Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a90023e8d1 | ||
|
|
db72e3184f | ||
|
|
4487a774fd | ||
|
|
a8e7a97f2d | ||
|
|
2f1d63c147 | ||
|
|
662ccf36f8 | ||
|
|
102d2306f0 | ||
|
|
28eca15d75 | ||
|
|
fb739f6e8f | ||
|
|
e6da39a3cd | ||
|
|
95d2e52cb5 | ||
|
|
283dec58ab | ||
|
|
7de1fe80ac | ||
|
|
89a502b39b | ||
|
|
61bec280e2 | ||
|
|
1791c91c5b | ||
|
|
e8c0f0250b | ||
|
|
94718308fc | ||
|
|
a4cbed0f5f | ||
|
|
25c7740739 | ||
|
|
8bbb049c39 | ||
|
|
1707cc4953 | ||
|
|
e397594200 | ||
|
|
68b7f2c1d2 | ||
|
|
fda98e61f5 | ||
|
|
ea9f599522 | ||
|
|
1aabcd8b62 | ||
|
|
4d68af9524 | ||
|
|
467b127804 | ||
|
|
50a73b211b | ||
|
|
f14d4b6e14 | ||
|
|
fc8bd8c8d4 | ||
|
|
382fe662a3 | ||
|
|
4754e5762a | ||
|
|
ce7d35a811 | ||
|
|
60ac7d9d0b | ||
|
|
2a10d1cdd9 | ||
|
|
677ea738e7 | ||
|
|
7154d62cca | ||
|
|
4e154c8baf | ||
|
|
b848361079 | ||
|
|
74224cfbd5 | ||
|
|
a7c09ba646 | ||
|
|
f055cb74bb | ||
|
|
071a378de6 | ||
|
|
a492b15df6 | ||
|
|
a9f0a4359b | ||
|
|
6a9fab894a | ||
|
|
e9111dea47 | ||
|
|
d25fbfa61e | ||
|
|
6b03c47625 | ||
|
|
770fe1ef66 | ||
|
|
7a025430f9 | ||
|
|
d079da4029 | ||
|
|
b8f7dc4112 | ||
|
|
947cdaff42 | ||
|
|
83b0c8bd74 | ||
|
|
fbd880cf8c | ||
|
|
819ac94c9f | ||
|
|
b02401e60d | ||
|
|
cbb2e232f5 | ||
|
|
9e46ac0504 | ||
|
|
ba7669c3b4 | ||
|
|
634f6b164f | ||
|
|
c9ce12d102 | ||
|
|
db50d2fa5a | ||
|
|
63fd23a464 | ||
|
|
2e03ed74f6 | ||
|
|
b86f51c9ab | ||
|
|
09448a5d3d | ||
|
|
18c719b2c6 | ||
|
|
b0a78fa9a8 | ||
|
|
0aca7dbcfc | ||
|
|
3f84d8991e | ||
|
|
5ac8f3ea6f | ||
|
|
bfb1c2fd52 | ||
|
|
cbfe1211c1 | ||
|
|
efd99e620c | ||
|
|
f23b694ad3 | ||
|
|
f97dea55ac | ||
|
|
efd08d7771 | ||
|
|
ff6cb2e217 | ||
|
|
d774620fea | ||
|
|
b26ff010fc | ||
|
|
4b49f2ba4b | ||
|
|
b4b8fe8828 | ||
|
|
4e8ab051a0 | ||
|
|
f61e35b218 | ||
|
|
b2f90f24a3 | ||
|
|
6721eb4752 | ||
|
|
a9e4fd1e40 | ||
|
|
621750976a | ||
|
|
5359e88806 | ||
|
|
76636931ba | ||
|
|
180c1fc66e | ||
|
|
c0ff052dab | ||
|
|
94cffb6ba3 | ||
|
|
9ad5628e69 | ||
|
|
6d397a7894 | ||
|
|
165fea6ba9 | ||
|
|
d079e2087c | ||
|
|
e3b36ebdcc | ||
|
|
5e791b11c0 | ||
|
|
50be65b76e | ||
|
|
7bb86e30bf | ||
|
|
ea56b45b7e | ||
|
|
f53682da7a | ||
|
|
71884ac088 | ||
|
|
969c278cb0 | ||
|
|
6fe2a1e036 | ||
|
|
9a60e0c68e | ||
|
|
46f553ca11 | ||
|
|
4f0a0c2184 | ||
|
|
c107b193d9 | ||
|
|
2db7ced7a4 | ||
|
|
6361d9a334 | ||
|
|
2cf54f04ef | ||
|
|
f840ce5c94 | ||
|
|
35e7b55490 | ||
|
|
1f8d1f23b3 | ||
|
|
e93011791e | ||
|
|
4460564a48 | ||
|
|
4d6658136e | ||
|
|
5767e665c2 | ||
|
|
3cf9958cb9 | ||
|
|
6b70a33080 | ||
|
|
8d23692320 | ||
|
|
33d3947da6 | ||
|
|
806163b8ba | ||
|
|
13c2a18286 | ||
|
|
b8f10951ea | ||
|
|
2fcf0879c6 | ||
|
|
1136b4186d | ||
|
|
cca73ad52f | ||
|
|
424bf36c03 | ||
|
|
9eb00da0c4 | ||
|
|
9269e81997 | ||
|
|
6642820aa0 | ||
|
|
8374c6b1c7 | ||
|
|
c8a3251834 | ||
|
|
2418f56273 | ||
|
|
297582941f | ||
|
|
958a61cbc4 | ||
|
|
3096212919 | ||
|
|
aa2b091966 | ||
|
|
1a9cb9095e | ||
|
|
0312159168 | ||
|
|
e204a90398 | ||
|
|
d8cf6058e9 | ||
|
|
2aefc19e3d | ||
|
|
28a430066f | ||
|
|
1013aef461 | ||
|
|
bb3210d74f | ||
|
|
745395e93b | ||
|
|
ae49bf0fa3 | ||
|
|
8410cd895e | ||
|
|
dc1642c2e8 | ||
|
|
c75b865710 | ||
|
|
e992b624e0 | ||
|
|
c60e4cd02c | ||
|
|
4b2996ca9f | ||
|
|
086076b74f | ||
|
|
7b2d694272 | ||
|
|
0583060c7c | ||
|
|
20e707fb52 | ||
|
|
6c75ec6bb2 | ||
|
|
e9fefd4c18 | ||
|
|
3ece481c74 | ||
|
|
33177548c3 | ||
|
|
ed1413a05e | ||
|
|
05d1e64228 | ||
|
|
64bbe1b51c | ||
|
|
3c6f2c8c65 | ||
|
|
f6d9bb1510 | ||
|
|
8ca4db3e8c | ||
|
|
d194d3a4d7 | ||
|
|
f5435e3087 | ||
|
|
88087dc7ff | ||
|
|
2f04b9f46c | ||
|
|
06d3b4cda6 | ||
|
|
09186fe551 | ||
|
|
c634f2e23b | ||
|
|
b3ccae4c2b | ||
|
|
85ac09110f | ||
|
|
6622ebb30e | ||
|
|
824b079fea | ||
|
|
2e5a8bfb5a | ||
|
|
ce36b790ea | ||
|
|
8d60aa921a | ||
|
|
78ce96a8db | ||
|
|
ce308f84ba | ||
|
|
7459f24696 | ||
|
|
8f90744ba0 | ||
|
|
4db407345c | ||
|
|
4a09eacfe4 | ||
|
|
a9e1b26652 | ||
|
|
513d90bb8a | ||
|
|
d03f06aa82 | ||
|
|
c657057826 | ||
|
|
84717341d7 | ||
|
|
f631a61330 | ||
|
|
38222c9fec | ||
|
|
055fc895a6 | ||
|
|
8ab38f142a | ||
|
|
1b3921f9c8 | ||
|
|
c15453db1a | ||
|
|
83641c2491 | ||
|
|
e1f4d1f267 | ||
|
|
00d37b2d1a | ||
|
|
887061e65b | ||
|
|
bb2b301c4e | ||
|
|
2cc1acebd2 | ||
|
|
9dd2d33cbb | ||
|
|
f648e19d4d | ||
|
|
9793239962 | ||
|
|
81d5744e8e | ||
|
|
5d37ecfff0 | ||
|
|
64577a1eb8 | ||
|
|
720a7026b4 | ||
|
|
e4a83388ae | ||
|
|
2e9b749ce2 | ||
|
|
a074b13a7a | ||
|
|
16877032ac | ||
|
|
21dd8d10c0 | ||
|
|
a2e9dab162 | ||
|
|
99d49b5d85 | ||
|
|
024bfc52f2 | ||
|
|
4588cdf2d9 | ||
|
|
81147e44bb | ||
|
|
0f41034b78 | ||
|
|
2c5d9995f9 | ||
|
|
aa71ce9062 | ||
|
|
967ef3bb3c | ||
|
|
d05055abb6 | ||
|
|
a905b92fcc | ||
|
|
797e301968 | ||
|
|
d8a426cea1 | ||
|
|
d5ded1e48a | ||
|
|
22d48bad4d | ||
|
|
99c50464d9 | ||
|
|
d0141450fe | ||
|
|
84c67fa743 | ||
|
|
d0536dbe14 | ||
|
|
4177a22936 | ||
|
|
5c38b23810 | ||
|
|
aa0f721ce8 | ||
|
|
2e94439f49 | ||
|
|
961c45c825 | ||
|
|
20f1f9820d | ||
|
|
a6f08472dd | ||
|
|
9f95029225 | ||
|
|
4ad4651ffa | ||
|
|
c0d008fae7 | ||
|
|
1974327e32 | ||
|
|
110817b60c | ||
|
|
95070ea029 | ||
|
|
44aea3a9a1 | ||
|
|
ce42691be5 | ||
|
|
6f823de67d | ||
|
|
7443fc7f26 | ||
|
|
e1d484655f | ||
|
|
362a41bff8 | ||
|
|
62974e879e | ||
|
|
cd713cd73a | ||
|
|
bd8afc3cc4 | ||
|
|
1688639d7d | ||
|
|
60d07f9b17 | ||
|
|
824ff5dc90 | ||
|
|
3d27f2eb43 | ||
|
|
a168610826 | ||
|
|
5447476b08 | ||
|
|
e58d99ba57 | ||
|
|
51d6f7e0c2 | ||
|
|
40459af09e | ||
|
|
c7dc61597a | ||
|
|
43d55ac3b1 | ||
|
|
736e981005 | ||
|
|
b84d6be3ca | ||
|
|
eff4940e9c | ||
|
|
0d6f2ce68d | ||
|
|
a654978813 | ||
|
|
a399e30a8e | ||
|
|
e0644c0297 | ||
|
|
37eed9df7d | ||
|
|
22582b834f | ||
|
|
8a0c5f0556 | ||
|
|
62b10d89c2 | ||
|
|
741206597b | ||
|
|
36755f5f8b | ||
|
|
fe36cc9241 | ||
|
|
c1e05f7c4a | ||
|
|
eb4a3adb3f | ||
|
|
f1ebd2cf99 | ||
|
|
cb3b5f1e01 | ||
|
|
6fc538bf50 | ||
|
|
665c33f69a | ||
|
|
880591fc00 | ||
|
|
68060fbcba | ||
|
|
db1ebc29e0 | ||
|
|
93b8709c36 | ||
|
|
7900c4df2e | ||
|
|
8b6fb1c06e | ||
|
|
de8b996dea | ||
|
|
eb8d229f28 |
@@ -0,0 +1,3 @@
|
||||
d23bb1ec24a7f49359314e04cd2c04c8f38876e45f25a701506499d1b34f270f MANIFEST-AIOS-V2R1-HERMES-LIFECYCLE-20260721.json
|
||||
5ce2894fdf8a22622954a1a10fb09fbab74af04f0260b249615c70236ff31731 RESULT-AIOS-V2R1-HERMES-LIFECYCLE-20260721.md
|
||||
ca2ab3c22c2b2b33bbc03e59f1206b999ad1271de3e1938fd3a0b4234c613eef ../../../docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md
|
||||
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"schema_version": "aios.evidence.manifest.v1",
|
||||
"generated_at": "2026-07-21T05:50:00Z",
|
||||
"branch": "patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721",
|
||||
"validated_oid": "95d2e52cb55c7b913e89bc6bed2bcdacf67512d4",
|
||||
"evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z",
|
||||
"evidence_hashes": {
|
||||
"steps.tsv": "b2ad20585ba7f576e85657827a0b1db6f252887bbd73bcd718df38623e9d95cf",
|
||||
"final-live-gate.log": "82040c674759dacf587658c5e936c313a1f50e8e2425be48ad891927befdf4fa",
|
||||
"16R.log": "641246927a372ebaa9e6dde8b018b88275b2ba15a442473759b23fb1f215d9cf",
|
||||
"15.log": "b0a474e2a74164f560c4f7572091911f32011c75faccd37a3c7315046275011e",
|
||||
"13.log": "b9f637cca6e97ed893bf38530e05cd33b78e324c5e8865d4c602dfeac22a7710",
|
||||
"12R2.log": "0c431f5f5f1c1b17acda160c917b08c7f4036485016c23e1236b9b6f4a78de67"
|
||||
},
|
||||
"validation": {
|
||||
"candidate_tests": {"passed": 49, "failed": 0},
|
||||
"hermes_lifecycle": {"passed": 17, "failed": 0},
|
||||
"gate_b": {"passed": 10, "failed": 0},
|
||||
"offline_acceptance": {"passed": 8, "failed": 0, "expected_warnings": 1},
|
||||
"openclaw_real_http": "PASS",
|
||||
"restart_recovery": "PASS",
|
||||
"rollback_forward": "PASS",
|
||||
"state_preservation": "PASS",
|
||||
"final_health_corrected_16R": "PASS"
|
||||
},
|
||||
"git_gate": {
|
||||
"oid_match": true,
|
||||
"candidate_clean": true,
|
||||
"active_controller_clean": true,
|
||||
"locked": 0,
|
||||
"prunable": 0,
|
||||
"worktree_total": 88,
|
||||
"worktree_dirty": 10,
|
||||
"global_worktree_clean": false
|
||||
},
|
||||
"resolved_blockers": [],
|
||||
"active_blockers": [
|
||||
"BLK-LIVE-HERMES-FULL-LIFECYCLE-EVIDENCE-MISSING",
|
||||
"BLK-GLOBAL-WORKTREE-CLEANLINESS"
|
||||
],
|
||||
"overall": "PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS",
|
||||
"release_decision": "STOP_PREPRODUCTION",
|
||||
"secrets_recorded": false
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
# AIOS V2R1 Hermes Lifecycle Result
|
||||
|
||||
- Branch: `patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721`
|
||||
- Validated OID: `95d2e52cb55c7b913e89bc6bed2bcdacf67512d4`
|
||||
- Evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z`
|
||||
- Hermes blocker: `EVIDENCE_COMPLETE / FORMAL_CLOSURE_BLOCKED`
|
||||
- Overall: `PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS`
|
||||
- Release decision: `STOP_PREPRODUCTION`
|
||||
|
||||
Hermes lifecycle `17/17`, candidate `49/49`, Gate B `10/10`, offline acceptance `8/0/1`, OpenClaw real HTTP, restart recovery, rollback/forward, state preservation and corrected final health all passed at the validated OID. The Owner acceptance contract nevertheless forbids formally closing the Hermes blocker until every global gate also passes.
|
||||
|
||||
The candidate worktree and active Controller worktree are clean; local, worktree and Gitea OIDs match; locked/prunable are zero. The global authority currently has 10 dirty worktrees out of 88, so the Owner hard gate requiring every worktree to be clean fails.
|
||||
|
||||
No RC, Tag Approval Request, Tag, main mutation, force push, production traffic switch or secret disclosure was performed.
|
||||
|
||||
See `MANIFEST-AIOS-V2R1-HERMES-LIFECYCLE-20260721.json` and `docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md`.
|
||||
@@ -0,0 +1,10 @@
|
||||
# Independent Validator Result
|
||||
|
||||
- Model: `gpt-5.3-codex-spark`
|
||||
- Reviewer identity: `gpt-5.3-codex-spark-validator`
|
||||
- Broad live-review attempt: `TIMEOUT` after 600 seconds; no decision was accepted from that attempt.
|
||||
- Narrow immutable evidence-bundle review: `SUCCESS`
|
||||
- Cleanup review: `PASS`
|
||||
- Release decision: `STOP_PREPRODUCTION`
|
||||
- Verified: 10 Manifest records, 7 removed records, 3 retained roots, 7 local/remote Archive OID pairs, product OID equality, release/tag absence, and global dirty/locked/prunable all zero.
|
||||
- Blocking finding: archived Portal Adapter `portal-surface` and `seed-ucc` commands returned non-zero.
|
||||
@@ -0,0 +1,317 @@
|
||||
{
|
||||
"schema_version": "aios.incubator.worktree-archive.v1",
|
||||
"status": "CLEANUP_REVIEWED_RELEASE_STOPPED",
|
||||
"release_gate": "STOP_PREPRODUCTION",
|
||||
"release_gate_reasons": [
|
||||
"archived Portal Adapter portal-surface contract tests failed",
|
||||
"archived Portal Adapter Django test could not execute because Django is absent on the validation host"
|
||||
],
|
||||
"inventory_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-archive-20260721T064301Z",
|
||||
"archive_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-task-archive-20260721T070301Z",
|
||||
"removal_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-task-removal-20260721T070843Z",
|
||||
"controller_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-controller-migration-20260721T070749Z",
|
||||
"longterm_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-longterm-clean-20260721T071346Z",
|
||||
"global_gate_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-global-gate-20260721T071446Z",
|
||||
"release_source": false,
|
||||
"reviewed_count": 10,
|
||||
"removed_count": 7,
|
||||
"retained_active_count": 3,
|
||||
"global_dirty_count": 0,
|
||||
"locked_count": 0,
|
||||
"prunable_count": 0,
|
||||
"archive_validation": {
|
||||
"passed_commands": 7,
|
||||
"failed_commands": 1,
|
||||
"blocked_commands": 1
|
||||
},
|
||||
"worktrees": [
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/chatgpt/TASK-V2R1-PERSONAL-WEIXIN-GOLDEN-CONTRACT-R2-20260715",
|
||||
"owner": "chatgpt",
|
||||
"task_id": "TASK-V2R1-PERSONAL-WEIXIN-GOLDEN-CONTRACT-R2-20260715",
|
||||
"source_branch": "design/v2r1-personal-weixin-golden-contract-r2-20260715",
|
||||
"source_oid": "68d27879103990aac692207a8512b3725c6d0d41",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 36,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"channel-neutral versioned contract SDK and deterministic fixture validation pattern"
|
||||
],
|
||||
"excluded_items": [
|
||||
"Personal-Weixin schemas, fixtures, security document and release-specific plan"
|
||||
],
|
||||
"archive_branch": "archive/chatgpt/TASK-V2R1-PERSONAL-WEIXIN-GOLDEN-CONTRACT-R2-20260715-20260721",
|
||||
"archive_oid": "fe86e35257113853ba08b1438bc820bb4554e6e8",
|
||||
"archive_remote_oid": "fe86e35257113853ba08b1438bc820bb4554e6e8",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:45Z",
|
||||
"validation": "PASS: contract harness",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/chatgpt/TASK-V2R1-PERSONAL-WEIXIN-PORTAL-ADAPTER-20260715",
|
||||
"owner": "chatgpt",
|
||||
"task_id": "TASK-V2R1-PERSONAL-WEIXIN-PORTAL-ADAPTER-20260715",
|
||||
"source_branch": "fix/v2r1-personal-weixin-portal-adapter-20260715",
|
||||
"source_oid": "64270e74ba0835971ee20bf4d2b12b1d20b05533",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 2,
|
||||
"secret_scan": {
|
||||
"initial_violations": 1,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"generic auth-session state, expiry, challenge, replay and fail-closed policy"
|
||||
],
|
||||
"excluded_items": [
|
||||
"UCC/OpenClaw/Weixin adapter implementation; incomplete portal surface; runtime-specific binding code"
|
||||
],
|
||||
"archive_branch": "archive/chatgpt/TASK-V2R1-PERSONAL-WEIXIN-PORTAL-ADAPTER-20260715-20260721",
|
||||
"archive_oid": "79f529a91f8bf7cf3237feb01e98807ab5ad10b3",
|
||||
"archive_remote_oid": "79f529a91f8bf7cf3237feb01e98807ab5ad10b3",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:46Z",
|
||||
"validation": "REJECTED_FOR_ADOPTION: official-login tests pass; portal-surface tests fail; Django test blocked by missing dependency",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/chatgpt/TASK-WORKTREE-CONCURRENCY-CHATGPT-20260715T055106UTC8",
|
||||
"owner": "chatgpt",
|
||||
"task_id": "TASK-WORKTREE-CONCURRENCY-CHATGPT-20260715T055106UTC8",
|
||||
"source_branch": "task/chatgpt/TASK-WORKTREE-CONCURRENCY-CHATGPT-20260715T055106UTC8",
|
||||
"source_oid": "b05eb1babe9c657e8776c09eec71302166902cc3",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 2,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"registered-worktree classification and dirty-count governance model"
|
||||
],
|
||||
"excluded_items": [
|
||||
"agent task/result documents and ACL probe evidence"
|
||||
],
|
||||
"archive_branch": "archive/chatgpt/TASK-WORKTREE-CONCURRENCY-CHATGPT-20260715T055106UTC8-20260721",
|
||||
"archive_oid": "f0feed397dc67edab7daa16f0cdb5b553eca5668",
|
||||
"archive_remote_oid": "f0feed397dc67edab7daa16f0cdb5b553eca5668",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:47Z",
|
||||
"validation": "PASS: evidence integrity and zero-secret scan",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/codex/TASK-CODEX-AIOS-SPARK-RUNNER-PROVISIONING-20260717T103500UTC8",
|
||||
"owner": "codex",
|
||||
"task_id": "TASK-CODEX-AIOS-SPARK-RUNNER-PROVISIONING-20260717T103500UTC8",
|
||||
"source_branch": "patch/chatgpt/v2r1-personal-weixin-b3-repair3-owner-20260717T102830UTC8",
|
||||
"source_oid": "ef20c71247c6de6659e18fc57315da19d8a3834e",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 6,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"generic runner-provider preflight, immutable digest and reference-only credential contracts"
|
||||
],
|
||||
"excluded_items": [
|
||||
"Spark-specific systemd, provisioning, rollback and production wiring"
|
||||
],
|
||||
"archive_branch": "archive/codex/TASK-CODEX-AIOS-SPARK-RUNNER-PROVISIONING-20260717T103500UTC8-20260721",
|
||||
"archive_oid": "d97cd3642528bd3373fe4cf5161a5d99c0b9285f",
|
||||
"archive_remote_oid": "d97cd3642528bd3373fe4cf5161a5d99c0b9285f",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:48Z",
|
||||
"validation": "PASS: 27 pytest tests",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/openclaw/TASK-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8",
|
||||
"owner": "openclaw",
|
||||
"task_id": "TASK-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8",
|
||||
"source_branch": "patch/openclaw/v2r1-personal-weixin-b3-evidence-hardening-20260716T133000UTC8",
|
||||
"source_oid": "8d9c6da90fc8caa69b691d243c6fefb40b6b0575",
|
||||
"remote_oid": "8d9c6da90fc8caa69b691d243c6fefb40b6b0575",
|
||||
"dirty_files_before": 3,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"canonical evidence envelope, streaming hash and independent-review integrity policy"
|
||||
],
|
||||
"excluded_items": [
|
||||
"Personal-Weixin B3 evidence tool, empty owner facts and release-specific output path"
|
||||
],
|
||||
"archive_branch": "archive/openclaw/TASK-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8-20260721",
|
||||
"archive_oid": "2ddbc456124c02707dc23e8d6c241826d7026575",
|
||||
"archive_remote_oid": "2ddbc456124c02707dc23e8d6c241826d7026575",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:49Z",
|
||||
"validation": "PASS: compile, canonical template JSON and CLI help",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/openclaw/TASK-V2R1-OPENCLAW-WEIXIN-WEB-LOGIN-CONTRACT-20260715",
|
||||
"owner": "openclaw",
|
||||
"task_id": "TASK-V2R1-OPENCLAW-WEIXIN-WEB-LOGIN-CONTRACT-20260715",
|
||||
"source_branch": "fix/v2r1-openclaw-weixin-web-login-contract-20260715",
|
||||
"source_oid": "68d27879103990aac692207a8512b3725c6d0d41",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 20,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"generic auth-session state transitions and readiness/revocation contracts"
|
||||
],
|
||||
"excluded_items": [
|
||||
"OpenClaw and Tencent Weixin patches, candidate evidence and channel-specific code"
|
||||
],
|
||||
"archive_branch": "archive/openclaw/TASK-V2R1-OPENCLAW-WEIXIN-WEB-LOGIN-CONTRACT-20260715-20260721",
|
||||
"archive_oid": "d03b4ee34debe6e30ce2af233e2226b02e6dd029",
|
||||
"archive_remote_oid": "d03b4ee34debe6e30ce2af233e2226b02e6dd029",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:50Z",
|
||||
"validation": "PASS: Node contract tests",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/openclaw/TASK-WORKTREE-CONCURRENCY-OPENCLAW-20260715T055106UTC8",
|
||||
"owner": "openclaw",
|
||||
"task_id": "TASK-WORKTREE-CONCURRENCY-OPENCLAW-20260715T055106UTC8",
|
||||
"source_branch": "task/openclaw/TASK-WORKTREE-CONCURRENCY-OPENCLAW-20260715T055106UTC8",
|
||||
"source_oid": "b05eb1babe9c657e8776c09eec71302166902cc3",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 3,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"registered-worktree classification and cleanup authorization boundary"
|
||||
],
|
||||
"excluded_items": [
|
||||
"agent task/result documents and ACL probe evidence"
|
||||
],
|
||||
"archive_branch": "archive/openclaw/TASK-WORKTREE-CONCURRENCY-OPENCLAW-20260715T055106UTC8-20260721",
|
||||
"archive_oid": "d9a85bb86cc09c117d63de803a404ee5a864e7c1",
|
||||
"archive_remote_oid": "d9a85bb86cc09c117d63de803a404ee5a864e7c1",
|
||||
"cleanup_method": "archive_commit_push_verify_then_worktree_remove_and_prune",
|
||||
"removed_at": "2026-07-21T07:08:51Z",
|
||||
"validation": "PASS: evidence integrity and zero-secret scan",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/codex",
|
||||
"owner": "codex",
|
||||
"task_id": "codex-long-term-root",
|
||||
"source_branch": "acceptance/codex/TASK-CODEX-GITOPS-SECRET-ACL-AND-IDENTITY-HARDENING-20260715T004818UTC8-FINAL",
|
||||
"source_oid": "b87266d63f4d16ba25b9c0041d6769822dfa99d4",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 56,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"registered child-worktree governance classification"
|
||||
],
|
||||
"excluded_items": [
|
||||
"all 55 retained registered child worktrees and their contents"
|
||||
],
|
||||
"archive_branch": "acceptance/codex/TASK-CODEX-GITOPS-SECRET-ACL-AND-IDENTITY-HARDENING-20260715T004818UTC8-FINAL",
|
||||
"archive_oid": "0193a12b57c4974888b25753fd2bfb1f2028909b",
|
||||
"archive_remote_oid": "0193a12b57c4974888b25753fd2bfb1f2028909b",
|
||||
"cleanup_method": "retain active long-term root; commit exact registered-child ignore list",
|
||||
"removed_at": null,
|
||||
"validation": "PASS: 55 untracked entries exactly matched 55 registered child worktrees; final clean",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/controller",
|
||||
"owner": "controller",
|
||||
"task_id": "controller-long-term-root",
|
||||
"source_branch": "DETACHED",
|
||||
"source_oid": "102d2306f05397374fc91c711767021c5d9f41f9",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 11,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"runtime-state separation policy"
|
||||
],
|
||||
"excluded_items": [
|
||||
"generated health/watcher state and duplicate controller-run audit records"
|
||||
],
|
||||
"archive_branch": "archive/controller/runtime-baseline-20260721",
|
||||
"archive_oid": "102d2306f05397374fc91c711767021c5d9f41f9",
|
||||
"archive_remote_oid": "102d2306f05397374fc91c711767021c5d9f41f9",
|
||||
"cleanup_method": "retain active source root; migrate watcher state to runtime directory; restore tracked generated state; remove only hash-matched duplicates",
|
||||
"removed_at": null,
|
||||
"validation": "PASS: watcher, model API and autonomous controller active; final clean",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
},
|
||||
{
|
||||
"worktree_path": "/data/aios-gitops/worktrees/openclaw",
|
||||
"owner": "openclaw",
|
||||
"task_id": "openclaw-long-term-root",
|
||||
"source_branch": "acceptance/openclaw/TASK-CODEX-GITOPS-SECRET-ACL-AND-IDENTITY-HARDENING-20260715T004818UTC8-FINAL",
|
||||
"source_oid": "6cd0f5aa0ad28f767ffd5396c29d1a9182f88c43",
|
||||
"remote_oid": "ABSENT_AT_INVENTORY",
|
||||
"dirty_files_before": 5,
|
||||
"secret_scan": {
|
||||
"initial_violations": 0,
|
||||
"final_violations": 0,
|
||||
"secrets_recorded": false
|
||||
},
|
||||
"adopted_items": [
|
||||
"registered child-worktree governance classification"
|
||||
],
|
||||
"excluded_items": [
|
||||
"both retained registered child worktrees and their contents"
|
||||
],
|
||||
"archive_branch": "acceptance/openclaw/TASK-CODEX-GITOPS-SECRET-ACL-AND-IDENTITY-HARDENING-20260715T004818UTC8-FINAL",
|
||||
"archive_oid": "633c8308f53b0ad04ce054ceafb624cb0904cbf4",
|
||||
"archive_remote_oid": "633c8308f53b0ad04ce054ceafb624cb0904cbf4",
|
||||
"cleanup_method": "retain active long-term root; commit exact registered-child ignore list",
|
||||
"removed_at": null,
|
||||
"validation": "PASS: 2 untracked entries exactly matched 2 registered child worktrees; final clean",
|
||||
"reviewer": "gpt-5.3-codex-spark-validator"
|
||||
}
|
||||
],
|
||||
"unknown_value_policy": "UNVERIFIED_OWNER_INPUT_REQUIRED",
|
||||
"secrets_recorded": false,
|
||||
"reviewer": "gpt-5.3-codex-spark-validator",
|
||||
"reviewer_decision": {
|
||||
"cleanup_review": "PASS",
|
||||
"release_decision": "STOP_PREPRODUCTION",
|
||||
"verified_counts": {
|
||||
"manifest_records": 10,
|
||||
"removed_records": 7,
|
||||
"retained_roots": 3,
|
||||
"archive_oid_local_remote_pairs": 7,
|
||||
"global_dirty": 0,
|
||||
"global_locked": 0,
|
||||
"global_prunable": 0
|
||||
},
|
||||
"finding": "portal-surface and seed-ucc archive validation commands returned non-zero",
|
||||
"review_scope": "compact immutable evidence bundle after one broader live-review timeout"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
# Worktree Cleanup Result
|
||||
|
||||
Status: `CLEANUP_REVIEWED_RELEASE_STOPPED`
|
||||
|
||||
- Reviewed: `10/10`
|
||||
- Archived and removed: `7`
|
||||
- Retained active and cleaned: `3`
|
||||
- Global dirty worktrees: `0`
|
||||
- Locked: `0`
|
||||
- Prunable: `0`
|
||||
- Product OID: `fb739f6e8ff9c031d319221ace68dce157694086`
|
||||
- Incubator OID before this manifest commit: `4487a774fdeec51bc49253c2ad494c19d1b1c3e2`
|
||||
- Release branch created: `false`
|
||||
- V2R1C1 tag created: `false`
|
||||
- Release decision: `STOP_PREPRODUCTION`
|
||||
|
||||
The stop decision is evidence-driven: the archived Portal Adapter portal-surface contract suite failed, and its Django test could not run because Django is absent on the host. No failed archive candidate was adopted into the incubator or product branch.
|
||||
|
||||
Independent reviewer: `gpt-5.3-codex-spark-validator`; cleanup `PASS`; release `STOP_PREPRODUCTION`.
|
||||
@@ -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.
|
||||
@@ -10,3 +10,4 @@ node_modules/
|
||||
runtime/tmp/
|
||||
runtime/cache/
|
||||
logs/
|
||||
config/test_write_perms
|
||||
|
||||
@@ -0,0 +1,394 @@
|
||||
# AIOS V2R1 生产候选报告
|
||||
|
||||
- 候选版本:`V2R1C0-candidate`
|
||||
- 候选分支:`integration/aios-v2r1-cto-production-candidate-20260720`
|
||||
- 报告语言:中文
|
||||
- 架构负责人:AIOS V2 CTO
|
||||
- 当前状态:代码与文档闭环已完成;精确 Commit 测试、真实 Runtime 联调和预发布验证待执行
|
||||
|
||||
## 1. 执行摘要
|
||||
|
||||
AIOS V2R1 Candidate 已完成以下核心建设:
|
||||
|
||||
- AIOS 唯一控制面;
|
||||
- Tenant、Agent、Task、Policy、Approval 和 Audit 权威模型;
|
||||
- SQLite WAL 候选持久化与重启恢复;
|
||||
- Execution Orchestrator;
|
||||
- OpenClaw 签名命令、Adapter、Transport、Health 和 Audit Callback;
|
||||
- Hermes tenant/cell/profile 分区、Queue、Worker Lease、Heartbeat 和 Result;
|
||||
- Agent Execution Evidence;
|
||||
- Web Console;
|
||||
- GitOps Status;
|
||||
- systemd、Docker、Compose、Healthcheck 和 Rollback;
|
||||
- 用户需求、目标架构、迁移策略、模块契约、追踪矩阵、文档治理和 ADR;
|
||||
- 文档—代码匹配检查器;
|
||||
- 全量验收入口;
|
||||
- OpenClaw 预发布部署任务;
|
||||
- Codex 架构监督和阻塞处理任务。
|
||||
|
||||
本报告不把“代码已提交”误报为“生产已验证”。以下状态仍需由无人值守任务执行并形成证据:
|
||||
|
||||
- 精确 Candidate Commit 的自动测试;
|
||||
- 真实 OpenClaw Runtime 联调;
|
||||
- Hermes 长任务、Worker 崩溃和 Lease Recovery 演练;
|
||||
- systemd/Docker 预发布部署;
|
||||
- 重启恢复与回滚演练;
|
||||
- 本地仓库与 Gitea Candidate OID 一致验证;
|
||||
- 身份代理、安全、性能和容量验证;
|
||||
- Owner 对合并、Tag 和生产部署的批准。
|
||||
|
||||
## 2. 用户需求完成情况
|
||||
|
||||
| 需求 | 代码状态 | 测试状态 | 预发布状态 |
|
||||
|---|---|---|---|
|
||||
| AIOS 唯一控制面 | 已实现 | 已定义 | 待验证 |
|
||||
| 复用 OpenClaw/Hermes/Agent Router | 已实现 | 已定义 | 待真实联调 |
|
||||
| OpenClaw/Hermes 解耦 | 已实现 | 已定义 | 待旁路冻结验证 |
|
||||
| 全面 Web 化 | 候选实现完成 | 冒烟测试待执行 | 待反向代理接入 |
|
||||
| 多租户隔离 | 已实现 | Domain 负向测试已定义 | 待全链路安全验证 |
|
||||
| 统一任务生命周期 | 已实现 | 已定义 | 待精确 Commit 执行 |
|
||||
| 策略与审批 | 已实现 | 部分测试待补强 | 待身份代理验证 |
|
||||
| 幂等与并发安全 | 已实现 | 基础测试已定义 | 待压力和并发验证 |
|
||||
| 执行证据 | 已实现 | 已定义 | 待外部执行器持续回写 |
|
||||
| GitOps 唯一流程 | 已实现并修复 Controller 冲突 | Runtime 部分验证 | 待双目标持续镜像证据 |
|
||||
| 持久化与恢复 | 已实现 | 重启恢复测试已定义 | 待预发布演练 |
|
||||
| 审计与合规 | 已实现候选 | 部分断言待补强 | 待不可变外部固化 |
|
||||
| 密钥安全 | 引用模式已实现 | 基础扫描纳入验收 | 待 Secret Provider 联调 |
|
||||
| 部署与回滚 | 资产完成 | 验收脚本已定义 | 待实际演练 |
|
||||
| 文档与代码同步 | 已实现门禁 | 待精确 Commit 执行 | 待接入持续验收 |
|
||||
|
||||
## 3. 目标架构
|
||||
|
||||
```text
|
||||
浏览器 / Web Console / Public API
|
||||
|
|
||||
v
|
||||
AIOS 唯一控制面
|
||||
Tenant | Agent | Task | Policy | Approval | Audit
|
||||
|
|
||||
v
|
||||
Execution Orchestrator / Agent Router
|
||||
/ \
|
||||
v v
|
||||
OpenClaw Adapter Hermes Boundary
|
||||
| |
|
||||
v v
|
||||
OpenClaw Runtime Hermes Workers
|
||||
\ /
|
||||
v v
|
||||
结果回写 + 审计 + 执行证据
|
||||
```
|
||||
|
||||
权威边界:
|
||||
|
||||
- AIOS:租户、身份、Agent、任务、策略、审批、审计和执行证据;
|
||||
- Agent Router:调度与路由;
|
||||
- OpenClaw:签名命令执行、取消、状态、健康和回调;
|
||||
- Hermes:队列、Worker、Lease、Heartbeat 和结果;
|
||||
- Web:只调用 AIOS API;
|
||||
- GitOps:所有代码、文档、部署和修复变更入口。
|
||||
|
||||
## 4. 实现清单
|
||||
|
||||
### 4.1 Control Plane
|
||||
|
||||
```text
|
||||
active-runtime/app/aios_v2/control_plane.py
|
||||
active-runtime/app/aios_v2/persistence.py
|
||||
active-runtime/app/aios_v2/gateway.py
|
||||
active-runtime/app/aios_v2/app.py
|
||||
active-runtime/app/aios_v2/orchestrator.py
|
||||
active-runtime/app/aios_v2/execution_tracking.py
|
||||
active-runtime/app/aios_v2/gitops_status.py
|
||||
active-runtime/app/aios_v2/console.py
|
||||
```
|
||||
|
||||
### 4.2 OpenClaw
|
||||
|
||||
```text
|
||||
active-runtime/app/aios_openclaw/contract.py
|
||||
active-runtime/app/aios_openclaw/adapter.py
|
||||
active-runtime/app/aios_openclaw/transport.py
|
||||
active-runtime/app/aios_openclaw/health.py
|
||||
active-runtime/app/aios_openclaw/callback.py
|
||||
```
|
||||
|
||||
### 4.3 Hermes
|
||||
|
||||
```text
|
||||
active-runtime/app/aios_hermes/contract.py
|
||||
active-runtime/app/aios_hermes/adapter.py
|
||||
active-runtime/app/aios_hermes/worker.py
|
||||
```
|
||||
|
||||
### 4.4 测试与治理
|
||||
|
||||
```text
|
||||
tests/aios_v2_candidate/test_candidate_flow.py
|
||||
tools/aios_v2_docs_code_check.py
|
||||
deploy/aios-v2/acceptance/run-all.sh
|
||||
```
|
||||
|
||||
### 4.5 部署
|
||||
|
||||
```text
|
||||
deploy/aios-v2/systemd/aios-v2.service
|
||||
deploy/aios-v2/env/aios-v2.env.example
|
||||
deploy/aios-v2/docker/Dockerfile
|
||||
deploy/aios-v2/docker/compose.yaml
|
||||
deploy/aios-v2/healthcheck/check.sh
|
||||
deploy/aios-v2/rollback/rollback.sh
|
||||
```
|
||||
|
||||
### 4.6 文档与任务
|
||||
|
||||
```text
|
||||
docs/aios-v2/
|
||||
tasks/openclaw-production-deploy-task.yaml
|
||||
tasks/codex-production-supervisor-task.yaml
|
||||
```
|
||||
|
||||
## 5. 多租户与安全设计
|
||||
|
||||
### 5.1 权威上下文
|
||||
|
||||
```text
|
||||
tenant_id
|
||||
principal_id
|
||||
session_id
|
||||
trace_id
|
||||
task_id
|
||||
policy_version
|
||||
idempotency_key
|
||||
```
|
||||
|
||||
### 5.2 OpenClaw
|
||||
|
||||
- HMAC-SHA256 规范化签名;
|
||||
- 签名绑定 tenant/task/trace/action/payload/idempotency/time;
|
||||
- Runtime Result 身份字段必须匹配;
|
||||
- Secret 只通过受保护文件或引用解析。
|
||||
|
||||
### 5.3 Hermes
|
||||
|
||||
- tenant/cell/profile 分区;
|
||||
- Worker Lease 与 Heartbeat;
|
||||
- revision 乐观并发;
|
||||
- Lease 过期自动回到 QUEUED;
|
||||
- Worker 完成前停止 Heartbeat,避免 revision 竞态。
|
||||
|
||||
### 5.4 Web/API
|
||||
|
||||
- 可信代理注入 `X-AIOS-*`;
|
||||
- 浏览器不选择租户;
|
||||
- CSP、no-store、nosniff、DENY frame、no-referrer;
|
||||
- 应用端口不得直接暴露公网。
|
||||
|
||||
### 5.5 GitOps
|
||||
|
||||
- Controller detached + clean;
|
||||
- 禁止 fetch 到已检出本地分支;
|
||||
- 所有修改进入分支、Commit、测试和统一审查;
|
||||
- 明文 Secret 门禁;
|
||||
- 文档变化与代码变化同步门禁。
|
||||
|
||||
## 6. 持久化策略
|
||||
|
||||
候选版:
|
||||
|
||||
- SQLite WAL;
|
||||
- `synchronous=FULL`;
|
||||
- `BEGIN IMMEDIATE`;
|
||||
- 原子 Snapshot;
|
||||
- schema version;
|
||||
- 状态目录与代码版本分离;
|
||||
- Execution Evidence 租户分区原子 JSON。
|
||||
|
||||
已知限制:
|
||||
|
||||
- 单进程候选优先;
|
||||
- 尚无生产 RLS、多实例 HA、PITR 和容量证据;
|
||||
- 后续必须通过新 ADR 迁移到生产数据层。
|
||||
|
||||
## 7. 测试与验收
|
||||
|
||||
### 7.1 文档—代码匹配
|
||||
|
||||
```bash
|
||||
python3 tools/aios_v2_docs_code_check.py \
|
||||
--base-ref integration/aios-v2r1-cto-production-candidate-20260720
|
||||
```
|
||||
|
||||
### 7.2 候选测试
|
||||
|
||||
```bash
|
||||
python3 -m unittest discover \
|
||||
-s tests/aios_v2_candidate \
|
||||
-p 'test_*.py' \
|
||||
-v
|
||||
```
|
||||
|
||||
覆盖:
|
||||
|
||||
- OpenClaw 完整执行;
|
||||
- Hermes 完整执行;
|
||||
- 跨租户拒绝;
|
||||
- SQLite 重启恢复;
|
||||
- Execution Evidence。
|
||||
|
||||
### 7.3 全量验收
|
||||
|
||||
```bash
|
||||
bash deploy/aios-v2/acceptance/run-all.sh
|
||||
```
|
||||
|
||||
可选在线健康检查:
|
||||
|
||||
```bash
|
||||
AIOS_RUN_LIVE_HEALTHCHECK=1 \
|
||||
bash deploy/aios-v2/acceptance/run-all.sh
|
||||
```
|
||||
|
||||
### 7.4 健康检查
|
||||
|
||||
```bash
|
||||
bash deploy/aios-v2/healthcheck/check.sh
|
||||
```
|
||||
|
||||
检查:
|
||||
|
||||
- systemd;
|
||||
- HTTP Health;
|
||||
- 状态目录;
|
||||
- SQLite quick_check;
|
||||
- GitOps detached/clean;
|
||||
- Evidence 文件。
|
||||
|
||||
## 8. 部署方式
|
||||
|
||||
### 8.1 systemd
|
||||
|
||||
```text
|
||||
/etc/aios-v2/aios-v2.env
|
||||
/opt/aios/current
|
||||
/var/lib/aios-v2
|
||||
```
|
||||
|
||||
运行用户:`aios`。
|
||||
|
||||
安全选项:NoNewPrivileges、ProtectSystem、ProtectHome、PrivateTmp、Capability 限制。
|
||||
|
||||
### 8.2 Docker/Compose
|
||||
|
||||
- 非 root UID/GID;
|
||||
- Read-only root filesystem;
|
||||
- Drop all capabilities;
|
||||
- 独立 State Volume;
|
||||
- HTTP Healthcheck;
|
||||
- Secret 文件只读挂载。
|
||||
|
||||
## 9. 回滚
|
||||
|
||||
```bash
|
||||
bash deploy/aios-v2/rollback/rollback.sh <previous-release>
|
||||
```
|
||||
|
||||
原则:
|
||||
|
||||
- 回滚前自动备份状态;
|
||||
- 默认只回滚代码;
|
||||
- 状态恢复需显式 `AIOS_V2_RESTORE_STATE=1`;
|
||||
- 回滚后必须执行健康检查;
|
||||
- 目标版本失败时自动恢复 previous release。
|
||||
|
||||
## 10. 无人值守任务
|
||||
|
||||
### OpenClaw
|
||||
|
||||
任务:`tasks/openclaw-production-deploy-task.yaml`
|
||||
|
||||
职责:
|
||||
|
||||
- 预发布部署;
|
||||
- 健康检查;
|
||||
- Runtime 联调;
|
||||
- 小型部署与 Runtime Bug 修复;
|
||||
- 证据回写。
|
||||
|
||||
### Codex
|
||||
|
||||
任务:`tasks/codex-production-supervisor-task.yaml`
|
||||
|
||||
职责:
|
||||
|
||||
- 架构监督;
|
||||
- 阻塞分析和跨模块修复;
|
||||
- 文档、测试和安全审查;
|
||||
- 发布建议。
|
||||
|
||||
所有修改和阻塞必须进入 Git 和 Execution Evidence,最终统一审视。
|
||||
|
||||
## 11. 当前已知风险
|
||||
|
||||
| 风险 | 级别 | 当前处理 |
|
||||
|---|---|---|
|
||||
| 精确 Candidate Commit 尚未执行全部测试 | 高 | OpenClaw 执行,Codex 监督 |
|
||||
| 真实 OpenClaw Runtime 尚未联调 | 高 | 预发布任务必须完成 |
|
||||
| 候选 SQLite 不支持生产多实例 HA | 高 | Candidate 单实例;后续 ADR 迁移 |
|
||||
| 身份代理 Header 防伪尚未环境验证 | 高 | 预发布安全检查 |
|
||||
| Web Console 为候选只读 MVP | 中 | 生产前补充 E2E 与安全验证 |
|
||||
| 部分策略负向、并发和审计测试待补强 | 中 | Codex 登记 blocker 并补充 |
|
||||
| 本地/Gitea 自动双写状态仍需持续证明 | 中 | 验收记录 OID |
|
||||
| 性能、容量和 SLO 尚无实测 | 中 | 预发布基准测试 |
|
||||
| 外部不可变审计固化尚未实现 | 中 | 生产数据层阶段完成 |
|
||||
|
||||
## 12. 发布 Gate
|
||||
|
||||
### 允许进入预发布
|
||||
|
||||
条件:
|
||||
|
||||
- Candidate 分支可见;
|
||||
- 文档完整;
|
||||
- 任务合同已生成;
|
||||
- 部署资产存在;
|
||||
- 无明文 Secret。
|
||||
|
||||
### 允许进入合并审查
|
||||
|
||||
条件:
|
||||
|
||||
- 全量验收通过;
|
||||
- OpenClaw/Hermes 联调通过;
|
||||
- 重启和回滚通过;
|
||||
- 严重/高风险 blocker 已解决;
|
||||
- Codex 输出正向监督结论;
|
||||
- 本地/Gitea OID 一致。
|
||||
|
||||
### 允许生产发布
|
||||
|
||||
条件:
|
||||
|
||||
- Owner 明确批准;
|
||||
- Merge 与 Tag 通过受控流程;
|
||||
- 生产配置、Secret 和反向代理准备完成;
|
||||
- 发布窗口、观察指标、回滚负责人明确。
|
||||
|
||||
## 13. 当前结论
|
||||
|
||||
**代码和正式中文文档已经达到候选闭环状态,但尚不能宣称生产已验证。**
|
||||
|
||||
下一阶段由 OpenClaw 执行预发布部署和低风险 Bug 修复,由 Codex 监督架构、文档、安全、测试和阻塞。所有过程证据统一进入系统,满足 Gate 后再请求 Owner 批准。
|
||||
|
||||
## 14. 更新规则
|
||||
|
||||
以下变化必须更新本报告:
|
||||
|
||||
- Candidate Commit;
|
||||
- 测试结果;
|
||||
- 部署和回滚结果;
|
||||
- Blocker 和风险;
|
||||
- OpenClaw/Codex 任务状态;
|
||||
- 文档—代码匹配状态;
|
||||
- Gitea OID;
|
||||
- 发布建议和 Owner 决策。
|
||||
@@ -0,0 +1,56 @@
|
||||
"""API adapter for agent context routing and visibility."""
|
||||
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from fastapi import APIRouter
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .agent_context_dashboard import AgentContextDashboard
|
||||
from .agent_context_rbac import AgentContextRBAC
|
||||
from .agent_context_resolver import AgentContextResolver
|
||||
|
||||
resolver = AgentContextResolver()
|
||||
rbac = AgentContextRBAC()
|
||||
dashboard = AgentContextDashboard()
|
||||
|
||||
|
||||
def resolve_agent_context(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
route = rbac.route(payload["user_id"], payload.get("group_id"), payload.get("role", "user"))
|
||||
context = resolver.resolve(
|
||||
user_id=payload["user_id"],
|
||||
group_id=payload.get("group_id", ""),
|
||||
session=payload.get("session"),
|
||||
user_profile=payload.get("user_profile"),
|
||||
group_policy=payload.get("group_policy"),
|
||||
agent_default=payload.get("agent_default"),
|
||||
owner_policy=payload.get("owner_policy"),
|
||||
owner=payload.get("role") == "owner",
|
||||
)
|
||||
return {"routing": route.to_dict(), "context": context.to_dict()}
|
||||
|
||||
|
||||
def get_context_dashboard() -> dict[str, Any]:
|
||||
return dashboard.overview()
|
||||
|
||||
|
||||
def build_router():
|
||||
if APIRouter is None:
|
||||
return None
|
||||
router = APIRouter(prefix="/admin/ai-evolution/context", tags=["context-isolation"])
|
||||
|
||||
@router.post("/resolve", operation_id="resolveAgentContext")
|
||||
def resolve(payload: dict[str, Any]):
|
||||
return resolve_agent_context(payload)
|
||||
|
||||
@router.get("/overview", operation_id="getAgentContextDashboard")
|
||||
def overview():
|
||||
return get_context_dashboard()
|
||||
|
||||
return router
|
||||
|
||||
|
||||
router = build_router()
|
||||
|
||||
__all__ = ["router", "resolve_agent_context", "get_context_dashboard"]
|
||||
@@ -0,0 +1,23 @@
|
||||
"""Audit context resolution decisions."""
|
||||
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
|
||||
def utc_now():
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
class AgentContextAudit:
|
||||
def record(self, context: dict[str, Any]) -> dict[str, Any]:
|
||||
return {
|
||||
"event": "context_loaded",
|
||||
"agent_id": context.get("agent_id"),
|
||||
"user_id": context.get("user_id"),
|
||||
"group_id": context.get("group_id"),
|
||||
"layers": [x.get("name") for x in context.get("layers", [])],
|
||||
"timestamp": utc_now(),
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["AgentContextAudit"]
|
||||
@@ -0,0 +1,47 @@
|
||||
"""Web UI model for context isolation visibility."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
|
||||
class AgentContextDashboard:
|
||||
def overview(self, contexts: list[dict[str, Any]] | None = None) -> dict[str, Any]:
|
||||
contexts = contexts or []
|
||||
return {
|
||||
"module": "agent-context-isolation",
|
||||
"route": "/admin/ai-evolution/context",
|
||||
"title": "Agent Context Isolation",
|
||||
"panels": [
|
||||
{
|
||||
"name": "agent-routing",
|
||||
"title": "Agent 路由",
|
||||
"data": contexts,
|
||||
},
|
||||
{
|
||||
"name": "context-layers",
|
||||
"title": "Context 来源层级",
|
||||
"layers": [
|
||||
"safety_policy",
|
||||
"owner_policy",
|
||||
"group_policy",
|
||||
"role_policy",
|
||||
"user_profile",
|
||||
"session_context",
|
||||
"agent_default",
|
||||
],
|
||||
},
|
||||
{
|
||||
"name": "audit",
|
||||
"title": "Context 审计",
|
||||
"events": [
|
||||
"context_loaded",
|
||||
"profile_updated",
|
||||
"agent_selected",
|
||||
],
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["AgentContextDashboard"]
|
||||
@@ -0,0 +1,55 @@
|
||||
"""RBAC binding for group main agents and owner agents."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass
|
||||
from typing import Any
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AgentRoutingDecision:
|
||||
user_id: str
|
||||
group_id: str
|
||||
role: str
|
||||
agent_id: str
|
||||
scope: str
|
||||
allowed: bool
|
||||
reason: str
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class AgentContextRBAC:
|
||||
"""Routes users to group agents and owners to dedicated owner agents."""
|
||||
|
||||
VALID_ROLES = {"user", "group_admin", "owner"}
|
||||
|
||||
def route(self, user_id: str, group_id: str | None, role: str) -> AgentRoutingDecision:
|
||||
if role not in self.VALID_ROLES:
|
||||
return AgentRoutingDecision(user_id, group_id or "", role, "", "none", False, "unknown_role")
|
||||
if role == "owner":
|
||||
return AgentRoutingDecision(
|
||||
user_id=user_id,
|
||||
group_id=group_id or "global",
|
||||
role=role,
|
||||
agent_id=f"owner-agent:{user_id}",
|
||||
scope="global",
|
||||
allowed=True,
|
||||
reason="owner_dedicated_agent",
|
||||
)
|
||||
if not group_id:
|
||||
return AgentRoutingDecision(user_id, "", role, "", "none", False, "group_required")
|
||||
scope = "group" if role == "group_admin" else "self"
|
||||
return AgentRoutingDecision(
|
||||
user_id=user_id,
|
||||
group_id=group_id,
|
||||
role=role,
|
||||
agent_id=f"group-main-agent:{group_id}",
|
||||
scope=scope,
|
||||
allowed=True,
|
||||
reason="group_agent_routing",
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["AgentRoutingDecision", "AgentContextRBAC"]
|
||||
@@ -0,0 +1,82 @@
|
||||
"""Multi-user agent context resolver.
|
||||
|
||||
Architecture:
|
||||
- shared agent kernel
|
||||
- group main agent
|
||||
- owner dedicated agent
|
||||
- user profile overlay
|
||||
- session overlay
|
||||
|
||||
Personal preferences never enter shared USER.md.
|
||||
"""
|
||||
|
||||
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 ContextLayer:
|
||||
name: str
|
||||
priority: int
|
||||
data: dict[str, Any]
|
||||
|
||||
|
||||
@dataclass
|
||||
class EffectiveContext:
|
||||
agent_id: str
|
||||
user_id: str
|
||||
group_id: str
|
||||
layers: list[ContextLayer]
|
||||
resolved: dict[str, Any]
|
||||
resolved_at: str = field(default_factory=utc_now)
|
||||
|
||||
def to_dict(self):
|
||||
return {
|
||||
"agent_id": self.agent_id,
|
||||
"user_id": self.user_id,
|
||||
"group_id": self.group_id,
|
||||
"layers": [asdict(x) for x in self.layers],
|
||||
"resolved": self.resolved,
|
||||
"resolved_at": self.resolved_at,
|
||||
}
|
||||
|
||||
|
||||
class AgentContextResolver:
|
||||
"""Resolves context without shared user-state pollution."""
|
||||
|
||||
def resolve(
|
||||
self,
|
||||
user_id: str,
|
||||
group_id: str,
|
||||
session: dict[str, Any] | None = None,
|
||||
user_profile: dict[str, Any] | None = None,
|
||||
group_policy: dict[str, Any] | None = None,
|
||||
agent_default: dict[str, Any] | None = None,
|
||||
owner_policy: dict[str, Any] | None = None,
|
||||
owner: bool = False,
|
||||
) -> EffectiveContext:
|
||||
layers = [
|
||||
ContextLayer("agent_default", 10, agent_default or {}),
|
||||
ContextLayer("group_policy", 30, group_policy or {}),
|
||||
ContextLayer("user_profile", 50, user_profile or {}),
|
||||
ContextLayer("session", 70, session or {}),
|
||||
]
|
||||
agent_id = f"group-main-agent:{group_id}"
|
||||
if owner:
|
||||
agent_id = f"owner-agent:{user_id}"
|
||||
layers.append(ContextLayer("owner_policy", 90, owner_policy or {}))
|
||||
resolved: dict[str, Any] = {}
|
||||
# Higher priority overlays lower priority except safety policies handled upstream.
|
||||
for layer in sorted(layers, key=lambda x: x.priority):
|
||||
resolved.update(layer.data)
|
||||
return EffectiveContext(agent_id, user_id, group_id, layers, resolved)
|
||||
|
||||
|
||||
__all__ = ["ContextLayer", "EffectiveContext", "AgentContextResolver"]
|
||||
@@ -0,0 +1,37 @@
|
||||
"""Bridge Agent Event Bus events into Agent Observability metrics."""
|
||||
|
||||
from .agent_observability_hooks import AgentObservabilityHooks
|
||||
|
||||
|
||||
class AgentEventObservabilityBridge:
|
||||
def __init__(self, hooks: AgentObservabilityHooks | None = None):
|
||||
self.hooks = hooks or AgentObservabilityHooks()
|
||||
|
||||
def consume(self, event: dict):
|
||||
kind = event.get("kind")
|
||||
payload = event.get("payload", {})
|
||||
if kind == "agent_started":
|
||||
return self.hooks.start(
|
||||
user_id=payload.get("user_id", "unknown"),
|
||||
visible_scope=payload.get("scope", "self"),
|
||||
entry_agent=payload.get("agent", "unknown"),
|
||||
execution_id=event.get("id"),
|
||||
)
|
||||
if kind == "agent_delegated":
|
||||
return self.hooks.delegate(event["execution_id"], payload.get("agent", "unknown"))
|
||||
if kind == "token_consumed":
|
||||
return self.hooks.tokens(
|
||||
event["execution_id"],
|
||||
payload.get("input_tokens", 0),
|
||||
payload.get("output_tokens", 0),
|
||||
)
|
||||
if kind in {"agent_completed", "agent_failed"}:
|
||||
return self.hooks.finish(
|
||||
event["execution_id"],
|
||||
payload.get("closed_by"),
|
||||
"failed" if kind == "agent_failed" else "completed",
|
||||
)
|
||||
return {"status": "ignored", "kind": kind}
|
||||
|
||||
|
||||
__all__ = ["AgentEventObservabilityBridge"]
|
||||
@@ -0,0 +1,80 @@
|
||||
"""Agent orchestration observability model.
