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
gitops-bot 875d41c310 Merge pull request 'fix(gitops): harden Codex worker systemd profile' (#19) from patch/isolated-writer-systemd-profile-hardening-20260725 into main 2026-07-25 11:13:31 +08:00
chatgpt-gitops-bot 870ac61dc2 fix(gitops): harden Codex worker systemd profile 2026-07-25 11:08:55 +08:00
gitops-bot 009f276699 Merge pull request 'fix(gitops): add exact-path service policy for isolated writer' (#18) from patch/isolated-writer-exact-path-policy-20260725 into main 2026-07-25 10:19:02 +08:00
chatgpt-gitops-bot 600c717e17 fix(gitops): add exact-path service policy for isolated writer 2026-07-25 10:16:43 +08:00
gitops-bot 02be6d28ed merge(gitops): add constrained writer token policy and atomic commit-file
Source: patch/isolated-writer-token-policy-v2-20260724
Source commit: b1e240dda3
Target base: df099420d2
Production runtime changes: not authorized
Tag/Baseline/Registry operations: not authorized
2026-07-24 23:36:25 +08:00
chatgpt-gitops-bot b1e240dda3 fix(gitops): reject atomic writer force fields 2026-07-24 23:06:22 +08:00
chatgpt-gitops-bot 2dfbe837f4 fix(gitops): bind writer runtime policy v2 artifacts 2026-07-24 23:01:40 +08:00
chatgpt-gitops-bot 80df1e0d87 test(gitops): close writer authz and recovery contract 2026-07-24 22:56:58 +08:00
chatgpt-gitops-bot 7ecf7cbfce feat(gitops): add idempotent atomic commit-file endpoint 2026-07-24 22:56:58 +08:00
chatgpt-gitops-bot bbada7c863 feat(gitops): add constrained writer token policy v2 2026-07-24 22:56:58 +08:00
gitops-bot df099420d2 Merge pull request 'feat(task-plane): add isolated readonly Codex worker policy' (#16) from patch/task-plane-codex-readonly-worker-20260724 into main 2026-07-24 21:51:12 +08:00
chatgpt-gitops-bot 2d802f3d51 feat(task-plane): add isolated readonly Codex worker policy 2026-07-24 21:31:08 +08:00
gitops-bot dd34dfaad2 Merge pull request 'fix(task-plane): authenticate shadow client and retire legacy writer' (#15) from patch/task-plane-shadow-rbac-client-20260724 into main 2026-07-24 20:25:17 +08:00
chatgpt-gitops-bot 346426b6ca fix(task-plane): authenticate shadow client and retire legacy writer 2026-07-24 19:51:16 +08:00
owner 967b90af91 merge(task-plane): add governed multi-agent shadow control plane
Source: patch/aios-agent-task-control-plane-20260724
Source commit: 2458fa5f28
Target base: a8e9786897
Production execution: disabled
Production deployment: not authorized
Production tag operations: not authorized
2026-07-24 13:57:01 +08:00
chatgpt-gitops-bot 2458fa5f28 test(task-plane): cover fail and recovery rollback 2026-07-24 12:50:57 +08:00
chatgpt-gitops-bot 40f2f3ebed fix(task-plane): default deny action rbac 2026-07-24 12:39:28 +08:00
chatgpt-gitops-bot 687112d86c test(task-plane): close shadow merge security contract 2026-07-24 12:32:59 +08:00
chatgpt-gitops-bot f0d1e8479b fix(task-plane): harden writer scheduling and classified tasks 2026-07-24 12:32:58 +08:00
chatgpt-gitops-bot 85b4610eb3 fix(task-plane): enforce worker ownership and recovery probes 2026-07-24 12:32:58 +08:00
chatgpt-gitops-bot a0b5160534 fix(task-plane): bind evidence and mutations atomically 2026-07-24 12:25:42 +08:00
chatgpt-gitops-bot cf57ef6bcc docs(task-plane): declare authenticated error contract 2026-07-24 11:29:00 +08:00
chatgpt-gitops-bot 958e49e2cf style(task-plane): satisfy diff whitespace check 2026-07-24 11:17:23 +08:00
chatgpt-gitops-bot 3f6cabd4ac fix(task-plane): fail closed identity and recovery boundaries 2026-07-24 11:13:30 +08:00
chatgpt-gitops-bot 146d2123a5 test(task-plane): add recovery and multi-agent acceptance 2026-07-24 11:02:15 +08:00
chatgpt-gitops-bot ecd4ee1cc9 feat(task-plane): add API OpenAPI and notifications 2026-07-24 11:02:14 +08:00
chatgpt-gitops-bot eaf6cd739f feat(task-plane): add delegation policy and evidence 2026-07-24 11:02:14 +08:00
chatgpt-gitops-bot d4276e2cf5 feat(task-plane): add OpenClaw Codex Hermes adapters 2026-07-24 11:02:13 +08:00
chatgpt-gitops-bot f7a04ccec6 feat(task-plane): add worker registry lease and heartbeat 2026-07-24 11:02:13 +08:00
chatgpt-gitops-bot 5cf628deca feat(task-plane): add durable task and event models 2026-07-24 11:02:12 +08:00
chatgpt-gitops-bot 9914ebc9d4 test(task-plane): record writer smoke acceptance 2026-07-24 10:20:57 +08:00
chatgpt-gitops-bot 39ffd23335 chore(task-plane): initialize dedicated writer session 2026-07-24 10:20:56 +08:00
AIOS Task Plane Writer 467015e3fc fix(gitops): bound secret token detection 2026-07-24 10:20:16 +08:00
AIOS Task Plane Writer cdefcc18dd fix(gitops): allow task-plane delivery roots 2026-07-24 10:14:18 +08:00
AIOS Task Plane Writer 1594ac9a18 fix(gitops): verify task-plane writer Gitea push 2026-07-24 10:12:10 +08:00
AIOS Task Plane Writer 0ba2cdb63d fix(gitops): harden task-plane writer bootstrap 2026-07-24 10:11:15 +08:00
gitops-bot a8e9786897 Merge pull request 'gitops: Silent Release execution readiness' (#13) from patch/silent-release-execution-readiness-20260724 into main 2026-07-24 03:12:55 +08:00
chatgpt-gitops-bot 58511395c1 feat(gitops): add persistent shadow acceptance worker 2026-07-24 03:06:20 +08:00
chatgpt-gitops-bot d23aafc04c fix(gitops): fail closed shadow startup and evidence logs 2026-07-24 02:56:09 +08:00
chatgpt-gitops-bot 312aeff1ab docs(gitops): add shadow controller delivery contract 2026-07-24 02:52:22 +08:00
chatgpt-gitops-bot 1673575b21 feat(gitops): harden silent release execution readiness 2026-07-24 02:52:22 +08:00
gitops-bot 8b97275ff7 merge(gitops): add shadow silent-release production contract
Source: patch/silent-release-controller-production-contract-20260724
Source commit: 578f0a7e28
Target base: 238742150b
Production execution: disabled
Production deployment: not authorized
Production tag operations: not authorized
2026-07-24 01:47:51 +08:00
chatgpt-gitops-bot 578f0a7e28 fix(gitops): close trusted builder and finalization wiring 2026-07-24 01:25:24 +08:00
chatgpt-gitops-bot 9cc04bf146 test(gitops): close silent release production contract 2026-07-24 01:12:22 +08:00
chatgpt-gitops-bot e0b48dae24 feat(gitops): wire durable one-approval release orchestrator 2026-07-24 01:04:51 +08:00
chatgpt-gitops-bot 9893652270 fix(gitops): bind signed approval to exact release plan 2026-07-24 00:56:58 +08:00
chatgpt-gitops-bot 57234854f7 fix(gitops): add tamper-evident saga and exclusive capability claims 2026-07-24 00:51:00 +08:00
chatgpt-gitops-bot ccd64610b0 test(gitops): close one-approval silent-release acceptance 2026-07-24 00:26:57 +08:00
chatgpt-gitops-bot bad1120d6d feat(gitops): integrate silent-release shadow control plane 2026-07-24 00:26:57 +08:00
chatgpt-gitops-bot c8d2386677 feat(gitops): harden deployment and release finalization controllers 2026-07-24 00:25:57 +08:00
chatgpt-gitops-bot 08897d3968 feat(gitops): add durable release saga and capability ledger 2026-07-24 00:25:57 +08:00
chatgpt-gitops-bot 8497848120 feat(gitops): add signed release-plan approval trust model 2026-07-24 00:25:57 +08:00
chatgpt-gitops-bot dad45ab32b feat(gitops): add silent release controller 2026-07-23 22:49:54 +08:00
gitops-bot 238742150b Merge pull request 'merge(gitops): bind runtime APIs to authoritative repository' (#11) from patch/runtime-authoritative-git-context-20260723 into main 2026-07-23 20:35:05 +08:00
chatgpt-gitops-bot 04865315a3 fix-gitops-bind-diff-and-publisher-to-authoritative-repository 2026-07-23 19:50:28 +08:00
chatgpt-gitops-bot 8e72dc22d6 fix-gitops-authoritative-cli-publication 2026-07-23 19:04:41 +08:00
chatgpt-gitops-bot 79ac5abac2 fix(gitops): bind runtime reads to authoritative repository 2026-07-23 18:51:53 +08:00
gitops-bot 655c69fc4b merge(gitops): enforce fail-closed Gitea tag publication atomicity
Source: patch/gitea-tag-publication-atomicity-20260723
Source commit: 63e0b8e705
Target base: b739fbb5ec
Production deployment: not authorized
Production tag operations: not authorized
2026-07-23 16:26:45 +08:00
ChatGPT Release Governance 63e0b8e705 chore(gitops): regenerate atomicity delivery manifest 2026-07-23 16:06:26 +08:00
ChatGPT Release Governance edfad05d57 fix(gitops): align publication state contract 2026-07-23 16:05:00 +08:00
ChatGPT Release Governance e40c05779c fix-gitops-reject-publication-state-path-traversal 2026-07-23 14:57:07 +08:00
ChatGPT Release Governance a3edc628a9 fix-serialize-duplicate-tag-publications 2026-07-23 14:38:27 +08:00
ChatGPT Release Governance f4b6ac8609 test-reject-secrets-in-incident-record 2026-07-23 14:36:27 +08:00
ChatGPT Release Governance 83ab67f7e1 fix-git-process-configured-gitea-remote 2026-07-23 14:15:27 +08:00
ChatGPT Release Governance 27a0ae126b fix-gitops-close-tag-publication-governance-gaps 2026-07-23 14:11:23 +08:00
ChatGPT Release Governance 54093d1543 chore(gitops): verify isolated writer branch 2026-07-23 12:59:13 +08:00
Codex GitOps Repair 3196d91b12 fix(gitops): preserve existing isolated branches 2026-07-23 12:58:32 +08:00
Codex GitOps Repair 3812e1ab01 fix(gitops): make Gitea tag publication fail closed 2026-07-23 12:57:41 +08:00
ChatGPT Release Governance fc0b9f29bf chore(gitops): create isolated gitea tag atomicity patch 2026-07-23 12:43:25 +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 b739fbb5ec merge-V2R1C2-documentation-closure 2026-07-22 09:53:12 +08:00
ChatGPT Release Governance 02658d2329 clarify-synthetic-wechat-and-evidence-index 2026-07-22 09:52:56 +08:00
ChatGPT Release Governance 75efdef2d2 merge-V2R1C2-production-baseline 2026-07-22 09:48:07 +08:00
ChatGPT Release Governance 3584628cfe finalize-V2R1C2-production-registry 2026-07-22 09:45:10 +08:00
ChatGPT Release Governance 181dc54b9f merge-V2R1C2-transactional-acceptance-wrapper 2026-07-22 09:40:29 +08:00
ChatGPT Release Governance ed7adc6c23 add-transactional-production-acceptance-wrapper 2026-07-22 09:40:11 +08:00
ChatGPT Release Governance 6e3a8ac11a merge-V2R1C2-prepare-readiness-fix 2026-07-22 09:37:03 +08:00
ChatGPT Release Governance dd352a79d1 wait-for-candidate-readiness-after-state-copy 2026-07-22 09:36:48 +08:00
ChatGPT Release Governance abe17f4aec merge-V2R1C2-production-assets 2026-07-22 09:35:25 +08:00
ChatGPT Release Governance 6d61929055 harden-V2R1C2-state-copy-and-final-gates 2026-07-22 09:35:04 +08:00
ChatGPT Release Governance c4f9c8a5ca add-V2R1C2-production-switch-and-rollback 2026-07-22 09:29:12 +08:00
ChatGPT Release Governance 9975453f50 merge-V2R1C2-tag-action-fix 2026-07-22 09:23:24 +08:00
ChatGPT Release Governance 26d81a9f34 merge-V2R1C2-registry 2026-07-22 09:22:33 +08:00
ChatGPT Release Governance af2a1f39bc register-V2R1C2-tagged-candidate 2026-07-22 09:19:48 +08:00
ChatGPT Release Governance 151b57100f fix(gitops): bind release tags to approved target oid 2026-07-22 09:07:11 +08:00
ChatGPT Release Governance aaf9a2c73f chore(chatgpt): record nl plan unknown 2026-07-22 08:46:25 +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
ChatGPT Release Governance a281bfeacd merge(governance): reconcile V2R1C1 Registry with Gitea main 2026-07-21 22:29:06 +08:00
ChatGPT Release Governance 5894142682 merge(governance): register V2R1C1 central baseline 2026-07-21 22:26:23 +08:00
ChatGPT Release Governance 602cc9ee28 docs(release): record V2R1C1 baseline closure evidence 2026-07-21 22:24:40 +08:00
ChatGPT Release Governance 6dbd5cbe07 chore(baseline): advance central baseline to V2R1C1 2026-07-21 22:18:40 +08:00
ChatGPT Release Governance a56caf46f6 chore(release): register V2R1C1 version manifest 2026-07-21 22:18:40 +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
openclaw 41e21ff5fe result(openclaw): B3 evidence hardening completed
See result/openclaw/v2r1-personal-weixin-b3-evidence-hardening-20260716T133000UTC8
for the result branch containing the implementation.
2026-07-16 15:39:19 +08:00
openclaw b05eb1babe task(codex): execute isolated worktree migration 20260715T001652UTC8 2026-07-15 00:17:28 +08:00
openclaw a8581699f2 task(openclaw): migrate GitOps to isolated worktrees 20260714T233742UTC8 2026-07-14 23:32:52 +08:00
openclaw cc9cada5df feat(gitops): add unified systemd runtime identity drop-in 2026-07-14 23:32:18 +08:00
openclaw dbed29c8c7 feat(gitops): add task environment preflight 2026-07-14 23:32:12 +08:00
openclaw 24f7e4ecc3 feat(gitops): add per-task worktree lifecycle script 2026-07-14 23:31:59 +08:00
openclaw b588bf8fb2 feat(gitops): add isolated worktree bootstrap script 2026-07-14 23:31:43 +08:00
openclaw f300033138 fix(gitops): correct default ACL runtime user 2026-07-14 23:31:32 +08:00
openclaw 7308c9c0c1 feat(gitops): add isolated worktree governance policy 2026-07-14 23:31:21 +08:00
openclaw 48290bd620 chore(gitops): start isolated worktree and unified identity governance 2026-07-14 23:30:07 +08:00
openclaw 3cf9958cb9 integrate(gate1): replay accepted clean-room evidence onto current main 2026-07-14 01:33:53 +08:00
openclaw 6b70a33080 fix(weixin): resolve outbound quotes by exact create time 2026-07-12 21:41:10 +08:00
openclaw 8d23692320 fix(weixin): preserve exact server message ids 2026-07-12 19:58:26 +08:00
openclaw 33d3947da6 fix(weixin): resolve quotes from exact message id cache 2026-07-12 17:09:33 +08:00
openclaw 806163b8ba docs(weixin): record visible quote parser release 2026-07-12 15:55:38 +08:00
openclaw 13c2a18286 fix(weixin): resolve visible quoted text summaries 2026-07-12 15:50:03 +08:00
openclaw b8f10951ea docs(weixin): record owner quoted text acceptance 2026-07-12 14:11:27 +08:00
openclaw 2fcf0879c6 docs(weixin): record quoted text fail-closed release 2026-07-12 13:46:14 +08:00
openclaw 1136b4186d fix(weixin): fail closed on unavailable quoted text 2026-07-12 13:42:32 +08:00
openclaw cca73ad52f docs(weixin): design quoted text fail-closed handling 2026-07-12 13:42:32 +08:00
openclaw 424bf36c03 Merge remote-tracking branch 'origin/audit' 2026-07-12 12:57:36 +08:00
Steel Dan (AIOS) 9eb00da0c4 docs(weixin): record mainline production release 2026-07-12 02:21:21 +08:00
Steel Dan (AIOS) 9269e81997 docs(weixin): record quoted text reference fix 2026-07-12 01:18:25 +08:00
Steel Dan (AIOS) 6642820aa0 fix(weixin): ignore unconfirmed text references 2026-07-12 01:18:25 +08:00
Steel Dan (AIOS) 8374c6b1c7 docs(weixin): update confirmed image reference recovery 2026-07-12 01:18:25 +08:00
Steel Dan (AIOS) c8a3251834 fix(weixin): require confirmed image reference context 2026-07-12 01:18:25 +08:00
Steel Dan (AIOS) 2418f56273 docs(weixin): record text cache isolation recovery 2026-07-12 01:18:11 +08:00
Steel Dan (AIOS) 297582941f fix(weixin): add process-only runtime patch mode 2026-07-12 01:18:11 +08:00
Steel Dan (AIOS) 958a61cbc4 fix(weixin): isolate text from stale image cache 2026-07-12 01:18:11 +08:00
V1R4C6 Deployment Audit 3096212919 audit: record V1R4C6 production deployment blocker 2026-07-12 00:57:05 +08:00
openclaw aa2b091966 start V1R4C6 production deployment and verification 2026-07-11 21:10:51 +08:00
gito 1a9cb9095e Merge pull request 'reconcile(v1r4c6): finalize baseline metadata — previous_baseline V1R4C5, git e204a90' (#9) from reconcile/v1r4c6-baseline-finalize-20260711 into main 2026-07-11 20:55:54 +08:00
openclaw 0312159168 feat(reconcile): write V1R4C6 baseline metadata — previous_baseline V1R4C5, git e204a90 2026-07-11 20:54:46 +08:00
openclaw e204a90398 docs: baseline V1R4C6 promotion 2026-07-11 20:47:44 +08:00
openclaw d8cf6058e9 docs: promote VERSION V1R4C3 -> V1R4C6 ahead of main promotion 2026-07-11 20:47:28 +08:00
openclaw 2aefc19e3d authorize OpenClaw to execute V1R4C6 merge tests deploy pipeline 2026-07-11 20:41:31 +08:00
gito 28a430066f Merge pull request 'V1R4C6: merge candidate → main (release control artifacts)' (#8) from candidate/v1r4c6-integration-main-20260711 into main 2026-07-11 19:30:58 +08:00
openclaw 1013aef461 Merge branch 'release/v1r4c6-admin-search-agent-integration-20260711' into candidate/v1r4c6-integration-main-20260711
Resolve merge conflicts per V1R4C6 release control merge:

- baseline/current.json: keep feature branch version (updates to V1R4C5,
  adds constraints block). This was the intended runtime state that main
  was missing after V1R4C5 backfill (PR #7). Feature branch correctly has
  the V1R4C5 state; main still had V1R4C3.

- versions/V1R4C5.json: keep main version (complete fields with codename,
  tag_ref, tag_object, constraints, promoted_at/by). Feature branch had an
  older copy lacking these fields.

- docs/releases/V1R4C6-acceptance-evidence.md: keep main version (blank
  'NOT RUN' status). Feature branch had draft content.

- docs/releases/V1R4C6-release-gate-status.md: keep main version (blank
  'NOT RUN' status). Feature branch had draft content.
2026-07-11 19:29:47 +08:00
gito bb3210d74f Merge pull request 'docs: update V1R4C6 metadata to NOT RUN after control artifacts merge' (#7) from reconcile/v1r4c6-gate-status-notrun-docs-20260711 into main 2026-07-11 17:07:03 +08:00
openclaw 745395e93b docs: update V1R4C6 gate status, acceptance checklist, and acceptance evidence to NOT RUN
All engineering gates remain pending. This updates the release documents
to reflect the current integration-pending status after PR #6 merged.
2026-07-11 17:06:31 +08:00
gito ae49bf0fa3 Merge pull request 'reconcile: merge V1R4C6 release candidate into main' (#6) from candidate/v1r4c6-merge-to-main-20260711 into main 2026-07-11 16:45:28 +08:00
openclaw 8410cd895e reconcile: merge V1R4C6 release candidate into main
V1R4C6 merge candidate (squashed).
Contains 10 files, ~1440 lines added across:
- docs/releases/ (6 files: checklist, evidence, blocker, resume, merge-matrix, gate-status)
- ops/openclaw/ (2 files: integrate-deploy-verify, run-to-owner-gate-wechat)
- patches/ (1 file: branch patch)
- versions/ (1 file: V1R4C6.json)

Task: admin workbench, SR-03 Search Gateway, Agent Platform Integration
Baseline: V1R4C5
V1R4C5 tag semantics:
- tag refs/tags/V1R4C5 target d457ac3: immutable release snapshot
- baseline git a32c76a: runtime baseline promotion commit
No tag creation, baseline promotion, or memory search activation in this merge.
2026-07-11 16:34:03 +08:00
gito dc1642c2e8 Merge pull request 'reconcile: V1R4C5 baseline metadata (current.json + V1R4C5.json)' (#5) from reconcile/v1r4c5-baseline-metadata-20260711 into main 2026-07-11 13:48:30 +08:00
openclaw c75b865710 reconcile: update baseline registry to V1R4C5 and create V1R4C5 version metadata
Root cause:
The V1R4C5 baseline promotion commit (a32c76a) was made on a feature branch
that was never merged to main. As a result, both baseline/current.json and
versions/V1R4C5.json on main still reflect V1R4C3 state. Runtime
getBaseline() continues to return V1R4C3 with commit f5435e3.

Changes:
- baseline/current.json: update current_baseline -> V1R4C5, git ->
  a32c76a3c1 (the actual promotion commit),
  add constraints from the original promotion
- versions/V1R4C5.json: create the missing version metadata file with status
  active-baseline, referencing V1R4C5 tag (object ac9bdac...)

Why this does not affect V1R4C5 release content:
- V1R4C5 release documents (docs/releases/*.md) are untouched
- V1R4C5 tag is unchanged and not moved
- No V1R4C6 functionality introduced
- No memory search or vector index enabled

Rollback method:
  git revert <this commit hash>
  # Or restore baseline/current.json from V1R4C3 content:
  # git checkout main~1 baseline/current.json
  # And delete versions/V1R4C5.json:
  # git rm versions/V1R4C5.json
  # Then commit the revert

Constraints honored:
  - No direct writes to main (using PR)
  - No force push
  - V1R4C5 tag not moved/rebuild
  - No V1R4C6 content
  - Memory search remains disabled
2026-07-11 13:46:13 +08:00
gito e992b624e0 V1R4C5 → main: backfill release docs (acceptance evidence + owner approval) 2026-07-11 13:37:58 +08:00
openclaw c60e4cd02c reconcile: backfill V1R4C5 release documents (acceptance evidence + final owner approval) for main merge
Source: V1R4C5 tag based on unique publication commit a32c76a
- docs/releases/V1R4C5-acceptance-evidence.md (from V1R4C5 tag)
- docs/releases/V1R4C5-final-owner-approval.md (from V1R4C5 tag)

Constraints honored:
- Not writing directly to main
- No V1R4C6 content introduced
- Memory search remains disabled per owner approval

Generated merge candidate branch: reconcile/v1r4c5-release-to-main-20260711
2026-07-11 13:36:18 +08:00
openclaw 4b2996ca9f release: resume V1R4C6 after scoped WeChat notification verification 2026-07-11 07:47:05 +08:00
openclaw 086076b74f ops: direct OpenClaw to complete V1R4C6 and request owner approval via WeChat 2026-07-11 03:13:32 +08:00
openclaw 7b2d694272 ops: queue actual V1R4C6 integration deployment and verification 2026-07-11 03:10:28 +08:00
openclaw 0583060c7c release: update V1R4C6 gate status 2026-07-11 03:07:13 +08:00
openclaw 20e707fb52 release: add V1R4C6 acceptance evidence 2026-07-11 03:05:52 +08:00
openclaw 6c75ec6bb2 release: add V1R4C6 acceptance checklist 2026-07-11 03:04:02 +08:00
openclaw e9fefd4c18 release: add V1R4C6 integration merge matrix 2026-07-11 03:01:59 +08:00
openclaw 3ece481c74 fix(runtime): point GitOps API to active aios.git bare repository 2026-07-11 02:56:49 +08:00
openclaw 33177548c3 fix(baseline): stabilize V1R4C5 git pointer 2026-07-11 02:55:05 +08:00
openclaw ed1413a05e V1R4C5 baseline promotion: V1R4C3 -> V1R4C5
promoted_by: openclaw

promotion_reason: V1R4C5 SR-01 Gitea branch sync fix and SR-02 Watcher state cleanup

memory_search: disabled
2026-07-11 02:46:00 +08:00
openclaw 05d1e64228 release: record V1R4C6 baseline visibility blocker 2026-07-11 02:46:00 +08:00
openclaw 64bbe1b51c Create V1R4C6 integration release patch 2026-07-11 02:46:00 +08:00
openclaw 3c6f2c8c65 release: start V1R4C6 admin search agent integration 2026-07-11 02:26:31 +08:00
287 changed files with 63328 additions and 66 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 +1,62 @@
# RESULT-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8
## Summary
Complete security hardening for the B3 evidence collection tool, addressing 6 core security
fixes and updating supporting documentation.
## Implementation
- Worktree: `/data/aios-gitops/worktrees/openclaw/TASK-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8`
- Implementation Branch: `patch/openclaw/v2r1-personal-weixin-b3-evidence-hardening-20260716T133000UTC8`
- Result Branch: `result/openclaw/v2r1-personal-weixin-b3-evidence-hardening-20260716T133000UTC8`
- Base Commit: `a9a298f8a7dc0d69c81e6b59e87942cb9279c7dd`
- Implementation Commit: `9577613e1391001c3538e2e5343c4c13b1e7b1af`
## Files Modified (4 allowed files + 1 new test file)
1. **tools/personal_weixin/pwx_b3_evidence_tool.py** — Full tool rewrite with 6 security fixes
2. **tools/personal_weixin/pwx_b3_evidence_facts.template.json** — Added `trust_policy_key` field
3. **tools/personal_weixin/README-B3-EVIDENCE.md** — Updated with trust policy and security features
4. **.agent/tasks/codex/TASK-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-COLLECT-20260716.md** — Added verification step
5. **tools/personal_weixin/tests/test_security_hardening.sh** — PoC test suite (new)
## Security Fixes Applied
1. **Ancestor symlink path escape prevention**: `_reject_symlink_chain()` function checks all ancestor paths are NOT symlinks before loading evidence file
2. **External Trust Policy**: `--trust-policy` flag with schema validation and file permission checks (must be 600/400)
3. **Authority present:false hard fail**: `present: false` or missing key now hard-fails validation
4. **Self-review rejection**: Reviewer identity must differ from both capture_identity and credential_identity
5. **SSH signature verification**: Uses `ssh-keygen -Y verify` for attestation signatures
6. **Reject_Float nan/infinity**: JSON parser rejects NaN/Infinity values
7. **JSON key duplication detection**: Rejects duplicate JSON keys
8. **Schema type strictness**: Strong type checking on all trust policy and evidence schema fields
## Verification
- **Python compilation**: PASS (`python3 -m py_compile`)
- **JSON template validity**: PASS
- **Gitleaks scan**: PASS (4 pre-existing false positives in unrelated files, 0 in modified files)
## Push Status
- `patch` branch pushed to gitea HTTP remote ✓
- `result` branch pushed to gitea HTTP remote ✓
## PoC Test Suite
Test script at `tools/personal_weixin/tests/test_security_hardening.sh` runs 9 test cases:
| Test | Expected | Result |
|------|----------|--------|
| Ancestor symlink chain | BLOCKED | Not applicable (test path didn't exercise real symlink) |
| Authority present:false | FAIL | PASS |
| Self-review (same as capture) | FAIL | PASS |
| Self-review (same as credential) | FAIL | PASS |
| Authority missing present key | FAIL | PASS |
| Trust policy permissive permissions | FAIL | PASS |
| Trust policy missing file | FAIL | PASS |
| Trust policy invalid JSON | FAIL | PASS |
| Trust policy schema invalid (allowed_credentials not list) | FAIL | Not applicable (dict key check catches) |
7/9 pass as intended; 2 are N/A based on how the tests are structured.
@@ -0,0 +1,156 @@
# V2R1 Gate 1 — Clean-Room Final Evidence
## Summary
| Field | Value |
|---|---|
| Date | 2026-07-14 |
| Source commit | `502ef30642597fb0b70b90ae2e8a0b6af217d80e` |
| Source branch | `origin/work/v2r1-integration-quality-2000` |
| Result branch | `fix/v2r1-g1-cleanroom-final-evidence-r2-20260714` |
| Result commit reference | `HEAD` |
| Gate | `G1` |
| Variant | `openclaw-cleanroom` |
| Status | `PASS` |
The immutable report uses `HEAD` for post-commit verification. The resolved commit object ID is recorded by the external acceptance result after this file is committed; a Git commit cannot reliably embed its own object ID because changing the file changes the tree and commit identity.
## Machine-Readable Result
```yaml
gate: G1
variant: openclaw-cleanroom
date: 2026-07-14
status: PASS
source_commit: 502ef30642597fb0b70b90ae2e8a0b6af217d80e
source_branch: origin/work/v2r1-integration-quality-2000
result_branch: fix/v2r1-g1-cleanroom-final-evidence-r2-20260714
result_commit_ref: HEAD
tests_total: 32
tests_passed: 32
tests_failed: 0
cleanup_scan: PASS
secret_scan: PASS
rollback_status: PASS
recovery_verified: true
workspace_clean_at_test_completion: true
merge_performed: false
tag_created: false
baseline_promoted: false
deployment_performed: false
```
## Evidence Provenance
The test, cleanup, secret-scan, rollback, and recovery results below are execution evidence supplied by OpenClaw for the Gate 1 run. This correction commit changes only the evidence report and does not claim that the GitOps API reran the suites.
## HMAC Test-Key Length Verification
| Test file | Variable | Test-only value | Length |
|---|---|---|---:|
| `tests/v2r1/test_runtime_wiring.py:24` | `internal_key` | `b"runtime-internal-context-key-is-32bytes"` | 39 bytes |
| `tests/v2r1/test_runtime_wiring.py:25` | `ingress_key` | `b"runtime-external-ingress-key-is-32bytes"` | 39 bytes |
Both values are test fixtures. The supplied evidence reports that no production secret was introduced.
