Compare commits

...
Author SHA1 Message Date
Codex 6b0db21a85 review(codex): 固化 V2R1 最新发布审查结论 2026-07-21 12:34:00 +08:00
Codex be4726178a task(agent): 转入 provenance 后正式 Gate 复审 2026-07-21 11:23:44 +08:00
AIOS-Owner 0834b272f0 task(agent): 审查四项清障并保留 provenance 门禁 2026-07-20 18:18:36 +08:00
Codex Supervisor e28245f411 chore(evidence): refine AIOS V2 signing-material blocker 2026-07-20 17:05:10 +08:00
Codex Supervisor 8a9d033e9c chore(agent): record final V2R1 first-round blocked review 2026-07-20 17:03:08 +08:00
Codex Supervisor e567699283 chore(agent): claim V2R1 Codex supervision and block preproduction 2026-07-20 16:51:25 +08:00
Codex c935aac3b8 task(codex): 初始化无人值守监督状态 2026-07-20 12:08:06 +08:00
Codex 75f0148878 task(codex): 写入生产监督无人值守任务载荷 2026-07-20 12:07:58 +08:00
Codex 91afbfaf76 task(codex): launch architecture supervision and blocker resolution 2026-07-20 11:49:13 +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 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
openclaw f6d9bb1510 Promote baseline to V1R4C3
- baseline/current.json updated from V1R3C1 to V1R4C3
- Fixed test_single_provider_failure_is_not_terminal (provider_order override)
- All 38 tests passing

AIOS_V1R4C3_BASELINE_PROMOTED
AIOS_BASELINE_CURRENT_UPDATED
2026-07-09 17:45:09 +08:00
openclaw 8ca4db3e8c Close completed autonomous controller CMD
- Moved CMD-20260709-enable-autonomous-controller.md from active to completed
- All autonomous controller tasks verified complete

AIOS_AUTONOMOUS_CONTROLLER_CMD_CLOSED
AIOS_RUNNING_COMMAND_QUEUE_CLEAN
2026-07-09 17:38:04 +08:00
openclaw d194d3a4d7 Add Owner Gate Web UI panels with approve/reject functionality 2026-07-09 17:23:23 +08:00
openclaw f5435e3087 release: version bump to V1R4C3 2026-07-09 16:13:42 +08:00
gito 88087dc7ff Merge pull request 'V1R4C1 review fixes: arch change API, tests, owner gate, governance' (#3) from patch/v1r4c1-review-risk-fixes into main 2026-07-09 16:13:08 +08:00
openclaw 2f04b9f46c release: version bump to V1R4C2 2026-07-09 16:10:29 +08:00
openclaw d8a426cea1 Clean stale runtime state before PR #2 merge 2026-07-09 12:27:58 +08:00
openclaw 22d48bad4d v1r4c1: batch commit - arch change api + tests + owner gate 2026-07-09 12:12:02 +08:00
openclaw 99c50464d9 Add architecture change governance dashboard 2026-07-09 11:49:30 +08:00
openclaw d0141450fe Add OpenClaw command for tiered architecture owner gate 2026-07-09 11:47:58 +08:00
openclaw 84c67fa743 Add architecture change classification tests 2026-07-09 11:47:55 +08:00
openclaw d0536dbe14 Update owner gate to support small auto and large approval 2026-07-09 11:47:53 +08:00
openclaw 4177a22936 Add architecture change classifier for owner gate levels 2026-07-09 11:47:48 +08:00
openclaw 5c38b23810 Add OpenClaw command for architecture owner gate 2026-07-09 11:42:54 +08:00
openclaw aa0f721ce8 Add architecture owner gate tests 2026-07-09 11:42:51 +08:00
openclaw 2e94439f49 Add architecture owner gate policy 2026-07-09 11:42:48 +08:00
openclaw 961c45c825 Add owner approval gate for architecture changes 2026-07-09 11:42:43 +08:00
openclaw 20f1f9820d Add OpenClaw command for architect research timeline UI 2026-07-09 11:39:28 +08:00
openclaw a6f08472dd Add architect research timeline tests 2026-07-09 11:39:22 +08:00
openclaw 9f95029225 Add architect research timeline API 2026-07-09 11:39:13 +08:00
openclaw 4ad4651ffa Add architect research timeline dashboard model 2026-07-09 11:39:05 +08:00
openclaw c0d008fae7 Add OpenClaw command for architect weekly research 2026-07-09 11:33:25 +08:00
openclaw 1974327e32 Add architect research policy 2026-07-09 11:33:19 +08:00
openclaw 110817b60c Add Architect weekly research tests 2026-07-09 11:33:12 +08:00
openclaw 95070ea029 Add Architect research dashboard model 2026-07-09 11:33:09 +08:00
openclaw 44aea3a9a1 Add Architect weekly external research agent 2026-07-09 11:33:03 +08:00
openclaw ce42691be5 Add OpenClaw command for governance timeline UI 2026-07-09 11:31:36 +08:00
openclaw 6f823de67d Add governance timeline tests 2026-07-09 11:31:32 +08:00
openclaw 7443fc7f26 Add governance timeline API 2026-07-09 11:31:28 +08:00
openclaw e1d484655f Add governance timeline dashboard model 2026-07-09 11:31:24 +08:00
openclaw 362a41bff8 Add OpenClaw command for governance event loop 2026-07-09 11:26:22 +08:00
openclaw 62974e879e Add governance event bridge tests 2026-07-09 11:26:19 +08:00
openclaw cd713cd73a Add governance event bus policy 2026-07-09 11:26:16 +08:00
openclaw bd8afc3cc4 Bridge governance agents into unified event bus 2026-07-09 11:26:12 +08:00
openclaw 1688639d7d Add OpenClaw command for architect governance UI 2026-07-09 11:21:41 +08:00
openclaw 60d07f9b17 Add architect governance tests 2026-07-09 11:21:38 +08:00
openclaw 824ff5dc90 Add Architect Governance API 2026-07-09 11:21:35 +08:00
openclaw 3d27f2eb43 Add Architect Governance Web UI dashboard model 2026-07-09 11:21:30 +08:00
openclaw a168610826 Add OpenClaw command for architect governance loop 2026-07-09 11:20:25 +08:00
openclaw 5447476b08 Add architect output document template 2026-07-09 11:20:22 +08:00
openclaw e58d99ba57 Add architect agent governance policy 2026-07-09 11:20:18 +08:00
openclaw 51d6f7e0c2 Extend architect agent governance responsibilities 2026-07-09 11:20:13 +08:00
openclaw 40459af09e Add OpenClaw command for change governance UI 2026-07-09 11:11:17 +08:00
openclaw c7dc61597a Add change governance dashboard tests 2026-07-09 11:11:14 +08:00
openclaw 43d55ac3b1 Add change governance dashboard API 2026-07-09 11:11:11 +08:00
openclaw 736e981005 Add change governance Web UI dashboard model 2026-07-09 11:11:06 +08:00
openclaw b84d6be3ca Add OpenClaw command for change governance agents 2026-07-09 11:09:56 +08:00
openclaw eff4940e9c Add change governance policy for acceptance agents 2026-07-09 11:09:52 +08:00
openclaw 0d6f2ce68d Add independent architecture optimization agent 2026-07-09 11:09:49 +08:00
openclaw a654978813 Add independent user and architecture acceptance agents 2026-07-09 11:09:45 +08:00
openclaw a399e30a8e Add change acceptance governance gate 2026-07-09 11:09:40 +08:00
openclaw e0644c0297 Add OpenClaw validation command for V1R4C1 fixes 2026-07-09 11:06:46 +08:00
openclaw 37eed9df7d Add V1R4C1 risk fix tests 2026-07-09 11:06:42 +08:00
openclaw 22582b834f Move model list from hardcode to configurable registry 2026-07-09 11:06:38 +08:00
openclaw 8a0c5f0556 Add Git repository path resolver and validator 2026-07-09 11:06:33 +08:00
openclaw 62b10d89c2 Create V1R4C1 review risk fixes branch 2026-07-09 11:06:26 +08:00
177 changed files with 16045 additions and 4 deletions
+57
View File
@@ -0,0 +1,57 @@
{
"schema": "aios.v2.agent-blockers.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"updated_at": "2026-07-21T04:30:00Z",
"blockers": [
{
"blocker_id": "BLK-OPENCLAW-PLAINTEXT-SECRETS",
"severity": "high",
"status": "resolved",
"root_cause": "OpenClaw 三处 managed plaintext。",
"fix": "迁移为单一 file Secret Provider 并轮换 Gateway Token。",
"verification": "最终 audit 四类计数均为 0,OneAPI 实际调用通过。",
"commit": "bf01a13f3aaf42a386232ed2f5409feb0f79fcf6",
"resolved_at": "2026-07-20T10:18:36Z"
},
{
"blocker_id": "BLK-AIOS-V2-SIGNING-MATERIAL-MISSING",
"severity": "high",
"status": "resolved",
"root_cause": "Ed25519 Key ID 与 HMAC 实现不一致且材料缺失。",
"fix": "真实 Ed25519 合同及受保护材料。",
"verification": "0600、sign/verify、篡改拒绝通过。",
"commit": "8a36f7832bc105e4b9d32ffbe018abed2ff1b1ab",
"resolved_at": "2026-07-20T10:18:36Z"
},
{
"blocker_id": "BLK-CANDIDATE-NOT-MERGED",
"severity": "high",
"status": "resolved",
"root_cause": "OpenClaw 任务未包含 Candidate。",
"fix": "--no-ff 合并最新 Candidate。",
"verification": "Candidate 为 OpenClaw HEAD 祖先且 OID 同步。",
"commit": "f55dfd975e9d716b690c7693742e7cf2beaa55e7",
"resolved_at": "2026-07-20T10:18:36Z"
},
{
"blocker_id": "BLK-OPENCLAW-RUN-PROVENANCE-MISSING",
"severity": "high",
"status": "resolved",
"root_cause": "旧插件只有进程内 runId/sender Map,缺少 Owner-signed Schema、持久 Store 和限定 Git Writer。",
"fix": "部署 aios-tenant-boundary rc2,增加 Ed25519 issuer/store、Run/Sender/OID/期限绑定、一次性 permit 与七路径专用 Writer。",
"verification": "Provenance openclaw-v2r1-20260721T031523Z 完成 heartbeat 写入、Commit、普通 Push 和审计;README.md 越权写入被拒绝;Node 测试 9/9。",
"commit": "25c25abd3ed19091fe078d4d7a271c57f23e87fb",
"resolved_at": "2026-07-21T03:23:44Z"
},
{
"blocker_id": "BLK-CONTROLLER-LEGACY-GITEA-CHECK",
"severity": "high",
"status": "resolved",
"root_cause": "硬编码旧仓库。",
"fix": "配置化 V2R1 OID 健康检查并使用只读 Credential。",
"verification": "12 项测试、detached clean、fully_synced。",
"commit": "6188da26453505dacde9d6d298191437164c8d27",
"resolved_at": "2026-07-20T10:18:36Z"
}
]
}
+13
View File
@@ -0,0 +1,13 @@
{
"schema": "aios.v2.agent-claim.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"executor": "codex",
"executor_instance": "windows-chatgpt-owner-supervisor",
"task_branch": "task/codex/AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"candidate_branch": "integration/aios-v2r1-cto-production-candidate-20260720",
"candidate_commit": "ba7669c3b49f98cf3500af6ea966ba0db472ff3b",
"claimed_at": "2026-07-20T08:51:25Z",
"owner_observation": "五项 Blocker、Gate A/B、离线验收、OpenClaw 在线合同、双服务重启与回滚均通过;Hermes 完整在线 Worker 生命周期仍缺服务端点证据,Codex 维持 STOP_PREPRODUCTION。",
"owner_observation_at": "2026-07-21T04:30:00Z",
"reviewed_openclaw_commit_before_evidence": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a"
}
+18
View File
@@ -0,0 +1,18 @@
{
"schema": "aios.agent.credential-status.v1",
"task_id": "task/codex/AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"last_updated": "2026-07-21T04:30:00Z",
"plaintext_findings_before": 3,
"plaintext_findings_after": 0,
"gateway_token_rotated": true,
"secret_values_recorded": false,
"signing_material_configured": true,
"signing_key_id": "openclaw-v2r1-candidate-ed25519",
"runtime_sign_verify_test": "passed",
"controller_credential_scope": "read:repository",
"run_provenance_status": "resolved",
"provenance_id": "openclaw-v2r1-20260721T031523Z",
"openclaw_runtime_plugin_version": "2.1.0-rc.3",
"runtime_public_key_only_hot_path": true,
"secret_values_recorded_in_evidence": false
}
+10
View File
@@ -0,0 +1,10 @@
{
"schema": "aios.v2.agent-heartbeat.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"executor": "codex",
"heartbeat_at": "2026-07-21T04:30:00Z",
"state": "reviewing",
"current_step": "FINAL_REVIEW_HERMES_ONLINE_GAP",
"reviewed_commit": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a",
"openclaw_evidence_commit": "0be3ba09e42b4f6db56461e3ca3a3fcc0a487f31"
}
+73
View File
@@ -0,0 +1,73 @@
{
"schema": "aios.v2.agent-progress.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"updated_at": "2026-07-21T04:30:00Z",
"state": "reviewing",
"candidate_oid": "634f6b164f5b20372ab9ec8144bbf76df97de335",
"openclaw_task_oid_at_review": "0be3ba09e42b4f6db56461e3ca3a3fcc0a487f31",
"codex_task_oid_before_evidence": "be4726178aa8fa59321aafaabcff8a83653cc1b8",
"gitea_sync": {
"candidate_match": true,
"openclaw_task_match": true,
"codex_task_match_before_this_evidence": true
},
"completed_checks": [
"worktree",
"candidate_merge",
"secrets_audit_zero",
"ed25519_sign_verify",
"controller_fully_synced",
"owner_signed_provenance_writer",
"unauthorized_path_denied",
"provenance_audit_chain",
"gate_a",
"gate_b_10_of_10",
"offline_acceptance_8_0_1",
"openclaw_online_contract",
"aios_openclaw_restart_recovery",
"controlled_rollback_and_forward"
],
"review_conclusion": "五项 Blocker、文档/代码 Gate、候选测试、离线验收、OpenClaw 在线合同、重启与回滚均通过;Hermes 完整在线 Worker 生命周期未形成服务端点证据,预发布仍停止。",
"check_time_window": {
"started_at": "2026-07-20T08:24:30Z",
"ended_at": "2026-07-20T09:03:08Z"
},
"operator": "windows-chatgpt-owner-supervisor",
"reviewer": "codex-supervisor + Spark architect/explorer/implementer/validator/docs_reporter",
"approver": "AIOS Owner gate recorded by Windows ChatGPT Owner Supervisor",
"evidence_artifacts": [
"task/openclaw/AIOS-V2R1-PRODUCTION-DEPLOY-20260720@1aa71f233d2c2a6ed7290d0a3ddcb04dcd84febe",
"task/codex/AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720:.agent/",
"/data/aios-gitops/runtime/backups/gitea-db-before-openclaw-token-rotation-20260720T084251Z.sqlite3",
"/home/aiman/.ssh/known_hosts.aios-v2r1-backup-20260720T083647Z",
"/var/log/aios-openclaw-v2r1-evidence-repair-20260720.json"
],
"independent_reviews": {
"architect": "REJECT;只允许修复+复验,禁止生产放行。",
"explorer": "OpenClaw evidence OID 已重新闭环,但 Candidate 未合并、Secret 与预发布仍未确认。",
"implementer": "IMPLEMENTATION_SAFE_WITH_BLOCKERS;已实施动作无需立即回滚。",
"validator": "BLOCKED;Secret、环境、预发布门禁未通过。",
"docs_reporter": "已补齐时间窗、证据路径、operator/reviewer/approver、blocker 与 final_decision。"
},
"final_decision": "STOP_PREPRODUCTION",
"aios_v2_env_status": {
"exists": true,
"owner": "root",
"group": "gitops",
"mode": "0640",
"four_fields_nonempty": true,
"credential_ref_target_exists": true,
"signing_material_target_exists": true
},
"open_checks": [
"hermes_online_claim_start_heartbeat_complete_fail_cancel",
"hermes_online_lease_expiry_worker_crash_recovery",
"hermes_online_cell_profile_and_invalid_result_rejection"
],
"gate_a": "passed",
"gate_b": "passed_10_of_10",
"offline_acceptance": "passed_8_failed_0_warning_1",
"online_openclaw": "passed",
"restart_recovery": "passed",
"rollback_drill": "passed"
}
+27
View File
@@ -0,0 +1,27 @@
{
"schema": "aios.v2.agent-result.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"final_status": "PARTIAL",
"candidate_commit": "ba7669c3b49f98cf3500af6ea966ba0db472ff3b",
"reviewed_commit": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a",
"gitea_sync": {
"candidate_match": true,
"openclaw_task_match": true,
"codex_task_match_before_this_evidence": true
},
"credential_rotation_status": "secretref_resolved",
"test_status": "Gate A 通过;Gate B 10/10;离线 8/0/1;OpenClaw 在线、重启恢复、回滚通过;Hermes 完整在线 Worker 生命周期未覆盖",
"deployment_status": "STOP_PREPRODUCTION",
"rollback_status": "Previous 2a2b702 与 Current b158041 双向演练通过且业务状态保留",
"documentation_sync_status": "updated",
"open_blockers": [],
"release_recommendation": "STOP_PREPRODUCTION",
"completed_at": "2026-07-21T04:30:00Z",
"openclaw_evidence_commit": "0be3ba09e42b4f6db56461e3ca3a3fcc0a487f31",
"independent_validation": "PASS_FOR_IMPLEMENTED_OPENCLAW_BOUNDARY",
"operator": "windows-chatgpt-owner-supervisor",
"reviewer": "codex-supervisor + Spark roles",
"approver": "AIOS Owner gate recorded",
"remaining_risk": "Hermes 完整在线 Worker 生命周期缺少可调用服务端点与实时证据",
"formal_online_acceptance": "partial"
}
@@ -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.