|
||||
|
||||
Tracks OpenClaw, Hermes and sub-agent execution chains. Token usage is optional
|
||||
and depends on model adapter instrumentation.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
|
||||
def utc_now():
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
@dataclass
|
||||
class AgentExecutionRecord:
|
||||
execution_id: str
|
||||
user_id: str
|
||||
visible_scope: str
|
||||
entry_agent: str
|
||||
path: list[str]
|
||||
used_hermes: bool
|
||||
closed_by: str
|
||||
duration_ms: int = 0
|
||||
input_tokens: int | None = None
|
||||
output_tokens: int | None = None
|
||||
total_tokens: int | None = None
|
||||
status: str = "completed"
|
||||
started_at: str = field(default_factory=utc_now)
|
||||
ended_at: str = field(default_factory=utc_now)
|
||||
|
||||
def to_dict(self):
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class AgentObservability:
|
||||
def __init__(self):
|
||||
self.records: list[AgentExecutionRecord] = []
|
||||
|
||||
def record(self, record: AgentExecutionRecord):
|
||||
self.records.append(record)
|
||||
return record.to_dict()
|
||||
|
||||
def summary(self, user_id: str | None = None) -> dict[str, Any]:
|
||||
records = [r for r in self.records if not user_id or r.user_id == user_id]
|
||||
hermes = [r for r in records if r.used_hermes]
|
||||
direct = [r for r in records if not r.used_hermes]
|
||||
return {
|
||||
"total_executions": len(records),
|
||||
"openclaw_independent_loops": len(direct),
|
||||
"hermes_orchestrated_loops": len(hermes),
|
||||
"average_duration_ms": (
|
||||
sum(r.duration_ms for r in records) / len(records) if records else 0
|
||||
),
|
||||
"token_usage": {
|
||||
"input": sum(r.input_tokens or 0 for r in records),
|
||||
"output": sum(r.output_tokens or 0 for r in records),
|
||||
"total": sum(r.total_tokens or 0 for r in records),
|
||||
},
|
||||
}
|
||||
|
||||
def hermes_tree(self, user_id: str | None = None):
|
||||
return [
|
||||
{
|
||||
"execution_id": r.execution_id,
|
||||
"entry": r.entry_agent,
|
||||
"used_hermes": r.used_hermes,
|
||||
"children": r.path,
|
||||
"duration_ms": r.duration_ms,
|
||||
"tokens": r.total_tokens,
|
||||
}
|
||||
for r in self.records
|
||||
if (not user_id or r.user_id == user_id)
|
||||
]
|
||||
|
||||
|
||||
__all__ = ["AgentExecutionRecord", "AgentObservability"]
|
||||
@@ -0,0 +1,52 @@
|
||||
"""API for agent orchestration observability."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from fastapi import APIRouter
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .agent_observability import AgentExecutionRecord
|
||||
from .agent_observability_dashboard import AgentObservabilityDashboard
|
||||
from .agent_observability_store import AgentObservabilityStore
|
||||
|
||||
store = AgentObservabilityStore()
|
||||
dashboard = AgentObservabilityDashboard(store.load())
|
||||
|
||||
|
||||
def record_agent_execution(payload: dict[str, Any]):
|
||||
record = AgentExecutionRecord(**payload)
|
||||
return {"status": "ok", "record": store.append(record)}
|
||||
|
||||
|
||||
def get_agent_observability(user_id: str | None = None, group_id: str | None = None, role: str = "user"):
|
||||
records = store.query(user_id, group_id, role)
|
||||
return {
|
||||
"status": "ok",
|
||||
"records": records,
|
||||
"summary": store.load().summary(user_id if role != "owner" else None),
|
||||
}
|
||||
|
||||
|
||||
def build_router():
|
||||
if APIRouter is None:
|
||||
return None
|
||||
router = APIRouter(prefix="/admin/ai-evolution/agents", tags=["agent-observability"])
|
||||
|
||||
@router.post("/execution", operation_id="recordAgentExecution")
|
||||
def record(payload: dict[str, Any]):
|
||||
return record_agent_execution(payload)
|
||||
|
||||
@router.get("/overview", operation_id="getAgentObservabilityOverview")
|
||||
def overview(user_id: str | None = None, group_id: str | None = None, role: str = "user"):
|
||||
return get_agent_observability(user_id, group_id, role)
|
||||
|
||||
return router
|
||||
|
||||
|
||||
router = build_router()
|
||||
|
||||
__all__ = ["router", "record_agent_execution", "get_agent_observability"]
|
||||
@@ -0,0 +1,44 @@
|
||||
"""Web UI dashboard model for agent execution visibility."""
|
||||
|
||||
from .agent_observability import AgentObservability
|
||||
|
||||
|
||||
class AgentObservabilityDashboard:
|
||||
def __init__(self, observability: AgentObservability | None = None):
|
||||
self.observability = observability or AgentObservability()
|
||||
|
||||
def overview(self, user_id: str | None = None):
|
||||
return {
|
||||
"route": "/admin/ai-evolution/agents",
|
||||
"title": "Agent Orchestration Observability",
|
||||
"summary": self.observability.summary(user_id),
|
||||
"views": [
|
||||
{
|
||||
"name": "scheduler_flow",
|
||||
"title": "OpenClaw/Hermes 调度流程",
|
||||
"data": self.observability.hermes_tree(user_id),
|
||||
},
|
||||
{
|
||||
"name": "agent_metrics",
|
||||
"title": "智能体指标",
|
||||
"fields": [
|
||||
"duration_ms",
|
||||
"input_tokens",
|
||||
"output_tokens",
|
||||
"total_tokens",
|
||||
"status",
|
||||
],
|
||||
},
|
||||
{
|
||||
"name": "loop_distribution",
|
||||
"title": "闭环分布",
|
||||
"fields": [
|
||||
"openclaw_independent_loops",
|
||||
"hermes_orchestrated_loops",
|
||||
],
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["AgentObservabilityDashboard"]
|
||||
@@ -0,0 +1,113 @@
|
||||
"""Runtime hooks for Agent Observability.
|
||||
|
||||
OpenClaw/Hermes/sub-agents can call these hooks at start/end/delegation points.
|
||||
The hooks store sanitized metadata only: no prompts, no secrets, no private message
|
||||
content.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
from uuid import uuid4
|
||||
|
||||
from .agent_observability import AgentExecutionRecord
|
||||
from .agent_observability_store import AgentObservabilityStore
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def parse_time(value: str) -> datetime:
|
||||
return datetime.fromisoformat(value.replace("Z", "+00:00"))
|
||||
|
||||
|
||||
@dataclass
|
||||
class AgentRunContext:
|
||||
execution_id: str
|
||||
user_id: str
|
||||
visible_scope: str
|
||||
entry_agent: str
|
||||
path: list[str] = field(default_factory=list)
|
||||
used_hermes: bool = False
|
||||
started_at: str = field(default_factory=utc_now)
|
||||
input_tokens: int = 0
|
||||
output_tokens: int = 0
|
||||
status: str = "running"
|
||||
|
||||
def delegate(self, agent_name: str) -> None:
|
||||
if agent_name not in self.path:
|
||||
self.path.append(agent_name)
|
||||
if agent_name.lower() == "hermes":
|
||||
self.used_hermes = True
|
||||
|
||||
def add_tokens(self, input_tokens: int = 0, output_tokens: int = 0) -> None:
|
||||
self.input_tokens += max(input_tokens, 0)
|
||||
self.output_tokens += max(output_tokens, 0)
|
||||
|
||||
|
||||
class AgentObservabilityHooks:
|
||||
def __init__(self, store: AgentObservabilityStore | None = None):
|
||||
self.store = store or AgentObservabilityStore()
|
||||
self.active: dict[str, AgentRunContext] = {}
|
||||
|
||||
def start(
|
||||
self,
|
||||
user_id: str,
|
||||
visible_scope: str,
|
||||
entry_agent: str,
|
||||
execution_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
run = AgentRunContext(
|
||||
execution_id=execution_id or f"exec_{uuid4().hex[:12]}",
|
||||
user_id=user_id,
|
||||
visible_scope=visible_scope,
|
||||
entry_agent=entry_agent,
|
||||
path=[entry_agent],
|
||||
used_hermes=entry_agent.lower() == "hermes",
|
||||
)
|
||||
self.active[run.execution_id] = run
|
||||
return {"status": "started", "execution_id": run.execution_id, "run": run.__dict__}
|
||||
|
||||
def delegate(self, execution_id: str, agent_name: str) -> dict[str, Any]:
|
||||
run = self.active[execution_id]
|
||||
run.delegate(agent_name)
|
||||
return {"status": "delegated", "execution_id": execution_id, "path": run.path}
|
||||
|
||||
def tokens(self, execution_id: str, input_tokens: int = 0, output_tokens: int = 0) -> dict[str, Any]:
|
||||
run = self.active[execution_id]
|
||||
run.add_tokens(input_tokens, output_tokens)
|
||||
return {
|
||||
"status": "tokens_recorded",
|
||||
"execution_id": execution_id,
|
||||
"input_tokens": run.input_tokens,
|
||||
"output_tokens": run.output_tokens,
|
||||
"total_tokens": run.input_tokens + run.output_tokens,
|
||||
}
|
||||
|
||||
def finish(self, execution_id: str, closed_by: str | None = None, status: str = "completed") -> dict[str, Any]:
|
||||
run = self.active.pop(execution_id)
|
||||
ended_at = utc_now()
|
||||
duration_ms = int((parse_time(ended_at) - parse_time(run.started_at)).total_seconds() * 1000)
|
||||
record = AgentExecutionRecord(
|
||||
execution_id=run.execution_id,
|
||||
user_id=run.user_id,
|
||||
visible_scope=run.visible_scope,
|
||||
entry_agent=run.entry_agent,
|
||||
path=run.path,
|
||||
used_hermes=run.used_hermes,
|
||||
closed_by=closed_by or run.path[-1],
|
||||
duration_ms=duration_ms,
|
||||
input_tokens=run.input_tokens,
|
||||
output_tokens=run.output_tokens,
|
||||
total_tokens=run.input_tokens + run.output_tokens,
|
||||
status=status,
|
||||
started_at=run.started_at,
|
||||
ended_at=ended_at,
|
||||
)
|
||||
return {"status": "stored", "record": self.store.append(record)}
|
||||
|
||||
|
||||
__all__ = ["AgentRunContext", "AgentObservabilityHooks"]
|
||||
@@ -0,0 +1,45 @@
|
||||
"""Persistent store for agent observability records.
|
||||
|
||||
Stores sanitized execution metrics for OpenClaw/Hermes/sub-agents. No prompts,
|
||||
secrets, or private message contents are persisted here; only metrics and routing
|
||||
metadata are stored for Web UI statistics and audit.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from .agent_observability import AgentExecutionRecord, AgentObservability
|
||||
|
||||
|
||||
class AgentObservabilityStore:
|
||||
def __init__(self, root: str = "runtime/agent-observability"):
|
||||
self.root = Path(root)
|
||||
self.records_dir = self.root / "records"
|
||||
self.records_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def append(self, record: AgentExecutionRecord) -> dict[str, Any]:
|
||||
path = self.records_dir / f"{record.execution_id}.json"
|
||||
data = record.to_dict()
|
||||
path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
return data
|
||||
|
||||
def load(self) -> AgentObservability:
|
||||
observability = AgentObservability()
|
||||
for path in sorted(self.records_dir.glob("*.json")):
|
||||
raw = json.loads(path.read_text(encoding="utf-8"))
|
||||
observability.records.append(AgentExecutionRecord(**raw))
|
||||
return observability
|
||||
|
||||
def query(self, user_id: str | None = None, group_id: str | None = None, role: str = "user") -> list[dict[str, Any]]:
|
||||
records = [record.to_dict() for record in self.load().records]
|
||||
if role == "owner":
|
||||
return records
|
||||
if role == "group_admin" and group_id:
|
||||
return [r for r in records if r.get("visible_scope") == group_id or r.get("user_id") == user_id]
|
||||
return [r for r in records if r.get("user_id") == user_id]
|
||||
|
||||
|
||||
__all__ = ["AgentObservabilityStore"]
|
||||
Regular → Executable
+385
-82
@@ -1,95 +1,398 @@
|
||||
#!/usr/bin/env python3
|
||||
""" AI GitOps Actions API """
|
||||
import asyncio, base64, hashlib, hmac, json, os, re, shutil, subprocess, sys, time, uuid
|
||||
from __future__ import annotations
|
||||
import hashlib, hmac, json, os, re, subprocess, sys, time, urllib.parse, uuid
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from urllib.parse import parse_qs, urlparse
|
||||
from typing import Any
|
||||
|
||||
from aiohttp import web
|
||||
sys.path.insert(0, str(Path(os.getenv('AIOS_GITOPS_WORKSPACE', '/data/aios-gitops/workspace')) / 'runtime' / 'agent-os'))
|
||||
from orchestrator.action_monitor import ActionMonitor
|
||||
|
||||
# Environment
|
||||
WS = Path(os.environ.get("AIOS_WORKSPACE", "/data/aios-gitops/workspace"))
|
||||
BASE_DIR = WS / "active-runtime"
|
||||
APPDIR = BASE_DIR / "app"
|
||||
AUDITDIR = WS / "audit"
|
||||
WORKDIR = WS / "work"
|
||||
DOTDIR = WS.parent
|
||||
GITEA_DIR = DOTDIR / "runtime" / "gitea-bin" / "data" / "repositories" / "aios"
|
||||
ROOT = Path(os.getenv('AIOS_GITOPS_ROOT', '/data/aios-gitops'))
|
||||
WS = Path(os.getenv('AIOS_GITOPS_WORKSPACE', str(ROOT / 'workspace')))
|
||||
SECRETS = Path(os.getenv('AIOS_GITOPS_SECRETS_DIR', str(ROOT / 'runtime' / 'secrets')))
|
||||
TOKEN_FILE = Path(os.getenv('AIOS_GITOPS_TOKEN_FILE', str(SECRETS / 'gitops.tokens')))
|
||||
HOST = os.getenv('AIOS_GITOPS_HOST', '127.0.0.1')
|
||||
PORT = int(os.getenv('AIOS_GITOPS_PORT', '18890'))
|
||||
OPENAPI = WS / 'docs' / 'gitops' / 'openapi-chatgpt-actions.yaml'
|
||||
BARE_REPO = Path(os.getenv('AIOS_GITOPS_BARE_REPO', str(ROOT / 'runtime' / 'gitea-bin' / 'data' / 'repositories' / 'aios' / 'aios.git')))
|
||||
monitor = ActionMonitor()
|
||||
|
||||
# Load config
|
||||
try:
|
||||
import yaml
|
||||
config_path = WS / "active-runtime" / "app" / "config.yaml"
|
||||
with open(config_path) as f:
|
||||
CONFIG = yaml.safe_load(f) or {}
|
||||
except: CONFIG = {}
|
||||
BASE_MODELS = [
|
||||
{'id':'base.deepseekv4-flash','provider':'one-api','model':'deepseekv4-flash','display_name':'DeepSeek V4 Flash','scope':'global'},
|
||||
{'id':'base.qwen3.6-35b','provider':'one-api','model':'qwen3.6-35b','display_name':'Qwen 3.6 35B','scope':'global'},
|
||||
{'id':'base.gpt-5.5','provider':'openai','model':'gpt-5.5','display_name':'GPT-5.5','scope':'global'},
|
||||
]
|
||||
SECRET_RE = re.compile(r'(?i)(api[_-]?key|secret[_-]?access[_-]?key|secret|password|token)\s*[:=]\s*["\']?([A-Za-z0-9_./+=:-]{16,})')
|
||||
SECRET_VAL_RE = re.compile(r'(sk-[A-Za-z0-9_-]{20,}|HPUA[A-Z0-9]{10,}|SDC[A-Za-z0-9]{20,})')
|
||||
|
||||
start_time = time.time()
|
||||
log_ident = "aios-api"
|
||||
def now() -> str: return time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())
|
||||
def uid(p='id') -> str: return f'{p}-{int(time.time()*1000)}-{uuid.uuid4().hex[:8]}'
|
||||
def safe(s: str, n=160) -> str: return re.sub(r'[^A-Za-z0-9_./@-]+', '-', str(s or 'unknown')).strip('/-')[:n] or 'unknown'
|
||||
def sh(args, check=False):
|
||||
p = subprocess.run(['git'] + args, cwd=str(WS), text=True, capture_output=True)
|
||||
if check and p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or 'git failed')
|
||||
return {'code':p.returncode,'stdout':p.stdout.strip(),'stderr':p.stderr.strip(),'cmd':['git']+args}
|
||||
def jload(p: Path, default):
|
||||
try: return json.loads(p.read_text(encoding='utf-8'))
|
||||
except Exception: return default
|
||||
def relpath(path: str) -> str:
|
||||
x = str(path or '').replace('\\','/').strip()
|
||||
if not x or x.startswith('/') or '..' in Path(x).parts or Path(x).parts[0] == '.git': raise ValueError('invalid path')
|
||||
return str(Path(x))
|
||||
def branch_name(name: str | None, prefix='patch/chatgpt') -> str:
|
||||
b = safe(name or f'{prefix}-{uid("br")}', 180)
|
||||
if b in ('main','master') or b.startswith('main/') or b.startswith('master/'): raise ValueError('direct main/master writes are forbidden')
|
||||
return b
|
||||
def _json_has_plain_secret(obj: Any) -> bool:
|
||||
if isinstance(obj, dict):
|
||||
for k, v in obj.items():
|
||||
lk = str(k).lower()
|
||||
if lk == 'secret_ref' or lk.endswith('_secret_ref'):
|
||||
continue
|
||||
if lk in {'api_key', 'access_key', 'secret_access_key', 'secret_key', 'password', 'token', 'bearer_token'}:
|
||||
if isinstance(v, str) and v and not v.startswith('secret://') and v != 'REDACTED':
|
||||
return True
|
||||
if _json_has_plain_secret(v):
|
||||
return True
|
||||
return False
|
||||
if isinstance(obj, list):
|
||||
return any(_json_has_plain_secret(x) for x in obj)
|
||||
if isinstance(obj, str):
|
||||
return bool(obj and not obj.startswith('secret://') and obj != 'REDACTED' and SECRET_VAL_RE.search(obj))
|
||||
return False
|
||||
|
||||
def sh(cmd, **kw):
|
||||
try:
|
||||
r = subprocess.run(cmd, capture_output=True, text=True, cwd=WS, **kw)
|
||||
return r.stdout.strip() if r else None
|
||||
except: return None
|
||||
def content_has_secret(text: str) -> bool:
|
||||
text = text or ''
|
||||
try:
|
||||
return _json_has_plain_secret(json.loads(text))
|
||||
except Exception:
|
||||
pass
|
||||
if SECRET_VAL_RE.search(text):
|
||||
return True
|
||||
for m in SECRET_RE.finditer(text):
|
||||
key = str(m.group(1)).lower()
|
||||
value = str(m.group(2))
|
||||
if 'secret_ref' in key or value.startswith('secret://') or value == 'REDACTED':
|
||||
continue
|
||||
return True
|
||||
return False
|
||||
def token_records():
|
||||
if not TOKEN_FILE.exists(): return []
|
||||
out=[]
|
||||
for raw in TOKEN_FILE.read_text(encoding='utf-8').splitlines():
|
||||
line=raw.strip()
|
||||
if not line or line.startswith('#'): continue
|
||||
if line.startswith('{'):
|
||||
try: out.append(json.loads(line))
|
||||
except Exception: pass
|
||||
else:
|
||||
out.append({'account':'legacy-token','role':'owner','scopes':['*'],'token_plain':line})
|
||||
return out
|
||||
def authenticate(token: str):
|
||||
if os.getenv('AIOS_GITOPS_DEV_ALLOW','0') == '1': return {'account':'dev-owner','role':'owner','scopes':['*']}
|
||||
if not token: return None
|
||||
digest=hashlib.sha256(token.encode()).hexdigest()
|
||||
for r in token_records():
|
||||
if r.get('disabled'): continue
|
||||
if r.get('token_sha256') and hmac.compare_digest(str(r['token_sha256']), digest): return r
|
||||
if r.get('token_plain') and hmac.compare_digest(str(r['token_plain']), token): return r
|
||||
return None
|
||||
def sanitize(obj: Any) -> Any:
|
||||
if isinstance(obj, dict):
|
||||
return {k: ('REDACTED' if re.search(r'(?i)(api[_-]?key|secret|password|token)', str(k)) else sanitize(v)) for k,v in obj.items()}
|
||||
if isinstance(obj, list): return [sanitize(x) for x in obj]
|
||||
if isinstance(obj, str): return SECRET_VAL_RE.sub('REDACTED', obj)
|
||||
return obj
|
||||
def ensure_git():
|
||||
if not sh(['config','user.email'])['stdout']: sh(['config','user.email','chatgpt-gitops-bot@cnnetmkt.top'], True)
|
||||
if not sh(['config','user.name'])['stdout']: sh(['config','user.name','chatgpt-gitops-bot'], True)
|
||||
def checkout(branch, base='main', create=False):
|
||||
ensure_git(); b=branch_name(branch)
|
||||
if create or sh(['rev-parse','--verify',b])['code'] != 0:
|
||||
sh(['checkout',base], True); sh(['checkout','-B',b], True)
|
||||
else: sh(['checkout',b], True)
|
||||
return b
|
||||
def write_file(path, content):
|
||||
if content_has_secret(content): raise ValueError('secret_rejected: use secret_ref; plaintext API keys must not enter Git')
|
||||
r=relpath(path); t=WS/r; t.parent.mkdir(parents=True, exist_ok=True); t.write_text(content, encoding='utf-8'); return r
|
||||
def write_json(path, data): return write_file(path, json.dumps(data, ensure_ascii=False, indent=2) + '\n')
|
||||
def sync_branch(branch: str) -> dict:
|
||||
if not branch or branch in ('main','master') or branch.startswith('main/') or branch.startswith('master/'):
|
||||
return {'status':'skipped','reason':'protected_branch','branch':branch}
|
||||
if BARE_REPO.exists():
|
||||
ref=f'refs/heads/{branch}:refs/heads/{branch}'
|
||||
p=subprocess.run(['git','--git-dir',str(BARE_REPO),'fetch',str(WS),ref], text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git sync failed for {branch}')
|
||||
return {'status':'synced','target':'bare','branch':branch,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
p=subprocess.run(['git','push','origin',f'HEAD:refs/heads/{branch}'], cwd=str(WS), text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git push failed for {branch}')
|
||||
return {'status':'synced','target':'origin','branch':branch,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
|
||||
def baselines():
|
||||
p = WS / "baselines" / "current.json"
|
||||
if p.exists():
|
||||
try: return json.loads(p.read_text())
|
||||
except: pass
|
||||
return {}
|
||||
def sync_tag(tag: str) -> dict:
|
||||
if not tag: return {'status':'skipped','reason':'empty_tag'}
|
||||
if BARE_REPO.exists():
|
||||
ref=f'refs/tags/{tag}:refs/tags/{tag}'
|
||||
p=subprocess.run(['git','--git-dir',str(BARE_REPO),'fetch',str(WS),ref], text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git tag sync failed for {tag}')
|
||||
return {'status':'synced','target':'bare','tag':tag,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
p=subprocess.run(['git','push','origin',tag], cwd=str(WS), text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git tag push failed for {tag}')
|
||||
return {'status':'synced','target':'origin','tag':tag,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
|
||||
def commands(status):
|
||||
d = WS / "agents" / "commands" / status
|
||||
if not d.exists(): return []
|
||||
return [{"name": f.name, "state": status} for f in sorted(d.iterdir()) if f.name.endswith(".md")]
|
||||
def commit(paths, msg):
|
||||
ensure_git(); paths = [relpath(p) for p in paths] if paths else ['.']; sh(['add'] + paths, True)
|
||||
branch=sh(['rev-parse','--abbrev-ref','HEAD'])['stdout']
|
||||
if not sh(['status','--short'])['stdout']:
|
||||
return {'status':'no_changes','branch':branch,'sync':sync_branch(branch)}
|
||||
out=sh(['commit','-m',msg], True); branch=sh(['rev-parse','--abbrev-ref','HEAD'])['stdout']; sync=sync_branch(branch); return {'status':'committed','branch':branch,'rev':sh(['rev-parse','--short','HEAD'], True)['stdout'],'git':out,'sync':sync}
|
||||
def audit(actor, action, target, payload):
|
||||
p=ROOT/'artifacts'/'chatgpt-gitops-audit.jsonl'; p.parent.mkdir(parents=True, exist_ok=True)
|
||||
with p.open('a', encoding='utf-8') as f: f.write(json.dumps({'at':now(),'actor':actor,'action':action,'target':target,'payload':sanitize(payload)}, ensure_ascii=False)+'\n')
|
||||
def model_docs():
|
||||
out=[]
|
||||
for p in sorted((WS/'config'/'model_registry').glob('**/*.json')): out.append(jload(p, {'path':str(p.relative_to(WS))}))
|
||||
return out
|
||||
def patches():
|
||||
out=[]
|
||||
for p in sorted((WS/'patches').glob('**/*.json')): out.append(jload(p, {'path':str(p.relative_to(WS))}))
|
||||
return out
|
||||
|
||||
def agent_runs():
|
||||
d = AUDITDIR / "agent-runs"
|
||||
if not d.exists(): return []
|
||||
rs = []
|
||||
for f in sorted(d.iterdir(), reverse=True):
|
||||
if f.name.endswith(".json"):
|
||||
try:
|
||||
j = json.loads(f.read_text())
|
||||
j["file"] = f.stem
|
||||
rs.append(j)
|
||||
except: pass
|
||||
return rs
|
||||
class H(BaseHTTPRequestHandler):
|
||||
server_version='AIOSChatGPTGitOps/V1R1C0'
|
||||
def sendj(self, data, code=200):
|
||||
b=json.dumps(data, ensure_ascii=False, indent=2).encode(); self.send_response(code); self.send_header('Content-Type','application/json; charset=utf-8'); self.send_header('Content-Length',str(len(b))); self.end_headers(); self.wfile.write(b)
|
||||
def sendt(self, text, ctype='text/plain; charset=utf-8', code=200):
|
||||
b=text.encode(); self.send_response(code); self.send_header('Content-Type',ctype); self.send_header('Content-Length',str(len(b))); self.end_headers(); self.wfile.write(b)
|
||||
def body(self):
|
||||
n=int(self.headers.get('Content-Length','0') or '0'); raw=self.rfile.read(n).decode() if n else '{}'
|
||||
try: return json.loads(raw or '{}')
|
||||
except Exception: return {'_raw':raw}
|
||||
def actor(self):
|
||||
auth=self.headers.get('Authorization',''); tok=auth[7:].strip() if auth.startswith('Bearer ') else self.headers.get('X-AIOS-Token','')
|
||||
rec=authenticate(tok)
|
||||
if rec: return {'ok':True,'account':safe(rec.get('account') or rec.get('name') or 'token-user'),'role':rec.get('role','user'),'scopes':set(rec.get('scopes') or [])}
|
||||
return {'ok':False,'account':'anonymous','role':'anonymous','scopes':set()}
|
||||
def need(self, scope):
|
||||
a=self.actor()
|
||||
if not a['ok']: self.sendj({'error':'unauthorized','hint':'Bearer token required'},401); return None
|
||||
if '*' not in a['scopes'] and scope not in a['scopes']: self.sendj({'error':'forbidden','required_scope':scope,'account':a['account']},403); return None
|
||||
return a
|
||||
def do_GET(self):
|
||||
u=urllib.parse.urlparse(self.path); path=u.path.rstrip('/') if u.path != '/' else u.path; q=urllib.parse.parse_qs(u.query)
|
||||
try:
|
||||
if path in ('/health','/api/health'): return self.sendj({'status':'ok','service':'chatgpt-gitops-adapter','workspace':str(WS)})
|
||||
if path in ('/api/openapi.yaml','/api/openapi-chatgpt-actions.yaml','/api/schema'):
|
||||
return self.sendt(OPENAPI.read_text(encoding='utf-8'), 'application/yaml; charset=utf-8') if OPENAPI.exists() else self.sendj({'error':'schema_missing'},404)
|
||||
if path in ('/api','/api/status'): return self.sendj(api_spec())
|
||||
if path in ('/api/base','/api/baseline','/base'):
|
||||
data=jload(WS/'baseline'/'current.json', {}); data.setdefault('git', sh(['rev-parse','--short','HEAD'])['stdout']); return self.sendj(data)
|
||||
if path in ('/api/ver','/api/versions','/ver'):
|
||||
return self.sendj({'tags':sh(['tag','--list','V*'])['stdout'].splitlines(),'versions_dir':[p.name for p in (WS/'versions').glob('*')],'head':sh(['rev-parse','--short','HEAD'])['stdout']})
|
||||
if path in ('/api/diff','/diff'):
|
||||
frm=(q.get('from') or ['HEAD~1'])[0]; to=(q.get('to') or ['HEAD'])[0]; return self.sendj({'from':frm,'to':to,'diff':sh(['diff',frm,to])})
|
||||
if path in ('/api/patch','/api/patches','/api/branches','/patch'): return self.sendj({'patches':patches(),'branches':sh(['branch','--format','%(refname:short)'])['stdout'].splitlines()})
|
||||
if path in ('/api/model','/model'): return self.sendj({'base':BASE_MODELS,'custom':model_docs(),'priority':[jload(p,{}) for p in sorted((WS/'config'/'model_priority').glob('*.json'))]})
|
||||
if path in ('/api/run','/api/runtime-status','/run'):
|
||||
svc=subprocess.run(['systemctl','is-active','aios-gitops-model-api'], text=True, capture_output=True)
|
||||
return self.sendj({'service':'aios-gitops-model-api','status':svc.stdout.strip() or svc.stderr.strip(),'workspace_branch':sh(['rev-parse','--abbrev-ref','HEAD'])['stdout']})
|
||||
if path in ('/api/action-monitor','/action-monitor'):
|
||||
latest=monitor.latest()
|
||||
ldict={'event_id':latest.event_id,'action':latest.action,'error':latest.error,'context':latest.context,'created_at':latest.created_at} if latest else None
|
||||
return self.sendj({'events':[{"event_id":e.event_id,"action":e.action,"error":e.error,"context":e.context,"created_at":e.created_at} for e in monitor.list_events()],'latest':ldict})
|
||||
# Admin AI Evolution Dashboard
|
||||
if path in ('/admin/ai-evolution','/admin/ai-evolution/'):
|
||||
return self.ai_evolution_page()
|
||||
if path in ('/admin/ai-evolution/api/data'):
|
||||
return self.ai_evolution_data()
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
except Exception as e:
|
||||
monitor.record_failure('do_GET', str(e), {'path':path})
|
||||
return self.sendj({'error':str(e)},500)
|
||||
def do_PUT(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/'); data=self.body()
|
||||
if path == '/api/model-priority': return self.model_priority(data)
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
def do_POST(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/'); data=self.body()
|
||||
try:
|
||||
if path in ('/api/branch','/api/create-branch'): return self.branch(data)
|
||||
if path in ('/api/file','/api/commit-file'): return self.file(data)
|
||||
if path == '/api/commit': return self.commit(data)
|
||||
if path in ('/api/patch','/api/create-patch'): return self.patch(data)
|
||||
if path in ('/api/tag','/api/create-tag'): return self.tag(data)
|
||||
if path == '/api/rollback': return self.rollback(data)
|
||||
if path == '/api/model': return self.model(data)
|
||||
if path == '/api/model-priority': return self.model_priority(data)
|
||||
if path == '/api/nl': return self.nl(data)
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
except Exception as e:
|
||||
monitor.record_failure('do_POST', str(e), {'path':path})
|
||||
return self.sendj({'error':str(e)},500)
|
||||
def branch(self,data):
|
||||
a=self.need('branch:create');
|
||||
if not a: return
|
||||
b=checkout(data.get('branch'), data.get('base','main'), True); meta={'type':'branch','branch':b,'base':data.get('base','main'),'created_by':a['account'],'created_at':now(),'direct_main_push':False,'owner_approval_required':True}
|
||||
r=write_json(f'patches/{safe(b).replace("/","_")}.branch.json', meta); c=commit([r], data.get('message') or f'chore(chatgpt): create {b}'); audit(a['account'],'branch',b,meta); self.sendj({'status':'ok','branch':b,'commit':c})
|
||||
def file(self,data):
|
||||
a=self.need('file:write');
|
||||
if not a: return
|
||||
b=checkout(data.get('branch'), data.get('base','main'), bool(data.get('create_branch'))); r=write_file(data.get('path'), data.get('content','')); c=commit([r], data.get('message') or f'chore(chatgpt): update {r}'); audit(a['account'],'file',r,{'branch':b,'commit':c}); self.sendj({'status':'committed','branch':b,'path':r,'commit':c})
|
||||
def commit(self,data):
|
||||
a=self.need('commit:create');
|
||||
if not a: return
|
||||
b=checkout(data.get('branch') or sh(['rev-parse','--abbrev-ref','HEAD'])['stdout'], data.get('base','main'), False); paths=data.get('paths') or ['.']; paths=[paths] if isinstance(paths,str) else paths; c=commit(paths, data.get('message') or 'chore(chatgpt): commit changes'); audit(a['account'],'commit',b,{'paths':paths,'commit':c}); self.sendj({'status':c['status'],'branch':b,'commit':c})
|
||||
def patch(self,data):
|
||||
a=self.need('patch:create');
|
||||
if not a: return
|
||||
name=data.get('patch_name') or data.get('name') or uid('patch'); b=checkout(data.get('branch') or f'patch/{safe(name)}', data.get('base','main'), True); meta={'id':uid('patch'),'patch_name':name,'branch':b,'risk':data.get('risk','medium'),'description':data.get('description',''),'created_by':a['account'],'created_at':now()}
|
||||
r=write_json(f'patches/{safe(name)}.json', meta); c=commit([r], data.get('message') or f'chore(chatgpt): create patch {name}'); audit(a['account'],'patch',name,meta); self.sendj({'status':'patch_branch_created','patch':meta,'commit':c})
|
||||
def tag(self,data):
|
||||
a=self.need('tag:create');
|
||||
if not a: return
|
||||
ver=data.get('version') or data.get('tag')
|
||||
if not re.match(r'^V\d+R\d+C\d+(-[A-Za-z0-9_.-]+)?$', ver or ''): return self.sendj({'error':'version must match VxRxCx'},400)
|
||||
if data.get('confirm') != True:
|
||||
self.sendj({'status':'confirm_required','operation':'tag','hint':'This operation creates a Git tag. Confirm to proceed.','x-openai-isConsequential':True}, 428)
|
||||
return
|
||||
if a['role'] != 'owner' or not data.get('execute'):
|
||||
b=checkout(data.get('branch') or f'request/tag-{safe(ver)}', 'main', True); req={'version':ver,'requested_by':a['account'],'approval_required':True,'created_at':now()}; r=write_json(f'baseline/tag_requests/{safe(ver)}.json', req); c=commit([r], f'chore(chatgpt): request tag {ver}'); return self.sendj({'status':'approval_required','branch':b,'commit':c})
|
||||
out=sh(['tag','-a',ver,'-m',data.get('message') or f'release {ver}'], True); self.sendj({'status':'tagged','version':ver,'git':out,'sync':sync_tag(ver)})
|
||||
def rollback(self,data):
|
||||
a=self.need('rollback:request');
|
||||
if not a: return
|
||||
target=data.get('target_version') or data.get('version') or data.get('target')
|
||||
if not target: return self.sendj({'error':'target_version required'},400)
|
||||
b=checkout(data.get('branch') or f'request/rollback-{safe(target)}-{uid("rb")}', 'main', True); req={'id':uid('rollback'),'target_version':target,'reason':data.get('reason',''),'requested_by':a['account'],'approval_required':True,'execute':False,'created_at':now()}; r=write_json(f'baseline/rollback_requests/{safe(req["id"])}.json', req); c=commit([r], f'chore(chatgpt): request rollback {target}'); self.sendj({'status':'rollback_request_committed','branch':b,'request':req,'commit':c})
|
||||
def model(self,data):
|
||||
a=self.need('model:write');
|
||||
if not a: return
|
||||
name=data.get('model_name') or data.get('model'); base=(data.get('base_url') or '').rstrip('/'); prov=data.get('provider_name') or 'custom-provider'
|
||||
if not name or not base: return self.sendj({'error':'provider_name/base_url/model_name required'},400)
|
||||
owner=safe(data.get('username') or a['account']); secret_ref=data.get('api_key_secret_ref') or data.get('secret_ref')
|
||||
if data.get('api_key'):
|
||||
d=SECRETS/'llm'/owner; d.mkdir(parents=True, exist_ok=True); sid=uid('llmkey'); p=d/f'{sid}.secret'; p.write_text(str(data['api_key']), encoding='utf-8'); os.chmod(p,0o600); secret_ref=f'secret://llm/{owner}/{sid}'
|
||||
if not secret_ref: return self.sendj({'error':'api_key_secret_ref or api_key required'},400)
|
||||
mid=data.get('model_id') or f'custom.{owner}.{hashlib.sha1((prov+base+name).encode()).hexdigest()[:10]}'; b=checkout(data.get('branch') or f'patch/model-{safe(mid)}','main',True)
|
||||
doc=sanitize({k:v for k,v in data.items() if k!='api_key'}); doc.update({'model_id':mid,'provider_name':prov,'base_url':base,'model_name':name,'api_key_secret_ref':secret_ref,'created_by':a['account'],'created_at':now()})
|
||||
if data.get('confirm') != True:
|
||||
self.sendj({'status':'confirm_required','operation':'model','hint':'This operation registers a new model. Confirm to proceed.','x-openai-isConsequential':True}, 428)
|
||||
return
|
||||
r=write_json(f'config/model_registry/chatgpt/{safe(mid)}.json', doc); c=commit([r], data.get('message') or f'chore(chatgpt): register model {name}'); audit(a['account'],'model',mid,doc); self.sendj({'status':'model_registered','branch':b,'model_id':mid,'secret_ref':secret_ref,'commit':c})
|
||||
def model_priority(self,data):
|
||||
a=self.need('model:priority');
|
||||
if not a: return
|
||||
if data.get('confirm') != True:
|
||||
self.sendj({'status':'confirm_required','operation':'model-priority','hint':'This operation updates model priority. Confirm to proceed.','x-openai-isConsequential':True}, 428)
|
||||
return
|
||||
user=safe(data.get('username') or a['account']); b=checkout(data.get('branch') or f'patch/model-priority-{user}', 'main', True); doc={'username':user,'items':data.get('items') or data.get('priority') or [],'updated_by':a['account'],'updated_at':now()}; r=write_json(f'config/model_priority/{user}.json', doc); c=commit([r], data.get('message') or f'chore(chatgpt): update model priority {user}'); audit(a['account'],'model-priority',user,doc); self.sendj({'status':'updated','branch':b,'priority':doc,'commit':c})
|
||||
def nl(self,data):
|
||||
a=self.need('nl:plan');
|
||||
if not a: return
|
||||
text=data.get('text',''); low=text.lower(); intent='unknown'; plan=[]
|
||||
if 'rollback' in low or '回滚' in text: intent='rollback_request'; plan=['commit rollback request','wait owner/admin approval']
|
||||
elif 'diff' in low or '对比' in text: intent='diff'; plan=['call GET /api/diff']
|
||||
elif 'model' in low or '模型' in text: intent='model_change'; plan=['use POST /api/model or PUT /api/model-priority','commit metadata']
|
||||
elif 'patch' in low or '补丁' in text: intent='patch_create'; plan=['call POST /api/patch']
|
||||
b=checkout(data.get('branch') or f'patch/nl-{uid("nl")}', 'main', True); doc={'id':uid('nl'),'text':text,'intent':intent,'action_plan':plan,'execute':False,'owner_approval_required':True,'created_by':a['account'],'created_at':now()}; r=write_json(f'patches/nl/{safe(doc["id"])}.json', doc); c=commit([r], f'chore(chatgpt): record nl plan {intent}'); self.sendj({'status':'planned','branch':b,'request':doc,'commit':c})
|
||||
_EVOLUTION_HTML = '''<!DOCTYPE html>
|
||||
<html lang=zh-CN>
|
||||
<head>
|
||||
<meta charset=UTF-8>
|
||||
<meta name=viewport content="width=device-width,initial-scale=1.0">
|
||||
<title>AIOS Evolution Dashboard</title>
|
||||
<script src=https://cdn.jsdelivr.net/npm/vue@3/dist/vue.global.prod.js></script>
|
||||
<style>
|
||||
*{margin:0;padding:0;box-sizing:border-box}
|
||||
body{background:#0d1117;color:#c9d1d9;font-size:14px;line-height:1.7;font-family:-apple-system,BlinkMacSystemFont,Segoe UI,Helvetica,Arial,sans-serif}
|
||||
.c{max-width:1000px;margin:0 auto;padding:32px 24px}
|
||||
h1{font-size:24px;color:#58a6ff;margin-bottom:2px}
|
||||
.sub{color:#8b949e;font-size:13px;border-bottom:1px solid #21262d;padding-bottom:16px;margin-bottom:20px;display:flex;justify-content:space-between}
|
||||
.g{display:grid;grid-template-columns:repeat(auto-fill,minmax(160px,1fr));gap:16px;margin-bottom:20px}
|
||||
.s{background:#161b22;border:1px solid #21262d;border-radius:8px;padding:18px;text-align:center}
|
||||
.s .v{font-size:28px;font-weight:700;color:#f0f6fc}
|
||||
.s .l{font-size:11px;color:#8b949e;margin-top:4px}
|
||||
.bx{background:#161b22;border:1px solid #21262d;border-radius:8px;margin-bottom:14px}
|
||||
.bh{border-bottom:1px solid #21262d;padding:10px 16px;font-weight:600;font-size:14px;display:flex;gap:6px;align-items:center}
|
||||
.bd{padding:12px 16px}
|
||||
.rw{display:grid;grid-template-columns:1fr 1fr 100px 60px;gap:8px;padding:8px 16px;border-bottom:1px solid #21262d;font-size:13px;align-items:center;cursor:pointer;transition:background .15s}
|
||||
.rw:hover{background:#1c2128}.rw:last-child{border-bottom:none}
|
||||
.tg{display:inline-block;padding:2px 10px;border-radius:99px;font-size:11px;font-weight:600}
|
||||
.ok{background:#3fb95033;color:#3fb950}.fl{background:#da363333;color:#f85149}.if{background:#1f6feb33;color:#58a6ff}
|
||||
pre{background:#0d1117;padding:12px;border-radius:6px;overflow:auto;font-size:12px;color:#8b949e;max-height:300px;margin-top:8px}select{padding:8px 10px;border:1px solid #30363d;border-radius:6px;background:#21262d;color:#c9d1d9;font-size:13px;max-width:400px;width:100%;margin-bottom:4px;cursor:pointer}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div id=app class=c>
|
||||
<h1>AIOS Evolution Dashboard</h1>
|
||||
<div class=sub><span>Baseline: {{baseline}}</span><span style=color:#8b949e>{{refreshMsg}}</span></div>
|
||||
<div class=g><div class=s><div class=v>{{tot}}</div><div class=l>Commands</div></div><div class=s><div class=v style=color:#3fb950>{{sok}}</div><div class=l>Succeeded</div></div><div class=s><div class=v style=color:#f85149>{{sfail}}</div><div class=l>Failed</div></div><div class=s><div class=v>{{runs}}</div><div class=l>Executions</div></div></div>
|
||||
<div class=bx><div class=bh>Version Timeline</div><div class=bd><div class=rw style=font-weight:600;border-bottom:2px solid #30363d;cursor:default><span>Version</span><span>Time</span><span>Result</span></div><div v-for=v in vs class=rw @click=selVer(v)><span style=color:#58a6ff>{{v.tag}}</span><span>{{v.time||'-'}}</span><span :class="'tg '+v.result">{{v.result||'-'}}</span></div></div></div>
|
||||
<div class=bx><div class=bh>Commands</div><div class=bd><select v-model=cmd @change=loadCmd><option value>-- Select --</option><option v-for=c in cmds :value=c>{{c}}</option></select><pre v-if=cdet>{{cdet}}</pre></div></div>
|
||||
<div class=bx><div class=bh>Recent Agent Runs</div><div class=bd><div class=rw style=font-weight:600;border-bottom:2px solid #30363d;cursor:default><span>Agent</span><span>Command</span><span>Count</span><span>Result</span></div><div v-for=r in aruns class=rw><span>{{r.agent||'-'}}</span><span style=overflow:hidden;white-space:nowrap;text-overflow:ellipsis>{{r.command}}</span><span>{{r.interaction_count||0}}</span><span :class="'tg '+r.final_result">{{r.final_result||'-'}}</span></div></div></div></div>
|
||||
<script>
|
||||
const{createApp,ref,onMounted}=Vue;createApp({setup(){const vs=ref([]),cmds=ref([]),ar=ref([]),cmd=ref(''),cdet=ref(null),tot=ref(0),sok=ref(0),sfail=ref(0),runs=ref(0),baseline=ref('V1R3C1'),refreshMsg=ref('')
|
||||
async function ld(){try{const r=await fetch('/admin/ai-evolution/api/data'),d=await r.json();baseline.value=d.baseline||'V1R3C1';vs.value=d.versions||[];cmds.value=d.commands||[];ar.value=d.agent_runs||[];tot.value=d.stats?.total||0;sok.value=d.stats?.success||0;sfail.value=d.stats?.failed||0;runs.value=d.stats?.agent_runs||0;refreshMsg.value='Last updated: '+new Date().toLocaleString()}catch(e){}}
|
||||
async function loadCmd(){if(!cmd.value){cdet.value=null;return}try{const r=await fetch('/admin/ai-evolution/api/data?command='+encodeURIComponent(cmd.value)),d=await r.json();cdet.value=JSON.stringify(d,null,2)}catch(e){cdet.value='Error'}}
|
||||
function selVer(v){cmd.value=v.tag||v.id||v.version;loadCmd()}
|
||||
onMounted(()=>{ld();setInterval(ld,30000)})
|
||||
return{vs,cmds,ar,cmd,cdet,tot,sok,sfail,runs,baseline,refreshMsg,loadCmd,selVer}})mount('#app')
|
||||
</script></body></html>'''
|
||||
|
||||
async def handle_api(request):
|
||||
path = request.path
|
||||
if path in ('/admin/ai-evolution','/admin/ai-evolution/'):
|
||||
# Serve the HTML page
|
||||
html_path = APPDIR / 'static' / 'admin-ai-evolution.html'
|
||||
if html_path.exists():
|
||||
return web.Response(text=html_path.read_text(), content_type='text/html')
|
||||
return web.Response(text='Dashboard not found', status=404)
|
||||
if path == '/admin/ai-evolution/api/data':
|
||||
result = subprocess.run(['git','tag','--list','V*'], capture_output=True, text=True, cwd=WS)
|
||||
tags = result.stdout.strip().splitlines() if result.returncode == 0 else []
|
||||
h = subprocess.run(['git','rev-parse','--short','HEAD'], capture_output=True, text=True, cwd=WS)
|
||||
head = h.stdout.strip() if h.returncode == 0 else 'unknown'
|
||||
b = subprocess.run(['git','rev-parse','--abbrev-ref','HEAD'], capture_output=True, text=True, cwd=WS)
|
||||
branch = b.stdout.strip() if b.returncode == 0 else 'unknown'
|
||||
return web.json_response({
|
||||
'baseline': baselines(),
|
||||
'versions': [{'tag':t,'name':p.name} for p in sorted((WS/'versions').glob('*')) for t in tags if p.name in t],
|
||||
'commands': commands('active') + commands('running') + commands('completed'),
|
||||
'agent_runs': agent_runs(),
|
||||
'stats': {
|
||||
'current': head,
|
||||
'branch': branch,
|
||||
'uptime': round(time.time()-start_time, 2),
|
||||
'baseline': baselines().get('current_baseline','unknown'),
|
||||
}
|
||||
})
|
||||
return web.json_response({'error':'not_found','path':path}, status=404)
|
||||
def ai_evolution_page(self):
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Type', 'text/html; charset=utf-8')
|
||||
self.send_header('Content-Length', str(len(self._EVOLUTION_HTML)))
|
||||
self.end_headers()
|
||||
self.wfile.write(self._EVOLUTION_HTML.encode())
|
||||
|
||||
app = web.Application()
|
||||
app.router.add_route('GET', '/admin/ai-evolution', handle_api)
|
||||
app.router.add_route('GET', '/admin/ai-evolution/', handle_api)
|
||||
app.router.add_route('GET', '/admin/ai-evolution/api/data', handle_api)
|
||||
def ai_evolution_data(self):
|
||||
q=urllib.parse.urlparse(self.path).query
|
||||
params=urllib.parse.parse_qs(q)
|
||||
cmd_filter=(params.get('command') or [None])[0]
|
||||
bl=jload(WS/'baseline'/'current.json',{})
|
||||
current_ver=bl.get('current_baseline','V1R3C1')
|
||||
tags=sh(['tag','--list','V*'])['stdout'].splitlines() if WS.exists() else []
|
||||
versions=[]
|
||||
if (WS/'baseline'/'promotions').exists():
|
||||
for p in sorted((WS/'baseline'/'promotions').glob('*.json')):
|
||||
d=jload(p,{});v=d.get('version',p.stem)
|
||||
versions.append({'tag':v,'time':d.get('promoted_at','-'),'result':'ok'})
|
||||
for t in tags:
|
||||
if not any(v['tag']==t for v in versions):
|
||||
versions.append({'tag':t,'time':'-','result':'if'})
|
||||
agent_runs=[];ard=WS/'audit'/'agent-runs'
|
||||
if ard.exists():
|
||||
for f in sorted(ard.glob('*.json'),reverse=True)[:50]:
|
||||
d=jload(f,{});agent_runs.append(d) if isinstance(d,dict) else None
|
||||
cmd_dirs=[WS/'agents/commands/active',WS/'agents/commands/running',WS/'agents/commands/completed',WS/'agents/commands/failed']
|
||||
commands=[]
|
||||
for d in cmd_dirs:
|
||||
if d.exists():
|
||||
for f in sorted(d.glob('*.md')):
|
||||
commands.append(f.name)
|
||||
command_detail=None
|
||||
if cmd_filter:
|
||||
for d in cmd_dirs:
|
||||
if d.exists():
|
||||
fp=d/cmd_filter
|
||||
if fp.exists():
|
||||
command_detail={'command':cmd_filter,'content':fp.read_text(encoding='utf-8')}
|
||||
break
|
||||
if not command_detail:
|
||||
command_detail={'command':cmd_filter,'error':'not_found'}
|
||||
return self.sendj(command_detail)
|
||||
completed=list((WS/'agents/commands/completed').glob('*.md')) if (WS/'agents/commands/completed').exists() else []
|
||||
failed=list((WS/'agents/commands/failed').glob('*.md')) if (WS/'agents/commands/failed').exists() else []
|
||||
stats={'total':len(commands),'success':len(completed),'failed':len(failed),'agent_runs':len(agent_runs)}
|
||||
data={'baseline':current_ver,'versions':versions[-30:],'agent_runs':agent_runs,'commands':sorted(set(commands)),'stats':stats}
|
||||
self.sendj(data)
|
||||
|
||||
if __name__ == '__main__':
|
||||
web.run_app(app, host='127.0.0.1', port=18890)
|
||||
|
||||
def api_spec():
|
||||
return {'version':'V1R1C0-chatgpt-actions','openapi':'/api/openapi.yaml','read':['GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /admin/ai-evolution'],'write':['POST /api/branch','POST /api/file','POST /api/commit','POST /api/patch','POST /api/tag','POST /api/rollback','POST /api/model','PUT /api/model-priority','POST /api/nl'],'policy':{'bearer_required_for_write':True,'direct_main_push':False,'delete_tag':False,'owner_approval_required_for_v_level':True,'api_keys_in_git':False,'git_secret_field':'secret_ref','online_git_sync':True}}
|
||||
|
||||
def main():
|
||||
print(f'AIOS ChatGPT GitOps adapter listening on {HOST}:{PORT}')
|
||||
ThreadingHTTPServer((HOST,PORT), H).serve_forever()
|
||||
if __name__ == '__main__': main()
|
||||
@@ -0,0 +1,27 @@
|
||||
"""AIOS-managed Hermes runtime boundary."""
|
||||
|
||||
from .adapter import (
|
||||
HermesAdapter,
|
||||
HermesConflict,
|
||||
HermesNotFound,
|
||||
HermesRuntimeError,
|
||||
InMemoryHermesStore,
|
||||
SQLiteHermesStore,
|
||||
)
|
||||
from .contract import HermesHealth, HermesJob, HermesJobState, HermesResult
|
||||
from .worker import HermesWorker, WorkerRunResult
|
||||
|
||||
__all__ = [
|
||||
"HermesAdapter",
|
||||
"HermesConflict",
|
||||
"HermesHealth",
|
||||
"HermesJob",
|
||||
"HermesJobState",
|
||||
"HermesNotFound",
|
||||
"HermesResult",
|
||||
"HermesRuntimeError",
|
||||
"HermesWorker",
|
||||
"InMemoryHermesStore",
|
||||
"SQLiteHermesStore",
|
||||
"WorkerRunResult",
|
||||
]
|
||||
@@ -0,0 +1,593 @@
|
||||
"""Tenant-partitioned Hermes queue and worker lease boundary."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import sqlite3
|
||||
import threading
|
||||
from dataclasses import asdict, replace
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Iterable, Mapping
|
||||
|
||||
from .contract import (
|
||||
ALLOWED_TRANSITIONS,
|
||||
TERMINAL_STATES,
|
||||
HermesHealth,
|
||||
HermesJob,
|
||||
HermesJobState,
|
||||
HermesResult,
|
||||
utc_now,
|
||||
)
|
||||
|
||||
|
||||
class HermesRuntimeError(RuntimeError):
|
||||
"""Base Hermes runtime-boundary failure."""
|
||||
|
||||
|
||||
class HermesNotFound(HermesRuntimeError):
|
||||
"""A tenant-scoped job was not found."""
|
||||
|
||||
|
||||
class HermesConflict(HermesRuntimeError):
|
||||
"""A state, lease, idempotency, or revision conflict occurred."""
|
||||
|
||||
|
||||
class InMemoryHermesStore:
|
||||
"""Thread-safe reference store; production backends implement this contract."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.lock = threading.RLock()
|
||||
self.jobs: dict[str, HermesJob] = {}
|
||||
self.results: dict[str, HermesResult] = {}
|
||||
self.idempotency: dict[tuple[str, str], tuple[str, str]] = {}
|
||||
self.worker_heartbeats: dict[str, tuple[str, str | None]] = {}
|
||||
|
||||
def persist_locked(self) -> None:
|
||||
"""Persist a mutation while ``lock`` is held; memory stores are a no-op."""
|
||||
|
||||
|
||||
class SQLiteHermesStore(InMemoryHermesStore):
|
||||
"""Durable snapshot for the existing Hermes queue state machine.
|
||||
|
||||
The adapter remains the sole owner of transitions and lease rules. This
|
||||
store only makes its jobs, results, idempotency keys and worker heartbeats
|
||||
survive a process restart.
|
||||
"""
|
||||
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = Path(path).resolve()
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
super().__init__()
|
||||
with self._connect() as connection:
|
||||
connection.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS hermes_state (
|
||||
singleton INTEGER PRIMARY KEY CHECK (singleton = 1),
|
||||
payload TEXT NOT NULL
|
||||
)
|
||||
"""
|
||||
)
|
||||
self._load()
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(str(self.path), timeout=30)
|
||||
connection.execute("PRAGMA journal_mode=WAL")
|
||||
connection.execute("PRAGMA synchronous=FULL")
|
||||
return connection
|
||||
|
||||
@staticmethod
|
||||
def _record(value: HermesJob | HermesResult) -> dict[str, object]:
|
||||
record = asdict(value)
|
||||
record["state"] = value.state.value
|
||||
return record
|
||||
|
||||
def _load(self) -> None:
|
||||
with self.lock, self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT payload FROM hermes_state WHERE singleton = 1"
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return
|
||||
payload = json.loads(str(row[0]))
|
||||
self.jobs = {
|
||||
str(item["job_id"]): HermesJob(**item)
|
||||
for item in payload.get("jobs", [])
|
||||
}
|
||||
self.results = {
|
||||
str(item["job_id"]): HermesResult(**item)
|
||||
for item in payload.get("results", [])
|
||||
}
|
||||
self.idempotency = {
|
||||
(str(item["tenant_id"]), str(item["idempotency_key"])): (
|
||||
str(item["job_id"]),
|
||||
str(item["digest"]),
|
||||
)
|
||||
for item in payload.get("idempotency", [])
|
||||
}
|
||||
self.worker_heartbeats = {
|
||||
str(item["worker_id"]): (
|
||||
str(item["heartbeat_at"]),
|
||||
str(item["job_id"]) if item.get("job_id") is not None else None,
|
||||
)
|
||||
for item in payload.get("worker_heartbeats", [])
|
||||
}
|
||||
|
||||
def persist_locked(self) -> None:
|
||||
payload = {
|
||||
"version": 1,
|
||||
"jobs": [self._record(item) for item in self.jobs.values()],
|
||||
"results": [self._record(item) for item in self.results.values()],
|
||||
"idempotency": [
|
||||
{
|
||||
"tenant_id": tenant_id,
|
||||
"idempotency_key": idempotency_key,
|
||||
"job_id": job_id,
|
||||
"digest": digest,
|
||||
}
|
||||
for (tenant_id, idempotency_key), (job_id, digest)
|
||||
in self.idempotency.items()
|
||||
],
|
||||
"worker_heartbeats": [
|
||||
{
|
||||
"worker_id": worker_id,
|
||||
"heartbeat_at": heartbeat_at,
|
||||
"job_id": job_id,
|
||||
}
|
||||
for worker_id, (heartbeat_at, job_id)
|
||||
in self.worker_heartbeats.items()
|
||||
],
|
||||
}
|
||||
encoded = json.dumps(
|
||||
payload,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
connection.execute(
|
||||
"""
|
||||
INSERT INTO hermes_state(singleton, payload) VALUES(1, ?)