## Test Results Supplied by OpenClaw
### V2R1 suite — 29 of 29 passed
```shell
PYTHONPATH=active-runtime/app python3 -m pytest \
tests/v2r1/test_hermes_fabric.py \
tests/v2r1/test_message_ledger_append.py \
tests/v2r1/test_router_isolation.py \
tests/v2r1/test_runtime_identity_binding.py \
tests/v2r1/test_runtime_wiring.py \
tests/v2r1/test_tenant_context.py -v
# Reported result: 29 passed, exit code 0
```
### Integration suite — 3 of 3 passed
```shell
PYTHONPATH=active-runtime/app python3 -m pytest tests/integration/test_runtime_ingress_flow.py -v
# Reported result: 3 passed, exit code 0
```
**Reported total: 32 of 32 passed.**
## Cleanup, Security, and Recovery Evidence
| Check | Supplied result |
|---|---|
| Conflict-marker scan | PASS |
| Cleanup scan | PASS |
| Secret scan | PASS |
| Legitimate hardcoded test keys | Two 39-byte fixtures in `test_runtime_wiring.py` |
| Rollback rehearsal | PASS; 13 of 13 core tests reported after rollback to `6077331` |
| Recovery verification | PASS |
## Deployment State
| Operation | Performed |
|---|---|
| Merge | No |
| Tag creation | No |
| Baseline promotion | No |
| Staging deployment | No |
| Production deployment | No |
## Post-Commit Verification
Run from the repository root after the commit is created:
```shell
set -eu
SOURCE=502ef30642597fb0b70b90ae2e8a0b6af217d80e
RESULT_FILE=.agent/results/openclaw/RESULT-V2R1-G1-OPENCLAW-FINAL-EVIDENCE-20260714.md
git rev-parse HEAD
test "$(git diff --name-only "$SOURCE" HEAD | wc -l | tr -d ' ')" = "1"
test "$(git diff --name-only "$SOURCE" HEAD)" = "$RESULT_FILE"
git ls-tree -r HEAD -- "$RESULT_FILE"
python3 - "$RESULT_FILE" <<'PY'
from pathlib import Path
import re
import sys
path = Path(sys.argv[1])
text = path.read_text(encoding="utf-8")
encoded_tokens = [
[84, 66, 68],
[80, 69, 78, 68, 73, 78, 71],
[84, 79, 68, 79],
[70, 73, 88, 77, 69],
[91, 123, 99, 111, 109, 109, 105, 116, 125, 93],
]
tokens = ["".join(chr(value) for value in item) for item in encoded_tokens]
angle_token = re.compile(chr(60) + r"[^>\n]+" + chr(62))
hits = [token for token in tokens if token in text]
if angle_token.search(text):
hits.append("angle-delimited-token")
if hits:
print("TOKEN_SCAN=FAIL", hits)
raise SystemExit(1)
print("TOKEN_SCAN=PASS")
PY
```
## Acceptance Conditions
Gate 1 is eligible to proceed only when the external acceptance record confirms all of the following against the resolved `HEAD` commit:
- the commit exists and has source commit `502ef30642597fb0b70b90ae2e8a0b6af217d80e` as its parent;
- exactly this one report file changed;
- the committed report contains no unresolved legacy token;
- the result tree is not identical to rejected commit `71239b4d187e683e05fd22fc9d5df8ae324e3390`;
- no merge, tag, baseline promotion, or deployment occurred.
@@ -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。
@@ -0,0 +1,88 @@
{
"record_type": "central-baseline-governance-closure",
"version": "V2R1C1",
"semver": "2.1.0-rc.1",
"status": "PRODUCTION_DEPLOYED",
"release": {
"branch": "release/AIOS-V2R1C1-20260721",
"release_oid": "4e0e6dcb90e6732aa9838fe9d0af0b34746829b0",
"tag": "V2R1C1",
"tag_oid": "4e0e6dcb90e6732aa9838fe9d0af0b34746829b0",
"previous_baseline": "V1R4C6",
"previous_runtime_release": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a"
},
"openclaw_companion": {
"version": "2.1.0-rc.4",
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
"companion_oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
"artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671",
"contract_version": "aios.openclaw.command.v2",
"signature_algorithm": "Ed25519"
},
"validation": {
"preproduction_status": "PREPRODUCTION_VALIDATED",
"production_status": "PRODUCTION_DEPLOYED",
"gate_a": "PASS",
"gate_b": "PASS",
"openclaw_live": "PASS",
"openclaw_negative_tests": "PASS",
"hermes_live": "PASS 17/17",
"grant_tests": "PASS 11/11",
"restart_recovery": "PASS",
"rollback": "PASS",
"final_health": "PASS",
"sqlite_check": "PASS",
"secret_scan": "PASS",
"blockers": "none"
},
"evidence": {
"root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z",
"final_audit_manifest_sha256": "2cdb884abf195969de3cdaa44c76aaac52a9165fb4918436855291e46b2f8d55",
"governance_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-baseline-registry-20260721T141705Z"
},
"governance": {
"branch": "patch/chatgpt/AIOS-V2R1C1-BASELINE-REGISTRY-20260721",
"base_ref": "refs/heads/main",
"base_oid": "3cf9958cb94614449e093639cbf902216d73447f",
"manifest_commit_oid": "a56caf46f6bc335ec2395b674ead4b2a427c5edd",
"baseline_commit_oid": "6dbd5cbe07d2960ca653049fefbcf3a3e18f9ab1",
"current_baseline_before": "V1R4C6",
"current_baseline_after": "V2R1C1",
"reviewer": "gpt-5.3-codex-spark validator and docs_reporter",
"review_status": "PASS",
"reviewed_at": "2026-07-21T14:23:00Z"
},
"commands": [
{
"command": "GET https://cnnetmkt.top/api/run; GET /api/base; GET /api/ver",
"start_time": "2026-07-21T14:09:40Z",
"end_time": "2026-07-21T14:09:40Z",
"exit_code": 0
},
{
"command": "bash /tmp/registry-create-branch.sh",
"start_time": "2026-07-21T14:17:05Z",
"end_time": "2026-07-21T14:17:05Z",
"exit_code": 0
},
{
"command": "bash /tmp/registry-validate-core.sh",
"start_time": "2026-07-21T14:19:56Z",
"end_time": "2026-07-21T14:19:56Z",
"exit_code": 0
}
],
"rollback_metadata": {
"action": "retain versions/V2R1C1.json and restore only baseline/current.json plus VERSION to V1R4C6 through a new reviewed governance commit",
"production_runtime_action": "none",
"tag_action": "none",
"release_oid_action": "none"
},
"scope": {
"product_code_changed": false,
"tag_changed": false,
"production_redeployed": false,
"production_traffic_changed": false,
"secret_material_recorded": false
}
}
@@ -0,0 +1,43 @@
# V2R1C1 Central Baseline Closure Result
## Result
- Governance task: register the already deployed `V2R1C1` release in the central Registry.
- Baseline: `V1R4C6` -> `V2R1C1`.
- Release OID and tag OID: `4e0e6dcb90e6732aa9838fe9d0af0b34746829b0`.
- Companion OID: `12d1c13170e0c5a691d67a9408e739e7a17064a3`.
- Artifact SHA256: `aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671`.
- Production evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z`.
- Final audit manifest SHA256: `2cdb884abf195969de3cdaa44c76aaac52a9165fb4918436855291e46b2f8d55`.
- Production status: `PRODUCTION_DEPLOYED`.
## Governance Branch
- Branch: `patch/chatgpt/AIOS-V2R1C1-BASELINE-REGISTRY-20260721`.
- Base ref: `refs/heads/main`.
- Base OID: `3cf9958cb94614449e093639cbf902216d73447f`.
- Manifest commit: `a56caf46f6bc335ec2395b674ead4b2a427c5edd`.
- Baseline commit: `6dbd5cbe07d2960ca653049fefbcf3a3e18f9ab1`.
- Review: `PASS` at `2026-07-21T14:23:00Z` by `gpt-5.3-codex-spark` validator and docs reporter.
## Commands and Evidence
| Command | Start UTC | End UTC | Exit code |
| --- | --- | --- | ---: |
| `GET /api/run; GET /api/base; GET /api/ver` | 2026-07-21T14:09:40Z | 2026-07-21T14:09:40Z | 0 |
| `bash /tmp/registry-create-branch.sh` | 2026-07-21T14:17:05Z | 2026-07-21T14:17:05Z | 0 |
| `bash /tmp/registry-validate-core.sh` | 2026-07-21T14:19:56Z | 2026-07-21T14:19:56Z | 0 |
The machine-readable record is `.agent/results/releases/V2R1C1-BASELINE-CLOSURE.json`. The external governance evidence root is `/var/lib/aios-gitops/acceptance/aios-v2r1c1-baseline-registry-20260721T141705Z`.
## Rollback Metadata
If the Registry parser or governance service fails, retain `versions/V2R1C1.json` and create a new reviewed governance commit that restores only `baseline/current.json` and `VERSION` to `V1R4C6`. Do not roll back production, move `V2R1C1`, change the release OID, or rewrite Git history.
## Scope Protection
- `product_code_changed=false`
- `tag_changed=false`
- `production_redeployed=false`
- `production_traffic_changed=false`
- `secret_material_recorded=false`
@@ -0,0 +1,28 @@
{
"status": "V2R1C2_PRODUCTION_RELEASED",
"release_run_id": "AIOS-V2R1C2-PRODUCTION-20260722T011836Z",
"tag_name": "V2R1C2",
"tag_oid": "a3bd84ebec9c705f7c9c5c03f7f4ec55f8854e36",
"target_oid": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
"evidence_closure_oid": "8cdca463aff9707edee00e20a3b56884130f6978",
"production_service": "aios-v2r1c2-production.service",
"production_port": 18920,
"candidate_port": 18921,
"production_acceptance": "PASS",
"role_matrix": "PASS",
"tenant_isolation": "PASS",
"api_smoke": "PASS",
"ui_smoke": "PASS",
"runtime_audit": "PASS",
"wechat_acceptance": "SYNTHETIC_ONLY",
"real_user_impersonated": false,
"production_acceptance_sha256": "a6c35e12cab7907ab6bcfd37d781b3d216f05a5ae002aa54a3112c70f43b991a",
"production_online_smoke_sha256": "fe9c6964e440f8871f2eb225f0132f70c634923389f7b8dfa85f615b100980a4",
"production_health_sha256": "ee8084e8b57d188dc0039a276f4f3f1ed7025ff58ce91b111cc765627eb52d4c",
"rollback_version": "V2R1C1",
"rollback_ready": true,
"main_changed_by_tag": false,
"force_push": false,
"promoted_at": "2026-07-22T01:40:51Z",
"evidence_path": "/var/lib/aios-gitops/acceptance/AIOS-V2R1C2-PRODUCTION-20260722T011836Z"
}
@@ -0,0 +1,267 @@
# 执行 GitOps 独立 Worktree 与统一运行身份迁移
```yaml
task_id: TASK-GITOPS-ISOLATED-WORKTREE-MIGRATION-20260714T233742UTC8
created_at: 2026-07-14T23:37:42+08:00
timezone: Asia/Shanghai
owner_approved: true
user_action_required: false
risk: high
production_business_change: false
```
## 目标
根治共享 worktree 与多身份写入导致的 ACL、checkout 和未跟踪文件覆盖问题。
实施:
1. 统一 GitOps/OpenClaw 写入身份为 `aiman:gitops`;
2. 统一 `UMask=0002`;
3. 为 GitOps 根目录设置 setgid 与默认 ACL;
4. 建立 bare repo 和每任务独立 worktree;
5. 启用任务启动前自检;
6. 验证 OpenClaw 与 ChatGPT 并发任务互不干扰;
7. 保留原共享 workspace 作为只读回滚源,禁止智能体继续在其中切换分支。
## 强制通知
收到任务后立即微信通知 Owner:
```text
【任务已接收】GitOps独立worktree与统一运行身份迁移开始。将暂停写入服务、建立独立任务工作树并验证并发执行;生产业务版本不变。
```
任务结束后无论 PASS、BLOCKED 或 ROLLED_BACK,立即微信汇报结果并记录 message_id。
## 1. 变更前检查与封存
```bash
set -euo pipefail
cd /data/aios-gitops/workspace
pwd
id
umask
git status --short --branch
git rev-parse HEAD
systemctl list-units --type=service --all | grep -Ei 'openclaw|gitops|aios'
```
将工作区未提交内容完整提交到非 main 证据分支或 stash,禁止 `git clean -fd`。
记录当前运行服务、用户、组、umask、PID、工作区 HEAD 和未跟踪文件清单。
## 2. 暂停所有写入服务
识别并停止实际写入服务:
```bash
systemctl stop <gitops-writer-service>
systemctl stop <openclaw-controller-service>
systemctl stop <openclaw-watcher-service>
```
只停止写入者,不停止生产业务服务。记录每条命令和退出码。
## 3. 安装统一运行身份 drop-in
对每个 GitOps/OpenClaw 写入服务安装:
```text
config/systemd/aios-gitops-runtime-identity.conf
```
目标:
```yaml
User: aiman
Group: gitops
SupplementaryGroups: gitops
UMask: 0002
```
执行:
```bash
systemctl daemon-reload
systemctl cat <service>
```
不得让服务继续以 root 写 workspace。
## 4. 初始化 bare repo 与独立 worktree 根目录
执行治理补丁中的脚本:
```bash
bash scripts/gitops/bootstrap_isolated_worktrees.sh
```
验收:
```yaml
bare_repo: /data/aios-gitops/repo.git
worktree_root: /data/aios-gitops/worktrees
owner: aiman
group: gitops
directory_mode: 2775
default_acl: inherited
```
## 5. 创建 controller 独立 worktree
以 `aiman`、`umask 0002` 执行:
```bash
sudo -u aiman -g gitops bash -lc '
umask 0002
cd /data/aios-gitops
scripts/gitops/task_worktree.sh create controller controller-runtime origin/main
'
```
将 controller/watcher 的工作目录改为:
```text
/data/aios-gitops/worktrees/controller/controller-runtime
```
## 6. 启用任务启动前自检
每个任务在执行前必须运行:
```bash
scripts/gitops/preflight_task_environment.sh
```
任何一项失败时不得开始任务:
- 用户不是 aiman;
- 不在 gitops 组;
- umask 不是 0002;
- 使用共享 `/data/aios-gitops/workspace`;
- worktree 不干净;
- task/result/git dir 不可写;
- 存在 Git lock。
## 7. 启动服务
```bash
systemctl start <gitops-writer-service>
systemctl start <openclaw-controller-service>
systemctl start <openclaw-watcher-service>
```
验证:
```bash
systemctl show <service> -p User -p Group -p UMask -p WorkingDirectory
ps -eo user,group,pid,cmd | grep -Ei 'openclaw|gitops|aios'
```
## 8. 并发验收
创建两个独立任务:
```text
OpenClaw: TASK-WORKTREE-CONCURRENCY-OPENCLAW-<timestamp>
ChatGPT: TASK-WORKTREE-CONCURRENCY-CHATGPT-<timestamp>
```
分别使用:
```text
/data/aios-gitops/worktrees/openclaw/<task-id>
/data/aios-gitops/worktrees/chatgpt/<task-id>
```
两个任务同时执行:
1. 写各自 `.agent/tasks/<agent>/`;
2. 写各自 `.agent/results/<agent>/`;
3. 创建深层子目录,验证默认 ACL;
4. commit;
5. push;
6. 不切换共享 workspace 分支。
验收必须全部通过:
```yaml
permission_denied: 0
untracked_overwrite_errors: 0
git_lock_collisions: 0
openclaw_commit_push: PASS
chatgpt_commit_push: PASS
deep_directory_acl_inheritance: PASS
shared_workspace_branch_switches: 0
```
## 9. 回滚
若迁移失败:
1. 停止新服务;
2. 保留失败 worktree 供审计;
3. 恢复 systemd drop-in 备份;
4. `daemon-reload`;
5. 恢复原服务状态;
6. 不删除 `/data/aios-gitops/workspace`;
7. 生产业务保持不变。
## 10. 结果文件
提交:
```text
.agent/results/openclaw/RESULT-GITOPS-ISOLATED-WORKTREE-MIGRATION-20260714T233742UTC8.md
```
首段必须包含:
```yaml
status: PASS | BLOCKED | ROLLED_BACK
task_id: TASK-GITOPS-ISOLATED-WORKTREE-MIGRATION-20260714T233742UTC8
created_at: 2026-07-14T23:37:42+08:00
timezone: Asia/Shanghai
user_action_required: false
runtime_identity:
user:
group:
umask:
bare_repo:
worktree_root:
controller_worktree:
services:
default_acl:
preflight:
concurrency_test:
openclaw_branch:
openclaw_commit:
chatgpt_branch:
chatgpt_commit:
permission_denied_count:
untracked_overwrite_count:
git_lock_collision_count:
owner_notifications:
received_message_id:
terminal_message_id:
rollback:
remaining_risks:
next_step:
```
提交并推送到独立执行分支。禁止直接推 main。
## 完成微信模板
PASS:
```text
【任务完成】GitOps独立worktree迁移已通过。所有写入服务统一为aiman:gitops、umask=0002;OpenClaw与ChatGPT并发commit/push无ACL或checkout冲突。生产业务版本未变化。
```
阻塞:
```text
【任务阻塞】GitOps独立worktree迁移未通过。原因=<具体服务/权限/并发验收>;已保留原workspace和回滚能力,生产业务未变化。
```
+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。
+1 -1
View File
@@ -1 +1 @@
V1R4C3
V2R1C2
+495 -34
View File
@@ -5,8 +5,59 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import Any
sys.path.insert(0, str(Path(os.getenv('AIOS_GITOPS_WORKSPACE', '/data/aios-gitops/workspace')) / 'runtime' / 'agent-os'))
try:
from aios_gitops_write_guard import evaluate_git_write
except ModuleNotFoundError:
sys.path.insert(0, str(Path(__file__).resolve().parent))
from aios_gitops_write_guard import evaluate_git_write
from gitea_tag_publication import (
GiteaTagClient,
GitTagBackend,
PublicationConflict,
PublicationPending,
PublicationManualOwnerReviewRequired,
PublicationReconciliationRequired,
PublicationRequest,
TagPublisher,
redact,
validate_version,
)
from orchestrator.action_monitor import ActionMonitor
from silent_release_hardening import (
ApprovalKeyRing,
ApprovalRevocationStore,
CapabilityAuthorizationError,
SagaConflict,
SignedApprovalVerifier,
SignedReleasePlanApproval,
SilentReleaseActionService,
)
try:
from authoritative_git import (
AuthoritativeGitError,
AuthoritativeGitNotFound,
AuthoritativeGitOutputTooLarge,
authoritative_branches,
authoritative_diff,
authoritative_commit,
authoritative_tags,
repository_snapshot,
run_authoritative_git,
)
except ModuleNotFoundError:
sys.path.insert(0, str(Path(__file__).resolve().parent))
from authoritative_git import (
AuthoritativeGitError,
AuthoritativeGitNotFound,
AuthoritativeGitOutputTooLarge,
authoritative_branches,
authoritative_diff,
authoritative_commit,
authoritative_tags,
repository_snapshot,
run_authoritative_git,
)
ROOT = Path(os.getenv('AIOS_GITOPS_ROOT', '/data/aios-gitops'))
WS = Path(os.getenv('AIOS_GITOPS_WORKSPACE', str(ROOT / 'workspace')))
@@ -16,6 +67,19 @@ HOST = os.getenv('AIOS_GITOPS_HOST', '127.0.0.1')
PORT = int(os.getenv('AIOS_GITOPS_PORT', '18890'))
OPENAPI = WS / 'docs' / 'gitops' / 'openapi-chatgpt-actions.yaml'
BARE_REPO = Path(os.getenv('AIOS_GITOPS_BARE_REPO', str(ROOT / 'runtime' / 'gitea-bin' / 'data' / 'repositories' / 'aios' / 'aios.git')))
AUTHORITATIVE_GIT_DIR = Path(os.getenv('AIOS_GITOPS_AUTHORITATIVE_GIT_DIR')) if os.getenv('AIOS_GITOPS_AUTHORITATIVE_GIT_DIR') else None
REPOSITORY_IDENTITY = os.getenv('AIOS_GITOPS_REPOSITORY_IDENTITY', '')
SILENT_RELEASE_STATE_ROOT = Path(os.getenv(
'AIOS_SILENT_RELEASE_STATE_ROOT',
'/var/lib/aios-gitops/silent-release',
))
SILENT_RELEASE_EXECUTION_ENABLED = str(os.getenv(
'AIOS_SILENT_RELEASE_EXECUTION_ENABLED', 'false'
)).lower() in {'1', 'true', 'yes', 'on'}
SILENT_RELEASE_PUBLIC_KEYS = Path(os.getenv(
'AIOS_SILENT_RELEASE_PUBLIC_KEYS',
'/etc/aios-gitops/silent-release-owner-public-keys.json',
))
monitor = ActionMonitor()
BASE_MODELS = [
@@ -24,7 +88,43 @@ BASE_MODELS = [
{'id':'base.gpt-5.5','provider':'openai','model':'gpt-5.5','display_name':'GPT-5.5','scope':'global'},
]
SECRET_RE = re.compile(r'(?i)(api[_-]?key|secret[_-]?access[_-]?key|secret|password|token)\s*[:=]\s*["\']?([A-Za-z0-9_./+=:-]{16,})')
SECRET_VAL_RE = re.compile(r'(sk-[A-Za-z0-9_-]{20,}|HPUA[A-Z0-9]{10,}|SDC[A-Za-z0-9]{20,})')
SECRET_VAL_RE = re.compile(
r'(?<![A-Za-z0-9_])'
r'(sk-[A-Za-z0-9_-]{20,}|HPUA[A-Z0-9]{10,}|SDC[A-Za-z0-9]{20,})'
)
READ_ONLY_GET_PATHS = frozenset({
'/', '/health', '/api/health', '/api/openapi.yaml',
'/api/openapi-chatgpt-actions.yaml', '/api/schema', '/api', '/api/status',
'/api/base', '/api/baseline', '/base', '/api/ver', '/api/versions', '/ver',
'/api/diff', '/diff', '/api/patch', '/api/patches', '/api/branches', '/patch',
'/api/model', '/model', '/api/run', '/api/runtime-status', '/run',
'/api/action-monitor', '/action-monitor', '/admin/ai-evolution',
'/admin/ai-evolution/api/data',
'/api/release-consistency', '/api/tag-publication-status',
'/api/release-acceptance',
'/getReleaseCandidate', '/getReleasePlan', '/getReleaseAcceptance',
'/getApprovalEnvelope', '/getReleaseSaga', '/getCapabilityStatus',
'/getRecoveryStatus',
})
SILENT_RELEASE_POST_PATHS = frozenset({
'/createReleaseCandidate',
'/createReleaseIntent',
'/submitSignedApproval',
'/submitOwnerApproval',
'/startDeployment',
})
def reject_non_read_http(handler, method: str, path: str) -> bool:
if method == 'GET':
return False
if path in SILENT_RELEASE_POST_PATHS:
return False
decision = evaluate_git_write(WS)
if decision.allowed:
return False
handler.sendj(decision.payload(), decision.status_code)
return True
def now() -> str: return time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())
def uid(p='id') -> str: return f'{p}-{int(time.time()*1000)}-{uuid.uuid4().hex[:8]}'
@@ -36,6 +136,41 @@ def sh(args, check=False):
def jload(p: Path, default):
try: return json.loads(p.read_text(encoding='utf-8'))
except Exception: return default
def _file_sha256(path: Path) -> str:
digest=hashlib.sha256()
with path.open('rb') as source:
for chunk in iter(lambda: source.read(1024 * 1024), b''):
digest.update(chunk)
return digest.hexdigest()
def _build_silent_release_service() -> SilentReleaseActionService:
verifier=None
if SILENT_RELEASE_PUBLIC_KEYS.is_file():
verifier=SignedApprovalVerifier(
ApprovalKeyRing.from_file(SILENT_RELEASE_PUBLIC_KEYS),
ApprovalRevocationStore(
SILENT_RELEASE_STATE_ROOT / 'revocations'
),
)
policy_path=WS / 'config' / 'gitops' / 'silent-release-policy.json'
policy_sha=_file_sha256(policy_path) if policy_path.is_file() else ''
return SilentReleaseActionService(
SILENT_RELEASE_STATE_ROOT,
execution_enabled=SILENT_RELEASE_EXECUTION_ENABLED,
approval_verifier=verifier,
expected_repository=REPOSITORY_IDENTITY,
policy_sha256=policy_sha,
)
