Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4e0e6dcb90 | ||
|
|
0778a31ec0 | ||
|
|
80c4cbde03 | ||
|
|
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 |
@@ -0,0 +1,3 @@
|
||||
d23bb1ec24a7f49359314e04cd2c04c8f38876e45f25a701506499d1b34f270f MANIFEST-AIOS-V2R1-HERMES-LIFECYCLE-20260721.json
|
||||
5ce2894fdf8a22622954a1a10fb09fbab74af04f0260b249615c70236ff31731 RESULT-AIOS-V2R1-HERMES-LIFECYCLE-20260721.md
|
||||
ca2ab3c22c2b2b33bbc03e59f1206b999ad1271de3e1938fd3a0b4234c613eef ../../../docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md
|
||||
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"schema_version": "aios.evidence.manifest.v1",
|
||||
"generated_at": "2026-07-21T05:50:00Z",
|
||||
"branch": "patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721",
|
||||
"validated_oid": "95d2e52cb55c7b913e89bc6bed2bcdacf67512d4",
|
||||
"evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z",
|
||||
"evidence_hashes": {
|
||||
"steps.tsv": "b2ad20585ba7f576e85657827a0b1db6f252887bbd73bcd718df38623e9d95cf",
|
||||
"final-live-gate.log": "82040c674759dacf587658c5e936c313a1f50e8e2425be48ad891927befdf4fa",
|
||||
"16R.log": "641246927a372ebaa9e6dde8b018b88275b2ba15a442473759b23fb1f215d9cf",
|
||||
"15.log": "b0a474e2a74164f560c4f7572091911f32011c75faccd37a3c7315046275011e",
|
||||
"13.log": "b9f637cca6e97ed893bf38530e05cd33b78e324c5e8865d4c602dfeac22a7710",
|
||||
"12R2.log": "0c431f5f5f1c1b17acda160c917b08c7f4036485016c23e1236b9b6f4a78de67"
|
||||
},
|
||||
"validation": {
|
||||
"candidate_tests": {"passed": 49, "failed": 0},
|
||||
"hermes_lifecycle": {"passed": 17, "failed": 0},
|
||||
"gate_b": {"passed": 10, "failed": 0},
|
||||
"offline_acceptance": {"passed": 8, "failed": 0, "expected_warnings": 1},
|
||||
"openclaw_real_http": "PASS",
|
||||
"restart_recovery": "PASS",
|
||||
"rollback_forward": "PASS",
|
||||
"state_preservation": "PASS",
|
||||
"final_health_corrected_16R": "PASS"
|
||||
},
|
||||
"git_gate": {
|
||||
"oid_match": true,
|
||||
"candidate_clean": true,
|
||||
"active_controller_clean": true,
|
||||
"locked": 0,
|
||||
"prunable": 0,
|
||||
"worktree_total": 88,
|
||||
"worktree_dirty": 10,
|
||||
"global_worktree_clean": false
|
||||
},
|
||||
"resolved_blockers": [],
|
||||
"active_blockers": [
|
||||
"BLK-LIVE-HERMES-FULL-LIFECYCLE-EVIDENCE-MISSING",
|
||||
"BLK-GLOBAL-WORKTREE-CLEANLINESS"
|
||||
],
|
||||
"overall": "PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS",
|
||||
"release_decision": "STOP_PREPRODUCTION",
|
||||
"secrets_recorded": false
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
# AIOS V2R1 Hermes Lifecycle Result
|
||||
|
||||
- Branch: `patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721`
|
||||
- Validated OID: `95d2e52cb55c7b913e89bc6bed2bcdacf67512d4`
|
||||
- Evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z`
|
||||
- Hermes blocker: `EVIDENCE_COMPLETE / FORMAL_CLOSURE_BLOCKED`
|
||||
- Overall: `PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS`
|
||||
- Release decision: `STOP_PREPRODUCTION`
|
||||
|
||||
Hermes lifecycle `17/17`, candidate `49/49`, Gate B `10/10`, offline acceptance `8/0/1`, OpenClaw real HTTP, restart recovery, rollback/forward, state preservation and corrected final health all passed at the validated OID. The Owner acceptance contract nevertheless forbids formally closing the Hermes blocker until every global gate also passes.
|
||||
|
||||
The candidate worktree and active Controller worktree are clean; local, worktree and Gitea OIDs match; locked/prunable are zero. The global authority currently has 10 dirty worktrees out of 88, so the Owner hard gate requiring every worktree to be clean fails.
|
||||
|
||||
No RC, Tag Approval Request, Tag, main mutation, force push, production traffic switch or secret disclosure was performed.
|
||||
|
||||
See `MANIFEST-AIOS-V2R1-HERMES-LIFECYCLE-20260721.json` and `docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md`.
|
||||
@@ -0,0 +1,12 @@
|
||||
# V2R1C1 Cleanup Closure
|
||||
|
||||
- `CLEANUP_REVIEW=PASS`
|
||||
- `ARCHIVE_VALIDATION=PASS`
|
||||
- `GLOBAL_WORKTREE_CLEAN=true`
|
||||
- `global_dirty_count=0`
|
||||
- `locked=0`
|
||||
- `prunable=0`
|
||||
- Portal Archive OID: `99671cc14d2631f989e0763dc882e4001c50a1ea`
|
||||
- Spark Archive OID: `d97cd3642528bd3373fe4cf5161a5d99c0b9285f`
|
||||
|
||||
Closure evidence: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-blocker-clear-20260721T075647Z`.
|
||||
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"schema_version": "aios.v2r1c1.deployment-manifest.v1",
|
||||
"vrc": "V2R1C1",
|
||||
"release_branch": "release/AIOS-V2R1C1-20260721",
|
||||
"old_release_oid": "80c4cbde03a82c30648a09b817bc2f03d5402936",
|
||||
"validated_release_parent_oid": "0778a31ec073e7c90003ef091f1d093c16bf22e5",
|
||||
"product_baseline_oid": "fb739f6e8ff9c031d319221ace68dce157694086",
|
||||
"companion": {
|
||||
"branch": "patch/openclaw/AIOS-V2R1C1-COMMAND-V2-COMPANION-20260721",
|
||||
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
|
||||
"oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
|
||||
"plugin_version": "2.1.0-rc.4",
|
||||
"contract_version": "aios.openclaw.command.v2",
|
||||
"signature_algorithm": "Ed25519",
|
||||
"verification_key_id": "openclaw-v2r1-candidate-ed25519",
|
||||
"artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671"
|
||||
},
|
||||
"isolated_validation": {
|
||||
"service": "aios-v2r1c1-openclaw-companion.service",
|
||||
"account": "aios-v2r1c1-openclaw",
|
||||
"listen": "127.0.0.1:28789",
|
||||
"accept_v2": true,
|
||||
"accept_v1": false,
|
||||
"public_key_only": true,
|
||||
"production_traffic_switched": false,
|
||||
"result": "PASS"
|
||||
},
|
||||
"previous_plugin": {
|
||||
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
|
||||
"plugin_version": "2.1.0-rc.3",
|
||||
"artifact_sha256": "d0fd11be4aec03eee9ca24bf1585d9ef3597254ad4b1db0d0137eab4456b5737"
|
||||
},
|
||||
"rollback": {
|
||||
"production_plugin_unchanged": true,
|
||||
"failed_isolated_attempts_rolled_back": true,
|
||||
"previous_plugin_evidence": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z/00-baseline",
|
||||
"previous_oid": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a",
|
||||
"isolated_rollback_forward": "PASS",
|
||||
"production_symlink_modified": false
|
||||
},
|
||||
"release_validation": {
|
||||
"gate_a": "PASS",
|
||||
"gate_b": "PASS",
|
||||
"openclaw_v2_live": "PASS",
|
||||
"openclaw_negative_live": "PASS",
|
||||
"hermes_live": "PASS",
|
||||
"restart_recovery": "PASS",
|
||||
"rollback_forward": "PASS",
|
||||
"final_health": "PASS",
|
||||
"secret_violations": 0,
|
||||
"global_dirty_count": 0,
|
||||
"sync_status": "fully_synced"
|
||||
},
|
||||
"tag_status": "ABSENT",
|
||||
"preproduction_status": "NOT_STARTED",
|
||||
"production_status": "NOT_STARTED"
|
||||
}
|
||||
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"schema_version": "aios.v2r1c1.release-evidence.v2",
|
||||
"vrc": "V2R1C1",
|
||||
"semver": "2.1.0-rc.1",
|
||||
"product_baseline_oid": "fb739f6e8ff9c031d319221ace68dce157694086",
|
||||
"old_release_oid": "80c4cbde03a82c30648a09b817bc2f03d5402936",
|
||||
"validated_release_parent_oid": "0778a31ec073e7c90003ef091f1d093c16bf22e5",
|
||||
"release_branch": "release/AIOS-V2R1C1-20260721",
|
||||
"release_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-release-20260721",
|
||||
"companion_evidence_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z",
|
||||
"openclaw_companion": {
|
||||
"branch": "patch/openclaw/AIOS-V2R1C1-COMMAND-V2-COMPANION-20260721",
|
||||
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
|
||||
"companion_oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
|
||||
"plugin_version": "2.1.0-rc.4",
|
||||
"contract_version": "aios.openclaw.command.v2",
|
||||
"signature_algorithm": "Ed25519",
|
||||
"verification_key_id": "openclaw-v2r1-candidate-ed25519",
|
||||
"artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671"
|
||||
},
|
||||
"step13": {
|
||||
"original_result": "FAIL_HTTP_401",
|
||||
"original_diagnosis_manifest_sha256": "320017cbfc0f31392b4d0fb5996d0e32709982a967d102592ac45efdbdaad91f",
|
||||
"remediated_result": "PASS",
|
||||
"online_negative_evidence_sha256": "57ab8efd19d3bf659a65cbeda830785f6cea9172925a3cac9e027b9b842e644f",
|
||||
"remediated_evidence_sha256": "5db59096c0586fcc0a51851d9a25d0a0b94f2bade45063fab16cc2a729f23130",
|
||||
"task_state": "COMPLETED",
|
||||
"dispatch_state": "COMPLETED",
|
||||
"task_dispatch_audit_consistency": "PASS"
|
||||
},
|
||||
"release_validation": {
|
||||
"static_revalidation": "PASS",
|
||||
"static_evidence_sha256": "c33ffaf9a0f509d6e78bdfdc0848940c166b8a800940e259b7196adab04ec604",
|
||||
"gate_a": "PASS",
|
||||
"gate_b": "PASS",
|
||||
"documentation_sync": "PASS",
|
||||
"secret_scan_violations": 0,
|
||||
"release_metadata": "PASS",
|
||||
"hermes_live": "PASS",
|
||||
"hermes_evidence_sha256": "e6553c99db55c3cdf9e16a4c1e6712064e00c41dc9965d0d179b6b1a2a1ad3ac",
|
||||
"restart_recovery": "PASS",
|
||||
"restart_evidence_sha256": "6031c92cd890dffd1de28ba75d81bed908e7da11a24aa129bcfde8efb23f0149",
|
||||
"rollback_forward": "PASS",
|
||||
"rollback_evidence_sha256": "f3d49c54e3f722facf68df2da3d82a9c82eb576f2c7c8dacb0f62c424d25737c",
|
||||
"final_health": "PASS",
|
||||
"final_health_evidence_sha256": "121cd52c0a4852b818e06be69211ae18b9fcccf976fa064e2a09c54eb8a01300",
|
||||
"global_dirty_count": 0,
|
||||
"sync_status": "fully_synced"
|
||||
},
|
||||
"validation_status": "PASS",
|
||||
"tag_status": "ABSENT",
|
||||
"preproduction_status": "NOT_STARTED",
|
||||
"production_status": "NOT_STARTED",
|
||||
"secrets_recorded": false
|
||||
}
|
||||
@@ -0,0 +1,52 @@
|
||||
# V2R1C1 Validation Result
|
||||
|
||||
Status: `RELEASE_VALIDATION_PASS / FINAL_METADATA_COMMIT_REVALIDATION_REQUIRED`
|
||||
|
||||
Release decision: `STOP_PREPRODUCTION`
|
||||
|
||||
## OpenClaw Command v2 Companion
|
||||
|
||||
- Source OID: `83f8f878c7da5dd8263f2af2efa80750492e5cb3`
|
||||
- Companion OID: `12d1c13170e0c5a691d67a9408e739e7a17064a3`
|
||||
- Plugin version: `2.1.0-rc.4`
|
||||
- Contract: `aios.openclaw.command.v2`
|
||||
- Signature: `Ed25519`
|
||||
- Artifact SHA256: `aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671`
|
||||
- Companion unit/contract tests: `PASS`
|
||||
- V1 fallback: `REJECTED`
|
||||
- Isolated Gateway health: `PASS`
|
||||
- Online positive/negative contract: `PASS`
|
||||
- AIOS -> OpenClaw real HTTP: `PASS`
|
||||
- Task state: `COMPLETED`
|
||||
- Dispatch state: `COMPLETED`
|
||||
- Task/Dispatch/Audit consistency: `PASS`
|
||||
|
||||
## Evidence linkage
|
||||
|
||||
- Original failed Release OID: `80c4cbde03a82c30648a09b817bc2f03d5402936`
|
||||
- Original HTTP 401 diagnosis: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-release-20260721/pass1-80c4cbde/13-diagnosis`
|
||||
- Original manifest SHA256: `320017cbfc0f31392b4d0fb5996d0e32709982a967d102592ac45efdbdaad91f`
|
||||
- Companion evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z`
|
||||
- Validated Release parent OID: `0778a31ec073e7c90003ef091f1d093c16bf22e5`
|
||||
- Online negative evidence SHA256: `57ab8efd19d3bf659a65cbeda830785f6cea9172925a3cac9e027b9b842e644f`
|
||||
- Remediated Step 13 evidence SHA256: `5db59096c0586fcc0a51851d9a25d0a0b94f2bade45063fab16cc2a729f23130`
|
||||
|
||||
## Release validation closure
|
||||
|
||||
- Gate A: `PASS`
|
||||
- Gate B: `PASS`
|
||||
- Documentation sync: `PASS`
|
||||
- Secret violations: `0`
|
||||
- Release Metadata: `PASS`
|
||||
- Hermes live: `PASS`
|
||||
- Restart recovery: `PASS`
|
||||
- Previous ↔ V2R1C1 isolated rollback/forward: `PASS`
|
||||
- Final health: `PASS`
|
||||
- Global dirty / locked / prunable: `0 / 0 / 0`
|
||||
- OID sync: `fully_synced`
|
||||
- Production traffic switched: `false`
|
||||
- Tag: `ABSENT`
|
||||
|
||||
## Remaining mandatory validation
|
||||
|
||||
本次最终元数据闭环提交将形成新的 Release OID。必须针对该最终 OID 再次复验 Gate A、Gate B、文档同步、Secret Scan、Release Metadata 和 OpenClaw 第 13 步正向/负向验证。复验通过前不得创建 Tag 或部署预生产/生产。
|
||||
@@ -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 +1,8 @@
|
||||
# Changelog
|
||||
|
||||
## V2R1C1 - 2.1.0-rc.1
|
||||
|
||||
- 固定发布基线为 `fb739f6e8ff9c031d319221ace68dce157694086`。
|
||||
- 收口 Hermes 生命周期、Grant 隔离、Dispatch 恢复、运行证据和回滚/前滚验证。
|
||||
- Portal Adapter 与 Spark Provisioning 仅保留在 Archive,不属于产品发布图。
|
||||
- Future Incubator 保持隔离,不属于 V2R1C1 发布输入。
|
||||
@@ -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 +1,45 @@
|
||||
"""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 +1,183 @@
|
||||
#!/usr/bin/env bash
|
||||
set -Eeuo pipefail
|
||||
|
||||
REPO_ROOT="${AIOS_REPO_ROOT:-$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)}"
|
||||
BASE_REF="${AIOS_DOCS_BASE_REF:-}"
|
||||
RUN_LIVE_HEALTHCHECK="${AIOS_RUN_LIVE_HEALTHCHECK:-0}"
|
||||
RESULT_DIR="${AIOS_ACCEPTANCE_RESULT_DIR:-$REPO_ROOT/.aios-evidence/acceptance}"
|
||||
STAMP="$(date -u +%Y%m%dT%H%M%SZ)"
|
||||
RUN_DIR="$RESULT_DIR/$STAMP"
|
||||
SUMMARY="$RUN_DIR/summary.json"
|
||||
|
||||
install -d -m 0750 "$RUN_DIR"
|
||||
|
||||
pass=0
|
||||
failed=0
|
||||
warnings=0
|
||||
steps=()
|
||||
|
||||
record() {
|
||||
local name="$1" status="$2" code="$3" log="$4"
|
||||
steps+=("$name|$status|$code|$log")
|
||||
case "$status" in
|
||||
通过) pass=$((pass + 1)) ;;
|
||||
失败) failed=$((failed + 1)) ;;
|
||||
警告) warnings=$((warnings + 1)) ;;
|
||||
esac
|
||||
printf '%s:%s(退出码 %s)\n' "$status" "$name" "$code"
|
||||
}
|
||||
|
||||
run_step() {
|
||||
local name="$1"
|
||||
shift
|
||||
local safe_name
|
||||
safe_name="$(printf '%s' "$name" | tr ' /:' '___')"
|
||||
local log="$RUN_DIR/${safe_name}.log"
|
||||
set +e
|
||||
(cd "$REPO_ROOT" && "$@") >"$log" 2>&1
|
||||
local code=$?
|
||||
set -e
|
||||
if [[ "$code" -eq 0 ]]; then
|
||||
record "$name" "通过" "$code" "$log"
|
||||
else
|
||||
record "$name" "失败" "$code" "$log"
|
||||
fi
|
||||
}
|
||||
|
||||
run_optional_step() {
|
||||
local name="$1"
|
||||
shift
|
||||
local safe_name
|
||||
safe_name="$(printf '%s' "$name" | tr ' /:' '___')"
|
||||
local log="$RUN_DIR/${safe_name}.log"
|
||||
set +e
|
||||
(cd "$REPO_ROOT" && "$@") >"$log" 2>&1
|
||||
local code=$?
|
||||
set -e
|
||||
if [[ "$code" -eq 0 ]]; then
|
||||
record "$name" "通过" "$code" "$log"
|
||||
else
|
||||
record "$name" "警告" "$code" "$log"
|
||||
fi
|
||||
}
|
||||
|
||||
printf 'AIOS V2R1 Candidate 全量验收开始\n'
|
||||
printf '仓库:%s\n' "$REPO_ROOT"
|
||||
printf '结果目录:%s\n' "$RUN_DIR"
|
||||
|
||||
[[ -d "$REPO_ROOT" ]] || { echo "错误:仓库不存在" >&2; exit 2; }
|
||||
|
||||
DOCS_ARGS=(python3 tools/aios_v2_docs_code_check.py --repo "$REPO_ROOT")
|
||||
if [[ -n "$BASE_REF" ]]; then
|
||||
DOCS_ARGS+=(--base-ref "$BASE_REF")
|
||||
fi
|
||||
run_step "文档与代码匹配" "${DOCS_ARGS[@]}"
|
||||
|
||||
run_step "Python 语法编译" python3 -m compileall -q \
|
||||
active-runtime/app/aios_v2 \
|
||||
active-runtime/app/aios_openclaw \
|
||||
active-runtime/app/aios_hermes
|
||||
|
||||
run_step "候选单元与集成测试" python3 -m unittest discover \
|
||||
-s tests/aios_v2_candidate \
|
||||
-p 'test_*.py' \
|
||||
-v
|
||||
|
||||
run_step "Shell 脚本语法" bash -c '
|
||||
set -Eeuo pipefail
|
||||
while IFS= read -r -d "" path; do
|
||||
bash -n "$path"
|
||||
done < <(find deploy/aios-v2 -type f -name "*.sh" -print0)
|
||||
'
|
||||
|
||||
run_step "文档 Git 冲突标记" bash -c '
|
||||
set -Eeuo pipefail
|
||||
if grep -RInE "^(<<<<<<<|=======|>>>>>>>)" docs/aios-v2; then
|
||||
exit 1
|
||||
fi
|
||||
'
|
||||
|
||||
run_step "明文密钥基础扫描" python3 -c '
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sys
|
||||
|
||||
roots = [Path("active-runtime/app"), Path("deploy/aios-v2"), Path("docs/aios-v2"), Path("tasks")]
|
||||
patterns = [
|
||||
re.compile(r"(?i)(api[_-]?key|password|private[_-]?key|access[_-]?token)\s*[:=]\s*[\"\x27][^\"\x27\n]{12,}[\"\x27]"),
|
||||
re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH )?PRIVATE KEY-----"),
|
||||
]
|
||||
violations = []
|
||||
for root in roots:
|
||||
if not root.exists():
|
||||
continue
|
||||
for path in root.rglob("*"):
|
||||
if not path.is_file() or path.suffix in {".pyc", ".db", ".sqlite3"}:
|
||||
continue
|
||||
text = path.read_text(encoding="utf-8", errors="ignore")
|
||||
if any(pattern.search(text) for pattern in patterns):
|
||||
violations.append(str(path))
|
||||
if violations:
|
||||
print("疑似明文密钥文件:", *violations, sep="\n", file=sys.stderr)
|
||||
raise SystemExit(1)
|
||||
'
|
||||
|
||||
if command -v systemd-analyze >/dev/null 2>&1; then
|
||||
run_optional_step "systemd 单元验证" systemd-analyze verify \
|
||||
deploy/aios-v2/systemd/aios-v2.service
|
||||
else
|
||||
record "systemd 单元验证" "警告" "127" "未安装 systemd-analyze"
|
||||
fi
|
||||
|
||||
if command -v docker >/dev/null 2>&1 && docker compose version >/dev/null 2>&1; then
|
||||
run_optional_step "Docker Compose 配置验证" docker compose \
|
||||
-f deploy/aios-v2/docker/compose.yaml config
|
||||
else
|
||||
record "Docker Compose 配置验证" "警告" "127" "未安装 Docker Compose"
|
||||
fi
|
||||
|
||||
if [[ "$RUN_LIVE_HEALTHCHECK" == "1" ]]; then
|
||||
run_step "在线健康检查" bash deploy/aios-v2/healthcheck/check.sh
|
||||
else
|
||||
record "在线健康检查" "警告" "0" "未启用 AIOS_RUN_LIVE_HEALTHCHECK=1"
|
||||
fi
|
||||
|
||||
branch="$(git -C "$REPO_ROOT" branch --show-current 2>/dev/null || true)"
|
||||
commit="$(git -C "$REPO_ROOT" rev-parse HEAD 2>/dev/null || true)"
|
||||
dirty="$(git -C "$REPO_ROOT" status --porcelain=v1 2>/dev/null || true)"
|
||||
|
||||
python3 - "$SUMMARY" "$branch" "$commit" "$dirty" "$pass" "$failed" "$warnings" "${steps[@]}" <<'PY'
|
||||
import json
|
||||
import pathlib
|
||||
import sys
|
||||
from datetime import datetime, timezone
|
||||
|
||||
summary_path = pathlib.Path(sys.argv[1])
|
||||
branch, commit, dirty = sys.argv[2:5]
|
||||
passed, failed, warnings = map(int, sys.argv[5:8])
|
||||
steps = []
|
||||
for item in sys.argv[8:]:
|
||||
name, status, code, log = item.split("|", 3)
|
||||
steps.append({"name": name, "status": status, "exit_code": int(code), "log": log})
|
||||
payload = {
|
||||
"schema": "aios.v2.acceptance.v1",
|
||||
"generated_at": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
|
||||
"branch": branch or None,
|
||||
"commit": commit or None,
|
||||
"workspace_dirty": bool(dirty),
|
||||
"passed": passed,
|
||||
"failed": failed,
|
||||
"warnings": warnings,
|
||||
"steps": steps,
|
||||
"final_status": "passed" if failed == 0 else "failed",
|
||||
}
|
||||
summary_path.write_text(json.dumps(payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
|
||||
print(json.dumps(payload, ensure_ascii=False, indent=2))
|
||||
PY
|
||||
|
||||
printf '验收结果:通过 %s,失败 %s,警告 %s\n' "$pass" "$failed" "$warnings"
|
||||
printf '证据:%s\n' "$SUMMARY"
|
||||
|
||||
if [[ "$failed" -ne 0 ]]; then
|
||||
exit 1
|
||||
fi
|
||||
@@ -0,0 +1,24 @@
|
||||
FROM python:3.12-slim
|
||||
|
||||
ENV PYTHONDONTWRITEBYTECODE=1 \
|
||||
PYTHONUNBUFFERED=1 \
|
||||
PYTHONPATH=/opt/aios/app \
|
||||
AIOS_V2_HOST=0.0.0.0 \
|
||||
AIOS_V2_PORT=18920 \
|
||||
AIOS_V2_STATE_DIR=/var/lib/aios-v2
|
||||
|
||||
RUN groupadd --system --gid 12001 aios \
|
||||
&& useradd --system --uid 12001 --gid aios --home-dir /nonexistent --shell /usr/sbin/nologin aios \
|
||||
&& install -d -o aios -g aios -m 0750 /opt/aios/app /var/lib/aios-v2 \
|
||||
&& python3 -m pip install --no-cache-dir 'cryptography>=42'
|
||||
|
||||
WORKDIR /opt/aios/app
|
||||
COPY --chown=aios:aios active-runtime/app/ /opt/aios/app/
|
||||
|
||||
USER aios:aios
|
||||
EXPOSE 18920
|
||||
|
||||
HEALTHCHECK --interval=15s --timeout=5s --start-period=10s --retries=4 \
|
||||
CMD python3 -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:18920/api/v2/health', timeout=3).read()"
|
||||
|
||||
CMD ["python3", "-m", "aios_v2.app"]
|
||||
@@ -0,0 +1,44 @@
|
||||
services:
|
||||
aios-v2:
|
||||
build:
|
||||
context: ../../..
