: dict[str, Any]) -> None:
payload = (
json.dumps(
value,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
)
+ "\n"
).encode("utf-8")
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Cache-Control", "no-store")
self.send_header("Content-Length", str(len(payload)))
self.end_headers()
self.wfile.write(payload)
def _body(self) -> dict[str, Any]:
try:
length = int(self.headers.get("Content-Length", "0"))
except ValueError:
raise IdentityOverlayError("OVERLAY_CONTENT_LENGTH_INVALID") from None
if length <= 0 or length > MAX_BODY_BYTES:
raise IdentityOverlayError("OVERLAY_BODY_SIZE_REJECTED", 413)
raw = self.rfile.read(length)
try:
value = json.loads(raw)
except (UnicodeDecodeError, json.JSONDecodeError):
raise IdentityOverlayError("OVERLAY_BODY_JSON_INVALID") from None
if not isinstance(value, dict):
raise IdentityOverlayError("OVERLAY_BODY_OBJECT_REQUIRED")
return value
def do_GET(self) -> None:
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if path != "/healthz":
self._send(404, {"error": "NOT_FOUND"})
return
self._send(
200,
{
"service": "aios-task-identity-overlay",
"status": "active" if _enabled() else "disabled",
"global_token_registry_used": False,
"loopback_only": True,
},
)
def do_POST(self) -> None:
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if path != _ENDPOINT:
self._send(404, {"error": "NOT_FOUND"})
return
if not _enabled():
self._send(503, {"error": "IDENTITY_OVERLAY_DISABLED"})
return
try:
token = _bearer(self.headers.get("Authorization", ""))
result = self.overlay.provision(self._body(), token)
self._send(200, result)
except (IdentityOverlayError, OwnerAuthorizationError, ProvisioningError) as exc:
body: dict[str, Any] = {"error": exc.code}
if getattr(exc, "details", None):
body["details"] = exc.details
self._send(exc.status, body)
except Exception:
self._send(500, {"error": "IDENTITY_OVERLAY_API_INTERNAL_ERROR"})
class OverlayServer(ThreadingHTTPServer):
allow_reuse_address = True
def __init__(
self,
address: tuple[str, int],
overlay: TaskIdentityOverlayService,
) -> None:
super().__init__(address, OverlayHandler)
self.overlay = overlay
def main() -> None:
host = os.getenv("AIOS_GITOPS_IDENTITY_OVERLAY_HOST", "127.0.0.1")
if host not in {"127.0.0.1", "::1", "localhost"}:
raise SystemExit("identity overlay must listen on loopback")
try:
port = int(os.getenv("AIOS_GITOPS_IDENTITY_OVERLAY_PORT", "19864"))
except ValueError:
raise SystemExit("invalid overlay port") from None
if not 1024 <= port <= 65535:
raise SystemExit("invalid overlay port")
config = IdentityOverlayConfig.from_environment()
server = OverlayServer(
(host, port),
TaskIdentityOverlayService(config),
)
server.serve_forever(poll_interval=0.25)
if __name__ == "__main__":
main()
@@ -1,92 +0,0 @@
#!/usr/bin/env python3
"""Root-governed CLI for issuing and revoking task identity overlays.
The CLI never prints the bearer token. It returns only the root-owned secret
reference and non-secret metadata.
"""
from __future__ import annotations
import argparse
import json
import os
import sys
from pathlib import Path
from task_identity_overlay import (
IdentityOverlayConfig,
IdentityOverlayError,
TaskIdentityOverlayStore,
)
def _write_result(path: str, value: dict) -> None:
data = json.dumps(value, sort_keys=True, separators=(",", ":")) + "\n"
if path == "-":
sys.stdout.write(data)
return
target = Path(path)
target.parent.mkdir(parents=True, exist_ok=True)
target.write_text(data, encoding="utf-8")
os.chmod(target, 0o600)
def parser() -> argparse.ArgumentParser:
value = argparse.ArgumentParser(
description="Issue/status/revoke a task-scoped identity overlay"
)
sub = value.add_subparsers(dest="command", required=True)
issue = sub.add_parser("issue")
issue.add_argument("--ttl-seconds", type=int, default=900)
issue.add_argument("--authorization-assertion-ref", required=True)
issue.add_argument(
"--operator-identity",
default=os.getenv("SUDO_USER") or os.getenv("USER") or "root",
)
issue.add_argument("--result-json", default="-")
status = sub.add_parser("status")
status.add_argument("--overlay-id", required=True)
status.add_argument("--result-json", default="-")
revoke = sub.add_parser("revoke")
revoke.add_argument("--overlay-id", required=True)
revoke.add_argument("--reason", required=True)
revoke.add_argument("--result-json", default="-")
return value
def main() -> int:
args = parser().parse_args()
try:
store = TaskIdentityOverlayStore(
IdentityOverlayConfig.from_environment()
)
if args.command == "issue":
result = store.issue(
ttl_seconds=args.ttl_seconds,
authorization_assertion_ref=args.authorization_assertion_ref,
operator_identity=args.operator_identity,
)
elif args.command == "status":
result = store.status(args.overlay_id)
else:
result = store.revoke(args.overlay_id, reason=args.reason)
_write_result(args.result_json, result)
return 0
except IdentityOverlayError as exc:
body = {"status": "BLOCKED", "error": exc.code}
if exc.details:
body["details"] = exc.details
_write_result(getattr(args, "result_json", "-"), body)
return 2
except Exception:
_write_result(
getattr(args, "result_json", "-"),
{"status": "FAILED", "error": "IDENTITY_OVERLAY_CLI_INTERNAL_ERROR"},
)
return 1
if __name__ == "__main__":
raise SystemExit(main())
+110
View File
@@ -0,0 +1,110 @@
"""AIOS V2 控制面、执行编排与可信运行来源证明。"""
from .control_plane import (
AgentRecord,
AuditEvent,
ControlPlaneError,
ControlPlaneService,
IdempotencyConflict,
InMemoryControlPlaneStore,
InvalidTransition,
NotFound,
PolicyDenied,
RequestContext,
RevisionConflict,
TaskRecord,
TaskState,
TenantIsolationError,
TenantRecord,
Unauthorized,
)
from .execution_tracking import ExecutionEvidence, ExecutionTracker
from .orchestrator import DispatchRecord, ExecutionOrchestrator, OrchestrationError
from .provenance import (
Ed25519PrivateKeySigner,
Ed25519PublicKeyVerifier,
ExecutionPath,
GitOperation,
PRODUCTION_POLICY_VERSION,
ProvenanceAuthorization,
ProvenanceControlledWriter,
ProvenanceDenied,
ProvenanceError,
ProvenanceExpired,
ProvenanceIssuer,
ProvenanceNotFound,
ProvenanceReplay,
ProvenanceRevoked,
ProvenanceSignatureError,
ProvenanceStatus,
ProvenanceVerifier,
RunProvenance,
SQLiteProvenanceStore,
digest_payload,
)
from .provenance_git import (
GitCommandResult,
GitExecutionContext,
ProvenanceGitError,
ProvenanceGitWriter,
)
from .provenance_operations import (
OperationContext,
OperationReceipt,
ProvenanceOperationGate,
build_provenance_writer_from_env,
context_from_environment,
)
__all__ = [
"AgentRecord",
"AuditEvent",
"ControlPlaneError",
"ControlPlaneService",
"DispatchRecord",
"Ed25519PrivateKeySigner",
"Ed25519PublicKeyVerifier",
"ExecutionEvidence",
"ExecutionOrchestrator",
"ExecutionPath",
"ExecutionTracker",
"GitCommandResult",
"GitExecutionContext",
"GitOperation",
"IdempotencyConflict",
"InMemoryControlPlaneStore",
"InvalidTransition",
"NotFound",
"OperationContext",
"OperationReceipt",
"OrchestrationError",
"PRODUCTION_POLICY_VERSION",
"PolicyDenied",
"ProvenanceAuthorization",
"ProvenanceControlledWriter",
"ProvenanceDenied",
"ProvenanceError",
"ProvenanceExpired",
"ProvenanceGitError",
"ProvenanceGitWriter",
"ProvenanceIssuer",
"ProvenanceNotFound",
"ProvenanceOperationGate",
"ProvenanceReplay",
"ProvenanceRevoked",
"ProvenanceSignatureError",
"ProvenanceStatus",
"ProvenanceVerifier",
"RequestContext",
"RevisionConflict",
"RunProvenance",
"SQLiteProvenanceStore",
"TaskRecord",
"TaskState",
"TenantIsolationError",
"TenantRecord",
"Unauthorized",
"build_provenance_writer_from_env",
"context_from_environment",
"digest_payload",
]
+807
View File
@@ -0,0 +1,807 @@
"""AIOS V2 production-candidate application entrypoint."""
from __future__ import annotations
import dataclasses
import json
import os
import stat
import urllib.parse
from enum import Enum
from http import HTTPStatus
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import Any, Mapping
from aios_hermes import HermesAdapter, HermesJobState, HermesResult, SQLiteHermesStore
from aios_openclaw import (
Ed25519CommandSigner,
HTTPRuntimeTransport,
OpenClawAdapter,
)
from aios_openclaw.callback import AuditCallbackSink, EventPublisher
from .console import CONSOLE_HTML
from .control_plane import AuditEvent, RequestContext, Unauthorized
from .dispatch_store import SQLiteDispatchRepository
from .execution_tracking import ExecutionEvidence, ExecutionTracker
from .gateway import GatewayApplication, error_response
from .gitops_status import collect_gitops_status
from .orchestrator import ExecutionOrchestrator
from .persistence import DurableControlPlaneService, SQLiteSnapshotRepository
from .provenance_operations import build_provenance_writer_from_env
def _json_value(value: Any) -> Any:
if dataclasses.is_dataclass(value):
return {
item.name: _json_value(getattr(value, item.name))
for item in dataclasses.fields(value)
}
if isinstance(value, Enum):
return value.value
if isinstance(value, Mapping):
return {str(key): _json_value(item) for key, item in value.items()}
if isinstance(value, (list, tuple, set, frozenset)):
return [_json_value(item) for item in value]
return value
def _enabled(value: str | None) -> bool:
return str(value or "").strip().lower() in {"1", "true", "yes", "on"}
def _header(headers: Mapping[str, str], name: str) -> str | None:
target = name.lower()
for key, value in headers.items():
if str(key).lower() == target:
normalized = str(value or "").strip()
return normalized or None
return None
def _provenance_context(
headers: Mapping[str, str],
payload: Mapping[str, Any],
) -> tuple[str | None, str | None]:
header_provenance = _header(headers, "X-AIOS-Provenance-ID")
header_run = _header(headers, "X-AIOS-Run-ID")
body_provenance = str(payload.get("provenance_id") or "").strip() or None
body_run = str(payload.get("run_id") or "").strip() or None
if header_provenance and body_provenance and header_provenance != body_provenance:
raise ValueError("provenance_id header/body mismatch")
if header_run and body_run and header_run != body_run:
raise ValueError("run_id header/body mismatch")
return header_provenance or body_provenance, header_run or body_run
def _read_protected_file(path: Path, *, private: bool) -> bytes:
flags = os.O_RDONLY
if hasattr(os, "O_NOFOLLOW"):
flags |= os.O_NOFOLLOW
descriptor = os.open(str(path), flags)
try:
metadata = os.fstat(descriptor)
if not stat.S_ISREG(metadata.st_mode):
raise RuntimeError("key reference is not a regular file")
denied = 0o077 if private else 0o022
if metadata.st_mode & denied:
raise RuntimeError(
"private key file permissions must be 0600 or stricter"
if private
else "public key file must not be group/world writable"
)
chunks: list[bytes] = []
while True:
chunk = os.read(descriptor, 65536)
if not chunk:
break
chunks.append(chunk)
value = b"".join(chunks)
if not value:
raise RuntimeError("key file is empty")
return value
finally:
os.close(descriptor)
class FileCommandSignerResolver:
"""Resolve tenant/key-id scoped OpenClaw Ed25519 signing material."""
def __init__(self, path: str | Path, *, configured_key_id: str) -> None:
self.path = Path(path).resolve()
self.configured_key_id = str(configured_key_id or "").strip()
if not self.configured_key_id:
raise ValueError("configured_key_id is required")
def __call__(self, tenant_id: str, key_id: str) -> Ed25519CommandSigner:
if not str(tenant_id or "").strip():
raise RuntimeError("tenant_id is required for command signing")
if key_id != self.configured_key_id:
raise RuntimeError("OpenClaw signing key_id mismatch")
return Ed25519CommandSigner.from_bytes(
_read_protected_file(self.path, private=True),
key_id=key_id,
)
class ControlPlaneEventPublisher(EventPublisher):
"""Append Runtime callback events to the tenant audit stream.
Callback audit remains informational. Authoritative task reconciliation is
performed only by the orchestrator after dispatch/result validation.
"""
def __init__(self, service: DurableControlPlaneService) -> None:
self.service = service
def publish(self, event: Mapping[str, Any]) -> None:
tenant_id = str(event.get("tenant_id") or "").strip()
trace_id = str(event.get("trace_id") or "").strip()
command_id = str(event.get("command_id") or "").strip()
event_type = str(event.get("event_type") or "OPENCLAW_EVENT").strip()
if not tenant_id or not trace_id or not command_id:
raise ValueError("runtime audit event is missing tenant identity")
state_value = str(event.get("state") or "unknown").lower()
outcome = "allowed" if state_value == "completed" else state_value
runtime = str(event.get("runtime") or "openclaw").strip().lower()
principal_id = str(
event.get("principal_id") or f"{runtime}-runtime"
).strip()
audit = AuditEvent(
event_id=f"runtime_{command_id}_{len(self.service.store.audit_events) + 1}",
tenant_id=tenant_id,
principal_id=principal_id,
trace_id=trace_id,
action=event_type,
resource_type=f"{runtime}_execution",
resource_id=command_id,
outcome=outcome,
policy_version="runtime-v2",
details=dict(event.get("details") or {}),
)
with self.service.store.lock:
self.service.store.audit_events.append(audit)
self.service.repository.save(self.service._snapshot())
class CandidateApplication:
def __init__(
self,
gateway: GatewayApplication,
orchestrator: ExecutionOrchestrator,
tracker: ExecutionTracker,
hermes: HermesAdapter,
openclaw: OpenClawAdapter | None,
*,
hermes_lifecycle_api_enabled: bool = False,
) -> None:
self.gateway = gateway
self.orchestrator = orchestrator
self.tracker = tracker
self.hermes = hermes
self.openclaw = openclaw
self.hermes_lifecycle_api_enabled = bool(hermes_lifecycle_api_enabled)
self.runtime_events = ControlPlaneEventPublisher(orchestrator.control_plane)
def context(self, headers: Mapping[str, str]) -> RequestContext:
return self.gateway.context_from_headers(headers)
@staticmethod
def _require_runtime_role(context: RequestContext) -> None:
if not ({"runtime", "platform_admin"} & set(context.roles)):
raise Unauthorized("runtime reconciliation role is required")
@staticmethod
def _require_control_plane_cancel(context: RequestContext) -> None:
required = {"runtime", "platform_admin"}
if not required.issubset(set(context.roles)):
raise Unauthorized(
"Hermes cancellation requires trusted AIOS control-plane authority"
)
@staticmethod
def _required_identity(payload: Mapping[str, Any], name: str) -> str:
value = str(payload.get(name) or "").strip()
if not value:
raise ValueError(f"{name} is required")
return value
def _record_hermes_lifecycle(
self,
context: RequestContext,
dispatch: Any,
job: Any,
*,
action: str,
worker_id: str | None,
provenance_id: str,
run_id: str,
) -> None:
executor = worker_id or "aios-control-plane"
evidence = ExecutionEvidence(
execution_id=job.job_id,
tenant_id=job.tenant_id,
task_id=job.task_id,
agent_id=dispatch.agent_id,
executor=executor,
branch="runtime/hermes",
status=job.state.value.lower(),
progress_completed=0,
progress_total=3,
current_step=action,
provenance_id=provenance_id,
run_id=run_id,
)
current_evidence = self.tracker.claim(
evidence,
principal_id=context.principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
if job.state in {
HermesJobState.COMPLETED,
HermesJobState.FAILED,
HermesJobState.CANCELLED,
}:
if current_evidence.completed_at is None:
self.tracker.complete(
tenant_id=job.tenant_id,
execution_id=job.job_id,
status=job.state.value.lower(),
test_status="runtime_terminal",
test_summary={"lifecycle_action": action},
result_summary={
"state": job.state.value,
"worker_id": worker_id,
"dispatch_id": dispatch.dispatch_id,
},
principal_id=context.principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
else:
self.tracker.heartbeat(
tenant_id=job.tenant_id,
execution_id=job.job_id,
status=job.state.value.lower(),
current_step=action,
progress_completed=(1 if job.state == HermesJobState.RUNNING else 0),
progress_total=3,
principal_id=context.principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
self.runtime_events.publish(
{
"runtime": "hermes",
"tenant_id": job.tenant_id,
"principal_id": context.principal_id,
"trace_id": job.trace_id,
"command_id": job.job_id,
"event_type": f"HERMES_{action.upper()}",
"state": job.state.value,
"details": {
"dispatch_id": dispatch.dispatch_id,
"task_id": job.task_id,
"worker_id": worker_id,
"cell_id": job.cell_id,
"profile_id": job.profile_id,
"revision": job.revision,
"provenance_id": provenance_id,
"run_id": run_id,
},
}
)
def handle_json(
self,
method: str,
raw_path: str,
headers: Mapping[str, str],
body: Any,
) -> tuple[int, Mapping[str, Any]]:
parsed = urllib.parse.urlparse(raw_path)
path = parsed.path.rstrip("/") or "/"
method = method.upper()
if method == "GET" and path == "/api/v2/gitops":
context = self.context(headers)
return HTTPStatus.OK, {
"tenant_id": context.tenant_id,
"gitops": collect_gitops_status().as_dict(),
}
if method == "GET" and path == "/api/v2/runtime":
context = self.context(headers)
runtimes: list[dict[str, Any]] = []
if self.openclaw is None:
runtimes.append(
{
"name": "openclaw",
"status": "disabled",
"details": {"reason": "runtime_not_configured"},
}
)
else:
try:
health = self.openclaw.health()
runtimes.append(
{
"name": "openclaw",
"status": health.status,
"details": _json_value(health),
}
)
except Exception as exc:
runtimes.append(
{
"name": "openclaw",
"status": "unavailable",
"details": {"message": str(exc)},
}
)
hermes_health = self.hermes.health()
runtimes.append(
{
"name": "hermes",
"status": hermes_health.status,
"details": _json_value(hermes_health),
}
)
return HTTPStatus.OK, {
"tenant_id": context.tenant_id,
"runtimes": runtimes,
}
if method == "GET" and path == "/api/v2/executions":
context = self.context(headers)
return HTTPStatus.OK, {
"executions": _json_value(
self.tracker.list(tenant_id=context.tenant_id)
)
}
dispatch_match = __import__("re").fullmatch(
r"/api/v2/tasks/([^/]+)/dispatch", path
)
if method == "POST" and dispatch_match:
context = self.context(headers)
task_id = urllib.parse.unquote(dispatch_match.group(1))
payload = body if isinstance(body, Mapping) else {}
timeout = payload.get("timeout_seconds")
provenance_id, run_id = _provenance_context(headers, payload)
record = self.orchestrator.dispatch(
context,
task_id=task_id,
timeout_seconds=float(timeout) if timeout is not None else None,
provenance_id=provenance_id,
run_id=run_id,
)
return HTTPStatus.ACCEPTED, {"dispatch": _json_value(record)}
lifecycle_match = __import__("re").fullmatch(
r"/api/v2/internal/runtime/hermes/lifecycle/"
r"(claim|start|heartbeat|complete|fail|cancel|status)",
path,
)
if method == "POST" and lifecycle_match:
if not self.hermes_lifecycle_api_enabled:
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "route not found",
}
context = self.context(headers)
self._require_runtime_role(context)
if not isinstance(body, Mapping):
raise ValueError("JSON body must be an object")
payload = body
action = lifecycle_match.group(1)
identity = {
name: self._required_identity(payload, name)
for name in (
"dispatch_id",
"job_id",
"tenant_id",
"task_id",
"trace_id",
"principal_id",
"provenance_id",
"run_id",
"cell_id",
"profile_id",
)
}
header_provenance, header_run = _provenance_context(headers, payload)
if header_provenance != identity["provenance_id"]:
raise ValueError("provenance_id context mismatch")
if header_run != identity["run_id"]:
raise ValueError("run_id context mismatch")
requeued_job_ids = self.hermes.requeue_expired()
dispatch, job = self.orchestrator.hermes_lifecycle_context(
context,
dispatch_id=identity["dispatch_id"],
job_id=identity["job_id"],
tenant_id=identity["tenant_id"],
task_id=identity["task_id"],
trace_id=identity["trace_id"],
principal_id=identity["principal_id"],
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
if job.cell_id != identity["cell_id"]:
raise ValueError("cell_id mismatch")
if job.profile_id != identity["profile_id"]:
raise ValueError("profile_id mismatch")
if action == "status":
if job.job_id in requeued_job_ids:
self._record_hermes_lifecycle(
context,
dispatch,
job,
action="lease_expired_requeue",
worker_id=None,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
task = self.orchestrator.control_plane.get_task(
context, dispatch.task_id
)
response: dict[str, Any] = {
"job": _json_value(job),
"dispatch": _json_value(dispatch),
"task": _json_value(task),
}
if job.state in {
HermesJobState.COMPLETED,
HermesJobState.FAILED,
HermesJobState.CANCELLED,
}:
response["result"] = _json_value(
self.hermes.result(job.job_id, tenant_id=job.tenant_id)
)
return HTTPStatus.OK, response
expected_revision = payload.get("expected_revision")
expected = (
int(expected_revision) if expected_revision is not None else None
)
if action == "cancel":
self._require_control_plane_cancel(context)
if payload.get("worker_id") is not None:
raise Unauthorized("Hermes workers may observe but not initiate cancel")
if payload.get("cancellation_source") != "aios-control-plane":
raise ValueError(
"cancellation_source must be aios-control-plane"
)
result = self.hermes.cancel(
job.job_id,
tenant_id=job.tenant_id,
expected_revision=expected,
)
else:
worker_id = self._required_identity(payload, "worker_id")
if action == "claim":
claimed = self.hermes.claim(
tenant_id=job.tenant_id,
cell_id=job.cell_id,
profile_id=job.profile_id,
worker_id=worker_id,
lease_seconds=(
int(payload["lease_seconds"])
if payload.get("lease_seconds") is not None
else None
),
job_id=job.job_id,
)
if claimed is None:
raise ValueError("Hermes job is not claimable")
bound = self.orchestrator.bind_hermes_worker(
context,
claimed,
dispatch_id=dispatch.dispatch_id,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
worker_id=worker_id,
)
self._record_hermes_lifecycle(
context,
bound,
claimed,
action="claim",
worker_id=worker_id,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
return HTTPStatus.OK, {
"job": _json_value(claimed),
"dispatch": _json_value(bound),
}
if action == "start":
started = self.hermes.start(
job.job_id,
tenant_id=job.tenant_id,
worker_id=worker_id,
expected_revision=expected,
)
self._record_hermes_lifecycle(
context,
dispatch,
started,
action="start",
worker_id=worker_id,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
return HTTPStatus.OK, {"job": _json_value(started)}
if action == "heartbeat":
heartbeat = self.hermes.heartbeat(
job.job_id,
tenant_id=job.tenant_id,
worker_id=worker_id,
lease_seconds=(
int(payload["lease_seconds"])
if payload.get("lease_seconds") is not None
else None
),
)
self._record_hermes_lifecycle(
context,
dispatch,
heartbeat,
action="heartbeat",
worker_id=worker_id,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
return HTTPStatus.OK, {"job": _json_value(heartbeat)}
if action == "complete":
output = payload.get("output")
if not isinstance(output, Mapping):
raise ValueError("output must be an object")
result = self.hermes.complete(
job.job_id,
tenant_id=job.tenant_id,
worker_id=worker_id,
output=output,
expected_revision=expected,
)
elif action == "fail":
error = payload.get("error")
if not isinstance(error, Mapping):
raise ValueError("error must be an object")
result = self.hermes.fail(
job.job_id,
tenant_id=job.tenant_id,
worker_id=worker_id,
error=error,
expected_revision=expected,
)
else:
raise ValueError("unsupported Hermes lifecycle action")
task = self.orchestrator.reconcile_hermes(
context,
result,
dispatch_id=dispatch.dispatch_id,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
updated_dispatch = self.orchestrator.dispatch_repository.get(
dispatch.dispatch_id, tenant_id=dispatch.tenant_id
)
terminal_job = self.hermes.get(job.job_id, tenant_id=job.tenant_id)
self._record_hermes_lifecycle(
context,
updated_dispatch,
terminal_job,
action=action,
worker_id=result.worker_id,
provenance_id=identity["provenance_id"],
run_id=identity["run_id"],
)
return HTTPStatus.OK, {
"result": _json_value(result),
"task": _json_value(task),
"dispatch": _json_value(updated_dispatch),
}
if method == "POST" and path == "/api/v2/internal/runtime/hermes/reconcile":
context = self.context(headers)
self._require_runtime_role(context)
if not isinstance(body, Mapping):
raise ValueError("JSON body must be an object")
provenance_id, run_id = _provenance_context(headers, body)
if not provenance_id or not run_id:
raise ValueError("provenance_id and run_id are required")
dispatch_id = str(body.get("dispatch_id") or "").strip()
if not dispatch_id:
raise ValueError("dispatch_id is required")
result = HermesResult(
job_id=str(body["job_id"]),
tenant_id=str(body["tenant_id"]),
task_id=str(body["task_id"]),
trace_id=str(body["trace_id"]),
state=HermesJobState(str(body["state"])),
worker_id=(
str(body["worker_id"])
if body.get("worker_id") is not None
else None
),
output=body.get("output"),
error=body.get("error"),
started_at=body.get("started_at"),
finished_at=body.get("finished_at"),
)
task = self.orchestrator.reconcile_hermes(
context,
result,
dispatch_id=dispatch_id,
provenance_id=provenance_id,
run_id=run_id,
)
return HTTPStatus.OK, {"task": _json_value(task)}
if method == "POST" and path == "/api/v2/hermes/results/reconcile":
return HTTPStatus.GONE, {
"error": "RuntimeReconcileEndpointMoved",
"message": "use /api/v2/internal/runtime/hermes/reconcile",
}
return self.gateway.handle(method, raw_path, headers, body)
class CandidateRequestHandler(BaseHTTPRequestHandler):
server_version = "AIOSV2Candidate/2.0"
max_body_bytes = 1_048_576
@property
def application(self) -> CandidateApplication:
return self.server.application # type: ignore[attr-defined]
def _read_body(self) -> Any:
length = int(self.headers.get("Content-Length", "0") or "0")
if length < 0 or length > self.max_body_bytes:
raise ValueError("request body is too large")
if length == 0:
return {}
content_type = self.headers.get("Content-Type", "").split(";", 1)[0].strip()
if content_type != "application/json":
raise ValueError("Content-Type must be application/json")
return json.loads(self.rfile.read(length).decode("utf-8"))
def _security_headers(self) -> None:
self.send_header("Cache-Control", "no-store")
self.send_header("X-Content-Type-Options", "nosniff")
self.send_header("X-Frame-Options", "DENY")
self.send_header("Referrer-Policy", "no-referrer")
self.send_header(
"Content-Security-Policy",
"default-src 'self'; style-src 'unsafe-inline'; script-src 'unsafe-inline'; connect-src 'self'",
)
def _send_json(self, status_code: int, payload: Mapping[str, Any]) -> None:
encoded = json.dumps(
_json_value(payload), ensure_ascii=False, separators=(",", ":")
).encode("utf-8")
self.send_response(int(status_code))
self.send_header("Content-Type", "application/json; charset=utf-8")
self.send_header("Content-Length", str(len(encoded)))
self._security_headers()
self.end_headers()
self.wfile.write(encoded)
def _send_console(self) -> None:
encoded = CONSOLE_HTML.encode("utf-8")
self.send_response(HTTPStatus.OK)
self.send_header("Content-Type", "text/html; charset=utf-8")
self.send_header("Content-Length", str(len(encoded)))
self._security_headers()
self.end_headers()
self.wfile.write(encoded)
def _dispatch(self, method: str) -> None:
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if method == "GET" and path in {"/", "/console"}:
self._send_console()
return
try:
body = self._read_body() if method == "POST" else {}
status_code, payload = self.application.handle_json(
method,
self.path,
{key: value for key, value in self.headers.items()},
body,
)
except Exception as exc:
status_code, payload = error_response(exc)
self._send_json(status_code, payload)
def do_GET(self) -> None: # noqa: N802
self._dispatch("GET")
def do_POST(self) -> None: # noqa: N802
self._dispatch("POST")
class CandidateHTTPServer(ThreadingHTTPServer):
daemon_threads = True
allow_reuse_address = True
def __init__(self, address: tuple[str, int], application: CandidateApplication) -> None:
self.application = application
super().__init__(address, CandidateRequestHandler)
def build_application() -> CandidateApplication:
state_dir = Path(os.getenv("AIOS_V2_STATE_DIR", "/var/lib/aios-v2")).resolve()
state_dir.mkdir(parents=True, exist_ok=True)
repository = SQLiteSnapshotRepository(state_dir / "control-plane.sqlite3")
dispatch_repository = SQLiteDispatchRepository(state_dir / "dispatches.sqlite3")
service = DurableControlPlaneService(repository)
require_provenance = _enabled(os.getenv("AIOS_REQUIRE_RUN_PROVENANCE", "0"))
provenance_writer = build_provenance_writer_from_env(
state_dir=state_dir, required=require_provenance
)
tracker = ExecutionTracker(
state_dir / "executions",
provenance_writer=provenance_writer,
require_provenance=require_provenance,
)
hermes = HermesAdapter(store=SQLiteHermesStore(state_dir / "hermes.sqlite3"))
openclaw_url = os.getenv("AIOS_OPENCLAW_URL", "").strip()
signing_file = os.getenv("AIOS_OPENCLAW_SIGNING_MATERIAL_FILE", "").strip()
signing_key_id = os.getenv(
"AIOS_OPENCLAW_SIGNING_KEY_ID", "openclaw-v2r1-candidate-ed25519"
).strip()
openclaw = None
resolver = None
if openclaw_url and signing_file:
resolver = FileCommandSignerResolver(
signing_file,
configured_key_id=signing_key_id,
)
transport = HTTPRuntimeTransport(
openclaw_url,
credential_ref=os.getenv("AIOS_OPENCLAW_CREDENTIAL_REF") or None,
)
openclaw = OpenClawAdapter(
transport,
resolver,
callback_sink=AuditCallbackSink(ControlPlaneEventPublisher(service)),
)
gateway = GatewayApplication(service)
orchestrator = ExecutionOrchestrator(
service,
openclaw=openclaw,
hermes=hermes,
openclaw_signing_material_resolver=resolver,
openclaw_key_id=signing_key_id,
provenance_writer=provenance_writer,
require_provenance=require_provenance,
dispatch_repository=dispatch_repository,
)
return CandidateApplication(
gateway,
orchestrator,
tracker,
hermes,
openclaw,
hermes_lifecycle_api_enabled=_enabled(
os.getenv("AIOS_HERMES_LIFECYCLE_API_ENABLED", "0")
),
)
def main() -> None:
host = os.getenv("AIOS_V2_HOST", "127.0.0.1")
port = int(os.getenv("AIOS_V2_PORT", "18920"))
server = CandidateHTTPServer((host, port), build_application())
print(f"AIOS V2 candidate listening on {host}:{port}")
server.serve_forever()
if __name__ == "__main__":
main()
+83
View File
@@ -0,0 +1,83 @@
"""Dependency-free, role-aware AIOS unified portal.
The browser receives only server-authorized capabilities and tenant-scoped data.
It never selects a tenant, signs Provenance, mutates Git tags, or calls Runtime
services directly.
"""
CONSOLE_HTML = r'''<!doctype html>
<html lang="zh-CN">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="referrer" content="no-referrer">
<title>AIOS Unified Portal</title>
<style>
:root{font-family:Inter,"PingFang SC","Microsoft YaHei",ui-sans-serif,system-ui,sans-serif;color:#172033;background:#eef2f7;--nav:#0f172a;--card:#fff;--line:#dfe6ef;--muted:#667085;--blue:#2563eb;--green:#047857;--red:#b42318;--amber:#b54708}
*{box-sizing:border-box}body{margin:0;min-height:100vh}button,input,textarea,select{font:inherit}
.shell{display:grid;grid-template-columns:250px minmax(0,1fr);min-height:100vh}.sidebar{background:var(--nav);color:#e2e8f0;padding:22px 16px;position:sticky;top:0;height:100vh;overflow:auto}.brand{font-weight:800;font-size:20px;letter-spacing:.2px}.version{font-size:12px;color:#94a3b8;margin:5px 0 22px}.identity{padding:12px;background:#182338;border:1px solid #2b3950;border-radius:12px;margin-bottom:18px}.identity strong{display:block;color:#fff}.identity span{font-size:12px;color:#aebbd0;display:block;margin-top:3px;overflow-wrap:anywhere}.nav button{width:100%;display:flex;gap:10px;align-items:center;border:0;background:transparent;color:#cbd5e1;padding:11px 12px;border-radius:9px;text-align:left;cursor:pointer;margin:2px 0}.nav button:hover,.nav button.active{background:#24324b;color:#fff}.nav .dot{width:8px;height:8px;border-radius:50%;background:#60a5fa}.main{min-width:0}.topbar{height:70px;background:#fff;border-bottom:1px solid var(--line);display:flex;align-items:center;justify-content:space-between;padding:0 26px;position:sticky;top:0;z-index:4}.topbar h1{font-size:19px;margin:0}.top-actions{display:flex;align-items:center;gap:10px}.timestamp{font-size:12px;color:var(--muted)}.content{padding:24px;max-width:1680px;margin:auto}.notice{background:#eff6ff;border:1px solid #bfdbfe;border-radius:12px;padding:12px 14px;color:#1e3a8a;font-size:13px;margin-bottom:18px}.error{background:#fef3f2;border:1px solid #fecdca;color:var(--red);border-radius:10px;padding:10px 12px;white-space:pre-wrap;margin-bottom:14px;display:none}.cards{display:grid;grid-template-columns:repeat(auto-fit,minmax(170px,1fr));gap:14px;margin-bottom:18px}.card,.panel{background:var(--card);border:1px solid var(--line);border-radius:14px;box-shadow:0 1px 3px rgba(16,24,40,.05)}.card{padding:16px}.card small{color:var(--muted);font-weight:600}.card b{display:block;font-size:28px;margin-top:7px}.panel{padding:17px;margin-bottom:16px;overflow:auto}.panel h2{font-size:16px;margin:0}.panel-head{display:flex;align-items:center;justify-content:space-between;gap:12px;margin-bottom:13px}.grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(410px,1fr));gap:16px}.wide{grid-column:1/-1}.muted{color:var(--muted)}.good{color:var(--green);font-weight:700}.bad{color:var(--red);font-weight:700}.warn{color:var(--amber);font-weight:700}.pill{display:inline-block;border:1px solid #cbd5e1;border-radius:999px;padding:3px 8px;font-size:11px;margin:2px;background:#f8fafc}.pill.good{background:#ecfdf3;border-color:#a6f4c5}.pill.bad{background:#fef3f2;border-color:#fecdca}.toolbar{display:flex;gap:8px;align-items:center;flex-wrap:wrap}.btn{border:0;border-radius:9px;padding:9px 12px;background:var(--blue);color:#fff;cursor:pointer;font-weight:650}.btn.secondary{background:#fff;color:#344054;border:1px solid #d0d5dd}.btn.danger{background:#d92d20}.btn:disabled{opacity:.45;cursor:not-allowed}.icon-btn{padding:7px 10px}.view{display:none}.view.active{display:block}table{width:100%;border-collapse:collapse;font-size:12px}th,td{text-align:left;padding:9px 8px;border-bottom:1px solid #edf0f4;vertical-align:top}th{color:#667085;font-weight:700;white-space:nowrap}td{overflow-wrap:anywhere}.empty{padding:24px;text-align:center;color:var(--muted)}.timeline{border-left:2px solid #dbe4f0;margin-left:8px;padding-left:20px}.event{position:relative;padding:0 0 17px}.event:before{content:"";position:absolute;left:-27px;top:4px;width:11px;height:11px;border-radius:50%;background:#3b82f6;border:3px solid #fff;box-shadow:0 0 0 1px #93c5fd}.event strong{font-size:13px}.event p{margin:4px 0;color:var(--muted);font-size:12px}.chain{display:flex;align-items:stretch;gap:7px;overflow:auto;padding:5px 0}.chain-item{min-width:135px;border:1px solid var(--line);border-radius:10px;padding:10px;background:#f8fafc}.chain-arrow{display:flex;align-items:center;color:#94a3b8}.form-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(230px,1fr));gap:12px}.field label{font-size:12px;color:#475467;font-weight:650;display:block;margin-bottom:5px}.field input,.field textarea,.field select{width:100%;border:1px solid #d0d5dd;border-radius:9px;padding:9px;background:#fff}.field textarea{min-height:90px;resize:vertical}.dialog{border:0;border-radius:14px;padding:0;max-width:650px;width:calc(100% - 32px);box-shadow:0 20px 60px rgba(15,23,42,.28)}.dialog::backdrop{background:rgba(15,23,42,.6)}.dialog-head{padding:16px 18px;border-bottom:1px solid var(--line);font-weight:750}.dialog-body{padding:18px}.dialog-actions{padding:14px 18px;border-top:1px solid var(--line);display:flex;justify-content:flex-end;gap:8px}.kv{display:grid;grid-template-columns:150px minmax(0,1fr);gap:6px 12px;font-size:12px}.kv div:nth-child(odd){color:var(--muted)}pre{white-space:pre-wrap;word-break:break-word;font-size:11px;background:#0f172a;color:#dbeafe;border-radius:10px;padding:12px;max-height:300px;overflow:auto}
@media(max-width:900px){.shell{grid-template-columns:1fr}.sidebar{height:auto;position:static}.nav{display:flex;overflow:auto}.nav button{min-width:max-content}.topbar{position:static}.grid{grid-template-columns:1fr}.content{padding:16px}}
</style>
</head>
<body>
<div class="shell">
<aside class="sidebar">
<div class="brand">AIOS Unified Portal</div><div class="version">V2R1C1 · Role-aware Control Plane</div>
<div class="identity"><strong id="principal">加载身份…</strong><span id="tenant"></span><span id="roles"></span></div>
<nav id="navigation" class="nav"></nav>
</aside>
<section class="main">
<header class="topbar"><h1 id="pageTitle">系统总览</h1><div class="top-actions"><span id="updated" class="timestamp">尚未加载</span><button class="btn secondary icon-btn" id="refresh">刷新</button></div></header>
<main class="content">
<div class="notice">身份、租户和角色由可信反向代理注入。门户只调用 AIOS Control Plane;Provenance 签发、Tag、生产部署与 Runtime 权威状态仍由受控流程执行。</div>
<div id="error" class="error"></div>
<section id="overview" class="view active"></section>
<section id="tasks" class="view"></section>
<section id="authorization" class="view"></section>
<section id="runtime" class="view"></section>
<section id="evidence" class="view"></section>
<section id="audit" class="view"></section>
<section id="release" class="view"></section>
</main>
</section>
</div>
<dialog id="taskDialog" class="dialog">
<div class="dialog-head">创建任务</div><form id="taskForm"><div class="dialog-body form-grid">
<div class="field"><label>Agent ID</label><input name="agent_id" required></div>
<div class="field"><label>Action</label><input name="action" required></div>
<div class="field"><label>Idempotency Key</label><input name="idempotency_key" required></div>
<div class="field wide"><label>Payload JSON</label><textarea name="payload">{}</textarea></div>
</div><div class="dialog-actions"><button type="button" class="btn secondary" data-close="taskDialog">取消</button><button class="btn">创建</button></div></form>
</dialog>
<dialog id="confirmDialog" class="dialog"><div class="dialog-head" id="confirmTitle">确认操作</div><form id="confirmForm"><div class="dialog-body"><p id="confirmText"></p><div class="field"><label>原因</label><textarea id="confirmReason" required></textarea></div></div><div class="dialog-actions"><button type="button" class="btn secondary" data-close="confirmDialog">取消</button><button class="btn danger">确认</button></div></form></dialog>
<script>
const $=s=>document.querySelector(s), esc=v=>String(v??'').replace(/[&<>"']/g,c=>({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;',"'":'&#39;'}[c]));
const state={identity:null,current:'overview',cache:{},confirm:null};
const labels={overview:'系统总览',tasks:'任务中心',authorization:'授权中心',runtime:'运行与运维',evidence:'执行证据',audit:'审计中心',release:'GitOps 与发布'};
function has(c){return !!state.identity?.capabilities?.includes(c)}
async function api(path,options={}){const r=await fetch(path,{credentials:'same-origin',headers:{'Accept':'application/json','Content-Type':'application/json',...(options.headers||{})},...options});const d=await r.json().catch(()=>({}));if(!r.ok)throw new Error(`${r.status} ${d.message||d.error||path}`);return d}
function err(e){const el=$('#error');el.textContent=e?.message||String(e);el.style.display='block'}function clearErr(){$('#error').style.display='none';$('#error').textContent=''}
function pill(v){const s=String(v??'unknown'),c=/complete|pass|healthy|active|synced|approved|used/i.test(s)?'good':/fail|deny|reject|revoke|expire|cancel|unavailable/i.test(s)?'bad':'';return `<span class="pill ${c}">${esc(s)}</span>`}
function table(cols,rows){if(!rows?.length)return '<div class="empty">暂无数据</div>';return `<table><thead><tr>${cols.map(x=>`<th>${esc(x[0])}</th>`).join('')}</tr></thead><tbody>${rows.map(r=>`<tr>${cols.map(x=>`<td>${x[1](r)}</td>`).join('')}</tr>`).join('')}</tbody></table>`}
function card(label,value,detail=''){return `<div class="card"><small>${esc(label)}</small><b>${esc(value)}</b>${detail?`<span class="muted">${esc(detail)}</span>`:''}</div>`}
function json(v){return `<pre>${esc(JSON.stringify(v,null,2))}</pre>`}
function show(view){state.current=view;document.querySelectorAll('.view').forEach(x=>x.classList.toggle('active',x.id===view));document.querySelectorAll('.nav button').forEach(x=>x.classList.toggle('active',x.dataset.view===view));$('#pageTitle').textContent=labels[view]||view;load(view)}
function navigation(){const nav=$('#navigation');nav.innerHTML=(state.identity.navigation||[]).map(x=>`<button data-view="${esc(x.id)}"><span class="dot"></span>${esc(x.label)}</button>`).join('');nav.querySelectorAll('button').forEach(b=>b.onclick=()=>show(b.dataset.view));}
async function identity(){state.identity=await api('/api/v2/me/capabilities');$('#principal').textContent=state.identity.principal_id;$('#tenant').textContent=`租户:${state.identity.tenant_id}`;$('#roles').textContent=`角色:${state.identity.roles.join(', ')||'无'}`;navigation();if(!state.identity.navigation.some(x=>x.id===state.current))state.current=state.identity.navigation[0]?.id||'overview';show(state.current)}
async function load(view){clearErr();try{if(view==='overview')await overview();if(view==='tasks')await tasks();if(view==='authorization')await authorizations();if(view==='runtime')await runtime();if(view==='evidence')await evidence();if(view==='audit')await audit();if(view==='release')await release();$('#updated').textContent=`更新于 ${new Date().toLocaleString()}`}catch(e){err(e)}}
async function overview(){const d=await api('/api/v2/portal/overview');state.cache.overview=d;const s=d.summary||{},rt=d.sections?.runtime?.runtimes||[],rel=d.sections?.release||{};$('#overview').innerHTML=`<div class="cards">${card('任务',s.tasks||0)}${card('活动 Dispatch',s.active_dispatches||0,`总数 ${s.dispatches||0}`)}${card('执行证据',s.evidence||0)}${card('审计事件',s.audit_events||0)}${card('当前版本',rel.version||'—',rel.status||'')}${card('授权 Grant',d.sections?.authorization?.active_grants||0,`总数 ${d.sections?.authorization?.grants||0}`)}</div><div class="grid"><div class="panel"><div class="panel-head"><h2>Runtime 健康</h2></div>${table([['Runtime',x=>esc(x.name)],['状态',x=>pill(x.status)],['版本/详情',x=>esc(x.details?.version||x.details?.runtime_id||'—')]],rt)}</div><div class="panel"><div class="panel-head"><h2>任务状态</h2></div>${table([['状态',x=>pill(x[0])],['数量',x=>esc(x[1])]],Object.entries(s.task_states||{}))}</div><div class="panel wide"><div class="panel-head"><h2>最近任务</h2></div>${table([['任务',x=>esc(x.task_id)],['Agent',x=>esc(x.agent_id)],['动作',x=>esc(x.action)],['状态',x=>pill(x.state)],['更新时间',x=>esc(x.updated_at)]],d.recent?.tasks||[])}</div></div>`}
async function tasks(){const d=await api('/api/v2/portal/tasks');state.cache.tasks=d.items||[];const create=has('task.create')?'<button class="btn" id="newTask">创建任务</button>':'';$('#tasks').innerHTML=`<div class="panel"><div class="panel-head"><h2>任务全链路</h2><div class="toolbar">${create}</div></div>${(d.items||[]).map(taskBlock).join('')||'<div class="empty">暂无任务</div>'}</div>`;$('#newTask')?.addEventListener('click',()=>$('#taskDialog').showModal());document.querySelectorAll('[data-task-action]').forEach(b=>b.onclick=()=>taskAction(b.dataset.taskId,b.dataset.taskAction,b.dataset.revision))}
function taskBlock(x){const t=x.task||{},d=x.dispatch,e=x.evidence||[],a=x.audit||[],actions=(x.available_actions||[]).map(v=>`<button class="btn ${v==='cancel'?'danger':'secondary'}" data-task-action="${v}" data-task-id="${esc(t.task_id)}" data-revision="${esc(t.revision)}">${{approve:'审批',cancel:'取消',dispatch:'调度'}[v]||v}</button>`).join('');return `<div class="panel" style="background:#fbfcfe"><div class="panel-head"><h2>${esc(t.task_id)} · ${esc(t.action)}</h2><div class="toolbar">${pill(t.state)}${actions}</div></div><div class="chain"><div class="chain-item"><b>Task</b><div>${esc(t.agent_id)}</div><small>${esc(t.created_by)}</small></div><span class="chain-arrow">→</span><div class="chain-item"><b>Approval</b><div>${esc(t.approved_by||'待审批')}</div><small>revision ${esc(t.revision)}</small></div><span class="chain-arrow">→</span><div class="chain-item"><b>Provenance</b><div>${esc(d?.provenance_id||'未调度')}</div><small>${esc(d?.authorization_id||'')}</small></div><span class="chain-arrow">→</span><div class="chain-item"><b>Dispatch</b><div>${esc(d?.dispatch_id||'—')}</div><small>${pill(d?.state||'not_created')}</small></div><span class="chain-arrow">→</span><div class="chain-item"><b>Runtime</b><div>${esc(d?.runtime||'—')}</div><small>${esc(d?.runtime_execution_id||'')}</small></div><span class="chain-arrow">→</span><div class="chain-item"><b>Evidence</b><div>${e.length} 条</div><small>Audit ${a.length} 条</small></div></div></div>`}
async function taskAction(id,action,revision){clearErr();try{let body={expected_revision:Number(revision)};if(action==='dispatch'){body={};const p=prompt('Provenance ID(生产调度必填)','');const r=prompt('Run ID(生产调度必填)','');if(p)body.provenance_id=p;if(r)body.run_id=r}await api(`/api/v2/portal/tasks/${encodeURIComponent(id)}/${action}`,{method:'POST',body:JSON.stringify(body)});await tasks()}catch(e){err(e)}}
async function authorizations(){const d=await api('/api/v2/portal/authorizations');state.cache.authorization=d;const workflows=(d.workflows||[]),grants=(d.grants||[]);$('#authorization').innerHTML=`<div class="cards">${card('Workflow',d.summary?.workflows||0)}${card('Grant',d.summary?.grants||0)}${card('有效 Grant',d.summary?.active_grants||0)}${card('已撤销',d.summary?.revoked_grants||0)}</div><div class="panel"><div class="panel-head"><h2>Workflow Provenance</h2></div>${table([['ID',x=>esc(x.provenance_id)],['Run / Task',x=>`${esc(x.run_id)}<br>${esc(x.task_id)}`],['Principal / Agent',x=>`${esc(x.principal_id)}<br>${esc(x.agent_id)}`],['状态',x=>pill(x.status)],['有效期',x=>esc(x.expires_at)],['使用',x=>esc(x.usage_count)],['操作',x=>has('provenance.revoke')&&x.status!=='revoked'?`<button class="btn danger" data-revoke-workflow="${esc(x.provenance_id)}">撤销</button>`:'—']],workflows)}</div><div class="panel"><div class="panel-head"><h2>Child Grants</h2></div>${table([['Grant',x=>esc(x.grant_id)],['类型 / Scope',x=>`${esc(x.grant_type)}<br>${esc(x.execution_path)}`],['Git 操作',x=>esc((x.allowed_git_operations||[]).join(', ')||'—')],['状态',x=>pill(x.status)],['有效期',x=>esc(x.expires_at)],['使用',x=>esc(x.usage_count)],['操作',x=>has('provenance.revoke')&&x.status!=='revoked'?`<button class="btn danger" data-revoke-grant="${esc(x.grant_id)}">撤销</button>`:'—']],grants)}</div>`;document.querySelectorAll('[data-revoke-workflow]').forEach(b=>b.onclick=()=>confirmOp('撤销 Workflow',`撤销 ${b.dataset.revokeWorkflow} 将使所有子 Grant 失效。`,reason=>api(`/api/v2/portal/provenance/${encodeURIComponent(b.dataset.revokeWorkflow)}/revoke`,{method:'POST',body:JSON.stringify({reason})}).then(authorizations)));document.querySelectorAll('[data-revoke-grant]').forEach(b=>b.onclick=()=>confirmOp('撤销 Grant',`撤销 ${b.dataset.revokeGrant}。`,reason=>api(`/api/v2/portal/grants/${encodeURIComponent(b.dataset.revokeGrant)}/revoke`,{method:'POST',body:JSON.stringify({reason})}).then(authorizations)))}
async function runtime(){const d=await api('/api/v2/portal/runtime');const runtimes=d.runtimes||[],dispatches=d.dispatches||[],jobs=d.hermes_jobs||[];$('#runtime').innerHTML=`<div class="grid"><div class="panel"><div class="panel-head"><h2>Runtime</h2></div>${table([['名称',x=>esc(x.name)],['状态',x=>pill(x.status)],['详情',x=>esc(JSON.stringify(x.details||{}))]],runtimes)}</div><div class="panel"><div class="panel-head"><h2>Hermes Queue / Lease</h2></div>${table([['Job',x=>esc(x.job_id)],['Cell / Profile',x=>`${esc(x.cell_id)} / ${esc(x.profile_id)}`],['Worker',x=>esc(x.assigned_worker_id||'—')],['状态',x=>pill(x.state)],['Lease',x=>esc(x.lease_expires_at||'—')]],jobs)}</div><div class="panel wide"><div class="panel-head"><h2>Dispatch</h2></div>${table([['Dispatch',x=>esc(x.dispatch_id)],['Task',x=>esc(x.task_id)],['Runtime',x=>esc(x.runtime)],['执行 ID',x=>esc(x.runtime_execution_id)],['Principal',x=>esc(x.principal_id)],['状态',x=>pill(x.state)]],dispatches)}</div></div>`}
async function evidence(){const d=await api('/api/v2/portal/evidence');$('#evidence').innerHTML=`<div class="panel"><div class="panel-head"><h2>Execution Evidence</h2></div>${table([['Execution',x=>esc(x.execution_id)],['Task / Agent',x=>`${esc(x.task_id)}<br>${esc(x.agent_id)}`],['Executor',x=>esc(x.executor)],['状态',x=>pill(x.status)],['进度',x=>`${esc(x.progress_completed)}/${esc(x.progress_total)}`],['Test',x=>pill(x.test_status)],['Commit',x=>esc(x.last_commit||'—')],['授权',x=>esc(x.last_authorization_id||'—')]],d.executions||[])}</div>`}
async function audit(){const d=await api('/api/v2/portal/audit');const events=(d.events||[]).slice().reverse();$('#audit').innerHTML=`<div class="panel"><div class="panel-head"><h2>统一审计时间线</h2></div><div class="timeline">${events.map(x=>`<div class="event"><strong>${esc(x.action)} · ${pill(x.outcome)}</strong><p>${esc(x.created_at)} · ${esc(x.principal_id)} · ${esc(x.resource_type)}/${esc(x.resource_id)}</p><div class="muted">Trace ${esc(x.trace_id)} · Policy ${esc(x.policy_version)}</div></div>`).join('')||'<div class="empty">暂无审计事件</div>'}</div></div>`}
async function release(){const d=await api('/api/v2/portal/release');const g=d.gitops||{};$('#release').innerHTML=`<div class="cards">${card('版本',d.version||'—')}${card('Baseline',d.baseline||'—')}${card('发布状态',d.status||'—')}${card('Git 同步',g.sync_status||'unknown')}</div><div class="grid"><div class="panel"><div class="panel-head"><h2>当前 Release</h2></div><div class="kv"><div>Release OID</div><div>${esc(d.release_oid)}</div><div>Branch</div><div>${esc(g.workspace_branch||g.branch||'—')}</div><div>Workspace</div><div>${pill(g.workspace_clean===true?'clean':g.workspace_clean===false?'dirty':'unknown')}</div><div>Local Sync</div><div>${pill(g.local_sync||'unknown')}</div><div>Gitea Sync</div><div>${pill(g.gitea_sync||'unknown')}</div></div></div><div class="panel"><div class="panel-head"><h2>治理操作</h2></div><p class="muted">门户不直接移动 Tag、合并主线或部署生产。以下仅为可发起的 GitOps 请求目录。</p>${(d.operations||[]).map(x=>pill(x)).join('')||'<span class="muted">当前角色只读</span>'}</div><div class="panel wide"><div class="panel-head"><h2>原始 GitOps 状态</h2></div>${json(g)}</div></div>`}
function confirmOp(title,text,fn){state.confirm=fn;$('#confirmTitle').textContent=title;$('#confirmText').textContent=text;$('#confirmReason').value='';$('#confirmDialog').showModal()}
$('#taskForm').onsubmit=async e=>{e.preventDefault();clearErr();try{const fd=new FormData(e.target),payload=JSON.parse(fd.get('payload')||'{}');await api('/api/v2/portal/tasks',{method:'POST',body:JSON.stringify({agent_id:fd.get('agent_id'),action:fd.get('action'),idempotency_key:fd.get('idempotency_key'),payload})});$('#taskDialog').close();e.target.reset();await tasks()}catch(e){err(e)}};
$('#confirmForm').onsubmit=async e=>{e.preventDefault();const fn=state.confirm;$('#confirmDialog').close();state.confirm=null;try{await fn?.($('#confirmReason').value)}catch(e){err(e)}};
document.querySelectorAll('[data-close]').forEach(b=>b.onclick=()=>document.getElementById(b.dataset.close).close());$('#refresh').onclick=()=>load(state.current);
identity().catch(err);setInterval(()=>load(state.current),30000);
</script>
</body></html>'''
+627
View File
@@ -0,0 +1,627 @@
"""Tenant-isolated AIOS V2 control-plane domain service.
This module deliberately contains no OpenClaw or Hermes implementation details.
It owns authoritative tenant, agent, task-lifecycle, idempotency and audit state.
Runtime adapters consume approved tasks through a separate boundary.
"""
from __future__ import annotations
import copy
import hashlib
import json
import threading
import uuid
from dataclasses import dataclass, field
from datetime import datetime, timezone
from enum import Enum
from typing import Any, Callable, Iterable, Mapping
def _utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def _new_id(prefix: str) -> str:
return f"{prefix}_{uuid.uuid4().hex}"
def _canonical_digest(value: Mapping[str, Any]) -> str:
encoded = json.dumps(
value,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
default=str,
).encode("utf-8")
return hashlib.sha256(encoded).hexdigest()
class ControlPlaneError(RuntimeError):
"""Base error returned by the control-plane domain."""
class Unauthorized(ControlPlaneError):
"""The caller is not authenticated or lacks the required role."""
class TenantIsolationError(ControlPlaneError):
"""A request attempted to cross a tenant boundary."""
class NotFound(ControlPlaneError):
"""A tenant-scoped resource does not exist or is not visible."""
class InvalidTransition(ControlPlaneError):
"""A task state transition violates the lifecycle contract."""
class IdempotencyConflict(ControlPlaneError):
"""An idempotency key was reused for a different command."""
class RevisionConflict(ControlPlaneError):
"""Optimistic task revision does not match current state."""
class PolicyDenied(ControlPlaneError):
"""The policy gate denied a control-plane operation."""
@dataclass(frozen=True)
class RequestContext:
"""Authenticated request identity propagated across all AIOS layers."""
tenant_id: str
principal_id: str
trace_id: str
roles: frozenset[str] = field(default_factory=frozenset)
session_id: str | None = None
policy_version: str = "v1"
def __post_init__(self) -> None:
for name in ("tenant_id", "principal_id", "trace_id"):
if not str(getattr(self, name, "")).strip():
raise ValueError(f"{name} is required")
@classmethod
def create(
cls,
*,
tenant_id: str,
principal_id: str,
roles: Iterable[str] = (),
trace_id: str | None = None,
session_id: str | None = None,
policy_version: str = "v1",
) -> "RequestContext":
return cls(
tenant_id=tenant_id.strip(),
principal_id=principal_id.strip(),
trace_id=trace_id or _new_id("trace"),
roles=frozenset(str(role).strip() for role in roles if str(role).strip()),
session_id=session_id,
policy_version=policy_version,
)
@dataclass(frozen=True)
class TenantRecord:
tenant_id: str
display_name: str
status: str = "active"
metadata: Mapping[str, Any] = field(default_factory=dict)
created_at: str = field(default_factory=_utc_now)
updated_at: str = field(default_factory=_utc_now)
@dataclass(frozen=True)
class AgentRecord:
agent_id: str
tenant_id: str
display_name: str
runtime: str
capabilities: tuple[str, ...] = field(default_factory=tuple)
enabled: bool = True
metadata: Mapping[str, Any] = field(default_factory=dict)
created_at: str = field(default_factory=_utc_now)
updated_at: str = field(default_factory=_utc_now)
class TaskState(str, Enum):
CREATED = "CREATED"
APPROVED = "APPROVED"
RUNNING = "RUNNING"
COMPLETED = "COMPLETED"
FAILED = "FAILED"
CANCELLED = "CANCELLED"
TERMINAL_TASK_STATES = frozenset(
{TaskState.COMPLETED, TaskState.FAILED, TaskState.CANCELLED}
)
ALLOWED_TASK_TRANSITIONS: Mapping[TaskState, frozenset[TaskState]] = {
TaskState.CREATED: frozenset({TaskState.APPROVED, TaskState.CANCELLED}),
TaskState.APPROVED: frozenset({TaskState.RUNNING, TaskState.CANCELLED}),
TaskState.RUNNING: frozenset(
{TaskState.COMPLETED, TaskState.FAILED, TaskState.CANCELLED}
),
TaskState.COMPLETED: frozenset(),
TaskState.FAILED: frozenset(),
TaskState.CANCELLED: frozenset(),
}
@dataclass(frozen=True)
class TaskRecord:
task_id: str
tenant_id: str
agent_id: str
action: str
payload: Mapping[str, Any]
state: TaskState = TaskState.CREATED
revision: int = 1
idempotency_key: str | None = None
request_digest: str = ""
result: Mapping[str, Any] | None = None
error: Mapping[str, Any] | None = None
created_by: str = ""
approved_by: str | None = None
created_at: str = field(default_factory=_utc_now)
updated_at: str = field(default_factory=_utc_now)
@dataclass(frozen=True)
class AuditEvent:
event_id: str
tenant_id: str
principal_id: str
trace_id: str
action: str
resource_type: str
resource_id: str
outcome: str
policy_version: str
details: Mapping[str, Any] = field(default_factory=dict)
created_at: str = field(default_factory=_utc_now)
@dataclass(frozen=True)
class PolicyDecision:
allowed: bool
reason: str
policy_version: str
PolicyEvaluator = Callable[[RequestContext, str, Mapping[str, Any]], PolicyDecision]
class InMemoryControlPlaneStore:
"""Thread-safe reference store used by tests and the first gateway slice.
Production backends must preserve the same tenant-scoped interface and add
database row-level security, migrations, backup and HA evidence.