|
||||
ON CONFLICT(singleton) DO UPDATE SET payload=excluded.payload
|
||||
""",
|
||||
(encoded,),
|
||||
)
|
||||
connection.commit()
|
||||
|
||||
|
||||
class HermesAdapter:
|
||||
"""Queue and reconcile Hermes jobs without owning AIOS policy."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
store: InMemoryHermesStore | None = None,
|
||||
*,
|
||||
runtime_id: str = "hermes-runtime",
|
||||
runtime_version: str = "v1",
|
||||
default_lease_seconds: int = 60,
|
||||
) -> None:
|
||||
if default_lease_seconds < 5:
|
||||
raise ValueError("default_lease_seconds must be >= 5")
|
||||
self.store = store or InMemoryHermesStore()
|
||||
self.runtime_id = runtime_id
|
||||
self.runtime_version = runtime_version
|
||||
self.default_lease_seconds = int(default_lease_seconds)
|
||||
|
||||
@staticmethod
|
||||
def _digest(job: HermesJob) -> str:
|
||||
raw = json.dumps(
|
||||
{
|
||||
"tenant_id": job.tenant_id,
|
||||
"cell_id": job.cell_id,
|
||||
"profile_id": job.profile_id,
|
||||
"task_id": job.task_id,
|
||||
"trace_id": job.trace_id,
|
||||
"action": job.action,
|
||||
"payload": dict(job.payload),
|
||||
"priority": job.priority,
|
||||
},
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
).encode("utf-8")
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
@staticmethod
|
||||
def _parse(value: str | None) -> datetime | None:
|
||||
if value is None:
|
||||
return None
|
||||
normalized = value[:-1] + "+00:00" if value.endswith("Z") else value
|
||||
parsed = datetime.fromisoformat(normalized)
|
||||
if parsed.tzinfo is None:
|
||||
raise ValueError("timestamp must include timezone")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
@staticmethod
|
||||
def _format(value: datetime) -> str:
|
||||
return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
@staticmethod
|
||||
def _assert_tenant(job: HermesJob, tenant_id: str) -> None:
|
||||
if job.tenant_id != tenant_id:
|
||||
raise HermesNotFound("job not found")
|
||||
|
||||
def enqueue(self, job: HermesJob) -> HermesJob:
|
||||
if job.state != HermesJobState.QUEUED or job.revision != 1:
|
||||
raise HermesConflict("new job must be QUEUED at revision 1")
|
||||
digest = self._digest(job)
|
||||
idem_ref = (job.tenant_id, job.idempotency_key)
|
||||
with self.store.lock:
|
||||
existing = self.store.jobs.get(job.job_id)
|
||||
if existing is not None:
|
||||
if self._digest(existing) != digest:
|
||||
raise HermesConflict("job_id reused with different content")
|
||||
return existing
|
||||
prior = self.store.idempotency.get(idem_ref)
|
||||
if prior is not None:
|
||||
prior_id, prior_digest = prior
|
||||
if prior_digest != digest:
|
||||
raise HermesConflict("idempotency key reused with different content")
|
||||
return self.store.jobs[prior_id]
|
||||
self.store.jobs[job.job_id] = job
|
||||
self.store.idempotency[idem_ref] = (job.job_id, digest)
|
||||
self.store.persist_locked()
|
||||
return job
|
||||
|
||||
def get(self, job_id: str, *, tenant_id: str) -> HermesJob:
|
||||
with self.store.lock:
|
||||
job = self.store.jobs.get(job_id)
|
||||
if job is None:
|
||||
raise HermesNotFound("job not found")
|
||||
self._assert_tenant(job, tenant_id)
|
||||
return job
|
||||
|
||||
def list_jobs(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
cell_id: str | None = None,
|
||||
profile_id: str | None = None,
|
||||
states: Iterable[HermesJobState | str] | None = None,
|
||||
) -> list[HermesJob]:
|
||||
state_filter = {HermesJobState(item) for item in states} if states else None
|
||||
with self.store.lock:
|
||||
if self._requeue_expired_locked():
|
||||
self.store.persist_locked()
|
||||
jobs = [
|
||||
job
|
||||
for job in self.store.jobs.values()
|
||||
if job.tenant_id == tenant_id
|
||||
and (cell_id is None or job.cell_id == cell_id)
|
||||
and (profile_id is None or job.profile_id == profile_id)
|
||||
and (state_filter is None or job.state in state_filter)
|
||||
]
|
||||
return sorted(jobs, key=lambda item: (item.priority, item.created_at, item.job_id))
|
||||
|
||||
def claim(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
cell_id: str,
|
||||
profile_id: str,
|
||||
worker_id: str,
|
||||
lease_seconds: int | None = None,
|
||||
job_id: str | None = None,
|
||||
) -> HermesJob | None:
|
||||
worker_id = str(worker_id or "").strip()
|
||||
if not worker_id:
|
||||
raise ValueError("worker_id is required")
|
||||
duration = int(lease_seconds or self.default_lease_seconds)
|
||||
if duration < 5:
|
||||
raise ValueError("lease_seconds must be >= 5")
|
||||
with self.store.lock:
|
||||
self._requeue_expired_locked()
|
||||
candidates = [
|
||||
job
|
||||
for job in self.store.jobs.values()
|
||||
if job.tenant_id == tenant_id
|
||||
and job.cell_id == cell_id
|
||||
and job.profile_id == profile_id
|
||||
and (job_id is None or job.job_id == job_id)
|
||||
and job.state == HermesJobState.QUEUED
|
||||
]
|
||||
self.store.worker_heartbeats[worker_id] = (utc_now(), None)
|
||||
if not candidates:
|
||||
self.store.persist_locked()
|
||||
return None
|
||||
current = sorted(
|
||||
candidates,
|
||||
key=lambda item: (item.priority, item.created_at, item.job_id),
|
||||
)[0]
|
||||
claimed = self._transition_locked(
|
||||
current,
|
||||
HermesJobState.CLAIMED,
|
||||
assigned_worker_id=worker_id,
|
||||
lease_expires_at=self._format(
|
||||
datetime.now(timezone.utc) + timedelta(seconds=duration)
|
||||
),
|
||||
)
|
||||
self.store.worker_heartbeats[worker_id] = (utc_now(), claimed.job_id)
|
||||
self.store.persist_locked()
|
||||
return claimed
|
||||
|
||||
def start(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
worker_id: str,
|
||||
expected_revision: int | None = None,
|
||||
) -> HermesJob:
|
||||
with self.store.lock:
|
||||
self._requeue_expired_locked()
|
||||
current = self._owned_job_locked(job_id, tenant_id, worker_id)
|
||||
self._assert_revision(current, expected_revision)
|
||||
updated = self._transition_locked(current, HermesJobState.RUNNING)
|
||||
self.store.persist_locked()
|
||||
return updated
|
||||
|
||||
def heartbeat(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
worker_id: str,
|
||||
lease_seconds: int | None = None,
|
||||
) -> HermesJob:
|
||||
duration = int(lease_seconds or self.default_lease_seconds)
|
||||
if duration < 5:
|
||||
raise ValueError("lease_seconds must be >= 5")
|
||||
with self.store.lock:
|
||||
self._requeue_expired_locked()
|
||||
current = self._owned_job_locked(job_id, tenant_id, worker_id)
|
||||
if current.state not in {HermesJobState.CLAIMED, HermesJobState.RUNNING}:
|
||||
raise HermesConflict("job does not accept heartbeat")
|
||||
updated = replace(
|
||||
current,
|
||||
revision=current.revision + 1,
|
||||
lease_expires_at=self._format(
|
||||
datetime.now(timezone.utc) + timedelta(seconds=duration)
|
||||
),
|
||||
updated_at=utc_now(),
|
||||
)
|
||||
self.store.jobs[job_id] = updated
|
||||
self.store.worker_heartbeats[worker_id] = (utc_now(), job_id)
|
||||
self.store.persist_locked()
|
||||
return updated
|
||||
|
||||
def complete(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
worker_id: str,
|
||||
output: Mapping[str, object],
|
||||
expected_revision: int | None = None,
|
||||
) -> HermesResult:
|
||||
return self._finish(
|
||||
job_id,
|
||||
tenant_id=tenant_id,
|
||||
worker_id=worker_id,
|
||||
state=HermesJobState.COMPLETED,
|
||||
output=output,
|
||||
expected_revision=expected_revision,
|
||||
)
|
||||
|
||||
def fail(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
worker_id: str,
|
||||
error: Mapping[str, object],
|
||||
expected_revision: int | None = None,
|
||||
) -> HermesResult:
|
||||
return self._finish(
|
||||
job_id,
|
||||
tenant_id=tenant_id,
|
||||
worker_id=worker_id,
|
||||
state=HermesJobState.FAILED,
|
||||
error=error,
|
||||
expected_revision=expected_revision,
|
||||
)
|
||||
|
||||
def cancel(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
expected_revision: int | None = None,
|
||||
) -> HermesResult:
|
||||
with self.store.lock:
|
||||
current = self.store.jobs.get(job_id)
|
||||
if current is None:
|
||||
raise HermesNotFound("job not found")
|
||||
self._assert_tenant(current, tenant_id)
|
||||
self._assert_revision(current, expected_revision)
|
||||
if current.state in TERMINAL_STATES:
|
||||
result = self.store.results.get(job_id)
|
||||
if result is None:
|
||||
raise HermesConflict("terminal result missing")
|
||||
if result.state != HermesJobState.CANCELLED:
|
||||
raise HermesConflict("job already has a different terminal result")
|
||||
return result
|
||||
updated = self._transition_locked(current, HermesJobState.CANCELLED)
|
||||
result = HermesResult(
|
||||
job_id=updated.job_id,
|
||||
tenant_id=updated.tenant_id,
|
||||
task_id=updated.task_id,
|
||||
trace_id=updated.trace_id,
|
||||
state=HermesJobState.CANCELLED,
|
||||
worker_id=updated.assigned_worker_id,
|
||||
error={"code": "cancelled", "message": "cancelled by AIOS"},
|
||||
finished_at=utc_now(),
|
||||
)
|
||||
self.store.results[job_id] = result
|
||||
self.store.persist_locked()
|
||||
return result
|
||||
|
||||
def result(self, job_id: str, *, tenant_id: str) -> HermesResult:
|
||||
with self.store.lock:
|
||||
job = self.store.jobs.get(job_id)
|
||||
if job is None:
|
||||
raise HermesNotFound("job not found")
|
||||
self._assert_tenant(job, tenant_id)
|
||||
result = self.store.results.get(job_id)
|
||||
if result is None:
|
||||
raise HermesConflict("job has no terminal result")
|
||||
return result
|
||||
|
||||
def requeue_expired(self) -> tuple[str, ...]:
|
||||
"""Persistently release expired leases without changing policy state."""
|
||||
with self.store.lock:
|
||||
changed = self._requeue_expired_locked()
|
||||
if changed:
|
||||
self.store.persist_locked()
|
||||
return tuple(sorted(changed))
|
||||
|
||||
def health(self) -> HermesHealth:
|
||||
with self.store.lock:
|
||||
if self._requeue_expired_locked():
|
||||
self.store.persist_locked()
|
||||
active_jobs = sum(
|
||||
1 for job in self.store.jobs.values()
|
||||
if job.state in {HermesJobState.CLAIMED, HermesJobState.RUNNING}
|
||||
)
|
||||
queued_jobs = sum(
|
||||
1 for job in self.store.jobs.values()
|
||||
if job.state == HermesJobState.QUEUED
|
||||
)
|
||||
partitions = {
|
||||
(job.tenant_id, job.cell_id, job.profile_id)
|
||||
for job in self.store.jobs.values()
|
||||
}
|
||||
active_workers = sum(
|
||||
1 for heartbeat, _ in self.store.worker_heartbeats.values()
|
||||
if self._parse(heartbeat)
|
||||
and self._parse(heartbeat) >= datetime.now(timezone.utc) - timedelta(seconds=120)
|
||||
)
|
||||
return HermesHealth(
|
||||
runtime_id=self.runtime_id,
|
||||
status="healthy",
|
||||
version=self.runtime_version,
|
||||
heartbeat_at=utc_now(),
|
||||
active_workers=active_workers,
|
||||
active_jobs=active_jobs,
|
||||
queued_jobs=queued_jobs,
|
||||
tenant_partitions=len(partitions),
|
||||
profile_isolation_enforced=True,
|
||||
details={"store": type(self.store).__name__},
|
||||
)
|
||||
|
||||
def _finish(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
worker_id: str,
|
||||
state: HermesJobState,
|
||||
output: Mapping[str, object] | None = None,
|
||||
error: Mapping[str, object] | None = None,
|
||||
expected_revision: int | None,
|
||||
) -> HermesResult:
|
||||
with self.store.lock:
|
||||
self._requeue_expired_locked()
|
||||
current = self._owned_job_locked(job_id, tenant_id, worker_id)
|
||||
if current.state in TERMINAL_STATES:
|
||||
existing = self.store.results.get(job_id)
|
||||
if existing is None:
|
||||
raise HermesConflict("terminal result missing")
|
||||
if (
|
||||
existing.state == state
|
||||
and existing.worker_id == worker_id
|
||||
and existing.output == output
|
||||
and existing.error == error
|
||||
):
|
||||
return existing
|
||||
raise HermesConflict("job already has a different terminal result")
|
||||
self._assert_revision(current, expected_revision)
|
||||
updated = self._transition_locked(current, state)
|
||||
result = HermesResult(
|
||||
job_id=updated.job_id,
|
||||
tenant_id=updated.tenant_id,
|
||||
task_id=updated.task_id,
|
||||
trace_id=updated.trace_id,
|
||||
state=state,
|
||||
worker_id=worker_id,
|
||||
output=output,
|
||||
error=error,
|
||||
started_at=current.updated_at,
|
||||
finished_at=utc_now(),
|
||||
)
|
||||
self.store.results[job_id] = result
|
||||
self.store.worker_heartbeats[worker_id] = (utc_now(), None)
|
||||
self.store.persist_locked()
|
||||
return result
|
||||
|
||||
def _owned_job_locked(self, job_id: str, tenant_id: str, worker_id: str) -> HermesJob:
|
||||
current = self.store.jobs.get(job_id)
|
||||
if current is None:
|
||||
raise HermesNotFound("job not found")
|
||||
self._assert_tenant(current, tenant_id)
|
||||
if current.assigned_worker_id != worker_id:
|
||||
raise HermesConflict("worker does not own job lease")
|
||||
return current
|
||||
|
||||
@staticmethod
|
||||
def _assert_revision(job: HermesJob, expected: int | None) -> None:
|
||||
if expected is not None and job.revision != expected:
|
||||
raise HermesConflict("job revision changed")
|
||||
|
||||
def _transition_locked(
|
||||
self,
|
||||
current: HermesJob,
|
||||
target: HermesJobState,
|
||||
*,
|
||||
assigned_worker_id: str | None = None,
|
||||
lease_expires_at: str | None = None,
|
||||
) -> HermesJob:
|
||||
if target not in ALLOWED_TRANSITIONS[current.state]:
|
||||
raise HermesConflict(
|
||||
f"invalid transition {current.state.value} -> {target.value}"
|
||||
)
|
||||
updated = replace(
|
||||
current,
|
||||
state=target,
|
||||
revision=current.revision + 1,
|
||||
assigned_worker_id=(
|
||||
assigned_worker_id
|
||||
if assigned_worker_id is not None
|
||||
else current.assigned_worker_id
|
||||
),
|
||||
lease_expires_at=(
|
||||
lease_expires_at
|
||||
if lease_expires_at is not None
|
||||
else (None if target in TERMINAL_STATES else current.lease_expires_at)
|
||||
),
|
||||
updated_at=utc_now(),
|
||||
)
|
||||
self.store.jobs[current.job_id] = updated
|
||||
return updated
|
||||
|
||||
def _requeue_expired_locked(self) -> set[str]:
|
||||
now = datetime.now(timezone.utc)
|
||||
changed: set[str] = set()
|
||||
for current in list(self.store.jobs.values()):
|
||||
expiry = self._parse(current.lease_expires_at)
|
||||
if (
|
||||
current.state in {HermesJobState.CLAIMED, HermesJobState.RUNNING}
|
||||
and expiry is not None
|
||||
and expiry <= now
|
||||
):
|
||||
self.store.jobs[current.job_id] = replace(
|
||||
current,
|
||||
state=HermesJobState.QUEUED,
|
||||
revision=current.revision + 1,
|
||||
assigned_worker_id=None,
|
||||
lease_expires_at=None,
|
||||
updated_at=utc_now(),
|
||||
)
|
||||
changed.add(current.job_id)
|
||||
return changed
|
||||
@@ -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))
|
||||
@@ -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 +1,3 @@
|
||||
"""Future AIOS capabilities isolated from the V2R1C1 release line."""
|
||||
|
||||
__all__: list[str] = []
|
||||
@@ -0,0 +1,64 @@
|
||||
"""Channel-neutral adapter contracts for future evaluation."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
from typing import Any, Mapping, Protocol, Sequence, runtime_checkable
|
||||
|
||||
|
||||
class AdapterHealthStatus(str, Enum):
|
||||
HEALTHY = "healthy"
|
||||
DEGRADED = "degraded"
|
||||
UNAVAILABLE = "unavailable"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AdapterHealth:
|
||||
status: AdapterHealthStatus
|
||||
observed_at: str
|
||||
details: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AdapterCapability:
|
||||
name: str
|
||||
version: str = "1"
|
||||
metadata: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AdapterSession:
|
||||
session_id: str
|
||||
tenant_id: str
|
||||
state: str
|
||||
expires_at: str | None = None
|
||||
metadata: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AdapterResult:
|
||||
ok: bool
|
||||
state: str
|
||||
output: Mapping[str, Any] = field(default_factory=dict)
|
||||
error: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class ChannelAdapter(Protocol):
|
||||
def health(self) -> AdapterHealth: ...
|
||||
|
||||
def capabilities(self) -> Sequence[AdapterCapability]: ...
|
||||
|
||||
def open_session(self, *, tenant_id: str) -> AdapterSession: ...
|
||||
|
||||
def execute(
|
||||
self, *, session: AdapterSession, action: str, payload: Mapping[str, Any]
|
||||
) -> AdapterResult: ...
|
||||
|
||||
def cancel(self, *, session: AdapterSession) -> AdapterResult: ...
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class PortalAdapter(ChannelAdapter, Protocol):
|
||||
"""Marker protocol for user-facing portal adapters."""
|
||||
|
||||
@@ -0,0 +1,66 @@
|
||||
"""Platform-neutral authentication-session state machine."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, replace
|
||||
from enum import Enum
|
||||
from typing import Mapping, Any
|
||||
|
||||
|
||||
class AuthSessionState(str, Enum):
|
||||
CREATED = "CREATED"
|
||||
WAITING_FOR_USER = "WAITING_FOR_USER"
|
||||
USER_CONFIRMED = "USER_CONFIRMED"
|
||||
AUTHENTICATED = "AUTHENTICATED"
|
||||
EXPIRED = "EXPIRED"
|
||||
CANCELLED = "CANCELLED"
|
||||
FAILED = "FAILED"
|
||||
|
||||
|
||||
_TRANSITIONS = {
|
||||
AuthSessionState.CREATED: {
|
||||
AuthSessionState.WAITING_FOR_USER,
|
||||
AuthSessionState.CANCELLED,
|
||||
AuthSessionState.FAILED,
|
||||
},
|
||||
AuthSessionState.WAITING_FOR_USER: {
|
||||
AuthSessionState.USER_CONFIRMED,
|
||||
AuthSessionState.EXPIRED,
|
||||
AuthSessionState.CANCELLED,
|
||||
AuthSessionState.FAILED,
|
||||
},
|
||||
AuthSessionState.USER_CONFIRMED: {
|
||||
AuthSessionState.AUTHENTICATED,
|
||||
AuthSessionState.EXPIRED,
|
||||
AuthSessionState.CANCELLED,
|
||||
AuthSessionState.FAILED,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
class InvalidAuthSessionTransition(ValueError):
|
||||
pass
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AuthSession:
|
||||
session_id: str
|
||||
tenant_id: str
|
||||
state: AuthSessionState = AuthSessionState.CREATED
|
||||
expires_at: str | None = None
|
||||
metadata: Mapping[str, Any] | None = None
|
||||
|
||||
def transition(self, target: AuthSessionState) -> "AuthSession":
|
||||
allowed = _TRANSITIONS.get(self.state, set())
|
||||
if target not in allowed:
|
||||
raise InvalidAuthSessionTransition(f"{self.state.value} -> {target.value}")
|
||||
return replace(self, state=target)
|
||||
|
||||
@property
|
||||
def terminal(self) -> bool:
|
||||
return self.state in {
|
||||
AuthSessionState.AUTHENTICATED,
|
||||
AuthSessionState.EXPIRED,
|
||||
AuthSessionState.CANCELLED,
|
||||
AuthSessionState.FAILED,
|
||||
}
|
||||
|
||||
@@ -0,0 +1,147 @@
|
||||
"""Incubator-only versioned contract primitives.
|
||||
|
||||
This module distills the reusable contract-first practices observed in the
|
||||
Personal Weixin golden-contract work without importing channel-specific fields
|
||||
into the AIOS control plane. It is intentionally not imported by production
|
||||
AIOS V2R1 modules.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
|
||||
class ContractViolation(ValueError):
|
||||
"""A payload does not satisfy its declared contract."""
|
||||
|
||||
|
||||
class Compatibility(str, Enum):
|
||||
EXACT = "exact"
|
||||
BACKWARD_COMPATIBLE = "backward_compatible"
|
||||
INCOMPATIBLE = "incompatible"
|
||||
|
||||
|
||||
def canonical_json_bytes(value: Mapping[str, Any]) -> bytes:
|
||||
return json.dumps(
|
||||
dict(value),
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def payload_digest(value: Mapping[str, Any]) -> str:
|
||||
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
|
||||
|
||||
|
||||
@dataclass(frozen=True, order=True)
|
||||
class ContractVersion:
|
||||
major: int
|
||||
minor: int
|
||||
patch: int = 0
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
if min(self.major, self.minor, self.patch) < 0:
|
||||
raise ValueError("contract version components must be non-negative")
|
||||
|
||||
@classmethod
|
||||
def parse(cls, value: str) -> "ContractVersion":
|
||||
parts = str(value or "").strip().split(".")
|
||||
if len(parts) not in {2, 3} or any(not item.isdigit() for item in parts):
|
||||
raise ValueError("contract version must use MAJOR.MINOR[.PATCH]")
|
||||
numbers = [int(item) for item in parts]
|
||||
if len(numbers) == 2:
|
||||
numbers.append(0)
|
||||
return cls(*numbers)
|
||||
|
||||
def __str__(self) -> str:
|
||||
return f"{self.major}.{self.minor}.{self.patch}"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class VersionedContract:
|
||||
name: str
|
||||
version: ContractVersion
|
||||
required_fields: Sequence[str]
|
||||
optional_fields: Sequence[str] = ()
|
||||
forbidden_fields: Sequence[str] = ()
|
||||
secret_fields: Sequence[str] = ()
|
||||
allow_unknown_fields: bool = False
|
||||
metadata: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
name = str(self.name or "").strip()
|
||||
if not name:
|
||||
raise ValueError("contract name is required")
|
||||
object.__setattr__(self, "name", name)
|
||||
required = frozenset(str(item).strip() for item in self.required_fields if str(item).strip())
|
||||
optional = frozenset(str(item).strip() for item in self.optional_fields if str(item).strip())
|
||||
forbidden = frozenset(str(item).strip() for item in self.forbidden_fields if str(item).strip())
|
||||
secrets = frozenset(str(item).strip() for item in self.secret_fields if str(item).strip())
|
||||
if required & forbidden:
|
||||
raise ValueError("required fields cannot also be forbidden")
|
||||
if required & optional:
|
||||
raise ValueError("required and optional fields must be disjoint")
|
||||
object.__setattr__(self, "required_fields", tuple(sorted(required)))
|
||||
object.__setattr__(self, "optional_fields", tuple(sorted(optional)))
|
||||
object.__setattr__(self, "forbidden_fields", tuple(sorted(forbidden)))
|
||||
object.__setattr__(self, "secret_fields", tuple(sorted(secrets)))
|
||||
object.__setattr__(self, "metadata", json.loads(json.dumps(dict(self.metadata), default=str)))
|
||||
|
||||
@property
|
||||
def allowed_fields(self) -> frozenset[str]:
|
||||
return frozenset((*self.required_fields, *self.optional_fields))
|
||||
|
||||
def validate(self, payload: Mapping[str, Any]) -> dict[str, Any]:
|
||||
normalized = json.loads(json.dumps(dict(payload), ensure_ascii=False, default=str))
|
||||
fields = set(normalized)
|
||||
missing = sorted(set(self.required_fields) - fields)
|
||||
forbidden = sorted(set(self.forbidden_fields) & fields)
|
||||
unknown = sorted(fields - self.allowed_fields)
|
||||
if missing:
|
||||
raise ContractViolation(f"missing required fields: {missing}")
|
||||
if forbidden:
|
||||
raise ContractViolation(f"forbidden fields present: {forbidden}")
|
||||
if unknown and not self.allow_unknown_fields:
|
||||
raise ContractViolation(f"unknown fields present: {unknown}")
|
||||
return normalized
|
||||
|
||||
def redact(self, payload: Mapping[str, Any]) -> dict[str, Any]:
|
||||
normalized = json.loads(json.dumps(dict(payload), ensure_ascii=False, default=str))
|
||||
for field_name in self.secret_fields:
|
||||
if field_name in normalized:
|
||||
normalized[field_name] = "***"
|
||||
return normalized
|
||||
|
||||
def compatibility_with(self, previous: "VersionedContract") -> Compatibility:
|
||||
if self.name != previous.name:
|
||||
return Compatibility.INCOMPATIBLE
|
||||
if self.version == previous.version and self == previous:
|
||||
return Compatibility.EXACT
|
||||
if self.version.major != previous.version.major:
|
||||
return Compatibility.INCOMPATIBLE
|
||||
if not set(previous.required_fields).issubset(self.allowed_fields):
|
||||
return Compatibility.INCOMPATIBLE
|
||||
if set(previous.allowed_fields) & set(self.forbidden_fields):
|
||||
return Compatibility.INCOMPATIBLE
|
||||
if not self.allow_unknown_fields and not set(previous.allowed_fields).issubset(self.allowed_fields):
|
||||
return Compatibility.INCOMPATIBLE
|
||||
return Compatibility.BACKWARD_COMPATIBLE
|
||||
|
||||
def descriptor(self) -> dict[str, Any]:
|
||||
value = {
|
||||
"name": self.name,
|
||||
"version": str(self.version),
|
||||
"required_fields": list(self.required_fields),
|
||||
"optional_fields": list(self.optional_fields),
|
||||
"forbidden_fields": list(self.forbidden_fields),
|
||||
"secret_fields": list(self.secret_fields),
|
||||
"allow_unknown_fields": self.allow_unknown_fields,
|
||||
"metadata": dict(self.metadata),
|
||||
}
|
||||
value["descriptor_digest"] = payload_digest(value)
|
||||
return value
|
||||
@@ -0,0 +1,90 @@
|
||||
"""Evidence integrity and replacement-audit primitives."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
from dataclasses import dataclass, field, replace
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
|
||||
class EvidenceIntegrityError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def sha256_file(path: Path) -> str:
|
||||
digest = hashlib.sha256()
|
||||
with path.open("rb") as stream:
|
||||
for chunk in iter(lambda: stream.read(65536), b""):
|
||||
digest.update(chunk)
|
||||
return digest.hexdigest()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LogReplacement:
|
||||
artifact: str
|
||||
previous_sha256: str
|
||||
replacement_sha256: str
|
||||
reason: str
|
||||
replaced_at: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EvidenceManifest:
|
||||
command: Sequence[str]
|
||||
start_time: str
|
||||
end_time: str
|
||||
exit_code: int
|
||||
artifacts: Mapping[str, str]
|
||||
result_summary: Mapping[str, Any] = field(default_factory=dict)
|
||||
reviewer_status: str = "PENDING"
|
||||
supersedes: Sequence[str] = ()
|
||||
replacement_audit: Sequence[LogReplacement] = ()
|
||||
|
||||
def validate(self, root: Path) -> None:
|
||||
for relative, expected in self.artifacts.items():
|
||||
path = (root / relative).resolve()
|
||||
if root.resolve() not in path.parents:
|
||||
raise EvidenceIntegrityError("artifact escapes evidence root")
|
||||
if not path.is_file():
|
||||
raise EvidenceIntegrityError(f"artifact missing: {relative}")
|
||||
actual = sha256_file(path)
|
||||
if actual != expected:
|
||||
raise EvidenceIntegrityError(f"artifact hash mismatch: {relative}")
|
||||
|
||||
def replace_artifact(
|
||||
self, *, artifact: str, replacement_sha256: str, reason: str, replaced_at: str
|
||||
) -> "EvidenceManifest":
|
||||
previous = self.artifacts.get(artifact)
|
||||
if previous is None:
|
||||
raise EvidenceIntegrityError("replacement target is not registered")
|
||||
if not reason.strip():
|
||||
raise EvidenceIntegrityError("replacement reason is required")
|
||||
updated = dict(self.artifacts)
|
||||
updated[artifact] = replacement_sha256
|
||||
audit = LogReplacement(
|
||||
artifact=artifact,
|
||||
previous_sha256=previous,
|
||||
replacement_sha256=replacement_sha256,
|
||||
reason=reason,
|
||||
replaced_at=replaced_at,
|
||||
)
|
||||
return replace(
|
||||
self,
|
||||
artifacts=updated,
|
||||
replacement_audit=(*self.replacement_audit, audit),
|
||||
)
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"command": list(self.command),
|
||||
"start_time": self.start_time,
|
||||
"end_time": self.end_time,
|
||||
"exit_code": self.exit_code,
|
||||
"artifacts": dict(self.artifacts),
|
||||
"result_summary": json.loads(json.dumps(dict(self.result_summary), default=str)),
|
||||
"reviewer_status": self.reviewer_status,
|
||||
"supersedes": list(self.supersedes),
|
||||
"replacement_audit": [item.__dict__ for item in self.replacement_audit],
|
||||
}
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
"""Provider-neutral runner lifecycle contracts."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
from typing import Any, Mapping, Protocol, runtime_checkable
|
||||
|
||||
|
||||
class RunnerStatus(str, Enum):
|
||||
PROVISIONING = "provisioning"
|
||||
READY = "ready"
|
||||
RUNNING = "running"
|
||||
CANCELLED = "cancelled"
|
||||
FAILED = "failed"
|
||||
DEPROVISIONED = "deprovisioned"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RunnerHandle:
|
||||
runner_id: str
|
||||
provider: str
|
||||
status: RunnerStatus
|
||||
metadata: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RunnerHealth:
|
||||
ok: bool
|
||||
status: RunnerStatus
|
||||
observed_at: str
|
||||
details: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RunnerExecution:
|
||||
execution_id: str
|
||||
runner_id: str
|
||||
status: RunnerStatus
|
||||
exit_code: int | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RunnerEvidence:
|
||||
execution_id: str
|
||||
artifacts: Mapping[str, str]
|
||||
summary: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class RunnerProvider(Protocol):
|
||||
def provision(self, request: Mapping[str, Any]) -> RunnerHandle: ...
|
||||
|
||||
def health(self, handle: RunnerHandle) -> RunnerHealth: ...
|
||||
|
||||
def execute(
|
||||
self, handle: RunnerHandle, request: Mapping[str, Any]
|
||||
) -> RunnerExecution: ...
|
||||
|
||||
def cancel(self, execution: RunnerExecution) -> RunnerExecution: ...
|
||||
|
||||
def collect_evidence(self, execution: RunnerExecution) -> RunnerEvidence: ...
|
||||
|
||||
def deprovision(self, handle: RunnerHandle) -> RunnerHandle: ...
|
||||
|
||||
@@ -0,0 +1,102 @@
|
||||
"""Explicit worktree ownership and release-blocking classification."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, replace
|
||||
from enum import Enum
|
||||
from pathlib import PurePosixPath
|
||||
from typing import Iterable
|
||||
|
||||
|
||||
class WorktreeState(str, Enum):
|
||||
ACTIVE = "ACTIVE"
|
||||
READY_TO_COMMIT = "READY_TO_COMMIT"
|
||||
COMMITTED = "COMMITTED"
|
||||
ARCHIVED = "ARCHIVED"
|
||||
OWNER_REVIEW_REQUIRED = "OWNER_REVIEW_REQUIRED"
|
||||
TRUSTED_RUNTIME_DIRTY = "TRUSTED_RUNTIME_DIRTY"
|
||||
STALE_CLEANUP_REQUIRED = "STALE_CLEANUP_REQUIRED"
|
||||
REMOVED = "REMOVED"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class WorktreeRecord:
|
||||
path: str
|
||||
owner: str
|
||||
task_id: str
|
||||
branch: str
|
||||
base_oid: str
|
||||
current_oid: str
|
||||
heartbeat_at: str | None = None
|
||||
dirty_count: int = 0
|
||||
locked: bool = False
|
||||
prunable: bool = False
|
||||
active_runtime: bool = False
|
||||
archive_oid: str | None = None
|
||||
removed_at: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
if not PurePosixPath(self.path).is_absolute():
|
||||
raise ValueError("worktree path must be absolute")
|
||||
if not self.owner or not self.task_id or not self.current_oid:
|
||||
raise ValueError("owner, task_id and current_oid are required")
|
||||
if self.dirty_count < 0:
|
||||
raise ValueError("dirty_count cannot be negative")
|
||||
|
||||
@property
|
||||
def state(self) -> WorktreeState:
|
||||
if self.removed_at:
|
||||
return WorktreeState.REMOVED
|
||||
if self.locked or self.prunable:
|
||||
return WorktreeState.STALE_CLEANUP_REQUIRED
|
||||
if self.dirty_count and self.active_runtime:
|
||||
return WorktreeState.TRUSTED_RUNTIME_DIRTY
|
||||
if self.dirty_count:
|
||||
return WorktreeState.OWNER_REVIEW_REQUIRED
|
||||
if self.archive_oid:
|
||||
return WorktreeState.ARCHIVED
|
||||
if self.current_oid != self.base_oid:
|
||||
return WorktreeState.READY_TO_COMMIT
|
||||
return WorktreeState.ACTIVE
|
||||
|
||||
@property
|
||||
def release_blocking(self) -> bool:
|
||||
return self.state in {
|
||||
WorktreeState.OWNER_REVIEW_REQUIRED,
|
||||
WorktreeState.TRUSTED_RUNTIME_DIRTY,
|
||||
WorktreeState.STALE_CLEANUP_REQUIRED,
|
||||
}
|
||||
|
||||
|
||||
class WorktreeRegistry:
|
||||
def __init__(self, records: Iterable[WorktreeRecord] = ()) -> None:
|
||||
self._records: dict[str, WorktreeRecord] = {}
|
||||
for record in records:
|
||||
self.upsert(record)
|
||||
|
||||
def upsert(self, record: WorktreeRecord) -> None:
|
||||
self._records[record.path] = record
|
||||
|
||||
def get(self, path: str) -> WorktreeRecord:
|
||||
return self._records[path]
|
||||
|
||||
def mark_archived(self, path: str, archive_oid: str) -> WorktreeRecord:
|
||||
if not archive_oid:
|
||||
raise ValueError("archive_oid is required")
|
||||
current = self.get(path)
|
||||
if current.dirty_count:
|
||||
raise ValueError("dirty worktree cannot be marked archived")
|
||||
updated = replace(current, archive_oid=archive_oid)
|
||||
self.upsert(updated)
|
||||
return updated
|
||||
|
||||
def release_blockers(self) -> tuple[WorktreeRecord, ...]:
|
||||
return tuple(
|
||||
sorted(
|
||||
(record for record in self._records.values() if record.release_blocking),
|
||||
key=lambda item: item.path,
|
||||
)
|
||||
)
|
||||
|
||||
def snapshot(self) -> tuple[WorktreeRecord, ...]:
|
||||
return tuple(sorted(self._records.values(), key=lambda item: item.path))
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
"""AIOS-managed OpenClaw Ed25519 execution adapter."""
|
||||
|
||||
from .adapter import (
|
||||
AdapterError,
|
||||
CommandConflict,
|
||||
CommandNotFound,
|
||||
CommandRejected,
|
||||
InMemoryCallbackSink,
|
||||
OpenClawAdapter,
|
||||
)
|
||||
from .contract import (
|
||||
CONTRACT_VERSION,
|
||||
SIGNATURE_ALGORITHM,
|
||||
CommandState,
|
||||
Ed25519CommandSigner,
|
||||
Ed25519CommandVerifier,
|
||||
OpenClawCommand,
|
||||
OpenClawResult,
|
||||
RuntimeHealth,
|
||||
sign_command,
|
||||
verify_command_signature,
|
||||
)
|
||||
from .transport import HTTPRuntimeTransport, InProcessRuntimeTransport, RuntimeTransport
|
||||
|
||||
__all__ = [
|
||||
"AdapterError",
|
||||
"CONTRACT_VERSION",
|
||||
"CommandConflict",
|
||||
"CommandNotFound",
|
||||
"CommandRejected",
|
||||
"CommandState",
|
||||
"Ed25519CommandSigner",
|
||||
"Ed25519CommandVerifier",
|
||||
"HTTPRuntimeTransport",
|
||||
"InMemoryCallbackSink",
|
||||
"InProcessRuntimeTransport",
|
||||
"OpenClawAdapter",
|
||||
"OpenClawCommand",
|
||||
"OpenClawResult",
|
||||
"RuntimeHealth",
|
||||
"RuntimeTransport",
|
||||
"SIGNATURE_ALGORITHM",
|
||||
"sign_command",
|
||||
"verify_command_signature",
|
||||
]
|
||||
@@ -0,0 +1,228 @@
|
||||
"""Signed, tenant-isolated execution adapter for OpenClaw runtimes."""
|
||||
from __future__ import annotations
|
||||
|
||||
import threading
|
||||
from dataclasses import replace
|
||||
from typing import Callable, Mapping, Protocol
|
||||
|
||||
from .contract import (
|
||||
CommandState,
|
||||
OpenClawCommand,
|
||||
OpenClawResult,
|
||||
RuntimeHealth,
|
||||
utc_now,
|
||||
verify_command_signature,
|
||||
)
|
||||
|
||||
|
||||
class AdapterError(RuntimeError):
|
||||
"""Base adapter failure."""
|
||||
|
||||
|
||||
class CommandRejected(AdapterError):
|
||||
"""A command failed signature or contract validation."""
|
||||
|
||||
|
||||
class CommandNotFound(AdapterError):
|
||||
"""A tenant-scoped command is not visible."""
|
||||
|
||||
|
||||
class CommandConflict(AdapterError):
|
||||
"""A command or idempotency key conflicts with an existing execution."""
|
||||
|
||||
|
||||
class RuntimeTransport(Protocol):
|
||||
def execute(self, command: OpenClawCommand, timeout_seconds: float) -> OpenClawResult: ...
|
||||
def cancel(self, command_id: str) -> bool: ...
|
||||
def health(self) -> RuntimeHealth: ...
|
||||
|
||||
|
||||
class CallbackSink(Protocol):
|
||||
def on_started(self, result: OpenClawResult) -> None: ...
|
||||
def on_completed(self, result: OpenClawResult) -> None: ...
|
||||
def on_failed(self, result: OpenClawResult) -> None: ...
|
||||
|
||||
|
||||
class InMemoryCallbackSink:
|
||||
def __init__(self) -> None:
|
||||
self._lock = threading.RLock()
|
||||
self.started: list[OpenClawResult] = []
|
||||
self.completed: list[OpenClawResult] = []
|
||||
self.failed: list[OpenClawResult] = []
|
||||
|
||||
def on_started(self, result: OpenClawResult) -> None:
|
||||
with self._lock:
|
||||
self.started.append(result)
|
||||
|
||||
def on_completed(self, result: OpenClawResult) -> None:
|
||||
with self._lock:
|
||||
self.completed.append(result)
|
||||
|
||||
def on_failed(self, result: OpenClawResult) -> None:
|
||||
with self._lock:
|
||||
self.failed.append(result)
|
||||
|
||||
|
||||
SigningMaterialResolver = Callable[[str, str], bytes | str]
|
||||
|
||||
|
||||
class OpenClawAdapter:
|
||||
"""Verify, de-duplicate, execute, cancel and reconcile commands."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
transport: RuntimeTransport,
|
||||
signing_material_resolver: SigningMaterialResolver,
|
||||
*,
|
||||
callback_sink: CallbackSink | None = None,
|
||||
default_timeout_seconds: float = 300.0,
|
||||
) -> None:
|
||||
if default_timeout_seconds <= 0:
|
||||
raise ValueError("default_timeout_seconds must be positive")
|
||||
self.transport = transport
|
||||
self.signing_material_resolver = signing_material_resolver
|
||||
self.callback_sink = callback_sink or InMemoryCallbackSink()
|
||||
self.default_timeout_seconds = float(default_timeout_seconds)
|
||||
self._lock = threading.RLock()
|
||||
self._commands: dict[str, OpenClawCommand] = {}
|
||||
self._results: dict[str, OpenClawResult] = {}
|
||||
self._idempotency: dict[tuple[str, str], tuple[str, str]] = {}
|
||||
|
||||
def _verify(self, command: OpenClawCommand) -> None:
|
||||
try:
|
||||
key_material = self.signing_material_resolver(command.tenant_id, command.key_id)
|
||||
except Exception as exc:
|
||||
raise CommandRejected("signing material unavailable") from exc
|
||||
if not verify_command_signature(command, key_material):
|
||||
raise CommandRejected("invalid or expired command signature")
|
||||
|
||||
@staticmethod
|
||||
def _validate_result(command: OpenClawCommand, result: OpenClawResult) -> None:
|
||||
if (
|
||||
result.command_id != command.command_id
|
||||
or result.tenant_id != command.tenant_id
|
||||
or result.task_id != command.task_id
|
||||
or result.trace_id != command.trace_id
|
||||
):
|
||||
raise AdapterError("runtime returned mismatched command identity")
|
||||
if result.state not in {
|
||||
CommandState.COMPLETED,
|
||||
CommandState.FAILED,
|
||||
CommandState.CANCELLED,
|
||||
CommandState.TIMED_OUT,
|
||||
}:
|
||||
raise AdapterError("runtime returned a non-terminal result")
|
||||
|
||||
def execute(
|
||||
self,
|
||||
command: OpenClawCommand,
|
||||
*,
|
||||
timeout_seconds: float | None = None,
|
||||
) -> OpenClawResult:
|
||||
timeout = self.default_timeout_seconds if timeout_seconds is None else float(timeout_seconds)
|
||||
if timeout <= 0:
|
||||
raise ValueError("timeout_seconds must be positive")
|
||||
self._verify(command)
|
||||
digest = command.signature
|
||||
idem_ref = (command.tenant_id, command.idempotency_key)
|
||||
|
||||
with self._lock:
|
||||
prior_command = self._commands.get(command.command_id)
|
||||
if prior_command is not None:
|
||||
if prior_command.signature != command.signature:
|
||||
raise CommandConflict("command_id reused with different content")
|
||||
return self._results[command.command_id]
|
||||
prior_idem = self._idempotency.get(idem_ref)
|
||||
if prior_idem is not None:
|
||||
prior_id, prior_digest = prior_idem
|
||||
if prior_digest != digest:
|
||||
raise CommandConflict("idempotency key reused with different content")
|
||||
return self._results[prior_id]
|
||||
running = OpenClawResult(
|
||||
command_id=command.command_id,
|
||||
tenant_id=command.tenant_id,
|
||||
task_id=command.task_id,
|
||||
trace_id=command.trace_id,
|
||||
state=CommandState.RUNNING,
|
||||
started_at=utc_now(),
|
||||
)
|
||||
self._commands[command.command_id] = command
|
||||
self._results[command.command_id] = running
|
||||
self._idempotency[idem_ref] = (command.command_id, digest)
|
||||
|
||||
self.callback_sink.on_started(running)
|
||||
try:
|
||||
result = self.transport.execute(command, timeout)
|
||||
self._validate_result(command, result)
|
||||
except TimeoutError as exc:
|
||||
result = replace(
|
||||
running,
|
||||
state=CommandState.TIMED_OUT,
|
||||
error={"code": "runtime_timeout", "message": str(exc) or "runtime timeout"},
|
||||
finished_at=utc_now(),
|
||||
)
|
||||
except Exception as exc:
|
||||
result = replace(
|
||||
running,
|
||||
state=CommandState.FAILED,
|
||||
error={"code": "runtime_error", "message": str(exc)},
|
||||
finished_at=utc_now(),
|
||||
)
|
||||
|
||||
if result.started_at is None:
|
||||
result = replace(result, started_at=running.started_at)
|
||||
if result.finished_at is None:
|
||||
result = replace(result, finished_at=utc_now())
|
||||
with self._lock:
|
||||
self._results[command.command_id] = result
|
||||
if result.state == CommandState.COMPLETED:
|
||||
self.callback_sink.on_completed(result)
|
||||
else:
|
||||
self.callback_sink.on_failed(result)
|
||||
return result
|
||||
|
||||
def status(self, command_id: str, *, tenant_id: str) -> OpenClawResult:
|
||||
with self._lock:
|
||||
command = self._commands.get(command_id)
|
||||
result = self._results.get(command_id)
|
||||
if command is None or result is None or command.tenant_id != tenant_id:
|
||||
raise CommandNotFound("command not found")
|
||||
return result
|
||||
|
||||
def cancel(self, command_id: str, *, tenant_id: str) -> OpenClawResult:
|
||||
with self._lock:
|
||||
command = self._commands.get(command_id)
|
||||
current = self._results.get(command_id)
|
||||
if command is None or current is None or command.tenant_id != tenant_id:
|
||||
raise CommandNotFound("command not found")
|
||||
if current.state in {
|
||||
CommandState.COMPLETED,
|
||||
CommandState.FAILED,
|
||||
CommandState.CANCELLED,
|
||||
CommandState.TIMED_OUT,
|
||||
CommandState.REJECTED,
|
||||
}:
|
||||
return current
|
||||
if not self.transport.cancel(command_id):
|
||||
raise AdapterError("runtime rejected cancellation")
|
||||
cancelled = replace(
|
||||
current,
|
||||
state=CommandState.CANCELLED,
|
||||
error={"code": "cancelled", "message": "cancelled by AIOS"},
|
||||
finished_at=utc_now(),
|
||||
)
|
||||
with self._lock:
|
||||
self._results[command_id] = cancelled
|
||||
self.callback_sink.on_failed(cancelled)
|
||||
return cancelled
|
||||
|
||||
def health(self) -> RuntimeHealth:
|
||||
return self.transport.health()
|
||||
|
||||
def snapshot(self, *, tenant_id: str) -> Mapping[str, OpenClawResult]:
|
||||
with self._lock:
|
||||
return {
|
||||
command_id: result
|
||||
for command_id, result in self._results.items()
|
||||
if self._commands[command_id].tenant_id == tenant_id
|
||||
}
|
||||
@@ -0,0 +1,97 @@
|
||||
"""Audit-oriented lifecycle callbacks for OpenClaw execution."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import threading
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Mapping, Protocol
|
||||
|
||||
from .contract import OpenClawResult, utc_now
|
||||
|
||||
|
||||
class EventPublisher(Protocol):
|
||||
def publish(self, event: Mapping[str, Any]) -> None: ...
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecutionEvent:
|
||||
event_type: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
trace_id: str
|
||||
command_id: str
|
||||
state: str
|
||||
created_at: str = field(default_factory=utc_now)
|
||||
details: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"event_type": self.event_type,
|
||||
"tenant_id": self.tenant_id,
|
||||
"task_id": self.task_id,
|
||||
"trace_id": self.trace_id,
|
||||
"command_id": self.command_id,
|
||||
"state": self.state,
|
||||
"created_at": self.created_at,
|
||||
"details": json.loads(
|
||||
json.dumps(dict(self.details), ensure_ascii=False, default=str)
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
class InMemoryEventPublisher:
|
||||
"""Thread-safe publisher used by tests and first integration slice."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._lock = threading.RLock()
|
||||
self.events: list[dict[str, Any]] = []
|
||||
|
||||
def publish(self, event: Mapping[str, Any]) -> None:
|
||||
with self._lock:
|
||||
self.events.append(
|
||||
json.loads(json.dumps(dict(event), ensure_ascii=False, default=str))
|
||||
)
|
||||
|
||||
|
||||
class AuditCallbackSink:
|
||||
"""Convert runtime callbacks into tenant-scoped audit events."""
|
||||
|
||||
def __init__(self, publisher: EventPublisher) -> None:
|
||||
self.publisher = publisher
|
||||
|
||||
@staticmethod
|
||||
def _event(
|
||||
event_type: str,
|
||||
result: OpenClawResult,
|
||||
) -> ExecutionEvent:
|
||||
details: dict[str, Any] = {
|
||||
"runtime_id": result.runtime_id,
|
||||
"attempts": result.attempts,
|
||||
}
|
||||
if result.error:
|
||||
details["error"] = dict(result.error)
|
||||
if result.output:
|
||||
details["output_present"] = True
|
||||
return ExecutionEvent(
|
||||
event_type=event_type,
|
||||
tenant_id=result.tenant_id,
|
||||
task_id=result.task_id,
|
||||
trace_id=result.trace_id,
|
||||
command_id=result.command_id,
|
||||
state=result.state.value,
|
||||
details=details,
|
||||
)
|
||||
|
||||
def on_started(self, result: OpenClawResult) -> None:
|
||||
self.publisher.publish(self._event("OPENCLAW_STARTED", result).as_dict())
|
||||
|
||||
def on_completed(self, result: OpenClawResult) -> None:
|
||||
self.publisher.publish(self._event("OPENCLAW_COMPLETED", result).as_dict())
|
||||
|
||||
def on_failed(self, result: OpenClawResult) -> None:
|
||||
event_type = {
|
||||
"CANCELLED": "OPENCLAW_CANCELLED",
|
||||
"TIMED_OUT": "OPENCLAW_TIMED_OUT",
|
||||
"REJECTED": "OPENCLAW_REJECTED",
|
||||
}.get(result.state.value, "OPENCLAW_FAILED")
|
||||
self.publisher.publish(self._event(event_type, result).as_dict())
|
||||
@@ -0,0 +1,383 @@
|
||||
"""AIOS 到 OpenClaw 的 Ed25519 执行合同。"""
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import uuid
|
||||
from dataclasses import dataclass, field, replace
|
||||
from datetime import datetime, timezone
|
||||
from enum import Enum
|
||||
from typing import Any, Mapping, Protocol
|
||||
|
||||
CONTRACT_VERSION = "aios.openclaw.command.v2"
|
||||
SIGNATURE_ALGORITHM = "Ed25519"
|
||||
DEFAULT_CLOCK_SKEW_SECONDS = 300
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def _parse_timestamp(value: str) -> datetime:
|
||||
normalized = str(value or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError("timestamp is required")
|
||||
if normalized.endswith("Z"):
|
||||
normalized = normalized[:-1] + "+00:00"
|
||||
parsed = datetime.fromisoformat(normalized)
|
||||
if parsed.tzinfo is None:
|
||||
raise ValueError("timestamp must include a timezone")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def _required(value: str, label: str) -> str:
|
||||
normalized = str(value or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError(f"{label} is required")
|
||||
return normalized
|
||||
|
||||
|
||||
def _safe_mapping(value: Mapping[str, Any] | None) -> dict[str, Any]:
|
||||
return json.loads(
|
||||
json.dumps(dict(value or {}), ensure_ascii=False, sort_keys=True, default=str)
|
||||
)
|
||||
|
||||
|
||||
def _load_crypto() -> tuple[Any, Any, Any]:
|
||||
try:
|
||||
from cryptography.hazmat.primitives import serialization
|
||||
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
|
||||
Ed25519PrivateKey,
|
||||
Ed25519PublicKey,
|
||||
)
|
||||
except ImportError as exc: # pragma: no cover
|
||||
raise RuntimeError("cryptography with Ed25519 support is required") from exc
|
||||
return serialization, Ed25519PrivateKey, Ed25519PublicKey
|
||||
|
||||
|
||||
class CommandSigner(Protocol):
|
||||
key_id: str
|
||||
fingerprint: str
|
||||
|
||||
def sign(self, payload: bytes) -> bytes: ...
|
||||
|
||||
|
||||
class CommandVerifier(Protocol):
|
||||
key_id: str
|
||||
fingerprint: str
|
||||
|
||||
def verify(self, payload: bytes, signature: bytes) -> bool: ...
|
||||
|
||||
|
||||
class Ed25519CommandSigner:
|
||||
def __init__(self, private_key: Any, *, key_id: str) -> None:
|
||||
serialization, private_cls, _ = _load_crypto()
|
||||
if not isinstance(private_key, private_cls):
|
||||
raise ValueError("private key is not Ed25519")
|
||||
self.private_key = private_key
|
||||
self.key_id = _required(key_id, "key_id")
|
||||
raw = private_key.public_key().public_bytes(
|
||||
encoding=serialization.Encoding.Raw,
|
||||
format=serialization.PublicFormat.Raw,
|
||||
)
|
||||
self.fingerprint = hashlib.sha256(raw).hexdigest()
|
||||
|
||||
@classmethod
|
||||
def from_bytes(cls, value: bytes | str, *, key_id: str) -> "Ed25519CommandSigner":
|
||||
serialization, private_cls, _ = _load_crypto()
|
||||
raw = value.encode("utf-8") if isinstance(value, str) else bytes(value)
|
||||
if raw.startswith(b"-----BEGIN"):
|
||||
key = serialization.load_pem_private_key(raw, password=None)
|
||||
elif len(raw) == 32:
|
||||
key = private_cls.from_private_bytes(raw)
|
||||
else:
|
||||
raise ValueError("Ed25519 private key must be PEM or a raw 32-byte seed")
|
||||
return cls(key, key_id=key_id)
|
||||
|
||||
def sign(self, payload: bytes) -> bytes:
|
||||
return self.private_key.sign(bytes(payload))
|
||||
|
||||
def verifier(self) -> "Ed25519CommandVerifier":
|
||||
return Ed25519CommandVerifier(self.private_key.public_key(), key_id=self.key_id)
|
||||
|
||||
|
||||
class Ed25519CommandVerifier:
|
||||
def __init__(self, public_key: Any, *, key_id: str) -> None:
|
||||
serialization, _, public_cls = _load_crypto()
|
||||
if not isinstance(public_key, public_cls):
|
||||
raise ValueError("public key is not Ed25519")
|
||||
self.public_key = public_key
|
||||
self.key_id = _required(key_id, "key_id")
|
||||
raw = public_key.public_bytes(
|
||||
encoding=serialization.Encoding.Raw,
|
||||
format=serialization.PublicFormat.Raw,
|
||||
)
|
||||
self.fingerprint = hashlib.sha256(raw).hexdigest()
|
||||
|
||||
@classmethod
|
||||
def from_bytes(cls, value: bytes | str, *, key_id: str) -> "Ed25519CommandVerifier":
|
||||
serialization, private_cls, public_cls = _load_crypto()
|
||||
raw = value.encode("utf-8") if isinstance(value, str) else bytes(value)
|
||||
if raw.startswith(b"-----BEGIN"):
|
||||
try:
|
||||
key = serialization.load_pem_public_key(raw)
|
||||
except ValueError:
|
||||
private = serialization.load_pem_private_key(raw, password=None)
|
||||
if not isinstance(private, private_cls):
|
||||
raise ValueError("key is not Ed25519")
|
||||
key = private.public_key()
|
||||
elif len(raw) == 32:
|
||||
key = public_cls.from_public_bytes(raw)
|
||||
else:
|
||||
raise ValueError("Ed25519 public key must be PEM or raw 32-byte key")
|
||||
return cls(key, key_id=key_id)
|
||||
|
||||
def verify(self, payload: bytes, signature: bytes) -> bool:
|
||||
try:
|
||||
self.public_key.verify(bytes(signature), bytes(payload))
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
class CommandState(str, Enum):
|
||||
ACCEPTED = "ACCEPTED"
|
||||
RUNNING = "RUNNING"
|
||||
COMPLETED = "COMPLETED"
|
||||
FAILED = "FAILED"
|
||||
CANCELLED = "CANCELLED"
|
||||
TIMED_OUT = "TIMED_OUT"
|
||||
REJECTED = "REJECTED"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OpenClawCommand:
|
||||
command_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
trace_id: str
|
||||
action: str
|
||||
payload: Mapping[str, Any] = field(default_factory=dict)
|
||||
idempotency_key: str = ""
|
||||
created_at: str = field(default_factory=utc_now)
|
||||
expires_at: str | None = None
|
||||
contract_version: str = CONTRACT_VERSION
|
||||
signature_algorithm: str = SIGNATURE_ALGORITHM
|
||||
key_id: str = "default"
|
||||
public_key_fingerprint: str = ""
|
||||
signature: str = ""
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for field_name in (
|
||||
"command_id",
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"trace_id",
|
||||
"action",
|
||||
"idempotency_key",
|
||||
"created_at",
|
||||
"contract_version",
|
||||
"signature_algorithm",
|
||||
"key_id",
|
||||
):
|
||||
object.__setattr__(
|
||||
self, field_name, _required(getattr(self, field_name), field_name)
|
||||
)
|
||||
if self.contract_version != CONTRACT_VERSION:
|
||||
raise ValueError(f"unsupported contract_version: {self.contract_version}")
|
||||
if self.signature_algorithm != SIGNATURE_ALGORITHM:
|
||||
raise ValueError(
|
||||
f"unsupported signature_algorithm: {self.signature_algorithm}"
|
||||
)
|
||||
object.__setattr__(self, "payload", _safe_mapping(self.payload))
|
||||
object.__setattr__(
|
||||
self, "public_key_fingerprint", str(self.public_key_fingerprint or "").strip()
|
||||
)
|
||||
object.__setattr__(self, "signature", str(self.signature or "").strip())
|
||||
_parse_timestamp(self.created_at)
|
||||
if self.expires_at is not None:
|
||||
object.__setattr__(self, "expires_at", _required(self.expires_at, "expires_at"))
|
||||
if _parse_timestamp(self.expires_at) <= _parse_timestamp(self.created_at):
|
||||
raise ValueError("expires_at must be later than created_at")
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
*,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
trace_id: str,
|
||||
action: str,
|
||||
payload: Mapping[str, Any] | None,
|
||||
idempotency_key: str,
|
||||
expires_at: str | None = None,
|
||||
key_id: str = "default",
|
||||
command_id: str | None = None,
|
||||
) -> "OpenClawCommand":
|
||||
return cls(
|
||||
command_id=command_id or f"cmd_{uuid.uuid4().hex}",
|
||||
tenant_id=tenant_id,
|
||||
task_id=task_id,
|
||||
trace_id=trace_id,
|
||||
action=action,
|
||||
payload=_safe_mapping(payload),
|
||||
idempotency_key=idempotency_key,
|
||||
expires_at=expires_at,
|
||||
key_id=key_id,
|
||||
)
|
||||
|
||||
def unsigned_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"command_id": self.command_id,
|
||||
"tenant_id": self.tenant_id,
|
||||
"task_id": self.task_id,
|
||||
"trace_id": self.trace_id,
|
||||
"action": self.action,
|
||||
"payload": _safe_mapping(self.payload),
|
||||
"idempotency_key": self.idempotency_key,
|
||||
"created_at": self.created_at,
|
||||
"expires_at": self.expires_at,
|
||||
"contract_version": self.contract_version,
|
||||
"signature_algorithm": self.signature_algorithm,
|
||||
"key_id": self.key_id,
|
||||
"public_key_fingerprint": self.public_key_fingerprint,
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OpenClawResult:
|
||||
command_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
trace_id: str
|
||||
state: CommandState
|
||||
output: Mapping[str, Any] | None = None
|
||||
error: Mapping[str, Any] | None = None
|
||||
started_at: str | None = None
|
||||
finished_at: str | None = None
|
||||
runtime_id: str | None = None
|
||||
attempts: int = 1
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for field_name in ("command_id", "tenant_id", "task_id", "trace_id"):
|
||||
object.__setattr__(
|
||||
self, field_name, _required(getattr(self, field_name), field_name)
|
||||
)
|
||||
object.__setattr__(self, "state", CommandState(self.state))
|
||||
if self.output is not None:
|
||||
object.__setattr__(self, "output", _safe_mapping(self.output))
|
||||
if self.error is not None:
|
||||
object.__setattr__(self, "error", _safe_mapping(self.error))
|
||||
if self.started_at is not None:
|
||||
_parse_timestamp(self.started_at)
|
||||
if self.finished_at is not None:
|
||||
_parse_timestamp(self.finished_at)
|
||||
if self.attempts < 1:
|
||||
raise ValueError("attempts must be >= 1")
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RuntimeHealth:
|
||||
runtime: str
|
||||
runtime_id: str
|
||||
status: str
|
||||
version: str
|
||||
heartbeat_at: str
|
||||
active_tasks: int = 0
|
||||
workspace_isolated: bool = False
|
||||
credential_ref_configured: bool = False
|
||||
details: Mapping[str, Any] = field(default_factory=dict)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for field_name in (
|
||||
"runtime",
|
||||
"runtime_id",
|
||||
"status",
|
||||
"version",
|
||||
"heartbeat_at",
|
||||
):
|
||||
object.__setattr__(
|
||||
self, field_name, _required(getattr(self, field_name), field_name)
|
||||
)
|
||||
_parse_timestamp(self.heartbeat_at)
|
||||
if self.active_tasks < 0:
|
||||
raise ValueError("active_tasks must be >= 0")
|
||||
object.__setattr__(self, "details", _safe_mapping(self.details))
|
||||
|
||||
|
||||
def canonical_command_bytes(command: OpenClawCommand) -> bytes:
|
||||
return json.dumps(
|
||||
command.unsigned_dict(),
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def _as_signer(command: OpenClawCommand, value: Any) -> CommandSigner:
|
||||
if hasattr(value, "sign") and hasattr(value, "fingerprint") and hasattr(value, "key_id"):
|
||||
return value
|
||||
return Ed25519CommandSigner.from_bytes(value, key_id=command.key_id)
|
||||
|
||||
|
||||
def _as_verifier(command: OpenClawCommand, value: Any) -> CommandVerifier:
|
||||
if isinstance(value, Ed25519CommandSigner):
|
||||
return value.verifier()
|
||||
if hasattr(value, "verify") and hasattr(value, "fingerprint") and hasattr(value, "key_id"):
|
||||
return value
|
||||
return Ed25519CommandVerifier.from_bytes(value, key_id=command.key_id)
|
||||
|
||||
|
||||
def sign_command(command: OpenClawCommand, signing_key: Any) -> OpenClawCommand:
|
||||
signer = _as_signer(command, signing_key)
|
||||
if signer.key_id != command.key_id:
|
||||
raise ValueError("command key_id does not match signer")
|
||||
prepared = replace(
|
||||
command,
|
||||
signature_algorithm=SIGNATURE_ALGORITHM,
|
||||
public_key_fingerprint=signer.fingerprint,
|
||||
signature="",
|
||||
)
|
||||
signature = base64.b64encode(
|
||||
signer.sign(canonical_command_bytes(prepared))
|
||||
).decode("ascii")
|
||||
return replace(prepared, signature=signature)
|
||||
|
||||
|
||||
def verify_command_signature(
|
||||
command: OpenClawCommand,
|
||||
verification_key: Any,
|
||||
*,
|
||||
now: datetime | None = None,
|
||||
clock_skew_seconds: int = DEFAULT_CLOCK_SKEW_SECONDS,
|
||||
) -> bool:
|
||||
if (
|
||||
not command.signature
|
||||
or command.contract_version != CONTRACT_VERSION
|
||||
or command.signature_algorithm != SIGNATURE_ALGORITHM
|
||||
):
|
||||
return False
|
||||
try:
|
||||
verifier = _as_verifier(command, verification_key)
|
||||
signature = base64.b64decode(command.signature, validate=True)
|
||||
except Exception:
|
||||
return False
|
||||
if verifier.key_id != command.key_id:
|
||||
return False
|
||||
if not command.public_key_fingerprint or not hmac.compare_digest(
|
||||
command.public_key_fingerprint, verifier.fingerprint
|
||||
):
|
||||
return False
|
||||
if not verifier.verify(canonical_command_bytes(command), signature):
|
||||
return False
|
||||
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
|
||||
created = _parse_timestamp(command.created_at)
|
||||
if created.timestamp() - current.timestamp() > clock_skew_seconds:
|
||||
return False
|
||||
if command.expires_at is not None:
|
||||
expires = _parse_timestamp(command.expires_at)
|
||||
if current.timestamp() - expires.timestamp() > clock_skew_seconds:
|
||||
return False
|
||||
return True
|
||||
@@ -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 {},
|
||||
)
|
||||
@@ -0,0 +1,110 @@
|
||||
"""AIOS V2 控制面、执行编排与可信运行来源证明。"""
|
||||
|
||||
from .control_plane import (
|
||||
AgentRecord,
|
||||
AuditEvent,
|
||||
ControlPlaneError,
|
||||
ControlPlaneService,
|
||||
IdempotencyConflict,
|
||||
InMemoryControlPlaneStore,
|
||||
InvalidTransition,
|
||||
NotFound,
|
||||
PolicyDenied,
|
||||
RequestContext,
|
||||
RevisionConflict,
|
||||
TaskRecord,
|
||||
TaskState,
|
||||
TenantIsolationError,
|
||||
TenantRecord,
|
||||
Unauthorized,
|
||||
)
|
||||
from .execution_tracking import ExecutionEvidence, ExecutionTracker
|
||||
from .orchestrator import DispatchRecord, ExecutionOrchestrator, OrchestrationError
|
||||
from .provenance import (
|
||||
Ed25519PrivateKeySigner,
|
||||
Ed25519PublicKeyVerifier,
|
||||
ExecutionPath,
|
||||
GitOperation,
|
||||
PRODUCTION_POLICY_VERSION,
|
||||
ProvenanceAuthorization,
|
||||
ProvenanceControlledWriter,
|
||||
ProvenanceDenied,
|
||||
ProvenanceError,
|
||||
ProvenanceExpired,
|
||||
ProvenanceIssuer,
|
||||
ProvenanceNotFound,
|
||||
ProvenanceReplay,
|
||||
ProvenanceRevoked,
|
||||
ProvenanceSignatureError,
|
||||
ProvenanceStatus,
|
||||
ProvenanceVerifier,
|
||||
RunProvenance,
|
||||
SQLiteProvenanceStore,
|
||||
digest_payload,
|
||||
)
|
||||
from .provenance_git import (
|
||||
GitCommandResult,
|
||||
GitExecutionContext,
|
||||
ProvenanceGitError,
|
||||
ProvenanceGitWriter,
|
||||
)
|
||||
from .provenance_operations import (
|
||||
OperationContext,
|
||||
OperationReceipt,
|
||||
ProvenanceOperationGate,
|
||||
build_provenance_writer_from_env,
|
||||
context_from_environment,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"AgentRecord",
|
||||
"AuditEvent",
|
||||
"ControlPlaneError",
|
||||
"ControlPlaneService",
|
||||
"DispatchRecord",
|
||||
"Ed25519PrivateKeySigner",
|
||||
"Ed25519PublicKeyVerifier",
|
||||
"ExecutionEvidence",
|
||||
"ExecutionOrchestrator",
|
||||
"ExecutionPath",
|
||||
"ExecutionTracker",
|
||||
"GitCommandResult",
|
||||
"GitExecutionContext",
|
||||
"GitOperation",
|
||||
"IdempotencyConflict",
|
||||
"InMemoryControlPlaneStore",
|
||||
"InvalidTransition",
|
||||
"NotFound",
|
||||
"OperationContext",
|
||||
"OperationReceipt",
|
||||
"OrchestrationError",
|
||||
"PRODUCTION_POLICY_VERSION",
|
||||
"PolicyDenied",
|
||||
"ProvenanceAuthorization",
|
||||
"ProvenanceControlledWriter",
|
||||
"ProvenanceDenied",
|
||||
"ProvenanceError",
|
||||
"ProvenanceExpired",
|
||||
"ProvenanceGitError",
|
||||
"ProvenanceGitWriter",
|
||||
"ProvenanceIssuer",
|
||||
"ProvenanceNotFound",
|
||||
"ProvenanceOperationGate",
|
||||
"ProvenanceReplay",
|
||||
"ProvenanceRevoked",
|
||||
"ProvenanceSignatureError",
|
||||
"ProvenanceStatus",
|
||||
"ProvenanceVerifier",
|
||||
"RequestContext",
|
||||
"RevisionConflict",
|
||||
"RunProvenance",
|
||||
"SQLiteProvenanceStore",
|
||||
"TaskRecord",
|
||||
"TaskState",
|
||||
"TenantIsolationError",
|
||||
"TenantRecord",
|
||||
"Unauthorized",
|
||||
"build_provenance_writer_from_env",
|
||||
"context_from_environment",
|
||||
"digest_payload",
|
||||
]
|
||||
@@ -0,0 +1,807 @@
|
||||
"""AIOS V2 production-candidate application entrypoint."""