|
||||
dockerfile: deploy/aios-v2/docker/Dockerfile
|
||||
image: aios-v2:V2R1C0-candidate
|
||||
init: true
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "127.0.0.1:${AIOS_V2_PORT:-18920}:18920"
|
||||
environment:
|
||||
AIOS_V2_HOST: 0.0.0.0
|
||||
AIOS_V2_PORT: 18920
|
||||
AIOS_V2_STATE_DIR: /var/lib/aios-v2
|
||||
AIOS_OPENCLAW_URL: ${AIOS_OPENCLAW_URL:-}
|
||||
AIOS_OPENCLAW_CREDENTIAL_REF: ${AIOS_OPENCLAW_CREDENTIAL_REF:-}
|
||||
AIOS_OPENCLAW_SIGNING_MATERIAL_FILE: ${AIOS_OPENCLAW_SIGNING_MATERIAL_FILE:-}
|
||||
AIOS_RELEASE_CHANNEL: candidate
|
||||
AIOS_RELEASE_VERSION: V2R1C0-candidate
|
||||
volumes:
|
||||
- aios-v2-state:/var/lib/aios-v2
|
||||
# Mount runtime signing material explicitly when OpenClaw is enabled.
|
||||
# The host file must be mode 0600; never store it in this repository.
|
||||
# - /etc/aios-v2/openclaw-signing-material:/run/secrets/openclaw-signing-material:ro
|
||||
read_only: true
|
||||
tmpfs:
|
||||
- /tmp:rw,noexec,nosuid,nodev,size=64m
|
||||
cap_drop:
|
||||
- ALL
|
||||
security_opt:
|
||||
- no-new-privileges:true
|
||||
healthcheck:
|
||||
test:
|
||||
- CMD
|
||||
- python3
|
||||
- -c
|
||||
- "import urllib.request; urllib.request.urlopen('http://127.0.0.1:18920/api/v2/health', timeout=3).read()"
|
||||
interval: 15s
|
||||
timeout: 5s
|
||||
retries: 4
|
||||
start_period: 10s
|
||||
|
||||
volumes:
|
||||
aios-v2-state:
|
||||
+45
@@ -0,0 +1,45 @@
|
||||
# AIOS V2R1 Candidate 环境模板
|
||||
# 正式环境禁止保存明文 Secret。
|
||||
# Provenance/OpenClaw 私钥只用于签发端,不进入应用容器或 Git。
|
||||
|
||||
# Runtime
|
||||
AIOS_V2_HOST=127.0.0.1
|
||||
AIOS_V2_PORT=18920
|
||||
AIOS_V2_STATE_DIR=/var/lib/aios-v2
|
||||
|
||||
# OpenClaw Ed25519 Command v2
|
||||
AIOS_OPENCLAW_URL=
|
||||
AIOS_OPENCLAW_CREDENTIAL_REF=
|
||||
AIOS_OPENCLAW_SIGNING_MATERIAL_FILE=/run/credentials/aios-v2.service/openclaw-command-private-key
|
||||
AIOS_OPENCLAW_SIGNING_KEY_ID=openclaw-v2r1-candidate-ed25519
|
||||
|
||||
# Parent Workflow Provenance
|
||||
AIOS_REQUIRE_RUN_PROVENANCE=true
|
||||
AIOS_PROVENANCE_PUBLIC_KEY_FILE=/etc/aios-v2/provenance/public-key.pem
|
||||
AIOS_PROVENANCE_KEY_ID=openclaw-v2r1-candidate-ed25519
|
||||
AIOS_PROVENANCE_STORE_FILE=/var/lib/aios-v2/run-provenance.sqlite3
|
||||
AIOS_PROVENANCE_RECEIPT_DIR=/var/lib/aios-v2/provenance-receipts
|
||||
|
||||
# Least-privilege child Grants: production requires all seven IDs.
|
||||
AIOS_PROVENANCE_GRANT_CODE_CHANGE_ID=
|
||||
AIOS_PROVENANCE_GRANT_GIT_ID=
|
||||
AIOS_PROVENANCE_GRANT_DEPLOYMENT_ID=
|
||||
AIOS_PROVENANCE_GRANT_RUNTIME_ID=
|
||||
AIOS_PROVENANCE_GRANT_EVIDENCE_ID=
|
||||
AIOS_PROVENANCE_GRANT_ROLLBACK_ID=
|
||||
AIOS_PROVENANCE_GRANT_AUDIT_ID=
|
||||
|
||||
# Per-operation context. Deployment/rollback wrappers populate these from the
|
||||
# approved task execution context; do not hard-code shared production values.
|
||||
AIOS_PROVENANCE_ID=
|
||||
AIOS_RUN_ID=
|
||||
AIOS_TENANT_ID=
|
||||
AIOS_TASK_ID=
|
||||
AIOS_AGENT_ID=
|
||||
AIOS_PRINCIPAL_ID=
|
||||
|
||||
# 禁止:
|
||||
# AIOS_PROVENANCE_PRIVATE_KEY_FILE
|
||||
# AIOS_OPENCLAW_TOKEN
|
||||
# API_KEY=value
|
||||
# PASSWORD=value
|
||||
Executable
+86
@@ -0,0 +1,86 @@
|
||||
#!/usr/bin/env bash
|
||||
set -Eeuo pipefail
|
||||
|
||||
BASE_URL="${AIOS_V2_BASE_URL:-http://127.0.0.1:18920}"
|
||||
STATE_DIR="${AIOS_V2_STATE_DIR:-/var/lib/aios-v2}"
|
||||
CONTROLLER_WT="${AIOS_GITOPS_CONTROLLER_WORKTREE:-/data/aios-gitops/worktrees/controller}"
|
||||
SERVICE="${AIOS_V2_SERVICE:-aios-v2}"
|
||||
|
||||
fail() {
|
||||
echo "FAIL: $*" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
pass() {
|
||||
echo "PASS: $*"
|
||||
}
|
||||
|
||||
command -v python3 >/dev/null || fail "python3 not installed"
|
||||
|
||||
if command -v systemctl >/dev/null && systemctl list-unit-files "$SERVICE.service" >/dev/null 2>&1; then
|
||||
systemctl is-active --quiet "$SERVICE" || fail "$SERVICE is not active"
|
||||
pass "$SERVICE is active"
|
||||
fi
|
||||
|
||||
python3 - "$BASE_URL" <<'PY'
|
||||
import json
|
||||
import sys
|
||||
import urllib.request
|
||||
|
||||
base_url = sys.argv[1].rstrip("/")
|
||||
with urllib.request.urlopen(f"{base_url}/api/v2/health", timeout=5) as response:
|
||||
payload = json.loads(response.read().decode("utf-8"))
|
||||
if payload.get("status") not in {"ok", "healthy", "ready"}:
|
||||
raise SystemExit(f"unexpected health payload: {payload}")
|
||||
print(f"PASS: HTTP health status={payload.get('status')}")
|
||||
PY
|
||||
|
||||
[[ -d "$STATE_DIR" ]] || fail "state directory missing: $STATE_DIR"
|
||||
[[ -w "$STATE_DIR" ]] || fail "state directory not writable: $STATE_DIR"
|
||||
pass "state directory writable"
|
||||
|
||||
if [[ -e "$STATE_DIR/control-plane.sqlite3" ]]; then
|
||||
python3 - "$STATE_DIR/control-plane.sqlite3" <<'PY'
|
||||
import sqlite3
|
||||
import sys
|
||||
|
||||
path = sys.argv[1]
|
||||
connection = sqlite3.connect(f"file:{path}?mode=ro", uri=True, timeout=5)
|
||||
try:
|
||||
row = connection.execute("PRAGMA quick_check").fetchone()
|
||||
finally:
|
||||
connection.close()
|
||||
if not row or row[0] != "ok":
|
||||
raise SystemExit(f"SQLite quick_check failed: {row}")
|
||||
print("PASS: SQLite quick_check=ok")
|
||||
PY
|
||||
else
|
||||
echo "WARN: control-plane.sqlite3 not created yet"
|
||||
fi
|
||||
|
||||
if [[ -d "$CONTROLLER_WT" ]] && git -C "$CONTROLLER_WT" rev-parse --is-inside-work-tree >/dev/null 2>&1; then
|
||||
branch="$(git -C "$CONTROLLER_WT" branch --show-current)"
|
||||
dirty="$(git -C "$CONTROLLER_WT" status --porcelain=v1)"
|
||||
[[ -z "$branch" ]] || fail "GitOps controller attached to branch: $branch"
|
||||
[[ -z "$dirty" ]] || fail "GitOps controller workspace is dirty"
|
||||
pass "GitOps controller detached and clean"
|
||||
fi
|
||||
|
||||
python3 - "$STATE_DIR/executions" <<'PY'
|
||||
import json
|
||||
import pathlib
|
||||
import sys
|
||||
|
||||
root = pathlib.Path(sys.argv[1])
|
||||
if not root.exists():
|
||||
print("WARN: execution evidence directory not created yet")
|
||||
raise SystemExit(0)
|
||||
for path in root.glob("*/*.json"):
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
for key in ("execution_id", "tenant_id", "task_id", "executor", "status"):
|
||||
if not value.get(key):
|
||||
raise SystemExit(f"invalid execution evidence {path}: missing {key}")
|
||||
print("PASS: execution evidence files valid")
|
||||
PY
|
||||
|
||||
pass "AIOS V2 candidate healthcheck complete"
|
||||
@@ -0,0 +1,39 @@
|
||||
#!/usr/bin/env bash
|
||||
set -Eeuo pipefail
|
||||
|
||||
OPERATION_PATH="${1:-}"
|
||||
OPERATION_NAME="${2:-}"
|
||||
REQUEST_FILE="${3:-}"
|
||||
|
||||
fail() {
|
||||
echo "PROVENANCE_DENIED: $*" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
[[ -n "$OPERATION_PATH" ]] || fail "usage: $0 <deployment|rollback|audit|code_change|runtime_execute|evidence_write> <operation> <request-json-file>"
|
||||
[[ -n "$OPERATION_NAME" ]] || fail "operation name is required"
|
||||
[[ -n "$REQUEST_FILE" && -f "$REQUEST_FILE" ]] || fail "request JSON file is required"
|
||||
|
||||
: "${AIOS_PROVENANCE_PUBLIC_KEY_FILE:?missing AIOS_PROVENANCE_PUBLIC_KEY_FILE}"
|
||||
: "${AIOS_PROVENANCE_KEY_ID:?missing AIOS_PROVENANCE_KEY_ID}"
|
||||
: "${AIOS_PROVENANCE_STORE_FILE:?missing AIOS_PROVENANCE_STORE_FILE}"
|
||||
: "${AIOS_PROVENANCE_RECEIPT_DIR:?missing AIOS_PROVENANCE_RECEIPT_DIR}"
|
||||
: "${AIOS_PROVENANCE_ID:?missing AIOS_PROVENANCE_ID}"
|
||||
: "${AIOS_RUN_ID:?missing AIOS_RUN_ID}"
|
||||
: "${AIOS_TENANT_ID:?missing AIOS_TENANT_ID}"
|
||||
: "${AIOS_TASK_ID:?missing AIOS_TASK_ID}"
|
||||
: "${AIOS_AGENT_ID:?missing AIOS_AGENT_ID}"
|
||||
: "${AIOS_PRINCIPAL_ID:?missing AIOS_PRINCIPAL_ID}"
|
||||
|
||||
PYTHONPATH_VALUE="${AIOS_V2_PYTHONPATH:-/opt/aios/current/active-runtime/app}"
|
||||
|
||||
PYTHONPATH="$PYTHONPATH_VALUE${PYTHONPATH:+:$PYTHONPATH}" \
|
||||
python3 -m aios_v2.provenance_cli authorize \
|
||||
--context-from-env \
|
||||
--store-file "$AIOS_PROVENANCE_STORE_FILE" \
|
||||
--public-key-file "$AIOS_PROVENANCE_PUBLIC_KEY_FILE" \
|
||||
--key-id "$AIOS_PROVENANCE_KEY_ID" \
|
||||
--receipt-dir "$AIOS_PROVENANCE_RECEIPT_DIR" \
|
||||
--path "$OPERATION_PATH" \
|
||||
--operation "$OPERATION_NAME" \
|
||||
--request-file "$REQUEST_FILE"
|
||||
Executable
+98
@@ -0,0 +1,98 @@
|
||||
#!/usr/bin/env bash
|
||||
set -Eeuo pipefail
|
||||
|
||||
SERVICE="${AIOS_V2_SERVICE:-aios-v2}"
|
||||
RELEASE_ROOT="${AIOS_V2_RELEASE_ROOT:-/opt/aios/releases}"
|
||||
CURRENT_LINK="${AIOS_V2_CURRENT_LINK:-/opt/aios/current}"
|
||||
STATE_DIR="${AIOS_V2_STATE_DIR:-/var/lib/aios-v2}"
|
||||
BACKUP_ROOT="${AIOS_V2_BACKUP_ROOT:-/var/backups/aios-v2}"
|
||||
TARGET_RELEASE="${1:-}"
|
||||
RESTORE_STATE="${AIOS_V2_RESTORE_STATE:-0}"
|
||||
HEALTH_RETRIES="${AIOS_V2_ROLLBACK_HEALTH_RETRIES:-30}"
|
||||
HEALTH_RETRY_DELAY="${AIOS_V2_ROLLBACK_HEALTH_RETRY_DELAY:-1}"
|
||||
|
||||
fail() {
|
||||
echo "ERROR: $*" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
run_healthcheck() {
|
||||
local release="$1"
|
||||
local attempt
|
||||
for ((attempt = 1; attempt <= HEALTH_RETRIES; attempt++)); do
|
||||
if AIOS_V2_SERVICE="$SERVICE" \
|
||||
AIOS_V2_STATE_DIR="$STATE_DIR" \
|
||||
"$release/deploy/aios-v2/healthcheck/check.sh"; then
|
||||
return 0
|
||||
fi
|
||||
[[ "$attempt" -lt "$HEALTH_RETRIES" ]] && sleep "$HEALTH_RETRY_DELAY"
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
[[ "${EUID}" -eq 0 ]] || fail "rollback must run as root"
|
||||
[[ -n "$TARGET_RELEASE" ]] || fail "usage: $0 <release-name-or-absolute-path>"
|
||||
|
||||
if [[ "$TARGET_RELEASE" = /* ]]; then
|
||||
TARGET_PATH="$(readlink -f "$TARGET_RELEASE")"
|
||||
else
|
||||
[[ "$TARGET_RELEASE" != *"/"* && "$TARGET_RELEASE" != "." && "$TARGET_RELEASE" != ".." ]] \
|
||||
|| fail "invalid release name"
|
||||
TARGET_PATH="$(readlink -f "$RELEASE_ROOT/$TARGET_RELEASE")"
|
||||
fi
|
||||
|
||||
[[ -d "$TARGET_PATH/active-runtime/app" ]] || fail "target release is invalid: $TARGET_PATH"
|
||||
[[ -f "$TARGET_PATH/deploy/aios-v2/healthcheck/check.sh" ]] \
|
||||
|| fail "target release has no healthcheck"
|
||||
|
||||
PREVIOUS_PATH=""
|
||||
if [[ -L "$CURRENT_LINK" ]]; then
|
||||
PREVIOUS_PATH="$(readlink -f "$CURRENT_LINK")"
|
||||
fi
|
||||
|
||||
STAMP="$(date -u +%Y%m%dT%H%M%SZ)"
|
||||
BACKUP_DIR="$BACKUP_ROOT/rollback-$STAMP"
|
||||
install -d -m 0750 "$BACKUP_DIR"
|
||||
|
||||
if [[ -d "$STATE_DIR" ]]; then
|
||||
tar --xattrs --acls -C "$(dirname "$STATE_DIR")" \
|
||||
-czf "$BACKUP_DIR/state-before-rollback.tar.gz" \
|
||||
"$(basename "$STATE_DIR")"
|
||||
fi
|
||||
|
||||
printf '%s\n' "$PREVIOUS_PATH" > "$BACKUP_DIR/previous-release.txt"
|
||||
printf '%s\n' "$TARGET_PATH" > "$BACKUP_DIR/target-release.txt"
|
||||
|
||||
systemctl stop "$SERVICE"
|
||||
ln -sfn "$TARGET_PATH" "${CURRENT_LINK}.next"
|
||||
mv -Tf "${CURRENT_LINK}.next" "$CURRENT_LINK"
|
||||
systemctl daemon-reload
|
||||
systemctl start "$SERVICE"
|
||||
|
||||
if run_healthcheck "$TARGET_PATH"; then
|
||||
echo "ROLLBACK_COMPLETE target=$TARGET_PATH backup=$BACKUP_DIR"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "Target release failed healthcheck; restoring previous release." >&2
|
||||
systemctl stop "$SERVICE" || true
|
||||
|
||||
if [[ -n "$PREVIOUS_PATH" && -d "$PREVIOUS_PATH" ]]; then
|
||||
ln -sfn "$PREVIOUS_PATH" "${CURRENT_LINK}.previous"
|
||||
mv -Tf "${CURRENT_LINK}.previous" "$CURRENT_LINK"
|
||||
fi
|
||||
|
||||
if [[ "$RESTORE_STATE" == "1" && -f "$BACKUP_DIR/state-before-rollback.tar.gz" ]]; then
|
||||
rm -rf "$STATE_DIR"
|
||||
tar --xattrs --acls -C "$(dirname "$STATE_DIR")" \
|
||||
-xzf "$BACKUP_DIR/state-before-rollback.tar.gz"
|
||||
fi
|
||||
|
||||
systemctl daemon-reload
|
||||
systemctl start "$SERVICE" || true
|
||||
|
||||
if [[ -n "$PREVIOUS_PATH" && -x "$PREVIOUS_PATH/deploy/aios-v2/healthcheck/check.sh" ]]; then
|
||||
run_healthcheck "$PREVIOUS_PATH" || true
|
||||
fi
|
||||
|
||||
fail "rollback target failed; previous release restored; evidence=$BACKUP_DIR"
|
||||
@@ -0,0 +1,37 @@
|
||||
[Unit]
|
||||
Description=AIOS V2 Control Plane Candidate
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios
|
||||
Group=aios
|
||||
WorkingDirectory=/opt/aios/current/active-runtime/app
|
||||
EnvironmentFile=-/etc/aios-v2/aios-v2.env
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
ExecStart=/usr/bin/python3 -m aios_v2.app
|
||||
Restart=on-failure
|
||||
RestartSec=3
|
||||
TimeoutStartSec=30
|
||||
TimeoutStopSec=30
|
||||
KillSignal=SIGTERM
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
LockPersonality=true
|
||||
MemoryDenyWriteExecute=true
|
||||
ReadWritePaths=/var/lib/aios-v2
|
||||
StateDirectory=aios-v2
|
||||
StateDirectoryMode=0750
|
||||
UMask=0027
|
||||
LimitNOFILE=65536
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,342 @@
|
||||
# AIOS V2 用户需求规格
|
||||
|
||||
- 文档版本:`V2R1-hardening-candidate`
|
||||
- 状态:加固候选版本需求基线
|
||||
- 适用范围:AIOS Control Plane、Agent Router、OpenClaw Adapter、Hermes Runtime、Web Console、GitOps、Run Provenance、Dispatch、审计、部署与回滚
|
||||
|
||||
## 1. 背景与目标
|
||||
|
||||
现有系统已经具备 OpenClaw、Hermes、Agent Router、GitOps、局部 WebUI、审计和多租户候选能力。AIOS V2 的目标不是推倒重写,而是将这些分散能力收敛到统一、可审计、可 Web 化、可多租户隔离的控制面。
|
||||
|
||||
AIOS V2 必须成为唯一控制面,负责租户、身份、Agent、策略、任务生命周期、审批、审计、Runtime 目录、执行证据、Run Provenance 和 Dispatch。OpenClaw 与 Hermes 只承担执行职责,不得持有第二套控制面状态。
|
||||
|
||||
## 2. 用户角色
|
||||
|
||||
| 角色 | 主要诉求 |
|
||||
|---|---|
|
||||
| 平台管理员 | 管理租户、运行时、发布、GitOps 状态和全局策略 |
|
||||
| 租户管理员 | 管理本租户 Agent、任务、审批、审计和成员权限 |
|
||||
| 操作员 | 创建任务、发起执行、取消任务、查看运行状态 |
|
||||
| 审批人 | 审批高风险任务,查看策略判定依据 |
|
||||
| 审计员 | 查询本租户完整审计链和执行证据 |
|
||||
| Runtime Worker | 领取已批准任务、心跳、返回执行结果 |
|
||||
| 开发与运维人员 | 通过 GitOps 提交、测试、部署、回滚和修复 Bug |
|
||||
|
||||
## 3. 核心用户需求
|
||||
|
||||
### UR-001 唯一控制面
|
||||
|
||||
所有任务创建、审批、取消、状态变化、策略判定和审计必须由 AIOS Control Plane 统一处理。
|
||||
|
||||
验收:
|
||||
|
||||
- Web Console、API、Codex、OpenClaw 和 Hermes 均不得绕过 AIOS 创建或修改任务生命周期。
|
||||
- OpenClaw/Hermes 的公开接口仅限执行、状态、取消、心跳和结果回传。
|
||||
|
||||
### UR-002 复用现有能力
|
||||
|
||||
系统不得重写已经稳定的 OpenClaw 执行能力、Hermes Runtime、Agent Router 或 GitOps 基础设施。
|
||||
|
||||
验收:
|
||||
|
||||
- 通过 Adapter/Boundary 接入现有能力。
|
||||
- 替换控制逻辑时保留原执行接口和可迁移数据。
|
||||
|
||||
### UR-003 OpenClaw 与 Hermes 解耦
|
||||
|
||||
OpenClaw 与 Hermes 必须从策略、租户、审批和任务生命周期中逐步解耦。
|
||||
|
||||
验收:
|
||||
|
||||
- OpenClaw 仅接收已签名、已批准、带租户上下文的命令。
|
||||
- Hermes 仅接收已批准的租户分区 Job。
|
||||
- 二者均不得直接写 Control Plane 权威状态。
|
||||
|
||||
### UR-004 全面 Web 化
|
||||
|
||||
所有面向用户和运维的能力必须通过 Web Console 或稳定 API 访问。
|
||||
|
||||
Web Console 至少展示:
|
||||
|
||||
- Tenant、Agent、Task、Approval、Runtime、Audit、Execution Evidence、GitOps Status。
|
||||
- 所有写操作由 AIOS API 完成,浏览器不得直接调用 OpenClaw/Hermes。
|
||||
|
||||
### UR-005 多租户隔离
|
||||
|
||||
所有模块必须支持租户隔离,且默认拒绝跨租户访问。
|
||||
|
||||
隔离范围:
|
||||
|
||||
- API 与会话
|
||||
- Tenant/Agent/Task 数据
|
||||
- OpenClaw 命令
|
||||
- Hermes Queue、Cell、Profile、Worker Lease
|
||||
- Memory、Cache、Artifact、SecretRef
|
||||
- Audit、Execution Evidence、日志和指标
|
||||
|
||||
验收:
|
||||
|
||||
- 资源记录的 `tenant_id` 不可为空。
|
||||
- 跨租户访问返回拒绝或“资源不存在”,不得泄露存在性。
|
||||
- 必须有跨租户负向测试。
|
||||
|
||||
### UR-006 权威任务生命周期
|
||||
|
||||
任务必须遵循统一状态机:
|
||||
|
||||
```text
|
||||
CREATED -> APPROVED -> RUNNING -> COMPLETED
|
||||
| | |
|
||||
+----------+----------+-> CANCELLED
|
||||
+-> FAILED
|
||||
```
|
||||
|
||||
验收:
|
||||
|
||||
- 禁止越级变化,例如 `CREATED -> COMPLETED`。
|
||||
- 每次变化包含 revision、principal、trace、时间和审计事件。
|
||||
- 公共 API 不允许直接调用 `start`、`complete` 或 `fail` 推进权威状态。
|
||||
|
||||
### UR-007 策略与审批
|
||||
|
||||
所有有副作用任务必须经过策略判定;高风险任务必须支持人工审批。
|
||||
|
||||
验收:
|
||||
|
||||
- Policy Decision 包含 allow/deny、reason 和 policy version。
|
||||
- 拒绝事件进入审计。
|
||||
- Runtime 不得自行放宽策略。
|
||||
|
||||
### UR-008 幂等与并发安全
|
||||
|
||||
任务和 Runtime 执行必须支持幂等与乐观并发控制。
|
||||
|
||||
验收:
|
||||
|
||||
- 相同租户与幂等键、相同内容返回同一任务/执行。
|
||||
- 相同幂等键不同内容返回冲突。
|
||||
- revision 或 branch lease 冲突不得静默覆盖。
|
||||
|
||||
### UR-009 可观测与执行证据
|
||||
|
||||
平台必须能够确认 Codex、OpenClaw、Hermes 等执行器是否领取任务、当前进度、最近提交、测试结果和完成状态。
|
||||
|
||||
验收:
|
||||
|
||||
- 存在 claim、heartbeat、progress、result 和 evidence 记录。
|
||||
- Web/API 可按租户查询。
|
||||
- 执行证据不得包含明文密钥。
|
||||
|
||||
### UR-010 GitOps 唯一变更流程
|
||||
|
||||
所有代码、配置、文档和部署资产修改必须进入非 `main` 分支,通过 commit、测试、审查和受控提升。
|
||||
|
||||
验收:
|
||||
|
||||
- Controller worktree 必须 detached 且 clean。
|
||||
- 本地 bare repo 与 Gitea 目标分支 OID 一致。
|
||||
- 不允许直接 push `main`、直接创建生产 Tag 或绕过审批部署。
|
||||
|
||||
### UR-011 持久化与恢复
|
||||
|
||||
租户、Agent、Task、Audit、Idempotency、Dispatch、Run Provenance、Grant 使用记录和 Execution Evidence 必须在服务重启后恢复。
|
||||
|
||||
验收:
|
||||
|
||||
- 候选版支持 SQLite WAL 或等价原子持久化。
|
||||
- 有 Control Plane 与 Dispatch restart recovery 测试。
|
||||
- 生产版需进一步提供迁移、备份、恢复、HA 和容量证据。
|
||||
|
||||
### UR-012 审计与合规
|
||||
|
||||
所有控制与执行动作必须生成不可混租户的审计事件。
|
||||
|
||||
至少记录:
|
||||
|
||||
- tenant、principal、trace、action、resource、outcome、policy version、timestamp。
|
||||
- OpenClaw/Hermes Runtime 生命周期。
|
||||
- GitOps、部署和回滚动作。
|
||||
- Provenance Grant、Scope、Authorization Receipt 和 Dispatch 结果摘要。
|
||||
|
||||
### UR-013 密钥安全
|
||||
|
||||
Git、日志、Web、任务 payload 和审计记录中不得出现明文 API Key、密码、Token 或私钥。
|
||||
|
||||
验收:
|
||||
|
||||
- Git 只存 `secret_ref`、`credential_ref`、`key_id` 或受保护文件路径。
|
||||
- Secret 文件权限为 `0600` 或更严格。
|
||||
- Secret Scanner 默认拒绝可疑提交。
|
||||
- OpenClaw Command 和 Run Provenance 使用 Ed25519;生产应用只读取公钥。
|
||||
|
||||
### UR-014 部署与回滚
|
||||
|
||||
系统必须提供 systemd、Docker/Compose、健康检查和受保护回滚入口。
|
||||
|
||||
验收:
|
||||
|
||||
- 服务以非 root 权限运行。
|
||||
- 状态目录独立持久化。
|
||||
- 回滚前自动备份状态。
|
||||
- 默认只回滚代码,状态恢复需要显式授权。
|
||||
|
||||
### UR-015 文档与代码同步
|
||||
|
||||
任何影响用户行为、架构边界、API、数据模型、状态机、安全策略、部署或运维方式的变更,必须在同一分支同步更新 `docs/aios-v2/`。
|
||||
|
||||
验收:
|
||||
|
||||