"""
def __init__(self) -> None:
self.lock = threading.RLock()
self.tenants: dict[str, TenantRecord] = {}
self.agents: dict[str, AgentRecord] = {}
self.tasks: dict[str, TaskRecord] = {}
self.idempotency: dict[tuple[str, str], tuple[str, str]] = {}
self.audit_events: list[AuditEvent] = []
class ControlPlaneService:
"""Authoritative tenant, agent and task lifecycle service."""
def __init__(
self,
store: InMemoryControlPlaneStore | None = None,
*,
policy_evaluator: PolicyEvaluator | None = None,
) -> None:
self.store = store or InMemoryControlPlaneStore()
self.policy_evaluator = policy_evaluator or self._default_policy
@staticmethod
def _default_policy(
context: RequestContext,
action: str,
resource: Mapping[str, Any],
) -> PolicyDecision:
del resource
role_requirements = {
"tenant.register": {"platform_admin"},
"tenant.read": {"tenant_admin", "operator", "auditor", "platform_admin"},
"agent.register": {"tenant_admin", "operator", "platform_admin"},
"agent.read": {"tenant_admin", "operator", "auditor", "platform_admin"},
"task.create": {"tenant_admin", "operator", "platform_admin"},
"task.read": {"tenant_admin", "operator", "auditor", "platform_admin"},
"task.approve": {"tenant_admin", "approver", "platform_admin"},
"task.start": {"runtime", "operator", "platform_admin"},
"task.complete": {"runtime", "operator", "platform_admin"},
"task.fail": {"runtime", "operator", "platform_admin"},
"task.cancel": {"tenant_admin", "operator", "approver", "platform_admin"},
"audit.read": {"tenant_admin", "auditor", "platform_admin"},
}
required = role_requirements.get(action, {"platform_admin"})
allowed = bool(context.roles.intersection(required))
return PolicyDecision(
allowed=allowed,
reason="role_allowed" if allowed else "required_role_missing",
policy_version=context.policy_version,
)
def _require_context(self, context: RequestContext) -> None:
if not context.principal_id or not context.tenant_id or not context.trace_id:
raise Unauthorized("authenticated tenant context is required")
def _authorize(
self,
context: RequestContext,
action: str,
resource: Mapping[str, Any],
) -> PolicyDecision:
self._require_context(context)
decision = self.policy_evaluator(context, action, resource)
if not decision.allowed:
self._audit(
context,
action=action,
resource_type=str(resource.get("resource_type", "policy")),
resource_id=str(resource.get("resource_id", "unknown")),
outcome="denied",
details={"reason": decision.reason},
)
raise PolicyDenied(f"{action} denied: {decision.reason}")
return decision
@staticmethod
def _assert_same_tenant(context: RequestContext, tenant_id: str) -> None:
if context.tenant_id != tenant_id and "platform_admin" not in context.roles:
raise TenantIsolationError("cross-tenant access denied")
def _audit(
self,
context: RequestContext,
*,
action: str,
resource_type: str,
resource_id: str,
outcome: str,
details: Mapping[str, Any] | None = None,
) -> AuditEvent:
event = AuditEvent(
event_id=_new_id("audit"),
tenant_id=context.tenant_id,
principal_id=context.principal_id,
trace_id=context.trace_id,
action=action,
resource_type=resource_type,
resource_id=resource_id,
outcome=outcome,
policy_version=context.policy_version,
details=copy.deepcopy(dict(details or {})),
)
self.store.audit_events.append(event)
return event
def register_tenant(
self,
context: RequestContext,
*,
tenant_id: str,
display_name: str,
metadata: Mapping[str, Any] | None = None,
) -> TenantRecord:
tenant_id = tenant_id.strip()
if not tenant_id or not display_name.strip():
raise ValueError("tenant_id and display_name are required")
self._authorize(
context,
"tenant.register",
{"resource_type": "tenant", "resource_id": tenant_id},
)
self._assert_same_tenant(context, tenant_id)
with self.store.lock:
if tenant_id in self.store.tenants:
raise ControlPlaneError(f"tenant already exists: {tenant_id}")
tenant = TenantRecord(
tenant_id=tenant_id,
display_name=display_name.strip(),
metadata=copy.deepcopy(dict(metadata or {})),
)
self.store.tenants[tenant_id] = tenant
self._audit(
context,
action="tenant.register",
resource_type="tenant",
resource_id=tenant_id,
outcome="allowed",
)
return tenant
def get_tenant(self, context: RequestContext, tenant_id: str | None = None) -> TenantRecord:
tenant_id = tenant_id or context.tenant_id
self._authorize(
context,
"tenant.read",
{"resource_type": "tenant", "resource_id": tenant_id},
)
self._assert_same_tenant(context, tenant_id)
with self.store.lock:
tenant = self.store.tenants.get(tenant_id)
if tenant is None:
raise NotFound("tenant not found")
return tenant
def register_agent(
self,
context: RequestContext,
*,
agent_id: str,
display_name: str,
runtime: str,
capabilities: Iterable[str] = (),
metadata: Mapping[str, Any] | None = None,
) -> AgentRecord:
self._authorize(
context,
"agent.register",
{"resource_type": "agent", "resource_id": agent_id},
)
tenant = self.get_tenant(context)
if tenant.status != "active":
raise ControlPlaneError("tenant is not active")
normalized_capabilities = tuple(
sorted({str(item).strip() for item in capabilities if str(item).strip()})
)
if not agent_id.strip() or not display_name.strip() or not runtime.strip():
raise ValueError("agent_id, display_name and runtime are required")
with self.store.lock:
existing = self.store.agents.get(agent_id)
if existing is not None and existing.tenant_id != context.tenant_id:
raise TenantIsolationError("agent id belongs to another tenant")
if existing is not None:
raise ControlPlaneError(f"agent already exists: {agent_id}")
agent = AgentRecord(
agent_id=agent_id.strip(),
tenant_id=context.tenant_id,
display_name=display_name.strip(),
runtime=runtime.strip(),
capabilities=normalized_capabilities,
metadata=copy.deepcopy(dict(metadata or {})),
)
self.store.agents[agent.agent_id] = agent
self._audit(
context,
action="agent.register",
resource_type="agent",
resource_id=agent.agent_id,
outcome="allowed",
details={"runtime": agent.runtime},
)
return agent
def get_agent(self, context: RequestContext, agent_id: str) -> AgentRecord:
self._authorize(
context,
"agent.read",
{"resource_type": "agent", "resource_id": agent_id},
)
with self.store.lock:
agent = self.store.agents.get(agent_id)
if agent is None:
raise NotFound("agent not found")
self._assert_same_tenant(context, agent.tenant_id)
return agent
def list_agents(self, context: RequestContext) -> list[AgentRecord]:
self._authorize(
context,
"agent.read",
{"resource_type": "agent_collection", "resource_id": context.tenant_id},
)
with self.store.lock:
return [
agent
for agent in self.store.agents.values()
if agent.tenant_id == context.tenant_id
]
def create_task(
self,
context: RequestContext,
*,
agent_id: str,
action: str,
payload: Mapping[str, Any] | None = None,
idempotency_key: str | None = None,
) -> TaskRecord:
self._authorize(
context,
"task.create",
{"resource_type": "task", "resource_id": idempotency_key or "new"},
)
agent = self.get_agent(context, agent_id)
if not agent.enabled:
raise ControlPlaneError("agent is disabled")
if action not in agent.capabilities and "*" not in agent.capabilities:
raise PolicyDenied(f"agent does not advertise capability: {action}")
normalized_payload = copy.deepcopy(dict(payload or {}))
request_digest = _canonical_digest(
{"agent_id": agent_id, "action": action, "payload": normalized_payload}
)
normalized_key = idempotency_key.strip() if idempotency_key else None
with self.store.lock:
if normalized_key:
idempotency_ref = (context.tenant_id, normalized_key)
existing = self.store.idempotency.get(idempotency_ref)
if existing is not None:
existing_task_id, existing_digest = existing
if existing_digest != request_digest:
raise IdempotencyConflict(
"idempotency key was reused with a different request"
)
return self.store.tasks[existing_task_id]
task = TaskRecord(
task_id=_new_id("task"),
tenant_id=context.tenant_id,
agent_id=agent_id,
action=action,
payload=normalized_payload,
idempotency_key=normalized_key,
request_digest=request_digest,
created_by=context.principal_id,
)
self.store.tasks[task.task_id] = task
if normalized_key:
self.store.idempotency[(context.tenant_id, normalized_key)] = (
task.task_id,
request_digest,
)
self._audit(
context,
action="task.create",
resource_type="task",
resource_id=task.task_id,
outcome="allowed",
details={"agent_id": agent_id, "action": action},
)
return task
def get_task(self, context: RequestContext, task_id: str) -> TaskRecord:
self._authorize(
context,
"task.read",
{"resource_type": "task", "resource_id": task_id},
)
with self.store.lock:
task = self.store.tasks.get(task_id)
if task is None:
raise NotFound("task not found")
self._assert_same_tenant(context, task.tenant_id)
return task
def list_tasks(
self,
context: RequestContext,
*,
states: Iterable[TaskState | str] | None = None,
) -> list[TaskRecord]:
self._authorize(
context,
"task.read",
{"resource_type": "task_collection", "resource_id": context.tenant_id},
)
state_filter = (
{TaskState(item) for item in states}
if states is not None
else None
)
with self.store.lock:
return [
task
for task in self.store.tasks.values()
if task.tenant_id == context.tenant_id
and (state_filter is None or task.state in state_filter)
]
def transition_task(
self,
context: RequestContext,
*,
task_id: str,
target_state: TaskState | str,
expected_revision: int | None = None,
result: Mapping[str, Any] | None = None,
error: Mapping[str, Any] | None = None,
) -> TaskRecord:
target = TaskState(target_state)
action_name = {
TaskState.APPROVED: "task.approve",
TaskState.RUNNING: "task.start",
TaskState.COMPLETED: "task.complete",
TaskState.FAILED: "task.fail",
TaskState.CANCELLED: "task.cancel",
}.get(target)
if action_name is None:
raise InvalidTransition(f"cannot transition to {target.value}")
self._authorize(
context,
action_name,
{"resource_type": "task", "resource_id": task_id},
)
with self.store.lock:
current = self.store.tasks.get(task_id)
if current is None:
raise NotFound("task not found")
self._assert_same_tenant(context, current.tenant_id)
if expected_revision is not None and current.revision != expected_revision:
raise RevisionConflict(
f"expected revision {expected_revision}, current {current.revision}"
)
if target not in ALLOWED_TASK_TRANSITIONS[current.state]:
raise InvalidTransition(
f"invalid transition {current.state.value} -> {target.value}"
)
if target == TaskState.COMPLETED and result is None:
raise ValueError("completed task requires result")
if target == TaskState.FAILED and error is None:
raise ValueError("failed task requires error")
updated = TaskRecord(
task_id=current.task_id,
tenant_id=current.tenant_id,
agent_id=current.agent_id,
action=current.action,
payload=current.payload,
state=target,
revision=current.revision + 1,
idempotency_key=current.idempotency_key,
request_digest=current.request_digest,
result=copy.deepcopy(dict(result)) if result is not None else current.result,
error=copy.deepcopy(dict(error)) if error is not None else current.error,
created_by=current.created_by,
approved_by=(
context.principal_id
if target == TaskState.APPROVED
else current.approved_by
),
created_at=current.created_at,
updated_at=_utc_now(),
)
self.store.tasks[task_id] = updated
self._audit(
context,
action=action_name,
resource_type="task",
resource_id=task_id,
outcome="allowed",
details={
"from": current.state.value,
"to": target.value,
"revision": updated.revision,
},
)
return updated
def list_audit_events(
self,
context: RequestContext,
*,
resource_id: str | None = None,
) -> list[AuditEvent]:
self._authorize(
context,
"audit.read",
{"resource_type": "audit", "resource_id": resource_id or context.tenant_id},
)
with self.store.lock:
return [
event
for event in self.store.audit_events
if event.tenant_id == context.tenant_id
and (resource_id is None or event.resource_id == resource_id)
]
@@ -0,0 +1,379 @@
"""AIOS V2 持久化 Dispatch 记录。
Dispatch 是 AIOS Task 与 Runtime command/job 之间的唯一可信绑定。所有结果回写
必须匹配 tenant/task/trace/runtime_execution/provenance/run/principal。
"""
from __future__ import annotations
import json
import sqlite3
import threading
import uuid
from dataclasses import asdict, dataclass, replace
from datetime import datetime, timezone
from enum import Enum
from pathlib import Path
from typing import Any, Mapping, Protocol
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def _required(value: str, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
class DispatchState(str, Enum):
PREPARED = "PREPARED"
RUNNING = "RUNNING"
QUEUED = "QUEUED"
COMPLETED = "COMPLETED"
FAILED = "FAILED"
CANCELLED = "CANCELLED"
TERMINAL_DISPATCH_STATES = frozenset(
{DispatchState.COMPLETED, DispatchState.FAILED, DispatchState.CANCELLED}
)
@dataclass(frozen=True)
class DispatchRecord:
dispatch_id: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
runtime: str
runtime_execution_id: str
trace_id: str
provenance_id: str
run_id: str
authorization_id: str
state: DispatchState = DispatchState.PREPARED
expected_worker_id: str | None = None
result_digest: str | None = None
created_at: str = ""
updated_at: str = ""
completed_at: str | None = None
def __post_init__(self) -> None:
for name in (
"dispatch_id",
"tenant_id",
"task_id",
"agent_id",
"principal_id",
"runtime",
"runtime_execution_id",
"trace_id",
"provenance_id",
"run_id",
"authorization_id",
):
object.__setattr__(self, name, _required(getattr(self, name), name))
object.__setattr__(self, "state", DispatchState(self.state))
now = utc_now()
object.__setattr__(self, "created_at", self.created_at or now)
object.__setattr__(self, "updated_at", self.updated_at or now)
if self.expected_worker_id is not None:
object.__setattr__(
self,
"expected_worker_id",
_required(self.expected_worker_id, "expected_worker_id"),
)
@classmethod
def create(
cls,
*,
tenant_id: str,
task_id: str,
agent_id: str,
principal_id: str,
runtime: str,
runtime_execution_id: str,
trace_id: str,
provenance_id: str,
run_id: str,
authorization_id: str,
) -> "DispatchRecord":
return cls(
dispatch_id=f"dispatch_{uuid.uuid4().hex}",
tenant_id=tenant_id,
task_id=task_id,
agent_id=agent_id,
principal_id=principal_id,
runtime=runtime,
runtime_execution_id=runtime_execution_id,
trace_id=trace_id,
provenance_id=provenance_id,
run_id=run_id,
authorization_id=authorization_id,
)
def as_dict(self) -> dict[str, Any]:
value = asdict(self)
value["state"] = self.state.value
return value
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "DispatchRecord":
return cls(**dict(value))
class DispatchConflict(RuntimeError):
pass
class DispatchNotFound(RuntimeError):
pass
class DispatchRepository(Protocol):
def create(self, record: DispatchRecord) -> DispatchRecord: ...
def get(self, dispatch_id: str, *, tenant_id: str) -> DispatchRecord: ...
def get_by_task(self, task_id: str, *, tenant_id: str) -> DispatchRecord | None: ...
def get_by_runtime_execution(
self, runtime_execution_id: str, *, tenant_id: str
) -> DispatchRecord | None: ...
def update(
self,
dispatch_id: str,
*,
tenant_id: str,
state: DispatchState | str | None = None,
expected_worker_id: str | None = None,
result_digest: str | None = None,
) -> DispatchRecord: ...
def list(self, *, tenant_id: str) -> list[DispatchRecord]: ...
class InMemoryDispatchRepository:
def __init__(self) -> None:
self._lock = threading.RLock()
self._records: dict[str, DispatchRecord] = {}
self._by_task: dict[tuple[str, str], str] = {}
self._by_runtime: dict[tuple[str, str], str] = {}
def create(self, record: DispatchRecord) -> DispatchRecord:
with self._lock:
task_ref = (record.tenant_id, record.task_id)
runtime_ref = (record.tenant_id, record.runtime_execution_id)
if task_ref in self._by_task or runtime_ref in self._by_runtime:
existing = self.get_by_task(record.task_id, tenant_id=record.tenant_id)
if existing == record:
return record
raise DispatchConflict("task or runtime execution already has a dispatch")
self._records[record.dispatch_id] = record
self._by_task[task_ref] = record.dispatch_id
self._by_runtime[runtime_ref] = record.dispatch_id
return record
def get(self, dispatch_id: str, *, tenant_id: str) -> DispatchRecord:
with self._lock:
record = self._records.get(dispatch_id)
if record is None or record.tenant_id != tenant_id:
raise DispatchNotFound("dispatch not found")
return record
def get_by_task(self, task_id: str, *, tenant_id: str) -> DispatchRecord | None:
with self._lock:
dispatch_id = self._by_task.get((tenant_id, task_id))
return self._records.get(dispatch_id) if dispatch_id else None
def get_by_runtime_execution(
self, runtime_execution_id: str, *, tenant_id: str
) -> DispatchRecord | None:
with self._lock:
dispatch_id = self._by_runtime.get((tenant_id, runtime_execution_id))
return self._records.get(dispatch_id) if dispatch_id else None
def update(
self,
dispatch_id: str,
*,
tenant_id: str,
state: DispatchState | str | None = None,
expected_worker_id: str | None = None,
result_digest: str | None = None,
) -> DispatchRecord:
with self._lock:
current = self.get(dispatch_id, tenant_id=tenant_id)
target = DispatchState(state) if state is not None else current.state
if current.state in TERMINAL_DISPATCH_STATES and target != current.state:
raise DispatchConflict("terminal dispatch cannot transition")
updated = replace(
current,
state=target,
expected_worker_id=(
expected_worker_id
if expected_worker_id is not None
else current.expected_worker_id
),
result_digest=result_digest or current.result_digest,
updated_at=utc_now(),
completed_at=(utc_now() if target in TERMINAL_DISPATCH_STATES else None),
)
self._records[dispatch_id] = updated
return updated
def list(self, *, tenant_id: str) -> list[DispatchRecord]:
with self._lock:
return sorted(
[item for item in self._records.values() if item.tenant_id == tenant_id],
key=lambda item: (item.created_at, item.dispatch_id),
)
class SQLiteDispatchRepository:
SCHEMA_VERSION = 1
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
with self._connect() as connection:
connection.executescript(
"""
CREATE TABLE IF NOT EXISTS dispatch_records (
dispatch_id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL,
task_id TEXT NOT NULL,
runtime_execution_id TEXT NOT NULL,
payload_json TEXT NOT NULL,
state TEXT NOT NULL,
updated_at TEXT NOT NULL,
UNIQUE(tenant_id, task_id),
UNIQUE(tenant_id, runtime_execution_id)
);
CREATE INDEX IF NOT EXISTS idx_dispatch_tenant_state
ON dispatch_records(tenant_id, state, updated_at);
"""
)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(str(self.path), timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
return connection
@staticmethod
def _encode(record: DispatchRecord) -> str:
return json.dumps(
record.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
)
@staticmethod
def _decode(row: sqlite3.Row) -> DispatchRecord:
value = json.loads(row["payload_json"])
if not isinstance(value, Mapping):
raise RuntimeError("invalid dispatch record")
return DispatchRecord.from_dict(value)
def create(self, record: DispatchRecord) -> DispatchRecord:
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
try:
connection.execute(
"INSERT INTO dispatch_records VALUES (?, ?, ?, ?, ?, ?, ?)",
(
record.dispatch_id,
record.tenant_id,
record.task_id,
record.runtime_execution_id,
self._encode(record),
record.state.value,
record.updated_at,
),
)
connection.commit()
return record
except sqlite3.IntegrityError as exc:
connection.rollback()
existing = self.get_by_task(record.task_id, tenant_id=record.tenant_id)
if existing is not None and existing == record:
return existing
raise DispatchConflict("task or runtime execution already has a dispatch") from exc
def get(self, dispatch_id: str, *, tenant_id: str) -> DispatchRecord:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT payload_json FROM dispatch_records WHERE dispatch_id = ? AND tenant_id = ?",
(_required(dispatch_id, "dispatch_id"), _required(tenant_id, "tenant_id")),
).fetchone()
if row is None:
raise DispatchNotFound("dispatch not found")
return self._decode(row)
def get_by_task(self, task_id: str, *, tenant_id: str) -> DispatchRecord | None:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT payload_json FROM dispatch_records WHERE task_id = ? AND tenant_id = ?",
(_required(task_id, "task_id"), _required(tenant_id, "tenant_id")),
).fetchone()
return self._decode(row) if row is not None else None
def get_by_runtime_execution(
self, runtime_execution_id: str, *, tenant_id: str
) -> DispatchRecord | None:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT payload_json FROM dispatch_records WHERE runtime_execution_id = ? AND tenant_id = ?",
(
_required(runtime_execution_id, "runtime_execution_id"),
_required(tenant_id, "tenant_id"),
),
).fetchone()
return self._decode(row) if row is not None else None
def update(
self,
dispatch_id: str,
*,
tenant_id: str,
state: DispatchState | str | None = None,
expected_worker_id: str | None = None,
result_digest: str | None = None,
) -> DispatchRecord:
current = self.get(dispatch_id, tenant_id=tenant_id)
target = DispatchState(state) if state is not None else current.state
if current.state in TERMINAL_DISPATCH_STATES and target != current.state:
raise DispatchConflict("terminal dispatch cannot transition")
updated = replace(
current,
state=target,
expected_worker_id=(
expected_worker_id if expected_worker_id is not None else current.expected_worker_id
),
result_digest=result_digest or current.result_digest,
updated_at=utc_now(),
completed_at=(utc_now() if target in TERMINAL_DISPATCH_STATES else None),
)
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
connection.execute(
"UPDATE dispatch_records SET payload_json = ?, state = ?, updated_at = ? WHERE dispatch_id = ? AND tenant_id = ?",
(
self._encode(updated),
updated.state.value,
updated.updated_at,
updated.dispatch_id,
updated.tenant_id,
),
)
connection.commit()
return updated
def list(self, *, tenant_id: str) -> list[DispatchRecord]:
with self._lock, self._connect() as connection:
rows = connection.execute(
"SELECT payload_json FROM dispatch_records WHERE tenant_id = ? ORDER BY updated_at, dispatch_id",
(_required(tenant_id, "tenant_id"),),
).fetchall()
return [self._decode(row) for row in rows]
@@ -0,0 +1,543 @@
"""Portable multi-provider execution plans and aggregate release gates.
A plan is a DAG of executor-neutral stages. Only root stages are declared at
plan creation. A dependent stage is declared atomically after every dependency
passes its Truth + notification gate, so its start deadline cannot expire while
it is legitimately waiting for upstream work.
"""
from __future__ import annotations
import json
import sqlite3
import threading
from dataclasses import asdict, dataclass, field
from pathlib import Path
from typing import Any, Mapping, Sequence
from .executor_protocol import ExecutorProviderRegistry, normalize_executor
from .external_task_control import ExternalTaskCoordinator
from .external_task_query import list_records
from .task_execution_registry import (
ExecutionTaskManifest,
ExecutionTruthRecord,
ExecutionTruthState,
required,
utc_now,
)
PLAN_SCHEMA_VERSION = "aios.execution-plan.v2"
WAITING_DEPENDENCY = "WAITING_DEPENDENCY"
@dataclass(frozen=True)
class ExecutionStageManifest:
stage_id: str
task_id: str
executor_type: str
role: str
steps: Sequence[str]
depends_on: Sequence[str] = ()
required_evidence: Sequence[str] = ()
notification_events: Sequence[str] = ("STARTED", "SUCCEEDED", "FAILED")
owner_notification_ref: str = "AIOS_OWNER_WECHAT_TARGET_REF"
start_deadline_seconds: int = 300
heartbeat_timeout_seconds: int = 180
required: bool = True
metadata: Mapping[str, Any] = field(default_factory=dict)
def __post_init__(self) -> None:
for name in ("stage_id", "task_id", "role", "owner_notification_ref"):
object.__setattr__(self, name, required(getattr(self, name), name))
object.__setattr__(self, "executor_type", normalize_executor(self.executor_type))
steps = tuple(required(item, "step") for item in self.steps)
if not steps:
raise ValueError("execution stage requires at least one step")
object.__setattr__(self, "steps", steps)
object.__setattr__(
self,
"depends_on",
tuple(sorted({required(item, "depends_on") for item in self.depends_on})),
)
object.__setattr__(
self,
"required_evidence",
tuple(sorted({required(item, "required_evidence") for item in self.required_evidence})),
)
object.__setattr__(
self,
"notification_events",
tuple(sorted({required(item, "notification_event") for item in self.notification_events})),
)
if self.start_deadline_seconds < 1 or self.heartbeat_timeout_seconds < 1:
raise ValueError("stage deadlines must be positive")
object.__setattr__(
self,
"metadata",
json.loads(json.dumps(dict(self.metadata), ensure_ascii=False, default=str)),
)
def as_dict(self) -> dict[str, Any]:
value = asdict(self)
value["steps"] = list(self.steps)
value["depends_on"] = list(self.depends_on)
value["required_evidence"] = list(self.required_evidence)
value["notification_events"] = list(self.notification_events)
return value
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "ExecutionStageManifest":
return cls(**dict(value))
@dataclass(frozen=True)
class ExecutionPlanManifest:
plan_id: str
source_branch: str
source_oid: str
target_version: str
stages: Sequence[ExecutionStageManifest]
release_gate_policy: str = "all_required_stages"
schema_version: str = PLAN_SCHEMA_VERSION
metadata: Mapping[str, Any] = field(default_factory=dict)
def __post_init__(self) -> None:
for name in ("plan_id", "source_branch", "source_oid", "target_version"):
object.__setattr__(self, name, required(getattr(self, name), name))
if self.schema_version != PLAN_SCHEMA_VERSION:
raise ValueError("unsupported execution plan schema")
if self.release_gate_policy != "all_required_stages":
raise ValueError("unsupported release gate policy")
stages = tuple(self.stages)
if not stages:
raise ValueError("execution plan requires stages")
stage_ids = [item.stage_id for item in stages]
task_ids = [item.task_id for item in stages]
if len(stage_ids) != len(set(stage_ids)):
raise ValueError("execution plan stage_id values must be unique")
if len(task_ids) != len(set(task_ids)):
raise ValueError("execution plan task_id values must be unique")
known = set(stage_ids)
for stage in stages:
unknown = sorted(set(stage.depends_on) - known)
if unknown:
raise ValueError(f"stage {stage.stage_id} has unknown dependencies: {unknown}")
if stage.stage_id in stage.depends_on:
raise ValueError("stage cannot depend on itself")
self._assert_acyclic(stages)
object.__setattr__(self, "stages", stages)
object.__setattr__(
self,
"metadata",
json.loads(json.dumps(dict(self.metadata), ensure_ascii=False, default=str)),
)
@staticmethod
def _assert_acyclic(stages: Sequence[ExecutionStageManifest]) -> None:
dependencies = {item.stage_id: set(item.depends_on) for item in stages}
resolved: set[str] = set()
while len(resolved) < len(stages):
ready = {
stage_id
for stage_id, deps in dependencies.items()
if stage_id not in resolved and deps.issubset(resolved)
}
if not ready:
raise ValueError("execution plan contains a dependency cycle")
resolved.update(ready)
def as_dict(self) -> dict[str, Any]:
return {
"schema_version": self.schema_version,
"plan_id": self.plan_id,
"source_branch": self.source_branch,
"source_oid": self.source_oid,
"target_version": self.target_version,
"release_gate_policy": self.release_gate_policy,
"stages": [item.as_dict() for item in self.stages],
"metadata": dict(self.metadata),
}
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "ExecutionPlanManifest":
raw = dict(value)
raw["stages"] = tuple(
ExecutionStageManifest.from_dict(item) for item in raw.get("stages") or ()
)
return cls(**raw)
def stage(self, stage_id: str) -> ExecutionStageManifest:
normalized = required(stage_id, "stage_id")
for stage in self.stages:
if stage.stage_id == normalized:
return stage
raise KeyError(f"execution stage not found: {normalized}")
class SQLiteExecutionPlanStore:
"""Durable plan declarations; stage state remains in Truth Registry."""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
with self._connect() as connection:
connection.executescript(
"""
CREATE TABLE IF NOT EXISTS execution_plans (
plan_id TEXT PRIMARY KEY,
manifest_json TEXT NOT NULL,
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
);
"""
)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(str(self.path), timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
return connection
@staticmethod
def _encode(plan: ExecutionPlanManifest) -> str:
return json.dumps(
plan.as_dict(),
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
)
def save(
self,
plan: ExecutionPlanManifest,
*,
allow_source_oid_supersession: bool = False,
) -> None:
payload = self._encode(plan)
now = utc_now()
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
existing = connection.execute(
"SELECT manifest_json FROM execution_plans WHERE plan_id = ?",
(plan.plan_id,),
).fetchone()
if existing is not None:
if existing["manifest_json"] != payload:
previous = json.loads(existing["manifest_json"])
replacement = plan.as_dict()
previous_oid = previous.pop("source_oid", None)
replacement_oid = replacement.pop("source_oid", None)
if (
not allow_source_oid_supersession
or previous != replacement
or previous_oid == replacement_oid
):
connection.rollback()
raise RuntimeError(
"plan_id already exists with another manifest"
)
connection.execute(
"UPDATE execution_plans SET manifest_json = ?, updated_at = ? WHERE plan_id = ?",
(payload, now, plan.plan_id),
)
connection.commit()
return
connection.rollback()
return
connection.execute(
"INSERT INTO execution_plans VALUES (?, ?, ?, ?)",
(plan.plan_id, payload, now, now),
)
connection.commit()
def get(self, plan_id: str) -> ExecutionPlanManifest:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT manifest_json FROM execution_plans WHERE plan_id = ?",
(required(plan_id, "plan_id"),),
).fetchone()
if row is None:
raise KeyError("execution plan not found")
value = json.loads(row["manifest_json"])
if not isinstance(value, Mapping):
raise ValueError("stored execution plan is invalid")
return ExecutionPlanManifest.from_dict(value)
def list(self) -> list[ExecutionPlanManifest]:
with self._lock, self._connect() as connection:
rows = connection.execute(
"SELECT manifest_json FROM execution_plans ORDER BY created_at, plan_id"
).fetchall()
return [
ExecutionPlanManifest.from_dict(json.loads(row["manifest_json"]))
for row in rows
]
class ExecutionPlanCoordinator:
"""Declares dependency-ready stages and evaluates aggregate release gates."""
def __init__(
self,
*,
task_coordinator: ExternalTaskCoordinator,
plan_store: SQLiteExecutionPlanStore,
providers: ExecutorProviderRegistry,
) -> None:
self.task_coordinator = task_coordinator
self.plan_store = plan_store
self.providers = providers
@classmethod
def from_file(
cls,
path: str | Path,
*,
providers: ExecutorProviderRegistry,
) -> "ExecutionPlanCoordinator":
return cls(
task_coordinator=ExternalTaskCoordinator.from_file(path),
plan_store=SQLiteExecutionPlanStore(path),
providers=providers,
)
@staticmethod
def _task_manifest(
plan: ExecutionPlanManifest,
stage: ExecutionStageManifest,
) -> ExecutionTaskManifest:
return ExecutionTaskManifest(
task_id=stage.task_id,
executor=stage.executor_type,
source_branch=plan.source_branch,
source_oid=plan.source_oid,
target_version=plan.target_version,
steps=stage.steps,
start_deadline_seconds=stage.start_deadline_seconds,
heartbeat_timeout_seconds=stage.heartbeat_timeout_seconds,
required_evidence=stage.required_evidence,
notification_events=stage.notification_events,
owner_notification_ref=stage.owner_notification_ref,
manifest_version="aios.external-task.v2",
)
def _record(self, task_id: str) -> ExecutionTruthRecord | None:
try:
return self.task_coordinator.registry.get(task_id)
except KeyError:
return None
def _declare_stage(
self,
plan: ExecutionPlanManifest,
stage: ExecutionStageManifest,
) -> ExecutionTruthRecord:
self.providers.validate_manifest(self._task_manifest(plan, stage))
return self.task_coordinator.declare(self._task_manifest(plan, stage))
def declare(self, plan: ExecutionPlanManifest) -> Mapping[str, Any]:
for stage in plan.stages:
self.providers.get(stage.executor_type)
allow_source_oid_supersession = False
try:
previous = self.plan_store.get(plan.plan_id)
except KeyError:
previous = None
if previous is not None and previous.source_oid != plan.source_oid:
previous_value = previous.as_dict()
replacement_value = plan.as_dict()
previous_value.pop("source_oid")
replacement_value.pop("source_oid")
root_records = [
self._record(stage.task_id)
for stage in previous.stages
if not stage.depends_on
]
allow_source_oid_supersession = bool(
previous_value == replacement_value
and root_records
and all(
record is not None
and record.state == ExecutionTruthState.NOT_STARTED
for record in root_records
)
)
self.plan_store.save(
plan,
allow_source_oid_supersession=allow_source_oid_supersession,
)
for stage in plan.stages:
if not stage.depends_on:
self._declare_stage(plan, stage)
return self.snapshot(plan.plan_id)
def declare_file(self, path: str | Path) -> Mapping[str, Any]:
value = json.loads(Path(path).read_text(encoding="utf-8"))
if not isinstance(value, Mapping):
raise ValueError("execution plan file must contain a JSON object")
return self.declare(ExecutionPlanManifest.from_dict(value))
def dependency_gate(self, plan_id: str, stage_id: str) -> Mapping[str, Any]:
plan = self.plan_store.get(plan_id)
stage = plan.stage(stage_id)
dependencies: list[Mapping[str, Any]] = []
passed = True
for dependency_id in stage.depends_on:
dependency = plan.stage(dependency_id)
record = self._record(dependency.task_id)
if record is None:
gate: Mapping[str, Any] = {
"task_id": dependency.task_id,
"state": WAITING_DEPENDENCY,
"passed": False,
"release_blocking": True,
}
else:
gate = self.task_coordinator.gate(dependency.task_id)
dependencies.append(
{
"stage_id": dependency.stage_id,
"task_id": dependency.task_id,
"gate": gate,
}
)
if not gate["passed"]:
passed = False
return {
"plan_id": plan.plan_id,
"stage_id": stage.stage_id,
"passed": passed,
"release_blocking": not passed,
"dependencies": dependencies,
}
def activate_ready(self, plan_id: str) -> list[Mapping[str, Any]]:
plan = self.plan_store.get(plan_id)
activated: list[Mapping[str, Any]] = []
for stage in plan.stages:
if self._record(stage.task_id) is not None:
continue
dependency = self.dependency_gate(plan.plan_id, stage.stage_id)
if not dependency["passed"]:
continue
record = self._declare_stage(plan, stage)
activated.append(
{
"stage_id": stage.stage_id,
"task_id": record.task_id,
"executor_type": stage.executor_type,
"state": record.state.value,
}
)
return activated
def discover_ready(
self,
*,
plan_id: str,
executor_type: str,
) -> list[Mapping[str, Any]]:
plan = self.plan_store.get(plan_id)
self.activate_ready(plan.plan_id)
normalized = normalize_executor(executor_type)
records = {
item.task_id: item
for item in list_records(
self.task_coordinator.registry.path,
executor=normalized,
states=(
ExecutionTruthState.DECLARED.value,
ExecutionTruthState.REGISTERED.value,
),
)
}
ready: list[Mapping[str, Any]] = []
for stage in plan.stages:
if stage.executor_type != normalized or stage.task_id not in records:
continue
dependency = self.dependency_gate(plan.plan_id, stage.stage_id)
if dependency["passed"]:
ready.append(
{
"plan_id": plan.plan_id,
"stage": stage.as_dict(),
"record": records[stage.task_id].as_dict(),
}
)
return ready
def snapshot(self, plan_id: str) -> Mapping[str, Any]:
plan = self.plan_store.get(plan_id)
stages: list[Mapping[str, Any]] = []
for stage in plan.stages:
record = self._record(stage.task_id)
dependency = self.dependency_gate(plan.plan_id, stage.stage_id)
if record is None:
truth: Mapping[str, Any] = {
"task_id": stage.task_id,
"state": WAITING_DEPENDENCY,
"passed": False,
"release_blocking": True,
"executor_run_id": None,
"executor_id": None,
"current_step": 0,
"total_steps": len(stage.steps),
"evidence": {},
"error": {},
"notifications": [],
}
else:
truth = self.task_coordinator.status(stage.task_id)
stages.append(
{
"stage": stage.as_dict(),
"dependency_gate": dependency,
"truth": truth,
}
)
return {
"manifest": plan.as_dict(),
"stages": stages,
}
def gate(self, plan_id: str) -> Mapping[str, Any]:
plan = self.plan_store.get(plan_id)
self.activate_ready(plan.plan_id)
stages: list[Mapping[str, Any]] = []
required_passed = True
for stage in plan.stages:
dependency = self.dependency_gate(plan.plan_id, stage.stage_id)
record = self._record(stage.task_id)
if record is None:
truth_gate: Mapping[str, Any] = {
"task_id": stage.task_id,
"state": WAITING_DEPENDENCY,
"passed": False,
"release_blocking": True,
}
else:
truth_gate = self.task_coordinator.gate(stage.task_id)
stage_passed = bool(truth_gate["passed"] and dependency["passed"])
if stage.required and not stage_passed:
required_passed = False
stages.append(
{
"stage_id": stage.stage_id,
"task_id": stage.task_id,
"executor_type": stage.executor_type,
"role": stage.role,
"required": stage.required,
"passed": stage_passed,
"truth_gate": truth_gate,
"dependency_gate": dependency,
}
)
return {
"plan_id": plan.plan_id,
"target_version": plan.target_version,
"policy": plan.release_gate_policy,
"passed": required_passed,
"release_blocking": not required_passed,
"stages": stages,
}
@@ -0,0 +1,323 @@
"""AIOS V2 Agent 执行证据。
Evidence 按租户隔离并使用原子 JSON 写入。生产模式下,claim、heartbeat
和 complete 在落盘前必须通过最小权限 Evidence Grant 授权。
"""
from __future__ import annotations
import json
import os
import threading
from dataclasses import asdict, dataclass, field, replace
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Mapping, Protocol
from .provenance import ProvenanceDenied, digest_payload
class EvidenceAuthorizationWriter(Protocol):
def authorize_evidence_write(self, **values: Any) -> Any: ...
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def _required(value: str, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
def _safe(value: Mapping[str, Any] | None) -> dict[str, Any]:
return json.loads(json.dumps(dict(value or {}), ensure_ascii=False, default=str))
@dataclass(frozen=True)
class ExecutionEvidence:
execution_id: str
tenant_id: str
task_id: str
agent_id: str
executor: str
branch: str
status: str = "claimed"
progress_completed: int = 0
progress_total: int = 1
current_step: str = "claim"
last_commit: str | None = None
test_status: str = "not_run"
test_summary: Mapping[str, Any] = field(default_factory=dict)
result_summary: Mapping[str, Any] = field(default_factory=dict)
claimed_at: str = field(default_factory=utc_now)
heartbeat_at: str = field(default_factory=utc_now)
completed_at: str | None = None
provenance_id: str | None = None
run_id: str | None = None
last_authorization_id: str | None = None
def __post_init__(self) -> None:
for name in (
"execution_id",
"tenant_id",
"task_id",
"agent_id",
"executor",
"branch",
"status",
"current_step",
"claimed_at",
"heartbeat_at",
):
object.__setattr__(self, name, _required(getattr(self, name), name))
if self.progress_completed < 0 or self.progress_total < 1:
raise ValueError("invalid progress values")
if self.progress_completed > self.progress_total:
raise ValueError("progress_completed cannot exceed progress_total")
object.__setattr__(self, "test_summary", _safe(self.test_summary))
object.__setattr__(self, "result_summary", _safe(self.result_summary))
for optional in ("provenance_id", "run_id", "last_authorization_id"):
value = getattr(self, optional)
object.__setattr__(self, optional, str(value).strip() if value else None)
class ExecutionTracker:
"""每个租户、每次执行持久保存一份证据记录。"""
def __init__(
self,
root: str | Path,
*,
provenance_writer: EvidenceAuthorizationWriter | None = None,
require_provenance: bool = False,
) -> None:
self.root = Path(root).resolve()
self.root.mkdir(parents=True, exist_ok=True)
self.provenance_writer = provenance_writer
self.require_provenance = bool(require_provenance)
if self.require_provenance and self.provenance_writer is None:
raise ValueError("production evidence tracking requires a provenance writer")
self._lock = threading.RLock()
@staticmethod
def _component(value: str) -> str:
normalized = _required(value, "path component")
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
raise ValueError("invalid evidence path component")
return normalized
def _path(self, tenant_id: str, execution_id: str) -> Path:
tenant = self._component(tenant_id)
execution = self._component(execution_id)
return self.root / tenant / f"{execution}.json"
def _authorize(
self,
evidence: ExecutionEvidence,
*,
operation: str,
principal_id: str | None,
provenance_id: str | None,
run_id: str | None,
changes: Mapping[str, Any],
) -> str | None:
if not self.require_provenance:
return None
if self.provenance_writer is None:
raise RuntimeError("Run Provenance writer is not configured")
effective_provenance = provenance_id or evidence.provenance_id
effective_run = run_id or evidence.run_id
if not effective_provenance or not effective_run or not principal_id:
raise RuntimeError(
"production evidence write requires provenance_id, run_id and principal_id"
)
request_digest = digest_payload(
{
"operation": operation,
"execution_id": evidence.execution_id,
"tenant_id": evidence.tenant_id,
"task_id": evidence.task_id,
"agent_id": evidence.agent_id,
"executor": evidence.executor,
"branch": evidence.branch,
"changes": dict(changes),
}
)
try:
authorization = self.provenance_writer.authorize_evidence_write(
provenance_id=effective_provenance,
run_id=effective_run,
tenant_id=evidence.tenant_id,
task_id=evidence.task_id,
agent_id=evidence.agent_id,
principal_id=principal_id,
request_digest=request_digest,
)
except ProvenanceDenied as exc:
raise RuntimeError(f"Run Provenance denied evidence write: {exc}") from exc
return authorization.authorization_id
def claim(
self,
evidence: ExecutionEvidence,
*,
principal_id: str | None = None,
provenance_id: str | None = None,
run_id: str | None = None,
) -> ExecutionEvidence:
path = self._path(evidence.tenant_id, evidence.execution_id)
with self._lock:
if path.exists():
current = self._read(path)
if current.task_id != evidence.task_id or current.agent_id != evidence.agent_id:
raise RuntimeError("execution_id already belongs to another task")
if self.require_provenance and (
current.provenance_id != (provenance_id or evidence.provenance_id)
or current.run_id != (run_id or evidence.run_id)
):
raise RuntimeError(
"execution_id already belongs to another provenance context"
)
return current
effective_provenance = provenance_id or evidence.provenance_id
effective_run = run_id or evidence.run_id
authorization_id = self._authorize(
evidence,
operation="claim",
principal_id=principal_id,
provenance_id=effective_provenance,
run_id=effective_run,
changes={"status": evidence.status, "current_step": evidence.current_step},
)
persisted = replace(
evidence,
provenance_id=effective_provenance,
run_id=effective_run,
last_authorization_id=authorization_id,
)
self._write(path, persisted)
return persisted
def heartbeat(
self,
*,
tenant_id: str,
execution_id: str,
status: str | None = None,
current_step: str | None = None,
progress_completed: int | None = None,
progress_total: int | None = None,
last_commit: str | None = None,
principal_id: str | None = None,
provenance_id: str | None = None,
run_id: str | None = None,
) -> ExecutionEvidence:
path = self._path(tenant_id, execution_id)
with self._lock:
current = self._read(path)
changes = {
"status": status or current.status,
"current_step": current_step or current.current_step,
"progress_completed": (
progress_completed
if progress_completed is not None
else current.progress_completed
),
"progress_total": (
progress_total if progress_total is not None else current.progress_total
),
"last_commit": last_commit or current.last_commit,
}
authorization_id = self._authorize(
current,
operation="heartbeat",
principal_id=principal_id,
provenance_id=provenance_id,
run_id=run_id,
changes=changes,
)
updated = replace(
current,
**changes,
last_authorization_id=authorization_id or current.last_authorization_id,
heartbeat_at=utc_now(),
)
self._write(path, updated)
return updated
def complete(
self,
*,
tenant_id: str,
execution_id: str,
status: str,
test_status: str,
test_summary: Mapping[str, Any] | None = None,
result_summary: Mapping[str, Any] | None = None,
last_commit: str | None = None,
principal_id: str | None = None,
provenance_id: str | None = None,
run_id: str | None = None,
) -> ExecutionEvidence:
path = self._path(tenant_id, execution_id)
with self._lock:
current = self._read(path)
changes = {
"status": _required(status, "status"),
"current_step": "complete",
"progress_completed": current.progress_total,
"last_commit": last_commit or current.last_commit,
"test_status": _required(test_status, "test_status"),
"test_summary": _safe(test_summary),
"result_summary": _safe(result_summary),
}
authorization_id = self._authorize(
current,
operation="complete",
principal_id=principal_id,
provenance_id=provenance_id,
run_id=run_id,
changes=changes,
)
updated = replace(
current,
**changes,
last_authorization_id=authorization_id or current.last_authorization_id,
heartbeat_at=utc_now(),
completed_at=utc_now(),
)
self._write(path, updated)
return updated
def get(self, *, tenant_id: str, execution_id: str) -> ExecutionEvidence:
return self._read(self._path(tenant_id, execution_id))
def list(self, *, tenant_id: str) -> list[ExecutionEvidence]:
tenant_dir = self.root / self._component(tenant_id)
if not tenant_dir.exists():
return []
records = [self._read(path) for path in tenant_dir.glob("*.json")]
return sorted(records, key=lambda item: (item.heartbeat_at, item.execution_id), reverse=True)
@staticmethod
def _read(path: Path) -> ExecutionEvidence:
try:
value = json.loads(path.read_text(encoding="utf-8"))
except FileNotFoundError as exc:
raise KeyError("execution evidence not found") from exc
if not isinstance(value, Mapping):
raise RuntimeError("invalid execution evidence file")
return ExecutionEvidence(**dict(value))
@staticmethod
def _write(path: Path, evidence: ExecutionEvidence) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
temporary = path.with_suffix(f".tmp-{os.getpid()}")
temporary.write_text(
json.dumps(asdict(evidence), ensure_ascii=False, sort_keys=True, indent=2) + "\n",
encoding="utf-8",
)
os.chmod(temporary, 0o640)
os.replace(temporary, path)
@@ -0,0 +1,204 @@
"""Persistent and portable AIOS executor provider catalog.
The catalog contains descriptors only: provider names, protocol/adapter versions,
trust roles, capabilities and configuration schema identifiers. Credentials,
endpoints and runtime secrets are intentionally excluded and must be resolved in
the destination environment.
"""
from __future__ import annotations
import hashlib
import json
import os
import threading
from dataclasses import dataclass
from pathlib import Path
from typing import Any, Mapping, Sequence
from .executor_protocol import (
EXECUTOR_PROTOCOL_VERSION,
DescriptorOnlyProvider,
ExecutorProvider,
ExecutorProviderDescriptor,
ExecutorProviderRegistry,
default_provider_registry,
)
CATALOG_SCHEMA_VERSION = "aios.executor.catalog.v1"
MIGRATION_SCHEMA_VERSION = "aios.executor.migration.v1"
def canonical_json_bytes(value: Mapping[str, Any]) -> bytes:
return json.dumps(
dict(value),
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
default=str,
).encode("utf-8")
def sha256_payload(value: Mapping[str, Any]) -> str:
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
@dataclass(frozen=True)
class ExecutorCatalogSnapshot:
catalog: Mapping[str, Any]
catalog_sha256: str
path: str
def as_dict(self) -> dict[str, Any]:
return {
"catalog": dict(self.catalog),
"catalog_sha256": self.catalog_sha256,
"path": self.path,
}
class FileExecutorCatalogStore:
"""Atomic file store for provider descriptors and migration packages."""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
@staticmethod
def _validate_catalog(value: Mapping[str, Any]) -> ExecutorProviderRegistry:
if value.get("schema_version") != CATALOG_SCHEMA_VERSION:
raise ValueError("unsupported executor catalog schema")
if value.get("protocol_version") != EXECUTOR_PROTOCOL_VERSION:
raise ValueError("executor catalog protocol mismatch")
providers = value.get("providers")
if not isinstance(providers, Sequence) or isinstance(providers, (str, bytes)):
raise ValueError("executor catalog providers must be an array")
return ExecutorProviderRegistry.import_catalog(value)
def initialize_defaults(self) -> ExecutorCatalogSnapshot:
with self._lock:
if self.path.exists():
return self.load()
return self.save(default_provider_registry())
def load(self) -> ExecutorCatalogSnapshot:
with self._lock:
value = json.loads(self.path.read_text(encoding="utf-8"))
if not isinstance(value, Mapping):
raise ValueError("executor catalog must contain a JSON object")
registry = self._validate_catalog(value)
normalized = registry.export_catalog()
return ExecutorCatalogSnapshot(
catalog=normalized,
catalog_sha256=sha256_payload(normalized),
path=str(self.path),
)
def registry(
self,
*,
provider_factories: Mapping[str, ExecutorProvider] | None = None,
) -> ExecutorProviderRegistry:
snapshot = self.load()
return ExecutorProviderRegistry.import_catalog(
snapshot.catalog,
provider_factories=provider_factories,
)
def save(self, registry: ExecutorProviderRegistry) -> ExecutorCatalogSnapshot:
catalog = registry.export_catalog()
self._validate_catalog(catalog)
encoded = json.dumps(
catalog,
ensure_ascii=False,
sort_keys=True,
indent=2,
) + "\n"
with self._lock:
temporary = self.path.with_suffix(f".tmp-{os.getpid()}")
temporary.write_text(encoded, encoding="utf-8")
os.chmod(temporary, 0o640)
os.replace(temporary, self.path)
return ExecutorCatalogSnapshot(
catalog=catalog,
catalog_sha256=sha256_payload(catalog),
path=str(self.path),
)
def upsert_descriptor(
self,
descriptor: ExecutorProviderDescriptor,
) -> ExecutorCatalogSnapshot:
with self._lock:
if self.path.exists():
registry = self.registry()
else:
registry = default_provider_registry()
try:
registry.register(DescriptorOnlyProvider(descriptor), replace=True)
except KeyError:
registry.register(DescriptorOnlyProvider(descriptor))
return self.save(registry)
def export_migration_package(
self,
*,
source_environment: str,
required_executor_types: Sequence[str] = (),
) -> Mapping[str, Any]:
snapshot = self.load()
registry = ExecutorProviderRegistry.import_catalog(snapshot.catalog)
required = tuple(sorted({str(item).strip().lower() for item in required_executor_types if str(item).strip()}))
if required:
available = {item.executor_type for item in registry.list_descriptors()}
missing = sorted(set(required) - available)
if missing:
raise ValueError(f"migration package is missing providers: {missing}")
package = {
"schema_version": MIGRATION_SCHEMA_VERSION,
"source_environment": str(source_environment or "").strip(),
"catalog": snapshot.catalog,
"catalog_sha256": snapshot.catalog_sha256,
"required_executor_types": list(required),
"secret_values_included": False,
}
if not package["source_environment"]:
raise ValueError("source_environment is required")
return {
**package,
"package_sha256": sha256_payload(package),
}
@classmethod
def import_migration_package(
cls,
value: Mapping[str, Any],
*,
destination_path: str | Path,
destination_environment: str,
provider_factories: Mapping[str, ExecutorProvider] | None = None,
) -> ExecutorCatalogSnapshot:
if value.get("schema_version") != MIGRATION_SCHEMA_VERSION:
raise ValueError("unsupported executor migration schema")
if value.get("secret_values_included") is not False:
raise ValueError("executor migration package must not contain secrets")
package_without_hash = {key: item for key, item in value.items() if key != "package_sha256"}
if sha256_payload(package_without_hash) != value.get("package_sha256"):
raise ValueError("executor migration package hash mismatch")
catalog = value.get("catalog")
if not isinstance(catalog, Mapping):
raise ValueError("executor migration package has no catalog")
if sha256_payload(catalog) != value.get("catalog_sha256"):
raise ValueError("executor catalog hash mismatch")
registry = ExecutorProviderRegistry.import_catalog(
catalog,
provider_factories=provider_factories,
)
required = tuple(value.get("required_executor_types") or ())
available = {item.executor_type for item in registry.list_descriptors()}
missing = sorted(set(required) - available)
if missing:
raise ValueError(f"destination provider factories are missing: {missing}")
if not str(destination_environment or "").strip():
raise ValueError("destination_environment is required")
return cls(destination_path).save(registry)
@@ -0,0 +1,441 @@
"""Versioned, extensible executor protocol for AIOS external tasks.
The core lifecycle is executor-neutral. OpenClaw, Hermes, Codex and the scoped
ChatGPT supervisor are built-in
providers, not hard-coded protocol branches. Future providers register a
versioned descriptor and use the same Truth Registry, evidence, notification
and release-gate mechanisms without modifying the lifecycle state machine.
"""
from __future__ import annotations
import json
import re
import threading
from dataclasses import asdict, dataclass, field
from typing import Any, Mapping, Protocol, Sequence
from .external_task_control import ExternalTaskCoordinator
from .task_execution_registry import ExecutionTaskManifest, ExecutionTruthRecord
EXECUTOR_PROTOCOL_VERSION = "aios.executor.v1"
_PROVIDER_NAME = re.compile(r"^[a-z][a-z0-9._-]{1,63}$")
_VERSION = re.compile(r"^[0-9]+(?:\.[0-9]+){0,2}(?:[-+][A-Za-z0-9._-]+)?$")
DISCOVERABLE_STATES: Sequence[str] = ("DECLARED", "REGISTERED")
def normalize_executor(value: str) -> str:
normalized = str(value or "").strip().lower()
if not _PROVIDER_NAME.fullmatch(normalized):
raise ValueError("executor type must be a lowercase provider identifier")
return normalized
def _major(version: str) -> int:
normalized = str(version or "").strip()
if not _VERSION.fullmatch(normalized):
raise ValueError(f"invalid version: {version}")
return int(normalized.split(".", 1)[0])
@dataclass(frozen=True)
class ExecutorProviderDescriptor:
"""Portable provider metadata stored without credentials or runtime secrets."""
executor_type: str
adapter_version: str
protocol_version: str = EXECUTOR_PROTOCOL_VERSION
trust_roles: Sequence[str] = ()
capabilities: Sequence[str] = ()
configuration_schema: str = "aios.executor.config.v1"
portable: bool = True
metadata: Mapping[str, Any] = field(default_factory=dict)
def __post_init__(self) -> None:
object.__setattr__(self, "executor_type", normalize_executor(self.executor_type))
adapter_version = str(self.adapter_version or "").strip()
if not _VERSION.fullmatch(adapter_version):
raise ValueError("adapter_version must be version-like")
object.__setattr__(self, "adapter_version", adapter_version)
protocol_version = str(self.protocol_version or "").strip()
if not protocol_version.startswith("aios.executor.v"):
raise ValueError("unsupported executor protocol namespace")
int(protocol_version.rsplit("v", 1)[1])
object.__setattr__(self, "protocol_version", protocol_version)
roles = tuple(sorted({str(item).strip() for item in self.trust_roles if str(item).strip()}))
if not roles:
raise ValueError("provider must declare at least one trust role")
capabilities = tuple(
sorted({str(item).strip() for item in self.capabilities if str(item).strip()})
)
object.__setattr__(self, "trust_roles", roles)
object.__setattr__(self, "capabilities", capabilities)
object.__setattr__(
self,
"configuration_schema",
str(self.configuration_schema or "").strip(),
)
object.__setattr__(
self,
"metadata",
json.loads(json.dumps(dict(self.metadata), ensure_ascii=False, default=str)),
)
def as_dict(self) -> dict[str, Any]:
value = asdict(self)
value["trust_roles"] = list(self.trust_roles)
value["capabilities"] = list(self.capabilities)
return value
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "ExecutorProviderDescriptor":
return cls(**dict(value))
def protocol_compatible_with(self, other: "ExecutorProviderDescriptor") -> bool:
return (
self.executor_type == other.executor_type
and self.protocol_version == other.protocol_version
and _major(self.adapter_version) == _major(other.adapter_version)
)
class ExternalExecutorAdapter(Protocol):
"""Runtime-specific implementation behind the common lifecycle."""
descriptor: ExecutorProviderDescriptor
def discover(self) -> Sequence[ExecutionTruthRecord]: ...
def execute(self, manifest: ExecutionTaskManifest) -> Mapping[str, Any]: ...
def notify_owner(self, payload: Mapping[str, Any]) -> str: ...
class ExecutorProvider(Protocol):
descriptor: ExecutorProviderDescriptor
def validate_manifest(self, manifest: ExecutionTaskManifest) -> None: ...
def build_adapter(self, configuration: Mapping[str, Any]) -> ExternalExecutorAdapter: ...
class DescriptorOnlyProvider:
"""Default provider used when lifecycle integration is supplied externally."""
def __init__(self, descriptor: ExecutorProviderDescriptor) -> None:
self.descriptor = descriptor
def validate_manifest(self, manifest: ExecutionTaskManifest) -> None:
if normalize_executor(manifest.executor) != self.descriptor.executor_type:
raise ValueError("manifest executor does not match provider")
def build_adapter(self, configuration: Mapping[str, Any]) -> ExternalExecutorAdapter:
raise RuntimeError(
f"provider {self.descriptor.executor_type} requires an external adapter factory"
)
class ExecutorProviderRegistry:
"""Thread-safe registry supporting runtime registration and catalog migration."""
def __init__(self, providers: Sequence[ExecutorProvider] = ()) -> None:
self._lock = threading.RLock()
self._providers: dict[str, ExecutorProvider] = {}
for provider in providers:
self.register(provider)
def register(self, provider: ExecutorProvider, *, replace: bool = False) -> None:
descriptor = provider.descriptor
key = normalize_executor(descriptor.executor_type)
with self._lock:
current = self._providers.get(key)
if current is not None and not replace:
raise ValueError(f"executor provider already registered: {key}")
if current is not None and not descriptor.protocol_compatible_with(
current.descriptor
):
raise ValueError(
f"replacement provider is incompatible with registered provider: {key}"
)
self._providers[key] = provider
def unregister(self, executor_type: str) -> ExecutorProvider:
key = normalize_executor(executor_type)
with self._lock:
try:
return self._providers.pop(key)
except KeyError as exc:
raise KeyError(f"executor provider is not registered: {key}") from exc
def get(self, executor_type: str) -> ExecutorProvider:
key = normalize_executor(executor_type)
with self._lock:
provider = self._providers.get(key)
if provider is None:
raise KeyError(f"executor provider is not registered: {key}")
return provider
def descriptor(self, executor_type: str) -> ExecutorProviderDescriptor:
return self.get(executor_type).descriptor
def validate_manifest(self, manifest: ExecutionTaskManifest) -> None:
self.get(manifest.executor).validate_manifest(manifest)
def trusted(
self,
*,
executor_type: str,
roles: Sequence[str],
platform_admin: bool = False,
) -> bool:
if platform_admin or "platform_admin" in set(roles):
return True
descriptor = self.descriptor(executor_type)
return bool(set(descriptor.trust_roles).intersection(set(roles)))
def list_descriptors(self) -> tuple[ExecutorProviderDescriptor, ...]:
with self._lock:
return tuple(
self._providers[key].descriptor for key in sorted(self._providers)
)
def export_catalog(self) -> Mapping[str, Any]:
return {
"schema_version": "aios.executor.catalog.v1",
"protocol_version": EXECUTOR_PROTOCOL_VERSION,
"providers": [item.as_dict() for item in self.list_descriptors()],
}
@classmethod
def import_catalog(
cls,
value: Mapping[str, Any],
*,
provider_factories: Mapping[str, ExecutorProvider] | None = None,
) -> "ExecutorProviderRegistry":
if value.get("schema_version") != "aios.executor.catalog.v1":
raise ValueError("unsupported executor catalog schema")
if value.get("protocol_version") != EXECUTOR_PROTOCOL_VERSION:
raise ValueError("executor catalog protocol mismatch")
factories = dict(provider_factories or {})
providers: list[ExecutorProvider] = []
for raw in value.get("providers") or ():
descriptor = ExecutorProviderDescriptor.from_dict(raw)
provider = factories.get(descriptor.executor_type)
if provider is not None:
if not provider.descriptor.protocol_compatible_with(descriptor):
raise ValueError(
f"provider factory does not match imported descriptor: {descriptor.executor_type}"
)
providers.append(provider)
else:
providers.append(DescriptorOnlyProvider(descriptor))
return cls(providers)
BUILTIN_PROVIDER_DESCRIPTORS: Sequence[ExecutorProviderDescriptor] = (
ExecutorProviderDescriptor(
executor_type="openclaw",
adapter_version="2.1.0",
trust_roles=("runtime", "openclaw_executor"),
capabilities=(
"deploy",
"http_runtime",
"owner_notification",
"healthcheck",
"rollback",
),
configuration_schema="aios.executor.openclaw.config.v1",
metadata={"official": True},
),
ExecutorProviderDescriptor(
executor_type="hermes",
adapter_version="2.1.0",
trust_roles=("runtime", "hermes_executor"),
capabilities=(
"queue",
"lease",
"worker",
"runtime_validation",
"restart_recovery",
),
configuration_schema="aios.executor.hermes.config.v1",
metadata={"official": True},
),
ExecutorProviderDescriptor(
executor_type="codex",
adapter_version="2.1.0",
trust_roles=("codex", "codex_executor"),
capabilities=("code", "test", "docs", "gitops_patch", "security_review"),
configuration_schema="aios.executor.codex.config.v1",
metadata={"official": True},
),
ExecutorProviderDescriptor(
executor_type="chatgpt-supervisor",
adapter_version="2.1.0",
trust_roles=("chatgpt_supervisor",),
capabilities=(
"acceptance",
"deploy",
"evidence",
"healthcheck",
"rollback",
"wechat_simulation",
),
configuration_schema="aios.executor.chatgpt-supervisor.config.v1",
metadata={"official": True, "production_mutation_allowed": False},
),
)
def default_provider_registry() -> ExecutorProviderRegistry:
return ExecutorProviderRegistry(
[DescriptorOnlyProvider(item) for item in BUILTIN_PROVIDER_DESCRIPTORS]
)
def trusted_for_executor(
*,
executor: str,
roles: Sequence[str],
platform_admin: bool = False,
registry: ExecutorProviderRegistry | None = None,
) -> bool:
return (registry or default_provider_registry()).trusted(
executor_type=executor,
roles=roles,
platform_admin=platform_admin,
)
@dataclass(frozen=True)
class ExecutorIdentity:
executor_type: str
executor_id: str
executor_run_id: str
protocol_version: str = EXECUTOR_PROTOCOL_VERSION
def __post_init__(self) -> None:
object.__setattr__(self, "executor_type", normalize_executor(self.executor_type))
for name in ("executor_id", "executor_run_id"):
value = str(getattr(self, name) or "").strip()
if not value:
raise ValueError(f"{name} is required")
object.__setattr__(self, name, value)
if self.protocol_version != EXECUTOR_PROTOCOL_VERSION:
raise ValueError("executor identity protocol mismatch")
class ExecutorLifecycleSession:
"""Executor-neutral lifecycle facade used by every registered provider."""
def __init__(
self,
coordinator: ExternalTaskCoordinator,
identity: ExecutorIdentity,
*,
registry: ExecutorProviderRegistry | None = None,
) -> None:
self.coordinator = coordinator
self.identity = identity
self.registry = registry or default_provider_registry()
self.registry.get(identity.executor_type)
def _assert_manifest(self, task_id: str) -> ExecutionTaskManifest:
record = self.coordinator.registry.get(task_id)
manifest = record.manifest
self.registry.validate_manifest(manifest)
if normalize_executor(manifest.executor) != self.identity.executor_type:
raise PermissionError(
f"task executor is {manifest.executor}, not {self.identity.executor_type}"
)
return manifest
def register(self, task_id: str) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.register(
task_id,
executor_run_id=self.identity.executor_run_id,
)
def retry_not_started(self, task_id: str) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.retry_not_started(
task_id,
executor_run_id=self.identity.executor_run_id,
)
def claim(self, task_id: str) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.claim(
task_id,
executor_run_id=self.identity.executor_run_id,
executor_id=self.identity.executor_id,
)
def start(self, task_id: str) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.start(
task_id,
executor_run_id=self.identity.executor_run_id,
executor_id=self.identity.executor_id,
)
def heartbeat(self, task_id: str, *, current_step: int) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.heartbeat(
task_id,
executor_run_id=self.identity.executor_run_id,
executor_id=self.identity.executor_id,
current_step=current_step,
)
def succeed(
self,
task_id: str,
*,
evidence: Mapping[str, str],
) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.succeed(
task_id,
executor_run_id=self.identity.executor_run_id,
executor_id=self.identity.executor_id,
evidence=evidence,
)
def fail(
self,
task_id: str,
*,
error: Mapping[str, Any],
evidence: Mapping[str, str] | None = None,
) -> ExecutionTruthRecord:
self._assert_manifest(task_id)
return self.coordinator.fail(
task_id,
executor_run_id=self.identity.executor_run_id,
executor_id=self.identity.executor_id,
error=error,
evidence=evidence,
)
class OpenClawExecutorSession(ExecutorLifecycleSession):
def __init__(self, coordinator: ExternalTaskCoordinator, *, executor_id: str, executor_run_id: str) -> None:
super().__init__(
coordinator,
ExecutorIdentity("openclaw", executor_id, executor_run_id),
)
class HermesExecutorSession(ExecutorLifecycleSession):
def __init__(self, coordinator: ExternalTaskCoordinator, *, executor_id: str, executor_run_id: str) -> None:
super().__init__(
coordinator,
ExecutorIdentity("hermes", executor_id, executor_run_id),
)
class CodexExecutorSession(ExecutorLifecycleSession):
def __init__(self, coordinator: ExternalTaskCoordinator, *, executor_id: str, executor_run_id: str) -> None:
super().__init__(
coordinator,
ExecutorIdentity("codex", executor_id, executor_run_id),
)
@@ -0,0 +1,313 @@
"""Provider-neutral worker runtime for AIOS external executors.
Providers implement only step execution and notification delivery. Discovery,
dependency gates, lifecycle truth, heartbeat, evidence validation and durable
notification acknowledgement are identical for every current and future
executor Provider.
"""
from __future__ import annotations
import hashlib
import json
import uuid
from dataclasses import dataclass, field
from typing import Any, Mapping, Protocol, Sequence
from .execution_plan import ExecutionPlanCoordinator, ExecutionStageManifest
from .executor_protocol import (
ExecutorIdentity,
ExecutorLifecycleSession,
ExecutorProviderRegistry,
normalize_executor,
)
from .external_task_control import ExternalTaskCoordinator, NotificationRecord
from .task_execution_registry import ExecutionTruthState
class StepRunner(Protocol):
def run_step(
self,
*,
plan_id: str,
stage: ExecutionStageManifest,
step: str,
step_number: int,
executor_id: str,
executor_run_id: str,
) -> Mapping[str, str]: ...
class NotificationSender(Protocol):
def send(self, notification: NotificationRecord) -> str: ...
@dataclass(frozen=True)
class StageRunResult:
plan_id: str
stage_id: str
task_id: str
executor_type: str
executor_id: str
executor_run_id: str
state: str
evidence: Mapping[str, str] = field(default_factory=dict)
error: Mapping[str, Any] = field(default_factory=dict)
delivered_notifications: Sequence[str] = ()
def as_dict(self) -> dict[str, Any]:
return {
"plan_id": self.plan_id,
"stage_id": self.stage_id,
"task_id": self.task_id,
"executor_type": self.executor_type,
"executor_id": self.executor_id,
"executor_run_id": self.executor_run_id,
"state": self.state,
"evidence": dict(self.evidence),
"error": dict(self.error),
"delivered_notifications": list(self.delivered_notifications),
}
class UnifiedExecutorWorker:
"""Dependency-aware worker shared by every registered Provider."""
def __init__(
self,
*,
plan_coordinator: ExecutionPlanCoordinator,
task_coordinator: ExternalTaskCoordinator,
providers: ExecutorProviderRegistry,
executor_type: str,
executor_id: str,
step_runner: StepRunner,
notification_sender: NotificationSender,
) -> None:
self.plan_coordinator = plan_coordinator
self.task_coordinator = task_coordinator
self.providers = providers
self.executor_type = normalize_executor(executor_type)
self.executor_id = str(executor_id or "").strip()
if not self.executor_id:
raise ValueError("executor_id is required")
self.providers.get(self.executor_type)
self.step_runner = step_runner
self.notification_sender = notification_sender
def _session(self, executor_run_id: str) -> ExecutorLifecycleSession:
return ExecutorLifecycleSession(
self.task_coordinator,
ExecutorIdentity(
executor_type=self.executor_type,
executor_id=self.executor_id,
executor_run_id=executor_run_id,
),
registry=self.providers,
)
def _notification_candidates(self, task_id: str) -> tuple[NotificationRecord, ...]:
"""Return idempotent delivery candidates, including prior failures.
The outbox has a unique ``(task_id, event_type)`` key. Retrying therefore
reuses the same notification ID and cannot create duplicate STARTED or
SUCCEEDED events. A later successful acknowledgement replaces FAILED
with DELIVERED and records the receipt hash.