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import json
|
||||
import os
|
||||
import stat
|
||||
import urllib.parse
|
||||
from enum import Enum
|
||||
from http import HTTPStatus
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping
|
||||
|
||||
from aios_hermes import HermesAdapter, HermesJobState, HermesResult, SQLiteHermesStore
|
||||
from aios_openclaw import (
|
||||
Ed25519CommandSigner,
|
||||
HTTPRuntimeTransport,
|
||||
OpenClawAdapter,
|
||||
)
|
||||
from aios_openclaw.callback import AuditCallbackSink, EventPublisher
|
||||
|
||||
from .console import CONSOLE_HTML
|
||||
from .control_plane import AuditEvent, RequestContext, Unauthorized
|
||||
from .dispatch_store import SQLiteDispatchRepository
|
||||
from .execution_tracking import ExecutionEvidence, ExecutionTracker
|
||||
from .gateway import GatewayApplication, error_response
|
||||
from .gitops_status import collect_gitops_status
|
||||
from .orchestrator import ExecutionOrchestrator
|
||||
from .persistence import DurableControlPlaneService, SQLiteSnapshotRepository
|
||||
from .provenance_operations import build_provenance_writer_from_env
|
||||
|
||||
|
||||
def _json_value(value: Any) -> Any:
|
||||
if dataclasses.is_dataclass(value):
|
||||
return {
|
||||
item.name: _json_value(getattr(value, item.name))
|
||||
for item in dataclasses.fields(value)
|
||||
}
|
||||
if isinstance(value, Enum):
|
||||
return value.value
|
||||
if isinstance(value, Mapping):
|
||||
return {str(key): _json_value(item) for key, item in value.items()}
|
||||
if isinstance(value, (list, tuple, set, frozenset)):
|
||||
return [_json_value(item) for item in value]
|
||||
return value
|
||||
|
||||
|
||||
def _enabled(value: str | None) -> bool:
|
||||
return str(value or "").strip().lower() in {"1", "true", "yes", "on"}
|
||||
|
||||
|
||||
def _header(headers: Mapping[str, str], name: str) -> str | None:
|
||||
target = name.lower()
|
||||
for key, value in headers.items():
|
||||
if str(key).lower() == target:
|
||||
normalized = str(value or "").strip()
|
||||
return normalized or None
|
||||
return None
|
||||
|
||||
|
||||
def _provenance_context(
|
||||
headers: Mapping[str, str],
|
||||
payload: Mapping[str, Any],
|
||||
) -> tuple[str | None, str | None]:
|
||||
header_provenance = _header(headers, "X-AIOS-Provenance-ID")
|
||||
header_run = _header(headers, "X-AIOS-Run-ID")
|
||||
body_provenance = str(payload.get("provenance_id") or "").strip() or None
|
||||
body_run = str(payload.get("run_id") or "").strip() or None
|
||||
if header_provenance and body_provenance and header_provenance != body_provenance:
|
||||
raise ValueError("provenance_id header/body mismatch")
|
||||
if header_run and body_run and header_run != body_run:
|
||||
raise ValueError("run_id header/body mismatch")
|
||||
return header_provenance or body_provenance, header_run or body_run
|
||||
|
||||
|
||||
def _read_protected_file(path: Path, *, private: bool) -> bytes:
|
||||
flags = os.O_RDONLY
|
||||
if hasattr(os, "O_NOFOLLOW"):
|
||||
flags |= os.O_NOFOLLOW
|
||||
descriptor = os.open(str(path), flags)
|
||||
try:
|
||||
metadata = os.fstat(descriptor)
|
||||
if not stat.S_ISREG(metadata.st_mode):
|
||||
raise RuntimeError("key reference is not a regular file")
|
||||
denied = 0o077 if private else 0o022
|
||||
if metadata.st_mode & denied:
|
||||
raise RuntimeError(
|
||||
"private key file permissions must be 0600 or stricter"
|
||||
if private
|
||||
else "public key file must not be group/world writable"
|
||||
)
|
||||
chunks: list[bytes] = []
|
||||
while True:
|
||||
chunk = os.read(descriptor, 65536)
|
||||
if not chunk:
|
||||
break
|
||||
chunks.append(chunk)
|
||||
value = b"".join(chunks)
|
||||
if not value:
|
||||
raise RuntimeError("key file is empty")
|
||||
return value
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
|
||||
|
||||
class FileCommandSignerResolver:
|
||||
"""Resolve tenant/key-id scoped OpenClaw Ed25519 signing material."""
|
||||
|
||||
def __init__(self, path: str | Path, *, configured_key_id: str) -> None:
|
||||
self.path = Path(path).resolve()
|
||||
self.configured_key_id = str(configured_key_id or "").strip()
|
||||
if not self.configured_key_id:
|
||||
raise ValueError("configured_key_id is required")
|
||||
|
||||
def __call__(self, tenant_id: str, key_id: str) -> Ed25519CommandSigner:
|
||||
if not str(tenant_id or "").strip():
|
||||
raise RuntimeError("tenant_id is required for command signing")
|
||||
if key_id != self.configured_key_id:
|
||||
raise RuntimeError("OpenClaw signing key_id mismatch")
|
||||
return Ed25519CommandSigner.from_bytes(
|
||||
_read_protected_file(self.path, private=True),
|
||||
key_id=key_id,
|
||||
)
|
||||
|
||||
|
||||
class ControlPlaneEventPublisher(EventPublisher):
|
||||
"""Append Runtime callback events to the tenant audit stream.
|
||||
|
||||
Callback audit remains informational. Authoritative task reconciliation is
|
||||
performed only by the orchestrator after dispatch/result validation.
|
||||
"""
|
||||
|
||||
def __init__(self, service: DurableControlPlaneService) -> None:
|
||||
self.service = service
|
||||
|
||||
def publish(self, event: Mapping[str, Any]) -> None:
|
||||
tenant_id = str(event.get("tenant_id") or "").strip()
|
||||
trace_id = str(event.get("trace_id") or "").strip()
|
||||
command_id = str(event.get("command_id") or "").strip()
|
||||
event_type = str(event.get("event_type") or "OPENCLAW_EVENT").strip()
|
||||
if not tenant_id or not trace_id or not command_id:
|
||||
raise ValueError("runtime audit event is missing tenant identity")
|
||||
state_value = str(event.get("state") or "unknown").lower()
|
||||
outcome = "allowed" if state_value == "completed" else state_value
|
||||
runtime = str(event.get("runtime") or "openclaw").strip().lower()
|
||||
principal_id = str(
|
||||
event.get("principal_id") or f"{runtime}-runtime"
|
||||
).strip()
|
||||
audit = AuditEvent(
|
||||
event_id=f"runtime_{command_id}_{len(self.service.store.audit_events) + 1}",
|
||||
tenant_id=tenant_id,
|
||||
principal_id=principal_id,
|
||||
trace_id=trace_id,
|
||||
action=event_type,
|
||||
resource_type=f"{runtime}_execution",
|
||||
resource_id=command_id,
|
||||
outcome=outcome,
|
||||
policy_version="runtime-v2",
|
||||
details=dict(event.get("details") or {}),
|
||||
)
|
||||
with self.service.store.lock:
|
||||
self.service.store.audit_events.append(audit)
|
||||
self.service.repository.save(self.service._snapshot())
|
||||
|
||||
|
||||
class CandidateApplication:
|
||||
def __init__(
|
||||
self,
|
||||
gateway: GatewayApplication,
|
||||
orchestrator: ExecutionOrchestrator,
|
||||
tracker: ExecutionTracker,
|
||||
hermes: HermesAdapter,
|
||||
openclaw: OpenClawAdapter | None,
|
||||
*,
|
||||
hermes_lifecycle_api_enabled: bool = False,
|
||||
) -> None:
|
||||
self.gateway = gateway
|
||||
self.orchestrator = orchestrator
|
||||
self.tracker = tracker
|
||||
self.hermes = hermes
|
||||
self.openclaw = openclaw
|
||||
self.hermes_lifecycle_api_enabled = bool(hermes_lifecycle_api_enabled)
|
||||
self.runtime_events = ControlPlaneEventPublisher(orchestrator.control_plane)
|
||||
|
||||
def context(self, headers: Mapping[str, str]) -> RequestContext:
|
||||
return self.gateway.context_from_headers(headers)
|
||||
|
||||
@staticmethod
|
||||
def _require_runtime_role(context: RequestContext) -> None:
|
||||
if not ({"runtime", "platform_admin"} & set(context.roles)):
|
||||
raise Unauthorized("runtime reconciliation role is required")
|
||||
|
||||
@staticmethod
|
||||
def _require_control_plane_cancel(context: RequestContext) -> None:
|
||||
required = {"runtime", "platform_admin"}
|
||||
if not required.issubset(set(context.roles)):
|
||||
raise Unauthorized(
|
||||
"Hermes cancellation requires trusted AIOS control-plane authority"
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _required_identity(payload: Mapping[str, Any], name: str) -> str:
|
||||
value = str(payload.get(name) or "").strip()
|
||||
if not value:
|
||||
raise ValueError(f"{name} is required")
|
||||
return value
|
||||
|
||||
def _record_hermes_lifecycle(
|
||||
self,
|
||||
context: RequestContext,
|
||||
dispatch: Any,
|
||||
job: Any,
|
||||
*,
|
||||
action: str,
|
||||
worker_id: str | None,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
) -> None:
|
||||
executor = worker_id or "aios-control-plane"
|
||||
evidence = ExecutionEvidence(
|
||||
execution_id=job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
task_id=job.task_id,
|
||||
agent_id=dispatch.agent_id,
|
||||
executor=executor,
|
||||
branch="runtime/hermes",
|
||||
status=job.state.value.lower(),
|
||||
progress_completed=0,
|
||||
progress_total=3,
|
||||
current_step=action,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
current_evidence = self.tracker.claim(
|
||||
evidence,
|
||||
principal_id=context.principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
if job.state in {
|
||||
HermesJobState.COMPLETED,
|
||||
HermesJobState.FAILED,
|
||||
HermesJobState.CANCELLED,
|
||||
}:
|
||||
if current_evidence.completed_at is None:
|
||||
self.tracker.complete(
|
||||
tenant_id=job.tenant_id,
|
||||
execution_id=job.job_id,
|
||||
status=job.state.value.lower(),
|
||||
test_status="runtime_terminal",
|
||||
test_summary={"lifecycle_action": action},
|
||||
result_summary={
|
||||
"state": job.state.value,
|
||||
"worker_id": worker_id,
|
||||
"dispatch_id": dispatch.dispatch_id,
|
||||
},
|
||||
principal_id=context.principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
else:
|
||||
self.tracker.heartbeat(
|
||||
tenant_id=job.tenant_id,
|
||||
execution_id=job.job_id,
|
||||
status=job.state.value.lower(),
|
||||
current_step=action,
|
||||
progress_completed=(1 if job.state == HermesJobState.RUNNING else 0),
|
||||
progress_total=3,
|
||||
principal_id=context.principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
self.runtime_events.publish(
|
||||
{
|
||||
"runtime": "hermes",
|
||||
"tenant_id": job.tenant_id,
|
||||
"principal_id": context.principal_id,
|
||||
"trace_id": job.trace_id,
|
||||
"command_id": job.job_id,
|
||||
"event_type": f"HERMES_{action.upper()}",
|
||||
"state": job.state.value,
|
||||
"details": {
|
||||
"dispatch_id": dispatch.dispatch_id,
|
||||
"task_id": job.task_id,
|
||||
"worker_id": worker_id,
|
||||
"cell_id": job.cell_id,
|
||||
"profile_id": job.profile_id,
|
||||
"revision": job.revision,
|
||||
"provenance_id": provenance_id,
|
||||
"run_id": run_id,
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
def handle_json(
|
||||
self,
|
||||
method: str,
|
||||
raw_path: str,
|
||||
headers: Mapping[str, str],
|
||||
body: Any,
|
||||
) -> tuple[int, Mapping[str, Any]]:
|
||||
parsed = urllib.parse.urlparse(raw_path)
|
||||
path = parsed.path.rstrip("/") or "/"
|
||||
method = method.upper()
|
||||
|
||||
if method == "GET" and path == "/api/v2/gitops":
|
||||
context = self.context(headers)
|
||||
return HTTPStatus.OK, {
|
||||
"tenant_id": context.tenant_id,
|
||||
"gitops": collect_gitops_status().as_dict(),
|
||||
}
|
||||
|
||||
if method == "GET" and path == "/api/v2/runtime":
|
||||
context = self.context(headers)
|
||||
runtimes: list[dict[str, Any]] = []
|
||||
if self.openclaw is None:
|
||||
runtimes.append(
|
||||
{
|
||||
"name": "openclaw",
|
||||
"status": "disabled",
|
||||
"details": {"reason": "runtime_not_configured"},
|
||||
}
|
||||
)
|
||||
else:
|
||||
try:
|
||||
health = self.openclaw.health()
|
||||
runtimes.append(
|
||||
{
|
||||
"name": "openclaw",
|
||||
"status": health.status,
|
||||
"details": _json_value(health),
|
||||
}
|
||||
)
|
||||
except Exception as exc:
|
||||
runtimes.append(
|
||||
{
|
||||
"name": "openclaw",
|
||||
"status": "unavailable",
|
||||
"details": {"message": str(exc)},
|
||||
}
|
||||
)
|
||||
hermes_health = self.hermes.health()
|
||||
runtimes.append(
|
||||
{
|
||||
"name": "hermes",
|
||||
"status": hermes_health.status,
|
||||
"details": _json_value(hermes_health),
|
||||
}
|
||||
)
|
||||
return HTTPStatus.OK, {
|
||||
"tenant_id": context.tenant_id,
|
||||
"runtimes": runtimes,
|
||||
}
|
||||
|
||||
if method == "GET" and path == "/api/v2/executions":
|
||||
context = self.context(headers)
|
||||
return HTTPStatus.OK, {
|
||||
"executions": _json_value(
|
||||
self.tracker.list(tenant_id=context.tenant_id)
|
||||
)
|
||||
}
|
||||
|
||||
dispatch_match = __import__("re").fullmatch(
|
||||
r"/api/v2/tasks/([^/]+)/dispatch", path
|
||||
)
|
||||
if method == "POST" and dispatch_match:
|
||||
context = self.context(headers)
|
||||
task_id = urllib.parse.unquote(dispatch_match.group(1))
|
||||
payload = body if isinstance(body, Mapping) else {}
|
||||
timeout = payload.get("timeout_seconds")
|
||||
provenance_id, run_id = _provenance_context(headers, payload)
|
||||
record = self.orchestrator.dispatch(
|
||||
context,
|
||||
task_id=task_id,
|
||||
timeout_seconds=float(timeout) if timeout is not None else None,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
return HTTPStatus.ACCEPTED, {"dispatch": _json_value(record)}
|
||||
|
||||
lifecycle_match = __import__("re").fullmatch(
|
||||
r"/api/v2/internal/runtime/hermes/lifecycle/"
|
||||
r"(claim|start|heartbeat|complete|fail|cancel|status)",
|
||||
path,
|
||||
)
|
||||
if method == "POST" and lifecycle_match:
|
||||
if not self.hermes_lifecycle_api_enabled:
|
||||
return HTTPStatus.NOT_FOUND, {
|
||||
"error": "not_found",
|
||||
"message": "route not found",
|
||||
}
|
||||
context = self.context(headers)
|
||||
self._require_runtime_role(context)
|
||||
if not isinstance(body, Mapping):
|
||||
raise ValueError("JSON body must be an object")
|
||||
payload = body
|
||||
action = lifecycle_match.group(1)
|
||||
identity = {
|
||||
name: self._required_identity(payload, name)
|
||||
for name in (
|
||||
"dispatch_id",
|
||||
"job_id",
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"trace_id",
|
||||
"principal_id",
|
||||
"provenance_id",
|
||||
"run_id",
|
||||
"cell_id",
|
||||
"profile_id",
|
||||
)
|
||||
}
|
||||
header_provenance, header_run = _provenance_context(headers, payload)
|
||||
if header_provenance != identity["provenance_id"]:
|
||||
raise ValueError("provenance_id context mismatch")
|
||||
if header_run != identity["run_id"]:
|
||||
raise ValueError("run_id context mismatch")
|
||||
requeued_job_ids = self.hermes.requeue_expired()
|
||||
dispatch, job = self.orchestrator.hermes_lifecycle_context(
|
||||
context,
|
||||
dispatch_id=identity["dispatch_id"],
|
||||
job_id=identity["job_id"],
|
||||
tenant_id=identity["tenant_id"],
|
||||
task_id=identity["task_id"],
|
||||
trace_id=identity["trace_id"],
|
||||
principal_id=identity["principal_id"],
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
if job.cell_id != identity["cell_id"]:
|
||||
raise ValueError("cell_id mismatch")
|
||||
if job.profile_id != identity["profile_id"]:
|
||||
raise ValueError("profile_id mismatch")
|
||||
|
||||
if action == "status":
|
||||
if job.job_id in requeued_job_ids:
|
||||
self._record_hermes_lifecycle(
|
||||
context,
|
||||
dispatch,
|
||||
job,
|
||||
action="lease_expired_requeue",
|
||||
worker_id=None,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
task = self.orchestrator.control_plane.get_task(
|
||||
context, dispatch.task_id
|
||||
)
|
||||
response: dict[str, Any] = {
|
||||
"job": _json_value(job),
|
||||
"dispatch": _json_value(dispatch),
|
||||
"task": _json_value(task),
|
||||
}
|
||||
if job.state in {
|
||||
HermesJobState.COMPLETED,
|
||||
HermesJobState.FAILED,
|
||||
HermesJobState.CANCELLED,
|
||||
}:
|
||||
response["result"] = _json_value(
|
||||
self.hermes.result(job.job_id, tenant_id=job.tenant_id)
|
||||
)
|
||||
return HTTPStatus.OK, response
|
||||
|
||||
expected_revision = payload.get("expected_revision")
|
||||
expected = (
|
||||
int(expected_revision) if expected_revision is not None else None
|
||||
)
|
||||
if action == "cancel":
|
||||
self._require_control_plane_cancel(context)
|
||||
if payload.get("worker_id") is not None:
|
||||
raise Unauthorized("Hermes workers may observe but not initiate cancel")
|
||||
if payload.get("cancellation_source") != "aios-control-plane":
|
||||
raise ValueError(
|
||||
"cancellation_source must be aios-control-plane"
|
||||
)
|
||||
result = self.hermes.cancel(
|
||||
job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
expected_revision=expected,
|
||||
)
|
||||
else:
|
||||
worker_id = self._required_identity(payload, "worker_id")
|
||||
if action == "claim":
|
||||
claimed = self.hermes.claim(
|
||||
tenant_id=job.tenant_id,
|
||||
cell_id=job.cell_id,
|
||||
profile_id=job.profile_id,
|
||||
worker_id=worker_id,
|
||||
lease_seconds=(
|
||||
int(payload["lease_seconds"])
|
||||
if payload.get("lease_seconds") is not None
|
||||
else None
|
||||
),
|
||||
job_id=job.job_id,
|
||||
)
|
||||
if claimed is None:
|
||||
raise ValueError("Hermes job is not claimable")
|
||||
bound = self.orchestrator.bind_hermes_worker(
|
||||
context,
|
||||
claimed,
|
||||
dispatch_id=dispatch.dispatch_id,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
worker_id=worker_id,
|
||||
)
|
||||
self._record_hermes_lifecycle(
|
||||
context,
|
||||
bound,
|
||||
claimed,
|
||||
action="claim",
|
||||
worker_id=worker_id,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
return HTTPStatus.OK, {
|
||||
"job": _json_value(claimed),
|
||||
"dispatch": _json_value(bound),
|
||||
}
|
||||
if action == "start":
|
||||
started = self.hermes.start(
|
||||
job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
worker_id=worker_id,
|
||||
expected_revision=expected,
|
||||
)
|
||||
self._record_hermes_lifecycle(
|
||||
context,
|
||||
dispatch,
|
||||
started,
|
||||
action="start",
|
||||
worker_id=worker_id,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
return HTTPStatus.OK, {"job": _json_value(started)}
|
||||
if action == "heartbeat":
|
||||
heartbeat = self.hermes.heartbeat(
|
||||
job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
worker_id=worker_id,
|
||||
lease_seconds=(
|
||||
int(payload["lease_seconds"])
|
||||
if payload.get("lease_seconds") is not None
|
||||
else None
|
||||
),
|
||||
)
|
||||
self._record_hermes_lifecycle(
|
||||
context,
|
||||
dispatch,
|
||||
heartbeat,
|
||||
action="heartbeat",
|
||||
worker_id=worker_id,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
return HTTPStatus.OK, {"job": _json_value(heartbeat)}
|
||||
if action == "complete":
|
||||
output = payload.get("output")
|
||||
if not isinstance(output, Mapping):
|
||||
raise ValueError("output must be an object")
|
||||
result = self.hermes.complete(
|
||||
job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
worker_id=worker_id,
|
||||
output=output,
|
||||
expected_revision=expected,
|
||||
)
|
||||
elif action == "fail":
|
||||
error = payload.get("error")
|
||||
if not isinstance(error, Mapping):
|
||||
raise ValueError("error must be an object")
|
||||
result = self.hermes.fail(
|
||||
job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
worker_id=worker_id,
|
||||
error=error,
|
||||
expected_revision=expected,
|
||||
)
|
||||
else:
|
||||
raise ValueError("unsupported Hermes lifecycle action")
|
||||
|
||||
task = self.orchestrator.reconcile_hermes(
|
||||
context,
|
||||
result,
|
||||
dispatch_id=dispatch.dispatch_id,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
updated_dispatch = self.orchestrator.dispatch_repository.get(
|
||||
dispatch.dispatch_id, tenant_id=dispatch.tenant_id
|
||||
)
|
||||
terminal_job = self.hermes.get(job.job_id, tenant_id=job.tenant_id)
|
||||
self._record_hermes_lifecycle(
|
||||
context,
|
||||
updated_dispatch,
|
||||
terminal_job,
|
||||
action=action,
|
||||
worker_id=result.worker_id,
|
||||
provenance_id=identity["provenance_id"],
|
||||
run_id=identity["run_id"],
|
||||
)
|
||||
return HTTPStatus.OK, {
|
||||
"result": _json_value(result),
|
||||
"task": _json_value(task),
|
||||
"dispatch": _json_value(updated_dispatch),
|
||||
}
|
||||
|
||||
if method == "POST" and path == "/api/v2/internal/runtime/hermes/reconcile":
|
||||
context = self.context(headers)
|
||||
self._require_runtime_role(context)
|
||||
if not isinstance(body, Mapping):
|
||||
raise ValueError("JSON body must be an object")
|
||||
provenance_id, run_id = _provenance_context(headers, body)
|
||||
if not provenance_id or not run_id:
|
||||
raise ValueError("provenance_id and run_id are required")
|
||||
dispatch_id = str(body.get("dispatch_id") or "").strip()
|
||||
if not dispatch_id:
|
||||
raise ValueError("dispatch_id is required")
|
||||
result = HermesResult(
|
||||
job_id=str(body["job_id"]),
|
||||
tenant_id=str(body["tenant_id"]),
|
||||
task_id=str(body["task_id"]),
|
||||
trace_id=str(body["trace_id"]),
|
||||
state=HermesJobState(str(body["state"])),
|
||||
worker_id=(
|
||||
str(body["worker_id"])
|
||||
if body.get("worker_id") is not None
|
||||
else None
|
||||
),
|
||||
output=body.get("output"),
|
||||
error=body.get("error"),
|
||||
started_at=body.get("started_at"),
|
||||
finished_at=body.get("finished_at"),
|
||||
)
|
||||
task = self.orchestrator.reconcile_hermes(
|
||||
context,
|
||||
result,
|
||||
dispatch_id=dispatch_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
return HTTPStatus.OK, {"task": _json_value(task)}
|
||||
|
||||
if method == "POST" and path == "/api/v2/hermes/results/reconcile":
|
||||
return HTTPStatus.GONE, {
|
||||
"error": "RuntimeReconcileEndpointMoved",
|
||||
"message": "use /api/v2/internal/runtime/hermes/reconcile",
|
||||
}
|
||||
|
||||
return self.gateway.handle(method, raw_path, headers, body)
|
||||
|
||||
|
||||
class CandidateRequestHandler(BaseHTTPRequestHandler):
|
||||
server_version = "AIOSV2Candidate/2.0"
|
||||
max_body_bytes = 1_048_576
|
||||
|
||||
@property
|
||||
def application(self) -> CandidateApplication:
|
||||
return self.server.application # type: ignore[attr-defined]
|
||||
|
||||
def _read_body(self) -> Any:
|
||||
length = int(self.headers.get("Content-Length", "0") or "0")
|
||||
if length < 0 or length > self.max_body_bytes:
|
||||
raise ValueError("request body is too large")
|
||||
if length == 0:
|
||||
return {}
|
||||
content_type = self.headers.get("Content-Type", "").split(";", 1)[0].strip()
|
||||
if content_type != "application/json":
|
||||
raise ValueError("Content-Type must be application/json")
|
||||
return json.loads(self.rfile.read(length).decode("utf-8"))
|
||||
|
||||
def _security_headers(self) -> None:
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("X-Content-Type-Options", "nosniff")
|
||||
self.send_header("X-Frame-Options", "DENY")
|
||||
self.send_header("Referrer-Policy", "no-referrer")
|
||||
self.send_header(
|
||||
"Content-Security-Policy",
|
||||
"default-src 'self'; style-src 'unsafe-inline'; script-src 'unsafe-inline'; connect-src 'self'",
|
||||
)
|
||||
|
||||
def _send_json(self, status_code: int, payload: Mapping[str, Any]) -> None:
|
||||
encoded = json.dumps(
|
||||
_json_value(payload), ensure_ascii=False, separators=(",", ":")
|
||||
).encode("utf-8")
|
||||
self.send_response(int(status_code))
|
||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(encoded)))
|
||||
self._security_headers()
|
||||
self.end_headers()
|
||||
self.wfile.write(encoded)
|
||||
|
||||
def _send_console(self) -> None:
|
||||
encoded = CONSOLE_HTML.encode("utf-8")
|
||||
self.send_response(HTTPStatus.OK)
|
||||
self.send_header("Content-Type", "text/html; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(encoded)))
|
||||
self._security_headers()
|
||||
self.end_headers()
|
||||
self.wfile.write(encoded)
|
||||
|
||||
def _dispatch(self, method: str) -> None:
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if method == "GET" and path in {"/", "/console"}:
|
||||
self._send_console()
|
||||
return
|
||||
try:
|
||||
body = self._read_body() if method == "POST" else {}
|
||||
status_code, payload = self.application.handle_json(
|
||||
method,
|
||||
self.path,
|
||||
{key: value for key, value in self.headers.items()},
|
||||
body,
|
||||
)
|
||||
except Exception as exc:
|
||||
status_code, payload = error_response(exc)
|
||||
self._send_json(status_code, payload)
|
||||
|
||||
def do_GET(self) -> None: # noqa: N802
|
||||
self._dispatch("GET")
|
||||
|
||||
def do_POST(self) -> None: # noqa: N802
|
||||
self._dispatch("POST")
|
||||
|
||||
|
||||
class CandidateHTTPServer(ThreadingHTTPServer):
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], application: CandidateApplication) -> None:
|
||||
self.application = application
|
||||
super().__init__(address, CandidateRequestHandler)
|
||||
|
||||
|
||||
def build_application() -> CandidateApplication:
|
||||
state_dir = Path(os.getenv("AIOS_V2_STATE_DIR", "/var/lib/aios-v2")).resolve()
|
||||
state_dir.mkdir(parents=True, exist_ok=True)
|
||||
repository = SQLiteSnapshotRepository(state_dir / "control-plane.sqlite3")
|
||||
dispatch_repository = SQLiteDispatchRepository(state_dir / "dispatches.sqlite3")
|
||||
service = DurableControlPlaneService(repository)
|
||||
require_provenance = _enabled(os.getenv("AIOS_REQUIRE_RUN_PROVENANCE", "0"))
|
||||
provenance_writer = build_provenance_writer_from_env(
|
||||
state_dir=state_dir, required=require_provenance
|
||||
)
|
||||
tracker = ExecutionTracker(
|
||||
state_dir / "executions",
|
||||
provenance_writer=provenance_writer,
|
||||
require_provenance=require_provenance,
|
||||
)
|
||||
hermes = HermesAdapter(store=SQLiteHermesStore(state_dir / "hermes.sqlite3"))
|
||||
|
||||
openclaw_url = os.getenv("AIOS_OPENCLAW_URL", "").strip()
|
||||
signing_file = os.getenv("AIOS_OPENCLAW_SIGNING_MATERIAL_FILE", "").strip()
|
||||
signing_key_id = os.getenv(
|
||||
"AIOS_OPENCLAW_SIGNING_KEY_ID", "openclaw-v2r1-candidate-ed25519"
|
||||
).strip()
|
||||
openclaw = None
|
||||
resolver = None
|
||||
if openclaw_url and signing_file:
|
||||
resolver = FileCommandSignerResolver(
|
||||
signing_file,
|
||||
configured_key_id=signing_key_id,
|
||||
)
|
||||
transport = HTTPRuntimeTransport(
|
||||
openclaw_url,
|
||||
credential_ref=os.getenv("AIOS_OPENCLAW_CREDENTIAL_REF") or None,
|
||||
)
|
||||
openclaw = OpenClawAdapter(
|
||||
transport,
|
||||
resolver,
|
||||
callback_sink=AuditCallbackSink(ControlPlaneEventPublisher(service)),
|
||||
)
|
||||
|
||||
gateway = GatewayApplication(service)
|
||||
orchestrator = ExecutionOrchestrator(
|
||||
service,
|
||||
openclaw=openclaw,
|
||||
hermes=hermes,
|
||||
openclaw_signing_material_resolver=resolver,
|
||||
openclaw_key_id=signing_key_id,
|
||||
provenance_writer=provenance_writer,
|
||||
require_provenance=require_provenance,
|
||||
dispatch_repository=dispatch_repository,
|
||||
)
|
||||
return CandidateApplication(
|
||||
gateway,
|
||||
orchestrator,
|
||||
tracker,
|
||||
hermes,
|
||||
openclaw,
|
||||
hermes_lifecycle_api_enabled=_enabled(
|
||||
os.getenv("AIOS_HERMES_LIFECYCLE_API_ENABLED", "0")
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
host = os.getenv("AIOS_V2_HOST", "127.0.0.1")
|
||||
port = int(os.getenv("AIOS_V2_PORT", "18920"))
|
||||
server = CandidateHTTPServer((host, port), build_application())
|
||||
print(f"AIOS V2 candidate listening on {host}:{port}")
|
||||
server.serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -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=>({'&':'&','<':'<','>':'>','"':'"',"'":'''}[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>'''
|
||||
@@ -0,0 +1,627 @@
|
||||
"""Tenant-isolated AIOS V2 control-plane domain service.
|
||||
|
||||
This module deliberately contains no OpenClaw or Hermes implementation details.
|
||||
It owns authoritative tenant, agent, task-lifecycle, idempotency and audit state.
|
||||
Runtime adapters consume approved tasks through a separate boundary.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import copy
|
||||
import hashlib
|
||||
import json
|
||||
import threading
|
||||
import uuid
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from enum import Enum
|
||||
from typing import Any, Callable, Iterable, Mapping
|
||||
|
||||
|
||||
def _utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def _new_id(prefix: str) -> str:
|
||||
return f"{prefix}_{uuid.uuid4().hex}"
|
||||
|
||||
|
||||
def _canonical_digest(value: Mapping[str, Any]) -> str:
|
||||
encoded = json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
).encode("utf-8")
|
||||
return hashlib.sha256(encoded).hexdigest()
|
||||
|
||||
|
||||
class ControlPlaneError(RuntimeError):
|
||||
"""Base error returned by the control-plane domain."""
|
||||
|
||||
|
||||
class Unauthorized(ControlPlaneError):
|
||||
"""The caller is not authenticated or lacks the required role."""
|
||||
|
||||
|
||||
class TenantIsolationError(ControlPlaneError):
|
||||
"""A request attempted to cross a tenant boundary."""
|
||||
|
||||
|
||||
class NotFound(ControlPlaneError):
|
||||
"""A tenant-scoped resource does not exist or is not visible."""
|
||||
|
||||
|
||||
class InvalidTransition(ControlPlaneError):
|
||||
"""A task state transition violates the lifecycle contract."""
|
||||
|
||||
|
||||
class IdempotencyConflict(ControlPlaneError):
|
||||
"""An idempotency key was reused for a different command."""
|
||||
|
||||
|
||||
class RevisionConflict(ControlPlaneError):
|
||||
"""Optimistic task revision does not match current state."""
|
||||
|
||||
|
||||
class PolicyDenied(ControlPlaneError):
|
||||
"""The policy gate denied a control-plane operation."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RequestContext:
|
||||
"""Authenticated request identity propagated across all AIOS layers."""
|
||||
|
||||
tenant_id: str
|
||||
principal_id: str
|
||||
trace_id: str
|
||||
roles: frozenset[str] = field(default_factory=frozenset)
|
||||
session_id: str | None = None
|
||||
policy_version: str = "v1"
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in ("tenant_id", "principal_id", "trace_id"):
|
||||
if not str(getattr(self, name, "")).strip():
|
||||
raise ValueError(f"{name} is required")
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
*,
|
||||
tenant_id: str,
|
||||
principal_id: str,
|
||||
roles: Iterable[str] = (),
|
||||
trace_id: str | None = None,
|
||||
session_id: str | None = None,
|
||||
policy_version: str = "v1",
|
||||
) -> "RequestContext":
|
||||
return cls(
|
||||
tenant_id=tenant_id.strip(),
|
||||
principal_id=principal_id.strip(),
|
||||
trace_id=trace_id or _new_id("trace"),
|
||||
roles=frozenset(str(role).strip() for role in roles if str(role).strip()),
|
||||
session_id=session_id,
|
||||
policy_version=policy_version,
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TenantRecord:
|
||||
tenant_id: str
|
||||
display_name: str
|
||||
status: str = "active"
|
||||
metadata: Mapping[str, Any] = field(default_factory=dict)
|
||||
created_at: str = field(default_factory=_utc_now)
|
||||
updated_at: str = field(default_factory=_utc_now)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AgentRecord:
|
||||
agent_id: str
|
||||
tenant_id: str
|
||||
display_name: str
|
||||
runtime: str
|
||||
capabilities: tuple[str, ...] = field(default_factory=tuple)
|
||||
enabled: bool = True
|
||||
metadata: Mapping[str, Any] = field(default_factory=dict)
|
||||
created_at: str = field(default_factory=_utc_now)
|
||||
updated_at: str = field(default_factory=_utc_now)
|
||||
|
||||
|
||||
class TaskState(str, Enum):
|
||||
CREATED = "CREATED"
|
||||
APPROVED = "APPROVED"
|
||||
RUNNING = "RUNNING"
|
||||
COMPLETED = "COMPLETED"
|
||||
FAILED = "FAILED"
|
||||
CANCELLED = "CANCELLED"
|
||||
|
||||
|
||||
TERMINAL_TASK_STATES = frozenset(
|
||||
{TaskState.COMPLETED, TaskState.FAILED, TaskState.CANCELLED}
|
||||
)
|
||||
|
||||
ALLOWED_TASK_TRANSITIONS: Mapping[TaskState, frozenset[TaskState]] = {
|
||||
TaskState.CREATED: frozenset({TaskState.APPROVED, TaskState.CANCELLED}),
|
||||
TaskState.APPROVED: frozenset({TaskState.RUNNING, TaskState.CANCELLED}),
|
||||
TaskState.RUNNING: frozenset(
|
||||
{TaskState.COMPLETED, TaskState.FAILED, TaskState.CANCELLED}
|
||||
),
|
||||
TaskState.COMPLETED: frozenset(),
|
||||
TaskState.FAILED: frozenset(),
|
||||
TaskState.CANCELLED: frozenset(),
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskRecord:
|
||||
task_id: str
|
||||
tenant_id: str
|
||||
agent_id: str
|
||||
action: str
|
||||
payload: Mapping[str, Any]
|
||||
state: TaskState = TaskState.CREATED
|
||||
revision: int = 1
|
||||
idempotency_key: str | None = None
|
||||
request_digest: str = ""
|
||||
result: Mapping[str, Any] | None = None
|
||||
error: Mapping[str, Any] | None = None
|
||||
created_by: str = ""
|
||||
approved_by: str | None = None
|
||||
created_at: str = field(default_factory=_utc_now)
|
||||
updated_at: str = field(default_factory=_utc_now)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AuditEvent:
|
||||
event_id: str
|
||||
tenant_id: str
|
||||
principal_id: str
|
||||
trace_id: str
|
||||
action: str
|
||||
resource_type: str
|
||||
resource_id: str
|
||||
outcome: str
|
||||
policy_version: str
|
||||
details: Mapping[str, Any] = field(default_factory=dict)
|
||||
created_at: str = field(default_factory=_utc_now)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class PolicyDecision:
|
||||
allowed: bool
|
||||
reason: str
|
||||
policy_version: str
|
||||
|
||||
|
||||
PolicyEvaluator = Callable[[RequestContext, str, Mapping[str, Any]], PolicyDecision]
|
||||
|
||||
|
||||
class InMemoryControlPlaneStore:
|
||||
"""Thread-safe reference store used by tests and the first gateway slice.
|
||||
|
||||
Production backends must preserve the same tenant-scoped interface and add
|
||||
database row-level security, migrations, backup and HA evidence.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.lock = threading.RLock()
|
||||
self.tenants: dict[str, TenantRecord] = {}
|
||||
self.agents: dict[str, AgentRecord] = {}
|
||||
self.tasks: dict[str, TaskRecord] = {}
|
||||
self.idempotency: dict[tuple[str, str], tuple[str, str]] = {}
|
||||
self.audit_events: list[AuditEvent] = []
|
||||
|
||||
|
||||
class ControlPlaneService:
|
||||
"""Authoritative tenant, agent and task lifecycle service."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
store: InMemoryControlPlaneStore | None = None,
|
||||
*,
|
||||
policy_evaluator: PolicyEvaluator | None = None,
|
||||
) -> None:
|
||||
self.store = store or InMemoryControlPlaneStore()
|
||||
self.policy_evaluator = policy_evaluator or self._default_policy
|
||||
|
||||
@staticmethod
|
||||
def _default_policy(
|
||||
context: RequestContext,
|
||||
action: str,
|
||||
resource: Mapping[str, Any],
|
||||
) -> PolicyDecision:
|
||||
del resource
|
||||
role_requirements = {
|
||||
"tenant.register": {"platform_admin"},
|
||||
"tenant.read": {"tenant_admin", "operator", "auditor", "platform_admin"},
|
||||
"agent.register": {"tenant_admin", "operator", "platform_admin"},
|
||||
"agent.read": {"tenant_admin", "operator", "auditor", "platform_admin"},
|
||||
"task.create": {"tenant_admin", "operator", "platform_admin"},
|
||||
"task.read": {"tenant_admin", "operator", "auditor", "platform_admin"},
|
||||
"task.approve": {"tenant_admin", "approver", "platform_admin"},
|
||||
"task.start": {"runtime", "operator", "platform_admin"},
|
||||
"task.complete": {"runtime", "operator", "platform_admin"},
|
||||
"task.fail": {"runtime", "operator", "platform_admin"},
|
||||
"task.cancel": {"tenant_admin", "operator", "approver", "platform_admin"},
|
||||
"audit.read": {"tenant_admin", "auditor", "platform_admin"},
|
||||
}
|
||||
required = role_requirements.get(action, {"platform_admin"})
|
||||
allowed = bool(context.roles.intersection(required))
|
||||
return PolicyDecision(
|
||||
allowed=allowed,
|
||||
reason="role_allowed" if allowed else "required_role_missing",
|
||||
policy_version=context.policy_version,
|
||||
)
|
||||
|
||||
def _require_context(self, context: RequestContext) -> None:
|
||||
if not context.principal_id or not context.tenant_id or not context.trace_id:
|
||||
raise Unauthorized("authenticated tenant context is required")
|
||||
|
||||
def _authorize(
|
||||
self,
|
||||
context: RequestContext,
|
||||
action: str,
|
||||
resource: Mapping[str, Any],
|
||||
) -> PolicyDecision:
|
||||
self._require_context(context)
|
||||
decision = self.policy_evaluator(context, action, resource)
|
||||
if not decision.allowed:
|
||||
self._audit(
|
||||
context,
|
||||
action=action,
|
||||
resource_type=str(resource.get("resource_type", "policy")),
|
||||
resource_id=str(resource.get("resource_id", "unknown")),
|
||||
outcome="denied",
|
||||
details={"reason": decision.reason},
|
||||
)
|
||||
raise PolicyDenied(f"{action} denied: {decision.reason}")
|
||||
return decision
|
||||
|
||||
@staticmethod
|
||||
def _assert_same_tenant(context: RequestContext, tenant_id: str) -> None:
|
||||
if context.tenant_id != tenant_id and "platform_admin" not in context.roles:
|
||||
raise TenantIsolationError("cross-tenant access denied")
|
||||
|
||||
def _audit(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
action: str,
|
||||
resource_type: str,
|
||||
resource_id: str,
|
||||
outcome: str,
|
||||
details: Mapping[str, Any] | None = None,
|
||||
) -> AuditEvent:
|
||||
event = AuditEvent(
|
||||
event_id=_new_id("audit"),
|
||||
tenant_id=context.tenant_id,
|
||||
principal_id=context.principal_id,
|
||||
trace_id=context.trace_id,
|
||||
action=action,
|
||||
resource_type=resource_type,
|
||||
resource_id=resource_id,
|
||||
outcome=outcome,
|
||||
policy_version=context.policy_version,
|
||||
details=copy.deepcopy(dict(details or {})),
|
||||
)
|
||||
self.store.audit_events.append(event)
|
||||
return event
|
||||
|
||||
def register_tenant(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
tenant_id: str,
|
||||
display_name: str,
|
||||
metadata: Mapping[str, Any] | None = None,
|
||||
) -> TenantRecord:
|
||||
tenant_id = tenant_id.strip()
|
||||
if not tenant_id or not display_name.strip():
|
||||
raise ValueError("tenant_id and display_name are required")
|
||||
self._authorize(
|
||||
context,
|
||||
"tenant.register",
|
||||
{"resource_type": "tenant", "resource_id": tenant_id},
|
||||
)
|
||||
self._assert_same_tenant(context, tenant_id)
|
||||
with self.store.lock:
|
||||
if tenant_id in self.store.tenants:
|
||||
raise ControlPlaneError(f"tenant already exists: {tenant_id}")
|
||||
tenant = TenantRecord(
|
||||
tenant_id=tenant_id,
|
||||
display_name=display_name.strip(),
|
||||
metadata=copy.deepcopy(dict(metadata or {})),
|
||||
)
|
||||
self.store.tenants[tenant_id] = tenant
|
||||
self._audit(
|
||||
context,
|
||||
action="tenant.register",
|
||||
resource_type="tenant",
|
||||
resource_id=tenant_id,
|
||||
outcome="allowed",
|
||||
)
|
||||
return tenant
|
||||
|
||||
def get_tenant(self, context: RequestContext, tenant_id: str | None = None) -> TenantRecord:
|
||||
tenant_id = tenant_id or context.tenant_id
|
||||
self._authorize(
|
||||
context,
|
||||
"tenant.read",
|
||||
{"resource_type": "tenant", "resource_id": tenant_id},
|
||||
)
|
||||
self._assert_same_tenant(context, tenant_id)
|
||||
with self.store.lock:
|
||||
tenant = self.store.tenants.get(tenant_id)
|
||||
if tenant is None:
|
||||
raise NotFound("tenant not found")
|
||||
return tenant
|
||||
|
||||
def register_agent(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
agent_id: str,
|
||||
display_name: str,
|
||||
runtime: str,
|
||||
capabilities: Iterable[str] = (),
|
||||
metadata: Mapping[str, Any] | None = None,
|
||||
) -> AgentRecord:
|
||||
self._authorize(
|
||||
context,
|
||||
"agent.register",
|
||||
{"resource_type": "agent", "resource_id": agent_id},
|
||||
)
|
||||
tenant = self.get_tenant(context)
|
||||
if tenant.status != "active":
|
||||
raise ControlPlaneError("tenant is not active")
|
||||
normalized_capabilities = tuple(
|
||||
sorted({str(item).strip() for item in capabilities if str(item).strip()})
|
||||
)
|
||||
if not agent_id.strip() or not display_name.strip() or not runtime.strip():
|
||||
raise ValueError("agent_id, display_name and runtime are required")
|
||||
with self.store.lock:
|
||||
existing = self.store.agents.get(agent_id)
|
||||
if existing is not None and existing.tenant_id != context.tenant_id:
|
||||
raise TenantIsolationError("agent id belongs to another tenant")
|
||||
if existing is not None:
|
||||
raise ControlPlaneError(f"agent already exists: {agent_id}")
|
||||
agent = AgentRecord(
|
||||
agent_id=agent_id.strip(),
|
||||
tenant_id=context.tenant_id,
|
||||
display_name=display_name.strip(),
|
||||
runtime=runtime.strip(),
|
||||
capabilities=normalized_capabilities,
|
||||
metadata=copy.deepcopy(dict(metadata or {})),
|
||||
)
|
||||
self.store.agents[agent.agent_id] = agent
|
||||
self._audit(
|
||||
context,
|
||||
action="agent.register",
|
||||
resource_type="agent",
|
||||
resource_id=agent.agent_id,
|
||||
outcome="allowed",
|
||||
details={"runtime": agent.runtime},
|
||||
)
|
||||
return agent
|
||||
|
||||
def get_agent(self, context: RequestContext, agent_id: str) -> AgentRecord:
|
||||
self._authorize(
|
||||
context,
|
||||
"agent.read",
|
||||
{"resource_type": "agent", "resource_id": agent_id},
|
||||
)
|
||||
with self.store.lock:
|
||||
agent = self.store.agents.get(agent_id)
|
||||
if agent is None:
|
||||
raise NotFound("agent not found")
|
||||
self._assert_same_tenant(context, agent.tenant_id)
|
||||
return agent
|
||||
|
||||
def list_agents(self, context: RequestContext) -> list[AgentRecord]:
|
||||
self._authorize(
|
||||
context,
|
||||
"agent.read",
|
||||
{"resource_type": "agent_collection", "resource_id": context.tenant_id},
|
||||
)
|
||||
with self.store.lock:
|
||||
return [
|
||||
agent
|
||||
for agent in self.store.agents.values()
|
||||
if agent.tenant_id == context.tenant_id
|
||||
]
|
||||
|
||||
def create_task(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
agent_id: str,
|
||||
action: str,
|
||||
payload: Mapping[str, Any] | None = None,
|
||||
idempotency_key: str | None = None,
|
||||
) -> TaskRecord:
|
||||
self._authorize(
|
||||
context,
|
||||
"task.create",
|
||||
{"resource_type": "task", "resource_id": idempotency_key or "new"},
|
||||
)
|
||||
agent = self.get_agent(context, agent_id)
|
||||
if not agent.enabled:
|
||||
raise ControlPlaneError("agent is disabled")
|
||||
if action not in agent.capabilities and "*" not in agent.capabilities:
|
||||
raise PolicyDenied(f"agent does not advertise capability: {action}")
|
||||
normalized_payload = copy.deepcopy(dict(payload or {}))
|
||||
request_digest = _canonical_digest(
|
||||
{"agent_id": agent_id, "action": action, "payload": normalized_payload}
|
||||
)
|
||||
normalized_key = idempotency_key.strip() if idempotency_key else None
|
||||
with self.store.lock:
|
||||
if normalized_key:
|
||||
idempotency_ref = (context.tenant_id, normalized_key)
|
||||
existing = self.store.idempotency.get(idempotency_ref)
|
||||
if existing is not None:
|
||||
existing_task_id, existing_digest = existing
|
||||
if existing_digest != request_digest:
|
||||
raise IdempotencyConflict(
|
||||
"idempotency key was reused with a different request"
|
||||
)
|
||||
return self.store.tasks[existing_task_id]
|
||||
task = TaskRecord(
|
||||
task_id=_new_id("task"),
|
||||
tenant_id=context.tenant_id,
|
||||
agent_id=agent_id,
|
||||
action=action,
|
||||
payload=normalized_payload,
|
||||
idempotency_key=normalized_key,
|
||||
request_digest=request_digest,
|
||||
created_by=context.principal_id,
|
||||
)
|
||||
self.store.tasks[task.task_id] = task
|
||||
if normalized_key:
|
||||
self.store.idempotency[(context.tenant_id, normalized_key)] = (
|
||||
task.task_id,
|
||||
request_digest,
|
||||
)
|
||||
self._audit(
|
||||
context,
|
||||
action="task.create",
|
||||
resource_type="task",
|
||||
resource_id=task.task_id,
|
||||
outcome="allowed",
|
||||
details={"agent_id": agent_id, "action": action},
|
||||
)
|
||||
return task
|
||||
|
||||
def get_task(self, context: RequestContext, task_id: str) -> TaskRecord:
|
||||
self._authorize(
|
||||
context,
|
||||
"task.read",
|
||||
{"resource_type": "task", "resource_id": task_id},
|
||||
)
|
||||
with self.store.lock:
|
||||
task = self.store.tasks.get(task_id)
|
||||
if task is None:
|
||||
raise NotFound("task not found")
|
||||
self._assert_same_tenant(context, task.tenant_id)
|
||||
return task
|
||||
|
||||
def list_tasks(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
states: Iterable[TaskState | str] | None = None,
|
||||
) -> list[TaskRecord]:
|
||||
self._authorize(
|
||||
context,
|
||||
"task.read",
|
||||
{"resource_type": "task_collection", "resource_id": context.tenant_id},
|
||||
)
|
||||
state_filter = (
|
||||
{TaskState(item) for item in states}
|
||||
if states is not None
|
||||
else None
|
||||
)
|
||||
with self.store.lock:
|
||||
return [
|
||||
task
|
||||
for task in self.store.tasks.values()
|
||||
if task.tenant_id == context.tenant_id
|
||||
and (state_filter is None or task.state in state_filter)
|
||||
]
|
||||
|
||||
def transition_task(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
task_id: str,
|
||||
target_state: TaskState | str,
|
||||
expected_revision: int | None = None,
|
||||
result: Mapping[str, Any] | None = None,
|
||||
error: Mapping[str, Any] | None = None,
|
||||
) -> TaskRecord:
|
||||
target = TaskState(target_state)
|
||||
action_name = {
|
||||
TaskState.APPROVED: "task.approve",
|
||||
TaskState.RUNNING: "task.start",
|
||||
TaskState.COMPLETED: "task.complete",
|
||||
TaskState.FAILED: "task.fail",
|
||||
TaskState.CANCELLED: "task.cancel",
|
||||
}.get(target)
|
||||
if action_name is None:
|
||||
raise InvalidTransition(f"cannot transition to {target.value}")
|
||||
self._authorize(
|
||||
context,
|
||||
action_name,
|
||||
{"resource_type": "task", "resource_id": task_id},
|
||||
)
|
||||
with self.store.lock:
|
||||
current = self.store.tasks.get(task_id)
|
||||
if current is None:
|
||||
raise NotFound("task not found")
|
||||
self._assert_same_tenant(context, current.tenant_id)
|
||||
if expected_revision is not None and current.revision != expected_revision:
|
||||
raise RevisionConflict(
|
||||
f"expected revision {expected_revision}, current {current.revision}"
|
||||
)
|
||||
if target not in ALLOWED_TASK_TRANSITIONS[current.state]:
|
||||
raise InvalidTransition(
|
||||
f"invalid transition {current.state.value} -> {target.value}"
|
||||
)
|
||||
if target == TaskState.COMPLETED and result is None:
|
||||
raise ValueError("completed task requires result")
|
||||
if target == TaskState.FAILED and error is None:
|
||||
raise ValueError("failed task requires error")
|
||||
updated = TaskRecord(
|
||||
task_id=current.task_id,
|
||||
tenant_id=current.tenant_id,
|
||||
agent_id=current.agent_id,
|
||||
action=current.action,
|
||||
payload=current.payload,
|
||||
state=target,
|
||||
revision=current.revision + 1,
|
||||
idempotency_key=current.idempotency_key,
|
||||
request_digest=current.request_digest,
|
||||
result=copy.deepcopy(dict(result)) if result is not None else current.result,
|
||||
error=copy.deepcopy(dict(error)) if error is not None else current.error,
|
||||
created_by=current.created_by,
|
||||
approved_by=(
|
||||
context.principal_id
|
||||
if target == TaskState.APPROVED
|
||||
else current.approved_by
|
||||
),
|
||||
created_at=current.created_at,
|
||||
updated_at=_utc_now(),
|
||||
)
|
||||
self.store.tasks[task_id] = updated
|
||||
self._audit(
|
||||
context,
|
||||
action=action_name,
|
||||
resource_type="task",
|
||||
resource_id=task_id,
|
||||
outcome="allowed",
|
||||
details={
|
||||
"from": current.state.value,
|
||||
"to": target.value,
|
||||
"revision": updated.revision,
|
||||
},
|
||||
)
|
||||
return updated
|
||||
|
||||
def list_audit_events(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
resource_id: str | None = None,
|
||||
) -> list[AuditEvent]:
|
||||
self._authorize(
|
||||
context,
|
||||
"audit.read",
|
||||
{"resource_type": "audit", "resource_id": resource_id or context.tenant_id},
|
||||
)
|
||||
with self.store.lock:
|
||||
return [
|
||||
event
|
||||
for event in self.store.audit_events
|
||||
if event.tenant_id == context.tenant_id
|
||||
and (resource_id is None or event.resource_id == resource_id)
|
||||
]
|
||||
@@ -0,0 +1,379 @@
|
||||
"""AIOS V2 持久化 Dispatch 记录。
|
||||
|
||||
Dispatch 是 AIOS Task 与 Runtime command/job 之间的唯一可信绑定。所有结果回写
|
||||
必须匹配 tenant/task/trace/runtime_execution/provenance/run/principal。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import sqlite3
|
||||
import threading
|
||||
import uuid
|
||||
from dataclasses import asdict, dataclass, replace
|
||||
from datetime import datetime, timezone
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Protocol
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def _required(value: str, label: str) -> str:
|
||||
normalized = str(value or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError(f"{label} is required")
|
||||
return normalized
|
||||
|
||||
|
||||
class DispatchState(str, Enum):
|
||||
PREPARED = "PREPARED"
|
||||
RUNNING = "RUNNING"
|
||||
QUEUED = "QUEUED"
|
||||
COMPLETED = "COMPLETED"
|
||||
FAILED = "FAILED"
|
||||
CANCELLED = "CANCELLED"
|
||||
|
||||
|
||||
TERMINAL_DISPATCH_STATES = frozenset(
|
||||
{DispatchState.COMPLETED, DispatchState.FAILED, DispatchState.CANCELLED}
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class DispatchRecord:
|
||||
dispatch_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
runtime: str
|
||||
runtime_execution_id: str
|
||||
trace_id: str
|
||||
provenance_id: str
|
||||
run_id: str
|
||||
authorization_id: str
|
||||
state: DispatchState = DispatchState.PREPARED
|
||||
expected_worker_id: str | None = None
|
||||
result_digest: str | None = None
|
||||
created_at: str = ""
|
||||
updated_at: str = ""
|
||||
completed_at: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in (
|
||||
"dispatch_id",
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"agent_id",
|
||||
"principal_id",
|
||||
"runtime",
|
||||
"runtime_execution_id",
|
||||
"trace_id",
|
||||
"provenance_id",
|
||||
"run_id",
|
||||
"authorization_id",
|
||||
):
|
||||
object.__setattr__(self, name, _required(getattr(self, name), name))
|
||||
object.__setattr__(self, "state", DispatchState(self.state))
|
||||
now = utc_now()
|
||||
object.__setattr__(self, "created_at", self.created_at or now)
|
||||
object.__setattr__(self, "updated_at", self.updated_at or now)
|
||||
if self.expected_worker_id is not None:
|
||||
object.__setattr__(
|
||||
self,
|
||||
"expected_worker_id",
|
||||
_required(self.expected_worker_id, "expected_worker_id"),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
*,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
principal_id: str,
|
||||
runtime: str,
|
||||
runtime_execution_id: str,
|
||||
trace_id: str,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
authorization_id: str,
|
||||
) -> "DispatchRecord":
|
||||
return cls(
|
||||
dispatch_id=f"dispatch_{uuid.uuid4().hex}",
|
||||
tenant_id=tenant_id,
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
principal_id=principal_id,
|
||||
runtime=runtime,
|
||||
runtime_execution_id=runtime_execution_id,
|
||||
trace_id=trace_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
authorization_id=authorization_id,
|
||||
)
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
value = asdict(self)
|
||||
value["state"] = self.state.value
|
||||
return value
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, value: Mapping[str, Any]) -> "DispatchRecord":
|
||||
return cls(**dict(value))
|
||||
|
||||
|
||||
class DispatchConflict(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
class DispatchNotFound(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
class DispatchRepository(Protocol):
|
||||
def create(self, record: DispatchRecord) -> DispatchRecord: ...