+18
View File
@@ -0,0 +1,18 @@
{
"schema": "aios.v2.agent-status.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"executor": "codex",
"state": "reviewing",
"claimed_at": "2026-07-20T08:51:25Z",
"running_at": "2026-07-20T08:51:25Z",
"updated_at": "2026-07-21T04:30:00Z",
"last_heartbeat": "2026-07-21T04:30:00Z",
"current_step": "FINAL_REVIEW_HERMES_ONLINE_GAP",
"candidate_commit": "ba7669c3b49f98cf3500af6ea966ba0db472ff3b",
"reviewed_commit": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a",
"release_recommendation": "STOP_PREPRODUCTION",
"openclaw_evidence_commit": "0be3ba09e42b4f6db56461e3ca3a3fcc0a487f31",
"status": "reviewing"
,"formal_online_acceptance": "partial"
,"remaining_gap": "Hermes full online worker lifecycle"
}
+31
View File
@@ -0,0 +1,31 @@
{
"schema": "aios.v2.agent-task.v1",
"task_id": "AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720",
"display_name": "AIOS V2R1 Codex 架构监督、阻塞处理与发布审查任务",
"language": "zh-CN",
"executor": "codex",
"role": "architecture-supervisor",
"state": "queued",
"candidate_branch": "integration/aios-v2r1-cto-production-candidate-20260720",
"candidate_commit": "634f6b164f5b20372ab9ec8144bbf76df97de335",
"canonical_task": "tasks/codex-production-supervisor-task.yaml",
"supervises": "task/openclaw/AIOS-V2R1-PRODUCTION-DEPLOY-20260720",
"claim_required": true,
"heartbeat_interval_seconds": 300,
"evidence_directory": ".agent/evidence",
"instructions": [
"领取前读取候选分支完整中文文档、ADR、追踪矩阵和候选报告",
"领取后写入 .agent/claim.json 并把状态改为 claimed",
"持续审阅 OpenClaw 的 claim、heartbeat、progress、blocker、commit 和 result",
"分析失败测试、架构偏移、多租户、安全和文档同步阻塞",
"需要修改时创建 Patch 分支、增加复现测试并同步文档",
"所有阻塞和审查结论必须提交到系统统一审视",
"禁止缺少证据时批准发布或削弱安全门禁"
],
"acceptance_commands": [
"python3 tools/aios_v2_docs_code_check.py --base-ref integration/aios-v2r1-cto-production-candidate-20260720",
"python3 -m unittest discover -s tests/aios_v2_candidate -p test_*.py -v",
"bash deploy/aios-v2/acceptance/run-all.sh"
],
"created_at": "2026-07-20T00:00:00Z"
}
+1 -1
View File
@@ -1 +1 @@
V1R4C2
V1R4C6
@@ -0,0 +1,25 @@
"""AIOS-managed Hermes runtime boundary."""
from .adapter import (
HermesAdapter,
HermesConflict,
HermesNotFound,
HermesRuntimeError,
InMemoryHermesStore,
)
from .contract import HermesHealth, HermesJob, HermesJobState, HermesResult
from .worker import HermesWorker, WorkerRunResult
__all__ = [
"HermesAdapter",
"HermesConflict",
"HermesHealth",
"HermesJob",
"HermesJobState",
"HermesNotFound",
"HermesResult",
"HermesRuntimeError",
"HermesWorker",
"InMemoryHermesStore",
"WorkerRunResult",
]
+437
View File
@@ -0,0 +1,437 @@
"""Tenant-partitioned Hermes queue and worker lease boundary."""
from __future__ import annotations
import hashlib
import json
import threading
from dataclasses import replace
from datetime import datetime, timedelta, timezone
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]] = {}
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)
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:
self._requeue_expired_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,
) -> 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.state == HermesJobState.QUEUED
]
self.store.worker_heartbeats[worker_id] = (utc_now(), None)
if not candidates:
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)
return claimed
def start(
self,
job_id: str,
*,
tenant_id: str,
worker_id: str,
expected_revision: int | None = None,
) -> HermesJob:
with self.store.lock:
current = self._owned_job_locked(job_id, tenant_id, worker_id)
self._assert_revision(current, expected_revision)
return self._transition_locked(current, HermesJobState.RUNNING)
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)
with self.store.lock:
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)
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")
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
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 health(self) -> HermesHealth:
with self.store.lock:
self._requeue_expired_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:
current = self._owned_job_locked(job_id, tenant_id, worker_id)
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)
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) -> None:
now = datetime.now(timezone.utc)
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(),
)
+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 +1,37 @@
"""AIOS-managed OpenClaw execution adapter."""
from .adapter import (
AdapterError,
CommandConflict,
CommandNotFound,
CommandRejected,
InMemoryCallbackSink,
OpenClawAdapter,
)
from .contract import (
CommandState,
OpenClawCommand,
OpenClawResult,
RuntimeHealth,
sign_command,
verify_command_signature,
)
from .transport import HTTPRuntimeTransport, InProcessRuntimeTransport, RuntimeTransport
__all__ = [
"AdapterError",
"CommandConflict",
"CommandNotFound",
"CommandRejected",
"CommandState",
"HTTPRuntimeTransport",
"InMemoryCallbackSink",
"InProcessRuntimeTransport",
"OpenClawAdapter",
"OpenClawCommand",
"OpenClawResult",
"RuntimeHealth",
"RuntimeTransport",
"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 +1,213 @@
"""Versioned AIOS to OpenClaw execution contracts."""
from __future__ import annotations
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
CONTRACT_VERSION = "aios.openclaw.command.v1"
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))
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
key_id: str = "default"
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", "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}")
object.__setattr__(self, "payload", _safe_mapping(self.payload))
_parse_timestamp(self.created_at)
if self.expires_at is not None:
object.__setattr__(self, "expires_at", _required(self.expires_at, "expires_at"))
_parse_timestamp(self.expires_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,
"key_id": self.key_id,
}
@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 sign_command(command: OpenClawCommand, key_material: bytes | str) -> OpenClawCommand:
key = key_material.encode("utf-8") if isinstance(key_material, str) else bytes(key_material)
if not key:
raise ValueError("signing material is required")
signature = hmac.new(key, canonical_command_bytes(command), hashlib.sha256).hexdigest()
return replace(command, signature=signature)
def verify_command_signature(
command: OpenClawCommand,
key_material: bytes | str,
*,
now: datetime | None = None,
clock_skew_seconds: int = DEFAULT_CLOCK_SKEW_SECONDS,
) -> bool:
if not command.signature:
return False
key = key_material.encode("utf-8") if isinstance(key_material, str) else bytes(key_material)
if not key:
return False
expected = hmac.new(key, canonical_command_bytes(command), hashlib.sha256).hexdigest()
if not hmac.compare_digest(expected, 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 {},
)
+46
View File
@@ -0,0 +1,46 @@
"""AIOS V2 control plane and execution orchestration."""
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
__all__ = [
"AgentRecord",
"AuditEvent",
"ControlPlaneError",
"ControlPlaneService",
"DispatchRecord",
"ExecutionEvidence",
"ExecutionOrchestrator",
"ExecutionTracker",
"IdempotencyConflict",
"InMemoryControlPlaneStore",
"InvalidTransition",
"NotFound",
"OrchestrationError",
"PolicyDenied",
"RequestContext",
"RevisionConflict",
"TaskRecord",
"TaskState",
"TenantIsolationError",
"TenantRecord",
"Unauthorized",
]
+357
View File
@@ -0,0 +1,357 @@
"""Production-candidate AIOS V2 application entrypoint.
This process owns the public control-plane API and read-only web console. It
loads durable control-plane state, dispatches approved work through runtime
adapters, exposes tenant-scoped execution evidence and sanitized GitOps status,
and never exposes runtime credentials to the browser.
"""
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
from aios_openclaw import HTTPRuntimeTransport, OpenClawAdapter
from aios_openclaw.callback import AuditCallbackSink, EventPublisher
from .console import CONSOLE_HTML
from .control_plane import AuditEvent, RequestContext
from .execution_tracking import ExecutionTracker
from .gateway import GatewayApplication, error_response
from .gitops_status import collect_gitops_status
from .orchestrator import ExecutionOrchestrator
from .persistence import DurableControlPlaneService, SQLiteSnapshotRepository
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
class FileSigningMaterialResolver:
"""Resolve runtime signing material from a root-owned file reference."""
def __init__(self, path: str | Path) -> None:
self.path = Path(path).resolve()
def __call__(self, tenant_id: str, key_id: str) -> bytes:
del tenant_id, key_id
metadata = self.path.stat()
if not stat.S_ISREG(metadata.st_mode):
raise RuntimeError("signing material reference is not a regular file")
if metadata.st_mode & 0o077:
raise RuntimeError("signing material file permissions must be 0600 or stricter")
value = self.path.read_bytes().strip()
if len(value) < 32:
raise RuntimeError("signing material is too short")
return value
class ControlPlaneEventPublisher(EventPublisher):
"""Append OpenClaw runtime events to the tenant audit stream."""
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
audit = AuditEvent(
event_id=f"runtime_{command_id}_{len(self.service.store.audit_events) + 1}",
tenant_id=tenant_id,
principal_id="openclaw-runtime",
trace_id=trace_id,
action=event_type,
resource_type="openclaw_command",
resource_id=command_id,
outcome=outcome,
policy_version="runtime-v1",
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:
"""Compose durable control plane, runtimes, evidence and console routes."""
def __init__(
self,
gateway: GatewayApplication,
orchestrator: ExecutionOrchestrator,
tracker: ExecutionTracker,
hermes: HermesAdapter,
openclaw: OpenClawAdapter | None,
) -> None:
self.gateway = gateway
self.orchestrator = orchestrator
self.tracker = tracker
self.hermes = hermes
self.openclaw = openclaw
def context(self, headers: Mapping[str, str]) -> RequestContext:
return self.gateway.context_from_headers(headers)
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")
record = self.orchestrator.dispatch(
context,
task_id=task_id,
timeout_seconds=float(timeout) if timeout is not None else None,
)
return HTTPStatus.ACCEPTED, {"dispatch": _json_value(record)}
if method == "POST" and path == "/api/v2/hermes/results/reconcile":
context = self.context(headers)
if not isinstance(body, Mapping):
raise ValueError("JSON body must be an object")
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)
return HTTPStatus.OK, {"task": _json_value(task)}
return self.gateway.handle(method, raw_path, headers, body)
class CandidateRequestHandler(BaseHTTPRequestHandler):
server_version = "AIOSV2Candidate/1.0"
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 BaseException 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")
service = DurableControlPlaneService(repository)
tracker = ExecutionTracker(state_dir / "executions")
hermes = HermesAdapter()
openclaw_url = os.getenv("AIOS_OPENCLAW_URL", "").strip()
material_file = os.getenv("AIOS_OPENCLAW_SIGNING_MATERIAL_FILE", "").strip()
openclaw = None
resolver = None
if openclaw_url and material_file:
resolver = FileSigningMaterialResolver(material_file)
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,
)
return CandidateApplication(gateway, orchestrator, tracker, hermes, openclaw)
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()
+69
View File
@@ -0,0 +1,69 @@
"""Dependency-free AIOS V2 web console assets.
Authentication and tenant identity are injected by the trusted reverse proxy.
The browser never selects a tenant and never calls OpenClaw or Hermes directly.