"""
candidates: dict[str, NotificationRecord] = {}
for status in ("PENDING", "FAILED"):
for item in self.task_coordinator.notifications.list(
task_id=task_id,
status=status,
):
candidates[item.notification_id] = item
return tuple(
candidates[key]
for key in sorted(
candidates,
key=lambda item: (
candidates[item].created_at,
candidates[item].notification_id,
),
)
)
def _deliver_notifications(self, task_id: str) -> tuple[str, ...]:
delivered: list[str] = []
for item in self._notification_candidates(task_id):
try:
receipt = self.notification_sender.send(item)
acknowledged = self.task_coordinator.notifications.acknowledge(
item.notification_id,
receipt_sha256=receipt,
)
delivered.append(acknowledged.event_type)
except Exception as exc:
self.task_coordinator.notifications.fail(
item.notification_id,
error=f"{type(exc).__name__}: {exc}",
)
return tuple(sorted(set(delivered)))
def retry_failed_notifications(self, *, task_id: str) -> tuple[str, ...]:
"""Retry failed owner notifications without changing task truth."""
return self._deliver_notifications(task_id)
def run_ready(
self,
*,
plan_id: str,
max_stages: int = 1,
) -> list[StageRunResult]:
if max_stages < 1:
raise ValueError("max_stages must be positive")
ready = self.plan_coordinator.discover_ready(
plan_id=plan_id,
executor_type=self.executor_type,
)[:max_stages]
return [
self.run_stage(
plan_id=plan_id,
stage_id=item["stage"]["stage_id"],
)
for item in ready
]
def run_stage(
self,
*,
plan_id: str,
stage_id: str,
executor_run_id: str | None = None,
) -> StageRunResult:
plan = self.plan_coordinator.plan_store.get(plan_id)
stage = plan.stage(stage_id)
if stage.executor_type != self.executor_type:
raise PermissionError(
f"stage executor is {stage.executor_type}, not {self.executor_type}"
)
dependency = self.plan_coordinator.dependency_gate(plan_id, stage_id)
if not dependency["passed"]:
raise RuntimeError("stage dependencies are not satisfied")
run_id = executor_run_id or f"{self.executor_type}_run_{uuid.uuid4().hex}"
session = self._session(run_id)
record = self.task_coordinator.registry.get(stage.task_id)
evidence: dict[str, str] = dict(record.evidence)
delivered: list[str] = []
try:
if record.state == ExecutionTruthState.DECLARED:
record = session.register(stage.task_id)
if record.state == ExecutionTruthState.REGISTERED:
record = session.claim(stage.task_id)
if record.state == ExecutionTruthState.CLAIMED:
record = session.start(stage.task_id)
delivered.extend(self._deliver_notifications(stage.task_id))
if record.state != ExecutionTruthState.RUNNING:
raise RuntimeError(
f"stage cannot execute from state {record.state.value}"
)
# Re-running the current step is intentional: Provider steps must be
# idempotent and a crash between side effect and heartbeat cannot be
# safely interpreted as completed work.
start_step = max(1, record.current_step)
for number, step in enumerate(stage.steps, start=1):
if number < start_step:
continue
produced = self.step_runner.run_step(
plan_id=plan_id,
stage=stage,
step=step,
step_number=number,
executor_id=self.executor_id,
executor_run_id=run_id,
)
if not isinstance(produced, Mapping):
raise TypeError("step runner must return an evidence mapping")
evidence.update(
{
str(key).strip(): str(value).strip().lower()
for key, value in produced.items()
}
)
record = session.heartbeat(stage.task_id, current_step=number)
record = session.succeed(stage.task_id, evidence=evidence)
delivered.extend(self._deliver_notifications(stage.task_id))
return StageRunResult(
plan_id=plan_id,
stage_id=stage.stage_id,
task_id=stage.task_id,
executor_type=self.executor_type,
executor_id=self.executor_id,
executor_run_id=run_id,
state=record.state.value,
evidence=dict(record.evidence),
delivered_notifications=tuple(sorted(set(delivered))),
)
except Exception as exc:
current = self.task_coordinator.registry.get(stage.task_id)
if current.state in {
ExecutionTruthState.REGISTERED,
ExecutionTruthState.CLAIMED,
ExecutionTruthState.RUNNING,
}:
current = session.fail(
stage.task_id,
error={
"code": "executor_stage_failed",
"error_type": type(exc).__name__,
"message": str(exc),
},
evidence=evidence or None,
)
delivered.extend(self._deliver_notifications(stage.task_id))
return StageRunResult(
plan_id=plan_id,
stage_id=stage.stage_id,
task_id=stage.task_id,
executor_type=self.executor_type,
executor_id=self.executor_id,
executor_run_id=run_id,
state=current.state.value,
evidence=dict(current.evidence),
error=dict(current.error),
delivered_notifications=tuple(sorted(set(delivered))),
)
class JsonEvidenceStepRunner:
"""Adapter for handlers returning evidence-name to SHA256 mappings."""
def __init__(self, handler) -> None:
self.handler = handler
def run_step(self, **values: Any) -> Mapping[str, str]:
result = self.handler(**values)
if not isinstance(result, Mapping):
raise TypeError("step handler must return a mapping")
return {str(key): str(value) for key, value in result.items()}
class JsonReceiptNotificationSender:
"""Adapter for senders returning a SHA256 or receipt JSON object."""
def __init__(self, sender) -> None:
self.sender = sender
def send(self, notification: NotificationRecord) -> str:
result = self.sender(notification.as_dict())
if isinstance(result, str):
return result
if not isinstance(result, Mapping):
raise TypeError(
"notification sender must return SHA256 or a receipt object"
)
encoded = json.dumps(
dict(result),
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
default=str,
).encode("utf-8")
return hashlib.sha256(encoded).hexdigest()
@@ -0,0 +1,266 @@
#!/usr/bin/env python3
"""CLI for durable external-task truth and notification receipts.
The CLI is suitable for OpenClaw workers, systemd jobs and release gates. It
never infers execution from the presence of a manifest: each lifecycle action
must be recorded explicitly in the shared SQLite registry.
"""
from __future__ import annotations
import argparse
import json
import os
import sys
from pathlib import Path
from typing import Any, Mapping, Sequence
from .external_task_control import ExternalTaskCoordinator
from .external_task_query import list_records
def _json_mapping(value: str | None, path: str | None) -> Mapping[str, Any]:
if value and path:
raise ValueError("inline JSON and JSON file are mutually exclusive")
if path:
parsed = json.loads(Path(path).read_text(encoding="utf-8"))
else:
parsed = json.loads(value or "{}")
if not isinstance(parsed, Mapping):
raise ValueError("JSON value must be an object")
return dict(parsed)
def _coordinator(args: argparse.Namespace) -> ExternalTaskCoordinator:
return ExternalTaskCoordinator.from_file(args.store_file)
def _print(value: Any) -> None:
print(json.dumps(value, ensure_ascii=False, sort_keys=True, indent=2, default=str))
def cmd_declare(args: argparse.Namespace) -> int:
record = _coordinator(args).declare_file(args.manifest)
_print(record.as_dict())
return 0
def cmd_discover(args: argparse.Namespace) -> int:
records = list_records(
args.store_file,
executor=args.executor,
states=tuple(args.state or ()),
)
_print({"count": len(records), "items": [item.as_dict() for item in records]})
return 0
def cmd_register(args: argparse.Namespace) -> int:
_print(_coordinator(args).register(args.task_id, executor_run_id=args.executor_run_id).as_dict())
return 0
def cmd_claim(args: argparse.Namespace) -> int:
_print(
_coordinator(args).claim(
args.task_id,
executor_run_id=args.executor_run_id,
executor_id=args.executor_id,
).as_dict()
)
return 0
def cmd_start(args: argparse.Namespace) -> int:
_print(
_coordinator(args).start(
args.task_id,
executor_run_id=args.executor_run_id,
executor_id=args.executor_id,
).as_dict()
)
return 0
def cmd_heartbeat(args: argparse.Namespace) -> int:
_print(
_coordinator(args).heartbeat(
args.task_id,
executor_run_id=args.executor_run_id,
executor_id=args.executor_id,
current_step=args.current_step,
).as_dict()
)
return 0
def cmd_succeed(args: argparse.Namespace) -> int:
evidence = _json_mapping(args.evidence_json, args.evidence_file)
_print(
_coordinator(args).succeed(
args.task_id,
executor_run_id=args.executor_run_id,
executor_id=args.executor_id,
evidence={str(key): str(value) for key, value in evidence.items()},
).as_dict()
)
return 0
def cmd_fail(args: argparse.Namespace) -> int:
error = _json_mapping(args.error_json, args.error_file)
evidence = None
if args.evidence_json or args.evidence_file:
evidence_value = _json_mapping(args.evidence_json, args.evidence_file)
evidence = {str(key): str(value) for key, value in evidence_value.items()}
_print(
_coordinator(args).fail(
args.task_id,
executor_run_id=args.executor_run_id,
executor_id=args.executor_id,
error=error,
evidence=evidence,
).as_dict()
)
return 0
def cmd_status(args: argparse.Namespace) -> int:
_print(_coordinator(args).status(args.task_id))
return 0
def cmd_gate(args: argparse.Namespace) -> int:
value = _coordinator(args).gate(args.task_id)
_print(value)
return 0 if value["passed"] else 3
def cmd_notifications(args: argparse.Namespace) -> int:
items = _coordinator(args).notifications.list(task_id=args.task_id, status=args.status)
_print({"count": len(items), "items": [item.as_dict() for item in items]})
return 0
def cmd_ack(args: argparse.Namespace) -> int:
_print(
_coordinator(args).notifications.acknowledge(
args.notification_id,
receipt_sha256=args.receipt_sha256,
).as_dict()
)
return 0
def common(parser: argparse.ArgumentParser) -> None:
parser.add_argument(
"--store-file",
default=os.getenv(
"AIOS_EXTERNAL_TASK_STORE_FILE",
"/var/lib/aios-v2/external-task-truth.sqlite3",
),
)
def lifecycle(parser: argparse.ArgumentParser) -> None:
parser.add_argument("--task-id", required=True)
parser.add_argument("--executor-run-id", required=True)
parser.add_argument("--executor-id", required=True)
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(description="AIOS external task truth CLI")
commands = parser.add_subparsers(dest="command", required=True)
declare = commands.add_parser("declare")
common(declare)
declare.add_argument("--manifest", required=True)
declare.set_defaults(handler=cmd_declare)
discover = commands.add_parser("discover")
common(discover)
discover.add_argument("--executor", default="openclaw")
discover.add_argument("--state", action="append")
discover.set_defaults(handler=cmd_discover)
register = commands.add_parser("register")
common(register)
register.add_argument("--task-id", required=True)
register.add_argument("--executor-run-id", required=True)
register.set_defaults(handler=cmd_register)
claim = commands.add_parser("claim")
common(claim)
lifecycle(claim)
claim.set_defaults(handler=cmd_claim)
start = commands.add_parser("start")
common(start)
lifecycle(start)
start.set_defaults(handler=cmd_start)
heartbeat = commands.add_parser("heartbeat")
common(heartbeat)
lifecycle(heartbeat)
heartbeat.add_argument("--current-step", type=int, required=True)
heartbeat.set_defaults(handler=cmd_heartbeat)
succeed = commands.add_parser("succeed")
common(succeed)
lifecycle(succeed)
evidence = succeed.add_mutually_exclusive_group(required=True)
evidence.add_argument("--evidence-json")
evidence.add_argument("--evidence-file")
succeed.set_defaults(handler=cmd_succeed)
fail = commands.add_parser("fail")
common(fail)
lifecycle(fail)
error = fail.add_mutually_exclusive_group(required=True)
error.add_argument("--error-json")
error.add_argument("--error-file")
fail_evidence = fail.add_mutually_exclusive_group()
fail_evidence.add_argument("--evidence-json")
fail_evidence.add_argument("--evidence-file")
fail.set_defaults(handler=cmd_fail)
status = commands.add_parser("status")
common(status)
status.add_argument("--task-id", required=True)
status.set_defaults(handler=cmd_status)
gate = commands.add_parser("gate")
common(gate)
gate.add_argument("--task-id", required=True)
gate.set_defaults(handler=cmd_gate)
notifications = commands.add_parser("notifications")
common(notifications)
notifications.add_argument("--task-id")
notifications.add_argument("--status")
notifications.set_defaults(handler=cmd_notifications)
ack = commands.add_parser("ack-notification")
common(ack)
ack.add_argument("--notification-id", required=True)
ack.add_argument("--receipt-sha256", required=True)
ack.set_defaults(handler=cmd_ack)
return parser
def main(argv: Sequence[str] | None = None) -> int:
args = build_parser().parse_args(argv)
try:
return int(args.handler(args))
except Exception as exc:
print(
json.dumps(
{"status": "error", "error": type(exc).__name__, "message": str(exc)},
ensure_ascii=False,
),
file=sys.stderr,
)
return 1
if __name__ == "__main__":
raise SystemExit(main())
@@ -0,0 +1,420 @@
"""External executor coordination, notification outbox and release truth gate.
OpenClaw/Codex task declarations are not execution evidence. This module wraps
``SQLiteExecutionTruthRegistry`` with a durable notification outbox. A successful
release gate requires both terminal task evidence and acknowledged STARTED /
SUCCEEDED owner notifications when those events are required by the manifest.
"""
from __future__ import annotations
import hashlib
import json
import re
import sqlite3
import threading
import uuid
from dataclasses import asdict, dataclass
from pathlib import Path
from typing import Any, Mapping, Sequence
from .task_execution_registry import (
ExecutionTaskManifest,
ExecutionTruthRecord,
ExecutionTruthState,
SQLiteExecutionTruthRegistry,
utc_now,
)
_SHA256 = re.compile(r"^[0-9a-f]{64}$")
def sha256_value(value: str, label: str) -> str:
normalized = str(value or "").strip().lower()
if not _SHA256.fullmatch(normalized):
raise ValueError(f"{label} must be a lowercase SHA256 hex digest")
return normalized
@dataclass(frozen=True)
class NotificationRecord:
notification_id: str
task_id: str
event_type: str
target_ref: str
payload: Mapping[str, Any]
status: str
created_at: str
delivered_at: str | None = None
receipt_sha256: str | None = None
error: str | None = None
def as_dict(self) -> dict[str, Any]:
return asdict(self)
class SQLiteNotificationOutbox:
"""Durable owner-notification delivery and acknowledgement records."""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
with self._connect() as connection:
connection.executescript(
"""
CREATE TABLE IF NOT EXISTS external_task_notifications (
notification_id TEXT PRIMARY KEY,
task_id TEXT NOT NULL,
event_type TEXT NOT NULL,
target_ref TEXT NOT NULL,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
created_at TEXT NOT NULL,
delivered_at TEXT,
receipt_sha256 TEXT,
error TEXT,
UNIQUE(task_id, event_type)
);
CREATE INDEX IF NOT EXISTS idx_external_notification_status
ON external_task_notifications(status, created_at);
"""
)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(str(self.path), timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
return connection
@staticmethod
def _decode(row: sqlite3.Row) -> NotificationRecord:
return NotificationRecord(
notification_id=row["notification_id"],
task_id=row["task_id"],
event_type=row["event_type"],
target_ref=row["target_ref"],
payload=json.loads(row["payload_json"]),
status=row["status"],
created_at=row["created_at"],
delivered_at=row["delivered_at"],
receipt_sha256=row["receipt_sha256"],
error=row["error"],
)
def enqueue(
self,
*,
task_id: str,
event_type: str,
target_ref: str,
payload: Mapping[str, Any],
) -> NotificationRecord:
now = utc_now()
record = NotificationRecord(
notification_id=f"notify_{uuid.uuid4().hex}",
task_id=str(task_id).strip(),
event_type=str(event_type).strip().upper(),
target_ref=str(target_ref).strip(),
payload=json.loads(json.dumps(dict(payload), ensure_ascii=False, default=str)),
status="PENDING",
created_at=now,
)
if not record.task_id or not record.event_type or not record.target_ref:
raise ValueError("task_id, event_type and target_ref are required")
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
existing = connection.execute(
"SELECT * FROM external_task_notifications WHERE task_id = ? AND event_type = ?",
(record.task_id, record.event_type),
).fetchone()
if existing is not None:
connection.rollback()
return self._decode(existing)
connection.execute(
"""
INSERT INTO external_task_notifications
(notification_id, task_id, event_type, target_ref, payload_json,
status, created_at, delivered_at, receipt_sha256, error)
VALUES (?, ?, ?, ?, ?, ?, ?, NULL, NULL, NULL)
""",
(
record.notification_id,
record.task_id,
record.event_type,
record.target_ref,
json.dumps(record.payload, ensure_ascii=False, sort_keys=True, separators=(",", ":")),
record.status,
record.created_at,
),
)
connection.commit()
return record
def get(self, notification_id: str) -> NotificationRecord:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT * FROM external_task_notifications WHERE notification_id = ?",
(str(notification_id).strip(),),
).fetchone()
if row is None:
raise KeyError("notification not found")
return self._decode(row)
def acknowledge(self, notification_id: str, *, receipt_sha256: str) -> NotificationRecord:
digest = sha256_value(receipt_sha256, "receipt_sha256")
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
row = connection.execute(
"SELECT * FROM external_task_notifications WHERE notification_id = ?",
(str(notification_id).strip(),),
).fetchone()
if row is None:
connection.rollback()
raise KeyError("notification not found")
current = self._decode(row)
if current.status == "DELIVERED":
if current.receipt_sha256 != digest:
connection.rollback()
raise RuntimeError("notification already acknowledged with another receipt")
connection.rollback()
return current
delivered_at = utc_now()
connection.execute(
"""
UPDATE external_task_notifications
SET status = 'DELIVERED', delivered_at = ?, receipt_sha256 = ?, error = NULL
WHERE notification_id = ?
""",
(delivered_at, digest, current.notification_id),
)
connection.commit()
return self.get(current.notification_id)
def fail(self, notification_id: str, *, error: str) -> NotificationRecord:
message = str(error or "").strip()
if not message:
raise ValueError("notification error is required")
with self._lock, self._connect() as connection:
connection.execute(
"UPDATE external_task_notifications SET status = 'FAILED', error = ? WHERE notification_id = ?",
(message, str(notification_id).strip()),
)
connection.commit()
return self.get(notification_id)
def list(
self,
*,
task_id: str | None = None,
status: str | None = None,
) -> list[NotificationRecord]:
conditions: list[str] = []
values: list[str] = []
if task_id:
conditions.append("task_id = ?")
values.append(str(task_id).strip())
if status:
conditions.append("status = ?")
values.append(str(status).strip().upper())
where = f" WHERE {' AND '.join(conditions)}" if conditions else ""
with self._lock, self._connect() as connection:
rows = connection.execute(
f"SELECT * FROM external_task_notifications{where} ORDER BY created_at, notification_id",
tuple(values),
).fetchall()
return [self._decode(row) for row in rows]
class ExternalTaskCoordinator:
"""Single safe lifecycle used by external executors and release gates."""
def __init__(
self,
registry: SQLiteExecutionTruthRegistry,
notifications: SQLiteNotificationOutbox,
) -> None:
self.registry = registry
self.notifications = notifications
@classmethod
def from_file(cls, path: str | Path) -> "ExternalTaskCoordinator":
return cls(
SQLiteExecutionTruthRegistry(path),
SQLiteNotificationOutbox(path),
)
def declare(self, manifest: ExecutionTaskManifest) -> ExecutionTruthRecord:
return self.registry.declare(manifest)
def declare_file(self, path: str | Path) -> ExecutionTruthRecord:
value = json.loads(Path(path).read_text(encoding="utf-8"))
if not isinstance(value, Mapping):
raise ValueError("external task manifest must be a JSON object")
return self.declare(ExecutionTaskManifest.from_dict(value))
def register(self, task_id: str, *, executor_run_id: str) -> ExecutionTruthRecord:
return self.registry.register(task_id, executor_run_id=executor_run_id)
def retry_not_started(
self,
task_id: str,
*,
executor_run_id: str,
) -> ExecutionTruthRecord:
return self.registry.retry_not_started(
task_id,
executor_run_id=executor_run_id,
)
def claim(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
) -> ExecutionTruthRecord:
return self.registry.claim(
task_id,
executor_run_id=executor_run_id,
executor_id=executor_id,
)
def _notify(self, record: ExecutionTruthRecord, event_type: str) -> NotificationRecord | None:
event = event_type.upper()
if event not in set(record.manifest.notification_events):
return None
return self.notifications.enqueue(
task_id=record.task_id,
event_type=event,
target_ref=record.manifest.owner_notification_ref,
payload={
"task_id": record.task_id,
"target_version": record.manifest.target_version,
"executor": record.manifest.executor,
"executor_id": record.executor_id,
"executor_run_id": record.executor_run_id,
"state": record.state.value,
"current_step": record.current_step,
"total_steps": len(record.manifest.steps),
"timestamp": utc_now(),
},
)
def start(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
) -> ExecutionTruthRecord:
record = self.registry.start(
task_id,
executor_run_id=executor_run_id,
executor_id=executor_id,
)
self._notify(record, "STARTED")
return record
def heartbeat(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
current_step: int,
) -> ExecutionTruthRecord:
return self.registry.heartbeat(
task_id,
executor_run_id=executor_run_id,
executor_id=executor_id,
current_step=current_step,
)
def succeed(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
evidence: Mapping[str, str],
) -> ExecutionTruthRecord:
normalized = {
str(key).strip(): sha256_value(value, f"evidence[{key}]")
for key, value in evidence.items()
}
record = self.registry.succeed(
task_id,
executor_run_id=executor_run_id,
executor_id=executor_id,
evidence=normalized,
)
self._notify(record, "SUCCEEDED")
return record
def fail(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
error: Mapping[str, Any],
evidence: Mapping[str, str] | None = None,
) -> ExecutionTruthRecord:
normalized = None
if evidence is not None:
normalized = {
str(key).strip(): sha256_value(value, f"evidence[{key}]")
for key, value in evidence.items()
}
record = self.registry.fail(
task_id,
executor_run_id=executor_run_id,
executor_id=executor_id,
error=error,
evidence=normalized,
)
self._notify(record, "FAILED")
return record
def gate(self, task_id: str) -> Mapping[str, Any]:
before = self.registry.get(task_id)
truth = self.registry.gate(task_id)
after = self.registry.get(task_id)
if after.state != before.state and after.state in {
ExecutionTruthState.NOT_STARTED,
ExecutionTruthState.STALLED,
}:
self._notify(after, after.state.value)
notifications = self.notifications.list(task_id=task_id)
delivered = {item.event_type for item in notifications if item.status == "DELIVERED"}
required_success_notifications = {
item
for item in ("STARTED", "SUCCEEDED")
if item in set(after.manifest.notification_events)
}
notification_complete = required_success_notifications.issubset(delivered)
passed = bool(truth["passed"] and notification_complete)
return {
**dict(truth),
"passed": passed,
"release_blocking": not passed,
"notification_complete": notification_complete,
"required_success_notifications": sorted(required_success_notifications),
"delivered_notifications": sorted(delivered),
"notifications": [item.as_dict() for item in notifications],
}
def status(self, task_id: str) -> Mapping[str, Any]:
gate = self.gate(task_id)
record = self.registry.get(task_id)
return {
"record": record.as_dict(),
"gate": gate,
"events": self.registry.events(task_id),
}
@staticmethod
def content_receipt(value: Mapping[str, Any]) -> str:
encoded = json.dumps(dict(value), ensure_ascii=False, sort_keys=True, separators=(",", ":"), default=str).encode("utf-8")
return hashlib.sha256(encoded).hexdigest()
@@ -0,0 +1,51 @@
"""Read models for the durable external-task truth registry."""
from __future__ import annotations
import json
import sqlite3
from pathlib import Path
from typing import Sequence
from .task_execution_registry import ExecutionTruthRecord, ExecutionTruthState
def _decode(value: str) -> ExecutionTruthRecord:
payload = json.loads(value)
payload["state"] = ExecutionTruthState(payload["state"])
payload["evidence"] = dict(payload.get("evidence") or {})
payload["error"] = dict(payload.get("error") or {})
return ExecutionTruthRecord(**payload)
def list_records(
path: str | Path,
*,
executor: str | None = None,
states: Sequence[str] = (),
) -> list[ExecutionTruthRecord]:
database = Path(path).resolve()
if not database.exists():
return []
conditions: list[str] = []
values: list[str] = []
normalized_states = tuple(sorted({ExecutionTruthState(item).value for item in states}))
if normalized_states:
conditions.append(f"state IN ({','.join('?' for _ in normalized_states)})")
values.extend(normalized_states)
where = f" WHERE {' AND '.join(conditions)}" if conditions else ""
connection = sqlite3.connect(f"file:{database}?mode=ro", uri=True, timeout=10.0)
connection.row_factory = sqlite3.Row
try:
rows = connection.execute(
f"SELECT record_json FROM execution_truth{where} ORDER BY updated_at, task_id",
tuple(values),
).fetchall()
except sqlite3.OperationalError:
return []
finally:
connection.close()
records = [_decode(row["record_json"]) for row in rows]
if executor:
normalized = str(executor).strip().lower()
records = [item for item in records if item.manifest.executor.lower() == normalized]
return records
+353
View File
@@ -0,0 +1,353 @@
"""HTTP/JSON gateway for the AIOS V2 control plane.
The public gateway owns user-facing control operations only. Runtime lifecycle
transitions are deliberately absent: external callers cannot directly move a
task to RUNNING, COMPLETED or FAILED. Those transitions are available only
through the provenance-protected orchestrator and internal reconciliation API.
"""
from __future__ import annotations
import dataclasses
import json
import os
import re
import urllib.parse
from enum import Enum
from http import HTTPStatus
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from typing import Any, Mapping
from aios_hermes import HermesConflict, HermesNotFound
from .control_plane import (
ControlPlaneError,
ControlPlaneService,
IdempotencyConflict,
InvalidTransition,
NotFound,
PolicyDenied,
RequestContext,
RevisionConflict,
TaskState,
TenantIsolationError,
Unauthorized,
)
from .dispatch_store import DispatchConflict, DispatchNotFound
from .orchestrator import OrchestrationError
from .provenance import ProvenanceDenied, ProvenanceReplay
TENANT_HEADER = "X-AIOS-Tenant-ID"
PRINCIPAL_HEADER = "X-AIOS-Principal-ID"
ROLES_HEADER = "X-AIOS-Roles"
TRACE_HEADER = "X-AIOS-Trace-ID"
SESSION_HEADER = "X-AIOS-Session-ID"
POLICY_HEADER = "X-AIOS-Policy-Version"
AUTHENTICATED_HEADER = "X-AIOS-Authenticated"
_RESOURCE_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{0,191}$")
def _json_value(value: Any) -> Any:
if dataclasses.is_dataclass(value):
return {
field.name: _json_value(getattr(value, field.name))
for field in dataclasses.fields(value)
}
if isinstance(value, Enum):
return value.value
if isinstance(value, Mapping):
return {str(key): _json_value(item) for key, item in value.items()}
if isinstance(value, (list, tuple, set, frozenset)):
return [_json_value(item) for item in value]
return value
def _require_mapping(value: Any, *, label: str = "JSON body") -> Mapping[str, Any]:
if not isinstance(value, Mapping):
raise ValueError(f"{label} must be an object")
return value
def _require_resource_id(value: Any, *, label: str) -> str:
normalized = str(value or "").strip()
if not _RESOURCE_ID_RE.fullmatch(normalized):
raise ValueError(f"invalid {label}")
return normalized
class GatewayApplication:
"""Pure user-facing request router that can be tested without a socket."""
def __init__(self, service: ControlPlaneService | None = None) -> None:
self.service = service or ControlPlaneService()
@staticmethod
def context_from_headers(headers: Mapping[str, str]) -> RequestContext:
normalized_headers = {
str(key).strip().lower(): value for key, value in headers.items()
}
def header(name: str, default: str = "") -> str:
return str(normalized_headers.get(name.lower(), default))
authenticated = header(AUTHENTICATED_HEADER).strip().lower()
if authenticated not in {"1", "true", "yes"}:
raise Unauthorized("trusted authentication assertion is required")
roles = [
role.strip()
for role in header(ROLES_HEADER).split(",")
if role.strip()
]
return RequestContext.create(
tenant_id=header(TENANT_HEADER),
principal_id=header(PRINCIPAL_HEADER),
trace_id=header(TRACE_HEADER).strip() or None,
session_id=header(SESSION_HEADER).strip() or None,
policy_version=header(POLICY_HEADER, "v1").strip() or "v1",
roles=roles,
)
def handle(
self,
method: str,
raw_path: str,
headers: Mapping[str, str],
body: Any = None,
) -> tuple[int, Mapping[str, Any]]:
parsed = urllib.parse.urlparse(raw_path)
path = parsed.path.rstrip("/") or "/"
query = urllib.parse.parse_qs(parsed.query, keep_blank_values=False)
method = method.upper()
if method == "GET" and path in {"/healthz", "/api/v2/health"}:
return HTTPStatus.OK, {
"service": "aios-v2-control-plane",
"status": "ok",
"store": type(self.service.store).__name__,
}
context = self.context_from_headers(headers)
payload = _require_mapping(body or {})
if method == "POST" and path == "/api/v2/tenants":
tenant = self.service.register_tenant(
context,
tenant_id=_require_resource_id(payload.get("tenant_id"), label="tenant_id"),
display_name=str(payload.get("display_name", "")),
metadata=_require_mapping(payload.get("metadata", {}), label="metadata"),
)
return HTTPStatus.CREATED, {"tenant": _json_value(tenant)}
if method == "GET" and path == "/api/v2/tenants/current":
return HTTPStatus.OK, {"tenant": _json_value(self.service.get_tenant(context))}
if method == "POST" and path == "/api/v2/agents":
agent = self.service.register_agent(
context,
agent_id=_require_resource_id(payload.get("agent_id"), label="agent_id"),
display_name=str(payload.get("display_name", "")),
runtime=str(payload.get("runtime", "")),
capabilities=payload.get("capabilities", ()),
metadata=_require_mapping(payload.get("metadata", {}), label="metadata"),
)
return HTTPStatus.CREATED, {"agent": _json_value(agent)}
if method == "GET" and path == "/api/v2/agents":
return HTTPStatus.OK, {"agents": _json_value(self.service.list_agents(context))}
agent_match = re.fullmatch(r"/api/v2/agents/([^/]+)", path)
if method == "GET" and agent_match:
agent_id = _require_resource_id(
urllib.parse.unquote(agent_match.group(1)), label="agent_id"
)
return HTTPStatus.OK, {
"agent": _json_value(self.service.get_agent(context, agent_id))
}
if method == "POST" and path == "/api/v2/tasks":
task = self.service.create_task(
context,
agent_id=_require_resource_id(payload.get("agent_id"), label="agent_id"),
action=str(payload.get("action", "")).strip(),
payload=_require_mapping(payload.get("payload", {}), label="payload"),
idempotency_key=(
str(payload["idempotency_key"]).strip()
if payload.get("idempotency_key") is not None
else None
),
)
return HTTPStatus.CREATED, {"task": _json_value(task)}
if method == "GET" and path == "/api/v2/tasks":
tasks = self.service.list_tasks(context, states=query.get("state"))
return HTTPStatus.OK, {"tasks": _json_value(tasks)}
task_match = re.fullmatch(r"/api/v2/tasks/([^/]+)", path)
if method == "GET" and task_match:
task_id = _require_resource_id(
urllib.parse.unquote(task_match.group(1)), label="task_id"
)
return HTTPStatus.OK, {
"task": _json_value(self.service.get_task(context, task_id))
}
bypass_match = re.fullmatch(
r"/api/v2/tasks/([^/]+)/(start|complete|fail)", path
)
if method == "POST" and bypass_match:
return HTTPStatus.FORBIDDEN, {
"error": "RuntimeLifecycleBypassDenied",
"message": (
"RUNNING, COMPLETED and FAILED transitions are internal; "
"use the provenance-protected dispatch/reconcile flow"
),
}
transition_match = re.fullmatch(
r"/api/v2/tasks/([^/]+)/(approve|cancel)", path
)
if method == "POST" and transition_match:
task_id = _require_resource_id(
urllib.parse.unquote(transition_match.group(1)), label="task_id"
)
target = (
TaskState.APPROVED
if transition_match.group(2) == "approve"
else TaskState.CANCELLED
)
expected_revision = payload.get("expected_revision")
task = self.service.transition_task(
context,
task_id=task_id,
target_state=target,
expected_revision=(
int(expected_revision) if expected_revision is not None else None
),
)
return HTTPStatus.OK, {"task": _json_value(task)}
if method == "GET" and path == "/api/v2/audit":
resource_id = query.get("resource_id", [None])[0]
events = self.service.list_audit_events(
context,
resource_id=(
_require_resource_id(resource_id, label="resource_id")
if resource_id
else None
),
)
return HTTPStatus.OK, {"events": _json_value(events)}
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "route not found",
}
_ERROR_STATUS: tuple[tuple[type[BaseException], HTTPStatus], ...] = (
(Unauthorized, HTTPStatus.UNAUTHORIZED),
(PolicyDenied, HTTPStatus.FORBIDDEN),
(ProvenanceDenied, HTTPStatus.FORBIDDEN),
(TenantIsolationError, HTTPStatus.NOT_FOUND),
(NotFound, HTTPStatus.NOT_FOUND),
(DispatchNotFound, HTTPStatus.NOT_FOUND),
(HermesNotFound, HTTPStatus.NOT_FOUND),
(ProvenanceReplay, HTTPStatus.CONFLICT),
(IdempotencyConflict, HTTPStatus.CONFLICT),
(RevisionConflict, HTTPStatus.CONFLICT),
(InvalidTransition, HTTPStatus.CONFLICT),
(DispatchConflict, HTTPStatus.CONFLICT),
(HermesConflict, HTTPStatus.CONFLICT),
(OrchestrationError, HTTPStatus.CONFLICT),
(ValueError, HTTPStatus.BAD_REQUEST),
(ControlPlaneError, HTTPStatus.BAD_REQUEST),
)
def error_response(exc: BaseException) -> tuple[int, Mapping[str, Any]]:
for error_type, status in _ERROR_STATUS:
if isinstance(exc, error_type):
return status, {"error": error_type.__name__, "message": str(exc)}
return HTTPStatus.INTERNAL_SERVER_ERROR, {
"error": "InternalServerError",
"message": "internal server error",
}
class GatewayRequestHandler(BaseHTTPRequestHandler):
server_version = "AIOSV2Gateway/1.0"
max_body_bytes = 1_048_576
@property
def application(self) -> GatewayApplication:
return self.server.application # type: ignore[attr-defined]
def _read_body(self) -> Any:
length = int(self.headers.get("Content-Length", "0") or "0")
if length < 0 or length > self.max_body_bytes:
raise ValueError("request body is too large")
if length == 0:
return {}
content_type = self.headers.get("Content-Type", "").split(";", 1)[0].strip()
if content_type != "application/json":
raise ValueError("Content-Type must be application/json")
return json.loads(self.rfile.read(length).decode("utf-8"))
def _send_json(self, status: int, payload: Mapping[str, Any]) -> None:
encoded = json.dumps(
_json_value(payload), ensure_ascii=False, separators=(",", ":")
).encode("utf-8")
self.send_response(int(status))
self.send_header("Content-Type", "application/json; charset=utf-8")
self.send_header("Content-Length", str(len(encoded)))
self.send_header("Cache-Control", "no-store")
self.send_header("X-Content-Type-Options", "nosniff")
self.end_headers()
self.wfile.write(encoded)
def _dispatch(self, method: str) -> None:
try:
body = self._read_body() if method in {"POST", "PUT", "PATCH"} else {}
status, payload = self.application.handle(
method,
self.path,
{key: value for key, value in self.headers.items()},
body,
)
except Exception as exc:
status, payload = error_response(exc)
self._send_json(status, payload)
def do_GET(self) -> None: # noqa: N802
self._dispatch("GET")
def do_POST(self) -> None: # noqa: N802
self._dispatch("POST")
def log_message(self, format: str, *args: Any) -> None:
super().log_message(format, *args)
class GatewayHTTPServer(ThreadingHTTPServer):
daemon_threads = True
allow_reuse_address = True
def __init__(
self,
server_address: tuple[str, int],
application: GatewayApplication,
) -> None:
self.application = application
super().__init__(server_address, GatewayRequestHandler)
def main() -> None:
host = os.getenv("AIOS_V2_GATEWAY_HOST", "127.0.0.1")
port = int(os.getenv("AIOS_V2_GATEWAY_PORT", "18920"))
server = GatewayHTTPServer((host, port), GatewayApplication())
print(f"AIOS V2 control-plane gateway listening on {host}:{port}")
server.serve_forever()
if __name__ == "__main__":
main()
+123
View File
@@ -0,0 +1,123 @@
"""Sanitized GitOps runtime status for the AIOS Web control plane."""
from __future__ import annotations
import os
import subprocess
from dataclasses import dataclass, asdict
from pathlib import Path
from typing import Any, Mapping
@dataclass(frozen=True)
class GitOpsStatus:
available: bool
service_status: str
workspace_mode: str
workspace_branch: str | None
workspace_ref: str | None
workspace_dirty: bool | None
candidate_branch: str
release_channel: str
release_version: str
sync_status: str
details: Mapping[str, Any]
def as_dict(self) -> dict[str, Any]:
return asdict(self)
def _run_git(worktree: Path, *args: str) -> tuple[int, str, str]:
process = subprocess.run(
["git", "-C", str(worktree), *args],
text=True,
capture_output=True,
timeout=5,
)
return process.returncode, process.stdout.strip(), process.stderr.strip()
def collect_gitops_status() -> GitOpsStatus:
"""Return only non-sensitive Git/workspace metadata.
Remote URLs, environment values, credentials, filesystem contents and
command stderr are deliberately excluded from the Web response.
"""
candidate_branch = os.getenv(
"AIOS_CANDIDATE_BRANCH",
"integration/aios-v2r1-cto-production-candidate-20260720",
)
release_channel = os.getenv("AIOS_RELEASE_CHANNEL", "candidate")
release_version = os.getenv("AIOS_RELEASE_VERSION", "V2R1C0-candidate")
sync_status = os.getenv("AIOS_GITOPS_SYNC_STATUS", "unknown")
worktree = Path(
os.getenv(
"AIOS_GITOPS_CONTROLLER_WORKTREE",
"/data/aios-gitops/worktrees/controller",
)
)
if not worktree.is_dir():
return GitOpsStatus(
available=False,
service_status="unknown",
workspace_mode="unavailable",
workspace_branch=None,
workspace_ref=None,
workspace_dirty=None,
candidate_branch=candidate_branch,
release_channel=release_channel,
release_version=release_version,
sync_status=sync_status,
details={"reason": "controller_worktree_unavailable"},
)
inside_code, inside, _ = _run_git(worktree, "rev-parse", "--is-inside-work-tree")
if inside_code != 0 or inside != "true":
return GitOpsStatus(
available=False,
service_status="unknown",
workspace_mode="invalid",
workspace_branch=None,
workspace_ref=None,
workspace_dirty=None,
candidate_branch=candidate_branch,
release_channel=release_channel,
release_version=release_version,
sync_status=sync_status,
details={"reason": "controller_worktree_invalid"},
)
branch_code, branch, _ = _run_git(worktree, "branch", "--show-current")
ref_code, ref_value, _ = _run_git(worktree, "rev-parse", "HEAD")
dirty_code, dirty_value, _ = _run_git(worktree, "status", "--porcelain=v1")
service_status = "unknown"
try:
process = subprocess.run(
["systemctl", "is-active", "aios-gitops-model-api"],
text=True,
capture_output=True,
timeout=3,
)
service_status = process.stdout.strip() or "inactive"
except (FileNotFoundError, subprocess.TimeoutExpired):
service_status = "unavailable"
branch_value = branch if branch_code == 0 and branch else None
return GitOpsStatus(
available=True,
service_status=service_status,
workspace_mode="branch" if branch_value else "detached",
workspace_branch=branch_value,
workspace_ref=ref_value if ref_code == 0 else None,
workspace_dirty=bool(dirty_value) if dirty_code == 0 else None,
candidate_branch=candidate_branch,
release_channel=release_channel,
release_version=release_version,
sync_status=sync_status,
details={
"controller_clean": dirty_code == 0 and not dirty_value,
"controller_detached": branch_code == 0 and not branch,
},
)
@@ -0,0 +1,238 @@
"""Official AIOS executor providers built on the portable provider protocol.
The official providers contain no lifecycle implementation. They validate their
manifests, resolve a generic ``UnifiedExecutorWorker`` from runtime-supplied
boundaries and expose the same adapter contract. Future providers can use
``ConfiguredExecutorProvider`` directly without changing AIOS core modules.
"""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Mapping, Sequence
from .execution_plan import ExecutionPlanCoordinator, ExecutionStageManifest
from .executor_protocol import (
EXECUTOR_PROTOCOL_VERSION,
ExternalExecutorAdapter,
ExecutorProviderDescriptor,
normalize_executor,
)
from .executor_worker import NotificationSender, StepRunner, UnifiedExecutorWorker
from .external_task_control import ExternalTaskCoordinator
from .task_execution_registry import ExecutionTaskManifest, ExecutionTruthRecord
@dataclass(frozen=True)
class ProviderRuntimeConfiguration:
plan_id: str
executor_id: str
plan_coordinator: ExecutionPlanCoordinator
task_coordinator: ExternalTaskCoordinator
providers: Any
step_runner: StepRunner
notification_sender: NotificationSender
@classmethod
def from_mapping(cls, value: Mapping[str, Any]) -> "ProviderRuntimeConfiguration":
required = (
"plan_id",
"executor_id",
"plan_coordinator",
"task_coordinator",
"providers",
"step_runner",
"notification_sender",
)
missing = [name for name in required if value.get(name) is None]
if missing:
raise ValueError(f"provider runtime configuration is missing: {missing}")
return cls(**{name: value[name] for name in required})
class ConfiguredExecutorAdapter:
"""Generic adapter produced by every official or third-party provider."""
def __init__(
self,
descriptor: ExecutorProviderDescriptor,
configuration: ProviderRuntimeConfiguration,
) -> None:
self.descriptor = descriptor
self.configuration = configuration
self.worker = UnifiedExecutorWorker(
plan_coordinator=configuration.plan_coordinator,
task_coordinator=configuration.task_coordinator,
providers=configuration.providers,
executor_type=descriptor.executor_type,
executor_id=configuration.executor_id,
step_runner=configuration.step_runner,
notification_sender=configuration.notification_sender,
)
def discover(self) -> Sequence[ExecutionTruthRecord]:
ready = self.configuration.plan_coordinator.discover_ready(
plan_id=self.configuration.plan_id,
executor_type=self.descriptor.executor_type,
)
return tuple(item["record"] for item in ready)
def execute(self, manifest: ExecutionTaskManifest) -> Mapping[str, Any]:
if normalize_executor(manifest.executor) != self.descriptor.executor_type:
raise PermissionError("manifest executor does not match adapter provider")
plan = self.configuration.plan_coordinator.plan_store.get(
self.configuration.plan_id
)
stage: ExecutionStageManifest | None = None
for item in plan.stages:
if item.task_id == manifest.task_id:
stage = item
break
if stage is None:
raise KeyError("manifest task is not part of configured execution plan")
return self.worker.run_stage(
plan_id=plan.plan_id,
stage_id=stage.stage_id,
).as_dict()
def notify_owner(self, payload: Mapping[str, Any]) -> str:
# External callers normally use the durable NotificationOutbox. This
# method remains part of the portable adapter contract for providers
# that need to send a standalone operational notice.
from .external_task_control import NotificationRecord
from .task_execution_registry import utc_now
notification = NotificationRecord(
notification_id="provider_direct_notice",
task_id=str(payload.get("task_id") or "provider-notice"),
event_type=str(payload.get("event_type") or "INFO"),
target_ref=str(
payload.get("target_ref") or "AIOS_OWNER_WECHAT_TARGET_REF"
),
payload=dict(payload),
status="PENDING",
created_at=utc_now(),
)
return self.configuration.notification_sender.send(notification)
class ConfiguredExecutorProvider:
"""Reusable provider implementation for current and future executors."""
descriptor: ExecutorProviderDescriptor
def __init__(self, descriptor: ExecutorProviderDescriptor) -> None:
self.descriptor = descriptor
def validate_manifest(self, manifest: ExecutionTaskManifest) -> None:
if normalize_executor(manifest.executor) != self.descriptor.executor_type:
raise ValueError("manifest executor does not match provider")
if manifest.manifest_version not in {
"aios.external-task.v1",
"aios.external-task.v2",
}:
raise ValueError("unsupported external task manifest version")
if not manifest.steps:
raise ValueError("executor manifest has no steps")
def build_adapter(self, configuration: Mapping[str, Any]) -> ExternalExecutorAdapter:
return ConfiguredExecutorAdapter(
self.descriptor,
ProviderRuntimeConfiguration.from_mapping(configuration),
)
class OpenClawProvider(ConfiguredExecutorProvider):
def __init__(self) -> None:
super().__init__(
ExecutorProviderDescriptor(
executor_type="openclaw",
adapter_version="2.1.0",
protocol_version=EXECUTOR_PROTOCOL_VERSION,
trust_roles=("runtime", "openclaw_executor"),
capabilities=(
"deploy",
"http_runtime",
"owner_notification",
"healthcheck",
"rollback",
),
configuration_schema="aios.executor.openclaw.config.v1",
metadata={"official": True},
)
)
class HermesProvider(ConfiguredExecutorProvider):
def __init__(self) -> None:
super().__init__(
ExecutorProviderDescriptor(
executor_type="hermes",
adapter_version="2.1.0",
protocol_version=EXECUTOR_PROTOCOL_VERSION,
trust_roles=("runtime", "hermes_executor"),
capabilities=(
"queue",
"lease",
"worker",
"runtime_validation",
"restart_recovery",
),
configuration_schema="aios.executor.hermes.config.v1",
metadata={"official": True},
)
)
class CodexProvider(ConfiguredExecutorProvider):
def __init__(self) -> None:
super().__init__(
ExecutorProviderDescriptor(
executor_type="codex",
adapter_version="2.1.0",
protocol_version=EXECUTOR_PROTOCOL_VERSION,
trust_roles=("codex", "codex_executor"),
capabilities=(
"code",
"test",
"docs",
"gitops_patch",
"security_review",
),
configuration_schema="aios.executor.codex.config.v1",
metadata={"official": True},
)
)
class ChatGPTSupervisorProvider(ConfiguredExecutorProvider):
"""Explicit takeover provider; it does not inherit Codex permissions."""
def __init__(self) -> None:
super().__init__(
ExecutorProviderDescriptor(
executor_type="chatgpt-supervisor",
adapter_version="2.1.0",
protocol_version=EXECUTOR_PROTOCOL_VERSION,
trust_roles=("chatgpt_supervisor",),
capabilities=(
"acceptance",
"deploy",
"evidence",
"healthcheck",
"rollback",
"wechat_simulation",
),
configuration_schema="aios.executor.chatgpt-supervisor.config.v1",
metadata={"official": True, "production_mutation_allowed": False},
)
)
def official_provider_factories() -> Mapping[str, ConfiguredExecutorProvider]:
providers = (
OpenClawProvider(),
HermesProvider(),
CodexProvider(),
ChatGPTSupervisorProvider(),
)
return {item.descriptor.executor_type: item for item in providers}
+599
View File
@@ -0,0 +1,599 @@
"""AIOS V2 execution orchestrator.
The orchestrator is the only component allowed to translate an approved AIOS
Task into an OpenClaw command or Hermes job. Every dispatch is persisted before
Runtime side effects. Runtime results must bind to the exact dispatch,
command/job, tenant, task, trace, principal and provenance context.
"""
from __future__ import annotations
from typing import Any, Mapping, Protocol
from aios_hermes import HermesAdapter, HermesJob, HermesJobState, HermesResult
from aios_openclaw import (
CommandState,
OpenClawAdapter,
OpenClawCommand,
OpenClawResult,
sign_command,
)
from .control_plane import (
AgentRecord,
ControlPlaneService,
RequestContext,
TaskRecord,
TaskState,
)
from .dispatch_store import (
DispatchConflict,
DispatchRecord,
DispatchRepository,
DispatchState,
InMemoryDispatchRepository,
TERMINAL_DISPATCH_STATES,
)
from .provenance import ProvenanceDenied, digest_payload
class RuntimeAuthorizationWriter(Protocol):
def authorize_runtime_execute(self, **values: Any) -> Any: ...
class OrchestrationError(RuntimeError):
"""AIOS failed to dispatch or reconcile a runtime execution."""
class ExecutionOrchestrator:
"""Dispatch approved AIOS tasks and strictly reconcile Runtime results."""
def __init__(
self,
control_plane: ControlPlaneService,
*,
openclaw: OpenClawAdapter | None = None,
hermes: HermesAdapter | None = None,
openclaw_signing_material_resolver=None,
openclaw_key_id: str = "default",
default_cell_id: str = "default",
default_profile_id: str = "default",
provenance_writer: RuntimeAuthorizationWriter | None = None,
require_provenance: bool = False,
dispatch_repository: DispatchRepository | None = None,
) -> None:
self.control_plane = control_plane
self.openclaw = openclaw
self.hermes = hermes
self.openclaw_signing_material_resolver = openclaw_signing_material_resolver
self.openclaw_key_id = str(openclaw_key_id or "").strip() or "default"
self.default_cell_id = default_cell_id
self.default_profile_id = default_profile_id
self.provenance_writer = provenance_writer
self.require_provenance = bool(require_provenance)
self.dispatch_repository = dispatch_repository or InMemoryDispatchRepository()
if self.require_provenance and self.provenance_writer is None:
raise ValueError("production orchestration requires a provenance writer")
@staticmethod
def _record_provenance(value: str | None, *, required: bool, label: str) -> str:
normalized = str(value or "").strip()
if required and not normalized:
raise OrchestrationError(f"production dispatch requires {label}")
return normalized or f"{label}-not-required"
def _authorize_dispatch(
self,
context: RequestContext,
*,
task: TaskRecord,
agent: AgentRecord,
provenance_id: str | None,
run_id: str | None,
timeout_seconds: float | None,
) -> str:
if not self.require_provenance:
return "authorization-not-required"
if self.provenance_writer is None:
raise OrchestrationError("Run Provenance writer is not configured")
if not provenance_id or not run_id:
raise OrchestrationError(
"production dispatch requires provenance_id and run_id"
)
request_digest = digest_payload(
{
"operation": "dispatch",
"tenant_id": task.tenant_id,
"task_id": task.task_id,
"agent_id": agent.agent_id,
"principal_id": context.principal_id,
"runtime": agent.runtime.strip().lower(),
"action": task.action,
"payload": task.payload,
"trace_id": context.trace_id,
"timeout_seconds": timeout_seconds,
"task_revision": task.revision,
}
)
try:
authorization = self.provenance_writer.authorize_runtime_execute(
provenance_id=provenance_id,
run_id=run_id,
tenant_id=task.tenant_id,
task_id=task.task_id,
agent_id=agent.agent_id,
principal_id=context.principal_id,
request_digest=request_digest,
)
return authorization.authorization_id
except ProvenanceDenied as exc:
raise OrchestrationError(f"Run Provenance denied dispatch: {exc}") from exc
def dispatch(
self,
context: RequestContext,
*,
task_id: str,
timeout_seconds: float | None = None,
provenance_id: str | None = None,
run_id: str | None = None,
) -> DispatchRecord:
task = self.control_plane.get_task(context, task_id)
agent = self.control_plane.get_agent(context, task.agent_id)
persisted_provenance = self._record_provenance(
provenance_id, required=self.require_provenance, label="provenance_id"
)
persisted_run = self._record_provenance(
run_id, required=self.require_provenance, label="run_id"
)
existing = self.dispatch_repository.get_by_task(
task.task_id, tenant_id=task.tenant_id
)
if existing is not None:
if (
existing.provenance_id != persisted_provenance
or existing.run_id != persisted_run
or existing.principal_id != context.principal_id
):
raise OrchestrationError(
"existing dispatch belongs to another provenance or principal context"
)
return existing
if task.state != TaskState.APPROVED:
raise OrchestrationError("only APPROVED tasks may be dispatched")
authorization_id = self._authorize_dispatch(
context,
task=task,
agent=agent,
provenance_id=provenance_id,
run_id=run_id,
timeout_seconds=timeout_seconds,
)
runtime = agent.runtime.strip().lower()
prepared: DispatchRecord | None = None
try:
if runtime == "openclaw":
command = self._create_openclaw_command(context, task)
prepared = self.dispatch_repository.create(
DispatchRecord.create(
tenant_id=task.tenant_id,
task_id=task.task_id,
agent_id=agent.agent_id,
principal_id=context.principal_id,
runtime="openclaw",
runtime_execution_id=command.command_id,
trace_id=context.trace_id,
provenance_id=persisted_provenance,
run_id=persisted_run,
authorization_id=authorization_id,
)
)
self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.RUNNING,
expected_revision=task.revision,
)
self.dispatch_repository.update(
prepared.dispatch_id,
tenant_id=prepared.tenant_id,
state=DispatchState.RUNNING,
)
if self.openclaw is None:
raise OrchestrationError("OpenClaw runtime is not configured")
result = self.openclaw.execute(
command, timeout_seconds=timeout_seconds
)
self.reconcile_openclaw(
context,
result,
dispatch_id=prepared.dispatch_id,
provenance_id=persisted_provenance,
run_id=persisted_run,
)
return self.dispatch_repository.get(
prepared.dispatch_id, tenant_id=prepared.tenant_id
)
if runtime == "hermes":
if self.hermes is None:
raise OrchestrationError("Hermes runtime is not configured")
job = self._create_hermes_job(context, agent, task)
prepared = self.dispatch_repository.create(
DispatchRecord.create(
tenant_id=task.tenant_id,
task_id=task.task_id,
agent_id=agent.agent_id,
principal_id=context.principal_id,
runtime="hermes",
runtime_execution_id=job.job_id,
trace_id=context.trace_id,
provenance_id=persisted_provenance,
run_id=persisted_run,
authorization_id=authorization_id,
)
)
self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.RUNNING,
expected_revision=task.revision,
)
queued = self.hermes.enqueue(job)
return self.dispatch_repository.update(
prepared.dispatch_id,
tenant_id=prepared.tenant_id,
state=DispatchState.QUEUED,
result_digest=digest_payload(
{
"queued_job_id": queued.job_id,
"state": queued.state.value,
"revision": queued.revision,
}
),
)
raise OrchestrationError(f"unsupported runtime: {agent.runtime}")
except Exception as exc:
if prepared is not None:
try:
self.dispatch_repository.update(
prepared.dispatch_id,
tenant_id=prepared.tenant_id,
state=DispatchState.FAILED,
result_digest=digest_payload(
{
"code": "dispatch_failed",
"error_type": type(exc).__name__,
"message": str(exc),
}
),
)
except Exception:
pass
current = self.control_plane.get_task(context, task.task_id)
if current.state == TaskState.RUNNING:
self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.FAILED,
expected_revision=current.revision,
error={"code": "dispatch_failed", "message": str(exc)},
)
raise
def _create_openclaw_command(
self,
context: RequestContext,
task: TaskRecord,
) -> OpenClawCommand:
if self.openclaw_signing_material_resolver is None:
raise OrchestrationError("OpenClaw signing material is not configured")
key_material = self.openclaw_signing_material_resolver(
task.tenant_id,
self.openclaw_key_id,
)
command = OpenClawCommand.create(
tenant_id=task.tenant_id,
task_id=task.task_id,
trace_id=context.trace_id,
action=task.action,
payload=task.payload,
idempotency_key=task.idempotency_key or task.task_id,
key_id=self.openclaw_key_id,
)
return sign_command(command, key_material)
def _create_hermes_job(
self,
context: RequestContext,
agent: AgentRecord,
task: TaskRecord,
) -> HermesJob:
metadata = dict(agent.metadata)
return HermesJob.create(
tenant_id=task.tenant_id,
cell_id=str(metadata.get("cell_id") or self.default_cell_id),
profile_id=str(metadata.get("profile_id") or self.default_profile_id),
task_id=task.task_id,
trace_id=context.trace_id,
action=task.action,
payload=task.payload,
idempotency_key=task.idempotency_key or task.task_id,
priority=int(metadata.get("priority", 100)),
)
@staticmethod
def _assert_dispatch_context(
dispatch: DispatchRecord,
*,
runtime: str,
runtime_execution_id: str,
tenant_id: str,
task_id: str,
trace_id: str,
principal_id: str,
provenance_id: str,
run_id: str,
) -> None:
expected = {
"runtime": runtime,
"runtime_execution_id": runtime_execution_id,
"tenant_id": tenant_id,
"task_id": task_id,
"trace_id": trace_id,
"principal_id": principal_id,
"provenance_id": provenance_id,
"run_id": run_id,
}
for field_name, expected_value in expected.items():
if getattr(dispatch, field_name) != expected_value:
raise OrchestrationError(f"dispatch {field_name} mismatch")
def hermes_lifecycle_context(
self,
context: RequestContext,
*,
dispatch_id: str,
job_id: str,
tenant_id: str,
task_id: str,
trace_id: str,
principal_id: str,
provenance_id: str,
run_id: str,
) -> tuple[DispatchRecord, HermesJob]:
"""Resolve a runtime lifecycle request against its durable dispatch."""
dispatch = self.dispatch_repository.get(
dispatch_id, tenant_id=context.tenant_id
)
self._assert_dispatch_context(
dispatch,
runtime="hermes",
runtime_execution_id=job_id,
tenant_id=tenant_id,
task_id=task_id,
trace_id=trace_id,
principal_id=principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
if context.tenant_id != tenant_id:
raise OrchestrationError("runtime context tenant_id mismatch")
if context.principal_id != principal_id:
raise OrchestrationError("runtime context principal_id mismatch")
if context.trace_id != trace_id:
raise OrchestrationError("runtime context trace_id mismatch")
if self.hermes is None:
raise OrchestrationError("Hermes runtime is not configured")
job = self.hermes.get(job_id, tenant_id=tenant_id)
if job.task_id != task_id or job.trace_id != trace_id:
raise OrchestrationError("Hermes job identity mismatch")
return dispatch, job
def bind_hermes_worker(
self,
context: RequestContext,
job: HermesJob,
*,
dispatch_id: str,
provenance_id: str,
run_id: str,
worker_id: str,
) -> DispatchRecord:
dispatch, current = self.hermes_lifecycle_context(
context,
dispatch_id=dispatch_id,
job_id=job.job_id,
tenant_id=job.tenant_id,
task_id=job.task_id,
trace_id=job.trace_id,
principal_id=context.principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
if current.assigned_worker_id != worker_id:
raise OrchestrationError("Hermes worker does not own claimed job")
return self.dispatch_repository.update(
dispatch.dispatch_id,
tenant_id=dispatch.tenant_id,
expected_worker_id=worker_id,
)
def reconcile_openclaw(
self,
context: RequestContext,
result: OpenClawResult,
*,
dispatch_id: str,
provenance_id: str,
run_id: str,
) -> TaskRecord:
dispatch = self.dispatch_repository.get(
dispatch_id, tenant_id=context.tenant_id
)
self._assert_dispatch_context(
dispatch,
runtime="openclaw",
runtime_execution_id=result.command_id,
tenant_id=result.tenant_id,
task_id=result.task_id,
trace_id=result.trace_id,
principal_id=context.principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
result_digest = digest_payload(
{
"command_id": result.command_id,
"state": result.state.value,
"output": result.output,
"error": result.error,
"runtime_id": result.runtime_id,
"attempts": result.attempts,
"finished_at": result.finished_at,
}
)
if dispatch.state in TERMINAL_DISPATCH_STATES:
if dispatch.result_digest != result_digest:
raise DispatchConflict("terminal dispatch received a different result")
return self.control_plane.get_task(context, dispatch.task_id)
task = self.control_plane.get_task(context, dispatch.task_id)
if task.state != TaskState.RUNNING:
raise OrchestrationError("task is not RUNNING for active dispatch")
if result.state == CommandState.COMPLETED:
target = TaskState.COMPLETED
values = {"result": result.output or {}}
dispatch_state = DispatchState.COMPLETED
elif result.state in {
CommandState.FAILED,
CommandState.TIMED_OUT,
CommandState.REJECTED,
}:
target = TaskState.FAILED
values = {
"error": result.error or {"code": result.state.value.lower()}
}
dispatch_state = DispatchState.FAILED
elif result.state == CommandState.CANCELLED:
target = TaskState.CANCELLED
values = {}
dispatch_state = DispatchState.CANCELLED
else:
self.dispatch_repository.update(
dispatch.dispatch_id,
tenant_id=dispatch.tenant_id,
state=DispatchState.RUNNING,
result_digest=result_digest,
)
return task
updated_task = self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=target,
expected_revision=task.revision,
**values,
)
self.dispatch_repository.update(
dispatch.dispatch_id,
tenant_id=dispatch.tenant_id,
state=dispatch_state,
result_digest=result_digest,
)
return updated_task
def reconcile_hermes(
self,
context: RequestContext,
result: HermesResult,
*,
dispatch_id: str,
provenance_id: str,
run_id: str,
) -> TaskRecord:
dispatch = self.dispatch_repository.get(
dispatch_id, tenant_id=context.tenant_id
)
self._assert_dispatch_context(
dispatch,
runtime="hermes",
runtime_execution_id=result.job_id,
tenant_id=result.tenant_id,
task_id=result.task_id,
trace_id=result.trace_id,
principal_id=context.principal_id,
provenance_id=provenance_id,
run_id=run_id,
)
if self.hermes is None:
raise OrchestrationError("Hermes runtime is not configured")
job = self.hermes.get(result.job_id, tenant_id=result.tenant_id)
if result.state in {HermesJobState.COMPLETED, HermesJobState.FAILED}:
if not result.worker_id:
raise OrchestrationError("terminal Hermes result requires worker_id")
if job.assigned_worker_id != result.worker_id:
raise OrchestrationError("Hermes result worker does not own job lease")
if (
dispatch.expected_worker_id is not None
and dispatch.expected_worker_id != result.worker_id
):
raise OrchestrationError("Hermes result worker mismatch")
result_digest = digest_payload(
{
"job_id": result.job_id,
"worker_id": result.worker_id,
"state": result.state.value,
"output": result.output,
"error": result.error,
"finished_at": result.finished_at,
}
)
if dispatch.state in TERMINAL_DISPATCH_STATES:
if dispatch.result_digest != result_digest:
raise DispatchConflict("terminal dispatch received a different result")
return self.control_plane.get_task(context, dispatch.task_id)
task = self.control_plane.get_task(context, dispatch.task_id)
if task.state != TaskState.RUNNING:
raise OrchestrationError("task is not RUNNING for active dispatch")
if result.state == HermesJobState.COMPLETED:
target = TaskState.COMPLETED
values = {"result": result.output or {}}
dispatch_state = DispatchState.COMPLETED
elif result.state == HermesJobState.FAILED:
target = TaskState.FAILED
values = {"error": result.error or {"code": "hermes_failed"}}
dispatch_state = DispatchState.FAILED
elif result.state == HermesJobState.CANCELLED:
target = TaskState.CANCELLED
values = {}
dispatch_state = DispatchState.CANCELLED
else:
raise OrchestrationError("Hermes reconcile only accepts terminal results")
updated_task = self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=target,
expected_revision=task.revision,
**values,
)
self.dispatch_repository.update(
dispatch.dispatch_id,
tenant_id=dispatch.tenant_id,
state=dispatch_state,
expected_worker_id=result.worker_id,
result_digest=result_digest,
)
return updated_task
def dispatch_snapshot(self, *, tenant_id: str) -> Mapping[str, DispatchRecord]:
return {
item.task_id: item
for item in self.dispatch_repository.list(tenant_id=tenant_id)
}
+181
View File
@@ -0,0 +1,181 @@
"""Durable single-process persistence for the AIOS V2 control plane.
The candidate uses an atomic SQLite snapshot so a gateway restart does not lose
tenants, agents, task state, idempotency records, or audit events. The domain
service remains storage-agnostic; a later HA backend can replace this module
without changing API or runtime-adapter contracts.
"""
from __future__ import annotations
import json
import sqlite3
import threading
from dataclasses import asdict
from pathlib import Path
from typing import Any, Callable
from .control_plane import (
AgentRecord,
AuditEvent,
ControlPlaneService,
InMemoryControlPlaneStore,
TaskRecord,
TaskState,
TenantRecord,
)
class SQLiteSnapshotRepository:
"""Store one versioned control-plane snapshot in SQLite."""