|
||||
def get(self, dispatch_id: str, *, tenant_id: str) -> DispatchRecord: ...
|
||||
def get_by_task(self, task_id: str, *, tenant_id: str) -> DispatchRecord | None: ...
|
||||
def get_by_runtime_execution(
|
||||
self, runtime_execution_id: str, *, tenant_id: str
|
||||
) -> DispatchRecord | None: ...
|
||||
def update(
|
||||
self,
|
||||
dispatch_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
state: DispatchState | str | None = None,
|
||||
expected_worker_id: str | None = None,
|
||||
result_digest: str | None = None,
|
||||
) -> DispatchRecord: ...
|
||||
def list(self, *, tenant_id: str) -> list[DispatchRecord]: ...
|
||||
|
||||
|
||||
class InMemoryDispatchRepository:
|
||||
def __init__(self) -> None:
|
||||
self._lock = threading.RLock()
|
||||
self._records: dict[str, DispatchRecord] = {}
|
||||
self._by_task: dict[tuple[str, str], str] = {}
|
||||
self._by_runtime: dict[tuple[str, str], str] = {}
|
||||
|
||||
def create(self, record: DispatchRecord) -> DispatchRecord:
|
||||
with self._lock:
|
||||
task_ref = (record.tenant_id, record.task_id)
|
||||
runtime_ref = (record.tenant_id, record.runtime_execution_id)
|
||||
if task_ref in self._by_task or runtime_ref in self._by_runtime:
|
||||
existing = self.get_by_task(record.task_id, tenant_id=record.tenant_id)
|
||||
if existing == record:
|
||||
return record
|
||||
raise DispatchConflict("task or runtime execution already has a dispatch")
|
||||
self._records[record.dispatch_id] = record
|
||||
self._by_task[task_ref] = record.dispatch_id
|
||||
self._by_runtime[runtime_ref] = record.dispatch_id
|
||||
return record
|
||||
|
||||
def get(self, dispatch_id: str, *, tenant_id: str) -> DispatchRecord:
|
||||
with self._lock:
|
||||
record = self._records.get(dispatch_id)
|
||||
if record is None or record.tenant_id != tenant_id:
|
||||
raise DispatchNotFound("dispatch not found")
|
||||
return record
|
||||
|
||||
def get_by_task(self, task_id: str, *, tenant_id: str) -> DispatchRecord | None:
|
||||
with self._lock:
|
||||
dispatch_id = self._by_task.get((tenant_id, task_id))
|
||||
return self._records.get(dispatch_id) if dispatch_id else None
|
||||
|
||||
def get_by_runtime_execution(
|
||||
self, runtime_execution_id: str, *, tenant_id: str
|
||||
) -> DispatchRecord | None:
|
||||
with self._lock:
|
||||
dispatch_id = self._by_runtime.get((tenant_id, runtime_execution_id))
|
||||
return self._records.get(dispatch_id) if dispatch_id else None
|
||||
|
||||
def update(
|
||||
self,
|
||||
dispatch_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
state: DispatchState | str | None = None,
|
||||
expected_worker_id: str | None = None,
|
||||
result_digest: str | None = None,
|
||||
) -> DispatchRecord:
|
||||
with self._lock:
|
||||
current = self.get(dispatch_id, tenant_id=tenant_id)
|
||||
target = DispatchState(state) if state is not None else current.state
|
||||
if current.state in TERMINAL_DISPATCH_STATES and target != current.state:
|
||||
raise DispatchConflict("terminal dispatch cannot transition")
|
||||
updated = replace(
|
||||
current,
|
||||
state=target,
|
||||
expected_worker_id=(
|
||||
expected_worker_id
|
||||
if expected_worker_id is not None
|
||||
else current.expected_worker_id
|
||||
),
|
||||
result_digest=result_digest or current.result_digest,
|
||||
updated_at=utc_now(),
|
||||
completed_at=(utc_now() if target in TERMINAL_DISPATCH_STATES else None),
|
||||
)
|
||||
self._records[dispatch_id] = updated
|
||||
return updated
|
||||
|
||||
def list(self, *, tenant_id: str) -> list[DispatchRecord]:
|
||||
with self._lock:
|
||||
return sorted(
|
||||
[item for item in self._records.values() if item.tenant_id == tenant_id],
|
||||
key=lambda item: (item.created_at, item.dispatch_id),
|
||||
)
|
||||
|
||||
|
||||
class SQLiteDispatchRepository:
|
||||
SCHEMA_VERSION = 1
|
||||
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = Path(path).resolve()
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
self._lock = threading.RLock()
|
||||
with self._connect() as connection:
|
||||
connection.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS dispatch_records (
|
||||
dispatch_id TEXT PRIMARY KEY,
|
||||
tenant_id TEXT NOT NULL,
|
||||
task_id TEXT NOT NULL,
|
||||
runtime_execution_id TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
state TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL,
|
||||
UNIQUE(tenant_id, task_id),
|
||||
UNIQUE(tenant_id, runtime_execution_id)
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_dispatch_tenant_state
|
||||
ON dispatch_records(tenant_id, state, updated_at);
|
||||
"""
|
||||
)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(str(self.path), timeout=30.0)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA journal_mode=WAL")
|
||||
connection.execute("PRAGMA synchronous=FULL")
|
||||
return connection
|
||||
|
||||
@staticmethod
|
||||
def _encode(record: DispatchRecord) -> str:
|
||||
return json.dumps(
|
||||
record.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _decode(row: sqlite3.Row) -> DispatchRecord:
|
||||
value = json.loads(row["payload_json"])
|
||||
if not isinstance(value, Mapping):
|
||||
raise RuntimeError("invalid dispatch record")
|
||||
return DispatchRecord.from_dict(value)
|
||||
|
||||
def create(self, record: DispatchRecord) -> DispatchRecord:
|
||||
with self._lock, self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
connection.execute(
|
||||
"INSERT INTO dispatch_records VALUES (?, ?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
record.dispatch_id,
|
||||
record.tenant_id,
|
||||
record.task_id,
|
||||
record.runtime_execution_id,
|
||||
self._encode(record),
|
||||
record.state.value,
|
||||
record.updated_at,
|
||||
),
|
||||
)
|
||||
connection.commit()
|
||||
return record
|
||||
except sqlite3.IntegrityError as exc:
|
||||
connection.rollback()
|
||||
existing = self.get_by_task(record.task_id, tenant_id=record.tenant_id)
|
||||
if existing is not None and existing == record:
|
||||
return existing
|
||||
raise DispatchConflict("task or runtime execution already has a dispatch") from exc
|
||||
|
||||
def get(self, dispatch_id: str, *, tenant_id: str) -> DispatchRecord:
|
||||
with self._lock, self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT payload_json FROM dispatch_records WHERE dispatch_id = ? AND tenant_id = ?",
|
||||
(_required(dispatch_id, "dispatch_id"), _required(tenant_id, "tenant_id")),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise DispatchNotFound("dispatch not found")
|
||||
return self._decode(row)
|
||||
|
||||
def get_by_task(self, task_id: str, *, tenant_id: str) -> DispatchRecord | None:
|
||||
with self._lock, self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT payload_json FROM dispatch_records WHERE task_id = ? AND tenant_id = ?",
|
||||
(_required(task_id, "task_id"), _required(tenant_id, "tenant_id")),
|
||||
).fetchone()
|
||||
return self._decode(row) if row is not None else None
|
||||
|
||||
def get_by_runtime_execution(
|
||||
self, runtime_execution_id: str, *, tenant_id: str
|
||||
) -> DispatchRecord | None:
|
||||
with self._lock, self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT payload_json FROM dispatch_records WHERE runtime_execution_id = ? AND tenant_id = ?",
|
||||
(
|
||||
_required(runtime_execution_id, "runtime_execution_id"),
|
||||
_required(tenant_id, "tenant_id"),
|
||||
),
|
||||
).fetchone()
|
||||
return self._decode(row) if row is not None else None
|
||||
|
||||
def update(
|
||||
self,
|
||||
dispatch_id: str,
|
||||
*,
|
||||
tenant_id: str,
|
||||
state: DispatchState | str | None = None,
|
||||
expected_worker_id: str | None = None,
|
||||
result_digest: str | None = None,
|
||||
) -> DispatchRecord:
|
||||
current = self.get(dispatch_id, tenant_id=tenant_id)
|
||||
target = DispatchState(state) if state is not None else current.state
|
||||
if current.state in TERMINAL_DISPATCH_STATES and target != current.state:
|
||||
raise DispatchConflict("terminal dispatch cannot transition")
|
||||
updated = replace(
|
||||
current,
|
||||
state=target,
|
||||
expected_worker_id=(
|
||||
expected_worker_id if expected_worker_id is not None else current.expected_worker_id
|
||||
),
|
||||
result_digest=result_digest or current.result_digest,
|
||||
updated_at=utc_now(),
|
||||
completed_at=(utc_now() if target in TERMINAL_DISPATCH_STATES else None),
|
||||
)
|
||||
with self._lock, self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
connection.execute(
|
||||
"UPDATE dispatch_records SET payload_json = ?, state = ?, updated_at = ? WHERE dispatch_id = ? AND tenant_id = ?",
|
||||
(
|
||||
self._encode(updated),
|
||||
updated.state.value,
|
||||
updated.updated_at,
|
||||
updated.dispatch_id,
|
||||
updated.tenant_id,
|
||||
),
|
||||
)
|
||||
connection.commit()
|
||||
return updated
|
||||
|
||||
def list(self, *, tenant_id: str) -> list[DispatchRecord]:
|
||||
with self._lock, self._connect() as connection:
|
||||
rows = connection.execute(
|
||||
"SELECT payload_json FROM dispatch_records WHERE tenant_id = ? ORDER BY updated_at, dispatch_id",
|
||||
(_required(tenant_id, "tenant_id"),),
|
||||
).fetchall()
|
||||
return [self._decode(row) for row in rows]
|
||||
@@ -0,0 +1,323 @@
|
||||
"""AIOS V2 Agent 执行证据。
|
||||
|
||||
Evidence 按租户隔离并使用原子 JSON 写入。生产模式下,claim、heartbeat
|
||||
和 complete 在落盘前必须通过最小权限 Evidence Grant 授权。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import threading
|
||||
from dataclasses import asdict, dataclass, field, replace
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Protocol
|
||||
|
||||
from .provenance import ProvenanceDenied, digest_payload
|
||||
|
||||
|
||||
class EvidenceAuthorizationWriter(Protocol):
|
||||
def authorize_evidence_write(self, **values: Any) -> Any: ...
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def _required(value: str, label: str) -> str:
|
||||
normalized = str(value or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError(f"{label} is required")
|
||||
return normalized
|
||||
|
||||
|
||||
def _safe(value: Mapping[str, Any] | None) -> dict[str, Any]:
|
||||
return json.loads(json.dumps(dict(value or {}), ensure_ascii=False, default=str))
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecutionEvidence:
|
||||
execution_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
executor: str
|
||||
branch: str
|
||||
status: str = "claimed"
|
||||
progress_completed: int = 0
|
||||
progress_total: int = 1
|
||||
current_step: str = "claim"
|
||||
last_commit: str | None = None
|
||||
test_status: str = "not_run"
|
||||
test_summary: Mapping[str, Any] = field(default_factory=dict)
|
||||
result_summary: Mapping[str, Any] = field(default_factory=dict)
|
||||
claimed_at: str = field(default_factory=utc_now)
|
||||
heartbeat_at: str = field(default_factory=utc_now)
|
||||
completed_at: str | None = None
|
||||
provenance_id: str | None = None
|
||||
run_id: str | None = None
|
||||
last_authorization_id: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in (
|
||||
"execution_id",
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"agent_id",
|
||||
"executor",
|
||||
"branch",
|
||||
"status",
|
||||
"current_step",
|
||||
"claimed_at",
|
||||
"heartbeat_at",
|
||||
):
|
||||
object.__setattr__(self, name, _required(getattr(self, name), name))
|
||||
if self.progress_completed < 0 or self.progress_total < 1:
|
||||
raise ValueError("invalid progress values")
|
||||
if self.progress_completed > self.progress_total:
|
||||
raise ValueError("progress_completed cannot exceed progress_total")
|
||||
object.__setattr__(self, "test_summary", _safe(self.test_summary))
|
||||
object.__setattr__(self, "result_summary", _safe(self.result_summary))
|
||||
for optional in ("provenance_id", "run_id", "last_authorization_id"):
|
||||
value = getattr(self, optional)
|
||||
object.__setattr__(self, optional, str(value).strip() if value else None)
|
||||
|
||||
|
||||
class ExecutionTracker:
|
||||
"""每个租户、每次执行持久保存一份证据记录。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
root: str | Path,
|
||||
*,
|
||||
provenance_writer: EvidenceAuthorizationWriter | None = None,
|
||||
require_provenance: bool = False,
|
||||
) -> None:
|
||||
self.root = Path(root).resolve()
|
||||
self.root.mkdir(parents=True, exist_ok=True)
|
||||
self.provenance_writer = provenance_writer
|
||||
self.require_provenance = bool(require_provenance)
|
||||
if self.require_provenance and self.provenance_writer is None:
|
||||
raise ValueError("production evidence tracking requires a provenance writer")
|
||||
self._lock = threading.RLock()
|
||||
|
||||
@staticmethod
|
||||
def _component(value: str) -> str:
|
||||
normalized = _required(value, "path component")
|
||||
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
|
||||
raise ValueError("invalid evidence path component")
|
||||
return normalized
|
||||
|
||||
def _path(self, tenant_id: str, execution_id: str) -> Path:
|
||||
tenant = self._component(tenant_id)
|
||||
execution = self._component(execution_id)
|
||||
return self.root / tenant / f"{execution}.json"
|
||||
|
||||
def _authorize(
|
||||
self,
|
||||
evidence: ExecutionEvidence,
|
||||
*,
|
||||
operation: str,
|
||||
principal_id: str | None,
|
||||
provenance_id: str | None,
|
||||
run_id: str | None,
|
||||
changes: Mapping[str, Any],
|
||||
) -> str | None:
|
||||
if not self.require_provenance:
|
||||
return None
|
||||
if self.provenance_writer is None:
|
||||
raise RuntimeError("Run Provenance writer is not configured")
|
||||
effective_provenance = provenance_id or evidence.provenance_id
|
||||
effective_run = run_id or evidence.run_id
|
||||
if not effective_provenance or not effective_run or not principal_id:
|
||||
raise RuntimeError(
|
||||
"production evidence write requires provenance_id, run_id and principal_id"
|
||||
)
|
||||
request_digest = digest_payload(
|
||||
{
|
||||
"operation": operation,
|
||||
"execution_id": evidence.execution_id,
|
||||
"tenant_id": evidence.tenant_id,
|
||||
"task_id": evidence.task_id,
|
||||
"agent_id": evidence.agent_id,
|
||||
"executor": evidence.executor,
|
||||
"branch": evidence.branch,
|
||||
"changes": dict(changes),
|
||||
}
|
||||
)
|
||||
try:
|
||||
authorization = self.provenance_writer.authorize_evidence_write(
|
||||
provenance_id=effective_provenance,
|
||||
run_id=effective_run,
|
||||
tenant_id=evidence.tenant_id,
|
||||
task_id=evidence.task_id,
|
||||
agent_id=evidence.agent_id,
|
||||
principal_id=principal_id,
|
||||
request_digest=request_digest,
|
||||
)
|
||||
except ProvenanceDenied as exc:
|
||||
raise RuntimeError(f"Run Provenance denied evidence write: {exc}") from exc
|
||||
return authorization.authorization_id
|
||||
|
||||
def claim(
|
||||
self,
|
||||
evidence: ExecutionEvidence,
|
||||
*,
|
||||
principal_id: str | None = None,
|
||||
provenance_id: str | None = None,
|
||||
run_id: str | None = None,
|
||||
) -> ExecutionEvidence:
|
||||
path = self._path(evidence.tenant_id, evidence.execution_id)
|
||||
with self._lock:
|
||||
if path.exists():
|
||||
current = self._read(path)
|
||||
if current.task_id != evidence.task_id or current.agent_id != evidence.agent_id:
|
||||
raise RuntimeError("execution_id already belongs to another task")
|
||||
if self.require_provenance and (
|
||||
current.provenance_id != (provenance_id or evidence.provenance_id)
|
||||
or current.run_id != (run_id or evidence.run_id)
|
||||
):
|
||||
raise RuntimeError(
|
||||
"execution_id already belongs to another provenance context"
|
||||
)
|
||||
return current
|
||||
effective_provenance = provenance_id or evidence.provenance_id
|
||||
effective_run = run_id or evidence.run_id
|
||||
authorization_id = self._authorize(
|
||||
evidence,
|
||||
operation="claim",
|
||||
principal_id=principal_id,
|
||||
provenance_id=effective_provenance,
|
||||
run_id=effective_run,
|
||||
changes={"status": evidence.status, "current_step": evidence.current_step},
|
||||
)
|
||||
persisted = replace(
|
||||
evidence,
|
||||
provenance_id=effective_provenance,
|
||||
run_id=effective_run,
|
||||
last_authorization_id=authorization_id,
|
||||
)
|
||||
self._write(path, persisted)
|
||||
return persisted
|
||||
|
||||
def heartbeat(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
execution_id: str,
|
||||
status: str | None = None,
|
||||
current_step: str | None = None,
|
||||
progress_completed: int | None = None,
|
||||
progress_total: int | None = None,
|
||||
last_commit: str | None = None,
|
||||
principal_id: str | None = None,
|
||||
provenance_id: str | None = None,
|
||||
run_id: str | None = None,
|
||||
) -> ExecutionEvidence:
|
||||
path = self._path(tenant_id, execution_id)
|
||||
with self._lock:
|
||||
current = self._read(path)
|
||||
changes = {
|
||||
"status": status or current.status,
|
||||
"current_step": current_step or current.current_step,
|
||||
"progress_completed": (
|
||||
progress_completed
|
||||
if progress_completed is not None
|
||||
else current.progress_completed
|
||||
),
|
||||
"progress_total": (
|
||||
progress_total if progress_total is not None else current.progress_total
|
||||
),
|
||||
"last_commit": last_commit or current.last_commit,
|
||||
}
|
||||
authorization_id = self._authorize(
|
||||
current,
|
||||
operation="heartbeat",
|
||||
principal_id=principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
changes=changes,
|
||||
)
|
||||
updated = replace(
|
||||
current,
|
||||
**changes,
|
||||
last_authorization_id=authorization_id or current.last_authorization_id,
|
||||
heartbeat_at=utc_now(),
|
||||
)
|
||||
self._write(path, updated)
|
||||
return updated
|
||||
|
||||
def complete(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
execution_id: str,
|
||||
status: str,
|
||||
test_status: str,
|
||||
test_summary: Mapping[str, Any] | None = None,
|
||||
result_summary: Mapping[str, Any] | None = None,
|
||||
last_commit: str | None = None,
|
||||
principal_id: str | None = None,
|
||||
provenance_id: str | None = None,
|
||||
run_id: str | None = None,
|
||||
) -> ExecutionEvidence:
|
||||
path = self._path(tenant_id, execution_id)
|
||||
with self._lock:
|
||||
current = self._read(path)
|
||||
changes = {
|
||||
"status": _required(status, "status"),
|
||||
"current_step": "complete",
|
||||
"progress_completed": current.progress_total,
|
||||
"last_commit": last_commit or current.last_commit,
|
||||
"test_status": _required(test_status, "test_status"),
|
||||
"test_summary": _safe(test_summary),
|
||||
"result_summary": _safe(result_summary),
|
||||
}
|
||||
authorization_id = self._authorize(
|
||||
current,
|
||||
operation="complete",
|
||||
principal_id=principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
changes=changes,
|
||||
)
|
||||
updated = replace(
|
||||
current,
|
||||
**changes,
|
||||
last_authorization_id=authorization_id or current.last_authorization_id,
|
||||
heartbeat_at=utc_now(),
|
||||
completed_at=utc_now(),
|
||||
)
|
||||
self._write(path, updated)
|
||||
return updated
|
||||
|
||||
def get(self, *, tenant_id: str, execution_id: str) -> ExecutionEvidence:
|
||||
return self._read(self._path(tenant_id, execution_id))
|
||||
|
||||
def list(self, *, tenant_id: str) -> list[ExecutionEvidence]:
|
||||
tenant_dir = self.root / self._component(tenant_id)
|
||||
if not tenant_dir.exists():
|
||||
return []
|
||||
records = [self._read(path) for path in tenant_dir.glob("*.json")]
|
||||
return sorted(records, key=lambda item: (item.heartbeat_at, item.execution_id), reverse=True)
|
||||
|
||||
@staticmethod
|
||||
def _read(path: Path) -> ExecutionEvidence:
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except FileNotFoundError as exc:
|
||||
raise KeyError("execution evidence not found") from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise RuntimeError("invalid execution evidence file")
|
||||
return ExecutionEvidence(**dict(value))
|
||||
|
||||
@staticmethod
|
||||
def _write(path: Path, evidence: ExecutionEvidence) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
temporary = path.with_suffix(f".tmp-{os.getpid()}")
|
||||
temporary.write_text(
|
||||
json.dumps(asdict(evidence), ensure_ascii=False, sort_keys=True, indent=2) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
os.chmod(temporary, 0o640)
|
||||
os.replace(temporary, path)
|
||||
@@ -0,0 +1,353 @@
|
||||
"""HTTP/JSON gateway for the AIOS V2 control plane.
|
||||
|
||||
The public gateway owns user-facing control operations only. Runtime lifecycle
|
||||
transitions are deliberately absent: external callers cannot directly move a
|
||||
task to RUNNING, COMPLETED or FAILED. Those transitions are available only
|
||||
through the provenance-protected orchestrator and internal reconciliation API.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import urllib.parse
|
||||
from enum import Enum
|
||||
from http import HTTPStatus
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from typing import Any, Mapping
|
||||
|
||||
from aios_hermes import HermesConflict, HermesNotFound
|
||||
|
||||
from .control_plane import (
|
||||
ControlPlaneError,
|
||||
ControlPlaneService,
|
||||
IdempotencyConflict,
|
||||
InvalidTransition,
|
||||
NotFound,
|
||||
PolicyDenied,
|
||||
RequestContext,
|
||||
RevisionConflict,
|
||||
TaskState,
|
||||
TenantIsolationError,
|
||||
Unauthorized,
|
||||
)
|
||||
from .dispatch_store import DispatchConflict, DispatchNotFound
|
||||
from .orchestrator import OrchestrationError
|
||||
from .provenance import ProvenanceDenied, ProvenanceReplay
|
||||
|
||||
TENANT_HEADER = "X-AIOS-Tenant-ID"
|
||||
PRINCIPAL_HEADER = "X-AIOS-Principal-ID"
|
||||
ROLES_HEADER = "X-AIOS-Roles"
|
||||
TRACE_HEADER = "X-AIOS-Trace-ID"
|
||||
SESSION_HEADER = "X-AIOS-Session-ID"
|
||||
POLICY_HEADER = "X-AIOS-Policy-Version"
|
||||
AUTHENTICATED_HEADER = "X-AIOS-Authenticated"
|
||||
|
||||
_RESOURCE_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{0,191}$")
|
||||
|
||||
|
||||
def _json_value(value: Any) -> Any:
|
||||
if dataclasses.is_dataclass(value):
|
||||
return {
|
||||
field.name: _json_value(getattr(value, field.name))
|
||||
for field in dataclasses.fields(value)
|
||||
}
|
||||
if isinstance(value, Enum):
|
||||
return value.value
|
||||
if isinstance(value, Mapping):
|
||||
return {str(key): _json_value(item) for key, item in value.items()}
|
||||
if isinstance(value, (list, tuple, set, frozenset)):
|
||||
return [_json_value(item) for item in value]
|
||||
return value
|
||||
|
||||
|
||||
def _require_mapping(value: Any, *, label: str = "JSON body") -> Mapping[str, Any]:
|
||||
if not isinstance(value, Mapping):
|
||||
raise ValueError(f"{label} must be an object")
|
||||
return value
|
||||
|
||||
|
||||
def _require_resource_id(value: Any, *, label: str) -> str:
|
||||
normalized = str(value or "").strip()
|
||||
if not _RESOURCE_ID_RE.fullmatch(normalized):
|
||||
raise ValueError(f"invalid {label}")
|
||||
return normalized
|
||||
|
||||
|
||||
class GatewayApplication:
|
||||
"""Pure user-facing request router that can be tested without a socket."""
|
||||
|
||||
def __init__(self, service: ControlPlaneService | None = None) -> None:
|
||||
self.service = service or ControlPlaneService()
|
||||
|
||||
@staticmethod
|
||||
def context_from_headers(headers: Mapping[str, str]) -> RequestContext:
|
||||
normalized_headers = {
|
||||
str(key).strip().lower(): value for key, value in headers.items()
|
||||
}
|
||||
|
||||
def header(name: str, default: str = "") -> str:
|
||||
return str(normalized_headers.get(name.lower(), default))
|
||||
|
||||
authenticated = header(AUTHENTICATED_HEADER).strip().lower()
|
||||
if authenticated not in {"1", "true", "yes"}:
|
||||
raise Unauthorized("trusted authentication assertion is required")
|
||||
roles = [
|
||||
role.strip()
|
||||
for role in header(ROLES_HEADER).split(",")
|
||||
if role.strip()
|
||||
]
|
||||
return RequestContext.create(
|
||||
tenant_id=header(TENANT_HEADER),
|
||||
principal_id=header(PRINCIPAL_HEADER),
|
||||
trace_id=header(TRACE_HEADER).strip() or None,
|
||||
session_id=header(SESSION_HEADER).strip() or None,
|
||||
policy_version=header(POLICY_HEADER, "v1").strip() or "v1",
|
||||
roles=roles,
|
||||
)
|
||||
|
||||
def handle(
|
||||
self,
|
||||
method: str,
|
||||
raw_path: str,
|
||||
headers: Mapping[str, str],
|
||||
body: Any = None,
|
||||
) -> tuple[int, Mapping[str, Any]]:
|
||||
parsed = urllib.parse.urlparse(raw_path)
|
||||
path = parsed.path.rstrip("/") or "/"
|
||||
query = urllib.parse.parse_qs(parsed.query, keep_blank_values=False)
|
||||
method = method.upper()
|
||||
|
||||
if method == "GET" and path in {"/healthz", "/api/v2/health"}:
|
||||
return HTTPStatus.OK, {
|
||||
"service": "aios-v2-control-plane",
|
||||
"status": "ok",
|
||||
"store": type(self.service.store).__name__,
|
||||
}
|
||||
|
||||
context = self.context_from_headers(headers)
|
||||
payload = _require_mapping(body or {})
|
||||
|
||||
if method == "POST" and path == "/api/v2/tenants":
|
||||
tenant = self.service.register_tenant(
|
||||
context,
|
||||
tenant_id=_require_resource_id(payload.get("tenant_id"), label="tenant_id"),
|
||||
display_name=str(payload.get("display_name", "")),
|
||||
metadata=_require_mapping(payload.get("metadata", {}), label="metadata"),
|
||||
)
|
||||
return HTTPStatus.CREATED, {"tenant": _json_value(tenant)}
|
||||
|
||||
if method == "GET" and path == "/api/v2/tenants/current":
|
||||
return HTTPStatus.OK, {"tenant": _json_value(self.service.get_tenant(context))}
|
||||
|
||||
if method == "POST" and path == "/api/v2/agents":
|
||||
agent = self.service.register_agent(
|
||||
context,
|
||||
agent_id=_require_resource_id(payload.get("agent_id"), label="agent_id"),
|
||||
display_name=str(payload.get("display_name", "")),
|
||||
runtime=str(payload.get("runtime", "")),
|
||||
capabilities=payload.get("capabilities", ()),
|
||||
metadata=_require_mapping(payload.get("metadata", {}), label="metadata"),
|
||||
)
|
||||
return HTTPStatus.CREATED, {"agent": _json_value(agent)}
|
||||
|
||||
if method == "GET" and path == "/api/v2/agents":
|
||||
return HTTPStatus.OK, {"agents": _json_value(self.service.list_agents(context))}
|
||||
|
||||
agent_match = re.fullmatch(r"/api/v2/agents/([^/]+)", path)
|
||||
if method == "GET" and agent_match:
|
||||
agent_id = _require_resource_id(
|
||||
urllib.parse.unquote(agent_match.group(1)), label="agent_id"
|
||||
)
|
||||
return HTTPStatus.OK, {
|
||||
"agent": _json_value(self.service.get_agent(context, agent_id))
|
||||
}
|
||||
|
||||
if method == "POST" and path == "/api/v2/tasks":
|
||||
task = self.service.create_task(
|
||||
context,
|
||||
agent_id=_require_resource_id(payload.get("agent_id"), label="agent_id"),
|
||||
action=str(payload.get("action", "")).strip(),
|
||||
payload=_require_mapping(payload.get("payload", {}), label="payload"),
|
||||
idempotency_key=(
|
||||
str(payload["idempotency_key"]).strip()
|
||||
if payload.get("idempotency_key") is not None
|
||||
else None
|
||||
),
|
||||
)
|
||||
return HTTPStatus.CREATED, {"task": _json_value(task)}
|
||||
|
||||
if method == "GET" and path == "/api/v2/tasks":
|
||||
tasks = self.service.list_tasks(context, states=query.get("state"))
|
||||
return HTTPStatus.OK, {"tasks": _json_value(tasks)}
|
||||
|
||||
task_match = re.fullmatch(r"/api/v2/tasks/([^/]+)", path)
|
||||
if method == "GET" and task_match:
|
||||
task_id = _require_resource_id(
|
||||
urllib.parse.unquote(task_match.group(1)), label="task_id"
|
||||
)
|
||||
return HTTPStatus.OK, {
|
||||
"task": _json_value(self.service.get_task(context, task_id))
|
||||
}
|
||||
|
||||
bypass_match = re.fullmatch(
|
||||
r"/api/v2/tasks/([^/]+)/(start|complete|fail)", path
|
||||
)
|
||||
if method == "POST" and bypass_match:
|
||||
return HTTPStatus.FORBIDDEN, {
|
||||
"error": "RuntimeLifecycleBypassDenied",
|
||||
"message": (
|
||||
"RUNNING, COMPLETED and FAILED transitions are internal; "
|
||||
"use the provenance-protected dispatch/reconcile flow"
|
||||
),
|
||||
}
|
||||
|
||||
transition_match = re.fullmatch(
|
||||
r"/api/v2/tasks/([^/]+)/(approve|cancel)", path
|
||||
)
|
||||
if method == "POST" and transition_match:
|
||||
task_id = _require_resource_id(
|
||||
urllib.parse.unquote(transition_match.group(1)), label="task_id"
|
||||
)
|
||||
target = (
|
||||
TaskState.APPROVED
|
||||
if transition_match.group(2) == "approve"
|
||||
else TaskState.CANCELLED
|
||||
)
|
||||
expected_revision = payload.get("expected_revision")
|
||||
task = self.service.transition_task(
|
||||
context,
|
||||
task_id=task_id,
|
||||
target_state=target,
|
||||
expected_revision=(
|
||||
int(expected_revision) if expected_revision is not None else None
|
||||
),
|
||||
)
|
||||
return HTTPStatus.OK, {"task": _json_value(task)}
|
||||
|
||||
if method == "GET" and path == "/api/v2/audit":
|
||||
resource_id = query.get("resource_id", [None])[0]
|
||||
events = self.service.list_audit_events(
|
||||
context,
|
||||
resource_id=(
|
||||
_require_resource_id(resource_id, label="resource_id")
|
||||
if resource_id
|
||||
else None
|
||||
),
|
||||
)
|
||||
return HTTPStatus.OK, {"events": _json_value(events)}
|
||||
|
||||
return HTTPStatus.NOT_FOUND, {
|
||||
"error": "not_found",
|
||||
"message": "route not found",
|
||||
}
|
||||
|
||||
|
||||
_ERROR_STATUS: tuple[tuple[type[BaseException], HTTPStatus], ...] = (
|
||||
(Unauthorized, HTTPStatus.UNAUTHORIZED),
|
||||
(PolicyDenied, HTTPStatus.FORBIDDEN),
|
||||
(ProvenanceDenied, HTTPStatus.FORBIDDEN),
|
||||
(TenantIsolationError, HTTPStatus.NOT_FOUND),
|
||||
(NotFound, HTTPStatus.NOT_FOUND),
|
||||
(DispatchNotFound, HTTPStatus.NOT_FOUND),
|
||||
(HermesNotFound, HTTPStatus.NOT_FOUND),
|
||||
(ProvenanceReplay, HTTPStatus.CONFLICT),
|
||||
(IdempotencyConflict, HTTPStatus.CONFLICT),
|
||||
(RevisionConflict, HTTPStatus.CONFLICT),
|
||||
(InvalidTransition, HTTPStatus.CONFLICT),
|
||||
(DispatchConflict, HTTPStatus.CONFLICT),
|
||||
(HermesConflict, HTTPStatus.CONFLICT),
|
||||
(OrchestrationError, HTTPStatus.CONFLICT),
|
||||
(ValueError, HTTPStatus.BAD_REQUEST),
|
||||
(ControlPlaneError, HTTPStatus.BAD_REQUEST),
|
||||
)
|
||||
|
||||
|
||||
def error_response(exc: BaseException) -> tuple[int, Mapping[str, Any]]:
|
||||
for error_type, status in _ERROR_STATUS:
|
||||
if isinstance(exc, error_type):
|
||||
return status, {"error": error_type.__name__, "message": str(exc)}
|
||||
return HTTPStatus.INTERNAL_SERVER_ERROR, {
|
||||
"error": "InternalServerError",
|
||||
"message": "internal server error",
|
||||
}
|
||||
|
||||
|
||||
class GatewayRequestHandler(BaseHTTPRequestHandler):
|
||||
server_version = "AIOSV2Gateway/1.0"
|
||||
max_body_bytes = 1_048_576
|
||||
|
||||
@property
|
||||
def application(self) -> GatewayApplication:
|
||||
return self.server.application # type: ignore[attr-defined]
|
||||
|
||||
def _read_body(self) -> Any:
|
||||
length = int(self.headers.get("Content-Length", "0") or "0")
|
||||
if length < 0 or length > self.max_body_bytes:
|
||||
raise ValueError("request body is too large")
|
||||
if length == 0:
|
||||
return {}
|
||||
content_type = self.headers.get("Content-Type", "").split(";", 1)[0].strip()
|
||||
if content_type != "application/json":
|
||||
raise ValueError("Content-Type must be application/json")
|
||||
return json.loads(self.rfile.read(length).decode("utf-8"))
|
||||
|
||||
def _send_json(self, status: int, payload: Mapping[str, Any]) -> None:
|
||||
encoded = json.dumps(
|
||||
_json_value(payload), ensure_ascii=False, separators=(",", ":")
|
||||
).encode("utf-8")
|
||||
self.send_response(int(status))
|
||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(encoded)))
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("X-Content-Type-Options", "nosniff")
|
||||
self.end_headers()
|
||||
self.wfile.write(encoded)
|
||||
|
||||
def _dispatch(self, method: str) -> None:
|
||||
try:
|
||||
body = self._read_body() if method in {"POST", "PUT", "PATCH"} else {}
|
||||
status, payload = self.application.handle(
|
||||
method,
|
||||
self.path,
|
||||
{key: value for key, value in self.headers.items()},
|
||||
body,
|
||||
)
|
||||
except Exception as exc:
|
||||
status, payload = error_response(exc)
|
||||
self._send_json(status, payload)
|
||||
|
||||
def do_GET(self) -> None: # noqa: N802
|
||||
self._dispatch("GET")
|
||||
|
||||
def do_POST(self) -> None: # noqa: N802
|
||||
self._dispatch("POST")
|
||||
|
||||
def log_message(self, format: str, *args: Any) -> None:
|
||||
super().log_message(format, *args)
|
||||
|
||||
|
||||
class GatewayHTTPServer(ThreadingHTTPServer):
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
server_address: tuple[str, int],
|
||||
application: GatewayApplication,
|
||||
) -> None:
|
||||
self.application = application
|
||||
super().__init__(server_address, GatewayRequestHandler)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
host = os.getenv("AIOS_V2_GATEWAY_HOST", "127.0.0.1")
|
||||
port = int(os.getenv("AIOS_V2_GATEWAY_PORT", "18920"))
|
||||
server = GatewayHTTPServer((host, port), GatewayApplication())
|
||||
print(f"AIOS V2 control-plane gateway listening on {host}:{port}")
|
||||
server.serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,123 @@
|
||||
"""Sanitized GitOps runtime status for the AIOS Web control plane."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
from dataclasses import dataclass, asdict
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GitOpsStatus:
|
||||
available: bool
|
||||
service_status: str
|
||||
workspace_mode: str
|
||||
workspace_branch: str | None
|
||||
workspace_ref: str | None
|
||||
workspace_dirty: bool | None
|
||||
candidate_branch: str
|
||||
release_channel: str
|
||||
release_version: str
|
||||
sync_status: str
|
||||
details: Mapping[str, Any]
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
def _run_git(worktree: Path, *args: str) -> tuple[int, str, str]:
|
||||
process = subprocess.run(
|
||||
["git", "-C", str(worktree), *args],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
timeout=5,
|
||||
)
|
||||
return process.returncode, process.stdout.strip(), process.stderr.strip()
|
||||
|
||||
|
||||
def collect_gitops_status() -> GitOpsStatus:
|
||||
"""Return only non-sensitive Git/workspace metadata.
|
||||
|
||||
Remote URLs, environment values, credentials, filesystem contents and
|
||||
command stderr are deliberately excluded from the Web response.
|
||||
"""
|
||||
|
||||
candidate_branch = os.getenv(
|
||||
"AIOS_CANDIDATE_BRANCH",
|
||||
"integration/aios-v2r1-cto-production-candidate-20260720",
|
||||
)
|
||||
release_channel = os.getenv("AIOS_RELEASE_CHANNEL", "candidate")
|
||||
release_version = os.getenv("AIOS_RELEASE_VERSION", "V2R1C0-candidate")
|
||||
sync_status = os.getenv("AIOS_GITOPS_SYNC_STATUS", "unknown")
|
||||
worktree = Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_CONTROLLER_WORKTREE",
|
||||
"/data/aios-gitops/worktrees/controller",
|
||||
)
|
||||
)
|
||||
|
||||
if not worktree.is_dir():
|
||||
return GitOpsStatus(
|
||||
available=False,
|
||||
service_status="unknown",
|
||||
workspace_mode="unavailable",
|
||||
workspace_branch=None,
|
||||
workspace_ref=None,
|
||||
workspace_dirty=None,
|
||||
candidate_branch=candidate_branch,
|
||||
release_channel=release_channel,
|
||||
release_version=release_version,
|
||||
sync_status=sync_status,
|
||||
details={"reason": "controller_worktree_unavailable"},
|
||||
)
|
||||
|
||||
inside_code, inside, _ = _run_git(worktree, "rev-parse", "--is-inside-work-tree")
|
||||
if inside_code != 0 or inside != "true":
|
||||
return GitOpsStatus(
|
||||
available=False,
|
||||
service_status="unknown",
|
||||
workspace_mode="invalid",
|
||||
workspace_branch=None,
|
||||
workspace_ref=None,
|
||||
workspace_dirty=None,
|
||||
candidate_branch=candidate_branch,
|
||||
release_channel=release_channel,
|
||||
release_version=release_version,
|
||||
sync_status=sync_status,
|
||||
details={"reason": "controller_worktree_invalid"},
|
||||
)
|
||||
|
||||
branch_code, branch, _ = _run_git(worktree, "branch", "--show-current")
|
||||
ref_code, ref_value, _ = _run_git(worktree, "rev-parse", "HEAD")
|
||||
dirty_code, dirty_value, _ = _run_git(worktree, "status", "--porcelain=v1")
|
||||
|
||||
service_status = "unknown"
|
||||
try:
|
||||
process = subprocess.run(
|
||||
["systemctl", "is-active", "aios-gitops-model-api"],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
timeout=3,
|
||||
)
|
||||
service_status = process.stdout.strip() or "inactive"
|
||||
except (FileNotFoundError, subprocess.TimeoutExpired):
|
||||
service_status = "unavailable"
|
||||
|
||||
branch_value = branch if branch_code == 0 and branch else None
|
||||
return GitOpsStatus(
|
||||
available=True,
|
||||
service_status=service_status,
|
||||
workspace_mode="branch" if branch_value else "detached",
|
||||
workspace_branch=branch_value,
|
||||
workspace_ref=ref_value if ref_code == 0 else None,
|
||||
workspace_dirty=bool(dirty_value) if dirty_code == 0 else None,
|
||||
candidate_branch=candidate_branch,
|
||||
release_channel=release_channel,
|
||||
release_version=release_version,
|
||||
sync_status=sync_status,
|
||||
details={
|
||||
"controller_clean": dirty_code == 0 and not dirty_value,
|
||||
"controller_detached": branch_code == 0 and not branch,
|
||||
},
|
||||
)
|
||||
@@ -0,0 +1,599 @@
|
||||
"""AIOS V2 execution orchestrator.
|
||||
|
||||
The orchestrator is the only component allowed to translate an approved AIOS
|
||||
Task into an OpenClaw command or Hermes job. Every dispatch is persisted before
|
||||
Runtime side effects. Runtime results must bind to the exact dispatch,
|
||||
command/job, tenant, task, trace, principal and provenance context.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Mapping, Protocol
|
||||
|
||||
from aios_hermes import HermesAdapter, HermesJob, HermesJobState, HermesResult
|
||||
from aios_openclaw import (
|
||||
CommandState,
|
||||
OpenClawAdapter,
|
||||
OpenClawCommand,
|
||||
OpenClawResult,
|
||||
sign_command,
|
||||
)
|
||||
|
||||
from .control_plane import (
|
||||
AgentRecord,
|
||||
ControlPlaneService,
|
||||
RequestContext,
|
||||
TaskRecord,
|
||||
TaskState,
|
||||
)
|
||||
from .dispatch_store import (
|
||||
DispatchConflict,
|
||||
DispatchRecord,
|
||||
DispatchRepository,
|
||||
DispatchState,
|
||||
InMemoryDispatchRepository,
|
||||
TERMINAL_DISPATCH_STATES,
|
||||
)
|
||||
from .provenance import ProvenanceDenied, digest_payload
|
||||
|
||||
|
||||
class RuntimeAuthorizationWriter(Protocol):
|
||||
def authorize_runtime_execute(self, **values: Any) -> Any: ...
|
||||
|
||||
|
||||
class OrchestrationError(RuntimeError):
|
||||
"""AIOS failed to dispatch or reconcile a runtime execution."""
|
||||
|
||||
|
||||
class ExecutionOrchestrator:
|
||||
"""Dispatch approved AIOS tasks and strictly reconcile Runtime results."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
control_plane: ControlPlaneService,
|
||||
*,
|
||||
openclaw: OpenClawAdapter | None = None,
|
||||
hermes: HermesAdapter | None = None,
|
||||
openclaw_signing_material_resolver=None,
|
||||
openclaw_key_id: str = "default",
|
||||
default_cell_id: str = "default",
|
||||
default_profile_id: str = "default",
|
||||
provenance_writer: RuntimeAuthorizationWriter | None = None,
|
||||
require_provenance: bool = False,
|
||||
dispatch_repository: DispatchRepository | None = None,
|
||||
) -> None:
|
||||
self.control_plane = control_plane
|
||||
self.openclaw = openclaw
|
||||
self.hermes = hermes
|
||||
self.openclaw_signing_material_resolver = openclaw_signing_material_resolver
|
||||
self.openclaw_key_id = str(openclaw_key_id or "").strip() or "default"
|
||||
self.default_cell_id = default_cell_id
|
||||
self.default_profile_id = default_profile_id
|
||||
self.provenance_writer = provenance_writer
|
||||
self.require_provenance = bool(require_provenance)
|
||||
self.dispatch_repository = dispatch_repository or InMemoryDispatchRepository()
|
||||
if self.require_provenance and self.provenance_writer is None:
|
||||
raise ValueError("production orchestration requires a provenance writer")
|
||||
|
||||
@staticmethod
|
||||
def _record_provenance(value: str | None, *, required: bool, label: str) -> str:
|
||||
normalized = str(value or "").strip()
|
||||
if required and not normalized:
|
||||
raise OrchestrationError(f"production dispatch requires {label}")
|
||||
return normalized or f"{label}-not-required"
|
||||
|
||||
def _authorize_dispatch(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
task: TaskRecord,
|
||||
agent: AgentRecord,
|
||||
provenance_id: str | None,
|
||||
run_id: str | None,
|
||||
timeout_seconds: float | None,
|
||||
) -> str:
|
||||
if not self.require_provenance:
|
||||
return "authorization-not-required"
|
||||
if self.provenance_writer is None:
|
||||
raise OrchestrationError("Run Provenance writer is not configured")
|
||||
if not provenance_id or not run_id:
|
||||
raise OrchestrationError(
|
||||
"production dispatch requires provenance_id and run_id"
|
||||
)
|
||||
request_digest = digest_payload(
|
||||
{
|
||||
"operation": "dispatch",
|
||||
"tenant_id": task.tenant_id,
|
||||
"task_id": task.task_id,
|
||||
"agent_id": agent.agent_id,
|
||||
"principal_id": context.principal_id,
|
||||
"runtime": agent.runtime.strip().lower(),
|
||||
"action": task.action,
|
||||
"payload": task.payload,
|
||||
"trace_id": context.trace_id,
|
||||
"timeout_seconds": timeout_seconds,
|
||||
"task_revision": task.revision,
|
||||
}
|
||||
)
|
||||
try:
|
||||
authorization = self.provenance_writer.authorize_runtime_execute(
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
tenant_id=task.tenant_id,
|
||||
task_id=task.task_id,
|
||||
agent_id=agent.agent_id,
|
||||
principal_id=context.principal_id,
|
||||
request_digest=request_digest,
|
||||
)
|
||||
return authorization.authorization_id
|
||||
except ProvenanceDenied as exc:
|
||||
raise OrchestrationError(f"Run Provenance denied dispatch: {exc}") from exc
|
||||
|
||||
def dispatch(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
task_id: str,
|
||||
timeout_seconds: float | None = None,
|
||||
provenance_id: str | None = None,
|
||||
run_id: str | None = None,
|
||||
) -> DispatchRecord:
|
||||
task = self.control_plane.get_task(context, task_id)
|
||||
agent = self.control_plane.get_agent(context, task.agent_id)
|
||||
persisted_provenance = self._record_provenance(
|
||||
provenance_id, required=self.require_provenance, label="provenance_id"
|
||||
)
|
||||
persisted_run = self._record_provenance(
|
||||
run_id, required=self.require_provenance, label="run_id"
|
||||
)
|
||||
|
||||
existing = self.dispatch_repository.get_by_task(
|
||||
task.task_id, tenant_id=task.tenant_id
|
||||
)
|
||||
if existing is not None:
|
||||
if (
|
||||
existing.provenance_id != persisted_provenance
|
||||
or existing.run_id != persisted_run
|
||||
or existing.principal_id != context.principal_id
|
||||
):
|
||||
raise OrchestrationError(
|
||||
"existing dispatch belongs to another provenance or principal context"
|
||||
)
|
||||
return existing
|
||||
|
||||
if task.state != TaskState.APPROVED:
|
||||
raise OrchestrationError("only APPROVED tasks may be dispatched")
|
||||
|
||||
authorization_id = self._authorize_dispatch(
|
||||
context,
|
||||
task=task,
|
||||
agent=agent,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
timeout_seconds=timeout_seconds,
|
||||
)
|
||||
runtime = agent.runtime.strip().lower()
|
||||
prepared: DispatchRecord | None = None
|
||||
|
||||
try:
|
||||
if runtime == "openclaw":
|
||||
command = self._create_openclaw_command(context, task)
|
||||
prepared = self.dispatch_repository.create(
|
||||
DispatchRecord.create(
|
||||
tenant_id=task.tenant_id,
|
||||
task_id=task.task_id,
|
||||
agent_id=agent.agent_id,
|
||||
principal_id=context.principal_id,
|
||||
runtime="openclaw",
|
||||
runtime_execution_id=command.command_id,
|
||||
trace_id=context.trace_id,
|
||||
provenance_id=persisted_provenance,
|
||||
run_id=persisted_run,
|
||||
authorization_id=authorization_id,
|
||||
)
|
||||
)
|
||||
self.control_plane.transition_task(
|
||||
context,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.RUNNING,
|
||||
expected_revision=task.revision,
|
||||
)
|
||||
self.dispatch_repository.update(
|
||||
prepared.dispatch_id,
|
||||
tenant_id=prepared.tenant_id,
|
||||
state=DispatchState.RUNNING,
|
||||
)
|
||||
if self.openclaw is None:
|
||||
raise OrchestrationError("OpenClaw runtime is not configured")
|
||||
result = self.openclaw.execute(
|
||||
command, timeout_seconds=timeout_seconds
|
||||
)
|
||||
self.reconcile_openclaw(
|
||||
context,
|
||||
result,
|
||||
dispatch_id=prepared.dispatch_id,
|
||||
provenance_id=persisted_provenance,
|
||||
run_id=persisted_run,
|
||||
)
|
||||
return self.dispatch_repository.get(
|
||||
prepared.dispatch_id, tenant_id=prepared.tenant_id
|
||||
)
|
||||
|
||||
if runtime == "hermes":
|
||||
if self.hermes is None:
|
||||
raise OrchestrationError("Hermes runtime is not configured")
|
||||
job = self._create_hermes_job(context, agent, task)
|
||||
prepared = self.dispatch_repository.create(
|
||||
DispatchRecord.create(
|
||||
tenant_id=task.tenant_id,
|
||||
task_id=task.task_id,
|
||||
agent_id=agent.agent_id,
|
||||
principal_id=context.principal_id,
|
||||
runtime="hermes",
|
||||
runtime_execution_id=job.job_id,
|
||||
trace_id=context.trace_id,
|
||||
provenance_id=persisted_provenance,
|
||||
run_id=persisted_run,
|
||||
authorization_id=authorization_id,
|
||||
)
|
||||
)
|
||||
self.control_plane.transition_task(
|
||||
context,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.RUNNING,
|
||||
expected_revision=task.revision,
|
||||
)
|
||||
queued = self.hermes.enqueue(job)
|
||||
return self.dispatch_repository.update(
|
||||
prepared.dispatch_id,
|
||||
tenant_id=prepared.tenant_id,
|
||||
state=DispatchState.QUEUED,
|
||||
result_digest=digest_payload(
|
||||
{
|
||||
"queued_job_id": queued.job_id,
|
||||
"state": queued.state.value,
|
||||
"revision": queued.revision,
|
||||
}
|
||||
),
|
||||
)
|
||||
|
||||
raise OrchestrationError(f"unsupported runtime: {agent.runtime}")
|
||||
except Exception as exc:
|
||||
if prepared is not None:
|
||||
try:
|
||||
self.dispatch_repository.update(
|
||||
prepared.dispatch_id,
|
||||
tenant_id=prepared.tenant_id,
|
||||
state=DispatchState.FAILED,
|
||||
result_digest=digest_payload(
|
||||
{
|
||||
"code": "dispatch_failed",
|
||||
"error_type": type(exc).__name__,
|
||||
"message": str(exc),
|
||||
}
|
||||
),
|
||||
)
|
||||
except Exception:
|
||||
pass
|
||||
current = self.control_plane.get_task(context, task.task_id)
|
||||
if current.state == TaskState.RUNNING:
|
||||
self.control_plane.transition_task(
|
||||
context,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.FAILED,
|
||||
expected_revision=current.revision,
|
||||
error={"code": "dispatch_failed", "message": str(exc)},
|
||||
)
|
||||
raise
|
||||
|
||||
def _create_openclaw_command(
|
||||
self,
|
||||
context: RequestContext,
|
||||
task: TaskRecord,
|
||||
) -> OpenClawCommand:
|
||||
if self.openclaw_signing_material_resolver is None:
|
||||
raise OrchestrationError("OpenClaw signing material is not configured")
|
||||
key_material = self.openclaw_signing_material_resolver(
|
||||
task.tenant_id,
|
||||
self.openclaw_key_id,
|
||||
)
|
||||
command = OpenClawCommand.create(
|
||||
tenant_id=task.tenant_id,
|
||||
task_id=task.task_id,
|
||||
trace_id=context.trace_id,
|
||||
action=task.action,
|
||||
payload=task.payload,
|
||||
idempotency_key=task.idempotency_key or task.task_id,
|
||||
key_id=self.openclaw_key_id,
|
||||
)
|
||||
return sign_command(command, key_material)
|
||||
|
||||
def _create_hermes_job(
|
||||
self,
|
||||
context: RequestContext,
|
||||
agent: AgentRecord,
|
||||
task: TaskRecord,
|
||||
) -> HermesJob:
|
||||
metadata = dict(agent.metadata)
|
||||
return HermesJob.create(
|
||||
tenant_id=task.tenant_id,
|
||||
cell_id=str(metadata.get("cell_id") or self.default_cell_id),
|
||||
profile_id=str(metadata.get("profile_id") or self.default_profile_id),
|
||||
task_id=task.task_id,
|
||||
trace_id=context.trace_id,
|
||||
action=task.action,
|
||||
payload=task.payload,
|
||||
idempotency_key=task.idempotency_key or task.task_id,
|
||||
priority=int(metadata.get("priority", 100)),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _assert_dispatch_context(
|
||||
dispatch: DispatchRecord,
|
||||
*,
|
||||
runtime: str,
|
||||
runtime_execution_id: str,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
trace_id: str,
|
||||
principal_id: str,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
) -> None:
|
||||
expected = {
|
||||
"runtime": runtime,
|
||||
"runtime_execution_id": runtime_execution_id,
|
||||
"tenant_id": tenant_id,
|
||||
"task_id": task_id,
|
||||
"trace_id": trace_id,
|
||||
"principal_id": principal_id,
|
||||
"provenance_id": provenance_id,
|
||||
"run_id": run_id,
|
||||
}
|
||||
for field_name, expected_value in expected.items():
|
||||
if getattr(dispatch, field_name) != expected_value:
|
||||
raise OrchestrationError(f"dispatch {field_name} mismatch")
|
||||
|
||||
def hermes_lifecycle_context(
|
||||
self,
|
||||
context: RequestContext,
|
||||
*,
|
||||
dispatch_id: str,
|
||||
job_id: str,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
trace_id: str,
|
||||
principal_id: str,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
) -> tuple[DispatchRecord, HermesJob]:
|
||||
"""Resolve a runtime lifecycle request against its durable dispatch."""