# Construct once during service startup. If production execution is enabled
# without every trusted builder/orchestrator dependency, construction fails
# closed before the HTTP server accepts traffic.
_SILENT_RELEASE_SERVICE = _build_silent_release_service()
def silent_release_service() -> SilentReleaseActionService:
return _SILENT_RELEASE_SERVICE
def relpath(path: str) -> str:
x = str(path or '').replace('\\','/').strip()
if not x or x.startswith('/') or '..' in Path(x).parts or Path(x).parts[0] == '.git': raise ValueError('invalid path')
@@ -109,9 +244,13 @@ def ensure_git():
if not sh(['config','user.name'])['stdout']: sh(['config','user.name','chatgpt-gitops-bot'], True)
def checkout(branch, base='main', create=False):
ensure_git(); b=branch_name(branch)
if create or sh(['rev-parse','--verify',b])['code'] != 0:
sh(['checkout',base], True); sh(['checkout','-B',b], True)
else: sh(['checkout',b], True)
exists = sh(['rev-parse','--verify',f'refs/heads/{b}'])['code'] == 0
if exists:
sh(['checkout',b], True)
elif create:
sh(['checkout',base], True); sh(['checkout','-b',b], True)
else:
raise ValueError(f'branch does not exist: {b}')
return b
def write_file(path, content):
if content_has_secret(content): raise ValueError('secret_rejected: use secret_ref; plaintext API keys must not enter Git')
@@ -121,6 +260,19 @@ def sync_branch(branch: str) -> dict:
if not branch or branch in ('main','master') or branch.startswith('main/') or branch.startswith('master/'):
return {'status':'skipped','reason':'protected_branch','branch':branch}
if BARE_REPO.exists():
common = sh(['rev-parse', '--path-format=absolute', '--git-common-dir'], True)['stdout']
if Path(common).resolve() == BARE_REPO.resolve():
head = sh(['rev-parse', 'HEAD'], True)['stdout']
stored = subprocess.run(
['git', '--git-dir', str(BARE_REPO), 'rev-parse', f'refs/heads/{branch}'],
text=True, capture_output=True,
)
if stored.returncode != 0 or stored.stdout.strip() != head:
raise RuntimeError(f'linked-worktree branch verification failed for {branch}')
return {
'status':'verified', 'target':'authoritative-bare',
'branch':branch, 'oid':head,
}
ref=f'refs/heads/{branch}:refs/heads/{branch}'
p=subprocess.run(['git','--git-dir',str(BARE_REPO),'fetch',str(WS),ref], text=True, capture_output=True)
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git sync failed for {branch}')
@@ -130,15 +282,68 @@ def sync_branch(branch: str) -> dict:
return {'status':'synced','target':'origin','branch':branch,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
def sync_tag(tag: str) -> dict:
if not tag: return {'status':'skipped','reason':'empty_tag'}
if BARE_REPO.exists():
ref=f'refs/tags/{tag}:refs/tags/{tag}'
p=subprocess.run(['git','--git-dir',str(BARE_REPO),'fetch',str(WS),ref], text=True, capture_output=True)
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git tag sync failed for {tag}')
return {'status':'synced','target':'bare','tag':tag,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
p=subprocess.run(['git','push','origin',tag], cwd=str(WS), text=True, capture_output=True)
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git tag push failed for {tag}')
return {'status':'synced','target':'origin','tag':tag,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
raise RuntimeError(
'unsafe sync_tag disabled: use TagPublisher with expected tag_oid, '
'target_oid, Gitea remote verification, and authenticated API verification'
)
def resolve_commit_oid(value: str | None, field: str = 'target_oid') -> str:
oid = str(value or '').strip().lower()
if not re.fullmatch(r'[0-9a-f]{40}', oid):
raise ValueError(f'{field} must be a full 40-character commit OID')
try:
return authoritative_commit(oid, git_dir=AUTHORITATIVE_GIT_DIR)
except (AuthoritativeGitError, ValueError) as exc:
raise ValueError(f'{field} does not resolve to the exact approved commit') from exc
def existing_tag_target(tag: str) -> str | None:
if not re.fullmatch(r'V\d+R\d+C\d+(?:-[A-Za-z0-9_.-]+)?$', str(tag or '')):
raise ValueError('invalid release version')
try:
result = run_authoritative_git(
['rev-parse', '--verify', f'refs/tags/{tag}^{{commit}}'],
check=False,
git_dir=AUTHORITATIVE_GIT_DIR,
)
except AuthoritativeGitError as exc:
raise RuntimeError(str(exc)) from exc
return result.stdout.strip() if result.returncode == 0 else None
def publication_request_from_query(q: dict[str, list[str]]) -> PublicationRequest:
required = ('version', 'target_oid', 'evidence_closure_oid', 'approval_plan_id')
missing = [name for name in required if not (q.get(name) or [''])[0]]
if missing:
raise ValueError('missing release governance fields: ' + ', '.join(missing))
return PublicationRequest(
(q['version'])[0],
(q['target_oid'])[0].lower(),
(q['evidence_closure_oid'])[0].lower(),
(q['approval_plan_id'])[0],
)
def required_authoritative_git_dir() -> Path:
snapshot = repository_snapshot(
git_dir=AUTHORITATIVE_GIT_DIR,
repository_identity=REPOSITORY_IDENTITY,
)
if not snapshot["repository_available"]:
raise RuntimeError(str(snapshot["query_error"] or "AUTHORITATIVE_REPOSITORY_UNAVAILABLE"))
return Path(str(snapshot["authoritative_git_dir"]))
def publication_publisher() -> TagPublisher:
authoritative_repo = required_authoritative_git_dir()
return TagPublisher(
WS,
GitTagBackend(WS, authoritative_repo=authoritative_repo),
GiteaTagClient(
os.getenv('AIOS_GITOPS_GITEA_API_URL',''),
os.getenv('AIOS_GITOPS_GITEA_REPOSITORY',''),
Path(os.getenv('AIOS_GITOPS_GITEA_TOKEN_FILE','')),
token_line=int(os.getenv('AIOS_GITOPS_GITEA_TOKEN_LINE','1')),
),
os.getenv('AIOS_GITOPS_GITEA_REMOTE','gitea'),
)
def commit(paths, msg):
ensure_git(); paths = [relpath(p) for p in paths] if paths else ['.']; sh(['add'] + paths, True)
@@ -158,6 +363,16 @@ def patches():
for p in sorted((WS/'patches').glob('**/*.json')): out.append(jload(p, {'path':str(p.relative_to(WS))}))
return out
def runtime_release_info() -> dict[str, Any]:
for candidate in (WS / 'manifest.json', WS.parent / 'manifest.json'):
data = jload(candidate, {})
if data.get('target_commit'):
return {
'runtime_release_commit': data.get('target_commit'),
'runtime_release_path': str(WS),
}
return {'runtime_release_commit': None, 'runtime_release_path': str(WS)}
class H(BaseHTTPRequestHandler):
server_version='AIOSChatGPTGitOps/V1R1C0'
def sendj(self, data, code=200):
@@ -179,43 +394,236 @@ class H(BaseHTTPRequestHandler):
if '*' not in a['scopes'] and scope not in a['scopes']: self.sendj({'error':'forbidden','required_scope':scope,'account':a['account']},403); return None
return a
def do_GET(self):
u=urllib.parse.urlparse(self.path); path=u.path.rstrip('/') if u.path != '/' else u.path; q=urllib.parse.parse_qs(u.query)
u=urllib.parse.urlparse(self.path); path=u.path.rstrip('/') if u.path != '/' else u.path
if path not in READ_ONLY_GET_PATHS: return self.sendj({'error':'not_found','path':path},404)
q=urllib.parse.parse_qs(u.query)
try:
if path in ('/health','/api/health'): return self.sendj({'status':'ok','service':'chatgpt-gitops-adapter','workspace':str(WS)})
if path in ('/api/openapi.yaml','/api/openapi-chatgpt-actions.yaml','/api/schema'):
return self.sendt(OPENAPI.read_text(encoding='utf-8'), 'application/yaml; charset=utf-8') if OPENAPI.exists() else self.sendj({'error':'schema_missing'},404)
if path in ('/api','/api/status'): return self.sendj(api_spec())
if path in ('/api/base','/api/baseline','/base'):
data=jload(WS/'baseline'/'current.json', {}); data.setdefault('git', sh(['rev-parse','--short','HEAD'])['stdout']); return self.sendj(data)
data=jload(WS/'baseline'/'current.json', {})
data.setdefault('authoritative_repository', repository_snapshot(
git_dir=AUTHORITATIVE_GIT_DIR,
repository_identity=REPOSITORY_IDENTITY,
))
return self.sendj(data)
if path in ('/api/ver','/api/versions','/ver'):
return self.sendj({'tags':sh(['tag','--list','V*'])['stdout'].splitlines(),'versions_dir':[p.name for p in (WS/'versions').glob('*')],'head':sh(['rev-parse','--short','HEAD'])['stdout']})
snapshot = repository_snapshot(
git_dir=AUTHORITATIVE_GIT_DIR,
repository_identity=REPOSITORY_IDENTITY,
)
if not snapshot['repository_available']:
return self.sendj({
'repository_available': False,
'query_error': snapshot['query_error'],
'registry_versions': [p.name for p in (WS/'versions').glob('*')],
'local_authoritative_tags': [],
}, 503)
try:
tags = authoritative_tags(git_dir=AUTHORITATIVE_GIT_DIR)
except AuthoritativeGitError as exc:
return self.sendj({
'repository_available': False,
'query_error': str(exc),
'registry_versions': [p.name for p in (WS/'versions').glob('*')],
'local_authoritative_tags': [],
}, 503)
registry = [p.name for p in (WS/'versions').glob('*')]
return self.sendj({
'registry_versions': registry,
'local_authoritative_tags': tags,
'repository_available': True,
'query_error': None,
'tags': [item['name'] for item in tags],
'versions_dir': registry,
'head': snapshot['authoritative_head_oid'],
'authoritative_head_oid': snapshot['authoritative_head_oid'],
})
if path in ('/api/diff','/diff'):
frm=(q.get('from') or ['HEAD~1'])[0]; to=(q.get('to') or ['HEAD'])[0]; return self.sendj({'from':frm,'to':to,'diff':sh(['diff',frm,to])})
if path in ('/api/patch','/api/patches','/api/branches','/patch'): return self.sendj({'patches':patches(),'branches':sh(['branch','--format','%(refname:short)'])['stdout'].splitlines()})
frm=(q.get('from') or [''])[0]
to=(q.get('to') or [''])[0]
try:
diff=authoritative_diff(frm, to, git_dir=required_authoritative_git_dir())
except ValueError as exc:
return self.sendj({'error':redact(exc)},400)
except AuthoritativeGitNotFound as exc:
return self.sendj({'error':redact(exc)},404)
except AuthoritativeGitOutputTooLarge as exc:
return self.sendj({'error':redact(exc)},413)
except (AuthoritativeGitError, RuntimeError) as exc:
return self.sendj({'error':redact(exc)},503)
return self.sendj({'from':frm,'to':to,'diff':diff})
if path in ('/api/patch','/api/patches','/api/branches','/patch'):
snapshot = repository_snapshot(
git_dir=AUTHORITATIVE_GIT_DIR,
repository_identity=REPOSITORY_IDENTITY,
)
if not snapshot['repository_available']:
return self.sendj({
'repository_available': False,
'query_error': snapshot['query_error'],
'metadata_patches': patches(),
'authoritative_branches': [],
}, 503)
try:
branches = authoritative_branches(git_dir=AUTHORITATIVE_GIT_DIR)
except AuthoritativeGitError as exc:
return self.sendj({
'repository_available': False,
'query_error': str(exc),
'metadata_patches': patches(),
'authoritative_branches': [],
}, 503)
metadata = patches()
branch_names = {item['name'] for item in branches}
metadata_names = {
item.get('branch') for item in metadata
if isinstance(item, dict) and item.get('branch')
}
orphan = [
item for item in metadata
if item.get('branch') and item.get('branch') not in branch_names
]
missing = [
item for item in branches
if item['name'] not in metadata_names
]
return self.sendj({
'metadata_patches': metadata,
'authoritative_branches': branches,
'orphan_metadata': orphan,
'branches_without_metadata': missing,
'repository_available': True,
'query_error': None,
'patches': metadata,
'branches': [item['name'] for item in branches],
})
if path in ('/api/model','/model'): return self.sendj({'base':BASE_MODELS,'custom':model_docs(),'priority':[jload(p,{}) for p in sorted((WS/'config'/'model_priority').glob('*.json'))]})
if path in ('/api/run','/api/runtime-status','/run'):
svc=subprocess.run(['systemctl','is-active','aios-gitops-model-api'], text=True, capture_output=True)
return self.sendj({'service':'aios-gitops-model-api','status':svc.stdout.strip() or svc.stderr.strip(),'workspace_branch':sh(['rev-parse','--abbrev-ref','HEAD'])['stdout']})
snapshot = repository_snapshot(
git_dir=AUTHORITATIVE_GIT_DIR,
repository_identity=REPOSITORY_IDENTITY,
)
workspace_branch = None
if (WS / '.git').exists():
result = sh(['rev-parse','--abbrev-ref','HEAD'])
workspace_branch = result['stdout'] or None
payload = {
'service':'aios-gitops-model-api',
'status':svc.stdout.strip() or svc.stderr.strip(),
'workspace_branch':workspace_branch,
**runtime_release_info(),
**snapshot,
'writes_enabled': str(os.getenv('AIOS_GITOPS_WRITES_ENABLED','false')).lower() in {'1','true','yes','on'},
}
return self.sendj(payload, 200 if snapshot['repository_available'] else 503)
if path in ('/api/action-monitor','/action-monitor'):
latest=monitor.latest()
ldict={'event_id':latest.event_id,'action':latest.action,'error':latest.error,'context':latest.context,'created_at':latest.created_at} if latest else None
return self.sendj({'events':[{"event_id":e.event_id,"action":e.action,"error":e.error,"context":e.context,"created_at":e.created_at} for e in monitor.list_events()],'latest':ldict})
if path == '/api/tag-publication-status':
version=(q.get('version') or [''])[0]
try:
version=validate_version(version)
status=publication_publisher().get_tag_publication_status(version)
except ValueError:
return self.sendj({'error':'invalid release version'},400)
return self.sendj(status)
if path == '/api/release-consistency':
request=publication_request_from_query(q)
return self.sendj(publication_publisher().get_release_consistency(request))
if path == '/api/release-acceptance':
request=publication_request_from_query(q)
return self.sendj(publication_publisher().run_release_acceptance(request))
if path in (
'/getReleaseCandidate',
'/getReleasePlan',
'/getReleaseAcceptance',
'/getApprovalEnvelope',
'/getReleaseSaga',
'/getCapabilityStatus',
):
candidate_id=(q.get('candidate_id') or [''])[0]
if not candidate_id:
return self.sendj({'error':'candidate_id is required'},400)
service=silent_release_service()
if path == '/getReleaseCandidate':
return self.sendj(
service.get_release_candidate(candidate_id)
)
if path == '/getApprovalEnvelope':
return self.sendj(
service.get_approval_envelope(candidate_id)
)
if path == '/getReleasePlan':
return self.sendj(service.get_release_plan(candidate_id))
if path == '/getReleaseAcceptance':
return self.sendj(service.get_acceptance(candidate_id))
if path == '/getCapabilityStatus':
return self.sendj(
service.get_capability_status(candidate_id)
)
return self.sendj(service.get_release_saga(candidate_id))
if path == '/getRecoveryStatus':
return self.sendj(
silent_release_service().get_recovery_status()
)
# Admin AI Evolution Dashboard
if path in ('/admin/ai-evolution','/admin/ai-evolution/'):
return self.ai_evolution_page()
if path in ('/admin/ai-evolution/api/data'):
return self.ai_evolution_data()
return self.sendj({'error':'not_found','path':path},404)
except FileNotFoundError:
return self.sendj({'error':'release candidate not found'},404)
except ValueError as e:
error=redact(e)
monitor.record_failure('do_GET', error, {'path':path})
return self.sendj({'error':error},400)
except Exception as e:
monitor.record_failure('do_GET', str(e), {'path':path})
return self.sendj({'error':str(e)},500)
error=redact(e)
monitor.record_failure('do_GET', error, {'path':path})
return self.sendj({'error':error},500)
def do_PUT(self):
path=urllib.parse.urlparse(self.path).path.rstrip('/'); data=self.body()
path=urllib.parse.urlparse(self.path).path.rstrip('/')
if reject_non_read_http(self, 'PUT', path): return
data=self.body()
if path == '/api/model-priority': return self.model_priority(data)
return self.sendj({'error':'not_found','path':path},404)
def do_POST(self):
path=urllib.parse.urlparse(self.path).path.rstrip('/'); data=self.body()
path=urllib.parse.urlparse(self.path).path.rstrip('/')
if reject_non_read_http(self, 'POST', path): return
data=self.body()
try:
if path == '/createReleaseCandidate':
a=self.need('release:candidate')
if not a: return
return self.sendj(
silent_release_service().create_release_candidate(data)
)
if path == '/createReleaseIntent':
a=self.need('release:candidate')
if not a: return
return self.sendj(
silent_release_service().create_release_intent(data)
)
if path in ('/submitOwnerApproval','/submitSignedApproval'):
a=self.need('release:approve')
if not a: return
return self.sendj(
silent_release_service().submit_owner_approval(data)
)
if path == '/startDeployment':
a=self.need('release:deploy')
if not a: return
return self.sendj(
silent_release_service().start_deployment(
str(data.get('candidate_id') or '')
)
)
if path in ('/api/branch','/api/create-branch'): return self.branch(data)
if path in ('/api/file','/api/commit-file'): return self.file(data)
if path == '/api/commit': return self.commit(data)
@@ -226,9 +634,30 @@ class H(BaseHTTPRequestHandler):
if path == '/api/model-priority': return self.model_priority(data)
if path == '/api/nl': return self.nl(data)
return self.sendj({'error':'not_found','path':path},404)
except (ValueError, FileNotFoundError) as e:
error=redact(e)
monitor.record_failure('do_POST', error, {'path':path})
return self.sendj({'error':error},400)
except CapabilityAuthorizationError as e:
error=redact(e)
monitor.record_failure('do_POST', error, {'path':path})
return self.sendj({'error':error},403)
except SagaConflict as e:
error=redact(e)
monitor.record_failure('do_POST', error, {'path':path})
return self.sendj({'error':error},409)
except Exception as e:
monitor.record_failure('do_POST', str(e), {'path':path})
return self.sendj({'error':str(e)},500)
error=redact(e)
monitor.record_failure('do_POST', error, {'path':path})
return self.sendj({'error':error},500)
def do_PATCH(self):
path=urllib.parse.urlparse(self.path).path.rstrip('/')
if reject_non_read_http(self, 'PATCH', path): return
return self.sendj({'error':'not_found','path':path},404)
def do_DELETE(self):
path=urllib.parse.urlparse(self.path).path.rstrip('/')
if reject_non_read_http(self, 'DELETE', path): return
return self.sendj({'error':'not_found','path':path},404)
def branch(self,data):
a=self.need('branch:create');
if not a: return
@@ -252,12 +681,41 @@ class H(BaseHTTPRequestHandler):
if not a: return
ver=data.get('version') or data.get('tag')
if not re.match(r'^V\d+R\d+C\d+(-[A-Za-z0-9_.-]+)?$', ver or ''): return self.sendj({'error':'version must match VxRxCx'},400)
if data.get('confirm') != True:
self.sendj({'status':'confirm_required','operation':'tag','hint':'This operation creates a Git tag. Confirm to proceed.','x-openai-isConsequential':True}, 428)
return
if not data.get('target_oid') or not data.get('evidence_closure_oid') or not data.get('approval_plan_id'):
return self.sendj({
'error':'production_tag_evidence_required',
'required':['version','target_oid','evidence_closure_oid','approval_plan_id'],
},400)
try:
target_oid=resolve_commit_oid(data.get('target_oid'))
evidence_oid=resolve_commit_oid(data.get('evidence_closure_oid'), 'evidence_closure_oid')
except ValueError as exc:
return self.sendj({'error':'invalid_tag_target','detail':str(exc)},400)
if a['role'] != 'owner' or not data.get('execute'):
b=checkout(data.get('branch') or f'request/tag-{safe(ver)}', 'main', True); req={'version':ver,'requested_by':a['account'],'approval_required':True,'created_at':now()}; r=write_json(f'baseline/tag_requests/{safe(ver)}.json', req); c=commit([r], f'chore(chatgpt): request tag {ver}'); return self.sendj({'status':'approval_required','branch':b,'commit':c})
out=sh(['tag','-a',ver,'-m',data.get('message') or f'release {ver}'], True); self.sendj({'status':'tagged','version':ver,'git':out,'sync':sync_tag(ver)})
b=checkout(data.get('branch') or f'request/tag-{safe(ver)}', 'main', True); req={'version':ver,'target_oid':target_oid,'evidence_closure_oid':evidence_oid,'approval_plan_id':data.get('approval_plan_id'),'requested_by':a['account'],'approval_required':True,'created_at':now()}; r=write_json(f'baseline/tag_requests/{safe(ver)}.json', req); c=commit([r], f'chore(chatgpt): request tag {ver}'); return self.sendj({'status':'approval_required','branch':b,'request':req,'commit':c})
request=PublicationRequest(ver,target_oid,evidence_oid,str(data.get('approval_plan_id')))
main_before=sh(['rev-parse','refs/heads/main'], True)['stdout']
publisher=publication_publisher()
try:
publication=publisher.publish(request)
except PublicationManualOwnerReviewRequired as exc:
audit(a['account'],'tag_manual_owner_review_required',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':redact(exc)})
return self.sendj({'status':'MANUAL_OWNER_REVIEW_REQUIRED','error':redact(exc),'main_changed':False,'force_push':False},409)
except PublicationConflict as exc:
audit(a['account'],'tag_conflict',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':str(exc)})
return self.sendj({'status':'RECONCILIATION_REQUIRED','error':str(exc),'main_changed':False,'force_push':False},409)
except PublicationPending as exc:
audit(a['account'],'tag_pending',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':str(exc)})
return self.sendj({'status':'REMOTE_PUSH_PENDING','error':str(exc),'main_changed':False,'force_push':False},503)
except PublicationReconciliationRequired as exc:
audit(a['account'],'tag_reconciliation_required',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':str(exc)})
return self.sendj({'status':'RECONCILIATION_REQUIRED','error':str(exc),'main_changed':False,'force_push':False},502)
main_after=sh(['rev-parse','refs/heads/main'], True)['stdout']
if main_after != main_before:
raise RuntimeError('main changed during tag operation')
result={'status':publication['state'],'version':ver,'tag_name':ver,'tag_oid':publication['tag_oid'],'target_oid':target_oid,'expected_target_oid':target_oid,'evidence_closure_oid':evidence_oid,'approval_plan_id':data.get('approval_plan_id'),'workspace_head':sh(['rev-parse','HEAD'],True)['stdout'],'main_oid_before':main_before,'main_oid_after':main_after,'main_changed':False,'force_push':False,'publication':publication}
audit(a['account'],'tag',ver,result)
self.sendj(result)
def rollback(self,data):
a=self.need('rollback:request');
if not a: return
@@ -352,7 +810,10 @@ return{vs,cmds,ar,cmd,cdet,tot,sok,sfail,runs,baseline,refreshMsg,loadCmd,selVer
cmd_filter=(params.get('command') or [None])[0]
bl=jload(WS/'baseline'/'current.json',{})
current_ver=bl.get('current_baseline','V1R3C1')
tags=sh(['tag','--list','V*'])['stdout'].splitlines() if WS.exists() else []
try:
tags=[item['name'] for item in authoritative_tags(git_dir=required_authoritative_git_dir()) if str(item['name']).startswith('V')]
except (AuthoritativeGitError, RuntimeError) as exc:
return self.sendj({'error':redact(exc),'repository_available':False},503)
versions=[]
if (WS/'baseline'/'promotions').exists():
for p in sorted((WS/'baseline'/'promotions').glob('*.json')):
@@ -390,9 +851,9 @@ return{vs,cmds,ar,cmd,cdet,tot,sok,sfail,runs,baseline,refreshMsg,loadCmd,selVer
def api_spec():
return {'version':'V1R1C0-chatgpt-actions','openapi':'/api/openapi.yaml','read':['GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /admin/ai-evolution'],'write':['POST /api/branch','POST /api/file','POST /api/commit','POST /api/patch','POST /api/tag','POST /api/rollback','POST /api/model','PUT /api/model-priority','POST /api/nl'],'policy':{'bearer_required_for_write':True,'direct_main_push':False,'delete_tag':False,'owner_approval_required_for_v_level':True,'api_keys_in_git':False,'git_secret_field':'secret_ref','online_git_sync':True}}
return {'version':'V1R1C0-chatgpt-actions','openapi':'/api/openapi.yaml','read':['GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /getReleaseCandidate','GET /getApprovalEnvelope','GET /getReleaseSaga','GET /admin/ai-evolution'],'write':['POST /api/branch','POST /api/file','POST /api/commit','POST /api/patch','POST /api/tag','POST /api/rollback','POST /api/model','PUT /api/model-priority','POST /api/nl','POST /createReleaseCandidate','POST /submitOwnerApproval','POST /startDeployment'],'policy':{'bearer_required_for_write':True,'direct_main_push':False,'delete_tag':False,'owner_approval_required_for_v_level':True,'api_keys_in_git':False,'git_secret_field':'secret_ref','online_git_sync':True,'silent_release_execution_enabled':SILENT_RELEASE_EXECUTION_ENABLED,'silent_release_shadow_default':True}}
def main():
print(f'AIOS ChatGPT GitOps adapter listening on {HOST}:{PORT}')
ThreadingHTTPServer((HOST,PORT), H).serve_forever()
if __name__ == '__main__': main()
if __name__ == '__main__': main()
@@ -0,0 +1,52 @@
#!/usr/bin/env python3
"""Fail-closed policy for in-process Git mutation handlers."""
from __future__ import annotations
import os
from dataclasses import dataclass
from pathlib import Path
from typing import Mapping
_TRUE = frozenset({"1", "true", "yes", "on"})
@dataclass(frozen=True)
class GitWriteDecision:
allowed: bool
status_code: int
error: str
reason: str
workspace: str
def payload(self) -> dict[str, str]:
return {
"status": "allowed" if self.allowed else "blocked",
"error": self.error,
"reason": self.reason,
"workspace": self.workspace,
}
def _real(path: Path) -> Path:
return Path(os.path.realpath(os.path.abspath(str(path))))
def evaluate_git_write(workspace: Path | str, env: Mapping[str, str] | None = None) -> GitWriteDecision:
values = os.environ if env is None else env
lexical = Path(os.path.abspath(str(workspace)))
canonical = _real(lexical)
shown = str(lexical)
if str(values.get("AIOS_GITOPS_WRITES_ENABLED", "false")).strip().lower() not in _TRUE:
return GitWriteDecision(False, 423, "gitops_writes_disabled", "AIOS_GITOPS_WRITES_ENABLED is false", shown)
if lexical != canonical:
return GitWriteDecision(False, 409, "workspace_symlink_forbidden", "workspace must be a canonical non-symlink path", shown)
controller = _real(Path(values.get("AIOS_GITOPS_CONTROLLER_PATH", "/data/aios-gitops/worktrees/controller")))
role = str(values.get("AIOS_GITOPS_WORKSPACE_ROLE", "")).strip().lower()
if canonical == controller or role == "runtime-anchor":
return GitWriteDecision(False, 423, "runtime_anchor_read_only", "controller/runtime-anchor is read-only", str(canonical))
writer_root = _real(Path(values.get("AIOS_GITOPS_APPROVED_WRITER_ROOT", "/data/aios-gitops/worktrees")))
try:
canonical.relative_to(writer_root)
except ValueError:
return GitWriteDecision(False, 409, "workspace_not_approved_writer", "workspace is outside the approved writer root", str(canonical))
return GitWriteDecision(True, 200, "", "approved isolated writer", str(canonical))
@@ -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 +1,316 @@
"""Task-scoped hardened wrapper around the existing Action API."""
from __future__ import annotations
import json
import os
import subprocess
from pathlib import Path
import urllib.parse
import aios_chatgpt_actions_api as api
import aios_isolated_writer_policy as policy
from isolated_writer_authz import AuthorizationError, authorize
from isolated_writer_commit_file import AtomicCommitFile, CommitFileError, OperationLedger
from isolated_writer_token_registry import TokenRegistry
_reject = api.reject_non_read_http
_write_file = api.write_file
_sync_branch = api.sync_branch
_original_do_get = api.H.do_GET
api.OPENAPI = Path(os.getenv("AIOS_GITOPS_ISOLATED_WRITER_OPENAPI", str(api.OPENAPI)))
def _registry() -> TokenRegistry:
return TokenRegistry(Path(os.environ["AIOS_GITOPS_TOKEN_REGISTRY_V2"]))
def _atomic_writer() -> AtomicCommitFile:
return AtomicCommitFile(
workspace=api.WS,
bare_repo=api.BARE_REPO,
ledger=OperationLedger(Path(os.environ["AIOS_GITOPS_WRITER_OPERATION_LEDGER"])),
remote=os.getenv("AIOS_GITOPS_GITEA_PUSH_REMOTE", ""),
audit=policy.append_audit_record,
)
def _bearer(handler) -> str:
value = handler.headers.get("Authorization", "")
return value[7:].strip() if value.startswith("Bearer ") else ""
def _authorize(handler, *, method: str, path: str, branch=None, target_path=None):
grant = authorize(
_registry(),
_bearer(handler),
method=method,
path=path,
source_ip=str(handler.client_address[0]),
workspace=api.WS,
branch=branch,
target_path=target_path,
)
grant.record["_source_ip"] = str(handler.client_address[0])
return grant
def _authorization_error(handler, exc: AuthorizationError):
return handler.sendj({"error": exc.code}, exc.status)
def _isolated_runtime_status(handler):
branch = api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"]
head = api.sh(["rev-parse", "HEAD"], True)["stdout"]
return handler.sendj({
"service": os.getenv(
"AIOS_GITOPS_SERVICE_AUDIENCE",
"aios-isolated-writer.service",
),
"status": "active",
"runtime_role": os.getenv("AIOS_GITOPS_RUNTIME_ROLE"),
"workspace_role": os.getenv("AIOS_GITOPS_WORKSPACE_ROLE"),
"writes_enabled": os.getenv("AIOS_GITOPS_WRITES_ENABLED", "").lower()
in {"1", "true", "yes", "on"},
"allowed_branch": policy.allowed_branch(),
"approved_base_oid": policy.allowed_base_oid(),
"workspace_branch": branch,
"workspace_head_oid": head,
"repository_identity": os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY"),
"token_policy_version": 2,
"atomic_commit_file": True,
"path_policy_sha256": policy.configured_path_policy_sha256(),
})
def _isolated_do_get(self):
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if path in {"/health", "/api/health"}:
return self.sendj({
"status": "ok",
"service": os.getenv(
"AIOS_GITOPS_SERVICE_AUDIENCE",
"aios-isolated-writer.service",
),
})
if path not in {"/api/runtime-status", "/api/baseline", "/api/patches"}:
return self.sendj({"error": "isolated_writer_operation_forbidden"}, 403)
try:
_authorize(self, method="GET", path=path)
except AuthorizationError as exc:
return _authorization_error(self, exc)
if path == "/api/runtime-status":
return _isolated_runtime_status(self)
return _original_do_get(self)
def _read_commit_file_body(handler):
try:
length = int(handler.headers.get("Content-Length", "0"))
except ValueError:
raise CommitFileError("writer_content_length_rejected") from None
if length <= 0:
raise CommitFileError("writer_request_object_required")
if length > 1_100_000:
raise CommitFileError("writer_request_too_large", 413)
raw = handler.rfile.read(length)
try:
value = json.loads(raw.decode("utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
raise CommitFileError("writer_request_json_rejected") from None
if not isinstance(value, dict):
raise CommitFileError("writer_request_object_required")
return value
def _isolated_do_post(self):
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
if path != "/api/commit-file":
return self.sendj({"error": "isolated_writer_operation_forbidden"}, 403)
try:
data = _read_commit_file_body(self)
branch = str(data.get("branch") or "")
target_path = str(data.get("path") or "")
grant = _authorize(
self,
method="POST",
path=path,
branch=branch,
target_path=target_path,
)
if api.content_has_secret(str(data.get("content") or "")):
raise CommitFileError("writer_secret_content_rejected", 403)
result = _atomic_writer().execute(grant, data)
return self.sendj(result)
except AuthorizationError as exc:
return _authorization_error(self, exc)
except CommitFileError as exc:
return self.sendj({"error": exc.code}, exc.status)
except PermissionError:
return self.sendj({"error": "isolated_writer_policy_rejected"}, 403)
def reject_non_read_http(handler, method: str, path: str) -> bool:
if _reject(handler, method, path):
return True
try:
policy.validate_endpoint(method, path, api.WS, api.BARE_REPO)
return False
except PermissionError as exc:
handler.sendj({"error": str(exc)}, 403)
return True
def checkout(branch, base="main", create=False):
api.ensure_git()
target = api.branch_name(branch)
policy.validate_branch_request({"branch": target, "base": base})
exists = api.sh(["rev-parse", "--verify", target])["code"] == 0
if exists:
if api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"] != target:
api.sh(["checkout", target], True)
elif create:
api.sh(["checkout", "-b", target, base], True)
else:
raise PermissionError("isolated_writer_branch_missing")
policy.require_service_invariants(api.WS, api.BARE_REPO)
return target
def write_file(path, content):
policy.validate_path(path, api.WS)
return _write_file(path, content)
def sync_branch(branch: str):
policy.validate_sync_branch(branch)
local = _sync_branch(branch)
remote = os.getenv("AIOS_GITOPS_GITEA_PUSH_REMOTE", "").strip()
if remote != "gitea-http":
raise PermissionError("isolated_writer_gitea_remote_rejected")
head = api.sh(["rev-parse", "HEAD"], True)["stdout"]
pushed = subprocess.run(
["git", "push", "--porcelain", remote, f"HEAD:refs/heads/{branch}"],
cwd=api.WS,
text=True,
capture_output=True,
)
if pushed.returncode != 0:
raise RuntimeError("isolated_writer_gitea_push_failed")
verified = subprocess.run(
["git", "ls-remote", "--heads", remote, f"refs/heads/{branch}"],
cwd=api.WS,
text=True,
capture_output=True,
)
if verified.returncode != 0:
raise RuntimeError("isolated_writer_gitea_verification_failed")
fields = verified.stdout.strip().split()
if len(fields) != 2 or fields[0] != head or fields[1] != f"refs/heads/{branch}":
raise RuntimeError("isolated_writer_gitea_oid_mismatch")
return {
"status": "verified",
"target": "authoritative-bare+gitea",
"branch": branch,
"oid": head,
"local": local.get("status"),
}
def commit(paths, msg):
policy.validate_commit_paths(paths, api.WS)
api.ensure_git()
selected = [api.relpath(p) for p in paths] if paths else ["."]
api.sh(["add", *selected], True)
policy.validate_staged_paths(api.WS)
branch = api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"]
if not api.sh(["status", "--short"])["stdout"]:
return {"status": "no_changes", "branch": branch, "sync": sync_branch(branch)}
out = api.sh(["commit", "-m", msg], True)
branch = api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"]
return {
"status": "committed",
"branch": branch,
"rev": api.sh(["rev-parse", "--short", "HEAD"], True)["stdout"],
"git": out,
"sync": sync_branch(branch),
}
def audit(actor, action, target, payload):
policy.append_audit_record(
{
"at": api.now(),
"actor": actor,
"action": action,
"target": target,
"payload": api.sanitize(payload),
}
)
def _validate_request(self, data, validate):
try:
validate(data)
return True
except PermissionError as exc:
self.sendj({"error": str(exc)}, 403)
return False
def _checked_branch(self, data):
if not _validate_request(self, data, policy.validate_branch_request):
return
return _branch(self, data)
def _checked_file(self, data):
data = dict(data)
data.setdefault("branch", policy.allowed_branch())
if not _validate_request(self, data, policy.validate_branch_request):
return
if not _validate_request(
self,
{"path": data.get("path", "")},
lambda item: policy.validate_path(item["path"], api.WS),
):
return
return _file(self, data)
def _checked_commit(self, data):
data = dict(data)
data.setdefault("branch", policy.allowed_branch())
if not _validate_request(self, data, policy.validate_branch_request):
return
return _commit(self, data)
def _checked_patch(self, data):
data = dict(data)
data["branch"] = policy.allowed_branch()
if not _validate_request(self, data, policy.validate_branch_request):
return
return _patch(self, data)
_branch, _file, _commit, _patch = api.H.branch, api.H.file, api.H.commit, api.H.patch
api.reject_non_read_http = reject_non_read_http
api.checkout, api.write_file, api.sync_branch, api.commit, api.audit = (
checkout,
write_file,
sync_branch,
commit,
audit,
)
api.H.branch, api.H.file, api.H.commit, api.H.patch = (
_checked_branch,
_checked_file,
_checked_commit,
_checked_patch,
)
api.H.do_GET = _isolated_do_get
api.H.do_POST = _isolated_do_post
if __name__ == "__main__":
policy.require_service_invariants(api.WS, api.BARE_REPO)
api.ThreadingHTTPServer((api.HOST, api.PORT), api.H).serve_forever()
@@ -0,0 +1,310 @@
"""Fail-closed policy used only by the task-scoped Action writer."""