SCHEMA_VERSION = 1
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
self._initialize()
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(self.path, timeout=30.0)
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
connection.execute("PRAGMA foreign_keys=ON")
return connection
def _initialize(self) -> None:
with self._connect() as connection:
connection.execute(
"""
CREATE TABLE IF NOT EXISTS control_plane_snapshot (
singleton_id INTEGER PRIMARY KEY CHECK (singleton_id = 1),
schema_version INTEGER NOT NULL,
payload_json TEXT NOT NULL,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP
)
"""
)
def load(self) -> dict[str, Any] | None:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT schema_version, payload_json FROM control_plane_snapshot WHERE singleton_id = 1"
).fetchone()
if row is None:
return None
schema_version, payload_json = row
if int(schema_version) != self.SCHEMA_VERSION:
raise RuntimeError(
f"unsupported control-plane snapshot version: {schema_version}"
)
decoded = json.loads(str(payload_json))
if not isinstance(decoded, dict):
raise RuntimeError("invalid control-plane snapshot")
return decoded
def save(self, payload: dict[str, Any]) -> None:
encoded = json.dumps(
payload,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
default=str,
)
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
connection.execute(
"""
INSERT INTO control_plane_snapshot (
singleton_id, schema_version, payload_json, updated_at
) VALUES (1, ?, ?, CURRENT_TIMESTAMP)
ON CONFLICT(singleton_id) DO UPDATE SET
schema_version = excluded.schema_version,
payload_json = excluded.payload_json,
updated_at = CURRENT_TIMESTAMP
""",
(self.SCHEMA_VERSION, encoded),
)
connection.commit()
class DurableControlPlaneService(ControlPlaneService):
"""Control-plane service that persists after every successful mutation."""
def __init__(
self,
repository: SQLiteSnapshotRepository,
*,
policy_evaluator=None,
) -> None:
self.repository = repository
store = InMemoryControlPlaneStore()
self._restore(store, repository.load())
super().__init__(store, policy_evaluator=policy_evaluator)
@staticmethod
def _restore(
store: InMemoryControlPlaneStore,
snapshot: dict[str, Any] | None,
) -> None:
if not snapshot:
return
for item in snapshot.get("tenants", []):
record = TenantRecord(**item)
store.tenants[record.tenant_id] = record
for item in snapshot.get("agents", []):
normalized = dict(item)
normalized["capabilities"] = tuple(normalized.get("capabilities", ()))
record = AgentRecord(**normalized)
store.agents[record.agent_id] = record
for item in snapshot.get("tasks", []):
normalized = dict(item)
normalized["state"] = TaskState(normalized["state"])
record = TaskRecord(**normalized)
store.tasks[record.task_id] = record
store.audit_events.extend(AuditEvent(**item) for item in snapshot.get("audit", []))
for item in snapshot.get("idempotency", []):
store.idempotency[(item["tenant_id"], item["key"])] = (
item["task_id"],
item["digest"],
)
def _snapshot(self) -> dict[str, Any]:
with self.store.lock:
return {
"schema_version": self.repository.SCHEMA_VERSION,
"tenants": [asdict(item) for item in self.store.tenants.values()],
"agents": [asdict(item) for item in self.store.agents.values()],
"tasks": [
{**asdict(item), "state": item.state.value}
for item in self.store.tasks.values()
],
"audit": [asdict(item) for item in self.store.audit_events],
"idempotency": [
{
"tenant_id": tenant_id,
"key": key,
"task_id": task_id,
"digest": digest,
}
for (tenant_id, key), (task_id, digest)
in self.store.idempotency.items()
],
}
def _mutate(self, operation: Callable[[], Any]) -> Any:
with self.store.lock:
result = operation()
self.repository.save(self._snapshot())
return result
def register_tenant(self, *args, **kwargs):
return self._mutate(lambda: super(DurableControlPlaneService, self).register_tenant(*args, **kwargs))
def register_agent(self, *args, **kwargs):
return self._mutate(lambda: super(DurableControlPlaneService, self).register_agent(*args, **kwargs))
def create_task(self, *args, **kwargs):
return self._mutate(lambda: super(DurableControlPlaneService, self).create_task(*args, **kwargs))
def transition_task(self, *args, **kwargs):
return self._mutate(lambda: super(DurableControlPlaneService, self).transition_task(*args, **kwargs))
+831
View File
@@ -0,0 +1,831 @@
"""AIOS V2 可信 Run Provenance 签发、持久化与受控写入。
生产策略要求 Provenance 同时覆盖七类路径:代码变更、Git 操作、部署、
Runtime 执行、Evidence 写入、回滚和审计。任何缺失、篡改、过期、撤销、
重放或上下文不匹配都默认拒绝。
"""
from __future__ import annotations
import base64
import hashlib
import json
import os
import sqlite3
import stat
import threading
import uuid
from dataclasses import asdict, dataclass, field, replace
from datetime import datetime, timedelta, timezone
from enum import Enum
from pathlib import Path
from typing import Any, Mapping, Protocol, Sequence
PROVENANCE_VERSION = "aios.v2.run-provenance.v1"
PRODUCTION_POLICY_VERSION = "aios.v2.production.v1"
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def parse_timestamp(value: str) -> datetime:
normalized = str(value or "").strip()
if not normalized:
raise ValueError("timestamp is required")
if normalized.endswith("Z"):
normalized = normalized[:-1] + "+00:00"
parsed = datetime.fromisoformat(normalized)
if parsed.tzinfo is None:
raise ValueError("timestamp must include timezone")
return parsed.astimezone(timezone.utc)
def required(value: str, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
def canonical_json_bytes(value: Mapping[str, Any]) -> bytes:
return json.dumps(
dict(value),
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
default=str,
).encode("utf-8")
def digest_payload(value: Mapping[str, Any]) -> str:
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
def _validate_digest(value: str) -> str:
normalized = required(value, "request_digest").lower()
if len(normalized) != 64 or any(ch not in "0123456789abcdef" for ch in normalized):
raise ValueError("request_digest must be a SHA-256 hexadecimal digest")
return normalized
class ExecutionPath(str, Enum):
CODE_CHANGE = "code_change"
GIT_OPERATION = "git_operation"
DEPLOYMENT = "deployment"
RUNTIME_EXECUTE = "runtime_execute"
EVIDENCE_WRITE = "evidence_write"
ROLLBACK = "rollback"
AUDIT = "audit"
REQUIRED_PRODUCTION_PATHS = frozenset(item.value for item in ExecutionPath)
class GitOperation(str, Enum):
READ_REF = "read_ref"
FETCH = "fetch"
CREATE_BRANCH = "create_branch"
COMMIT = "commit"
MERGE = "merge"
PUSH = "push"
UPDATE_EVIDENCE = "update_evidence"
class ProvenanceStatus(str, Enum):
ISSUED = "issued"
VERIFIED = "verified"
USED = "used"
EXPIRED = "expired"
REVOKED = "revoked"
class ProvenanceError(RuntimeError):
"""Run Provenance 基础错误。"""
class ProvenanceDenied(ProvenanceError):
"""策略拒绝当前操作。"""
class ProvenanceNotFound(ProvenanceDenied):
"""未找到 Provenance。"""
class ProvenanceSignatureError(ProvenanceDenied):
"""签名无效。"""
class ProvenanceExpired(ProvenanceDenied):
"""Provenance 已过期。"""
class ProvenanceRevoked(ProvenanceDenied):
"""Provenance 已撤销。"""
class ProvenanceReplay(ProvenanceDenied):
"""检测到相同授权摘要重放。"""
class Signer(Protocol):
key_id: str
def sign(self, payload: bytes) -> str: ...
class SignatureVerifier(Protocol):
key_id: str
fingerprint: str
def verify(self, payload: bytes, signature: str) -> bool: ...
def _load_crypto() -> tuple[Any, Any, Any]:
try:
from cryptography.hazmat.primitives import serialization
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
Ed25519PrivateKey,
Ed25519PublicKey,
)
except ImportError as exc: # pragma: no cover - depends on deployment image
raise RuntimeError(
"cryptography package with Ed25519 support is required"
) from exc
return serialization, Ed25519PrivateKey, Ed25519PublicKey
def _check_private_key_file(path: Path) -> bytes:
resolved = path.resolve()
metadata = resolved.stat()
if not stat.S_ISREG(metadata.st_mode):
raise RuntimeError("private key reference is not a regular file")
if metadata.st_mode & 0o077:
raise RuntimeError("private key file permissions must be 0600 or stricter")
return resolved.read_bytes()
def _check_public_key_file(path: Path) -> bytes:
resolved = path.resolve()
metadata = resolved.stat()
if not stat.S_ISREG(metadata.st_mode):
raise RuntimeError("public key reference is not a regular file")
if metadata.st_mode & 0o022:
raise RuntimeError("public key file must not be group/world writable")
return resolved.read_bytes()
class Ed25519PrivateKeySigner:
"""Ed25519 Owner/Control Plane 签发器。"""
def __init__(self, private_key: Any, *, key_id: str) -> None:
self.private_key = private_key
self.key_id = required(key_id, "key_id")
@classmethod
def from_file(cls, path: str | Path, *, key_id: str) -> "Ed25519PrivateKeySigner":
serialization, private_cls, _ = _load_crypto()
value = _check_private_key_file(Path(path))
if value.startswith(b"-----BEGIN"):
key = serialization.load_pem_private_key(value, password=None)
elif len(value) == 32:
key = private_cls.from_private_bytes(value)
else:
raise RuntimeError("private key must be PEM or a raw 32-byte Ed25519 seed")
if not isinstance(key, private_cls):
raise RuntimeError("private key is not Ed25519")
return cls(key, key_id=key_id)
def sign(self, payload: bytes) -> str:
return base64.b64encode(self.private_key.sign(bytes(payload))).decode("ascii")
def public_verifier(self) -> "Ed25519PublicKeyVerifier":
return Ed25519PublicKeyVerifier(self.private_key.public_key(), key_id=self.key_id)
class Ed25519PublicKeyVerifier:
"""Ed25519 签名验证器。"""
def __init__(self, public_key: Any, *, key_id: str) -> None:
serialization, _, public_cls = _load_crypto()
if not isinstance(public_key, public_cls):
raise RuntimeError("public key is not Ed25519")
self.public_key = public_key
self.key_id = required(key_id, "key_id")
raw = public_key.public_bytes(
encoding=serialization.Encoding.Raw,
format=serialization.PublicFormat.Raw,
)
self.fingerprint = hashlib.sha256(raw).hexdigest()
@classmethod
def from_file(cls, path: str | Path, *, key_id: str) -> "Ed25519PublicKeyVerifier":
serialization, _, public_cls = _load_crypto()
value = _check_public_key_file(Path(path))
if value.startswith(b"-----BEGIN"):
key = serialization.load_pem_public_key(value)
elif len(value) == 32:
key = public_cls.from_public_bytes(value)
else:
raise RuntimeError("public key must be PEM or raw 32-byte Ed25519 key")
if not isinstance(key, public_cls):
raise RuntimeError("public key is not Ed25519")
return cls(key, key_id=key_id)
def verify(self, payload: bytes, signature: str) -> bool:
try:
decoded = base64.b64decode(required(signature, "signature"), validate=True)
self.public_key.verify(decoded, bytes(payload))
return True
except Exception:
return False
@dataclass(frozen=True)
class RunProvenance:
provenance_id: str
run_id: str
issuer: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
allowed_paths: Sequence[str]
allowed_git_operations: Sequence[str]
issued_at: str
expires_at: str
policy_version: str
key_id: str
nonce: str
signature: str = ""
schema_version: str = PROVENANCE_VERSION
def __post_init__(self) -> None:
for name in (
"provenance_id",
"run_id",
"issuer",
"tenant_id",
"task_id",
"agent_id",
"principal_id",
"issued_at",
"expires_at",
"policy_version",
"key_id",
"nonce",
"schema_version",
):
object.__setattr__(self, name, required(getattr(self, name), name))
if self.schema_version != PROVENANCE_VERSION:
raise ValueError(f"unsupported schema_version: {self.schema_version}")
issued = parse_timestamp(self.issued_at)
expires = parse_timestamp(self.expires_at)
if expires <= issued:
raise ValueError("expires_at must be later than issued_at")
paths = tuple(sorted({ExecutionPath(item).value for item in self.allowed_paths}))
operations = tuple(
sorted({GitOperation(item).value for item in self.allowed_git_operations})
)
object.__setattr__(self, "allowed_paths", paths)
object.__setattr__(self, "allowed_git_operations", operations)
object.__setattr__(self, "signature", str(self.signature or "").strip())
def unsigned_dict(self) -> dict[str, Any]:
return {
"schema_version": self.schema_version,
"provenance_id": self.provenance_id,
"run_id": self.run_id,
"issuer": self.issuer,
"tenant_id": self.tenant_id,
"task_id": self.task_id,
"agent_id": self.agent_id,
"principal_id": self.principal_id,
"allowed_paths": list(self.allowed_paths),
"allowed_git_operations": list(self.allowed_git_operations),
"issued_at": self.issued_at,
"expires_at": self.expires_at,
"policy_version": self.policy_version,
"key_id": self.key_id,
"nonce": self.nonce,
}
def canonical_bytes(self) -> bytes:
return canonical_json_bytes(self.unsigned_dict())
def as_dict(self) -> dict[str, Any]:
value = self.unsigned_dict()
value["signature"] = self.signature
return value
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "RunProvenance":
return cls(**dict(value))
class ProvenanceIssuer:
"""只由 Owner 或 AIOS Control Plane 持有的签发服务。"""
def __init__(self, signer: Signer, store: "SQLiteProvenanceStore") -> None:
self.signer = signer
self.store = store
def issue(
self,
*,
run_id: str,
issuer: str,
tenant_id: str,
task_id: str,
agent_id: str,
principal_id: str,
allowed_paths: Sequence[str] = tuple(REQUIRED_PRODUCTION_PATHS),
allowed_git_operations: Sequence[str] = tuple(item.value for item in GitOperation),
ttl_seconds: int = 3600,
policy_version: str = PRODUCTION_POLICY_VERSION,
provenance_id: str | None = None,
nonce: str | None = None,
now: datetime | None = None,
) -> RunProvenance:
if ttl_seconds <= 0:
raise ValueError("ttl_seconds must be positive")
normalized_paths = frozenset(ExecutionPath(item).value for item in allowed_paths)
if policy_version == PRODUCTION_POLICY_VERSION and normalized_paths != REQUIRED_PRODUCTION_PATHS:
missing = sorted(REQUIRED_PRODUCTION_PATHS - normalized_paths)
extra = sorted(normalized_paths - REQUIRED_PRODUCTION_PATHS)
raise ProvenanceDenied(
f"production provenance must cover exactly seven paths; missing={missing}, extra={extra}"
)
normalized_operations = tuple(
sorted({GitOperation(item).value for item in allowed_git_operations})
)
if ExecutionPath.GIT_OPERATION.value in normalized_paths and not normalized_operations:
raise ProvenanceDenied("git_operation path requires explicit allowed Git operations")
issued = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
unsigned = RunProvenance(
provenance_id=provenance_id or f"prov_{uuid.uuid4().hex}",
run_id=run_id,
issuer=issuer,
tenant_id=tenant_id,
task_id=task_id,
agent_id=agent_id,
principal_id=principal_id,
allowed_paths=tuple(normalized_paths),
allowed_git_operations=normalized_operations,
issued_at=issued.isoformat().replace("+00:00", "Z"),
expires_at=(issued + timedelta(seconds=ttl_seconds))
.isoformat()
.replace("+00:00", "Z"),
policy_version=policy_version,
key_id=self.signer.key_id,
nonce=nonce or uuid.uuid4().hex,
)
signed = replace(unsigned, signature=self.signer.sign(unsigned.canonical_bytes()))
self.store.save_issued(signed)
return signed
@dataclass(frozen=True)
class ProvenanceAuthorization:
authorization_id: str
provenance_id: str
run_id: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
execution_path: str
git_operation: str | None
request_digest: str
policy_version: str
key_id: str
public_key_fingerprint: str
authorized_at: str = field(default_factory=utc_now)
def as_dict(self) -> dict[str, Any]:
return asdict(self)
class SQLiteProvenanceStore:
"""持久化 Provenance、状态、授权使用和不可变事件。"""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
self._connection = sqlite3.connect(
str(self.path), timeout=30.0, check_same_thread=False
)
self._connection.row_factory = sqlite3.Row
with self._lock:
self._connection.execute("PRAGMA journal_mode=WAL")
self._connection.execute("PRAGMA synchronous=FULL")
self._connection.execute("PRAGMA foreign_keys=ON")
self._connection.executescript(
"""
CREATE TABLE IF NOT EXISTS provenance_records (
provenance_id TEXT PRIMARY KEY,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
signature_verified INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS provenance_usage (
authorization_id TEXT PRIMARY KEY,
provenance_id TEXT NOT NULL,
execution_path TEXT NOT NULL,
git_operation TEXT NOT NULL DEFAULT '',
request_digest TEXT NOT NULL,
authorized_at TEXT NOT NULL,
receipt_json TEXT NOT NULL,
UNIQUE(provenance_id, execution_path, git_operation, request_digest),
FOREIGN KEY(provenance_id) REFERENCES provenance_records(provenance_id)
);
CREATE TABLE IF NOT EXISTS provenance_events (
event_id TEXT PRIMARY KEY,
provenance_id TEXT NOT NULL,
event_type TEXT NOT NULL,
details_json TEXT NOT NULL,
created_at TEXT NOT NULL,
FOREIGN KEY(provenance_id) REFERENCES provenance_records(provenance_id)
);
CREATE INDEX IF NOT EXISTS idx_provenance_usage_id
ON provenance_usage(provenance_id, authorized_at);
CREATE INDEX IF NOT EXISTS idx_provenance_events_id
ON provenance_events(provenance_id, created_at);
"""
)
self._connection.commit()
def close(self) -> None:
with self._lock:
self._connection.close()
def _event(
self,
provenance_id: str,
event_type: str,
details: Mapping[str, Any] | None = None,
) -> None:
self._connection.execute(
"INSERT INTO provenance_events VALUES (?, ?, ?, ?, ?)",
(
f"pevt_{uuid.uuid4().hex}",
provenance_id,
event_type,
json.dumps(dict(details or {}), ensure_ascii=False, sort_keys=True),
utc_now(),
),
)
def save_issued(self, provenance: RunProvenance) -> None:
payload = json.dumps(
provenance.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
)
now = utc_now()
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
prior = self._connection.execute(
"SELECT payload_json FROM provenance_records WHERE provenance_id = ?",
(provenance.provenance_id,),
).fetchone()
if prior is not None:
if prior["payload_json"] != payload:
raise ProvenanceDenied("provenance_id reused with different payload")
self._connection.rollback()
return
self._connection.execute(
"INSERT INTO provenance_records VALUES (?, ?, ?, 0, ?, ?)",
(
provenance.provenance_id,
payload,
ProvenanceStatus.ISSUED.value,
now,
now,
),
)
self._event(provenance.provenance_id, "issued")
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def get(self, provenance_id: str) -> RunProvenance:
with self._lock:
row = self._connection.execute(
"SELECT payload_json FROM provenance_records WHERE provenance_id = ?",
(required(provenance_id, "provenance_id"),),
).fetchone()
if row is None:
raise ProvenanceNotFound("provenance not found")
value = json.loads(row["payload_json"])
if not isinstance(value, Mapping):
raise ProvenanceError("stored provenance payload is invalid")
return RunProvenance.from_dict(value)
def status(self, provenance_id: str) -> ProvenanceStatus:
with self._lock:
row = self._connection.execute(
"SELECT status FROM provenance_records WHERE provenance_id = ?",
(required(provenance_id, "provenance_id"),),
).fetchone()
if row is None:
raise ProvenanceNotFound("provenance not found")
return ProvenanceStatus(row["status"])
def mark_verified(self, provenance_id: str, *, fingerprint: str) -> None:
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
current = self.status(provenance_id)
if current in {ProvenanceStatus.REVOKED, ProvenanceStatus.EXPIRED}:
raise ProvenanceDenied(f"cannot verify provenance in state {current.value}")
next_status = (
ProvenanceStatus.USED.value
if current == ProvenanceStatus.USED
else ProvenanceStatus.VERIFIED.value
)
self._connection.execute(
"UPDATE provenance_records SET status = ?, signature_verified = 1, updated_at = ? WHERE provenance_id = ?",
(next_status, utc_now(), provenance_id),
)
self._event(
provenance_id,
"verified",
{"public_key_fingerprint": fingerprint},
)
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def mark_expired(self, provenance_id: str) -> None:
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
current = self.status(provenance_id)
if current == ProvenanceStatus.REVOKED:
self._connection.rollback()
return
self._connection.execute(
"UPDATE provenance_records SET status = ?, updated_at = ? WHERE provenance_id = ?",
(ProvenanceStatus.EXPIRED.value, utc_now(), provenance_id),
)
self._event(provenance_id, "expired")
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def revoke(self, provenance_id: str, *, reason: str, principal_id: str) -> None:
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
self.get(provenance_id)
self._connection.execute(
"UPDATE provenance_records SET status = ?, updated_at = ? WHERE provenance_id = ?",
(ProvenanceStatus.REVOKED.value, utc_now(), provenance_id),
)
self._event(
provenance_id,
"revoked",
{
"reason": required(reason, "reason"),
"principal_id": required(principal_id, "principal_id"),
},
)
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def record_authorization(self, authorization: ProvenanceAuthorization) -> None:
receipt = json.dumps(
authorization.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
)
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
current = self.status(authorization.provenance_id)
if current in {ProvenanceStatus.REVOKED, ProvenanceStatus.EXPIRED}:
raise ProvenanceDenied(f"provenance state is {current.value}")
try:
self._connection.execute(
"INSERT INTO provenance_usage VALUES (?, ?, ?, ?, ?, ?, ?)",
(
authorization.authorization_id,
authorization.provenance_id,
authorization.execution_path,
authorization.git_operation or "",
authorization.request_digest,
authorization.authorized_at,
receipt,
),
)
except sqlite3.IntegrityError as exc:
raise ProvenanceReplay(
"identical provenance path/operation/request digest already used"
) from exc
self._connection.execute(
"UPDATE provenance_records SET status = ?, updated_at = ? WHERE provenance_id = ?",
(
ProvenanceStatus.USED.value,
authorization.authorized_at,
authorization.provenance_id,
),
)
self._event(
authorization.provenance_id,
"used",
{
"authorization_id": authorization.authorization_id,
"execution_path": authorization.execution_path,
"git_operation": authorization.git_operation,
"request_digest": authorization.request_digest,
},
)
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def authorization_count(self, provenance_id: str) -> int:
with self._lock:
row = self._connection.execute(
"SELECT COUNT(*) AS total FROM provenance_usage WHERE provenance_id = ?",
(required(provenance_id, "provenance_id"),),
).fetchone()
return int(row["total"])
def events(self, provenance_id: str) -> list[dict[str, Any]]:
with self._lock:
rows = self._connection.execute(
"SELECT event_type, details_json, created_at FROM provenance_events WHERE provenance_id = ? ORDER BY created_at, event_id",
(required(provenance_id, "provenance_id"),),
).fetchall()
return [
{
"event_type": row["event_type"],
"details": json.loads(row["details_json"]),
"created_at": row["created_at"],
}
for row in rows
]
class ProvenanceVerifier:
"""验证 Owner 签名、上下文、路径、Git 操作、时效和重放。"""
def __init__(
self,
store: SQLiteProvenanceStore,
verifiers: Mapping[str, SignatureVerifier],
) -> None:
if not verifiers:
raise ValueError("at least one public key verifier is required")
self.store = store
self.verifiers = {required(key, "key_id"): value for key, value in verifiers.items()}
def authorize(
self,
*,
provenance_id: str,
run_id: str,
tenant_id: str,
task_id: str,
agent_id: str,
principal_id: str,
execution_path: str,
request_digest: str,
git_operation: str | None = None,
now: datetime | None = None,
) -> ProvenanceAuthorization:
provenance = self.store.get(provenance_id)
status = self.store.status(provenance.provenance_id)
if status == ProvenanceStatus.REVOKED:
raise ProvenanceRevoked("provenance is revoked")
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
if current >= parse_timestamp(provenance.expires_at):
self.store.mark_expired(provenance.provenance_id)
raise ProvenanceExpired("provenance is expired")
verifier = self.verifiers.get(provenance.key_id)
if verifier is None:
raise ProvenanceSignatureError("no trusted public key for provenance key_id")
if not provenance.signature or not verifier.verify(
provenance.canonical_bytes(), provenance.signature
):
raise ProvenanceSignatureError("invalid provenance signature")
expected = {
"run_id": required(run_id, "run_id"),
"tenant_id": required(tenant_id, "tenant_id"),
"task_id": required(task_id, "task_id"),
"agent_id": required(agent_id, "agent_id"),
"principal_id": required(principal_id, "principal_id"),
}
for field_name, expected_value in expected.items():
if getattr(provenance, field_name) != expected_value:
raise ProvenanceDenied(f"provenance {field_name} mismatch")
path = ExecutionPath(execution_path).value
if path not in provenance.allowed_paths:
raise ProvenanceDenied(f"execution path is not allowed: {path}")
operation: str | None = None
if path == ExecutionPath.GIT_OPERATION.value:
if git_operation is None:
raise ProvenanceDenied("git operation is required for git_operation path")
operation = GitOperation(git_operation).value
if operation not in provenance.allowed_git_operations:
raise ProvenanceDenied(f"Git operation is not allowed: {operation}")
elif git_operation is not None:
raise ProvenanceDenied("git_operation is only valid for git_operation path")
digest = _validate_digest(request_digest)
self.store.mark_verified(
provenance.provenance_id, fingerprint=verifier.fingerprint
)
authorization = ProvenanceAuthorization(
authorization_id=f"pauth_{uuid.uuid4().hex}",
provenance_id=provenance.provenance_id,
run_id=provenance.run_id,
tenant_id=provenance.tenant_id,
task_id=provenance.task_id,
agent_id=provenance.agent_id,
principal_id=provenance.principal_id,
execution_path=path,
git_operation=operation,
request_digest=digest,
policy_version=provenance.policy_version,
key_id=provenance.key_id,
public_key_fingerprint=verifier.fingerprint,
)
self.store.record_authorization(authorization)
return authorization
class ProvenanceControlledWriter:
"""七路径统一策略入口并持久写入授权回执。"""
def __init__(
self,
verifier: ProvenanceVerifier,
receipt_root: str | Path,
*,
writer_id: str = "aios-v2-provenance-writer",
) -> None:
self.verifier = verifier
self.receipt_root = Path(receipt_root).resolve()
self.receipt_root.mkdir(parents=True, exist_ok=True)
self.writer_id = required(writer_id, "writer_id")
self._lock = threading.RLock()
@staticmethod
def _component(value: str) -> str:
normalized = required(value, "path component")
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
raise ProvenanceDenied("invalid receipt path component")
return normalized
def authorize(self, **values: Any) -> ProvenanceAuthorization:
authorization = self.verifier.authorize(**values)
tenant = self._component(authorization.tenant_id)
provenance_id = self._component(authorization.provenance_id)
target_dir = self.receipt_root / tenant / provenance_id
target = target_dir / f"{authorization.authorization_id}.json"
payload = authorization.as_dict()
payload["writer_id"] = self.writer_id
with self._lock:
target_dir.mkdir(parents=True, exist_ok=True)
temporary = target.with_suffix(f".tmp-{os.getpid()}")
temporary.write_text(
json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2) + "\n",
encoding="utf-8",
)
os.chmod(temporary, 0o640)
os.replace(temporary, target)
return authorization
def authorize_code_change(self, **values: Any) -> ProvenanceAuthorization:
return self.authorize(execution_path=ExecutionPath.CODE_CHANGE.value, **values)
def authorize_git_operation(
self, *, git_operation: str, **values: Any
) -> ProvenanceAuthorization:
return self.authorize(
execution_path=ExecutionPath.GIT_OPERATION.value,
git_operation=git_operation,
**values,
)
def authorize_deployment(self, **values: Any) -> ProvenanceAuthorization:
return self.authorize(execution_path=ExecutionPath.DEPLOYMENT.value, **values)
def authorize_runtime_execute(self, **values: Any) -> ProvenanceAuthorization:
return self.authorize(execution_path=ExecutionPath.RUNTIME_EXECUTE.value, **values)
def authorize_evidence_write(self, **values: Any) -> ProvenanceAuthorization:
return self.authorize(execution_path=ExecutionPath.EVIDENCE_WRITE.value, **values)
def authorize_rollback(self, **values: Any) -> ProvenanceAuthorization:
return self.authorize(execution_path=ExecutionPath.ROLLBACK.value, **values)
def authorize_audit(self, **values: Any) -> ProvenanceAuthorization:
return self.authorize(execution_path=ExecutionPath.AUDIT.value, **values)
@@ -0,0 +1,381 @@
#!/usr/bin/env python3
"""AIOS V2 Run Provenance 与最小权限 Grant 运维 CLI。
私钥只用于签发;授权命令只加载一个与 ``--path`` 对应的 Grant。所有输出均为
不含 Secret 的 JSON。旧 ``issue`` 仅为候选兼容,生产必须使用
``issue-workflow`` 与 ``issue-grant``。
"""
from __future__ import annotations
import argparse
import json
import os
import sys
from pathlib import Path
from typing import Any, Mapping, Sequence
from .provenance import (
Ed25519PrivateKeySigner,
Ed25519PublicKeyVerifier,
ExecutionPath,
GitOperation,
ProvenanceIssuer,
SQLiteProvenanceStore,
)
from .provenance_grants import (
GrantIssuer,
GrantType,
GrantVerifier,
SQLiteGrantStore,
WorkflowProvenanceIssuer,
)
from .provenance_operations import (
OperationContext,
ProvenanceOperationGate,
context_from_environment,
load_request_file,
)
from .provenance_scoped import ScopedLeastPrivilegeProvenanceWriter
def _json_object(value: str | None, file_path: str | None) -> Mapping[str, Any]:
if value and file_path:
raise ValueError("request-json and request-file are mutually exclusive")
if file_path:
return load_request_file(file_path)
parsed = json.loads(value or "{}")
if not isinstance(parsed, Mapping):
raise ValueError("request JSON must be an object")
return dict(parsed)
def _csv(value: str | None) -> tuple[str, ...]:
return tuple(item.strip() for item in str(value or "").split(",") if item.strip())
def _write_json(path: str | None, payload: Mapping[str, Any]) -> None:
encoded = json.dumps(dict(payload), ensure_ascii=False, sort_keys=True, indent=2) + "\n"
if path:
target = Path(path).resolve()
target.parent.mkdir(parents=True, exist_ok=True)
temporary = target.with_suffix(f".tmp-{os.getpid()}")
temporary.write_text(encoded, encoding="utf-8")
os.chmod(temporary, 0o640)
os.replace(temporary, target)
print(encoded, end="")
def _parent_store(args: argparse.Namespace) -> SQLiteProvenanceStore:
return SQLiteProvenanceStore(args.store_file)
def _grant_store(args: argparse.Namespace) -> SQLiteGrantStore:
return SQLiteGrantStore(args.store_file)
def _context(args: argparse.Namespace) -> OperationContext:
if args.context_from_env:
return context_from_environment()
values = {
"provenance_id": args.provenance_id,
"run_id": args.run_id,
"tenant_id": args.tenant_id,
"task_id": args.task_id,
"agent_id": args.agent_id,
"principal_id": args.principal_id,
}
missing = [name for name, value in values.items() if not str(value or "").strip()]
if missing:
raise ValueError(f"missing context arguments: {missing}")
return OperationContext(**{name: str(value).strip() for name, value in values.items()})
def command_issue_legacy(args: argparse.Namespace) -> int:
store = _parent_store(args)
signer = Ed25519PrivateKeySigner.from_file(args.private_key_file, key_id=args.key_id)
provenance = ProvenanceIssuer(signer, store).issue(
run_id=args.run_id,
issuer=args.issuer,
tenant_id=args.tenant_id,
task_id=args.task_id,
agent_id=args.agent_id,
principal_id=args.principal_id,
allowed_paths=_csv(args.allowed_paths) or tuple(item.value for item in ExecutionPath),
allowed_git_operations=_csv(args.allowed_git_operations)
or tuple(item.value for item in GitOperation),
ttl_seconds=args.ttl_seconds,
policy_version=args.policy_version,
)
_write_json(
args.output,
{
"mode": "legacy-full-rights-candidate-only",
"provenance": provenance.as_dict(),
"status": store.status(provenance.provenance_id).value,
"secret_value_stored": False,
},
)
return 0
def command_issue_workflow(args: argparse.Namespace) -> int:
store = _parent_store(args)
signer = Ed25519PrivateKeySigner.from_file(args.private_key_file, key_id=args.key_id)
workflow = WorkflowProvenanceIssuer(signer, store).issue(
run_id=args.run_id,
issuer=args.issuer,
tenant_id=args.tenant_id,
task_id=args.task_id,
agent_id=args.agent_id,
principal_id=args.principal_id,
ttl_seconds=args.ttl_seconds,
)
_write_json(
args.output,
{
"mode": "least-privilege-workflow",
"workflow_provenance": workflow.as_dict(),
"status": store.status(workflow.provenance_id).value,
"secret_value_stored": False,
},
)
return 0
def command_issue_grant(args: argparse.Namespace) -> int:
parent_store = _parent_store(args)
grant_store = _grant_store(args)
signer = Ed25519PrivateKeySigner.from_file(args.private_key_file, key_id=args.key_id)
grant = GrantIssuer(signer, parent_store, grant_store).issue(
parent_provenance_id=args.parent_provenance_id,
grant_type=GrantType(args.grant_type),
ttl_seconds=args.ttl_seconds,
allowed_git_operations=_csv(args.allowed_git_operations),
)
_write_json(
args.output,
{
"grant": grant.as_dict(),
"status": grant_store.status(grant.grant_id).value,
"secret_value_stored": False,
},
)
return 0
def _single_scope_writer(args: argparse.Namespace) -> ScopedLeastPrivilegeProvenanceWriter:
path = ExecutionPath(args.path).value
parent_store = _parent_store(args)
grant_store = _grant_store(args)
verifier = Ed25519PublicKeyVerifier.from_file(args.public_key_file, key_id=args.key_id)
trusted = GrantVerifier(parent_store, grant_store, {args.key_id: verifier})
return ScopedLeastPrivilegeProvenanceWriter(
trusted,
args.receipt_dir,
{path: args.grant_id},
required_paths=(path,),
writer_id=f"aios-v2-cli-{path}",
)
def command_authorize(args: argparse.Namespace) -> int:
writer = _single_scope_writer(args)
context = _context(args)
receipt = ProvenanceOperationGate(writer).authorize(
context,
execution_path=args.path,
operation=args.operation,
request=_json_object(args.request_json, args.request_file),
)
_write_json(args.output, {"authorization": receipt.as_dict()})
return 0
def command_revoke(args: argparse.Namespace) -> int:
store = _parent_store(args)
store.revoke(args.provenance_id, reason=args.reason, principal_id=args.principal_id)
_write_json(
args.output,
{"provenance_id": args.provenance_id, "status": store.status(args.provenance_id).value},
)
return 0
def command_status(args: argparse.Namespace) -> int:
store = _parent_store(args)
provenance = store.get(args.provenance_id)
grant_store = _grant_store(args)
_write_json(
args.output,
{
"provenance": provenance.as_dict(),
"status": store.status(args.provenance_id).value,
"authorization_count": store.authorization_count(args.provenance_id),
"events": store.events(args.provenance_id),
"grants": [item.as_dict() for item in grant_store.list_for_parent(args.provenance_id)],
},
)
return 0
def command_grant_revoke(args: argparse.Namespace) -> int:
store = _grant_store(args)
store.revoke(args.grant_id, reason=args.reason, principal_id=args.principal_id)
_write_json(
args.output,
{"grant_id": args.grant_id, "status": store.status(args.grant_id).value},
)
return 0
def command_grant_status(args: argparse.Namespace) -> int:
store = _grant_store(args)
grant = store.get(args.grant_id)
_write_json(
args.output,
{"grant": grant.as_dict(), "status": store.status(args.grant_id).value},
)
return 0
def add_common_store(parser: argparse.ArgumentParser) -> None:
parser.add_argument(
"--store-file",
default=os.getenv(
"AIOS_PROVENANCE_STORE_FILE",
"/var/lib/aios-v2/run-provenance.sqlite3",
),
)
parser.add_argument("--output", default=None)
def add_signing_context(parser: argparse.ArgumentParser) -> None:
parser.add_argument("--private-key-file", required=True)
parser.add_argument("--key-id", required=True)
def add_workflow_identity(parser: argparse.ArgumentParser) -> None:
parser.add_argument("--run-id", required=True)
parser.add_argument("--issuer", required=True)
parser.add_argument("--tenant-id", required=True)
parser.add_argument("--task-id", required=True)
parser.add_argument("--agent-id", required=True)
parser.add_argument("--principal-id", required=True)
def add_context(parser: argparse.ArgumentParser) -> None:
parser.add_argument("--context-from-env", action="store_true")
parser.add_argument("--provenance-id")
parser.add_argument("--run-id")
parser.add_argument("--tenant-id")
parser.add_argument("--task-id")
parser.add_argument("--agent-id")
parser.add_argument("--principal-id")
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(description="AIOS V2 Run Provenance CLI")
subcommands = parser.add_subparsers(dest="command", required=True)
issue = subcommands.add_parser("issue", help="候选兼容:签发全权限 Provenance;生产禁止")
add_common_store(issue)
add_signing_context(issue)
add_workflow_identity(issue)
issue.add_argument("--allowed-paths")
issue.add_argument("--allowed-git-operations")
issue.add_argument("--ttl-seconds", type=int, default=3600)
issue.add_argument("--policy-version", default="aios.v2.candidate.legacy")
issue.set_defaults(handler=command_issue_legacy)
workflow = subcommands.add_parser(
"issue-workflow", help="签发不含操作权限的父 Workflow Provenance"
)
add_common_store(workflow)
add_signing_context(workflow)
add_workflow_identity(workflow)
workflow.add_argument("--ttl-seconds", type=int, default=14400)
workflow.set_defaults(handler=command_issue_workflow)
grant = subcommands.add_parser("issue-grant", help="签发单一路径最小权限 Grant")
add_common_store(grant)
add_signing_context(grant)
grant.add_argument("--parent-provenance-id", required=True)
grant.add_argument("--grant-type", choices=[item.value for item in GrantType], required=True)
grant.add_argument("--allowed-git-operations")
grant.add_argument("--ttl-seconds", type=int, default=900)
grant.set_defaults(handler=command_issue_grant)
authorize = subcommands.add_parser("authorize", help="使用单一子 Grant 授权一次运维操作")
add_common_store(authorize)
add_context(authorize)
authorize.add_argument("--public-key-file", required=True)
authorize.add_argument("--key-id", required=True)
authorize.add_argument("--grant-id", required=True)
authorize.add_argument(
"--receipt-dir",
default=os.getenv(
"AIOS_PROVENANCE_RECEIPT_DIR",
"/var/lib/aios-v2/provenance-receipts",
),
)
authorize.add_argument(
"--path",
required=True,
choices=[
ExecutionPath.CODE_CHANGE.value,
ExecutionPath.DEPLOYMENT.value,
ExecutionPath.RUNTIME_EXECUTE.value,
ExecutionPath.EVIDENCE_WRITE.value,
ExecutionPath.ROLLBACK.value,
ExecutionPath.AUDIT.value,
],
)
authorize.add_argument("--operation", required=True)
request_group = authorize.add_mutually_exclusive_group()
request_group.add_argument("--request-json")
request_group.add_argument("--request-file")
authorize.set_defaults(handler=command_authorize)
revoke = subcommands.add_parser("revoke", help="撤销父 Workflow Provenance")
add_common_store(revoke)
revoke.add_argument("--provenance-id", required=True)
revoke.add_argument("--reason", required=True)
revoke.add_argument("--principal-id", required=True)
revoke.set_defaults(handler=command_revoke)
status = subcommands.add_parser("status", help="查询父 Workflow 与子 Grant")
add_common_store(status)
status.add_argument("--provenance-id", required=True)
status.set_defaults(handler=command_status)
grant_revoke = subcommands.add_parser("grant-revoke", help="单独撤销子 Grant")
add_common_store(grant_revoke)
grant_revoke.add_argument("--grant-id", required=True)
grant_revoke.add_argument("--reason", required=True)
grant_revoke.add_argument("--principal-id", required=True)
grant_revoke.set_defaults(handler=command_grant_revoke)
grant_status = subcommands.add_parser("grant-status", help="查询子 Grant 状态")
add_common_store(grant_status)
grant_status.add_argument("--grant-id", required=True)
grant_status.set_defaults(handler=command_grant_status)
return parser
def main(argv: Sequence[str] | None = None) -> int:
args = build_parser().parse_args(argv)
try:
return int(args.handler(args))
except Exception as exc:
print(
json.dumps(
{"status": "denied", "error": type(exc).__name__, "message": str(exc)},
ensure_ascii=False,
),
file=sys.stderr,
)
return 1
if __name__ == "__main__":
raise SystemExit(main())
@@ -0,0 +1,416 @@
"""受最小权限 Run Provenance Grant 约束的 Git 写入器。
所有 Git 操作都使用参数数组执行。对于 Commit 和 Evidence Commit,先计算
工作树内容摘要并完成 Provenance 授权,之后才允许执行 ``git add``,避免未授权
请求改变 Git Index。
"""
from __future__ import annotations
import hashlib
import os
import re
import subprocess
import uuid
from dataclasses import asdict, dataclass
from pathlib import Path
from typing import Any, Mapping, Protocol, Sequence
from .provenance import GitOperation, ProvenanceDenied, digest_payload, utc_now
_BRANCH_PATTERN = re.compile(r"^(?![-./])(?!.*\.\.)(?!.*//)[A-Za-z0-9._/-]{1,240}$")
_SECRET_URL = re.compile(r"(?i)(https?://)([^/@\s]+)@")
_TOKENISH = re.compile(r"(?i)(token|password|secret|authorization)([=:]\s*)([^\s]+)")
class GitAuthorizationWriter(Protocol):
def authorize_code_change(self, **values: Any) -> Any: ...
def authorize_git_operation(self, *, git_operation: str, **values: Any) -> Any: ...
class ProvenanceGitError(RuntimeError):
"""Git 操作被拒绝或执行失败。"""
@dataclass(frozen=True)
class GitExecutionContext:
provenance_id: str
run_id: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
@dataclass(frozen=True)
class GitCommandResult:
operation_id: str
operation: str
authorization_ids: Sequence[str]
command: Sequence[str]
exit_code: int
stdout: str
stderr: str
head_before: str | None
head_after: str | None
started_at: str
completed_at: str
def as_dict(self) -> dict[str, Any]:
return asdict(self)
class ProvenanceGitWriter:
"""执行经过单路径 Grant 授权的窄范围 Git 操作。"""
def __init__(
self,
repo: str | Path,
writer: GitAuthorizationWriter,
*,
timeout_seconds: float = 120.0,
output_limit: int = 16000,
) -> None:
self.repo = Path(repo).resolve()
self.writer = writer
self.timeout_seconds = float(timeout_seconds)
self.output_limit = int(output_limit)
if self.timeout_seconds <= 0 or self.output_limit < 1024:
raise ValueError("invalid Git writer limits")
self._run_raw(["rev-parse", "--is-inside-work-tree"], check=True)
@staticmethod
def _validate_branch(branch: str) -> str:
normalized = str(branch or "").strip()
if not _BRANCH_PATTERN.fullmatch(normalized) or normalized.endswith((".", "/")):
raise ProvenanceGitError("invalid Git branch name")
if normalized in {"main", "master"}:
raise ProvenanceGitError("direct main/master operation is prohibited")
return normalized
def _validate_path(self, value: str | Path) -> str:
raw = Path(value)
candidate = (self.repo / raw).resolve() if not raw.is_absolute() else raw.resolve()
try:
relative = candidate.relative_to(self.repo)
except ValueError as exc:
raise ProvenanceGitError("Git path escapes repository") from exc
if str(relative) in {"", "."}:
raise ProvenanceGitError("repository root is not a valid file path")
return relative.as_posix()
@staticmethod
def _redact(value: str, limit: int) -> str:
text = _SECRET_URL.sub(r"\1***@", str(value or ""))
text = _TOKENISH.sub(r"\1\2***", text)
if len(text) > limit:
return text[:limit] + "\n...[truncated]"
return text
def _head(self) -> str | None:
process = self._run_raw(["rev-parse", "HEAD"], check=False)
return process.stdout.strip() if process.returncode == 0 else None
def _run_raw(
self,
args: Sequence[str],
*,
check: bool,
env: Mapping[str, str] | None = None,
) -> subprocess.CompletedProcess[str]:
command = ["git", "-C", str(self.repo), *[str(item) for item in args]]
safe_env = {
**os.environ,
"GIT_TERMINAL_PROMPT": "0",
"GIT_CONFIG_NOSYSTEM": os.environ.get("GIT_CONFIG_NOSYSTEM", "1"),
}
if env:
safe_env.update({str(key): str(value) for key, value in env.items()})
process = subprocess.run(
command,
text=True,
capture_output=True,
timeout=self.timeout_seconds,
env=safe_env,
)
if check and process.returncode != 0:
raise ProvenanceGitError(
self._redact(process.stderr or process.stdout, self.output_limit)
or f"Git command failed with exit code {process.returncode}"
)
return process
def _path_digest(self, relative: str) -> str:
target = self.repo / relative
if target.exists():
if not target.is_file():
raise ProvenanceGitError("Git writer accepts file paths only")
hasher = hashlib.sha256()
with target.open("rb") as handle:
while True:
block = handle.read(65536)
if not block:
break
hasher.update(block)
return hasher.hexdigest()
tracked = self._run_raw(["ls-files", "--error-unmatch", "--", relative], check=False)
if tracked.returncode != 0:
raise ProvenanceGitError(f"path does not exist and is not tracked: {relative}")
return "deleted"
def _content_manifest(self, paths: Sequence[str]) -> Mapping[str, str]:
return {path: self._path_digest(path) for path in sorted(set(paths))}
def _authorize(
self,
context: GitExecutionContext,
*,
operation: GitOperation,
request: Mapping[str, Any],
code_change: bool,
) -> list[str]:
request_digest = digest_payload(
{
"operation": operation.value,
"repo": self.repo.name,
"request": dict(request),
"head": self._head(),
}
)
ids: list[str] = []
try:
if code_change:
code_authorization = self.writer.authorize_code_change(
provenance_id=context.provenance_id,
run_id=context.run_id,
tenant_id=context.tenant_id,
task_id=context.task_id,
agent_id=context.agent_id,
principal_id=context.principal_id,
request_digest=digest_payload(
{
"git_operation": operation.value,
"request_digest": request_digest,
}
),
)
ids.append(code_authorization.authorization_id)
git_authorization = self.writer.authorize_git_operation(
provenance_id=context.provenance_id,
run_id=context.run_id,
tenant_id=context.tenant_id,
task_id=context.task_id,
agent_id=context.agent_id,
principal_id=context.principal_id,
git_operation=operation.value,
request_digest=request_digest,
)
ids.append(git_authorization.authorization_id)
return ids
except ProvenanceDenied as exc:
raise ProvenanceGitError(f"Run Provenance denied Git operation: {exc}") from exc
def _run_authorized(
self,
*,
operation: GitOperation,
args: Sequence[str],
authorization_ids: Sequence[str],
) -> GitCommandResult:
started = utc_now()
before = self._head()
process = self._run_raw(args, check=False)
after = self._head()
result = GitCommandResult(
operation_id=f"gitop_{uuid.uuid4().hex}",
operation=operation.value,
authorization_ids=tuple(authorization_ids),
command=tuple(["git", "-C", "<repo>", *[str(item) for item in args]]),
exit_code=int(process.returncode),
stdout=self._redact(process.stdout, self.output_limit),
stderr=self._redact(process.stderr, self.output_limit),
head_before=before,
head_after=after,
started_at=started,
completed_at=utc_now(),
)
if process.returncode != 0:
raise ProvenanceGitError(
result.stderr or result.stdout or f"Git {operation.value} failed"
)
return result
def _execute(
self,
context: GitExecutionContext,
*,
operation: GitOperation,
args: Sequence[str],
request: Mapping[str, Any],
code_change: bool,
) -> GitCommandResult:
authorization_ids = self._authorize(
context,
operation=operation,
request=request,
code_change=code_change,
)
return self._run_authorized(
operation=operation,
args=args,
authorization_ids=authorization_ids,
)
def read_ref(self, context: GitExecutionContext, ref: str) -> GitCommandResult:
normalized = str(ref or "").strip()
if not normalized or any(ch.isspace() for ch in normalized):
raise ProvenanceGitError("invalid Git ref")
return self._execute(
context,
operation=GitOperation.READ_REF,
args=["rev-parse", "--verify", normalized],
request={"ref": normalized},
code_change=False,
)
def fetch(
self,
context: GitExecutionContext,
*,
remote: str,
refspecs: Sequence[str],
) -> GitCommandResult:
normalized_remote = str(remote or "").strip()
normalized_refspecs = tuple(str(item).strip() for item in refspecs if str(item).strip())
if not normalized_remote or not normalized_refspecs:
raise ProvenanceGitError("remote and refspecs are required")
if any(item.startswith("+") and ":refs/heads/" in item for item in normalized_refspecs):
raise ProvenanceGitError(
"fetching directly into local branch refs is prohibited; use remote-tracking refs"
)
return self._execute(
context,
operation=GitOperation.FETCH,
args=["fetch", "--prune", normalized_remote, *normalized_refspecs],
request={"remote": normalized_remote, "refspecs": normalized_refspecs},
code_change=False,
)
def create_branch(
self,
context: GitExecutionContext,
*,
branch: str,
start_point: str,
) -> GitCommandResult:
normalized = self._validate_branch(branch)
start = str(start_point or "").strip()
if not start:
raise ProvenanceGitError("start_point is required")
return self._execute(
context,
operation=GitOperation.CREATE_BRANCH,
args=["branch", normalized, start],
request={"branch": normalized, "start_point": start},
code_change=False,
)
def commit(
self,
context: GitExecutionContext,
*,
paths: Sequence[str | Path],
message: str,
) -> GitCommandResult:
normalized_paths = tuple(self._validate_path(item) for item in paths)
normalized_message = str(message or "").strip()
if not normalized_paths or not normalized_message:
raise ProvenanceGitError("commit paths and message are required")
if len(normalized_message) > 500:
raise ProvenanceGitError("commit message is too long")
request = {
"paths": normalized_paths,
"message": normalized_message,
"content_manifest": self._content_manifest(normalized_paths),
}
authorization_ids = self._authorize(
context,
operation=GitOperation.COMMIT,
request=request,
code_change=True,
)
self._run_raw(["add", "--", *normalized_paths], check=True)
return self._run_authorized(
operation=GitOperation.COMMIT,
args=["commit", "--no-gpg-sign", "-m", normalized_message, "--", *normalized_paths],
authorization_ids=authorization_ids,
)
def merge(
self,
context: GitExecutionContext,
*,
source_ref: str,
message: str,
) -> GitCommandResult:
source = str(source_ref or "").strip()
normalized_message = str(message or "").strip()
if not source or not normalized_message:
raise ProvenanceGitError("source_ref and message are required")
return self._execute(
context,
operation=GitOperation.MERGE,
args=["merge", "--no-ff", "--no-edit", "-m", normalized_message, source],
request={"source_ref": source, "message": normalized_message},
code_change=True,
)
def push(
self,
context: GitExecutionContext,
*,
remote: str,
branch: str,
) -> GitCommandResult:
normalized_remote = str(remote or "").strip()
normalized_branch = self._validate_branch(branch)
if not normalized_remote:
raise ProvenanceGitError("remote is required")
return self._execute(
context,
operation=GitOperation.PUSH,
args=["push", normalized_remote, f"refs/heads/{normalized_branch}:refs/heads/{normalized_branch}"],
request={"remote": normalized_remote, "branch": normalized_branch},
code_change=False,
)
def update_evidence(
self,
context: GitExecutionContext,
*,
paths: Sequence[str | Path],
message: str,
) -> GitCommandResult:
normalized_paths = tuple(self._validate_path(item) for item in paths)
normalized_message = str(message or "").strip()
if not normalized_paths or not normalized_message:
raise ProvenanceGitError("evidence paths and message are required")
if any(not path.startswith(".agent/") for path in normalized_paths):
raise ProvenanceGitError("UPDATE_EVIDENCE may only commit .agent/ paths")
request = {
"paths": normalized_paths,
"message": normalized_message,
"content_manifest": self._content_manifest(normalized_paths),
}
authorization_ids = self._authorize(
context,
operation=GitOperation.UPDATE_EVIDENCE,
request=request,
code_change=False,
)
self._run_raw(["add", "--", *normalized_paths], check=True)
return self._run_authorized(
operation=GitOperation.UPDATE_EVIDENCE,
args=["commit", "--no-gpg-sign", "-m", normalized_message, "--", *normalized_paths],
authorization_ids=authorization_ids,
)
@@ -0,0 +1,744 @@
"""AIOS V2 最小权限 Run Provenance 子 Grant。
父 Workflow Provenance 只绑定 run/tenant/task/agent/principal 身份,不直接授予
操作权限。每个子 Grant 只允许一个 ExecutionPath;Git Grant 还必须限定具体
GitOperation。子 Grant 具备独立 TTL、nonce、状态、撤销和重放防护。
"""
from __future__ import annotations
import json
import os
import sqlite3
import threading
import uuid
from dataclasses import asdict, dataclass, field, replace
from datetime import datetime, timedelta, timezone
from enum import Enum
from pathlib import Path
from typing import Any, Mapping, Sequence
from .provenance import (
ExecutionPath,
GitOperation,
ProvenanceDenied,
ProvenanceExpired,
ProvenanceIssuer,
ProvenanceNotFound,
ProvenanceReplay,
ProvenanceRevoked,
ProvenanceSignatureError,
ProvenanceStatus,
ProvenanceVerifier,
RunProvenance,
SQLiteProvenanceStore,
Signer,
SignatureVerifier,
_validate_digest,
canonical_json_bytes,
parse_timestamp,
required,
utc_now,
)
WORKFLOW_POLICY_VERSION = "aios.v2.workflow.v1"
GRANT_SCHEMA_VERSION = "aios.v2.provenance-grant.v1"
class GrantType(str, Enum):
CODE_CHANGE = "code_change"
GIT = "git"
DEPLOYMENT = "deployment"
RUNTIME = "runtime"
EVIDENCE = "evidence"
ROLLBACK = "rollback"
AUDIT = "audit"
GRANT_PATHS: Mapping[GrantType, ExecutionPath] = {
GrantType.CODE_CHANGE: ExecutionPath.CODE_CHANGE,
GrantType.GIT: ExecutionPath.GIT_OPERATION,
GrantType.DEPLOYMENT: ExecutionPath.DEPLOYMENT,
GrantType.RUNTIME: ExecutionPath.RUNTIME_EXECUTE,
GrantType.EVIDENCE: ExecutionPath.EVIDENCE_WRITE,
GrantType.ROLLBACK: ExecutionPath.ROLLBACK,
GrantType.AUDIT: ExecutionPath.AUDIT,
}
class GrantStatus(str, Enum):
ISSUED = "issued"
VERIFIED = "verified"
USED = "used"
EXPIRED = "expired"
REVOKED = "revoked"
@dataclass(frozen=True)
class ProvenanceGrant:
grant_id: str
parent_provenance_id: str
grant_type: GrantType
execution_path: ExecutionPath
run_id: str
issuer: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
allowed_git_operations: Sequence[str]
issued_at: str
expires_at: str
policy_version: str
key_id: str
nonce: str
signature: str = ""
schema_version: str = GRANT_SCHEMA_VERSION
def __post_init__(self) -> None:
for name in (
"grant_id",
"parent_provenance_id",
"run_id",
"issuer",
"tenant_id",
"task_id",
"agent_id",
"principal_id",
"issued_at",
"expires_at",
"policy_version",
"key_id",
"nonce",
"schema_version",
):
object.__setattr__(self, name, required(getattr(self, name), name))
if self.schema_version != GRANT_SCHEMA_VERSION:
raise ValueError(f"unsupported grant schema: {self.schema_version}")
grant_type = GrantType(self.grant_type)
path = ExecutionPath(self.execution_path)
if GRANT_PATHS[grant_type] != path:
raise ValueError("grant_type does not match execution_path")
object.__setattr__(self, "grant_type", grant_type)
object.__setattr__(self, "execution_path", path)
operations = tuple(
sorted({GitOperation(item).value for item in self.allowed_git_operations})
)
if grant_type == GrantType.GIT and not operations:
raise ValueError("Git Grant requires explicit Git operations")
if grant_type != GrantType.GIT and operations:
raise ValueError("only Git Grant may contain Git operations")
object.__setattr__(self, "allowed_git_operations", operations)
issued = parse_timestamp(self.issued_at)
expires = parse_timestamp(self.expires_at)
if expires <= issued:
raise ValueError("grant expires_at must be later than issued_at")
object.__setattr__(self, "signature", str(self.signature or "").strip())
def unsigned_dict(self) -> dict[str, Any]:
return {
"schema_version": self.schema_version,
"grant_id": self.grant_id,
"parent_provenance_id": self.parent_provenance_id,
"grant_type": self.grant_type.value,
"execution_path": self.execution_path.value,
"run_id": self.run_id,
"issuer": self.issuer,
"tenant_id": self.tenant_id,
"task_id": self.task_id,
"agent_id": self.agent_id,
"principal_id": self.principal_id,
"allowed_git_operations": list(self.allowed_git_operations),
"issued_at": self.issued_at,
"expires_at": self.expires_at,
"policy_version": self.policy_version,
"key_id": self.key_id,
"nonce": self.nonce,
}
def canonical_bytes(self) -> bytes:
return canonical_json_bytes(self.unsigned_dict())
def as_dict(self) -> dict[str, Any]:
value = self.unsigned_dict()
value["signature"] = self.signature
return value
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "ProvenanceGrant":
return cls(**dict(value))
@dataclass(frozen=True)
class GrantAuthorization:
authorization_id: str
grant_id: str
parent_provenance_id: str
run_id: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
execution_path: str
git_operation: str | None
request_digest: str
policy_version: str
key_id: str
public_key_fingerprint: str
authorized_at: str = field(default_factory=utc_now)
@property
def provenance_id(self) -> str:
return self.parent_provenance_id
def as_dict(self) -> dict[str, Any]:
return asdict(self)
class WorkflowProvenanceIssuer:
"""签发不携带操作权限的父 Workflow Provenance。"""
def __init__(self, signer: Signer, store: SQLiteProvenanceStore) -> None:
self._issuer = ProvenanceIssuer(signer, store)
def issue(
self,
*,
run_id: str,
issuer: str,
tenant_id: str,
task_id: str,
agent_id: str,
principal_id: str,
ttl_seconds: int = 14400,
provenance_id: str | None = None,
nonce: str | None = None,
now: datetime | None = None,
) -> RunProvenance:
return self._issuer.issue(
run_id=run_id,
issuer=issuer,
tenant_id=tenant_id,
task_id=task_id,
agent_id=agent_id,
principal_id=principal_id,
allowed_paths=(),
allowed_git_operations=(),
ttl_seconds=ttl_seconds,
policy_version=WORKFLOW_POLICY_VERSION,
provenance_id=provenance_id,
nonce=nonce,
now=now,
)
class SQLiteGrantStore:
"""在 Provenance SQLite 数据库中持久化子 Grant 与使用记录。"""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
self._connection = sqlite3.connect(
str(self.path), timeout=30.0, check_same_thread=False
)
self._connection.row_factory = sqlite3.Row
with self._lock:
self._connection.execute("PRAGMA journal_mode=WAL")
self._connection.execute("PRAGMA synchronous=FULL")
self._connection.execute("PRAGMA foreign_keys=ON")
self._connection.executescript(
"""
CREATE TABLE IF NOT EXISTS provenance_grants (
grant_id TEXT PRIMARY KEY,
parent_provenance_id TEXT NOT NULL,
grant_type TEXT NOT NULL,
execution_path TEXT NOT NULL,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
signature_verified INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_grants_parent
ON provenance_grants(parent_provenance_id, grant_type, status);
CREATE TABLE IF NOT EXISTS provenance_grant_usage (
authorization_id TEXT PRIMARY KEY,
grant_id TEXT NOT NULL,
execution_path TEXT NOT NULL,
git_operation TEXT NOT NULL DEFAULT '',
request_digest TEXT NOT NULL,
authorized_at TEXT NOT NULL,
receipt_json TEXT NOT NULL,
UNIQUE(grant_id, execution_path, git_operation, request_digest),
FOREIGN KEY(grant_id) REFERENCES provenance_grants(grant_id)
);
CREATE TABLE IF NOT EXISTS provenance_grant_events (
event_id TEXT PRIMARY KEY,
grant_id TEXT NOT NULL,
event_type TEXT NOT NULL,
details_json TEXT NOT NULL,
created_at TEXT NOT NULL,
FOREIGN KEY(grant_id) REFERENCES provenance_grants(grant_id)
);
"""
)
self._connection.commit()
def close(self) -> None:
with self._lock:
self._connection.close()
def _event(
self,
grant_id: str,
event_type: str,
details: Mapping[str, Any] | None = None,
) -> None:
self._connection.execute(
"INSERT INTO provenance_grant_events VALUES (?, ?, ?, ?, ?)",
(
f"gevt_{uuid.uuid4().hex}",
grant_id,
event_type,
json.dumps(dict(details or {}), ensure_ascii=False, sort_keys=True),
utc_now(),
),
)
def save_issued(self, grant: ProvenanceGrant) -> None:
payload = json.dumps(
grant.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
)
now = utc_now()
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
self._connection.execute(
"INSERT INTO provenance_grants VALUES (?, ?, ?, ?, ?, ?, 0, ?, ?)",
(
grant.grant_id,
grant.parent_provenance_id,
grant.grant_type.value,
grant.execution_path.value,
payload,
GrantStatus.ISSUED.value,
now,
now,
),
)
self._event(grant.grant_id, "issued")
self._connection.commit()
except sqlite3.IntegrityError as exc:
self._connection.rollback()
raise ProvenanceDenied("grant_id already exists") from exc
except Exception:
self._connection.rollback()
raise
def get(self, grant_id: str) -> ProvenanceGrant:
with self._lock:
row = self._connection.execute(
"SELECT payload_json FROM provenance_grants WHERE grant_id = ?",
(required(grant_id, "grant_id"),),
).fetchone()
if row is None:
raise ProvenanceNotFound("provenance grant not found")
value = json.loads(row["payload_json"])
if not isinstance(value, Mapping):
raise ProvenanceDenied("stored grant is invalid")
return ProvenanceGrant.from_dict(value)
def status(self, grant_id: str) -> GrantStatus:
with self._lock:
row = self._connection.execute(
"SELECT status FROM provenance_grants WHERE grant_id = ?",
(required(grant_id, "grant_id"),),
).fetchone()
if row is None:
raise ProvenanceNotFound("provenance grant not found")
return GrantStatus(row["status"])
def mark_verified(self, grant_id: str, *, fingerprint: str) -> None:
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
current = self.status(grant_id)
if current in {GrantStatus.REVOKED, GrantStatus.EXPIRED}:
raise ProvenanceDenied(f"cannot verify grant in state {current.value}")
next_status = (
GrantStatus.USED.value
if current == GrantStatus.USED
else GrantStatus.VERIFIED.value
)
self._connection.execute(
"UPDATE provenance_grants SET status = ?, signature_verified = 1, updated_at = ? WHERE grant_id = ?",
(next_status, utc_now(), grant_id),
)
self._event(
grant_id,
"verified",
{"public_key_fingerprint": fingerprint},
)
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def mark_expired(self, grant_id: str) -> None:
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
if self.status(grant_id) == GrantStatus.REVOKED:
self._connection.rollback()
return
self._connection.execute(
"UPDATE provenance_grants SET status = ?, updated_at = ? WHERE grant_id = ?",
(GrantStatus.EXPIRED.value, utc_now(), grant_id),
)
self._event(grant_id, "expired")
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def revoke(self, grant_id: str, *, reason: str, principal_id: str) -> None:
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
self.get(grant_id)
self._connection.execute(
"UPDATE provenance_grants SET status = ?, updated_at = ? WHERE grant_id = ?",
(GrantStatus.REVOKED.value, utc_now(), grant_id),
)
self._event(
grant_id,
"revoked",
{
"reason": required(reason, "reason"),
"principal_id": required(principal_id, "principal_id"),
},
)
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def record_authorization(self, authorization: GrantAuthorization) -> None:
receipt = json.dumps(
authorization.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
)
with self._lock:
self._connection.execute("BEGIN IMMEDIATE")
try:
current = self.status(authorization.grant_id)
if current in {GrantStatus.REVOKED, GrantStatus.EXPIRED}:
raise ProvenanceDenied(f"grant state is {current.value}")
try:
self._connection.execute(
"INSERT INTO provenance_grant_usage VALUES (?, ?, ?, ?, ?, ?, ?)",
(
authorization.authorization_id,
authorization.grant_id,
authorization.execution_path,
authorization.git_operation or "",
authorization.request_digest,
authorization.authorized_at,
receipt,
),
)
except sqlite3.IntegrityError as exc:
raise ProvenanceReplay(
"identical grant path/operation/request digest already used"
) from exc
self._connection.execute(
"UPDATE provenance_grants SET status = ?, updated_at = ? WHERE grant_id = ?",
(GrantStatus.USED.value, authorization.authorized_at, authorization.grant_id),
)
self._event(
authorization.grant_id,
"used",
{
"authorization_id": authorization.authorization_id,
"execution_path": authorization.execution_path,
"git_operation": authorization.git_operation,
"request_digest": authorization.request_digest,
},
)
self._connection.commit()
except Exception:
self._connection.rollback()
raise
def list_for_parent(self, parent_provenance_id: str) -> list[ProvenanceGrant]:
with self._lock:
rows = self._connection.execute(
"SELECT payload_json FROM provenance_grants WHERE parent_provenance_id = ? ORDER BY grant_type, grant_id",
(required(parent_provenance_id, "parent_provenance_id"),),
).fetchall()
return [ProvenanceGrant.from_dict(json.loads(row["payload_json"])) for row in rows]
class GrantIssuer:
"""从父 Workflow Provenance 派生单一路径最小权限 Grant。"""
def __init__(
self,
signer: Signer,
parent_store: SQLiteProvenanceStore,
grant_store: SQLiteGrantStore,
) -> None:
self.signer = signer
self.parent_store = parent_store
self.grant_store = grant_store
def issue(
self,
*,
parent_provenance_id: str,
grant_type: GrantType | str,
ttl_seconds: int = 900,
allowed_git_operations: Sequence[str] = (),
grant_id: str | None = None,
nonce: str | None = None,
now: datetime | None = None,
) -> ProvenanceGrant:
if ttl_seconds <= 0:
raise ValueError("grant ttl_seconds must be positive")
parent = self.parent_store.get(parent_provenance_id)
if parent.policy_version != WORKFLOW_POLICY_VERSION:
raise ProvenanceDenied("child grants require a workflow provenance parent")
if parent.allowed_paths or parent.allowed_git_operations:
raise ProvenanceDenied("workflow provenance parent must not contain operation rights")
parent_status = self.parent_store.status(parent.provenance_id)
if parent_status == ProvenanceStatus.REVOKED:
raise ProvenanceRevoked("workflow provenance is revoked")
issued = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
parent_expiry = parse_timestamp(parent.expires_at)
expires = min(issued + timedelta(seconds=ttl_seconds), parent_expiry)
if expires <= issued:
raise ProvenanceExpired("workflow provenance has expired")
normalized_type = GrantType(grant_type)
operations = tuple(allowed_git_operations)
unsigned = ProvenanceGrant(
grant_id=grant_id or f"grant_{uuid.uuid4().hex}",
parent_provenance_id=parent.provenance_id,
grant_type=normalized_type,
execution_path=GRANT_PATHS[normalized_type],
run_id=parent.run_id,
issuer=parent.issuer,
tenant_id=parent.tenant_id,
task_id=parent.task_id,
agent_id=parent.agent_id,
principal_id=parent.principal_id,
allowed_git_operations=operations,
issued_at=issued.isoformat().replace("+00:00", "Z"),
expires_at=expires.isoformat().replace("+00:00", "Z"),
policy_version=f"{WORKFLOW_POLICY_VERSION}.{normalized_type.value}",
key_id=self.signer.key_id,
nonce=nonce or uuid.uuid4().hex,
)
signed = replace(unsigned, signature=self.signer.sign(unsigned.canonical_bytes()))
self.grant_store.save_issued(signed)
return signed
class GrantVerifier:
"""验证父 Workflow 与子 Grant,确保单一路径最小权限。"""
def __init__(
self,
parent_store: SQLiteProvenanceStore,
grant_store: SQLiteGrantStore,
verifiers: Mapping[str, SignatureVerifier],
) -> None:
if not verifiers:
raise ValueError("at least one trusted verifier is required")
self.parent_store = parent_store
self.grant_store = grant_store
self.verifiers = {required(key, "key_id"): value for key, value in verifiers.items()}
def _verify_parent(self, parent: RunProvenance, *, now: datetime) -> SignatureVerifier:
status = self.parent_store.status(parent.provenance_id)
if status == ProvenanceStatus.REVOKED:
raise ProvenanceRevoked("workflow provenance is revoked")
if now >= parse_timestamp(parent.expires_at):
self.parent_store.mark_expired(parent.provenance_id)
raise ProvenanceExpired("workflow provenance is expired")
verifier = self.verifiers.get(parent.key_id)
if verifier is None or not parent.signature or not verifier.verify(
parent.canonical_bytes(), parent.signature
):
raise ProvenanceSignatureError("invalid workflow provenance signature")
if parent.policy_version != WORKFLOW_POLICY_VERSION:
raise ProvenanceDenied("parent is not a workflow provenance")
if parent.allowed_paths or parent.allowed_git_operations:
raise ProvenanceDenied("workflow provenance must not contain operation rights")
return verifier
def authorize(
self,
*,
grant_id: str,
parent_provenance_id: str,
run_id: str,
tenant_id: str,
task_id: str,
agent_id: str,
principal_id: str,
execution_path: str,
request_digest: str,
git_operation: str | None = None,
now: datetime | None = None,
) -> GrantAuthorization:
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
parent = self.parent_store.get(parent_provenance_id)
self._verify_parent(parent, now=current)
grant = self.grant_store.get(grant_id)
grant_status = self.grant_store.status(grant.grant_id)
if grant_status == GrantStatus.REVOKED:
raise ProvenanceRevoked("provenance grant is revoked")
if current >= parse_timestamp(grant.expires_at):
self.grant_store.mark_expired(grant.grant_id)
raise ProvenanceExpired("provenance grant is expired")
verifier = self.verifiers.get(grant.key_id)
if verifier is None or not grant.signature or not verifier.verify(
grant.canonical_bytes(), grant.signature
):
raise ProvenanceSignatureError("invalid provenance grant signature")
expected = {
"parent_provenance_id": parent.provenance_id,
"run_id": required(run_id, "run_id"),
"tenant_id": required(tenant_id, "tenant_id"),
"task_id": required(task_id, "task_id"),
"agent_id": required(agent_id, "agent_id"),
"principal_id": required(principal_id, "principal_id"),
}
for field_name, expected_value in expected.items():
if getattr(grant, field_name) != expected_value:
raise ProvenanceDenied(f"grant {field_name} mismatch")
if field_name != "parent_provenance_id" and getattr(parent, field_name) != expected_value:
raise ProvenanceDenied(f"workflow {field_name} mismatch")
path = ExecutionPath(execution_path)
if grant.execution_path != path:
raise ProvenanceDenied(
f"grant permits {grant.execution_path.value}, not {path.value}"
)
operation: str | None = None
if path == ExecutionPath.GIT_OPERATION:
if git_operation is None:
raise ProvenanceDenied("Git operation is required")
operation = GitOperation(git_operation).value
if operation not in grant.allowed_git_operations:
raise ProvenanceDenied(f"Git operation is not allowed: {operation}")
elif git_operation is not None:
raise ProvenanceDenied("git_operation is only valid for a Git Grant")
digest = _validate_digest(request_digest)
self.grant_store.mark_verified(grant.grant_id, fingerprint=verifier.fingerprint)
authorization = GrantAuthorization(
authorization_id=f"gauth_{uuid.uuid4().hex}",
grant_id=grant.grant_id,
parent_provenance_id=parent.provenance_id,
run_id=grant.run_id,
tenant_id=grant.tenant_id,
task_id=grant.task_id,
agent_id=grant.agent_id,
principal_id=grant.principal_id,
execution_path=path.value,
git_operation=operation,
request_digest=digest,
policy_version=grant.policy_version,
key_id=grant.key_id,
public_key_fingerprint=verifier.fingerprint,
)
self.grant_store.record_authorization(authorization)
return authorization
class LeastPrivilegeProvenanceWriter:
"""按路径选择独立子 Grant 的生产 Writer。
``provenance_id`` 参数始终指父 Workflow Provenance;Grant ID 来自受保护
配置映射,调用方无法通过请求体临时扩大权限。
"""
def __init__(
self,
verifier: GrantVerifier,
receipt_root: str | Path,
grant_ids: Mapping[str, str],
*,
writer_id: str = "aios-v2-least-privilege-writer",
) -> None:
self.verifier = verifier
self.receipt_root = Path(receipt_root).resolve()
self.receipt_root.mkdir(parents=True, exist_ok=True)
self.grant_ids = {
ExecutionPath(path).value: required(grant_id, f"grant_id[{path}]")
for path, grant_id in grant_ids.items()
}
missing = sorted(path.value for path in ExecutionPath if path.value not in self.grant_ids)
if missing:
raise ValueError(f"missing least-privilege Grant mappings: {missing}")
self.writer_id = required(writer_id, "writer_id")
self._lock = threading.RLock()
@staticmethod
def _component(value: str) -> str:
normalized = required(value, "path component")
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
raise ProvenanceDenied("invalid receipt path component")
return normalized
def authorize(self, **values: Any) -> GrantAuthorization:
path = ExecutionPath(values["execution_path"]).value
grant_id = self.grant_ids[path]
parent_provenance_id = values.pop("provenance_id")
authorization = self.verifier.authorize(
grant_id=grant_id,
parent_provenance_id=parent_provenance_id,
**values,
)
tenant = self._component(authorization.tenant_id)
parent = self._component(authorization.parent_provenance_id)
grant = self._component(authorization.grant_id)
target_dir = self.receipt_root / tenant / parent / grant
target = target_dir / f"{authorization.authorization_id}.json"
payload = authorization.as_dict()
payload["writer_id"] = self.writer_id
with self._lock:
target_dir.mkdir(parents=True, exist_ok=True)
temporary = target.with_suffix(f".tmp-{os.getpid()}")
temporary.write_text(
json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2) + "\n",
encoding="utf-8",
)
os.chmod(temporary, 0o640)
os.replace(temporary, target)
return authorization
def authorize_code_change(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.CODE_CHANGE.value, **values)
def authorize_git_operation(
self, *, git_operation: str, **values: Any
) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.GIT_OPERATION.value,
git_operation=git_operation,
**values,
)
def authorize_deployment(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.DEPLOYMENT.value, **values)
def authorize_runtime_execute(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.RUNTIME_EXECUTE.value, **values)
def authorize_evidence_write(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.EVIDENCE_WRITE.value, **values)
def authorize_rollback(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.ROLLBACK.value, **values)
def authorize_audit(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.AUDIT.value, **values)
@@ -0,0 +1,265 @@
"""AIOS V2 运维操作 Provenance Gate 与服务级 Scoped Writer 工厂。"""
from __future__ import annotations
import json
import os
from dataclasses import asdict, dataclass
from pathlib import Path
from typing import Any, Mapping, Protocol, Sequence
from .provenance import (
Ed25519PublicKeyVerifier,
ExecutionPath,
ProvenanceAuthorization,
ProvenanceControlledWriter,
ProvenanceDenied,
ProvenanceVerifier,
SQLiteProvenanceStore,
digest_payload,
)
from .provenance_grants import GrantAuthorization, GrantVerifier, SQLiteGrantStore
from .provenance_scoped import ScopedLeastPrivilegeProvenanceWriter
APPLICATION_PROVENANCE_SCOPE = (
ExecutionPath.RUNTIME_EXECUTE.value,
ExecutionPath.EVIDENCE_WRITE.value,
ExecutionPath.AUDIT.value,
)
class AuthorizationWriter(Protocol):
def authorize_deployment(self, **values: Any) -> Any: ...
def authorize_rollback(self, **values: Any) -> Any: ...
def authorize_audit(self, **values: Any) -> Any: ...
def authorize_code_change(self, **values: Any) -> Any: ...
def authorize_evidence_write(self, **values: Any) -> Any: ...
def authorize_runtime_execute(self, **values: Any) -> Any: ...