- 架构/功能代码变化但无文档变化时,文档同步门禁失败。
|
||||
- Traceability Matrix 必须指向当前代码和测试。
|
||||
- 新架构决策必须增加或更新 ADR。
|
||||
|
||||
### UR-016 Workflow Run Provenance
|
||||
|
||||
每次生产 Run 必须具有一个可验证、可撤销、可过期的 Workflow Provenance,用于绑定 Run、Tenant、Task、Agent 与 Principal,但父 Workflow 本身不得授予操作权限。
|
||||
|
||||
验收:
|
||||
|
||||
- Workflow Provenance 使用 Ed25519 签名。
|
||||
- `allowed_paths` 与 `allowed_git_operations` 为空。
|
||||
- 上下文、签名、TTL、Nonce、Key ID 不合法时默认拒绝。
|
||||
- 撤销父 Workflow 后全部子 Grant 失效。
|
||||
|
||||
### UR-017 最小权限子 Grant
|
||||
|
||||
所有生产副作用必须通过与单一 ExecutionPath 对应的子 Grant 授权。
|
||||
|
||||
验收:
|
||||
|
||||
- Runtime、Evidence、Git、Deployment、Rollback、Audit 和 Code Change 使用独立 Grant。
|
||||
- 一个 Grant 只能包含一个路径。
|
||||
- Git Grant 必须限定具体 GitOperation。
|
||||
- 子 Grant 具有独立 TTL、撤销、状态和重放防护。
|
||||
|
||||
### UR-018 Runtime Result 信任绑定
|
||||
|
||||
OpenClaw/Hermes 结果只有在与持久 Dispatch 的身份和执行上下文完全匹配时,才能更新权威 Task。
|
||||
|
||||
验收:
|
||||
|
||||
- 至少校验 tenant、task、agent、principal、trace、runtime、runtime execution、provenance 和 run。
|
||||
- 不同终态结果摘要不得覆盖已有终态。
|
||||
- Hermes 终态结果必须来自持有 Job Lease 的 Worker。
|
||||
- Hermes Worker 生命周期验收入口必须是默认关闭的内部接口,仅接受可信
|
||||
`runtime` 或 `platform_admin` 身份;普通 Operator、浏览器和公共 API 不得直接调用。
|
||||
- 每次 Claim/Start/Heartbeat/Complete/Fail/Cancel 必须绑定
|
||||
tenant、task、trace、principal、provenance、run、dispatch、job、cell 和 profile。
|
||||
- Complete/Fail/Cancel 必须通过 `ExecutionOrchestrator.reconcile_hermes` 更新权威
|
||||
Task/Dispatch,并同步生成 Audit/Event 与 Execution Evidence。
|
||||
- Lease 到期必须持久化清除旧 Owner、递增 revision 并允许安全重领;旧 Worker
|
||||
后续 Result 必须拒绝。
|
||||
- Runtime callback 审计不得绕过 Orchestrator Reconcile。
|
||||
|
||||
### UR-019 Dispatch 持久化与恢复
|
||||
|
||||
Runtime 副作用之前必须持久化唯一 Dispatch,重启后能够恢复并继续严格 Reconcile。
|
||||
|
||||
验收:
|
||||
|
||||
- 同租户 Task 和 Runtime Execution 各自唯一绑定一个 Dispatch。
|
||||
- Dispatch 支持按 ID、Task 与 Runtime Execution 查询。
|
||||
- 终态 Dispatch 不得迁移到不同终态。
|
||||
- Hermes Job、Result、Lease、幂等键和 Worker heartbeat 必须与 Dispatch 一样在
|
||||
服务重启后恢复;不得以只存在于进程内的 Map 作为在线验收依据。
|
||||
- 有 SQLite Repository 重启恢复测试。
|
||||
|
||||
### UR-020 OpenClaw Ed25519 命令合同
|
||||
|
||||
OpenClaw 生产命令必须使用版本化 Ed25519 合同,不得继续使用 HMAC 作为新命令信任根。
|
||||
|
||||
验收:
|
||||
|
||||
- 合同版本为 `aios.openclaw.command.v2`。
|
||||
- 签名覆盖 Key ID、算法、公钥 Fingerprint、Tenant、Task、Trace、Payload、Idempotency 与时间字段。
|
||||
- Key ID/Fingerprint/签名/过期或时钟偏差不合法时拒绝。
|
||||
- Fingerprint 使用恒定时间比较。
|
||||
|
||||
### UR-021 服务级权限隔离
|
||||
|
||||
每个生产服务或 Worker 只能加载其职责所需的 Grant,不得加载全部 Grant 备用。
|
||||
|
||||
验收:
|
||||
|
||||
- 默认 AIOS Application 仅加载 Runtime、Evidence 与 Audit Grant。
|
||||
- Git、Deployment、Rollback 与 Code Change 由独立 Scope 加载。
|
||||
- 空 Scope、多余 Grant 映射和未声明路径调用全部拒绝。
|
||||
- Authorization Receipt 记录 Grant ID、Writer ID 和 Scope。
|
||||
|
||||
### UR-022 CLI 单 Grant 授权
|
||||
|
||||
运维 CLI 的一次授权操作只能加载一个与请求路径一致的 Grant。
|
||||
|
||||
验收:
|
||||
|
||||
- `authorize` 使用一个 `--path` 和一个 `--grant-id`。
|
||||
- Grant 类型与 Path 不一致时拒绝。
|
||||
- CLI 不提供一次加载七个生产 Grant 的授权入口。
|
||||
- 旧全权限 `issue` 仅允许候选兼容,不得进入生产流程。
|
||||
|
||||
## 4. 非功能需求
|
||||
|
||||
### NFR-001 安全
|
||||
|
||||
- 默认拒绝、最小权限、租户隔离、身份可信链、SecretRef、审计、可撤销 Provenance 和 Runtime 结果绑定。
|
||||
|
||||
### NFR-002 可靠性
|
||||
|
||||
- 幂等、revision、worker lease、heartbeat、重试边界、原子持久化、Dispatch 恢复、健康检查和回滚。
|
||||
|
||||
### NFR-003 可维护性
|
||||
|
||||
- 模块边界稳定,Control Plane 与 Runtime 解耦;代码、文档、测试和部署可追踪。
|
||||
|
||||
### NFR-004 可扩展性
|
||||
|
||||
- Store、Transport、Policy、EventPublisher、Runtime Adapter、Provenance Verifier 与 Writer 均通过接口扩展。
|
||||
|
||||
### NFR-005 可运维性
|
||||
|
||||
- Web/API 状态、systemd/Docker、健康检查、日志、GitOps 状态、候选报告、Grant 状态和 Receipt。
|
||||
|
||||
### NFR-006 性能候选指标
|
||||
|
||||
候选版上线前至少验证:
|
||||
|
||||
- API P95、任务调度延迟、队列等待、Worker 心跳、SQLite 锁等待、审计写入时间、Grant 授权延迟和 Dispatch 恢复时间。
|
||||
- 具体 SLO 在预发布基准测试后固化,禁止无证据承诺。
|
||||
|
||||
## 5. 本候选版本范围
|
||||
|
||||
### 已纳入代码
|
||||
|
||||
- Control Plane、持久化、Gateway、Orchestrator、OpenClaw Adapter、Hermes Boundary、Execution Tracking、Web Console、GitOps Status、Run Provenance、Least-Privilege Grant、Scoped Writer、Dispatch Repository、部署和回滚资产。
|
||||
|
||||
### 已纳入测试代码
|
||||
|
||||
- Control Plane/Runtime 候选流程。
|
||||
- OpenClaw Ed25519 签名与验证。
|
||||
- Hermes Worker Lease 与严格 Reconcile。
|
||||
- Dispatch SQLite 重启恢复。
|
||||
- Workflow/Grant 撤销、过期、重放和服务 Scope 隔离。
|
||||
|
||||
### 尚需环境验证
|
||||
|
||||
- 完整 Acceptance 实际执行证据。
|
||||
- OpenClaw 真实 Runtime 联调。
|
||||
- 生产数据库/队列替换或容量验证。
|
||||
- 预发布性能、安全、重启和回滚演练。
|
||||
- Owner 对 merge、Tag 和生产部署的批准。
|
||||
|
||||
## 6. 用户验收场景
|
||||
|
||||
1. 平台管理员创建租户并注册 OpenClaw/Hermes Agent。
|
||||
2. 操作员创建任务,审批人批准。
|
||||
3. Owner 或受控签发端签发 Workflow Provenance 与所需最小权限 Grant。
|
||||
4. AIOS Orchestrator 持久化 Dispatch,并创建 Ed25519 命令或租户分区 Job。
|
||||
5. Runtime 执行并返回与 Dispatch 完全匹配的结果。
|
||||
6. AIOS 更新 Task、Audit、Authorization Receipt 和 Execution Evidence。
|
||||
7. 租户用户在 Web Console 查看完整链路。
|
||||
8. 跨租户、跨 Principal、跨 Grant Path 和重放请求被拒绝。
|
||||
9. 服务重启后 Control Plane、Dispatch 和 Provenance 状态恢复。
|
||||
10. 候选部署健康检查、Acceptance 和回滚演练实际执行并保存证据。
|
||||
@@ -0,0 +1,461 @@
|
||||
# AIOS V2 目标架构
|
||||
|
||||
- 文档版本:`V2R1C0-candidate`
|
||||
- 架构状态:目标架构已实现为候选代码,待预发布验证
|
||||
- 适用范围:Control Plane、Agent Router、OpenClaw、Hermes、Web Console、GitOps、审计、部署与运维
|
||||
|
||||
## 1. 架构目标
|
||||
|
||||
AIOS V2 的核心目标是把分散在 OpenClaw、Hermes、Agent Router、局部 WebUI 和 GitOps 中的控制能力收敛为一个权威控制面,同时保留现有执行能力,避免推倒重写。
|
||||
|
||||
目标状态:
|
||||
|
||||
```text
|
||||
用户 / Web Console / Public API
|
||||
|
|
||||
v
|
||||
AIOS Control Plane
|
||||
Tenant | Identity | Agent | Task | Policy | Approval | Audit
|
||||
|
|
||||
v
|
||||
Execution Orchestrator / Agent Router
|
||||
/ \
|
||||
v v
|
||||
OpenClaw Adapter Hermes Boundary
|
||||
| |
|
||||
v v
|
||||
OpenClaw Runtime Hermes Workers
|
||||
\ /
|
||||
v v
|
||||
Result Reconciliation + Execution Evidence
|
||||
```
|
||||
|
||||
设计结论:
|
||||
|
||||
- AIOS 是唯一控制面。
|
||||
- Agent Router 是调度平面,不是第二控制面。
|
||||
- OpenClaw 是执行适配与 Runtime。
|
||||
- Hermes 是队列、Worker、Profile 与执行 Runtime。
|
||||
- Web Console 只调用 AIOS API。
|
||||
- GitOps 是代码、配置、文档和发布变更的唯一入口。
|
||||
|
||||
## 2. 从现有架构到目标架构
|
||||
|
||||
### 2.1 现有能力
|
||||
|
||||
现有系统已经具备:
|
||||
|
||||
- OpenClaw 执行与 Fleet 能力。
|
||||
- Hermes Worker、Profile、队列和工作区能力。
|
||||
- Agent Router 路由经验和部分调度接口。
|
||||
- GitOps 分支、提交、审批、回滚和审计能力。
|
||||
- Tenant Context、Tenant Router、Memory Scope、SecretRef、Message Ledger 和审计候选实现。
|
||||
- 局部 WebUI、Gateway 和自动任务领取能力。
|
||||
|
||||
### 2.2 现有问题
|
||||
|
||||
- 控制逻辑分散,可能存在多个任务事实源。
|
||||
- OpenClaw/Hermes 内部仍可能保存租户、策略或任务状态。
|
||||
- 候选能力分散在多个分支,主线缺少权威实现。
|
||||
- WebUI 与 API 入口不统一。
|
||||
- 分支名称、代码、测试和部署证据之间缺少映射。
|
||||
- 多租户隔离多为逻辑约束,尚缺全链路生产证据。
|
||||
|
||||
### 2.3 演进原则
|
||||
|
||||
- 先加边界和适配器,再迁移控制权。
|
||||
- 先复用接口,再替换内部实现。
|
||||
- 先在候选分支验证,再受控提升。
|
||||
- 不允许同时存在两套权威任务生命周期。
|
||||
- 不以“大分支存在”代替验收证据。
|
||||
|
||||
## 3. 逻辑分层
|
||||
|
||||
### 3.1 Web 与 API 层
|
||||
|
||||
职责:
|
||||
|
||||
- 提供 Tenant、Agent、Task、Approval、Runtime、Audit、Execution Evidence 和 GitOps 页面/API。
|
||||
- 依赖可信身份代理注入 `X-AIOS-*` 身份头。
|
||||
- 不允许浏览器直接访问 OpenClaw 或 Hermes。
|
||||
- 不允许客户端自行选择或覆盖 `tenant_id`。
|
||||
|
||||
候选实现:
|
||||
|
||||
- `active-runtime/app/aios_v2/app.py`
|
||||
- `active-runtime/app/aios_v2/gateway.py`
|
||||
- `active-runtime/app/aios_v2/console.py`
|
||||
|
||||
### 3.2 AIOS Control Plane
|
||||
|
||||
权威职责:
|
||||
|
||||
- Tenant Registry
|
||||
- Agent Registry
|
||||
- Task Lifecycle
|
||||
- Policy Decision
|
||||
- Approval
|
||||
- Audit Event
|
||||
- Runtime Inventory
|
||||
- Execution Evidence
|
||||
- Deployment/GitOps Status
|
||||
|
||||
不负责:
|
||||
|
||||
- OpenClaw 内部执行细节。
|
||||
- Hermes Worker 内部执行细节。
|
||||
- 直接持有 Runtime 凭据明文。
|
||||
|
||||
候选实现:
|
||||
|
||||
- `active-runtime/app/aios_v2/control_plane.py`
|
||||
- `active-runtime/app/aios_v2/persistence.py`
|
||||
- `active-runtime/app/aios_v2/execution_tracking.py`
|
||||
- `active-runtime/app/aios_v2/gitops_status.py`
|
||||
|
||||
### 3.3 Execution Orchestrator / Agent Router
|
||||
|
||||
职责:
|
||||
|
||||
- 只接受 `APPROVED` 任务。
|
||||
- 根据 Agent Registry 和 Policy Result 选择 Runtime。
|
||||
- 生成 OpenClawCommand 或 HermesJob。
|
||||
- 传播 tenant、task、trace、idempotency 和 policy version。
|
||||
- 将 Runtime Result 回写 AIOS Task。
|
||||
|
||||
不负责:
|
||||
|
||||
- 创建租户。
|
||||
- 修改策略。
|
||||
- 绕过审批。
|
||||
- 保存第二套任务状态机。
|
||||
|
||||
候选实现:
|
||||
|
||||
- `active-runtime/app/aios_v2/orchestrator.py`
|
||||
|
||||
### 3.4 OpenClaw Adapter
|
||||
|
||||
职责:
|
||||
|
||||
- 验证签名命令。
|
||||
- 执行、查询、取消、健康检查和回调。
|
||||
- 支持幂等、超时和租户隔离。
|
||||
- 把 Runtime 生命周期转换为 AIOS 审计事件。
|
||||
|
||||
不负责:
|
||||
|
||||
- Tenant、Policy、Approval、Task Lifecycle。
|
||||
- 向浏览器暴露公网控制接口。
|
||||
|
||||
候选实现:
|
||||
|
||||
- `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`
|
||||
|
||||
### 3.5 Hermes Runtime Boundary
|
||||
|
||||
职责:
|
||||
|
||||
- Tenant/Cell/Profile 分区队列。
|
||||
- Worker claim、start、heartbeat、complete、fail、cancel。
|
||||
- Lease 超时和自动回队列。
|
||||
- Result 回传和 Runtime Health。
|
||||
|
||||
不负责:
|
||||
|
||||
- Policy、Approval、Tenant Registry、权威 Task Lifecycle。
|
||||
|
||||
候选实现:
|
||||
|
||||
- `active-runtime/app/aios_hermes/contract.py`
|
||||
- `active-runtime/app/aios_hermes/adapter.py`
|
||||
- `active-runtime/app/aios_hermes/worker.py`
|
||||
|
||||
### 3.6 Persistence
|
||||
|
||||
候选实现使用 SQLite WAL 原子快照,持久化:
|
||||
|
||||
- Tenant
|
||||
- Agent
|
||||
- Task
|
||||
- Audit
|
||||
- Idempotency
|
||||
- Execution Evidence 文件
|
||||
|
||||
生产演进:
|
||||
|
||||
- Store 接口保持稳定。
|
||||
- 可替换为 PostgreSQL、对象存储或分布式事件存储。
|
||||
- 生产替换必须提供迁移、备份、恢复、HA、容量和租户隔离证据。
|
||||
|
||||
## 4. 多租户架构
|
||||
|
||||
### 4.1 权威租户上下文
|
||||
|
||||
每次请求和执行至少传播:
|
||||
|
||||
```text
|
||||
tenant_id
|
||||
principal_id
|
||||
session_id
|
||||
trace_id
|
||||
task_id
|
||||
policy_version
|
||||
```
|
||||
|
||||
Runtime 还传播:
|
||||
|
||||
```text
|
||||
command_id / job_id
|
||||
cell_id
|
||||
profile_id
|
||||
idempotency_key
|
||||
worker_id
|
||||
```
|
||||
|
||||
### 4.2 隔离层级
|
||||
|
||||
| 层级 | 隔离要求 |
|
||||
|---|---|
|
||||
| HTTP/API | 可信身份头、租户不可由浏览器覆盖 |
|
||||
| Control Plane | 所有资源带 `tenant_id`,跨租户默认拒绝 |
|
||||
| OpenClaw | 签名命令绑定 tenant/task/trace |
|
||||
| Hermes | tenant/cell/profile 三层分区 |
|
||||
| Storage | 候选为显式租户字段;生产需 RLS 或物理隔离策略 |
|
||||
| Evidence/Audit | 仅按当前租户查询 |
|
||||
| Cache/Memory | key 必须包含 tenant namespace |
|
||||
| Secret | 只保存引用,不保存明文 |
|
||||
| Logs/Metrics | 必须包含 tenant/task/trace 标签,并限制查询范围 |
|
||||
|
||||
### 4.3 失败行为
|
||||
|
||||
- 跨租户资源访问返回拒绝或“未找到”。
|
||||
- 不泄露其他租户资源存在性。
|
||||
- 缺少 tenant context 时 fail closed。
|
||||
- Runtime 返回的 tenant/task/trace 不匹配时拒绝回写。
|
||||
|
||||
## 5. 任务与执行数据流
|
||||
|
||||
### 5.1 任务创建与审批
|
||||
|
||||
```text
|
||||
User/API
|
||||
|
|
||||
v
|
||||
Trusted Identity
|
||||
|
|
||||
v
|
||||
AIOS Gateway
|
||||
|
|
||||
v
|
||||
Policy Gate
|
||||
|
|
||||
v
|
||||
Task CREATED
|
||||
|
|
||||
v
|
||||
Approval
|
||||
|
|
||||
v
|
||||
Task APPROVED
|
||||
```
|
||||
|
||||
### 5.2 OpenClaw 执行
|
||||
|
||||
```text
|
||||
APPROVED Task
|
||||
|
|
||||
v
|
||||
Execution Orchestrator
|
||||
|
|
||||
v
|
||||
Signed OpenClawCommand
|
||||
|
|
||||
v
|
||||
OpenClaw Adapter
|
||||
|
|
||||
v
|
||||
Runtime Result
|
||||
|
|
||||
v
|
||||
Task Reconciliation + Audit + Evidence
|
||||
```
|
||||
|
||||
### 5.3 Hermes 执行
|
||||
|
||||
```text
|
||||
APPROVED Task
|
||||
|
|
||||
v
|
||||
Execution Orchestrator
|
||||
|
|
||||
v
|
||||
Tenant/Cell/Profile HermesJob
|
||||
|
|
||||
v
|
||||
Worker Claim + Lease + Heartbeat
|
||||
|
|
||||
v
|
||||
HermesResult
|
||||
|
|
||||
v
|
||||
Task Reconciliation + Audit + Evidence
|
||||
```
|
||||
|
||||
## 6. 安全架构
|
||||
|
||||
### 6.1 身份边界
|
||||
|
||||
- Public API 位于可信反向代理之后。
|
||||
- 反向代理完成登录、会话、MFA 和身份头注入。
|
||||
- 候选应用拒绝未认证身份断言。
|
||||
- 生产不得允许客户端直接伪造 `X-AIOS-*`。
|
||||
|
||||
### 6.2 Runtime 命令完整性
|
||||
|
||||
OpenClawCommand 使用规范化序列化和 HMAC-SHA256:
|
||||
|
||||
- 签名覆盖 tenant、task、trace、action、payload、idempotency 和时间。
|
||||
- 支持 key ID、到期时间和时钟偏差。
|
||||
- Runtime 密钥通过受保护文件或外部 Secret Provider 解析。
|
||||
|
||||
### 6.3 Secret 边界
|
||||
|
||||
Git 允许:
|
||||
|
||||
```text
|
||||
secret_ref
|
||||
credential_ref
|
||||
key_id
|
||||
受保护文件路径
|
||||
```
|
||||
|
||||
Git 禁止:
|
||||
|
||||
```text
|
||||
API Key
|
||||
密码
|
||||
Token
|
||||
私钥
|
||||
签名材料
|
||||
```
|
||||
|
||||
### 6.4 Web 安全
|
||||
|
||||
候选应用设置:
|
||||
|
||||
- no-store
|
||||
- nosniff
|
||||
- DENY frame
|
||||
- no-referrer
|
||||
- CSP
|
||||
- 请求体大小限制
|
||||
|
||||
生产还需验证:
|
||||
|
||||
- CSRF/CORS
|
||||
- Rate Limit
|
||||
- Session Timeout
|
||||
- CSP Nonce/Hash
|
||||
- WAF 和反向代理访问策略
|
||||
|
||||
## 7. 可靠性架构
|
||||
|
||||
### 7.1 幂等
|
||||
|
||||
- Control Plane:`tenant_id + idempotency_key + request_digest`。
|
||||
- OpenClaw:`tenant_id + idempotency_key + signature`。
|
||||
- Hermes:`tenant_id + idempotency_key + job_digest`。
|
||||
|
||||
### 7.2 并发
|
||||
|
||||
- Task 使用 revision。
|
||||
- Hermes 使用 revision + worker lease。
|
||||
- GitOps 使用 detached controller + branch lease。
|
||||
- 持久化使用 SQLite `BEGIN IMMEDIATE` 和原子快照。
|
||||
|
||||
### 7.3 恢复
|
||||
|
||||
- Controller restart:detached guard。
|
||||
- AIOS restart:SQLite restore。
|
||||
- Worker crash:lease 到期后 Job 回到 QUEUED。
|
||||
- Release failure:健康检查失败自动恢复 previous release。
|
||||
|
||||
## 8. 可观测架构
|
||||
|
||||
统一关联键:
|
||||
|
||||
```text
|
||||
tenant_id
|
||||
principal_id
|
||||
trace_id
|
||||
task_id
|
||||
agent_id
|
||||
command_id / job_id
|
||||
worker_id
|
||||
commit
|
||||
```
|
||||
|
||||
Web Console 展示:
|
||||
|
||||
- Tasks
|
||||
- Agents
|
||||
- Runtime Health
|
||||
- Audit
|
||||
- Execution Evidence
|
||||
- GitOps Status
|
||||
|
||||
生产还需接入:
|
||||
|
||||
- 结构化日志
|
||||
- Metrics
|
||||
- Distributed Tracing
|
||||
- Alerting
|
||||
- SLO Dashboard
|
||||
|
||||
## 9. 部署架构
|
||||
|
||||
支持两种候选部署:
|
||||
|
||||
### systemd
|
||||
|
||||
- 非 root `aios` 用户。
|
||||
- `ProtectSystem=strict`、`NoNewPrivileges` 等安全选项。
|
||||
- 状态目录 `/var/lib/aios-v2`。
|
||||
|
||||
### Docker/Compose
|
||||
|
||||
- 非 root UID/GID。
|
||||
- Read-only root filesystem。
|
||||
- Drop all capabilities。
|
||||
- State volume。
|
||||
- HTTP healthcheck。
|
||||
|
||||
## 10. 架构约束
|
||||
|
||||
以下行为视为架构违规:
|
||||
|
||||
1. OpenClaw/Hermes 直接创建或批准 AIOS Task。
|
||||
2. Web Console 直接调用 Runtime。
|
||||
3. 新模块不携带 `tenant_id`。
|
||||
4. 新增第二套任务状态机或租户事实源。
|
||||
5. 在 Git 中提交明文凭据。
|
||||
6. 绕过 GitOps 修改生产代码/配置。
|
||||
7. 架构或功能变化未同步更新 `docs/aios-v2/`。
|
||||
8. 未通过测试和预发布门禁直接提升候选版本。
|
||||
|
||||
## 11. 目标架构完成判定
|
||||
|
||||
目标架构只有在以下证据齐全时才视为完成:
|
||||
|
||||
- 文档与代码映射完整。
|
||||
- Candidate tests 对精确 commit 执行通过。
|
||||
- OpenClaw/Hermes 实际 Runtime 联调通过。
|
||||
- 多租户负向测试通过。
|
||||
- 重启恢复和回滚演练通过。
|
||||
- GitOps 本地/Gitea OID 一致。
|
||||
- Owner 批准 merge、Tag 和生产部署。
|
||||
@@ -0,0 +1,313 @@
|
||||
# AIOS V2 迁移与交付策略
|
||||
|
||||
- 文档版本:`V2R1C0-candidate`
|
||||
- 交付原则:增量迁移、能力复用、控制权收敛、GitOps 唯一变更入口
|
||||
|
||||
## 1. 迁移目标
|
||||
|
||||
AIOS V2 不通过一次性重写替换现有系统,而是在保留 OpenClaw、Hermes、Agent Router、GitOps 和既有运行能力的前提下,将租户、策略、任务、审批、审计和发布治理收敛到 AIOS Control Plane。
|
||||
|
||||
迁移完成的标志不是“新代码存在”,而是:
|
||||
|
||||
- AIOS 成为唯一权威控制面;
|
||||
- OpenClaw/Hermes 不再保存第二套控制状态;
|
||||
- 所有控制功能 Web/API 化;
|
||||
- 所有模块通过租户隔离、测试和预发布门禁;
|
||||
- 本地 Git、Gitea、测试、部署和回滚证据可追踪。
|
||||
|
||||
## 2. 为什么采用增量迁移
|
||||
|
||||
### 2.1 避免能力回退
|
||||
|
||||
OpenClaw、Hermes 和 Agent Router 已经包含大量运行经验、边界处理和执行能力。整体重写会扩大风险面,并导致业务能力、操作流程和历史数据回退。
|
||||
|
||||
### 2.2 保持可回滚
|
||||
|
||||
每个迁移步骤必须:
|
||||
|
||||
- 独立分支;
|
||||
- 小范围提交;
|
||||
- 独立测试;
|
||||
- 可单独回滚;
|
||||
- 不要求立即关闭旧执行路径。
|
||||
|
||||
### 2.3 先收敛控制权,再优化内部实现
|
||||
|
||||
迁移优先级:
|
||||
|
||||
```text
|
||||
唯一入口
|
||||
-> 权威租户/任务/策略
|
||||
-> Runtime Adapter
|
||||
-> 数据层生产化
|
||||
-> Web 与可观测
|
||||
-> 性能与 HA
|
||||
```
|
||||
|
||||
## 3. 分阶段迁移路线
|
||||
|
||||
### Phase 0:GitOps 与架构事实源
|
||||
|
||||
目标:建立可靠变更链和权威设计基线。
|
||||
|
||||
已完成候选能力:
|
||||
|
||||
- Controller detached guard;
|
||||
- 避免 fetch 到已检出本地分支;
|
||||
- Gitea SSH 镜像;
|
||||
- `docs/aios-v2/` 架构事实源;
|
||||
- 候选分支、部署和回滚资产。
|
||||
|
||||
退出条件:
|
||||
|
||||
- Controller detached 且 clean;
|
||||
- 本地/Gitea OID 一致;
|
||||
- 架构与需求文档纳入版本。
|
||||
|
||||
### Phase 1:Control Plane 权威化
|
||||
|
||||
目标:将 Tenant、Agent、Task、Policy、Approval 和 Audit 收敛到 AIOS。
|
||||
|
||||
候选实现:
|
||||
|
||||
- `aios_v2/control_plane.py`
|
||||
- `aios_v2/persistence.py`
|
||||
- `aios_v2/gateway.py`
|
||||
- `aios_v2/app.py`
|
||||
|
||||
退出条件:
|
||||
|
||||
- 任务状态机统一;
|
||||
- 幂等、revision、审计和跨租户拒绝通过测试;
|
||||
- 服务重启后权威状态恢复。
|
||||
|
||||
### Phase 2:OpenClaw 解耦
|
||||
|
||||
目标:OpenClaw 从控制逻辑转为执行适配器。
|
||||
|
||||
步骤:
|
||||
|
||||
1. 定义签名命令合同;
|
||||
2. 引入 Adapter;
|
||||
3. 将直接调用迁移到 AIOS Orchestrator;
|
||||
4. Runtime 只返回执行结果和健康状态;
|
||||
5. 关闭或网络隔离旧公共控制入口。
|
||||
|
||||
退出条件:
|
||||
|
||||
- 未批准任务无法生成有效命令;
|
||||
- 命令绑定 tenant/task/trace/idempotency;
|
||||
- 旧控制接口冻结并记录替代路径。
|
||||
|
||||
### Phase 3:Hermes 解耦
|
||||
|
||||
目标:Hermes 只承担租户分区队列和 Worker Runtime。
|
||||
|
||||
步骤:
|
||||
|
||||
1. 定义 HermesJob/HermesResult;
|
||||
2. 强制 tenant/cell/profile 分区;
|
||||
3. 引入 claim/lease/heartbeat;
|
||||
4. 将结果统一回写 AIOS;
|
||||
5. 移除 Hermes 内部策略和任务事实源。
|
||||
|
||||
退出条件:
|
||||
|
||||
- Worker 无权创建 AIOS Task;
|
||||
- 租约过期后 Job 可恢复;
|
||||
- 跨租户 claim/read/result 被拒绝。
|
||||
|
||||
### Phase 4:Web 与运维统一
|
||||
|
||||
目标:所有用户与运维功能通过 AIOS Web/API。
|
||||
|
||||
范围:
|
||||
|
||||
- Tenant、Agent、Task、Runtime、Audit、Execution Evidence、GitOps;
|
||||
- systemd/Docker/Compose;
|
||||
- healthcheck、rollback、release report。
|
||||
|
||||
退出条件:
|
||||
|
||||
- 浏览器不直接调用 Runtime;
|
||||
- 生产身份代理和权限模型通过验证;
|
||||
- 部署、重启和回滚演练通过。
|
||||
|
||||
### Phase 5:生产数据层与 HA
|
||||
|
||||
目标:将候选 SQLite/内存运行状态替换或强化为生产级后端。