|
||||
dispatch = self.dispatch_repository.get(
|
||||
dispatch_id, tenant_id=context.tenant_id
|
||||
)
|
||||
self._assert_dispatch_context(
|
||||
dispatch,
|
||||
runtime="hermes",
|
||||
runtime_execution_id=job_id,
|
||||
tenant_id=tenant_id,
|
||||
task_id=task_id,
|
||||
trace_id=trace_id,
|
||||
principal_id=principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
if context.tenant_id != tenant_id:
|
||||
raise OrchestrationError("runtime context tenant_id mismatch")
|
||||
if context.principal_id != principal_id:
|
||||
raise OrchestrationError("runtime context principal_id mismatch")
|
||||
if context.trace_id != trace_id:
|
||||
raise OrchestrationError("runtime context trace_id mismatch")
|
||||
if self.hermes is None:
|
||||
raise OrchestrationError("Hermes runtime is not configured")
|
||||
job = self.hermes.get(job_id, tenant_id=tenant_id)
|
||||
if job.task_id != task_id or job.trace_id != trace_id:
|
||||
raise OrchestrationError("Hermes job identity mismatch")
|
||||
return dispatch, job
|
||||
|
||||
def bind_hermes_worker(
|
||||
self,
|
||||
context: RequestContext,
|
||||
job: HermesJob,
|
||||
*,
|
||||
dispatch_id: str,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
worker_id: str,
|
||||
) -> DispatchRecord:
|
||||
dispatch, current = self.hermes_lifecycle_context(
|
||||
context,
|
||||
dispatch_id=dispatch_id,
|
||||
job_id=job.job_id,
|
||||
tenant_id=job.tenant_id,
|
||||
task_id=job.task_id,
|
||||
trace_id=job.trace_id,
|
||||
principal_id=context.principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
if current.assigned_worker_id != worker_id:
|
||||
raise OrchestrationError("Hermes worker does not own claimed job")
|
||||
return self.dispatch_repository.update(
|
||||
dispatch.dispatch_id,
|
||||
tenant_id=dispatch.tenant_id,
|
||||
expected_worker_id=worker_id,
|
||||
)
|
||||
|
||||
def reconcile_openclaw(
|
||||
self,
|
||||
context: RequestContext,
|
||||
result: OpenClawResult,
|
||||
*,
|
||||
dispatch_id: str,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
) -> TaskRecord:
|
||||
dispatch = self.dispatch_repository.get(
|
||||
dispatch_id, tenant_id=context.tenant_id
|
||||
)
|
||||
self._assert_dispatch_context(
|
||||
dispatch,
|
||||
runtime="openclaw",
|
||||
runtime_execution_id=result.command_id,
|
||||
tenant_id=result.tenant_id,
|
||||
task_id=result.task_id,
|
||||
trace_id=result.trace_id,
|
||||
principal_id=context.principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
result_digest = digest_payload(
|
||||
{
|
||||
"command_id": result.command_id,
|
||||
"state": result.state.value,
|
||||
"output": result.output,
|
||||
"error": result.error,
|
||||
"runtime_id": result.runtime_id,
|
||||
"attempts": result.attempts,
|
||||
"finished_at": result.finished_at,
|
||||
}
|
||||
)
|
||||
if dispatch.state in TERMINAL_DISPATCH_STATES:
|
||||
if dispatch.result_digest != result_digest:
|
||||
raise DispatchConflict("terminal dispatch received a different result")
|
||||
return self.control_plane.get_task(context, dispatch.task_id)
|
||||
|
||||
task = self.control_plane.get_task(context, dispatch.task_id)
|
||||
if task.state != TaskState.RUNNING:
|
||||
raise OrchestrationError("task is not RUNNING for active dispatch")
|
||||
if result.state == CommandState.COMPLETED:
|
||||
target = TaskState.COMPLETED
|
||||
values = {"result": result.output or {}}
|
||||
dispatch_state = DispatchState.COMPLETED
|
||||
elif result.state in {
|
||||
CommandState.FAILED,
|
||||
CommandState.TIMED_OUT,
|
||||
CommandState.REJECTED,
|
||||
}:
|
||||
target = TaskState.FAILED
|
||||
values = {
|
||||
"error": result.error or {"code": result.state.value.lower()}
|
||||
}
|
||||
dispatch_state = DispatchState.FAILED
|
||||
elif result.state == CommandState.CANCELLED:
|
||||
target = TaskState.CANCELLED
|
||||
values = {}
|
||||
dispatch_state = DispatchState.CANCELLED
|
||||
else:
|
||||
self.dispatch_repository.update(
|
||||
dispatch.dispatch_id,
|
||||
tenant_id=dispatch.tenant_id,
|
||||
state=DispatchState.RUNNING,
|
||||
result_digest=result_digest,
|
||||
)
|
||||
return task
|
||||
|
||||
updated_task = self.control_plane.transition_task(
|
||||
context,
|
||||
task_id=task.task_id,
|
||||
target_state=target,
|
||||
expected_revision=task.revision,
|
||||
**values,
|
||||
)
|
||||
self.dispatch_repository.update(
|
||||
dispatch.dispatch_id,
|
||||
tenant_id=dispatch.tenant_id,
|
||||
state=dispatch_state,
|
||||
result_digest=result_digest,
|
||||
)
|
||||
return updated_task
|
||||
|
||||
def reconcile_hermes(
|
||||
self,
|
||||
context: RequestContext,
|
||||
result: HermesResult,
|
||||
*,
|
||||
dispatch_id: str,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
) -> TaskRecord:
|
||||
dispatch = self.dispatch_repository.get(
|
||||
dispatch_id, tenant_id=context.tenant_id
|
||||
)
|
||||
self._assert_dispatch_context(
|
||||
dispatch,
|
||||
runtime="hermes",
|
||||
runtime_execution_id=result.job_id,
|
||||
tenant_id=result.tenant_id,
|
||||
task_id=result.task_id,
|
||||
trace_id=result.trace_id,
|
||||
principal_id=context.principal_id,
|
||||
provenance_id=provenance_id,
|
||||
run_id=run_id,
|
||||
)
|
||||
if self.hermes is None:
|
||||
raise OrchestrationError("Hermes runtime is not configured")
|
||||
job = self.hermes.get(result.job_id, tenant_id=result.tenant_id)
|
||||
if result.state in {HermesJobState.COMPLETED, HermesJobState.FAILED}:
|
||||
if not result.worker_id:
|
||||
raise OrchestrationError("terminal Hermes result requires worker_id")
|
||||
if job.assigned_worker_id != result.worker_id:
|
||||
raise OrchestrationError("Hermes result worker does not own job lease")
|
||||
if (
|
||||
dispatch.expected_worker_id is not None
|
||||
and dispatch.expected_worker_id != result.worker_id
|
||||
):
|
||||
raise OrchestrationError("Hermes result worker mismatch")
|
||||
result_digest = digest_payload(
|
||||
{
|
||||
"job_id": result.job_id,
|
||||
"worker_id": result.worker_id,
|
||||
"state": result.state.value,
|
||||
"output": result.output,
|
||||
"error": result.error,
|
||||
"finished_at": result.finished_at,
|
||||
}
|
||||
)
|
||||
if dispatch.state in TERMINAL_DISPATCH_STATES:
|
||||
if dispatch.result_digest != result_digest:
|
||||
raise DispatchConflict("terminal dispatch received a different result")
|
||||
return self.control_plane.get_task(context, dispatch.task_id)
|
||||
|
||||
task = self.control_plane.get_task(context, dispatch.task_id)
|
||||
if task.state != TaskState.RUNNING:
|
||||
raise OrchestrationError("task is not RUNNING for active dispatch")
|
||||
if result.state == HermesJobState.COMPLETED:
|
||||
target = TaskState.COMPLETED
|
||||
values = {"result": result.output or {}}
|
||||
dispatch_state = DispatchState.COMPLETED
|
||||
elif result.state == HermesJobState.FAILED:
|
||||
target = TaskState.FAILED
|
||||
values = {"error": result.error or {"code": "hermes_failed"}}
|
||||
dispatch_state = DispatchState.FAILED
|
||||
elif result.state == HermesJobState.CANCELLED:
|
||||
target = TaskState.CANCELLED
|
||||
values = {}
|
||||
dispatch_state = DispatchState.CANCELLED
|
||||
else:
|
||||
raise OrchestrationError("Hermes reconcile only accepts terminal results")
|
||||
|
||||
updated_task = self.control_plane.transition_task(
|
||||
context,
|
||||
task_id=task.task_id,
|
||||
target_state=target,
|
||||
expected_revision=task.revision,
|
||||
**values,
|
||||
)
|
||||
self.dispatch_repository.update(
|
||||
dispatch.dispatch_id,
|
||||
tenant_id=dispatch.tenant_id,
|
||||
state=dispatch_state,
|
||||
expected_worker_id=result.worker_id,
|
||||
result_digest=result_digest,
|
||||
)
|
||||
return updated_task
|
||||
|
||||
def dispatch_snapshot(self, *, tenant_id: str) -> Mapping[str, DispatchRecord]:
|
||||
return {
|
||||
item.task_id: item
|
||||
for item in self.dispatch_repository.list(tenant_id=tenant_id)
|
||||
}
|
||||
@@ -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 +1,831 @@
|
||||
"""AIOS V2 可信 Run Provenance 签发、持久化与受控写入。
|
||||
|
||||
生产策略要求 Provenance 同时覆盖七类路径:代码变更、Git 操作、部署、
|
||||
Runtime 执行、Evidence 写入、回滚和审计。任何缺失、篡改、过期、撤销、
|
||||
重放或上下文不匹配都默认拒绝。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import sqlite3
|
||||
import stat
|
||||
import threading
|
||||
import uuid
|
||||
from dataclasses import asdict, dataclass, field, replace
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Protocol, Sequence
|
||||
|
||||
PROVENANCE_VERSION = "aios.v2.run-provenance.v1"
|
||||
PRODUCTION_POLICY_VERSION = "aios.v2.production.v1"
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def parse_timestamp(value: str) -> datetime:
|
||||
normalized = str(value or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError("timestamp is required")
|
||||
if normalized.endswith("Z"):
|
||||
normalized = normalized[:-1] + "+00:00"
|
||||
parsed = datetime.fromisoformat(normalized)
|
||||
if parsed.tzinfo is None:
|
||||
raise ValueError("timestamp must include timezone")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def required(value: str, label: str) -> str:
|
||||
normalized = str(value or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError(f"{label} is required")
|
||||
return normalized
|
||||
|
||||
|
||||
def canonical_json_bytes(value: Mapping[str, Any]) -> bytes:
|
||||
return json.dumps(
|
||||
dict(value),
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
default=str,
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def digest_payload(value: Mapping[str, Any]) -> str:
|
||||
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
|
||||
|
||||
|
||||
def _validate_digest(value: str) -> str:
|
||||
normalized = required(value, "request_digest").lower()
|
||||
if len(normalized) != 64 or any(ch not in "0123456789abcdef" for ch in normalized):
|
||||
raise ValueError("request_digest must be a SHA-256 hexadecimal digest")
|
||||
return normalized
|
||||
|
||||
|
||||
class ExecutionPath(str, Enum):
|
||||
CODE_CHANGE = "code_change"
|
||||
GIT_OPERATION = "git_operation"
|
||||
DEPLOYMENT = "deployment"
|
||||
RUNTIME_EXECUTE = "runtime_execute"
|
||||
EVIDENCE_WRITE = "evidence_write"
|
||||
ROLLBACK = "rollback"
|
||||
AUDIT = "audit"
|
||||
|
||||
|
||||
REQUIRED_PRODUCTION_PATHS = frozenset(item.value for item in ExecutionPath)
|
||||
|
||||
|
||||
class GitOperation(str, Enum):
|
||||
READ_REF = "read_ref"
|
||||
FETCH = "fetch"
|
||||
CREATE_BRANCH = "create_branch"
|
||||
COMMIT = "commit"
|
||||
MERGE = "merge"
|
||||
PUSH = "push"
|
||||
UPDATE_EVIDENCE = "update_evidence"
|
||||
|
||||
|
||||
class ProvenanceStatus(str, Enum):
|
||||
ISSUED = "issued"
|
||||
VERIFIED = "verified"
|
||||
USED = "used"
|
||||
EXPIRED = "expired"
|
||||
REVOKED = "revoked"
|
||||
|
||||
|
||||
class ProvenanceError(RuntimeError):
|
||||
"""Run Provenance 基础错误。"""
|
||||
|
||||
|
||||
class ProvenanceDenied(ProvenanceError):
|
||||
"""策略拒绝当前操作。"""
|
||||
|
||||
|
||||
class ProvenanceNotFound(ProvenanceDenied):
|
||||
"""未找到 Provenance。"""
|
||||
|
||||
|
||||
class ProvenanceSignatureError(ProvenanceDenied):
|
||||
"""签名无效。"""
|
||||
|
||||
|
||||
class ProvenanceExpired(ProvenanceDenied):
|
||||
"""Provenance 已过期。"""
|
||||
|
||||
|
||||
class ProvenanceRevoked(ProvenanceDenied):
|
||||
"""Provenance 已撤销。"""
|
||||
|
||||
|
||||
class ProvenanceReplay(ProvenanceDenied):
|
||||
"""检测到相同授权摘要重放。"""
|
||||
|
||||
|
||||
class Signer(Protocol):
|
||||
key_id: str
|
||||
|
||||
def sign(self, payload: bytes) -> str: ...
|
||||
|
||||
|
||||
class SignatureVerifier(Protocol):
|
||||
key_id: str
|
||||
fingerprint: str
|
||||
|
||||
def verify(self, payload: bytes, signature: str) -> bool: ...
|
||||
|
||||
|
||||
def _load_crypto() -> tuple[Any, Any, Any]:
|
||||
try:
|
||||
from cryptography.hazmat.primitives import serialization
|
||||
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
|
||||
Ed25519PrivateKey,
|
||||
Ed25519PublicKey,
|
||||
)
|
||||
except ImportError as exc: # pragma: no cover - depends on deployment image
|
||||
raise RuntimeError(
|
||||
"cryptography package with Ed25519 support is required"
|
||||
) from exc
|
||||
return serialization, Ed25519PrivateKey, Ed25519PublicKey
|
||||
|
||||
|
||||
def _check_private_key_file(path: Path) -> bytes:
|
||||
resolved = path.resolve()
|
||||
metadata = resolved.stat()
|
||||
if not stat.S_ISREG(metadata.st_mode):
|
||||
raise RuntimeError("private key reference is not a regular file")
|
||||
if metadata.st_mode & 0o077:
|
||||
raise RuntimeError("private key file permissions must be 0600 or stricter")
|
||||
return resolved.read_bytes()
|
||||
|
||||
|
||||
def _check_public_key_file(path: Path) -> bytes:
|
||||
resolved = path.resolve()
|
||||
metadata = resolved.stat()
|
||||
if not stat.S_ISREG(metadata.st_mode):
|
||||
raise RuntimeError("public key reference is not a regular file")
|
||||
if metadata.st_mode & 0o022:
|
||||
raise RuntimeError("public key file must not be group/world writable")
|
||||
return resolved.read_bytes()
|
||||
|
||||
|
||||
class Ed25519PrivateKeySigner:
|
||||
"""Ed25519 Owner/Control Plane 签发器。"""
|
||||
|
||||
def __init__(self, private_key: Any, *, key_id: str) -> None:
|
||||
self.private_key = private_key
|
||||
self.key_id = required(key_id, "key_id")
|
||||
|
||||
@classmethod
|
||||
def from_file(cls, path: str | Path, *, key_id: str) -> "Ed25519PrivateKeySigner":
|
||||
serialization, private_cls, _ = _load_crypto()
|
||||
value = _check_private_key_file(Path(path))
|
||||
if value.startswith(b"-----BEGIN"):
|
||||
key = serialization.load_pem_private_key(value, password=None)
|
||||
elif len(value) == 32:
|
||||
key = private_cls.from_private_bytes(value)
|
||||
else:
|
||||
raise RuntimeError("private key must be PEM or a raw 32-byte Ed25519 seed")
|
||||
if not isinstance(key, private_cls):
|
||||
raise RuntimeError("private key is not Ed25519")
|
||||
return cls(key, key_id=key_id)
|
||||
|
||||
def sign(self, payload: bytes) -> str:
|
||||
return base64.b64encode(self.private_key.sign(bytes(payload))).decode("ascii")
|
||||
|
||||
def public_verifier(self) -> "Ed25519PublicKeyVerifier":
|
||||
return Ed25519PublicKeyVerifier(self.private_key.public_key(), key_id=self.key_id)
|
||||
|
||||
|
||||
class Ed25519PublicKeyVerifier:
|
||||
"""Ed25519 签名验证器。"""
|
||||
|
||||
def __init__(self, public_key: Any, *, key_id: str) -> None:
|
||||
serialization, _, public_cls = _load_crypto()
|
||||
if not isinstance(public_key, public_cls):
|
||||
raise RuntimeError("public key is not Ed25519")
|
||||
self.public_key = public_key
|
||||
self.key_id = required(key_id, "key_id")
|
||||
raw = public_key.public_bytes(
|
||||
encoding=serialization.Encoding.Raw,
|
||||
format=serialization.PublicFormat.Raw,
|
||||
)
|
||||
self.fingerprint = hashlib.sha256(raw).hexdigest()
|
||||
|
||||
@classmethod
|
||||
def from_file(cls, path: str | Path, *, key_id: str) -> "Ed25519PublicKeyVerifier":
|
||||
serialization, _, public_cls = _load_crypto()
|
||||
value = _check_public_key_file(Path(path))
|
||||
if value.startswith(b"-----BEGIN"):
|
||||
key = serialization.load_pem_public_key(value)
|
||||
elif len(value) == 32:
|
||||
key = public_cls.from_public_bytes(value)
|
||||
else:
|
||||
raise RuntimeError("public key must be PEM or raw 32-byte Ed25519 key")
|
||||
if not isinstance(key, public_cls):
|
||||
raise RuntimeError("public key is not Ed25519")
|
||||
return cls(key, key_id=key_id)
|
||||
|
||||
def verify(self, payload: bytes, signature: str) -> bool:
|
||||
try:
|
||||
decoded = base64.b64decode(required(signature, "signature"), validate=True)
|
||||
self.public_key.verify(decoded, bytes(payload))
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RunProvenance:
|
||||
provenance_id: str
|
||||
run_id: str
|
||||
issuer: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
allowed_paths: Sequence[str]
|
||||
allowed_git_operations: Sequence[str]
|
||||
issued_at: str
|
||||
expires_at: str
|
||||
policy_version: str
|
||||
key_id: str
|
||||
nonce: str
|
||||
signature: str = ""
|
||||
schema_version: str = PROVENANCE_VERSION
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in (
|
||||
"provenance_id",
|
||||
"run_id",
|
||||
"issuer",
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"agent_id",
|
||||
"principal_id",
|
||||
"issued_at",
|
||||
"expires_at",
|
||||
"policy_version",
|
||||
"key_id",
|
||||
"nonce",
|
||||
"schema_version",
|
||||
):
|
||||
object.__setattr__(self, name, required(getattr(self, name), name))
|
||||
if self.schema_version != PROVENANCE_VERSION:
|
||||
raise ValueError(f"unsupported schema_version: {self.schema_version}")
|
||||
issued = parse_timestamp(self.issued_at)
|
||||
expires = parse_timestamp(self.expires_at)
|
||||
if expires <= issued:
|
||||
raise ValueError("expires_at must be later than issued_at")
|
||||
paths = tuple(sorted({ExecutionPath(item).value for item in self.allowed_paths}))
|
||||
operations = tuple(
|
||||
sorted({GitOperation(item).value for item in self.allowed_git_operations})
|
||||
)
|
||||
object.__setattr__(self, "allowed_paths", paths)
|
||||
object.__setattr__(self, "allowed_git_operations", operations)
|
||||
object.__setattr__(self, "signature", str(self.signature or "").strip())
|
||||
|
||||
def unsigned_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"schema_version": self.schema_version,
|
||||
"provenance_id": self.provenance_id,
|
||||
"run_id": self.run_id,
|
||||
"issuer": self.issuer,
|
||||
"tenant_id": self.tenant_id,
|
||||
"task_id": self.task_id,
|
||||
"agent_id": self.agent_id,
|
||||
"principal_id": self.principal_id,
|
||||
"allowed_paths": list(self.allowed_paths),
|
||||
"allowed_git_operations": list(self.allowed_git_operations),
|
||||
"issued_at": self.issued_at,
|
||||
"expires_at": self.expires_at,
|
||||
"policy_version": self.policy_version,
|
||||
"key_id": self.key_id,
|
||||
"nonce": self.nonce,
|
||||
}
|
||||
|
||||
def canonical_bytes(self) -> bytes:
|
||||
return canonical_json_bytes(self.unsigned_dict())
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
value = self.unsigned_dict()
|
||||
value["signature"] = self.signature
|
||||
return value
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, value: Mapping[str, Any]) -> "RunProvenance":
|
||||
return cls(**dict(value))
|
||||
|
||||
|
||||
class ProvenanceIssuer:
|
||||
"""只由 Owner 或 AIOS Control Plane 持有的签发服务。"""
|
||||
|
||||
def __init__(self, signer: Signer, store: "SQLiteProvenanceStore") -> None:
|
||||
self.signer = signer
|
||||
self.store = store
|
||||
|
||||
def issue(
|
||||
self,
|
||||
*,
|
||||
run_id: str,
|
||||
issuer: str,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
principal_id: str,
|
||||
allowed_paths: Sequence[str] = tuple(REQUIRED_PRODUCTION_PATHS),
|
||||
allowed_git_operations: Sequence[str] = tuple(item.value for item in GitOperation),
|
||||
ttl_seconds: int = 3600,
|
||||
policy_version: str = PRODUCTION_POLICY_VERSION,
|
||||
provenance_id: str | None = None,
|
||||
nonce: str | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> RunProvenance:
|
||||
if ttl_seconds <= 0:
|
||||
raise ValueError("ttl_seconds must be positive")
|
||||
normalized_paths = frozenset(ExecutionPath(item).value for item in allowed_paths)
|
||||
if policy_version == PRODUCTION_POLICY_VERSION and normalized_paths != REQUIRED_PRODUCTION_PATHS:
|
||||
missing = sorted(REQUIRED_PRODUCTION_PATHS - normalized_paths)
|
||||
extra = sorted(normalized_paths - REQUIRED_PRODUCTION_PATHS)
|
||||
raise ProvenanceDenied(
|
||||
f"production provenance must cover exactly seven paths; missing={missing}, extra={extra}"
|
||||
)
|
||||
normalized_operations = tuple(
|
||||
sorted({GitOperation(item).value for item in allowed_git_operations})
|
||||
)
|
||||
if ExecutionPath.GIT_OPERATION.value in normalized_paths and not normalized_operations:
|
||||
raise ProvenanceDenied("git_operation path requires explicit allowed Git operations")
|
||||
issued = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
|
||||
unsigned = RunProvenance(
|
||||
provenance_id=provenance_id or f"prov_{uuid.uuid4().hex}",
|
||||
run_id=run_id,
|
||||
issuer=issuer,
|
||||
tenant_id=tenant_id,
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
principal_id=principal_id,
|
||||
allowed_paths=tuple(normalized_paths),
|
||||
allowed_git_operations=normalized_operations,
|
||||
issued_at=issued.isoformat().replace("+00:00", "Z"),
|
||||
expires_at=(issued + timedelta(seconds=ttl_seconds))
|
||||
.isoformat()
|
||||
.replace("+00:00", "Z"),
|
||||
policy_version=policy_version,
|
||||
key_id=self.signer.key_id,
|
||||
nonce=nonce or uuid.uuid4().hex,
|
||||
)
|
||||
signed = replace(unsigned, signature=self.signer.sign(unsigned.canonical_bytes()))
|
||||
self.store.save_issued(signed)
|
||||
return signed
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProvenanceAuthorization:
|
||||
authorization_id: str
|
||||
provenance_id: str
|
||||
run_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
execution_path: str
|
||||
git_operation: str | None
|
||||
request_digest: str
|
||||
policy_version: str
|
||||
key_id: str
|
||||
public_key_fingerprint: str
|
||||
authorized_at: str = field(default_factory=utc_now)
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class SQLiteProvenanceStore:
|
||||
"""持久化 Provenance、状态、授权使用和不可变事件。"""
|
||||
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = Path(path).resolve()
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
self._lock = threading.RLock()
|
||||
self._connection = sqlite3.connect(
|
||||
str(self.path), timeout=30.0, check_same_thread=False
|
||||
)
|
||||
self._connection.row_factory = sqlite3.Row
|
||||
with self._lock:
|
||||
self._connection.execute("PRAGMA journal_mode=WAL")
|
||||
self._connection.execute("PRAGMA synchronous=FULL")
|
||||
self._connection.execute("PRAGMA foreign_keys=ON")
|
||||
self._connection.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS provenance_records (
|
||||
provenance_id TEXT PRIMARY KEY,
|
||||
payload_json TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
signature_verified INTEGER NOT NULL DEFAULT 0,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS provenance_usage (
|
||||
authorization_id TEXT PRIMARY KEY,
|
||||
provenance_id TEXT NOT NULL,
|
||||
execution_path TEXT NOT NULL,
|
||||
git_operation TEXT NOT NULL DEFAULT '',
|
||||
request_digest TEXT NOT NULL,
|
||||
authorized_at TEXT NOT NULL,
|
||||
receipt_json TEXT NOT NULL,
|
||||
UNIQUE(provenance_id, execution_path, git_operation, request_digest),
|
||||
FOREIGN KEY(provenance_id) REFERENCES provenance_records(provenance_id)
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS provenance_events (
|
||||
event_id TEXT PRIMARY KEY,
|
||||
provenance_id TEXT NOT NULL,
|
||||
event_type TEXT NOT NULL,
|
||||
details_json TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
FOREIGN KEY(provenance_id) REFERENCES provenance_records(provenance_id)
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_provenance_usage_id
|
||||
ON provenance_usage(provenance_id, authorized_at);
|
||||
CREATE INDEX IF NOT EXISTS idx_provenance_events_id
|
||||
ON provenance_events(provenance_id, created_at);
|
||||
"""
|
||||
)
|
||||
self._connection.commit()
|
||||
|
||||
def close(self) -> None:
|
||||
with self._lock:
|
||||
self._connection.close()
|
||||
|
||||
def _event(
|
||||
self,
|
||||
provenance_id: str,
|
||||
event_type: str,
|
||||
details: Mapping[str, Any] | None = None,
|
||||
) -> None:
|
||||
self._connection.execute(
|
||||
"INSERT INTO provenance_events VALUES (?, ?, ?, ?, ?)",
|
||||
(
|
||||
f"pevt_{uuid.uuid4().hex}",
|
||||
provenance_id,
|
||||
event_type,
|
||||
json.dumps(dict(details or {}), ensure_ascii=False, sort_keys=True),
|
||||
utc_now(),
|
||||
),
|
||||
)
|
||||
|
||||
def save_issued(self, provenance: RunProvenance) -> None:
|
||||
payload = json.dumps(
|
||||
provenance.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
|
||||
)
|
||||
now = utc_now()
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
prior = self._connection.execute(
|
||||
"SELECT payload_json FROM provenance_records WHERE provenance_id = ?",
|
||||
(provenance.provenance_id,),
|
||||
).fetchone()
|
||||
if prior is not None:
|
||||
if prior["payload_json"] != payload:
|
||||
raise ProvenanceDenied("provenance_id reused with different payload")
|
||||
self._connection.rollback()
|
||||
return
|
||||
self._connection.execute(
|
||||
"INSERT INTO provenance_records VALUES (?, ?, ?, 0, ?, ?)",
|
||||
(
|
||||
provenance.provenance_id,
|
||||
payload,
|
||||
ProvenanceStatus.ISSUED.value,
|
||||
now,
|
||||
now,
|
||||
),
|
||||
)
|
||||
self._event(provenance.provenance_id, "issued")
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def get(self, provenance_id: str) -> RunProvenance:
|
||||
with self._lock:
|
||||
row = self._connection.execute(
|
||||
"SELECT payload_json FROM provenance_records WHERE provenance_id = ?",
|
||||
(required(provenance_id, "provenance_id"),),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise ProvenanceNotFound("provenance not found")
|
||||
value = json.loads(row["payload_json"])
|
||||
if not isinstance(value, Mapping):
|
||||
raise ProvenanceError("stored provenance payload is invalid")
|
||||
return RunProvenance.from_dict(value)
|
||||
|
||||
def status(self, provenance_id: str) -> ProvenanceStatus:
|
||||
with self._lock:
|
||||
row = self._connection.execute(
|
||||
"SELECT status FROM provenance_records WHERE provenance_id = ?",
|
||||
(required(provenance_id, "provenance_id"),),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise ProvenanceNotFound("provenance not found")
|
||||
return ProvenanceStatus(row["status"])
|
||||
|
||||
def mark_verified(self, provenance_id: str, *, fingerprint: str) -> None:
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
current = self.status(provenance_id)
|
||||
if current in {ProvenanceStatus.REVOKED, ProvenanceStatus.EXPIRED}:
|
||||
raise ProvenanceDenied(f"cannot verify provenance in state {current.value}")
|
||||
next_status = (
|
||||
ProvenanceStatus.USED.value
|
||||
if current == ProvenanceStatus.USED
|
||||
else ProvenanceStatus.VERIFIED.value
|
||||
)
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_records SET status = ?, signature_verified = 1, updated_at = ? WHERE provenance_id = ?",
|
||||
(next_status, utc_now(), provenance_id),
|
||||
)
|
||||
self._event(
|
||||
provenance_id,
|
||||
"verified",
|
||||
{"public_key_fingerprint": fingerprint},
|
||||
)
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def mark_expired(self, provenance_id: str) -> None:
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
current = self.status(provenance_id)
|
||||
if current == ProvenanceStatus.REVOKED:
|
||||
self._connection.rollback()
|
||||
return
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_records SET status = ?, updated_at = ? WHERE provenance_id = ?",
|
||||
(ProvenanceStatus.EXPIRED.value, utc_now(), provenance_id),
|
||||
)
|
||||
self._event(provenance_id, "expired")
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def revoke(self, provenance_id: str, *, reason: str, principal_id: str) -> None:
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
self.get(provenance_id)
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_records SET status = ?, updated_at = ? WHERE provenance_id = ?",
|
||||
(ProvenanceStatus.REVOKED.value, utc_now(), provenance_id),
|
||||
)
|
||||
self._event(
|
||||
provenance_id,
|
||||
"revoked",
|
||||
{
|
||||
"reason": required(reason, "reason"),
|
||||
"principal_id": required(principal_id, "principal_id"),
|
||||
},
|
||||
)
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def record_authorization(self, authorization: ProvenanceAuthorization) -> None:
|
||||
receipt = json.dumps(
|
||||
authorization.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
|
||||
)
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
current = self.status(authorization.provenance_id)
|
||||
if current in {ProvenanceStatus.REVOKED, ProvenanceStatus.EXPIRED}:
|
||||
raise ProvenanceDenied(f"provenance state is {current.value}")
|
||||
try:
|
||||
self._connection.execute(
|
||||
"INSERT INTO provenance_usage VALUES (?, ?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
authorization.authorization_id,
|
||||
authorization.provenance_id,
|
||||
authorization.execution_path,
|
||||
authorization.git_operation or "",
|
||||
authorization.request_digest,
|
||||
authorization.authorized_at,
|
||||
receipt,
|
||||
),
|
||||
)
|
||||
except sqlite3.IntegrityError as exc:
|
||||
raise ProvenanceReplay(
|
||||
"identical provenance path/operation/request digest already used"
|
||||
) from exc
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_records SET status = ?, updated_at = ? WHERE provenance_id = ?",
|
||||
(
|
||||
ProvenanceStatus.USED.value,
|
||||
authorization.authorized_at,
|
||||
authorization.provenance_id,
|
||||
),
|
||||
)
|
||||
self._event(
|
||||
authorization.provenance_id,
|
||||
"used",
|
||||
{
|
||||
"authorization_id": authorization.authorization_id,
|
||||
"execution_path": authorization.execution_path,
|
||||
"git_operation": authorization.git_operation,
|
||||
"request_digest": authorization.request_digest,
|
||||
},
|
||||
)
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def authorization_count(self, provenance_id: str) -> int:
|
||||
with self._lock:
|
||||
row = self._connection.execute(
|
||||
"SELECT COUNT(*) AS total FROM provenance_usage WHERE provenance_id = ?",
|
||||
(required(provenance_id, "provenance_id"),),
|
||||
).fetchone()
|
||||
return int(row["total"])
|
||||
|
||||
def events(self, provenance_id: str) -> list[dict[str, Any]]:
|
||||
with self._lock:
|
||||
rows = self._connection.execute(
|
||||
"SELECT event_type, details_json, created_at FROM provenance_events WHERE provenance_id = ? ORDER BY created_at, event_id",
|
||||
(required(provenance_id, "provenance_id"),),
|
||||
).fetchall()
|
||||
return [
|
||||
{
|
||||
"event_type": row["event_type"],
|
||||
"details": json.loads(row["details_json"]),
|
||||
"created_at": row["created_at"],
|
||||
}
|
||||
for row in rows
|
||||
]
|
||||
|
||||
|
||||
class ProvenanceVerifier:
|
||||
"""验证 Owner 签名、上下文、路径、Git 操作、时效和重放。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
store: SQLiteProvenanceStore,
|
||||
verifiers: Mapping[str, SignatureVerifier],
|
||||
) -> None:
|
||||
if not verifiers:
|
||||
raise ValueError("at least one public key verifier is required")
|
||||
self.store = store
|
||||
self.verifiers = {required(key, "key_id"): value for key, value in verifiers.items()}
|
||||
|
||||
def authorize(
|
||||
self,
|
||||
*,
|
||||
provenance_id: str,
|
||||
run_id: str,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
principal_id: str,
|
||||
execution_path: str,
|
||||
request_digest: str,
|
||||
git_operation: str | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> ProvenanceAuthorization:
|
||||
provenance = self.store.get(provenance_id)
|
||||
status = self.store.status(provenance.provenance_id)
|
||||
if status == ProvenanceStatus.REVOKED:
|
||||
raise ProvenanceRevoked("provenance is revoked")
|
||||
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
|
||||
if current >= parse_timestamp(provenance.expires_at):
|
||||
self.store.mark_expired(provenance.provenance_id)
|
||||
raise ProvenanceExpired("provenance is expired")
|
||||
verifier = self.verifiers.get(provenance.key_id)
|
||||
if verifier is None:
|
||||
raise ProvenanceSignatureError("no trusted public key for provenance key_id")
|
||||
if not provenance.signature or not verifier.verify(
|
||||
provenance.canonical_bytes(), provenance.signature
|
||||
):
|
||||
raise ProvenanceSignatureError("invalid provenance signature")
|
||||
expected = {
|
||||
"run_id": required(run_id, "run_id"),
|
||||
"tenant_id": required(tenant_id, "tenant_id"),
|
||||
"task_id": required(task_id, "task_id"),
|
||||
"agent_id": required(agent_id, "agent_id"),
|
||||
"principal_id": required(principal_id, "principal_id"),
|
||||
}
|
||||
for field_name, expected_value in expected.items():
|
||||
if getattr(provenance, field_name) != expected_value:
|
||||
raise ProvenanceDenied(f"provenance {field_name} mismatch")
|
||||
path = ExecutionPath(execution_path).value
|
||||
if path not in provenance.allowed_paths:
|
||||
raise ProvenanceDenied(f"execution path is not allowed: {path}")
|
||||
operation: str | None = None
|
||||
if path == ExecutionPath.GIT_OPERATION.value:
|
||||
if git_operation is None:
|
||||
raise ProvenanceDenied("git operation is required for git_operation path")
|
||||
operation = GitOperation(git_operation).value
|
||||
if operation not in provenance.allowed_git_operations:
|
||||
raise ProvenanceDenied(f"Git operation is not allowed: {operation}")
|
||||
elif git_operation is not None:
|
||||
raise ProvenanceDenied("git_operation is only valid for git_operation path")
|
||||
digest = _validate_digest(request_digest)
|
||||
self.store.mark_verified(
|
||||
provenance.provenance_id, fingerprint=verifier.fingerprint
|
||||
)
|
||||
authorization = ProvenanceAuthorization(
|
||||
authorization_id=f"pauth_{uuid.uuid4().hex}",
|
||||
provenance_id=provenance.provenance_id,
|
||||
run_id=provenance.run_id,
|
||||
tenant_id=provenance.tenant_id,
|
||||
task_id=provenance.task_id,
|
||||
agent_id=provenance.agent_id,
|
||||
principal_id=provenance.principal_id,
|
||||
execution_path=path,
|
||||
git_operation=operation,
|
||||
request_digest=digest,
|
||||
policy_version=provenance.policy_version,
|
||||
key_id=provenance.key_id,
|
||||
public_key_fingerprint=verifier.fingerprint,
|
||||
)
|
||||
self.store.record_authorization(authorization)
|
||||
return authorization
|
||||
|
||||
|
||||
class ProvenanceControlledWriter:
|
||||
"""七路径统一策略入口并持久写入授权回执。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
verifier: ProvenanceVerifier,
|
||||
receipt_root: str | Path,
|
||||
*,
|
||||
writer_id: str = "aios-v2-provenance-writer",
|
||||
) -> None:
|
||||
self.verifier = verifier
|
||||
self.receipt_root = Path(receipt_root).resolve()
|
||||
self.receipt_root.mkdir(parents=True, exist_ok=True)
|
||||
self.writer_id = required(writer_id, "writer_id")
|
||||
self._lock = threading.RLock()
|
||||
|
||||
@staticmethod
|
||||
def _component(value: str) -> str:
|
||||
normalized = required(value, "path component")
|
||||
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
|
||||
raise ProvenanceDenied("invalid receipt path component")
|
||||
return normalized
|
||||
|
||||
def authorize(self, **values: Any) -> ProvenanceAuthorization:
|
||||
authorization = self.verifier.authorize(**values)
|
||||
tenant = self._component(authorization.tenant_id)
|
||||
provenance_id = self._component(authorization.provenance_id)
|
||||
target_dir = self.receipt_root / tenant / provenance_id
|
||||
target = target_dir / f"{authorization.authorization_id}.json"
|
||||
payload = authorization.as_dict()
|
||||
payload["writer_id"] = self.writer_id
|
||||
with self._lock:
|
||||
target_dir.mkdir(parents=True, exist_ok=True)
|
||||
temporary = target.with_suffix(f".tmp-{os.getpid()}")
|
||||
temporary.write_text(
|
||||
json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
os.chmod(temporary, 0o640)
|
||||
os.replace(temporary, target)
|
||||
return authorization
|
||||
|
||||
def authorize_code_change(self, **values: Any) -> ProvenanceAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.CODE_CHANGE.value, **values)
|
||||
|
||||
def authorize_git_operation(
|
||||
self, *, git_operation: str, **values: Any
|
||||
) -> ProvenanceAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.GIT_OPERATION.value,
|
||||
git_operation=git_operation,
|
||||
**values,
|
||||
)
|
||||
|
||||
def authorize_deployment(self, **values: Any) -> ProvenanceAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.DEPLOYMENT.value, **values)
|
||||
|
||||
def authorize_runtime_execute(self, **values: Any) -> ProvenanceAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.RUNTIME_EXECUTE.value, **values)
|
||||
|
||||
def authorize_evidence_write(self, **values: Any) -> ProvenanceAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.EVIDENCE_WRITE.value, **values)
|
||||
|
||||
def authorize_rollback(self, **values: Any) -> ProvenanceAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.ROLLBACK.value, **values)
|
||||
|
||||
def authorize_audit(self, **values: Any) -> ProvenanceAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.AUDIT.value, **values)
|
||||
@@ -0,0 +1,381 @@
|
||||
#!/usr/bin/env python3
|
||||
"""AIOS V2 Run Provenance 与最小权限 Grant 运维 CLI。
|
||||
|
||||
私钥只用于签发;授权命令只加载一个与 ``--path`` 对应的 Grant。所有输出均为
|
||||
不含 Secret 的 JSON。旧 ``issue`` 仅为候选兼容,生产必须使用
|
||||
``issue-workflow`` 与 ``issue-grant``。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
from .provenance import (
|
||||
Ed25519PrivateKeySigner,
|
||||
Ed25519PublicKeyVerifier,
|
||||
ExecutionPath,
|
||||
GitOperation,
|
||||
ProvenanceIssuer,
|
||||
SQLiteProvenanceStore,
|
||||
)
|
||||
from .provenance_grants import (
|
||||
GrantIssuer,
|
||||
GrantType,
|
||||
GrantVerifier,
|
||||
SQLiteGrantStore,
|
||||
WorkflowProvenanceIssuer,
|
||||
)
|
||||
from .provenance_operations import (
|
||||
OperationContext,
|
||||
ProvenanceOperationGate,
|
||||
context_from_environment,
|
||||
load_request_file,
|
||||
)
|
||||
from .provenance_scoped import ScopedLeastPrivilegeProvenanceWriter
|
||||
|
||||
|
||||
def _json_object(value: str | None, file_path: str | None) -> Mapping[str, Any]:
|
||||
if value and file_path:
|
||||
raise ValueError("request-json and request-file are mutually exclusive")
|
||||
if file_path:
|
||||
return load_request_file(file_path)
|
||||
parsed = json.loads(value or "{}")
|
||||
if not isinstance(parsed, Mapping):
|
||||
raise ValueError("request JSON must be an object")
|
||||
return dict(parsed)
|
||||
|
||||
|
||||
def _csv(value: str | None) -> tuple[str, ...]:
|
||||
return tuple(item.strip() for item in str(value or "").split(",") if item.strip())
|
||||
|
||||
|
||||
def _write_json(path: str | None, payload: Mapping[str, Any]) -> None:
|
||||
encoded = json.dumps(dict(payload), ensure_ascii=False, sort_keys=True, indent=2) + "\n"
|
||||
if path:
|
||||
target = Path(path).resolve()
|
||||
target.parent.mkdir(parents=True, exist_ok=True)
|
||||
temporary = target.with_suffix(f".tmp-{os.getpid()}")
|
||||
temporary.write_text(encoded, encoding="utf-8")
|
||||
os.chmod(temporary, 0o640)
|
||||
os.replace(temporary, target)
|
||||
print(encoded, end="")
|
||||
|
||||
|
||||
def _parent_store(args: argparse.Namespace) -> SQLiteProvenanceStore:
|
||||
return SQLiteProvenanceStore(args.store_file)
|
||||
|
||||
|
||||
def _grant_store(args: argparse.Namespace) -> SQLiteGrantStore:
|
||||
return SQLiteGrantStore(args.store_file)
|
||||
|
||||
|
||||
def _context(args: argparse.Namespace) -> OperationContext:
|
||||
if args.context_from_env:
|
||||
return context_from_environment()
|
||||
values = {
|
||||
"provenance_id": args.provenance_id,
|
||||
"run_id": args.run_id,
|
||||
"tenant_id": args.tenant_id,
|
||||
"task_id": args.task_id,
|
||||
"agent_id": args.agent_id,
|
||||
"principal_id": args.principal_id,
|
||||
}
|
||||
missing = [name for name, value in values.items() if not str(value or "").strip()]
|
||||
if missing:
|
||||
raise ValueError(f"missing context arguments: {missing}")
|
||||
return OperationContext(**{name: str(value).strip() for name, value in values.items()})
|
||||
|
||||
|
||||
def command_issue_legacy(args: argparse.Namespace) -> int:
|
||||
store = _parent_store(args)
|
||||
signer = Ed25519PrivateKeySigner.from_file(args.private_key_file, key_id=args.key_id)
|
||||
provenance = ProvenanceIssuer(signer, store).issue(
|
||||
run_id=args.run_id,
|
||||
issuer=args.issuer,
|
||||
tenant_id=args.tenant_id,
|
||||
task_id=args.task_id,
|
||||
agent_id=args.agent_id,
|
||||
principal_id=args.principal_id,
|
||||
allowed_paths=_csv(args.allowed_paths) or tuple(item.value for item in ExecutionPath),
|
||||
allowed_git_operations=_csv(args.allowed_git_operations)
|
||||
or tuple(item.value for item in GitOperation),
|
||||
ttl_seconds=args.ttl_seconds,
|
||||
policy_version=args.policy_version,
|
||||
)
|
||||
_write_json(
|
||||
args.output,
|
||||
{
|
||||
"mode": "legacy-full-rights-candidate-only",
|
||||
"provenance": provenance.as_dict(),
|
||||
"status": store.status(provenance.provenance_id).value,
|
||||
"secret_value_stored": False,
|
||||
},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def command_issue_workflow(args: argparse.Namespace) -> int:
|
||||
store = _parent_store(args)
|
||||
signer = Ed25519PrivateKeySigner.from_file(args.private_key_file, key_id=args.key_id)
|
||||
workflow = WorkflowProvenanceIssuer(signer, store).issue(
|
||||
run_id=args.run_id,
|
||||
issuer=args.issuer,
|
||||
tenant_id=args.tenant_id,
|
||||
task_id=args.task_id,
|
||||
agent_id=args.agent_id,
|
||||
principal_id=args.principal_id,
|
||||
ttl_seconds=args.ttl_seconds,
|
||||
)
|
||||
_write_json(
|
||||
args.output,
|
||||
{
|
||||
"mode": "least-privilege-workflow",
|
||||
"workflow_provenance": workflow.as_dict(),
|
||||
"status": store.status(workflow.provenance_id).value,
|
||||
"secret_value_stored": False,
|
||||
},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def command_issue_grant(args: argparse.Namespace) -> int:
|
||||
parent_store = _parent_store(args)
|
||||
grant_store = _grant_store(args)
|
||||
signer = Ed25519PrivateKeySigner.from_file(args.private_key_file, key_id=args.key_id)
|
||||
grant = GrantIssuer(signer, parent_store, grant_store).issue(
|
||||
parent_provenance_id=args.parent_provenance_id,
|
||||
grant_type=GrantType(args.grant_type),
|
||||
ttl_seconds=args.ttl_seconds,
|
||||
allowed_git_operations=_csv(args.allowed_git_operations),
|
||||
)
|
||||
_write_json(
|
||||
args.output,
|
||||
{
|
||||
"grant": grant.as_dict(),
|
||||
"status": grant_store.status(grant.grant_id).value,
|
||||
"secret_value_stored": False,
|
||||
},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def _single_scope_writer(args: argparse.Namespace) -> ScopedLeastPrivilegeProvenanceWriter:
|
||||
path = ExecutionPath(args.path).value
|
||||
parent_store = _parent_store(args)
|
||||
grant_store = _grant_store(args)
|
||||
verifier = Ed25519PublicKeyVerifier.from_file(args.public_key_file, key_id=args.key_id)
|
||||
trusted = GrantVerifier(parent_store, grant_store, {args.key_id: verifier})
|
||||
return ScopedLeastPrivilegeProvenanceWriter(
|
||||
trusted,
|
||||
args.receipt_dir,
|
||||
{path: args.grant_id},
|
||||
required_paths=(path,),
|
||||
writer_id=f"aios-v2-cli-{path}",
|
||||
)
|
||||
|
||||
|
||||
def command_authorize(args: argparse.Namespace) -> int:
|
||||
writer = _single_scope_writer(args)
|
||||
context = _context(args)
|
||||
receipt = ProvenanceOperationGate(writer).authorize(
|
||||
context,
|
||||
execution_path=args.path,
|
||||
operation=args.operation,
|
||||
request=_json_object(args.request_json, args.request_file),
|
||||
)
|
||||
_write_json(args.output, {"authorization": receipt.as_dict()})
|
||||
return 0
|
||||
|
||||
|
||||
def command_revoke(args: argparse.Namespace) -> int:
|
||||
store = _parent_store(args)
|
||||
store.revoke(args.provenance_id, reason=args.reason, principal_id=args.principal_id)
|
||||
_write_json(
|
||||
args.output,
|
||||
{"provenance_id": args.provenance_id, "status": store.status(args.provenance_id).value},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def command_status(args: argparse.Namespace) -> int:
|
||||
store = _parent_store(args)
|
||||
provenance = store.get(args.provenance_id)
|
||||
grant_store = _grant_store(args)
|
||||
_write_json(
|
||||
args.output,
|
||||
{
|
||||
"provenance": provenance.as_dict(),
|
||||
"status": store.status(args.provenance_id).value,
|
||||
"authorization_count": store.authorization_count(args.provenance_id),
|
||||
"events": store.events(args.provenance_id),
|
||||
"grants": [item.as_dict() for item in grant_store.list_for_parent(args.provenance_id)],
|
||||
},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def command_grant_revoke(args: argparse.Namespace) -> int:
|
||||
store = _grant_store(args)
|
||||
store.revoke(args.grant_id, reason=args.reason, principal_id=args.principal_id)
|
||||
_write_json(
|
||||
args.output,
|
||||
{"grant_id": args.grant_id, "status": store.status(args.grant_id).value},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def command_grant_status(args: argparse.Namespace) -> int:
|
||||
store = _grant_store(args)
|
||||
grant = store.get(args.grant_id)
|
||||
_write_json(
|
||||
args.output,
|
||||
{"grant": grant.as_dict(), "status": store.status(args.grant_id).value},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def add_common_store(parser: argparse.ArgumentParser) -> None:
|
||||
parser.add_argument(
|
||||
"--store-file",
|
||||
default=os.getenv(
|
||||
"AIOS_PROVENANCE_STORE_FILE",
|
||||
"/var/lib/aios-v2/run-provenance.sqlite3",
|
||||
),
|
||||
)
|
||||
parser.add_argument("--output", default=None)
|
||||
|
||||
|
||||
def add_signing_context(parser: argparse.ArgumentParser) -> None:
|
||||
parser.add_argument("--private-key-file", required=True)
|
||||
parser.add_argument("--key-id", required=True)
|
||||
|
||||
|
||||
def add_workflow_identity(parser: argparse.ArgumentParser) -> None:
|
||||
parser.add_argument("--run-id", required=True)
|
||||
parser.add_argument("--issuer", required=True)
|
||||
parser.add_argument("--tenant-id", required=True)
|
||||
parser.add_argument("--task-id", required=True)
|
||||
parser.add_argument("--agent-id", required=True)
|
||||
parser.add_argument("--principal-id", required=True)
|
||||
|
||||
|
||||
def add_context(parser: argparse.ArgumentParser) -> None:
|
||||
parser.add_argument("--context-from-env", action="store_true")
|
||||
parser.add_argument("--provenance-id")
|
||||
parser.add_argument("--run-id")
|
||||
parser.add_argument("--tenant-id")
|
||||
parser.add_argument("--task-id")
|
||||
parser.add_argument("--agent-id")
|
||||
parser.add_argument("--principal-id")
|
||||
|
||||
|
||||
def build_parser() -> argparse.ArgumentParser:
|
||||
parser = argparse.ArgumentParser(description="AIOS V2 Run Provenance CLI")
|
||||
subcommands = parser.add_subparsers(dest="command", required=True)
|
||||
|
||||
issue = subcommands.add_parser("issue", help="候选兼容:签发全权限 Provenance;生产禁止")
|
||||
add_common_store(issue)
|
||||
add_signing_context(issue)
|
||||
add_workflow_identity(issue)
|
||||
issue.add_argument("--allowed-paths")
|
||||
issue.add_argument("--allowed-git-operations")
|
||||
issue.add_argument("--ttl-seconds", type=int, default=3600)
|
||||
issue.add_argument("--policy-version", default="aios.v2.candidate.legacy")
|
||||
issue.set_defaults(handler=command_issue_legacy)
|
||||
|
||||
workflow = subcommands.add_parser(
|
||||
"issue-workflow", help="签发不含操作权限的父 Workflow Provenance"
|
||||
)
|
||||
add_common_store(workflow)
|
||||
add_signing_context(workflow)
|
||||
add_workflow_identity(workflow)
|
||||
workflow.add_argument("--ttl-seconds", type=int, default=14400)
|
||||
workflow.set_defaults(handler=command_issue_workflow)
|
||||
|
||||
grant = subcommands.add_parser("issue-grant", help="签发单一路径最小权限 Grant")
|
||||
add_common_store(grant)
|
||||
add_signing_context(grant)
|
||||
grant.add_argument("--parent-provenance-id", required=True)
|
||||
grant.add_argument("--grant-type", choices=[item.value for item in GrantType], required=True)
|
||||
grant.add_argument("--allowed-git-operations")
|
||||
grant.add_argument("--ttl-seconds", type=int, default=900)
|
||||
grant.set_defaults(handler=command_issue_grant)
|
||||
|
||||
authorize = subcommands.add_parser("authorize", help="使用单一子 Grant 授权一次运维操作")
|
||||
add_common_store(authorize)
|
||||
add_context(authorize)
|
||||
authorize.add_argument("--public-key-file", required=True)
|
||||
authorize.add_argument("--key-id", required=True)
|
||||
authorize.add_argument("--grant-id", required=True)
|
||||
authorize.add_argument(
|
||||
"--receipt-dir",
|
||||
default=os.getenv(
|
||||
"AIOS_PROVENANCE_RECEIPT_DIR",
|
||||
"/var/lib/aios-v2/provenance-receipts",
|
||||
),
|
||||
)
|
||||
authorize.add_argument(
|
||||
"--path",
|
||||
required=True,
|
||||
choices=[
|
||||
ExecutionPath.CODE_CHANGE.value,
|
||||
ExecutionPath.DEPLOYMENT.value,
|
||||
ExecutionPath.RUNTIME_EXECUTE.value,
|
||||
ExecutionPath.EVIDENCE_WRITE.value,
|
||||
ExecutionPath.ROLLBACK.value,
|
||||
ExecutionPath.AUDIT.value,
|
||||
],
|
||||
)
|
||||
authorize.add_argument("--operation", required=True)
|
||||
request_group = authorize.add_mutually_exclusive_group()
|
||||
request_group.add_argument("--request-json")
|
||||
request_group.add_argument("--request-file")
|
||||
authorize.set_defaults(handler=command_authorize)
|
||||
|
||||
revoke = subcommands.add_parser("revoke", help="撤销父 Workflow Provenance")
|
||||
add_common_store(revoke)
|
||||
revoke.add_argument("--provenance-id", required=True)
|
||||
revoke.add_argument("--reason", required=True)
|
||||
revoke.add_argument("--principal-id", required=True)
|
||||
revoke.set_defaults(handler=command_revoke)
|
||||
|
||||
status = subcommands.add_parser("status", help="查询父 Workflow 与子 Grant")
|
||||
add_common_store(status)
|
||||
status.add_argument("--provenance-id", required=True)
|
||||
status.set_defaults(handler=command_status)
|
||||
|
||||
grant_revoke = subcommands.add_parser("grant-revoke", help="单独撤销子 Grant")
|
||||
add_common_store(grant_revoke)
|
||||
grant_revoke.add_argument("--grant-id", required=True)
|
||||
grant_revoke.add_argument("--reason", required=True)
|
||||
grant_revoke.add_argument("--principal-id", required=True)
|
||||
grant_revoke.set_defaults(handler=command_grant_revoke)
|
||||
|
||||
grant_status = subcommands.add_parser("grant-status", help="查询子 Grant 状态")
|
||||
add_common_store(grant_status)
|
||||
grant_status.add_argument("--grant-id", required=True)
|
||||
grant_status.set_defaults(handler=command_grant_status)
|
||||
return parser
|
||||
|
||||
|
||||
def main(argv: Sequence[str] | None = None) -> int:
|
||||
args = build_parser().parse_args(argv)
|
||||
try:
|
||||
return int(args.handler(args))
|
||||
except Exception as exc:
|
||||
print(
|
||||
json.dumps(
|
||||
{"status": "denied", "error": type(exc).__name__, "message": str(exc)},
|
||||
ensure_ascii=False,
|
||||
),
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,416 @@
|
||||
"""受最小权限 Run Provenance Grant 约束的 Git 写入器。
|
||||
|
||||
所有 Git 操作都使用参数数组执行。对于 Commit 和 Evidence Commit,先计算
|
||||
工作树内容摘要并完成 Provenance 授权,之后才允许执行 ``git add``,避免未授权
|
||||
请求改变 Git Index。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
import uuid
|
||||
from dataclasses import asdict, dataclass
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Protocol, Sequence
|
||||
|
||||
from .provenance import GitOperation, ProvenanceDenied, digest_payload, utc_now
|
||||
|
||||
_BRANCH_PATTERN = re.compile(r"^(?![-./])(?!.*\.\.)(?!.*//)[A-Za-z0-9._/-]{1,240}$")
|
||||
_SECRET_URL = re.compile(r"(?i)(https?://)([^/@\s]+)@")
|
||||
_TOKENISH = re.compile(r"(?i)(token|password|secret|authorization)([=:]\s*)([^\s]+)")
|
||||
|
||||
|
||||
class GitAuthorizationWriter(Protocol):
|
||||
def authorize_code_change(self, **values: Any) -> Any: ...
|
||||
|
||||
def authorize_git_operation(self, *, git_operation: str, **values: Any) -> Any: ...