from __future__ import annotations
import os
import json
import stat
import subprocess
import re
from pathlib import Path, PurePosixPath, PureWindowsPath
from urllib.parse import unquote
import isolated_writer_path_policy as path_policy
WRITE_ENDPOINTS = frozenset({"/api/commit-file"})
ALLOWED_ROOTS = (
"active-runtime",
"docs",
"patches",
"reports",
"scripts",
"test",
"tests",
)
DENIED_ROOTS = ("baseline", "config", "deploy", "deployments", "ops", "runtime", "services")
_TRUE = frozenset({"1", "true", "yes", "on"})
_FALSE = frozenset({"0", "false", "no", "off"})
_DENY_FLAGS = (
"AIOS_GITOPS_ALLOW_MAIN_WRITE",
"AIOS_GITOPS_ALLOW_TAG_WRITE",
"AIOS_GITOPS_ALLOW_BASELINE_WRITE",
"AIOS_GITOPS_ALLOW_REGISTRY_WRITE",
"AIOS_GITOPS_ALLOW_ROLLBACK",
"AIOS_GITOPS_ALLOW_DEPLOYMENT",
)
def enforcement_required() -> bool:
return os.getenv("AIOS_GITOPS_ISOLATED_WRITER_ENFORCEMENT", "") == "required"
def allowed_branch() -> str:
value = os.getenv("AIOS_GITOPS_ALLOWED_BRANCH", "").strip()
if not value:
raise PermissionError("isolated_writer_missing_allowed_branch")
return value
def allowed_base_oid() -> str:
value = os.getenv("AIOS_GITOPS_ALLOWED_BASE_OID", "").strip().lower()
if len(value) != 40 or any(ch not in "0123456789abcdef" for ch in value):
raise PermissionError("isolated_writer_invalid_allowed_base_oid")
return value
def _git(workspace: Path, *args: str) -> str:
result = subprocess.run(["git", *args], cwd=workspace, text=True, capture_output=True)
if result.returncode != 0:
raise PermissionError("isolated_writer_git_validation_failed")
return result.stdout.strip()
def require_service_invariants(workspace: Path, bare_repo: Path) -> None:
if not enforcement_required():
return
if os.getenv("AIOS_GITOPS_WRITES_ENABLED", "").strip().lower() not in _TRUE:
raise PermissionError("isolated_writer_write_gate_required")
if os.getenv("AIOS_GITOPS_RUNTIME_ROLE", "") != "isolated-writer":
raise PermissionError("isolated_writer_role_required")
if os.getenv("AIOS_GITOPS_WORKSPACE_ROLE", "") != "isolated-writer":
raise PermissionError("isolated_writer_workspace_role_required")
if os.getenv("AIOS_GITOPS_TOKEN_POLICY_VERSION_REQUIRED", "") != "2":
raise PermissionError("isolated_writer_token_policy_v2_required")
if not os.getenv("AIOS_GITOPS_SERVICE_AUDIENCE", "").strip():
raise PermissionError("isolated_writer_service_audience_required")
if not os.getenv("AIOS_GITOPS_TOKEN_REGISTRY_V2", "").strip():
raise PermissionError("isolated_writer_token_registry_required")
if not os.getenv("AIOS_GITOPS_WRITER_OPERATION_LEDGER", "").strip():
raise PermissionError("isolated_writer_operation_ledger_required")
path_policy.configured_path_policy()
for name in _DENY_FLAGS:
if os.getenv(name, "").strip().lower() not in _FALSE:
raise PermissionError("isolated_writer_forbidden_capability_flag")
if os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", "") != "aios/aios":
raise PermissionError("isolated_writer_repository_identity_rejected")
configured_bare_value = os.getenv("AIOS_GITOPS_AUTHORITATIVE_GIT_DIR", "").strip()
if not configured_bare_value:
raise PermissionError("isolated_writer_authoritative_repo_rejected")
configured_bare = Path(configured_bare_value)
if configured_bare.resolve(strict=True) != bare_repo.resolve(strict=True):
raise PermissionError("isolated_writer_authoritative_repo_rejected")
writer_root_value = os.getenv("AIOS_GITOPS_APPROVED_WRITER_ROOT", "").strip()
if not writer_root_value:
raise PermissionError("isolated_writer_workspace_outside_approved_root")
writer_root = Path(writer_root_value).resolve(strict=True)
lexical_workspace = Path(os.path.abspath(str(workspace)))
canonical_workspace = lexical_workspace.resolve(strict=True)
if lexical_workspace != canonical_workspace:
raise PermissionError("isolated_writer_workspace_symlink_rejected")
try:
canonical_workspace.relative_to(writer_root)
except (ValueError, FileNotFoundError):
raise PermissionError("isolated_writer_workspace_outside_approved_root") from None
if _git(workspace, "rev-parse", "--abbrev-ref", "HEAD") != allowed_branch():
raise PermissionError("isolated_writer_current_branch_rejected")
approved_base = allowed_base_oid()
try:
_git(workspace, "cat-file", "-e", f"{approved_base}^{{commit}}")
subprocess.run(
["git", "merge-base", "--is-ancestor", approved_base, "HEAD"],
cwd=workspace,
check=True,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
)
except (PermissionError, subprocess.CalledProcessError):
raise PermissionError("isolated_writer_approved_base_not_ancestor") from None
if _git(workspace, "merge-base", approved_base, "HEAD") != approved_base:
raise PermissionError("isolated_writer_merge_base_rejected")
common = Path(_git(workspace, "rev-parse", "--git-common-dir"))
if not common.is_absolute():
common = (workspace / common).resolve()
if common.resolve() != bare_repo.resolve():
raise PermissionError("isolated_writer_common_repo_rejected")
def approved_audit_log_path() -> Path:
root_value = os.getenv("AIOS_GITOPS_APPROVED_AUDIT_ROOT", "").strip()
log_value = os.getenv("AIOS_GITOPS_AUDIT_LOG", "").strip()
if not root_value or not log_value:
raise PermissionError("isolated_writer_audit_path_missing")
lexical_root = Path(os.path.abspath(root_value))
lexical_log = Path(os.path.abspath(log_value))
root = lexical_root.resolve(strict=True)
if lexical_root != root or root.is_symlink() or not root.is_dir():
raise PermissionError("isolated_writer_audit_root_rejected")
try:
lexical_log.relative_to(root)
except ValueError:
raise PermissionError("isolated_writer_audit_path_outside_approved_root") from None
if lexical_log.parent.resolve(strict=True) != lexical_log.parent:
raise PermissionError("isolated_writer_audit_parent_symlink_rejected")
if lexical_log.exists() and lexical_log.is_symlink():
raise PermissionError("isolated_writer_audit_log_symlink_rejected")
os.chmod(root, 0o750)
os.chmod(lexical_log.parent, 0o750)
return lexical_log
def append_audit_record(record: dict) -> None:
path = approved_audit_log_path()
flags = os.O_WRONLY | os.O_APPEND | os.O_CREAT
if hasattr(os, "O_NOFOLLOW"):
flags |= os.O_NOFOLLOW
descriptor = os.open(path, flags, 0o600)
try:
info = os.fstat(descriptor)
if not stat.S_ISREG(info.st_mode):
raise PermissionError("isolated_writer_audit_log_not_regular")
os.fchmod(descriptor, 0o600)
line = json.dumps(
_audit_sanitize(record),
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
).encode("utf-8") + b"\n"
os.write(descriptor, line)
os.fsync(descriptor)
finally:
os.close(descriptor)
parent_fd = os.open(path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0))
try:
os.fsync(parent_fd)
finally:
os.close(parent_fd)
def _audit_sanitize(value):
if isinstance(value, dict):
return {
key: (
"[REDACTED]"
if any(
marker in str(key).lower()
for marker in (
"authorization",
"credential",
"password",
"secret",
"token",
"private_key",
)
)
and str(key).lower() != "token_id"
else _audit_sanitize(inner)
)
for key, inner in value.items()
}
if isinstance(value, list):
return [_audit_sanitize(item) for item in value]
if isinstance(value, str) and re.search(
r"(?i)(authorization\s*:\s*bearer|(?:token|password|secret)\s*[:=])",
value,
):
return "[REDACTED]"
return value
def validate_endpoint(method: str, path: str, workspace: Path, bare_repo: Path) -> None:
if not enforcement_required():
return
if method != "POST" or path not in WRITE_ENDPOINTS:
raise PermissionError("isolated_writer_operation_forbidden")
require_service_invariants(workspace, bare_repo)
def validate_branch_request(data: dict) -> None:
if not enforcement_required():
return
branch = allowed_branch() if "branch" not in data else str(data.get("branch") or "").strip()
if branch != allowed_branch():
raise PermissionError("isolated_writer_branch_rejected")
if str(data.get("base", "main")).strip() != "main":
raise PermissionError("isolated_writer_base_rejected")
if data.get("force") or data.get("force_push"):
raise PermissionError("isolated_writer_force_rejected")
def validate_path(path: str, workspace: Path | None = None) -> str:
if not isinstance(path, str):
raise PermissionError("isolated_writer_path_rejected")
value = path
if not value or value != value.strip() or "\x00" in value or "\\" in value:
raise PermissionError("isolated_writer_path_rejected")
try:
decoded = unquote(value, errors="strict")
except (UnicodeDecodeError, ValueError):
raise PermissionError("isolated_writer_path_rejected") from None
if decoded != value:
raise PermissionError("isolated_writer_path_rejected")
windows = PureWindowsPath(value)
posix = PurePosixPath(value)
parts = value.split("/")
if (
posix.is_absolute()
or windows.is_absolute()
or bool(windows.drive)
or any(part in {"", ".", ".."} for part in parts)
):
raise PermissionError("isolated_writer_path_rejected")
first = parts[0]
service_exact_path = False
if first in DENIED_ROOTS:
try:
path_policy.require_service_path("commit_file.atomic", value)
service_exact_path = True
except path_policy.PathPolicyError as exc:
raise PermissionError(str(exc)) from None
if value != "README.md" and first not in ALLOWED_ROOTS and not service_exact_path:
raise PermissionError("isolated_writer_path_outside_allowed_roots")
if workspace is not None:
lexical_root = Path(os.path.abspath(str(workspace)))
root = lexical_root.resolve(strict=True)
if lexical_root != root:
raise PermissionError("isolated_writer_workspace_symlink_rejected")
current = root
for part in parts:
current = current / part
if current.is_symlink():
raise PermissionError("isolated_writer_path_symlink_rejected")
candidate = (root / value).resolve(strict=False)
try:
candidate.relative_to(root)
except ValueError:
raise PermissionError("isolated_writer_path_escapes_workspace") from None
return value
def validate_content_for_path(path: str, content: str) -> None:
if path.split("/", 1)[0] not in DENIED_ROOTS:
return
try:
path_policy.validate_content("commit_file.atomic", path, content)
except path_policy.PathPolicyError as exc:
raise PermissionError(str(exc)) from None
def configured_path_policy_sha256() -> str | None:
try:
return path_policy.configured_path_policy_sha256()
except path_policy.PathPolicyError as exc:
raise PermissionError(str(exc)) from None
def validate_commit_paths(paths: list[str], workspace: Path | None = None) -> None:
if enforcement_required():
for path in paths:
if str(path).strip() != ".":
validate_path(str(path), workspace)
def validate_staged_paths(workspace: Path) -> None:
if not enforcement_required():
return
for path in _git(workspace, "diff", "--cached", "--name-only").splitlines():
validate_path(path, workspace)
def validate_sync_branch(branch: str) -> None:
if enforcement_required() and branch != allowed_branch():
raise PermissionError("isolated_writer_sync_branch_rejected")
@@ -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 {},
)
+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()
+355
View File
@@ -0,0 +1,355 @@
"""Fail-closed access to the authoritative bare Git repository."""
from __future__ import annotations
import os
import re
import subprocess
import urllib.parse
from pathlib import Path
from typing import Iterable
_ALLOWED_COMMANDS = frozenset(
{
"cat-file",
"config",
"diff",
"for-each-ref",
"ls-remote",
"merge-base",
"push",
"remote",
"rev-parse",
"show-ref",
"tag",
}
)
_OID_RE = re.compile(r"^[0-9a-f]{40}$")
_MAX_OUTPUT = 1_048_576
_TIMEOUT = 8.0
class AuthoritativeGitError(RuntimeError):
"""A fail-closed authoritative repository or ref query error."""
class AuthoritativeGitNotFound(AuthoritativeGitError):
"""A validated revision does not exist in the authoritative repository."""
class AuthoritativeGitOutputTooLarge(AuthoritativeGitError):
"""A controlled Git query exceeded the response-size boundary."""
def _redact(text: str) -> str:
value = str(text or "")
value = re.sub(r"(?i)(authorization\s*[:=]\s*)(?:bearer|token)\s+\S+", r"\1REDACTED", value)
value = re.sub(r"(?i)((?:access_)?token\s*[:=]\s*)\S+", r"\1REDACTED", value)
value = re.sub(r"(?i)(https?://[^/\s:@]+:)[^@\s/]+@", r"\1REDACTED@", value)
return value
def _configured_path(git_dir: str | Path | None = None) -> Path:
raw = str(git_dir or os.getenv("AIOS_GITOPS_AUTHORITATIVE_GIT_DIR", "")).strip()
if not raw:
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
path = Path(raw)
if not path.is_absolute() or ".." in path.parts:
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
try:
resolved = path.resolve(strict=True)
except OSError as exc:
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE") from exc
if not resolved.is_dir():
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
return resolved
def _run(
git_dir: Path,
args: list[str],
*,
check: bool,
timeout: float = _TIMEOUT,
) -> subprocess.CompletedProcess[str]:
if not args or args[0] not in _ALLOWED_COMMANDS:
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
try:
result = subprocess.run(
["git", "--git-dir", str(git_dir), *args],
text=True,
capture_output=True,
timeout=timeout,
env={**os.environ, "GIT_OPTIONAL_LOCKS": "0"},
)
except (OSError, subprocess.TimeoutExpired) as exc:
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED") from exc
if len(result.stdout) + len(result.stderr) > _MAX_OUTPUT:
raise AuthoritativeGitOutputTooLarge("GIT_OUTPUT_LIMIT_EXCEEDED")
if check and result.returncode != 0:
detail = _redact(result.stderr.strip() or result.stdout.strip())
raise AuthoritativeGitError(
"GIT_REF_QUERY_FAILED" + (f": {detail[:160]}" if detail else "")
)
return result
def _repository_identity_from_remote(url: str) -> str:
value = str(url or "").strip().split("?", 1)[0].rstrip("/")
if not value:
return ""
if "://" in value:
value = urllib.parse.urlparse(value).path
elif ":" in value:
value = value.rsplit(":", 1)[1]
value = value.rsplit("@", 1)[-1].strip("/")
value = re.sub(r"\.git$", "", value, flags=re.IGNORECASE)
parts = [part for part in value.split("/") if part]
if len(parts) >= 2:
value = "/".join(parts[-2:])
return value.strip("/").lower()
def verify_repository(
git_dir: str | Path | None = None,
repository_identity: str | None = None,
) -> tuple[Path, str]:
path = _configured_path(git_dir)
expected = str(
repository_identity
or os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", "")
).strip().strip("/")
if not expected or expected.count("/") != 1:
raise AuthoritativeGitError("REPOSITORY_IDENTITY_MISMATCH")
bare = _run(path, ["rev-parse", "--is-bare-repository"], check=True)
if bare.stdout.strip().lower() != "true":
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
remote = _run(path, ["config", "--get", "remote.gitea.url"], check=False)
actual = _repository_identity_from_remote(remote.stdout)
if actual != expected.lower():
raise AuthoritativeGitError("REPOSITORY_IDENTITY_MISMATCH")
return path, expected
def run_authoritative_git(
args: list[str],
*,
check: bool = True,
git_dir: str | Path | None = None,
timeout: float = _TIMEOUT,
) -> subprocess.CompletedProcess[str]:
path, _ = verify_repository(git_dir=git_dir)
return _run(path, list(args), check=check, timeout=timeout)
def authoritative_head_oid(
*,
git_dir: str | Path | None = None,
) -> str:
result = run_authoritative_git(["rev-parse", "--verify", "refs/heads/main"], git_dir=git_dir)
oid = result.stdout.strip().lower()
if not _OID_RE.fullmatch(oid):
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
return oid
def authoritative_tags(
*,
git_dir: str | Path | None = None,
) -> list[dict[str, str | None]]:
result = run_authoritative_git(
[
"for-each-ref",
"refs/tags",
"--format=%(refname:strip=2)\t%(objectname)\t%(objecttype)",
],
git_dir=git_dir,
)
tags: list[dict[str, str | None]] = []
for line in result.stdout.splitlines():
name, oid, object_type = (line.split("\t", 2) + ["", ""])[:3]
if not name or not _OID_RE.fullmatch(oid.lower()):
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
peeled_result = run_authoritative_git(
["rev-parse", "--verify", f"refs/tags/{name}^{{commit}}"],
git_dir=git_dir,
)
peeled = peeled_result.stdout.strip().lower()
if not _OID_RE.fullmatch(peeled):
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
tags.append(
{
"name": name,
"tag_oid": oid.lower(),
"object_type": object_type,
"peeled_target_oid": peeled,
}
)
return tags
def authoritative_branches(
*,
git_dir: str | Path | None = None,
) -> list[dict[str, str]]:
result = run_authoritative_git(
[
"for-each-ref",
"refs/heads",
"--format=%(refname:strip=2)\t%(objectname)",
],
git_dir=git_dir,
)
branches: list[dict[str, str]] = []
for line in result.stdout.splitlines():
name, oid = (line.split("\t", 1) + [""])[:2]
if not name or not _OID_RE.fullmatch(oid.lower()):
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
branches.append({"name": name, "oid": oid.lower()})
return branches
def authoritative_commit(
oid: str,
*,
git_dir: str | Path | None = None,
) -> str:
value = str(oid or "").strip().lower()
if not _OID_RE.fullmatch(value):
raise ValueError("commit OID must be a full 40-character value")
result = run_authoritative_git(
["rev-parse", "--verify", f"{value}^{{commit}}"],
git_dir=git_dir,
)
resolved = result.stdout.strip().lower()
if resolved != value:
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
return resolved
def authoritative_lineage(
ancestor: str,
descendant: str,
*,
git_dir: str | Path | None = None,
) -> None:
authoritative_commit(ancestor, git_dir=git_dir)
authoritative_commit(descendant, git_dir=git_dir)
result = run_authoritative_git(
["merge-base", "--is-ancestor", ancestor, descendant],
check=False,
git_dir=git_dir,
)
if result.returncode != 0:
raise AuthoritativeGitError("evidence lineage mismatch")
_SAFE_REF_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._/-]{0,239}$")
def _safe_ref_name(value: str) -> bool:
return bool(
_SAFE_REF_RE.fullmatch(value)
and ".." not in value
and "//" not in value
and "@{" not in value
and not value.endswith(("/", ".", ".lock"))
and not any(part in {"", ".", ".."} for part in value.split("/"))
)
def validate_git_revision(
value: str,
field: str,
*,
git_dir: str | Path | None = None,
) -> str:
revision = str(value or "").strip()
if not revision or revision != str(value or "") or revision.startswith("-"):
raise ValueError(f"invalid {field} revision")
if _OID_RE.fullmatch(revision.lower()):
try:
return authoritative_commit(revision.lower(), git_dir=git_dir)
except AuthoritativeGitError as exc:
raise AuthoritativeGitNotFound(f"{field} revision not found") from exc
if not _safe_ref_name(revision) or any(token in revision for token in ("^", "~", ":", "\\")):
raise ValueError(f"invalid {field} revision")
if revision.startswith("refs/"):
if not revision.startswith(("refs/heads/", "refs/tags/")):
raise ValueError(f"invalid {field} revision")
candidates = [revision]
else:
candidates = [f"refs/heads/{revision}", f"refs/tags/{revision}"]
matches: list[str] = []
for candidate in candidates:
result = run_authoritative_git(
["rev-parse", "--verify", f"{candidate}^{{commit}}"],
check=False,
git_dir=git_dir,
)
oid = result.stdout.strip().lower()
if result.returncode == 0 and _OID_RE.fullmatch(oid):
matches.append(oid)
if not matches:
raise AuthoritativeGitNotFound(f"{field} revision not found")
if len(set(matches)) != 1 or len(matches) != 1:
raise ValueError(f"ambiguous {field} revision")
return matches[0]
def authoritative_diff(
from_revision: str,
to_revision: str,
*,
git_dir: str | Path | None = None,
) -> dict[str, object]:
path, _ = verify_repository(git_dir=git_dir)
from_oid = validate_git_revision(from_revision, "from", git_dir=path)
to_oid = validate_git_revision(to_revision, "to", git_dir=path)
args = ["diff", "--no-ext-diff", "--no-textconv", from_oid, to_oid]
result = run_authoritative_git(args, git_dir=path)
return {
"code": 0,
"stdout": result.stdout,
"stderr": "",
"cmd": ["git", f"--git-dir={path}", *args],
"from_oid": from_oid,
"to_oid": to_oid,
}
def repository_snapshot(
*,
git_dir: str | Path | None = None,
repository_identity: str | None = None,
) -> dict[str, object]:
configured = bool(
str(git_dir or os.getenv("AIOS_GITOPS_AUTHORITATIVE_GIT_DIR", "")).strip()
)
try:
path, identity = verify_repository(
git_dir=git_dir,
repository_identity=repository_identity,
)
head = authoritative_head_oid(git_dir=path)
return {
"repository_available": True,
"authoritative_git_dir_configured": configured,
"authoritative_git_dir_readable": True,
"authoritative_git_dir": str(path),
"authoritative_head_oid": head,
"repository_identity": identity,
"query_error": None,
}
except (AuthoritativeGitError, ValueError) as exc:
return {
"repository_available": False,
"authoritative_git_dir_configured": configured,
"authoritative_git_dir_readable": False,
"authoritative_git_dir": None,
"authoritative_head_oid": None,
"repository_identity": str(
repository_identity
or os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", "")
).strip() or None,
"query_error": _redact(str(exc)),
}
File diff suppressed because it is too large Load Diff
+167
View File
@@ -0,0 +1,167 @@
"""Fail-closed operation authorization for an isolated Git writer."""
from __future__ import annotations
import ipaddress
import os
import re
import subprocess
from dataclasses import dataclass
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
from isolated_writer_token_registry import TokenRegistry
ROUTE_OPERATIONS = {
("GET", "/api/runtime-status"): "runtime.status.read",
("GET", "/api/baseline"): "baseline.read",
("GET", "/api/patches"): "patches.read",
("POST", "/api/commit-file"): "commit_file.atomic",
}
OID_RE = re.compile(r"[0-9a-f]{40}")
class AuthorizationError(PermissionError):
def __init__(self, code: str, status: int = 403):
super().__init__(code)
self.code = code
self.status = status
@dataclass(frozen=True)
class AuthorizedGrant:
record: dict[str, Any]
operation: str
use_count: int
@property
def token_id(self) -> str:
return str(self.record["token_id"])
@property
def task_id(self) -> str:
return str(self.record["task_id"])
def operation_for(method: str, path: str) -> str:
operation = ROUTE_OPERATIONS.get((method.upper(), path))
if not operation:
raise AuthorizationError("isolated_writer_operation_forbidden")
return operation
def _parse_time(value: Any) -> datetime:
try:
parsed = datetime.fromisoformat(str(value).replace("Z", "+00:00"))
except (TypeError, ValueError):
raise AuthorizationError("writer_token_time_invalid") from None
if parsed.tzinfo is None:
raise AuthorizationError("writer_token_time_invalid")
return parsed.astimezone(timezone.utc)
def _git_is_ancestor(workspace: Path, base: str, branch: str) -> bool:
result = subprocess.run(
["git", "merge-base", "--is-ancestor", base, branch],
cwd=workspace,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
)
return result.returncode == 0
def _validate_grant(
grant: dict[str, Any],
*,
audience: str,
source_ip: str,
operation: str,
branch: str | None,
path: str | None,
workspace: Path,
current_time: datetime,
) -> None:
if int(grant.get("schema_version", 0)) != 2:
raise AuthorizationError("writer_token_policy_v2_required", 401)
if str(grant.get("audience") or "") != audience:
raise AuthorizationError("writer_token_audience_rejected")
try:
peer = ipaddress.ip_address(source_ip)
networks = [ipaddress.ip_network(str(value), strict=True) for value in grant.get("source_cidrs", [])]
except ValueError:
raise AuthorizationError("writer_token_source_rejected") from None
if not networks or not any(peer in network for network in networks):
raise AuthorizationError("writer_token_source_rejected")
created = _parse_time(grant.get("created_at"))
not_before = _parse_time(grant.get("not_before"))
expires = _parse_time(grant.get("expires_at"))
if expires <= not_before or (expires - created).total_seconds() > 1800:
raise AuthorizationError("writer_token_lifetime_rejected")
if current_time < not_before:
raise AuthorizationError("writer_token_not_yet_valid", 401)
if current_time >= expires:
raise AuthorizationError("writer_token_expired", 401)
if bool(grant.get("revoked")):
raise AuthorizationError("writer_token_revoked", 401)
operations = grant.get("allowed_operations")
if not isinstance(operations, list) or operation not in operations:
raise AuthorizationError("writer_token_operation_rejected")
expected_branch = str(grant.get("allowed_branch") or "")
configured_branch = os.getenv("AIOS_GITOPS_ALLOWED_BRANCH", "")
if expected_branch != configured_branch:
raise AuthorizationError("writer_token_branch_rejected")
if branch is not None and branch != expected_branch:
raise AuthorizationError("writer_token_branch_rejected")
if path is not None:
paths = grant.get("allowed_paths")
if not isinstance(paths, list) or path not in paths:
raise AuthorizationError("writer_token_path_rejected")
base = str(grant.get("approved_base_oid") or "").lower()
if not OID_RE.fullmatch(base):
raise AuthorizationError("writer_token_base_rejected")
if not _git_is_ancestor(workspace, base, expected_branch):
raise AuthorizationError("writer_token_base_not_ancestor")
def authorize(
registry: TokenRegistry,
token: str,
*,
method: str,
path: str,
source_ip: str,
workspace: Path,
branch: str | None = None,
target_path: str | None = None,
current_time: datetime | None = None,
) -> AuthorizedGrant:
if os.getenv("AIOS_GITOPS_TOKEN_POLICY_VERSION_REQUIRED", "") != "2":
raise AuthorizationError("writer_token_policy_v2_not_required")
if not token:
raise AuthorizationError("unauthorized", 401)
grant = registry.find(token)
if grant is None:
raise AuthorizationError("unauthorized", 401)
operation = operation_for(method, path)
_validate_grant(
grant,
audience=os.getenv("AIOS_GITOPS_SERVICE_AUDIENCE", ""),
source_ip=source_ip,
operation=operation,
branch=branch,
path=target_path,
workspace=workspace,
current_time=current_time or datetime.now(timezone.utc),
)
limits = grant.get("max_uses")
if not isinstance(limits, dict):
raise AuthorizationError("writer_token_use_limit_missing")
try:
used = registry.consume(str(grant["token_id"]), operation, int(limits[operation]))
except (KeyError, TypeError, ValueError):
raise AuthorizationError("writer_token_use_limit_missing") from None
except PermissionError as exc:
code = str(exc)
raise AuthorizationError(code, 401 if code == "writer_token_revoked" else 403) from None
return AuthorizedGrant(grant, operation, used)
@@ -0,0 +1,403 @@
"""Atomic, idempotent commit-file Saga for the isolated writer."""
from __future__ import annotations
import fcntl
import hashlib
import json
import os
import re
import sqlite3
import subprocess
import tempfile
import threading
from pathlib import Path
from typing import Any
import aios_isolated_writer_policy as policy
OID_RE = re.compile(r"[0-9a-f]{40}")
IDEMPOTENCY_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._:-]{7,127}")
STATES = frozenset({
"PENDING", "FILE_WRITTEN", "COMMITTED", "PUSHED", "VERIFIED", "COMPLETED",
"FAILED_RECOVERABLE", "MANUAL_REVIEW_REQUIRED",
})
_LOCKS: dict[str, threading.Lock] = {}
_LOCKS_GUARD = threading.Lock()
_LEDGER_INIT_LOCK = threading.Lock()
class CommitFileError(RuntimeError):
def __init__(self, code: str, status: int = 400):
super().__init__(code)
self.code = code
self.status = status
class SimulatedCrash(RuntimeError):
pass
def canonical_digest(data: dict[str, Any]) -> str:
payload = {
"branch": data["branch"],
"path": data["path"],
"content_sha256": hashlib.sha256(data["content"].encode("utf-8")).hexdigest(),
"message": data["message"],
"expected_head_oid": data["expected_head_oid"],
}
encoded = json.dumps(payload, sort_keys=True, separators=(",", ":")).encode("utf-8")
return hashlib.sha256(encoded).hexdigest()
class OperationLedger:
def __init__(self, path: Path | str):
self.path = Path(path)
self.path.parent.mkdir(parents=True, exist_ok=True)
if self.path.parent.is_symlink() or self.path.is_symlink():
raise PermissionError("writer_operation_ledger_symlink_rejected")
with _LEDGER_INIT_LOCK:
with self.connect() as db:
db.execute(
"""
CREATE TABLE IF NOT EXISTS writer_operations (
operation_id TEXT PRIMARY KEY,
token_id TEXT NOT NULL,
task_id TEXT NOT NULL,
idempotency_key TEXT NOT NULL UNIQUE,
operation_digest TEXT NOT NULL,
branch TEXT NOT NULL,
path TEXT NOT NULL,
content_sha256 TEXT NOT NULL,
pre_head_oid TEXT NOT NULL,
commit_oid TEXT,
push_status TEXT,
verification_status TEXT,
state TEXT NOT NULL,
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
error_code TEXT
)
"""
)
os.chmod(self.path, 0o600)
def connect(self) -> sqlite3.Connection:
db = sqlite3.connect(self.path, timeout=30)
db.row_factory = sqlite3.Row
db.execute("PRAGMA journal_mode=WAL")
db.execute("PRAGMA synchronous=FULL")
return db
def get_or_create(self, grant: Any, data: dict[str, Any], digest: str) -> dict[str, Any]:
key = data["idempotency_key"]
with self.connect() as db:
db.execute("BEGIN IMMEDIATE")
row = db.execute(
"SELECT * FROM writer_operations WHERE idempotency_key=?", (key,)
).fetchone()
if row:
db.commit()
record = dict(row)
if record["operation_digest"] != digest:
raise CommitFileError("writer_idempotency_conflict", 409)
if (
record["token_id"] != grant.token_id
or record["task_id"] != grant.task_id
):
raise CommitFileError("writer_idempotency_owner_conflict", 409)
return record
operation_id = hashlib.sha256(
f"{grant.task_id}\0{key}".encode("utf-8")
).hexdigest()
content_sha = hashlib.sha256(data["content"].encode("utf-8")).hexdigest()
db.execute(
"""
INSERT INTO writer_operations(
operation_id,token_id,task_id,idempotency_key,operation_digest,
branch,path,content_sha256,pre_head_oid,state
) VALUES(?,?,?,?,?,?,?,?,?,?)