|
||||
|
||||
要求:
|
||||
|
||||
- 数据迁移;
|
||||
- RLS 或物理隔离;
|
||||
- 备份恢复;
|
||||
- HA 与容量;
|
||||
- 多实例并发;
|
||||
- 灾难恢复目标。
|
||||
|
||||
该阶段不得改变上层合同,避免 Runtime 和 Web 再次耦合存储实现。
|
||||
|
||||
## 4. 分支与提交策略
|
||||
|
||||
### 4.1 分支类型
|
||||
|
||||
| 类型 | 用途 |
|
||||
|---|---|
|
||||
| `task/*` | 可执行任务合同与主体实现 |
|
||||
| `patch/*` | 独立修复或窄范围增强 |
|
||||
| `integration/*` | 多模块候选收敛 |
|
||||
| `result/*` | 自动执行结果与证据 |
|
||||
| `release/*` | 受控发布候选 |
|
||||
|
||||
### 4.2 规则
|
||||
|
||||
- 禁止直接修改 `main`;
|
||||
- 一个提交应可独立审阅和回滚;
|
||||
- 大文件和大范围变更应拆分;
|
||||
- 所有行为变化必须同步文档和测试;
|
||||
- 生产 Tag、部署和回滚需要 Owner 批准。
|
||||
|
||||
## 5. GitOps 交付流程
|
||||
|
||||
```text
|
||||
需求/架构更新
|
||||
|
|
||||
v
|
||||
任务分支 + 文档 + 测试
|
||||
|
|
||||
v
|
||||
代码提交 + Secret Gate
|
||||
|
|
||||
v
|
||||
本地 bare repo 同步
|
||||
|
|
||||
v
|
||||
Gitea 镜像与 OID 校验
|
||||
|
|
||||
v
|
||||
Candidate 集成
|
||||
|
|
||||
v
|
||||
自动测试与预发布
|
||||
|
|
||||
v
|
||||
Owner 审批
|
||||
|
|
||||
v
|
||||
Merge / Tag / Production Deploy
|
||||
```
|
||||
|
||||
### 5.1 同步状态
|
||||
|
||||
GitOps 返回必须区分:
|
||||
|
||||
- local sync;
|
||||
- Gitea sync;
|
||||
- branch OID;
|
||||
- workspace mode;
|
||||
- dirty state。
|
||||
|
||||
仅返回 `common_git_dir synced` 不足以证明 Web 远端可见。
|
||||
|
||||
## 6. 发布门禁
|
||||
|
||||
### Gate A:设计完整性
|
||||
|
||||
- 用户需求、目标架构、模块契约、ADR 和追踪矩阵同步;
|
||||
- 无冲突标记、断链或过期路径。
|
||||
|
||||
### Gate B:代码质量
|
||||
|
||||
- 包可导入;
|
||||
- 静态编译通过;
|
||||
- Secret Scanner 通过;
|
||||
- 无已知越权旁路。
|
||||
|
||||
### Gate C:测试
|
||||
|
||||
- 单元、集成、多租户负向、重启恢复、Runtime 边界测试通过;
|
||||
- 记录 commit、命令、exit code、pass/fail 和 artifact digest。
|
||||
|
||||
### Gate D:预发布
|
||||
|
||||
- systemd 或 Compose 启动成功;
|
||||
- 健康检查通过;
|
||||
- OpenClaw/Hermes 真实联调通过;
|
||||
- 备份、重启和回滚演练通过;
|
||||
- 日志中无敏感信息。
|
||||
|
||||
### Gate E:生产批准
|
||||
|
||||
- Owner 批准 merge、Tag 和生产部署;
|
||||
- 发布窗口、回滚负责人和观察指标明确;
|
||||
- 生产变更通过 GitOps 记录。
|
||||
|
||||
## 7. 回滚策略
|
||||
|
||||
### 7.1 代码回滚
|
||||
|
||||
- 使用 `/opt/aios/current` 原子 symlink 切换;
|
||||
- 回滚前备份状态;
|
||||
- 健康检查失败自动恢复 previous release。
|
||||
|
||||
### 7.2 状态回滚
|
||||
|
||||
默认不自动回滚状态,避免覆盖候选运行期间新增的 Task、Audit 和 Evidence。
|
||||
|
||||
状态恢复只有在:
|
||||
|
||||
- 明确确认 schema 不兼容;
|
||||
- 数据备份可验证;
|
||||
- Owner 显式授权;
|
||||
|
||||
时启用。
|
||||
|
||||
### 7.3 Runtime 回滚
|
||||
|
||||
OpenClaw/Hermes Adapter 采用稳定合同。若候选执行层失败,可恢复旧 Runtime 版本,但不得恢复旧控制权旁路。
|
||||
|
||||
## 8. Bug 修复流程
|
||||
|
||||
生产或预发布 Bug:
|
||||
|
||||
1. 创建 `patch/bugfix/*`;
|
||||
2. 添加可复现测试;
|
||||
3. 修复代码;
|
||||
4. 更新相关需求/架构/契约/ADR;
|
||||
5. 运行候选验收;
|
||||
6. 进入新的 release candidate;
|
||||
7. Owner 批准部署。
|
||||
|
||||
禁止在生产目录直接编辑文件后不回写 Git。
|
||||
|
||||
## 9. 文档同步规则
|
||||
|
||||
以下变化必须更新文档:
|
||||
|
||||
- 用户行为或页面;
|
||||
- API 路径、Header、请求/响应;
|
||||
- 数据模型、状态机、策略;
|
||||
- OpenClaw/Hermes/Router 边界;
|
||||
- 多租户与安全模型;
|
||||
- 部署、健康检查、回滚;
|
||||
- 测试或发布门禁。
|
||||
|
||||
对应关系:
|
||||
|
||||
- 需求变化:更新 `01-USER-REQUIREMENTS.md`;
|
||||
- 架构变化:更新 `02-TARGET-ARCHITECTURE.md` 和 ADR;
|
||||
- 迁移/发布变化:更新本文件;
|
||||
- 合同变化:更新 `04-MODULE-CONTRACTS.md`;
|
||||
- 代码/测试路径变化:更新 `05-TRACEABILITY-MATRIX.md`。
|
||||
|
||||
## 10. 当前候选后续步骤
|
||||
|
||||
1. 完成文档同步门禁和 Acceptance Runner;
|
||||
2. 在精确 Candidate commit 执行测试;
|
||||
3. 推送 Gitea 并校验 OID;
|
||||
4. 部署隔离预发布环境;
|
||||
5. 联调真实 OpenClaw/Hermes;
|
||||
6. 执行重启、性能、安全和回滚演练;
|
||||
7. 生成最终 evidence;
|
||||
8. 请求 Owner 的 merge/Tag/production approval。
|
||||
@@ -0,0 +1,608 @@
|
||||
# AIOS V2 模块契约
|
||||
|
||||
- 文档版本:`V2R1-hardening-candidate`
|
||||
- 状态:加固候选契约基线
|
||||
- 原则:Control Plane 权威、Runtime 仅执行、默认拒绝、服务级最小权限、全链路租户隔离、所有权威状态可审计和恢复
|
||||
|
||||
核心模型名称与实现保持逐字同步:`RequestContext` 承载可信租户、主体、角色、trace、
|
||||
session 与 policy version;`TaskState` 是 AIOS 权威 Task 生命周期枚举,Runtime Worker
|
||||
不得直接写入或复制该状态机。
|
||||
|
||||
## 1. 通用可信上下文契约
|
||||
|
||||
所有控制与执行请求必须携带以下上下文:
|
||||
|
||||
| 字段 | 必填 | 说明 |
|
||||
|---|---:|---|
|
||||
| `tenant_id` | 是 | 权威租户标识 |
|
||||
| `principal_id` | 控制和 Reconcile 是 | 已认证主体 |
|
||||
| `trace_id` | 是 | 全链路追踪 |
|
||||
| `task_id` | 执行阶段是 | AIOS 权威任务 |
|
||||
| `agent_id` | 执行和 Provenance 是 | 任务绑定 Agent |
|
||||
| `provenance_id` | 生产副作用操作是 | 父 Workflow Provenance |
|
||||
| `run_id` | 生产副作用操作是 | 本次执行 Run |
|
||||
| `dispatch_id` | Runtime Result 是 | 持久化 Dispatch 记录 |
|
||||
| `policy_version` | 控制请求是 | 策略版本 |
|
||||
| `idempotency_key` | 创建/执行是 | 幂等键 |
|
||||
|
||||
规则:
|
||||
|
||||
- 缺少必填字段时 fail closed。
|
||||
- 客户端不得覆盖可信代理或 AIOS 生成的租户、身份和追踪字段。
|
||||
- Runtime 返回的 tenant/task/trace/runtime execution 必须与持久 Dispatch 完全匹配。
|
||||
- Runtime Result 还必须匹配 Principal、Parent Provenance 和 Run。
|
||||
- 所有持久化键、缓存键、队列分区、Receipt 和 Evidence 路径必须包含租户命名空间。
|
||||
|
||||
## 2. Tenant Contract
|
||||
|
||||
### 2.1 TenantRecord
|
||||
|
||||
```text
|
||||
tenant_id
|
||||
display_name
|
||||
status
|
||||
metadata
|
||||
created_at
|
||||
updated_at
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- `tenant_id` 不可为空且不可变。
|
||||
- Tenant 只由 AIOS Control Plane 创建和维护。
|
||||
- Runtime 不得创建或修改租户。
|
||||
- 跨租户读取默认返回拒绝或资源不存在,不得泄露存在性。
|
||||
|
||||
实现:`active-runtime/app/aios_v2/control_plane.py`
|
||||
|
||||
## 3. Agent Contract
|
||||
|
||||
### 3.1 AgentRecord
|
||||
|
||||
```text
|
||||
agent_id
|
||||
tenant_id
|
||||
display_name
|
||||
runtime
|
||||
capabilities
|
||||
enabled
|
||||
metadata
|
||||
created_at
|
||||
updated_at
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- Agent 属于唯一租户。
|
||||
- `runtime` 由 Registry 决定,可取 `openclaw`、`hermes` 或后续注册 Runtime。
|
||||
- `capabilities` 是允许调度的动作集合。
|
||||
- `metadata` 仅保存非敏感引用,不得保存明文凭据。
|
||||
|
||||
## 4. Task Contract
|
||||
|
||||
### 4.1 TaskRecord
|
||||
|
||||
```text
|
||||
task_id
|
||||
tenant_id
|
||||
agent_id
|
||||
action
|
||||
payload
|
||||
state
|
||||
revision
|
||||
idempotency_key
|
||||
request_digest
|
||||
result
|
||||
error
|
||||
created_by
|
||||
approved_by
|
||||
created_at
|
||||
updated_at
|
||||
```
|
||||
|
||||
### 4.2 权威状态机
|
||||
|
||||
```text
|
||||
CREATED -> APPROVED -> RUNNING -> COMPLETED
|
||||
| | |
|
||||
+----------+----------+-> CANCELLED
|
||||
+-> FAILED
|
||||
```
|
||||
|
||||
允许转换:
|
||||
|
||||
| 当前 | 允许目标 | 权威入口 |
|
||||
|---|---|---|
|
||||
| CREATED | APPROVED, CANCELLED | Control Plane Approval/Cancel |
|
||||
| APPROVED | RUNNING, CANCELLED | Orchestrator Dispatch / Control Plane Cancel |
|
||||
| RUNNING | COMPLETED, FAILED, CANCELLED | Orchestrator Reconcile / Control Plane Cancel |
|
||||
| COMPLETED | 无 | 终态 |
|
||||
| FAILED | 无 | 终态 |
|
||||
| CANCELLED | 无 | 终态 |
|
||||
|
||||
约束:
|
||||
|
||||
- 每次转换必须校验 `revision`。
|
||||
- COMPLETED 必须带 `result`;FAILED 必须带 `error`。
|
||||
- 每次转换生成 AuditEvent。
|
||||
- Runtime 不得直接写 Task Store。
|
||||
- 公共 API 不得直接把任务推进到 `RUNNING`、`COMPLETED` 或 `FAILED`。
|
||||
|
||||
## 5. Policy Contract
|
||||
|
||||
### 5.1 PolicyDecision
|
||||
|
||||
```text
|
||||
allowed
|
||||
reason
|
||||
policy_version
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- Policy 默认拒绝。
|
||||
- Runtime 不得覆盖 PolicyDecision。
|
||||
- 拒绝必须审计。
|
||||
- 高风险动作必须经过 Approval。
|
||||
|
||||
## 6. Audit Contract
|
||||
|
||||
### 6.1 AuditEvent
|
||||
|
||||
```text
|
||||
event_id
|
||||
tenant_id
|
||||
principal_id
|
||||
trace_id
|
||||
action
|
||||
resource_type
|
||||
resource_id
|
||||
outcome
|
||||
policy_version
|
||||
details
|
||||
created_at
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- 按租户写入和查询。
|
||||
- `details` 不得包含明文凭据、私钥或完整敏感 Payload。
|
||||
- Runtime callback 可以生成非权威审计事件,但不得单独触发 Task 状态变化。
|
||||
- Task 状态变化必须经过 Orchestrator 严格 Reconcile。
|
||||
- 生产版需增加不可变外部固化和完整性验证。
|
||||
|
||||
## 7. Workflow Provenance Contract
|
||||
|
||||
### 7.1 RunProvenance
|
||||
|
||||
父 Workflow Provenance 只绑定身份与 Run,不授予操作权限:
|
||||
|
||||
```text
|
||||
provenance_id
|
||||
run_id
|
||||
issuer
|
||||
tenant_id
|
||||
task_id
|
||||
agent_id
|
||||
principal_id
|
||||
allowed_paths = []
|
||||
allowed_git_operations = []
|
||||
issued_at
|
||||
expires_at
|
||||
policy_version
|
||||
key_id
|
||||
nonce
|
||||
signature
|
||||
schema_version
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- 使用 Ed25519 签名。
|
||||
- `allowed_paths` 和 `allowed_git_operations` 必须为空。
|
||||
- 撤销或过期父 Workflow 后,全部子 Grant 自动失效。
|
||||
- 私钥只存在签发端,生产应用只读取公钥。
|
||||
|
||||
实现:`active-runtime/app/aios_v2/provenance.py`
|
||||
|
||||
## 8. Provenance Grant Contract
|
||||
|
||||
### 8.1 ProvenanceGrant
|
||||
|
||||
```text
|
||||
grant_id
|
||||
parent_provenance_id
|
||||
grant_type
|
||||
execution_path
|
||||
run_id
|
||||
issuer
|
||||
tenant_id
|
||||
task_id
|
||||
agent_id
|
||||
principal_id
|
||||
allowed_git_operations
|
||||
issued_at
|
||||
expires_at
|
||||
policy_version
|
||||
key_id
|
||||
nonce
|
||||
signature
|
||||
schema_version
|
||||
```
|
||||
|
||||
Grant 类型与唯一允许路径:
|
||||
|
||||
| GrantType | ExecutionPath |
|
||||
|---|---|
|
||||
| `code_change` | `code_change` |
|
||||
| `git` | `git_operation` |
|
||||
| `deployment` | `deployment` |
|
||||
| `runtime` | `runtime_execute` |
|
||||
| `evidence` | `evidence_write` |
|
||||
| `rollback` | `rollback` |
|
||||
| `audit` | `audit` |
|
||||
|
||||
约束:
|
||||
|
||||
- 一个 Grant 只允许一个路径。
|
||||
- Git Grant 必须显式声明具体 GitOperation;非 Git Grant 不得包含 Git 操作。
|
||||
- 子 Grant 身份字段必须与父 Workflow 完全一致。
|
||||
- 子 Grant TTL 不得超过父 Workflow。
|
||||
- `(grant_id, path, git_operation, request_digest)` 重复使用时拒绝。
|
||||
- Grant 支持独立 `issued/verified/used/expired/revoked` 生命周期。
|
||||
|
||||
实现:
|
||||
|
||||
- `active-runtime/app/aios_v2/provenance_grants.py`
|
||||
- `active-runtime/app/aios_v2/provenance_scoped.py`
|
||||
|
||||
## 9. Service Scoped Writer Contract
|
||||
|
||||
生产进程只加载职责所需 Grant:
|
||||
|
||||
- AIOS Application:`runtime_execute`、`evidence_write`、`audit`。
|
||||
- Git Worker:`git_operation`,代码提交场景另需独立 `code_change` Grant。
|
||||
- Deployment Worker:`deployment`。
|
||||
- Rollback Worker:`rollback`。
|
||||
- CLI 单次授权:一个 `--path` + 一个 `--grant-id`。
|
||||
|
||||
约束:
|
||||
|
||||
- 空 Scope 拒绝。
|
||||
- 多余 Grant 映射拒绝。
|
||||
- 未配置路径的方法调用拒绝。
|
||||
- Receipt 必须记录 `grant_id`、`writer_id` 和服务 Scope。
|
||||
|
||||
## 10. Dispatch Contract
|
||||
|
||||
### 10.1 DispatchRecord
|
||||
|
||||
```text
|
||||
dispatch_id
|
||||
tenant_id
|
||||
task_id
|
||||
agent_id
|
||||
principal_id
|
||||
runtime
|
||||
runtime_execution_id
|
||||
trace_id
|
||||
provenance_id
|
||||
run_id
|
||||
authorization_id
|
||||
state
|
||||
expected_worker_id
|
||||
result_digest
|
||||
created_at
|
||||
updated_at
|
||||
completed_at
|
||||
```
|
||||
|
||||
状态:
|
||||
|
||||
```text
|
||||
PREPARED
|
||||
RUNNING
|
||||
QUEUED
|
||||
COMPLETED
|
||||
FAILED
|
||||
CANCELLED
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- Dispatch 必须在 Runtime 副作用之前持久化。
|
||||
- 同一租户的 Task 和 Runtime Execution 各只能绑定一个 Dispatch。
|
||||
- 终态 Dispatch 不得跳转到不同终态。
|
||||
- 相同终态结果允许幂等读取,不同结果摘要拒绝。
|
||||
- SQLite Repository 必须支持按 Task 和 Runtime Execution 恢复。
|
||||
|
||||
实现:`active-runtime/app/aios_v2/dispatch_store.py`
|
||||
|
||||
## 11. OpenClaw Contract
|
||||
|
||||
### 11.1 OpenClawCommand v2
|
||||
|
||||
```text
|
||||
contract_version = aios.openclaw.command.v2
|
||||
signature_algorithm = Ed25519
|
||||
command_id
|
||||
tenant_id
|
||||
task_id
|
||||
trace_id
|
||||
action
|
||||
payload
|
||||
idempotency_key
|
||||
created_at
|
||||
expires_at
|
||||
key_id
|
||||
public_key_fingerprint
|
||||
signature
|
||||
```
|
||||
|
||||
签名覆盖全部未签名字段,包括算法、Key ID 和公钥 Fingerprint。
|
||||
|
||||
约束:
|
||||
|
||||
- 使用规范化 JSON 与 Ed25519。
|
||||
- HMAC-SHA256 不再是生产命令合同。
|
||||
- 只接受由已批准任务和已授权 Dispatch 生成的命令。
|
||||
- 过期、未来时间超差、签名错误、Key ID 或 Fingerprint 不匹配时拒绝。
|
||||
- Fingerprint 使用恒定时间比较。
|
||||
- `key_id` 只引用密钥,不包含密钥材料。
|
||||
- Candidate 组合层必须把 `AIOS_OPENCLAW_SIGNING_KEY_ID` 原样传入 Orchestrator,
|
||||
不得在已有批准 Key ID 时回落为默认值。
|
||||
|
||||
### 11.2 OpenClawResult
|
||||
|
||||
```text
|
||||
command_id
|
||||
tenant_id
|
||||
task_id
|
||||
trace_id
|
||||
state
|
||||
output
|
||||
error
|
||||
started_at
|
||||
finished_at
|
||||
runtime_id
|
||||
attempts
|
||||
```
|
||||
|
||||
终态:`COMPLETED`、`FAILED`、`CANCELLED`、`TIMED_OUT`、`REJECTED`。
|
||||
|
||||
约束:
|
||||
|
||||
- Result 必须匹配持久 Dispatch 的 command、tenant、task、trace、principal、provenance 和 run。
|
||||
- 只有 Orchestrator 可以更新 AIOS Task。
|
||||
- callback 审计不是权威 Reconcile。
|
||||
|
||||
实现:`active-runtime/app/aios_openclaw/`
|
||||
|
||||
## 12. Hermes Contract
|
||||
|
||||
### 12.0 内部生命周期入口
|
||||
|
||||
- 路径:`/api/v2/internal/runtime/hermes/lifecycle/{claim,start,heartbeat,complete,fail,cancel,status}`。
|
||||
- `AIOS_HERMES_LIFECYCLE_API_ENABLED` 默认关闭;关闭时按不存在的路由 fail closed。
|
||||
- 仅可信反向代理注入且具备 `runtime` 或 `platform_admin` 角色的身份可调用。
|
||||
- 所有写请求必须携带并严格匹配 tenant、task、trace、principal、provenance、run、
|
||||
dispatch、job、cell、profile;Claim 还必须指定精确 job,不能从分区中误领其他 Job。
|
||||
- Worker 不得直接修改 Task Store。Complete、Fail 和 Cancel 产生的 HermesResult
|
||||
必须经持久 Dispatch 校验并由 `ExecutionOrchestrator.reconcile_hermes` 终态化。
|
||||
- 每次成功生命周期写入同时落盘 Hermes 状态、Audit/Event 和 Execution Evidence。
|
||||
|
||||
### 12.1 HermesJob
|
||||
|
||||
```text
|
||||
job_id
|
||||
tenant_id
|
||||
cell_id
|
||||
profile_id
|
||||
task_id
|
||||
trace_id
|
||||
action
|
||||
payload
|
||||
idempotency_key
|
||||
priority
|
||||
state
|
||||
revision
|
||||
assigned_worker_id
|
||||
lease_expires_at
|
||||
created_at
|
||||
updated_at
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- `tenant_id + cell_id + profile_id` 形成执行分区。
|
||||
- claim 只能领取同分区 Job。
|
||||
- Lease 到期 Job 回到 QUEUED。
|
||||
- Hermes Store 使用 `AIOS_V2_STATE_DIR/hermes.sqlite3` 保存 Job、Result、Lease、
|
||||
Idempotency 和 Worker heartbeat;Adapter 仍是唯一 Queue/Lease 状态机。
|
||||
- Lease 到期重排必须清空 `assigned_worker_id`、清空 `lease_expires_at`、递增 revision
|
||||
并持久化。重启后由显式 lifecycle status/claim 或健康检查安全触发重排。
|
||||
- revision 冲突不得覆盖。
|
||||
|
||||
### 12.2 HermesResult
|
||||
|
||||
```text
|
||||
job_id
|
||||
tenant_id
|
||||
task_id
|
||||
trace_id
|
||||
state
|
||||
worker_id
|
||||
output
|
||||
error
|
||||
started_at
|
||||
finished_at
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- 终态 Result 必须携带 Worker ID。
|
||||
- Worker 必须持有 Job Lease。
|
||||
- Result 必须匹配 Dispatch、Principal、Parent Provenance 和 Run。
|
||||
- 相同 Worker、相同终态和相同 output/error 的重复提交返回原 Result;不同终态或
|
||||
不同结果内容返回 Conflict,不得覆盖已持久化终态。
|
||||
- 只允许内部入口 `POST /api/v2/internal/runtime/hermes/reconcile` 处理。
|
||||
- 旧入口 `POST /api/v2/hermes/results/reconcile` 返回 `410 Gone`。
|
||||
|
||||
实现:`active-runtime/app/aios_hermes/`
|
||||
|
||||
## 13. Execution Evidence Contract
|
||||
|
||||
### 13.1 ExecutionEvidence
|
||||
|
||||
```text
|
||||
execution_id
|
||||
tenant_id
|
||||
task_id
|
||||
agent_id
|
||||
executor
|
||||
branch
|
||||
status
|
||||
progress_completed
|
||||
progress_total
|
||||
current_step
|
||||
last_commit
|
||||
test_status
|
||||
test_summary
|
||||
result_summary
|
||||
claimed_at
|
||||
heartbeat_at
|
||||
completed_at
|
||||
provenance_id
|
||||
run_id
|
||||
last_authorization_id
|
||||
```
|
||||
|
||||
约束:
|
||||
|
||||
- 按租户存储和查询。
|
||||
- 生产 `claim/heartbeat/complete` 落盘前必须通过 Evidence Grant。
|
||||
- Evidence ID 不得被不同 Task、Agent 或 Provenance Context 复用。
|
||||
- 不得包含 Secret 或完整敏感 Payload。
|
||||
|
||||
实现:`active-runtime/app/aios_v2/execution_tracking.py`
|
||||
|
||||
## 14. Git Writer Contract
|
||||
|
||||
允许操作:`READ_REF`、`FETCH`、`CREATE_BRANCH`、`COMMIT`、`MERGE`、`PUSH`、`UPDATE_EVIDENCE`,具体能力由 Git Grant 限定。
|
||||
|
||||
约束:
|
||||
|
||||
- 禁止直接操作 `main` 或 `master`。
|
||||
- 所有命令使用参数数组,禁止 Shell 字符串拼接。
|
||||
- Commit 和 Evidence Commit 必须先计算文件内容摘要并完成 Grant 授权,再执行 `git add`。
|
||||
- `UPDATE_EVIDENCE` 只允许 `.agent/` 路径。
|
||||
- 输出必须脱敏并截断。
|
||||
|
||||
实现:`active-runtime/app/aios_v2/provenance_git.py`
|
||||
|
||||
## 15. Web/API Contract
|
||||
|
||||
### 15.1 可信身份头
|
||||
|
||||
```text
|
||||
X-AIOS-Authenticated
|
||||
X-AIOS-Tenant-ID
|
||||
X-AIOS-Principal-ID
|
||||
X-AIOS-Roles
|
||||
X-AIOS-Trace-ID
|
||||
X-AIOS-Session-ID
|
||||
X-AIOS-Policy-Version
|
||||
X-AIOS-Provenance-ID
|
||||
X-AIOS-Run-ID
|
||||
```
|
||||
|
||||
生产约束:
|
||||
|
||||
- 可信代理必须删除客户端同名头后重新注入。
|
||||
- 应用不得直接暴露公网端口。
|
||||
- Header 与 Body 中重复的 Provenance/Run 值必须一致。
|
||||
|
||||
### 15.2 核心 API
|
||||
|
||||
```text
|
||||
GET /api/v2/health
|
||||
POST /api/v2/tenants
|
||||
GET /api/v2/tenants/current
|
||||
POST /api/v2/agents
|
||||
GET /api/v2/agents
|
||||
POST /api/v2/tasks
|
||||
GET /api/v2/tasks
|
||||
GET /api/v2/tasks/{id}
|
||||
POST /api/v2/tasks/{id}/approve
|
||||
POST /api/v2/tasks/{id}/cancel
|
||||
POST /api/v2/tasks/{id}/dispatch
|
||||
GET /api/v2/audit
|
||||
GET /api/v2/runtime
|
||||
GET /api/v2/executions
|
||||
GET /api/v2/gitops
|
||||
POST /api/v2/internal/runtime/hermes/reconcile
|
||||
```
|
||||
|
||||
公共生命周期旁路:
|
||||
|
||||
```text
|
||||
POST /api/v2/tasks/{id}/start -> 403
|
||||
POST /api/v2/tasks/{id}/complete -> 403
|
||||
POST /api/v2/tasks/{id}/fail -> 403
|
||||
```
|
||||
|
||||
## 16. Persistence Contract
|
||||
|
||||
候选版:
|
||||
|
||||
- Control Plane:SQLite Snapshot。
|
||||
- Dispatch:独立 SQLite Repository。
|
||||
- Provenance/Grant/Usage/Event:SQLite WAL。
|
||||
- Evidence/Receipt:租户隔离原子文件写入。
|
||||
- 写事务使用原子替换或 `BEGIN IMMEDIATE`。
|
||||
|
||||
生产替换要求:
|
||||
|
||||
- 不改变 Domain/API Contract。
|
||||
- 提供 migration、backup、restore、HA、隔离和容量测试。
|
||||
- 恢复时保留已使用 Grant 与终态 Dispatch,禁止旧授权重放。
|
||||
|
||||
## 17. Deployment Contract
|
||||
|
||||
### systemd
|
||||
|
||||
- 非 root `aios` 用户。
|
||||
- 状态目录 `/var/lib/aios-v2`。
|
||||
- 私钥通过受保护 credential 注入,不写入 Git 或普通环境文件。
|
||||
- 私钥文件必须是 regular file、禁止 symlink、权限 `0600` 或更严格。
|
||||
|
||||
### Docker
|
||||
|
||||
- 非 root UID/GID。
|
||||
- read-only root filesystem。
|
||||
- drop all capabilities。