|
||||
|
||||
|
||||
class ProvenanceGitError(RuntimeError):
|
||||
"""Git 操作被拒绝或执行失败。"""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GitExecutionContext:
|
||||
provenance_id: str
|
||||
run_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GitCommandResult:
|
||||
operation_id: str
|
||||
operation: str
|
||||
authorization_ids: Sequence[str]
|
||||
command: Sequence[str]
|
||||
exit_code: int
|
||||
stdout: str
|
||||
stderr: str
|
||||
head_before: str | None
|
||||
head_after: str | None
|
||||
started_at: str
|
||||
completed_at: str
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class ProvenanceGitWriter:
|
||||
"""执行经过单路径 Grant 授权的窄范围 Git 操作。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
repo: str | Path,
|
||||
writer: GitAuthorizationWriter,
|
||||
*,
|
||||
timeout_seconds: float = 120.0,
|
||||
output_limit: int = 16000,
|
||||
) -> None:
|
||||
self.repo = Path(repo).resolve()
|
||||
self.writer = writer
|
||||
self.timeout_seconds = float(timeout_seconds)
|
||||
self.output_limit = int(output_limit)
|
||||
if self.timeout_seconds <= 0 or self.output_limit < 1024:
|
||||
raise ValueError("invalid Git writer limits")
|
||||
self._run_raw(["rev-parse", "--is-inside-work-tree"], check=True)
|
||||
|
||||
@staticmethod
|
||||
def _validate_branch(branch: str) -> str:
|
||||
normalized = str(branch or "").strip()
|
||||
if not _BRANCH_PATTERN.fullmatch(normalized) or normalized.endswith((".", "/")):
|
||||
raise ProvenanceGitError("invalid Git branch name")
|
||||
if normalized in {"main", "master"}:
|
||||
raise ProvenanceGitError("direct main/master operation is prohibited")
|
||||
return normalized
|
||||
|
||||
def _validate_path(self, value: str | Path) -> str:
|
||||
raw = Path(value)
|
||||
candidate = (self.repo / raw).resolve() if not raw.is_absolute() else raw.resolve()
|
||||
try:
|
||||
relative = candidate.relative_to(self.repo)
|
||||
except ValueError as exc:
|
||||
raise ProvenanceGitError("Git path escapes repository") from exc
|
||||
if str(relative) in {"", "."}:
|
||||
raise ProvenanceGitError("repository root is not a valid file path")
|
||||
return relative.as_posix()
|
||||
|
||||
@staticmethod
|
||||
def _redact(value: str, limit: int) -> str:
|
||||
text = _SECRET_URL.sub(r"\1***@", str(value or ""))
|
||||
text = _TOKENISH.sub(r"\1\2***", text)
|
||||
if len(text) > limit:
|
||||
return text[:limit] + "\n...[truncated]"
|
||||
return text
|
||||
|
||||
def _head(self) -> str | None:
|
||||
process = self._run_raw(["rev-parse", "HEAD"], check=False)
|
||||
return process.stdout.strip() if process.returncode == 0 else None
|
||||
|
||||
def _run_raw(
|
||||
self,
|
||||
args: Sequence[str],
|
||||
*,
|
||||
check: bool,
|
||||
env: Mapping[str, str] | None = None,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
command = ["git", "-C", str(self.repo), *[str(item) for item in args]]
|
||||
safe_env = {
|
||||
**os.environ,
|
||||
"GIT_TERMINAL_PROMPT": "0",
|
||||
"GIT_CONFIG_NOSYSTEM": os.environ.get("GIT_CONFIG_NOSYSTEM", "1"),
|
||||
}
|
||||
if env:
|
||||
safe_env.update({str(key): str(value) for key, value in env.items()})
|
||||
process = subprocess.run(
|
||||
command,
|
||||
text=True,
|
||||
capture_output=True,
|
||||
timeout=self.timeout_seconds,
|
||||
env=safe_env,
|
||||
)
|
||||
if check and process.returncode != 0:
|
||||
raise ProvenanceGitError(
|
||||
self._redact(process.stderr or process.stdout, self.output_limit)
|
||||
or f"Git command failed with exit code {process.returncode}"
|
||||
)
|
||||
return process
|
||||
|
||||
def _path_digest(self, relative: str) -> str:
|
||||
target = self.repo / relative
|
||||
if target.exists():
|
||||
if not target.is_file():
|
||||
raise ProvenanceGitError("Git writer accepts file paths only")
|
||||
hasher = hashlib.sha256()
|
||||
with target.open("rb") as handle:
|
||||
while True:
|
||||
block = handle.read(65536)
|
||||
if not block:
|
||||
break
|
||||
hasher.update(block)
|
||||
return hasher.hexdigest()
|
||||
tracked = self._run_raw(["ls-files", "--error-unmatch", "--", relative], check=False)
|
||||
if tracked.returncode != 0:
|
||||
raise ProvenanceGitError(f"path does not exist and is not tracked: {relative}")
|
||||
return "deleted"
|
||||
|
||||
def _content_manifest(self, paths: Sequence[str]) -> Mapping[str, str]:
|
||||
return {path: self._path_digest(path) for path in sorted(set(paths))}
|
||||
|
||||
def _authorize(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
operation: GitOperation,
|
||||
request: Mapping[str, Any],
|
||||
code_change: bool,
|
||||
) -> list[str]:
|
||||
request_digest = digest_payload(
|
||||
{
|
||||
"operation": operation.value,
|
||||
"repo": self.repo.name,
|
||||
"request": dict(request),
|
||||
"head": self._head(),
|
||||
}
|
||||
)
|
||||
ids: list[str] = []
|
||||
try:
|
||||
if code_change:
|
||||
code_authorization = self.writer.authorize_code_change(
|
||||
provenance_id=context.provenance_id,
|
||||
run_id=context.run_id,
|
||||
tenant_id=context.tenant_id,
|
||||
task_id=context.task_id,
|
||||
agent_id=context.agent_id,
|
||||
principal_id=context.principal_id,
|
||||
request_digest=digest_payload(
|
||||
{
|
||||
"git_operation": operation.value,
|
||||
"request_digest": request_digest,
|
||||
}
|
||||
),
|
||||
)
|
||||
ids.append(code_authorization.authorization_id)
|
||||
git_authorization = self.writer.authorize_git_operation(
|
||||
provenance_id=context.provenance_id,
|
||||
run_id=context.run_id,
|
||||
tenant_id=context.tenant_id,
|
||||
task_id=context.task_id,
|
||||
agent_id=context.agent_id,
|
||||
principal_id=context.principal_id,
|
||||
git_operation=operation.value,
|
||||
request_digest=request_digest,
|
||||
)
|
||||
ids.append(git_authorization.authorization_id)
|
||||
return ids
|
||||
except ProvenanceDenied as exc:
|
||||
raise ProvenanceGitError(f"Run Provenance denied Git operation: {exc}") from exc
|
||||
|
||||
def _run_authorized(
|
||||
self,
|
||||
*,
|
||||
operation: GitOperation,
|
||||
args: Sequence[str],
|
||||
authorization_ids: Sequence[str],
|
||||
) -> GitCommandResult:
|
||||
started = utc_now()
|
||||
before = self._head()
|
||||
process = self._run_raw(args, check=False)
|
||||
after = self._head()
|
||||
result = GitCommandResult(
|
||||
operation_id=f"gitop_{uuid.uuid4().hex}",
|
||||
operation=operation.value,
|
||||
authorization_ids=tuple(authorization_ids),
|
||||
command=tuple(["git", "-C", "<repo>", *[str(item) for item in args]]),
|
||||
exit_code=int(process.returncode),
|
||||
stdout=self._redact(process.stdout, self.output_limit),
|
||||
stderr=self._redact(process.stderr, self.output_limit),
|
||||
head_before=before,
|
||||
head_after=after,
|
||||
started_at=started,
|
||||
completed_at=utc_now(),
|
||||
)
|
||||
if process.returncode != 0:
|
||||
raise ProvenanceGitError(
|
||||
result.stderr or result.stdout or f"Git {operation.value} failed"
|
||||
)
|
||||
return result
|
||||
|
||||
def _execute(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
operation: GitOperation,
|
||||
args: Sequence[str],
|
||||
request: Mapping[str, Any],
|
||||
code_change: bool,
|
||||
) -> GitCommandResult:
|
||||
authorization_ids = self._authorize(
|
||||
context,
|
||||
operation=operation,
|
||||
request=request,
|
||||
code_change=code_change,
|
||||
)
|
||||
return self._run_authorized(
|
||||
operation=operation,
|
||||
args=args,
|
||||
authorization_ids=authorization_ids,
|
||||
)
|
||||
|
||||
def read_ref(self, context: GitExecutionContext, ref: str) -> GitCommandResult:
|
||||
normalized = str(ref or "").strip()
|
||||
if not normalized or any(ch.isspace() for ch in normalized):
|
||||
raise ProvenanceGitError("invalid Git ref")
|
||||
return self._execute(
|
||||
context,
|
||||
operation=GitOperation.READ_REF,
|
||||
args=["rev-parse", "--verify", normalized],
|
||||
request={"ref": normalized},
|
||||
code_change=False,
|
||||
)
|
||||
|
||||
def fetch(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
remote: str,
|
||||
refspecs: Sequence[str],
|
||||
) -> GitCommandResult:
|
||||
normalized_remote = str(remote or "").strip()
|
||||
normalized_refspecs = tuple(str(item).strip() for item in refspecs if str(item).strip())
|
||||
if not normalized_remote or not normalized_refspecs:
|
||||
raise ProvenanceGitError("remote and refspecs are required")
|
||||
if any(item.startswith("+") and ":refs/heads/" in item for item in normalized_refspecs):
|
||||
raise ProvenanceGitError(
|
||||
"fetching directly into local branch refs is prohibited; use remote-tracking refs"
|
||||
)
|
||||
return self._execute(
|
||||
context,
|
||||
operation=GitOperation.FETCH,
|
||||
args=["fetch", "--prune", normalized_remote, *normalized_refspecs],
|
||||
request={"remote": normalized_remote, "refspecs": normalized_refspecs},
|
||||
code_change=False,
|
||||
)
|
||||
|
||||
def create_branch(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
branch: str,
|
||||
start_point: str,
|
||||
) -> GitCommandResult:
|
||||
normalized = self._validate_branch(branch)
|
||||
start = str(start_point or "").strip()
|
||||
if not start:
|
||||
raise ProvenanceGitError("start_point is required")
|
||||
return self._execute(
|
||||
context,
|
||||
operation=GitOperation.CREATE_BRANCH,
|
||||
args=["branch", normalized, start],
|
||||
request={"branch": normalized, "start_point": start},
|
||||
code_change=False,
|
||||
)
|
||||
|
||||
def commit(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
paths: Sequence[str | Path],
|
||||
message: str,
|
||||
) -> GitCommandResult:
|
||||
normalized_paths = tuple(self._validate_path(item) for item in paths)
|
||||
normalized_message = str(message or "").strip()
|
||||
if not normalized_paths or not normalized_message:
|
||||
raise ProvenanceGitError("commit paths and message are required")
|
||||
if len(normalized_message) > 500:
|
||||
raise ProvenanceGitError("commit message is too long")
|
||||
request = {
|
||||
"paths": normalized_paths,
|
||||
"message": normalized_message,
|
||||
"content_manifest": self._content_manifest(normalized_paths),
|
||||
}
|
||||
authorization_ids = self._authorize(
|
||||
context,
|
||||
operation=GitOperation.COMMIT,
|
||||
request=request,
|
||||
code_change=True,
|
||||
)
|
||||
self._run_raw(["add", "--", *normalized_paths], check=True)
|
||||
return self._run_authorized(
|
||||
operation=GitOperation.COMMIT,
|
||||
args=["commit", "--no-gpg-sign", "-m", normalized_message, "--", *normalized_paths],
|
||||
authorization_ids=authorization_ids,
|
||||
)
|
||||
|
||||
def merge(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
source_ref: str,
|
||||
message: str,
|
||||
) -> GitCommandResult:
|
||||
source = str(source_ref or "").strip()
|
||||
normalized_message = str(message or "").strip()
|
||||
if not source or not normalized_message:
|
||||
raise ProvenanceGitError("source_ref and message are required")
|
||||
return self._execute(
|
||||
context,
|
||||
operation=GitOperation.MERGE,
|
||||
args=["merge", "--no-ff", "--no-edit", "-m", normalized_message, source],
|
||||
request={"source_ref": source, "message": normalized_message},
|
||||
code_change=True,
|
||||
)
|
||||
|
||||
def push(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
remote: str,
|
||||
branch: str,
|
||||
) -> GitCommandResult:
|
||||
normalized_remote = str(remote or "").strip()
|
||||
normalized_branch = self._validate_branch(branch)
|
||||
if not normalized_remote:
|
||||
raise ProvenanceGitError("remote is required")
|
||||
return self._execute(
|
||||
context,
|
||||
operation=GitOperation.PUSH,
|
||||
args=["push", normalized_remote, f"refs/heads/{normalized_branch}:refs/heads/{normalized_branch}"],
|
||||
request={"remote": normalized_remote, "branch": normalized_branch},
|
||||
code_change=False,
|
||||
)
|
||||
|
||||
def update_evidence(
|
||||
self,
|
||||
context: GitExecutionContext,
|
||||
*,
|
||||
paths: Sequence[str | Path],
|
||||
message: str,
|
||||
) -> GitCommandResult:
|
||||
normalized_paths = tuple(self._validate_path(item) for item in paths)
|
||||
normalized_message = str(message or "").strip()
|
||||
if not normalized_paths or not normalized_message:
|
||||
raise ProvenanceGitError("evidence paths and message are required")
|
||||
if any(not path.startswith(".agent/") for path in normalized_paths):
|
||||
raise ProvenanceGitError("UPDATE_EVIDENCE may only commit .agent/ paths")
|
||||
request = {
|
||||
"paths": normalized_paths,
|
||||
"message": normalized_message,
|
||||
"content_manifest": self._content_manifest(normalized_paths),
|
||||
}
|
||||
authorization_ids = self._authorize(
|
||||
context,
|
||||
operation=GitOperation.UPDATE_EVIDENCE,
|
||||
request=request,
|
||||
code_change=False,
|
||||
)
|
||||
self._run_raw(["add", "--", *normalized_paths], check=True)
|
||||
return self._run_authorized(
|
||||
operation=GitOperation.UPDATE_EVIDENCE,
|
||||
args=["commit", "--no-gpg-sign", "-m", normalized_message, "--", *normalized_paths],
|
||||
authorization_ids=authorization_ids,
|
||||
)
|
||||
@@ -0,0 +1,744 @@
|
||||
"""AIOS V2 最小权限 Run Provenance 子 Grant。
|
||||
|
||||
父 Workflow Provenance 只绑定 run/tenant/task/agent/principal 身份,不直接授予
|
||||
操作权限。每个子 Grant 只允许一个 ExecutionPath;Git Grant 还必须限定具体
|
||||
GitOperation。子 Grant 具备独立 TTL、nonce、状态、撤销和重放防护。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import sqlite3
|
||||
import threading
|
||||
import uuid
|
||||
from dataclasses import asdict, dataclass, field, replace
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
from .provenance import (
|
||||
ExecutionPath,
|
||||
GitOperation,
|
||||
ProvenanceDenied,
|
||||
ProvenanceExpired,
|
||||
ProvenanceIssuer,
|
||||
ProvenanceNotFound,
|
||||
ProvenanceReplay,
|
||||
ProvenanceRevoked,
|
||||
ProvenanceSignatureError,
|
||||
ProvenanceStatus,
|
||||
ProvenanceVerifier,
|
||||
RunProvenance,
|
||||
SQLiteProvenanceStore,
|
||||
Signer,
|
||||
SignatureVerifier,
|
||||
_validate_digest,
|
||||
canonical_json_bytes,
|
||||
parse_timestamp,
|
||||
required,
|
||||
utc_now,
|
||||
)
|
||||
|
||||
WORKFLOW_POLICY_VERSION = "aios.v2.workflow.v1"
|
||||
GRANT_SCHEMA_VERSION = "aios.v2.provenance-grant.v1"
|
||||
|
||||
|
||||
class GrantType(str, Enum):
|
||||
CODE_CHANGE = "code_change"
|
||||
GIT = "git"
|
||||
DEPLOYMENT = "deployment"
|
||||
RUNTIME = "runtime"
|
||||
EVIDENCE = "evidence"
|
||||
ROLLBACK = "rollback"
|
||||
AUDIT = "audit"
|
||||
|
||||
|
||||
GRANT_PATHS: Mapping[GrantType, ExecutionPath] = {
|
||||
GrantType.CODE_CHANGE: ExecutionPath.CODE_CHANGE,
|
||||
GrantType.GIT: ExecutionPath.GIT_OPERATION,
|
||||
GrantType.DEPLOYMENT: ExecutionPath.DEPLOYMENT,
|
||||
GrantType.RUNTIME: ExecutionPath.RUNTIME_EXECUTE,
|
||||
GrantType.EVIDENCE: ExecutionPath.EVIDENCE_WRITE,
|
||||
GrantType.ROLLBACK: ExecutionPath.ROLLBACK,
|
||||
GrantType.AUDIT: ExecutionPath.AUDIT,
|
||||
}
|
||||
|
||||
|
||||
class GrantStatus(str, Enum):
|
||||
ISSUED = "issued"
|
||||
VERIFIED = "verified"
|
||||
USED = "used"
|
||||
EXPIRED = "expired"
|
||||
REVOKED = "revoked"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProvenanceGrant:
|
||||
grant_id: str
|
||||
parent_provenance_id: str
|
||||
grant_type: GrantType
|
||||
execution_path: ExecutionPath
|
||||
run_id: str
|
||||
issuer: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
allowed_git_operations: Sequence[str]
|
||||
issued_at: str
|
||||
expires_at: str
|
||||
policy_version: str
|
||||
key_id: str
|
||||
nonce: str
|
||||
signature: str = ""
|
||||
schema_version: str = GRANT_SCHEMA_VERSION
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in (
|
||||
"grant_id",
|
||||
"parent_provenance_id",
|
||||
"run_id",
|
||||
"issuer",
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"agent_id",
|
||||
"principal_id",
|
||||
"issued_at",
|
||||
"expires_at",
|
||||
"policy_version",
|
||||
"key_id",
|
||||
"nonce",
|
||||
"schema_version",
|
||||
):
|
||||
object.__setattr__(self, name, required(getattr(self, name), name))
|
||||
if self.schema_version != GRANT_SCHEMA_VERSION:
|
||||
raise ValueError(f"unsupported grant schema: {self.schema_version}")
|
||||
grant_type = GrantType(self.grant_type)
|
||||
path = ExecutionPath(self.execution_path)
|
||||
if GRANT_PATHS[grant_type] != path:
|
||||
raise ValueError("grant_type does not match execution_path")
|
||||
object.__setattr__(self, "grant_type", grant_type)
|
||||
object.__setattr__(self, "execution_path", path)
|
||||
operations = tuple(
|
||||
sorted({GitOperation(item).value for item in self.allowed_git_operations})
|
||||
)
|
||||
if grant_type == GrantType.GIT and not operations:
|
||||
raise ValueError("Git Grant requires explicit Git operations")
|
||||
if grant_type != GrantType.GIT and operations:
|
||||
raise ValueError("only Git Grant may contain Git operations")
|
||||
object.__setattr__(self, "allowed_git_operations", operations)
|
||||
issued = parse_timestamp(self.issued_at)
|
||||
expires = parse_timestamp(self.expires_at)
|
||||
if expires <= issued:
|
||||
raise ValueError("grant expires_at must be later than issued_at")
|
||||
object.__setattr__(self, "signature", str(self.signature or "").strip())
|
||||
|
||||
def unsigned_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"schema_version": self.schema_version,
|
||||
"grant_id": self.grant_id,
|
||||
"parent_provenance_id": self.parent_provenance_id,
|
||||
"grant_type": self.grant_type.value,
|
||||
"execution_path": self.execution_path.value,
|
||||
"run_id": self.run_id,
|
||||
"issuer": self.issuer,
|
||||
"tenant_id": self.tenant_id,
|
||||
"task_id": self.task_id,
|
||||
"agent_id": self.agent_id,
|
||||
"principal_id": self.principal_id,
|
||||
"allowed_git_operations": list(self.allowed_git_operations),
|
||||
"issued_at": self.issued_at,
|
||||
"expires_at": self.expires_at,
|
||||
"policy_version": self.policy_version,
|
||||
"key_id": self.key_id,
|
||||
"nonce": self.nonce,
|
||||
}
|
||||
|
||||
def canonical_bytes(self) -> bytes:
|
||||
return canonical_json_bytes(self.unsigned_dict())
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
value = self.unsigned_dict()
|
||||
value["signature"] = self.signature
|
||||
return value
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, value: Mapping[str, Any]) -> "ProvenanceGrant":
|
||||
return cls(**dict(value))
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GrantAuthorization:
|
||||
authorization_id: str
|
||||
grant_id: str
|
||||
parent_provenance_id: str
|
||||
run_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
execution_path: str
|
||||
git_operation: str | None
|
||||
request_digest: str
|
||||
policy_version: str
|
||||
key_id: str
|
||||
public_key_fingerprint: str
|
||||
authorized_at: str = field(default_factory=utc_now)
|
||||
|
||||
@property
|
||||
def provenance_id(self) -> str:
|
||||
return self.parent_provenance_id
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class WorkflowProvenanceIssuer:
|
||||
"""签发不携带操作权限的父 Workflow Provenance。"""
|
||||
|
||||
def __init__(self, signer: Signer, store: SQLiteProvenanceStore) -> None:
|
||||
self._issuer = ProvenanceIssuer(signer, store)
|
||||
|
||||
def issue(
|
||||
self,
|
||||
*,
|
||||
run_id: str,
|
||||
issuer: str,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
principal_id: str,
|
||||
ttl_seconds: int = 14400,
|
||||
provenance_id: str | None = None,
|
||||
nonce: str | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> RunProvenance:
|
||||
return self._issuer.issue(
|
||||
run_id=run_id,
|
||||
issuer=issuer,
|
||||
tenant_id=tenant_id,
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
principal_id=principal_id,
|
||||
allowed_paths=(),
|
||||
allowed_git_operations=(),
|
||||
ttl_seconds=ttl_seconds,
|
||||
policy_version=WORKFLOW_POLICY_VERSION,
|
||||
provenance_id=provenance_id,
|
||||
nonce=nonce,
|
||||
now=now,
|
||||
)
|
||||
|
||||
|
||||
class SQLiteGrantStore:
|
||||
"""在 Provenance SQLite 数据库中持久化子 Grant 与使用记录。"""
|
||||
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = Path(path).resolve()
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
self._lock = threading.RLock()
|
||||
self._connection = sqlite3.connect(
|
||||
str(self.path), timeout=30.0, check_same_thread=False
|
||||
)
|
||||
self._connection.row_factory = sqlite3.Row
|
||||
with self._lock:
|
||||
self._connection.execute("PRAGMA journal_mode=WAL")
|
||||
self._connection.execute("PRAGMA synchronous=FULL")
|
||||
self._connection.execute("PRAGMA foreign_keys=ON")
|
||||
self._connection.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS provenance_grants (
|
||||
grant_id TEXT PRIMARY KEY,
|
||||
parent_provenance_id TEXT NOT NULL,
|
||||
grant_type TEXT NOT NULL,
|
||||
execution_path TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
signature_verified INTEGER NOT NULL DEFAULT 0,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_grants_parent
|
||||
ON provenance_grants(parent_provenance_id, grant_type, status);
|
||||
CREATE TABLE IF NOT EXISTS provenance_grant_usage (
|
||||
authorization_id TEXT PRIMARY KEY,
|
||||
grant_id TEXT NOT NULL,
|
||||
execution_path TEXT NOT NULL,
|
||||
git_operation TEXT NOT NULL DEFAULT '',
|
||||
request_digest TEXT NOT NULL,
|
||||
authorized_at TEXT NOT NULL,
|
||||
receipt_json TEXT NOT NULL,
|
||||
UNIQUE(grant_id, execution_path, git_operation, request_digest),
|
||||
FOREIGN KEY(grant_id) REFERENCES provenance_grants(grant_id)
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS provenance_grant_events (
|
||||
event_id TEXT PRIMARY KEY,
|
||||
grant_id TEXT NOT NULL,
|
||||
event_type TEXT NOT NULL,
|
||||
details_json TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
FOREIGN KEY(grant_id) REFERENCES provenance_grants(grant_id)
|
||||
);
|
||||
"""
|
||||
)
|
||||
self._connection.commit()
|
||||
|
||||
def close(self) -> None:
|
||||
with self._lock:
|
||||
self._connection.close()
|
||||
|
||||
def _event(
|
||||
self,
|
||||
grant_id: str,
|
||||
event_type: str,
|
||||
details: Mapping[str, Any] | None = None,
|
||||
) -> None:
|
||||
self._connection.execute(
|
||||
"INSERT INTO provenance_grant_events VALUES (?, ?, ?, ?, ?)",
|
||||
(
|
||||
f"gevt_{uuid.uuid4().hex}",
|
||||
grant_id,
|
||||
event_type,
|
||||
json.dumps(dict(details or {}), ensure_ascii=False, sort_keys=True),
|
||||
utc_now(),
|
||||
),
|
||||
)
|
||||
|
||||
def save_issued(self, grant: ProvenanceGrant) -> None:
|
||||
payload = json.dumps(
|
||||
grant.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
|
||||
)
|
||||
now = utc_now()
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
self._connection.execute(
|
||||
"INSERT INTO provenance_grants VALUES (?, ?, ?, ?, ?, ?, 0, ?, ?)",
|
||||
(
|
||||
grant.grant_id,
|
||||
grant.parent_provenance_id,
|
||||
grant.grant_type.value,
|
||||
grant.execution_path.value,
|
||||
payload,
|
||||
GrantStatus.ISSUED.value,
|
||||
now,
|
||||
now,
|
||||
),
|
||||
)
|
||||
self._event(grant.grant_id, "issued")
|
||||
self._connection.commit()
|
||||
except sqlite3.IntegrityError as exc:
|
||||
self._connection.rollback()
|
||||
raise ProvenanceDenied("grant_id already exists") from exc
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def get(self, grant_id: str) -> ProvenanceGrant:
|
||||
with self._lock:
|
||||
row = self._connection.execute(
|
||||
"SELECT payload_json FROM provenance_grants WHERE grant_id = ?",
|
||||
(required(grant_id, "grant_id"),),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise ProvenanceNotFound("provenance grant not found")
|
||||
value = json.loads(row["payload_json"])
|
||||
if not isinstance(value, Mapping):
|
||||
raise ProvenanceDenied("stored grant is invalid")
|
||||
return ProvenanceGrant.from_dict(value)
|
||||
|
||||
def status(self, grant_id: str) -> GrantStatus:
|
||||
with self._lock:
|
||||
row = self._connection.execute(
|
||||
"SELECT status FROM provenance_grants WHERE grant_id = ?",
|
||||
(required(grant_id, "grant_id"),),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise ProvenanceNotFound("provenance grant not found")
|
||||
return GrantStatus(row["status"])
|
||||
|
||||
def mark_verified(self, grant_id: str, *, fingerprint: str) -> None:
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
current = self.status(grant_id)
|
||||
if current in {GrantStatus.REVOKED, GrantStatus.EXPIRED}:
|
||||
raise ProvenanceDenied(f"cannot verify grant in state {current.value}")
|
||||
next_status = (
|
||||
GrantStatus.USED.value
|
||||
if current == GrantStatus.USED
|
||||
else GrantStatus.VERIFIED.value
|
||||
)
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_grants SET status = ?, signature_verified = 1, updated_at = ? WHERE grant_id = ?",
|
||||
(next_status, utc_now(), grant_id),
|
||||
)
|
||||
self._event(
|
||||
grant_id,
|
||||
"verified",
|
||||
{"public_key_fingerprint": fingerprint},
|
||||
)
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def mark_expired(self, grant_id: str) -> None:
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
if self.status(grant_id) == GrantStatus.REVOKED:
|
||||
self._connection.rollback()
|
||||
return
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_grants SET status = ?, updated_at = ? WHERE grant_id = ?",
|
||||
(GrantStatus.EXPIRED.value, utc_now(), grant_id),
|
||||
)
|
||||
self._event(grant_id, "expired")
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def revoke(self, grant_id: str, *, reason: str, principal_id: str) -> None:
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
self.get(grant_id)
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_grants SET status = ?, updated_at = ? WHERE grant_id = ?",
|
||||
(GrantStatus.REVOKED.value, utc_now(), grant_id),
|
||||
)
|
||||
self._event(
|
||||
grant_id,
|
||||
"revoked",
|
||||
{
|
||||
"reason": required(reason, "reason"),
|
||||
"principal_id": required(principal_id, "principal_id"),
|
||||
},
|
||||
)
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def record_authorization(self, authorization: GrantAuthorization) -> None:
|
||||
receipt = json.dumps(
|
||||
authorization.as_dict(), ensure_ascii=False, sort_keys=True, separators=(",", ":")
|
||||
)
|
||||
with self._lock:
|
||||
self._connection.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
current = self.status(authorization.grant_id)
|
||||
if current in {GrantStatus.REVOKED, GrantStatus.EXPIRED}:
|
||||
raise ProvenanceDenied(f"grant state is {current.value}")
|
||||
try:
|
||||
self._connection.execute(
|
||||
"INSERT INTO provenance_grant_usage VALUES (?, ?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
authorization.authorization_id,
|
||||
authorization.grant_id,
|
||||
authorization.execution_path,
|
||||
authorization.git_operation or "",
|
||||
authorization.request_digest,
|
||||
authorization.authorized_at,
|
||||
receipt,
|
||||
),
|
||||
)
|
||||
except sqlite3.IntegrityError as exc:
|
||||
raise ProvenanceReplay(
|
||||
"identical grant path/operation/request digest already used"
|
||||
) from exc
|
||||
self._connection.execute(
|
||||
"UPDATE provenance_grants SET status = ?, updated_at = ? WHERE grant_id = ?",
|
||||
(GrantStatus.USED.value, authorization.authorized_at, authorization.grant_id),
|
||||
)
|
||||
self._event(
|
||||
authorization.grant_id,
|
||||
"used",
|
||||
{
|
||||
"authorization_id": authorization.authorization_id,
|
||||
"execution_path": authorization.execution_path,
|
||||
"git_operation": authorization.git_operation,
|
||||
"request_digest": authorization.request_digest,
|
||||
},
|
||||
)
|
||||
self._connection.commit()
|
||||
except Exception:
|
||||
self._connection.rollback()
|
||||
raise
|
||||
|
||||
def list_for_parent(self, parent_provenance_id: str) -> list[ProvenanceGrant]:
|
||||
with self._lock:
|
||||
rows = self._connection.execute(
|
||||
"SELECT payload_json FROM provenance_grants WHERE parent_provenance_id = ? ORDER BY grant_type, grant_id",
|
||||
(required(parent_provenance_id, "parent_provenance_id"),),
|
||||
).fetchall()
|
||||
return [ProvenanceGrant.from_dict(json.loads(row["payload_json"])) for row in rows]
|
||||
|
||||
|
||||
class GrantIssuer:
|
||||
"""从父 Workflow Provenance 派生单一路径最小权限 Grant。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
signer: Signer,
|
||||
parent_store: SQLiteProvenanceStore,
|
||||
grant_store: SQLiteGrantStore,
|
||||
) -> None:
|
||||
self.signer = signer
|
||||
self.parent_store = parent_store
|
||||
self.grant_store = grant_store
|
||||
|
||||
def issue(
|
||||
self,
|
||||
*,
|
||||
parent_provenance_id: str,
|
||||
grant_type: GrantType | str,
|
||||
ttl_seconds: int = 900,
|
||||
allowed_git_operations: Sequence[str] = (),
|
||||
grant_id: str | None = None,
|
||||
nonce: str | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> ProvenanceGrant:
|
||||
if ttl_seconds <= 0:
|
||||
raise ValueError("grant ttl_seconds must be positive")
|
||||
parent = self.parent_store.get(parent_provenance_id)
|
||||
if parent.policy_version != WORKFLOW_POLICY_VERSION:
|
||||
raise ProvenanceDenied("child grants require a workflow provenance parent")
|
||||
if parent.allowed_paths or parent.allowed_git_operations:
|
||||
raise ProvenanceDenied("workflow provenance parent must not contain operation rights")
|
||||
parent_status = self.parent_store.status(parent.provenance_id)
|
||||
if parent_status == ProvenanceStatus.REVOKED:
|
||||
raise ProvenanceRevoked("workflow provenance is revoked")
|
||||
issued = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
|
||||
parent_expiry = parse_timestamp(parent.expires_at)
|
||||
expires = min(issued + timedelta(seconds=ttl_seconds), parent_expiry)
|
||||
if expires <= issued:
|
||||
raise ProvenanceExpired("workflow provenance has expired")
|
||||
normalized_type = GrantType(grant_type)
|
||||
operations = tuple(allowed_git_operations)
|
||||
unsigned = ProvenanceGrant(
|
||||
grant_id=grant_id or f"grant_{uuid.uuid4().hex}",
|
||||
parent_provenance_id=parent.provenance_id,
|
||||
grant_type=normalized_type,
|
||||
execution_path=GRANT_PATHS[normalized_type],
|
||||
run_id=parent.run_id,
|
||||
issuer=parent.issuer,
|
||||
tenant_id=parent.tenant_id,
|
||||
task_id=parent.task_id,
|
||||
agent_id=parent.agent_id,
|
||||
principal_id=parent.principal_id,
|
||||
allowed_git_operations=operations,
|
||||
issued_at=issued.isoformat().replace("+00:00", "Z"),
|
||||
expires_at=expires.isoformat().replace("+00:00", "Z"),
|
||||
policy_version=f"{WORKFLOW_POLICY_VERSION}.{normalized_type.value}",
|
||||
key_id=self.signer.key_id,
|
||||
nonce=nonce or uuid.uuid4().hex,
|
||||
)
|
||||
signed = replace(unsigned, signature=self.signer.sign(unsigned.canonical_bytes()))
|
||||
self.grant_store.save_issued(signed)
|
||||
return signed
|
||||
|
||||
|
||||
class GrantVerifier:
|
||||
"""验证父 Workflow 与子 Grant,确保单一路径最小权限。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
parent_store: SQLiteProvenanceStore,
|
||||
grant_store: SQLiteGrantStore,
|
||||
verifiers: Mapping[str, SignatureVerifier],
|
||||
) -> None:
|
||||
if not verifiers:
|
||||
raise ValueError("at least one trusted verifier is required")
|
||||
self.parent_store = parent_store
|
||||
self.grant_store = grant_store
|
||||
self.verifiers = {required(key, "key_id"): value for key, value in verifiers.items()}
|
||||
|
||||
def _verify_parent(self, parent: RunProvenance, *, now: datetime) -> SignatureVerifier:
|
||||
status = self.parent_store.status(parent.provenance_id)
|
||||
if status == ProvenanceStatus.REVOKED:
|
||||
raise ProvenanceRevoked("workflow provenance is revoked")
|
||||
if now >= parse_timestamp(parent.expires_at):
|
||||
self.parent_store.mark_expired(parent.provenance_id)
|
||||
raise ProvenanceExpired("workflow provenance is expired")
|
||||
verifier = self.verifiers.get(parent.key_id)
|
||||
if verifier is None or not parent.signature or not verifier.verify(
|
||||
parent.canonical_bytes(), parent.signature
|
||||
):
|
||||
raise ProvenanceSignatureError("invalid workflow provenance signature")
|
||||
if parent.policy_version != WORKFLOW_POLICY_VERSION:
|
||||
raise ProvenanceDenied("parent is not a workflow provenance")
|
||||
if parent.allowed_paths or parent.allowed_git_operations:
|
||||
raise ProvenanceDenied("workflow provenance must not contain operation rights")
|
||||
return verifier
|
||||
|
||||
def authorize(
|
||||
self,
|
||||
*,
|
||||
grant_id: str,
|
||||
parent_provenance_id: str,
|
||||
run_id: str,
|
||||
tenant_id: str,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
principal_id: str,
|
||||
execution_path: str,
|
||||
request_digest: str,
|
||||
git_operation: str | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> GrantAuthorization:
|
||||
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
|
||||
parent = self.parent_store.get(parent_provenance_id)
|
||||
self._verify_parent(parent, now=current)
|
||||
grant = self.grant_store.get(grant_id)
|
||||
grant_status = self.grant_store.status(grant.grant_id)
|
||||
if grant_status == GrantStatus.REVOKED:
|
||||
raise ProvenanceRevoked("provenance grant is revoked")
|
||||
if current >= parse_timestamp(grant.expires_at):
|
||||
self.grant_store.mark_expired(grant.grant_id)
|
||||
raise ProvenanceExpired("provenance grant is expired")
|
||||
verifier = self.verifiers.get(grant.key_id)
|
||||
if verifier is None or not grant.signature or not verifier.verify(
|
||||
grant.canonical_bytes(), grant.signature
|
||||
):
|
||||
raise ProvenanceSignatureError("invalid provenance grant signature")
|
||||
expected = {
|
||||
"parent_provenance_id": parent.provenance_id,
|
||||
"run_id": required(run_id, "run_id"),
|
||||
"tenant_id": required(tenant_id, "tenant_id"),
|
||||
"task_id": required(task_id, "task_id"),
|
||||
"agent_id": required(agent_id, "agent_id"),
|
||||
"principal_id": required(principal_id, "principal_id"),
|
||||
}
|
||||
for field_name, expected_value in expected.items():
|
||||
if getattr(grant, field_name) != expected_value:
|
||||
raise ProvenanceDenied(f"grant {field_name} mismatch")
|
||||
if field_name != "parent_provenance_id" and getattr(parent, field_name) != expected_value:
|
||||
raise ProvenanceDenied(f"workflow {field_name} mismatch")
|
||||
path = ExecutionPath(execution_path)
|
||||
if grant.execution_path != path:
|
||||
raise ProvenanceDenied(
|
||||
f"grant permits {grant.execution_path.value}, not {path.value}"
|
||||
)
|
||||
operation: str | None = None
|
||||
if path == ExecutionPath.GIT_OPERATION:
|
||||
if git_operation is None:
|
||||
raise ProvenanceDenied("Git operation is required")
|
||||
operation = GitOperation(git_operation).value
|
||||
if operation not in grant.allowed_git_operations:
|
||||
raise ProvenanceDenied(f"Git operation is not allowed: {operation}")
|
||||
elif git_operation is not None:
|
||||
raise ProvenanceDenied("git_operation is only valid for a Git Grant")
|
||||
digest = _validate_digest(request_digest)
|
||||
self.grant_store.mark_verified(grant.grant_id, fingerprint=verifier.fingerprint)
|
||||
authorization = GrantAuthorization(
|
||||
authorization_id=f"gauth_{uuid.uuid4().hex}",
|
||||
grant_id=grant.grant_id,
|
||||
parent_provenance_id=parent.provenance_id,
|
||||
run_id=grant.run_id,
|
||||
tenant_id=grant.tenant_id,
|
||||
task_id=grant.task_id,
|
||||
agent_id=grant.agent_id,
|
||||
principal_id=grant.principal_id,
|
||||
execution_path=path.value,
|
||||
git_operation=operation,
|
||||
request_digest=digest,
|
||||
policy_version=grant.policy_version,
|
||||
key_id=grant.key_id,
|
||||
public_key_fingerprint=verifier.fingerprint,
|
||||
)
|
||||
self.grant_store.record_authorization(authorization)
|
||||
return authorization
|
||||
|
||||
|
||||
class LeastPrivilegeProvenanceWriter:
|
||||
"""按路径选择独立子 Grant 的生产 Writer。
|
||||
|
||||
``provenance_id`` 参数始终指父 Workflow Provenance;Grant ID 来自受保护
|
||||
配置映射,调用方无法通过请求体临时扩大权限。
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
verifier: GrantVerifier,
|
||||
receipt_root: str | Path,
|
||||
grant_ids: Mapping[str, str],
|
||||
*,
|
||||
writer_id: str = "aios-v2-least-privilege-writer",
|
||||
) -> None:
|
||||
self.verifier = verifier
|
||||
self.receipt_root = Path(receipt_root).resolve()
|
||||
self.receipt_root.mkdir(parents=True, exist_ok=True)
|
||||
self.grant_ids = {
|
||||
ExecutionPath(path).value: required(grant_id, f"grant_id[{path}]")
|
||||
for path, grant_id in grant_ids.items()
|
||||
}
|
||||
missing = sorted(path.value for path in ExecutionPath if path.value not in self.grant_ids)
|
||||
if missing:
|
||||
raise ValueError(f"missing least-privilege Grant mappings: {missing}")
|
||||
self.writer_id = required(writer_id, "writer_id")
|
||||
self._lock = threading.RLock()
|
||||
|
||||
@staticmethod
|
||||
def _component(value: str) -> str:
|
||||
normalized = required(value, "path component")
|
||||
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
|
||||
raise ProvenanceDenied("invalid receipt path component")
|
||||
return normalized
|
||||
|
||||
def authorize(self, **values: Any) -> GrantAuthorization:
|
||||
path = ExecutionPath(values["execution_path"]).value
|
||||
grant_id = self.grant_ids[path]
|
||||
parent_provenance_id = values.pop("provenance_id")
|
||||
authorization = self.verifier.authorize(
|
||||
grant_id=grant_id,
|
||||
parent_provenance_id=parent_provenance_id,
|
||||
**values,
|
||||
)
|
||||
tenant = self._component(authorization.tenant_id)
|
||||
parent = self._component(authorization.parent_provenance_id)
|
||||
grant = self._component(authorization.grant_id)
|
||||
target_dir = self.receipt_root / tenant / parent / grant
|
||||
target = target_dir / f"{authorization.authorization_id}.json"
|
||||
payload = authorization.as_dict()
|
||||
payload["writer_id"] = self.writer_id
|
||||
with self._lock:
|
||||
target_dir.mkdir(parents=True, exist_ok=True)
|
||||
temporary = target.with_suffix(f".tmp-{os.getpid()}")
|
||||
temporary.write_text(
|
||||
json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
os.chmod(temporary, 0o640)
|
||||
os.replace(temporary, target)
|
||||
return authorization
|
||||
|
||||
def authorize_code_change(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.CODE_CHANGE.value, **values)
|
||||
|
||||
def authorize_git_operation(
|
||||
self, *, git_operation: str, **values: Any
|
||||
) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.GIT_OPERATION.value,
|
||||
git_operation=git_operation,
|
||||
**values,
|
||||
)
|
||||
|
||||
def authorize_deployment(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.DEPLOYMENT.value, **values)
|
||||
|
||||
def authorize_runtime_execute(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.RUNTIME_EXECUTE.value, **values)
|
||||
|
||||
def authorize_evidence_write(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.EVIDENCE_WRITE.value, **values)
|
||||
|
||||
def authorize_rollback(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.ROLLBACK.value, **values)
|
||||
|
||||
def authorize_audit(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.AUDIT.value, **values)
|
||||
@@ -0,0 +1,265 @@
|
||||
"""AIOS V2 运维操作 Provenance Gate 与服务级 Scoped Writer 工厂。"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
from dataclasses import asdict, dataclass
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Protocol, Sequence
|
||||
|
||||
from .provenance import (
|
||||
Ed25519PublicKeyVerifier,
|
||||
ExecutionPath,
|
||||
ProvenanceAuthorization,
|
||||
ProvenanceControlledWriter,
|
||||
ProvenanceDenied,
|
||||
ProvenanceVerifier,
|
||||
SQLiteProvenanceStore,
|
||||
digest_payload,
|
||||
)
|
||||
from .provenance_grants import GrantAuthorization, GrantVerifier, SQLiteGrantStore
|
||||
from .provenance_scoped import ScopedLeastPrivilegeProvenanceWriter
|
||||
|
||||
|
||||
APPLICATION_PROVENANCE_SCOPE = (
|
||||
ExecutionPath.RUNTIME_EXECUTE.value,
|
||||
ExecutionPath.EVIDENCE_WRITE.value,
|
||||
ExecutionPath.AUDIT.value,
|
||||
)
|
||||
|
||||
|
||||
class AuthorizationWriter(Protocol):
|
||||
def authorize_deployment(self, **values: Any) -> Any: ...
|
||||
def authorize_rollback(self, **values: Any) -> Any: ...
|
||||
def authorize_audit(self, **values: Any) -> Any: ...
|
||||
def authorize_code_change(self, **values: Any) -> Any: ...
|
||||
def authorize_evidence_write(self, **values: Any) -> Any: ...
|
||||
def authorize_runtime_execute(self, **values: Any) -> Any: ...
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OperationContext:
|
||||
provenance_id: str
|
||||
run_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
|
||||
def as_dict(self) -> dict[str, str]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OperationReceipt:
|
||||
operation: str
|
||||
request_digest: str
|
||||
authorization_id: str
|
||||
provenance_id: str
|
||||
grant_id: str | None
|
||||
run_id: str
|
||||
tenant_id: str
|
||||
task_id: str
|
||||
agent_id: str
|
||||
principal_id: str
|
||||
execution_path: str
|
||||
authorized_at: str
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class ProvenanceOperationGate:
|
||||
"""部署、回滚、审计和运行操作的统一授权入口。"""
|
||||
|
||||
def __init__(self, writer: AuthorizationWriter) -> None:
|
||||
self.writer = writer
|
||||
|
||||
def authorize(
|
||||
self,
|
||||
context: OperationContext,
|
||||
*,
|
||||
execution_path: str,
|
||||
operation: str,
|
||||
request: Mapping[str, Any],
|
||||
) -> OperationReceipt:
|
||||
path = ExecutionPath(execution_path).value
|
||||
normalized_operation = str(operation or "").strip()
|
||||
if not normalized_operation:
|
||||
raise ValueError("operation is required")
|
||||
digest = digest_payload(
|
||||
{
|
||||
"operation": normalized_operation,
|
||||
"execution_path": path,
|
||||
"request": dict(request),
|
||||
}
|
||||
)
|
||||
values = {
|
||||
"provenance_id": context.provenance_id,
|
||||
"run_id": context.run_id,
|
||||
"tenant_id": context.tenant_id,
|
||||
"task_id": context.task_id,
|
||||
"agent_id": context.agent_id,
|
||||
"principal_id": context.principal_id,
|
||||
"request_digest": digest,
|
||||
}
|
||||
if path == ExecutionPath.DEPLOYMENT.value:
|
||||
authorization = self.writer.authorize_deployment(**values)
|
||||
elif path == ExecutionPath.ROLLBACK.value:
|
||||
authorization = self.writer.authorize_rollback(**values)
|
||||
elif path == ExecutionPath.AUDIT.value:
|
||||
authorization = self.writer.authorize_audit(**values)
|
||||
elif path == ExecutionPath.CODE_CHANGE.value:
|
||||
authorization = self.writer.authorize_code_change(**values)
|
||||
elif path == ExecutionPath.EVIDENCE_WRITE.value:
|
||||
authorization = self.writer.authorize_evidence_write(**values)
|
||||
elif path == ExecutionPath.RUNTIME_EXECUTE.value:
|
||||
authorization = self.writer.authorize_runtime_execute(**values)
|
||||
else:
|
||||
raise ProvenanceDenied(
|
||||
"generic operation gate does not authorize git_operation; use ProvenanceGitWriter"
|
||||
)
|
||||
return self._receipt(normalized_operation, digest, authorization)
|
||||
|
||||
@staticmethod
|
||||
def _receipt(
|
||||
operation: str,
|
||||
request_digest: str,
|
||||
authorization: ProvenanceAuthorization | GrantAuthorization | Any,
|
||||
) -> OperationReceipt:
|
||||
return OperationReceipt(
|
||||
operation=operation,
|
||||
request_digest=request_digest,
|
||||
authorization_id=authorization.authorization_id,
|
||||
provenance_id=authorization.provenance_id,
|
||||
grant_id=getattr(authorization, "grant_id", None),
|
||||
run_id=authorization.run_id,
|
||||
tenant_id=authorization.tenant_id,
|
||||
task_id=authorization.task_id,
|
||||
agent_id=authorization.agent_id,
|
||||
principal_id=authorization.principal_id,
|
||||
execution_path=authorization.execution_path,
|
||||
authorized_at=authorization.authorized_at,
|
||||
)
|
||||
|
||||
|
||||
_GRANT_ENV_BY_PATH: Mapping[str, str] = {
|
||||
ExecutionPath.CODE_CHANGE.value: "AIOS_PROVENANCE_GRANT_CODE_CHANGE_ID",
|
||||
ExecutionPath.GIT_OPERATION.value: "AIOS_PROVENANCE_GRANT_GIT_ID",
|
||||
ExecutionPath.DEPLOYMENT.value: "AIOS_PROVENANCE_GRANT_DEPLOYMENT_ID",
|
||||
ExecutionPath.RUNTIME_EXECUTE.value: "AIOS_PROVENANCE_GRANT_RUNTIME_ID",
|
||||
ExecutionPath.EVIDENCE_WRITE.value: "AIOS_PROVENANCE_GRANT_EVIDENCE_ID",
|
||||
ExecutionPath.ROLLBACK.value: "AIOS_PROVENANCE_GRANT_ROLLBACK_ID",
|
||||
ExecutionPath.AUDIT.value: "AIOS_PROVENANCE_GRANT_AUDIT_ID",
|
||||
}
|
||||
|
||||
|
||||
def grant_ids_from_environment(
|
||||
*,
|
||||
required_paths: Sequence[str] | None = None,
|
||||
) -> dict[str, str]:
|
||||
paths = tuple(
|
||||
sorted(
|
||||
{
|
||||
ExecutionPath(path).value
|
||||
for path in (required_paths or tuple(item.value for item in ExecutionPath))
|
||||
}
|
||||
)
|
||||
)
|
||||
values = {path: os.getenv(_GRANT_ENV_BY_PATH[path], "").strip() for path in paths}
|
||||
missing = [_GRANT_ENV_BY_PATH[path] for path, value in values.items() if not value]
|
||||
if missing:
|
||||
raise RuntimeError(f"missing scoped Provenance Grant configuration: {missing}")
|
||||
return values
|
||||
|
||||
|
||||
def build_provenance_writer_from_env(
|
||||
*,
|
||||
state_dir: str | Path | None = None,
|
||||
required: bool | None = None,
|
||||
required_paths: Sequence[str] | None = None,
|
||||
writer_id: str = "aios-v2-application-grant-writer",
|
||||
) -> AuthorizationWriter | None:
|
||||
"""从环境构建服务级最小权限 Writer。
|
||||
|
||||
生产应用默认只加载 Runtime、Evidence、Audit Grant。Git、部署和回滚进程
|
||||
必须显式传入自己的 ``required_paths``,不能继承应用默认范围。旧全权限 Writer
|
||||
只允许在显式关闭强制模式的候选/测试环境中使用。
|
||||
"""
|
||||
|
||||
require_value = (
|
||||
bool(required)
|
||||
if required is not None
|
||||
else os.getenv("AIOS_REQUIRE_RUN_PROVENANCE", "0").strip().lower()
|
||||
in {"1", "true", "yes", "on"}
|
||||
)
|
||||
public_key_file = os.getenv("AIOS_PROVENANCE_PUBLIC_KEY_FILE", "").strip()
|
||||
key_id = os.getenv("AIOS_PROVENANCE_KEY_ID", "").strip()
|
||||
base = Path(state_dir or os.getenv("AIOS_V2_STATE_DIR", "/var/lib/aios-v2")).resolve()
|
||||
store_file = os.getenv(
|
||||
"AIOS_PROVENANCE_STORE_FILE", str(base / "run-provenance.sqlite3")
|
||||
).strip()
|
||||
receipt_root = os.getenv(
|
||||
"AIOS_PROVENANCE_RECEIPT_DIR", str(base / "provenance-receipts")
|
||||
).strip()
|
||||
configured = bool(public_key_file and key_id)
|
||||
if not configured:
|
||||
if require_value:
|
||||
raise RuntimeError(
|
||||
"Run Provenance is required but AIOS_PROVENANCE_PUBLIC_KEY_FILE or AIOS_PROVENANCE_KEY_ID is missing"
|
||||
)
|
||||
return None
|
||||
|
||||
verifier = Ed25519PublicKeyVerifier.from_file(public_key_file, key_id=key_id)
|
||||
parent_store = SQLiteProvenanceStore(store_file)
|
||||
normalized_paths = tuple(
|
||||
sorted(
|
||||
{
|
||||
ExecutionPath(path).value
|
||||
for path in (
|
||||
required_paths
|
||||
if required_paths is not None
|
||||
else APPLICATION_PROVENANCE_SCOPE
|
||||
)
|
||||
}
|
||||
)
|
||||
)
|
||||
|
||||
if require_value:
|
||||
if not normalized_paths:
|
||||
raise RuntimeError("production Run Provenance requires a non-empty service scope")
|
||||
grant_ids = grant_ids_from_environment(required_paths=normalized_paths)
|
||||
grant_store = SQLiteGrantStore(store_file)
|
||||
trusted_grants = GrantVerifier(parent_store, grant_store, {key_id: verifier})
|
||||
return ScopedLeastPrivilegeProvenanceWriter(
|
||||
trusted_grants,
|
||||
receipt_root,
|
||||
grant_ids,
|
||||
required_paths=normalized_paths,
|
||||
writer_id=writer_id,
|
||||
)
|
||||
|
||||
legacy = ProvenanceVerifier(parent_store, {key_id: verifier})
|
||||
return ProvenanceControlledWriter(legacy, receipt_root)
|
||||
|
||||
|
||||
def context_from_environment() -> OperationContext:
|
||||
values = {
|
||||
"provenance_id": os.getenv("AIOS_PROVENANCE_ID", ""),
|
||||
"run_id": os.getenv("AIOS_RUN_ID", ""),
|
||||
"tenant_id": os.getenv("AIOS_TENANT_ID", ""),
|
||||
"task_id": os.getenv("AIOS_TASK_ID", ""),
|
||||
"agent_id": os.getenv("AIOS_AGENT_ID", ""),
|
||||
"principal_id": os.getenv("AIOS_PRINCIPAL_ID", ""),
|
||||
}
|
||||
missing = [name for name, value in values.items() if not str(value).strip()]
|
||||
if missing:
|
||||
raise RuntimeError(f"missing Provenance context environment variables: {missing}")
|
||||
return OperationContext(**{name: str(value).strip() for name, value in values.items()})
|
||||
|
||||
|
||||
def load_request_file(path: str | Path) -> Mapping[str, Any]:
|
||||
value = json.loads(Path(path).read_text(encoding="utf-8"))
|
||||
if not isinstance(value, Mapping):
|
||||
raise ValueError("request file must contain a JSON object")
|
||||
return dict(value)
|
||||
@@ -0,0 +1,131 @@
|
||||
"""按服务范围加载的最小权限 Provenance Writer。
|
||||
|
||||
该 Writer 只持有调用进程需要的 Grant ID。未配置路径的方法即使被调用也会
|
||||
默认拒绝,避免应用进程获得 Git、部署或回滚权限。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import threading
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
from .provenance import ExecutionPath, ProvenanceDenied, required
|
||||
from .provenance_grants import GrantAuthorization, GrantVerifier
|
||||
|
||||
|
||||
class ScopedLeastPrivilegeProvenanceWriter:
|
||||
"""只暴露指定 ExecutionPath 的最小权限 Writer。"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
verifier: GrantVerifier,
|
||||
receipt_root: str | Path,
|
||||
grant_ids: Mapping[str, str],
|
||||
*,
|
||||
required_paths: Sequence[str],
|
||||
writer_id: str = "aios-v2-scoped-grant-writer",
|
||||
) -> None:
|
||||
self.verifier = verifier
|
||||
self.receipt_root = Path(receipt_root).resolve()
|
||||
self.receipt_root.mkdir(parents=True, exist_ok=True)
|
||||
normalized_required = tuple(
|
||||
sorted({ExecutionPath(path).value for path in required_paths})
|
||||
)
|
||||
if not normalized_required:
|
||||
raise ValueError("required_paths must not be empty")
|
||||
self.required_paths = frozenset(normalized_required)
|
||||
self.grant_ids = {
|
||||
path: required(grant_ids.get(path, ""), f"grant_id[{path}]")
|
||||
for path in normalized_required
|
||||
}
|
||||
unexpected = sorted(set(grant_ids) - self.required_paths)
|
||||
if unexpected:
|
||||
raise ValueError(
|
||||
f"scoped writer received unnecessary Grant mappings: {unexpected}"
|
||||
)
|
||||
self.writer_id = required(writer_id, "writer_id")
|
||||
self._lock = threading.RLock()
|
||||
|
||||
@staticmethod
|
||||
def _component(value: str) -> str:
|
||||
normalized = required(value, "path component")
|
||||
if normalized in {".", ".."} or "/" in normalized or "\\" in normalized:
|
||||
raise ProvenanceDenied("invalid receipt path component")
|
||||
return normalized
|
||||
|
||||
def _grant_for(self, path: str) -> str:
|
||||
normalized = ExecutionPath(path).value
|
||||
grant_id = self.grant_ids.get(normalized)
|
||||
if grant_id is None:
|
||||
raise ProvenanceDenied(
|
||||
f"this process is not allowed to authorize {normalized}"
|
||||
)
|
||||
return grant_id
|
||||
|
||||
def authorize(self, **values: Any) -> GrantAuthorization:
|
||||
path = ExecutionPath(values["execution_path"]).value
|
||||
grant_id = self._grant_for(path)
|
||||
parent_provenance_id = values.pop("provenance_id")
|
||||
authorization = self.verifier.authorize(
|
||||
grant_id=grant_id,
|
||||
parent_provenance_id=parent_provenance_id,
|
||||
**values,
|
||||
)
|
||||
tenant = self._component(authorization.tenant_id)
|
||||
parent = self._component(authorization.parent_provenance_id)
|
||||
grant = self._component(authorization.grant_id)
|
||||
target_dir = self.receipt_root / tenant / parent / grant
|
||||
target = target_dir / f"{authorization.authorization_id}.json"
|
||||
payload = authorization.as_dict()
|
||||
payload["writer_id"] = self.writer_id
|
||||
payload["scope"] = sorted(self.required_paths)
|
||||
with self._lock:
|
||||
target_dir.mkdir(parents=True, exist_ok=True)
|
||||
temporary = target.with_suffix(f".tmp-{os.getpid()}")
|
||||
temporary.write_text(
|
||||
json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2)
|
||||
+ "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
os.chmod(temporary, 0o640)
|
||||
os.replace(temporary, target)
|
||||
return authorization
|
||||
|
||||
def authorize_code_change(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.CODE_CHANGE.value, **values
|
||||
)
|
||||
|
||||
def authorize_git_operation(
|
||||
self, *, git_operation: str, **values: Any
|
||||
) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.GIT_OPERATION.value,
|
||||
git_operation=git_operation,
|
||||
**values,
|
||||
)
|
||||
|
||||
def authorize_deployment(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.DEPLOYMENT.value, **values
|
||||
)
|
||||
|
||||
def authorize_runtime_execute(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.RUNTIME_EXECUTE.value, **values
|
||||
)
|
||||
|
||||
def authorize_evidence_write(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.EVIDENCE_WRITE.value, **values
|
||||
)
|
||||
|
||||
def authorize_rollback(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(
|
||||
execution_path=ExecutionPath.ROLLBACK.value, **values
|
||||
)
|
||||
|
||||
def authorize_audit(self, **values: Any) -> GrantAuthorization:
|
||||
return self.authorize(execution_path=ExecutionPath.AUDIT.value, **values)
|
||||
@@ -0,0 +1,120 @@
|
||||
"""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"]
|
||||
@@ -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"]
|
||||
@@ -0,0 +1,92 @@
|
||||
"""Agent adapters for AIOS Search Gateway.
|
||||
|
||||
All runtime agents should call SearchGatewayAgentAdapter instead of performing
|
||||
ad-hoc network search. This gives consistent provider fallback, profile
|
||||
resolution, evidence capture, audit and event visibility.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from .search_gateway_orchestrator import SearchGatewayOrchestrator
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AgentSearchContext:
|
||||
agent: str
|
||||
user_id: str | None = None
|
||||
group_id: str | None = None
|
||||
role: str = "user"
|
||||
group_profile: dict[str, Any] | None = None
|
||||
user_profile: dict[str, Any] | None = None
|
||||
session_profile: dict[str, Any] | None = None
|
||||
authorized_sources: list[str] = field(default_factory=list)
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class SearchGatewayAgentAdapter:
|
||||
def __init__(self, orchestrator: SearchGatewayOrchestrator | None = None):
|
||||
self.orchestrator = orchestrator or SearchGatewayOrchestrator()
|
||||
|
||||
def search(
|
||||
self,
|
||||
query: str,
|
||||
context: AgentSearchContext,
|
||||
intent: str = "general",
|
||||
region: str | None = None,
|
||||
time_range: str | None = None,
|
||||
data_type: str | None = None,
|
||||
domain_profiles: list[str] | None = None,
|
||||
user_scope: str = "public",
|
||||
correlation_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
payload = {
|
||||
"query": query,
|
||||
"requester": context.agent,
|
||||
"intent": intent,
|
||||
"region": region,
|
||||
"time_range": time_range,
|
||||
"data_type": data_type,
|
||||
"domain_profiles": domain_profiles or [],
|
||||
"user_scope": user_scope,
|
||||
"authorized_sources": context.authorized_sources,
|
||||
"group_profile": context.group_profile,
|
||||
"user_profile": context.user_profile,
|
||||
"session_profile": context.session_profile,
|
||||
"correlation_id": correlation_id,
|
||||
}
|
||||
return self.orchestrator.execute(payload)
|
||||
|
||||
|
||||
class OpenClawSearchClient(SearchGatewayAgentAdapter):
|
||||
def search_public(self, query: str, context: AgentSearchContext, **kwargs) -> dict[str, Any]:
|
||||
return self.search(query, context, user_scope="public", **kwargs)
|
||||
|
||||
|
||||
class HermesSearchClient(SearchGatewayAgentAdapter):
|
||||
def delegate_search(self, query: str, context: AgentSearchContext, **kwargs) -> dict[str, Any]:
|
||||
return self.search(query, context, **kwargs)
|
||||
|
||||
|
||||
class CodexSearchClient(SearchGatewayAgentAdapter):
|
||||
def technical_search(self, query: str, context: AgentSearchContext, **kwargs) -> dict[str, Any]:
|
||||
return self.search(query, context, intent=kwargs.pop("intent", "software_library"), **kwargs)
|
||||
|
||||
|
||||
class CustomGPTSearchClient(SearchGatewayAgentAdapter):
|
||||
def user_search(self, query: str, context: AgentSearchContext, **kwargs) -> dict[str, Any]:
|
||||
return self.search(query, context, **kwargs)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"AgentSearchContext",
|
||||
"SearchGatewayAgentAdapter",
|
||||
"OpenClawSearchClient",
|
||||
"HermesSearchClient",
|
||||
"CodexSearchClient",
|
||||
"CustomGPTSearchClient",
|
||||
]
|
||||
@@ -0,0 +1,73 @@
|
||||
"""Architect governance integration for Search Gateway.