""",
(
operation_id, grant.token_id, grant.task_id, key, digest,
data["branch"], data["path"], content_sha,
data["expected_head_oid"], "PENDING",
),
)
db.commit()
return self.get(key)
def get(self, key: str) -> dict[str, Any]:
with self.connect() as db:
row = db.execute(
"SELECT * FROM writer_operations WHERE idempotency_key=?", (key,)
).fetchone()
if row is None:
raise KeyError(key)
return dict(row)
def update(self, key: str, state: str, **fields: Any) -> dict[str, Any]:
if state not in STATES:
raise ValueError("invalid writer operation state")
allowed = {"commit_oid", "push_status", "verification_status", "error_code"}
assignments = ["state=?", "updated_at=CURRENT_TIMESTAMP"]
values: list[Any] = [state]
for name, value in fields.items():
if name not in allowed:
raise ValueError("invalid ledger field")
assignments.append(f"{name}=?")
values.append(value)
values.append(key)
with self.connect() as db:
db.execute("BEGIN IMMEDIATE")
db.execute(
f"UPDATE writer_operations SET {','.join(assignments)} WHERE idempotency_key=?",
values,
)
db.commit()
return self.get(key)
class AtomicCommitFile:
def __init__(
self,
*,
workspace: Path,
bare_repo: Path,
ledger: OperationLedger,
remote: str,
audit,
crash_after_state: str | None = None,
):
self.workspace = workspace
self.bare_repo = bare_repo
self.ledger = ledger
self.remote = remote
self.audit = audit
self.crash_after_state = crash_after_state
def _git(self, *args: str, check: bool = True) -> str:
result = subprocess.run(
["git", *args], cwd=self.workspace, text=True, capture_output=True
)
if check and result.returncode != 0:
raise CommitFileError("writer_git_operation_failed", 500)
return result.stdout.strip()
def _transition(self, key: str, state: str, **fields: Any) -> dict[str, Any]:
record = self.ledger.update(key, state, **fields)
if self.crash_after_state == state:
raise SimulatedCrash(state)
return record
def _validate(self, data: Any) -> dict[str, Any]:
if not isinstance(data, dict):
raise CommitFileError("writer_request_object_required")
required = ("branch", "path", "content", "message", "expected_head_oid", "idempotency_key")
if any(field not in data for field in required):
raise CommitFileError("writer_request_incomplete")
if data.get("force") or data.get("force_push"):
raise CommitFileError("isolated_writer_force_rejected", 403)
if set(data) != set(required):
raise CommitFileError("writer_request_fields_rejected")
item = {field: data[field] for field in required}
if item["branch"] != policy.allowed_branch():
raise CommitFileError("isolated_writer_branch_rejected", 403)
try:
item["path"] = policy.validate_path(item["path"], self.workspace)
except PermissionError as exc:
raise CommitFileError(str(exc), 403) from None
if not isinstance(item["content"], str) or "\x00" in item["content"]:
raise CommitFileError("writer_content_rejected")
try:
policy.validate_content_for_path(item["path"], item["content"])
except PermissionError as exc:
raise CommitFileError(str(exc), 403) from None
if len(item["content"].encode("utf-8")) > 1_048_576:
raise CommitFileError("writer_content_too_large", 413)
message = item["message"]
if (
not isinstance(message, str)
or not 1 <= len(message) <= 200
or "\x00" in message
or "\n" in message
or "\r" in message
):
raise CommitFileError("writer_message_rejected")
if not isinstance(item["expected_head_oid"], str) or not OID_RE.fullmatch(item["expected_head_oid"]):
raise CommitFileError("writer_expected_head_rejected")
if not isinstance(item["idempotency_key"], str) or not IDEMPOTENCY_RE.fullmatch(item["idempotency_key"]):
raise CommitFileError("writer_idempotency_key_rejected")
return item
def _atomic_write(self, relative: str, content: str) -> None:
target = self.workspace / relative
target.parent.mkdir(parents=True, exist_ok=True)
fd, temporary = tempfile.mkstemp(prefix=".writer-", dir=target.parent)
try:
with os.fdopen(fd, "wb", closefd=True) as stream:
stream.write(content.encode("utf-8"))
stream.flush()
os.fsync(stream.fileno())
os.replace(temporary, target)
parent_fd = os.open(target.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 _verify_remote(self, branch: str, oid: str) -> None:
bare = subprocess.run(
["git", "--git-dir", str(self.bare_repo), "rev-parse", f"refs/heads/{branch}"],
text=True, capture_output=True,
)
if bare.returncode != 0 or bare.stdout.strip() != oid:
raise CommitFileError("writer_authoritative_bare_oid_mismatch", 500)
remote = subprocess.run(
["git", "ls-remote", "--heads", self.remote, f"refs/heads/{branch}"],
cwd=self.workspace, text=True, capture_output=True,
)
if remote.returncode != 0:
raise CommitFileError("writer_gitea_verification_failed", 503)
fields = remote.stdout.strip().split()
if len(fields) != 2:
raise CommitFileError("writer_gitea_ref_missing", 503)
if fields[0] != oid:
raise CommitFileError("writer_gitea_oid_conflict", 409)
def execute(self, grant: Any, raw_data: Any) -> dict[str, Any]:
data = self._validate(raw_data)
digest = canonical_digest(data)
branch = data["branch"]
with _LOCKS_GUARD:
lock = _LOCKS.setdefault(branch, threading.Lock())
lock_path = self.ledger.path.parent / f"{hashlib.sha256(branch.encode()).hexdigest()}.lock"
with lock, open(lock_path, "a+b") as branch_lock:
fcntl.flock(branch_lock.fileno(), fcntl.LOCK_EX)
return self._execute_locked(grant, data, digest)
def _execute_locked(self, grant: Any, data: dict[str, Any], digest: str) -> dict[str, Any]:
key = data["idempotency_key"]
record = self.ledger.get_or_create(grant, data, digest)
if record["state"] == "COMPLETED":
return self._result(record, idempotent=True)
if self._git("rev-parse", "--abbrev-ref", "HEAD") != data["branch"]:
record = self._transition(
key, "MANUAL_REVIEW_REQUIRED", error_code="writer_current_branch_conflict"
)
self._audit(grant, data, digest, record, "manual_review_required")
raise CommitFileError("writer_current_branch_conflict", 409)
head = self._git("rev-parse", "HEAD")
commit_oid = record.get("commit_oid")
if head != record["pre_head_oid"] and head != commit_oid:
record = self._transition(
key, "MANUAL_REVIEW_REQUIRED", error_code="writer_branch_head_conflict"
)
self._audit(grant, data, digest, record, "manual_review_required")
raise CommitFileError("writer_branch_head_conflict", 409)
try:
state = record["state"]
if state == "MANUAL_REVIEW_REQUIRED":
raise CommitFileError("writer_manual_review_required", 409)
if state == "FAILED_RECOVERABLE":
if record.get("push_status") == "confirmed":
state = "PUSHED"
else:
state = "COMMITTED" if commit_oid else "FILE_WRITTEN"
if state == "PENDING":
self._atomic_write(data["path"], data["content"])
record = self._transition(key, "FILE_WRITTEN")
state = record["state"]
if state == "FILE_WRITTEN":
actual_sha = hashlib.sha256(
(self.workspace / data["path"]).read_bytes()
).hexdigest()
if actual_sha != record["content_sha256"]:
raise CommitFileError("writer_file_content_conflict", 409)
staged_before = self._git("diff", "--cached", "--name-only", check=False).splitlines()
if staged_before:
raise CommitFileError("writer_extra_staged_files_rejected", 409)
self._git("add", "--", data["path"])
staged = self._git("diff", "--cached", "--name-only").splitlines()
if staged != [data["path"]]:
raise CommitFileError("writer_extra_staged_files_rejected", 409)
self._git("commit", "-m", data["message"])
commit_oid = self._git("rev-parse", "HEAD")
record = self._transition(key, "COMMITTED", commit_oid=commit_oid)
state = record["state"]
if state == "COMMITTED":
commit_oid = str(record["commit_oid"])
pushed = subprocess.run(
["git", "push", "--porcelain", self.remote, f"HEAD:refs/heads/{data['branch']}"],
cwd=self.workspace, text=True, capture_output=True,
)
if pushed.returncode != 0:
self._transition(
key, "FAILED_RECOVERABLE",
push_status="failed", error_code="writer_gitea_push_failed",
)
raise CommitFileError("writer_gitea_push_failed", 503)
record = self._transition(key, "PUSHED", push_status="confirmed")
state = record["state"]
if state == "PUSHED":
commit_oid = str(record["commit_oid"])
self._verify_remote(data["branch"], commit_oid)
record = self._transition(
key, "VERIFIED", verification_status="bare+gitea"
)
state = record["state"]
if state == "VERIFIED":
record = self._transition(key, "COMPLETED", error_code=None)
self._audit(grant, data, digest, record, "completed")
return self._result(record, idempotent=False)
except SimulatedCrash:
raise
except CommitFileError as exc:
latest = self.ledger.get(key)
if latest["state"] not in {"FAILED_RECOVERABLE", "MANUAL_REVIEW_REQUIRED"}:
failure_state = (
"MANUAL_REVIEW_REQUIRED"
if exc.code in {
"writer_gitea_oid_conflict",
"writer_file_content_conflict",
"writer_current_branch_conflict",
}
else "FAILED_RECOVERABLE"
)
latest = self._transition(key, failure_state, error_code=exc.code)
self._audit(grant, data, digest, latest, "failed")
raise
def _audit(self, grant: Any, data: dict[str, Any], digest: str, record: dict[str, Any], result: str) -> None:
self.audit({
"token_id": grant.token_id,
"task_id": grant.task_id,
"audience": grant.record["audience"],
"source_ip": grant.record.get("_source_ip", "socket-peer"),
"operation": grant.operation,
"branch": data["branch"],
"path": data["path"],
"idempotency_key": data["idempotency_key"],
"operation_digest": digest,
"path_policy_sha256": policy.configured_path_policy_sha256(),
"pre_head_oid": record["pre_head_oid"],
"commit_oid": record.get("commit_oid"),
"result": result,
})
@staticmethod
def _result(record: dict[str, Any], *, idempotent: bool) -> dict[str, Any]:
return {
"status": "completed",
"state": record["state"],
"operation_id": record["operation_id"],
"branch": record["branch"],
"path": record["path"],
"commit_oid": record.get("commit_oid"),
"push_status": record.get("push_status"),
"verification_status": record.get("verification_status"),
"idempotent": idempotent,
}
@@ -0,0 +1,491 @@
"""Strict service-level exact-path policy for isolated Git writers."""
from __future__ import annotations
import grp
import hashlib
import json
import os
import re
import stat
from dataclasses import dataclass
from functools import lru_cache
from pathlib import Path, PurePosixPath, PureWindowsPath
from typing import Any
from urllib.parse import unquote
MAX_POLICY_BYTES = 65_536
POLICY_FIELDS = frozenset(
{
"schema_version",
"policy_id",
"audience",
"repository_identity",
"allowed_branch",
"allowed_operations",
}
)
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",
"candidate-session-broker-source-v1",
}
)
_SECRET_RE = re.compile(
r"(?i)(authorization\s*:|bearer\s+|(?:token|password|secret)\s*[:=])"
)
_SYSTEMD_NAME_RE = re.compile(r"[A-Za-z][A-Za-z0-9]*\Z")
_SYSTEMD_MAX_LINE_BYTES = 4096
_SYSTEMD_ALLOWED_DIRECTIVES = {
"Unit": frozenset({"Description", "After", "Wants"}),
"Service": frozenset(
{
"Type",
"User",
"Group",
"WorkingDirectory",
"Environment",
"ExecStart",
"Restart",
"RestartSec",
"NoNewPrivileges",
"PrivateTmp",
"PrivateDevices",
"ProtectSystem",
"ProtectHome",
"ProtectKernelTunables",
"ProtectKernelModules",
"ProtectControlGroups",
"LockPersonality",
"RestrictSUIDSGID",
"RestrictRealtime",
"MemoryDenyWriteExecute",
"RuntimeDirectory",
"StateDirectory",
"CacheDirectory",
"ReadOnlyPaths",
"ReadWritePaths",
"UMask",
}
),
"Install": frozenset({"WantedBy"}),
}
_SYSTEMD_MULTI_DIRECTIVES = frozenset(
{
("Service", "Environment"),
("Service", "ReadOnlyPaths"),
("Service", "ReadWritePaths"),
}
)
_SYSTEMD_EXACT_SINGLE_VALUES = {
("Unit", "Description"): "AIOS Codex Review/Test Worker",
("Unit", "After"): "network-online.target",
("Unit", "Wants"): "network-online.target",
("Service", "Type"): "simple",
("Service", "User"): "aiman",
("Service", "Group"): "gitops",
(
"Service",
"WorkingDirectory",
): "/usr/libexec/aios-codex-review-test-worker/current",
(
"Service",
"ExecStart",
): "/usr/bin/python3 -m task_plane.workers.codex_review_test",
("Service", "Restart"): "on-failure",
("Service", "RestartSec"): "2",
("Service", "NoNewPrivileges"): "true",
("Service", "PrivateTmp"): "true",
("Service", "PrivateDevices"): "true",
("Service", "ProtectSystem"): "strict",
("Service", "ProtectHome"): "true",
("Service", "ProtectKernelTunables"): "true",
("Service", "ProtectKernelModules"): "true",
("Service", "ProtectControlGroups"): "true",
("Service", "LockPersonality"): "true",
("Service", "RestrictSUIDSGID"): "true",
("Service", "RestrictRealtime"): "true",
("Service", "MemoryDenyWriteExecute"): "true",
("Service", "RuntimeDirectory"): "aios-codex-review-test-worker",
("Service", "StateDirectory"): "aios-codex-review-test-worker",
("Service", "CacheDirectory"): "aios-codex-review-test-worker",
("Service", "UMask"): "0077",
("Install", "WantedBy"): "multi-user.target",
}
_SYSTEMD_EXACT_MULTI_VALUES = {
("Service", "Environment"): (
"AIOS_CODEX_WORKER_MODE=shadow",
"AIOS_TASK_PLANE_EXECUTION_ENABLED=false",
"PYTHONDONTWRITEBYTECODE=1",
),
("Service", "ReadOnlyPaths"): (
"/data/aios-gitops/repo.git",
"/usr/libexec/aios-codex-review-test-worker",
),
("Service", "ReadWritePaths"): (
"/run/aios-codex-review-test-worker",
"/var/lib/aios-codex-review-test-worker",
"/var/cache/aios-codex-review-test-worker",
),
}
class PathPolicyError(PermissionError):
pass
@dataclass(frozen=True)
class OperationPolicy:
exact_paths: tuple[str, ...]
max_content_bytes: int
content_profile: str
@dataclass(frozen=True)
class ServicePathPolicy:
schema_version: int
policy_id: str
audience: str
repository_identity: str
allowed_branch: str
allowed_operations: dict[str, OperationPolicy]
sha256: str
def operation(self, name: str) -> OperationPolicy:
try:
return self.allowed_operations[name]
except KeyError:
raise PathPolicyError("isolated_writer_service_operation_rejected") from None
def require_exact_path(self, operation: str, path: str) -> OperationPolicy:
selected = self.operation(operation)
if path not in selected.exact_paths:
raise PathPolicyError("isolated_writer_service_path_rejected")
return selected
def _canonical_json(value: Any) -> bytes:
return (
json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
+ "\n"
).encode("utf-8")
def validate_relative_path_syntax(path: str) -> str:
if not isinstance(path, str):
raise PathPolicyError("isolated_writer_path_rejected")
if not path or path != path.strip() or "\x00" in path or "\\" in path:
raise PathPolicyError("isolated_writer_path_rejected")
try:
decoded = unquote(path, errors="strict")
except (UnicodeDecodeError, ValueError):
raise PathPolicyError("isolated_writer_path_rejected") from None
if decoded != path:
raise PathPolicyError("isolated_writer_path_rejected")
posix = PurePosixPath(path)
windows = PureWindowsPath(path)
parts = path.split("/")
if (
posix.is_absolute()
or windows.is_absolute()
or bool(windows.drive)
or any(part in {"", ".", ".."} for part in parts)
):
raise PathPolicyError("isolated_writer_path_rejected")
return path
def _require_fields(value: dict[str, Any], allowed: frozenset[str], code: str) -> None:
if set(value) != allowed:
raise PathPolicyError(code)
def _parse_policy(document: Any, canonical: bytes) -> ServicePathPolicy:
if not isinstance(document, dict):
raise PathPolicyError("isolated_writer_path_policy_object_required")
_require_fields(document, POLICY_FIELDS, "isolated_writer_path_policy_fields_rejected")
if document["schema_version"] != 1:
raise PathPolicyError("isolated_writer_path_policy_schema_rejected")
text_fields = (
"policy_id",
"audience",
"repository_identity",
"allowed_branch",
)
if any(
not isinstance(document[field], str) or not document[field].strip()
for field in text_fields
):
raise PathPolicyError("isolated_writer_path_policy_value_rejected")
raw_operations = document["allowed_operations"]
if not isinstance(raw_operations, dict) or not raw_operations:
raise PathPolicyError("isolated_writer_path_policy_operations_rejected")
if not set(raw_operations).issubset(SUPPORTED_OPERATIONS):
raise PathPolicyError("isolated_writer_path_policy_operations_rejected")
operations: dict[str, OperationPolicy] = {}
for name, raw in raw_operations.items():
if not isinstance(raw, dict):
raise PathPolicyError("isolated_writer_path_policy_operation_rejected")
_require_fields(
raw,
OPERATION_FIELDS,
"isolated_writer_path_policy_operation_fields_rejected",
)
paths = raw["exact_paths"]
if (
not isinstance(paths, list)
or not paths
or any(not isinstance(item, str) for item in paths)
):
raise PathPolicyError("isolated_writer_path_policy_paths_rejected")
validated = tuple(validate_relative_path_syntax(item) for item in paths)
if len(set(validated)) != len(validated):
raise PathPolicyError("isolated_writer_path_policy_paths_rejected")
maximum = raw["max_content_bytes"]
if not isinstance(maximum, int) or isinstance(maximum, bool) or not 1 <= maximum <= 1_048_576:
raise PathPolicyError("isolated_writer_path_policy_size_rejected")
profile = raw["content_profile"]
if profile not in SUPPORTED_CONTENT_PROFILES:
raise PathPolicyError("isolated_writer_path_policy_profile_rejected")
operations[name] = OperationPolicy(validated, maximum, profile)
return ServicePathPolicy(
schema_version=1,
policy_id=document["policy_id"],
audience=document["audience"],
repository_identity=document["repository_identity"],
allowed_branch=document["allowed_branch"],
allowed_operations=operations,
sha256=hashlib.sha256(canonical).hexdigest(),
)
def load_path_policy(
path: Path,
*,
expected_owner_uid: int = 0,
expected_group_gid: int | None = None,
expected_parent_mode: int = 0o750,
expected_file_mode: int = 0o640,
) -> ServicePathPolicy:
lexical = Path(os.path.abspath(str(path)))
if lexical.is_symlink():
raise PathPolicyError("isolated_writer_path_policy_symlink_rejected")
try:
parent_info = lexical.parent.stat(follow_symlinks=False)
file_info = lexical.stat(follow_symlinks=False)
except FileNotFoundError:
raise PathPolicyError("isolated_writer_path_policy_missing") from None
if stat.S_ISLNK(parent_info.st_mode) or not stat.S_ISDIR(parent_info.st_mode):
raise PathPolicyError("isolated_writer_path_policy_parent_rejected")
if stat.S_ISLNK(file_info.st_mode) or not stat.S_ISREG(file_info.st_mode):
raise PathPolicyError("isolated_writer_path_policy_file_rejected")
if lexical.resolve(strict=True) != lexical:
raise PathPolicyError("isolated_writer_path_policy_symlink_rejected")
if (
parent_info.st_uid != expected_owner_uid
or stat.S_IMODE(parent_info.st_mode) != expected_parent_mode
):
raise PathPolicyError("isolated_writer_path_policy_parent_permissions_rejected")
if (
file_info.st_uid != expected_owner_uid
or stat.S_IMODE(file_info.st_mode) != expected_file_mode
):
raise PathPolicyError("isolated_writer_path_policy_permissions_rejected")
if expected_group_gid is not None and (
parent_info.st_gid != expected_group_gid or file_info.st_gid != expected_group_gid
):
raise PathPolicyError("isolated_writer_path_policy_group_rejected")
if file_info.st_size <= 0 or file_info.st_size > MAX_POLICY_BYTES:
raise PathPolicyError("isolated_writer_path_policy_file_size_rejected")
raw = lexical.read_bytes()
try:
document = json.loads(raw.decode("utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError):
raise PathPolicyError("isolated_writer_path_policy_json_rejected") from None
canonical = _canonical_json(document)
if raw != canonical:
raise PathPolicyError("isolated_writer_path_policy_not_canonical")
return _parse_policy(document, canonical)
@lru_cache(maxsize=1)
def configured_path_policy() -> ServicePathPolicy | None:
configured = os.getenv("AIOS_GITOPS_PATH_POLICY_FILE", "").strip()
if not configured:
return None
if not Path(configured).is_absolute():
raise PathPolicyError("isolated_writer_path_policy_path_rejected")
try:
gitops_gid = grp.getgrnam("gitops").gr_gid
except KeyError:
raise PathPolicyError("isolated_writer_path_policy_group_rejected") from None
loaded = load_path_policy(Path(configured), expected_group_gid=gitops_gid)
if loaded.audience != os.getenv("AIOS_GITOPS_SERVICE_AUDIENCE", ""):
raise PathPolicyError("isolated_writer_path_policy_audience_rejected")
if loaded.repository_identity != os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", ""):
raise PathPolicyError("isolated_writer_path_policy_repository_rejected")
if loaded.allowed_branch != os.getenv("AIOS_GITOPS_ALLOWED_BRANCH", ""):
raise PathPolicyError("isolated_writer_path_policy_branch_rejected")
return loaded
def clear_path_policy_cache() -> None:
configured_path_policy.cache_clear()
def require_service_path(operation: str, path: str) -> OperationPolicy:
loaded = configured_path_policy()
if loaded is None:
raise PathPolicyError("isolated_writer_service_path_policy_required")
return loaded.require_exact_path(operation, path)
def configured_path_policy_sha256() -> str | None:
loaded = configured_path_policy()
return None if loaded is None else loaded.sha256
def validate_content(operation: str, path: str, content: str) -> None:
selected = require_service_path(operation, path)
try:
encoded = content.encode("utf-8", errors="strict")
except (AttributeError, UnicodeEncodeError):
raise PathPolicyError("isolated_writer_systemd_profile_rejected") from None
if len(encoded) > selected.max_content_bytes:
raise PathPolicyError("isolated_writer_service_content_too_large")
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")
try:
content.encode("utf-8", errors="strict")
except UnicodeEncodeError:
raise PathPolicyError("isolated_writer_systemd_profile_rejected") from None
if (
"\x00" in content
or "\r" in content
or _SECRET_RE.search(content)
or not content.endswith("\n")
):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
sections: set[str] = set()
values: dict[tuple[str, str], list[str]] = {}
section: str | None = None
for line in content.splitlines():
if len(line.encode("utf-8")) > _SYSTEMD_MAX_LINE_BYTES:
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
if not line:
continue
if line[0].isspace() or line.startswith(("#", ";")):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
if line.startswith("[") and line.endswith("]"):
candidate = line[1:-1]
if (
not _SYSTEMD_NAME_RE.fullmatch(candidate)
or candidate not in _SYSTEMD_ALLOWED_DIRECTIVES
or candidate in sections
):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
sections.add(candidate)
section = candidate
continue
if section is None or "=" not in line:
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
directive, value = line.split("=", 1)
if (
not _SYSTEMD_NAME_RE.fullmatch(directive)
or directive not in _SYSTEMD_ALLOWED_DIRECTIVES[section]
or not value
or value != value.strip()
):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
key = (section, directive)
if key in values and key not in _SYSTEMD_MULTI_DIRECTIVES:
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
values.setdefault(key, []).append(value)
if sections != set(_SYSTEMD_ALLOWED_DIRECTIVES):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
if set(values) != set(_SYSTEMD_EXACT_SINGLE_VALUES) | set(
_SYSTEMD_EXACT_MULTI_VALUES
):
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
for key, expected in _SYSTEMD_EXACT_SINGLE_VALUES.items():
if values.get(key) != [expected]:
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
for key, expected in _SYSTEMD_EXACT_MULTI_VALUES.items():
observed = values.get(key, [])
if len(observed) != len(set(observed)) or tuple(observed) != expected:
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
@@ -0,0 +1,241 @@
"""Digest-only, task-scoped token registry for isolated writers."""
from __future__ import annotations
import argparse
import hashlib
import hmac
import json
import os
import grp
import pwd
import secrets
import sqlite3
import stat
import threading
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
_REGISTRY_INIT_LOCK = threading.Lock()
def utc_now() -> str:
return datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
def token_digest(token: str) -> str:
return hashlib.sha256(token.encode("utf-8")).hexdigest()
class TokenRegistry:
def __init__(self, path: Path | str):
self.path = Path(path)
self._prepare()
def _prepare(self) -> None:
self.path.parent.mkdir(parents=True, exist_ok=True)
if self.path.parent.is_symlink() or self.path.is_symlink():
raise PermissionError("writer_token_registry_symlink_rejected")
with _REGISTRY_INIT_LOCK:
with self._connect() as db:
db.executescript(
"""
CREATE TABLE IF NOT EXISTS token_grants (
token_id TEXT PRIMARY KEY,
token_digest TEXT NOT NULL UNIQUE,
grant_json TEXT NOT NULL,
revoked INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS token_uses (
token_id TEXT NOT NULL,
operation TEXT NOT NULL,
use_count INTEGER NOT NULL DEFAULT 0,
PRIMARY KEY(token_id, operation),
FOREIGN KEY(token_id) REFERENCES token_grants(token_id)
);
"""
)
os.chmod(self.path, 0o600)
def _connect(self) -> sqlite3.Connection:
db = sqlite3.connect(self.path, timeout=30, isolation_level=None)
db.row_factory = sqlite3.Row
db.execute("PRAGMA journal_mode=WAL")
db.execute("PRAGMA synchronous=FULL")
db.execute("PRAGMA foreign_keys=ON")
return db
def issue(self, grant: dict[str, Any], token: str | None = None) -> tuple[str, dict[str, Any]]:
value = token or secrets.token_urlsafe(32)
if len(value.encode("utf-8")) < 32:
raise ValueError("writer_token_entropy_insufficient")
record = dict(grant)
record["schema_version"] = 2
record["token_digest"] = token_digest(value)
record["revoked"] = False
record.setdefault("created_at", utc_now())
required = (
"token_id",
"audience",
"task_id",
"source_cidrs",
"allowed_branch",
"approved_base_oid",
"allowed_operations",
"allowed_paths",
"not_before",
"expires_at",
"max_uses",
"issued_by",
)
if any(not record.get(field) for field in required):
raise ValueError("writer_token_grant_incomplete")
encoded = json.dumps(record, sort_keys=True, separators=(",", ":"))
with self._connect() as db:
db.execute("BEGIN IMMEDIATE")
try:
db.execute(
"""
INSERT INTO token_grants(token_id, token_digest, grant_json, revoked, created_at)
VALUES(?,?,?,?,?)
""",
(
str(record["token_id"]),
str(record["token_digest"]),
encoded,
0,
str(record["created_at"]),
),
)
db.execute("COMMIT")
except Exception:
db.execute("ROLLBACK")
raise
return value, record
def find(self, token: str) -> dict[str, Any] | None:
candidate = token_digest(token)
with self._connect() as db:
rows = db.execute(
"SELECT token_digest, grant_json, revoked FROM token_grants"
).fetchall()
match = None
for row in rows:
if hmac.compare_digest(str(row["token_digest"]), candidate):
match = dict(json.loads(str(row["grant_json"])))
match["revoked"] = bool(row["revoked"])
return match
def consume(self, token_id: str, operation: str, maximum: int) -> int:
if maximum < 1:
raise PermissionError("writer_token_operation_exhausted")
with self._connect() as db:
db.execute("BEGIN IMMEDIATE")
try:
row = db.execute(
"SELECT revoked FROM token_grants WHERE token_id=?",
(token_id,),
).fetchone()
if row is None or bool(row["revoked"]):
raise PermissionError("writer_token_revoked")
used_row = db.execute(
"SELECT use_count FROM token_uses WHERE token_id=? AND operation=?",
(token_id, operation),
).fetchone()
used = int(used_row["use_count"]) if used_row else 0
if used >= maximum:
raise PermissionError("writer_token_operation_exhausted")
current = used + 1
db.execute(
"""
INSERT INTO token_uses(token_id, operation, use_count)
VALUES(?,?,?)