|
||||
- 独立状态 volume 和 Secret mount。
|
||||
|
||||
### Rollback
|
||||
|
||||
- 回滚前备份状态。
|
||||
- 默认只回滚代码。
|
||||
- 状态恢复需独立 Rollback Grant 和显式批准。
|
||||
- 回滚后必须执行 Healthcheck 与恢复验证。
|
||||
- Release Archive 必须保留 `rollback.sh` 与 `healthcheck/check.sh` 的 executable bit;
|
||||
验收测试必须阻止非执行模式进入候选包。
|
||||
- `systemctl start` 后的回滚健康检查必须执行有界 readiness 重试,默认最多 30 次、
|
||||
每次间隔 1 秒;不得因服务尚未监听的一次瞬时拒绝误判目标 Release 失败。
|
||||
|
||||
## 18. 契约变更规则
|
||||
|
||||
以下变化必须在同一分支更新本文档、追踪矩阵和相关 ADR:
|
||||
|
||||
- 字段、状态、Header、API、错误语义;
|
||||
- 租户、安全和 Provenance 约束;
|
||||
- OpenClaw/Hermes 边界;
|
||||
- Dispatch、Persistence、Deployment、Rollback Contract;
|
||||
- Evidence、Audit、Receipt 格式;
|
||||
- 服务 Scope 或 Grant 类型。
|
||||
|
||||
不兼容变化必须新增 ADR 和版本号,不得静默修改。正式 Gate A 结论必须基于实际执行 Acceptance 和保存的证据,不得仅凭测试文件存在宣布通过。
|
||||
@@ -0,0 +1,79 @@
|
||||
# AIOS V2 需求—架构—代码—测试—部署追踪矩阵
|
||||
|
||||
- 文档版本:`V2R1-hardening-candidate`
|
||||
- 状态:实现与测试代码已提交;测试执行和 Acceptance 证据待完成
|
||||
- 基线需求:`UR-001`~`UR-022`
|
||||
- 判定规则:测试文件存在不等于测试通过;只有实际执行并保存证据后,状态才能改为“已验证”
|
||||
|
||||
## 1. 状态定义
|
||||
|
||||
| 状态 | 含义 |
|
||||
|---|---|
|
||||
| 已实现 | 代码、配置或文档已经提交到当前加固分支 |
|
||||
| 测试已提交 | 自动测试代码已经提交,但本报告没有实际执行结果 |
|
||||
| 待验收 | 需要运行 `deploy/aios-v2/acceptance/run-all.sh` 或对应预发布检查并保存证据 |
|
||||
| 未批准 | 尚未获得 Owner 的 Merge、Tag 或生产部署批准 |
|
||||
|
||||
## 2. 用户需求追踪
|
||||
|
||||
| 需求 | 架构/决策 | 主要实现 | 测试代码 | 部署/验收入口 | 当前状态 |
|
||||
|---|---|---|---|---|---|
|
||||
| UR-001 唯一控制面 | ADR-001;模块契约第 2~6 节 | `active-runtime/app/aios_v2/control_plane.py`、`gateway.py`、`orchestrator.py` | `tests/aios_v2_candidate/test_candidate_flow.py` | `deploy/aios-v2/acceptance/run-all.sh`;公共生命周期旁路负向检查 | 已实现;测试已提交;待验收 |
|
||||
| UR-002 复用现有能力 | ADR-002 | `active-runtime/app/aios_openclaw/`、`active-runtime/app/aios_hermes/`、`active-runtime/app/aios_v2/orchestrator.py` | `test_candidate_flow.py` | OpenClaw/Hermes 联调 | 已实现;真实 Runtime 联调待验收 |
|
||||
| UR-003 OpenClaw/Hermes 解耦 | ADR-002、ADR-010;模块契约第 11、12 节 | OpenClaw Adapter、Hermes Adapter/Worker、内部 Lifecycle/Reconcile | `test_candidate_flow.py`、`test_hermes_live_lifecycle.py` | 默认关闭的内部 Runtime API;Runtime audit/evidence 检查 | 已实现;Hermes 专项 17/17 |
|
||||
| UR-004 全面 Web 化 | 目标架构;模块契约第 15 节 | `active-runtime/app/aios_v2/app.py`、`console.py`、`gateway.py` | `test_candidate_flow.py` | Web/API 冒烟、Healthcheck | 已实现;UI/浏览器验收待执行 |
|
||||
| UR-005 多租户隔离 | ADR-004 | `control_plane.py`、`persistence.py`、`execution_tracking.py`、`dispatch_store.py` | `test_candidate_flow.py::test_cross_tenant_task_read_is_denied` | 跨租户负向 Acceptance | 已实现;测试已提交;待验收 |
|
||||
| UR-006 权威任务生命周期 | ADR-001;模块契约第 4 节 | `control_plane.py`、`gateway.py`、`orchestrator.py` | `test_candidate_flow.py` | `/start`、`/complete`、`/fail` 应返回拒绝;Runtime 严格 Reconcile | 已实现;测试/接口验收待执行 |
|
||||
| UR-007 策略与审批 | ADR-001 | `control_plane.py`、`gateway.py` | `test_candidate_flow.py` | Approval、deny audit、policy version 检查 | 已实现;策略场景验收待执行 |
|
||||
| UR-008 幂等与并发安全 | 模块契约第 4、10、12 节 | Task idempotency/revision、Hermes lease/revision、Dispatch 唯一约束 | `test_candidate_flow.py`、`test_hermes_live_lifecycle.py` | Lease 到期重排、换主、相同终态幂等、不同终态冲突 | 已实现;专项测试通过 |
|
||||
| UR-009 可观测与执行证据 | 模块契约第 6、13 节 | `execution_tracking.py`、`gitops_status.py`、`console.py` | `test_candidate_flow.py::test_execution_tracking_persists_claim_heartbeat_and_result` | `/api/v2/executions`、Evidence Receipt 检查 | 已实现;测试已提交;待验收 |
|
||||
| UR-010 GitOps 唯一变更流程 | ADR-003 | `active-runtime/app/aios_v2/provenance_git.py`、GitOps 工具与任务资产 | `test_provenance.py`、Grant 隔离测试 | Branch/Commit/Push 门禁、Controller clean、OID 同步 | 已实现候选控制;环境 GitOps 验收待执行 |
|
||||
| UR-011 持久化与恢复 | ADR-006、ADR-010;模块契约第 10、12、16 节 | `persistence.py`、`dispatch_store.py`、`aios_hermes/adapter.py::SQLiteHermesStore`、Provenance/Grant Store | `test_candidate_flow.py`、`test_hermes_live_lifecycle.py` | 运行中 Job 重启恢复、重启后 Reconcile、SQLite quick_check | Hermes/Dispatch/Task 恢复测试通过;生产 HA/容量待验收 |
|
||||
| UR-012 审计与合规 | ADR-001、ADR-004、ADR-009 | `control_plane.py` AuditEvent、`app.py` callback audit、Provenance/Grant Event/Receipt | `test_candidate_flow.py`、`test_provenance.py`、`test_provenance_grant_isolation.py` | `/api/v2/audit`、Receipt/Event 完整性检查 | 已实现候选审计;不可变外部固化待预发布 |
|
||||
| UR-013 密钥安全 | ADR-009;模块契约第 6、11、17 节 | Ed25519 Signer/Verifier、protected file reader、SecretRef 配置 | `test_provenance.py`、`test_candidate_flow.py` | Secret scanner、权限检查、容器/systemd credential 检查 | 已实现;环境密钥注入验收待执行 |
|
||||
| UR-014 部署与回滚 | 迁移与交付文档;模块契约第 17 节 | `deploy/aios-v2/systemd/`、`docker/`、`healthcheck/`、`rollback/` | Acceptance 脚本与候选测试 | systemd/Docker 安装、Healthcheck、备份与回滚演练 | 资产已提交;实际部署/回滚未执行 |
|
||||
| UR-015 文档与代码同步 | ADR-005 | `tools/aios_v2_docs_code_check.py`、`docs/aios-v2/` | 文档门禁脚本 | Acceptance Runner 调用文档门禁 | 已实现;门禁尚未实际执行 |
|
||||
| UR-016 Workflow Run Provenance | ADR-009;模块契约第 7 节 | `active-runtime/app/aios_v2/provenance.py`、`provenance_grants.py::WorkflowProvenanceIssuer` | `test_provenance.py`、`test_provenance_grant_isolation.py::test_parent_workflow_has_no_operational_rights` | CLI `issue-workflow`、状态/撤销检查 | 已实现;测试已提交;待验收 |
|
||||
| UR-017 最小权限子 Grant | ADR-009;模块契约第 8 节 | `provenance_grants.py`、`provenance_scoped.py` | `test_provenance_grant_isolation.py` | `issue-grant`、Grant status/revoke、Receipt 检查 | 已实现;专项测试已提交;待验收 |
|
||||
| UR-018 Runtime Result 信任绑定 | ADR-009、ADR-010;模块契约第 10~12 节 | `orchestrator.py`、`dispatch_store.py`、内部 Hermes Lifecycle/Reconcile | `test_hermes_live_lifecycle.py` | tenant/task/trace/principal/provenance/run/dispatch/job/cell/profile/worker 负向矩阵 | 已实现;专项 17/17 |
|
||||
| UR-019 Dispatch 持久化与恢复 | ADR-009、ADR-010;模块契约第 10、12 节 | `dispatch_store.py`、`orchestrator.py`、`app.py`、`SQLiteHermesStore` | Dispatch recovery 与 Hermes restart-reconcile 测试 | 进程重启后读取 Dispatch/Job 并完成 Reconcile | 已实现;测试通过 |
|
||||
| UR-020 OpenClaw Ed25519 命令合同 | ADR-009;模块契约第 11 节 | `active-runtime/app/aios_openclaw/contract.py`、`adapter.py`、`app.py` | `test_candidate_flow.py`、`test_provenance.py` | 真实 OpenClaw v2 合同联调、Key rotation、clock skew/expiry 负向验收 | 已实现;测试代码已升级;真实联调待执行 |
|
||||
| UR-021 服务级权限隔离 | ADR-009;模块契约第 9 节 | `provenance_scoped.py`、`provenance_operations.py`、`app.py` | `test_provenance_grant_isolation.py` | Application 仅加载 Runtime/Evidence/Audit;Git/Deploy/Rollback 单独 Scope | 已实现;专项测试已提交;配置验收待执行 |
|
||||
| UR-022 CLI 单 Grant 授权 | ADR-009;模块契约第 9 节 | `provenance_cli.py` | `test_provenance_grant_isolation.py` 提供 Writer/Grant 基础验证;CLI 端到端待补执行证据 | `authorize --path ... --grant-id ...`;旧批量 Grant 参数应不存在 | 已实现;CLI 端到端验收待执行 |
|
||||
|
||||
## 3. P0 加固项追踪
|
||||
|
||||
| P0 | 风险 | 实现 | 测试/证据 | 状态 |
|
||||
|---|---|---|---|---|
|
||||
| P0-1 公共生命周期旁路 | 客户端直接推进 RUNNING/COMPLETED/FAILED | `gateway.py` 公共入口拒绝;`orchestrator.py` 权威推进 | API 负向 Acceptance | 代码完成;待执行 |
|
||||
| P0-2 Dispatch 持久化 | 重启丢失 Runtime 绑定 | `dispatch_store.py` SQLite Repository;`app.py` 接线 | Dispatch restart recovery 测试 | 代码/测试已提交;待执行 |
|
||||
| P0-3 Result 严格绑定 | 伪造或错配 Runtime Result 更新 Task | `orchestrator.py` 校验 Runtime Execution、Tenant、Task、Trace、Principal、Provenance、Run | Runtime 正向恢复测试;负向 Acceptance | 代码完成;完整验收待执行 |
|
||||
| P0-4 OpenClaw Ed25519 | HMAC 共享密钥和合同不一致 | `aios_openclaw/contract.py` v2 Ed25519;安全文件读取 | 候选 Flow 测试;真实 Runtime 联调 | 代码/测试已提交;联调待执行 |
|
||||
| P0-5 最小权限 Grant | 单凭证拥有全部生产路径 | Workflow + Child Grant + Scoped Writer + 单 Grant CLI | Grant isolation 专项测试 | 代码/测试已提交;待执行 |
|
||||
|
||||
## 4. Acceptance 证据要求
|
||||
|
||||
完整 Acceptance 至少应保存:
|
||||
|
||||
1. 测试命令、开始/结束时间、退出码和完整日志。
|
||||
2. `test_candidate_flow.py`、`test_provenance.py`、`test_provenance_grant_isolation.py` 的实际结果。
|
||||
3. 文档—代码同步门禁实际结果。
|
||||
4. Secret scanner、依赖和容器/systemd 安全检查结果。
|
||||
5. OpenClaw Ed25519 v2 真实联调结果。
|
||||
6. Hermes 内部 Reconcile 正向与伪造上下文负向结果。
|
||||
7. Control Plane、Dispatch、Provenance/Grant 的重启恢复结果。
|
||||
8. 部署、Healthcheck、备份和回滚演练结果。
|
||||
9. 分支、Commit、Controller clean、远端 OID 同步证据。
|
||||
10. Owner 对 Merge、Tag 和生产部署的独立批准。
|
||||
|
||||
## 5. 当前发布门禁
|
||||
|
||||
| Gate | 状态 | 说明 |
|
||||
|---|---|---|
|
||||
| 实现 | 完成 | 五项 P0 代码与配置已提交当前加固分支 |
|
||||
| 测试代码 | 完成 | 回归、Dispatch recovery、Grant isolation 测试已提交 |
|
||||
| 测试执行 | 未完成 | 当前没有可验证的实际运行日志和退出码 |
|
||||
| 文档同步 | 已提交 | 需求、契约、ADR、追踪矩阵已更新;门禁尚未执行 |
|
||||
| Acceptance | 未完成 | `run-all.sh` 尚无本轮实际执行证据 |
|
||||
| Gate A | 未批准 | 只能在 Acceptance 通过并完成独立审查后批准 |
|
||||
| Merge/Tag/生产部署 | 未批准 | 需要 AIOS Owner 明确批准 |
|
||||
@@ -0,0 +1,272 @@
|
||||
# AIOS V2 文档治理规范
|
||||
|
||||
- 文档版本:`V2R1C0-candidate`
|
||||
- 适用范围:`docs/aios-v2/`、架构决策记录、生产候选报告、在线任务合同、部署与验收说明
|
||||
- 状态:已采纳
|
||||
|
||||
## 1. 目的
|
||||
|
||||
本规范用于保证 AIOS V2 的需求、架构、代码、测试、部署和运行事实始终保持一致,避免出现以下问题:
|
||||
|
||||
- 代码已经变化,但架构文档仍描述旧边界;
|
||||
- API、字段或状态机变化后,测试与追踪矩阵未同步;
|
||||
- OpenClaw、Hermes 或 Agent Router 的控制职责发生漂移;
|
||||
- 候选分支存在实现,但版本无法解释为什么这样设计;
|
||||
- 部署、回滚或安全策略发生变化,却没有形成可审计文档;
|
||||
- 归档包只包含摘要或占位符,无法作为正式交付材料。
|
||||
|
||||
## 2. 文档语言要求
|
||||
|
||||
所有面向用户、产品、架构、运维、审计和发布的正式文档统一使用中文。
|
||||
|
||||
以下内容保留原始英文技术标识:
|
||||
|
||||
- 类名、函数名、字段名、环境变量;
|
||||
- API 路径、HTTP 方法和 Header;
|
||||
- Git 分支、Commit、Tag;
|
||||
- OpenClaw、Hermes、Agent Router、GitOps 等专有名称;
|
||||
- systemd、Docker、SQLite、HMAC、HTTP、JSON 等标准术语。
|
||||
|
||||
禁止在同一文档中无必要地切换中英文叙述。
|
||||
|
||||
## 3. 文档完整性要求
|
||||
|
||||
每份正式文档至少包含:
|
||||
|
||||
1. 文档目的;
|
||||
2. 适用范围;
|
||||
3. 当前版本和状态;
|
||||
4. 完整正文;
|
||||
5. 与代码、测试或部署的映射;
|
||||
6. 验收规则;
|
||||
7. 已知限制;
|
||||
8. 后续演进方向;
|
||||
9. 更新触发条件。
|
||||
|
||||
正式归档包禁止使用以下内容代替正文:
|
||||
|
||||
- “后续补充”;
|
||||
- “待完善”;
|
||||
- 只有标题没有说明;
|
||||
- 只包含目录摘要;
|
||||
- 与候选分支代码不一致的旧文档。
|
||||
|
||||
确实尚未验证的项目,应明确标记为“已实现但尚未验证”,并说明验证命令、责任方和进入下一状态的条件。
|
||||
|
||||
## 4. 文档分类与维护责任
|
||||
|
||||
| 文档 | 主要内容 | 触发更新的变化 |
|
||||
|---|---|---|
|
||||
| `README.md` | 文档索引、版本状态、实现地图 | 新增模块、目录、版本或交付物 |
|
||||
| `01-USER-REQUIREMENTS.md` | 用户目标、功能需求、非功能需求、验收场景 | 用户行为、产品范围、验收标准变化 |
|
||||
| `02-TARGET-ARCHITECTURE.md` | 分层、边界、数据流、安全、租户、部署架构 | 控制权、Runtime 边界、数据流或安全模型变化 |
|
||||
| `03-MIGRATION-AND-DELIVERY.md` | 迁移阶段、GitOps、发布门禁、回滚、Bug 修复 | 迁移路线、发布流程、门禁或回滚方式变化 |
|
||||
| `04-MODULE-CONTRACTS.md` | 数据模型、API、状态机、错误语义、Runtime Contract | 字段、接口、状态机、Header、错误行为变化 |
|
||||
| `05-TRACEABILITY-MATRIX.md` | 需求到代码、测试、部署、验收的映射 | 代码、测试、部署路径或状态变化 |
|
||||
| `adr/*` | 跨模块、长期或不可逆架构决策 | 关键决策新增、替换或废弃 |
|
||||
| `AIOS-V2R1-PRODUCTION-CANDIDATE.md` | 候选版本总览、测试、部署、风险和发布结论 | Candidate SHA、测试证据、部署或风险变化 |
|
||||
| `tasks/*` | OpenClaw、Codex 等在线执行任务 | 职责、边界、阻塞、验收或执行流程变化 |
|
||||
|
||||
## 5. 代码变化与文档同步规则
|
||||
|
||||
以下代码或配置路径发生变化时,必须同步更新 `docs/aios-v2/`:
|
||||
|
||||
### 5.1 Control Plane
|
||||
|
||||
触发路径:
|
||||
|
||||
```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
|
||||
```
|
||||
|
||||
至少检查:
|
||||
|
||||
- 用户需求;
|
||||
- 目标架构;
|
||||
- 模块契约;
|
||||
- 追踪矩阵;
|
||||
- 必要时新增或更新 ADR。
|
||||
|
||||
### 5.2 OpenClaw
|
||||
|
||||
触发路径:
|
||||
|
||||
```text
|
||||
active-runtime/app/aios_openclaw/
|
||||
```
|
||||
|
||||
至少检查:
|
||||
|
||||
- OpenClawCommand、OpenClawResult、RuntimeHealth;
|
||||
- 签名、幂等、取消、超时和审计边界;
|
||||
- ADR-002;
|
||||
- 真实 Runtime 联调要求。
|
||||
|
||||
### 5.3 Hermes
|
||||
|
||||
触发路径:
|
||||
|
||||
```text
|
||||
active-runtime/app/aios_hermes/
|
||||
```
|
||||
|
||||
至少检查:
|
||||
|
||||
- HermesJob、HermesResult、HermesHealth;
|
||||
- tenant/cell/profile 分区;
|
||||
- Worker Lease、Heartbeat、Recovery;
|
||||
- ADR-002、ADR-004。
|
||||
|
||||
### 5.4 部署与运维
|
||||
|
||||
触发路径:
|
||||
|
||||
```text
|
||||
deploy/aios-v2/
|
||||
```
|
||||
|
||||
至少检查:
|
||||
|
||||
- 迁移与交付策略;
|
||||
- 部署契约;
|
||||
- 健康检查;
|
||||
- 回滚;
|
||||
- 候选报告。
|
||||
|
||||
### 5.5 API、Web 与用户行为
|
||||
|
||||
任何 API 路径、Header、请求/响应、页面或用户操作变化,必须同步:
|
||||
|
||||
- `01-USER-REQUIREMENTS.md`;
|
||||
- `02-TARGET-ARCHITECTURE.md`;
|
||||
- `04-MODULE-CONTRACTS.md`;
|
||||
- `05-TRACEABILITY-MATRIX.md`。
|
||||
|
||||
## 6. ADR 治理
|
||||
|
||||
必须新增或更新 ADR 的场景:
|
||||
|
||||
- AIOS、OpenClaw、Hermes、Agent Router 的控制边界变化;
|
||||
- 多租户隔离模型变化;
|
||||
- 持久化、消息、审计、密钥或部署出现跨模块变化;
|
||||
- 不兼容 API、字段或状态机变化;
|
||||
- GitOps、文档门禁或发布策略变化;
|
||||
- 替换核心基础设施或引入新的权威事实源。
|
||||
|
||||
ADR 状态:
|
||||
|
||||
- `已提出`:尚未正式采纳;
|
||||
- `已采纳`:当前有效;
|
||||
- `已替代`:被新 ADR 替代;
|
||||
- `已废弃`:保留历史但禁止新实现采用。
|
||||
|
||||
任何 ADR 替代必须说明:
|
||||
|
||||
- 被替代的 ADR;
|
||||
- 迁移影响;
|
||||
- 兼容性和回滚方案;
|
||||
- 受影响代码、测试和文档。
|
||||
|
||||
## 7. 文档—代码匹配门禁
|
||||
|
||||
验收必须执行:
|
||||
|
||||
```text
|
||||
python3 tools/aios_v2_docs_code_check.py
|
||||
```
|
||||
|
||||
门禁至少检查:
|
||||
|
||||
1. 必需文档存在且非空;
|
||||
2. 文档语言以中文为主;
|
||||
3. 文档引用的关键代码、测试和部署路径存在;
|
||||
4. 文档列出的核心 API 能在代码中找到;
|
||||
5. 文档列出的核心模型和字段能在代码中找到;
|
||||
6. Traceability Matrix 覆盖所有 `UR-*` 需求;
|
||||
7. ADR 索引引用的文件存在;
|
||||
8. 架构或功能代码变化时,当前交付范围包含 `docs/aios-v2/` 变化;
|
||||
9. 文档中不存在未解决 Git 冲突标记;
|
||||
10. 正式文档中不存在摘要占位符或空章节。
|
||||
|
||||
门禁失败时:
|
||||
|
||||
- Candidate 不得标记为 `Test-verified`;
|
||||
- OpenClaw 不得继续生产部署;
|
||||
- Codex 必须登记 blocker 并给出修复建议;
|
||||
- 修复必须进入 Git 分支并统一审视。
|
||||
|
||||
## 8. 在线任务文档要求
|
||||
|
||||
OpenClaw 和 Codex 任务必须使用中文说明,并保留可执行字段名。
|
||||
|
||||
每个任务至少包含:
|
||||
|
||||
- 任务目标;
|
||||
- 责任范围;
|
||||
- 禁止事项;
|
||||
- 输入和输出;
|
||||
- 分支;
|
||||
- 执行状态;
|
||||
- 验收命令;
|
||||
- claim、heartbeat、progress、blocker、commit、test_status、result 证据要求;
|
||||
- 阻塞升级路径。
|
||||
|
||||
## 9. 归档包要求
|
||||
|
||||
正式归档包必须包含完整正文:
|
||||
|
||||
```text
|
||||
docs/aios-v2/
|
||||
tasks/openclaw-production-deploy-task.yaml
|
||||
tasks/codex-production-supervisor-task.yaml
|
||||
deploy/aios-v2/
|
||||
AIOS-V2R1-PRODUCTION-CANDIDATE.md
|
||||
```
|
||||
|
||||
归档包必须同时生成清单:
|
||||
|
||||
- 文件路径;
|
||||
- 文件大小;
|
||||
- SHA-256;
|
||||
- Candidate branch;
|
||||
- Candidate commit;
|
||||
- 生成时间。
|
||||
|
||||
禁止只打包摘要副本。
|
||||
|
||||
## 10. 审查职责
|
||||
|
||||
### OpenClaw
|
||||
|
||||
- 部署和运行修复时同步相关部署、运维和已知问题文档;
|
||||
- 不得修改架构边界;
|
||||
- 发现架构影响时升级给 Codex。
|
||||
|
||||
### Codex
|
||||
|
||||
- 监督需求、架构、契约、追踪和 ADR 一致性;
|
||||
- 解决阻塞;
|
||||
- 拒绝缺少文档或证据的补丁;
|
||||
- 输出统一发布建议。
|
||||
|
||||
### AIOS Owner
|
||||
|
||||
- 审批合并、Tag 和生产部署;
|
||||
- 对重大架构决策和风险接受做最终确认。
|
||||
|
||||
## 11. 验收状态
|
||||
|
||||
文档完成状态只有在以下条件全部满足时才标记为“完整”:
|
||||
|
||||
- 所有必需文档和 ADR 已提交;
|
||||
- 文档—代码匹配检查通过;
|
||||
- 归档包包含仓库完整正文;
|
||||
- 任务合同为中文完整版本;
|
||||
- Candidate commit、清单和 SHA-256 已记录;
|
||||
- Codex 监督结论不存在未解决阻塞。
|
||||
@@ -0,0 +1,224 @@
|
||||
# AIOS V2R1 监督状态与阻塞处置清单
|
||||
|
||||
- 文档版本:`V2R1C0-candidate`
|
||||
- 快照时间:`2026-07-20 17:03:53 CST`
|
||||
- 候选分支:`integration/aios-v2r1-cto-production-candidate-20260720`
|
||||
- 候选 OID:`634f6b164f5b20372ab9ec8144bbf76df97de335`
|
||||
- 当前决策:`STOP_PREPRODUCTION`
|
||||
- 当前状态:`BLOCKED`
|
||||
|
||||
## 1. 执行摘要
|
||||
|
||||
AIOS V2R1 的核心代码、完整中文文档、任务合同、部署资产和 GitOps 证据机制已经形成。OpenClaw 与 Codex 已经领取任务并向 Gitea 提交监督证据,三个关键分支的本地 OID 与 Gitea OID 已一致。
|
||||
|
||||
当前仍不允许进入预发布,原因不是主体功能缺失,而是安全、签名材料、Candidate 合并、执行来源证明和 Controller 健康检查五项高风险门禁未通过。
|
||||
|
||||
当前禁止:
|
||||
|
||||
- 进入 Gate A–D;
|
||||
- 执行在线 Runtime 联调;
|
||||
- 执行重启恢复和回滚演练;
|
||||
- 合并 `main`;
|
||||
- 创建 Tag;
|
||||
- 正式部署或切换流量。
|
||||
|
||||
## 2. 权威仓库与执行状态
|
||||
|
||||
| 项目 | 当前值 |
|
||||
|---|---|
|
||||
| 权威 Bare Repo | `/data/aios-gitops/repo.git` |
|
||||
| OpenClaw Worktree | 独立且 clean |
|
||||
| Codex Worktree | 独立且 clean |
|
||||
| Gitea Remote | `https://g.cnnetmkt.top/git/aios/aios.git` |
|
||||
| Candidate OID | `634f6b164f5b20372ab9ec8144bbf76df97de335` |
|
||||
| OpenClaw Task OID | `bd2784015d40c328d158cd52ebd8683b6e56b3ad` |
|
||||
| Codex Task OID | `e28245f411dd85ff9384ed595dacc53aab8a91ba` |
|
||||
| 三分支 Gitea 同步 | `local_oid == gitea_oid` |
|
||||
| OpenClaw 状态 | `blocked` |
|
||||
| OpenClaw Heartbeat | 有记录,但 `valid_for_running=false` |
|
||||
| Codex 状态 | `blocked` |
|
||||
| Codex Heartbeat | 新鲜 |
|
||||
| Codex 发布建议 | `STOP_PREPRODUCTION` |
|
||||
|
||||
## 3. 已完成的安全与运行修复
|
||||
|
||||
### 3.1 Gitea 凭据轮换
|
||||
|
||||
已完成:
|
||||
|
||||
- 旧 `owner/openclaw-deploy-cli`、`scope=all` 凭据 live count 为 `0`;
|
||||
- 新凭据:`gitops-bot/openclaw-deploy-cli-v2-20260720`;
|
||||
- 新凭据作用域:`write:repository`;
|
||||
- 凭据文件权限:`root:gitops 0640`;
|
||||
- 令牌值未进入 Git、日志、Evidence 或报告。
|
||||
|
||||
### 3.2 Gitea 与执行服务
|
||||
|
||||
已完成:
|
||||
|
||||
- 验证 Gitea SSH 指纹;
|
||||
- 备份并修复 `known_hosts`;
|
||||
- 恢复 `aios-agent-command-watcher`;
|
||||
- 恢复 `aios-autonomous-controller`;
|
||||
- 两项服务均为 `active`;
|
||||
- OpenClaw/One API 真实模型调用返回 HTTP 200;
|
||||
- OpenClaw/Codex claim、heartbeat、progress、blockers、result、status 已提交并同步 Gitea。
|
||||
|
||||
## 4. 当前开放阻塞
|
||||
|
||||
### 4.1 BLK-OPENCLAW-PLAINTEXT-SECRETS
|
||||
|
||||
- 严重级别:高
|
||||
- 状态:开放
|
||||
- 现象:OpenClaw 受管配置仍发现 3 处 `PLAINTEXT_FOUND`。
|
||||
- 风险:明文 Secret 可能进入配置、日志、命令参数或执行证据。
|
||||
- 解除条件:
|
||||
1. 三处明文内容全部迁移为 SecretRef、systemd Credential、只读 Secret Volume 或仓库外受保护文件;
|
||||
2. 旧值完成撤销和轮换;
|
||||
3. Secret Scanner 复验通过;
|
||||
4. Git 历史、日志和 Evidence 不包含明文。
|
||||
|
||||
### 4.2 BLK-AIOS-V2-SIGNING-MATERIAL-MISSING
|
||||
|
||||
- 严重级别:高
|
||||
- 状态:开放
|
||||
- 现象:`/etc/aios-v2/aios-v2.env` 已存在且权限合规,但 `/etc/aios-v2/openclaw-signing-material.bin` 不存在。
|
||||
- 风险:无法验证 OpenClaw 签名命令、Key ID 与真实 Runtime 身份链。
|
||||
- 外部受信输入:批准的签名材料。
|
||||
- 解除条件:
|
||||
1. 签名材料由批准的 Secret/Key 交付链安装到仓库外;
|
||||
2. 权限为 `0600` 或更严格;
|
||||
3. 运行用户可读;
|
||||
4. Key ID 与材料匹配;
|
||||
5. execute/status 路径完成真实签名验证;
|
||||
6. 不输出材料内容、Hash 或长度特征。
|
||||
|
||||
### 4.3 BLK-CANDIDATE-NOT-MERGED
|
||||
|
||||
- 严重级别:高
|
||||
- 状态:开放
|
||||
- 现象:OpenClaw Task 尚未包含当前 Candidate,`merge-base --is-ancestor` 未通过。
|
||||
- 风险:后续测试和部署不能证明当前 Candidate 可用。
|
||||
- 解除条件:
|
||||
1. 保护已有 `.agent/` Evidence;
|
||||
2. 普通 Merge 当前 Candidate 到 OpenClaw Task;
|
||||
3. 解决冲突并由 Codex 审查;
|
||||
4. 更新所有 Evidence 中的 `candidate_commit`;
|
||||
5. 本地与 Gitea OID 再次一致。
|
||||
|
||||
### 4.4 BLK-OPENCLAW-RUN-PROVENANCE-MISSING
|
||||
|
||||
- 严重级别:高
|
||||
- 状态:开放
|
||||