"""
CONSOLE_HTML = r'''<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="referrer" content="no-referrer">
<title>AIOS V2 Console</title>
<style>
:root{font-family:Inter,ui-sans-serif,system-ui,sans-serif;color:#152033;background:#f4f7fb}
*{box-sizing:border-box} body{margin:0} header{background:#111827;color:white;padding:18px 24px;display:flex;justify-content:space-between;align-items:center}
header h1{font-size:20px;margin:0} header span{font-size:12px;color:#cbd5e1}
main{padding:24px;max-width:1440px;margin:auto}.notice{background:#fff7ed;border:1px solid #fed7aa;padding:12px 14px;border-radius:10px;margin-bottom:18px;font-size:13px}
.cards{display:grid;grid-template-columns:repeat(auto-fit,minmax(190px,1fr));gap:14px;margin-bottom:20px}.card,.panel{background:white;border:1px solid #e5e7eb;border-radius:12px;box-shadow:0 1px 2px rgba(0,0,0,.04)}
.card{padding:16px}.card b{display:block;font-size:28px;margin-top:8px}.card small{color:#64748b}.grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(420px,1fr));gap:16px}.panel{padding:16px;overflow:auto}.panel h2{font-size:16px;margin:0 0 12px}
table{width:100%;border-collapse:collapse;font-size:12px}th,td{text-align:left;border-bottom:1px solid #edf0f4;padding:8px;vertical-align:top}th{color:#64748b;font-weight:600}.state{font-weight:700}.ok{color:#047857}.bad{color:#b91c1c}.muted{color:#64748b}
button{border:0;border-radius:8px;padding:9px 13px;background:#2563eb;color:white;cursor:pointer}button:disabled{opacity:.5}.toolbar{display:flex;gap:8px;align-items:center;margin-bottom:16px}.error{color:#b91c1c;white-space:pre-wrap}
</style>
</head>
<body>
<header><h1>AIOS V2 Control Plane</h1><span id="updated">Not loaded</span></header>
<main>
<div class="notice">Read-only candidate console. Identity and tenant context must be injected by the trusted reverse proxy. The console never calls OpenClaw or Hermes directly.</div>
<div class="toolbar"><button id="refresh">Refresh</button><span id="error" class="error"></span></div>
<section class="cards">
<div class="card"><small>Agents</small><b id="agentCount">—</b></div>
<div class="card"><small>Tasks</small><b id="taskCount">—</b></div>
<div class="card"><small>Audit events</small><b id="auditCount">—</b></div>
<div class="card"><small>Executions</small><b id="executionCount">—</b></div>
</section>
<section class="grid">
<div class="panel"><h2>Runtime health</h2><div id="runtime"></div></div>
<div class="panel"><h2>Tasks</h2><div id="tasks"></div></div>
<div class="panel"><h2>Agents</h2><div id="agents"></div></div>
<div class="panel"><h2>Execution evidence</h2><div id="executions"></div></div>
<div class="panel"><h2>Audit</h2><div id="audit"></div></div>
</section>
</main>
<script>
const esc=v=>String(v??'').replace(/[&<>"']/g,c=>({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;',"'":'&#39;'}[c]));
const table=(cols,rows)=>`<table><thead><tr>${cols.map(c=>`<th>${esc(c[0])}</th>`).join('')}</tr></thead><tbody>${rows.map(r=>`<tr>${cols.map(c=>`<td>${esc(c[1](r))}</td>`).join('')}</tr>`).join('')}</tbody></table>`;
async function api(path){const r=await fetch(path,{credentials:'same-origin',headers:{'Accept':'application/json'}});const data=await r.json().catch(()=>({}));if(!r.ok)throw new Error(`${r.status} ${data.message||data.error||path}`);return data}
async function refresh(){
const btn=document.getElementById('refresh');btn.disabled=true;document.getElementById('error').textContent='';
try{
const [agents,tasks,audit,runtime,executions]=await Promise.all([
api('/api/v2/agents'),api('/api/v2/tasks'),api('/api/v2/audit'),api('/api/v2/runtime'),api('/api/v2/executions')
]);
document.getElementById('agentCount').textContent=agents.agents.length;
document.getElementById('taskCount').textContent=tasks.tasks.length;
document.getElementById('auditCount').textContent=audit.events.length;
document.getElementById('executionCount').textContent=executions.executions.length;
document.getElementById('agents').innerHTML=table([['ID',x=>x.agent_id],['Runtime',x=>x.runtime],['Enabled',x=>x.enabled]],agents.agents);
document.getElementById('tasks').innerHTML=table([['Task',x=>x.task_id],['Action',x=>x.action],['State',x=>x.state],['Rev',x=>x.revision]],tasks.tasks);
document.getElementById('audit').innerHTML=table([['Time',x=>x.created_at],['Action',x=>x.action],['Outcome',x=>x.outcome],['Resource',x=>x.resource_id]],audit.events.slice(-100).reverse());
document.getElementById('executions').innerHTML=table([['Executor',x=>x.executor],['Task',x=>x.task_id],['Status',x=>x.status],['Progress',x=>`${x.progress_completed}/${x.progress_total}`],['Commit',x=>x.last_commit||'']],executions.executions);
document.getElementById('runtime').innerHTML=table([['Runtime',x=>x.name],['Status',x=>x.status],['Details',x=>JSON.stringify(x.details)]],runtime.runtimes);
document.getElementById('updated').textContent=`Updated ${new Date().toLocaleString()}`;
}catch(e){document.getElementById('error').textContent=e.message||String(e)}finally{btn.disabled=false}
}
document.getElementById('refresh').addEventListener('click',refresh);refresh();setInterval(refresh,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 +1,195 @@
"""Git-backed agent execution evidence for AIOS V2.
Evidence is tenant-scoped, append-friendly, and contains no runtime credentials.
It provides a deterministic source for claim, heartbeat, progress, result and
verification state across Codex, OpenClaw and Hermes executors.
"""
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
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
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))
class ExecutionTracker:
"""Persist one JSON evidence record per tenant and execution."""
def __init__(self, root: str | Path) -> None:
self.root = Path(root).resolve()
self.root.mkdir(parents=True, exist_ok=True)
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 claim(self, evidence: ExecutionEvidence) -> 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")
return current
self._write(path, evidence)
return evidence
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,
) -> ExecutionEvidence:
path = self._path(tenant_id, execution_id)
with self._lock:
current = self._read(path)
updated = replace(
current,
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,
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,
) -> ExecutionEvidence:
path = self._path(tenant_id, execution_id)
with self._lock:
current = self._read(path)
updated = replace(
current,
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),
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.replace(temporary, path)
+346
View File
@@ -0,0 +1,346 @@
"""HTTP/JSON gateway for the AIOS V2 control plane.
The gateway is intentionally runtime-neutral: browsers and external clients
call this API, while OpenClaw and Hermes remain behind authenticated adapters.
Identity headers are accepted only from a trusted reverse proxy in v1; direct
public exposure is prohibited until signed identity middleware is enabled.
"""
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 .control_plane import (
ControlPlaneError,
ControlPlaneService,
IdempotencyConflict,
InvalidTransition,
NotFound,
PolicyDenied,
RequestContext,
RevisionConflict,
TaskState,
TenantIsolationError,
Unauthorized,
)
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 request router that can be tested without a listening socket."""
def __init__(self, service: ControlPlaneService | None = None) -> None:
self.service = service or ControlPlaneService()
@staticmethod
def context_from_headers(headers: Mapping[str, str]) -> RequestContext:
authenticated = str(headers.get(AUTHENTICATED_HEADER, "")).strip().lower()
if authenticated not in {"1", "true", "yes"}:
raise Unauthorized("trusted authentication assertion is required")
roles = [
role.strip()
for role in str(headers.get(ROLES_HEADER, "")).split(",")
if role.strip()
]
return RequestContext.create(
tenant_id=str(headers.get(TENANT_HEADER, "")),
principal_id=str(headers.get(PRINCIPAL_HEADER, "")),
trace_id=str(headers.get(TRACE_HEADER, "")).strip() or None,
session_id=str(headers.get(SESSION_HEADER, "")).strip() or None,
policy_version=str(headers.get(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":
tenant = self.service.get_tenant(context)
return HTTPStatus.OK, {"tenant": _json_value(tenant)}
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":
requested_states = query.get("state")
tasks = self.service.list_tasks(context, states=requested_states)
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))
}
transition_match = re.fullmatch(
r"/api/v2/tasks/([^/]+)/(approve|start|complete|fail|cancel)", path
)
if method == "POST" and transition_match:
task_id = _require_resource_id(
urllib.parse.unquote(transition_match.group(1)), label="task_id"
)
transition = transition_match.group(2)
target = {
"approve": TaskState.APPROVED,
"start": TaskState.RUNNING,
"complete": TaskState.COMPLETED,
"fail": TaskState.FAILED,
"cancel": TaskState.CANCELLED,
}[transition]
expected_revision = payload.get("expected_revision")
if expected_revision is not None:
expected_revision = int(expected_revision)
task = self.service.transition_task(
context,
task_id=task_id,
target_state=target,
expected_revision=expected_revision,
result=(
_require_mapping(payload.get("result"), label="result")
if payload.get("result") is not None
else None
),
error=(
_require_mapping(payload.get("error"), label="error")
if payload.get("error") 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),
(TenantIsolationError, HTTPStatus.NOT_FOUND),
(NotFound, HTTPStatus.NOT_FOUND),
(IdempotencyConflict, HTTPStatus.CONFLICT),
(RevisionConflict, HTTPStatus.CONFLICT),
(InvalidTransition, 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")
raw = self.rfile.read(length)
return json.loads(raw.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 BaseException as exc: # handler boundary; sanitized below
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:
# Production deployment routes structured access logs through the
# reverse proxy; do not log identity headers or request bodies here.
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,
},
)
+264
View File
@@ -0,0 +1,264 @@
"""AIOS V2 execution orchestrator.
The orchestrator is the only component allowed to translate an approved AIOS
task into an OpenClaw command or Hermes job. OpenClaw and Hermes remain pure
execution runtimes and never own tenant policy or task lifecycle.
"""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Mapping
from aios_hermes import HermesAdapter, HermesJob, HermesResult
from aios_openclaw import (
CommandState,
OpenClawAdapter,
OpenClawCommand,
OpenClawResult,
sign_command,
)
from .control_plane import (
AgentRecord,
ControlPlaneService,
RequestContext,
TaskRecord,
TaskState,
)
class OrchestrationError(RuntimeError):
"""AIOS failed to dispatch or reconcile a runtime execution."""
@dataclass(frozen=True)
class DispatchRecord:
tenant_id: str
task_id: str
agent_id: str
runtime: str
runtime_execution_id: str
state: str
trace_id: str
class ExecutionOrchestrator:
"""Dispatch approved AIOS tasks to runtime adapters and reconcile 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",
) -> 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 = openclaw_key_id
self.default_cell_id = default_cell_id
self.default_profile_id = default_profile_id
self._dispatches: dict[tuple[str, str], DispatchRecord] = {}
def dispatch(
self,
context: RequestContext,
*,
task_id: str,
timeout_seconds: float | None = None,
) -> DispatchRecord:
task = self.control_plane.get_task(context, task_id)
if task.state != TaskState.APPROVED:
raise OrchestrationError("only APPROVED tasks may be dispatched")
agent = self.control_plane.get_agent(context, task.agent_id)
existing = self._dispatches.get((task.tenant_id, task.task_id))
if existing is not None:
return existing
running = self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.RUNNING,
expected_revision=task.revision,
)
runtime = agent.runtime.strip().lower()
try:
if runtime == "openclaw":
record = self._dispatch_openclaw(
context,
agent,
running,
timeout_seconds=timeout_seconds,
)
elif runtime == "hermes":
record = self._dispatch_hermes(context, agent, running)
else:
raise OrchestrationError(f"unsupported runtime: {agent.runtime}")
except Exception as exc:
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
self._dispatches[(task.tenant_id, task.task_id)] = record
return record
def _dispatch_openclaw(
self,
context: RequestContext,
agent: AgentRecord,
task: TaskRecord,
*,
timeout_seconds: float | None,
) -> DispatchRecord:
if self.openclaw is None or self.openclaw_signing_material_resolver is None:
raise OrchestrationError("OpenClaw runtime 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,
)
command = sign_command(command, key_material)
result = self.openclaw.execute(command, timeout_seconds=timeout_seconds)
self.reconcile_openclaw(context, result)
return DispatchRecord(
tenant_id=task.tenant_id,
task_id=task.task_id,
agent_id=agent.agent_id,
runtime="openclaw",
runtime_execution_id=command.command_id,
state=result.state.value,
trace_id=context.trace_id,
)
def _dispatch_hermes(
self,
context: RequestContext,
agent: AgentRecord,
task: TaskRecord,
) -> DispatchRecord:
if self.hermes is None:
raise OrchestrationError("Hermes runtime is not configured")
metadata = dict(agent.metadata)
job = 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)),
)
queued = self.hermes.enqueue(job)
return DispatchRecord(
tenant_id=task.tenant_id,
task_id=task.task_id,
agent_id=agent.agent_id,
runtime="hermes",
runtime_execution_id=queued.job_id,
state=queued.state.value,
trace_id=context.trace_id,
)
def reconcile_openclaw(
self,
context: RequestContext,
result: OpenClawResult,
) -> TaskRecord:
task = self.control_plane.get_task(context, result.task_id)
if result.tenant_id != task.tenant_id:
raise OrchestrationError("OpenClaw result tenant mismatch")
if task.state != TaskState.RUNNING:
return task
if result.state == CommandState.COMPLETED:
return self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.COMPLETED,
expected_revision=task.revision,
result=result.output or {},
)
if result.state in {
CommandState.FAILED,
CommandState.TIMED_OUT,
CommandState.REJECTED,
}:
return self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.FAILED,
expected_revision=task.revision,
error=result.error or {"code": result.state.value.lower()},
)
if result.state == CommandState.CANCELLED:
return self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.CANCELLED,
expected_revision=task.revision,
)
return task
def reconcile_hermes(
self,
context: RequestContext,
result: HermesResult,
) -> TaskRecord:
task = self.control_plane.get_task(context, result.task_id)
if result.tenant_id != task.tenant_id:
raise OrchestrationError("Hermes result tenant mismatch")
if task.state != TaskState.RUNNING:
return task
if result.state.value == "COMPLETED":
return self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.COMPLETED,
expected_revision=task.revision,
result=result.output or {},
)
if result.state.value == "FAILED":
return self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.FAILED,
expected_revision=task.revision,
error=result.error or {"code": "hermes_failed"},
)
if result.state.value == "CANCELLED":
return self.control_plane.transition_task(
context,
task_id=task.task_id,
target_state=TaskState.CANCELLED,
expected_revision=task.revision,
)
return task
def dispatch_snapshot(self, *, tenant_id: str) -> Mapping[str, DispatchRecord]:
return {
task_id: record
for (record_tenant, task_id), record in self._dispatches.items()
if record_tenant == 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))
@@ -0,0 +1,120 @@
"""Architect governance agent responsibilities.