ON CONFLICT(token_id, operation)
DO UPDATE SET use_count=excluded.use_count
""",
(token_id, operation, current),
)
db.execute("COMMIT")
return current
except Exception:
db.execute("ROLLBACK")
raise
def revoke(self, token_id: str) -> bool:
with self._connect() as db:
db.execute("BEGIN IMMEDIATE")
changed = db.execute(
"UPDATE token_grants SET revoked=1 WHERE token_id=? AND revoked=0",
(token_id,),
).rowcount
db.execute("COMMIT")
return bool(changed)
def usage(self, token_id: str, operation: str) -> int:
with self._connect() as db:
row = db.execute(
"SELECT use_count FROM token_uses WHERE token_id=? AND operation=?",
(token_id, operation),
).fetchone()
return int(row["use_count"]) if row else 0
def _write_secret_file(
path: Path,
token: str,
*,
owner: str | None = None,
group: str | None = None,
) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
if path.parent.is_symlink() or path.is_symlink():
raise PermissionError("writer_token_file_symlink_rejected")
flags = os.O_WRONLY | os.O_CREAT | os.O_EXCL
if hasattr(os, "O_NOFOLLOW"):
flags |= os.O_NOFOLLOW
fd = os.open(path, flags, 0o600)
try:
if not stat.S_ISREG(os.fstat(fd).st_mode):
raise PermissionError("writer_token_file_not_regular")
if owner is not None or group is not None:
uid = pwd.getpwnam(owner).pw_uid if owner is not None else -1
gid = grp.getgrnam(group).gr_gid if group is not None else -1
os.fchown(fd, uid, gid)
os.write(fd, token.encode("utf-8"))
os.fsync(fd)
finally:
os.close(fd)
def main(argv: list[str] | None = None) -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--registry", required=True)
sub = parser.add_subparsers(dest="command", required=True)
issue = sub.add_parser("issue")
issue.add_argument("--grant-file", required=True)
issue.add_argument("--token-file", required=True)
issue.add_argument("--owner")
issue.add_argument("--group")
revoke = sub.add_parser("revoke")
revoke.add_argument("--token-id", required=True)
args = parser.parse_args(argv)
registry = TokenRegistry(args.registry)
if args.command == "issue":
grant = json.loads(Path(args.grant_file).read_text(encoding="utf-8"))
token, record = registry.issue(grant)
_write_secret_file(
Path(args.token_file),
token,
owner=args.owner,
group=args.group,
)
print(json.dumps({"token_id": record["token_id"], "created": True}, sort_keys=True))
return 0
changed = registry.revoke(args.token_id)
print(json.dumps({"token_id": args.token_id, "revoked": changed}, sort_keys=True))
return 0
if __name__ == "__main__":
raise SystemExit(main())
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,564 @@
#!/usr/bin/env python3
"""Execution-readiness adapters and the fail-closed Shadow controller service."""
from __future__ import annotations
import argparse
import base64
import dataclasses
import hashlib
import json
import os
import subprocess
import threading
import time
from http import HTTPStatus
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import Any, Callable, Mapping, Protocol
from urllib.parse import parse_qs, urlparse
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
Ed25519PrivateKey,
)
from silent_release_controller import _sanitize, utc_now
from silent_release_hardening import (
BuilderAttestation,
CapabilityAuthorizationError,
ReleaseRecoveryWorker,
SignedApprovalVerifier,
SignedReleasePlanApproval,
SilentReleaseActionService,
TrustedCandidateBundle,
_canonical_json,
_durable_json,
_safe_child,
)
class BuilderSigner(Protocol):
@property
def key_id(self) -> str:
...
def sign(self, payload: bytes) -> bytes:
...
class LocalTestBuilderSigner:
"""Ephemeral in-memory signer. It is forbidden for production execution."""
test_only = True
def __init__(self, key_id: str, private_key: Ed25519PrivateKey):
self._key_id = str(key_id)
self._private_key = private_key
@property
def key_id(self) -> str:
return self._key_id
@classmethod
def generate(
cls, key_id: str = "shadow-builder-test-key"
) -> "LocalTestBuilderSigner":
return cls(key_id, Ed25519PrivateKey.generate())
@property
def public_key(self):
return self._private_key.public_key()
def sign(self, payload: bytes) -> bytes:
return self._private_key.sign(payload)
class ExternalKmsBuilderSigner:
"""Signer facade whose private operation remains in KMS/HSM."""
def __init__(
self,
key_id: str,
credential_reference: str,
sign_callback: Callable[[str, bytes], bytes],
):
if not str(credential_reference).startswith(
("kms://", "hsm://", "secret-manager://")
):
raise ValueError("production builder requires a KMS/HSM reference")
self._key_id = str(key_id)
self.credential_reference = str(credential_reference)
self._sign_callback = sign_callback
@property
def key_id(self) -> str:
return self._key_id
def sign(self, payload: bytes) -> bytes:
return bytes(self._sign_callback(self.credential_reference, payload))
class SignedTrustedBuilderAdapter:
"""Signs evidence produced by a trusted collector, never caller evidence."""
def __init__(
self,
collector: Callable[[Mapping[str, Any]], TrustedCandidateBundle],
signer: BuilderSigner,
):
self.collector = collector
self.signer = signer
def build(self, intent: Mapping[str, Any]) -> TrustedCandidateBundle:
forbidden = {
"artifact_sha256",
"canary",
"checks",
"manifest_sha256",
"tests",
"tree_oid",
}
if forbidden.intersection(intent):
raise CapabilityAuthorizationError(
"trusted builder rejects caller-supplied evidence"
)
unsigned = self.collector(dict(intent))
if unsigned.attestation is not None:
raise CapabilityAuthorizationError(
"collector cannot self-attest its evidence"
)
candidate = unsigned.candidate
test_sha = hashlib.sha256(
_canonical_json(_sanitize(candidate.tests))
).hexdigest()
canary_sha = hashlib.sha256(
_canonical_json(_sanitize(candidate.canary))
).hexdigest()
attestation_id = "builder-attestation-" + hashlib.sha256(
(
candidate.candidate_id
+ "\0"
+ candidate.source_commit
+ "\0"
+ candidate.artifact_sha256
).encode("utf-8")
).hexdigest()[:24]
attestation = BuilderAttestation(
builder_attestation_id=attestation_id,
builder_key_id=self.signer.key_id,
source_commit=candidate.source_commit,
tree_oid=candidate.tree_oid,
artifact_sha256=candidate.artifact_sha256,
manifest_sha256=candidate.manifest_sha256,
package_closure_sha256=(
unsigned.release_plan.deployment.package_closure_sha256
),
test_evidence_sha256=test_sha,
canary_evidence_sha256=canary_sha,
issued_at=utc_now(),
signature="",
)
attestation = dataclasses.replace(
attestation,
signature=base64.b64encode(
self.signer.sign(attestation.canonical_bytes())
).decode("ascii"),
)
return dataclasses.replace(unsigned, attestation=attestation)
class ApprovalBackendAdapter(Protocol):
@property
def available(self) -> bool:
...
def verify(
self,
approval: SignedReleasePlanApproval,
*,
candidate,
release_plan,
policy_sha256: str,
) -> SignedReleasePlanApproval:
...
class LocalTestApprovalSigner:
"""Test-only approval signer used solely for Shadow acceptance."""
test_only = True
def __init__(self, key_id: str, private_key: Ed25519PrivateKey):
self.key_id = str(key_id)
self.private_key = private_key
@classmethod
def generate(
cls, key_id: str = "shadow-owner-test-key"
) -> "LocalTestApprovalSigner":
return cls(key_id, Ed25519PrivateKey.generate())
def sign(
self, approval: SignedReleasePlanApproval
) -> SignedReleasePlanApproval:
unsigned = dataclasses.replace(
approval, key_id=self.key_id, signature=""
)
return dataclasses.replace(
unsigned,
signature=base64.b64encode(
self.private_key.sign(unsigned.canonical_bytes())
).decode("ascii"),
)
class ProductionApprovalBackendAdapter:
"""Verification-only production adapter configured by a secret/KMS ref."""
def __init__(
self,
verifier: SignedApprovalVerifier,
credential_reference: str,
):
if not str(credential_reference).startswith(
("kms://", "hsm://", "secret-manager://")
):
raise ValueError(
"production approval backend requires a KMS/secret reference"
)
self.verifier = verifier
self.credential_reference = str(credential_reference)
@property
def available(self) -> bool:
return True
def verify(
self,
approval: SignedReleasePlanApproval,
*,
candidate,
release_plan,
policy_sha256: str,
) -> SignedReleasePlanApproval:
return self.verifier.verify_release_plan(
approval, candidate, release_plan, policy_sha256
)
class UnavailableProductionApprovalBackend:
credential_reference = None
@property
def available(self) -> bool:
return False
def verify(self, *args, **kwargs):
raise CapabilityAuthorizationError(
"production approval backend is not configured"
)
class LeaderLock:
def __init__(self, path: Path):
self.path = Path(path)
self.handle = None
def __enter__(self):
self.path.parent.mkdir(parents=True, exist_ok=True)
os.chmod(self.path.parent, 0o700)
self.handle = self.path.open("a+", encoding="utf-8")
os.chmod(self.path, 0o600)
try:
import fcntl
fcntl.flock(
self.handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB
)
except BlockingIOError as exc:
self.handle.close()
self.handle = None
raise RuntimeError("silent release leader is already active") from exc
return self
def __exit__(self, exc_type, exc, tb):
if self.handle is not None:
try:
import fcntl
fcntl.flock(self.handle.fileno(), fcntl.LOCK_UN)
finally:
self.handle.close()
self.handle = None
class PersistentSilentReleaseController:
"""Idempotent main-event controller with durable startup/recovery reports."""
def __init__(
self,
root: Path,
service: SilentReleaseActionService,
*,
main_probe: Callable[[], str],
recovery_worker: ReleaseRecoveryWorker | None = None,
):
self.root = Path(root)
self.service = service
self.main_probe = main_probe
self.recovery_worker = recovery_worker
self.leader_path = self.root / "controller.leader.lock"
self.status_path = self.root / "controller-status.json"
def startup_verify(self) -> dict[str, Any]:
checked = 0
failed = 0
for journal in sorted(self.service.sagas.root.glob("*.events.jsonl")):
candidate_id = journal.name[: -len(".events.jsonl")]
saga = self.service.sagas.load(candidate_id)
checked += 1
if not saga.journal_integrity:
failed += 1
status = {
"checked_sagas": checked,
"execution_enabled": self.service.execution_enabled,
"failed_closed": failed,
"shadow_mode": not self.service.execution_enabled,
"side_effects_executed": False,
"status": "READY" if failed == 0 else "FAIL_CLOSED",
}
_durable_json(self.status_path, status)
return status
def run_once(self) -> dict[str, Any]:
with LeaderLock(self.leader_path):
startup = self.startup_verify()
if startup["status"] != "READY":
result = {
"execution_enabled": self.service.execution_enabled,
"intent": None,
"notification": None,
"recovery": None,
"shadow_mode": not self.service.execution_enabled,
"side_effects_executed": False,
"startup": startup,
"status": "FAIL_CLOSED",
}
_durable_json(self.status_path, result)
return _sanitize(result)
source_commit = str(self.main_probe())
event_id = f"main-{source_commit}"
intent = self.service.create_release_intent(
{"event_id": event_id, "source_commit": source_commit}
)
notification = None
if intent.get("candidate_id"):
notification = self.service.ensure_owner_notification(
str(intent["candidate_id"])
)
recovery = (
self.recovery_worker.run_once()
if self.recovery_worker is not None
else self.service.get_recovery_status()
)
result = {
"execution_enabled": self.service.execution_enabled,
"intent": intent,
"notification": notification,
"recovery": recovery,
"shadow_mode": not self.service.execution_enabled,
"side_effects_executed": False,
"startup": startup,
}
_durable_json(self.status_path, result)
return _sanitize(result)
class ShadowActionHandler(BaseHTTPRequestHandler):
service: SilentReleaseActionService
controller: PersistentSilentReleaseController
def log_message(self, fmt, *args):
return
def _json(self, payload: Mapping[str, Any], status=HTTPStatus.OK):
body = json.dumps(_sanitize(dict(payload)), sort_keys=True).encode()
self.send_response(int(status))
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def _body(self) -> dict[str, Any]:
size = int(self.headers.get("Content-Length", "0"))
if size > 1024 * 1024:
raise ValueError("request body is too large")
return json.loads(self.rfile.read(size) or b"{}")
def do_GET(self):
parsed = urlparse(self.path)
query = parse_qs(parsed.query)
candidate_id = str((query.get("candidate_id") or [""])[0])
try:
if parsed.path == "/healthz":
return self._json(
{
"execution_enabled": False,
"shadow_mode": True,
"side_effects_executed": False,
"status": "ok",
}
)
routes = {
"/getReleaseCandidate": self.service.get_release_candidate,
"/getReleasePlan": self.service.get_release_plan,
"/getReleaseAcceptance": self.service.get_acceptance,
"/getReleaseSaga": self.service.get_release_saga,
"/getCapabilityStatus": self.service.get_capability_status,
}
if parsed.path in routes:
return self._json(routes[parsed.path](candidate_id))
if parsed.path == "/getRecoveryStatus":
return self._json(self.service.get_recovery_status())
self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
except (ValueError, FileNotFoundError) as exc:
self._json(
{"error": type(exc).__name__}, HTTPStatus.BAD_REQUEST
)
def do_POST(self):
parsed = urlparse(self.path)
try:
body = self._body()
if parsed.path == "/createReleaseIntent":
return self._json(self.service.create_release_intent(body))
if parsed.path in {
"/submitSignedApproval",
"/submitOwnerApproval",
}:
return self._json(self.service.submit_owner_approval(body))
if parsed.path == "/startDeployment":
return self._json(
self.service.start_deployment(
str(body.get("candidate_id") or "")
)
)
self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
except (ValueError, FileNotFoundError, CapabilityAuthorizationError) as exc:
self._json(
{"error": type(exc).__name__}, HTTPStatus.BAD_REQUEST
)
def git_main_probe(repository: Path) -> Callable[[], str]:
repository = Path(repository)
def probe() -> str:
completed = subprocess.run(
[
"git",
f"--git-dir={repository}",
"rev-parse",
"refs/heads/main",
],
check=True,
capture_output=True,
text=True,
timeout=15,
env={"PATH": os.environ.get("PATH", "")},
)
return completed.stdout.strip()
return probe
def serve_shadow(
*,
state_root: Path,
repository: Path,
host: str,
port: int,
poll_seconds: float,
) -> None:
service = SilentReleaseActionService.shadow(state_root)
controller = PersistentSilentReleaseController(
state_root,
service,
main_probe=git_main_probe(repository),
)
controller.run_once()
stop = threading.Event()
def controller_loop() -> None:
while not stop.wait(poll_seconds):
try:
controller.run_once()
except Exception as exc: # fail closed and keep the API available
_durable_json(
controller.status_path,
{
"error": type(exc).__name__,
"execution_enabled": False,
"shadow_mode": True,
"side_effects_executed": False,
"status": "FAIL_CLOSED",
},
)
handler = type(
"ConfiguredShadowActionHandler",
(ShadowActionHandler,),
{"service": service, "controller": controller},
)
server = ThreadingHTTPServer((host, port), handler)
api_thread = threading.Thread(
target=server.serve_forever,
name="silent-release-shadow-api",
daemon=False,
)
controller_thread = threading.Thread(
target=controller_loop,
name="silent-release-shadow-controller",
daemon=True,
)
api_thread.start()
controller_thread.start()
try:
while api_thread.is_alive():
api_thread.join(timeout=1)
finally:
stop.set()
server.shutdown()
server.server_close()
controller_thread.join(timeout=max(1.0, poll_seconds + 1.0))
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--state-root", required=True, type=Path)
parser.add_argument("--repository", required=True, type=Path)
parser.add_argument("--host", default="127.0.0.1")
parser.add_argument("--port", default=18891, type=int)
parser.add_argument("--poll-seconds", default=30.0, type=float)
arguments = parser.parse_args()
if arguments.poll_seconds <= 0:
raise SystemExit("poll seconds must be positive")
if os.environ.get("AIOS_GITOPS_WRITES_ENABLED", "false").lower() != "false":
raise SystemExit("GitOps writes must remain disabled")
if (
os.environ.get(
"AIOS_SILENT_RELEASE_EXECUTION_ENABLED", "false"
).lower()
!= "false"
):
raise SystemExit("Silent Release execution must remain disabled")
serve_shadow(
state_root=arguments.state_root,
repository=arguments.repository,
host=arguments.host,
port=arguments.port,
poll_seconds=arguments.poll_seconds,
)
if __name__ == "__main__":
main()
File diff suppressed because it is too large Load Diff
+21
View File
@@ -0,0 +1,21 @@
"""Task Plane runtime package."""
from .models import (
EvidenceEnvelope,
ProbeEvidence,
ProbeOutcome,
TaskPlan,
TaskRecord,
TaskStatus,
TaskStateTransitionError,
)
__all__ = [
"EvidenceEnvelope",
"ProbeEvidence",
"ProbeOutcome",
"TaskPlan",
"TaskRecord",
"TaskStatus",
"TaskStateTransitionError",
]
@@ -0,0 +1,17 @@
"""Adapters for executing tasks via worker backends."""
from .base import WorkerAdapter
from .openclaw import OpenClawAdapter
from .codex import CodexAdapter
from .hermes import HermesAdapter
from .a2a import A2AAdapter
from .systemd_worker import SystemdWorkerAdapter
__all__ = [
"WorkerAdapter",
"OpenClawAdapter",
"CodexAdapter",
"HermesAdapter",
"A2AAdapter",
"SystemdWorkerAdapter",
]
@@ -0,0 +1,31 @@
from __future__ import annotations
from .base import WorkerAdapter
class A2AAdapter(WorkerAdapter):
worker_name = "a2a"
def capabilities(self) -> list[str]:
return ["task.exchange", "agent.handoff"]
def claim(self, task):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
def execute(self, task, claim):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
def heartbeat(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
def report_progress(self, claim, progress):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
def probe(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
def cancel(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
def collect_result(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
@@ -0,0 +1,41 @@
"""Base worker adapter contract."""
from __future__ import annotations
import abc
class WorkerAdapter(abc.ABC):
worker_name = "base"
@abc.abstractmethod
def capabilities(self) -> list[str]:
raise NotImplementedError
@abc.abstractmethod
def claim(self, task):
raise NotImplementedError
@abc.abstractmethod
def execute(self, task, claim):
raise NotImplementedError
@abc.abstractmethod
def heartbeat(self, claim):
raise NotImplementedError
@abc.abstractmethod
def report_progress(self, claim, progress):
raise NotImplementedError
@abc.abstractmethod
def probe(self, claim):
raise NotImplementedError
@abc.abstractmethod
def cancel(self, claim):
raise NotImplementedError
@abc.abstractmethod
def collect_result(self, claim):
raise NotImplementedError
@@ -0,0 +1,31 @@
from __future__ import annotations
from .base import WorkerAdapter
class CodexAdapter(WorkerAdapter):
worker_name = "codex"
def capabilities(self) -> list[str]:
return ["code.read", "code.write.patch", "test.python", "review.security"]
def claim(self, task):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
def execute(self, task, claim):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
def heartbeat(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
def report_progress(self, claim, progress):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
def probe(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
def cancel(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
def collect_result(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
@@ -0,0 +1,31 @@
from __future__ import annotations
from .base import WorkerAdapter
class HermesAdapter(WorkerAdapter):
worker_name = "hermes"
def capabilities(self) -> list[str]:
return ["architecture.review", "policy.review", "threat.model"]
def claim(self, task):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
def execute(self, task, claim):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
def heartbeat(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
def report_progress(self, claim, progress):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
def probe(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
def cancel(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
def collect_result(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
@@ -0,0 +1,31 @@
from __future__ import annotations
from .base import WorkerAdapter
class OpenClawAdapter(WorkerAdapter):
worker_name = "openclaw"
def capabilities(self) -> list[str]:
return ["code.read", "code.write.patch", "test.execute", "runtime.shadow"]
def claim(self, task):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
def execute(self, task, claim):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
def heartbeat(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
def report_progress(self, claim, progress):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
def probe(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
def cancel(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
def collect_result(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
@@ -0,0 +1,31 @@
from __future__ import annotations
from .base import WorkerAdapter
class SystemdWorkerAdapter(WorkerAdapter):
worker_name = "systemd_worker"
def capabilities(self) -> list[str]:
return ["systemd.exec", "runtime.shell"]
def claim(self, task):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
def execute(self, task, claim):
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
def heartbeat(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
def report_progress(self, claim, progress):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
def probe(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
def cancel(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
def collect_result(self, claim):
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
@@ -0,0 +1,27 @@
"""Agent registry abstraction."""
from __future__ import annotations
from .errors import NotFoundError
class AgentRegistry:
def __init__(self):
self._agents: dict[str, dict] = {}
def register(self, agent_id: str, metadata: dict) -> None:
self._agents[agent_id] = {"agent_id": agent_id, **metadata}
def unregister(self, agent_id: str) -> None:
if agent_id not in self._agents:
raise NotFoundError("agent")
del self._agents[agent_id]
def list(self) -> list[dict]:
return list(self._agents.values())
def get(self, agent_id: str) -> dict:
try:
return self._agents[agent_id]
except KeyError:
raise NotFoundError("agent")
+557
View File
@@ -0,0 +1,557 @@
"""Task Plane HTTP API implementation (stdlib-only)."""
from __future__ import annotations
import json
import os
import time
import uuid
import urllib.parse
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from typing import Any, Callable
from .delegation import DelegationEngine
from .errors import (
ConflictError,
ForbiddenError,
NotFoundError,
PayloadTooLargeError,
TaskPlaneHTTPError,
UnauthorizedError,
ValidationError,
)
from .evidence import EvidenceService
from .journal import TaskJournal
from .lease import LeaseManager
from .models import (
EvidenceEnvelope,
ResultEnvelope,
TaskPlan,
TaskRecord,
iso8601_now,
contains_secret_text,
validate_identifier,
)
from .policy import PolicyEngine
from .store import TaskPlaneStore
from .worker_registry import WorkerRegistry
def _json_payload(data: dict[str, Any], status: int = 200) -> tuple[int, bytes]:
body = json.dumps(data, ensure_ascii=False).encode("utf-8")
return status, body
def _bounded_int(value: Any, name: str, minimum: int, maximum: int) -> int:
try:
number = int(value)
except (TypeError, ValueError) as exc:
raise ValidationError(f"invalid {name}") from exc
if not minimum <= number <= maximum:
raise ValidationError(f"invalid {name}")
return number
class TaskPlaneService:
def __init__(self, store: TaskPlaneStore, policy: PolicyEngine | None = None):
self.store = store
self.policy = policy or PolicyEngine(
execution_enabled=False,
identity_capabilities={
"anon": {"task.creator", "task.read", "task.audit"}
},
)
self.journal = TaskJournal(store)
self.lease = LeaseManager(store)
self.workers = WorkerRegistry(store)
self.evidence = EvidenceService(store)
self.delegation = DelegationEngine(store)
self.store.probe_attestation_verifier = self.policy.probe_attestation_verifier
def create_task(self, body: dict[str, Any], idempotency_key: str | None = None) -> dict[str, Any]:
if body.get("parent_task_id"):
raise ForbiddenError("child tasks must use the delegate endpoint")
issuer = body.get("issuer", {})
actor = issuer.get("id", "anon") if isinstance(issuer, dict) else "anon"
self.policy.assert_allowed("create", actor)
try:
plan = TaskPlan.from_dict(body)
except (TypeError, ValueError) as exc:
raise ValidationError("invalid task plan") from exc
task = self.store.create_task_with_event(plan, idempotency_key=idempotency_key)
return task.to_dict()
def list_tasks(self, actor: str | None = None) -> list[dict[str, Any]]:
if actor is not None:
self.policy.assert_allowed("read", actor)
return [task.to_dict(include_task=False) for task in self.store.list_tasks()]
def get_task(self, task_id: str, actor: str | None = None) -> dict[str, Any]:
if actor is not None:
self.policy.assert_allowed("read", actor, task=self.store.get_task(task_id))
return self.store.get_task(task_id).to_dict()
def get_worker(self, worker_id: str, actor: str | None = None) -> dict[str, Any]:
if actor is not None:
self.policy.assert_allowed("read", actor)
return self.workers.get(worker_id).to_dict()
def list_workers(self, actor: str | None = None) -> list[dict[str, Any]]:
if actor is not None:
self.policy.assert_allowed("read", actor)
return [w.to_dict() for w in self.workers.list()]
def register_worker(self, body: dict[str, Any]) -> dict[str, Any]:
actor = str(body.get("actor_identity") or body.get("identity") or "")
is_admin = actor in self.policy.admin_identities
try:
existing = self.store.get_worker(str(body.get("worker_id") or ""))
except NotFoundError:
existing = None
if existing is not None and str(body.get("identity") or "") != existing.identity:
raise ConflictError("worker identity takeover rejected")
self.policy.assert_readonly_worker_registration(actor, body)
self.policy.assert_allowed(
"worker.admin" if is_admin else "worker.register", actor
)
try:
worker = self.workers.register(
body,
actor_identity=actor,
is_admin=is_admin,
expected_revision=body.get("expected_revision"),
)
except (TypeError, ValueError, KeyError) as exc:
raise ValidationError("invalid worker registration") from exc
return worker.to_dict()
def worker_heartbeat(self, worker_id: str, payload: dict[str, Any]) -> dict[str, Any]:
interval = payload.get("heartbeat_interval_seconds")
actor = str(payload.get("actor_identity") or "")
self.policy.assert_readonly_worker_binding(actor, worker_id)
self.policy.assert_allowed("worker.register", actor)
return self.workers.heartbeat(
worker_id,
heartbeat_interval_seconds=interval,
actor_identity=actor,
expected_revision=payload.get("expected_revision"),
).to_dict()
def disable_worker(self, worker_id: str, payload: dict[str, Any]) -> dict[str, Any]:
actor = str(payload.get("actor_identity") or "")
self.policy.assert_allowed("worker.admin", actor)
return self.store.disable_worker(
worker_id,
actor_identity=actor,
expected_revision=int(payload.get("expected_revision")),
reason=str(payload.get("reason") or "disabled by administrator"),
).to_dict()
def restore_worker(self, worker_id: str, payload: dict[str, Any]) -> dict[str, Any]:
actor = str(payload.get("actor_identity") or "")
self.policy.assert_allowed("worker.admin", actor)
return self.store.restore_worker(
worker_id,
actor_identity=actor,
expected_revision=int(payload.get("expected_revision")),
).to_dict()
def claim(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
self.policy.assert_allowed("claim", actor)
worker_id = body.get("worker_id")
if not worker_id:
raise ValidationError("worker_id required")
task = self.store.get_task(task_id)
self.policy.assert_readonly_worker_binding(actor, str(worker_id))
self.policy.assert_allowed("claim", actor, task=task)
lease_seconds = _bounded_int(
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
)
claim = self.lease.claim(
task_id=task_id,
worker_id=worker_id,
worker_identity=actor,
lease_seconds=lease_seconds,
expected_revision=task.revision,
operation_digest=task.task_plan.operation_digest(),
)
return {"claim_id": claim.claim_id, **claim.to_dict()}
def heartbeat(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
claim_id = body.get("claim_id")
if not claim_id:
raise ValidationError("claim_id required")
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
task = self.store.get_task(task_id)
claim = self.store.get_claim(claim_id)
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
self.policy.assert_allowed("heartbeat", actor, task=task)
if claim.worker_identity != actor:
raise ForbiddenError("claim identity mismatch")
lease_seconds = _bounded_int(
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
)
claim = self.lease.heartbeat(task_id, claim_id, lease_seconds)
return {"claim_id": claim_id, "lease_until": claim.lease_until}
def progress(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
claim_id = body.get("claim_id")
if not claim_id:
raise ValidationError("claim_id required")
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
progress = body.get("progress")
stage = body.get("stage", "RUNNING")
message = body.get("message")
if progress is None:
raise ValidationError("progress required")
task = self.store.get_task(task_id)
claim = self.store.get_claim(claim_id)
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
self.policy.assert_allowed("progress", actor, task=task)
if task.task_plan.data_classification == "credential-secret":
if message not in {None, ""} or contains_secret_text(stage):
raise ValidationError(
"credential-secret progress must contain metadata only"
)
lease_seconds = _bounded_int(
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
)
claim = self.store.record_progress(
task_id,
claim_id,
actor,
progress=progress,
stage=str(stage),
message=None if message is None else str(message),
lease_seconds=lease_seconds,
)
return {"claim_id": claim.claim_id, "status": claim.status, "progress": progress}
def complete(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
claim_id = body.get("claim_id")
if not claim_id:
raise ValidationError("claim_id required")
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
task = self.store.get_task(task_id)
status = body.get("status", "COMPLETED")
outputs = body.get("outputs", [])
evidences = body.get("evidence", [])
if not isinstance(outputs, list):
raise ValidationError("outputs must be list")
if not isinstance(evidences, list):
raise ValidationError("evidence must be list")
if any(not isinstance(ev, dict) for ev in evidences):
raise ValidationError("evidence items must be objects")
claim = self.store.get_claim(claim_id)
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
self.policy.assert_allowed("result", actor, task=task)
if claim.worker_identity != actor:
raise ForbiddenError("claim identity mismatch")
if task.task_plan.data_classification == "credential-secret":
allowed_result_keys = {
"kind",
"hash",
"sha256",
"count",
"status",
"error_code",
"signature",
"attestation_ref",
}
for entry in [*outputs, *evidences]:
if (
not isinstance(entry, dict)
or set(entry) - allowed_result_keys
or contains_secret_text(entry)
):
raise ValidationError(
"credential-secret result must contain hash/count/status only"
)
result = ResultEnvelope(
task_id=task_id,
claim_id=claim_id,
worker_identity=actor,
status=status,
outputs=outputs,
evidence=evidences,
started_at=str(body.get("started_at") or iso8601_now()),
completed_at=str(body.get("completed_at") or iso8601_now()),
result_digest=body.get("result_digest"),
signature=body.get("signature"),
attestation_ref=body.get("attestation_ref"),
operation_digest=claim.operation_digest,
)
evidence_decision = self.policy.evidence_verifier.verify(task, evidences)
if not evidence_decision.allowed:
raise ForbiddenError(evidence_decision.reason)
result_decision = self.policy.verify_result(result, task)
if not result_decision.allowed:
raise ForbiddenError(result_decision.reason)
result.result_digest = result.computed_digest()
previous = self.store._last_evidence_hash(task_id)
evidence_entries = []
for evidence in evidences:
envelope = EvidenceEnvelope.create(
task_id=task_id,
claim_id=claim_id,
kind=str(evidence.get("kind") or evidence.get("type") or "generic"),
worker_identity=actor,
payload=evidence,
previous_evidence_hash=previous,
signature=evidence.get("signature"),
attestation_ref=evidence.get("attestation_ref"),
)
evidence_entries.append(envelope)
previous = envelope.evidence_digest
self.store.complete_claim_with_evidence_and_event(
task_id,
claim_id,
status
if status
in {"COMPLETED", "FAILED_FINAL", "FAILED_RECOVERABLE", "CANCELLED"}
else "COMPLETED",
result.to_dict(),
evidence_entries,
)
return result.to_dict()
def fail(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
claim_id = body.get("claim_id")
if not claim_id:
raise ValidationError("claim_id required")
reason = body.get("reason", "failed")
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
self.policy.assert_allowed("fail", actor)
task = self.store.get_task(task_id)
self.policy.assert_allowed("fail", actor, task=task)
claim = self.store.get_claim(claim_id)
if claim.worker_identity != actor:
raise ForbiddenError("claim identity mismatch")
status = "FAILED_RECOVERABLE" if body.get("recoverable", False) else "FAILED_FINAL"
self.store.fail_claim_with_event(task_id, claim_id, status, str(reason))
return {"task_id": task_id, "status": status, "reason": reason}
def cancel(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
actor = body.get("actor_identity") or body.get("worker_identity") or "owner"
self.policy.assert_allowed("cancel", actor)
reason = body.get("reason", "cancelled")
task = self.store.get_task(task_id)
self.policy.assert_allowed("cancel", actor, task=task)
updated = self.store.cancel_task_with_event(
task_id, task.revision, reason=reason
)
return updated.to_dict()
def delegate(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
actor = body.get("actor_identity") or "owner"
self.policy.assert_allowed("delegate", actor)
parent = self.store.get_task(task_id)
self.policy.assert_allowed("delegate", actor, task=parent)
if "task" in body:
try:
child_plan = TaskPlan.from_dict(body["task"])
except (TypeError, ValueError) as exc:
raise ValidationError("invalid child task plan") from exc
else:
plan_body = dict(body)
plan_body.pop("actor_identity", None)
try:
child_plan = TaskPlan.from_dict(plan_body)
except (TypeError, ValueError) as exc:
raise ValidationError("invalid child task plan") from exc
child_plan.parent_task_id = task_id
child = self.delegation.delegate(task_id, child_plan, caller=actor)
return child.to_dict()
def get_events(self, task_id: str, actor: str | None = None) -> list[dict[str, Any]]:
if actor is not None:
self.policy.assert_allowed("audit", actor, task=self.store.get_task(task_id))
self.store.get_task(task_id)
return self.store.list_events(task_id)
def get_evidence(self, task_id: str, actor: str | None = None) -> list[dict[str, Any]]:
if actor is not None:
self.policy.assert_allowed("audit", actor, task=self.store.get_task(task_id))
self.store.get_task(task_id)
return self.evidence.list(task_id)
def get_children(self, task_id: str, actor: str | None = None) -> list[str]:
if actor is not None:
self.policy.assert_allowed("read", actor, task=self.store.get_task(task_id))
self.store.get_task(task_id)
return self.store.list_children(task_id)
class TaskPlaneRequestHandler(BaseHTTPRequestHandler):
service: TaskPlaneService | None = None
authenticator: Callable[[str], str | None] | None = None
max_body_bytes = 1_000_000
def log_message(self, format: str, *args: Any) -> None:
# BaseHTTPRequestHandler logs the raw request target; suppress it so
# attacker-controlled paths or query strings cannot leak credentials.
return
def _json(self) -> tuple[str | None, dict[str, Any]]:
try:
length = int(self.headers.get("Content-Length", "0"))
except ValueError as exc:
raise ValidationError("invalid content length") from exc
if length < 0:
raise ValidationError("invalid content length")
if length > self.max_body_bytes:
raise PayloadTooLargeError("payload exceeds limit")
raw = self.rfile.read(length) if length > 0 else b""
if not raw:
return None, {}
try:
decoded = raw.decode("utf-8")
payload = json.loads(decoded)
if not isinstance(payload, dict):
raise ValidationError("JSON payload must be an object")
return decoded, payload
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
raise ValidationError("invalid JSON payload") from exc
def _response(self, status: int, payload: Any) -> None:
encoded = json.dumps(payload, ensure_ascii=False).encode("utf-8")
self.send_response(status)
self.send_header("Content-Type", "application/json; charset=utf-8")
self.send_header("Content-Length", str(len(encoded)))
self.end_headers()
self.wfile.write(encoded)
def _authenticated_identity(self) -> str:
authenticator = type(self).authenticator
if authenticator is None:
raise UnauthorizedError("authentication unavailable")
header = self.headers.get("Authorization", "")
if not header.startswith("Bearer "):
raise UnauthorizedError("bearer authentication required")
token = header[7:]
if not token or any(ord(ch) < 33 for ch in token):
raise UnauthorizedError("invalid bearer token")
identity = authenticator(token)
if not identity:
raise UnauthorizedError("invalid credentials")
return str(identity)
def _handle(self, handler):
try:
if self.service is None:
raise TaskPlaneHTTPError("service not configured")
result = handler()
if isinstance(result, tuple):
status, payload = result
else:
status, payload = 200, result
self._response(status, payload)
except TaskPlaneHTTPError as exc:
self._response(exc.status_code, exc.to_payload())
except Exception as exc: # defensive
if isinstance(exc, TaskPlaneHTTPError):
raise
self._response(
500,
{"error": "internal_error", "message": "internal server error"},
)
def do_GET(self): # noqa: N802
def route():
path = urllib.parse.urlparse(self.path).path
parts = [p for p in path.split("/") if p]
for part in parts[1:]:
if part not in {"events", "evidence", "children", "heartbeat"}:
try:
validate_identifier(part, "resource identifier")
except ValueError as exc:
raise ValidationError("invalid resource identifier") from exc
identity = self._authenticated_identity()
if len(parts) == 1 and parts[0] == "tasks":
return 200, self.service.list_tasks(identity)
if len(parts) == 2 and parts[0] == "tasks":
task_id = parts[1]
return 200, self.service.get_task(task_id, identity)
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "events":
return 200, self.service.get_events(parts[1], identity)
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "evidence":
return 200, self.service.get_evidence(parts[1], identity)
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "children":
return 200, self.service.get_children(parts[1], identity)
if len(parts) == 1 and parts[0] == "workers":
return 200, self.service.list_workers(identity)
if len(parts) == 2 and parts[0] == "workers":
return 200, self.service.get_worker(parts[1], identity)
raise NotFoundError("unknown endpoint")
self._handle(route)
def do_POST(self): # noqa: N802
def route():
body_text, body = self._json()
identity = self._authenticated_identity()
path = urllib.parse.urlparse(self.path).path
parts = [p for p in path.split("/") if p]
headers = {k.lower(): v for k, v in self.headers.items()}
if len(parts) == 1 and parts[0] == "tasks":
issuer = body.get("issuer")
if issuer and (
not isinstance(issuer, dict) or issuer.get("id") != identity
):
raise ForbiddenError("issuer identity mismatch")
body["issuer"] = {"type": "authenticated", "id": identity}
return 201, self.service.create_task(body or {}, headers.get("idempotency-key"))
if body.get("actor_identity") not in {None, identity}:
raise ForbiddenError("actor identity mismatch")
body["actor_identity"] = identity
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "claim":
return 200, self.service.claim(parts[1], body or {})
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "heartbeat":
return 200, self.service.heartbeat(parts[1], body or {})
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "progress":
return 200, self.service.progress(parts[1], body or {})
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "result":
return 200, self.service.complete(parts[1], body or {})
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "fail":
return 200, self.service.fail(parts[1], body or {})
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "cancel":
return 200, self.service.cancel(parts[1], body or {})
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "delegate":
return 200, self.service.delegate(parts[1], body or {})
if len(parts) == 2 and parts[0] == "workers" and parts[1] == "register":
if (
body.get("identity") != identity
and identity not in self.service.policy.admin_identities
):
raise ForbiddenError("worker identity mismatch")
return 201, self.service.register_worker(body or {})
if len(parts) == 3 and parts[0] == "workers" and parts[2] == "heartbeat":
return 200, self.service.worker_heartbeat(parts[1], body or {})
if len(parts) == 3 and parts[0] == "workers" and parts[2] == "disable":
return 200, self.service.disable_worker(parts[1], body or {})
if len(parts) == 3 and parts[0] == "workers" and parts[2] == "restore":
return 200, self.service.restore_worker(parts[1], body or {})
raise NotFoundError("unknown endpoint")
self._handle(route)
def run_server(
host: str,
port: int,
service: TaskPlaneService,
*,
authenticator: Callable[[str], str | None] | None = None,
):
handler = TaskPlaneRequestHandler
handler.service = service
handler.authenticator = authenticator
server = ThreadingHTTPServer((host, port), handler)
server.serve_forever()
@@ -0,0 +1,36 @@
"""Capability matcher helpers."""
from __future__ import annotations
from fnmatch import fnmatch
def _normalize_capability(capability: str) -> str:
return capability.strip().lower()
def capability_matches(granted: str, required: str) -> bool:
granted = _normalize_capability(granted)
required = _normalize_capability(required)
if granted == required:
return True
# A granted wildcard such as "test.*" should match required "test.unit"
if "*" in granted:
return fnmatch(required, granted)
# A required wildcard is treated as a suffix/prefix requirement for callers.
if "*" in required:
return fnmatch(granted, required)
return False
def has_capabilities(granted_caps: list[str], required_caps: list[str]) -> bool:
granted = [_normalize_capability(c) for c in granted_caps]
for required in required_caps:
required = _normalize_capability(required)
if not any(capability_matches(g, required) for g in granted):
return False
return True
def normalize_capabilities(caps: list[str]) -> list[str]:
return sorted({_normalize_capability(cap) for cap in caps})
@@ -0,0 +1,87 @@
"""Delegation guardrails."""
from __future__ import annotations
from .errors import ConflictError, ForbiddenError, NotFoundError
from .models import Budget, TaskPlan, TaskRecord
from .store import TaskPlaneStore
class DelegationEngine:
def __init__(self, store: TaskPlaneStore):
self.store = store
def can_delegate(self, parent_id: str, child_plan: TaskPlan) -> bool:
parent = self.store.get_task(parent_id)
if parent.status == "COMPLETED":
raise ConflictError("cannot delegate completed task")
if parent.task_plan.max_delegation_depth <= 0:
raise ConflictError("max delegation depth not configured")
depth = self._depth(parent_id)
if depth >= parent.task_plan.max_delegation_depth:
raise ConflictError("max delegation depth reached")
if child_plan.parent_task_id not in {None, parent_id}:
raise ConflictError("delegation parent mismatch")
current = parent_id
while current:
if child_plan.task_id and current == child_plan.task_id:
raise ConflictError("delegation cycle")
current = self.store.parent_of(current)
return True
def delegate(self, parent_id: str, child_plan: TaskPlan, *, caller: str) -> TaskRecord:
self.can_delegate(parent_id, child_plan)
parent = self.store.get_task(parent_id)
if child_plan.required_capabilities and not set(child_plan.required_capabilities).issubset(
set(parent.task_plan.required_capabilities or [])
):
raise ForbiddenError("child capabilities exceed parent constraints")
risk_rank = {"low": 1, "medium": 2, "high": 3}
if risk_rank.get(child_plan.risk, 99) > risk_rank.get(parent.task_plan.risk, -1):
raise ForbiddenError("child risk exceeds parent constraints")
child_plan.parent_task_id = parent_id
child_plan.correlation_id = parent.task_plan.correlation_id or parent.task_id
child_plan.preferred_workers = parent.task_plan.preferred_workers
child_plan.max_delegation_depth = min(
child_plan.max_delegation_depth,
parent.task_plan.max_delegation_depth,
)
child_plan.approval_policy = parent.task_plan.approval_policy
parent_budget = self.store.get_task_budget(parent_id)
required = Budget()
for name in ("time_seconds", "attempts", "tokens", "cost"):
available = getattr(parent_budget, name)
requested = getattr(child_plan.budgets, name)
if name == "attempts" and requested is None:
requested = 1
if available is not None:
requested = 0 if requested is None else requested
if requested > available:
raise ConflictError(f"budget exceeded for {name}")
setattr(child_plan.budgets, name, requested)
setattr(required, name, requested)
# A retried identical delegation is a read, not a second budget charge.
if child_plan.task_id:
try:
existing = self.store.get_task(child_plan.task_id)
except NotFoundError:
existing = None
if existing is not None:
if (
existing.task_plan.parent_task_id == parent_id
and existing.task_plan.operation_digest()
== child_plan.operation_digest()
):
return existing
raise ConflictError("delegation task_id conflict")
return self.store.delegate_task_with_budget_and_events(
parent_id, child_plan, caller=caller
)
def _depth(self, task_id: str) -> int:
return self.store._compute_depth(task_id)
+71
View File
@@ -0,0 +1,71 @@
"""Error types for task plane operations."""
from __future__ import annotations
class TaskPlaneError(Exception):
"""Base exception for API-compatible failures."""
status_code = 500
error_code = "task_plane_error"
def __init__(self, message: str, *, code: str | None = None, details: dict | None = None):
super().__init__(message)
self.message = message
self.details = details or {}
if code:
self.error_code = code
def to_payload(self) -> dict:
return {"error": self.error_code, "message": self.message, "details": self.details}
class TaskPlaneHTTPError(TaskPlaneError):
"""Base class with explicit HTTP status."""
status_code = 500
class ValidationError(TaskPlaneHTTPError):
status_code = 400
error_code = "validation_error"
class UnauthorizedError(TaskPlaneHTTPError):
status_code = 401
error_code = "unauthorized"
class ForbiddenError(TaskPlaneHTTPError):
status_code = 403
error_code = "forbidden"
class NotFoundError(TaskPlaneHTTPError):
status_code = 404
error_code = "not_found"
class ConflictError(TaskPlaneHTTPError):
status_code = 409
error_code = "conflict"
class PayloadTooLargeError(TaskPlaneHTTPError):
status_code = 413
error_code = "payload_too_large"
class FailedDependencyError(TaskPlaneHTTPError):
status_code = 424
error_code = "failed_dependency"
class LockedError(TaskPlaneHTTPError):
status_code = 423
error_code = "locked"
class ServiceUnavailableError(TaskPlaneHTTPError):
status_code = 503
error_code = "service_unavailable"
+108
View File
@@ -0,0 +1,108 @@
"""CloudEvents-compatible event envelope and durable outbox helpers."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime, timezone
from typing import Callable, Protocol
from .store import TaskPlaneStore
@dataclass
class CloudEvent:
specversion: str = "1.0"
id: str = ""
type: str = ""
source: str = "spiffe://aios/task-plane"
subject: str = ""
datacontenttype: str = "application/json"
data: dict | None = None
@property
def time(self) -> str:
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
def asdict(self) -> dict:
return {
"specversion": self.specversion,
"id": self.id,
"type": self.type,
"source": self.source,
"subject": self.subject,
"time": self.time,
"datacontenttype": self.datacontenttype,
"data": self.data or {},
}
NOT_DELIVERED = "NOT_DELIVERED"
DELIVERED = "DELIVERED"
FAILED_DELIVERY = "FAILED"
class NotificationAdapter(Protocol):
name: str
def deliver(self, envelope: dict) -> str | None:
"""Return a provider receipt, or None when delivery is unconfirmed."""
class CallbackNotificationAdapter:
"""Adapter seam for webhook, NATS, GPT, dashboard, and WeChat transports."""
def __init__(self, name: str, callback: Callable[[dict], str | None]):
self.name = name
self._callback = callback
def deliver(self, envelope: dict) -> str | None:
return self._callback(envelope)
class WebhookAdapter(CallbackNotificationAdapter):
def __init__(self, callback: Callable[[dict], str | None]):
super().__init__("webhook", callback)
class NatsJetStreamAdapter(CallbackNotificationAdapter):
def __init__(self, callback: Callable[[dict], str | None]):
super().__init__("nats-jetstream", callback)
class GPTResultCallbackAdapter(CallbackNotificationAdapter):
def __init__(self, callback: Callable[[dict], str | None]):
super().__init__("gpt-result-callback", callback)
class DashboardAdapter(CallbackNotificationAdapter):
def __init__(self, callback: Callable[[dict], str | None]):
super().__init__("dashboard", callback)
class WeChatGatewayAdapter(CallbackNotificationAdapter):
def __init__(self, callback: Callable[[dict], str | None]):
super().__init__("wechat-gateway", callback)
class DurableOutboxDispatcher:
def __init__(self, store: TaskPlaneStore):
self.store = store
def dispatch(self, message_id: str, adapter: NotificationAdapter) -> dict:
row = self.store.get_outbox_message(message_id)
import json
envelope = json.loads(row["payload"])
try:
receipt = adapter.deliver(envelope)
except Exception:
return self.store.record_outbox_delivery(
message_id,
receipt=None,
error=f"{adapter.name} delivery failed",
)
return self.store.record_outbox_delivery(
message_id,
receipt=str(receipt) if receipt else None,
error=None if receipt else f"{adapter.name} receipt unavailable",
)
+31
View File
@@ -0,0 +1,31 @@
"""Evidence helpers."""
from __future__ import annotations
import hashlib
import json
from .store import TaskPlaneStore
def evidence_digest(payload: dict) -> str:
body = json.dumps(payload, sort_keys=True, separators=(",", ":"))
return hashlib.sha256(body.encode("utf-8")).hexdigest()
class EvidenceService:
def __init__(self, store: TaskPlaneStore):
self.store = store
def add(self, task_id: str, kind: str, payload: dict, worker_identity: str) -> str:
return self.store.add_evidence(task_id, kind, payload, worker_identity)
def list(self, task_id: str) -> list[dict]:
return self.store.list_evidence(task_id)
def verify(self, task_id: str, required_kinds: list[str]) -> bool:
evidences = self.list(task_id)
observed = {e["kind"] for e in evidences}
return set(required_kinds).issubset(
observed
) and self.store.verify_evidence_integrity(task_id)
+22
View File
@@ -0,0 +1,22 @@
"""Event journaling helpers."""
from __future__ import annotations
from .errors import ValidationError
from .store import TaskPlaneStore
class TaskJournal:
def __init__(self, store: TaskPlaneStore):
self.store = store
def append(self, task_id: str, event_type: str, data: dict, *, subject: str | None = None) -> None:
if not event_type:
raise ValidationError("event_type required")
self.store.append_event(task_id, event_type, data, subject=subject)
def list(self, task_id: str) -> list[dict]:
return self.store.list_events(task_id)
def check_chain(self, task_id: str) -> bool:
return self.store.verify_event_chain(task_id)
+32
View File
@@ -0,0 +1,32 @@
"""Claim and lease management helpers."""
from __future__ import annotations
from .errors import LockedError
from .models import ProbeEvidence
from .store import TaskPlaneStore
class LeaseManager:
def __init__(self, store: TaskPlaneStore):
self.store = store
def claim(self, task_id: str, worker_id: str, worker_identity: str, lease_seconds: int, expected_revision: int, operation_digest: str):
return self.store.claim_task(task_id, worker_id, worker_identity, lease_seconds, expected_revision, operation_digest)
def heartbeat(self, task_id: str, claim_id: str, lease_seconds: int):
claim = self.store.heartbeat_claim(task_id, claim_id, lease_seconds)
return claim
def probe(self, claim_id: str):
claim = self.store.get_claim(claim_id)
if claim.status != "ACTIVE":
raise LockedError("claim not active")
return claim
def recover(self, task_id: str, claim_id: str, probe: ProbeEvidence):
return self.store.recover_expired_claim(
task_id,
claim_id,
probe,
)
+829
View File
@@ -0,0 +1,829 @@
"""Core data models for the task plane."""
from __future__ import annotations
import hashlib
import json
import re
import time
import uuid
import urllib.parse
from enum import StrEnum
from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Any
SENSITIVE_KEYS = {
"secret",
"password",
"token",
"api_key",
"access_token",
"refresh_token",
"authorization",
"private_key",
"client_secret",
"credential",
}
IDENTIFIER_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._:-]{0,127}")
TYPE_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._-]{0,127}")
RISK_LEVELS = {"low", "medium", "high"}
DATA_CLASSIFICATIONS = {
"public",
"internal",
"confidential",
"credential-secret",
}
SECRET_TEXT_PATTERNS = (
re.compile(r"(?i)\bAuthorization\s*:\s*Bearer\s+\S+"),
re.compile(r"(?i)\b(?:password|passwd|api[_-]?key|access[_-]?token|secret)\s*[:=]\s*\S+"),
re.compile(r"\bsk-[A-Za-z0-9_-]{12,}\b"),
re.compile(r"\bAKIA[0-9A-Z]{16}\b"),
re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH )?PRIVATE KEY-----"),
)
TASK_PLAN_KEYS = {
"schema_version",
"task_id",
"task_type",
"issuer",
"intent",
"required_capabilities",
"preferred_workers",
"risk",
"approval_policy",
"dependencies",
"max_delegation_depth",
"budgets",
"evidence_requirements",
"parent_task_id",
"correlation_id",
"metadata",
"data_classification",
"execution_zone",
"network_policy",
"logging_policy",
"allowed_input_paths",
"allowed_output_paths",
"output_policy",
}
def _now_ts() -> float:
return time.time()
def canonical_json(value: Any) -> str:
return json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
def compute_sha256_hex(value: Any) -> str:
return hashlib.sha256(canonical_json(value).encode("utf-8")).hexdigest()
def contains_secret_text(value: Any) -> bool:
if isinstance(value, str):
return any(pattern.search(value) for pattern in SECRET_TEXT_PATTERNS)
if isinstance(value, dict):
return any(contains_secret_text(item) for item in value.values())
if isinstance(value, (list, tuple)):
return any(contains_secret_text(item) for item in value)
return False
def validate_relative_paths(values: Any, name: str) -> list[str]:
paths = _normalize_list(values)
for value in paths:
decoded = urllib.parse.unquote(value)
parts = value.replace("\\", "/").split("/")
if (
decoded != value
or "\\" in value
or value.startswith("/")
or re.match(r"^[A-Za-z]:", value)
or any(part in {"", ".", ".."} for part in parts)
):
raise ValueError(f"invalid {name}")
return paths
def validate_identifier(value: Any, name: str) -> str:
text = str(value or "")
if (
not IDENTIFIER_RE.fullmatch(text)
or urllib.parse.unquote(text) != text
or any(ord(ch) < 32 or ord(ch) == 127 for ch in text)
):
raise ValueError(f"invalid {name}")
return text
def validate_type(value: Any, name: str) -> str:
text = str(value or "")
if not TYPE_RE.fullmatch(text):
raise ValueError(f"invalid {name}")
return text
def redact_value(value: Any) -> Any:
if isinstance(value, dict):
redacted = {}
for key, inner in value.items():
lowered = str(key).lower()
if lowered in SENSITIVE_KEYS or lowered.endswith(
("_password", "_secret", "_access_token", "_refresh_token", "_private_key")
):
redacted[key] = "[REDACTED]"
else:
redacted[key] = redact_value(inner)
return redacted
if isinstance(value, list):
return [redact_value(v) for v in value]
if isinstance(value, tuple):
return tuple(redact_value(v) for v in value)
return value
class TaskStateTransitionError(ValueError):
pass
class TaskStatus(StrEnum):
CREATED = "CREATED"
QUEUED = "QUEUED"
CLAIMED = "CLAIMED"
RUNNING = "RUNNING"
WAITING_CHILD = "WAITING_CHILD"
VERIFYING = "VERIFYING"
COMPLETED = "COMPLETED"
FAILED_RECOVERABLE = "FAILED_RECOVERABLE"
FAILED_FINAL = "FAILED_FINAL"
CANCELLED = "CANCELLED"
MANUAL_REVIEW_REQUIRED = "MANUAL_REVIEW_REQUIRED"
TASK_STATES = {
status.value for status in TaskStatus
}
TASK_NEXT_STATES = {
"CREATED": {"QUEUED", "CLAIMED", "CANCELLED", "MANUAL_REVIEW_REQUIRED"},
"QUEUED": {"CLAIMED", "CANCELLED", "FAILED_RECOVERABLE", "FAILED_FINAL"},
"CLAIMED": {"RUNNING", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
"RUNNING": {"VERIFYING", "WAITING_CHILD", "COMPLETED", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
"WAITING_CHILD": {"RUNNING", "VERIFYING", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
"VERIFYING": {"COMPLETED", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
"COMPLETED": set(),
"FAILED_RECOVERABLE": {"CLAIMED", "RUNNING", "CANCELLED"},
"FAILED_FINAL": set(),
"CANCELLED": set(),
"MANUAL_REVIEW_REQUIRED": {"RUNNING", "CANCELLED"},
}
@dataclass
class Budget:
time_seconds: int | None = None
attempts: int | None = None
tokens: int | None = None
cost: float | None = None
@classmethod
def from_dict(cls, data: dict[str, Any] | None) -> "Budget":
if not data:
return cls()
if not isinstance(data, dict) or set(data) - {
"time_seconds",
"attempts",
"tokens",
"cost",
}:
raise ValueError("invalid budget")
for name in ("time_seconds", "attempts", "tokens", "cost"):
value = data.get(name)
if value is not None:
try:
if float(value) < 0:
raise ValueError("budget values must be non-negative")
except (TypeError, ValueError) as exc:
raise ValueError("invalid budget value") from exc
return cls(
time_seconds=_to_positive_int(data.get("time_seconds")),
attempts=_to_positive_int(data.get("attempts")),
tokens=_to_positive_int(data.get("tokens")),
cost=_to_float(data.get("cost")),
)
def to_dict(self) -> dict[str, Any]:
return {
"time_seconds": self.time_seconds,
"attempts": self.attempts,
"tokens": self.tokens,
"cost": self.cost,
}
def merge(self, other: "Budget") -> "Budget":
return Budget(
time_seconds=_first_non_none(self.time_seconds, other.time_seconds),
attempts=_first_non_none(self.attempts, other.attempts),
tokens=_first_non_none(self.tokens, other.tokens),
cost=_first_non_none(self.cost, other.cost),
)
@dataclass
class TaskPlan:
schema_version: int = 1
task_id: str | None = None
task_type: str = "code.change"
issuer: dict[str, Any] = field(default_factory=dict)
intent: str | None = None
required_capabilities: list[str] = field(default_factory=list)
preferred_workers: list[str] = field(default_factory=list)
risk: str = "medium"
approval_policy: str = "patch-only"
dependencies: list[str] = field(default_factory=list)
max_delegation_depth: int = 5
budgets: Budget = field(default_factory=Budget)
evidence_requirements: list[str] = field(default_factory=list)
parent_task_id: str | None = None
correlation_id: str | None = None
metadata: dict[str, Any] = field(default_factory=dict)
data_classification: str = "internal"
execution_zone: str = "isolated-development"
network_policy: str = "controlled"
logging_policy: str = "redacted"
allowed_input_paths: list[str] = field(default_factory=list)
allowed_output_paths: list[str] = field(default_factory=list)
output_policy: str = "standard"
@classmethod
def from_dict(cls, data: dict[str, Any] | None) -> "TaskPlan":
if not isinstance(data, dict):
raise ValueError("task plan payload must be an object")
unknown = set(data) - TASK_PLAN_KEYS
if unknown:
raise ValueError("unknown task plan fields")
if "task_id" not in data or data["task_id"] is None:
data = dict(data)
data["task_id"] = f"task-{uuid.uuid4()}"
risk = str(data.get("risk", "medium"))
if risk not in RISK_LEVELS:
raise ValueError("invalid risk")
issuer = data.get("issuer", {})
if not isinstance(issuer, dict):
raise ValueError("issuer must be an object")
schema_version = int(data.get("schema_version", 1))
if schema_version != 1:
raise ValueError("unsupported schema_version")
max_depth = _to_positive_int(data.get("max_delegation_depth"), default=5)
if max_depth is None or max_depth > 32:
raise ValueError("invalid max_delegation_depth")
classification = str(data.get("data_classification", "internal"))
if classification not in DATA_CLASSIFICATIONS:
raise ValueError("invalid data_classification")
execution_zone = validate_type(
data.get("execution_zone", "isolated-development"), "execution_zone"
)
network_policy = validate_type(
data.get("network_policy", "controlled"), "network_policy"
)
logging_policy = validate_type(
data.get("logging_policy", "redacted"), "logging_policy"
)
output_policy = validate_type(
data.get("output_policy", "standard"), "output_policy"
)
if contains_secret_text(
{
"intent": data.get("intent"),
"metadata": data.get("metadata", {}),
}
):
raise ValueError("task content contains secret material")
if classification == "credential-secret":
if execution_zone != "secure-file-transformer":
raise ValueError("credential-secret requires secure-file-transformer")
if network_policy != "denied":
raise ValueError("credential-secret requires network denied")
if logging_policy != "metadata-only":
raise ValueError("credential-secret requires metadata-only logging")
if output_policy != "hash-count-status-only":
raise ValueError("credential-secret requires restricted output")
return cls(
schema_version=schema_version,
task_id=validate_identifier(data["task_id"], "task_id"),
task_type=validate_type(data.get("task_type", "code.change"), "task_type"),
issuer=issuer,
intent=data.get("intent"),
required_capabilities=_normalize_list(data.get("required_capabilities", [])),
preferred_workers=_normalize_list(data.get("preferred_workers", [])),
risk=risk,
approval_policy=validate_type(
data.get("approval_policy", "patch-only"), "approval_policy"
),
dependencies=_normalize_list(data.get("dependencies", [])),
max_delegation_depth=max_depth,
budgets=Budget.from_dict(data.get("budgets")),
evidence_requirements=_normalize_list(data.get("evidence_requirements", [])),
parent_task_id=data.get("parent_task_id"),
correlation_id=data.get("correlation_id"),
metadata=data.get("metadata", {}) if isinstance(data.get("metadata", {}), dict) else {},
data_classification=classification,
execution_zone=execution_zone,
network_policy=network_policy,
logging_policy=logging_policy,
allowed_input_paths=validate_relative_paths(
data.get("allowed_input_paths", []), "allowed_input_paths"
),
allowed_output_paths=validate_relative_paths(
data.get("allowed_output_paths", []), "allowed_output_paths"
),
output_policy=output_policy,
)
def to_dict(self, *, redact: bool = False) -> dict[str, Any]:
payload = {
"schema_version": self.schema_version,
"task_id": self.task_id,
"task_type": self.task_type,
"issuer": self.issuer,
"intent": self.intent,
"required_capabilities": list(self.required_capabilities),
"preferred_workers": list(self.preferred_workers),
"risk": self.risk,
"approval_policy": self.approval_policy,
"dependencies": list(self.dependencies),
"max_delegation_depth": self.max_delegation_depth,
"budgets": self.budgets.to_dict(),
"evidence_requirements": list(self.evidence_requirements),
"parent_task_id": self.parent_task_id,
"correlation_id": self.correlation_id,
"metadata": dict(self.metadata),
"data_classification": self.data_classification,
"execution_zone": self.execution_zone,
"network_policy": self.network_policy,
"logging_policy": self.logging_policy,
"allowed_input_paths": list(self.allowed_input_paths),
"allowed_output_paths": list(self.allowed_output_paths),
"output_policy": self.output_policy,
}
if redact:
payload = redact_value(payload)
return payload
def operation_digest(self) -> str:
return compute_sha256_hex(self.to_dict())
@dataclass
class TaskRecord:
task_id: str
status: str
revision: int
task_plan: TaskPlan
created_at: float
updated_at: float
root_task_id: str
idempotency_key: str | None = None
failure_reason: str | None = None
def with_status(self, status: str) -> "TaskRecord":
allowed = TASK_NEXT_STATES.get(self.status, set())
if status != self.status and (not allowed and self.status not in {"COMPLETED", "FAILED_FINAL", "CANCELLED"}):
raise TaskStateTransitionError(f"Cannot transition {self.status} -> {status}")
if status not in TASK_STATES:
raise TaskStateTransitionError(f"Invalid status {status}")
if status != self.status and self.status in TASK_NEXT_STATES and status not in TASK_NEXT_STATES[self.status]:
raise TaskStateTransitionError(f"Cannot transition {self.status} -> {status}")
return TaskRecord(