- 现象:OpenClaw 写工具被 `run_provenance_missing` 策略拒绝。
|
||||
- 风险:无法证明写操作来自已领取、已授权、可审计的执行会话。
|
||||
- 外部受信输入:允许七个 `.agent` JSON 写入的 OpenClaw Provenance 授权。
|
||||
- 解除条件:
|
||||
1. 创建带任务 ID、执行器实例、Claim OID、Candidate OID 和授权主体的 Run Provenance;
|
||||
2. Provenance 与七个 `.agent` JSON 写入范围绑定;
|
||||
3. 权限仅覆盖当前任务分支和 Evidence 路径;
|
||||
4. 由 Owner 或批准策略签发;
|
||||
5. 写入、Commit、Push 和审计链验证通过。
|
||||
|
||||
### 4.5 BLK-CONTROLLER-LEGACY-GITEA-CHECK
|
||||
|
||||
- 严重级别:高
|
||||
- 状态:开放
|
||||
- 现象:Controller 健康检查仍硬编码旧 `aios-v23`,并返回 `gitea=false`、`branch_sync=false`。
|
||||
- 风险:健康状态与当前 AIOS V2R1 仓库不一致,可能错误阻止或错误放行发布。
|
||||
- 解除条件:
|
||||
1. 移除旧仓库硬编码;
|
||||
2. 从配置读取权威仓库、Remote 和目标分支;
|
||||
3. 健康检查分别报告 `local_sync`、`gitea_sync` 和 `oid_match`;
|
||||
4. 不再把本地 Bare Repo 更新当作完全同步;
|
||||
5. 增加回归测试;
|
||||
6. 更新中文文档和追踪矩阵。
|
||||
|
||||
## 5. 模型审查策略修正
|
||||
|
||||
`gpt-5.3-codex-spark` 是子 Agent 审查的优先推荐模型,不是强制依赖。
|
||||
|
||||
执行规则:
|
||||
|
||||
1. Spark 可用时优先使用;
|
||||
2. Spark 不可用时,使用模型注册表中已批准、已启用且优先级最高的合适模型;
|
||||
3. 必须记录实际 `model_id`、模型名称和审查结果;
|
||||
4. 禁止冒充使用不存在的模型;
|
||||
5. 只有完全没有可用审查模型时,模型能力才构成阻塞。
|
||||
|
||||
当前五个 Spark 角色的独立结论一致为“禁止生产放行”,该结论作为已有审查证据保留;后续复验可使用任何满足上述规则的批准模型。
|
||||
|
||||
## 6. Gate 状态
|
||||
|
||||
| Gate | 当前状态 | 说明 |
|
||||
|---|---|---|
|
||||
| Gate A:文档与设计 | 未运行 | Candidate 未合并到任务,阻塞未解除 |
|
||||
| Gate B:代码与测试 | 未运行 | 不能基于不完整任务分支测试 |
|
||||
| Gate C:预发布 | 禁止 | Secret、签名、Provenance、Controller Health 未通过 |
|
||||
| Gate D:发布审查 | `STOP_PREPRODUCTION` | Codex 明确停止预发布 |
|
||||
| Gate E:生产发布 | 禁止 | 未满足任何生产 Gate |
|
||||
|
||||
## 7. 阻塞解除顺序
|
||||
|
||||
必须按以下顺序处理,避免重复测试和错误放行:
|
||||
|
||||
```text
|
||||
1. 清除 3 处明文 Secret
|
||||
↓
|
||||
2. 安装批准的签名材料
|
||||
↓
|
||||
3. 签发最小范围 Run Provenance
|
||||
↓
|
||||
4. 修复 Controller 旧仓库健康检查
|
||||
↓
|
||||
5. Merge 当前 Candidate 到 OpenClaw Task
|
||||
↓
|
||||
6. 校验 local_oid == gitea_oid
|
||||
↓
|
||||
7. 执行 Gate A:文档—代码检查
|
||||
↓
|
||||
8. 执行 Gate B:单元与集成测试
|
||||
↓
|
||||
9. 执行离线全量验收
|
||||
↓
|
||||
10. 执行在线 Runtime 联调
|
||||
↓
|
||||
11. 执行重启恢复与回滚
|
||||
↓
|
||||
12. Codex 重新审查并给出发布建议
|
||||
```
|
||||
|
||||
## 8. 外部受信输入
|
||||
|
||||
目前仅有两项确实需要外部受信输入:
|
||||
|
||||
1. **批准的签名材料**
|
||||
- 不得通过聊天、Git 或普通日志传递;
|
||||
- 必须通过批准的 Secret/Key 交付链安装。
|
||||
|
||||
2. **OpenClaw Run Provenance 授权**
|
||||
- 仅允许当前任务所需的七个 `.agent` JSON 写入;
|
||||
- 必须绑定任务、执行器实例、Claim、Candidate 和分支;
|
||||
- 不得授予通用生产写权限。
|
||||
|
||||
其余阻塞均可由 OpenClaw、Codex、Windows ChatGPT Owner 和 GitOps 运维流程处理。
|
||||
|
||||
## 9. 监督结论
|
||||
|
||||
当前状态保持:
|
||||
|
||||
```text
|
||||
BLOCKED
|
||||
STOP_PREPRODUCTION
|
||||
```
|
||||
|
||||
虽然三分支已经同步 Gitea、凭据已经最小权限轮换、执行服务已经恢复,但当前尚无足够证据允许执行 Gate A–D 或进入预发布。
|
||||
|
||||
任何后续状态更新必须同步:
|
||||
|
||||
- OpenClaw `.agent/status.json`、`blockers.json`、`progress.json`、`result.json`;
|
||||
- Codex 对应监督 Evidence;
|
||||
- 本文档;
|
||||
- `05-TRACEABILITY-MATRIX.md`;
|
||||
- `AIOS-V2R1-PRODUCTION-CANDIDATE.md`;
|
||||
- 如涉及架构或发布语义,更新 ADR。
|
||||
@@ -0,0 +1,104 @@
|
||||
# AIOS V2R1 Hermes 生命周期最终验证报告
|
||||
|
||||
- 报告版本:`V2R1-hermes-lifecycle-20260721.3`
|
||||
- 日期:`2026-07-21`
|
||||
- 分支:`patch/chatgpt/AIOS-V2R1-HERMES-LIFECYCLE-20260721`
|
||||
- 固定验证 OID:`95d2e52cb55c7b913e89bc6bed2bcdacf67512d4`
|
||||
- 总体状态:`PARTIAL / BLOCKED_GLOBAL_WORKTREE_CLEANLINESS`
|
||||
- 发布决策:`STOP_PREPRODUCTION`
|
||||
- 生产发布:`NOT_APPROVED`
|
||||
|
||||
## 1. 执行结论
|
||||
|
||||
`BLK-LIVE-HERMES-FULL-LIFECYCLE-EVIDENCE-MISSING` 的 Hermes 功能与证据子条件已在固定 OID 上全部通过。候选实现复用现有 Hermes Adapter、Queue、Lease、Task 与 Orchestrator 状态机,新增持久 SQLite Store 和默认关闭的受保护内部生命周期接口。Hermes 完整生命周期 `17/17`、候选测试 `49/49`、Gate A、Gate B `10/10`、离线 Acceptance `8/0/1`、真实 OpenClaw HTTP、重启恢复、双向回滚和最终健康检查均通过。
|
||||
|
||||
但 Owner 指令规定只有全部 Acceptance 条件同时满足时才允许正式解除该 Blocker。由于“所有 Worktree clean”失败,本报告不得把它标记为正式 `RESOLVED`;准确状态是 `EVIDENCE_COMPLETE / FORMAL_CLOSURE_BLOCKED`。
|
||||
|
||||
最终发布门禁仍失败:权威 Bare Repo 登记的 88 个 worktree 中有 10 个脏 worktree。候选 worktree 和活动 Controller worktree 均 clean,且无 locked/prunable;但 Owner 的验收条件要求所有 worktree clean,因此不得准备 RC、不得发起 Tag Approval Request、不得进入预生产评审。
|
||||
|
||||
## 2. 关键实现
|
||||
|
||||
- `SQLiteHermesStore` 持久保存 Job、Result、Idempotency 与 Worker Heartbeat。
|
||||
- 现有 `HermesAdapter` 保持唯一 Queue/Lease 状态机,支持指定 Job claim、租约到期 requeue、重启恢复与严格终态冲突。
|
||||
- 生命周期身份绑定覆盖 tenant、task、trace、principal、provenance、run、dispatch、job、cell、profile。
|
||||
- start/heartbeat/complete/fail 强制 Lease Owner;complete/fail/cancel 通过 `ExecutionOrchestrator.reconcile_hermes` 更新 Task 与 Dispatch。
|
||||
- cancel 仅允许同时具备 `runtime` 与 `platform_admin` 的 AIOS Control Plane,要求 `cancellation_source=aios-control-plane`,并拒绝携带 `worker_id`,Worker 只能观察取消。
|
||||
- 所有成功生命周期操作写入 Audit/Event/Execution Evidence;接口由 `AIOS_HERMES_LIFECYCLE_API_ENABLED` 控制,默认关闭。
|
||||
|
||||
## 3. 固定 OID 验证
|
||||
|
||||
| 项目 | 结果 |
|
||||
|---|---|
|
||||
| Python syntax/import | PASS |
|
||||
| 全部 candidate tests | `49/49` |
|
||||
| Grant isolation | `11/11` |
|
||||
| Dispatch recovery | `1/1` |
|
||||
| Hermes lifecycle | `17/17` |
|
||||
| Docs code gate / Gate A | `0 errors / 0 warnings` |
|
||||
| Secret scan | `547 tracked files / 0 violations` |
|
||||
| SQLite quick_check | `2/2 ok` |
|
||||
| Gate B | `10/10` |
|
||||
| Offline Acceptance | `8 passed / 0 failed / 1 expected warning` |
|
||||
| OpenClaw real HTTP | `COMPLETED` |
|
||||
| Hermes full live rerun | `17/17` |
|
||||
| Restart recovery | `2/2` |
|
||||
| Previous → Current rollback/forward | PASS |
|
||||
| State preservation | `STATE_PRESERVED_EXACTLY=PASS` |
|
||||
| Corrected final health (`16R`) | PASS,三服务 active |
|
||||
|
||||
原 `16.log` 由非服务用户执行健康脚本,打印 state-dir 权限失败后被外层脚本错误覆盖为退出码 0,因此不作为通过证据。纠错后的 `16R.log` 使用受控 `sudo env`,子 shell 保留失败码,所有健康项实际 PASS 且 `EXIT_CODE=0`。原文件保留用于审计。
|
||||
|
||||
回滚日志中的短暂 connection-refused 发生于 systemd 重启窗口内,受 `AIOS_V2_ROLLBACK_HEALTH_RETRIES=30` 与 1 秒间隔限制;前后两次均在界限内达到健康、输出 `ROLLBACK_COMPLETE`,并完成状态文件精确哈希对账。
|
||||
|
||||
## 4. Evidence
|
||||
|
||||
- 根目录:`/var/lib/aios-gitops/acceptance/aios-v2r1-hermes-lifecycle-20260721T054205Z`
|
||||
- `steps.tsv` SHA256:`b2ad20585ba7f576e85657827a0b1db6f252887bbd73bcd718df38623e9d95cf`
|
||||
- `final-live-gate.log` SHA256:`82040c674759dacf587658c5e936c313a1f50e8e2425be48ad891927befdf4fa`
|
||||
- `16R.log` SHA256:`641246927a372ebaa9e6dde8b018b88275b2ba15a442473759b23fb1f215d9cf`
|
||||
- `15.log` SHA256:`b0a474e2a74164f560c4f7572091911f32011c75faccd37a3c7315046275011e`
|
||||
- `13.log` SHA256:`b9f637cca6e97ed893bf38530e05cd33b78e324c5e8865d4c602dfeac22a7710`
|
||||
- `12R2.log` SHA256:`0c431f5f5f1c1b17acda160c917b08c7f4036485016c23e1236b9b6f4a78de67`
|
||||
|
||||
证据只记录身份、状态、命令、时间、退出码与 Hash,不记录 Secret 值。
|
||||
|
||||
## 5. Git 与运行态门禁
|
||||
|
||||
| 门禁 | 当前值 | 结果 |
|
||||
|---|---|---|
|
||||
| Bare/Gitea/Candidate OID | 全部 `95d2e52cb55c7b913e89bc6bed2bcdacf67512d4` | PASS |
|
||||
| Candidate worktree | clean | PASS |
|
||||
| Active Controller | `6188da26453505dacde9d6d298191437164c8d27`,detached、clean | PASS |
|
||||
| Locked worktree | `0` | PASS |
|
||||
| Prunable worktree | `0` | PASS |
|
||||
| 全局 worktree clean | `10 dirty / 88 total` | FAIL |
|
||||
| 当前隔离 Release | `b158041b8633e658c34ce182f3c8aa97b4bf5f9a` | 已恢复 |
|
||||
| AIOS/OpenClaw/Controller services | active | PASS |
|
||||
|
||||
10 个脏 worktree 均不属于本任务允许清理的范围:
|
||||
|
||||
1. `chatgpt/TASK-V2R1-PERSONAL-WEIXIN-GOLDEN-CONTRACT-R2-20260715`(36)
|
||||
2. `chatgpt/TASK-V2R1-PERSONAL-WEIXIN-PORTAL-ADAPTER-20260715`(2)
|
||||
3. `chatgpt/TASK-WORKTREE-CONCURRENCY-CHATGPT-20260715T055106UTC8`(2)
|
||||
4. `codex`(56)
|
||||
5. `codex/TASK-CODEX-AIOS-SPARK-RUNNER-PROVISIONING-20260717T103500UTC8`(6)
|
||||
6. `controller`(11)
|
||||
7. `openclaw`(5)
|
||||
8. `openclaw/TASK-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8`(3)
|
||||
9. `openclaw/TASK-V2R1-OPENCLAW-WEIXIN-WEB-LOGIN-CONTRACT-20260715`(20)
|
||||
10. `openclaw/TASK-WORKTREE-CONCURRENCY-OPENCLAW-20260715T055106UTC8`(3)
|
||||
|
||||
## 6. Reviewer
|
||||
|
||||
独立 Spark Reviewer 首先发现 cancel 权限边界不够明确;该问题已在 `95d2e52` 修复并新增三条 HTTP 断言。纠错后 Reviewer 确认代码安全边界、16 步证据与有界回滚均 PASS。对发布门禁的最终布尔复核为:`DIRTY_WORKTREE_COUNT=10` 且 `GLOBAL_WORKTREE_CLEAN=false`,所以全局门禁 FAIL,不能进入预生产评审。
|
||||
|
||||
## 7. Blocker 与发布决策
|
||||
|
||||
- 功能与证据子条件通过、正式关闭受阻:`BLK-LIVE-HERMES-FULL-LIFECYCLE-EVIDENCE-MISSING`
|
||||
- 直接阻断条件:`BLK-GLOBAL-WORKTREE-CLEANLINESS`
|
||||
- 状态:`BLOCKED_EVIDENCE_REQUIRED`
|
||||
- 决策:`STOP_PREPRODUCTION`
|
||||
|
||||
本轮未修改 `main`、未创建 Tag、未 Force Push、未切换生产流量、未部署新 RC、未输出 Secret。
|
||||
|
||||
下一步唯一允许动作:由各 worktree Owner 审查并提交、归档或可信清理上述 10 个脏 worktree,然后重新执行全局 Git 门禁。只有全局 dirty 数量降为 0 后,才允许准备 RC 与 Tag Approval Request。
|
||||
@@ -0,0 +1,129 @@
|
||||
# AIOS V2 架构与交付文档索引
|
||||
|
||||
- 版本线:`V2R1C0-candidate`
|
||||
- 候选分支:`integration/aios-v2r1-cto-production-candidate-20260720`
|
||||
- 架构负责人:AIOS V2 CTO
|
||||
- 当前状态:候选代码闭环已完成,运行时、预发布和生产验证尚待执行
|
||||
|
||||
## 1. 文档目的
|
||||
|
||||
本目录是 AIOS V2 用户需求、目标架构、模块边界、迁移策略、发布门禁和架构决策的唯一事实源。
|
||||
|
||||
所有后续架构、功能、接口、数据模型、安全策略、部署方式和验收流程变化,都必须在同一交付流程中同步更新本目录。
|
||||
|
||||
AIOS V2 遵循以下不可协商原则:
|
||||
|
||||
1. 不推倒重写现有平台。
|
||||
2. 优先复用 OpenClaw、Hermes 和 Agent Router 能力。
|
||||
3. OpenClaw 与 Hermes 从控制面职责中逐步解耦。
|
||||
4. AIOS 是唯一控制面。
|
||||
5. 所有面向用户和运维的能力必须通过 Web 或 API 访问。
|
||||
6. 所有模块必须强制多租户隔离。
|
||||
7. 所有修改必须通过 Git 分支、提交、测试、审查和受控提升完成。
|
||||
8. 代码变化必须同步更新需求、架构、契约、追踪矩阵或 ADR。
|
||||
|
||||
## 2. 文档地图
|
||||
|
||||
| 文档 | 用途 |
|
||||
|---|---|
|
||||
| [01-USER-REQUIREMENTS.md](01-USER-REQUIREMENTS.md) | 产品目标、用户角色、功能需求、非功能需求和验收标准 |
|
||||
| [02-TARGET-ARCHITECTURE.md](02-TARGET-ARCHITECTURE.md) | 目标逻辑架构、控制边界、数据流、安全模型和多租户模型 |
|
||||
| [03-MIGRATION-AND-DELIVERY.md](03-MIGRATION-AND-DELIVERY.md) | 增量迁移、能力复用、GitOps 流程、发布门禁和回滚策略 |
|
||||
| [04-MODULE-CONTRACTS.md](04-MODULE-CONTRACTS.md) | 租户上下文、任务生命周期、OpenClaw、Hermes、审计和执行证据契约 |
|
||||
| [05-TRACEABILITY-MATRIX.md](05-TRACEABILITY-MATRIX.md) | 需求、设计、代码、测试、部署和验收之间的追踪关系 |
|
||||
| [06-DOCUMENT-GOVERNANCE.md](06-DOCUMENT-GOVERNANCE.md) | 文档语言、完整性、同步门禁、版本与审查要求 |
|
||||
| [adr/README.md](adr/README.md) | 架构决策记录索引与治理规则 |
|
||||
|
||||
## 3. 当前实现映射
|
||||
|
||||
| 架构能力 | 候选实现 |
|
||||
|---|---|
|
||||
| Tenant、Agent、Task、Policy 和 Audit 控制面 | `active-runtime/app/aios_v2/control_plane.py` |
|
||||
| 控制面持久化 | `active-runtime/app/aios_v2/persistence.py` |
|
||||
| Web/API Gateway | `active-runtime/app/aios_v2/gateway.py` |
|
||||
| 统一应用入口 | `active-runtime/app/aios_v2/app.py` |
|
||||
| Runtime 调度与结果回写 | `active-runtime/app/aios_v2/orchestrator.py` |
|
||||
| Agent 执行证据 | `active-runtime/app/aios_v2/execution_tracking.py` |
|
||||
| GitOps 状态可视化 | `active-runtime/app/aios_v2/gitops_status.py` |
|
||||
| Web Console | `active-runtime/app/aios_v2/console.py` |
|
||||
| OpenClaw 执行边界 | `active-runtime/app/aios_openclaw/` |
|
||||
| Hermes Runtime 边界 | `active-runtime/app/aios_hermes/` |
|
||||
| 候选测试 | `tests/aios_v2_candidate/` |
|
||||
| 部署、健康检查与回滚 | `deploy/aios-v2/` |
|
||||
| OpenClaw 生产部署任务 | `tasks/openclaw-production-deploy-task.yaml` |
|
||||
| Codex 生产监督任务 | `tasks/codex-production-supervisor-task.yaml` |
|
||||
|
||||
## 4. 状态术语
|
||||
|
||||
项目必须严格区分“代码存在”和“可生产发布”:
|
||||
|
||||
- **已设计**:文档中存在明确边界和验收标准。
|
||||
- **已实现**:代码已经提交到候选分支。
|
||||
- **已定义测试**:Git 中存在自动化测试代码。
|
||||
- **已验证测试**:已对精确 commit 执行测试并保存证据。
|
||||
- **已验证预发布**:已在隔离环境完成部署、健康检查、重启和回滚演练。
|
||||
- **已生产发布**:已取得 Owner 批准并完成合并、Tag 和生产部署。
|
||||
|
||||
分支、文件、测试脚本或部署脚本存在,并不自动代表能力已通过生产验收。
|
||||
|
||||
## 5. 设计摘要
|
||||
|
||||
```text
|
||||
浏览器 / Web Console / Public API
|
||||
|
|
||||
v
|
||||
AIOS 唯一控制面
|
||||
Tenant | Agent | Task | Policy | Audit
|
||||
|
|
||||
v
|
||||
Execution Orchestrator / Agent Router
|
||||
/ \
|
||||
v v
|
||||
OpenClaw Adapter Hermes Boundary
|
||||
| |
|
||||
v v
|
||||
OpenClaw Runtime Hermes Workers
|
||||
\
|
||||
v
|
||||
结果回写 + 审计 + 执行证据
|
||||
```
|
||||
|
||||
控制面拥有权威身份、策略、审批、任务生命周期和审计状态。OpenClaw 与 Hermes 只接收带租户上下文、已经批准的执行工作,并返回运行结果。
|
||||
|
||||
## 6. 发布规则
|
||||
|
||||
候选版本在满足以下条件前不得提升:
|
||||
|
||||
- 需求到代码的追踪关系完整;
|
||||
- 文档—代码匹配检查通过;
|
||||
- 多租户负向测试通过;
|
||||
- GitOps Controller worktree 保持 detached 且 clean;
|
||||
- 本地 Git 与 Gitea 目标分支 OID 一致;
|
||||
- 持久化重启恢复测试通过;
|
||||
- 预发布健康检查和回滚演练通过;
|
||||
- Git 中不存在明文密钥;
|
||||
- OpenClaw 与 Hermes 真实 Runtime 联调通过;
|
||||
- Owner 对合并、Tag 和生产部署做出明确批准。
|
||||
|
||||
## 7. 文档完整性要求
|
||||
|
||||
每份正式文档必须包含:
|
||||
|
||||
- 文档目的与适用范围;
|
||||
- 当前版本和状态;
|
||||
- 关键设计或需求正文;
|
||||
- 代码、测试或部署映射;
|
||||
- 验收与更新规则;
|
||||
- 已知限制和后续演进方向。
|
||||
|
||||
禁止在正式归档包中以摘要、占位符或“后续补充”代替正文。
|
||||
|
||||
## 8. 中文输出要求
|
||||
|
||||
所有面向用户、产品、架构、运维和审计的正式文档统一使用中文。以下技术标识保留原始英文,避免与代码不一致:
|
||||
|
||||
- 类名、函数名、字段名;
|
||||
- API 路径和 HTTP Header;
|
||||
- Git 分支、Commit、Tag;
|
||||
- OpenClaw、Hermes、Agent Router、GitOps 等专有名称;
|
||||
- systemd、Docker、SQLite、HMAC、HTTP 等标准技术术语。
|
||||
@@ -0,0 +1,108 @@
|
||||
# ADR-001:AIOS 作为唯一控制面
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:Control Plane、Agent Router、OpenClaw、Hermes、Web Console、GitOps、审计
|
||||
|
||||
## 1. 背景
|
||||
|
||||
现有系统已经包含多个执行、调度和治理能力。如果 OpenClaw、Hermes、Agent Router 或 Web 层分别保存自己的租户、策略、审批和任务状态,就会形成多个权威事实源,带来以下问题:
|
||||
|
||||
- 同一任务在不同模块中状态不一致;
|
||||
- 审计链不完整;
|
||||
- 多租户隔离难以统一验证;
|
||||
- Web、Runtime 和运维入口可能绕过策略;
|
||||
- Bug 修复和发布无法判断应该修改哪个事实源。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
AIOS Control Plane 是唯一权威控制面,负责:
|
||||
|
||||
- Tenant Registry;
|
||||
- Identity 与角色上下文;
|
||||
- Agent Registry;
|
||||
- Task Lifecycle;
|
||||
- Policy Decision;
|
||||
- Approval;
|
||||
- Audit Event;
|
||||
- Runtime Inventory;
|
||||
- Execution Evidence;
|
||||
- GitOps 与发布状态可视化。
|
||||
|
||||
OpenClaw、Hermes 和 Agent Router 只能执行、路由或调度已经由 AIOS 批准的工作,不得拥有第二套租户、策略、审批或任务生命周期。
|
||||
|
||||
## 3. 目标边界
|
||||
|
||||
```text
|
||||
Web / API
|
||||
|
|
||||
v
|
||||
AIOS Control Plane
|
||||
|
|
||||
v
|
||||
Execution Orchestrator / Agent Router
|
||||
|
|
||||
+--> OpenClaw Adapter --> OpenClaw Runtime
|
||||
|
|
||||
+--> Hermes Boundary --> Hermes Workers
|
||||
```
|
||||
|
||||
## 4. 备选方案
|
||||
|
||||
### 方案 A:保持多个控制面
|
||||
|
||||
拒绝原因:状态会持续分裂,无法形成统一审计和租户隔离。
|
||||
|
||||
### 方案 B:由 OpenClaw 或 Hermes 成为主控制面
|
||||
|
||||
拒绝原因:二者主要价值是执行与 Runtime,不适合作为统一产品、租户、审批和发布控制面。
|
||||
|
||||
### 方案 C:推倒重写全部能力
|
||||
|
||||
拒绝原因:会丢失现有执行能力、运行经验和迁移可回滚性。
|
||||
|
||||
## 5. 正面影响
|
||||
|
||||
- 任务、策略和租户状态唯一;
|
||||
- Web/API、OpenClaw、Hermes 和 GitOps 使用同一权威模型;
|
||||
- 审计、执行证据和发布判断可以统一;
|
||||
- 新 Runtime 可以通过稳定 Adapter 接入;
|
||||
- 多租户和权限模型可集中验证。
|
||||
|
||||
## 6. 负面影响与风险
|
||||
|
||||
- 所有旧执行入口需要迁移到 Orchestrator;
|
||||
- Runtime 需要稳定 Contract;
|
||||
- Control Plane 可靠性要求提高;
|
||||
- 在迁移完成前可能短期存在旧旁路,需要明确冻结和监控。
|
||||
|
||||
## 7. 迁移与回滚
|
||||
|
||||
迁移顺序:
|
||||
|
||||
1. 建立 AIOS Control Plane 权威模型;
|
||||
2. 引入 Orchestrator;
|
||||
3. OpenClaw/Hermes 通过 Adapter 接入;
|
||||
4. 将 Web 和自动任务切换到 AIOS API;
|
||||
5. 关闭旧控制旁路。
|
||||
|
||||
回滚只允许回滚 Runtime 或应用版本,不允许恢复第二套权威控制状态。
|
||||
|
||||
## 8. 合规检查
|
||||
|
||||
任何新功能必须回答:
|
||||
|
||||
- 权威状态是否存放在 AIOS?
|
||||
- Runtime 是否只接收已批准工作?
|
||||
- Web 是否只调用 AIOS API?
|
||||
- 是否新增了第二套状态机或租户事实源?
|
||||
|
||||
若最后一项为“是”,变更必须拒绝或新增替代 ADR。
|
||||
|
||||
## 9. 实现与测试映射
|
||||
|
||||
- 实现:`active-runtime/app/aios_v2/control_plane.py`
|
||||
- 编排:`active-runtime/app/aios_v2/orchestrator.py`
|
||||
- 应用入口:`active-runtime/app/aios_v2/app.py`
|
||||
- 测试:`tests/aios_v2_candidate/test_candidate_flow.py`
|
||||
- 追踪:`docs/aios-v2/05-TRACEABILITY-MATRIX.md`
|
||||
@@ -0,0 +1,108 @@
|
||||
# ADR-002:OpenClaw 与 Hermes 从控制面职责中解耦
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:OpenClaw、Hermes、Execution Orchestrator、Agent Router、Audit、Web Console
|
||||
|
||||
## 1. 背景
|
||||
|
||||
OpenClaw 和 Hermes 已经具备成熟的执行能力,但历史实现可能同时承担部分租户、策略、任务状态或运维控制职责。如果继续扩展这种模式,AIOS 将无法成为唯一控制面,也无法统一 Web、审计和多租户隔离。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
OpenClaw 与 Hermes 通过稳定的 Adapter/Boundary 接入 AIOS:
|
||||
|
||||
```text
|
||||
AIOS Control Plane
|
||||
|
|
||||
v
|
||||
Execution Orchestrator
|
||||
|
|
||||
+--> OpenClaw Adapter --> OpenClaw Runtime
|
||||
|
|
||||
+--> Hermes Boundary --> Hermes Workers
|
||||
```
|
||||
|
||||
OpenClaw 只负责:
|
||||
|
||||
- 验证签名命令;
|
||||
- 执行;
|
||||
- 查询状态;
|
||||
- 取消;
|
||||
- 健康检查;
|
||||
- 返回结果和生命周期事件。
|
||||
|
||||
Hermes 只负责:
|
||||
|
||||
- tenant/cell/profile 分区队列;
|
||||
- Worker claim;
|
||||
- Lease 与 Heartbeat;
|
||||
- 执行;
|
||||
- 完成、失败、取消和结果回传。
|
||||
|
||||
二者均不得:
|
||||
|
||||
- 创建或批准 AIOS Task;
|
||||
- 修改租户或策略;
|
||||
- 维护第二套任务生命周期;
|
||||
- 绕过 AIOS Audit;
|
||||
- 向浏览器提供直接控制入口。
|
||||
|
||||
## 3. 备选方案
|
||||
|
||||
### 方案 A:让 OpenClaw 继续拥有控制职责
|
||||
|
||||
拒绝原因:会产生第二控制面,并使 Web、审批和审计持续分裂。
|
||||
|
||||
### 方案 B:让 Hermes 统一控制和执行
|
||||
|
||||
拒绝原因:Hermes 的核心价值是 Worker Runtime 与队列,不应承担产品、租户和策略治理。
|
||||
|
||||
### 方案 C:直接替换 OpenClaw/Hermes
|
||||
|
||||
拒绝原因:不符合能力复用原则,会扩大迁移风险和开发量。
|
||||
|
||||
## 4. 正面影响
|
||||
|
||||
- AIOS 保持唯一权威状态;
|
||||
- OpenClaw/Hermes 可以独立升级;
|
||||
- 新 Runtime 可使用相同接入模式;
|
||||
- Web 和审计不再依赖 Runtime 内部实现;
|
||||
- 可逐步关闭旧旁路,而不需要一次性重写执行层。
|
||||
|
||||
## 5. 负面影响与风险
|
||||
|
||||
- 需要维护稳定的命令、结果和健康 Contract;
|
||||
- 旧调用路径可能在迁移期并存;
|
||||
- Runtime 联调和错误语义需要统一;
|
||||
- Adapter 本身成为重要可靠性边界。
|
||||
|
||||
## 6. 迁移步骤
|
||||
|
||||
1. 定义 OpenClawCommand/OpenClawResult/RuntimeHealth;
|
||||
2. 定义 HermesJob/HermesResult/HermesHealth;
|
||||
3. 引入 AIOS Orchestrator;
|
||||
4. 将新任务先通过 Adapter 执行;
|
||||
5. 迁移 Web、Codex 和自动任务入口;
|
||||
6. 冻结旧 Runtime 控制接口;
|
||||
7. 通过网络策略或代码门禁关闭旁路。
|
||||
|
||||
## 7. 回滚原则
|
||||
|
||||
允许回滚 Runtime 或 Adapter 版本,但不允许回滚到 Runtime 重新拥有 Tenant、Policy、Approval 或 Task Lifecycle 的模式。
|
||||
|
||||
## 8. 合规检查
|
||||
|
||||
- OpenClaw 输入是否为 AIOS 生成的签名命令?
|
||||
- Hermes Job 是否包含 tenant/cell/profile?
|
||||
- Runtime 是否只返回结果,不直接写 AIOS Store?
|
||||
- Web 是否只调用 AIOS API?
|
||||
- Runtime Bug 修复是否同步更新 Contract、测试和文档?