This agent records requirement changes, maintains versioned human-readable
requirement/architecture/deployment/test documents, reviews architecture changes,
validates deployment docs against actual configuration, and produces version bump
recommendations.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class RequirementChange:
id: str
source: str
actor: str
requirement: str
created_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class DocumentRefreshPlan:
requirement_doc: bool
architecture_doc: bool
deployment_doc: bool
test_case_doc: bool
reason: str
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class ArchitectureReviewDecision:
status: str
findings: list[str]
optimization_recommendations: list[str]
version_bump: str
docs_to_refresh: DocumentRefreshPlan
created_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return {
"status": self.status,
"findings": self.findings,
"optimization_recommendations": self.optimization_recommendations,
"version_bump": self.version_bump,
"docs_to_refresh": self.docs_to_refresh.to_dict(),
"created_at": self.created_at,
}
class ArchitectGovernanceAgent:
"""Independent architecture governance role."""
def record_requirement_change(self, source: str, actor: str, requirement: str) -> RequirementChange:
change_id = "REQ-" + datetime.now(timezone.utc).strftime("%Y%m%d%H%M%S")
return RequirementChange(change_id, source, actor, requirement)
def review_architecture_change(self, proposal: dict[str, Any]) -> ArchitectureReviewDecision:
impact = proposal.get("impact", "medium")
findings = [
"requirement_traceability_checked",
"architecture_consistency_checked",
"deployment_doc_alignment_checked",
"test_case_doc_required",
"rollback_and_owner_gate_checked",
]
recommendations = [
"refresh user requirements document",
"refresh architecture design document",
"refresh engineering deployment document",
"generate acceptance test case document",
]
version_bump = self.decide_version_bump(proposal)
return ArchitectureReviewDecision(
status="review_required" if impact in {"high", "architecture"} else "pass",
findings=findings,
optimization_recommendations=recommendations,
version_bump=version_bump,
docs_to_refresh=DocumentRefreshPlan(True, True, True, True, "architecture or requirement changed"),
)
def decide_version_bump(self, proposal: dict[str, Any]) -> str:
if proposal.get("breaks_architecture") or proposal.get("major_capability"):
return "V"
if proposal.get("new_release_capability") or proposal.get("architecture_change"):
return "R"
return "C"
def validate_deployment_doc(self, deployment_doc: dict[str, Any], actual_config: dict[str, Any]) -> dict[str, Any]:
expected = set(deployment_doc.get("services", []))
actual = set(actual_config.get("services", []))
missing = sorted(expected - actual)
extra = sorted(actual - expected)
return {
"status": "pass" if not missing else "attention_required",
"missing_services": missing,
"extra_services": extra,
"checked_at": utc_now(),
}
__all__ = [
"RequirementChange",
"DocumentRefreshPlan",
"ArchitectureReviewDecision",
"ArchitectGovernanceAgent",
]
@@ -0,0 +1,32 @@
"""API for Architect Governance Center."""
try:
from fastapi import APIRouter
except Exception:
APIRouter = None
from .architect_governance_dashboard import ArchitectGovernanceDashboard
dashboard = ArchitectGovernanceDashboard()
def get_architect_governance_overview():
return dashboard.overview()
def build_router():
if APIRouter is None:
return None
router = APIRouter(prefix="/admin/ai-evolution/architect", tags=["architect-governance"])
@router.get("/overview", operation_id="getArchitectGovernanceOverview")
def overview():
return get_architect_governance_overview()
return router
router = build_router()
__all__ = ["router", "get_architect_governance_overview"]
@@ -0,0 +1,153 @@
"""Web UI dashboard model for Architect Governance Agent.
Shows requirement changes, architecture review findings, document refresh status,
deployment consistency, test case readiness, weekly research and V/R/C version
recommendations.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ArchitectPanelMetric:
key: str
title: str
value: Any
status: str = "ok"
detail: str = ""
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class ArchitectPanel:
key: str
title: str
description: str
metrics: list[ArchitectPanelMetric] = field(default_factory=list)
def to_dict(self) -> dict[str, Any]:
return {
"key": self.key,
"title": self.title,
"description": self.description,
"metrics": [m.to_dict() for m in self.metrics],
}
class ArchitectGovernanceDashboard:
def overview(
self,
requirement_changes: list[dict[str, Any]] | None = None,
architecture_reviews: list[dict[str, Any]] | None = None,
document_status: dict[str, Any] | None = None,
research_status: dict[str, Any] | None = None,
version_recommendations: list[dict[str, Any]] | None = None,
) -> dict[str, Any]:
requirement_changes = requirement_changes or []
architecture_reviews = architecture_reviews or []
document_status = document_status or {}
research_status = research_status or {}
version_recommendations = version_recommendations or []
panels = [
self.requirement_panel(requirement_changes),
self.architecture_panel(architecture_reviews),
self.document_panel(document_status),
self.research_panel(research_status),
self.version_panel(version_recommendations),
]
return {
"module": "architect-governance",
"route": "/admin/ai-evolution/architect",
"title": "架构师 Agent 治理中心",
"status": "attention_required" if any(self._panel_warn(panel) for panel in panels) else "healthy",
"generated_at": utc_now(),
"panels": [panel.to_dict() for panel in panels],
"requirement_changes": requirement_changes,
"architecture_reviews": architecture_reviews,
"version_recommendations": version_recommendations,
}
def requirement_panel(self, changes: list[dict[str, Any]]) -> ArchitectPanel:
return ArchitectPanel(
key="requirements",
title="需求变化记录",
description="记录来自 Custom GPT、Codex、OpenClaw、Hermes 和用户反馈的需求变化。",
metrics=[
ArchitectPanelMetric("total_requirement_changes", "需求变化数量", len(changes)),
ArchitectPanelMetric(
"undocumented_changes",
"待刷新到用户需求文档",
len([c for c in changes if not c.get("documented")]),
"warn" if any(not c.get("documented") for c in changes) else "ok",
),
],
)
def architecture_panel(self, reviews: list[dict[str, Any]]) -> ArchitectPanel:
pending = [r for r in reviews if r.get("status") not in {"pass", "not_required"}]
return ArchitectPanel(
key="architecture_review",
title="全量架构审视",
description="展示架构一致性、扩展性、安全边界、可运维性和回滚策略审查。",
metrics=[
ArchitectPanelMetric("review_count", "架构审查数量", len(reviews)),
ArchitectPanelMetric("pending_reviews", "待处理架构审查", len(pending), "warn" if pending else "ok"),
],
)
def document_panel(self, status: dict[str, Any]) -> ArchitectPanel:
required_docs = ["requirements", "architecture", "deployment", "test_cases"]
missing = [doc for doc in required_docs if status.get(doc) not in {"ready", "updated"}]
return ArchitectPanel(
key="documents",
title="文档版本化状态",
description="用户需求、架构设计、工程部署、测试例文档刷新状态。",
metrics=[
ArchitectPanelMetric("requirements_doc", "用户需求文档", status.get("requirements", "unknown"), "warn" if "requirements" in missing else "ok"),
ArchitectPanelMetric("architecture_doc", "架构设计文档", status.get("architecture", "unknown"), "warn" if "architecture" in missing else "ok"),
ArchitectPanelMetric("deployment_doc", "工程部署文档", status.get("deployment", "unknown"), "warn" if "deployment" in missing else "ok"),
ArchitectPanelMetric("test_case_doc", "测试例文档", status.get("test_cases", "unknown"), "warn" if "test_cases" in missing else "ok"),
],
)
def research_panel(self, status: dict[str, Any]) -> ArchitectPanel:
overdue = bool(status.get("overdue"))
return ArchitectPanel(
key="weekly_research",
title="每周外部技术情报",
description="联网搜索 Agent/模型版本、GitHub top 实现、潜在安全影响。",
metrics=[
ArchitectPanelMetric("last_research_at", "最近调研时间", status.get("last_research_at", "never"), "warn" if overdue else "ok"),
ArchitectPanelMetric("findings", "发现数量", status.get("findings", 0)),
ArchitectPanelMetric("optimization_candidates", "可借鉴优化项", status.get("optimization_candidates", 0)),
],
)
def version_panel(self, recommendations: list[dict[str, Any]]) -> ArchitectPanel:
latest = recommendations[-1] if recommendations else {}
return ArchitectPanel(
key="version_decision",
title="V/R/C 版本建议",
description="由架构师 Agent 判断变更应进入 C、R 或 V。",
metrics=[
ArchitectPanelMetric("recommendation_count", "版本建议数量", len(recommendations)),
ArchitectPanelMetric("latest_recommendation", "最近建议", latest.get("version_bump", "none")),
ArchitectPanelMetric("reason", "建议原因", latest.get("reason", "")),
],
)
def _panel_warn(self, panel: ArchitectPanel) -> bool:
return any(metric.status == "warn" for metric in panel.metrics)
__all__ = ["ArchitectPanelMetric", "ArchitectPanel", "ArchitectGovernanceDashboard"]
@@ -0,0 +1,40 @@
"""Web UI model for Architect weekly research."""
from .architect_weekly_research_agent import ArchitectWeeklyResearchAgent
class ArchitectResearchDashboard:
def __init__(self, agent=None):
self.agent = agent or ArchitectWeeklyResearchAgent()
def overview(self):
return {
"module": "architect-weekly-research",
"route": "/admin/ai-evolution/architect/research",
"title": "架构师 Agent 技术情报中心",
"panels": [
{
"title": "Research Targets",
"data": self.agent.plan(),
},
{
"title": "Evaluation",
"fields": [
"relevance",
"impact",
"recommendation",
],
},
{
"title": "Version Decision",
"fields": [
"C",
"R",
"V",
],
},
],
}
__all__ = ["ArchitectResearchDashboard"]
@@ -0,0 +1,122 @@
"""Architect research timeline dashboard.
Shows weekly external research findings as a traceable architecture-impact flow:
research target -> finding -> impact -> recommendation -> version decision ->
governance event.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ResearchTimelineStep:
id: str
title: str
step_type: str
status: str
source: str
timestamp: str
impact: str = "none"
version_bump: str = "none"
detail: dict[str, Any] = field(default_factory=dict)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
class ArchitectResearchTimeline:
ORDER = {
"research_planned": 10,
"finding_created": 20,
"impact_analyzed": 30,
"recommendation_created": 40,
"version_decision_created": 50,
"architecture_review_event_created": 60,
}
def build(self, findings: list[dict[str, Any]] | None = None, decisions: list[dict[str, Any]] | None = None) -> dict[str, Any]:
findings = findings or []
decisions = decisions or []
steps: list[ResearchTimelineStep] = [
ResearchTimelineStep(
id="research-plan",
title="每周技术情报调研计划",
step_type="research_planned",
status="ok",
source="architect-agent",
timestamp=utc_now(),
detail={"cadence": "weekly"},
)
]
for idx, finding in enumerate(findings):
steps.append(
ResearchTimelineStep(
id=finding.get("id", f"finding-{idx}"),
title=finding.get("title", "research finding"),
step_type="finding_created",
status="ok",
source=finding.get("source", "unknown"),
timestamp=finding.get("created_at", utc_now()),
impact=finding.get("impact", "none"),
detail=finding,
)
)
steps.append(
ResearchTimelineStep(
id=f"impact-{finding.get('id', idx)}",
title="架构影响分析",
step_type="impact_analyzed",
status="attention_required" if finding.get("impact") in {"architecture", "breaking", "new_capability"} else "ok",
source="architect-agent",
timestamp=utc_now(),
impact=finding.get("impact", "none"),
detail={"relevance": finding.get("relevance"), "recommendation": finding.get("recommendation")},
)
)
for idx, decision in enumerate(decisions):
steps.append(
ResearchTimelineStep(
id=decision.get("id", f"decision-{idx}"),
title="C/R/V 版本建议",
step_type="version_decision_created",
status=decision.get("status", "ok"),
source="architect-agent",
timestamp=decision.get("created_at", utc_now()),
version_bump=decision.get("version_bump", "none"),
detail=decision,
)
)
steps.sort(key=lambda s: (self.ORDER.get(s.step_type, 999), s.timestamp))
return {
"module": "architect-research-timeline",
"route": "/admin/ai-evolution/architect/research/timeline",
"title": "架构师技术情报时间线",
"status": self._status(steps),
"generated_at": utc_now(),
"steps": [step.to_dict() for step in steps],
"summary": self._summary(steps),
}
def _status(self, steps: list[ResearchTimelineStep]) -> str:
if any(step.status == "attention_required" for step in steps):
return "attention_required"
return "healthy"
def _summary(self, steps: list[ResearchTimelineStep]) -> dict[str, Any]:
return {
"findings": len([s for s in steps if s.step_type == "finding_created"]),
"architecture_impacts": len([s for s in steps if s.impact in {"architecture", "breaking", "new_capability"}]),
"version_decisions": len([s for s in steps if s.step_type == "version_decision_created"]),
"recommended_bumps": sorted({s.version_bump for s in steps if s.version_bump != "none"}),
}
__all__ = ["ResearchTimelineStep", "ArchitectResearchTimeline"]
@@ -0,0 +1,32 @@
"""API for architect research timeline."""
try:
from fastapi import APIRouter
except Exception:
APIRouter = None
from .architect_research_timeline import ArchitectResearchTimeline
timeline = ArchitectResearchTimeline()
def get_architect_research_timeline():
return timeline.build()
def build_router():
if APIRouter is None:
return None
router = APIRouter(prefix="/admin/ai-evolution/architect/research", tags=["architect-research"])
@router.get("/timeline", operation_id="getArchitectResearchTimeline")
def get_timeline():
return get_architect_research_timeline()
return router
router = build_router()
__all__ = ["router", "get_architect_research_timeline"]
@@ -0,0 +1,113 @@
"""Weekly external research loop for Architect Governance Agent.