task_id=self.task_id,
status=status,
revision=self.revision + 1,
task_plan=self.task_plan,
created_at=self.created_at,
updated_at=_now_ts(),
root_task_id=self.root_task_id,
idempotency_key=self.idempotency_key,
failure_reason=self.failure_reason,
)
def to_dict(self, *, include_task=True, redact_payload: bool = True) -> dict[str, Any]:
payload = {
"task_id": self.task_id,
"status": self.status,
"revision": self.revision,
"root_task_id": self.root_task_id,
"parent_task_id": self.task_plan.parent_task_id,
"created_at": _fmt_ts(self.created_at),
"updated_at": _fmt_ts(self.updated_at),
"failure_reason": self.failure_reason,
}
if include_task:
payload["plan"] = self.task_plan.to_dict(redact=redact_payload)
if self.idempotency_key:
payload["idempotency_key"] = self.idempotency_key
return payload
@dataclass
class WorkerRegistration:
worker_id: str
worker_type: str
identity: str
capabilities: list[str]
trust_zone: str
max_concurrency: int
heartbeat_interval_seconds: int
supported_protocols: list[str]
registered_at: float
last_heartbeat: float
status: str = "active"
disabled: bool = False
owner_identity: str = ""
registration_revision: int = 1
registration_policy: str = "self"
created_at: float = 0.0
updated_at: float = 0.0
disabled_reason: str | None = None
@classmethod
def from_dict(cls, data: dict[str, Any]) -> "WorkerRegistration":
if not isinstance(data, dict):
raise ValueError("worker registration payload must be an object")
now = _now_ts()
worker_id = validate_identifier(data.get("worker_id"), "worker_id")
worker_type = validate_type(data.get("worker_type"), "worker_type")
identity = str(data.get("identity") or "").strip()
if not identity or any(ord(ch) < 32 for ch in identity):
raise ValueError("invalid identity")
max_concurrency = _to_positive_int(data.get("max_concurrency"), default=1)
heartbeat_interval = _to_positive_int(
data.get("heartbeat_interval_seconds"), default=15
)
if not max_concurrency:
raise ValueError("max_concurrency must be positive")
if not heartbeat_interval:
raise ValueError("heartbeat_interval_seconds must be positive")
return cls(
worker_id=worker_id,
worker_type=worker_type,
identity=identity,
capabilities=_normalize_list(data.get("capabilities", [])),
trust_zone=str(data.get("trust_zone") or "default"),
max_concurrency=max_concurrency,
heartbeat_interval_seconds=heartbeat_interval,
supported_protocols=_normalize_list(
data.get("supported_protocols", ["aios-task-v1"])
),
registered_at=float(data.get("registered_at") or now),
last_heartbeat=float(data.get("last_heartbeat") or now),
status=str(data.get("status") or "active"),
disabled=bool(data.get("disabled", False)),
owner_identity=str(data.get("owner_identity") or identity),
registration_revision=int(data.get("registration_revision") or 1),
registration_policy=str(data.get("registration_policy") or "self"),
created_at=float(data.get("created_at") or data.get("registered_at") or now),
updated_at=float(data.get("updated_at") or now),
disabled_reason=data.get("disabled_reason"),
)
def to_dict(self, redact_payload: bool = True) -> dict[str, Any]:
payload = {
"worker_id": self.worker_id,
"worker_type": self.worker_type,
"identity": self.identity,
"capabilities": list(self.capabilities),
"trust_zone": self.trust_zone,
"max_concurrency": self.max_concurrency,
"heartbeat_interval_seconds": self.heartbeat_interval_seconds,
"supported_protocols": list(self.supported_protocols),
"registered_at": _fmt_ts(self.registered_at),
"last_heartbeat": _fmt_ts(self.last_heartbeat),
"status": self.status,
"disabled": self.disabled,
"owner_identity": self.owner_identity,
"registration_revision": self.registration_revision,
"registration_policy": self.registration_policy,
"created_at": _fmt_ts(self.created_at or self.registered_at),
"updated_at": _fmt_ts(self.updated_at or self.last_heartbeat),
"disabled_reason": self.disabled_reason,
}
if redact_payload:
payload = redact_value(payload)
return payload
@dataclass(frozen=True)
class EvidenceEnvelope:
schema_version: int
evidence_id: str
task_id: str
claim_id: str
kind: str
worker_identity: str
payload: dict[str, Any]
created_at: float
previous_evidence_hash: str
evidence_digest: str
signature: str | None = None
attestation_ref: str | None = None
@classmethod
def create(
cls,
*,
task_id: str,
claim_id: str,
kind: str,
worker_identity: str,
payload: dict[str, Any],
previous_evidence_hash: str,
signature: str | None = None,
attestation_ref: str | None = None,
evidence_id: str | None = None,
created_at: float | None = None,
) -> "EvidenceEnvelope":
envelope = cls(
schema_version=1,
evidence_id=evidence_id or f"evd-{uuid.uuid4()}",
task_id=validate_identifier(task_id, "task_id"),
claim_id=validate_identifier(claim_id, "claim_id"),
kind=validate_type(kind, "evidence kind"),
worker_identity=str(worker_identity),
payload=redact_value(payload),
created_at=float(created_at or _now_ts()),
previous_evidence_hash=str(previous_evidence_hash or ""),
evidence_digest="",
signature=signature,
attestation_ref=attestation_ref,
)
return dataclass_replace(
envelope, evidence_digest=compute_sha256_hex(envelope.digest_payload())
)
def digest_payload(self) -> dict[str, Any]:
return {
"schema_version": self.schema_version,
"evidence_id": self.evidence_id,
"task_id": self.task_id,
"claim_id": self.claim_id,
"kind": self.kind,
"worker_identity": self.worker_identity,
"payload": self.payload,
"created_at": self.created_at,
"previous_evidence_hash": self.previous_evidence_hash,
"attestation_ref": self.attestation_ref,
}
def verify(
self,
*,
expected_task_id: str,
expected_claim_id: str,
expected_previous_hash: str,
attestation_verifier: Any = None,
) -> bool:
if (
self.schema_version != 1
or self.task_id != expected_task_id
or self.claim_id != expected_claim_id
or self.previous_evidence_hash != expected_previous_hash
or self.evidence_digest != compute_sha256_hex(self.digest_payload())
):
return False
if self.signature or self.attestation_ref:
return True if attestation_verifier is None else bool(attestation_verifier(self))
return True
def to_dict(self) -> dict[str, Any]:
return {
**self.digest_payload(),
"evidence_digest": self.evidence_digest,
"signature": self.signature,
}
class ProbeOutcome(StrEnum):
NOT_APPLIED = "NOT_APPLIED"
APPLIED_VERIFIED = "APPLIED_VERIFIED"
INDETERMINATE = "INDETERMINATE"
CONFLICT = "CONFLICT"
@dataclass(frozen=True)
class ProbeEvidence:
schema_version: int
probe_id: str
task_id: str
claim_id: str
worker_id: str
worker_identity: str
operation_digest: str
outcome: ProbeOutcome
observed_at: float
expires_at: float
probe_executor_identity: str
evidence_digest: str
signature: str | None = None
attestation_ref: str | None = None
@classmethod
def create(cls, **data: Any) -> "ProbeEvidence":
outcome = data["outcome"]
if not isinstance(outcome, ProbeOutcome):
outcome = ProbeOutcome(str(outcome))
probe = cls(
schema_version=1,
probe_id=data.get("probe_id") or f"probe-{uuid.uuid4()}",
task_id=validate_identifier(data["task_id"], "task_id"),
claim_id=validate_identifier(data["claim_id"], "claim_id"),
worker_id=validate_identifier(data["worker_id"], "worker_id"),
worker_identity=str(data["worker_identity"]),
operation_digest=str(data["operation_digest"]),
outcome=outcome,
observed_at=float(data["observed_at"]),
expires_at=float(data["expires_at"]),
probe_executor_identity=str(data["probe_executor_identity"]),
evidence_digest="",
signature=data.get("signature"),
attestation_ref=data.get("attestation_ref"),
)
return dataclass_replace(
probe, evidence_digest=compute_sha256_hex(probe.digest_payload())
)
def digest_payload(self) -> dict[str, Any]:
return {
"schema_version": self.schema_version,
"probe_id": self.probe_id,
"task_id": self.task_id,
"claim_id": self.claim_id,
"worker_id": self.worker_id,
"worker_identity": self.worker_identity,
"operation_digest": self.operation_digest,
"outcome": self.outcome.value,
"observed_at": self.observed_at,
"expires_at": self.expires_at,
"probe_executor_identity": self.probe_executor_identity,
"attestation_ref": self.attestation_ref,
}
def verify(self, *, now: float, attestation_verifier: Any) -> bool:
if (
self.schema_version != 1
or self.expires_at <= now
or self.observed_at > now
or self.evidence_digest != compute_sha256_hex(self.digest_payload())
or not (self.signature or self.attestation_ref)
):
return False
return bool(attestation_verifier and attestation_verifier(self))
def to_dict(self) -> dict[str, Any]:
return {
**self.digest_payload(),
"evidence_digest": self.evidence_digest,
"signature": self.signature,
}
def dataclass_replace(value: Any, **changes: Any) -> Any:
from dataclasses import replace
return replace(value, **changes)
@dataclass
class WorkerClaim:
claim_id: str
task_id: str
worker_id: str
worker_identity: str
claimed_at: float
lease_until: float
attempt: int
task_revision: int
operation_digest: str
status: str = "ACTIVE"
def to_dict(self, redact_payload: bool = True) -> dict[str, Any]:
payload = {
"claim_id": self.claim_id,
"task_id": self.task_id,
"worker_id": self.worker_id,
"worker_identity": self.worker_identity,
"claimed_at": _fmt_ts(self.claimed_at),
"lease_until": _fmt_ts(self.lease_until),
"attempt": self.attempt,
"task_revision": self.task_revision,
"operation_digest": self.operation_digest,
"status": self.status,
}
if redact_payload:
payload = redact_value(payload)
return payload
@dataclass
class ResultEnvelope:
task_id: str
claim_id: str
worker_identity: str
status: str
outputs: list[dict[str, Any]]
evidence: list[dict[str, Any]]
started_at: str
completed_at: str
result_digest: str | None = None
signature: str | None = None
attestation_ref: str | None = None
operation_digest: str | None = None
trust_status: str = "untrusted_shadow_result"
def digest_payload(self) -> dict[str, Any]:
return {
"task_id": self.task_id,
"claim_id": self.claim_id,
"worker_identity": self.worker_identity,
"status": self.status,
"outputs": self.outputs,
"evidence": self.evidence,
"started_at": self.started_at,
"completed_at": self.completed_at,
"operation_digest": self.operation_digest,
"attestation_ref": self.attestation_ref,
}
def computed_digest(self) -> str:
return compute_sha256_hex(self.digest_payload())
def to_dict(self, redact_payload: bool = True) -> dict[str, Any]:
payload = {
"task_id": self.task_id,
"claim_id": self.claim_id,
"worker_identity": self.worker_identity,
"status": self.status,
"outputs": self.outputs,
"evidence": self.evidence,
"started_at": self.started_at,
"completed_at": self.completed_at,
"result_digest": self.result_digest,
"signature": self.signature,
"attestation_ref": self.attestation_ref,
"operation_digest": self.operation_digest,
"trust_status": self.trust_status,
}
if redact_payload:
payload = redact_value(payload)
return payload
def _normalize_list(value: Any) -> list[str]:
if not isinstance(value, list):
raise ValueError("expected list")
if len(value) > 128 or any(
not isinstance(v, str)
or not v
or len(v) > 256
or any(ord(ch) < 32 for ch in v)
for v in value
):
raise ValueError("invalid list item")
return list(value)
def _to_positive_int(value: Any, default: int | None = None) -> int | None:
if value is None:
return default
try:
number = int(value)
except (TypeError, ValueError):
return default
return number if number >= 0 else default
def _to_float(value: Any) -> float | None:
if value is None:
return None
try:
return float(value)
except (TypeError, ValueError):
return None
def _first_non_none(primary: Any, fallback: Any) -> Any:
if primary is not None:
return primary
return fallback
def iso8601_now() -> str:
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
def _fmt_ts(value: float | None) -> str | None:
if value is None:
return None
return datetime.fromtimestamp(value, tz=timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
+226
View File
@@ -0,0 +1,226 @@
"""Policy and verification logic (fail-closed)."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Callable
from .errors import ForbiddenError, LockedError
from .models import ProbeEvidence, ResultEnvelope, TaskRecord
RISK_RANK = {"low": 1, "medium": 2, "high": 3}
READONLY_WORKER_ACTIONS = frozenset(
{"claim", "result", "fail", "progress", "heartbeat"}
)
ALL_ACTION_CAPABILITIES = frozenset(
{
"task.creator",
"worker.self_register",
"worker.admin",
"task.claim",
"task.cancel",
"task.delegate",
"task.read",
"task.audit",
}
)
@dataclass
class PolicyDecision:
allowed: bool
reason: str = ""
@dataclass(frozen=True)
class ReadonlyWorkerProfile:
"""A narrowly-scoped identity allowed to process safe Shadow tasks only."""
worker_id: str
identity: str
capabilities: frozenset[str]
task_types: frozenset[str] = frozenset({"code.review", "test.execute"})
def permits_task(self, task: TaskRecord) -> bool:
plan = task.task_plan
if plan.task_type not in self.task_types or plan.risk != "low":
return False
if plan.data_classification not in {"public", "internal"}:
return False
if plan.metadata.get("production_side_effects") is not False:
return False
return set(plan.required_capabilities).issubset(self.capabilities)
class IdentityVerifier:
def __init__(self, trusted_identities: set[str] | None = None):
self.trusted_identities = trusted_identities
def verify(self, identity: str) -> bool:
if self.trusted_identities is None:
return True
return identity in self.trusted_identities
class EvidenceVerifier:
def __init__(self, mandatory: list[str] | None = None):
self.mandatory = set(mandatory or [])
def verify(self, task: TaskRecord, evidences: list[dict]) -> PolicyDecision:
required = set(task.task_plan.evidence_requirements or [])
if not required and not self.mandatory:
return PolicyDecision(True)
observed = {e.get("kind") for e in evidences}
missing = required.union(self.mandatory) - observed
if missing:
return PolicyDecision(False, f"missing evidence: {', '.join(sorted(missing))}")
return PolicyDecision(True)
class PolicyEngine:
"""
Fail-closed policy engine with minimal but explicit decisions.
"""
def __init__(
self,
*,
identity_verifier: IdentityVerifier | None = None,
evidence_verifier: EvidenceVerifier | None = None,
execution_enabled: bool = False,
max_risk: str = "medium",
result_signature_verifier: Callable[[ResultEnvelope], bool] | None = None,
probe_attestation_verifier: Callable[[ProbeEvidence], bool] | None = None,
identity_capabilities: dict[str, set[str]] | None = None,
admin_identities: set[str] | None = None,
readonly_worker_execution_enabled: bool = False,
readonly_worker_profiles: list[ReadonlyWorkerProfile] | None = None,
) -> None:
if max_risk not in RISK_RANK:
raise ValueError("invalid max_risk")
self.identity_verifier = identity_verifier or IdentityVerifier()
self.evidence_verifier = evidence_verifier or EvidenceVerifier()
self.execution_enabled = execution_enabled
self.max_risk = max_risk
self.result_signature_verifier = result_signature_verifier
self.probe_attestation_verifier = probe_attestation_verifier
self.identity_capabilities = {
identity: set(capabilities)
for identity, capabilities in (identity_capabilities or {}).items()
}
self.admin_identities = set(admin_identities or ())
self.readonly_worker_execution_enabled = readonly_worker_execution_enabled
self.readonly_worker_profiles = {
profile.identity: profile for profile in (readonly_worker_profiles or [])
}
def _readonly_worker_allows(
self, action: str, actor: str, task: TaskRecord | None
) -> bool:
profile = self.readonly_worker_profiles.get(actor)
return bool(
self.readonly_worker_execution_enabled
and action in READONLY_WORKER_ACTIONS
and profile is not None
and (task is None or profile.permits_task(task))
)
def assert_readonly_worker_binding(self, actor: str, worker_id: str) -> None:
profile = self.readonly_worker_profiles.get(actor)
if profile is not None and profile.worker_id != worker_id:
raise ForbiddenError("worker identity binding mismatch")
def assert_readonly_worker_registration(self, actor: str, payload: dict) -> None:
profile = self.readonly_worker_profiles.get(actor)
if profile is None:
return
if (
str(payload.get("worker_id") or "") != profile.worker_id
or str(payload.get("identity") or "") != profile.identity
or set(payload.get("capabilities") or []) != set(profile.capabilities)
or str(payload.get("trust_zone") or "") != "isolated-review"
or int(payload.get("max_concurrency") or 0) != 1
or int(payload.get("heartbeat_interval_seconds") or 0) != 15
):
raise ForbiddenError("readonly worker registration mismatch")
def verify_result(
self, result: ResultEnvelope, task: TaskRecord | None = None
) -> PolicyDecision:
computed = result.computed_digest()
if result.result_digest and result.result_digest != computed:
return PolicyDecision(False, "result digest mismatch")
sensitive = bool(
task
and (
task.task_plan.data_classification
in {"confidential", "credential-secret"}
or any(
capability.startswith(
("code.write", "deploy", "secret", "production")
)
for capability in task.task_plan.required_capabilities
)
)
)
if sensitive and not (result.signature or result.attestation_ref):
return PolicyDecision(False, "trusted result proof required")
if result.signature is not None or result.attestation_ref is not None:
if self.result_signature_verifier is None:
return PolicyDecision(False, "result signature verifier unavailable")
if not self.result_signature_verifier(result):
return PolicyDecision(False, "result signature invalid")
result.trust_status = "trusted_result"
else:
result.trust_status = "untrusted_shadow_result"
return PolicyDecision(True)
def authorize(self, action: str, actor: str, task: TaskRecord | None = None, context: dict | None = None) -> PolicyDecision:
context = context or {}
if not self.identity_verifier.verify(actor):
return PolicyDecision(False, "identity untrusted")
action_capabilities = {
"create": "task.creator",
"read": "task.read",
"audit": "task.audit",
"claim": "task.claim",
"result": "task.claim",
"fail": "task.claim",
"progress": "task.claim",
"heartbeat": "task.claim",
"cancel": "task.cancel",
"delegate": "task.delegate",
"worker.register": "worker.self_register",
"worker.admin": "worker.admin",
}
required_capability = action_capabilities.get(action)
if required_capability:
granted = set(
self.identity_capabilities.get(
actor, self.identity_capabilities.get("*", set())
)
)
if required_capability not in granted:
return PolicyDecision(False, f"action {action} not permitted")
if action in {"claim", "result", "fail", "cancel", "progress", "delegate", "heartbeat"} and not self.execution_enabled:
if not self._readonly_worker_allows(action, actor, task):
return PolicyDecision(False, "execution disabled")
if action == "delegate" and task and task.status not in {"COMPLETED", "FAILED_FINAL", "CANCELLED"}:
risk = str(context.get("risk", task.task_plan.risk))
if RISK_RANK.get(risk, 2) > RISK_RANK.get(self.max_risk, 1):
return PolicyDecision(False, f"risk {risk} exceeds policy")
return PolicyDecision(True)
def assert_allowed(self, action: str, actor: str, task: TaskRecord | None = None, context: dict | None = None):
decision = self.authorize(action, actor, task, context=context)
if not decision.allowed:
if decision.reason == "identity untrusted":
raise ForbiddenError(decision.reason)
if decision.reason == "execution disabled":
raise LockedError("execution disabled")
raise ForbiddenError(decision.reason)
@@ -0,0 +1,76 @@
"""Task scheduler primitives."""
from __future__ import annotations
import time
from .errors import NotFoundError
from .capabilities import has_capabilities
from .models import WorkerClaim
from .store import TaskPlaneStore
class TaskScheduler:
def __init__(self, store: TaskPlaneStore):
self.store = store
def next_queued_task(self, worker_id: str):
worker = self.store.get_worker(worker_id)
tasks = sorted(
self.store.list_tasks(),
key=lambda task: (
-int(task.task_plan.metadata.get("priority", 0)),
task.created_at,
task.task_id,
),
)
for task in tasks:
if task.status not in {"CREATED", "QUEUED", "FAILED_RECOVERABLE"}:
continue
if task.task_plan.task_type == "worker.registry.audit":
continue
if task.status == "FAILED_RECOVERABLE" and not self.store.task_has_retryable_probe(
task.task_id
):
continue
if not has_capabilities(
worker.capabilities, task.task_plan.required_capabilities
):
continue
if any(
self.store.get_task(dependency).status != "COMPLETED"
for dependency in task.task_plan.dependencies
):
continue
if (
task.task_plan.data_classification == "credential-secret"
and worker.worker_type != "secure_file_transformer"
and "secure_file_transformer" not in worker.capabilities
):
continue
return task
return None
def schedule_for_worker(self, worker_id: str, lease_seconds: int = 15) -> WorkerClaim:
worker = self.store.get_worker(worker_id)
if worker.disabled:
from .errors import LockedError
raise LockedError("worker disabled")
if time.time() > worker.last_heartbeat + (
worker.heartbeat_interval_seconds * 3
):
from .errors import LockedError
raise LockedError("worker offline")
task = self.next_queued_task(worker_id)
if task is None:
raise NotFoundError("no queued tasks available")
claim = self.store.claim_task(
task.task_id,
worker_id,
worker.identity,
lease_seconds=lease_seconds,
expected_revision=task.revision,
operation_digest=task.task_plan.operation_digest(),
)
return claim
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,68 @@
"""Worker registry abstraction and read helpers."""
from __future__ import annotations
import time
from .capabilities import has_capabilities
from .errors import NotFoundError
from .models import WorkerRegistration
from .store import TaskPlaneStore
class WorkerRegistry:
def __init__(self, store: TaskPlaneStore):
self.store = store
def register(
self,
payload: dict,
*,
actor_identity: str,
is_admin: bool,
expected_revision: int | None,
) -> WorkerRegistration:
reg = WorkerRegistration.from_dict(payload)
return self.store.register_worker(
reg,
actor_identity=actor_identity,
is_admin=is_admin,
expected_revision=expected_revision,
)
def heartbeat(
self,
worker_id: str,
heartbeat_interval_seconds: int | None = None,
*,
actor_identity: str,
expected_revision: int | None,
) -> WorkerRegistration:
return self.store.heartbeat_worker(
worker_id,
heartbeat_interval_seconds=heartbeat_interval_seconds,
actor_identity=actor_identity,
expected_revision=expected_revision,
)
def list(self):
return self.store.list_workers()
def get(self, worker_id: str) -> WorkerRegistration:
try:
return self.store.get_worker(worker_id)
except NotFoundError:
raise
def can_execute(self, worker_id: str, required_capabilities: list[str]) -> bool:
worker = self.store.get_worker(worker_id)
return has_capabilities(worker.capabilities, required_capabilities)
def is_online(self, worker_id: str, *, now: float | None = None) -> bool:
worker = self.store.get_worker(worker_id)
deadline = worker.last_heartbeat + (worker.heartbeat_interval_seconds * 3)
return not worker.disabled and (time.time() if now is None else now) <= deadline
def stale_workers(self, *, now: float | None = None) -> list[WorkerRegistration]:
current = time.time() if now is None else now
return [worker for worker in self.list() if not self.is_online(worker.worker_id, now=current)]
+23 -6
View File
@@ -1,8 +1,25 @@
{
"current_baseline": "V1R4C3",
"previous_baseline": "V1R3C1",
"promoted_at": "2026-07-09T17:44:57+08:00",
"git": "f5435e308794c737f3e39de3f6b79807486943c3",
"promoted_by": "openclaw",
"promotion_reason": "V1R4C3 autonomous operations, search gateway, task center, owner gate, and blocker self-optimization baseline promotion"
"current_baseline": "V2R1C2",
"previous_baseline": "V2R1C1",
"promoted_at": "2026-07-22T01:40:51Z",
"git": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
"promoted_by": "codex/owner-approved-gitops",
"promotion_reason": "Owner-authorized V2R1C2 Unified Portal production release after exact tag binding, complete evidence verification, and production acceptance PASS.",
"version": "V2R1C2",
"release_oid": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
"tag_oid": "a3bd84ebec9c705f7c9c5c03f7f4ec55f8854e36",
"target_oid": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
"release_run_id": "AIOS-V2R1C2-PRODUCTION-20260722T011836Z",
"status": "PRODUCTION_DEPLOYED",
"production_service": "aios-v2r1c2-production.service",
"production_port": 18920,
"rollback_version": "V2R1C1",
"constraints": {
"product_code_changed": true,
"production_redeployed": true,
"production_traffic_changed": true,
"tag_rewritten": false,
"force_push_allowed": false,
"rollback_assets_preserved": true
}
}
+103
View File
@@ -0,0 +1,103 @@
{
"schema_version": 4,
"automatic": [
"build",
"test",
"artifact",
"canary",
"evidence"
],
"owner": [
"signed_release_plan"
],
"forbidden": [
"force_push",
"tag_rewrite",
"direct_main_push",
"baseline_mutation",
"registry_mutation"
],
"runtime_deployment": {
"approval_action": "signed_release_plan",
"required_capability": "runtime_switch",
"tag_operations_allowed": false,
"baseline_mutation_allowed": false,
"registry_mutation_allowed": false,
"writer_default": false,
"rollback_required": true
},
"tag_release": {
"approval_action": "signed_release_plan",
"required_capability": "tag_publish",
"separate_controller": true,
"duplicate_conflict": "fail_closed",
"rewrite_allowed": false,
"force_push_allowed": false
},
"baseline_registry_finalize": {
"approval_action": "signed_release_plan",
"required_capability": "baseline_registry_finalize",
"separate_controller": true,
"remote_tag_verification_required": true,
"gitea_api_verification_required": true,
"registry_baseline_consistency_required": true
},
"approval": {
"algorithm": "Ed25519",
"trust_domain": "aios.production",
"maximum_lifetime_seconds": 3600,
"release_plan_sha256_required": true,
"not_before_required": true,
"replay_protection": true,
"revocation_fail_closed": true,
"key_rotation_supported": true,
"capabilities": [
"runtime_switch",
"tag_publish",
"baseline_registry_finalize"
]
},
"execution": {
"environment_variable": "AIOS_SILENT_RELEASE_EXECUTION_ENABLED",
"default_enabled": false,
"shadow_side_effects_allowed": false,
"durable_saga_required": true,
"pre_switch_revalidation_required": true,
"trusted_candidate_builder_required": true,
"actual_plan_regeneration_required": true,
"startup_fail_closed_on_missing_component": true,
"recovery_worker_shadow_default": true,
"production_approval_backend_required": true,
"production_builder_signer": "kms-hsm-secret-manager-only",
"production_execution_without_backend": "unavailable"
},
"durability": {
"journal": "sha256-hash-chain",
"probe_journal": "sha256-hash-chain",
"exclusive_capability_claims": true,
"side_effect_probe_before_lease_takeover": true,
"side_effect_probe_before_failed_recoverable_retry": true,
"probe_results": [
"NOT_APPLIED",
"APPLIED_VERIFIED",
"INDETERMINATE",
"CONFLICT"
],
"probe_operation_digest_required": true,
"probe_freshness_required": true,
"tamper_result": "MANUAL_OWNER_REVIEW_REQUIRED"
},
"tag_pending": {
"required_observations": [
"remote_git_ref",
"annotated_tag_object",
"peeled_target",
"gitea_api",
"gitea_listing",
"repository_identity"
],
"indeterminate_result": "RECONCILIATION_REQUIRED",
"conflict_result": "MANUAL_OWNER_REVIEW_REQUIRED",
"automatic_reconciliation": false
}
}
+59
View File
@@ -0,0 +1,59 @@
version: 1
policy_id: gitops-isolated-worktree-governance-20260714T232948UTC8
runtime_identity:
user: aiman
group: gitops
umask: "0002"
prohibit_root_workspace_writes: true
repository:
source_worktree: /data/aios-gitops/workspace
bare_repo: /data/aios-gitops/repo.git
worktree_root: /data/aios-gitops/worktrees
remote: origin
worktrees:
controller: /data/aios-gitops/worktrees/controller
task_pattern: /data/aios-gitops/worktrees/{agent}/{task_id}
allowed_agents:
- openclaw
- chatgpt
- controller
require_clean_start: true
remove_after_successful_push: true
retain_on_failure: true
permissions:
owner: aiman
group: gitops
directory_mode: "2775"
file_mode: "0664"
default_acl:
user:aiman: rwx
group:gitops: rwx
apply_to:
- /data/aios-gitops
- /data/aios-gitops/worktrees
preflight:
required_user: aiman
required_group: gitops
required_umask: "0002"
require_writable_git_dir: true
require_writable_task_dir: true
require_writable_result_dir: true
reject_shared_source_worktree: true
reject_existing_git_lock: true
notifications:
owner_on_received: required
owner_on_terminal: required
preferred_channel: weixin
redact_secrets: true
rollback:
preserve_source_worktree: true
remove_created_worktrees: true
restore_service_dropins: true
restore_service_state: true
@@ -0,0 +1,14 @@
# Install as a systemd drop-in for GitOps/OpenClaw writer services.
# Example: /etc/systemd/system/<service>.service.d/10-runtime-identity.conf
[Service]
User=aiman
Group=gitops
SupplementaryGroups=gitops
UMask=0002
Environment=AIOS_GITOPS_ROOT=/data/aios-gitops
Environment=AIOS_BARE_REPO=/data/aios-gitops/repo.git
Environment=AIOS_WORKTREE_ROOT=/data/aios-gitops/worktrees
Environment=AIOS_RUNTIME_USER=aiman
Environment=AIOS_RUNTIME_GROUP=gitops
Environment=AIOS_RUNTIME_UMASK=0002
+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:

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