|
||||
|
||||
Search Gateway is a shared platform capability. The Architect Agent periodically
|
||||
reviews provider health, external search/browser capabilities, cost, security and
|
||||
privacy impact, then emits C/R/V 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 SearchArchitectureFinding:
|
||||
finding_id: str
|
||||
title: str
|
||||
impact: str
|
||||
recommendation: str
|
||||
evidence: list[str] = field(default_factory=list)
|
||||
created_at: str = field(default_factory=utc_now)
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchArchitectureDecision:
|
||||
status: str
|
||||
version_bump: str
|
||||
reason: str
|
||||
findings: list[SearchArchitectureFinding]
|
||||
owner_gate_required: bool
|
||||
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],
|
||||
"owner_gate_required": self.owner_gate_required,
|
||||
"created_at": self.created_at,
|
||||
}
|
||||
|
||||
|
||||
class SearchArchitectIntegration:
|
||||
def review(self, signals: dict[str, Any]) -> SearchArchitectureDecision:
|
||||
findings: list[SearchArchitectureFinding] = []
|
||||
if signals.get("provider_breaking_change"):
|
||||
findings.append(SearchArchitectureFinding("search-provider-breaking", "Provider breaking change", "breaking", "owner_review"))
|
||||
if signals.get("new_search_capability"):
|
||||
findings.append(SearchArchitectureFinding("search-new-capability", "New search capability available", "architecture", "evaluate_adoption"))
|
||||
if signals.get("cost_increase"):
|
||||
findings.append(SearchArchitectureFinding("search-cost", "Search provider cost increase", "minor", "optimize_provider_order"))
|
||||
if signals.get("security_advisory"):
|
||||
findings.append(SearchArchitectureFinding("search-security", "Search security advisory", "breaking", "owner_review"))
|
||||
|
||||
if any(f.impact == "breaking" for f in findings):
|
||||
return SearchArchitectureDecision("action_required", "V", "breaking search ecosystem/security change", findings, True)
|
||||
if any(f.impact == "architecture" for f in findings):
|
||||
return SearchArchitectureDecision("optimization_recommended", "R", "new search capability may improve architecture", findings, True)
|
||||
if findings:
|
||||
return SearchArchitectureDecision("minor_change_recommended", "C", "compatible provider optimization", findings, False)
|
||||
return SearchArchitectureDecision("no_action", "none", "no relevant search architecture change", findings, False)
|
||||
|
||||
|
||||
__all__ = ["SearchArchitectureFinding", "SearchArchitectureDecision", "SearchArchitectIntegration"]
|
||||
@@ -0,0 +1,27 @@
|
||||
"""Audit storage for Search Gateway executions."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
|
||||
class SearchAuditStore:
|
||||
def __init__(self, root: str = "runtime/search-gateway/audit"):
|
||||
self.root = Path(root)
|
||||
self.root.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def append(self, record: dict[str, Any]) -> str:
|
||||
path = self.root / f"{record.get('request_id', 'search')}.json"
|
||||
path.write_text(json.dumps(record, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
return str(path)
|
||||
|
||||
def list_recent(self) -> list[dict[str, Any]]:
|
||||
result = []
|
||||
for path in sorted(self.root.glob("*.json")):
|
||||
result.append(json.loads(path.read_text(encoding="utf-8")))
|
||||
return result[-50:]
|
||||
|
||||
|
||||
__all__ = ["SearchAuditStore"]
|
||||
@@ -0,0 +1,118 @@
|
||||
"""Search Gateway event bridge.
|
||||
|
||||
Publishes normalized search lifecycle events into the AIOS Agent Event Bus when a
|
||||
bus is available, with an in-memory fallback for tests and offline runs.
|
||||
"""
|
||||
|
||||
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 SearchEventPublisher(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 SearchEvent:
|
||||
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 InMemorySearchEventBus:
|
||||
def __init__(self):
|
||||
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 = SearchEvent(
|
||||
id=f"search_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 SearchEventBridge:
|
||||
def __init__(self, bus: SearchEventPublisher | None = None):
|
||||
self.bus = bus or InMemorySearchEventBus()
|
||||
|
||||
def search_started(self, request: dict[str, Any]) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="search_started",
|
||||
source=request.get("requester", "unknown"),
|
||||
target="search-gateway",
|
||||
summary=request.get("query", "search started"),
|
||||
payload=request,
|
||||
correlation_id=request.get("correlation_id"),
|
||||
)
|
||||
|
||||
def provider_attempted(self, request_id: str, attempt: dict[str, Any]) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="search_provider_attempted",
|
||||
source="search-gateway",
|
||||
target=attempt.get("provider", "unknown"),
|
||||
summary=f"provider {attempt.get('provider', 'unknown')} {attempt.get('status', 'attempted')}",
|
||||
payload=attempt,
|
||||
correlation_id=request_id,
|
||||
)
|
||||
|
||||
def fallback_triggered(self, request_id: str, reason: str) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="search_fallback_triggered",
|
||||
source="search-gateway",
|
||||
target="search-provider-router",
|
||||
summary=reason,
|
||||
payload={"reason": reason},
|
||||
correlation_id=request_id,
|
||||
)
|
||||
|
||||
def search_completed(self, response: dict[str, Any]) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="search_completed",
|
||||
source="search-gateway",
|
||||
target=response.get("requester", "requester"),
|
||||
summary=f"search {response.get('status', 'completed')}",
|
||||
payload=response,
|
||||
correlation_id=response.get("request_id"),
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["SearchEvent", "InMemorySearchEventBus", "SearchEventBridge"]
|
||||
@@ -0,0 +1,252 @@
|
||||
"""Governed general-purpose Search Gateway for AIOS.
|
||||
|
||||
The gateway coordinates query planning, provider routing, fallback, evidence
|
||||
normalization and compliance checks. It is provider-agnostic: runtime workers plug
|
||||
in public or explicitly authorized search providers.
|
||||
|
||||
Search is a shared capability. Groups and users may customize provider order,
|
||||
trusted domains, query expansion hints and domain profiles, but customization may
|
||||
not override hard authorization, privacy, safety or audit rules.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any, Protocol
|
||||
from uuid import uuid4
|
||||
|
||||
from .search_profile_resolver import DomainQueryProfileRegistry, SearchProfile, SearchProfileResolver
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchRequest:
|
||||
query: str
|
||||
requester: str
|
||||
intent: str = "general"
|
||||
region: str | None = None
|
||||
time_range: str | None = None
|
||||
data_type: str | None = None
|
||||
user_scope: str = "public"
|
||||
authorized_sources: list[str] = field(default_factory=list)
|
||||
domain_profiles: list[str] = field(default_factory=list)
|
||||
group_profile: dict[str, Any] | None = None
|
||||
user_profile: dict[str, Any] | None = None
|
||||
session_profile: dict[str, Any] | None = None
|
||||
correlation_id: str | None = None
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchEvidence:
|
||||
title: str
|
||||
url: str | None
|
||||
source: str
|
||||
snippet: str
|
||||
evidence_type: str = "web"
|
||||
confidence: str = "medium"
|
||||
retrieved_at: str = field(default_factory=utc_now)
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchProviderAttempt:
|
||||
provider: str
|
||||
status: str
|
||||
result_count: int = 0
|
||||
reason: str = ""
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchResponse:
|
||||
request_id: str
|
||||
status: str
|
||||
answer: str
|
||||
evidence: list[SearchEvidence]
|
||||
attempts: list[SearchProviderAttempt]
|
||||
confidence: str
|
||||
expanded_queries: list[str] = field(default_factory=list)
|
||||
resolved_profile: dict[str, Any] | None = None
|
||||
need_clarification: list[str] = field(default_factory=list)
|
||||
blocked_reasons: list[str] = field(default_factory=list)
|
||||
created_at: str = field(default_factory=utc_now)
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"request_id": self.request_id,
|
||||
"status": self.status,
|
||||
"answer": self.answer,
|
||||
"evidence": [e.to_dict() for e in self.evidence],
|
||||
"attempts": [a.to_dict() for a in self.attempts],
|
||||
"confidence": self.confidence,
|
||||
"expanded_queries": self.expanded_queries,
|
||||
"resolved_profile": self.resolved_profile,
|
||||
"need_clarification": self.need_clarification,
|
||||
"blocked_reasons": self.blocked_reasons,
|
||||
"created_at": self.created_at,
|
||||
}
|
||||
|
||||
|
||||
class SearchProvider(Protocol):
|
||||
name: str
|
||||
|
||||
def search(self, request: SearchRequest, queries: list[str]) -> tuple[list[SearchEvidence], SearchProviderAttempt]:
|
||||
...
|
||||
|
||||
|
||||
class QueryPlanner:
|
||||
def __init__(self, domain_registry: DomainQueryProfileRegistry | None = None):
|
||||
self.domain_registry = domain_registry or DomainQueryProfileRegistry()
|
||||
|
||||
def expand(self, request: SearchRequest, profile: SearchProfile) -> list[str]:
|
||||
base = request.query.strip()
|
||||
queries = [base]
|
||||
if request.region:
|
||||
queries.append(f"{request.region} {base}")
|
||||
if request.time_range:
|
||||
queries.append(f"{base} {request.time_range}")
|
||||
domain_profiles = list(dict.fromkeys([request.intent] + request.domain_profiles + profile.domain_profiles))
|
||||
hints = list(profile.query_expansion_hints) + self.domain_registry.hints_for(domain_profiles)
|
||||
for hint in hints:
|
||||
queries.append(f"{base} {hint}")
|
||||
for domain in profile.trusted_domains:
|
||||
queries.append(f"site:{domain} {base}")
|
||||
return list(dict.fromkeys([q for q in queries if q]))
|
||||
|
||||
|
||||
class SearchPolicyGuard:
|
||||
"""Blocks non-public or unauthorized collection patterns."""
|
||||
|
||||
FORBIDDEN_TERMS = (
|
||||
"绕过登录",
|
||||
"绕过验证码",
|
||||
"验证码绕过",
|
||||
"破解登录",
|
||||
"个人成绩",
|
||||
"学生隐私",
|
||||
"受保护平台批量爬取",
|
||||
)
|
||||
|
||||
def evaluate(self, request: SearchRequest, profile: SearchProfile) -> list[str]:
|
||||
q = request.query.lower()
|
||||
reasons: list[str] = []
|
||||
for term in self.FORBIDDEN_TERMS:
|
||||
if term.lower() in q:
|
||||
reasons.append(f"blocked_term:{term}")
|
||||
if request.user_scope not in {"public", "authorized_user_file", "authorized_link", "internal_archive"}:
|
||||
reasons.append(f"unsupported_scope:{request.user_scope}")
|
||||
if request.data_type in {"personal_grade", "student_private_data", "private_person_data"} and request.user_scope != "authorized_user_file":
|
||||
reasons.append("private_data_requires_user_authorized_file")
|
||||
if not profile.audit_required:
|
||||
reasons.append("audit_cannot_be_disabled")
|
||||
if not profile.fallback_required:
|
||||
reasons.append("fallback_cannot_be_disabled")
|
||||
return reasons
|
||||
|
||||
|
||||
class SearchGateway:
|
||||
def __init__(self, providers: list[SearchProvider] | None = None):
|
||||
self.providers = providers or []
|
||||
self.profile_resolver = SearchProfileResolver()
|
||||
self.planner = QueryPlanner()
|
||||
self.guard = SearchPolicyGuard()
|
||||
|
||||
def search(self, request: SearchRequest) -> SearchResponse:
|
||||
request_id = request.correlation_id or f"search_{uuid4().hex[:12]}"
|
||||
profile = self.profile_resolver.resolve(request.group_profile, request.user_profile, request.session_profile)
|
||||
expanded_queries = self.planner.expand(request, profile)
|
||||
blocked = self.guard.evaluate(request, profile)
|
||||
if blocked:
|
||||
return SearchResponse(
|
||||
request_id=request_id,
|
||||
status="blocked",
|
||||
answer="该搜索请求涉及未授权访问、验证码/登录绕过、受保护平台批量抓取或个人隐私数据,已阻断。可改为搜索公开网页、官方公告、公开文档,或处理用户授权上传的文件/链接。",
|
||||
evidence=[],
|
||||
attempts=[],
|
||||
confidence="high",
|
||||
expanded_queries=expanded_queries,
|
||||
resolved_profile=profile.to_dict(),
|
||||
blocked_reasons=blocked,
|
||||
)
|
||||
|
||||
evidence: list[SearchEvidence] = []
|
||||
attempts: list[SearchProviderAttempt] = []
|
||||
providers = self._ordered_providers(profile)
|
||||
for provider in providers:
|
||||
try:
|
||||
provider_evidence, attempt = provider.search(request, expanded_queries)
|
||||
evidence.extend(provider_evidence)
|
||||
attempts.append(attempt)
|
||||
if provider_evidence:
|
||||
break
|
||||
except Exception as exc:
|
||||
attempts.append(SearchProviderAttempt(provider=getattr(provider, "name", "unknown"), status="failed", reason=str(exc)))
|
||||
|
||||
if evidence:
|
||||
return SearchResponse(
|
||||
request_id=request_id,
|
||||
status="found",
|
||||
answer="已找到公开或授权来源结果。",
|
||||
evidence=evidence,
|
||||
attempts=attempts,
|
||||
confidence=self._confidence(evidence),
|
||||
expanded_queries=expanded_queries,
|
||||
resolved_profile=profile.to_dict(),
|
||||
)
|
||||
|
||||
return SearchResponse(
|
||||
request_id=request_id,
|
||||
status="not_found",
|
||||
answer="未找到足够可靠的公开或授权结果;已记录 provider 尝试和失败原因。",
|
||||
evidence=[],
|
||||
attempts=attempts,
|
||||
confidence="low",
|
||||
expanded_queries=expanded_queries,
|
||||
resolved_profile=profile.to_dict(),
|
||||
need_clarification=self._clarification(request),
|
||||
)
|
||||
|
||||
def _ordered_providers(self, profile: SearchProfile) -> list[SearchProvider]:
|
||||
if not self.providers:
|
||||
return []
|
||||
by_name = {provider.name: provider for provider in self.providers}
|
||||
ordered = [by_name[name] for name in profile.provider_order if name in by_name]
|
||||
remaining = [provider for provider in self.providers if provider.name not in {p.name for p in ordered}]
|
||||
return ordered + remaining
|
||||
|
||||
def _confidence(self, evidence: list[SearchEvidence]) -> str:
|
||||
if any(e.confidence == "high" for e in evidence):
|
||||
return "high"
|
||||
if evidence:
|
||||
return "medium"
|
||||
return "low"
|
||||
|
||||
def _clarification(self, request: SearchRequest) -> list[str]:
|
||||
if request.intent == "education_exam_data":
|
||||
return ["请补充学校名称、联考名称、年级、科目,以及需要试卷/答案还是成绩统计。"]
|
||||
if request.intent in {"company_research", "policy_regulation", "software_library", "product_research"}:
|
||||
return ["请补充主体名称、地区/版本、时间范围、需要的数据类型或可信来源范围。"]
|
||||
return ["请补充更具体的主体、平台、地区、时间、数据类型或授权文件/链接。"]
|
||||
|
||||
|
||||
__all__ = [
|
||||
"SearchRequest",
|
||||
"SearchEvidence",
|
||||
"SearchProviderAttempt",
|
||||
"SearchResponse",
|
||||
"SearchProvider",
|
||||
"QueryPlanner",
|
||||
"SearchPolicyGuard",
|
||||
"SearchGateway",
|
||||
]
|
||||
@@ -0,0 +1,65 @@
|
||||
"""API endpoints for AIOS Search Gateway."""
|
||||
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from fastapi import APIRouter
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .search_gateway import SearchGateway, SearchRequest
|
||||
from .search_gateway_dashboard import SearchGatewayDashboard
|
||||
|
||||
|
||||
gateway = SearchGateway()
|
||||
dashboard = SearchGatewayDashboard()
|
||||
|
||||
|
||||
def search_gateway_request(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
request = SearchRequest(**payload)
|
||||
return gateway.search(request).to_dict()
|
||||
|
||||
|
||||
def get_search_gateway_status() -> dict[str, Any]:
|
||||
return {
|
||||
"module": "search-gateway",
|
||||
"status": "ready",
|
||||
"providers_configured": len(gateway.providers),
|
||||
"policy_guard": "enabled",
|
||||
"profile_customization": "enabled",
|
||||
"fallback_required_when_provider_unavailable": True,
|
||||
}
|
||||
|
||||
|
||||
def get_search_gateway_overview() -> dict[str, Any]:
|
||||
return dashboard.overview()
|
||||
|
||||
|
||||
def build_router():
|
||||
if APIRouter is None:
|
||||
return None
|
||||
router = APIRouter(prefix="/admin/ai-evolution/search", tags=["search-gateway"])
|
||||
|
||||
@router.get("/status", operation_id="getSearchGatewayStatus")
|
||||
def status():
|
||||
return get_search_gateway_status()
|
||||
|
||||
@router.get("/overview", operation_id="getSearchGatewayOverview")
|
||||
def overview():
|
||||
return get_search_gateway_overview()
|
||||
|
||||
@router.post("/query", operation_id="runSearchGatewayQuery")
|
||||
def query(payload: dict[str, Any]):
|
||||
return search_gateway_request(payload)
|
||||
|
||||
return router
|
||||
|
||||
|
||||
router = build_router()
|
||||
|
||||
__all__ = [
|
||||
"router",
|
||||
"search_gateway_request",
|
||||
"get_search_gateway_status",
|
||||
"get_search_gateway_overview",
|
||||
]
|
||||
@@ -0,0 +1,85 @@
|
||||
"""Search Gateway Web UI dashboard model."""
|
||||
|
||||
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 SearchDashboardMetric:
|
||||
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 SearchDashboardPanel:
|
||||
key: str
|
||||
title: str
|
||||
metrics: list[SearchDashboardMetric] = 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 SearchGatewayDashboard:
|
||||
def overview(self, search_runs: list[dict[str, Any]] | None = None, providers: list[dict[str, Any]] | None = None) -> dict[str, Any]:
|
||||
search_runs = search_runs or []
|
||||
providers = providers or []
|
||||
blocked = [r for r in search_runs if r.get("status") == "blocked"]
|
||||
not_found = [r for r in search_runs if r.get("status") == "not_found"]
|
||||
provider_failures = [p for p in providers if p.get("status") == "failed"]
|
||||
panels = [
|
||||
SearchDashboardPanel(
|
||||
"search_health",
|
||||
"搜索健康度",
|
||||
[
|
||||
SearchDashboardMetric("total_runs", "搜索请求数", len(search_runs)),
|
||||
SearchDashboardMetric("not_found", "未找到结果", len(not_found), "warn" if not_found else "ok"),
|
||||
SearchDashboardMetric("blocked", "合规阻断", len(blocked), "warn" if blocked else "ok"),
|
||||
],
|
||||
),
|
||||
SearchDashboardPanel(
|
||||
"provider_health",
|
||||
"Provider 可用性",
|
||||
[
|
||||
SearchDashboardMetric("providers", "Provider 数量", len(providers)),
|
||||
SearchDashboardMetric("provider_failures", "Provider 失败", len(provider_failures), "warn" if provider_failures else "ok"),
|
||||
],
|
||||
),
|
||||
SearchDashboardPanel(
|
||||
"evidence_quality",
|
||||
"证据质量",
|
||||
[
|
||||
SearchDashboardMetric("with_evidence", "有证据的回答", len([r for r in search_runs if r.get("evidence")])) ,
|
||||
SearchDashboardMetric("fallback_required", "要求多源降级", True),
|
||||
],
|
||||
),
|
||||
]
|
||||
return {
|
||||
"module": "search-gateway",
|
||||
"route": "/admin/ai-evolution/search",
|
||||
"title": "AIOS 联网搜索治理中心",
|
||||
"status": "attention_required" if provider_failures else "healthy",
|
||||
"generated_at": utc_now(),
|
||||
"panels": [p.to_dict() for p in panels],
|
||||
"recent_runs": search_runs[-20:],
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["SearchDashboardMetric", "SearchDashboardPanel", "SearchGatewayDashboard"]
|
||||
@@ -0,0 +1,41 @@
|
||||
"""Runtime orchestrator joining Search Gateway, registry, audit and events."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from .search_audit_store import SearchAuditStore
|
||||
from .search_event_bridge import SearchEventBridge
|
||||
from .search_gateway import SearchGateway, SearchRequest
|
||||
from .search_provider_registry import SearchProviderRegistry
|
||||
|
||||
|
||||
class SearchGatewayOrchestrator:
|
||||
def __init__(self):
|
||||
self.registry = SearchProviderRegistry()
|
||||
self.audit = SearchAuditStore()
|
||||
self.events = SearchEventBridge()
|
||||
self.gateway = SearchGateway(self.registry.ordered())
|
||||
|
||||
def execute(self, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
request = SearchRequest(**payload)
|
||||
self.events.search_started(request.to_dict())
|
||||
response = self.gateway.search(request)
|
||||
result = response.to_dict()
|
||||
for attempt in result.get("attempts", []):
|
||||
self.events.provider_attempted(result["request_id"], attempt)
|
||||
if len(result.get("attempts", [])) > 1:
|
||||
self.events.fallback_triggered(result["request_id"], "multiple providers attempted")
|
||||
self.audit.append(result)
|
||||
self.events.search_completed(result)
|
||||
return result
|
||||
|
||||
def status(self) -> dict[str, Any]:
|
||||
return {
|
||||
"registry": self.registry.status(),
|
||||
"audit": "enabled",
|
||||
"events": "enabled",
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["SearchGatewayOrchestrator"]
|
||||
@@ -0,0 +1,124 @@
|
||||
"""Search profile resolver for general-purpose AIOS Search Gateway.
|
||||
|
||||
The Search Gateway is a shared platform capability. Groups and users may customize
|
||||
provider preference, query expansion hints, trusted sources and domain profiles on
|
||||
top of the shared base profile. Customization is intentionally layered and cannot
|
||||
override hard safety, authorization or audit rules.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from typing import Any
|
||||
|
||||
|
||||
HARD_BLOCKED_BEHAVIORS = {
|
||||
"bypass_login",
|
||||
"bypass_captcha",
|
||||
"scrape_private_student_grades",
|
||||
"scrape_student_private_data",
|
||||
"bulk_scrape_protected_platforms",
|
||||
"collect_data_without_authorization",
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchProfile:
|
||||
profile_id: str
|
||||
scope: str
|
||||
provider_order: list[str] = field(default_factory=lambda: [
|
||||
"cache",
|
||||
"official_site",
|
||||
"general_web",
|
||||
"vertical_source",
|
||||
"browser_fetch",
|
||||
"user_authorized_file",
|
||||
"internal_archive",
|
||||
])
|
||||
trusted_domains: list[str] = field(default_factory=list)
|
||||
query_expansion_hints: list[str] = field(default_factory=list)
|
||||
domain_profiles: list[str] = field(default_factory=list)
|
||||
blocked_behaviors: set[str] = field(default_factory=lambda: set(HARD_BLOCKED_BEHAVIORS))
|
||||
audit_required: bool = True
|
||||
fallback_required: bool = True
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
data = asdict(self)
|
||||
data["blocked_behaviors"] = sorted(self.blocked_behaviors)
|
||||
return data
|
||||
|
||||
|
||||
class SearchProfileResolver:
|
||||
"""Resolves base -> group -> user -> session search preferences."""
|
||||
|
||||
def base_profile(self) -> SearchProfile:
|
||||
return SearchProfile(profile_id="base", scope="global")
|
||||
|
||||
def resolve(
|
||||
self,
|
||||
group_profile: dict[str, Any] | None = None,
|
||||
user_profile: dict[str, Any] | None = None,
|
||||
session_profile: dict[str, Any] | None = None,
|
||||
) -> SearchProfile:
|
||||
profile = self.base_profile().to_dict()
|
||||
for overlay in (group_profile, user_profile, session_profile):
|
||||
if overlay:
|
||||
profile = self._merge(profile, overlay)
|
||||
profile["blocked_behaviors"] = set(HARD_BLOCKED_BEHAVIORS)
|
||||
profile["audit_required"] = True
|
||||
profile["fallback_required"] = True
|
||||
return SearchProfile(**profile)
|
||||
|
||||
def _merge(self, base: dict[str, Any], overlay: dict[str, Any]) -> dict[str, Any]:
|
||||
merged = dict(base)
|
||||
if overlay.get("provider_order"):
|
||||
merged["provider_order"] = list(overlay["provider_order"])
|
||||
for list_key in ("trusted_domains", "query_expansion_hints", "domain_profiles"):
|
||||
merged[list_key] = self._dedupe(list(merged.get(list_key, [])) + list(overlay.get(list_key, [])))
|
||||
merged["profile_id"] = overlay.get("profile_id", merged.get("profile_id", "custom"))
|
||||
merged["scope"] = overlay.get("scope", merged.get("scope", "custom"))
|
||||
return merged
|
||||
|
||||
def _dedupe(self, items: list[str]) -> list[str]:
|
||||
return list(dict.fromkeys([item for item in items if item]))
|
||||
|
||||
|
||||
class DomainQueryProfileRegistry:
|
||||
"""Optional domain-specific expansions for the general Search Gateway."""
|
||||
|
||||
DEFAULT_PROFILES = {
|
||||
"education_exam_data": [
|
||||
"学校 年级 科目 试卷 答案 成绩统计",
|
||||
"联考 月考 期中 期末 质量检测",
|
||||
],
|
||||
"policy_regulation": [
|
||||
"官方 通知 政策 解读 实施细则",
|
||||
"site:gov.cn OR site:edu.cn",
|
||||
],
|
||||
"software_library": [
|
||||
"release notes changelog migration guide",
|
||||
"official documentation GitHub issues",
|
||||
],
|
||||
"product_research": [
|
||||
"specs review comparison price availability",
|
||||
"official page manual support",
|
||||
],
|
||||
"company_research": [
|
||||
"official announcement press release filings",
|
||||
"leadership product financial report",
|
||||
],
|
||||
}
|
||||
|
||||
def hints_for(self, domain_profiles: list[str]) -> list[str]:
|
||||
hints: list[str] = []
|
||||
for profile in domain_profiles:
|
||||
hints.extend(self.DEFAULT_PROFILES.get(profile, []))
|
||||
return list(dict.fromkeys(hints))
|
||||
|
||||
|
||||
__all__ = [
|
||||
"HARD_BLOCKED_BEHAVIORS",
|
||||
"SearchProfile",
|
||||
"SearchProfileResolver",
|
||||
"DomainQueryProfileRegistry",
|
||||
]
|
||||
@@ -0,0 +1,121 @@
|
||||
"""Provider registry for the general AIOS Search Gateway.
|
||||
|
||||
The registry makes provider availability explicit and auditable. Provider
|
||||
implementations are pluggable: production can register real public search,
|
||||
official-site, vertical-source, browser-fetch, authorized-file or archive
|
||||
providers without changing the Search Gateway core.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from .search_gateway import SearchEvidence, SearchProviderAttempt, SearchRequest
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SearchProviderConfig:
|
||||
name: str
|
||||
provider_type: str
|
||||
enabled: bool = True
|
||||
requires_secret: bool = False
|
||||
supports_public_web: bool = True
|
||||
supports_authorized_sources: bool = False
|
||||
health: str = "unknown"
|
||||
metadata: dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
class NullSearchProvider:
|
||||
"""Safe placeholder provider used until runtime wires a real adapter."""
|
||||
|
||||
def __init__(self, config: SearchProviderConfig):
|
||||
self.config = config
|
||||
self.name = config.name
|
||||
|
||||
def search(self, request: SearchRequest, queries: list[str]):
|
||||
return [], SearchProviderAttempt(
|
||||
provider=self.name,
|
||||
status="not_configured" if self.config.enabled else "disabled",
|
||||
result_count=0,
|
||||
reason="provider adapter not wired in runtime",
|
||||
)
|
||||
|
||||
|
||||
class StaticArchiveProvider:
|
||||
"""Small deterministic provider for tests and internal archived evidence."""
|
||||
|
||||
name = "internal_archive"
|
||||
|
||||
def __init__(self, records: list[dict[str, Any]] | None = None):
|
||||
self.records = records or []
|
||||
|
||||
def search(self, request: SearchRequest, queries: list[str]):
|
||||
evidence: list[SearchEvidence] = []
|
||||
for record in self.records:
|
||||
haystack = " ".join([record.get("title", ""), record.get("snippet", ""), record.get("tags", "")]).lower()
|
||||
if any(q.lower() in haystack for q in queries):
|
||||
evidence.append(
|
||||
SearchEvidence(
|
||||
title=record.get("title", "archive result"),
|
||||
url=record.get("url"),
|
||||
source=self.name,
|
||||
snippet=record.get("snippet", ""),
|
||||
evidence_type="internal_archive",
|
||||
confidence=record.get("confidence", "medium"),
|
||||
)
|
||||
)
|
||||
return evidence, SearchProviderAttempt(provider=self.name, status="ok", result_count=len(evidence))
|
||||
|
||||
|
||||
class SearchProviderRegistry:
|
||||
DEFAULT_PROVIDER_CONFIGS = [
|
||||
SearchProviderConfig("cache", "cache", supports_public_web=False),
|
||||
SearchProviderConfig("official_site", "official_site"),
|
||||
SearchProviderConfig("general_web", "general_web"),
|
||||
SearchProviderConfig("vertical_source", "vertical_source"),
|
||||
SearchProviderConfig("browser_fetch", "browser_fetch"),
|
||||
SearchProviderConfig("user_authorized_file", "authorized_file", supports_public_web=False, supports_authorized_sources=True),
|
||||
SearchProviderConfig("internal_archive", "archive", supports_public_web=False),
|
||||
]
|
||||
|
||||
def __init__(self):
|
||||
self.configs: dict[str, SearchProviderConfig] = {}
|
||||
self.providers: dict[str, Any] = {}
|
||||
for config in self.DEFAULT_PROVIDER_CONFIGS:
|
||||
self.register_config(config)
|
||||
|
||||
def register_config(self, config: SearchProviderConfig) -> None:
|
||||
self.configs[config.name] = config
|
||||
self.providers.setdefault(config.name, NullSearchProvider(config))
|
||||
|
||||
def register_provider(self, name: str, provider: Any, config: SearchProviderConfig | None = None) -> None:
|
||||
if config:
|
||||
self.configs[name] = config
|
||||
elif name not in self.configs:
|
||||
self.configs[name] = SearchProviderConfig(name=name, provider_type="custom")
|
||||
self.providers[name] = provider
|
||||
|
||||
def ordered(self, order: list[str] | None = None) -> list[Any]:
|
||||
order = order or list(self.configs)
|
||||
result = [self.providers[name] for name in order if name in self.providers and self.configs[name].enabled]
|
||||
result.extend([provider for name, provider in self.providers.items() if name not in order and self.configs[name].enabled])
|
||||
return result
|
||||
|
||||
def status(self) -> dict[str, Any]:
|
||||
return {
|
||||
"providers": [self.configs[name].to_dict() for name in sorted(self.configs)],
|
||||
"enabled": len([c for c in self.configs.values() if c.enabled]),
|
||||
"configured": len([name for name, provider in self.providers.items() if not isinstance(provider, NullSearchProvider)]),
|
||||
}
|
||||
|
||||
|
||||
__all__ = [
|
||||
"SearchProviderConfig",
|
||||
"NullSearchProvider",
|
||||
"StaticArchiveProvider",
|
||||
"SearchProviderRegistry",
|
||||
]
|
||||
@@ -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 +1,41 @@
|
||||
"""Task Center action API model for Web UI buttons."""
|
||||
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from fastapi import APIRouter
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .task_lifecycle import TaskLifecycle
|
||||
|
||||
|
||||
lifecycle = TaskLifecycle()
|
||||
|
||||
|
||||
def get_task_actions(task: dict[str, Any], role: str) -> dict[str, Any]:
|
||||
return {
|
||||
"task_id": task.get("task_id"),
|
||||
"actions": lifecycle.available_actions(task, role),
|
||||
}
|
||||
|
||||
|
||||
def execute_task_action(task: dict[str, Any], action: str, role: str, reason: str | None = None):
|
||||
return lifecycle.transition(task, action, role, reason)
|
||||
|
||||
|
||||
def build_router():
|
||||
if APIRouter is None:
|
||||
return None
|
||||
router = APIRouter(prefix="/admin/ai-evolution/tasks", tags=["task-actions"])
|
||||
|
||||
@router.post("/{task_id}/actions/{action}", operation_id="executeTaskAction")
|
||||
def action(task_id: str, action: str, payload: dict[str, Any]):
|
||||
return execute_task_action(payload.get("task", {}), action, payload.get("role", "user"), payload.get("reason"))
|
||||
|
||||
return router
|
||||
|
||||
|
||||
router = build_router()
|
||||
|
||||
__all__ = ["router", "get_task_actions", "execute_task_action"]
|
||||
@@ -0,0 +1,115 @@
|
||||
"""AIOS Task Center domain model.
|
||||
|
||||
The Task Center gives owners and authorized users a single Web UI page showing:
|
||||
who assigned a task, who is executing it, progress, elapsed time, remaining
|
||||
work, and whether completion notifications were sent.
|
||||
"""
|
||||
|
||||
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()
|
||||
|
||||
|
||||
def parse_time(value: str | None) -> datetime | None:
|
||||
if not value:
|
||||
return None
|
||||
return datetime.fromisoformat(value.replace("Z", "+00:00"))
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskNotificationStatus:
|
||||
required: bool = True
|
||||
sent: bool = False
|
||||
channel: str | None = None
|
||||
sent_at: str | None = None
|
||||
recipient_scope: str | None = None
|
||||
last_error: str | None = None
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskProgress:
|
||||
percent: int = 0
|
||||
current_step: str = "pending"
|
||||
completed_steps: list[str] = field(default_factory=list)
|
||||
remaining_steps: list[str] = field(default_factory=list)
|
||||
blocked_reason: str | None = None
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AIOSTaskRecord:
|
||||
task_id: str
|
||||
title: str
|
||||
assigned_by: str
|
||||
executor: str
|
||||
source: str
|
||||
status: str = "pending"
|
||||
priority: str = "normal"
|
||||
created_at: str = field(default_factory=utc_now)
|
||||
started_at: str | None = None
|
||||
updated_at: str = field(default_factory=utc_now)
|
||||
completed_at: str | None = None
|
||||
progress: TaskProgress = field(default_factory=TaskProgress)
|
||||
notification: TaskNotificationStatus = field(default_factory=TaskNotificationStatus)
|
||||
owner_gate_required: bool = False
|
||||
owner_gate_status: str | None = None
|
||||
evidence: list[str] = field(default_factory=list)
|
||||
|
||||
def elapsed_seconds(self) -> int:
|
||||
start = parse_time(self.started_at) or parse_time(self.created_at)
|
||||
end = parse_time(self.completed_at) or datetime.now(timezone.utc)
|
||||
return int((end - start).total_seconds()) if start else 0
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
data = asdict(self)
|
||||
data["elapsed_seconds"] = self.elapsed_seconds()
|
||||
data["progress"] = self.progress.to_dict()
|
||||
data["notification"] = self.notification.to_dict()
|
||||
return data
|
||||
|
||||
|
||||
class TaskCenter:
|
||||
def summarize(self, tasks: list[AIOSTaskRecord] | list[dict[str, Any]] | None = None) -> dict[str, Any]:
|
||||
raw_tasks = tasks or []
|
||||
task_dicts = [t.to_dict() if hasattr(t, "to_dict") else dict(t) for t in raw_tasks]
|
||||
active = [t for t in task_dicts if t.get("status") in {"running", "pending", "blocked"}]
|
||||
blocked = [t for t in task_dicts if t.get("status") == "blocked"]
|
||||
completed = [t for t in task_dicts if t.get("status") == "completed"]
|
||||
notification_pending = [
|
||||
t for t in completed
|
||||
if t.get("notification", {}).get("required") and not t.get("notification", {}).get("sent")
|
||||
]
|
||||
return {
|
||||
"module": "task-center",
|
||||
"route": "/admin/ai-evolution/tasks",
|
||||
"title": "AIOS 任务中心",
|
||||
"status": "attention_required" if blocked or notification_pending else "healthy",
|
||||
"generated_at": utc_now(),
|
||||
"summary": {
|
||||
"total": len(task_dicts),
|
||||
"active": len(active),
|
||||
"blocked": len(blocked),
|
||||
"completed": len(completed),
|
||||
"notification_pending": len(notification_pending),
|
||||
},
|
||||
"tasks": sorted(task_dicts, key=lambda t: t.get("updated_at", ""), reverse=True),
|
||||
}
|
||||
|
||||
|
||||
__all__ = [
|
||||
"TaskNotificationStatus",
|
||||
"TaskProgress",
|
||||
"AIOSTaskRecord",
|
||||
"TaskCenter",
|
||||
]
|
||||
@@ -0,0 +1,34 @@
|
||||
"""Task Center API."""
|
||||
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from fastapi import APIRouter
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .task_center import TaskCenter
|
||||
|
||||
|
||||
task_center = TaskCenter()
|
||||
|
||||
|
||||
def get_task_overview(tasks: list[dict[str, Any]] | None = None):
|
||||
return task_center.summarize(tasks)
|
||||
|
||||
|
||||
def build_router():
|
||||
if APIRouter is None:
|
||||
return None
|
||||
router = APIRouter(prefix="/admin/ai-evolution/tasks", tags=["task-center"])
|
||||
|
||||
@router.get("/overview", operation_id="getTaskCenterOverview")
|
||||
def overview():
|
||||
return get_task_overview()
|
||||
|
||||
return router
|
||||
|
||||
|
||||
router = build_router()
|
||||
|
||||
__all__ = ["router", "get_task_overview"]
|
||||
@@ -0,0 +1,81 @@
|
||||
"""Task Center visualization model."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
|
||||
class TaskDashboardView:
|
||||
def build(self, tasks: list[dict[str, Any]] | None = None) -> dict[str, Any]:
|
||||
tasks = tasks or []
|
||||
return {
|
||||
"module": "task-center",
|
||||
"route": "/admin/ai-evolution/tasks",
|
||||
"title": "AIOS Task Center",
|
||||
"views": {
|
||||
"kanban": self._kanban(tasks),
|
||||
"timeline": self._timeline(tasks),
|
||||
"flow": self._flow(tasks),
|
||||
"statistics": self._statistics(tasks),
|
||||
},
|
||||
"tasks": [self._task_card(task) for task in tasks],
|
||||
}
|
||||
|
||||
def _task_card(self, task: dict[str, Any]) -> dict[str, Any]:
|
||||
return {
|
||||
"task_id": task.get("task_id"),
|
||||
"title": task.get("title"),
|
||||
"assigned_by": task.get("assigned_by"),
|
||||
"executor": task.get("executor"),
|
||||
"status": task.get("status"),
|
||||
"progress": task.get("progress", {}),
|
||||
"elapsed_seconds": task.get("elapsed_seconds", 0),
|
||||
"remaining_steps": task.get("progress", {}).get("remaining_steps", []),
|
||||
"notification": task.get("notification", {}),
|
||||
"actions": [
|
||||
"start",
|
||||
"update_progress",
|
||||
"block",
|
||||
"request_approval",
|
||||
"approve",
|
||||
"reject",
|
||||
"retry",
|
||||
"complete",
|
||||
"notify",
|
||||
"close",
|
||||
],
|
||||
}
|
||||
|
||||
def _kanban(self, tasks):
|
||||
columns = {"pending": [], "running": [], "blocked": [], "waiting_approval": [], "completed": []}
|
||||
for task in tasks:
|
||||
columns.setdefault(task.get("status", "pending"), []).append(task.get("task_id"))
|
||||
return columns
|
||||
|
||||
def _timeline(self, tasks):
|
||||
return [
|
||||
{
|
||||
"task_id": task.get("task_id"),
|
||||
"updated_at": task.get("updated_at"),
|
||||
"status": task.get("status"),
|
||||
}
|
||||
for task in tasks
|
||||
]
|
||||
|
||||
def _flow(self, tasks):
|
||||
return {
|
||||
"nodes": ["created", "assigned", "running", "blocked", "approval", "completed", "closed"],
|
||||
"task_count": len(tasks),
|
||||
}
|
||||
|
||||
def _statistics(self, tasks):
|
||||
return {
|
||||
"total": len(tasks),
|
||||
"running": len([t for t in tasks if t.get("status") == "running"]),
|
||||
"blocked": len([t for t in tasks if t.get("status") == "blocked"]),
|
||||
"waiting_approval": len([t for t in tasks if t.get("status") == "waiting_approval"]),
|
||||
"completed": len([t for t in tasks if t.get("status") == "completed"]),
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["TaskDashboardView"]
|
||||
@@ -0,0 +1,129 @@
|
||||
"""Task Center event bridge.
|
||||
|
||||
Converts task lifecycle actions and agent execution events into normalized AIOS
|
||||
Task Center events. Uses duck-typed Agent Event Bus publisher when available and
|
||||
an in-memory fallback for tests/offline runs.
|
||||
"""
|
||||
|
||||
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 TaskEventPublisher(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 TaskEvent:
|
||||
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 InMemoryTaskEventBus:
|
||||
def __init__(self):
|
||||
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 = TaskEvent(
|
||||
id=f"task_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 TaskEventBridge:
|
||||
def __init__(self, bus: TaskEventPublisher | None = None):
|
||||
self.bus = bus or InMemoryTaskEventBus()
|
||||
|
||||
def task_created(self, task: dict[str, Any]) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="task_created",
|
||||
source=task.get("assigned_by", "unknown"),
|
||||
target=task.get("executor", "task-center"),
|
||||
summary=task.get("title", "task created"),
|
||||
payload=task,
|
||||
correlation_id=task.get("task_id"),
|
||||
)
|
||||
|
||||
def task_updated(self, task: dict[str, Any], action: str) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="task_updated",
|
||||
source=task.get("executor", "task-center"),
|
||||
target="task-center",
|
||||
summary=f"task {action}: {task.get('status')}",
|
||||
payload={"action": action, "task": task},
|
||||
correlation_id=task.get("task_id"),
|
||||
)
|
||||
|
||||
def task_blocked(self, task: dict[str, Any], reason: str) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="task_blocked",
|
||||
source=task.get("executor", "unknown"),
|
||||
target="owner-gate",
|
||||
summary=reason,
|
||||
payload={"task": task, "reason": reason},
|
||||
correlation_id=task.get("task_id"),
|
||||
)
|
||||
|
||||
def approval_requested(self, task: dict[str, Any], reason: str) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="task_approval_requested",
|
||||
source=task.get("executor", "unknown"),
|
||||
target="owner-gate",
|
||||
summary=reason,
|
||||
payload={"task": task, "reason": reason},
|
||||
correlation_id=task.get("task_id"),
|
||||
)
|
||||
|
||||
def notification_sent(self, task: dict[str, Any], channel: str) -> dict[str, Any]:
|
||||
return self.bus.publish(
|
||||
kind="task_notification_sent",
|
||||
source="notification-agent",
|
||||
target=task.get("assigned_by", "owner"),
|
||||
summary=f"notification sent via {channel}",
|
||||
payload={"task": task, "channel": channel},
|
||||
correlation_id=task.get("task_id"),
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["TaskEvent", "InMemoryTaskEventBus", "TaskEventBridge"]
|
||||
@@ -0,0 +1,147 @@
|
||||
"""AIOS Task Lifecycle.
|
||||
|
||||
Defines a governed task state machine for task creation, assignment, execution,
|
||||
blocking, approval, retry, completion, notification and closure.
|
||||
"""
|
||||
|
||||
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()
|
||||
|
||||
|
||||
TERMINAL_STATES = {"completed", "cancelled", "failed", "closed"}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskTransition:
|
||||
action: str
|
||||
from_states: set[str]
|
||||
to_state: str
|
||||
required_role: str = "agent"
|
||||
requires_reason: bool = False
|
||||
notify: bool = False
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
data = asdict(self)
|
||||
data["from_states"] = sorted(self.from_states)
|
||||
return data
|
||||
|
||||
|
||||
class TaskLifecycle:
|
||||
"""Central task state machine."""
|
||||
|
||||
TRANSITIONS = {
|
||||
"assign": TaskTransition("assign", {"new", "pending"}, "assigned", "dispatcher"),
|
||||
"start": TaskTransition("start", {"assigned", "pending"}, "running", "executor"),
|
||||
"update_progress": TaskTransition("update_progress", {"running"}, "running", "executor"),
|
||||
"block": TaskTransition("block", {"running", "assigned", "pending"}, "blocked", "executor", requires_reason=True, notify=True),
|
||||
"request_approval": TaskTransition("request_approval", {"running", "blocked"}, "waiting_approval", "executor", requires_reason=True, notify=True),
|
||||
"approve": TaskTransition("approve", {"waiting_approval"}, "approved", "owner", notify=True),
|
||||
"reject": TaskTransition("reject", {"waiting_approval"}, "rejected", "owner", requires_reason=True, notify=True),
|
||||
"resume": TaskTransition("resume", {"blocked", "approved"}, "running", "executor"),
|
||||
"retry": TaskTransition("retry", {"failed", "blocked"}, "running", "executor", notify=True),
|
||||
"complete": TaskTransition("complete", {"running", "approved"}, "completed", "executor", notify=True),
|
||||
"notify": TaskTransition("notify", {"completed"}, "completed", "notifier"),
|
||||
"close": TaskTransition("close", {"completed", "cancelled", "failed"}, "closed", "owner"),
|
||||
"cancel": TaskTransition("cancel", {"new", "pending", "assigned", "running", "blocked", "waiting_approval"}, "cancelled", "owner", requires_reason=True, notify=True),
|
||||
"fail": TaskTransition("fail", {"running", "assigned"}, "failed", "executor", requires_reason=True, notify=True),
|
||||
}
|
||||
|
||||
ROLE_ORDER = {
|
||||
"user": 1,
|
||||
"agent": 2,
|
||||
"executor": 3,
|
||||
"dispatcher": 4,
|
||||
"notifier": 4,
|
||||
"group_admin": 5,
|
||||
"owner": 9,
|
||||
}
|
||||
|
||||
def available_actions(self, task: dict[str, Any], role: str) -> list[dict[str, Any]]:
|
||||
state = task.get("status", "new")
|
||||
actions = []
|
||||
for name, transition in self.TRANSITIONS.items():
|
||||
allowed_state = state in transition.from_states
|
||||
allowed_role = self._role_allows(role, transition.required_role)
|
||||
actions.append({
|
||||
"action": name,
|
||||
"label": self._label(name),
|
||||
"enabled": allowed_state and allowed_role,
|
||||
"from_state": state,
|
||||
"to_state": transition.to_state,
|
||||
"required_role": transition.required_role,
|
||||
"requires_reason": transition.requires_reason,
|
||||
"notify": transition.notify,
|
||||
"disabled_reason": None if allowed_state and allowed_role else self._disabled_reason(allowed_state, allowed_role, transition),
|
||||
})
|
||||
return actions
|
||||
|
||||
def transition(self, task: dict[str, Any], action: str, actor_role: str, reason: str | None = None) -> dict[str, Any]:
|
||||
if action not in self.TRANSITIONS:
|
||||
raise ValueError(f"unknown task action: {action}")
|
||||
transition = self.TRANSITIONS[action]
|
||||
state = task.get("status", "new")
|
||||
if state not in transition.from_states:
|
||||
raise ValueError(f"action {action} not allowed from state {state}")
|
||||
if not self._role_allows(actor_role, transition.required_role):
|
||||
raise PermissionError(f"role {actor_role} cannot execute {action}; requires {transition.required_role}")
|
||||
if transition.requires_reason and not reason:
|
||||
raise ValueError(f"action {action} requires reason")
|
||||
updated = dict(task)
|
||||
updated["status"] = transition.to_state
|
||||
updated["updated_at"] = utc_now()
|
||||
history = list(updated.get("history", []))
|
||||
history.append({
|
||||
"action": action,
|
||||
"from": state,
|
||||
"to": transition.to_state,
|
||||
"actor_role": actor_role,
|
||||
"reason": reason,
|
||||
"ts": utc_now(),
|
||||
})
|
||||
updated["history"] = history
|
||||
if action == "complete":
|
||||
updated["completed_at"] = utc_now()
|
||||
notification = dict(updated.get("notification", {}))
|
||||
notification.setdefault("required", True)
|
||||
notification.setdefault("sent", False)
|
||||
updated["notification"] = notification
|
||||
return updated
|
||||
|
||||
def _role_allows(self, role: str, required: str) -> bool:
|
||||
return self.ROLE_ORDER.get(role, 0) >= self.ROLE_ORDER.get(required, 0)
|
||||
|
||||
def _label(self, action: str) -> str:
|
||||
labels = {
|
||||
"assign": "分配任务",
|
||||
"start": "开始执行",
|
||||
"update_progress": "更新进度",
|
||||
"block": "标记阻塞",
|
||||
"request_approval": "请求审批",
|
||||
"approve": "批准",
|
||||
"reject": "拒绝",
|
||||
"resume": "继续执行",
|
||||
"retry": "重试",
|
||||
"complete": "标记完成",
|
||||
"notify": "发送通知",
|
||||
"close": "关闭任务",
|
||||
"cancel": "取消任务",
|
||||
"fail": "标记失败",
|
||||
}
|
||||
return labels.get(action, action)
|
||||
|
||||
def _disabled_reason(self, allowed_state: bool, allowed_role: bool, transition: TaskTransition) -> str:
|
||||
if not allowed_state:
|
||||
return "当前状态不允许该操作"
|
||||
if not allowed_role:
|
||||
return f"需要角色: {transition.required_role}"
|
||||
return "不可用"
|
||||
|
||||
|
||||
__all__ = ["TaskTransition", "TaskLifecycle", "TERMINAL_STATES"]
|
||||
@@ -0,0 +1,50 @@
|
||||
"""Task Center orchestrator.
|
||||
|
||||
Coordinates task ingestion, persistence, lifecycle updates, events and statistics.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from .task_event_bridge import TaskEventBridge
|
||||
from .task_source_ingestor import TaskSourceIngestor
|
||||
from .task_statistics import TaskStatistics
|
||||
from .task_store import TaskStore
|
||||
|
||||
|
||||
class TaskOrchestrator:
|
||||
def __init__(self):
|
||||
self.ingestor = TaskSourceIngestor()
|
||||
self.store = TaskStore()
|
||||
self.events = TaskEventBridge()
|
||||
self.statistics = TaskStatistics()
|
||||
|
||||
def create_from_command(self, path: str, bucket: str = "active") -> dict[str, Any]:
|
||||
task = self.ingestor.command_file_to_task(path, bucket)
|
||||
self.store.append(task)
|
||||
self.events.task_created(task)
|
||||
return task
|
||||
|
||||
def create_from_agent_execution(self, record: dict[str, Any]) -> dict[str, Any]:
|
||||
task = self.ingestor.agent_execution_to_task(record)
|
||||
self.store.append(task)
|
||||
self.events.task_created(task)
|
||||
return task
|
||||
|
||||
def sync_event(self, event: dict[str, Any]) -> dict[str, Any] | None:
|
||||
task = self.ingestor.event_to_task(event)
|
||||
if task:
|
||||
self.store.append(task)
|
||||
self.events.task_updated(task, event.get("kind", "event"))
|
||||
return task
|
||||
|
||||
def dashboard(self) -> dict[str, Any]:
|
||||
tasks = self.store.latest()
|
||||
return {
|
||||
"tasks": tasks,
|
||||
"statistics": self.statistics.summarize(tasks),
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["TaskOrchestrator"]
|
||||
@@ -0,0 +1,159 @@
|
||||
"""Task source ingestion for AIOS Task Center.
|
||||
|
||||
Converts Command Watcher files, OpenClaw/Hermes/Codex execution records and
|
||||
Generic Agent Event Bus records into normalized Task Center task dictionaries.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskSourceRecord:
|
||||
source_type: str
|
||||
source_id: str
|
||||
title: str
|
||||
assigned_by: str
|
||||
executor: str
|
||||
status: str
|
||||
priority: str = "normal"
|
||||
created_at: str = field(default_factory=utc_now)
|
||||
updated_at: str = field(default_factory=utc_now)
|
||||
evidence: list[str] = field(default_factory=list)
|
||||
metadata: dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
def to_task(self) -> dict[str, Any]:
|
||||
return {
|
||||
"task_id": f"task-{self.source_type}-{self.source_id}",
|
||||
"title": self.title,
|
||||
"assigned_by": self.assigned_by,
|
||||
"executor": self.executor,
|
||||
"source": self.source_type,
|
||||
"status": self.status,
|
||||
"priority": self.priority,
|
||||
"created_at": self.created_at,
|
||||
"updated_at": self.updated_at,
|
||||
"progress": {
|
||||
"percent": self._progress_percent(),
|
||||
"current_step": self.status,
|
||||
"completed_steps": [],
|
||||
"remaining_steps": [],
|
||||
"blocked_reason": self.metadata.get("blocked_reason"),
|
||||
},
|
||||
"notification": {
|
||||
"required": True,
|
||||
"sent": bool(self.metadata.get("notification_sent")),
|
||||
"channel": self.metadata.get("notification_channel"),
|
||||
"sent_at": self.metadata.get("notification_sent_at"),
|
||||
},
|
||||
"evidence": self.evidence,
|
||||
"metadata": self.metadata,
|
||||
}
|
||||
|
||||
def _progress_percent(self) -> int:
|
||||
mapping = {
|
||||
"new": 0,
|
||||
"pending": 5,
|
||||
"assigned": 15,
|
||||
"running": 50,
|
||||
"blocked": 50,
|
||||
"waiting_approval": 60,
|
||||
"approved": 70,
|
||||
"completed": 100,
|
||||
"closed": 100,
|
||||
"failed": 100,
|
||||
"cancelled": 100,
|
||||
}
|
||||
return mapping.get(self.status, 0)
|
||||
|
||||
|
||||
class TaskSourceIngestor:
|
||||
COMMAND_STATUS_MAP = {
|
||||
"active": "pending",
|
||||
"running": "running",
|
||||
"completed": "completed",
|
||||
"failed": "failed",
|
||||
"archive": "closed",
|
||||
}
|
||||
|
||||
def command_file_to_task(self, path: str, bucket: str = "active") -> dict[str, Any]:
|
||||
p = Path(path)
|
||||
title = p.stem
|
||||
return TaskSourceRecord(
|
||||
source_type="command_watcher",
|
||||
source_id=title,
|
||||
title=title,
|
||||
assigned_by="command-watcher",
|
||||
executor=self._infer_executor(title),
|
||||
status=self.COMMAND_STATUS_MAP.get(bucket, "pending"),
|
||||
priority="high" if "P0" in title or "fix" in title.lower() else "normal",
|
||||
evidence=[str(p)],
|
||||
metadata={"bucket": bucket},
|
||||
).to_task()
|
||||
|
||||
def agent_execution_to_task(self, record: dict[str, Any]) -> dict[str, Any]:
|
||||
source_id = record.get("execution_id", record.get("id", "unknown"))
|
||||
status = record.get("status", "running")
|
||||
return TaskSourceRecord(
|
||||
source_type="agent_execution",
|
||||
source_id=source_id,
|
||||
title=record.get("title", f"Agent execution {source_id}"),
|
||||
assigned_by=record.get("assigned_by", record.get("entry_agent", "agent-system")),
|
||||
executor=record.get("closed_by", record.get("entry_agent", "unknown-agent")),
|
||||
status=status,
|
||||
priority=record.get("priority", "normal"),
|
||||
created_at=record.get("started_at", utc_now()),
|
||||
updated_at=record.get("ended_at", utc_now()),
|
||||
evidence=[record.get("execution_id", source_id)],
|
||||
metadata=record,
|
||||
).to_task()
|
||||
|
||||
def event_to_task(self, event: dict[str, Any]) -> dict[str, Any] | None:
|
||||
kind = event.get("kind")
|
||||
payload = event.get("payload", {})
|
||||
if kind not in {"task_created", "task_updated", "agent_started", "agent_completed", "agent_failed", "search_started", "search_completed"}:
|
||||
return None
|
||||
source_id = event.get("correlation_id") or event.get("id", "event")
|
||||
status = self._status_from_event(kind, payload)
|
||||
return TaskSourceRecord(
|
||||
source_type="event_bus",
|
||||
source_id=source_id,
|
||||
title=payload.get("title") or event.get("summary", kind),
|
||||
assigned_by=event.get("source", "event-bus"),
|
||||
executor=event.get("target", "task-center"),
|
||||
status=status,
|
||||
created_at=event.get("created_at", utc_now()),
|
||||
updated_at=event.get("created_at", utc_now()),
|
||||
evidence=[event.get("id", source_id)],
|
||||
metadata={"event_kind": kind, "payload": payload},
|
||||
).to_task()
|
||||
|
||||
def _status_from_event(self, kind: str, payload: dict[str, Any]) -> str:
|
||||
if kind.endswith("completed"):
|
||||
return "completed"
|
||||
if kind.endswith("failed"):
|
||||
return "failed"
|
||||
return payload.get("status", "running")
|
||||
|
||||
def _infer_executor(self, title: str) -> str:
|
||||
lower = title.lower()
|
||||
if "openclaw" in lower:
|
||||
return "openclaw"
|
||||
if "hermes" in lower:
|
||||
return "hermes"
|
||||
if "codex" in lower:
|
||||
return "codex"
|
||||
if "search" in lower:
|
||||
return "openclaw"
|
||||
return "openclaw"
|
||||
|
||||
|
||||
__all__ = ["TaskSourceRecord", "TaskSourceIngestor"]
|
||||
@@ -0,0 +1,33 @@
|
||||
"""Task Center statistics."""
|
||||
|
||||
from typing import Any
|
||||
|
||||
|
||||
class TaskStatistics:
|
||||
def summarize(self, tasks: list[dict[str, Any]] | None = None) -> dict[str, Any]:
|
||||
tasks = tasks or []
|
||||
completed = [t for t in tasks if t.get("status") == "completed"]
|
||||
blocked = [t for t in tasks if t.get("status") == "blocked"]
|
||||
waiting = [t for t in tasks if t.get("status") == "waiting_approval"]
|
||||
elapsed = [t.get("elapsed_seconds", 0) for t in tasks if t.get("elapsed_seconds") is not None]
|
||||
return {
|
||||
"total": len(tasks),
|
||||
"completed": len(completed),
|
||||
"blocked": len(blocked),
|
||||
"waiting_approval": len(waiting),
|
||||
"completion_rate": round(len(completed) / len(tasks) * 100, 2) if tasks else 0,
|
||||
"average_elapsed_seconds": round(sum(elapsed) / len(elapsed), 2) if elapsed else 0,
|
||||
"top_blockers": self._top_values(blocked, "blocker"),
|
||||
"executor_distribution": self._top_values(tasks, "executor"),
|
||||
}
|
||||
|
||||
def _top_values(self, tasks: list[dict[str, Any]], key: str):
|
||||
result: dict[str, int] = {}
|
||||
for task in tasks:
|
||||
value = task.get(key)
|
||||
if value:
|
||||
result[value] = result.get(value, 0) + 1
|
||||
return result
|
||||
|
||||
|
||||
__all__ = ["TaskStatistics"]
|
||||
@@ -0,0 +1,29 @@
|
||||
"""Persistent Task Center store."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
|
||||
class TaskStore:
|
||||
def __init__(self, root: str = "runtime/task-center"):
|
||||
self.root = Path(root)
|
||||
self.root.mkdir(parents=True, exist_ok=True)
|
||||
self.path = self.root / "tasks.jsonl"
|
||||
|
||||
def append(self, task: dict[str, Any]) -> None:
|
||||
with self.path.open("a", encoding="utf-8") as f:
|
||||
f.write(json.dumps(task, ensure_ascii=False) + "\n")
|
||||
|
||||
def list_all(self) -> list[dict[str, Any]]:
|
||||
if not self.path.exists():
|
||||
return []
|
||||
return [json.loads(line) for line in self.path.read_text(encoding="utf-8").splitlines() if line]
|
||||
|
||||
def latest(self) -> list[dict[str, Any]]:
|
||||
return self.list_all()[-100:]
|
||||
|
||||
|
||||
__all__ = ["TaskStore"]
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user