The agent plans and normalizes weekly research tasks. Actual internet access is
provided by the runtime/search worker; this module defines the audited workflow,
findings, impact analysis, and V/R/C recommendations.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
from uuid import uuid4
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ResearchTarget:
id: str
topic: str
source_type: str
query: str
cadence: str = "weekly"
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class ResearchFinding:
id: str
target_id: str
title: str
summary: str
source: str
relevance: str
impact: str
recommendation: str
created_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class ResearchDecision:
status: str
version_bump: str
reason: str
findings: list[ResearchFinding]
created_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return {
"status": self.status,
"version_bump": self.version_bump,
"reason": self.reason,
"findings": [f.to_dict() for f in self.findings],
"created_at": self.created_at,
}
class ArchitectWeeklyResearchAgent:
DEFAULT_TARGETS = (
ResearchTarget("agent-frameworks", "Agent framework versions", "web", "latest multi-agent orchestration framework releases"),
ResearchTarget("model-ecosystem", "Model ecosystem changes", "web", "latest LLM model releases tool calling agent features"),
ResearchTarget("github-top-agentops", "GitHub top AgentOps implementations", "github", "top repositories agent observability multi agent orchestration"),
ResearchTarget("security-agent-risks", "Agent security changes", "web", "latest AI agent security sandbox prompt injection tool use risks"),
)
def plan(self) -> dict[str, Any]:
return {
"status": "planned",
"cadence": "weekly",
"targets": [target.to_dict() for target in self.DEFAULT_TARGETS],
"created_at": utc_now(),
}
def normalize_finding(
self,
target_id: str,
title: str,
summary: str,
source: str,
relevance: str = "medium",
impact: str = "none",
recommendation: str = "monitor",
) -> ResearchFinding:
return ResearchFinding(
id=f"finding_{uuid4().hex[:12]}",
target_id=target_id,
title=title,
summary=summary,
source=source,
relevance=relevance,
impact=impact,
recommendation=recommendation,
)
def decide(self, findings: list[ResearchFinding]) -> ResearchDecision:
if any(f.impact == "breaking" for f in findings):
return ResearchDecision("action_required", "V", "breaking external ecosystem change", findings)
if any(f.impact in {"architecture", "new_capability"} for f in findings):
return ResearchDecision("optimization_recommended", "R", "external capability may improve architecture", findings)
if any(f.impact in {"bugfix", "minor"} for f in findings):
return ResearchDecision("minor_change_recommended", "C", "minor compatible improvement", findings)
return ResearchDecision("no_action", "none", "no relevant external change", findings)
__all__ = ["ResearchTarget", "ResearchFinding", "ResearchDecision", "ArchitectWeeklyResearchAgent"]
@@ -0,0 +1,32 @@
"""API for architecture change governance dashboard."""
try:
from fastapi import APIRouter
except Exception:
APIRouter = None
from .architecture_change_dashboard import ArchitectureChangeDashboard
dashboard = ArchitectureChangeDashboard()
def get_architecture_change_overview():
return dashboard.overview()
def build_router():
if APIRouter is None:
return None
router = APIRouter(prefix="/admin/ai-evolution/architecture-changes", tags=["architecture-changes"])
@router.get("/overview", operation_id="getArchitectureChangeOverview")
def overview():
return get_architecture_change_overview()
return router
router = build_router()
__all__ = ["router", "get_architecture_change_overview"]
@@ -0,0 +1,90 @@
"""Architecture change classification.
Small compatible architecture changes may be handled automatically by the
Architect Agent with audit evidence. Large, risky, production-impacting or
breaking architecture changes require explicit Owner approval before
implementation.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from typing import Any
@dataclass(frozen=True)
class ArchitectureChangeClassification:
level: str
owner_required: bool
auto_implement_allowed: bool
version_bump: str
reasons: list[str] = field(default_factory=list)
required_gates: list[str] = field(default_factory=list)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
class ArchitectureChangeClassifier:
"""Classifies architecture changes into small/medium/large governance paths."""
LARGE_FLAGS = {
"breaking_change",
"breaks_architecture",
"production_architecture_update",
"security_boundary_change",
"cross_tenant_effect",
"cross_user_data_effect",
"data_migration",
"permission_model_change",
"runtime_infrastructure_change",
}
def classify(self, change: dict[str, Any]) -> ArchitectureChangeClassification:
risk = str(change.get("risk", "medium")).lower()
version_bump = str(change.get("version_bump", change.get("recommended_version_bump", "C"))).upper()
scope = str(change.get("scope", "component")).lower()
reasons: list[str] = []
for flag in sorted(self.LARGE_FLAGS):
if change.get(flag):
reasons.append(flag)
if risk in {"high", "critical"}:
reasons.append(f"risk={risk}")
if version_bump == "V":
reasons.append("version_bump=V")
if version_bump == "R" and scope in {"system", "platform", "production", "cross_agent", "cross_tenant"}:
reasons.append(f"version_bump=R scope={scope}")
if reasons:
return ArchitectureChangeClassification(
level="large",
owner_required=True,
auto_implement_allowed=False,
version_bump=version_bump,
reasons=reasons,
required_gates=["architect_review", "owner_architecture_approval", "test_gate", "promotion_gate"],
)
if risk == "low" and version_bump in {"C", "NONE"} and scope in {"component", "local", "documentation", "test"}:
return ArchitectureChangeClassification(
level="small",
owner_required=False,
auto_implement_allowed=True,
version_bump=version_bump,
reasons=["low_risk_compatible_change"],
required_gates=["architect_review", "audit", "test_gate"],
)
return ArchitectureChangeClassification(
level="medium",
owner_required=False,
auto_implement_allowed=False,
version_bump=version_bump,
reasons=["requires_architect_review_before_implementation"],
required_gates=["architect_review", "test_gate", "audit"],
)
__all__ = ["ArchitectureChangeClassification", "ArchitectureChangeClassifier"]
@@ -0,0 +1,93 @@
"""Architecture change governance dashboard.
Displays architecture change classification, owner approval requirements,
implementation readiness, version recommendation and audit evidence for Web UI.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
from .architecture_change_classifier import ArchitectureChangeClassifier
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ArchitectureChangeView:
change_id: str
title: str
level: str
owner_required: bool
auto_implement_allowed: bool
version_bump: str
status: str
reasons: list[str] = field(default_factory=list)
required_gates: list[str] = field(default_factory=list)
owner_decision: str | None = None
def to_dict(self) -> dict[str, Any]:
return asdict(self)
class ArchitectureChangeDashboard:
def __init__(self, classifier: ArchitectureChangeClassifier | None = None):
self.classifier = classifier or ArchitectureChangeClassifier()
def overview(self, changes: list[dict[str, Any]] | None = None) -> dict[str, Any]:
changes = changes or []
views = [self._view(change) for change in changes]
return {
"module": "architecture-change-governance",
"route": "/admin/ai-evolution/architecture-changes",
"title": "架构变更治理中心",
"status": self._status(views),
"generated_at": utc_now(),
"summary": self._summary(views),
"changes": [view.to_dict() for view in views],
}
def _view(self, change: dict[str, Any]) -> ArchitectureChangeView:
classification = self.classifier.classify(change)
owner_decision = change.get("owner_decision")
if classification.owner_required and owner_decision != "approved":
status = "waiting_owner_approval"
elif classification.auto_implement_allowed:
status = "auto_implementation_allowed"
else:
status = "ready_after_required_gates"
return ArchitectureChangeView(
change_id=change.get("change_id", change.get("id", "unknown")),
title=change.get("title", "architecture change"),
level=classification.level,
owner_required=classification.owner_required,
auto_implement_allowed=classification.auto_implement_allowed,
version_bump=classification.version_bump,
status=status,
reasons=classification.reasons,
required_gates=classification.required_gates,
owner_decision=owner_decision,
)
def _status(self, views: list[ArchitectureChangeView]) -> str:
if any(view.status == "waiting_owner_approval" for view in views):
return "attention_required"
return "healthy"
def _summary(self, views: list[ArchitectureChangeView]) -> dict[str, Any]:
return {
"total": len(views),
"small": len([v for v in views if v.level == "small"]),
"medium": len([v for v in views if v.level == "medium"]),
"large": len([v for v in views if v.level == "large"]),
"waiting_owner_approval": len([v for v in views if v.status == "waiting_owner_approval"]),
"auto_allowed": len([v for v in views if v.auto_implement_allowed]),
"version_bumps": sorted({v.version_bump for v in views if v.version_bump and v.version_bump != "NONE"}),
}
__all__ = ["ArchitectureChangeView", "ArchitectureChangeDashboard"]
@@ -0,0 +1,89 @@
"""Owner approval gate for architecture changes.
Architecture changes may be proposed, reviewed and optimized by agents, but they
must not be implemented until owner approval is recorded. This gate sits before
implementation and before promotion.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ArchitectureOwnerApprovalRequest:
request_id: str
change_id: str
title: str
reason: str
risk: str
architect_decision: str
status: str = "pending_owner_approval"
created_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class ArchitectureOwnerDecision:
request_id: str
change_id: str
decision: str
decided_by: str
reason: str = ""
decided_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
class ArchitectureOwnerGate:
"""Blocks architecture implementation until owner explicitly approves."""
def create_request(self, change: dict[str, Any], architect_decision: dict[str, Any]) -> ArchitectureOwnerApprovalRequest:
return ArchitectureOwnerApprovalRequest(
request_id=f"ARCH-OWNER-{change.get('change_id', change.get('id', 'unknown'))}",
change_id=change.get("change_id", change.get("id", "unknown")),
title=change.get("title", "architecture change"),
reason=change.get("reason", "architecture impact requires owner approval"),
risk=change.get("risk", "medium"),
architect_decision=architect_decision.get("status", "reviewed"),
)
def can_implement(self, request: dict[str, Any], decision: dict[str, Any] | None = None) -> dict[str, Any]:
if not decision:
return {
"allowed": False,
"status": "waiting_owner_approval",
"reason": "architecture change requires owner approval before implementation",
"request": request,
}
if decision.get("decision") == "approved":
return {
"allowed": True,
"status": "owner_approved",
"reason": decision.get("reason", "approved by owner"),
"request": request,
"decision": decision,
}
return {
"allowed": False,
"status": "owner_rejected",
"reason": decision.get("reason", "rejected by owner"),
"request": request,
"decision": decision,
}
__all__ = [
"ArchitectureOwnerApprovalRequest",
"ArchitectureOwnerDecision",
"ArchitectureOwnerGate",
]
@@ -0,0 +1,79 @@
"""HTTP handler and display data for architecture owner gate."""
from __future__ import annotations
from dataclasses import asdict
from datetime import datetime, timezone
from typing import Any
from .architecture_owner_gate import ArchitectureOwnerGate, ArchitectureOwnerApprovalRequest
gate = ArchitectureOwnerGate()
# In-memory store for pending approval requests
_pending_requests: dict[str, dict[str, Any]] = {}
_decisions: dict[str, dict[str, Any]] = {}
def create_owner_approval_request(change: dict[str, Any], architect_decision: dict[str, Any]) -> dict[str, Any]:
req = gate.create_request(change, architect_decision)
d = asdict(req)
_pending_requests[req.change_id] = d
return d
def approve_request(change_id: str, decided_by: str = "owner", reason: str = "") -> dict[str, Any]:
req = _pending_requests.get(change_id)
if not req:
return {"error": f"no pending request for change_id={change_id}"}
decision = asdict(
ArchitectureOwnerApprovalRequest.__bases__[1].__new__(type("_ArchitectureOwnerDecision", (), {})) # noqa
)
try:
from .architecture_owner_gate import ArchitectureOwnerDecision
dec = ArchitectureOwnerDecision(
request_id=req["request_id"],
change_id=change_id,
decision="approved",
decided_by=decided_by,
reason=reason,
)
d = asdict(dec)
_decisions[change_id] = d
# remove from pending
_pending_requests.pop(change_id, None)
return {"allowed": True, "decision": d}
except Exception as exc:
return {"error": str(exc)}
def reject_request(change_id: str, decided_by: str = "owner", reason: str = "") -> dict[str, Any]:
from .architecture_owner_gate import ArchitectureOwnerDecision
req = _pending_requests.get(change_id)
if not req:
return {"error": f"no pending request for change_id={change_id}"}
try:
dec = ArchitectureOwnerDecision(
request_id=req["request_id"],
change_id=change_id,
decision="rejected",
decided_by=decided_by,
reason=reason,
)
d = asdict(dec)
_decisions[change_id] = d
_pending_requests.pop(change_id, None)
return {"allowed": False, "decision": d}
except Exception as exc:
return {"error": str(exc)}
def get_owner_gate_overview() -> dict[str, Any]:
return {
"pending_requests": list(_pending_requests.values()),
"decisions": list(_decisions.values()),
"pending_count": len(_pending_requests),
"approved_count": sum(1 for d in _decisions.values() if d.get("decision") == "approved"),
"rejected_count": sum(1 for d in _decisions.values() if d.get("decision") == "rejected"),
}
@@ -0,0 +1,40 @@
"""Independent architecture optimization agent."""
from dataclasses import dataclass, asdict
from datetime import datetime, timezone
def utc_now():
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ArchitectureReview:
agent: str
decision: str
findings: list[str]
created_at: str = utc_now()
def to_dict(self):
return asdict(self)
class ArchitectureReviewAgent:
"""Reviews architecture changes from system-wide optimal perspective."""
def review(self, proposal: dict) -> ArchitectureReview:
findings = [
"dependency_impact_checked",
"security_boundary_checked",
"scalability_checked",
"operability_checked",
"rollback_strategy_checked",
]
return ArchitectureReview(
"architecture-optimization-agent",
"pass" if proposal.get("architecture_change") else "not_required",
findings,
)
__all__ = ["ArchitectureReviewAgent", "ArchitectureReview"]
@@ -0,0 +1,103 @@
"""Change acceptance governance for AIOS.
Every feature change must provide matching tests. Every architecture change must
be reviewed by an independent architecture agent. User-facing changes must be
validated by an independent user acceptance agent.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class ChangeDescriptor:
change_id: str
change_type: str
title: str
files_changed: list[str]
tests: list[str] = field(default_factory=list)
user_facing: bool = False
architecture_impact: bool = False
risk: str = "low"
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class AcceptanceFinding:
check: str
status: str
detail: str
required: bool = True
def passed(self) -> bool:
return self.status == "pass" or not self.required
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class AcceptanceDecision:
status: str
findings: list[AcceptanceFinding]
decided_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return {
"status": self.status,
"findings": [f.to_dict() for f in self.findings],
"decided_at": self.decided_at,
}
class ChangeAcceptanceGate:
def evaluate(self, change: ChangeDescriptor) -> AcceptanceDecision:
findings: list[AcceptanceFinding] = []
findings.append(self._tests_required(change))
findings.append(self._user_acceptance_required(change))
findings.append(self._architecture_review_required(change))
findings.append(self._risk_gate(change))
status = "pass" if all(f.passed() for f in findings) else "blocked"
return AcceptanceDecision(status, findings)
def _tests_required(self, change: ChangeDescriptor) -> AcceptanceFinding:
if change.tests:
return AcceptanceFinding("tests_present", "pass", "matching tests declared")
return AcceptanceFinding("tests_present", "fail", "every feature change requires tests")
def _user_acceptance_required(self, change: ChangeDescriptor) -> AcceptanceFinding:
if not change.user_facing:
return AcceptanceFinding("user_acceptance", "pass", "not user-facing")
has_user_test = any("user" in t.lower() or "acceptance" in t.lower() for t in change.tests)
return AcceptanceFinding(
"user_acceptance",
"pass" if has_user_test else "fail",
"user-facing change requires user acceptance test",
)
def _architecture_review_required(self, change: ChangeDescriptor) -> AcceptanceFinding:
if not change.architecture_impact:
return AcceptanceFinding("architecture_review", "pass", "no architecture impact")
has_arch_test = any("arch" in t.lower() or "architecture" in t.lower() for t in change.tests)
return AcceptanceFinding(
"architecture_review",
"pass" if has_arch_test else "fail",
"architecture change requires independent architect review artifact/test",
)
def _risk_gate(self, change: ChangeDescriptor) -> AcceptanceFinding:
if change.risk in {"low", "medium", "high"}:
return AcceptanceFinding("risk_classified", "pass", f"risk={change.risk}")
return AcceptanceFinding("risk_classified", "fail", "risk must be low/medium/high")
__all__ = ["ChangeDescriptor", "AcceptanceFinding", "AcceptanceDecision", "ChangeAcceptanceGate"]
@@ -0,0 +1,34 @@
"""API for AIOS change governance dashboard."""
from typing import Any
try:
from fastapi import APIRouter
except Exception:
APIRouter = None
from .change_governance_dashboard import ChangeGovernanceDashboard
dashboard = ChangeGovernanceDashboard()
def get_change_governance_overview(changes: list[dict[str, Any]] | None = None):
return dashboard.overview(changes)
def build_router():
if APIRouter is None:
return None
router = APIRouter(prefix="/admin/ai-evolution/governance", tags=["change-governance"])
@router.get("/overview", operation_id="getChangeGovernanceOverview")
def overview():
return get_change_governance_overview()
return router
router = build_router()
__all__ = ["router", "get_change_governance_overview"]
@@ -0,0 +1,93 @@
"""Web UI dashboard model for AIOS change governance.