|
||||
|
||||
## 9. 实现与测试映射
|
||||
|
||||
- OpenClaw:`active-runtime/app/aios_openclaw/`
|
||||
- Hermes:`active-runtime/app/aios_hermes/`
|
||||
- Orchestrator:`active-runtime/app/aios_v2/orchestrator.py`
|
||||
- 测试:`tests/aios_v2_candidate/test_candidate_flow.py`
|
||||
- 模块契约:`docs/aios-v2/04-MODULE-CONTRACTS.md`
|
||||
@@ -0,0 +1,121 @@
|
||||
# ADR-003:所有变更必须通过 GitOps
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:代码、配置、文档、测试、部署、回滚、生产修复
|
||||
|
||||
## 1. 背景
|
||||
|
||||
直接在生产目录、长期 worktree、主分支或运行容器中修改代码,会造成以下问题:
|
||||
|
||||
- 变更不可追踪;
|
||||
- 无法稳定回滚;
|
||||
- 本地仓库与 Gitea 不一致;
|
||||
- Worktree 和 Branch Ref 冲突;
|
||||
- 紧急修复无法统一审视;
|
||||
- 文档、测试和部署资产无法同步。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
所有代码、配置、文档、测试、部署和回滚资产必须经过以下流程:
|
||||
|
||||
```text
|
||||
非 main 分支
|
||||
-> Commit
|
||||
-> 本地仓库同步
|
||||
-> Gitea 镜像与 OID 校验
|
||||
-> 自动测试
|
||||
-> Codex 监督审查
|
||||
-> 候选集成
|
||||
-> Owner 批准
|
||||
-> Merge / Tag / Deploy
|
||||
```
|
||||
|
||||
GitOps Controller worktree 必须长期保持 detached 且 clean。相同分支写入必须串行,任务工作区必须可回收。
|
||||
|
||||
## 3. 必需证据
|
||||
|
||||
每个任务必须记录:
|
||||
|
||||
- 任务 ID;
|
||||
- 执行器;
|
||||
- 分支;
|
||||
- Commit;
|
||||
- 修改文件;
|
||||
- claim;
|
||||
- heartbeat;
|
||||
- progress;
|
||||
- blocker;
|
||||
- 测试命令、exit code 和结果;
|
||||
- 本地/Gitea 同步状态;
|
||||
- 回滚说明;
|
||||
- 最终结果和监督结论。
|
||||
|
||||
## 4. 禁止事项
|
||||
|
||||
- 直接 push `main`;
|
||||
- 未审批创建生产 Tag;
|
||||
- 未记录任务直接修改生产;
|
||||
- 在生产目录手工修复后不回写 Git;
|
||||
- fetch 到已被 worktree 检出的本地 branch ref;
|
||||
- 以新分支名反复规避 Worktree 生命周期缺陷;
|
||||
- 在 Git 中提交明文凭据;
|
||||
- 缺少文档和测试时标记为完成。
|
||||
|
||||
## 5. 备选方案
|
||||
|
||||
### 方案 A:允许紧急生产手工修改
|
||||
|
||||
拒绝原因:即使紧急修复也必须形成 Patch、Commit 和证据,否则无法统一审视和回滚。
|
||||
|
||||
### 方案 B:只同步本地 Bare Repo
|
||||
|
||||
拒绝原因:Web Gitea 无法看到真实任务进度,团队无法审查。
|
||||
|
||||
### 方案 C:Controller 长期检出任务分支
|
||||
|
||||
拒绝原因:会触发 `refusing to fetch into branch checked out at worktree`,并破坏并发任务。
|
||||
|
||||
## 6. 正面影响
|
||||
|
||||
- 所有变更可审计;
|
||||
- 本地和 Web 远端一致;
|
||||
- 紧急修复也可回滚;
|
||||
- OpenClaw/Codex 进度可统一查询;
|
||||
- 文档与代码可通过门禁同步。
|
||||
|
||||
## 7. 负面影响与风险
|
||||
|
||||
- 生产修复增加提交与证据步骤;
|
||||
- GitOps Runtime 成为关键基础设施;
|
||||
- 需要处理分支锁、任务恢复和镜像失败;
|
||||
- 自动执行器必须遵循统一任务格式。
|
||||
|
||||
## 8. 运行规则
|
||||
|
||||
- Controller:detached + clean;
|
||||
- Fetch:更新 remote-tracking ref,不写已检出本地 branch;
|
||||
- Write:独立任务工作区或受控写入;
|
||||
- Lock:同一分支串行;
|
||||
- Mirror:本地成功和 Gitea 成功分别记录;
|
||||
- Failure:状态标记为 degraded/blocked,不得伪报 synced。
|
||||
|
||||
## 9. 紧急 Bug 修复流程
|
||||
|
||||
1. 创建 `patch/bugfix/*`;
|
||||
2. 登记 blocker 和影响;
|
||||
3. 添加复现测试;
|
||||
4. 修复代码;
|
||||
5. 同步文档;
|
||||
6. 执行验收;
|
||||
7. Codex 审核;
|
||||
8. Owner 批准发布;
|
||||
9. 生产观察并记录结果。
|
||||
|
||||
## 10. 实现与验收映射
|
||||
|
||||
- GitOps 状态:`active-runtime/app/aios_v2/gitops_status.py`
|
||||
- 健康检查:`deploy/aios-v2/healthcheck/check.sh`
|
||||
- 回滚:`deploy/aios-v2/rollback/rollback.sh`
|
||||
- 任务:`tasks/openclaw-production-deploy-task.yaml`、`tasks/codex-production-supervisor-task.yaml`
|
||||
- 文档门禁:`tools/aios_v2_docs_code_check.py`
|
||||
@@ -0,0 +1,150 @@
|
||||
# ADR-004:多租户隔离采用默认拒绝模型
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:Web/API、Control Plane、OpenClaw、Hermes、Persistence、Audit、Execution Evidence、Logs、Metrics、Secret
|
||||
|
||||
## 1. 背景
|
||||
|
||||
AIOS V2 同时承载多个租户的用户请求、控制面状态、OpenClaw 命令、Hermes 队列、执行证据、审计和 GitOps 状态。任何一层缺失租户边界,都可能造成数据泄露、跨租户任务执行或错误回写。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
多租户隔离采用:
|
||||
|
||||
```text
|
||||
显式租户上下文
|
||||
+
|
||||
默认拒绝
|
||||
+
|
||||
全链路传播
|
||||
+
|
||||
负向测试
|
||||
```
|
||||
|
||||
所有资源、命令、Job、证据和审计记录都必须显式绑定 `tenant_id`。缺少上下文、上下文不匹配或无法确认所有权时,系统必须 fail closed。
|
||||
|
||||
## 3. 权威上下文
|
||||
|
||||
控制请求至少包含:
|
||||
|
||||
- `tenant_id`;
|
||||
- `principal_id`;
|
||||
- `trace_id`;
|
||||
- `policy_version`;
|
||||
- 可选 `session_id`。
|
||||
|
||||
执行请求增加:
|
||||
|
||||
- `task_id`;
|
||||
- `command_id` 或 `job_id`;
|
||||
- `idempotency_key`。
|
||||
|
||||
Hermes 额外包含:
|
||||
|
||||
- `cell_id`;
|
||||
- `profile_id`;
|
||||
- `worker_id`。
|
||||
|
||||
## 4. 各层执行规则
|
||||
|
||||
### Web/API
|
||||
|
||||
- 可信代理必须删除客户端同名 `X-AIOS-*` Header 后重新注入;
|
||||
- 浏览器不得自行选择或覆盖租户;
|
||||
- 未认证身份断言必须拒绝。
|
||||
|
||||
### Control Plane
|
||||
|
||||
- Tenant、Agent、Task、Audit 全部带不可为空的 `tenant_id`;
|
||||
- 跨租户读取返回拒绝或“未找到”;
|
||||
- 不泄露其他租户资源存在性。
|
||||
|
||||
### OpenClaw
|
||||
|
||||
- 签名覆盖 tenant/task/trace/action/payload/idempotency/time;
|
||||
- Result 身份字段必须与命令完全一致;
|
||||
- 跨租户 status/cancel 返回“未找到”。
|
||||
|
||||
### Hermes
|
||||
|
||||
- Job 按 tenant/cell/profile 分区;
|
||||
- Worker 只能 claim 自己的分区;
|
||||
- Worker ID 不得在未授权分区之间迁移;
|
||||
- Result 必须匹配 tenant/task/trace。
|
||||
|
||||
### Persistence
|
||||
|
||||
- 候选版使用显式租户字段;
|
||||
- 生产数据库必须提供 RLS 或物理隔离策略;
|
||||
- 备份、恢复和迁移必须保持租户边界。
|
||||
|
||||
### Audit 与 Evidence
|
||||
|
||||
- 仅按当前租户查询;
|
||||
- 不记录明文 Secret;
|
||||
- 统一包含 tenant/task/trace。
|
||||
|
||||
### Cache、Memory、Artifact、Logs、Metrics
|
||||
|
||||
- Key 或标签必须包含租户命名空间;
|
||||
- 查询和导出必须受租户权限限制;
|
||||
- 不允许使用无租户前缀的全局缓存保存业务数据。
|
||||
|
||||
## 5. 备选方案
|
||||
|
||||
### 方案 A:仅在 API 层检查租户
|
||||
|
||||
拒绝原因:后台任务、Runtime、缓存和结果回写仍可能跨租户。
|
||||
|
||||
### 方案 B:仅依赖数据库隔离
|
||||
|
||||
拒绝原因:命令、队列、审计和文件系统仍需要显式边界。
|
||||
|
||||
### 方案 C:发生冲突时自动推断租户
|
||||
|
||||
拒绝原因:推断可能产生跨租户副作用,必须默认拒绝。
|
||||
|
||||
## 6. 正面影响
|
||||
|
||||
- 安全模型一致;
|
||||
- Runtime 无法绕过租户边界;
|
||||
- 负向测试可自动化;
|
||||
- 审计和问题定位更明确。
|
||||
|
||||
## 7. 负面影响与风险
|
||||
|
||||
- 所有接口和模型都需要传播租户上下文;
|
||||
- 日志、指标和缓存设计更复杂;
|
||||
- 候选 SQLite 只有逻辑隔离,生产仍需更强存储证据;
|
||||
- 身份代理配置错误可能破坏入口隔离。
|
||||
|
||||
## 8. 测试要求
|
||||
|
||||
至少覆盖:
|
||||
|
||||
- Tenant B 读取 Tenant A Task;
|
||||
- Tenant B 查询或取消 Tenant A OpenClawCommand;
|
||||
- Worker 跨 tenant/cell/profile claim;
|
||||
- Runtime 返回错误 tenant/task/trace;
|
||||
- Evidence 和 Audit 跨租户查询;
|
||||
- 缺少 Tenant Context 的请求;
|
||||
- 客户端伪造身份 Header。
|
||||
|
||||
## 9. 合规检查
|
||||
|
||||
任何新模块没有以下内容时不得进入 Candidate:
|
||||
|
||||
- 显式 `tenant_id`;
|
||||
- 所有权检查;
|
||||
- 跨租户负向测试;
|
||||
- 审计映射;
|
||||
- 文档与追踪矩阵更新。
|
||||
|
||||
## 10. 实现与测试映射
|
||||
|
||||
- Control Plane:`active-runtime/app/aios_v2/control_plane.py`
|
||||
- OpenClaw:`active-runtime/app/aios_openclaw/`
|
||||
- Hermes:`active-runtime/app/aios_hermes/`
|
||||
- Evidence:`active-runtime/app/aios_v2/execution_tracking.py`
|
||||
- 测试:`tests/aios_v2_candidate/test_candidate_flow.py`
|
||||
@@ -0,0 +1,116 @@
|
||||
# ADR-005:文档与代码同步门禁
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:需求、架构、代码、测试、部署、在线任务、发布和归档
|
||||
|
||||
## 1. 背景
|
||||
|
||||
架构、功能和部署变化如果不同步文档,会导致版本无法审计,后续 Agent 无法判断真实设计,发布人员也无法确认代码是否符合用户需求。历史上还出现过文档目录不存在、文档含冲突标记、分支名与代码内容不一致等问题。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
所有影响以下内容的变更必须在同一交付流程中同步 `docs/aios-v2/`:
|
||||
|
||||
- 用户行为和功能范围;
|
||||
- API、Header、请求和响应;
|
||||
- 数据模型、字段和状态机;
|
||||
- Control Plane、Agent Router、OpenClaw、Hermes 的边界;
|
||||
- 多租户和安全策略;
|
||||
- 持久化、审计和执行证据;
|
||||
- 部署、健康检查和回滚;
|
||||
- 测试和发布门禁。
|
||||
|
||||
正式文档统一使用中文,技术标识保留代码中的原始英文名称。
|
||||
|
||||
## 3. 门禁要求
|
||||
|
||||
验收必须执行:
|
||||
|
||||
```text
|
||||
python3 tools/aios_v2_docs_code_check.py
|
||||
```
|
||||
|
||||
检查至少包括:
|
||||
|
||||
1. 必需文档和 ADR 存在且非空;
|
||||
2. 文档以中文叙述为主;
|
||||
3. 文档引用的代码、测试和部署路径存在;
|
||||
4. 核心 API 能在代码中找到;
|
||||
5. 核心模型和字段能在代码中找到;
|
||||
6. Traceability Matrix 覆盖所有 `UR-*`;
|
||||
7. ADR 索引引用的文件存在;
|
||||
8. 文档中不存在 Git 冲突标记;
|
||||
9. 不存在摘要占位符或空章节;
|
||||
10. 架构/功能代码变化时,同一交付范围包含文档变化。
|
||||
|
||||
## 4. 状态影响
|
||||
|
||||
门禁失败时:
|
||||
|
||||
- Candidate 不得标记为 `Test-verified`;
|
||||
- OpenClaw 不得继续生产部署;
|
||||
- Codex 必须登记 blocker;
|
||||
- 修复必须进入 Git 分支;
|
||||
- Owner 不得批准 Tag 或生产部署。
|
||||
|
||||
## 5. 备选方案
|
||||
|
||||
### 方案 A:依赖人工记忆更新文档
|
||||
|
||||
拒绝原因:长期必然产生文档漂移。
|
||||
|
||||
### 方案 B:发布前集中补文档
|
||||
|
||||
拒绝原因:无法确定每次代码变化对应的真实设计,也会增加错误归因。
|
||||
|
||||
### 方案 C:只检查文件存在
|
||||
|
||||
拒绝原因:文件存在不代表内容完整、路径有效或与代码一致。
|
||||
|
||||
## 6. 正面影响
|
||||
|
||||
- 架构和代码长期一致;
|
||||
- Agent 有明确执行上下文;
|
||||
- Bug 修复可以追踪需求和决策;
|
||||
- 归档包可以作为正式交付材料;
|
||||
- 发布风险和未验证项更透明。
|
||||
|
||||
## 7. 负面影响与风险
|
||||
|
||||
- 小功能也需要更新对应文档;
|
||||
- 检查器需要随代码结构维护;
|
||||
- 自动检查不能替代架构审查;
|
||||
- 文档完整性会增加提交内容,但这是可审计交付的必要成本。
|
||||
|
||||
## 8. 文档更新映射
|
||||
|
||||
- 用户需求变化:`01-USER-REQUIREMENTS.md`;
|
||||
- 架构边界变化:`02-TARGET-ARCHITECTURE.md` 和 ADR;
|
||||
- 迁移/发布变化:`03-MIGRATION-AND-DELIVERY.md`;
|
||||
- Contract 变化:`04-MODULE-CONTRACTS.md`;
|
||||
- 路径和状态变化:`05-TRACEABILITY-MATRIX.md`;
|
||||
- 文档规则变化:`06-DOCUMENT-GOVERNANCE.md`。
|
||||
|
||||
## 9. 在线任务要求
|
||||
|
||||
OpenClaw 和 Codex 的任何修改或阻塞必须回写:
|
||||
|
||||
- claim;
|
||||
- heartbeat;
|
||||
- progress;
|
||||
- blocker;
|
||||
- branch;
|
||||
- commit;
|
||||
- test_status;
|
||||
- result;
|
||||
- 文档同步状态。
|
||||
|
||||
OpenClaw 发现架构影响时必须停止扩大修复范围,并升级给 Codex。
|
||||
|
||||
## 10. 实现与验收映射
|
||||
|
||||
- 检查器:`tools/aios_v2_docs_code_check.py`
|
||||
- 验收入口:`deploy/aios-v2/acceptance/run-all.sh`
|
||||
- 治理规范:`docs/aios-v2/06-DOCUMENT-GOVERNANCE.md`
|
||||
- 追踪矩阵:`docs/aios-v2/05-TRACEABILITY-MATRIX.md`
|
||||
@@ -0,0 +1,142 @@
|
||||
# ADR-006:候选持久化采用可替换 SQLite Snapshot
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:Control Plane、Persistence、Deployment、Backup、Recovery、HA 演进
|
||||
|
||||
## 1. 背景
|
||||
|
||||
AIOS V2 候选版本需要在服务重启后恢复 Tenant、Agent、Task、Audit 和 Idempotency 状态,同时又必须尽快进入预发布部署与 Bug 修复阶段。
|
||||
|
||||
候选阶段如果立即引入完整分布式数据库、消息系统和 HA,会显著扩大开发范围,推迟控制面、Runtime Boundary 和多租户模型的验证。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
候选版本使用可替换的 SQLite WAL 原子 Snapshot:
|
||||
|
||||
- `SQLiteSnapshotRepository` 保存版本化 Control Plane Snapshot;
|
||||
- `DurableControlPlaneService` 在成功变更后持久化;
|
||||
- 使用 WAL、`synchronous=FULL` 和 `BEGIN IMMEDIATE`;
|
||||
- 状态目录独立于代码版本;
|
||||
- 上层 Domain、API、Orchestrator 和 Runtime Contract 不依赖 SQLite 实现。
|
||||
|
||||
执行证据使用租户分区 JSON 文件,由 `ExecutionTracker` 原子写入。
|
||||
|
||||
## 3. 持久化范围
|
||||
|
||||
候选 Snapshot 包含:
|
||||
|
||||
- Tenant;
|
||||
- Agent;
|
||||
- Task;
|
||||
- Audit;
|
||||
- Idempotency。
|
||||
|
||||
独立 Evidence 目录包含:
|
||||
|
||||
- claim;
|
||||
- heartbeat;
|
||||
- progress;
|
||||
- blocker;
|
||||
- commit;
|
||||
- test_status;
|
||||
- result。
|
||||
|
||||
## 4. 选择理由
|
||||
|
||||
- 无额外外部依赖;
|
||||
- 易于快速部署和回滚;
|
||||
- 支持事务、WAL 和完整性检查;
|
||||
- 可以验证上层控制面和 Runtime Contract;
|
||||
- 便于在预发布阶段复现和修复 Bug;
|
||||
- 可通过 Repository 边界替换为生产数据库。
|
||||
|
||||
## 5. 备选方案
|
||||
|
||||
### 方案 A:候选阶段直接使用 PostgreSQL 集群
|
||||
|
||||
暂不采用原因:会增加部署、迁移、HA、Secret、网络和容量范围,延迟核心架构验证。
|
||||
|
||||
### 方案 B:继续使用纯内存状态
|
||||
|
||||
拒绝原因:服务重启会丢失权威状态,无法进入预发布。
|
||||
|
||||
### 方案 C:每个模块各自使用 SQLite
|
||||
|
||||
拒绝原因:会形成多个事实源和跨模块事务问题。
|
||||
|
||||
### 方案 D:将完整状态写入 Git
|
||||
|
||||
拒绝原因:运行状态不应成为 Git 内容,可能暴露敏感业务数据并造成提交风暴。
|
||||
|
||||
## 6. 正面影响
|
||||
|
||||
- 候选版具备重启恢复能力;
|
||||
- 状态与代码版本解耦;
|
||||
- 回滚默认只切换代码,不覆盖新状态;
|
||||
- 可快速进入预发布测试;
|
||||
- 生产后端替换不改变上层 Contract。
|
||||
|
||||
## 7. 负面影响与风险
|
||||
|
||||
- SQLite 主要适用于单进程候选部署;
|
||||
- 尚未提供多实例写入和分布式锁;
|
||||
- 租户隔离是逻辑隔离,不是 RLS 或物理隔离;
|
||||
- 大规模任务、审计和并发容量尚未验证;
|
||||
- Evidence 文件数量增长需要归档策略;
|
||||
- Snapshot 粒度可能导致状态增长后的写放大。
|
||||
|
||||
## 8. 生产迁移要求
|
||||
|
||||
生产数据层替换必须满足:
|
||||
|
||||
1. 保持 Control Plane Domain/API Contract 不变;
|
||||
2. 提供 schema migration;
|
||||
3. 提供租户 RLS 或物理隔离;
|
||||
4. 提供备份、恢复、PITR 和灾难恢复;
|
||||
5. 提供 HA、多实例并发和故障转移;
|
||||
6. 提供容量、延迟和锁等待测试;
|
||||
7. 保持 Audit 与 Evidence 可追踪;
|
||||
8. 提供从 SQLite Candidate 到生产后端的数据迁移工具;
|
||||
9. 通过新的 ADR 说明生产持久化决策。
|
||||
|
||||
## 9. 回滚策略
|
||||
|
||||
- 回滚前备份 `/var/lib/aios-v2`;
|
||||
- 默认只回滚代码;
|
||||
- 状态恢复必须由 Owner 显式授权;
|
||||
- 恢复前必须验证 Snapshot schema 兼容性;
|
||||
- 回滚后执行 SQLite `PRAGMA quick_check` 和 AIOS Healthcheck。
|
||||
|
||||
## 10. 验收要求
|
||||
|
||||
候选版至少通过:
|
||||
|
||||
- 创建 Tenant、Agent、Task;
|
||||
- 服务重启;
|
||||
- 读取恢复后的 Task;
|
||||
- Idempotency 仍有效;
|
||||
- Audit 仍存在;
|
||||
- SQLite `quick_check=ok`;
|
||||
- 状态目录权限正确;
|
||||
- 回滚演练不丢失新增状态。
|
||||
|
||||
## 11. 实现与测试映射
|
||||
|
||||
- Repository:`active-runtime/app/aios_v2/persistence.py`
|
||||
- 应用入口:`active-runtime/app/aios_v2/app.py`
|
||||
- Evidence:`active-runtime/app/aios_v2/execution_tracking.py`
|
||||
- 测试:`tests/aios_v2_candidate/test_candidate_flow.py`
|
||||
- 健康检查:`deploy/aios-v2/healthcheck/check.sh`
|
||||
- 回滚:`deploy/aios-v2/rollback/rollback.sh`
|
||||
|
||||
## 12. 更新触发条件
|
||||
|
||||
以下变化必须更新或替代本 ADR:
|
||||
|
||||
- 引入生产数据库;
|
||||
- 支持多实例写入;
|
||||
- 修改 Snapshot 格式;
|
||||
- 改变 Evidence 存储;
|
||||
- 增加 RLS、HA、分片或事件溯源;
|
||||
- 修改状态回滚策略。
|
||||
@@ -0,0 +1,107 @@
|
||||
# ADR-007:AIOS V2 Run Provenance 可信执行来源控制
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-20
|
||||
- 影响范围:Runtime 执行、Evidence、GitOps、部署、回滚、审计
|
||||
|
||||
## 1. 背景
|
||||
|
||||
AIOS V2 在进入预生产阶段前,需要证明每一次高权限动作来源可信。仅依靠进程内 runId、sender 或任务字段无法证明:
|
||||
|
||||
- 谁授权了执行;
|
||||
- 执行是否属于当前任务;
|
||||
- Git、部署、回滚和 Evidence 写入是否经过批准;
|
||||
- 是否存在重放或伪造运行记录。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
引入 Run Provenance:
|
||||
|
||||
```text
|
||||
Owner / Control Plane
|
||||
|
|
||||
v
|
||||
Ed25519 Signed Provenance
|
||||
|
|
||||
v
|
||||
Persistent Provenance Store
|
||||
|
|
||||
v
|
||||
Controlled Writer
|
||||
|
|
||||
v
|
||||
Runtime / GitOps / Deploy / Evidence / Rollback
|
||||
```
|
||||
|
||||
## 3. 七类受保护路径
|
||||
|
||||
生产 Provenance 必须覆盖:
|
||||
|
||||
1. code_change
|
||||
2. git_operation
|
||||
3. deployment
|
||||
4. runtime_execute
|
||||
5. evidence_write
|
||||
6. rollback
|
||||
7. audit
|
||||
|
||||
任何未授权路径默认拒绝。
|
||||
|
||||
## 4. 安全规则
|
||||
|
||||
- 私钥只用于签发端。
|
||||
- Runtime 只持有公钥验证能力。
|
||||
- Provenance 使用 Ed25519 签名。
|
||||
- 状态持久保存 issued、verified、used、expired、revoked。
|
||||
- 相同 provenance/path/request_digest 不允许重复授权。
|
||||
- Secret 不进入 Git、日志和 Evidence。
|
||||
|
||||
## 5. 实现映射
|
||||
|
||||
代码:
|
||||
|
||||
```text
|
||||
active-runtime/app/aios_v2/provenance.py
|
||||
active-runtime/app/aios_v2/provenance_git.py
|
||||
active-runtime/app/aios_v2/provenance_operations.py
|
||||
active-runtime/app/aios_v2/provenance_cli.py
|
||||
```
|
||||
|
||||
接入:
|
||||
|
||||
```text
|
||||
orchestrator.py
|
||||
execution_tracking.py
|
||||
app.py
|
||||
```
|
||||
|
||||
## 6. 验收要求
|
||||
|
||||
必须验证:
|
||||
|
||||
- 签名正确执行;
|
||||
- 篡改拒绝;
|
||||
- 过期拒绝;
|
||||
- revoke 拒绝;
|
||||
- replay 拒绝;
|
||||
- 无 Provenance Runtime Dispatch 拒绝;
|
||||
- 无 Evidence 授权写入拒绝;
|
||||
- 无 Git 授权操作拒绝;
|
||||
- 无 Deployment/Rollback 授权拒绝。
|
||||
|
||||
## 7. 回滚
|
||||
|
||||
若 Provenance 服务异常:
|
||||
|
||||
- 不允许降级绕过安全检查进入生产;
|
||||
- 候选环境可以在明确测试配置中关闭强制模式;
|
||||
- 生产模式必须保持 AIOS_REQUIRE_RUN_PROVENANCE=true。
|
||||
|
||||
## 8. 后续演进
|
||||
|
||||
生产阶段可进一步接入:
|
||||
|
||||
- HSM/KMS;
|
||||
- 外部不可变审计;
|
||||
- 多签审批;
|
||||
- 硬件密钥认证。
|
||||
@@ -0,0 +1,156 @@
|
||||
# ADR-009:Workflow Provenance 与最小权限子 Grant
|
||||
|
||||
- 状态:已采纳
|
||||
- 日期:2026-07-21
|
||||
- 决策范围:AIOS V2R1 生产授权、Runtime 调度、Evidence、Git、部署、回滚与审计
|
||||
|
||||
## 1. 背景
|
||||
|
||||
早期候选实现使用一个 Run Provenance 同时承载身份绑定和七类生产操作权限。该模型可以证明一次执行来自哪个租户、任务、Agent 与 Principal,但同一凭证能够授权 Runtime、Evidence、Git、部署、回滚、审计和代码变更,违反最小权限原则。任何持有该凭证的进程都可能获得超出职责的能力。
|
||||
|
||||
同时,Runtime Result 回写、Git 写入和部署包装器需要可撤销、可过期、可重放防护且可持久恢复的独立授权。仅依赖进程角色或环境变量不足以形成可审计的生产信任链。
|
||||
|
||||
## 2. 决策
|
||||
|
||||
采用两层 Provenance 模型:
|
||||
|
||||
1. **Workflow Provenance** 只绑定 `run_id`、`tenant_id`、`task_id`、`agent_id`、`principal_id`、签发者、TTL、Key ID、Nonce 和签名,不授予任何操作路径。
|
||||
2. **Provenance Grant** 由 Workflow Provenance 派生,每个 Grant 只绑定一个 `ExecutionPath`,拥有独立的 TTL、Nonce、状态、撤销和重放记录。
|
||||
3. Git Grant 还必须显式限定允许的 `GitOperation`,例如只允许 `READ_REF` 而不允许 `PUSH`。
|
||||
4. 子 Grant 的身份字段必须与父 Workflow 完全一致,且子 Grant 的有效期不得超过父 Workflow。
|
||||
5. 父 Workflow 被撤销或过期后,其全部子 Grant 自动失效。
|
||||
6. 授权使用 `(grant_id, execution_path, git_operation, request_digest)` 建立唯一使用记录,重复请求默认拒绝。
|
||||
|
||||
## 3. Grant 类型
|
||||
|
||||
| GrantType | 唯一允许路径 |
|
||||
|---|---|
|
||||
| `code_change` | `code_change` |
|
||||
| `git` | `git_operation` |
|
||||
| `deployment` | `deployment` |
|
||||
| `runtime` | `runtime_execute` |
|
||||
| `evidence` | `evidence_write` |
|
||||
| `rollback` | `rollback` |
|
||||
| `audit` | `audit` |
|
||||
|
||||
Grant 类型与路径不一致时,构造阶段即拒绝。非 Git Grant 不得包含 Git 操作;Git Grant 未声明具体操作时不得签发。
|
||||
|
||||
## 4. 服务级 Scope
|
||||
|
||||
生产进程不得加载全部 Grant。`ScopedLeastPrivilegeProvenanceWriter` 只接受当前服务声明的路径和对应 Grant ID,多余 Grant 映射会导致启动失败。
|
||||
|
||||
默认 AIOS Application Scope 仅包含:
|
||||
|
||||
- `runtime_execute`
|
||||
- `evidence_write`
|
||||
- `audit`
|
||||
|
||||
Git、部署、回滚和代码变更必须由独立进程或包装器显式声明自己的单一路径 Scope。运维 CLI 的一次授权命令只接受一个 `--grant-id`,并要求它与 `--path` 一致。
|
||||
|
||||
## 5. Runtime 与 Dispatch 绑定
|
||||
|
||||
Runtime 执行还必须经过持久化 `DispatchRecord`。记录至少绑定:
|
||||
|
||||
- `dispatch_id`
|
||||
- `tenant_id`
|
||||
- `task_id`
|
||||
- `agent_id`
|
||||
- `principal_id`
|
||||
- `runtime`
|
||||
- `runtime_execution_id`
|
||||
- `trace_id`
|
||||
- `provenance_id`
|
||||
- `run_id`
|
||||
- `authorization_id`
|
||||
|
||||
OpenClaw/Hermes 结果只有在上述上下文完全匹配时才能由 Orchestrator 更新 Task。公开 Task API 不允许直接把任务推进到 `RUNNING`、`COMPLETED` 或 `FAILED`;Hermes 结果只通过内部 Runtime Reconcile 入口处理。
|
||||
|
||||
## 6. 密钥与签名
|
||||
|
||||
Workflow Provenance、子 Grant 和 OpenClaw Command 均采用 Ed25519。生产应用只读取公钥;私钥仅存在于受保护的签发端或 systemd credential。Git、日志、环境模板和审计中不得出现私钥内容。
|
||||
|
||||
Key ID 用于选择受信任密钥,不包含密钥材料。公钥 Fingerprint 使用恒定时间比较。OpenClaw Command 合同版本为 `aios.openclaw.command.v2`。
|
||||
|
||||
## 7. 备选方案
|
||||
|
||||
### 7.1 单一全权限 Provenance
|
||||