@dataclass(frozen=True)
class OperationContext:
provenance_id: str
run_id: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
def as_dict(self) -> dict[str, str]:
return asdict(self)
@dataclass(frozen=True)
class OperationReceipt:
operation: str
request_digest: str
authorization_id: str
provenance_id: str
grant_id: str | None
run_id: str
tenant_id: str
task_id: str
agent_id: str
principal_id: str
execution_path: str
authorized_at: str
def as_dict(self) -> dict[str, Any]:
return asdict(self)
class ProvenanceOperationGate:
"""部署、回滚、审计和运行操作的统一授权入口。"""
def __init__(self, writer: AuthorizationWriter) -> None:
self.writer = writer
def authorize(
self,
context: OperationContext,
*,
execution_path: str,
operation: str,
request: Mapping[str, Any],
) -> OperationReceipt:
path = ExecutionPath(execution_path).value
normalized_operation = str(operation or "").strip()
if not normalized_operation:
raise ValueError("operation is required")
digest = digest_payload(
{
"operation": normalized_operation,
"execution_path": path,
"request": dict(request),
}
)
values = {
"provenance_id": context.provenance_id,
"run_id": context.run_id,
"tenant_id": context.tenant_id,
"task_id": context.task_id,
"agent_id": context.agent_id,
"principal_id": context.principal_id,
"request_digest": digest,
}
if path == ExecutionPath.DEPLOYMENT.value:
authorization = self.writer.authorize_deployment(**values)
elif path == ExecutionPath.ROLLBACK.value:
authorization = self.writer.authorize_rollback(**values)
elif path == ExecutionPath.AUDIT.value:
authorization = self.writer.authorize_audit(**values)
elif path == ExecutionPath.CODE_CHANGE.value:
authorization = self.writer.authorize_code_change(**values)
elif path == ExecutionPath.EVIDENCE_WRITE.value:
authorization = self.writer.authorize_evidence_write(**values)
elif path == ExecutionPath.RUNTIME_EXECUTE.value:
authorization = self.writer.authorize_runtime_execute(**values)
else:
raise ProvenanceDenied(
"generic operation gate does not authorize git_operation; use ProvenanceGitWriter"
)
return self._receipt(normalized_operation, digest, authorization)
@staticmethod
def _receipt(
operation: str,
request_digest: str,
authorization: ProvenanceAuthorization | GrantAuthorization | Any,
) -> OperationReceipt:
return OperationReceipt(
operation=operation,
request_digest=request_digest,
authorization_id=authorization.authorization_id,
provenance_id=authorization.provenance_id,
grant_id=getattr(authorization, "grant_id", None),
run_id=authorization.run_id,
tenant_id=authorization.tenant_id,
task_id=authorization.task_id,
agent_id=authorization.agent_id,
principal_id=authorization.principal_id,
execution_path=authorization.execution_path,
authorized_at=authorization.authorized_at,
)
_GRANT_ENV_BY_PATH: Mapping[str, str] = {
ExecutionPath.CODE_CHANGE.value: "AIOS_PROVENANCE_GRANT_CODE_CHANGE_ID",
ExecutionPath.GIT_OPERATION.value: "AIOS_PROVENANCE_GRANT_GIT_ID",
ExecutionPath.DEPLOYMENT.value: "AIOS_PROVENANCE_GRANT_DEPLOYMENT_ID",
ExecutionPath.RUNTIME_EXECUTE.value: "AIOS_PROVENANCE_GRANT_RUNTIME_ID",
ExecutionPath.EVIDENCE_WRITE.value: "AIOS_PROVENANCE_GRANT_EVIDENCE_ID",
ExecutionPath.ROLLBACK.value: "AIOS_PROVENANCE_GRANT_ROLLBACK_ID",
ExecutionPath.AUDIT.value: "AIOS_PROVENANCE_GRANT_AUDIT_ID",
}
def grant_ids_from_environment(
*,
required_paths: Sequence[str] | None = None,
) -> dict[str, str]:
paths = tuple(
sorted(
{
ExecutionPath(path).value
for path in (required_paths or tuple(item.value for item in ExecutionPath))
}
)
)
values = {path: os.getenv(_GRANT_ENV_BY_PATH[path], "").strip() for path in paths}
missing = [_GRANT_ENV_BY_PATH[path] for path, value in values.items() if not value]
if missing:
raise RuntimeError(f"missing scoped Provenance Grant configuration: {missing}")
return values
def build_provenance_writer_from_env(
*,
state_dir: str | Path | None = None,
required: bool | None = None,
required_paths: Sequence[str] | None = None,
writer_id: str = "aios-v2-application-grant-writer",
) -> AuthorizationWriter | None:
"""从环境构建服务级最小权限 Writer。
生产应用默认只加载 Runtime、Evidence、Audit Grant。Git、部署和回滚进程
必须显式传入自己的 ``required_paths``,不能继承应用默认范围。旧全权限 Writer
只允许在显式关闭强制模式的候选/测试环境中使用。
"""
require_value = (
bool(required)
if required is not None
else os.getenv("AIOS_REQUIRE_RUN_PROVENANCE", "0").strip().lower()
in {"1", "true", "yes", "on"}
)
public_key_file = os.getenv("AIOS_PROVENANCE_PUBLIC_KEY_FILE", "").strip()
key_id = os.getenv("AIOS_PROVENANCE_KEY_ID", "").strip()
base = Path(state_dir or os.getenv("AIOS_V2_STATE_DIR", "/var/lib/aios-v2")).resolve()
store_file = os.getenv(
"AIOS_PROVENANCE_STORE_FILE", str(base / "run-provenance.sqlite3")
).strip()
receipt_root = os.getenv(
"AIOS_PROVENANCE_RECEIPT_DIR", str(base / "provenance-receipts")
).strip()
configured = bool(public_key_file and key_id)
if not configured:
if require_value:
raise RuntimeError(
"Run Provenance is required but AIOS_PROVENANCE_PUBLIC_KEY_FILE or AIOS_PROVENANCE_KEY_ID is missing"
)
return None
verifier = Ed25519PublicKeyVerifier.from_file(public_key_file, key_id=key_id)
parent_store = SQLiteProvenanceStore(store_file)
normalized_paths = tuple(
sorted(
{
ExecutionPath(path).value
for path in (
required_paths
if required_paths is not None
else APPLICATION_PROVENANCE_SCOPE
)
}
)
)
if require_value:
if not normalized_paths:
raise RuntimeError("production Run Provenance requires a non-empty service scope")
grant_ids = grant_ids_from_environment(required_paths=normalized_paths)
grant_store = SQLiteGrantStore(store_file)
trusted_grants = GrantVerifier(parent_store, grant_store, {key_id: verifier})
return ScopedLeastPrivilegeProvenanceWriter(
trusted_grants,
receipt_root,
grant_ids,
required_paths=normalized_paths,
writer_id=writer_id,
)
legacy = ProvenanceVerifier(parent_store, {key_id: verifier})
return ProvenanceControlledWriter(legacy, receipt_root)
def context_from_environment() -> OperationContext:
values = {
"provenance_id": os.getenv("AIOS_PROVENANCE_ID", ""),
"run_id": os.getenv("AIOS_RUN_ID", ""),
"tenant_id": os.getenv("AIOS_TENANT_ID", ""),
"task_id": os.getenv("AIOS_TASK_ID", ""),
"agent_id": os.getenv("AIOS_AGENT_ID", ""),
"principal_id": os.getenv("AIOS_PRINCIPAL_ID", ""),
}
missing = [name for name, value in values.items() if not str(value).strip()]
if missing:
raise RuntimeError(f"missing Provenance context environment variables: {missing}")
return OperationContext(**{name: str(value).strip() for name, value in values.items()})
def load_request_file(path: str | Path) -> Mapping[str, Any]:
value = json.loads(Path(path).read_text(encoding="utf-8"))
if not isinstance(value, Mapping):
raise ValueError("request file must contain a JSON object")
return dict(value)
@@ -0,0 +1,131 @@
"""按服务范围加载的最小权限 Provenance Writer。
该 Writer 只持有调用进程需要的 Grant ID。未配置路径的方法即使被调用也会
默认拒绝,避免应用进程获得 Git、部署或回滚权限。
"""
from __future__ import annotations
import json
import os
import threading
from pathlib import Path
from typing import Any, Mapping, Sequence
from .provenance import ExecutionPath, ProvenanceDenied, required
from .provenance_grants import GrantAuthorization, GrantVerifier
class ScopedLeastPrivilegeProvenanceWriter:
"""只暴露指定 ExecutionPath 的最小权限 Writer。"""
def __init__(
self,
verifier: GrantVerifier,
receipt_root: str | Path,
grant_ids: Mapping[str, str],
*,
required_paths: Sequence[str],
writer_id: str = "aios-v2-scoped-grant-writer",
) -> None:
self.verifier = verifier
self.receipt_root = Path(receipt_root).resolve()
self.receipt_root.mkdir(parents=True, exist_ok=True)
normalized_required = tuple(
sorted({ExecutionPath(path).value for path in required_paths})
)
if not normalized_required:
raise ValueError("required_paths must not be empty")
self.required_paths = frozenset(normalized_required)
self.grant_ids = {
path: required(grant_ids.get(path, ""), f"grant_id[{path}]")
for path in normalized_required
}
unexpected = sorted(set(grant_ids) - self.required_paths)
if unexpected:
raise ValueError(
f"scoped writer received unnecessary Grant mappings: {unexpected}"
)
self.writer_id = required(writer_id, "writer_id")
self._lock = threading.RLock()
@staticmethod
def _component(value: str) -> str:
normalized = required(value, "path component")
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
raise ProvenanceDenied("invalid receipt path component")
return normalized
def _grant_for(self, path: str) -> str:
normalized = ExecutionPath(path).value
grant_id = self.grant_ids.get(normalized)
if grant_id is None:
raise ProvenanceDenied(
f"this process is not allowed to authorize {normalized}"
)
return grant_id
def authorize(self, **values: Any) -> GrantAuthorization:
path = ExecutionPath(values["execution_path"]).value
grant_id = self._grant_for(path)
parent_provenance_id = values.pop("provenance_id")
authorization = self.verifier.authorize(
grant_id=grant_id,
parent_provenance_id=parent_provenance_id,
**values,
)
tenant = self._component(authorization.tenant_id)
parent = self._component(authorization.parent_provenance_id)
grant = self._component(authorization.grant_id)
target_dir = self.receipt_root / tenant / parent / grant
target = target_dir / f"{authorization.authorization_id}.json"
payload = authorization.as_dict()
payload["writer_id"] = self.writer_id
payload["scope"] = sorted(self.required_paths)
with self._lock:
target_dir.mkdir(parents=True, exist_ok=True)
temporary = target.with_suffix(f".tmp-{os.getpid()}")
temporary.write_text(
json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2)
+ "\n",
encoding="utf-8",
)
os.chmod(temporary, 0o640)
os.replace(temporary, target)
return authorization
def authorize_code_change(self, **values: Any) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.CODE_CHANGE.value, **values
)
def authorize_git_operation(
self, *, git_operation: str, **values: Any
) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.GIT_OPERATION.value,
git_operation=git_operation,
**values,
)
def authorize_deployment(self, **values: Any) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.DEPLOYMENT.value, **values
)
def authorize_runtime_execute(self, **values: Any) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.RUNTIME_EXECUTE.value, **values
)
def authorize_evidence_write(self, **values: Any) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.EVIDENCE_WRITE.value, **values
)
def authorize_rollback(self, **values: Any) -> GrantAuthorization:
return self.authorize(
execution_path=ExecutionPath.ROLLBACK.value, **values
)
def authorize_audit(self, **values: Any) -> GrantAuthorization:
return self.authorize(execution_path=ExecutionPath.AUDIT.value, **values)
@@ -0,0 +1,607 @@
"""Durable execution truth registry for externally executed AIOS tasks.
A task manifest being present in Git is not evidence that an executor discovered
or ran it. This registry separates declaration, registration, claim, start,
heartbeat and terminal evidence. Release gates must require a terminal success
record with immutable evidence hashes.
"""
from __future__ import annotations
import json
import sqlite3
import threading
import uuid
from dataclasses import asdict, dataclass, field, replace
from datetime import datetime, timedelta, timezone
from enum import Enum
from pathlib import Path
from typing import Any, Mapping, Sequence
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
def parse_time(value: str) -> datetime:
normalized = str(value or "").strip()
if normalized.endswith("Z"):
normalized = normalized[:-1] + "+00:00"
parsed = datetime.fromisoformat(normalized)
if parsed.tzinfo is None:
raise ValueError("timestamp requires timezone")
return parsed.astimezone(timezone.utc)
def required(value: str, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
class ExecutionTruthState(str, Enum):
DECLARED = "DECLARED"
REGISTERED = "REGISTERED"
CLAIMED = "CLAIMED"
RUNNING = "RUNNING"
SUCCEEDED = "SUCCEEDED"
FAILED = "FAILED"
CANCELLED = "CANCELLED"
NOT_STARTED = "NOT_STARTED"
STALLED = "STALLED"
TERMINAL_STATES = frozenset(
{
ExecutionTruthState.SUCCEEDED,
ExecutionTruthState.FAILED,
ExecutionTruthState.CANCELLED,
ExecutionTruthState.NOT_STARTED,
ExecutionTruthState.STALLED,
}
)
@dataclass(frozen=True)
class ExecutionTaskManifest:
task_id: str
executor: str
source_branch: str
source_oid: str
target_version: str
steps: Sequence[str]
start_deadline_seconds: int = 300
heartbeat_timeout_seconds: int = 180
required_evidence: Sequence[str] = ()
notification_events: Sequence[str] = ("STARTED", "SUCCEEDED", "FAILED")
owner_notification_ref: str = "AIOS_OWNER_WECHAT_TARGET_REF"
manifest_version: str = "aios.external-task.v1"
def __post_init__(self) -> None:
for name in (
"task_id",
"executor",
"source_branch",
"source_oid",
"target_version",
"manifest_version",
"owner_notification_ref",
):
object.__setattr__(self, name, required(getattr(self, name), name))
steps = tuple(required(item, "step") for item in self.steps)
if not steps:
raise ValueError("at least one execution step is required")
if self.start_deadline_seconds < 1 or self.heartbeat_timeout_seconds < 1:
raise ValueError("execution deadlines must be positive")
object.__setattr__(self, "steps", steps)
object.__setattr__(
self,
"required_evidence",
tuple(sorted({required(item, "required_evidence") for item in self.required_evidence})),
)
object.__setattr__(
self,
"notification_events",
tuple(sorted({required(item, "notification_event") for item in self.notification_events})),
)
def as_dict(self) -> dict[str, Any]:
value = asdict(self)
value["steps"] = list(self.steps)
value["required_evidence"] = list(self.required_evidence)
value["notification_events"] = list(self.notification_events)
return value
@classmethod
def from_dict(cls, value: Mapping[str, Any]) -> "ExecutionTaskManifest":
return cls(**dict(value))
@dataclass(frozen=True)
class ExecutionTruthRecord:
task_id: str
manifest_json: str
state: ExecutionTruthState
executor_run_id: str | None = None
executor_id: str | None = None
declared_at: str = field(default_factory=utc_now)
registered_at: str | None = None
claimed_at: str | None = None
started_at: str | None = None
heartbeat_at: str | None = None
completed_at: str | None = None
current_step: int = 0
evidence: Mapping[str, str] = field(default_factory=dict)
error: Mapping[str, Any] = field(default_factory=dict)
revision: int = 1
@property
def manifest(self) -> ExecutionTaskManifest:
return ExecutionTaskManifest.from_dict(json.loads(self.manifest_json))
def as_dict(self) -> dict[str, Any]:
return {
**asdict(self),
"state": self.state.value,
"manifest": self.manifest.as_dict(),
"evidence": dict(self.evidence),
"error": dict(self.error),
}
class ExecutionTruthConflict(RuntimeError):
pass
class SQLiteExecutionTruthRegistry:
"""Persistent registration and run-evidence store."""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
self.path.parent.mkdir(parents=True, exist_ok=True)
self._lock = threading.RLock()
with self._connect() as connection:
connection.executescript(
"""
CREATE TABLE IF NOT EXISTS execution_truth (
task_id TEXT PRIMARY KEY,
manifest_json TEXT NOT NULL,
state TEXT NOT NULL,
record_json TEXT NOT NULL,
revision INTEGER NOT NULL,
updated_at TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS execution_truth_events (
event_id TEXT PRIMARY KEY,
task_id TEXT NOT NULL,
event_type TEXT NOT NULL,
details_json TEXT NOT NULL,
created_at TEXT NOT NULL,
FOREIGN KEY(task_id) REFERENCES execution_truth(task_id)
);
CREATE INDEX IF NOT EXISTS idx_execution_truth_state
ON execution_truth(state, updated_at);
"""
)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(str(self.path), timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
connection.execute("PRAGMA foreign_keys=ON")
return connection
@staticmethod
def _manifest_json(manifest: ExecutionTaskManifest) -> str:
return json.dumps(manifest.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":"))
@staticmethod
def _record_json(record: ExecutionTruthRecord) -> str:
value = record.as_dict()
value.pop("manifest", None)
return json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"), default=str)
@staticmethod
def _decode(row: sqlite3.Row) -> ExecutionTruthRecord:
value = json.loads(row["record_json"])
value["state"] = ExecutionTruthState(value["state"])
value["evidence"] = dict(value.get("evidence") or {})
value["error"] = dict(value.get("error") or {})
return ExecutionTruthRecord(**value)
def _event(
self,
connection: sqlite3.Connection,
task_id: str,
event_type: str,
details: Mapping[str, Any] | None = None,
) -> None:
connection.execute(
"INSERT INTO execution_truth_events VALUES (?, ?, ?, ?, ?)",
(
f"truth_evt_{uuid.uuid4().hex}",
task_id,
event_type,
json.dumps(dict(details or {}), ensure_ascii=False, sort_keys=True, default=str),
utc_now(),
),
)
def declare(self, manifest: ExecutionTaskManifest) -> ExecutionTruthRecord:
manifest_json = self._manifest_json(manifest)
record = ExecutionTruthRecord(
task_id=manifest.task_id,
manifest_json=manifest_json,
state=ExecutionTruthState.DECLARED,
)
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
existing = connection.execute(
"SELECT record_json FROM execution_truth WHERE task_id = ?",
(manifest.task_id,),
).fetchone()
if existing is not None:
current = self._decode(existing)
if current.manifest_json != manifest_json:
previous_manifest = current.manifest.as_dict()
replacement_manifest = manifest.as_dict()
previous_oid = previous_manifest.pop("source_oid")
replacement_oid = replacement_manifest.pop("source_oid")
if (
current.state != ExecutionTruthState.NOT_STARTED
or previous_manifest != replacement_manifest
):
connection.rollback()
raise ExecutionTruthConflict(
"task_id already declared with another manifest"
)
now = utc_now()
updated = replace(
current,
manifest_json=manifest_json,
revision=current.revision + 1,
)
connection.execute(
"UPDATE execution_truth SET manifest_json = ?, record_json = ?, revision = ?, updated_at = ? WHERE task_id = ?",
(
manifest_json,
self._record_json(updated),
updated.revision,
now,
updated.task_id,
),
)
self._event(
connection,
updated.task_id,
"MANIFEST_SUPERSEDED",
{
"previous_source_oid": previous_oid,
"source_oid": replacement_oid,
"state": updated.state.value,
},
)
connection.commit()
return updated
connection.rollback()
return current
connection.execute(
"INSERT INTO execution_truth VALUES (?, ?, ?, ?, ?, ?)",
(
record.task_id,
manifest_json,
record.state.value,
self._record_json(record),
record.revision,
record.declared_at,
),
)
self._event(connection, record.task_id, "DECLARED", {"source_oid": manifest.source_oid})
connection.commit()
return record
def get(self, task_id: str) -> ExecutionTruthRecord:
with self._lock, self._connect() as connection:
row = connection.execute(
"SELECT record_json FROM execution_truth WHERE task_id = ?",
(required(task_id, "task_id"),),
).fetchone()
if row is None:
raise KeyError("execution task not declared")
return self._decode(row)
def _transition(
self,
task_id: str,
*,
allowed: Sequence[ExecutionTruthState],
target: ExecutionTruthState,
executor_run_id: str | None = None,
executor_id: str | None = None,
current_step: int | None = None,
evidence: Mapping[str, str] | None = None,
error: Mapping[str, Any] | None = None,
) -> ExecutionTruthRecord:
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
row = connection.execute(
"SELECT record_json FROM execution_truth WHERE task_id = ?",
(required(task_id, "task_id"),),
).fetchone()
if row is None:
connection.rollback()
raise KeyError("execution task not declared")
current = self._decode(row)
if current.state not in set(allowed):
connection.rollback()
raise ExecutionTruthConflict(
f"cannot transition {current.state.value} to {target.value}"
)
now = utc_now()
updates: dict[str, Any] = {
"state": target,
"revision": current.revision + 1,
}
if executor_run_id is not None:
if current.executor_run_id and current.executor_run_id != executor_run_id:
connection.rollback()
raise ExecutionTruthConflict("executor_run_id mismatch")
updates["executor_run_id"] = required(executor_run_id, "executor_run_id")
if executor_id is not None:
if current.executor_id and current.executor_id != executor_id:
connection.rollback()
raise ExecutionTruthConflict("executor_id mismatch")
updates["executor_id"] = required(executor_id, "executor_id")
if target == ExecutionTruthState.REGISTERED:
updates["registered_at"] = now
if target == ExecutionTruthState.CLAIMED:
updates["claimed_at"] = now
updates["heartbeat_at"] = now
if target == ExecutionTruthState.RUNNING:
updates["started_at"] = current.started_at or now
updates["heartbeat_at"] = now
if current_step is not None:
if current_step < current.current_step or current_step > len(current.manifest.steps):
connection.rollback()
raise ExecutionTruthConflict("invalid task step progression")
updates["current_step"] = current_step
updates["heartbeat_at"] = now
if evidence is not None:
updates["evidence"] = {
**dict(current.evidence),
**{required(key, "evidence key"): required(value, "evidence hash") for key, value in evidence.items()},
}
if error is not None:
updates["error"] = json.loads(json.dumps(dict(error), default=str))
if target in TERMINAL_STATES:
updates["completed_at"] = now
updated = replace(current, **updates)
connection.execute(
"UPDATE execution_truth SET state = ?, record_json = ?, revision = ?, updated_at = ? WHERE task_id = ?",
(
updated.state.value,
self._record_json(updated),
updated.revision,
now,
updated.task_id,
),
)
self._event(
connection,
updated.task_id,
target.value,
{
"executor_run_id": updated.executor_run_id,
"executor_id": updated.executor_id,
"current_step": updated.current_step,
},
)
connection.commit()
return updated
def register(self, task_id: str, *, executor_run_id: str) -> ExecutionTruthRecord:
return self._transition(
task_id,
allowed=(ExecutionTruthState.DECLARED,),
target=ExecutionTruthState.REGISTERED,
executor_run_id=executor_run_id,
)
def retry_not_started(
self,
task_id: str,
*,
executor_run_id: str,
) -> ExecutionTruthRecord:
"""Start a new audited attempt after the declaration deadline expired."""
with self._lock, self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
row = connection.execute(
"SELECT record_json FROM execution_truth WHERE task_id = ?",
(required(task_id, "task_id"),),
).fetchone()
if row is None:
connection.rollback()
raise KeyError("execution task not declared")
current = self._decode(row)
if current.state != ExecutionTruthState.NOT_STARTED:
connection.rollback()
raise ExecutionTruthConflict(
f"cannot retry task from {current.state.value}"
)
now = utc_now()
updated = replace(
current,
state=ExecutionTruthState.REGISTERED,
executor_run_id=required(executor_run_id, "executor_run_id"),
executor_id=None,
registered_at=now,
claimed_at=None,
started_at=None,
heartbeat_at=None,
completed_at=None,
current_step=0,
evidence={},
error={},
revision=current.revision + 1,
)
connection.execute(
"UPDATE execution_truth SET state = ?, record_json = ?, revision = ?, updated_at = ? WHERE task_id = ?",
(
updated.state.value,
self._record_json(updated),
updated.revision,
now,
updated.task_id,
),
)
self._event(
connection,
updated.task_id,
"RETRIED",
{
"previous_state": current.state.value,
"previous_executor_run_id": current.executor_run_id,
"executor_run_id": updated.executor_run_id,
"previous_error": dict(current.error),
},
)
connection.commit()
return updated
def claim(self, task_id: str, *, executor_run_id: str, executor_id: str) -> ExecutionTruthRecord:
return self._transition(
task_id,
allowed=(ExecutionTruthState.REGISTERED,),
target=ExecutionTruthState.CLAIMED,
executor_run_id=executor_run_id,
executor_id=executor_id,
)
def start(self, task_id: str, *, executor_run_id: str, executor_id: str) -> ExecutionTruthRecord:
return self._transition(
task_id,
allowed=(ExecutionTruthState.CLAIMED,),
target=ExecutionTruthState.RUNNING,
executor_run_id=executor_run_id,
executor_id=executor_id,
current_step=1,
)
def heartbeat(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
current_step: int,
) -> ExecutionTruthRecord:
return self._transition(
task_id,
allowed=(ExecutionTruthState.RUNNING,),
target=ExecutionTruthState.RUNNING,
executor_run_id=executor_run_id,
executor_id=executor_id,
current_step=current_step,
)
def succeed(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
evidence: Mapping[str, str],
) -> ExecutionTruthRecord:
current = self.get(task_id)
missing = sorted(set(current.manifest.required_evidence) - set(evidence))
if missing:
raise ExecutionTruthConflict(f"missing required evidence: {missing}")
if current.current_step != len(current.manifest.steps):
raise ExecutionTruthConflict("all declared steps must complete before success")
return self._transition(
task_id,
allowed=(ExecutionTruthState.RUNNING,),
target=ExecutionTruthState.SUCCEEDED,
executor_run_id=executor_run_id,
executor_id=executor_id,
evidence=evidence,
)
def fail(
self,
task_id: str,
*,
executor_run_id: str,
executor_id: str,
error: Mapping[str, Any],
evidence: Mapping[str, str] | None = None,
) -> ExecutionTruthRecord:
return self._transition(
task_id,
allowed=(ExecutionTruthState.REGISTERED, ExecutionTruthState.CLAIMED, ExecutionTruthState.RUNNING),
target=ExecutionTruthState.FAILED,
executor_run_id=executor_run_id,
executor_id=executor_id,
evidence=evidence,
error=error,
)
def evaluate_deadlines(self, task_id: str, *, now: datetime | None = None) -> ExecutionTruthRecord:
current = self.get(task_id)
current_time = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
manifest = current.manifest
if current.state in TERMINAL_STATES:
return current
declared = parse_time(current.declared_at)
if current.state in {ExecutionTruthState.DECLARED, ExecutionTruthState.REGISTERED}:
if current_time >= declared + timedelta(seconds=manifest.start_deadline_seconds):
return self._transition(
task_id,
allowed=(current.state,),
target=ExecutionTruthState.NOT_STARTED,
error={"code": "start_deadline_exceeded"},
)
if current.state in {ExecutionTruthState.CLAIMED, ExecutionTruthState.RUNNING}:
heartbeat = parse_time(current.heartbeat_at or current.claimed_at or current.declared_at)
if current_time >= heartbeat + timedelta(seconds=manifest.heartbeat_timeout_seconds):
return self._transition(
task_id,
allowed=(current.state,),
target=ExecutionTruthState.STALLED,
error={"code": "heartbeat_timeout"},
)
return current
def gate(self, task_id: str) -> Mapping[str, Any]:
record = self.evaluate_deadlines(task_id)
passed = record.state == ExecutionTruthState.SUCCEEDED
return {
"task_id": record.task_id,
"state": record.state.value,
"passed": passed,
"release_blocking": not passed,
"executor_run_id": record.executor_run_id,
"executor_id": record.executor_id,
"current_step": record.current_step,
"total_steps": len(record.manifest.steps),
"evidence": dict(record.evidence),
"error": dict(record.error),
}
def events(self, task_id: str) -> list[Mapping[str, Any]]:
with self._lock, self._connect() as connection:
rows = connection.execute(
"SELECT event_id, event_type, details_json, created_at FROM execution_truth_events WHERE task_id = ? ORDER BY created_at, event_id",
(required(task_id, "task_id"),),
).fetchall()
return [
{
"event_id": row["event_id"],
"event_type": row["event_type"],
"details": json.loads(row["details_json"]),
"created_at": row["created_at"],
}
for row in rows
]
+13
View File
@@ -0,0 +1,13 @@
"""AIOS unified, role-aware web portal."""
from .application import UnifiedPortalApplication, build_application
from .capabilities import ROLE_CAPABILITIES, allows, require, resolve
__all__ = [
"ROLE_CAPABILITIES",
"UnifiedPortalApplication",
"allows",
"build_application",
"require",
"resolve",
]
+512
View File
@@ -0,0 +1,512 @@
"""Unified, role-aware AIOS web application.
The portal wraps the production CandidateApplication instead of replacing its
runtime/control-plane routes. Portal endpoints aggregate existing authoritative
stores and require server-side capabilities before delegating any state change.
"""
from __future__ import annotations
import dataclasses
import json
import os
import re
import sqlite3
import urllib.parse
from enum import Enum
from http import HTTPStatus
from pathlib import Path
from typing import Any, Mapping
from aios_v2.app import (
CandidateApplication,
CandidateHTTPServer,
build_application as build_candidate_application,
)
from aios_v2.control_plane import RequestContext, TaskState
from aios_v2.gitops_status import collect_gitops_status
from aios_v2.provenance import SQLiteProvenanceStore
from aios_v2.provenance_grants import SQLiteGrantStore
from .capabilities import allows, require, resolve
def _json_value(value: Any) -> Any:
if dataclasses.is_dataclass(value):
return {
field.name: _json_value(getattr(value, field.name))
for field in dataclasses.fields(value)
}
if isinstance(value, Enum):
return value.value
if isinstance(value, Mapping):
return {str(key): _json_value(item) for key, item in value.items()}
if isinstance(value, (list, tuple, set, frozenset)):
return [_json_value(item) for item in value]
return value
def _mapping(value: Any) -> Mapping[str, Any]:
if not isinstance(value, Mapping):
raise ValueError("JSON body must be an object")
return value
def _required(value: Any, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
def _safe_count(items: list[Any]) -> int:
return len(items)
class AuthorizationCatalog:
"""Tenant-filtered read/revoke access to existing Provenance stores."""
def __init__(self, store_file: str | Path) -> None:
self.store_file = Path(store_file).resolve()
def _read_connection(self) -> sqlite3.Connection | None:
if not self.store_file.exists():
return None
connection = sqlite3.connect(
f"file:{self.store_file}?mode=ro",
uri=True,
timeout=10.0,
)
connection.row_factory = sqlite3.Row
return connection
def snapshot(self, *, tenant_id: str) -> Mapping[str, Any]:
connection = self._read_connection()
if connection is None:
return {
"configured": False,
"workflows": [],
"grants": [],
"summary": {"workflows": 0, "grants": 0, "active_grants": 0},
}
try:
workflows: list[dict[str, Any]] = []
grants: list[dict[str, Any]] = []
tables = {
row["name"]
for row in connection.execute(
"SELECT name FROM sqlite_master WHERE type='table'"
).fetchall()
}
if "provenance_records" in tables:
rows = connection.execute(
"""
SELECT r.payload_json, r.status, r.signature_verified,
r.created_at, r.updated_at,
COUNT(u.authorization_id) AS usage_count
FROM provenance_records r
LEFT JOIN provenance_usage u
ON u.provenance_id = r.provenance_id
GROUP BY r.provenance_id
ORDER BY r.updated_at DESC, r.provenance_id
"""
).fetchall()
for row in rows:
payload = json.loads(row["payload_json"])
if payload.get("tenant_id") != tenant_id:
continue
workflows.append(
{
**payload,
"status": row["status"],
"signature_verified": bool(row["signature_verified"]),
"usage_count": int(row["usage_count"]),
"created_at": row["created_at"],
"updated_at": row["updated_at"],
}
)
if "provenance_grants" in tables:
rows = connection.execute(
"""
SELECT g.payload_json, g.status, g.signature_verified,
g.created_at, g.updated_at,
COUNT(u.authorization_id) AS usage_count
FROM provenance_grants g
LEFT JOIN provenance_grant_usage u
ON u.grant_id = g.grant_id
GROUP BY g.grant_id
ORDER BY g.updated_at DESC, g.grant_id
"""
).fetchall()
for row in rows:
payload = json.loads(row["payload_json"])
if payload.get("tenant_id") != tenant_id:
continue
grants.append(
{
**payload,
"status": row["status"],
"signature_verified": bool(row["signature_verified"]),
"usage_count": int(row["usage_count"]),
"created_at": row["created_at"],
"updated_at": row["updated_at"],
}
)
active = sum(
1
for item in grants
if item.get("status") not in {"revoked", "expired"}
)
return {
"configured": True,
"workflows": workflows,
"grants": grants,
"summary": {
"workflows": len(workflows),
"grants": len(grants),
"active_grants": active,
"revoked_grants": sum(
1 for item in grants if item.get("status") == "revoked"
),
},
}
finally:
connection.close()
def revoke_workflow(
self,
*,
provenance_id: str,
tenant_id: str,
principal_id: str,
reason: str,
) -> Mapping[str, Any]:
store = SQLiteProvenanceStore(self.store_file)
try:
record = store.get(provenance_id)
if record.tenant_id != tenant_id:
raise KeyError("workflow provenance not found")
store.revoke(
record.provenance_id,
reason=reason,
principal_id=principal_id,
)
return {
"provenance_id": record.provenance_id,
"status": store.status(record.provenance_id).value,
}
finally:
store.close()
def revoke_grant(
self,
*,
grant_id: str,
tenant_id: str,
principal_id: str,
reason: str,
) -> Mapping[str, Any]:
store = SQLiteGrantStore(self.store_file)
try:
grant = store.get(grant_id)
if grant.tenant_id != tenant_id:
raise KeyError("provenance grant not found")
store.revoke(
grant.grant_id,
reason=reason,
principal_id=principal_id,
)
return {
"grant_id": grant.grant_id,
"status": store.status(grant.grant_id).value,
}
finally:
store.close()
class UnifiedPortalApplication:
"""Role-aware portal facade over the existing production application."""
def __init__(
self,
base: CandidateApplication,
*,
provenance_store_file: str | Path,
) -> None:
self.base = base
self.gateway = base.gateway
self.orchestrator = base.orchestrator
self.tracker = base.tracker
self.hermes = base.hermes
self.openclaw = base.openclaw
self.authorization_catalog = AuthorizationCatalog(provenance_store_file)
def context(self, headers: Mapping[str, str]) -> RequestContext:
return self.base.context(headers)
def _runtime(self, headers: Mapping[str, str]) -> Mapping[str, Any]:
status, payload = self.base.handle_json("GET", "/api/v2/runtime", headers, {})
if int(status) != HTTPStatus.OK:
raise RuntimeError("runtime status is unavailable")
return payload
def _gitops(self, context: RequestContext) -> Mapping[str, Any]:
return {
"tenant_id": context.tenant_id,
"gitops": collect_gitops_status().as_dict(),
}
def _tasks_view(self, context: RequestContext) -> list[Mapping[str, Any]]:
service = self.orchestrator.control_plane
tasks = service.list_tasks(context)
dispatches = {
item.task_id: item
for item in self.orchestrator.dispatch_repository.list(
tenant_id=context.tenant_id
)
}
evidence_by_task: dict[str, list[Any]] = {}
for evidence in self.tracker.list(tenant_id=context.tenant_id):
evidence_by_task.setdefault(evidence.task_id, []).append(evidence)
audit_by_task: dict[str, list[Any]] = {}
for event in service.list_audit_events(context):
if event.resource_type == "task":
audit_by_task.setdefault(event.resource_id, []).append(event)
capabilities = set(resolve(context).capabilities)
result: list[Mapping[str, Any]] = []
for task in tasks:
actions: list[str] = []
if task.state == TaskState.CREATED and "task.approve" in capabilities:
actions.append("approve")
if task.state in {TaskState.CREATED, TaskState.APPROVED, TaskState.RUNNING} and "task.cancel" in capabilities:
actions.append("cancel")
if task.state == TaskState.APPROVED and "task.dispatch" in capabilities:
actions.append("dispatch")
result.append(
{
"task": _json_value(task),
"dispatch": _json_value(dispatches.get(task.task_id)),
"evidence": _json_value(evidence_by_task.get(task.task_id, [])),
"audit": _json_value(audit_by_task.get(task.task_id, [])[-12:]),
"available_actions": actions,
}
)
return result
def _overview(
self,
context: RequestContext,
headers: Mapping[str, str],
) -> Mapping[str, Any]:
service = self.orchestrator.control_plane
capabilities = resolve(context)
sections: dict[str, Any] = {}
tasks = service.list_tasks(context) if allows(context, "task.read") else []
dispatches = (
self.orchestrator.dispatch_repository.list(tenant_id=context.tenant_id)
if allows(context, "dispatch.read")
else []
)
evidence = (
self.tracker.list(tenant_id=context.tenant_id)
if allows(context, "evidence.read")
else []
)
audit = (
service.list_audit_events(context)
if allows(context, "audit.read")
else []
)
if allows(context, "runtime.read"):
sections["runtime"] = self._runtime(headers)
if allows(context, "release.read"):
sections["release"] = {
**self._gitops(context),
"version": os.getenv("AIOS_RELEASE_VERSION", "V2R1C1"),
"release_oid": os.getenv("AIOS_RELEASE_OID", "unknown"),
"baseline": os.getenv("AIOS_BASELINE_VERSION", "V2R1C1"),
"status": os.getenv("AIOS_RELEASE_STATUS", "PRODUCTION_DEPLOYED"),
}
if allows(context, "provenance.read"):
sections["authorization"] = self.authorization_catalog.snapshot(
tenant_id=context.tenant_id
)["summary"]
task_states: dict[str, int] = {}
for task in tasks:
task_states[task.state.value] = task_states.get(task.state.value, 0) + 1
return {
"identity": capabilities.as_dict(),
"summary": {
"tasks": _safe_count(tasks),
"task_states": task_states,
"dispatches": _safe_count(dispatches),
"active_dispatches": sum(
1
for item in dispatches
if item.state.value not in {"COMPLETED", "FAILED", "CANCELLED"}
),
"evidence": _safe_count(evidence),
"audit_events": _safe_count(audit),
},
"sections": sections,
"recent": {
"tasks": _json_value(tasks[:8]),
"dispatches": _json_value(dispatches[-8:]),
"audit": _json_value(audit[-12:]),
},
}
def handle_json(
self,
method: str,
raw_path: str,
headers: Mapping[str, str],
body: Any,
) -> tuple[int, Mapping[str, Any]]:
parsed = urllib.parse.urlparse(raw_path)
path = parsed.path.rstrip("/") or "/"
method = method.upper()
if not path.startswith("/api/v2/portal") and path != "/api/v2/me/capabilities":
return self.base.handle_json(method, raw_path, headers, body)
context = self.context(headers)
payload = _mapping(body or {})
if method == "GET" and path == "/api/v2/me/capabilities":
require(context, "portal.access")
return HTTPStatus.OK, resolve(context).as_dict()
if method == "GET" and path == "/api/v2/portal/overview":
require(context, "dashboard.read")
return HTTPStatus.OK, self._overview(context, headers)
if method == "GET" and path == "/api/v2/portal/tasks":
require(context, "task.read")
return HTTPStatus.OK, {"items": self._tasks_view(context)}
if method == "GET" and path == "/api/v2/portal/authorizations":
require(context, "provenance.read")
return HTTPStatus.OK, self.authorization_catalog.snapshot(
tenant_id=context.tenant_id
)
if method == "GET" and path == "/api/v2/portal/runtime":
require(context, "runtime.read")
return HTTPStatus.OK, {
**self._runtime(headers),
"dispatches": _json_value(
self.orchestrator.dispatch_repository.list(
tenant_id=context.tenant_id
)
),
"hermes_jobs": _json_value(
self.hermes.list(tenant_id=context.tenant_id)
),
}
if method == "GET" and path == "/api/v2/portal/evidence":
require(context, "evidence.read")
return HTTPStatus.OK, {
"executions": _json_value(
self.tracker.list(tenant_id=context.tenant_id)
)
}
if method == "GET" and path == "/api/v2/portal/audit":
require(context, "audit.read")
return HTTPStatus.OK, {
"events": _json_value(
self.orchestrator.control_plane.list_audit_events(context)
)
}
if method == "GET" and path == "/api/v2/portal/release":
require(context, "release.read")
return HTTPStatus.OK, {
**self._gitops(context),
"version": os.getenv("AIOS_RELEASE_VERSION", "V2R1C1"),
"release_oid": os.getenv("AIOS_RELEASE_OID", "unknown"),
"baseline": os.getenv("AIOS_BASELINE_VERSION", "V2R1C1"),
"status": os.getenv("AIOS_RELEASE_STATUS", "PRODUCTION_DEPLOYED"),
"operations": (
["review_release", "request_tag", "request_rollback"]
if allows(context, "release.operate")
else []
),
"note": "Release operations remain GitOps approval requests; the portal does not mutate tags or production directly.",
}
if method == "POST" and path == "/api/v2/portal/tasks":
require(context, "task.create")
return self.base.handle_json("POST", "/api/v2/tasks", headers, payload)
task_action = re.fullmatch(
r"/api/v2/portal/tasks/([^/]+)/(approve|cancel|dispatch)", path
)
if method == "POST" and task_action:
action = task_action.group(2)
require(context, f"task.{action}")
task_id = urllib.parse.unquote(task_action.group(1))
target = (
f"/api/v2/tasks/{task_id}/dispatch"
if action == "dispatch"
else f"/api/v2/tasks/{task_id}/{action}"
)
return self.base.handle_json("POST", target, headers, payload)
workflow_revoke = re.fullmatch(
r"/api/v2/portal/provenance/([^/]+)/revoke", path
)
if method == "POST" and workflow_revoke:
require(context, "provenance.revoke")
reason = _required(payload.get("reason"), "reason")
result = self.authorization_catalog.revoke_workflow(
provenance_id=urllib.parse.unquote(workflow_revoke.group(1)),
tenant_id=context.tenant_id,
principal_id=context.principal_id,
reason=reason,
)
return HTTPStatus.OK, {"workflow": result}
grant_revoke = re.fullmatch(r"/api/v2/portal/grants/([^/]+)/revoke", path)
if method == "POST" and grant_revoke:
require(context, "provenance.revoke")
reason = _required(payload.get("reason"), "reason")
result = self.authorization_catalog.revoke_grant(
grant_id=urllib.parse.unquote(grant_revoke.group(1)),
tenant_id=context.tenant_id,
principal_id=context.principal_id,
reason=reason,
)
return HTTPStatus.OK, {"grant": result}
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "portal route not found",
}
def build_application() -> UnifiedPortalApplication:
state_dir = Path(os.getenv("AIOS_V2_STATE_DIR", "/var/lib/aios-v2")).resolve()
provenance_file = Path(
os.getenv(
"AIOS_PROVENANCE_STORE_FILE",
str(state_dir / "run-provenance.sqlite3"),
)
)
return UnifiedPortalApplication(
build_candidate_application(),
provenance_store_file=provenance_file,
)
def main() -> None:
host = os.getenv("AIOS_V2_HOST", "127.0.0.1")
port = int(os.getenv("AIOS_V2_PORT", "18920"))
server = CandidateHTTPServer((host, port), build_application())
print(f"AIOS V2 unified portal listening on {host}:{port}")
server.serve_forever()
if __name__ == "__main__":
main()
+111
View File
@@ -0,0 +1,111 @@
"""Server-side role and capability resolution for the unified AIOS portal."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Mapping, Sequence
from aios_v2.control_plane import RequestContext, Unauthorized
ROLE_CAPABILITIES: Mapping[str, frozenset[str]] = {
"platform_admin": frozenset({
"portal.access", "dashboard.read", "tenant.read", "tenant.manage",
"agent.read", "agent.manage", "task.read", "task.create", "task.approve",
"task.cancel", "task.dispatch", "policy.read", "audit.read", "evidence.read",
"runtime.read", "runtime.operate", "dispatch.read", "provenance.read",
"provenance.revoke", "external_task.read", "gitops.read", "release.read",
"release.operate", "worktree.read", "system.admin",
}),
"tenant_admin": frozenset({
"portal.access", "dashboard.read", "tenant.read", "agent.read", "agent.manage",
"task.read", "task.create", "task.approve", "task.cancel", "task.dispatch",
"policy.read", "audit.read", "evidence.read", "runtime.read", "dispatch.read",
"provenance.read", "provenance.revoke", "external_task.read", "gitops.read",
"release.read",
}),
"operator": frozenset({
"portal.access", "dashboard.read", "tenant.read", "agent.read", "task.read",
"task.create", "task.cancel", "task.dispatch", "runtime.read", "dispatch.read",
"evidence.read", "provenance.read", "external_task.read", "gitops.read",
"release.read",
}),
"approver": frozenset({
"portal.access", "dashboard.read", "tenant.read", "task.read", "task.approve",
"task.cancel", "policy.read", "audit.read", "provenance.read", "evidence.read",
"external_task.read", "release.read",
}),
"auditor": frozenset({
"portal.access", "dashboard.read", "tenant.read", "agent.read", "task.read",
"audit.read", "evidence.read", "runtime.read", "dispatch.read",
"provenance.read", "external_task.read", "gitops.read", "release.read",
"worktree.read",
}),
"runtime": frozenset({
"portal.access", "dashboard.read", "task.read", "runtime.read", "runtime.operate",
"dispatch.read", "evidence.read", "provenance.read", "external_task.read",
}),
"release_manager": frozenset({
"portal.access", "dashboard.read", "audit.read", "runtime.read", "dispatch.read",
"provenance.read", "external_task.read", "gitops.read", "release.read",
"release.operate", "worktree.read",
}),
"viewer": frozenset({
"portal.access", "dashboard.read", "task.read", "runtime.read",
"external_task.read",
}),
}
NAVIGATION: Sequence[Mapping[str, str]] = (
{"id": "overview", "label": "总览", "capability": "dashboard.read"},
{"id": "resources", "label": "租户与 Agent", "capability": "tenant.read"},
{"id": "tasks", "label": "任务中心", "capability": "task.read"},
{"id": "execution", "label": "执行中心", "capability": "external_task.read"},
{"id": "authorization", "label": "授权中心", "capability": "provenance.read"},
{"id": "runtime", "label": "运行与运维", "capability": "runtime.read"},
{"id": "evidence", "label": "执行证据", "capability": "evidence.read"},
{"id": "audit", "label": "审计中心", "capability": "audit.read"},
{"id": "release", "label": "GitOps 与发布", "capability": "release.read"},
)
@dataclass(frozen=True)
class ResolvedCapabilities:
tenant_id: str
principal_id: str
roles: tuple[str, ...]
capabilities: tuple[str, ...]
navigation: tuple[Mapping[str, str], ...]
def as_dict(self) -> dict[str, object]:
return {
"tenant_id": self.tenant_id,
"principal_id": self.principal_id,
"roles": list(self.roles),
"capabilities": list(self.capabilities),
"navigation": [dict(item) for item in self.navigation],
}
def resolve(context: RequestContext) -> ResolvedCapabilities:
capabilities: set[str] = set()
for role in context.roles:
capabilities.update(ROLE_CAPABILITIES.get(role, ()))
ordered = tuple(sorted(capabilities))
navigation = tuple(item for item in NAVIGATION if item["capability"] in capabilities)
return ResolvedCapabilities(
tenant_id=context.tenant_id,
principal_id=context.principal_id,
roles=tuple(sorted(context.roles)),
capabilities=ordered,
navigation=navigation,
)
def require(context: RequestContext, capability: str) -> None:
if capability not in resolve(context).capabilities:
raise Unauthorized(f"portal capability is required: {capability}")
def allows(context: RequestContext, capability: str) -> bool:
return capability in resolve(context).capabilities
+48
View File
@@ -0,0 +1,48 @@
"""Unified portal HTML export with V2R1C2 resource and execution centers.
The canonical dependency-free portal remains in ``aios_v2.console``. This
module applies deterministic, fail-fast extensions at import time so the
V2R1C1 production entrypoint remains unchanged while the V2R1C2 candidate gets
resource and portable-executor views.
"""
from __future__ import annotations
from aios_v2.console import CONSOLE_HTML as _BASE_PORTAL_HTML
def _extend_portal(source: str) -> str:
replacements = (
(
'<section id="overview" class="view active"></section>\n <section id="tasks" class="view"></section>\n <section id="authorization" class="view"></section>',
'<section id="overview" class="view active"></section>\n <section id="resources" class="view"></section>\n <section id="tasks" class="view"></section>\n <section id="execution" class="view"></section>\n <section id="authorization" class="view"></section>',
),
(
"const labels={overview:'系统总览',tasks:'任务中心',authorization:'授权中心'",
"const labels={overview:'系统总览',resources:'租户与 Agent',tasks:'任务中心',execution:'执行中心',authorization:'授权中心'",
),
(
"if(view==='overview')await overview();if(view==='tasks')await tasks();if(view==='authorization')await authorizations();",
"if(view==='overview')await overview();if(view==='resources')await resources();if(view==='tasks')await tasks();if(view==='execution')await execution();if(view==='authorization')await authorizations();",
),
(
"async function tasks(){const d=await api('/api/v2/portal/tasks');",
"""async function resources(){const d=await api('/api/v2/portal/resources');const t=d.tenant||{},agents=d.agents||[],ops=d.operations||{};const agentButton=ops.agent_create?'<button class=\"btn\" id=\"newAgent\">注册 Agent</button>':'';$('#resources').innerHTML=`<div class=\"cards\">${card('租户',t.tenant_id||'—',t.status||'')}${card('Agent',d.summary?.agents||0,`启用 ${d.summary?.enabled_agents||0}`)}${card('任务',d.summary?.tasks||0)}${card('Runtime 类型',(d.summary?.runtimes||[]).length,(d.summary?.runtimes||[]).join(', '))}</div><div class=\"grid\"><div class=\"panel\"><div class=\"panel-head\"><h2>当前租户</h2></div><div class=\"kv\"><div>Tenant ID</div><div>${esc(t.tenant_id||'—')}</div><div>名称</div><div>${esc(t.display_name||'—')}</div><div>状态</div><div>${pill(t.status||'unknown')}</div><div>创建时间</div><div>${esc(t.created_at||'—')}</div><div>更新时间</div><div>${esc(t.updated_at||'—')}</div></div></div><div class=\"panel\"><div class=\"panel-head\"><h2>Agent Registry</h2><div>${agentButton}</div></div>${table([['Agent',x=>esc(x.agent_id)],['名称',x=>esc(x.display_name)],['Runtime',x=>pill(x.runtime)],['能力',x=>(x.capabilities||[]).map(pill).join('')],['启用',x=>pill(x.enabled?'enabled':'disabled')],['任务数',x=>esc(x.task_count)]],agents)}</div></div>`;$('#newAgent')?.addEventListener('click',()=>{const agent_id=prompt('Agent ID');const display_name=prompt('显示名称',agent_id||'');const runtime=prompt('Runtime Provider','openclaw');const capabilities=prompt('能力,逗号分隔','');if(!agent_id||!display_name||!runtime)return;api('/api/v2/portal/agents',{method:'POST',body:JSON.stringify({agent_id,display_name,runtime,capabilities:String(capabilities||'').split(',').map(x=>x.trim()).filter(Boolean),metadata:{source:'unified-portal'}})}).then(resources).catch(err)})}
function executionStage(x){const s=x.stage||{},status=x.truth||{},record=status.record||{},gate=status.gate||{},d=x.dependency_gate||{},notifications=gate.notifications||[],evidence=record.evidence||{};const stateName=record.state||'WAITING_DEPENDENCY';const deps=(s.depends_on||[]).join(', ')||'根阶段';return `<div class=\"panel\" style=\"background:#fbfcfe\"><div class=\"panel-head\"><h2>${esc(s.stage_id)} · ${esc(s.role)}</h2><div>${pill(stateName)} ${pill(s.executor_type)}</div></div><div class=\"chain\"><div class=\"chain-item\"><b>Provider</b><div>${esc(s.executor_type)}</div><small>${esc(deps)}</small></div><span class=\"chain-arrow\">→</span><div class=\"chain-item\"><b>Run</b><div>${esc(record.executor_run_id||'未注册')}</div><small>${esc(record.executor_id||'')}</small></div><span class=\"chain-arrow\">→</span><div class=\"chain-item\"><b>Progress</b><div>${esc(record.current_step||0)}/${esc((record.manifest?.steps||s.steps||[]).length)}</div><small>${esc(record.heartbeat_at||'无心跳')}</small></div><span class=\"chain-arrow\">→</span><div class=\"chain-item\"><b>Evidence</b><div>${Object.keys(evidence).length} 项</div><small>${Object.keys(evidence).slice(0,2).map(esc).join(', ')}</small></div><span class=\"chain-arrow\">→</span><div class=\"chain-item\"><b>Notification</b><div>${notifications.length} 条</div><small>${notifications.map(n=>n.status).join(', ')||'无'}</small></div><span class=\"chain-arrow\">→</span><div class=\"chain-item\"><b>Gate</b><div>${pill(gate.passed?'PASS':'BLOCKED')}</div><small>${d.passed?'依赖满足':'等待依赖'}</small></div></div>${Object.keys(record.error||{}).length?json(record.error):''}</div>`}
async function execution(){const d=await api('/api/v2/portal/execution');const providers=d.providers||[],plans=d.plans||[];$('#execution').innerHTML=`<div class=\"cards\">${card('Provider',providers.length)}${card('Execution Plan',plans.length)}${card('协议',d.protocol_version||'—')}${card('Plan Schema',d.plan_schema_version||'—')}</div><div class=\"panel\"><div class=\"panel-head\"><h2>Executor Provider Catalog</h2></div>${table([['Provider',x=>esc(x.executor_type)],['Adapter',x=>esc(x.adapter_version)],['协议',x=>esc(x.protocol_version)],['Trust Roles',x=>(x.trust_roles||[]).map(pill).join('')],['Capabilities',x=>(x.capabilities||[]).map(pill).join('')]],providers)}</div>${plans.map(p=>`<div class=\"panel\"><div class=\"panel-head\"><h2>${esc(p.plan_id)} · ${esc(p.target_version)}</h2><div>${pill(p.gate?.passed?'PASS':'BLOCKED')}</div></div><div class=\"kv\"><div>Source Branch</div><div>${esc(p.source_branch)}</div><div>Source OID</div><div>${esc(p.source_oid)}</div><div>Release Gate</div><div>${pill(p.gate?.passed?'PASS':'BLOCKED')}</div></div></div>${(p.snapshot?.stages||[]).map(executionStage).join('')}`).join('')||'<div class=\"empty\">尚未声明执行计划</div>'}`}
async function tasks(){const d=await api('/api/v2/portal/tasks');""",
),
)
result = source
for old, new in replacements:
if old not in result:
raise RuntimeError(f"unified portal extension anchor not found: {old[:100]}")
result = result.replace(old, new, 1)
return result
PORTAL_HTML = _extend_portal(_BASE_PORTAL_HTML)
if "\n+function executionStage" in PORTAL_HTML or "\n+async function execution" in PORTAL_HTML:
raise RuntimeError("execution center contains an invalid diff marker")
__all__ = ["PORTAL_HTML"]
@@ -0,0 +1,130 @@
"""HTTP facade for portable multi-provider execution plans."""
from __future__ import annotations
import urllib.parse
from http import HTTPStatus
from typing import Any, Mapping
from aios_v2.control_plane import RequestContext, Unauthorized
from aios_v2.execution_plan import ExecutionPlanCoordinator
from aios_v2.executor_protocol import ExecutorProviderRegistry, normalize_executor
from .capabilities import require
class ExecutionPlanAPI:
"""Portal read model and provider-authenticated plan discovery API."""