Shows test gates, user acceptance, architecture review, risk gates and release
blocking status for human operators and owner review.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class GovernanceMetric:
key: str
title: str
value: Any
status: str = "ok"
detail: str = ""
def to_dict(self) -> dict[str, Any]:
return asdict(self)
@dataclass(frozen=True)
class GovernancePanel:
key: str
title: str
metrics: list[GovernanceMetric] = field(default_factory=list)
def to_dict(self) -> dict[str, Any]:
return {
"key": self.key,
"title": self.title,
"metrics": [m.to_dict() for m in self.metrics],
}
class ChangeGovernanceDashboard:
def overview(self, changes: list[dict[str, Any]] | None = None) -> dict[str, Any]:
changes = changes or []
blocked = [c for c in changes if c.get("status") == "blocked"]
waiting_arch = [c for c in changes if c.get("architecture_review") == "required"]
waiting_user = [c for c in changes if c.get("user_acceptance") == "required"]
missing_tests = [c for c in changes if not c.get("tests")]
panels = [
GovernancePanel(
"test_gate",
"测试 Gate",
[
GovernanceMetric("total_changes", "变更总数", len(changes)),
GovernanceMetric("missing_tests", "缺少测试的变更", len(missing_tests), "warn" if missing_tests else "ok"),
],
),
GovernancePanel(
"user_acceptance",
"用户验收 Agent",
[
GovernanceMetric("waiting_user_acceptance", "等待用户验收", len(waiting_user), "warn" if waiting_user else "ok"),
],
),
GovernancePanel(
"architecture_review",
"架构师 Agent",
[
GovernanceMetric("waiting_architecture_review", "等待架构审查", len(waiting_arch), "warn" if waiting_arch else "ok"),
],
),
GovernancePanel(
"release_gate",
"发布 Gate",
[
GovernanceMetric("blocked_changes", "阻塞发布的变更", len(blocked), "warn" if blocked else "ok"),
],
),
]
return {
"module": "change-governance",
"route": "/admin/ai-evolution/governance",
"title": "AIOS 变更治理中心",
"status": "attention_required" if blocked or missing_tests or waiting_arch or waiting_user else "healthy",
"generated_at": utc_now(),
"panels": [p.to_dict() for p in panels],
"changes": changes,
}
__all__ = ["GovernanceMetric", "GovernancePanel", "ChangeGovernanceDashboard"]
+36
View File
@@ -0,0 +1,36 @@
"""Git repository location resolver with validation.
Prevents hard-coded repository names from silently pointing to stale paths.
"""
from __future__ import annotations
import os
from pathlib import Path
class GitRepoLocator:
def __init__(self, root: str | None = None):
self.root = Path(root or os.getenv("AIOS_GITOPS_ROOT", "/data/aios-gitops/runtime/gitea-bin/data/repositories"))
def candidates(self, owner: str = "aios", names: tuple[str, ...] = ("aios.git", "aios-v23.git")):
return [self.root / owner / name for name in names]
def locate(self, owner: str = "aios") -> dict:
found = [str(path) for path in self.candidates(owner) if path.exists()]
return {
"root": str(self.root),
"owner": owner,
"found": found,
"healthy": len(found) == 1,
"warning": "multiple repositories found" if len(found) > 1 else None,
}
def require(self, owner: str = "aios") -> Path:
result = self.locate(owner)
if not result["healthy"]:
raise RuntimeError(f"Git repo resolution failed: {result}")
return Path(result["found"][0])
__all__ = ["GitRepoLocator"]
@@ -0,0 +1,148 @@
"""Bridge governance agents into the unified Agent Event Bus.
This module emits normalized governance events for requirement changes,
architecture reviews, user acceptance, test gates and version decisions. It uses
duck typing so it can work with the unified AgentEventBus when available, while
remaining testable without a running bus.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any, Protocol
from uuid import uuid4
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
class EventPublisher(Protocol):
def publish(
self,
kind: str,
source: str,
target: str,
summary: str,
payload: dict[str, Any],
correlation_id: str | None = None,
) -> dict[str, Any]:
...
@dataclass(frozen=True)
class GovernanceEventEnvelope:
id: str
kind: str
source: str
target: str
summary: str
payload: dict[str, Any]
correlation_id: str | None = None
created_at: str = field(default_factory=utc_now)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
class InMemoryGovernanceEventBus:
"""Small fallback bus for tests and offline governance runs."""
def __init__(self) -> None:
self.events: list[dict[str, Any]] = []
def publish(
self,
kind: str,
source: str,
target: str,
summary: str,
payload: dict[str, Any],
correlation_id: str | None = None,
) -> dict[str, Any]:
event = GovernanceEventEnvelope(
id=f"evt_{uuid4().hex[:12]}",
kind=kind,
source=source,
target=target,
summary=summary,
payload=payload,
correlation_id=correlation_id,
).to_dict()
self.events.append(event)
return event
class GovernanceEventBridge:
"""Publishes governance lifecycle events to the Agent Event Bus."""
def __init__(self, bus: EventPublisher | None = None):
self.bus = bus or InMemoryGovernanceEventBus()
def requirement_changed(self, requirement: dict[str, Any]) -> dict[str, Any]:
return self.bus.publish(
kind="requirement_changed",
source=requirement.get("source", "unknown"),
target="architect-agent",
summary=requirement.get("requirement", "requirement changed"),
payload=requirement,
correlation_id=requirement.get("id"),
)
def architecture_review_started(self, proposal: dict[str, Any]) -> dict[str, Any]:
return self.bus.publish(
kind="architecture_review_started",
source="architect-agent",
target="architecture-review-agent",
summary=proposal.get("title", "architecture review started"),
payload=proposal,
correlation_id=proposal.get("change_id"),
)
def architecture_review_completed(self, decision: dict[str, Any]) -> dict[str, Any]:
return self.bus.publish(
kind="architecture_review_completed",
source="architecture-review-agent",
target="change-governance",
summary=f"architecture review {decision.get('status', 'completed')}",
payload=decision,
correlation_id=decision.get("change_id"),
)
def user_acceptance_completed(self, report: dict[str, Any]) -> dict[str, Any]:
return self.bus.publish(
kind="user_acceptance_completed",
source="user-acceptance-agent",
target="change-governance",
summary=f"user acceptance {report.get('decision', 'completed')}",
payload=report,
correlation_id=report.get("change_id"),
)
def test_gate_completed(self, result: dict[str, Any]) -> dict[str, Any]:
return self.bus.publish(
kind="test_gate_completed",
source="test-gate",
target="change-governance",
summary=f"test gate {result.get('status', 'completed')}",
payload=result,
correlation_id=result.get("change_id"),
)
def version_decision_created(self, decision: dict[str, Any]) -> dict[str, Any]:
return self.bus.publish(
kind="version_decision_created",
source="architect-agent",
target="owner-gate",
summary=f"version bump recommendation: {decision.get('version_bump', 'unknown')}",
payload=decision,
correlation_id=decision.get("change_id"),
)
__all__ = [
"GovernanceEventEnvelope",
"InMemoryGovernanceEventBus",
"GovernanceEventBridge",
]
@@ -0,0 +1,32 @@
"""API for governance timeline visualization."""
try:
from fastapi import APIRouter
except Exception:
APIRouter = None
from .governance_timeline_dashboard import GovernanceTimelineDashboard
dashboard = GovernanceTimelineDashboard()
def get_governance_timeline(events=None):
return dashboard.build(events)
def build_router():
if APIRouter is None:
return None
router = APIRouter(prefix="/admin/ai-evolution/governance", tags=["governance-timeline"])
@router.get("/timeline", operation_id="getGovernanceTimeline")
def timeline():
return get_governance_timeline()
return router
router = build_router()
__all__ = ["router", "get_governance_timeline"]
@@ -0,0 +1,106 @@
"""Governance timeline dashboard.
Turns governance events into a human-readable flow for Web UI so operators can
see why a change is blocked or ready for promotion.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
def utc_now() -> str:
return datetime.now(timezone.utc).isoformat()
EVENT_ORDER = {
"requirement_changed": 10,
"architecture_review_started": 20,
"architecture_review_completed": 30,
"test_gate_completed": 40,
"user_acceptance_completed": 50,
"version_decision_created": 60,
"owner_gate_completed": 70,
"promotion_completed": 80,
}
@dataclass(frozen=True)
class GovernanceTimelineStep:
id: str
kind: str
title: str
actor: str
status: str
timestamp: str
correlation_id: str | None = None
detail: dict[str, Any] = field(default_factory=dict)
def to_dict(self) -> dict[str, Any]:
return asdict(self)
class GovernanceTimelineDashboard:
def build(self, events: list[dict[str, Any]] | None = None) -> dict[str, Any]:
events = events or []
steps = [self._event_to_step(event) for event in events]
steps.sort(key=lambda step: (EVENT_ORDER.get(step.kind, 999), step.timestamp))
blockers = [step for step in steps if step.status in {"blocked", "fail", "attention_required"}]
return {
"module": "governance-timeline",
"route": "/admin/ai-evolution/governance/timeline",
"title": "治理事件时间线",
"status": "attention_required" if blockers else "healthy",
"generated_at": utc_now(),
"steps": [step.to_dict() for step in steps],
"blockers": [step.to_dict() for step in blockers],
"flow": self._flow_summary(steps),
}
def _event_to_step(self, event: dict[str, Any]) -> GovernanceTimelineStep:
payload = event.get("payload", {})
kind = event.get("kind", "unknown")
return GovernanceTimelineStep(
id=event.get("id", f"event-{len(str(event))}"),
kind=kind,
title=self._title(kind, payload),
actor=event.get("source", payload.get("actor", "unknown")),
status=payload.get("status") or payload.get("decision") or event.get("status", "ok"),
timestamp=event.get("created_at") or payload.get("created_at") or utc_now(),
correlation_id=event.get("correlation_id") or payload.get("change_id") or payload.get("id"),
detail=payload,
)
def _title(self, kind: str, payload: dict[str, Any]) -> str:
titles = {
"requirement_changed": "需求变化",
"architecture_review_started": "架构审查开始",
"architecture_review_completed": "架构审查完成",
"test_gate_completed": "测试 Gate 完成",
"user_acceptance_completed": "用户验收完成",
"version_decision_created": "版本建议产生",
"owner_gate_completed": "Owner Gate 完成",
"promotion_completed": "Promotion 完成",
}
return payload.get("title") or payload.get("summary") or titles.get(kind, kind)
def _flow_summary(self, steps: list[GovernanceTimelineStep]) -> dict[str, Any]:
present = {step.kind for step in steps}
required = [
"requirement_changed",
"architecture_review_completed",
"test_gate_completed",
"user_acceptance_completed",
"version_decision_created",
]
missing = [kind for kind in required if kind not in present]
return {
"required_steps": required,
"missing_steps": missing,
"ready_for_owner_gate": not missing,
}
__all__ = ["GovernanceTimelineStep", "GovernanceTimelineDashboard"]
@@ -0,0 +1,59 @@
"""Independent acceptance agents.
Simulates independent roles: user representative and architecture reviewer.
They provide acceptance evidence, not implementation decisions.
"""
from dataclasses import dataclass, asdict
from datetime import datetime, timezone
from typing import Any
def utc_now():
return datetime.now(timezone.utc).isoformat()
@dataclass(frozen=True)
class AcceptanceReport:
agent: str
role: str
decision: str
evidence: list[str]
created_at: str = utc_now()
def to_dict(self):
return asdict(self)
class UserAcceptanceAgent:
def review(self, change: dict[str, Any]) -> AcceptanceReport:
checks = [
"user_requirement_match",
"user_workflow_validation",
"permission_visibility_check",
]
return AcceptanceReport(
"user-acceptance-agent",
"user_representative",
"pass" if change.get("user_facing") else "not_required",
checks,
)
class ArchitectureAcceptanceAgent:
def review(self, change: dict[str, Any]) -> AcceptanceReport:
checks = [
"architecture_consistency",
"scalability_review",
"security_boundary_review",
"operability_review",
]
return AcceptanceReport(
"architecture-review-agent",
"system_architect",
"pass" if change.get("architecture_impact") else "not_required",
checks,
)
__all__ = ["AcceptanceReport", "UserAcceptanceAgent", "ArchitectureAcceptanceAgent"]
@@ -58,6 +58,8 @@ pre { white-space: pre-wrap; word-break: break-word; }
<li onclick="showPanel('versions')"><i>🏷️</i> Versions</li>
<li onclick="showPanel('commands')"><i>⚡</i> Commands</li>
<li onclick="showPanel('agents')"><i>🤖</i> Agent Runs</li>
<li onclick="showPanel('arch-owner')"><i>🔐</i> Owner Gate</li>
<li onclick="showPanel('arch-approve')"><i>✓</i> Approve Changes</li>
</ul>
</div>
<div class="main">
@@ -90,6 +92,14 @@ pre { white-space: pre-wrap; word-break: break-word; }
</div>
<div id="panel-agents" class="panel" style="display:none;">
<div class="main-header"><h2>Recent Agent Executions</h2></div>
<div id="panel-arch-owner" class="panel" style="display:none;">
<div class="main-header"><h2>🔐 Architecture Owner Gate</h2></div>
<div id="arch-owner-content">Loading...</div>
</div>
<div id="panel-arch-approve" class="panel" style="display:none;">
<div class="main-header"><h2>✓ Approve Architecture Changes</h2></div>
<div id="arch-approve-content">Loading...</div>
</div>
<div id="agents-list">Loading...</div>
</div>
</div>
@@ -97,3 +107,159 @@ pre { white-space: pre-wrap; word-break: break-word; }
<script>
async function fetchData() {
const r = await fetch('/admin/ai-evolution/api/data');
const data = await r.json();
document.getElementById('loading').style.display = 'none';
document.getElementById('error').style.display = 'none';
document.getElementById('content').style.display = '';
const hs = document.getElementById('header-status');
hs.className = 'status-badge ' + (data.healthy ? 'ok' : 'fail');
hs.textContent = data.healthy ? '▪ operational' : '⚠ degraded';
document.getElementById('base').textContent = data.baseline || '-';
document.getElementById('branch').textContent = data.main_branch || 'main';
document.getElementById('uptime').textContent = data.uptime || '-';
document.getElementById('bus-status').textContent = data.bus ? JSON.stringify(data.bus, null, 2) : 'no event bus data';
}
async function loadVersions() {
const el = document.getElementById('versions-list');
el.innerHTML = '<div class="loading">Loading versions...</div>';
try {
const r = await fetch('/admin/ai-evolution/api/versions');
const data = await r.json();
if (data.error) { el.innerHTML = '<div class="error">' + data.error + '</div>'; return; }
let html = '<div class="grid">';
for (const v of data.versions || []) {
html += '<div class="card"><div class="card-title">' + v.tag + '</div><div class="card-value">' + (v.version || v.tag) + '</div></div>';
}
html += '</div>';
el.innerHTML = html;
} catch(e) {
el.innerHTML = '<div class="error">Failed to load versions: ' + e.message + '</div>';
}
}
async function loadCommands() {
const el = document.getElementById('commands-list');
el.innerHTML = '<div class="loading">Loading commands...</div>';
try {
const r = await fetch('/admin/ai-evolution/api/data');
const data = await r.json();
let cmds = data.commands || [];
let html = '<div style="display:flex;gap:24px;margin-bottom:16px;">';
html += '<div><div class="card"><div class="card-title">Total</div><div class="card-value">' + cmds.length + '</div></div></div>';
html += '<div><div class="card"><div class="card-title">By Category</div>';
const cats = {};
for (const c of cmds) { const k = c.category || 'uncategorized'; cats[k] = (cats[k] || 0) + 1; }
for (const [k, v] of Object.entries(cats)) html += '<div style="font-size:14px;color:#8b949e;margin:4px 0;">' + k + ': ' + v + '</div>';
html += '</div></div></div>';
for (const cmd of cmds.slice().reverse()) {
html += '<div class="command-item"><div class="meta">' + cmd.category + ' | ' + cmd.filename + '</div><div class="name">' + cmd.title + '</div><div style="font-size:13px;color:#c9d1d9;margin-top:4px;">' + cmd.summary + '</div></div>';
}
el.innerHTML = html;
} catch(e) {
el.innerHTML = '<div class="error">Failed to load commands: ' + e.message + '</div>';
}
}
async function loadAgents() {
const el = document.getElementById('agents-list');
el.innerHTML = '<div class="loading">Loading agent runs...</div>';
try {
const r = await fetch('/admin/ai-evolution/api/agents');
const data = await r.json();
if (data.error) { el.innerHTML = '<div class="error">' + data.error + '</div>'; return; }
let html = '';
for (const agent of data.agents || []) {
html += '<div class="agent-item"><div class="agent-title">' + agent.name + ' <span class="state state-' + (agent.status === 'running' ? 'running' : (agent.status === 'ok' ? 'completed' : 'failed')) + '">' + agent.status + '</span></div><div class="agent-meta">' + (agent.runs || 0) + ' runs | last: ' + (agent.last_run || '-') + '</div></div>';
}
el.innerHTML = html || '<div style="padding:24px;color:#8b949e;">No agent runs recorded yet.</div>';
} catch(e) {
el.innerHTML = '<div class="error">Failed to load agents: ' + e.message + '</div>';
}
}
function showPanel(name) {
async function loadOwnerGate() {
const el = document.getElementById('arch-owner-content');
el.innerHTML = '<div class="loading">Loading owner gate data...</div>';
try {
const r = await fetch('/admin/ai-evolution/api/owner-gate');
const data = await r.json();
let html = '<div class="row">';
html += '<div class="col"><div class="card"><div class="card-title">Pending Requests</div><div class="card-value">' + data.pending_count + '</div></div></div>';
html += '<div class="col"><div class="card"><div class="card-title">Approved</div><div class="card-value">' + data.approved_count + '</div></div></div>';
html += '<div class="col"><div class="card"><div class="card-title">Rejected</div><div class="card-value">' + data.rejected_count + '</div></div></div>';
html += '</div>';
html += '<div class="card"><div class="card-title">Pending Approval Requests</div>';
if (data.pending_requests && data.pending_requests.length) {
for (const req of data.pending_requests) {
html += '<div class="command-item">';
html += '<div class="name">' + (req.title || req.change_id) + '</div>';
html += '<div class="meta">ID: ' + req.change_id + ' | Risk: ' + req.risk + '</div>';
html += '<div style="font-size:13px;color:#c9d1d9;margin-top:4px;">' + (req.reason || '') + '</div>';
html += '</div>';
}
} else {
html += '<div style="color:#8b949e;padding:12px;">No pending requests.</div>';
}
html += '</div>';
el.innerHTML = html;
} catch(e) {
el.innerHTML = '<div class="error">Failed to load: ' + e.message + '</div>';
}
}
async function loadApprove() {
const el = document.getElementById('arch-approve-content');
el.innerHTML = '<div class="loading">Loading pending approvals...</div>';
try {
const r = await fetch('/admin/ai-evolution/api/owner-gate');
const data = await r.json();
let html = '';
if (data.pending_requests && data.pending_requests.length) {
html += '<div class="card"><div class="card-title">Pending changes requiring your approval</div>';
for (const req of data.pending_requests) {
html += '<div class="command-item">';
html += '<div class="name">' + (req.title || req.change_id) + '</div>';
html += '<div class="meta">Risk: <strong>' + req.risk + '</strong></div>';
html += '<div style="font-size:13px;color:#c9d1d9;margin:8px 0;">' + (req.reason || '') + '</div>';
html += '<div style="display:flex;gap:8px;">';
html += '<button onclick="ownerAction.classList.add('\'approved\');this.disabled=true" style="padding:6px 16px;background:#238636;color:#fff;border:none;border-radius:6px;cursor:pointer;font-size:13px;">✓ Approve</button>';
html += '</div></div>';
}
html += '</div>';
} else {
html += '<div class="card"><div style="padding:24px;text-align:center;color:#8b949e;">✅ All changes processed. No pending approval requests.</div></div>';
}
el.innerHTML = html;
} catch(e) {
el.innerHTML = '<div class="error">Failed to load: ' + e.message + '</div>';
}
}
document.querySelectorAll('.panel').forEach(p => p.style.display = 'none');
document.getElementById('panel-' + name).style.display = '';
document.querySelectorAll('.sidebar-nav li').forEach(li => li.classList.remove('active'));
document.querySelector('.sidebar-nav li:nth-child(' + ({overview:1,versions:2,commands:3,agents:4}[name] || 1) + ')').classList.add('active');
if (name === 'overview') {
document.getElementById('panel-overview').innerHTML = '<div class="main-header"><h2>System Overview</h2><div id="header-status" class="status-badge">Loading...</div></div><div id="loading" class="loading">Loading...</div><div id="error" class="error" style="display:none;"></div><div id="content"><div class="row"><div class="col"><div class="card"><div class="card-title">Current Baseline</div><div id="base" class="card-value">-</div></div></div><div class="col"><div class="card"><div class="card-title">Git Branch</div><div id="branch" class="card-value">-</div></div></div><div class="col"><div class="card"><div class="card-title">Uptime</div><div id="uptime" class="card-value">-</div></div></div></div><div class="card" style="margin-top:16px"><div class="card-title">Event Bus Status</div><pre id="bus-status">-</pre></div></div>';
fetchData();
}
const loaders = {
'arch-owner': loadOwnerGate,
'arch-approve': loadApprove,
versions: loadVersions,
commands: loadCommands,
agents: loadAgents,
};
const fn = loaders[name];
if (fn) fn();
}
fetchData();
</script>
</body>
</html>
@@ -0,0 +1,36 @@
# CMD-20260708-fix-git-actions-write-and-enable-audit-plane
## Command ID
CMD-20260708-fix-git-actions-write-and-enable-audit-plane
## Priority
P0
## Mode
autonomous
## Target
Primary: OpenClaw
Supporting: Hermes
Review: Codex
## Objective
解决当前 AIOS Git Actions 写权限问题,恢复 ChatGPT Actions → AIOS GitOps API → Git Commit 链路,
同时建立 Agent 全生命周期审计体系。
## Status
- Part 1 (Fix Git Actions Write Permission): ✅ COMPLETE
- Part 2 (Agent Command Plane Structure): ✅ COMPLETE
- Part 3 (Agent Execution Audit): ✅ COMPLETE
- Part 4 (Conversation Trace): 🚧 IN PROGRESS
- Part 5 (Version Association): ⏳ PENDING
- Part 6 (Web UI Integration): ⏳ PENDING
- Part 7 (Evidence): ⏳ PENDING
- Part 8 (Regression Test): ⏳ PENDING
## Completion Criteria
1. Code committed: agents/, audit/, evidence/, web-ui/
2. Doc: docs/architecture/AIOS_AGENT_AUDIT_PLANE.md
3. Report: evidence/CMD-20260708.../final-report.md
4. Output: AIOS_AGENT_AUDIT_PLANE_READY, AIOS_GIT_ACTION_WRITE_READY
5. Next command created: CMD-20260709-autonomous-controller-enable
@@ -0,0 +1,35 @@
# CMD-20260709-enable-autonomous-controller
## Command ID
CMD-20260709-enable-autonomous-controller
## Priority
P0
## Mode
autonomous
## Target
Primary: OpenClaw
Supporting: Hermes
Review: Codex
## Objective
Enable autonomous controller for AIOS GitOps:
- Auto-detect issues
- Auto-diagnose
- Auto-generate fixes
- Auto-test
- Auto-create patches
- Auto-request approval
## Preconditions
- Agent Command Plane initialized (CMD-BOOTSTRAP-001)
- Git Actions write permission fixed (CMD-20260708)
- Audit plane enabled (CMD-20260708)
- Notification service enabled (CMD-20260708)
## Completion Criteria
- Autonomous controller service running
- Can detect, diagnose, fix, and report
- Pipeline: detect → diagnose → fix → test → patch → approve → commit → notify
@@ -0,0 +1,7 @@
{
"nid": "n-1783527185",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T00:13:05+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783529900",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T00:58:20+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783529914",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T00:58:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783530514",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T01:08:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783531114",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T01:18:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783531714",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T01:28:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783532314",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T01:38:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783532914",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T01:48:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783533514",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T01:58:34+0800"
}
@@ -0,0 +1,7 @@
{
"nid": "n-1783534114",
"title": "⚠️ Issue Detected: branch_sync",
"body": "10 branches missing from Gitea DB",
"urgency": "warning",
"ts": "2026-07-09T02:08:34+0800"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783527185",
"created": "2026-07-09T00:13:05+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/agent-event-bus-unified",
"test/alias-write-verify",
"patch/V1R2C3-tag-execute-idempotent-permission",
"patch/gitops-write-auth-smoke-20260706T115230Z",
"patch/gpt-actions-auth-live-20260708"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783529900",
"created": "2026-07-09T00:58:20+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"test/alias-test-file-branch",
"patch/codex-online-sync-acceptance-20260706T102819Z",
"patch/V1R2C3-tag-execute-idempotent-permission",
"patch/actions-invalid-diag-smoke-20260706T140311Z",
"patch/V1R2C2-autonomous-recovery-loop"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783529914",
"created": "2026-07-09T00:58:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783530514",
"created": "2026-07-09T01:08:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783531114",
"created": "2026-07-09T01:18:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783531714",
"created": "2026-07-09T01:28:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783532314",
"created": "2026-07-09T01:38:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783532914",
"created": "2026-07-09T01:48:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783533514",
"created": "2026-07-09T01:58:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,16 @@
{
"patch_id": "patch-1783534114",
"created": "2026-07-09T02:08:34+0800",
"check": "branch_sync",