INTERNAL_PREFIX = "/api/v2/internal/execution-plans"
PORTAL_PATH = "/api/v2/portal/execution"
def __init__(
self,
coordinator: ExecutionPlanCoordinator,
*,
providers: ExecutorProviderRegistry,
) -> None:
self.coordinator = coordinator
self.providers = providers
@classmethod
def is_route(cls, raw_path: str) -> bool:
path = urllib.parse.urlparse(raw_path).path.rstrip("/") or "/"
return path == cls.PORTAL_PATH or path.startswith(cls.INTERNAL_PREFIX)
def _require_provider(
self,
context: RequestContext,
executor_type: str,
) -> str:
normalized = normalize_executor(executor_type)
if not self.providers.trusted(
executor_type=normalized,
roles=tuple(context.roles),
platform_admin="platform_admin" in context.roles,
):
raise Unauthorized(
f"trusted role for executor Provider is required: {normalized}"
)
return normalized
def _portal_snapshot(self) -> Mapping[str, Any]:
plans = []
for plan in self.coordinator.plan_store.list():
plans.append(
{
"plan_id": plan.plan_id,
"target_version": plan.target_version,
"source_branch": plan.source_branch,
"source_oid": plan.source_oid,
"snapshot": self.coordinator.snapshot(plan.plan_id),
"gate": self.coordinator.gate(plan.plan_id),
}
)
return {
"protocol_version": "aios.executor.v1",
"plan_schema_version": "aios.execution-plan.v2",
"providers": [
item.as_dict() for item in self.providers.list_descriptors()
],
"plans": plans,
}
def handle(
self,
method: str,
raw_path: str,
context: RequestContext,
body: Any,
) -> tuple[int, Mapping[str, Any]]:
del body
parsed = urllib.parse.urlparse(raw_path)
path = parsed.path.rstrip("/") or "/"
method = method.upper()
if method == "GET" and path == self.PORTAL_PATH:
require(context, "external_task.read")
return HTTPStatus.OK, self._portal_snapshot()
if not path.startswith(f"{self.INTERNAL_PREFIX}/"):
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "execution plan route not found",
}
remainder = urllib.parse.unquote(path[len(self.INTERNAL_PREFIX) + 1 :])
parts = tuple(item for item in remainder.split("/") if item)
if len(parts) != 2:
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "execution plan route not found",
}
plan_id, action = parts
query = urllib.parse.parse_qs(parsed.query)
executor_type = self._require_provider(
context,
str(query.get("executor", [""])[0]),
)
if method == "GET" and action == "discover":
items = self.coordinator.discover_ready(
plan_id=plan_id,
executor_type=executor_type,
)
return HTTPStatus.OK, {
"plan_id": plan_id,
"executor_type": executor_type,
"count": len(items),
"items": items,
}
if method == "GET" and action == "snapshot":
return HTTPStatus.OK, self.coordinator.snapshot(plan_id)
if method == "GET" and action == "gate":
return HTTPStatus.OK, self.coordinator.gate(plan_id)
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "execution plan route not found",
}
@@ -0,0 +1,276 @@
"""Protected HTTP facade for portable executor truth and notification receipts."""
from __future__ import annotations
import urllib.parse
from http import HTTPStatus
from pathlib import Path
from typing import Any, Mapping, Sequence
from aios_v2.control_plane import RequestContext, Unauthorized
from aios_v2.executor_protocol import ExecutorProviderRegistry, normalize_executor
from aios_v2.external_task_control import ExternalTaskCoordinator
from aios_v2.external_task_query import list_records
from aios_v2.task_execution_registry import ExecutionTruthState
from .capabilities import require
def _body(value: Any) -> Mapping[str, Any]:
if not isinstance(value, Mapping):
raise ValueError("JSON body must be an object")
return value
def _required(value: Any, label: str) -> str:
normalized = str(value or "").strip()
if not normalized:
raise ValueError(f"{label} is required")
return normalized
def _mapping_strings(value: Any, label: str) -> dict[str, str]:
if not isinstance(value, Mapping):
raise ValueError(f"{label} must be an object")
return {
_required(key, f"{label} key"): _required(item, f"{label}[{key}]")
for key, item in value.items()
}
class ExternalTaskAPI:
"""Fail-closed external task API shared by every registered Provider."""
INTERNAL_PREFIX = "/api/v2/internal/external-tasks"
def __init__(
self,
coordinator: ExternalTaskCoordinator,
*,
store_file: str | Path,
providers: ExecutorProviderRegistry,
) -> None:
self.coordinator = coordinator
self.store_file = Path(store_file).resolve()
self.providers = providers
@staticmethod
def is_route(path: str) -> bool:
normalized = path.rstrip("/") or "/"
return normalized.startswith(ExternalTaskAPI.INTERNAL_PREFIX) or normalized == "/api/v2/portal/external-tasks"
def _require_executor(self, context: RequestContext, executor_type: str) -> str:
normalized = normalize_executor(executor_type)
if not self.providers.trusted(
executor_type=normalized,
roles=tuple(context.roles),
platform_admin="platform_admin" in context.roles,
):
raise Unauthorized(
f"trusted role for executor Provider is required: {normalized}"
)
return normalized
def _task_executor(self, task_id: str) -> str:
return normalize_executor(
self.coordinator.registry.get(task_id).manifest.executor
)
@staticmethod
def _executor_identity(
context: RequestContext,
payload: Mapping[str, Any],
) -> str:
executor_id = _required(payload.get("executor_id"), "executor_id")
if executor_id != context.principal_id and "platform_admin" not in context.roles:
raise Unauthorized("executor_id must match trusted principal")
return executor_id
def declare_directory(self, directory: str | Path) -> list[Mapping[str, Any]]:
root = Path(directory).resolve()
if not root.exists():
return []
declared: list[Mapping[str, Any]] = []
for manifest in sorted(root.glob("*.json")):
record = self.coordinator.declare_file(manifest)
self.providers.validate_manifest(record.manifest)
declared.append(
{
"manifest": str(manifest),
"task_id": record.task_id,
"executor_type": record.manifest.executor,
"state": record.state.value,
}
)
return declared
def handle(
self,
method: str,
raw_path: str,
context: RequestContext,
body: Any,
) -> tuple[int, Mapping[str, Any]]:
parsed = urllib.parse.urlparse(raw_path)
path = parsed.path.rstrip("/") or "/"
method = method.upper()
payload = _body(body or {})
if method == "GET" and path == "/api/v2/portal/external-tasks":
require(context, "external_task.read")
records = list_records(self.store_file)
return HTTPStatus.OK, {
"count": len(records),
"items": [self.coordinator.status(item.task_id) for item in records],
}
if method == "GET" and path == f"{self.INTERNAL_PREFIX}/discover":
query = urllib.parse.parse_qs(parsed.query)
states = tuple(query.get("state", ()))
executor = self._require_executor(
context,
str(query.get("executor", [""])[0]),
)
records = list_records(
self.store_file,
executor=executor,
states=states,
)
return HTTPStatus.OK, {
"count": len(records),
"executor_type": executor,
"items": [item.as_dict() for item in records],
}
if method == "GET" and path == f"{self.INTERNAL_PREFIX}/notifications":
query = urllib.parse.parse_qs(parsed.query)
executor = self._require_executor(
context,
str(query.get("executor", [""])[0]),
)
task_id = query.get("task_id", [None])[0]
status = query.get("status", [None])[0]
items = self.coordinator.notifications.list(
task_id=task_id,
status=status,
)
filtered = [
item
for item in items
if self._task_executor(item.task_id) == executor
]
return HTTPStatus.OK, {
"count": len(filtered),
"executor_type": executor,
"items": [item.as_dict() for item in filtered],
}
notification_ack = self._match(
path,
f"{self.INTERNAL_PREFIX}/notifications/",
"/ack",
)
if method == "POST" and notification_ack:
notification = self.coordinator.notifications.get(notification_ack)
executor = self._task_executor(notification.task_id)
self._require_executor(context, executor)
self._executor_identity(context, payload)
record = self.coordinator.notifications.acknowledge(
notification_ack,
receipt_sha256=_required(
payload.get("receipt_sha256"),
"receipt_sha256",
),
)
return HTTPStatus.OK, {"notification": record.as_dict()}
truth_task = self._match(path, f"{self.INTERNAL_PREFIX}/", "/truth")
if method == "GET" and truth_task:
self._require_executor(context, self._task_executor(truth_task))
return HTTPStatus.OK, self.coordinator.status(truth_task)
for action in ("register", "retry", "claim", "start", "heartbeat", "succeed", "fail"):
task_id = self._match(path, f"{self.INTERNAL_PREFIX}/", f"/{action}")
if method != "POST" or not task_id:
continue
executor_type = self._task_executor(task_id)
self._require_executor(context, executor_type)
run_id = _required(payload.get("executor_run_id"), "executor_run_id")
if action == "register":
return HTTPStatus.OK, {
"record": self.coordinator.register(
task_id,
executor_run_id=run_id,
).as_dict()
}
if action == "retry":
return HTTPStatus.OK, {
"record": self.coordinator.retry_not_started(
task_id,
executor_run_id=run_id,
).as_dict()
}
executor_id = self._executor_identity(context, payload)
if action == "claim":
record = self.coordinator.claim(
task_id,
executor_run_id=run_id,
executor_id=executor_id,
)
elif action == "start":
record = self.coordinator.start(
task_id,
executor_run_id=run_id,
executor_id=executor_id,
)
elif action == "heartbeat":
record = self.coordinator.heartbeat(
task_id,
executor_run_id=run_id,
executor_id=executor_id,
current_step=int(payload.get("current_step")),
)
elif action == "succeed":
record = self.coordinator.succeed(
task_id,
executor_run_id=run_id,
executor_id=executor_id,
evidence=_mapping_strings(payload.get("evidence"), "evidence"),
)
else:
error = payload.get("error")
if not isinstance(error, Mapping):
raise ValueError("error must be an object")
evidence_value = payload.get("evidence")
evidence = (
_mapping_strings(evidence_value, "evidence")
if evidence_value is not None
else None
)
record = self.coordinator.fail(
task_id,
executor_run_id=run_id,
executor_id=executor_id,
error=dict(error),
evidence=evidence,
)
return HTTPStatus.OK, {"record": record.as_dict()}
return HTTPStatus.NOT_FOUND, {
"error": "not_found",
"message": "external task route not found",
}
@staticmethod
def _match(path: str, prefix: str, suffix: str) -> str | None:
if not path.startswith(prefix) or not path.endswith(suffix):
return None
middle = path[len(prefix) : len(path) - len(suffix)]
if not middle or "/" in middle:
return None
return urllib.parse.unquote(middle)
DISCOVERABLE_STATES: Sequence[str] = (
ExecutionTruthState.DECLARED.value,
ExecutionTruthState.REGISTERED.value,
)
@@ -0,0 +1,376 @@
"""V2R1C2 unified portal and portable executor release entrypoint.
The V2R1C1 production entrypoint remains unchanged. This candidate entrypoint
uses an isolated state directory, loads a versioned executor catalog, declares
portable multi-provider execution plans and exposes both portal read models and
provider-authenticated lifecycle APIs.
"""
from __future__ import annotations
import json
import os
import re
import urllib.parse
from dataclasses import replace
from http import HTTPStatus
from pathlib import Path
from typing import Any, Mapping, Sequence
import aios_v2.app as candidate_app_module
from aios_v2.app import (
CandidateApplication,
CandidateHTTPServer,
build_application as build_candidate_application,
)
from aios_v2.control_plane import RequestContext
from aios_v2.execution_plan import ExecutionPlanCoordinator, ExecutionPlanManifest
from aios_v2.executor_catalog import FileExecutorCatalogStore
from aios_v2.official_executor_providers import official_provider_factories
from .application import UnifiedPortalApplication, _json_value, _mapping
from .capabilities import allows, require
from .console import PORTAL_HTML
from .execution_plan_api import ExecutionPlanAPI
from .external_task_api import ExternalTaskAPI
_READ_BRIDGE_ROLES = frozenset({"approver", "runtime", "viewer", "release_manager"})
_GIT_OID = re.compile(r"^[0-9a-f]{40}$")
def _resolve_environment_value(value: Any, *, label: str) -> Any:
if not isinstance(value, str) or not value.startswith("ENV:"):
return value
variable = value[4:].strip()
if not variable:
raise ValueError(f"{label} environment variable name is empty")
resolved = str(os.getenv(variable, "")).strip()
if not resolved:
raise RuntimeError(f"required environment variable is not set: {variable}")
return resolved
def _load_execution_plan(path: str | Path) -> ExecutionPlanManifest:
source = Path(path).resolve()
value = json.loads(source.read_text(encoding="utf-8"))
if not isinstance(value, Mapping):
raise ValueError(f"execution plan must contain a JSON object: {source}")
payload = dict(value)
for label in ("source_branch", "source_oid", "target_version"):
payload[label] = _resolve_environment_value(payload.get(label), label=label)
source_oid = str(payload.get("source_oid") or "").strip().lower()
if not _GIT_OID.fullmatch(source_oid):
raise ValueError(
"execution plan source_oid must resolve to an exact 40-character Git OID"
)
payload["source_oid"] = source_oid
return ExecutionPlanManifest.from_dict(payload)
def _path_list(value: str) -> tuple[Path, ...]:
return tuple(
Path(item).expanduser().resolve()
for item in value.split(os.pathsep)
if item.strip()
)
class V2R1C2PortalApplication(UnifiedPortalApplication):
"""Unified portal candidate with provider-neutral execution governance."""
def __init__(
self,
base: CandidateApplication,
*,
provenance_store_file: str | Path,
external_task_api: ExternalTaskAPI,
execution_plan_api: ExecutionPlanAPI,
plan_coordinator: ExecutionPlanCoordinator,
catalog_snapshot: Mapping[str, Any],
declared_plans: Sequence[str],
) -> None:
super().__init__(base, provenance_store_file=provenance_store_file)
self.external_task_api = external_task_api
self.execution_plan_api = execution_plan_api
self.plan_coordinator = plan_coordinator
self.catalog_snapshot = dict(catalog_snapshot)
self.declared_plans = tuple(declared_plans)
def context(self, headers: Mapping[str, str]) -> RequestContext:
original = self.base.context(headers)
if original.roles.intersection(_READ_BRIDGE_ROLES):
return replace(original, roles=frozenset((*original.roles, "auditor")))
return original
def _resource_snapshot(self, context: RequestContext) -> Mapping[str, Any]:
service = self.orchestrator.control_plane
tenant = service.get_tenant(context)
agents = service.list_agents(context) if allows(context, "agent.read") else []
tasks = service.list_tasks(context) if allows(context, "task.read") else []
tasks_by_agent: dict[str, int] = {}
for task in tasks:
tasks_by_agent[task.agent_id] = tasks_by_agent.get(task.agent_id, 0) + 1
return {
"tenant": _json_value(tenant),
"agents": [
{
**_json_value(agent),
"task_count": tasks_by_agent.get(agent.agent_id, 0),
}
for agent in agents
],
"summary": {
"agents": len(agents),
"enabled_agents": sum(1 for agent in agents if agent.enabled),
"tasks": len(tasks),
"runtimes": sorted({agent.runtime for agent in agents}),
},
"operations": {
"tenant_create": allows(context, "tenant.manage"),
"agent_create": allows(context, "agent.manage"),
},
}
def _runtime_snapshot(
self,
context: RequestContext,
headers: Mapping[str, str],
) -> Mapping[str, Any]:
return {
**self._runtime(headers),
"dispatches": _json_value(
self.orchestrator.dispatch_repository.list(
tenant_id=context.tenant_id
)
),
"hermes_jobs": _json_value(
self.hermes.list_jobs(tenant_id=context.tenant_id)
),
"contract": {
"openclaw": os.getenv(
"AIOS_OPENCLAW_CONTRACT_VERSION",
"aios.openclaw.command.v2",
),
"signature_algorithm": os.getenv(
"AIOS_OPENCLAW_SIGNATURE_ALGORITHM",
"Ed25519",
),
"plugin_version": os.getenv(
"AIOS_OPENCLAW_PLUGIN_VERSION",
"2.1.0-rc.4",
),
"key_id": os.getenv(
"AIOS_OPENCLAW_SIGNING_KEY_ID",
"openclaw-v2r1-candidate-ed25519",
),
"executor_protocol": "aios.executor.v1",
"execution_plan": "aios.execution-plan.v2",
},
}
def _release_snapshot(self, context: RequestContext) -> Mapping[str, Any]:
plans = []
for plan_id in self.declared_plans:
plans.append(
{
"plan_id": plan_id,
"gate": self.plan_coordinator.gate(plan_id),
}
)
aggregate_passed = bool(plans) and all(
item["gate"]["passed"] for item in plans
)
return {
**self._gitops(context),
"version": os.getenv("AIOS_RELEASE_VERSION", "V2R1C2-CANDIDATE"),
"target_version": os.getenv("AIOS_TARGET_VERSION", "V2R1C2"),
"release_oid": os.getenv("AIOS_RELEASE_OID", "candidate-not-tagged"),
"source_oid": os.getenv("AIOS_RELEASE_SOURCE_OID", "missing"),
"tag": os.getenv("AIOS_RELEASE_TAG", "NOT_CREATED"),
"baseline": os.getenv("AIOS_BASELINE_VERSION", "V2R1C1"),
"previous_version": os.getenv("AIOS_PREVIOUS_VERSION", "V2R1C1"),
"status": os.getenv("AIOS_RELEASE_STATUS", "CANDIDATE_VALIDATION"),
"evidence_manifest_sha256": os.getenv(
"AIOS_RELEASE_EVIDENCE_SHA256",
"pending",
),
"executor_catalog": {
"path": self.catalog_snapshot.get("path"),
"sha256": self.catalog_snapshot.get("catalog_sha256"),
"protocol_version": "aios.executor.v1",
},
"execution_plans": plans,
"execution_gate": {
"passed": aggregate_passed,
"release_blocking": not aggregate_passed,
},
"operations": (
["review_release", "request_tag", "request_rollback"]
if allows(context, "release.operate")
else []
),
"note": (
"Release operations remain GitOps approval requests. The portal "
"never mutates tags, main, or production directly. Tag approval "
"must remain blocked until every required execution-plan gate passes."
),
}
def handle_json(
self,
method: str,
raw_path: str,
headers: Mapping[str, str],
body: Any,
) -> tuple[int, Mapping[str, Any]]:
parsed = urllib.parse.urlparse(raw_path)
path = parsed.path.rstrip("/") or "/"
method = method.upper()
if self.execution_plan_api.is_route(raw_path):
context = (
self.context(headers)
if path == ExecutionPlanAPI.PORTAL_PATH
else self.base.context(headers)
)
return self.execution_plan_api.handle(
method,
raw_path,
context,
body,
)
if self.external_task_api.is_route(path):
context = (
self.context(headers)
if path == "/api/v2/portal/external-tasks"
else self.base.context(headers)
)
return self.external_task_api.handle(
method,
raw_path,
context,
body,
)
context: RequestContext | None = None
if path in {
"/api/v2/portal/resources",
"/api/v2/portal/runtime",
"/api/v2/portal/release",
"/api/v2/portal/tenants",
"/api/v2/portal/agents",
}:
context = self.context(headers)
if method == "GET" and path == "/api/v2/portal/resources":
assert context is not None
require(context, "tenant.read")
return HTTPStatus.OK, self._resource_snapshot(context)
if method == "POST" and path == "/api/v2/portal/tenants":
assert context is not None
require(context, "tenant.manage")
return self.base.handle_json(
"POST",
"/api/v2/tenants",
headers,
_mapping(body),
)
if method == "POST" and path == "/api/v2/portal/agents":
assert context is not None
require(context, "agent.manage")
return self.base.handle_json(
"POST",
"/api/v2/agents",
headers,
_mapping(body),
)
if method == "GET" and path == "/api/v2/portal/runtime":
assert context is not None
require(context, "runtime.read")
return HTTPStatus.OK, self._runtime_snapshot(context, headers)
if method == "GET" and path == "/api/v2/portal/release":
assert context is not None
require(context, "release.read")
return HTTPStatus.OK, self._release_snapshot(context)
return super().handle_json(method, raw_path, headers, body)
def build_application() -> V2R1C2PortalApplication:
state_dir = Path(
os.getenv("AIOS_V2_STATE_DIR", "/var/lib/aios-v2r1c2-portal")
).resolve()
state_dir.mkdir(parents=True, exist_ok=True)
provenance_file = Path(
os.getenv(
"AIOS_PROVENANCE_STORE_FILE",
str(state_dir / "run-provenance.sqlite3"),
)
).resolve()
truth_file = Path(
os.getenv(
"AIOS_EXTERNAL_TASK_STORE_FILE",
str(state_dir / "external-task-truth.sqlite3"),
)
).resolve()
catalog_file = Path(
os.getenv(
"AIOS_EXECUTOR_CATALOG_FILE",
str(state_dir / "executor-catalog.json"),
)
).resolve()
catalog_store = FileExecutorCatalogStore(catalog_file)
catalog_snapshot = catalog_store.initialize_defaults()
providers = catalog_store.registry(
provider_factories=official_provider_factories()
)
plan_coordinator = ExecutionPlanCoordinator.from_file(
truth_file,
providers=providers,
)
declared_plans: list[str] = []
plan_files = _path_list(os.getenv("AIOS_EXECUTION_PLAN_FILES", ""))
for plan_file in plan_files:
plan = _load_execution_plan(plan_file)
plan_coordinator.declare(plan)
declared_plans.append(plan.plan_id)
base: CandidateApplication = build_candidate_application()
external_task_api = ExternalTaskAPI(
plan_coordinator.task_coordinator,
store_file=truth_file,
providers=providers,
)
execution_plan_api = ExecutionPlanAPI(
plan_coordinator,
providers=providers,
)
return V2R1C2PortalApplication(
base,
provenance_store_file=provenance_file,
external_task_api=external_task_api,
execution_plan_api=execution_plan_api,
plan_coordinator=plan_coordinator,
catalog_snapshot=catalog_snapshot.as_dict(),
declared_plans=declared_plans,
)
def main() -> None:
candidate_app_module.CONSOLE_HTML = PORTAL_HTML
host = os.getenv("AIOS_V2_HOST", "127.0.0.1")
port = int(os.getenv("AIOS_V2_PORT", "18921"))
server = CandidateHTTPServer((host, port), build_application())
print(f"AIOS V2R1C2 unified portal listening on {host}:{port}")
server.serve_forever()
if __name__ == "__main__":
main()
@@ -1,953 +0,0 @@
"""Owner-authorized, fail-closed task writer provisioning bridge.
This module converts an authenticated Owner authorization into a canonical,
short-lived, one-time grant request. It delegates signing, validation and
worktree/writer provisioning to existing root-governed executables.
It never writes Git refs directly and never authorizes main, tag, baseline or
production mutations.
"""
from __future__ import annotations
import fcntl
import hashlib
import json
import os
import re
import secrets
import shutil
import stat
import subprocess
import tempfile
from dataclasses import dataclass
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Mapping
from signer_contract_compatibility import (
deployed_signer_help,
run_compatible_signer,
run_compatible_validator,
)
OID_RE = re.compile(r"^[0-9a-f]{40}$")
SHA256_RE = re.compile(r"^[0-9a-f]{64}$")
TASK_RE = re.compile(r"^[A-Z0-9][A-Z0-9._:-]{7,127}$")
BRANCH_RE = re.compile(r"^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$")
OWNER_REF_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:/@+-]{3,255}$")
REQUIRED_REQUEST_FIELDS = frozenset(
{
"task_id",
"repository",
"base_ref",
"base_oid",
"target_branch",
"owner_authorization_reference",
"one_time_use",
"expires_in_seconds",
"production_change_authorized",
"tag_change_authorized",
"baseline_change_authorized",
"main_write_authorized",
"allowed_operations",
"denied_operations",
}
)
REQUIRED_ALLOWED_OPERATIONS = frozenset(
{
"create_worktree",
"create_target_branch_if_absent",
"commit_to_target_branch",
"push_target_branch",
}
)
REQUIRED_DENIED_OPERATIONS = frozenset(
{
"direct_main_push",
"force_push",
"tag_create",
"tag_update",
"tag_delete",
"branch_delete",
"repository_admin",
"baseline_write",
"production_deploy",
"production_marker_write",
"history_rewrite",
}
)
REQUIRED_NEGATIVE_TESTS = frozenset(
{
"main_write_denied",
"other_branch_write_denied",
"tag_create_denied",
"tag_update_denied",
"baseline_write_denied",
"force_push_denied",
"branch_delete_denied",
}
)
SENSITIVE_KEY_MARKERS = (
"authorization",
"credential",
"private_key",
"secret",
"signature",
"token",
)
class ProvisioningError(RuntimeError):
"""Stable fail-closed error returned to the API adapter."""
def __init__(
self,
code: str,
status: int = 400,
*,
details: Mapping[str, Any] | None = None,
) -> None:
super().__init__(code)
self.code = code
self.status = status
self.details = dict(details or {})
@dataclass(frozen=True)
class OwnerContext:
identity: str
role: str
authorization_reference: str
@dataclass(frozen=True)
class ProvisioningConfig:
repository_identity: str
authority_git_dir: Path
state_root: Path
signer: Path
validator: Path
provisioner: Path
governed_use_sudo: bool = False
sudo_path: Path = Path("/usr/bin/sudo")
max_expiry_seconds: int = 1800
@classmethod
def from_environment(cls) -> "ProvisioningConfig":
return cls(
repository_identity=os.getenv(
"AIOS_GITOPS_REPOSITORY_IDENTITY", "aios/aios"
).strip(),
authority_git_dir=Path(
os.getenv("AIOS_GITOPS_AUTHORITY_GIT_DIR", "/data/aios-gitops/repo.git")
),
state_root=Path(
os.getenv(
"AIOS_GITOPS_AUTHORIZED_WRITER_STATE_ROOT",
"/var/lib/aios-gitops/authorized-writer-bridge",
)
),
signer=Path(
os.getenv(
"AIOS_GITOPS_GRANT_SIGNER_ADAPTER",
"/usr/local/libexec/aios-grant-signer-adapter",
)
),
validator=Path(
os.getenv(
"AIOS_GITOPS_GRANT_VALIDATOR",
"/usr/local/libexec/aios-grant-validator",
)
),
provisioner=Path(
os.getenv(
"AIOS_GITOPS_TASK_WRITER_PROVISIONER",
"/usr/local/libexec/aios-task-writer-provisioner",
)
),
governed_use_sudo=os.getenv(
"AIOS_GITOPS_GOVERNED_USE_SUDO", ""
).strip().lower() in {"1", "true", "yes", "on"},
sudo_path=Path(
os.getenv("AIOS_GITOPS_SUDO_PATH", "/usr/bin/sudo")
),
)
def utc_now() -> datetime:
return datetime.now(timezone.utc)
def iso_utc(value: datetime) -> str:
return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
def canonical_json_bytes(value: Any) -> bytes:
return (
json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
+ "\n"
).encode("utf-8")
def sha256_json(value: Any) -> str:
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
def _atomic_write_json(path: Path, value: Any, mode: int = 0o600) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
if path.parent.is_symlink() or path.is_symlink():
raise ProvisioningError("STATE_PATH_SYMLINK_REJECTED", 500)
fd, temporary = tempfile.mkstemp(prefix=".tmp-", dir=path.parent)
try:
os.fchmod(fd, mode)
with os.fdopen(fd, "wb", closefd=True) as stream:
stream.write(canonical_json_bytes(value))
stream.flush()
os.fsync(stream.fileno())
os.replace(temporary, path)
os.chmod(path, mode)
parent_fd = os.open(path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0))
try:
os.fsync(parent_fd)
finally:
os.close(parent_fd)
finally:
if os.path.exists(temporary):
os.unlink(temporary)
def _read_json(path: Path) -> dict[str, Any]:
if path.is_symlink() or not path.is_file():
raise ProvisioningError("RESULT_FILE_INVALID", 500)
if path.stat().st_size <= 0 or path.stat().st_size > 1_048_576:
raise ProvisioningError("RESULT_FILE_INVALID", 500)
try:
value = json.loads(path.read_text(encoding="utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
raise ProvisioningError("RESULT_JSON_INVALID", 500) from None
if not isinstance(value, dict):
raise ProvisioningError("RESULT_OBJECT_REQUIRED", 500)
return value
def _safe_receipt_id(task_id: str, repository: str, branch: str) -> str:
return hashlib.sha256(f"{task_id}\0{repository}\0{branch}".encode()).hexdigest()
def _redacted(value: Any) -> Any:
if isinstance(value, dict):
cleaned = {}
for key, inner in value.items():
lowered = str(key).lower()
if any(marker in lowered for marker in SENSITIVE_KEY_MARKERS):
if lowered in {
"owner_authorization_reference",
"signing_key_identity",
"signer_identity",
}:
cleaned[key] = inner
else:
cleaned[key] = "[REDACTED]"
else:
cleaned[key] = _redacted(inner)
return cleaned
if isinstance(value, list):
return [_redacted(item) for item in value]
return value
def _run(
argv: list[str],
*,
env: Mapping[str, str] | None = None,
timeout: int = 60,
allowed_returncodes: tuple[int, ...] = (0,),
) -> subprocess.CompletedProcess[str]:
result = subprocess.run(
argv,
text=True,
capture_output=True,
check=False,
timeout=timeout,
env=dict(env) if env is not None else None,
)
if result.returncode not in allowed_returncodes:
raise ProvisioningError(
"GOVERNED_TOOL_FAILED",
503,
details={
"tool": Path(argv[0]).name,
"returncode": result.returncode,
"stderr": result.stderr[-1000:],
},
)
return result
def _git(git_dir: Path, *args: str, allowed_returncodes: tuple[int, ...] = (0,)) -> str:
result = _run(
["git", "--git-dir", str(git_dir), *args],
timeout=30,
allowed_returncodes=allowed_returncodes,
)
return result.stdout.strip()
def _verify_executable(path: Path, name: str) -> None:
if not path.is_absolute() or path.is_symlink() or not path.is_file():
raise ProvisioningError(f"{name}_EXECUTABLE_INVALID", 503)
info = path.stat(follow_symlinks=False)
if not stat.S_ISREG(info.st_mode) or not os.access(path, os.X_OK):
raise ProvisioningError(f"{name}_EXECUTABLE_INVALID", 503)
if info.st_mode & (stat.S_IWGRP | stat.S_IWOTH):
raise ProvisioningError(f"{name}_EXECUTABLE_PERMISSIONS_REJECTED", 503)
def _tool_argv(
config: ProvisioningConfig,
path: Path,
*args: str,
) -> list[str]:
if config.governed_use_sudo:
return [str(config.sudo_path), "-n", "--", str(path), *args]
return [str(path), *args]
def _verify_tool_contract(
path: Path,
name: str,
config: ProvisioningConfig,
) -> None:
_verify_executable(path, name)
if config.governed_use_sudo:
_verify_executable(config.sudo_path, "SUDO")
help_result = _run(_tool_argv(config, path, "--help"), timeout=15)
if name == "SIGNER":
sign_help = _run(
_tool_argv(config, path, "sign", "--help"),
timeout=15,
)
if deployed_signer_help(sign_help.stdout, sign_help.stderr):
_run(_tool_argv(config, path, "self-test"), timeout=30)
return
for flag in ("--grant-dir", "--result-json"):
if flag not in help_result.stdout and flag not in help_result.stderr:
raise ProvisioningError(f"{name}_CONTRACT_UNSUPPORTED", 503)
_run(_tool_argv(config, path, "--self-test"), timeout=30)
def _validate_request(
raw: Mapping[str, Any],
*,
owner: OwnerContext,
config: ProvisioningConfig,
) -> dict[str, Any]:
if owner.role != "owner" or not owner.identity.strip():
raise ProvisioningError("OWNER_AUTHORIZATION_REQUIRED", 403)
if set(raw) != REQUIRED_REQUEST_FIELDS:
raise ProvisioningError("REQUEST_FIELDS_REJECTED")
if raw["repository"] != config.repository_identity:
raise ProvisioningError("REPOSITORY_IDENTITY_MISMATCH", 409)
if raw["base_ref"] != "refs/heads/main":
raise ProvisioningError("BASE_REF_REJECTED", 409)
if not isinstance(raw["base_oid"], str) or not OID_RE.fullmatch(raw["base_oid"]):
raise ProvisioningError("BASE_OID_REJECTED")
if (
not isinstance(raw["target_branch"], str)
or not BRANCH_RE.fullmatch(raw["target_branch"])
or raw["target_branch"] in {"main", "master"}
):
raise ProvisioningError("TARGET_BRANCH_REJECTED")
if not isinstance(raw["task_id"], str) or not TASK_RE.fullmatch(raw["task_id"]):
raise ProvisioningError("TASK_ID_REJECTED")
if (
not isinstance(raw["owner_authorization_reference"], str)
or not OWNER_REF_RE.fullmatch(raw["owner_authorization_reference"])
or raw["owner_authorization_reference"] != owner.authorization_reference
):
raise ProvisioningError("OWNER_AUTHORIZATION_REFERENCE_MISMATCH", 403)
if raw["one_time_use"] is not True:
raise ProvisioningError("ONE_TIME_USE_REQUIRED")
expiry = raw["expires_in_seconds"]
if (
not isinstance(expiry, int)
or isinstance(expiry, bool)
or not 60 <= expiry <= config.max_expiry_seconds
):
raise ProvisioningError("GRANT_LIFETIME_REJECTED")
for name in (
"production_change_authorized",
"tag_change_authorized",
"baseline_change_authorized",
"main_write_authorized",
):
if raw[name] is not False:
raise ProvisioningError("PRODUCTION_CAPABILITY_REJECTED", 403)
allowed = raw["allowed_operations"]
denied = raw["denied_operations"]
if not isinstance(allowed, list) or frozenset(allowed) != REQUIRED_ALLOWED_OPERATIONS:
raise ProvisioningError("ALLOWED_OPERATIONS_MISMATCH", 403)
if len(allowed) != len(set(allowed)):
raise ProvisioningError("ALLOWED_OPERATIONS_MISMATCH", 403)
if not isinstance(denied, list) or frozenset(denied) != REQUIRED_DENIED_OPERATIONS:
raise ProvisioningError("DENIED_OPERATIONS_MISMATCH", 403)
if len(denied) != len(set(denied)):
raise ProvisioningError("DENIED_OPERATIONS_MISMATCH", 403)
return dict(raw)
def _prepare_state_root(path: Path) -> None:
if not path.is_absolute() or path.is_symlink():
raise ProvisioningError("STATE_ROOT_INVALID", 500)
path.mkdir(parents=True, exist_ok=True, mode=0o700)
os.chmod(path, 0o700)
if path.stat().st_mode & (stat.S_IWGRP | stat.S_IWOTH):
raise ProvisioningError("STATE_ROOT_PERMISSIONS_REJECTED", 500)
(path / "receipts").mkdir(mode=0o700, exist_ok=True)
(path / "locks").mkdir(mode=0o700, exist_ok=True)
def _prestart_git_check(
request: Mapping[str, Any],
config: ProvisioningConfig,
*,
receipt_exists: bool,
) -> dict[str, Any]:
git_dir = config.authority_git_dir
if not git_dir.is_absolute() or git_dir.is_symlink() or not git_dir.is_dir():
raise ProvisioningError("AUTHORITY_GIT_DIR_INVALID", 503)
actual_main = _git(git_dir, "rev-parse", request["base_ref"])
if actual_main != request["base_oid"]:
raise ProvisioningError(
"AUTHORIZED_BASE_OID_DRIFT",
409,
details={"expected": request["base_oid"], "actual": actual_main},
)
ref = f"refs/heads/{request['target_branch']}"
existing = _git(
git_dir,
"show-ref",
"--verify",
"--hash",
ref,
allowed_returncodes=(0, 1, 128),
)
if existing and not receipt_exists:
raise ProvisioningError(
"EXISTING_BRANCH_OID_CONFLICT",
409,
details={"branch_oid": existing},
)
if existing and receipt_exists:
ancestor = _run(
[
"git",
"--git-dir",
str(git_dir),
"merge-base",
"--is-ancestor",
request["base_oid"],
ref,
],
allowed_returncodes=(0, 1),
)
if ancestor.returncode != 0:
raise ProvisioningError("EXISTING_BRANCH_OID_CONFLICT", 409)
return {
"authoritative_main_oid": actual_main,
"target_branch_preexisting": bool(existing),
"target_branch_oid": existing or None,
}
def _build_plan(
request: Mapping[str, Any],
owner: OwnerContext,
*,
now: datetime,
) -> tuple[dict[str, Any], dict[str, Any]]:
expires_at = now + timedelta(seconds=int(request["expires_in_seconds"]))
grant_request = {
"schema": "aios.task-scoped-writer-grant-request.v1",
"task_id": request["task_id"],
"repository": request["repository"],
"base": {"ref": request["base_ref"], "oid": request["base_oid"]},
"target": {"branch": request["target_branch"]},
"execution_contract": {
"branch_creation": "governed_one_shot_provisioner",
"writer_route": "POST /api/commit-file",
"createBranch_route_required": False,
},
"owner_authorization": {
"identity": owner.identity,
"reference": owner.authorization_reference,
"authenticated_role": owner.role,
},
"allowed_operations": sorted(request["allowed_operations"]),
"denied_operations": sorted(request["denied_operations"]),
"one_time_use": True,
"authorization": {
"production_change_authorized": False,
"tag_change_authorized": False,
"baseline_change_authorized": False,
"main_write_authorized": False,
},
"issued_at": iso_utc(now),
"not_before": iso_utc(now - timedelta(seconds=2)),
"expires_at": iso_utc(expires_at),
"nonce": secrets.token_hex(32),
}
binding_digest = sha256_json(grant_request)
plan = {
"schema": "aios.task-scoped-writer-approval-plan.v1",
"approval_plan_id": f"sha256:{binding_digest}",
"grant_request_sha256": binding_digest,
"owner_authorization_reference": owner.authorization_reference,
"owner_identity": owner.identity,
"created_at": iso_utc(now),
"expires_at": iso_utc(expires_at),
"execute": True,
"production_change_authorized": False,
}
return plan, grant_request
def _expect_text(result: Mapping[str, Any], name: str) -> str:
value = result.get(name)
if not isinstance(value, str) or not value.strip():
raise ProvisioningError(f"{name.upper()}_MISSING", 503)
return value
def _verify_signer_result(
result: Mapping[str, Any],
*,
approval_plan_id: str,
) -> dict[str, str]:
if result.get("status") not in {"SIGNED", "PASS", "COMPLETED"}:
raise ProvisioningError("GRANT_SIGNING_FAILED", 503)
if result.get("approval_plan_id") != approval_plan_id:
raise ProvisioningError("APPROVAL_PLAN_ID_MISMATCH", 503)
digest = _expect_text(result, "grant_digest_sha256")
if not SHA256_RE.fullmatch(digest):
raise ProvisioningError("GRANT_DIGEST_INVALID", 503)
signer = result.get("signing_key_identity") or result.get("signer_identity")
if not isinstance(signer, str) or not signer.strip():
raise ProvisioningError("SIGNING_KEY_IDENTITY_MISSING", 503)
signature_present = bool(result.get("signature_present")) or bool(
result.get("owner_signature")
)
if not signature_present:
raise ProvisioningError("OWNER_SIGNATURE_MISSING", 503)
return {
"grant_id": _expect_text(result, "grant_id"),
"grant_digest_sha256": digest,
"signing_key_identity": signer,
}
def _verify_validator_result(
result: Mapping[str, Any],
*,
approval_plan_id: str,
grant_digest: str,
) -> None:
if result.get("status") not in {"PASS", "VALID", "COMPLETED"}:
raise ProvisioningError("GOVERNED_GRANT_VALIDATION_FAILED", 503)
if result.get("approval_plan_id") != approval_plan_id:
raise ProvisioningError("VALIDATED_PLAN_ID_MISMATCH", 503)
if result.get("grant_digest_sha256") != grant_digest:
raise ProvisioningError("VALIDATED_GRANT_DIGEST_MISMATCH", 503)
checks = result.get("checks")
required = {
"schema_valid",
"signature_valid",
"signer_trusted",
"approval_plan_active",
"repository_match",
"base_ref_match",
"base_oid_match",
"target_branch_match",
"one_time_use",
"allowed_operations_match",
"denied_operations_match",
}
if not isinstance(checks, dict) or any(checks.get(name) is not True for name in required):
raise ProvisioningError("GOVERNED_GRANT_VALIDATION_FAILED", 503)
def _verify_provisioner_result(
result: Mapping[str, Any],
request: Mapping[str, Any],
*,
grant_id: str,
validator_config_path: Path,
) -> dict[str, Any]:
if result.get("status") not in {"READY_FOR_CODE_AUTHORING", "COMPLETED"}:
raise ProvisioningError("TASK_WRITER_PROVISIONING_FAILED", 503)
# The legacy bridge created the target ref itself. Keep accepting it for
# controlled test doubles, but prefer the deployed direct one-shot writer.
if result.get("status") == "COMPLETED" and result.get("writer_mode") == "direct_one_shot_detached":
if result.get("target_branch") != request["target_branch"]:
raise ProvisioningError("PROVISIONED_BRANCH_MISMATCH", 503)
if result.get("base_oid") != request["base_oid"]:
raise ProvisioningError("PROVISIONED_BASE_MISMATCH", 503)
if result.get("writer_created") is not True:
raise ProvisioningError("TASK_WRITER_PROVISIONING_FAILED", 503)
writer_config_name = result.get("writer_config")
if not isinstance(writer_config_name, str) or not Path(writer_config_name).is_absolute():
raise ProvisioningError("WRITER_CONFIG_INVALID", 503)
writer_config_path = Path(writer_config_name)
writer_config = _read_json(writer_config_path)
if writer_config.get("status") != "READY":
raise ProvisioningError("WRITER_CONFIG_NOT_READY", 503)
if writer_config.get("target_branch") != request["target_branch"]:
raise ProvisioningError("WRITER_CONFIG_BRANCH_MISMATCH", 503)
if writer_config.get("base_oid") != request["base_oid"]:
raise ProvisioningError("WRITER_CONFIG_BASE_MISMATCH", 503)
if writer_config.get("worktree_mode") != "detached":
raise ProvisioningError("WRITER_MODE_UNSUPPORTED", 503)
workspace = writer_config.get("worktree")
if not isinstance(workspace, str) or not Path(workspace).is_absolute():
raise ProvisioningError("PROVISIONED_WORKSPACE_INVALID", 503)
credential_name = writer_config.get("runtime_credential_file")
if not isinstance(credential_name, str) or not Path(credential_name).is_absolute():
raise ProvisioningError("WRITER_CREDENTIAL_REF_INVALID", 503)
credential = Path(credential_name)
if not credential.is_file() or credential.is_symlink():
raise ProvisioningError("WRITER_CREDENTIAL_MISSING", 503)
credential_stat = credential.stat()
if credential_stat.st_uid != 0 or stat.S_IMODE(credential_stat.st_mode) != 0o400:
raise ProvisioningError("WRITER_CREDENTIAL_PERMISSIONS_INVALID", 503)
dynamic_config = _read_json(validator_config_path)
ledger_name = dynamic_config.get("consumed_grants_ledger")
if not isinstance(ledger_name, str) or not Path(ledger_name).is_absolute():
raise ProvisioningError("GRANT_LEDGER_REF_INVALID", 503)
ledger = Path(ledger_name)
consumed = False
if ledger.is_file() and not ledger.is_symlink():
for line in ledger.read_text(encoding="utf-8").splitlines():
try:
row = json.loads(line)
except json.JSONDecodeError:
continue
if (
isinstance(row, dict)
and row.get("grant_id") == grant_id
and row.get("target_branch") == request["target_branch"]
and row.get("base_oid") == request["base_oid"]
):
consumed = True
break
if not consumed:
raise ProvisioningError("ONE_TIME_GRANT_NOT_CONSUMED", 503)
scope = {
"workspace_role": "task-scoped-isolated-writer",
"writes_enabled": True,
"allowed_branch": request["target_branch"],
"allowed_base_oid": request["base_oid"],
"allow_main_write": False,
"allow_tag_write": False,
"allow_baseline_write": False,
"allow_force_push": False,
"allowed_routes": ["POST /api/commit-file"],
"writer_mode": "direct_one_shot_detached",
}
negatives = {name: True for name in sorted(REQUIRED_NEGATIVE_TESTS)}
return {
"branch": request["target_branch"],
"branch_oid": request["base_oid"],
"base_oid": request["base_oid"],
"workspace_path": workspace,
"writer_scope": scope,
"negative_tests": negatives,
"grant_consumed": True,
"remote_ref_status": "target_branch_absent_until_writer_push",
"remote_oid": None,
"detached_writer": True,
"writer_config_path": str(writer_config_path),
}
if result.get("branch") != request["target_branch"]:
raise ProvisioningError("PROVISIONED_BRANCH_MISMATCH", 503)
if result.get("base_oid") != request["base_oid"]:
raise ProvisioningError("PROVISIONED_BASE_MISMATCH", 503)
if result.get("branch_oid") != request["base_oid"]:
raise ProvisioningError("PROVISIONED_BRANCH_OID_MISMATCH", 503)
if result.get("grant_consumed") is not True:
raise ProvisioningError("ONE_TIME_GRANT_NOT_CONSUMED", 503)
workspace = result.get("workspace_path")
if not isinstance(workspace, str) or not Path(workspace).is_absolute():
raise ProvisioningError("PROVISIONED_WORKSPACE_INVALID", 503)
scope = result.get("writer_scope")
if not isinstance(scope, dict):
raise ProvisioningError("WRITER_SCOPE_ATTESTATION_MISSING", 503)
required_scope = {
"workspace_role": "task-scoped-isolated-writer",
"writes_enabled": True,
"allowed_branch": request["target_branch"],
"allowed_base_oid": request["base_oid"],
"allow_main_write": False,
"allow_tag_write": False,
"allow_baseline_write": False,
"allow_force_push": False,
}
for key, expected in required_scope.items():
if scope.get(key) != expected:
raise ProvisioningError("WRITER_SCOPE_ATTESTATION_MISMATCH", 503)
routes = scope.get("allowed_routes")
if routes != ["POST /api/commit-file"]:
raise ProvisioningError("WRITER_ROUTE_ATTESTATION_MISMATCH", 503)
negatives = result.get("negative_tests")
if not isinstance(negatives, dict) or any(
negatives.get(name) is not True for name in REQUIRED_NEGATIVE_TESTS
):
raise ProvisioningError("NEGATIVE_POLICY_TESTS_FAILED", 503)
return {
"branch": result["branch"],
"branch_oid": result["branch_oid"],
"base_oid": result["base_oid"],
"workspace_path": workspace,
"writer_scope": scope,
"negative_tests": {
name: True for name in sorted(REQUIRED_NEGATIVE_TESTS)
},
"grant_consumed": True,
"remote_ref_status": result.get("remote_ref_status"),
"remote_oid": result.get("remote_oid"),
"detached_writer": False,
"writer_config_path": None,
}
class AuthorizedTaskWriterProvisioner:
def __init__(
self,
config: ProvisioningConfig | None = None,
*,
clock=utc_now,
) -> None:
self.config = config or ProvisioningConfig.from_environment()
self.clock = clock
def provision(
self,
raw_request: Mapping[str, Any],
owner: OwnerContext,
) -> dict[str, Any]:
request = _validate_request(raw_request, owner=owner, config=self.config)
_prepare_state_root(self.config.state_root)
receipt_id = _safe_receipt_id(
request["task_id"], request["repository"], request["target_branch"]
)
receipt_path = self.config.state_root / "receipts" / f"{receipt_id}.json"
lock_path = self.config.state_root / "locks" / f"{receipt_id}.lock"
with open(lock_path, "a+b") as lock:
os.chmod(lock_path, 0o600)
fcntl.flock(lock.fileno(), fcntl.LOCK_EX)
return self._provision_locked(request, owner, receipt_path)
def _provision_locked(
self,
request: dict[str, Any],
owner: OwnerContext,
receipt_path: Path,
) -> dict[str, Any]:
receipt_exists = receipt_path.exists()
prestart = _prestart_git_check(
request, self.config, receipt_exists=receipt_exists
)
if receipt_exists:
receipt = _read_json(receipt_path)
expected_digest = sha256_json(
{
"task_id": request["task_id"],
"repository": request["repository"],
"base_ref": request["base_ref"],
"base_oid": request["base_oid"],
"target_branch": request["target_branch"],
"owner_authorization_reference": request[
"owner_authorization_reference"
],
}
)
if receipt.get("request_identity_sha256") != expected_digest:
raise ProvisioningError("IDEMPOTENCY_SCOPE_CONFLICT", 409)
return {
**receipt["public_result"],
"idempotent": True,
"prestart": prestart,
}
for path, name in (
(self.config.signer, "SIGNER"),
(self.config.validator, "VALIDATOR"),
(self.config.provisioner, "PROVISIONER"),
):
_verify_tool_contract(path, name, self.config)
now = self.clock()
plan, grant_request = _build_plan(request, owner, now=now)
temporary_root = Path(
tempfile.mkdtemp(
prefix="grant-",
dir=self.config.state_root,
)
)
os.chmod(temporary_root, 0o700)
try:
grant_dir = temporary_root / "grant"
grant_dir.mkdir(mode=0o700)
_atomic_write_json(grant_dir / "approval-plan.json", plan)
_atomic_write_json(grant_dir / "grant-request.json", grant_request)
signer_result_path = temporary_root / "signer-result.json"
validator_result_path = temporary_root / "validator-result.json"
provisioner_result_path = temporary_root / "provisioner-result.json"
try:
run_compatible_signer(
_tool_argv(self.config, self.config.signer),
grant_dir,
signer_result_path,
)
except Exception as exc:
raise ProvisioningError(
"SIGNER_COMPATIBILITY_FAILED",
503,
details={"error": type(exc).__name__},
) from exc
signer_result = _read_json(signer_result_path)
signer = _verify_signer_result(
signer_result,
approval_plan_id=plan["approval_plan_id"],
)
try:
validator_config_path = run_compatible_validator(
_tool_argv(self.config, self.config.validator),
grant_dir,
validator_result_path,
)
except Exception as exc:
raise ProvisioningError(
"VALIDATOR_COMPATIBILITY_FAILED",
503,
details={"error": type(exc).__name__},
) from exc
validator_result = _read_json(validator_result_path)
_verify_validator_result(
validator_result,
approval_plan_id=plan["approval_plan_id"],
grant_digest=signer["grant_digest_sha256"],
)
provisioner_env = dict(os.environ)
provisioner_env["AIOS_GRANT_ROOT_CONFIG"] = str(
validator_config_path
)
_run(
_tool_argv(
self.config,
self.config.provisioner,
"--grant-dir",
str(grant_dir),
"--result-json",
str(provisioner_result_path),
),
env=provisioner_env,
timeout=180,
)
provisioner_result = _read_json(provisioner_result_path)
provisioned = _verify_provisioner_result(
provisioner_result,
request,
grant_id=signer["grant_id"],
validator_config_path=validator_config_path,
)
post_branch_oid = _git(
self.config.authority_git_dir,
"show-ref",
"--verify",
"--hash",
f"refs/heads/{request['target_branch']}",
allowed_returncodes=(0, 1, 128),
)
if provisioned["detached_writer"]:
if post_branch_oid:
raise ProvisioningError("POST_PROVISION_TARGET_BRANCH_EXISTS", 503)
post_branch_oid = request["base_oid"]
elif post_branch_oid != request["base_oid"]:
raise ProvisioningError("POST_PROVISION_BRANCH_OID_MISMATCH", 503)
post_main_oid = _git(
self.config.authority_git_dir,
"rev-parse",
request["base_ref"],
)
if post_main_oid != request["base_oid"]:
raise ProvisioningError("POST_PROVISION_MAIN_DRIFT", 409)
public_result = {
"status": "READY_FOR_CODE_AUTHORING",
"task_id": request["task_id"],
"repository": request["repository"],
"approval_plan_id": plan["approval_plan_id"],
"grant_id": signer["grant_id"],
"grant_digest_sha256": signer["grant_digest_sha256"],
"signing_key_identity": signer["signing_key_identity"],
"branch": provisioned["branch"],
"branch_oid": provisioned["branch_oid"],
"base_oid": request["base_oid"],
"workspace_path": provisioned["workspace_path"],
"writer_scope": provisioned["writer_scope"],
"negative_tests": provisioned["negative_tests"],
"grant_consumed": True,
"main_unchanged": True,
"production_change_authorized": False,
"tag_change_authorized": False,
"baseline_change_authorized": False,
"idempotent": False,
}
request_identity = sha256_json(
{
"task_id": request["task_id"],
"repository": request["repository"],
"base_ref": request["base_ref"],
"base_oid": request["base_oid"],
"target_branch": request["target_branch"],
"owner_authorization_reference": request[
"owner_authorization_reference"
],
}
)
receipt = {
"schema": "aios.task-scoped-writer-provisioning-receipt.v1",
"request_identity_sha256": request_identity,
"created_at": iso_utc(self.clock()),
"public_result": _redacted(public_result),
"prestart": prestart,
"tool_evidence": {
"signer": {
"status": signer_result.get("status"),
"grant_digest_sha256": signer["grant_digest_sha256"],
"signing_key_identity": signer["signing_key_identity"],
},
"validator": {
"status": validator_result.get("status"),
"checks": validator_result.get("checks"),
},
"provisioner": {
"status": provisioner_result.get("status"),
"grant_consumed": provisioner_result.get("grant_consumed"),
},
},
}
_atomic_write_json(receipt_path, receipt)
return {**public_result, "prestart": prestart}
finally:
shutil.rmtree(temporary_root, ignore_errors=True)
@@ -1,89 +0,0 @@
"""Durable Owner/GPT notification outbox with retry and acknowledgement."""
from __future__ import annotations
import json
import sqlite3
import time
import uuid
from dataclasses import dataclass
from pathlib import Path
from typing import Any, Callable, Mapping
@dataclass(frozen=True)
class OutboxEvent:
event_id: str
recipient: str
kind: str
payload: Mapping[str, Any]
attempts: int
available_at: float
acknowledged: bool
class DurableOutbox:
RECIPIENTS = ("owner", "gpt")
def __init__(self, path: str | Path) -> None:
self.path = str(path)
self.db = sqlite3.connect(self.path)
self.db.execute("PRAGMA journal_mode=WAL")
self.db.execute("CREATE TABLE IF NOT EXISTS outbox (event_id TEXT PRIMARY KEY, recipient TEXT NOT NULL, kind TEXT NOT NULL, payload TEXT NOT NULL, attempts INTEGER NOT NULL DEFAULT 0, available_at REAL NOT NULL, delivered_at REAL, acknowledged INTEGER NOT NULL DEFAULT 0, last_error TEXT)")
self.db.commit()
def enqueue(self, kind: str, payload: Mapping[str, Any], *, event_id: str | None = None, recipients: tuple[str, ...] = RECIPIENTS) -> list[str]:
ids: list[str] = []
for recipient in recipients:
if recipient not in self.RECIPIENTS:
raise ValueError("recipient is outside the governed notification plane")
eid = event_id or str(uuid.uuid4())
if event_id is not None and len(recipients) > 1:
eid = f"{event_id}:{recipient}"
self.db.execute("INSERT OR IGNORE INTO outbox(event_id,recipient,kind,payload,available_at) VALUES(?,?,?,?,?)", (eid, recipient, kind, json.dumps(dict(payload), sort_keys=True), time.time()))
ids.append(eid)
self.db.commit()
return ids
def due(self, *, now: float | None = None, limit: int = 20) -> list[OutboxEvent]:
now = time.time() if now is None else now
rows = self.db.execute("SELECT event_id,recipient,kind,payload,attempts,available_at,acknowledged FROM outbox WHERE delivered_at IS NULL AND available_at<=? ORDER BY available_at,event_id LIMIT ?", (now, limit)).fetchall()
return [OutboxEvent(r[0], r[1], r[2], json.loads(r[3]), r[4], r[5], bool(r[6])) for r in rows]
def delivered(self, event_id: str, *, now: float | None = None) -> None:
self.db.execute("UPDATE outbox SET delivered_at=? WHERE event_id=?", (time.time() if now is None else now, event_id))
self.db.commit()
def failed(self, event_id: str, error: str, *, now: float | None = None, max_backoff: float = 300.0) -> None:
now = time.time() if now is None else now
row = self.db.execute("SELECT attempts FROM outbox WHERE event_id=?", (event_id,)).fetchone()
attempts = int(row[0]) + 1 if row else 1
delay = min(max_backoff, 2 ** min(attempts, 8))
self.db.execute("UPDATE outbox SET attempts=?,available_at=?,last_error=? WHERE event_id=?", (attempts, now + delay, error[:200], event_id))
self.db.commit()
def acknowledge(self, event_id: str) -> None:
self.db.execute("UPDATE outbox SET acknowledged=1 WHERE event_id=?", (event_id,))
self.db.commit()
def close(self) -> None:
self.db.close()
class NotificationPlane:
def __init__(self, outbox: DurableOutbox) -> None:
self.outbox = outbox
def emit(self, kind: str, payload: Mapping[str, Any], *, event_id: str | None = None) -> list[str]:
return self.outbox.enqueue(kind, payload, event_id=event_id)
def deliver_once(self, send: Callable[[OutboxEvent], None], *, now: float | None = None) -> list[str]:
delivered: list[str] = []
for event in self.outbox.due(now=now):
try:
send(event)
except Exception as exc:
self.outbox.failed(event.event_id, type(exc).__name__, now=now)
else:
self.outbox.delivered(event.event_id, now=now)
delivered.append(event.event_id)
return delivered
-491
View File
@@ -1,491 +0,0 @@
"""Fail-closed, branch-bound repair leases for governed AIOS GitOps work."""
from __future__ import annotations
import hashlib
import json
import os
import posixpath
import re
import secrets
import subprocess
import tempfile
import uuid
from dataclasses import asdict, dataclass, field
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Iterable, Mapping, Protocol, Sequence
TASK_ID = "V2R1C6_GOVERNED_LOCAL_BOOTSTRAP"
MAX_LEASE_SECONDS = 86_400
OID_RE = re.compile(r"^[0-9a-fA-F]{40}$")
DENIED_BRANCHES = {"main", "master", "HEAD"}
PROTECTED_PREFIXES = (
".git",
"VERSION",
"versions/V2R1C5.json",
"artifacts/V2R1C5",
"baseline",
"config/gitops.tokens",
"gitops.tokens",
"secrets",
"credentials",
)
SECRET_PATTERNS = (
re.compile(r"(?i)-----BEGIN [A-Z ]*PRIVATE KEY-----"),
re.compile(r"(?i)(?:api[_-]?key|secret|password|token)\s*[:=]\s*\S+"),
re.compile(r"\b(?:sk|HPUA|SDC)-[A-Za-z0-9_-]{16,}\b"),
)
class LeaseError(Exception):
"""Raised for any invalid, stale, expired, or prohibited lease action."""
class GitProbeProtocol(Protocol):
"""Read-only Git seam used by the lease manager."""
def branch_head(self, branch: str) -> str: ...
def parent(self, commit: str) -> str: ...
def is_ancestor(self, older: str, newer: str) -> bool: ...
def changed_paths(self, commit: str) -> tuple[str, ...]: ...
def commits_between(self, older: str, newer: str) -> tuple[str, ...]: ...
def _now() -> datetime:
return datetime.now(timezone.utc)
def _ts(value: datetime) -> str:
return value.astimezone(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
def _parse_ts(value: str) -> datetime:
if value.endswith("Z"):
value = value[:-1] + "+00:00"
parsed = datetime.fromisoformat(value)
return parsed if parsed.tzinfo else parsed.replace(tzinfo=timezone.utc)
def _oid(value: str, field: str = "oid") -> str:
if not isinstance(value, str) or not OID_RE.fullmatch(value):
raise LeaseError(f"{field} must be a full commit OID")
return value.lower()
def normalize_path(path: str) -> str:
"""Normalize a repository-relative path without resolving through the FS."""
if not isinstance(path, str) or not path.strip():
raise LeaseError("path must be a non-empty string")
value = path.replace("\\", "/").strip()
if value.startswith("/") or "\x00" in value:
raise LeaseError("path must be relative")
parts = value.split("/")
if any(part in {"", ".", ".."} for part in parts):
raise LeaseError("path contains a prohibited component")
normalized = posixpath.normpath(value)
if normalized == "." or normalized.startswith("../"):
raise LeaseError("path is not normalized")
return normalized
def path_is_protected(path: str) -> bool:
normalized = normalize_path(path)
lower = normalized.lower()
return any(
lower == prefix.lower() or lower.startswith(prefix.lower().rstrip("/") + "/")
for prefix in PROTECTED_PREFIXES
) or lower.startswith("refs/")
def contains_secret_like_content(content: str) -> bool:
return any(pattern.search(content or "") for pattern in SECRET_PATTERNS)
def validate_paths(paths: Iterable[str], allowed_paths: Sequence[str]) -> tuple[str, ...]:
allowed = tuple(normalize_path(path) for path in allowed_paths)
if not allowed:
raise LeaseError("allowed_paths must not be empty")
result: list[str] = []
for raw in paths:
path = normalize_path(raw)
if path_is_protected(path):
raise LeaseError("protected path is not lease-writable")
if not any(path == prefix or path.startswith(prefix + "/") for prefix in allowed):
raise LeaseError("path is outside the lease allowlist")
if path not in result:
result.append(path)
if not result:
raise LeaseError("at least one changed path is required")
return tuple(result)
@dataclass
class CommitEntry:
commit_oid: str
parent_oid: str
paths: tuple[str, ...]
recorded_at: str
@dataclass
class RepairLease:
lease_id: str
task_id: str
owner_identity: str
branch: str
description: str
allowed_paths: tuple[str, ...]
initial_head_oid: str
current_head_oid: str
created_at: str
expires_at: str
max_expires_at: str
state: str = "ACTIVE"
revision: int = 0
commits: list[CommitEntry] = field(default_factory=list)
attached: bool = False
def to_json(self) -> dict[str, Any]:
payload = asdict(self)
payload["allowed_paths"] = list(self.allowed_paths)
payload["commits"] = [asdict(entry) for entry in self.commits]
return payload
@classmethod
def from_json(cls, raw: dict[str, Any]) -> "RepairLease":
commits = tuple(
CommitEntry(
commit_oid=_oid(item["commit_oid"], "commit_oid"),
parent_oid=_oid(item["parent_oid"], "parent_oid"),
paths=tuple(normalize_path(path) for path in item["paths"]),
recorded_at=str(item["recorded_at"]),
)
for item in raw.get("commits", [])
)
return cls(
lease_id=str(raw["lease_id"]),
task_id=str(raw["task_id"]),
owner_identity=str(raw["owner_identity"]),
branch=str(raw["branch"]),
description=str(raw["description"]),
allowed_paths=tuple(normalize_path(path) for path in raw["allowed_paths"]),
initial_head_oid=_oid(raw["initial_head_oid"], "initial_head_oid"),
current_head_oid=_oid(raw["current_head_oid"], "current_head_oid"),
created_at=str(raw["created_at"]),
expires_at=str(raw["expires_at"]),
max_expires_at=str(raw["max_expires_at"]),
state=str(raw.get("state", "ACTIVE")),
revision=int(raw.get("revision", 0)),
commits=list(commits),
attached=bool(raw.get("attached", False)),
)
class LeaseStore:
"""Atomic JSON store for restart-recoverable lease state."""
def __init__(self, directory: str | os.PathLike[str]) -> None:
self.directory = Path(directory)
self.directory.mkdir(parents=True, exist_ok=True)
if self.directory.is_symlink():
raise LeaseError("lease store must not be a symlink")
os.chmod(self.directory, 0o700)
def _path(self, lease_id: str) -> Path:
if not re.fullmatch(r"lease-[0-9a-f]{32}", lease_id):
raise LeaseError("invalid lease id")
return self.directory / f"{lease_id}.json"
def create(self, lease: RepairLease) -> None:
path = self._path(lease.lease_id)
if path.exists() or path.is_symlink():
raise LeaseError("lease already exists")
self._write(path, lease.to_json(), exclusive=True)
def load(self, lease_id: str) -> RepairLease:
path = self._path(lease_id)
try:
raw = json.loads(path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError, TypeError) as exc:
raise LeaseError("lease state is unavailable or invalid") from exc
if not isinstance(raw, dict):
raise LeaseError("lease state must be an object")
return RepairLease.from_json(raw)
def save(self, lease: RepairLease) -> None:
self._write(self._path(lease.lease_id), lease.to_json())
@staticmethod
def _write(path: Path, payload: dict[str, Any], *, exclusive: bool = False) -> None:
flags = os.O_WRONLY | os.O_CREAT | (os.O_EXCL if exclusive else 0)
fd, temp_name = tempfile.mkstemp(prefix=".lease-", dir=path.parent)
try:
os.fchmod(fd, 0o600)
with os.fdopen(fd, "w", encoding="utf-8") as stream:
json.dump(payload, stream, ensure_ascii=True, sort_keys=True, separators=(",", ":"))
stream.write("\n")
if exclusive:
os.link(temp_name, path)
os.unlink(temp_name)
else:
os.replace(temp_name, path)
os.chmod(path, 0o600)
except Exception:
try:
os.unlink(temp_name)
except FileNotFoundError:
pass
raise
class GitProbe:
"""Read-only Git implementation; it never changes a ref or working tree."""
def __init__(self, bare_repo: str | os.PathLike[str]) -> None:
self.bare_repo = Path(bare_repo)
def _run(self, args: list[str]) -> str:
result = subprocess.run(
["git", "--git-dir", str(self.bare_repo), *args],
text=True,
capture_output=True,
check=False,
)
if result.returncode != 0:
raise LeaseError("read-only Git probe failed")
return result.stdout.strip()
def branch_head(self, branch: str) -> str:
return _oid(self._run(["rev-parse", f"refs/heads/{branch}"]), "branch_head")
def parent(self, commit: str) -> str:
return _oid(self._run(["rev-parse", f"{_oid(commit)}^1"]), "parent")
def is_ancestor(self, older: str, newer: str) -> bool:
old, new = _oid(older), _oid(newer)
result = subprocess.run(
["git", "--git-dir", str(self.bare_repo), "merge-base", "--is-ancestor", old, new],
check=False,
)
return result.returncode == 0
def changed_paths(self, commit: str) -> tuple[str, ...]:
raw = self._run(["diff-tree", "--no-commit-id", "--name-only", "-r", _oid(commit)])
return tuple(normalize_path(line) for line in raw.splitlines() if line.strip())
def commits_between(self, older: str, newer: str) -> tuple[str, ...]:
raw = self._run(["rev-list", "--reverse", f"{_oid(older)}..{_oid(newer)}"])
return tuple(_oid(line, "commit") for line in raw.splitlines() if line.strip())
class RepairLeaseManager:
"""Issue, recover, renew, and close branch-bound repair leases."""
def __init__(self, store: LeaseStore, git: GitProbeProtocol, *, clock=_now) -> None:
self.store = store
self.git = git
self.clock = clock
def _require_owner(self, lease: RepairLease, owner_identity: str) -> None:
if owner_identity != lease.owner_identity:
raise LeaseError("lease identity mismatch")
def _active(self, lease: RepairLease) -> RepairLease:
now = self.clock()
if lease.state != "ACTIVE":
raise LeaseError(f"lease is {lease.state.lower()}")
if now >= _parse_ts(lease.expires_at):
lease.state = "EXPIRED"
self.store.save(lease)
raise LeaseError("lease expired")
return lease
def issue(
self,
*,
task_id: str,
owner_identity: str,
branch: str,
description: str,
allowed_paths: Sequence[str],
ttl_seconds: int = 3600,
) -> RepairLease:
if task_id != TASK_ID:
raise LeaseError("unexpected task id")
if not owner_identity or not description or len(description) > 240:
raise LeaseError("owner identity and description are required")
if "\n" in description or "\r" in description:
raise LeaseError("description must be a single line")
if branch in DENIED_BRANCHES or branch.startswith(("main/", "refs/", "tags/")):
raise LeaseError("protected branch cannot receive a repair lease")
if not isinstance(ttl_seconds, int) or not 0 < ttl_seconds <= MAX_LEASE_SECONDS:
raise LeaseError("lease TTL exceeds the maximum")
allowed = tuple(normalize_path(path) for path in allowed_paths)
if any(path_is_protected(path) for path in allowed):
raise LeaseError("protected path in lease allowlist")
head = self.git.branch_head(branch)
created = self.clock()
expires = created + timedelta(seconds=ttl_seconds)
max_expires = created + timedelta(seconds=MAX_LEASE_SECONDS)
lease_id = "lease-" + secrets.token_hex(16)
lease = RepairLease(
lease_id=lease_id,
task_id=task_id,
owner_identity=owner_identity,
branch=branch,
description=description,
allowed_paths=allowed,
initial_head_oid=head,
current_head_oid=head,
created_at=_ts(created),
expires_at=_ts(expires),
max_expires_at=_ts(max_expires),
)
self.store.create(lease)
return lease
def attach_existing_branch(
self, lease_id: str, *, owner_identity: str, expected_head_oid: str
) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
current = self.git.branch_head(lease.branch)
expected = _oid(expected_head_oid, "expected_head_oid")
if current != expected or current != lease.current_head_oid:
raise LeaseError("branch head does not match the lease")
lease.attached = True
lease.revision += 1
self.store.save(lease)
return lease
def authorize_commit(
self,
lease_id: str,
*,
owner_identity: str,
expected_head_oid: str,
paths: Sequence[str],
content: Mapping[str, str] | None = None,
) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
expected = _oid(expected_head_oid, "expected_head_oid")
current = self.git.branch_head(lease.branch)
if current != expected or current != lease.current_head_oid:
raise LeaseError("stale or externally advanced branch head")
if not lease.attached:
raise LeaseError("lease is not attached")
validate_paths(paths, lease.allowed_paths)
if content and any(contains_secret_like_content(value) for value in content.values()):
raise LeaseError("secret-like content rejected")
return lease
def record_commit(
self,
lease_id: str,
*,
owner_identity: str,
expected_head_oid: str,
new_head_oid: str,
paths: Sequence[str],
) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
new_head = _oid(new_head_oid, "new_head_oid")
expected = _oid(expected_head_oid, "expected_head_oid")
if not lease.attached or lease.current_head_oid != expected:
raise LeaseError("stale lease head")
if self.git.branch_head(lease.branch) != new_head:
raise LeaseError("branch head does not match committed head")
validate_paths(paths, lease.allowed_paths)
if self.git.parent(new_head) != expected or not self.git.is_ancestor(expected, new_head):
raise LeaseError("commit is not a fast-forward child of the expected head")
actual_paths = self.git.changed_paths(new_head)
allowed = validate_paths(actual_paths, lease.allowed_paths)
requested = set(validate_paths(paths, lease.allowed_paths))
if not set(allowed).issubset(requested):
raise LeaseError("commit changed an unrequested path")
lease.current_head_oid = new_head
lease.revision += 1
lease.commits.append(
CommitEntry(
commit_oid=new_head,
parent_oid=expected,
paths=allowed,
recorded_at=_ts(self.clock()),
)
)
self.store.save(lease)
return lease
def recover(self, lease_id: str, *, owner_identity: str) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
current = self.git.branch_head(lease.branch)
if current == lease.current_head_oid:
return lease
if not self.git.is_ancestor(lease.current_head_oid, current):
raise LeaseError("branch moved non-fast-forward")
commits = self.git.commits_between(lease.current_head_oid, current)
for commit in commits:
actual = self.git.changed_paths(commit)
validate_paths(actual, lease.allowed_paths)
lease.current_head_oid = current
lease.revision += 1
self.store.save(lease)
return lease
def renew(self, lease_id: str, *, owner_identity: str, ttl_seconds: int) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
if not isinstance(ttl_seconds, int) or ttl_seconds <= 0:
raise LeaseError("renewal TTL must be positive")
candidate = self.clock() + timedelta(seconds=ttl_seconds)
maximum = _parse_ts(lease.max_expires_at)
if candidate > maximum:
raise LeaseError("renewal exceeds maximum lease lifetime")
lease.expires_at = _ts(candidate)
lease.revision += 1
self.store.save(lease)
return lease
def complete(self, lease_id: str, *, owner_identity: str) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
lease.state = "COMPLETED"
lease.revision += 1
self.store.save(lease)
return lease
def revoke(self, lease_id: str, *, owner_identity: str) -> RepairLease:
lease = self._active(self.store.load(lease_id))
self._require_owner(lease, owner_identity)
lease.state = "REVOKED"
lease.revision += 1
self.store.save(lease)
return lease
def sanitized_lease_view(lease: RepairLease) -> dict[str, Any]:
"""Return lease metadata only; no content, token, or credential values."""
return {
"lease_id": lease.lease_id,
"task_id": lease.task_id,
"owner_identity": lease.owner_identity,
"branch": lease.branch,
"description": lease.description,
"initial_head_oid": lease.initial_head_oid,
"current_head_oid": lease.current_head_oid,
"created_at": lease.created_at,
"expires_at": lease.expires_at,
"state": lease.state,
"revision": lease.revision,
"commit_count": len(lease.commits),
"attached": lease.attached,
}
-473
View File
@@ -1,473 +0,0 @@
"""Shared primitives for the V2R1C6 governed local writer contract."""
from __future__ import annotations
import hashlib
import json
import os
import posixpath
import re
import socket
import stat
import struct
from dataclasses import dataclass
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Mapping, Sequence
TASK_ID = "V2R1C6_GOVERNED_LOCAL_BOOTSTRAP"
REPO = "aios/aios"
PRINCIPAL = "governed-local-bootstrap"
OIDSIZ = 40
AUTHORIZATION_TTL = timedelta(hours=2)
class GovernedLocalWriterError(Exception):
"""Base error for governed-local-writer validation and runtime failures."""
class AuthorizationError(GovernedLocalWriterError):
"""Raised when authorization input is invalid, expired, or tampered."""