"severity": "high",
"diagnosis": "10 branches missing from Gitea DB",
"branches": [
"patch/codex-write-auth-smoke-20260706T115256Z",
"patch/v1r3c0-user-portal-rbac-ops-20260708",
"request/tag-V1R3C0-self-loop-autonomous-engine",
"patch/fix-tag-confirmation-state-machine",
"patch/gitops-write-auth-fix"
],
"stuck": [],
"fix": "sync_branches"
}
@@ -0,0 +1,12 @@
{
"ts": "2026-07-09T02:08:34+0800",
"ok": false,
"checks": {
"gitea": false,
"api": true,
"branch_sync": false,
"stuck": true
},
"plans": 1,
"applied": 0
}
+11
View File
@@ -0,0 +1,11 @@
{
"ts": "2026-07-09T00:00:00+09:00",
"ok": true,
"checks": {
"git_object_permission": true,
"api": true,
"branch_sync": true,
"stale_runtime_state_cleaned": true
},
"note": "Updated during PR #2 cleanup before merge"
}
@@ -0,0 +1,21 @@
{
"ts": "2026-07-09T00:59:30+0800",
"action": "command_watcher_state_clean",
"description": "清除了 command watcher 目录中的 stale 重复副本",
"result": "clean",
"stale_removed": [
{
"name": "CMD-20260708-fix-git-actions-write-and-enable-audit-plane.md",
"removed_from": ["active/", "running/"],
"preserved_in": "completed/",
"archive_path": "agents/commands/archive/"
},
{
"name": "CMD-20260709-enable-autonomous-controller.md",
"removed_from": ["running/"],
"preserved_in": "active/",
"archive_path": "agents/commands/archive/"
}
],
"note": "已完成命令保留在 completed/,副本移动到 archive/;未完成命令仅保留 active/"
}
@@ -0,0 +1,17 @@
{
"ts": "2026-07-09T01:00:00+0800",
"action": "daily_wechat_cron_verification",
"description": "验证每日 08:00 WeChat 汇报 cron 配置并手动触发 dry-run",
"cron_name": "AIOS每日自治报告",
"cron_id": "987f8619-6ccc-4370-8720-87149479a222",
"schedule": "0 8 * * * Asia/Shanghai",
"delivery": {
"mode": "announce",
"channel": "openclaw-weixin",
"to": "o9cq80wSaJq6utQBkUC4fE1sJWxY@im.wechat",
"accountId": "ed3da13663c0-im-bot"
},
"dry_run_triggered": true,
"dry_run_result": "enqueued",
"status": "verified"
}
+19
View File
@@ -0,0 +1,19 @@
{
"run_id": "c-1783527185",
"check": "stuck",
"status": "degraded",
"ts": "2026-07-09T00:13:05+0800",
"details": {
"ok": false,
"stuck": [
{
"n": "CMD-20260709-enable-autonomous-controller.md",
"age": 184.6
},
{
"n": "CMD-20260708-fix-git-actions-write-and-enable-audit-plane.md",
"age": 185.8
}
]
}
}
+19
View File
@@ -0,0 +1,19 @@
{
"run_id": "c-1783529900",
"check": "stuck",
"status": "degraded",
"ts": "2026-07-09T00:58:20+0800",
"details": {
"ok": false,
"stuck": [
{
"n": "CMD-20260709-enable-autonomous-controller.md",
"age": 229.8
},
{
"n": "CMD-20260708-fix-git-actions-write-and-enable-audit-plane.md",
"age": 231.0
}
]
}
}
+19
View File
@@ -0,0 +1,19 @@
{
"run_id": "c-1783529914",
"check": "stuck",
"status": "degraded",
"ts": "2026-07-09T00:58:34+0800",
"details": {
"ok": false,
"stuck": [
{
"n": "CMD-20260709-enable-autonomous-controller.md",
"age": 230.1
},
{
"n": "CMD-20260708-fix-git-actions-write-and-enable-audit-plane.md",
"age": 231.3
}
]
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783530514",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T01:08:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783531114",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T01:18:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783531714",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T01:28:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783532314",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T01:38:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783532914",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T01:48:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783533514",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T01:58:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+10
View File
@@ -0,0 +1,10 @@
{
"run_id": "c-1783534114",
"check": "stuck",
"status": "ok",
"ts": "2026-07-09T02:08:34+0800",
"details": {
"ok": true,
"stuck": []
}
}
+13 -1
View File
@@ -1 +1,13 @@
{"current_baseline":"V1R3C1","promoted_at":"2026-07-08T14:31:00+08:00","previous_baseline":"V1R2C3"}
{
"current_baseline": "V1R4C6",
"previous_baseline": "V1R4C5",
"promoted_at": "2026-07-11T21:00:00+08:00",
"git": "e204a90398bf646d46245b3088226749fa056edd",
"promoted_by": "openclaw/admin",
"promotion_reason": "V1R4C6 admin search agent integration, search gateway, agent platform, VERSION bump, merge tests deploy pipeline — not yet deployed to production",
"constraints": {
"memory_search_enabled": false,
"force_push_allowed": false,
"gitea_db_mutation_requires_owner_approval": true
}
}
@@ -0,0 +1,33 @@
architect_agent_governance:
enabled: true
responsibilities:
requirement_change_tracking: true
requirement_document_refresh: true
architecture_document_refresh: true
deployment_document_validation: true
test_case_document_generation: true
architecture_optimization_review: true
weekly_external_research: true
github_top_implementation_review: true
sources:
requirement_sources:
- custom_gpt
- codex
- openclaw
- hermes
- user_feedback
version_decision:
criteria:
C: bug_fix_or_small_compatible_change
R: architecture_or_capability_release
V: major_architecture_or_breaking_change
research_cycle:
frequency: weekly
targets:
- agent_framework_versions
- model_versions
- github_top_implementations
- security_changes
governance:
owner_gate_required: true
audit_required: true
+22
View File
@@ -0,0 +1,22 @@
architect_research:
enabled: true
schedule:
frequency: weekly
research_sources:
- agent_framework_releases
- model_ecosystem_updates
- github_top_implementations
- security_advisories
evaluation:
required:
- relevance
- architecture_impact
- security_impact
- migration_cost
output:
- optimization_recommendation
- version_recommendation
- architecture_review_event
governance:
owner_gate_required: true
audit_required: true
@@ -0,0 +1,36 @@
architecture_owner_gate:
enabled: true
principle: owner_approves_large_architecture_changes_only
classification:
small:
owner_required: false
architect_auto_implementation: true
requirements:
- architect_review
- test_gate
- audit
medium:
owner_required: false
architect_review_required: true
implementation_after_review: true
requirements:
- architect_review
- test_gate
- audit
large:
owner_required: true
architect_auto_implementation: false
requirements:
- architect_review
- owner_architecture_approval
- test_gate
- promotion_gate
mandatory_owner_cases:
- breaking_change
- V_version_change
- production_architecture_update
- security_boundary_change
- cross_tenant_change
- permission_model_change
audit:
required: true
+18
View File
@@ -0,0 +1,18 @@
change_governance:
enabled: true
feature_change:
require_tests: true
require_user_acceptance_if_user_facing: true
architecture_change:
require_architecture_review_agent: true
require_system_optimization_review: true
acceptance_agents:
user_agent: user-acceptance-agent
architect_agent: architecture-review-agent
merge_gate:
required:
- tests_passed
- acceptance_passed
- architecture_review_passed
audit:
enabled: true
+22
View File
@@ -0,0 +1,22 @@
governance_event_bus:
enabled: true
event_types:
- requirement_changed
- architecture_review_started
- architecture_review_completed
- user_acceptance_completed
- test_gate_completed
- version_decision_created
producers:
- architect-agent
- user-acceptance-agent
- test-gate-agent
- change-governance-agent
consumers:
- web-ui
- audit-plane
- owner-gate
- reporting-agent
audit:
required: true
retention: versioned
+21
View File
@@ -0,0 +1,21 @@
models:
default:
- id: gpt-5.5
provider: openai
enabled: true
fallback: false
- id: qwen-3.6-35b
provider: qwen
enabled: true
fallback: true
- id: deepseek-v4-flash
provider: deepseek
enabled: true
fallback: true
runtime_behavior:
unavailable_model:
action: warn_and_fallback
hardcoded_model_list: false
health_check_required: true
audit_model_selection: true
+23
View File
@@ -0,0 +1,23 @@
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
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: ${AIOS_OPENCLAW_SIGNING_MATERIAL_FILE:-}
AIOS_RELEASE_CHANNEL: candidate
AIOS_RELEASE_VERSION: V2R1C0-candidate
volumes:
- aios-v2-state:/var/lib/aios-v2
# Mount runtime signing material explicitly when OpenClaw is enabled.
# The host file must be mode 0600; never store it in this repository.
# - /etc/aios-v2/openclaw-signing-material:/run/secrets/openclaw-signing-material:ro
read_only: true
tmpfs:
- /tmp:rw,noexec,nosuid,nodev,size=64m
cap_drop:
- ALL
security_opt:
- no-new-privileges:true
healthcheck:
test:
- CMD
- python3
- -c
- "import urllib.request; urllib.request.urlopen('http://127.0.0.1:18920/api/v2/health', timeout=3).read()"
interval: 15s
timeout: 5s
retries: 4
start_period: 10s
volumes:
aios-v2-state:
+21
View File
@@ -0,0 +1,21 @@
# AIOS V2 candidate runtime configuration.
# Copy to /etc/aios-v2/aios-v2.env and keep ownership root:aios, mode 0640.
AIOS_V2_HOST=127.0.0.1
AIOS_V2_PORT=18920
AIOS_V2_STATE_DIR=/var/lib/aios-v2
# Optional OpenClaw runtime. Leave blank to run with OpenClaw disabled.
AIOS_OPENCLAW_URL=
AIOS_OPENCLAW_CREDENTIAL_REF=
# File path only. The referenced file must be mode 0600 or stricter and contain
# at least 32 bytes. Never place signing material in this env file or Git.
AIOS_OPENCLAW_SIGNING_MATERIAL_FILE=
# Reverse proxy must authenticate users and inject X-AIOS-* identity headers.
AIOS_TRUST_PROXY_HEADERS=true
# Candidate deployment metadata exposed through health tooling.
AIOS_RELEASE_CHANNEL=candidate
AIOS_RELEASE_VERSION=V2R1C0-candidate
+86
View File
@@ -0,0 +1,86 @@
#!/usr/bin/env bash
set -Eeuo pipefail
BASE_URL="${AIOS_V2_BASE_URL:-http://127.0.0.1:18920}"
STATE_DIR="${AIOS_V2_STATE_DIR:-/var/lib/aios-v2}"
CONTROLLER_WT="${AIOS_GITOPS_CONTROLLER_WORKTREE:-/data/aios-gitops/worktrees/controller}"
SERVICE="${AIOS_V2_SERVICE:-aios-v2}"
fail() {
echo "FAIL: $*" >&2
exit 1
}
pass() {
echo "PASS: $*"
}
command -v python3 >/dev/null || fail "python3 not installed"
if command -v systemctl >/dev/null && systemctl list-unit-files "$SERVICE.service" >/dev/null 2>&1; then
systemctl is-active --quiet "$SERVICE" || fail "$SERVICE is not active"
pass "$SERVICE is active"
fi
python3 - "$BASE_URL" <<'PY'
import json
import sys
import urllib.request
base_url = sys.argv[1].rstrip("/")
with urllib.request.urlopen(f"{base_url}/api/v2/health", timeout=5) as response:
payload = json.loads(response.read().decode("utf-8"))
if payload.get("status") not in {"ok", "healthy", "ready"}:
raise SystemExit(f"unexpected health payload: {payload}")
print(f"PASS: HTTP health status={payload.get('status')}")
PY
[[ -d "$STATE_DIR" ]] || fail "state directory missing: $STATE_DIR"
[[ -w "$STATE_DIR" ]] || fail "state directory not writable: $STATE_DIR"
pass "state directory writable"
if [[ -e "$STATE_DIR/control-plane.sqlite3" ]]; then
python3 - "$STATE_DIR/control-plane.sqlite3" <<'PY'
import sqlite3
import sys
path = sys.argv[1]
connection = sqlite3.connect(f"file:{path}?mode=ro", uri=True, timeout=5)
try:
row = connection.execute("PRAGMA quick_check").fetchone()
finally:
connection.close()
if not row or row[0] != "ok":
raise SystemExit(f"SQLite quick_check failed: {row}")
print("PASS: SQLite quick_check=ok")
PY
else
echo "WARN: control-plane.sqlite3 not created yet"
fi
if [[ -d "$CONTROLLER_WT" ]] && git -C "$CONTROLLER_WT" rev-parse --is-inside-work-tree >/dev/null 2>&1; then
branch="$(git -C "$CONTROLLER_WT" branch --show-current)"
dirty="$(git -C "$CONTROLLER_WT" status --porcelain=v1)"
[[ -z "$branch" ]] || fail "GitOps controller attached to branch: $branch"
[[ -z "$dirty" ]] || fail "GitOps controller workspace is dirty"
pass "GitOps controller detached and clean"
fi
python3 - "$STATE_DIR/executions" <<'PY'
import json
import pathlib
import sys
root = pathlib.Path(sys.argv[1])
if not root.exists():
print("WARN: execution evidence directory not created yet")
raise SystemExit(0)
for path in root.glob("*/*.json"):
value = json.loads(path.read_text(encoding="utf-8"))
for key in ("execution_id", "tenant_id", "task_id", "executor", "status"):
if not value.get(key):
raise SystemExit(f"invalid execution evidence {path}: missing {key}")
print("PASS: execution evidence files valid")
PY
pass "AIOS V2 candidate healthcheck complete"
+86
View File
@@ -0,0 +1,86 @@
#!/usr/bin/env bash
set -Eeuo pipefail
SERVICE="${AIOS_V2_SERVICE:-aios-v2}"
RELEASE_ROOT="${AIOS_V2_RELEASE_ROOT:-/opt/aios/releases}"
CURRENT_LINK="${AIOS_V2_CURRENT_LINK:-/opt/aios/current}"
STATE_DIR="${AIOS_V2_STATE_DIR:-/var/lib/aios-v2}"
BACKUP_ROOT="${AIOS_V2_BACKUP_ROOT:-/var/backups/aios-v2}"
TARGET_RELEASE="${1:-}"
RESTORE_STATE="${AIOS_V2_RESTORE_STATE:-0}"
fail() {
echo "ERROR: $*" >&2
exit 1
}
[[ "${EUID}" -eq 0 ]] || fail "rollback must run as root"
[[ -n "$TARGET_RELEASE" ]] || fail "usage: $0 <release-name-or-absolute-path>"
if [[ "$TARGET_RELEASE" = /* ]]; then
TARGET_PATH="$(readlink -f "$TARGET_RELEASE")"
else
[[ "$TARGET_RELEASE" != *"/"* && "$TARGET_RELEASE" != "." && "$TARGET_RELEASE" != ".." ]] \
|| fail "invalid release name"
TARGET_PATH="$(readlink -f "$RELEASE_ROOT/$TARGET_RELEASE")"
fi
[[ -d "$TARGET_PATH/active-runtime/app" ]] || fail "target release is invalid: $TARGET_PATH"
[[ -f "$TARGET_PATH/deploy/aios-v2/healthcheck/check.sh" ]] \
|| fail "target release has no healthcheck"
PREVIOUS_PATH=""
if [[ -L "$CURRENT_LINK" ]]; then
PREVIOUS_PATH="$(readlink -f "$CURRENT_LINK")"
fi
STAMP="$(date -u +%Y%m%dT%H%M%SZ)"
BACKUP_DIR="$BACKUP_ROOT/rollback-$STAMP"
install -d -m 0750 "$BACKUP_DIR"
if [[ -d "$STATE_DIR" ]]; then
tar --xattrs --acls -C "$(dirname "$STATE_DIR")" \
-czf "$BACKUP_DIR/state-before-rollback.tar.gz" \
"$(basename "$STATE_DIR")"
fi
printf '%s\n' "$PREVIOUS_PATH" > "$BACKUP_DIR/previous-release.txt"
printf '%s\n' "$TARGET_PATH" > "$BACKUP_DIR/target-release.txt"
systemctl stop "$SERVICE"
ln -sfn "$TARGET_PATH" "${CURRENT_LINK}.next"
mv -Tf "${CURRENT_LINK}.next" "$CURRENT_LINK"
systemctl daemon-reload
systemctl start "$SERVICE"
if AIOS_V2_SERVICE="$SERVICE" \
AIOS_V2_STATE_DIR="$STATE_DIR" \
"$TARGET_PATH/deploy/aios-v2/healthcheck/check.sh"; then
echo "ROLLBACK_COMPLETE target=$TARGET_PATH backup=$BACKUP_DIR"
exit 0
fi
echo "Target release failed healthcheck; restoring previous release." >&2
systemctl stop "$SERVICE" || true
if [[ -n "$PREVIOUS_PATH" && -d "$PREVIOUS_PATH" ]]; then
ln -sfn "$PREVIOUS_PATH" "${CURRENT_LINK}.previous"
mv -Tf "${CURRENT_LINK}.previous" "$CURRENT_LINK"
fi
if [[ "$RESTORE_STATE" == "1" && -f "$BACKUP_DIR/state-before-rollback.tar.gz" ]]; then
rm -rf "$STATE_DIR"
tar --xattrs --acls -C "$(dirname "$STATE_DIR")" \
-xzf "$BACKUP_DIR/state-before-rollback.tar.gz"
fi
systemctl daemon-reload
systemctl start "$SERVICE" || true
if [[ -n "$PREVIOUS_PATH" && -x "$PREVIOUS_PATH/deploy/aios-v2/healthcheck/check.sh" ]]; then
AIOS_V2_SERVICE="$SERVICE" \
AIOS_V2_STATE_DIR="$STATE_DIR" \
"$PREVIOUS_PATH/deploy/aios-v2/healthcheck/check.sh" || true
fi
fail "rollback target failed; previous release restored; evidence=$BACKUP_DIR"

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