@dataclass(frozen=True)
class BranchCreatePolicy:
"""Exact branch creation contract."""
branch: str
base_oid: str
head_oid: str
@dataclass(frozen=True)
class BranchAppendPolicy:
"""Exact append-commit contract for candidate branch updates."""
branch: str
expected_head_oid: str | None
allowed_paths: tuple[str, ...]
@dataclass(frozen=True)
class BranchPolicy:
"""Per-branch operation policies loaded from authorization."""
create_branch: BranchCreatePolicy | None
append_commit: BranchAppendPolicy | None
@dataclass(frozen=True)
class GovernedAuthorization:
"""Parsed and validated authorization object."""
task_id: str
repo: str
created_at: datetime
expires_at: datetime
authorization_sha256: str
one_time_use: bool
branch_operations: dict[str, BranchPolicy]
denied_operations: tuple[str, ...]
@property
def create_branches(self) -> set[str]:
"""Branches that are allowed for branch-creation operations."""
return {
branch
for branch, policy in self.branch_operations.items()
if policy.create_branch is not None
}
@property
def append_branches(self) -> set[str]:
"""Branches that are allowed for commit-append operations."""
return {
branch
for branch, policy in self.branch_operations.items()
if policy.append_commit is not None
}
@dataclass(frozen=True)
class PeerIdentity:
"""Verified peer identity from SO_PEERCRED."""
pid: int
uid: int
gid: int
executable: str | None
@dataclass(frozen=True)
class FileChange:
"""Single file modification payload."""
path: str
content: str
@dataclass(frozen=True)
class CreateBranchRequest:
"""Validated create-branch request payload."""
branch: str
base_oid: str
head_oid: str | None
authorization_digest: str
@dataclass(frozen=True)
class AppendCommitRequest:
"""Validated append-commit request payload."""
branch: str
expected_head_oid: str
changes: tuple[FileChange, ...]
authorization_digest: str
commit_message: str = "chore(governance): append governed commit"
_OID_RE = re.compile(r"^[0-9a-fA-F]{40}$")
_DENIED_PATH_SEGMENTS = (
"main",
"tag",
"baseline",
"credential",
"credentials",
"secret",
"registry",
)
_SECRET_PATTERNS = (
re.compile(r"(?i)-----BEGIN [A-Z ]*PRIVATE KEY-----"),
re.compile(r"(?i)api[_-]?key\s*[:=]\s*\S+"),
re.compile(r"(?i)secret\s*[:=]\s*\S+"),
re.compile(r"(?i)password\s*[:=]\s*\S+"),
re.compile(r"(?i)token\s*[:=]\s*\S+"),
)
_SAFE_SECRET_MARKERS = re.compile(
r"(?i)(?:api[_-]?key|secret|password|token)\s*[:=]\s*(?:REDACTED|TEST_FIXTURE|NOT_A_SECRET)"
)
def canonicalize_authorization_payload(payload: Mapping[str, Any]) -> str:
"""Serialize authorization payload without the signature hash, in canonical form."""
canonical = dict(payload)
canonical.pop("authorization_sha256", None)
return json.dumps(
canonical, sort_keys=True, separators=(",", ":"), ensure_ascii=True
)
def compute_authorization_sha256(payload: Mapping[str, Any]) -> str:
"""Compute canonical sha256 over authorization payload."""
digest = hashlib.sha256()
digest.update(canonicalize_authorization_payload(payload).encode("utf-8"))
return digest.hexdigest()
def _assert_authorization_file_permissions(path: Path) -> None:
"""Fail-closed checks for root-only secret-like authorization files."""
if path.is_symlink():
raise AuthorizationError("authorization path must not be a symlink")
st = path.stat()
if not stat.S_ISREG(st.st_mode):
raise AuthorizationError("authorization path must be a regular file")
if (st.st_mode & 0o777) != 0o600:
raise AuthorizationError("authorization file mode must be exactly 0600")
if hasattr(st, "st_uid") and os.name != "nt" and st.st_uid != 0:
raise AuthorizationError("authorization file owner must be uid 0")
def _parse_iso8601(value: str) -> datetime:
"""Parse ISO 8601 timestamps used by authorization payloads."""
try:
if value.endswith("Z"):
value = value[:-1] + "+00:00"
parsed = datetime.fromisoformat(value)
except (TypeError, ValueError) as exc:
raise AuthorizationError("created_at must be an ISO 8601 timestamp") from exc
if parsed.tzinfo is None:
parsed = parsed.replace(tzinfo=timezone.utc)
return parsed
def _require_type(value: Any, expected: type, *, key: str) -> None:
if not isinstance(value, expected):
raise AuthorizationError(f"{key} must be {expected.__name__}")
def _parse_oid(value: Any, *, field: str) -> str:
if not isinstance(value, str):
raise AuthorizationError(f"{field} must be a string")
if not _OID_RE.fullmatch(value):
raise AuthorizationError(f"{field} must be a 40-char hex object id")
return value.lower()
def _parse_allowed_paths(paths: Any) -> tuple[str, ...]:
if not isinstance(paths, list) or not paths:
raise AuthorizationError("allowed_paths must be a non-empty list")
normalized: list[str] = []
for path in paths:
if not isinstance(path, str) or not path.strip():
raise AuthorizationError("allowed_paths entries must be non-empty strings")
normalized.append(path.strip())
return tuple(normalized)
def parse_authorization(
raw: Mapping[str, Any], *, now: datetime | None = None
) -> GovernedAuthorization:
"""Validate an authorization payload and return a typed object."""
_require_type(raw.get("task_id"), str, key="task_id")
if raw["task_id"] != TASK_ID:
raise AuthorizationError("unexpected task_id")
_require_type(raw.get("repo"), str, key="repo")
if raw["repo"] != REPO:
raise AuthorizationError("unexpected repo value")
created_at = _parse_iso8601(raw.get("created_at"))
check_time = now or datetime.now(tz=timezone.utc)
if created_at.tzinfo is None:
created_at = created_at.replace(tzinfo=timezone.utc)
if created_at - check_time > timedelta(seconds=30):
raise AuthorizationError("authorization created_at is in the future")
if check_time - created_at > AUTHORIZATION_TTL:
raise AuthorizationError("authorization expired")
raw_expires_at = raw.get("expires_at")
expires_at = (
_parse_iso8601(raw_expires_at)
if raw_expires_at is not None
else created_at + AUTHORIZATION_TTL
)
if expires_at <= check_time:
raise AuthorizationError("authorization expiry is in the past")
if expires_at > created_at + AUTHORIZATION_TTL:
raise AuthorizationError("authorization expiry exceeds two-hour maximum")
_require_type(raw.get("one_time_use"), bool, key="one_time_use")
if raw["one_time_use"] is not True:
raise AuthorizationError("one_time_use must be true")
_require_type(raw.get("authorization_sha256"), str, key="authorization_sha256")
expected_hash = compute_authorization_sha256(raw)
provided_hash = str(raw["authorization_sha256"]).lower()
if provided_hash != expected_hash:
raise AuthorizationError("authorization_sha256 mismatch")
op_map = raw.get("allowed_branch_operations")
if not isinstance(op_map, dict) or not op_map:
raise AuthorizationError("allowed_branch_operations must be a non-empty object")
branch_operations: dict[str, BranchPolicy] = {}
for branch, operation in op_map.items():
if not isinstance(branch, str) or not branch.strip():
raise AuthorizationError("branch names must be non-empty strings")
if not isinstance(operation, dict):
raise AuthorizationError("operation policy must be an object")
create_block = operation.get("create_branch")
append_block = operation.get("append_commit")
create_policy: BranchCreatePolicy | None = None
append_policy: BranchAppendPolicy | None = None
if create_block is not None:
if not isinstance(create_block, dict):
raise AuthorizationError("create_branch block must be an object")
raw_head_oid = create_block.get("head_oid")
create_policy = BranchCreatePolicy(
branch=branch,
base_oid=_parse_oid(create_block.get("base_oid"), field="create_branch.base_oid"),
head_oid=(
_parse_oid(raw_head_oid, field="create_branch.head_oid")
if raw_head_oid is not None
else None
),
)
if append_block is not None:
if not isinstance(append_block, dict):
raise AuthorizationError("append_commit block must be an object")
raw_expected_head_oid = append_block.get("expected_head_oid")
append_policy = BranchAppendPolicy(
branch=branch,
expected_head_oid=(
_parse_oid(
raw_expected_head_oid,
field="append_commit.expected_head_oid",
)
if raw_expected_head_oid is not None
else None
),
allowed_paths=_parse_allowed_paths(append_block.get("allowed_paths")),
)
if create_policy is None and append_policy is None:
raise AuthorizationError("branch policy must define at least one operation")
branch_operations[branch] = BranchPolicy(
create_branch=create_policy, append_commit=append_policy
)
denied_raw = raw.get("denied_operations", ())
if not isinstance(denied_raw, list):
raise AuthorizationError("denied_operations must be a list")
denied_operations: list[str] = []
for value in denied_raw:
if not isinstance(value, str):
raise AuthorizationError("denied operations must be strings")
denied_operations.append(value.lower())
return GovernedAuthorization(
task_id=raw["task_id"],
repo=raw["repo"],
created_at=created_at,
expires_at=expires_at,
authorization_sha256=provided_hash,
one_time_use=True,
branch_operations=branch_operations,
denied_operations=tuple(denied_operations),
)
def load_authorization_file(
path: str | os.PathLike[str], *, now: datetime | None = None
) -> GovernedAuthorization:
"""Load and validate the root-only authorization file."""
auth_path = Path(path)
_assert_authorization_file_permissions(auth_path)
try:
raw_text = auth_path.read_text(encoding="utf-8")
except (OSError, ValueError) as exc:
raise AuthorizationError("unable to read authorization file") from exc
try:
raw_obj = json.loads(raw_text)
except json.JSONDecodeError as exc:
raise AuthorizationError("authorization must be JSON") from exc
if not isinstance(raw_obj, dict):
raise AuthorizationError("authorization top-level must be an object")
return parse_authorization(raw_obj, now=now)
def _resolve_peer_executable(pid: int) -> str | None:
"""Resolve peer executable from /proc/<pid>/exe when available."""
if pid <= 0:
return None
exe_path = f"/proc/{pid}/exe"
try:
return os.readlink(exe_path)
except OSError:
return None
def extract_peer_identity(
connection: socket.socket, *, require_root_uid: bool = True
) -> PeerIdentity:
"""Validate SO_PEERCRED and return peer identity."""
if not hasattr(socket, "SO_PEERCRED"):
raise AuthorizationError("SO_PEERCRED not available on this platform")
data = connection.getsockopt(
socket.SOL_SOCKET,
socket.SO_PEERCRED,
struct.calcsize("3i"),
)
if len(data) != struct.calcsize("3i"):
raise AuthorizationError("SO_PEERCRED payload size mismatch")
pid, uid, gid = struct.unpack("3i", data)
if require_root_uid and uid != 0:
raise PermissionError("peer uid must be 0")
return PeerIdentity(
pid=pid,
uid=uid,
gid=gid,
executable=_resolve_peer_executable(pid),
)
def _normalize_file_path(path: str) -> str:
normalized = posixpath.normpath(path.replace("\\", "/").strip())
return normalized.lstrip("/")
def _path_has_disallowed_segment(path: str) -> bool:
lowered = path.lower()
if ".." in path.split("/"):
return True
parts = [p for p in lowered.split("/") if p]
for part in parts:
for segment in _DENIED_PATH_SEGMENTS:
if part == segment or part.startswith(f"{segment}.") or segment in part:
return True
return False
def _is_allowed_path(path: str, allowed_paths: Sequence[str]) -> bool:
normalized = _normalize_file_path(path)
for prefix in allowed_paths:
normalized_prefix = _normalize_file_path(prefix)
if normalized == normalized_prefix:
return True
if normalized.startswith(normalized_prefix + "/"):
return True
return False
def contains_secret_like_content(content: str) -> bool:
"""Heuristic detector for obvious secret-like strings."""
content = _SAFE_SECRET_MARKERS.sub("", content or "")
for pattern in _SECRET_PATTERNS:
if pattern.search(content):
return True
return False
def validate_file_changes(
changes: Any, allowed_paths: Sequence[str]
) -> tuple[FileChange, ...]:
"""Validate append-commit file changes against path and content policy."""
if not isinstance(changes, list):
raise AuthorizationError("changes must be a list")
result: list[FileChange] = []
for change in changes:
if not isinstance(change, Mapping):
raise AuthorizationError("each file change must be an object")
raw_path = change.get("path")
raw_content = change.get("content")
if not isinstance(raw_path, str) or not raw_path.strip():
raise AuthorizationError("file change path must be a non-empty string")
if raw_path.startswith(("/", "\\")):
raise AuthorizationError("file change path must be relative")
if not isinstance(raw_content, str):
raise AuthorizationError("file change content must be a string")
normalized = _normalize_file_path(raw_path)
if not normalized or normalized.startswith("../") or normalized == "..":
raise AuthorizationError("file paths must be normalized relative paths")
if not _is_allowed_path(normalized, allowed_paths):
raise AuthorizationError("file path outside allowed_paths")
if _path_has_disallowed_segment(normalized):
raise AuthorizationError("file path uses denied segment")
if contains_secret_like_content(raw_content):
raise AuthorizationError("file content failed secret-like scan")
result.append(FileChange(path=normalized, content=raw_content))
return tuple(result)
-47
View File
@@ -1,47 +0,0 @@
"""Supplement Gitea native protection when review identity is not expressible."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Mapping, Sequence
class MergeGateDenied(RuntimeError):
pass
@dataclass(frozen=True)
class MergeGateDecision:
allowed: bool
owner_review_id: int
required_contexts: tuple[str, ...]
def validate_protected_merge(
pull_request: Mapping[str, Any],
reviews: Sequence[Mapping[str, Any]],
statuses: Mapping[str, str],
*,
required_contexts: Sequence[str],
unresolved_conversations: int,
owner_login: str = "owner",
owner_id: int = 2,
) -> MergeGateDecision:
if pull_request.get("state") != "open" or pull_request.get("mergeable") is not True:
raise MergeGateDenied("pull_request_not_mergeable")
author = (pull_request.get("user") or {}).get("login")
owner_review = None
for review in reviews:
user = review.get("user") or {}
if review.get("state") == "APPROVED" and user.get("login") == owner_login and user.get("id") == owner_id:
if author == owner_login or (pull_request.get("author_id") == owner_id):
raise MergeGateDenied("pr_author_self_approval_denied")
owner_review = review
if owner_review is None:
raise MergeGateDenied("owner_review_required")
if unresolved_conversations != 0:
raise MergeGateDenied("unresolved_conversations_block_merge")
missing = [context for context in required_contexts if statuses.get(context) != "success"]
if missing:
raise MergeGateDenied("required_checks_missing:" + ",".join(missing))
return MergeGateDecision(True, int(owner_review.get("id", 0)), tuple(required_contexts))
@@ -27,7 +27,12 @@ POLICY_FIELDS = frozenset(
)
OPERATION_FIELDS = frozenset({"exact_paths", "max_content_bytes", "content_profile"})
SUPPORTED_OPERATIONS = frozenset({"commit_file.atomic"})
SUPPORTED_CONTENT_PROFILES = frozenset({"systemd-codex-review-worker-v1"})
SUPPORTED_CONTENT_PROFILES = frozenset(
{
"systemd-codex-review-worker-v1",
"candidate-session-broker-source-v1",
}
)
_SECRET_RE = re.compile(
r"(?i)(authorization\s*:|bearer\s+|(?:token|password|secret)\s*[:=])"
)
@@ -353,9 +358,73 @@ def validate_content(operation: str, path: str, content: str) -> None:
if selected.content_profile == "systemd-codex-review-worker-v1":
_validate_systemd_codex_review_worker(content)
return
if selected.content_profile == "candidate-session-broker-source-v1":
_validate_candidate_session_broker_source(path, content)
return
raise PathPolicyError("isolated_writer_path_policy_profile_rejected")
def _validate_candidate_session_broker_source(path: str, content: str) -> None:
if (
not isinstance(content, str)
or "\x00" in content
or "\r" in content
or not content.endswith("\n")
):
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected")
forbidden = (
"BEGIN PRIVATE KEY",
"GITEA_DATABASE",
"gitea admin",
"ssh-keyscan",
"/home/aiman/.codex",
"/root/.codex",
"AIOS_GITOPS_ALLOW_MAIN_WRITE=true",
"AIOS_GITOPS_ALLOW_TAG_WRITE=true",
"AIOS_GITOPS_ALLOW_BASELINE_WRITE=true",
"AIOS_GITOPS_ALLOW_REGISTRY_WRITE=true",
"AIOS_TASK_PLANE_EXECUTION_ENABLED=true",
"AIOS_SILENT_RELEASE_EXECUTION_ENABLED=true",
)
if any(value in content for value in forbidden):
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected")
if path.endswith(".py"):
try:
compile(content, path, "exec")
except (SyntaxError, ValueError, TypeError):
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected") from None
return
if path.endswith(".service"):
if _SECRET_RE.search(content):
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected")
required = (
"User=aiman",
"Group=gitops",
"UMask=0077",
"NoNewPrivileges=true",
"PrivateTmp=true",
"PrivateDevices=true",
"ProtectSystem=strict",
"ProtectHome=true",
"ProtectKernelTunables=true",
"ProtectKernelModules=true",
"ProtectControlGroups=true",
"LockPersonality=true",
"RestrictSUIDSGID=true",
"RestrictRealtime=true",
"127.0.0.1",
)
if any(value not in content for value in required):
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected")
for line in content.splitlines():
if line.startswith("Environment=") and re.search(
r"(?i)(token|password|secret|private[_-]?key)=", line
):
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected")
return
raise PathPolicyError("isolated_writer_candidate_source_profile_rejected")
def _validate_systemd_codex_review_worker(content: str) -> None:
if not isinstance(content, str):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
@@ -1,611 +0,0 @@
"""Audited Owner authorization broker for task-scoped writer provisioning.
The broker closes the bootstrap gap without minting a new general-purpose
Owner token and without modifying the bearer-token registry. It accepts an
already-authenticated, explicitly allow-listed Owner principal, records a
tamper-evident authorization event, and invokes the existing
AuthorizedTaskWriterProvisioner with a generated authorization reference.
The broker never writes Git refs itself. The governed signer, validator and
one-shot provisioner remain the only components allowed to create the task
branch/worktree/writer.
"""
from __future__ import annotations
import fcntl
import hashlib
import json
import os
import re
import tempfile
from dataclasses import dataclass
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Mapping, Protocol
from authorized_task_writer_provisioning import (
AuthorizedTaskWriterProvisioner,
BRANCH_RE,
OID_RE,
OwnerContext,
ProvisioningError,
REQUIRED_ALLOWED_OPERATIONS,
REQUIRED_DENIED_OPERATIONS,
TASK_RE,
)
ACTION = "AUTHORIZE_TASK_WRITER_PROVISIONING"
SCHEMA = "aios.owner-authorization-event.v1"
BROKER_REQUEST_FIELDS = frozenset(
{
"action",
"task_id",
"repository",
"base_ref",
"base_oid",
"target_branch",
"one_time_use",
"expires_in_seconds",
"production_change_authorized",
"tag_change_authorized",
"baseline_change_authorized",
"main_write_authorized",
"allowed_operations",
"denied_operations",
}
)
IDENTITY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._@:+/-]{1,254}$")
SCOPE_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{1,127}$")
CREDENTIAL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:@+-]{1,255}$")
WILDCARD_SCOPE_RE = re.compile(r"(^\*$)|(^.+:\*$)")
class OwnerAuthorizationError(RuntimeError):
"""Stable fail-closed broker error."""
def __init__(
self,
code: str,
status: int = 400,
*,
details: Mapping[str, Any] | None = None,
) -> None:
super().__init__(code)
self.code = code
self.status = status
self.details = dict(details or {})
@dataclass(frozen=True)
class OwnerPrincipal:
"""Non-secret authentication evidence returned by the existing API."""
identity: str
role: str
authenticated_scope: str
token_scopes: frozenset[str]
credential_id: str = ""
@dataclass(frozen=True)
class OwnerAuthorizationBrokerConfig:
repository_identity: str
state_root: Path
allowed_owner_identities: frozenset[str]
allowed_intake_scopes: frozenset[str]
allowed_credential_ids: frozenset[str] = frozenset()
max_expiry_seconds: int = 900
@classmethod
def from_environment(cls) -> "OwnerAuthorizationBrokerConfig":
identities = _csv_set(
os.getenv("AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_IDENTITIES", "")
)
scopes = _csv_set(
os.getenv("AIOS_GITOPS_OWNER_AUTHORIZATION_INTAKE_SCOPES", "")
)
credential_ids = _csv_set(
os.getenv("AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_CREDENTIAL_IDS", "")
)
if not identities:
raise OwnerAuthorizationError(
"OWNER_IDENTITY_ALLOWLIST_REQUIRED", 503
)
if not scopes:
raise OwnerAuthorizationError(
"OWNER_INTAKE_SCOPE_ALLOWLIST_REQUIRED", 503
)
if any(_is_wildcard_scope(item) for item in scopes):
raise OwnerAuthorizationError(
"WILDCARD_INTAKE_SCOPE_REJECTED", 503
)
if "writer:provision" in scopes:
raise OwnerAuthorizationError(
"WRITER_PROVISION_SCOPE_BOOTSTRAP_REJECTED", 503
)
try:
maximum = int(
os.getenv(
"AIOS_GITOPS_OWNER_AUTHORIZATION_MAX_EXPIRY_SECONDS", "900"
)
)
except ValueError:
raise OwnerAuthorizationError(
"BROKER_MAX_EXPIRY_INVALID", 503
) from None
if maximum < 60 or maximum > 1800:
raise OwnerAuthorizationError("BROKER_MAX_EXPIRY_INVALID", 503)
return cls(
repository_identity=os.getenv(
"AIOS_GITOPS_REPOSITORY_IDENTITY", "aios/aios"
).strip(),
state_root=Path(
os.getenv(
"AIOS_GITOPS_OWNER_AUTHORIZATION_STATE_ROOT",
"/var/lib/aios-gitops/owner-authorization-broker",
)
),
allowed_owner_identities=identities,
allowed_intake_scopes=scopes,
allowed_credential_ids=credential_ids,
max_expiry_seconds=maximum,
)
class TaskWriterProvisioner(Protocol):
def provision(
self, raw: Mapping[str, Any], owner: OwnerContext
) -> dict[str, Any]:
...
def utc_now() -> datetime:
return datetime.now(timezone.utc)
def iso_utc(value: datetime) -> str:
return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
def canonical_json_bytes(value: Any) -> bytes:
return (
json.dumps(
value,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
)
+ "\n"
).encode("utf-8")
def sha256_json(value: Any) -> str:
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
def _csv_set(value: str) -> frozenset[str]:
return frozenset(
item.strip() for item in value.split(",") if item.strip()
)
def _is_wildcard_scope(scope: str) -> bool:
return bool(WILDCARD_SCOPE_RE.fullmatch(scope.strip()))
def _atomic_write_json(path: Path, value: Any, mode: int = 0o600) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
if path.parent.is_symlink() or path.is_symlink():
raise OwnerAuthorizationError("BROKER_STATE_SYMLINK_REJECTED", 500)
fd, temporary = tempfile.mkstemp(prefix=".tmp-", dir=path.parent)
try:
os.fchmod(fd, mode)
with os.fdopen(fd, "wb", closefd=True) as stream:
stream.write(canonical_json_bytes(value))
stream.flush()
os.fsync(stream.fileno())
os.replace(temporary, path)
os.chmod(path, mode)
parent_fd = os.open(
path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0)
)
try:
os.fsync(parent_fd)
finally:
os.close(parent_fd)
finally:
if os.path.exists(temporary):
os.unlink(temporary)
def _read_json(path: Path) -> dict[str, Any]:
if path.is_symlink() or not path.is_file():
raise OwnerAuthorizationError("BROKER_RECEIPT_INVALID", 500)
if path.stat().st_size <= 0 or path.stat().st_size > 1_048_576:
raise OwnerAuthorizationError("BROKER_RECEIPT_INVALID", 500)
try:
value = json.loads(path.read_text(encoding="utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
raise OwnerAuthorizationError(
"BROKER_RECEIPT_JSON_INVALID", 500
) from None
if not isinstance(value, dict):
raise OwnerAuthorizationError("BROKER_RECEIPT_INVALID", 500)
return value
def _prepare_state_root(root: Path) -> None:
if root.is_symlink():
raise OwnerAuthorizationError("BROKER_STATE_SYMLINK_REJECTED", 500)
root.mkdir(parents=True, exist_ok=True, mode=0o700)
os.chmod(root, 0o700)
if root.stat().st_mode & 0o077:
raise OwnerAuthorizationError(
"BROKER_STATE_PERMISSIONS_REJECTED", 500
)
def _event_id(
principal: OwnerPrincipal, request_digest: str
) -> str:
material = (
f"{principal.identity}\0{principal.authenticated_scope}\0"
f"{request_digest}"
).encode("utf-8")
return "owner-auth-" + hashlib.sha256(material).hexdigest()[:32]
def _authorization_reference(event_id: str, request_digest: str) -> str:
return f"owner-auth:{event_id}:{request_digest[:16]}"
def _validate_principal(
principal: OwnerPrincipal,
config: OwnerAuthorizationBrokerConfig,
) -> None:
if principal.role != "owner":
raise OwnerAuthorizationError("OWNER_ROLE_REQUIRED", 403)
if (
not principal.identity
or not IDENTITY_RE.fullmatch(principal.identity)
or principal.identity not in config.allowed_owner_identities
):
raise OwnerAuthorizationError("OWNER_IDENTITY_NOT_ALLOWED", 403)
if (
not principal.authenticated_scope
or not SCOPE_RE.fullmatch(principal.authenticated_scope)
or principal.authenticated_scope
not in config.allowed_intake_scopes
):
raise OwnerAuthorizationError("OWNER_INTAKE_SCOPE_REJECTED", 403)
if principal.authenticated_scope == "writer:provision":
raise OwnerAuthorizationError(
"WRITER_PROVISION_SCOPE_BOOTSTRAP_REJECTED", 403
)
scopes = principal.token_scopes
if any(_is_wildcard_scope(scope) for scope in scopes):
raise OwnerAuthorizationError(
"WILDCARD_OWNER_CREDENTIAL_REJECTED", 403
)
if scopes:
if principal.authenticated_scope not in scopes:
raise OwnerAuthorizationError(
"OWNER_SCOPE_EVIDENCE_MISMATCH", 403
)
elif (
not principal.credential_id
or principal.credential_id not in config.allowed_credential_ids
):
# handler.need(scope) proves authorization but may hide whether the
# credential was wildcard. When scope metadata is absent, require an
# exact non-secret credential ID allowlist as the alternative proof.
raise OwnerAuthorizationError(
"OWNER_CREDENTIAL_SCOPE_NOT_PROVABLE", 403
)
if principal.credential_id:
if not CREDENTIAL_ID_RE.fullmatch(principal.credential_id):
raise OwnerAuthorizationError("OWNER_CREDENTIAL_ID_INVALID", 403)
if (
config.allowed_credential_ids
and principal.credential_id not in config.allowed_credential_ids
):
raise OwnerAuthorizationError(
"OWNER_CREDENTIAL_ID_NOT_ALLOWED", 403
)
def _validate_request(
raw: Mapping[str, Any],
config: OwnerAuthorizationBrokerConfig,
) -> dict[str, Any]:
if set(raw) != BROKER_REQUEST_FIELDS:
raise OwnerAuthorizationError("BROKER_REQUEST_FIELDS_REJECTED")
if raw["action"] != ACTION:
raise OwnerAuthorizationError("BROKER_ACTION_REJECTED")
if raw["repository"] != config.repository_identity:
raise OwnerAuthorizationError(
"REPOSITORY_IDENTITY_MISMATCH", 409
)
if raw["base_ref"] != "refs/heads/main":
raise OwnerAuthorizationError("BASE_REF_REJECTED", 409)
if (
not isinstance(raw["base_oid"], str)
or not OID_RE.fullmatch(raw["base_oid"])
):
raise OwnerAuthorizationError("BASE_OID_REJECTED")
if (
not isinstance(raw["target_branch"], str)
or not BRANCH_RE.fullmatch(raw["target_branch"])
or raw["target_branch"] in {"main", "master"}
):
raise OwnerAuthorizationError("TARGET_BRANCH_REJECTED")
if (
not isinstance(raw["task_id"], str)
or not TASK_RE.fullmatch(raw["task_id"])
):
raise OwnerAuthorizationError("TASK_ID_REJECTED")
if raw["one_time_use"] is not True:
raise OwnerAuthorizationError("ONE_TIME_USE_REQUIRED")
expiry = raw["expires_in_seconds"]
if (
not isinstance(expiry, int)
or isinstance(expiry, bool)
or not 60 <= expiry <= config.max_expiry_seconds
):
raise OwnerAuthorizationError("GRANT_LIFETIME_REJECTED")
for field in (
"production_change_authorized",
"tag_change_authorized",
"baseline_change_authorized",
"main_write_authorized",
):
if raw[field] is not False:
raise OwnerAuthorizationError(
"PRODUCTION_CAPABILITY_REJECTED", 403
)
allowed = raw["allowed_operations"]
denied = raw["denied_operations"]
if (
not isinstance(allowed, list)
or frozenset(allowed) != REQUIRED_ALLOWED_OPERATIONS
):
raise OwnerAuthorizationError("ALLOWED_OPERATIONS_MISMATCH", 403)
if (
not isinstance(denied, list)
or frozenset(denied) != REQUIRED_DENIED_OPERATIONS
):
raise OwnerAuthorizationError("DENIED_OPERATIONS_MISMATCH", 403)
return dict(raw)
def _response_is_safe(value: Any) -> bool:
"""Reject accidental credential material before writing a receipt."""
sensitive_markers = (
"access_token",
"bearer",
"client_secret",
"private_key",
"raw_token",
"secret_value",
)
if isinstance(value, Mapping):
for key, inner in value.items():
lowered = str(key).lower()
if any(marker in lowered for marker in sensitive_markers):
return False
if not _response_is_safe(inner):
return False
elif isinstance(value, list):
return all(_response_is_safe(item) for item in value)
return True
class OwnerAuthorizationBroker:
"""Create an audited Owner event and invoke the governed bridge."""
def __init__(
self,
config: OwnerAuthorizationBrokerConfig | None = None,
provisioner: TaskWriterProvisioner | None = None,
) -> None:
self.config = (
config or OwnerAuthorizationBrokerConfig.from_environment()
)
self.provisioner = provisioner or AuthorizedTaskWriterProvisioner()
def authorize_and_provision(
self,
raw: Mapping[str, Any],
principal: OwnerPrincipal,
) -> dict[str, Any]:
config = self.config
_validate_principal(principal, config)
request = _validate_request(raw, config)
_prepare_state_root(config.state_root)
request_digest = sha256_json(request)
event_id = _event_id(principal, request_digest)
reference = _authorization_reference(event_id, request_digest)
event_dir = config.state_root / "events" / event_id
event_dir.mkdir(parents=True, exist_ok=True, mode=0o700)
os.chmod(event_dir, 0o700)
lock_path = event_dir / "event.lock"
lock_path.touch(mode=0o600, exist_ok=True)
os.chmod(lock_path, 0o600)
with lock_path.open("r+b") as lock:
fcntl.flock(lock.fileno(), fcntl.LOCK_EX)
response_path = event_dir / "response.json"
event_path = event_dir / "event.json"
if response_path.exists():
response = _read_json(response_path)
response["owner_authorization_idempotent"] = True
return response
issued_at = utc_now()
expires_at = issued_at + timedelta(
seconds=int(request["expires_in_seconds"])
)
event: dict[str, Any] = {
"schema": SCHEMA,
"event_id": event_id,
"authorization_reference": reference,
"status": "AUTHORIZED",
"owner": {
"identity": principal.identity,
"role": principal.role,
"authenticated_scope": principal.authenticated_scope,
"credential_id": principal.credential_id or None,
"token_scope_digest_sha256": sha256_json(
sorted(principal.token_scopes)
),
"wildcard_scope_used": False,
},
"request": {
"task_id": request["task_id"],
"repository": request["repository"],
"base_ref": request["base_ref"],
"base_oid": request["base_oid"],
"target_branch": request["target_branch"],
"one_time_use": True,
"production_change_authorized": False,
"tag_change_authorized": False,
"baseline_change_authorized": False,
"main_write_authorized": False,
"allowed_operations": sorted(
REQUIRED_ALLOWED_OPERATIONS
),
"denied_operations": sorted(
REQUIRED_DENIED_OPERATIONS
),
},
"request_digest_sha256": request_digest,
"issued_at": iso_utc(issued_at),
"expires_at": iso_utc(expires_at),
}
event["event_digest_sha256"] = sha256_json(event)
_atomic_write_json(event_path, event)
bridge_request = dict(request)
bridge_request.pop("action")
bridge_request["owner_authorization_reference"] = reference
try:
result = self.provisioner.provision(
bridge_request,
OwnerContext(
identity=principal.identity,
role=principal.role,
authorization_reference=reference,
),
)
if not isinstance(result, dict):
raise OwnerAuthorizationError(
"PROVISIONER_RESPONSE_INVALID", 502
)
if result.get("status") != "READY_FOR_CODE_AUTHORING":
raise OwnerAuthorizationError(
"PROVISIONER_NOT_READY",
409,
details={"status": result.get("status")},
)
if not _response_is_safe(result):
raise OwnerAuthorizationError(
"PROVISIONER_RESPONSE_CONTAINS_SENSITIVE_DATA", 500
)
except ProvisioningError as exc:
event.update(
{
"status": "PROVISIONING_BLOCKED",
"failed_at": iso_utc(utc_now()),
"error": exc.code,
"error_status": exc.status,
}
)
event["event_digest_sha256"] = sha256_json(
{
key: value
for key, value in event.items()
if key != "event_digest_sha256"
}
)
_atomic_write_json(event_path, event)
raise
except OwnerAuthorizationError as exc:
event.update(
{
"status": "PROVISIONING_BLOCKED",
"failed_at": iso_utc(utc_now()),
"error": exc.code,
"error_status": exc.status,
}
)
event["event_digest_sha256"] = sha256_json(
{
key: value
for key, value in event.items()
if key != "event_digest_sha256"
}
)
_atomic_write_json(event_path, event)
raise
except Exception as exc:
event.update(
{
"status": "PROVISIONING_FAILED",
"failed_at": iso_utc(utc_now()),
"error": "OWNER_AUTHORIZATION_BROKER_INTERNAL_ERROR",
}
)
event["event_digest_sha256"] = sha256_json(
{
key: value
for key, value in event.items()
if key != "event_digest_sha256"
}
)
_atomic_write_json(event_path, event)
raise OwnerAuthorizationError(
"OWNER_AUTHORIZATION_BROKER_INTERNAL_ERROR", 500
) from exc
completed_at = utc_now()
event.update(
{
"status": "CONSUMED",
"consumed_at": iso_utc(completed_at),
"approval_plan_id": result.get("approval_plan_id"),
"grant_id": result.get("grant_id"),
"grant_digest_sha256": result.get(
"grant_digest_sha256"
),
"branch_oid": result.get("branch_oid"),
"grant_consumed": result.get("grant_consumed") is True,
}
)
event["event_digest_sha256"] = sha256_json(
{
key: value
for key, value in event.items()
if key != "event_digest_sha256"
}
)
_atomic_write_json(event_path, event)
response = dict(result)
response.update(
{
"owner_authorization_event_id": event_id,
"owner_authorization_reference": reference,
"owner_authorization_digest_sha256": event[
"event_digest_sha256"
],
"owner_authorization_consumed": True,
"owner_authorization_idempotent": False,
}
)
_atomic_write_json(response_path, response)
return response
@@ -1,32 +0,0 @@
"""Read-only release reconciliation and durable follow-up intent."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Mapping
@dataclass(frozen=True)
class ReconciliationReport:
healthy: bool
drift: tuple[str, ...]
actions: tuple[str, ...]
class ReconciliationController:
CHECKS = (
("authority_main", "gitea_main", "main_drift"),
("local_tag_oid", "remote_tag_oid", "tag_drift"),
("remote_peeled_target", "approved_target_oid", "peeled_target_drift"),
("registry_version", "baseline_version", "registry_baseline_drift"),
("approved_artifact_digest", "deployed_artifact_digest", "artifact_drift"),
("declared_production_state", "service_healthy", "service_health_drift"),
)
def reconcile(self, actual: Mapping[str, Any]) -> ReconciliationReport:
drift: list[str] = []
for left, right, label in self.CHECKS:
if actual.get(left) != actual.get(right):
drift.append(label)
actions = () if not drift else ("open_reconciliation_task", "open_reconciliation_pr", "attach_evidence", "notify_owner")
return ReconciliationReport(not drift, tuple(drift), actions)
@@ -1,65 +0,0 @@
"""Durable-friendly recurring task scheduling primitives."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime, timedelta, timezone
from typing import Any
class RecurringTaskError(ValueError):
pass
@dataclass
class RecurringTask:
task_id: str
interval_seconds: int
next_run_at: datetime
run_count: int = 0
max_runs: int | None = None
cancelled: bool = False
def due(self, now: datetime) -> bool:
return not self.cancelled and (self.max_runs is None or self.run_count < self.max_runs) and now >= self.next_run_at
class RecurringTaskScheduler:
def __init__(self) -> None:
self.tasks: dict[str, RecurringTask] = {}
self.successors: set[str] = set()
def schedule(self, task_id: str, interval_seconds: int, *, now: datetime | None = None, max_runs: int | None = None) -> RecurringTask:
if task_id in self.tasks:
raise RecurringTaskError("task already exists")
if interval_seconds <= 0 or (max_runs is not None and max_runs <= 0):
raise RecurringTaskError("invalid recurring task bounds")
now = now or datetime.now(timezone.utc)
task = RecurringTask(task_id, interval_seconds, now, 0, max_runs, False)
self.tasks[task_id] = task
return task
def due(self, *, now: datetime | None = None) -> list[RecurringTask]:
now = now or datetime.now(timezone.utc)
return [task for task in self.tasks.values() if task.due(now)]
def mark_run(self, task_id: str, *, now: datetime | None = None) -> RecurringTask:
task = self.tasks[task_id]
now = now or datetime.now(timezone.utc)
if not task.due(now):
raise RecurringTaskError("task is not due")
task.run_count += 1
task.next_run_at = now + timedelta(seconds=task.interval_seconds)
return task
def cancel(self, task_id: str) -> None:
self.tasks[task_id].cancelled = True
def create_successor_once(self, predecessor: str, successor: str, *, interval_seconds: int, now: datetime | None = None) -> RecurringTask:
key = f"{predecessor}->{successor}"
if key in self.successors:
return self.tasks[successor]
self.successors.add(key)
if successor not in self.tasks:
return self.schedule(successor, interval_seconds, now=now)
return self.tasks[successor]
@@ -1,53 +0,0 @@
"""Release state machine with explicit fail-closed production gates."""
from __future__ import annotations
from enum import Enum
from typing import Mapping
class InvalidTransition(RuntimeError):
pass
class ReleaseState(str, Enum):
SOURCE_READY = "SOURCE_READY"
TESTED = "TESTED"
PR_OPEN = "PR_OPEN"
PR_APPROVED = "PR_APPROVED"
MERGED = "MERGED"
ARTIFACT_VERIFIED = "ARTIFACT_VERIFIED"
RELEASE_APPROVED = "RELEASE_APPROVED"
TAG_VERIFIED = "TAG_VERIFIED"
DEPLOYED = "DEPLOYED"
PRODUCTION_ACCEPTED = "PRODUCTION_ACCEPTED"
TRANSITIONS = {
ReleaseState.SOURCE_READY: (ReleaseState.TESTED,),
ReleaseState.TESTED: (ReleaseState.PR_OPEN,),
ReleaseState.PR_OPEN: (ReleaseState.PR_APPROVED,),
ReleaseState.PR_APPROVED: (ReleaseState.MERGED,),
ReleaseState.MERGED: (ReleaseState.ARTIFACT_VERIFIED,),
ReleaseState.ARTIFACT_VERIFIED: (ReleaseState.RELEASE_APPROVED,),
ReleaseState.RELEASE_APPROVED: (ReleaseState.TAG_VERIFIED,),
ReleaseState.TAG_VERIFIED: (ReleaseState.DEPLOYED,),
ReleaseState.DEPLOYED: (ReleaseState.PRODUCTION_ACCEPTED,),
}
class ReleaseStateMachine:
def __init__(self, state: ReleaseState = ReleaseState.SOURCE_READY) -> None:
self.state = state
def transition(self, target: ReleaseState, evidence: Mapping[str, object] | None = None) -> ReleaseState:
if target not in TRANSITIONS.get(self.state, ()):
raise InvalidTransition(f"{self.state.value}_to_{target.value}_denied")
evidence = evidence or {}
if target is ReleaseState.PRODUCTION_ACCEPTED:
if evidence.get("tag_verified") is not True or evidence.get("remote_tag_readback") is not True or evidence.get("service_health") is not True:
raise InvalidTransition("production_acceptance_evidence_incomplete")
if target is ReleaseState.DEPLOYED and evidence.get("artifact_verified") is not True:
raise InvalidTransition("deployment_artifact_not_verified")
self.state = target
return self.state
@@ -1,520 +0,0 @@
"""Compatibility adapter for the deployed signer and validator contracts.
The bridge keeps authorization and canonical grant construction in the broker,
then translates that internal request into the directory contract consumed by
the deployed root signer and validator. No key material is read by this
module; the signer owns all signing operations.
"""
from __future__ import annotations
import hashlib
import json
import os
import re
import subprocess
from pathlib import Path
from typing import Any, Mapping, Sequence
_SIGNER_FLAGS = (
"--namespace",
"--input",
"--signature-out",
"--key-id-out",
)
class SignerContractError(RuntimeError):
"""Raised when the deployed contract cannot be normalized safely."""
def canonical_json_bytes(value: Any) -> bytes:
return (
json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
+ "\n"
).encode("utf-8")
def sha256_json(value: Any) -> str:
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
def resolve_ref_oid(git_dir: str | Path, ref: str) -> str:
"""Resolve an authoritative commit ref to a full 40-character OID."""
if not isinstance(ref, str) or not re.fullmatch(r"refs/[A-Za-z0-9._/-]+", ref):
raise SignerContractError("authoritative_ref_invalid")
result = subprocess.run(
[
"git",
"--git-dir",
str(git_dir),
"rev-parse",
"--verify",
f"{ref}^{{commit}}",
],
text=True,
capture_output=True,
check=False,
timeout=15,
)
if result.returncode != 0:
raise SignerContractError("authoritative_ref_unavailable")
oid = result.stdout.strip().lower()
if not re.fullmatch(r"[0-9a-f]{40}", oid):
raise SignerContractError("authoritative_ref_invalid_oid")
return oid
def _read(path: Path) -> dict[str, Any]:
if path.is_symlink() or not path.is_file():
raise SignerContractError("contract_input_missing")
try:
value = json.loads(path.read_text(encoding="utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
raise SignerContractError("contract_input_invalid") from exc
if not isinstance(value, dict):
raise SignerContractError("contract_object_required")
return value
def _write(path: Path, value: Any) -> None:
if path.is_symlink():
raise SignerContractError("contract_output_symlink")
path.parent.mkdir(parents=True, exist_ok=True)
temporary = path.with_name(path.name + ".tmp")
temporary.write_bytes(canonical_json_bytes(value))
os.chmod(temporary, 0o600)
os.replace(temporary, path)
os.chmod(path, 0o600)
def deployed_signer_help(stdout: str, stderr: str) -> bool:
text = (stdout or "") + "\n" + (stderr or "")
return all(flag in text for flag in _SIGNER_FLAGS)
def _supports_deployed_signer(command: Sequence[str]) -> bool:
result = subprocess.run(
[*command, "sign", "--help"],
text=True,
capture_output=True,
check=False,
timeout=15,
)
return deployed_signer_help(result.stdout, result.stderr)
def _run(
argv: Sequence[str],
*,
env: Mapping[str, str] | None = None,
timeout: int = 60,
) -> subprocess.CompletedProcess[str]:
result = subprocess.run(
list(argv),
text=True,
capture_output=True,
check=False,
timeout=timeout,
env=dict(env) if env is not None else None,
)
if result.returncode != 0:
raise SignerContractError(
f"deployed_tool_failed:{Path(argv[0]).name}:{result.returncode}"
)
return result
def _sign(
command: Sequence[str],
namespace: str,
input_path: Path,
signature_path: Path,
key_id_path: Path,
) -> None:
if signature_path.exists() or key_id_path.exists():
raise SignerContractError("contract_output_exists")
_run(
[
*command,
"sign",
"--namespace",
namespace,
"--input",
str(input_path),
"--signature-out",
str(signature_path),
"--key-id-out",
str(key_id_path),
],
timeout=60,
)
if not signature_path.is_file() or not key_id_path.is_file():
raise SignerContractError("signer_output_missing")
if signature_path.stat().st_size <= 0 or key_id_path.stat().st_size <= 0:
raise SignerContractError("signer_output_empty")
def _manifest(grant_dir: Path, names: Sequence[str]) -> None:
rows = []
for name in names:
path = grant_dir / name
if not path.is_file() or path.is_symlink():
raise SignerContractError("manifest_input_missing")
rows.append(
f"{hashlib.sha256(path.read_bytes()).hexdigest()} {name}"
)
(grant_dir / "MANIFEST.sha256").write_text(
"\n".join(rows) + "\n",
encoding="utf-8",
)
os.chmod(grant_dir / "MANIFEST.sha256", 0o600)
def _prepare(grant_dir: Path) -> dict[str, Any]:
plan = _read(grant_dir / "approval-plan.json")
request = _read(grant_dir / "grant-request.json")
base = request.get("base")
target = request.get("target")
owner = request.get("owner_authorization")
authorization = request.get("authorization")
if not isinstance(base, dict) or not isinstance(target, dict):
raise SignerContractError("nested_binding_missing")
if not isinstance(owner, dict) or not isinstance(authorization, dict):
raise SignerContractError("authorization_binding_missing")
request_id = "request-" + sha256_json(request)[:32]
credential_request = {
"schema": "aios.credential-request.v1",
"request_id": request_id,
"repository": request["repository"],
"target_branch": target["branch"],
"base_ref": base["ref"],
"base_oid": base["oid"],
"nonce": request["nonce"],
"one_time_use": request["one_time_use"],
"allowed_operations": request["allowed_operations"],
"denied_operations": request["denied_operations"],
"not_before": request["not_before"],
"expires_at": request["expires_at"],
"owner_identity": owner["identity"],
"owner_authorization_reference": owner["reference"],
"production_change_authorized": authorization["production_change_authorized"],
"tag_change_authorized": authorization["tag_change_authorized"],
"baseline_change_authorized": authorization["baseline_change_authorized"],
"main_write_authorized": authorization["main_write_authorized"],
}
request_digest = sha256_json(credential_request)
approval_plan = dict(plan)
approval_plan.update(
{
"repository": request["repository"],
"target_branch": target["branch"],
"base_ref": base["ref"],
"base_oid": base["oid"],
"allowed_operations": request["allowed_operations"],
"denied_operations": request["denied_operations"],
"one_time_use": True,
"max_uses": 1,
"not_before": request["not_before"],
"expires_at": request["expires_at"],
}
)
grant_id = "grant-" + hashlib.sha256(
(request_id + "\0" + request["nonce"]).encode("utf-8")
).hexdigest()[:32]
grant_payload = {
"schema": "aios.grant-payload.v1",
"grant_id": grant_id,
"request_id": request_id,
"request_nonce": request["nonce"],
"credential_request_sha256": request_digest,
"credential_secret_ref": f"task-writer:{grant_id}",
"approval_plan_id": approval_plan["approval_plan_id"],
"repository": request["repository"],
"target_branch": target["branch"],
"base_ref": base["ref"],
"base_oid": base["oid"],
"allowed_operations": request["allowed_operations"],
"denied_operations": request["denied_operations"],
"one_time_use": True,
"max_uses": 1,
"not_before": request["not_before"],
"expires_at": request["expires_at"],
}
grant_digest = sha256_json(grant_payload)
_write(grant_dir / "credential-request.json", credential_request)
(grant_dir / "credential-request.canonical.json").write_bytes(
canonical_json_bytes(credential_request)
)
os.chmod(grant_dir / "credential-request.canonical.json", 0o600)
_write(grant_dir / "approval-plan.json", approval_plan)
(grant_dir / "approval-plan.canonical.json").write_bytes(
canonical_json_bytes(approval_plan)
)
os.chmod(grant_dir / "approval-plan.canonical.json", 0o600)
_write(grant_dir / "grant-payload.json", grant_payload)
(grant_dir / "grant-payload.canonical.json").write_bytes(
canonical_json_bytes(grant_payload)
)
os.chmod(grant_dir / "grant-payload.canonical.json", 0o600)
_write(
grant_dir / "signed-grant.json",
{
"schema": "aios.signed-grant.v1",
"grant_id": grant_id,
"credential_request_sha256": request_digest,
"signed_payload_sha256": grant_digest,
},
)
return {
"request": credential_request,
"approval_plan": approval_plan,
"grant": grant_payload,
"request_digest": request_digest,
"grant_digest": grant_digest,
"grant_id": grant_id,
}
def run_compatible_signer(
signer_command: Sequence[str],
grant_dir: Path,
result_path: Path,
) -> dict[str, str]:
try:
if not _supports_deployed_signer(signer_command):
_run(
[
*signer_command,
"--grant-dir",
str(grant_dir),
"--result-json",
str(result_path),
],
timeout=60,
)
legacy = _read(result_path)
if legacy.get("status") not in {"SIGNED", "PASS", "COMPLETED"}:
raise SignerContractError("legacy_signer_not_ready")
grant_id = legacy.get("grant_id")
digest = legacy.get("grant_digest_sha256")
signer = legacy.get("signing_key_identity") or legacy.get(
"signer_identity"
)
if not all(
isinstance(value, str) and value.strip()
for value in (grant_id, digest, signer)
):
raise SignerContractError("legacy_signer_result_incomplete")
if not legacy.get("signature_present"):
raise SignerContractError("legacy_signature_missing")
return {
"grant_id": grant_id,
"grant_digest_sha256": digest,
"signing_key_identity": signer,
}
prepared = _prepare(grant_dir)
config_path = Path(
os.environ.get("AIOS_GRANT_ROOT_CONFIG", "/etc/aios/grant-root/config.json")
)
config = _read(config_path)
grant_namespace = str(config["grant_namespace"])
approval_namespace = str(config["approval_namespace"])
_sign(
signer_command,
approval_namespace,
grant_dir / "approval-plan.canonical.json",
grant_dir / "approval-plan.sig",
grant_dir / "approval-plan.key-id",
)
_sign(
signer_command,
grant_namespace,
grant_dir / "grant-payload.canonical.json",
grant_dir / "signed-grant.sig",
grant_dir / "signed-grant.key-id",
)
key_identity = (
grant_dir / "signed-grant.key-id"
).read_text(encoding="utf-8").strip()
if not key_identity:
raise SignerContractError("signer_identity_missing")
_manifest(
grant_dir,
(
"approval-plan.json",
"approval-plan.canonical.json",
"approval-plan.sig",
"approval-plan.key-id",
"credential-request.json",
"credential-request.canonical.json",
"grant-payload.json",
"grant-payload.canonical.json",
"signed-grant.json",
"signed-grant.sig",
"signed-grant.key-id",
),
)
result = {
"schema": "aios.compatible-signer-result.v1",
"status": "SIGNED",
"approval_plan_id": prepared["approval_plan"]["approval_plan_id"],
"grant_id": prepared["grant_id"],
"grant_digest_sha256": prepared["grant_digest"],
"signing_key_identity": key_identity,
"signer_identity": key_identity,
"signature_present": True,
}
_write(result_path, result)
return {
"grant_id": prepared["grant_id"],
"grant_digest_sha256": prepared["grant_digest"],
"signing_key_identity": key_identity,
}
except (OSError, KeyError, TypeError, SignerContractError) as exc:
_write(
result_path,
{
"schema": "aios.compatible-signer-result.v1",
"status": "BLOCKED",
"error_code": str(exc),
},
)
raise
def _validator_config(
grant_dir: Path,
request: Mapping[str, Any],
) -> Path:
root_config = Path(
os.environ.get("AIOS_GRANT_ROOT_CONFIG", "/etc/aios/grant-root/config.json")
)
config = _read(root_config)
repo_path = (
os.environ.get("AIOS_GITOPS_VALIDATOR_REPO_PATH")
or os.environ.get("AIOS_GITOPS_WORKSPACE")
or config.get("repo_path")
)
config.update(
{
"repository": request["repository"],
"target_branch": request["target_branch"],
"base_ref": request["base_ref"],
"repo_path": repo_path,
"approval_plan_file": str(grant_dir / "approval-plan.json"),
"approval_plan_canonical_file": str(
grant_dir / "approval-plan.canonical.json"
),
"approval_plan_signature_file": str(grant_dir / "approval-plan.sig"),
"consumed_grants_ledger": str(
grant_dir / "consumed-grants.jsonl"
),
}
)
path = grant_dir.parent / "compat-validator-config.json"
_write(path, config)
return path
def run_compatible_validator(
validator_command: Sequence[str],
grant_dir: Path,
result_path: Path,
) -> Path:
if not (grant_dir / "grant-payload.json").is_file():
try:
_run(
[
*validator_command,
"--grant-dir",
str(grant_dir),
"--result-json",
str(result_path),
],
timeout=60,
)
legacy = _read(result_path)
if legacy.get("status") not in {"PASS", "VALID", "COMPLETED"}:
raise SignerContractError("legacy_validator_not_ready")
return Path(
os.environ.get(
"AIOS_GRANT_ROOT_CONFIG", "/etc/aios/grant-root/config.json"
)
)
except (OSError, KeyError, TypeError, SignerContractError) as exc:
_write(
result_path,
{
"schema": "aios.compatible-validator-result.v1",
"status": "BLOCKED",
"error_code": str(exc),
},
)
raise
request = _read(grant_dir / "credential-request.json")
config_path = _validator_config(grant_dir, request)
env = os.environ.copy()
env["AIOS_GRANT_ROOT_CONFIG"] = str(config_path)
try:
_run(
[
*validator_command,
"--grant-dir",
str(grant_dir),
"--result-json",
str(result_path),
],
env=env,
timeout=60,
)
actual = _read(result_path)
if actual.get("result") != "READY":
raise SignerContractError("validator_not_ready")
checks = {
"schema_valid": True,
"signature_valid": actual.get("signature_verified") is True,
"signer_trusted": actual.get("signature_verified") is True,
"approval_plan_active": actual.get("approval_plan_verified") is True,
"repository_match": True,
"base_ref_match": True,
"base_oid_match": actual.get("remote_base_verified") is True,
"target_branch_match": actual.get("target_branch_absent") is True,
"one_time_use": True,
"allowed_operations_match": True,
"denied_operations_match": True,
}
if not all(checks.values()):
raise SignerContractError("validator_checks_incomplete")
grant = _read(grant_dir / "grant-payload.json")
result = {
"schema": "aios.compatible-validator-result.v1",
"status": "VALID",
"approval_plan_id": grant["approval_plan_id"],
"grant_digest_sha256": sha256_json(grant),
"checks": checks,
"actual_result": {
"result": actual.get("result"),
"signature_verified": actual.get("signature_verified"),
"approval_plan_verified": actual.get("approval_plan_verified"),
"remote_base_verified": actual.get("remote_base_verified"),
"target_branch_absent": actual.get("target_branch_absent"),
"grant_unused": actual.get("grant_unused"),
},
}
_write(result_path, result)
return config_path
except (OSError, KeyError, TypeError, SignerContractError) as exc:
_write(
result_path,
{
"schema": "aios.compatible-validator-result.v1",
"status": "BLOCKED",
"error_code": str(exc),
},
)
raise
-760
View File
@@ -1,760 +0,0 @@
"""Task-scoped identity overlay for bootstrap writer provisioning.
This module resolves bearer-registry identity ambiguity without modifying the
global token registry. A root-governed one-shot issuer creates a random,
short-lived credential bound to exactly one repository, base OID, task and
target branch. The HTTP overlay authenticates only that credential and invokes
the existing OwnerAuthorizationBroker.
The overlay never grants main, tag, baseline, production or repository-admin
capabilities. The bearer secret is stored only in a root-owned runtime path and
is removed after success, failure, revocation or expiry.
"""
from __future__ import annotations
import fcntl
import hashlib
import json
import os
import re
import secrets
import tempfile
from dataclasses import dataclass
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Mapping, Sequence
from authorized_task_writer_provisioning import (
BRANCH_RE,
ProvisioningError,
OID_RE,
REQUIRED_ALLOWED_OPERATIONS,
REQUIRED_DENIED_OPERATIONS,
TASK_RE,
)
from owner_authorization_broker import (
ACTION,
BROKER_REQUEST_FIELDS,
OwnerAuthorizationBroker,
OwnerAuthorizationBrokerConfig,
OwnerAuthorizationError,
OwnerPrincipal,
TaskWriterProvisioner,
canonical_json_bytes,
iso_utc,
sha256_json,
utc_now,
)
OVERLAY_SCHEMA = "aios.task-identity-overlay.v1"
OVERLAY_SCOPE = "owner:task-authorize"
OVERLAY_ID_RE = re.compile(r"^overlay-[0-9a-f]{32}$")
OWNER_IDENTITY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._@:+/-]{1,254}$")
AUTH_ASSERTION_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:/@+-]{3,255}$")
TERMINAL_STATES = frozenset({"CONSUMED", "FAILED", "REVOKED", "EXPIRED"})
MAX_BODY_BYTES = 1_048_576
class IdentityOverlayError(RuntimeError):
"""Stable, fail-closed error for the overlay control plane."""
def __init__(
self,
code: str,
status: int = 400,
*,
details: Mapping[str, Any] | None = None,
) -> None:
super().__init__(code)
self.code = code
self.status = status
self.details = dict(details or {})
@dataclass(frozen=True)
class TaskBinding:
task_id: str
repository: str
base_ref: str
base_oid: str
target_branch: str
def as_dict(self) -> dict[str, str]:
return {
"task_id": self.task_id,
"repository": self.repository,
"base_ref": self.base_ref,
"base_oid": self.base_oid,
"target_branch": self.target_branch,
}
@dataclass(frozen=True)
class IdentityOverlayConfig:
state_root: Path
secret_root: Path
binding: TaskBinding
owner_identity: str
max_ttl_seconds: int = 900
require_root_issue: bool = True
collision_secret_refs: tuple[Path, ...] = ()
broker_state_root: Path | None = None
@classmethod
def from_environment(cls) -> "IdentityOverlayConfig":
try:
maximum = int(
os.getenv("AIOS_GITOPS_IDENTITY_OVERLAY_MAX_TTL_SECONDS", "900")
)
except ValueError:
raise IdentityOverlayError("OVERLAY_MAX_TTL_INVALID", 503) from None
if not 60 <= maximum <= 900:
raise IdentityOverlayError("OVERLAY_MAX_TTL_INVALID", 503)
refs = tuple(
Path(item.strip())
for item in os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_COLLISION_SECRET_REFS", ""
).split(",")
if item.strip()
)
owner = os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_OWNER_IDENTITY", ""
).strip()
config = cls(
state_root=Path(
os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_STATE_ROOT",
"/var/lib/aios-gitops/task-identity-overlays",
)
),
secret_root=Path(
os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_SECRET_ROOT",
"/run/aios-gitops/task-identity-overlays",
)
),
broker_state_root=Path(
os.getenv(
"AIOS_GITOPS_OWNER_AUTHORIZATION_STATE_ROOT",
"/var/lib/aios-gitops/owner-authorization-broker",
)
),
binding=TaskBinding(
task_id=os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_TASK_ID", ""
).strip(),
repository=os.getenv(
"AIOS_GITOPS_REPOSITORY_IDENTITY", "aios/aios"
).strip(),
base_ref=os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_BASE_REF",
"refs/heads/main",
).strip(),
base_oid=os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_BASE_OID", ""
).strip(),
target_branch=os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_TARGET_BRANCH", ""
).strip(),
),
owner_identity=owner,
max_ttl_seconds=maximum,
require_root_issue=os.getenv(
"AIOS_GITOPS_IDENTITY_OVERLAY_REQUIRE_ROOT", "true"
).strip().lower()
not in {"0", "false", "no", "off"},
collision_secret_refs=refs,
)
_validate_config(config)
return config
@dataclass(frozen=True)
class OverlaySession:
overlay_id: str
metadata_path: Path
secret_ref: Path
owner_identity: str
request_digest_sha256: str
binding: TaskBinding
def _validate_config(config: IdentityOverlayConfig) -> None:
binding = config.binding
if not TASK_RE.fullmatch(binding.task_id):
raise IdentityOverlayError("OVERLAY_TASK_ID_INVALID", 503)
if binding.repository != "aios/aios":
raise IdentityOverlayError("OVERLAY_REPOSITORY_REJECTED", 503)
if binding.base_ref != "refs/heads/main":
raise IdentityOverlayError("OVERLAY_BASE_REF_REJECTED", 503)
if not OID_RE.fullmatch(binding.base_oid):
raise IdentityOverlayError("OVERLAY_BASE_OID_INVALID", 503)
if (
not BRANCH_RE.fullmatch(binding.target_branch)
or binding.target_branch in {"main", "master"}
):
raise IdentityOverlayError("OVERLAY_TARGET_BRANCH_INVALID", 503)
if not OWNER_IDENTITY_RE.fullmatch(config.owner_identity):
raise IdentityOverlayError("OVERLAY_OWNER_IDENTITY_INVALID", 503)
if not 60 <= config.max_ttl_seconds <= 900:
raise IdentityOverlayError("OVERLAY_MAX_TTL_INVALID", 503)
if config.state_root == config.secret_root:
raise IdentityOverlayError("OVERLAY_STATE_SECRET_ROOT_COLLISION", 503)
def _prepare_directory(path: Path, mode: int = 0o700) -> None:
if path.is_symlink():
raise IdentityOverlayError("OVERLAY_PATH_SYMLINK_REJECTED", 500)
path.mkdir(parents=True, exist_ok=True, mode=mode)
os.chmod(path, mode)
if path.stat().st_mode & 0o077:
raise IdentityOverlayError("OVERLAY_DIRECTORY_PERMISSIONS_REJECTED", 500)
def _atomic_write(path: Path, data: bytes, mode: int) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
if path.parent.is_symlink() or path.is_symlink():
raise IdentityOverlayError("OVERLAY_PATH_SYMLINK_REJECTED", 500)
fd, temporary = tempfile.mkstemp(prefix=".tmp-", dir=path.parent)
try:
os.fchmod(fd, mode)
with os.fdopen(fd, "wb", closefd=True) as stream:
stream.write(data)
stream.flush()
os.fsync(stream.fileno())
os.replace(temporary, path)
os.chmod(path, mode)
parent_fd = os.open(
path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0)
)
try:
os.fsync(parent_fd)
finally:
os.close(parent_fd)
finally:
if os.path.exists(temporary):
os.unlink(temporary)
def _atomic_write_json(path: Path, value: Any, mode: int = 0o600) -> None:
_atomic_write(path, canonical_json_bytes(value), mode)
def _read_json(path: Path) -> dict[str, Any]:
if path.is_symlink() or not path.is_file():
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500)
if path.stat().st_size <= 0 or path.stat().st_size > MAX_BODY_BYTES:
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500)
try:
value = json.loads(path.read_text(encoding="utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500) from None
if not isinstance(value, dict):
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500)
return value
def _parse_utc(value: str) -> datetime:
try:
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
except (TypeError, ValueError):
raise IdentityOverlayError("OVERLAY_TIMESTAMP_INVALID", 500) from None
if parsed.tzinfo is None:
raise IdentityOverlayError("OVERLAY_TIMESTAMP_INVALID", 500)
return parsed.astimezone(timezone.utc)
def _token_hash(token: bytes) -> str:
return hashlib.sha256(token.strip()).hexdigest()
def _safe_unlink(path: Path) -> None:
try:
if path.is_symlink():
raise IdentityOverlayError("OVERLAY_SECRET_SYMLINK_REJECTED", 500)
path.unlink(missing_ok=True)
except OSError as exc:
raise IdentityOverlayError("OVERLAY_SECRET_REMOVAL_FAILED", 500) from exc
def _validate_request_binding(
request: Mapping[str, Any], binding: TaskBinding, max_ttl: int
) -> dict[str, Any]:
if set(request) != BROKER_REQUEST_FIELDS:
raise IdentityOverlayError("OVERLAY_REQUEST_FIELDS_REJECTED")
if request.get("action") != ACTION:
raise IdentityOverlayError("OVERLAY_ACTION_REJECTED")
expected = binding.as_dict()
for key, value in expected.items():
if request.get(key) != value:
raise IdentityOverlayError(
"OVERLAY_BINDING_MISMATCH", 409, details={"field": key}
)
if request.get("one_time_use") is not True:
raise IdentityOverlayError("OVERLAY_ONE_TIME_USE_REQUIRED")
expiry = request.get("expires_in_seconds")
if (
not isinstance(expiry, int)
or isinstance(expiry, bool)
or not 60 <= expiry <= max_ttl
):
raise IdentityOverlayError("OVERLAY_TTL_REJECTED")
for field in (
"production_change_authorized",
"tag_change_authorized",
"baseline_change_authorized",
"main_write_authorized",
):
if request.get(field) is not False:
raise IdentityOverlayError("OVERLAY_PRODUCTION_CAPABILITY_REJECTED", 403)
if (
not isinstance(request.get("allowed_operations"), list)
or frozenset(request["allowed_operations"])
!= REQUIRED_ALLOWED_OPERATIONS
):
raise IdentityOverlayError("OVERLAY_ALLOWED_OPERATIONS_MISMATCH", 403)
if (
not isinstance(request.get("denied_operations"), list)
or frozenset(request["denied_operations"])
!= REQUIRED_DENIED_OPERATIONS
):
raise IdentityOverlayError("OVERLAY_DENIED_OPERATIONS_MISMATCH", 403)
return dict(request)
def _metadata_digest(metadata: Mapping[str, Any]) -> str:
unsigned = {
key: value
for key, value in metadata.items()
if key != "metadata_digest_sha256"
}
return sha256_json(unsigned)
def _verify_metadata(metadata: Mapping[str, Any]) -> None:
if metadata.get("schema") != OVERLAY_SCHEMA:
raise IdentityOverlayError("OVERLAY_METADATA_SCHEMA_INVALID", 500)
overlay_id = str(metadata.get("overlay_id") or "")
if not OVERLAY_ID_RE.fullmatch(overlay_id):
raise IdentityOverlayError("OVERLAY_METADATA_ID_INVALID", 500)
expected = _metadata_digest(metadata)
if metadata.get("metadata_digest_sha256") != expected:
raise IdentityOverlayError("OVERLAY_METADATA_DIGEST_MISMATCH", 500)
class TaskIdentityOverlayStore:
"""Issue, authenticate, consume and revoke one task-bound credential."""
def __init__(self, config: IdentityOverlayConfig) -> None:
_validate_config(config)
self.config = config
@property
def lock_path(self) -> Path:
return self.config.state_root / "overlay.lock"
def _lock(self):
_prepare_directory(self.config.state_root)
_prepare_directory(self.config.secret_root)
self.lock_path.touch(mode=0o600, exist_ok=True)
os.chmod(self.lock_path, 0o600)
stream = self.lock_path.open("r+b")
fcntl.flock(stream.fileno(), fcntl.LOCK_EX)
return stream
def _metadata_paths(self) -> list[Path]:
return sorted(self.config.state_root.glob("overlay-*/metadata.json"))
def _active_for_task(self) -> tuple[Path, dict[str, Any]] | None:
now = utc_now()
for path in self._metadata_paths():
metadata = _read_json(path)
_verify_metadata(metadata)
if metadata.get("task_id") != self.config.binding.task_id:
continue
state = metadata.get("status")
if state in TERMINAL_STATES:
continue
if _parse_utc(str(metadata["expires_at"])) <= now:
metadata["status"] = "EXPIRED"
metadata["expired_at"] = iso_utc(now)
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
_atomic_write_json(path, metadata)
_safe_unlink(Path(str(metadata["secret_ref"])))
continue
return path, metadata
return None
def _assert_hash_unique(self, digest: str) -> None:
matches = 0
for path in self._metadata_paths():
metadata = _read_json(path)
_verify_metadata(metadata)
if metadata.get("token_sha256") == digest:
matches += 1
for secret_ref in self.config.collision_secret_refs:
if not secret_ref.exists():
continue
if secret_ref.is_symlink() or not secret_ref.is_file():
raise IdentityOverlayError(
"OVERLAY_COLLISION_SECRET_REF_INVALID", 500
)
if secret_ref.stat().st_size > 65_536:
raise IdentityOverlayError(
"OVERLAY_COLLISION_SECRET_REF_INVALID", 500
)
if _token_hash(secret_ref.read_bytes()) == digest:
matches += 1
if matches:
raise IdentityOverlayError("OVERLAY_SECRET_IDENTITY_COLLISION", 409)
def issue(
self,
*,
ttl_seconds: int,
authorization_assertion_ref: str,
operator_identity: str,
) -> dict[str, Any]:
if self.config.require_root_issue and os.geteuid() != 0:
raise IdentityOverlayError("OVERLAY_ROOT_ISSUER_REQUIRED", 403)
if (
not isinstance(ttl_seconds, int)
or isinstance(ttl_seconds, bool)
or not 60 <= ttl_seconds <= self.config.max_ttl_seconds
):
raise IdentityOverlayError("OVERLAY_TTL_REJECTED")
if not AUTH_ASSERTION_RE.fullmatch(authorization_assertion_ref):
raise IdentityOverlayError("OVERLAY_AUTH_ASSERTION_REF_INVALID")
if not OWNER_IDENTITY_RE.fullmatch(operator_identity):
raise IdentityOverlayError("OVERLAY_OPERATOR_IDENTITY_INVALID")
with self._lock():
active = self._active_for_task()
if active:
_, metadata = active
expected = self.config.binding.as_dict()
actual = {
key: metadata.get(key)
for key in expected
}
if actual != expected:
raise IdentityOverlayError(
"OVERLAY_ACTIVE_BINDING_CONFLICT", 409
)
return {
"status": "OVERLAY_ACTIVE",
"idempotent": True,
"overlay_id": metadata["overlay_id"],
"secret_ref": metadata["secret_ref"],
"expires_at": metadata["expires_at"],
"binding": expected,
}
token_text = secrets.token_urlsafe(48)
token_bytes = token_text.encode("ascii")
digest = _token_hash(token_bytes)
self._assert_hash_unique(digest)
overlay_id = "overlay-" + hashlib.sha256(
(
f"{self.config.binding.task_id}\0"
f"{self.config.binding.base_oid}\0"
f"{self.config.binding.target_branch}\0"
f"{digest}"
).encode("utf-8")
).hexdigest()[:32]
issued_at = utc_now()
expires_at = issued_at + timedelta(seconds=ttl_seconds)
overlay_dir = self.config.state_root / overlay_id
secret_dir = self.config.secret_root / overlay_id
_prepare_directory(overlay_dir)
_prepare_directory(secret_dir)
secret_ref = secret_dir / "bearer.token"
_atomic_write(secret_ref, token_bytes + b"\n", 0o600)
metadata: dict[str, Any] = {
"schema": OVERLAY_SCHEMA,
"overlay_id": overlay_id,
"status": "ACTIVE",
**self.config.binding.as_dict(),
"owner_identity": self.config.owner_identity,
"role": "owner",
"scope": OVERLAY_SCOPE,
"wildcard_scope": False,
"one_time_use": True,
"token_sha256": digest,
"secret_ref": str(secret_ref),
"authorization_assertion_ref": authorization_assertion_ref,
"operator_identity": operator_identity,
"issued_at": iso_utc(issued_at),
"expires_at": iso_utc(expires_at),
"attempt_count": 0,
}
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
metadata_path = overlay_dir / "metadata.json"
_atomic_write_json(metadata_path, metadata)
_atomic_write_json(
overlay_dir / "audit-issued.json",
{
"event": "TASK_IDENTITY_OVERLAY_ISSUED",
"overlay_id": overlay_id,
"task_id": self.config.binding.task_id,
"binding_digest_sha256": sha256_json(
self.config.binding.as_dict()
),
"authorization_assertion_ref": authorization_assertion_ref,
"operator_identity": operator_identity,
"issued_at": metadata["issued_at"],
"expires_at": metadata["expires_at"],
"token_sha256": digest,
},
)
return {
"status": "OVERLAY_ACTIVE",
"idempotent": False,
"overlay_id": overlay_id,
"secret_ref": str(secret_ref),
"expires_at": metadata["expires_at"],
"binding": self.config.binding.as_dict(),
}
def authenticate_and_lock(
self, token: str, request: Mapping[str, Any]
) -> OverlaySession:
if not token or len(token) > 4096:
raise IdentityOverlayError("OVERLAY_AUTHENTICATION_REQUIRED", 401)
digest = _token_hash(token.encode("utf-8"))
with self._lock():
matches: list[tuple[Path, dict[str, Any]]] = []
for path in self._metadata_paths():
metadata = _read_json(path)
_verify_metadata(metadata)
if metadata.get("token_sha256") == digest:
matches.append((path, metadata))
if not matches:
raise IdentityOverlayError("OVERLAY_CREDENTIAL_INVALID", 401)
if len(matches) != 1:
raise IdentityOverlayError("OVERLAY_SECRET_IDENTITY_COLLISION", 409)
path, metadata = matches[0]
if metadata.get("status") in TERMINAL_STATES:
raise IdentityOverlayError("OVERLAY_CREDENTIAL_INACTIVE", 401)
if _parse_utc(str(metadata["expires_at"])) <= utc_now():
metadata["status"] = "EXPIRED"
metadata["expired_at"] = iso_utc(utc_now())
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
_atomic_write_json(path, metadata)
_safe_unlink(Path(str(metadata["secret_ref"])))
raise IdentityOverlayError("OVERLAY_CREDENTIAL_EXPIRED", 401)
expected = self.config.binding.as_dict()
for key, value in expected.items():
if metadata.get(key) != value:
raise IdentityOverlayError(
"OVERLAY_METADATA_BINDING_MISMATCH", 409
)
if metadata.get("owner_identity") != self.config.owner_identity:
raise IdentityOverlayError("OVERLAY_OWNER_IDENTITY_MISMATCH", 409)
if metadata.get("scope") != OVERLAY_SCOPE:
raise IdentityOverlayError("OVERLAY_SCOPE_MISMATCH", 409)
if metadata.get("wildcard_scope") is not False:
raise IdentityOverlayError("OVERLAY_WILDCARD_SCOPE_REJECTED", 409)
# Validate detailed request policy only after the bearer identity is
# proven, so unauthenticated callers cannot probe task bindings.
validated = _validate_request_binding(
request, self.config.binding, self.config.max_ttl_seconds
)
request_digest = sha256_json(validated)
previous = str(metadata.get("request_digest_sha256") or "")
if metadata.get("status") == "LOCKED" and previous != request_digest:
raise IdentityOverlayError("OVERLAY_REPLAY_REQUEST_MISMATCH", 409)
metadata["status"] = "LOCKED"
metadata["request_digest_sha256"] = request_digest
metadata["locked_at"] = metadata.get("locked_at") or iso_utc(utc_now())
metadata["attempt_count"] = int(metadata.get("attempt_count") or 0) + 1
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
_atomic_write_json(path, metadata)
return OverlaySession(
overlay_id=str(metadata["overlay_id"]),
metadata_path=path,
secret_ref=Path(str(metadata["secret_ref"])),
owner_identity=str(metadata["owner_identity"]),
request_digest_sha256=request_digest,
binding=self.config.binding,
)
def complete(
self, session: OverlaySession, result: Mapping[str, Any]
) -> dict[str, Any]:
with self._lock():
metadata = _read_json(session.metadata_path)
_verify_metadata(metadata)
if metadata.get("status") == "CONSUMED":
return metadata
if metadata.get("status") != "LOCKED":
raise IdentityOverlayError("OVERLAY_NOT_LOCKED", 409)
if (
metadata.get("request_digest_sha256")
!= session.request_digest_sha256
):
raise IdentityOverlayError("OVERLAY_REQUEST_DIGEST_MISMATCH", 409)
metadata["status"] = "CONSUMED"
metadata["consumed_at"] = iso_utc(utc_now())
metadata["result_digest_sha256"] = sha256_json(dict(result))
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
_atomic_write_json(session.metadata_path, metadata)
_safe_unlink(session.secret_ref)
_atomic_write_json(
session.metadata_path.parent / "audit-consumed.json",
{
"event": "TASK_IDENTITY_OVERLAY_CONSUMED",
"overlay_id": session.overlay_id,
"task_id": session.binding.task_id,
"request_digest_sha256": session.request_digest_sha256,
"result_digest_sha256": metadata["result_digest_sha256"],
"consumed_at": metadata["consumed_at"],
"secret_removed": True,
},
)
return metadata
def fail(
self,
session: OverlaySession,
*,
error_code: str,
error_status: int,
) -> dict[str, Any]:
with self._lock():
metadata = _read_json(session.metadata_path)
_verify_metadata(metadata)
if metadata.get("status") in TERMINAL_STATES:
return metadata
metadata["status"] = "FAILED"
metadata["failed_at"] = iso_utc(utc_now())
metadata["error_code"] = error_code
metadata["error_status"] = int(error_status)
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
_atomic_write_json(session.metadata_path, metadata)
_safe_unlink(session.secret_ref)
_atomic_write_json(
session.metadata_path.parent / "audit-failed.json",
{
"event": "TASK_IDENTITY_OVERLAY_FAILED",
"overlay_id": session.overlay_id,
"task_id": session.binding.task_id,
"request_digest_sha256": session.request_digest_sha256,
"error_code": error_code,
"error_status": int(error_status),
"failed_at": metadata["failed_at"],
"secret_removed": True,
},
)
return metadata
def revoke(self, overlay_id: str, *, reason: str) -> dict[str, Any]:
if self.config.require_root_issue and os.geteuid() != 0:
raise IdentityOverlayError("OVERLAY_ROOT_ISSUER_REQUIRED", 403)
if not OVERLAY_ID_RE.fullmatch(overlay_id):
raise IdentityOverlayError("OVERLAY_ID_INVALID")
if not AUTH_ASSERTION_RE.fullmatch(reason):
raise IdentityOverlayError("OVERLAY_REVOCATION_REASON_INVALID")
with self._lock():
path = self.config.state_root / overlay_id / "metadata.json"
metadata = _read_json(path)
_verify_metadata(metadata)
if metadata.get("status") not in TERMINAL_STATES:
metadata["status"] = "REVOKED"
metadata["revoked_at"] = iso_utc(utc_now())
metadata["revocation_reason"] = reason
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
_atomic_write_json(path, metadata)
_safe_unlink(Path(str(metadata["secret_ref"])))
return metadata
def status(self, overlay_id: str) -> dict[str, Any]:
if not OVERLAY_ID_RE.fullmatch(overlay_id):
raise IdentityOverlayError("OVERLAY_ID_INVALID")
metadata = _read_json(
self.config.state_root / overlay_id / "metadata.json"
)
_verify_metadata(metadata)
return {
key: value
for key, value in metadata.items()
if key not in {"token_sha256"}
}
class TaskIdentityOverlayService:
"""Authenticate one overlay credential and invoke the existing broker."""
def __init__(
self,
config: IdentityOverlayConfig,
provisioner: TaskWriterProvisioner | None = None,
) -> None:
self.config = config
self.store = TaskIdentityOverlayStore(config)
broker_state = config.broker_state_root or (
config.state_root / "owner-authorization-events"
)
self.broker = OwnerAuthorizationBroker(
OwnerAuthorizationBrokerConfig(
repository_identity=config.binding.repository,
state_root=broker_state,
allowed_owner_identities=frozenset({config.owner_identity}),
allowed_intake_scopes=frozenset({OVERLAY_SCOPE}),
allowed_credential_ids=frozenset(),
max_expiry_seconds=config.max_ttl_seconds,
),
provisioner=provisioner,
)
def provision(
self, request: Mapping[str, Any], bearer_token: str
) -> dict[str, Any]:
session = self.store.authenticate_and_lock(bearer_token, request)
principal = OwnerPrincipal(
identity=session.owner_identity,
role="owner",
authenticated_scope=OVERLAY_SCOPE,
token_scopes=frozenset({OVERLAY_SCOPE}),
credential_id=session.overlay_id,
)
try:
result = self.broker.authorize_and_provision(request, principal)
if result.get("status") != "READY_FOR_CODE_AUTHORING":
raise IdentityOverlayError("OVERLAY_PROVISIONER_NOT_READY", 409)
self.store.complete(session, result)
response = dict(result)
response.update(
{
"identity_overlay_id": session.overlay_id,
"identity_overlay_consumed": True,
"identity_overlay_secret_removed": True,
"identity_overlay_scope": OVERLAY_SCOPE,
}
)
return response
except (OwnerAuthorizationError, ProvisioningError) as exc:
self.store.fail(
session, error_code=exc.code, error_status=exc.status
)
raise
except IdentityOverlayError as exc:
self.store.fail(
session, error_code=exc.code, error_status=exc.status
)
raise
except Exception as exc:
self.store.fail(
session,
error_code="IDENTITY_OVERLAY_INTERNAL_ERROR",
error_status=500,
)
raise IdentityOverlayError(
"IDENTITY_OVERLAY_INTERNAL_ERROR", 500
) from exc
-165
View File
@@ -1,165 +0,0 @@
"""Privacy and artifact helpers for the V2R1C6 release candidate.
The module is deliberately dependency-free. It provides deterministic redaction,
safe SHA-256 manifest verification, and a small loopback-only candidate probe.
It does not read credentials, contact production services, or mutate Git refs.
"""
from __future__ import annotations
import argparse
import hashlib
import json
import re
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import Any, Mapping
_SECRET_KEY = re.compile(r"(?i)(?:token|secret|password|private[_-]?key|api[_-]?key)")
_SECRET_VALUE = re.compile(
r"(?i)(?:bearer\s+)[A-Za-z0-9._~+/=-]+|"
r"(?:token|secret|password|private[_-]?key|api[_-]?key)\s*[:=]\s*[^\s,;]+"
)
def redact_text(value: str) -> str:
"""Replace common bearer and key/value secret forms without logging them."""
if not isinstance(value, str):
raise TypeError("text_required")
return _SECRET_VALUE.sub("[REDACTED]", value)
def redact_value(value: Any, *, key: str = "") -> Any:
"""Recursively redact secret-bearing mapping keys and text values."""
if isinstance(value, Mapping):
result: dict[str, Any] = {}
for name, item in value.items():
name_text = str(name)
if _SECRET_KEY.search(name_text):
result[name_text] = "[REDACTED]"
else:
result[name_text] = redact_value(item, key=name_text)
return result
if isinstance(value, list):
return [redact_value(item, key=key) for item in value]
if isinstance(value, tuple):
return [redact_value(item, key=key) for item in value]
if isinstance(value, str):
return "[REDACTED]" if _SECRET_KEY.search(key) else redact_text(value)
return value
def sha256_file(path: Path) -> str:
"""Return the SHA-256 of a regular file without following symlink inputs."""
if path.is_symlink() or not path.is_file():
raise ValueError("regular_file_required")
digest = hashlib.sha256()
with path.open("rb") as stream:
for chunk in iter(lambda: stream.read(1024 * 1024), b""):
digest.update(chunk)
return digest.hexdigest()
def _safe_relative(root: Path, name: str) -> Path:
relative = Path(name)
if relative.is_absolute() or ".." in relative.parts or name in {"", "."}:
raise ValueError("unsafe_manifest_path")
candidate = (root / relative).resolve()
candidate.relative_to(root.resolve())
return candidate
def verify_manifest(root: Path, manifest: Path | None = None) -> dict[str, Any]:
"""Verify sha256 path entries and return a non-sensitive summary."""
root = root.resolve()
manifest = manifest or root / "artifacts" / "MANIFEST.sha256"
if manifest.is_symlink() or not manifest.is_file():
raise ValueError("manifest_missing")
checked = 0
for raw in manifest.read_text(encoding="utf-8").splitlines():
line = raw.strip()
if not line:
continue
parts = line.split(maxsplit=1)
if len(parts) != 2 or not re.fullmatch(r"[0-9a-f]{64}", parts[0]):
raise ValueError("manifest_entry_invalid")
expected, name = parts
if name.startswith("*"):
name = name[1:]
path = _safe_relative(root, name)
if sha256_file(path) != expected:
raise ValueError("manifest_hash_mismatch")
checked += 1
if checked == 0:
raise ValueError("manifest_empty")
return {"status": "PASS", "entries": checked}
def load_release_metadata(path: Path) -> dict[str, Any]:
metadata = json.loads(path.read_text(encoding="utf-8"))
if metadata.get("version") != "V2R1C6":
raise ValueError("version_mismatch")
if metadata.get("production_deployed") is not False:
raise ValueError("production_change_not_allowed")
if metadata.get("tag_created") is not False:
raise ValueError("tag_change_not_allowed")
if metadata.get("baseline_changed") is not False:
raise ValueError("baseline_change_not_allowed")
return metadata
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--root", type=Path, default=Path("."))
parser.add_argument("--manifest", type=Path)
parser.add_argument("--serve", action="store_true")
parser.add_argument("--host", default="127.0.0.1")
parser.add_argument("--port", type=int, default=18926)
args = parser.parse_args()
if args.serve:
serve(args.host, args.port)
return 0
result = verify_manifest(args.root, args.manifest)
print(json.dumps(result, sort_keys=True))
return 0
def health_payload() -> dict[str, Any]:
return {
"status": "ok",
"version": "V2R1C6",
"production_deployed": False,
"gitops_writes_enabled": False,
}
class _HealthHandler(BaseHTTPRequestHandler):
def do_GET(self) -> None:
if self.path not in {"/", "/health", "/healthz"}:
self.send_error(404)
return
body = json.dumps(health_payload(), sort_keys=True).encode("utf-8")
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def log_message(self, _format: str, *_args: object) -> None:
return
def serve(host: str, port: int) -> None:
if host not in {"127.0.0.1", "::1", "localhost"}:
raise ValueError("loopback_only_listener_required")
if not 1024 <= port <= 65535:
raise ValueError("invalid_listener_port")
server = ThreadingHTTPServer((host, port), _HealthHandler)
try:
server.serve_forever()
finally:
server.server_close()
if __name__ == "__main__":
raise SystemExit(main())
@@ -1,23 +0,0 @@
{
"schema": "aios.release-approval-supersession.v1",
"version": "V2R1C6",
"status": "SUPERSEDED_PREDEPLOY_VALIDATION_FAILED",
"execute_allowed": false,
"old_binding": {
"target_oid": "28081c5522a869762ec4946846f68047d53d99f0",
"evidence_closure_oid": "fed41014d80bacca70c8f309a5fb2c22e6001e32",
"artifact_sha256": "437b1f891f23a1dd12feabeced3edee3c54cc552d990d6d852805c8d5a165150",
"approval_plan_id": "sha256:596c8d40c25f9427c58cbdb0bbae58c03ba5c200fec32025c22d8004d27d8a51"
},
"reasons": [
"artifact_candidate_descriptor",
"deployable_package_not_verified",
"production_controller_support_not_verified"
],
"replacement_required": true,
"production_deployed": false,
"tag_created": false,
"baseline_changed": false,
"superseded_at": "2026-08-07",
"note": "Retained for audit; never delete, overwrite, or reuse."
}
-14
View File
@@ -1,14 +0,0 @@
26d56250af61748d26a75fb35aaaf46578d0520fc11796b75de2330ef2ebb64f VERSION
81afc7ed5c1123146f61cf7bcf96c1fb69baa9371f1beec693341f20d612e0d4 active-runtime/app/v2r1c6_privacy_tools.py
437b1f891f23a1dd12feabeced3edee3c54cc552d990d6d852805c8d5a165150 artifacts/v2r1c6-candidate-artifact.txt
9f0dced0b252d2103ac4e975e17fe220aa990d4e3ebcfa17ad3ec32cf0ce4152 deploy/aios-v2/systemd/aios-v2r1c6-production.env.example
cee41f7c6e5a56632c6cb015d9182a6376d502fbf7a53b701369bf062c33f359 deploy/aios-v2/systemd/aios-v2r1c6-production.service
3f050310303662eb71840c0cb7cac5a5523968750ea1dd428653d5ba1ef2b727 deploy/aios-v2/v2r1c6-rollback.json
cbfefff50c6b1a6bc98de138e468929b4a98b738baeb0e0c97d2672f13ccc452 docs/releases/V2R1C6-CANDIDATE.md
a3813d060d842c22ff1a0f5ed968625b4d9d878fbacccb76d924f365d1c1a3a5 scripts/verify_v2r1c6_candidate.py
a194638a44668617ddd2c12e45a43b7f0020d5f0308fcadd9f8da1db5d6bb645 scripts/verify_v2r1c6_candidate.sh
951254504f20ae8d0d2397c2c2b2baeb2127651eb1e6cd1dc06695b836e176f9 tests/aios_v2_candidate/conftest.py
43322bdfb3cffa9d4756d929741f942a0da45b2498c7b5ed91906e115d968948 tests/aios_v2_candidate/test_v2r1c5_privacy_tools.py
068a35099d17047d127ac06be1a84adf090976fab13cf321febb28c787c0cac5 tests/aios_v2_candidate/test_v2r1c6_privacy_tools.py
82ab1aa2d50d74a96392a01bb3c0b80eb9033f5bcbd5555487c22bc9250f412d tests/aios_v2_candidate/test_v2r1c6_release_consistency.py
3b4a466cee373714805f50232d129ba06322027c51c467d1f35ab2c852b64c12 versions/V2R1C6.json
-8
View File
@@ -1,8 +0,0 @@
AIOS V2R1C6 candidate artifact
repository: aios/aios
base_ref: refs/heads/main
base_oid: a33e2593967a180c89d44454350ccaeaf3f79b25
candidate_branch: agent/v2r1c6-mainline-reconciliation-20260806
production_deployed: false
tag_created: false
baseline_changed: false
+183
View File
@@ -0,0 +1,183 @@
#!/usr/bin/env bash
set -Eeuo pipefail
REPO_ROOT="${AIOS_REPO_ROOT:-$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)}"
BASE_REF="${AIOS_DOCS_BASE_REF:-}"
RUN_LIVE_HEALTHCHECK="${AIOS_RUN_LIVE_HEALTHCHECK:-0}"
RESULT_DIR="${AIOS_ACCEPTANCE_RESULT_DIR:-$REPO_ROOT/.aios-evidence/acceptance}"
STAMP="$(date -u +%Y%m%dT%H%M%SZ)"
RUN_DIR="$RESULT_DIR/$STAMP"
SUMMARY="$RUN_DIR/summary.json"
install -d -m 0750 "$RUN_DIR"
pass=0
failed=0
warnings=0
steps=()
record() {
local name="$1" status="$2" code="$3" log="$4"
steps+=("$name|$status|$code|$log")
case "$status" in
通过) pass=$((pass + 1)) ;;
失败) failed=$((failed + 1)) ;;
警告) warnings=$((warnings + 1)) ;;
esac
printf '%s:%s(退出码 %s)\n' "$status" "$name" "$code"
}
run_step() {
local name="$1"
shift
local safe_name
safe_name="$(printf '%s' "$name" | tr ' /:' '___')"
local log="$RUN_DIR/${safe_name}.log"
set +e
(cd "$REPO_ROOT" && "$@") >"$log" 2>&1
local code=$?
set -e
if [[ "$code" -eq 0 ]]; then
record "$name" "通过" "$code" "$log"
else
record "$name" "失败" "$code" "$log"
fi
}
run_optional_step() {
local name="$1"
shift
local safe_name
safe_name="$(printf '%s' "$name" | tr ' /:' '___')"
local log="$RUN_DIR/${safe_name}.log"
set +e
(cd "$REPO_ROOT" && "$@") >"$log" 2>&1
local code=$?
set -e
if [[ "$code" -eq 0 ]]; then
record "$name" "通过" "$code" "$log"
else
record "$name" "警告" "$code" "$log"
fi
}
printf 'AIOS V2R1 Candidate 全量验收开始\n'
printf '仓库:%s\n' "$REPO_ROOT"
printf '结果目录:%s\n' "$RUN_DIR"
[[ -d "$REPO_ROOT" ]] || { echo "错误:仓库不存在" >&2; exit 2; }
DOCS_ARGS=(python3 tools/aios_v2_docs_code_check.py --repo "$REPO_ROOT")
if [[ -n "$BASE_REF" ]]; then
DOCS_ARGS+=(--base-ref "$BASE_REF")
fi
run_step "文档与代码匹配" "${DOCS_ARGS[@]}"
run_step "Python 语法编译" python3 -m compileall -q \
active-runtime/app/aios_v2 \
active-runtime/app/aios_openclaw \
active-runtime/app/aios_hermes
run_step "候选单元与集成测试" python3 -m unittest discover \
-s tests/aios_v2_candidate \
-p 'test_*.py' \
-v
run_step "Shell 脚本语法" bash -c '
set -Eeuo pipefail
while IFS= read -r -d "" path; do
bash -n "$path"
done < <(find deploy/aios-v2 -type f -name "*.sh" -print0)
'
run_step "文档 Git 冲突标记" bash -c '
set -Eeuo pipefail
if grep -RInE "^(<<<<<<<|=======|>>>>>>>)" docs/aios-v2; then
exit 1
fi
'
run_step "明文密钥基础扫描" python3 -c '
from pathlib import Path
import re
import sys
roots = [Path("active-runtime/app"), Path("deploy/aios-v2"), Path("docs/aios-v2"), Path("tasks")]
patterns = [
re.compile(r"(?i)(api[_-]?key|password|private[_-]?key|access[_-]?token)\s*[:=]\s*[\"\x27][^\"\x27\n]{12,}[\"\x27]"),
re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH )?PRIVATE KEY-----"),
]
violations = []
for root in roots:
if not root.exists():
continue
for path in root.rglob("*"):
if not path.is_file() or path.suffix in {".pyc", ".db", ".sqlite3"}:
continue
text = path.read_text(encoding="utf-8", errors="ignore")
if any(pattern.search(text) for pattern in patterns):
violations.append(str(path))
if violations:
print("疑似明文密钥文件:", *violations, sep="\n", file=sys.stderr)
raise SystemExit(1)
'
if command -v systemd-analyze >/dev/null 2>&1; then
run_optional_step "systemd 单元验证" systemd-analyze verify \
deploy/aios-v2/systemd/aios-v2.service
else
record "systemd 单元验证" "警告" "127" "未安装 systemd-analyze"
fi
if command -v docker >/dev/null 2>&1 && docker compose version >/dev/null 2>&1; then
run_optional_step "Docker Compose 配置验证" docker compose \
-f deploy/aios-v2/docker/compose.yaml config
else
record "Docker Compose 配置验证" "警告" "127" "未安装 Docker Compose"
fi
if [[ "$RUN_LIVE_HEALTHCHECK" == "1" ]]; then
run_step "在线健康检查" bash deploy/aios-v2/healthcheck/check.sh
else
record "在线健康检查" "警告" "0" "未启用 AIOS_RUN_LIVE_HEALTHCHECK=1"
fi
branch="$(git -C "$REPO_ROOT" branch --show-current 2>/dev/null || true)"
commit="$(git -C "$REPO_ROOT" rev-parse HEAD 2>/dev/null || true)"
dirty="$(git -C "$REPO_ROOT" status --porcelain=v1 2>/dev/null || true)"
python3 - "$SUMMARY" "$branch" "$commit" "$dirty" "$pass" "$failed" "$warnings" "${steps[@]}" <<'PY'
import json
import pathlib
import sys
from datetime import datetime, timezone
summary_path = pathlib.Path(sys.argv[1])
branch, commit, dirty = sys.argv[2:5]
passed, failed, warnings = map(int, sys.argv[5:8])
steps = []
for item in sys.argv[8:]:
name, status, code, log = item.split("|", 3)
steps.append({"name": name, "status": status, "exit_code": int(code), "log": log})
payload = {
"schema": "aios.v2.acceptance.v1",
"generated_at": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
"branch": branch or None,
"commit": commit or None,
"workspace_dirty": bool(dirty),
"passed": passed,
"failed": failed,
"warnings": warnings,
"steps": steps,
"final_status": "passed" if failed == 0 else "failed",
}
summary_path.write_text(json.dumps(payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
print(json.dumps(payload, ensure_ascii=False, indent=2))
PY
printf '验收结果:通过 %s,失败 %s,警告 %s\n' "$pass" "$failed" "$warnings"
printf '证据:%s\n' "$SUMMARY"
if [[ "$failed" -ne 0 ]]; then
exit 1
fi
+24
View File
@@ -0,0 +1,24 @@
FROM python:3.12-slim
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
PYTHONPATH=/opt/aios/app \
AIOS_V2_HOST=0.0.0.0 \
AIOS_V2_PORT=18920 \
AIOS_V2_STATE_DIR=/var/lib/aios-v2
RUN groupadd --system --gid 12001 aios \
&& useradd --system --uid 12001 --gid aios --home-dir /nonexistent --shell /usr/sbin/nologin aios \
&& install -d -o aios -g aios -m 0750 /opt/aios/app /var/lib/aios-v2 \
&& python3 -m pip install --no-cache-dir 'cryptography>=42'
WORKDIR /opt/aios/app
COPY --chown=aios:aios active-runtime/app/ /opt/aios/app/
USER aios:aios
EXPOSE 18920
HEALTHCHECK --interval=15s --timeout=5s --start-period=10s --retries=4 \
CMD python3 -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:18920/api/v2/health', timeout=3).read()"
CMD ["python3", "-m", "aios_v2.app"]
+44
View File
@@ -0,0 +1,44 @@
services:
aios-v2:
build:
context: ../../..
dockerfile: deploy/aios-v2/docker/Dockerfile
image: aios-v2:V2R1C0-candidate
init: true
restart: unless-stopped
ports:
- "127.0.0.1:${AIOS_V2_PORT:-18920}:18920"
environment:
AIOS_V2_HOST: 0.0.0.0
AIOS_V2_PORT: 18920
AIOS_V2_STATE_DIR: /var/lib/aios-v2
AIOS_OPENCLAW_URL: ${AIOS_OPENCLAW_URL:-}
AIOS_OPENCLAW_CREDENTIAL_REF: ${AIOS_OPENCLAW_CREDENTIAL_REF:-}
AIOS_OPENCLAW_SIGNING_MATERIAL_FILE: ${AIOS_OPENCLAW_SIGNING_MATERIAL_FILE:-}
AIOS_RELEASE_CHANNEL: candidate
AIOS_RELEASE_VERSION: V2R1C0-candidate
volumes:
- aios-v2-state:/var/lib/aios-v2
# Mount runtime signing material explicitly when OpenClaw is enabled.
# The host file must be mode 0600; never store it in this repository.
# - /etc/aios-v2/openclaw-signing-material:/run/secrets/openclaw-signing-material:ro
read_only: true
tmpfs:
- /tmp:rw,noexec,nosuid,nodev,size=64m
cap_drop:
- ALL
security_opt:
- no-new-privileges:true
healthcheck:
test:
- CMD
- python3
- -c
- "import urllib.request; urllib.request.urlopen('http://127.0.0.1:18920/api/v2/health', timeout=3).read()"
interval: 15s
timeout: 5s
retries: 4
start_period: 10s
volumes:
aios-v2-state:
+45
View File
@@ -0,0 +1,45 @@
# AIOS V2R1 Candidate 环境模板
# 正式环境禁止保存明文 Secret。
# Provenance/OpenClaw 私钥只用于签发端,不进入应用容器或 Git。
# Runtime
AIOS_V2_HOST=127.0.0.1
AIOS_V2_PORT=18920
AIOS_V2_STATE_DIR=/var/lib/aios-v2
# OpenClaw Ed25519 Command v2
AIOS_OPENCLAW_URL=
AIOS_OPENCLAW_CREDENTIAL_REF=
AIOS_OPENCLAW_SIGNING_MATERIAL_FILE=/run/credentials/aios-v2.service/openclaw-command-private-key
AIOS_OPENCLAW_SIGNING_KEY_ID=openclaw-v2r1-candidate-ed25519
# Parent Workflow Provenance
AIOS_REQUIRE_RUN_PROVENANCE=true
AIOS_PROVENANCE_PUBLIC_KEY_FILE=/etc/aios-v2/provenance/public-key.pem
AIOS_PROVENANCE_KEY_ID=openclaw-v2r1-candidate-ed25519
AIOS_PROVENANCE_STORE_FILE=/var/lib/aios-v2/run-provenance.sqlite3
AIOS_PROVENANCE_RECEIPT_DIR=/var/lib/aios-v2/provenance-receipts
# Least-privilege child Grants: production requires all seven IDs.
AIOS_PROVENANCE_GRANT_CODE_CHANGE_ID=
AIOS_PROVENANCE_GRANT_GIT_ID=
AIOS_PROVENANCE_GRANT_DEPLOYMENT_ID=
AIOS_PROVENANCE_GRANT_RUNTIME_ID=
AIOS_PROVENANCE_GRANT_EVIDENCE_ID=
AIOS_PROVENANCE_GRANT_ROLLBACK_ID=
AIOS_PROVENANCE_GRANT_AUDIT_ID=
# Per-operation context. Deployment/rollback wrappers populate these from the
# approved task execution context; do not hard-code shared production values.
AIOS_PROVENANCE_ID=
AIOS_RUN_ID=
AIOS_TENANT_ID=
AIOS_TASK_ID=
AIOS_AGENT_ID=
AIOS_PRINCIPAL_ID=
# 禁止:
# AIOS_PROVENANCE_PRIVATE_KEY_FILE
# AIOS_OPENCLAW_TOKEN
# API_KEY=value
# PASSWORD=value
+86
View File
@@ -0,0 +1,86 @@
#!/usr/bin/env bash
set -Eeuo pipefail
BASE_URL="${AIOS_V2_BASE_URL:-http://127.0.0.1:18920}"
STATE_DIR="${AIOS_V2_STATE_DIR:-/var/lib/aios-v2}"
CONTROLLER_WT="${AIOS_GITOPS_CONTROLLER_WORKTREE:-/data/aios-gitops/worktrees/controller}"
SERVICE="${AIOS_V2_SERVICE:-aios-v2}"
fail() {
echo "FAIL: $*" >&2
exit 1
}
pass() {
echo "PASS: $*"
}
command -v python3 >/dev/null || fail "python3 not installed"
if command -v systemctl >/dev/null && systemctl list-unit-files "$SERVICE.service" >/dev/null 2>&1; then
systemctl is-active --quiet "$SERVICE" || fail "$SERVICE is not active"
pass "$SERVICE is active"
fi
python3 - "$BASE_URL" <<'PY'
import json
import sys
import urllib.request
base_url = sys.argv[1].rstrip("/")
with urllib.request.urlopen(f"{base_url}/api/v2/health", timeout=5) as response:
payload = json.loads(response.read().decode("utf-8"))
if payload.get("status") not in {"ok", "healthy", "ready"}:
raise SystemExit(f"unexpected health payload: {payload}")
print(f"PASS: HTTP health status={payload.get('status')}")
PY
[[ -d "$STATE_DIR" ]] || fail "state directory missing: $STATE_DIR"
[[ -w "$STATE_DIR" ]] || fail "state directory not writable: $STATE_DIR"
pass "state directory writable"
if [[ -e "$STATE_DIR/control-plane.sqlite3" ]]; then
python3 - "$STATE_DIR/control-plane.sqlite3" <<'PY'
import sqlite3
import sys
path = sys.argv[1]
connection = sqlite3.connect(f"file:{path}?mode=ro", uri=True, timeout=5)
try:
row = connection.execute("PRAGMA quick_check").fetchone()
finally:
connection.close()
if not row or row[0] != "ok":
raise SystemExit(f"SQLite quick_check failed: {row}")
print("PASS: SQLite quick_check=ok")
PY
else
echo "WARN: control-plane.sqlite3 not created yet"
fi
if [[ -d "$CONTROLLER_WT" ]] && git -C "$CONTROLLER_WT" rev-parse --is-inside-work-tree >/dev/null 2>&1; then
branch="$(git -C "$CONTROLLER_WT" branch --show-current)"
dirty="$(git -C "$CONTROLLER_WT" status --porcelain=v1)"
[[ -z "$branch" ]] || fail "GitOps controller attached to branch: $branch"
[[ -z "$dirty" ]] || fail "GitOps controller workspace is dirty"
pass "GitOps controller detached and clean"
fi
python3 - "$STATE_DIR/executions" <<'PY'
import json
import pathlib
import sys
root = pathlib.Path(sys.argv[1])
if not root.exists():
print("WARN: execution evidence directory not created yet")
raise SystemExit(0)
for path in root.glob("*/*.json"):
value = json.loads(path.read_text(encoding="utf-8"))
for key in ("execution_id", "tenant_id", "task_id", "executor", "status"):
if not value.get(key):
raise SystemExit(f"invalid execution evidence {path}: missing {key}")
print("PASS: execution evidence files valid")
PY
pass "AIOS V2 candidate healthcheck complete"
@@ -0,0 +1,39 @@
#!/usr/bin/env bash
set -Eeuo pipefail
OPERATION_PATH="${1:-}"
OPERATION_NAME="${2:-}"
REQUEST_FILE="${3:-}"
fail() {
echo "PROVENANCE_DENIED: $*" >&2
exit 1
}
[[ -n "$OPERATION_PATH" ]] || fail "usage: $0 <deployment|rollback|audit|code_change|runtime_execute|evidence_write> <operation> <request-json-file>"
[[ -n "$OPERATION_NAME" ]] || fail "operation name is required"
[[ -n "$REQUEST_FILE" && -f "$REQUEST_FILE" ]] || fail "request JSON file is required"
: "${AIOS_PROVENANCE_PUBLIC_KEY_FILE:?missing AIOS_PROVENANCE_PUBLIC_KEY_FILE}"
: "${AIOS_PROVENANCE_KEY_ID:?missing AIOS_PROVENANCE_KEY_ID}"
: "${AIOS_PROVENANCE_STORE_FILE:?missing AIOS_PROVENANCE_STORE_FILE}"
: "${AIOS_PROVENANCE_RECEIPT_DIR:?missing AIOS_PROVENANCE_RECEIPT_DIR}"
: "${AIOS_PROVENANCE_ID:?missing AIOS_PROVENANCE_ID}"
: "${AIOS_RUN_ID:?missing AIOS_RUN_ID}"
: "${AIOS_TENANT_ID:?missing AIOS_TENANT_ID}"
: "${AIOS_TASK_ID:?missing AIOS_TASK_ID}"
: "${AIOS_AGENT_ID:?missing AIOS_AGENT_ID}"
: "${AIOS_PRINCIPAL_ID:?missing AIOS_PRINCIPAL_ID}"
PYTHONPATH_VALUE="${AIOS_V2_PYTHONPATH:-/opt/aios/current/active-runtime/app}"
PYTHONPATH="$PYTHONPATH_VALUE${PYTHONPATH:+:$PYTHONPATH}" \
python3 -m aios_v2.provenance_cli authorize \
--context-from-env \
--store-file "$AIOS_PROVENANCE_STORE_FILE" \
--public-key-file "$AIOS_PROVENANCE_PUBLIC_KEY_FILE" \
--key-id "$AIOS_PROVENANCE_KEY_ID" \
--receipt-dir "$AIOS_PROVENANCE_RECEIPT_DIR" \
--path "$OPERATION_PATH" \
--operation "$OPERATION_NAME" \
--request-file "$REQUEST_FILE"
+98
View File
@@ -0,0 +1,98 @@
#!/usr/bin/env bash
set -Eeuo pipefail
SERVICE="${AIOS_V2_SERVICE:-aios-v2}"
RELEASE_ROOT="${AIOS_V2_RELEASE_ROOT:-/opt/aios/releases}"
CURRENT_LINK="${AIOS_V2_CURRENT_LINK:-/opt/aios/current}"
STATE_DIR="${AIOS_V2_STATE_DIR:-/var/lib/aios-v2}"
BACKUP_ROOT="${AIOS_V2_BACKUP_ROOT:-/var/backups/aios-v2}"
TARGET_RELEASE="${1:-}"
RESTORE_STATE="${AIOS_V2_RESTORE_STATE:-0}"
HEALTH_RETRIES="${AIOS_V2_ROLLBACK_HEALTH_RETRIES:-30}"
HEALTH_RETRY_DELAY="${AIOS_V2_ROLLBACK_HEALTH_RETRY_DELAY:-1}"
fail() {
echo "ERROR: $*" >&2
exit 1
}
run_healthcheck() {
local release="$1"
local attempt
for ((attempt = 1; attempt <= HEALTH_RETRIES; attempt++)); do
if AIOS_V2_SERVICE="$SERVICE" \
AIOS_V2_STATE_DIR="$STATE_DIR" \
"$release/deploy/aios-v2/healthcheck/check.sh"; then
return 0
fi
[[ "$attempt" -lt "$HEALTH_RETRIES" ]] && sleep "$HEALTH_RETRY_DELAY"
done
return 1
}
[[ "${EUID}" -eq 0 ]] || fail "rollback must run as root"
[[ -n "$TARGET_RELEASE" ]] || fail "usage: $0 <release-name-or-absolute-path>"
if [[ "$TARGET_RELEASE" = /* ]]; then
TARGET_PATH="$(readlink -f "$TARGET_RELEASE")"
else
[[ "$TARGET_RELEASE" != *"/"* && "$TARGET_RELEASE" != "." && "$TARGET_RELEASE" != ".." ]] \
|| fail "invalid release name"
TARGET_PATH="$(readlink -f "$RELEASE_ROOT/$TARGET_RELEASE")"
fi
[[ -d "$TARGET_PATH/active-runtime/app" ]] || fail "target release is invalid: $TARGET_PATH"
[[ -f "$TARGET_PATH/deploy/aios-v2/healthcheck/check.sh" ]] \
|| fail "target release has no healthcheck"
PREVIOUS_PATH=""
if [[ -L "$CURRENT_LINK" ]]; then
PREVIOUS_PATH="$(readlink -f "$CURRENT_LINK")"
fi
STAMP="$(date -u +%Y%m%dT%H%M%SZ)"
BACKUP_DIR="$BACKUP_ROOT/rollback-$STAMP"
install -d -m 0750 "$BACKUP_DIR"
if [[ -d "$STATE_DIR" ]]; then
tar --xattrs --acls -C "$(dirname "$STATE_DIR")" \
-czf "$BACKUP_DIR/state-before-rollback.tar.gz" \
"$(basename "$STATE_DIR")"
fi
printf '%s\n' "$PREVIOUS_PATH" > "$BACKUP_DIR/previous-release.txt"
printf '%s\n' "$TARGET_PATH" > "$BACKUP_DIR/target-release.txt"
systemctl stop "$SERVICE"
ln -sfn "$TARGET_PATH" "${CURRENT_LINK}.next"
mv -Tf "${CURRENT_LINK}.next" "$CURRENT_LINK"
systemctl daemon-reload
systemctl start "$SERVICE"
if run_healthcheck "$TARGET_PATH"; then
echo "ROLLBACK_COMPLETE target=$TARGET_PATH backup=$BACKUP_DIR"
exit 0
fi
echo "Target release failed healthcheck; restoring previous release." >&2
systemctl stop "$SERVICE" || true
if [[ -n "$PREVIOUS_PATH" && -d "$PREVIOUS_PATH" ]]; then
ln -sfn "$PREVIOUS_PATH" "${CURRENT_LINK}.previous"
mv -Tf "${CURRENT_LINK}.previous" "$CURRENT_LINK"
fi
if [[ "$RESTORE_STATE" == "1" && -f "$BACKUP_DIR/state-before-rollback.tar.gz" ]]; then
rm -rf "$STATE_DIR"
tar --xattrs --acls -C "$(dirname "$STATE_DIR")" \
-xzf "$BACKUP_DIR/state-before-rollback.tar.gz"
fi
systemctl daemon-reload
systemctl start "$SERVICE" || true
if [[ -n "$PREVIOUS_PATH" && -x "$PREVIOUS_PATH/deploy/aios-v2/healthcheck/check.sh" ]]; then
run_healthcheck "$PREVIOUS_PATH" || true
fi
fail "rollback target failed; previous release restored; evidence=$BACKUP_DIR"
+37
View File
@@ -0,0 +1,37 @@
[Unit]
Description=AIOS V2 Control Plane Candidate
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=aios
Group=aios
WorkingDirectory=/opt/aios/current/active-runtime/app
EnvironmentFile=-/etc/aios-v2/aios-v2.env
Environment=PYTHONUNBUFFERED=1
ExecStart=/usr/bin/python3 -m aios_v2.app
Restart=on-failure
RestartSec=3
TimeoutStartSec=30
TimeoutStopSec=30
KillSignal=SIGTERM
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectControlGroups=true
RestrictSUIDSGID=true
RestrictRealtime=true
LockPersonality=true
MemoryDenyWriteExecute=true
ReadWritePaths=/var/lib/aios-v2
StateDirectory=aios-v2
StateDirectoryMode=0750
UMask=0027
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,30 @@
# AIOS V2R1C2 Unified Portal Candidate
# Install as /etc/aios-v2/aios-v2r1c2-portal.env with mode 0640.
# Do not place secret values in this file. Use secret references only.
AIOS_V2_HOST=127.0.0.1
AIOS_V2_PORT=18921
AIOS_V2_STATE_DIR=/var/lib/aios-v2r1c2-portal
AIOS_PROVENANCE_STORE_FILE=/var/lib/aios-v2r1c2-portal/run-provenance.sqlite3
AIOS_EXTERNAL_TASK_STORE_FILE=/var/lib/aios-v2r1c2-portal/external-task-truth.sqlite3
AIOS_EXECUTOR_CATALOG_FILE=/var/lib/aios-v2r1c2-portal/executor-catalog.json
AIOS_EXECUTION_PLAN_FILES=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-RELEASE.json:/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-TAKEOVER.json
AIOS_EXECUTION_PLAN_FILE=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-TAKEOVER.json
AIOS_RELEASE_VERSION=V2R1C2-CANDIDATE
AIOS_TARGET_VERSION=V2R1C2
AIOS_BASELINE_VERSION=V2R1C1
AIOS_PREVIOUS_VERSION=V2R1C1
AIOS_RELEASE_STATUS=CANDIDATE_VALIDATION
AIOS_RELEASE_SOURCE_OID=REPLACE_WITH_EXACT_40_CHARACTER_GIT_OID
AIOS_RELEASE_OID=candidate-not-tagged
AIOS_RELEASE_TAG=NOT_CREATED
AIOS_RELEASE_EVIDENCE_SHA256=pending
AIOS_OPENCLAW_CONTRACT_VERSION=aios.openclaw.command.v2
AIOS_OPENCLAW_SIGNATURE_ALGORITHM=Ed25519
AIOS_OPENCLAW_PLUGIN_VERSION=2.1.0-rc.4
AIOS_OPENCLAW_SIGNING_KEY_ID=openclaw-v2r1-candidate-ed25519
# Runtime resolves this reference through its secret store.
AIOS_OWNER_WECHAT_TARGET_REF=AIOS_OWNER_WECHAT_TARGET_REF
@@ -0,0 +1,44 @@
[Unit]
Description=AIOS V2R1C2 Unified Portal Candidate
After=network-online.target
Wants=network-online.target
ConditionPathExists=/opt/aios-v2r1c2/active-runtime/app/aios_web/release_application.py
ConditionPathExists=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-RELEASE.json
ConditionPathExists=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-TAKEOVER.json
[Service]
Type=simple
User=aios
Group=aios
WorkingDirectory=/opt/aios-v2r1c2/active-runtime/app
EnvironmentFile=/etc/aios-v2/aios-v2r1c2-portal.env
Environment=PYTHONUNBUFFERED=1
Environment=PYTHONDONTWRITEBYTECODE=1
ExecStartPre=/usr/bin/test "$AIOS_V2_PORT" = "18921"
ExecStartPre=/usr/bin/test -n "$AIOS_RELEASE_SOURCE_OID"
ExecStartPre=/usr/bin/test "$AIOS_RELEASE_SOURCE_OID" != "candidate-not-tagged"
ExecStart=/usr/bin/python3 -m aios_web.release_application
Restart=on-failure
RestartSec=3
TimeoutStartSec=60
TimeoutStopSec=30
KillSignal=SIGTERM
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectControlGroups=true
RestrictSUIDSGID=true
RestrictRealtime=true
LockPersonality=true
MemoryDenyWriteExecute=true
ReadWritePaths=/var/lib/aios-v2r1c2-portal
StateDirectory=aios-v2r1c2-portal
StateDirectoryMode=0750
UMask=0027
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
@@ -1,4 +0,0 @@
AIOS_V2_VERSION=V2R1C6
AIOS_V2R1C6_PORT=18926
AIOS_GITOPS_WRITES_ENABLED=false
AIOS_V2R1C6_PRODUCTION_DEPLOYED=false
@@ -1,30 +0,0 @@
[Unit]
Description=AIOS V2R1C6 candidate privacy service (not production-enabled)
After=network.target
[Service]
Type=simple
User=aios-v2r1c6
Group=aios-v2r1c6
WorkingDirectory=/opt/aios/v2r1c6
EnvironmentFile=-/etc/aios/aios-v2r1c6.env
Environment=AIOS_GITOPS_WRITES_ENABLED=false
Environment=AIOS_V2R1C6_PRODUCTION_DEPLOYED=false
ExecStart=/usr/bin/python3 /opt/aios/v2r1c6/active-runtime/app/v2r1c6_privacy_tools.py --serve --host 127.0.0.1 --port 18926
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
PrivateTmp=true
ProtectHome=true
ProtectSystem=strict
ProtectKernelLogs=true
ProtectKernelModules=true
ProtectKernelTunables=true
ProtectControlGroups=true
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
IPAddressDeny=any
IPAddressAllow=localhost
UMask=0077
[Install]
WantedBy=multi-user.target
-17
View File
@@ -1,17 +0,0 @@
{
"schema": "aios.v2r1c6.candidate-rollback.v1",
"candidate_version": "V2R1C6",
"rollback_version": "V2R1C5",
"previous_tag": "V2R1C5",
"previous_tag_oid": "9e65bd59baea392294c0f253046d3ab116f63145",
"previous_target_oid": "aa60e891547abd7e215af7cf2bf3f21fd23541da",
"baseline_unchanged": true,
"tag_rewrite": false,
"force_push": false,
"production_deploy_authorized": false,
"rollback_steps": [
"stop aios-v2r1c6-production.service if a separately approved deployment exists",
"restore the V2R1C5 production artifact and service configuration",
"verify V2R1C5 tag and Baseline before any restart"
]
}
@@ -1,24 +0,0 @@
[Unit]
Description=AIOS manifest-driven release controller (validation only)
ConditionPathExists=/var/lib/aios-release/release-source-manifest.json
ConditionPathExists=/var/lib/aios-release/release-request.json
After=network-online.target
[Service]
Type=oneshot
User=aios-release
Group=aios-release
Environment=PYTHONPATH=/opt/aios/release-controller
Environment=AIOS_GITOPS_WRITES_ENABLED=false
Environment=AIOS_PRODUCTION_DEPLOYMENT_AUTHORIZED=false
ExecStart=/usr/bin/python3 -m aios_release_controller.cli validate-release /var/lib/aios-release/release-source-manifest.json /var/lib/aios-release/release-request.json
NoNewPrivileges=yes
PrivateTmp=yes
ProtectSystem=strict
ProtectHome=yes
ReadWritePaths=/var/lib/aios-release
CapabilityBoundingSet=
RestrictAddressFamilies=AF_UNIX
[Install]
WantedBy=multi-user.target
@@ -1,24 +0,0 @@
[Unit]
Description=AIOS governed Agent Pull Runner (example)
After=network.target
[Service]
Type=simple
User=aios-agent
Group=aios-agent
UMask=0077
ExecStart=/usr/bin/python3 -B /opt/aios-gitops/active-runtime/app/agent_pull_runner_cli.py --worker-id %H
NoNewPrivileges=true
PrivateTmp=true
PrivateDevices=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectControlGroups=true
RestrictSUIDSGID=true
RestrictAddressFamilies=AF_UNIX AF_INET
ReadWritePaths=/var/lib/aios-gitops/runtime/agent-pull-runner
Restart=on-failure
RestartSec=5
@@ -1,42 +0,0 @@
[Unit]
Description=AIOS Autonomous Release Candidate API (Dormant/Shadow Only)
After=network.target
ConditionPathExists=/opt/aios-autonomous-release-candidate/aios_autonomous_release_candidate
[Service]
Type=simple
User=aiman
Group=gitops
UMask=0077
WorkingDirectory=/opt/aios-autonomous-release-candidate
Environment=PYTHONDONTWRITEBYTECODE=1
Environment=PYTHONPATH=/opt/aios-autonomous-release-candidate
Environment=AIOS_TASK_PLANE_EXECUTION_ENABLED=false
Environment=AIOS_GITOPS_WRITES_ENABLED=false
Environment=AIOS_PRODUCTION_DEPLOYMENT_ENABLED=false
ExecStart=/usr/bin/python3 -m aios_autonomous_release_candidate.service --host 127.0.0.1 --port 19951 --state /var/lib/aios-autonomous-release-candidate/state.sqlite3
StateDirectory=aios-autonomous-release-candidate
RuntimeDirectory=aios-autonomous-release-candidate
NoNewPrivileges=true
PrivateTmp=true
PrivateDevices=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectKernelLogs=true
ProtectControlGroups=true
ProtectClock=true
ProtectHostname=true
LockPersonality=true
RestrictSUIDSGID=true
RestrictRealtime=true
MemoryDenyWriteExecute=true
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
IPAddressDeny=any
IPAddressAllow=localhost
ReadOnlyPaths=/opt/aios-autonomous-release-candidate
ReadWritePaths=/var/lib/aios-autonomous-release-candidate
[Install]
WantedBy=multi-user.target
@@ -1,51 +0,0 @@
[Unit]
Description=AIOS Autonomous Release Candidate Worker (Dormant/Shadow Only)
After=network.target
ConditionPathExists=/opt/aios-autonomous-release-candidate/aios_autonomous_release_candidate
[Service]
Type=simple
User=aiman
Group=gitops
UMask=0077
WorkingDirectory=/opt/aios-autonomous-release-candidate
Environment=PYTHONDONTWRITEBYTECODE=1
Environment=PYTHONPATH=/opt/aios-autonomous-release-candidate
Environment=AIOS_TASK_PLANE_EXECUTION_ENABLED=false
Environment=AIOS_GITOPS_WRITES_ENABLED=false
Environment=AIOS_PRODUCTION_DEPLOYMENT_ENABLED=false
Environment=AIOS_CANDIDATE_CONTROL_ENDPOINT=127.0.0.1:19951
Environment=AIOS_OPENCLAW_CREDENTIAL_REFERENCE=systemd-credential:openclaw-gateway-candidate
Environment=AIOS_CODEX_CREDENTIAL_REFERENCE=systemd-credential:codex-app-server-candidate
Environment=AIOS_NATIVE_CONTROL_CREDENTIAL_REFERENCE=systemd-credential:session-native-adapter-control-candidate
Environment=AIOS_GITEA_CREDENTIAL_REFERENCE=systemd-credential:gitea-admin-api-candidate
ImportCredential=openclaw-gateway-candidate
ImportCredential=codex-app-server-candidate
ImportCredential=session-native-adapter-control-candidate
ImportCredential=gitea-admin-api-candidate
ExecStart=/usr/bin/python3 -m aios_autonomous_release_candidate.worker_service --state-directory /var/lib/aios-autonomous-release-worker-candidate
StateDirectory=aios-autonomous-release-worker-candidate
RuntimeDirectory=aios-autonomous-release-worker-candidate
NoNewPrivileges=true
PrivateTmp=true
PrivateDevices=true
ProtectSystem=strict
ProtectHome=true
ProtectKernelTunables=true
ProtectKernelModules=true
ProtectKernelLogs=true
ProtectControlGroups=true
ProtectClock=true
ProtectHostname=true
LockPersonality=true
RestrictSUIDSGID=true
RestrictRealtime=true
MemoryDenyWriteExecute=true
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
IPAddressDeny=any
IPAddressAllow=localhost
ReadOnlyPaths=/opt/aios-autonomous-release-candidate
ReadWritePaths=/var/lib/aios-autonomous-release-worker-candidate
[Install]
WantedBy=multi-user.target

Some files were not shown because too many files have changed in this diff Show More