|
||||
拒绝。实现简单,但任何服务泄漏都可能获得全部生产能力,无法独立撤销 Runtime、Git 或部署权限。
|
||||
|
||||
### 7.2 仅依赖 RBAC
|
||||
|
||||
拒绝。RBAC 可以限制 API 调用者,但不能把具体 Run、Task、Agent、请求摘要和 Runtime Result 绑定到一次可验证授权。
|
||||
|
||||
### 7.3 每个操作重新签发完整 Workflow
|
||||
|
||||
拒绝。会复制身份数据和生命周期状态,难以统一撤销整次工作流,也增加签发和审计复杂度。
|
||||
|
||||
## 8. 正面影响
|
||||
|
||||
- 服务与操作权限按职责隔离。
|
||||
- Runtime、Evidence、Git、部署、回滚和审计可以独立撤销。
|
||||
- 父 Workflow 可作为整次 Run 的紧急停止开关。
|
||||
- SQLite 持久化支持重启后的授权与 Dispatch 恢复。
|
||||
- Receipt 明确记录 Grant、Scope、请求摘要和授权时间。
|
||||
- Git Index 只有在 Grant 授权完成后才允许修改。
|
||||
|
||||
## 9. 负面影响与风险
|
||||
|
||||
- 签发和部署配置比单凭证模式复杂。
|
||||
- 每个生产服务必须配置正确的 Grant ID。
|
||||
- Grant 状态与 Dispatch 状态需要备份、迁移和容量治理。
|
||||
- 当前候选实现使用 SQLite;高可用生产部署仍需外部持久化和并发容量证据。
|
||||
- OpenClaw callback 目前只作为非权威审计事件;状态变化仍必须经过 Orchestrator 严格 Reconcile。
|
||||
|
||||
## 10. 迁移与回滚
|
||||
|
||||
迁移步骤:
|
||||
|
||||
1. 签发无操作权限的 Workflow Provenance。
|
||||
2. 按所需路径签发独立子 Grant。
|
||||
3. 为每个服务配置其最小 Grant ID。
|
||||
4. 启用 `AIOS_REQUIRE_RUN_PROVENANCE=true`。
|
||||
5. 验证 Scope 拒绝、撤销、过期、重放和重启恢复测试。
|
||||
6. 完成预发布 Acceptance 后,禁止旧全权限 `issue` 命令进入生产流程。
|
||||
|
||||
回滚仅允许回到前一个已验证候选版本,不得回滚为生产全权限 Provenance。状态恢复必须保留父 Workflow、Grant 使用记录、Dispatch 和 Receipt,防止旧授权被再次使用。
|
||||
|
||||
## 11. 合规检查
|
||||
|
||||
必须满足:
|
||||
|
||||
- 父 Workflow 无操作路径。
|
||||
- 子 Grant 只包含一个路径。
|
||||
- 生产服务只加载职责所需 Grant。
|
||||
- 上下文不匹配、签名错误、过期、撤销和重放全部 fail closed。
|
||||
- Runtime Result 必须匹配持久 Dispatch。
|
||||
- 测试与文档在同一分支提交。
|
||||
- 正式 Gate A 结论必须基于实际执行 Acceptance,不得仅凭测试文件存在声明通过。
|
||||
|
||||
## 12. 受影响资产
|
||||
|
||||
代码:
|
||||
|
||||
- `active-runtime/app/aios_v2/provenance.py`
|
||||
- `active-runtime/app/aios_v2/provenance_grants.py`
|
||||
- `active-runtime/app/aios_v2/provenance_scoped.py`
|
||||
- `active-runtime/app/aios_v2/provenance_operations.py`
|
||||
- `active-runtime/app/aios_v2/provenance_cli.py`
|
||||
- `active-runtime/app/aios_v2/dispatch_store.py`
|
||||
- `active-runtime/app/aios_v2/orchestrator.py`
|
||||
- `active-runtime/app/aios_v2/execution_tracking.py`
|
||||
- `active-runtime/app/aios_v2/provenance_git.py`
|
||||
- `active-runtime/app/aios_openclaw/contract.py`
|
||||
|
||||
测试:
|
||||
|
||||
- `tests/aios_v2_candidate/test_provenance.py`
|
||||
- `tests/aios_v2_candidate/test_provenance_grant_isolation.py`
|
||||
- `tests/aios_v2_candidate/test_candidate_flow.py`
|
||||
|
||||
部署与文档:
|
||||
|
||||
- `deploy/aios-v2/env/aios-v2.env.example`
|
||||
- `docs/aios-v2/04-MODULE-CONTRACTS.md`
|
||||
- `docs/aios-v2/05-TRACEABILITY-MATRIX.md`
|
||||
- `docs/aios-v2/AIOS-V2R1-HARDENING-GATE-A-REPORT.md`
|
||||
@@ -0,0 +1,80 @@
|
||||
# ADR-010:Hermes 在线生命周期使用默认关闭的内部 Runtime API
|
||||
|
||||
- 状态:Accepted for Release Candidate
|
||||
- 日期:2026-07-21
|
||||
- 范围:AIOS V2R1 Hermes Worker Lifecycle Acceptance
|
||||
|
||||
## 决策
|
||||
|
||||
使用现有 `HermesAdapter` Queue/Lease 状态机,增加 SQLite 持久 Store,并通过默认关闭的
|
||||
内部 Runtime API 执行 Claim、Start、Heartbeat、Complete、Fail、Cancel 与 Status。
|
||||
不建立第二套 Queue、Lease 或 Task 状态机。
|
||||
|
||||
内部 API 只接受可信代理注入且具有 `runtime`/`platform_admin` 角色的身份。请求必须绑定
|
||||
tenant、task、trace、principal、provenance、run、dispatch、job、cell 和 profile。
|
||||
Complete、Fail、Cancel 只能经 `ExecutionOrchestrator.reconcile_hermes` 更新权威 Task。
|
||||
|
||||
## 背景
|
||||
|
||||
原 Candidate 已具有进程内 Hermes Claim/Lease/Worker 能力及持久 Dispatch,但在线服务
|
||||
只暴露 enqueue/reconcile,且 Hermes Job/Lease 本身在重启后丢失,不能形成完整在线证据。
|
||||
|
||||
## 原因
|
||||
|
||||
直接验收驱动会形成 Adapter 之外的额外变更入口,难以证明 HTTP 身份、Dispatch 与
|
||||
Orchestrator 边界。受保护的内部 API 可以在真实 localhost 服务、真实 SQLite Store 和
|
||||
真实 HTTP 解析路径上验证完整生命周期,同时在生产通过配置保持关闭。
|
||||
|
||||
## 备选方案
|
||||
|
||||
- 受信验收驱动直接导入 Adapter:改动较小,但不能证明内部 HTTP 身份与请求解析边界,拒绝。
|
||||
- 新建独立 Queue/Lease 服务:会产生第二状态机和双写一致性问题,禁止。
|
||||
- 开放公共 Worker API:扩大攻击面并允许浏览器/Operator 触发 Runtime 状态,禁止。
|
||||
|
||||
## 安全不变量
|
||||
|
||||
1. 只有 APPROVED Task 可由 Orchestrator 创建 Hermes Job。
|
||||
2. Dispatch 在 Runtime 副作用前持久化。
|
||||
3. Worker 只能操作精确绑定且由其持有 Lease 的 Job。
|
||||
4. Runtime 结果必须通过完整身份元组与持久 Dispatch 校验。
|
||||
5. 只有 Orchestrator 能把 Task/Dispatch 推进到 Runtime 终态。
|
||||
6. 生命周期写入同步生成 Audit/Event 与 Execution Evidence。
|
||||
7. 相同终态重放幂等,不同终态或不同内容 fail closed。
|
||||
|
||||
## 恢复语义
|
||||
|
||||
`SQLiteHermesStore` 持久保存 Job、Result、Lease、幂等键与 Worker heartbeat。服务重启
|
||||
加载同一状态;过期 Lease 被持久重排为 QUEUED,清理旧 Owner 并递增 revision。新 Worker
|
||||
可重领,旧 Worker 的 Start/Heartbeat/Result 被拒绝。
|
||||
|
||||
## 影响与风险
|
||||
|
||||
- 正面:同一 Adapter 状态机获得持久恢复、真实 HTTP 验收、严格身份绑定和可审计证据。
|
||||
- 负面:SQLite Snapshot 每次生命周期变更都执行同步事务,需在预生产观察锁等待与吞吐。
|
||||
- 风险:可信代理头是身份边界;因此接口必须保持 localhost/内部路由、默认关闭,并由部署
|
||||
配置保证外部请求不能自行注入身份头。
|
||||
|
||||
## 迁移与回滚
|
||||
|
||||
新 Store 文件为新增的 `hermes.sqlite3`,不修改既有 Control Plane/Dispatch schema。回滚到
|
||||
Previous OID 时保留该文件但旧版本不读取;不得用旧备份覆盖新业务状态。重新升级时可继续
|
||||
加载。接口回滚只需关闭环境开关并恢复 Previous Release OID。
|
||||
|
||||
## 合规检查
|
||||
|
||||
- 不修改 main,不创建 Tag,不绕过 Provenance/Grant。
|
||||
- 生产默认关闭生命周期验收入口。
|
||||
- Secret 不进入请求、Audit、Evidence 或测试数据。
|
||||
- Result 由 Orchestrator 与持久 Dispatch 校验,负向场景 fail closed。
|
||||
|
||||
## 受影响资产
|
||||
|
||||
- 代码:`aios_hermes/adapter.py`、`aios_v2/app.py`、`orchestrator.py`、`gateway.py`。
|
||||
- 测试:`test_hermes_live_lifecycle.py` 及 Candidate/Provenance 回归。
|
||||
- 文档:用户需求、模块合同、追踪矩阵、Gate A 报告与本 ADR。
|
||||
|
||||
## 验证
|
||||
|
||||
`tests/aios_v2_candidate/test_hermes_live_lifecycle.py` 通过真实 localhost HTTP Server 与
|
||||
临时 SQLite 状态目录覆盖 17 项正向、负向、Lease、幂等和重启场景。最终发布结论仍必须
|
||||
以提交后的 Gate、在线回归、Secret Audit、SQLite 检查、回滚与独立 Reviewer 证据为准。
|
||||
@@ -0,0 +1,82 @@
|
||||
# AIOS V2 架构决策记录索引
|
||||
|
||||
- 文档版本:`V2R1-hardening-candidate`
|
||||
- 适用范围:影响多个模块、长期演进、兼容性、安全、数据、部署或交付流程的关键架构决策
|
||||
|
||||
## 1. 架构决策记录列表
|
||||
|
||||
| 编号 | 决策 | 状态 |
|
||||
|---|---|---|
|
||||
| [ADR-001](ADR-001-single-control-plane.md) | AIOS 作为唯一控制面 | 已采纳 |
|
||||
| [ADR-002](ADR-002-openclaw-hermes-decoupling.md) | OpenClaw 与 Hermes 从控制面职责中解耦 | 已采纳 |
|
||||
| [ADR-003](ADR-003-gitops-only-change-flow.md) | 所有变更必须通过 GitOps | 已采纳 |
|
||||
| [ADR-004](ADR-004-multi-tenant-isolation.md) | 多租户隔离采用默认拒绝模型 | 已采纳 |
|
||||
| [ADR-005](ADR-005-document-code-sync-gate.md) | 文档与代码同步门禁 | 已采纳 |
|
||||
| [ADR-006](ADR-006-candidate-persistence-strategy.md) | 候选持久化采用可替换 SQLite Snapshot | 已采纳 |
|
||||
| ADR-007 | 当前仓库未分配;禁止补写不存在的历史决策 | 未分配 |
|
||||
| ADR-008 | 当前仓库未分配;禁止补写不存在的历史决策 | 未分配 |
|
||||
| [ADR-009](ADR-009-provenance-least-privilege.md) | Workflow Provenance、最小权限子 Grant 与服务级 Scope | 已采纳 |
|
||||
| [ADR-010](ADR-010-hermes-live-lifecycle.md) | Hermes 在线生命周期使用默认关闭的内部 Runtime API | RC 已采纳;待 Owner 发布批准 |
|
||||
|
||||
## 2. 编号规则
|
||||
|
||||
- ADR 编号一经发布不得重用。
|
||||
- 编号缺口可以保留,不能通过伪造历史文件填补。
|
||||
- 新决策使用下一个未占用编号,并在同一分支更新本索引、模块契约和追踪矩阵。
|
||||
- ADR-007 与 ADR-008 在当前仓库没有可验证历史文件,因此明确标记为未分配。
|
||||
|
||||
## 3. 状态定义
|
||||
|
||||
- **已提出**:决策已提出,但尚未被正式采纳。
|
||||
- **已采纳**:当前有效,所有新实现必须遵守。
|
||||
- **已替代**:已被新的 ADR 替代,保留用于历史追踪。
|
||||
- **已废弃**:保留历史,但禁止新实现继续采用。
|
||||
- **未分配**:该编号当前没有 ADR 文件,不代表存在隐含历史决策。
|
||||
|
||||
## 4. 必须新增或更新 ADR 的场景
|
||||
|
||||
以下变化必须新增或更新 ADR:
|
||||
|
||||
1. AIOS、OpenClaw、Hermes、Agent Router 的控制边界变化;
|
||||
2. 多租户隔离模型变化;
|
||||
3. API、数据模型或状态机出现不兼容变化;
|
||||
4. 持久化、消息、密钥、审计或部署方案发生跨模块变化;
|
||||
5. GitOps、发布、回滚或文档门禁变化;
|
||||
6. 替换 OpenClaw、Hermes、Agent Router 或核心基础设施;
|
||||
7. 引入新的权威事实源、任务生命周期或租户状态;
|
||||
8. 生产安全模型、身份代理、Run Provenance、Grant 或 Secret 管理方式变化;
|
||||
9. Runtime Result、Dispatch 或服务 Scope 信任边界变化。
|
||||
|
||||
## 5. ADR 内容要求
|
||||
|
||||
每份 ADR 必须包含:
|
||||
|
||||
- 背景;
|
||||
- 决策;
|
||||
- 备选方案;
|
||||
- 采用理由;
|
||||
- 正面影响;
|
||||
- 负面影响和风险;
|
||||
- 迁移与回滚;
|
||||
- 合规检查;
|
||||
- 受影响的代码、测试和文档。
|
||||
|
||||
## 6. ADR 变更联动
|
||||
|
||||
ADR 新增、替代或废弃时,必须同步检查并更新:
|
||||
|
||||
- `01-USER-REQUIREMENTS.md`;
|
||||
- `02-TARGET-ARCHITECTURE.md`;
|
||||
- `03-MIGRATION-AND-DELIVERY.md`;
|
||||
- `04-MODULE-CONTRACTS.md`;
|
||||
- `05-TRACEABILITY-MATRIX.md`;
|
||||
- 相关代码、测试和部署资产;
|
||||
- 候选或 Gate 报告中的风险与发布结论。
|
||||
|
||||
## 7. 审查规则
|
||||
|
||||
- OpenClaw 不得自行采纳改变控制面边界的 ADR;发现需求后必须升级给 Codex。
|
||||
- Codex 负责审查 ADR 与代码、测试和文档是否一致。
|
||||
- 涉及合并、Tag、生产部署或重大风险接受的 ADR,必须由 AIOS Owner 最终批准。
|
||||
- ADR 未完成审查前,相关变更不得标记为 `Test-verified` 或 `Production released`。
|
||||
- ADR、测试文件或 Acceptance 脚本存在,不等于 Gate 已通过;必须有实际执行日志、退出码和证据。
|
||||
@@ -0,0 +1,25 @@
|
||||
# AIOS V2R1C1 Release Notes
|
||||
|
||||
- VRC: `V2R1C1`
|
||||
- SemVer: `2.1.0-rc.1`
|
||||
- 固定产品基线: `fb739f6e8ff9c031d319221ace68dce157694086`
|
||||
- 当前状态: `RELEASE_VALIDATION_PASS / FINAL_METADATA_COMMIT_REVALIDATION_REQUIRED`
|
||||
- 发布决策: `STOP_PREPRODUCTION`
|
||||
|
||||
OpenClaw Command v2 Companion:
|
||||
|
||||
- 分支: `patch/openclaw/AIOS-V2R1C1-COMMAND-V2-COMPANION-20260721`
|
||||
- 源 OID: `83f8f878c7da5dd8263f2af2efa80750492e5cb3`
|
||||
- Companion OID: `12d1c13170e0c5a691d67a9408e739e7a17064a3`
|
||||
- 插件版本: `2.1.0-rc.4`
|
||||
- 合同: `aios.openclaw.command.v2` / `Ed25519`
|
||||
- Artifact SHA256: `aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671`
|
||||
- 隔离验证: `AIOS -> OpenClaw V2 PASS`,正向与负向在线合同均通过。
|
||||
|
||||
旧 Release OID `80c4cbde03a82c30648a09b817bc2f03d5402936` 保留为原始 HTTP 401 失败诊断基线。Release OID `0778a31ec073e7c90003ef091f1d093c16bf22e5` 已实际完成 Gate A/B、文档同步、Secret Scan、Release Metadata、OpenClaw 第 13 步正负向、Hermes、重启恢复、隔离回滚/前滚和最终健康门禁,全部通过。
|
||||
|
||||
本次最终元数据闭环仍只修改五个允许的 Release 元数据文件;提交后形成的最终 OID 必须再次执行 Gate A/B、文档同步、Secret Scan、Release Metadata 和 OpenClaw 第 13 步正负向复验。复验通过前 Tag 保持不存在,生产流量保持未切换。
|
||||
|
||||
本分支只包含发布元数据。Personal Weixin Portal Adapter、Spark 专有 Provisioning、Future Incubator、Worktree 并发实验和长期 Agent 工作目录均未进入发布图。
|
||||
|
||||
只有最终 Release OID 的全部复验和步骤 14–17 通过后,才允许创建不可变 `V2R1C1` Tag。
|
||||
@@ -0,0 +1,47 @@
|
||||
# TASK-AIOS-CONTROL-PLANE-GATEWAY-V1
|
||||
|
||||
## Owner
|
||||
Codex
|
||||
|
||||
## Goal
|
||||
建立 AIOS V2 唯一控制面 Gateway v1。
|
||||
|
||||
## Architecture Boundary
|
||||
|
||||
AIOS Control Plane:
|
||||
- Tenant Registry
|
||||
- Agent Registry
|
||||
- Task Lifecycle
|
||||
- Policy Gate
|
||||
- Approval
|
||||
- Audit Event
|
||||
|
||||
不允许:
|
||||
- OpenClaw 直接管理任务生命周期
|
||||
- Hermes 直接暴露控制 API
|
||||
- Web UI 绕过 AIOS API
|
||||
|
||||
## Deliverables
|
||||
|
||||
1. Control Plane API skeleton
|
||||
2. Tenant context middleware
|
||||
3. Task state machine
|
||||
4. Agent registration contract
|
||||
5. Audit event interface
|
||||
|
||||
## Acceptance
|
||||
|
||||
- 所有 API 携带 tenant_id
|
||||
- 未授权跨租户访问拒绝
|
||||
- Task create/update/cancel 可审计
|
||||
- GitOps commit 可追踪
|
||||
- pytest + integration test 通过
|
||||
|
||||
## Migration
|
||||
|
||||
复用:
|
||||
- Agent Router
|
||||
- OpenClaw adapter
|
||||
- Hermes runtime
|
||||
|
||||
不重写执行层。
|
||||
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"type": "branch",
|
||||
"branch": "integration/aios-v2r1-cto-production-candidate-20260720",
|
||||
"base": "task/codex/AIOS-V2-CONTROL-PLANE-GATEWAY-V1-20260720",
|
||||
"created_by": "chatgpt-gitops-bot",
|
||||
"created_at": "2026-07-20T01:47:01Z",
|
||||
"direct_main_push": false,
|
||||
"owner_approval_required": true
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"type": "branch",
|
||||
"branch": "patch/chatgpt/AIOS-V2R1-HARDENING-20260721",
|
||||
"base": "patch/codex/AIOS-V2R1-RUN-PROVENANCE-CONTROL-20260720",
|
||||
"created_by": "chatgpt-gitops-bot",
|
||||
"created_at": "2026-07-21T02:46:59Z",
|
||||
"direct_main_push": false,
|
||||
"owner_approval_required": true
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"type": "branch",
|
||||
"branch": "patch/codex/AIOS-V2R1-RUN-PROVENANCE-CONTROL-20260720",
|
||||
"base": "integration/aios-v2r1-cto-production-candidate-20260720",
|
||||
"created_by": "chatgpt-gitops-bot",
|
||||
"created_at": "2026-07-20T12:11:59Z",
|
||||
"direct_main_push": false,
|
||||
"owner_approval_required": true
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"type": "branch",
|
||||
"branch": "task/codex/AIOS-V2-CONTROL-PLANE-GATEWAY-V1-20260720",
|
||||
"base": "main",
|
||||
"created_by": "chatgpt-gitops-bot",
|
||||
"created_at": "2026-07-19T17:06:04Z",
|
||||
"direct_main_push": false,
|
||||
"owner_approval_required": true
|
||||
}
|
||||
@@ -0,0 +1,127 @@
|
||||
apiVersion: aios.v2/v1
|
||||
kind: AgentTask
|
||||
metadata:
|
||||
name: codex-production-supervisor-task
|
||||
displayName: AIOS V2R1 Codex 架构监督、阻塞处理与发布审查任务
|
||||
owner: AIOS-Control-Plane
|
||||
language: zh-CN
|
||||
spec:
|
||||
executor: codex
|
||||
role: architecture-supervisor
|
||||
candidateBranch: integration/aios-v2r1-cto-production-candidate-20260720
|
||||
taskBranch: task/codex/AIOS-V2R1-PRODUCTION-SUPERVISOR-20260720
|
||||
initialState: queued
|
||||
objective: >-
|
||||
监督 AIOS V2R1 Candidate 的预发布部署和缺陷修复,持续检查唯一控制面、
|
||||
多租户、安全、文档、测试和回滚边界;分析并解决 OpenClaw 无法独立处理的阻塞,
|
||||
最终输出统一的发布就绪结论。
|
||||
inputs:
|
||||
- docs/aios-v2/
|
||||
- docs/aios-v2/adr/
|
||||
- AIOS-V2R1-PRODUCTION-CANDIDATE.md
|
||||
- tasks/openclaw-production-deploy-task.yaml
|
||||
- deploy/aios-v2/
|
||||
- active-runtime/app/
|
||||
- tests/aios_v2_candidate/
|
||||
- tools/aios_v2_docs_code_check.py
|
||||
responsibilities:
|
||||
- 领取任务并写入 claim 证据
|
||||
- 定期写入 heartbeat、progress 和监督结论
|
||||
- 审阅 OpenClaw 的部署、健康检查、联调和回滚证据
|
||||
- 分析失败测试、运行时异常和阻塞根因
|
||||
- 审查所有 patch 的架构边界、租户隔离和 Secret 安全
|
||||
- 解决需要跨模块修改的阻塞问题
|
||||
- 对控制面、数据模型、状态机或 Runtime Contract 变化要求新增或更新 ADR
|
||||
- 执行文档与代码匹配检查
|
||||
- 验证需求、架构、契约、代码、测试、部署和验收追踪完整
|
||||
- 拒绝缺少复现、测试、文档或回滚说明的修改
|
||||
- 将所有阻塞、审查结论、修复 Commit 和剩余风险提交到系统
|
||||
- 输出是否允许进入合并、Tag 和生产部署 Gate 的最终建议
|
||||
prohibited:
|
||||
- 绕过 GitOps 直接应用生产修改
|
||||
- 直接 push main 或创建生产 Tag
|
||||
- 在没有证据时批准发布
|
||||
- 为快速通过测试而削弱租户隔离、安全门禁或文档门禁
|
||||
- 忽略 OpenClaw 提交的 blocker
|
||||
- 未经 AIOS Owner 批准接受重大剩余风险
|
||||
requiredChecks:
|
||||
architecture:
|
||||
- AIOS 仍是唯一控制面
|
||||
- Agent Router 只承担调度
|
||||
- OpenClaw 与 Hermes 不拥有权威 Task Lifecycle
|
||||
- Web 不直接访问 Runtime
|
||||
tenancy:
|
||||
- 所有新资源和接口包含 tenant_id
|
||||
- 跨租户负向测试存在且通过
|
||||
- Runtime Result tenant/task/trace 校验存在
|
||||
security:
|
||||
- Git 中无明文 Secret
|
||||
- Secret 仅通过引用或受保护文件解析
|
||||
- 身份代理防伪边界明确
|
||||
quality:
|
||||
- 文档—代码匹配检查通过
|
||||
- 测试命令、exit code 和 pass/fail 有证据
|
||||
- 重启、健康检查和回滚演练有证据
|
||||
- 本地与 Gitea Candidate OID 一致
|
||||
documentation:
|
||||
- 用户需求已同步
|
||||
- 目标架构已同步
|
||||
- 模块契约已同步
|
||||
- 追踪矩阵已同步
|
||||
- ADR 已同步
|
||||
- 候选报告已同步
|
||||
blockerWorkflow:
|
||||
states: [new, analyzing, fix_proposed, fix_in_progress, verification, resolved, accepted_risk]
|
||||
requiredFields:
|
||||
- blocker_id
|
||||
- severity
|
||||
- affected_requirement
|
||||
- affected_module
|
||||
- reproduction
|
||||
- root_cause
|
||||
- proposed_fix
|
||||
- owner
|
||||
- patch_branch
|
||||
- verification
|
||||
- documentation_updates
|
||||
- exit_condition
|
||||
evidenceRequired:
|
||||
claim:
|
||||
fields: [task_id, executor, branch, candidate_commit, claimed_at]
|
||||
heartbeat:
|
||||
intervalSeconds: 300
|
||||
fields: [status, current_step, reviewed_commits, open_blockers, heartbeat_at]
|
||||
review:
|
||||
fields:
|
||||
- patch_branch
|
||||
- patch_commit
|
||||
- architecture_result
|
||||
- tenant_result
|
||||
- security_result
|
||||
- documentation_result
|
||||
- test_result
|
||||
- decision
|
||||
result:
|
||||
fields:
|
||||
- final_status
|
||||
- candidate_commit
|
||||
- reviewed_commits
|
||||
- resolved_blockers
|
||||
- open_blockers
|
||||
- accepted_risks
|
||||
- documentation_sync_status
|
||||
- test_evidence_status
|
||||
- preproduction_status
|
||||
- rollback_status
|
||||
- local_gitea_oid_status
|
||||
- final_recommendation
|
||||
acceptanceCommands:
|
||||
- python3 tools/aios_v2_docs_code_check.py --base-ref integration/aios-v2r1-cto-production-candidate-20260720
|
||||
- python3 -m unittest discover -s tests/aios_v2_candidate -p 'test_*.py' -v
|
||||
- bash deploy/aios-v2/acceptance/run-all.sh
|
||||
completionCriteria:
|
||||
- OpenClaw 部署与修复结果已完整审阅
|
||||
- 所有严重和高风险 blocker 已解决或由 Owner 明确接受
|
||||
- 文档、代码、测试和部署一致
|
||||
- Candidate 精确 Commit 的测试和预发布证据完整
|
||||
- 输出明确的进入下一 Gate、继续修复或停止发布建议
|
||||
@@ -0,0 +1,96 @@
|
||||
apiVersion: aios.v2/v1
|
||||
kind: AgentTask
|
||||
metadata:
|
||||
name: openclaw-production-deploy-task
|
||||
displayName: AIOS V2R1 OpenClaw 预发布部署与小型缺陷修复任务
|
||||
owner: AIOS-Control-Plane
|
||||
language: zh-CN
|
||||
spec:
|
||||
executor: openclaw
|
||||
role: deployment-operator
|
||||
candidateBranch: integration/aios-v2r1-cto-production-candidate-20260720
|
||||
taskBranch: task/openclaw/AIOS-V2R1-PRODUCTION-DEPLOY-20260720
|
||||
initialState: queued
|
||||
objective: >-
|
||||
在隔离预发布环境部署 AIOS V2R1 Candidate,执行健康检查、运行时联调、
|
||||
重启与回滚演练;对部署、配置、脚本和 Runtime 适配中的低风险缺陷进行小范围修复。
|
||||
inputs:
|
||||
- docs/aios-v2/
|
||||
- AIOS-V2R1-PRODUCTION-CANDIDATE.md
|
||||
- deploy/aios-v2/
|
||||
- active-runtime/app/aios_v2/
|
||||
- active-runtime/app/aios_openclaw/
|
||||
- active-runtime/app/aios_hermes/
|
||||
- tests/aios_v2_candidate/
|
||||
responsibilities:
|
||||
- 领取任务并写入 claim 证据
|
||||
- 每个主要步骤写入 heartbeat 和 progress
|
||||
- 安装或验证 systemd 部署
|
||||
- 构建或验证 Docker/Compose 部署
|
||||
- 配置非敏感环境变量和 Secret 引用
|
||||
- 执行文档与代码匹配检查
|
||||
- 执行候选测试和健康检查
|
||||
- 验证 SQLite 状态目录和重启恢复
|
||||
- 联调真实 OpenClaw Runtime 的 execute、status、cancel、timeout 和 health
|
||||
- 验证 Hermes Worker claim、heartbeat、complete、fail 和 lease recovery
|
||||
- 执行代码回滚和健康检查演练
|
||||
- 对低风险部署或 Runtime 缺陷创建 patch 分支并修复
|
||||
- 所有修改同步更新 docs/aios-v2/ 和追踪矩阵
|
||||
- 所有阻塞提交到 Execution Evidence,交由 Codex 监督任务统一审视
|
||||
prohibited:
|
||||
- 修改 AIOS 唯一控制面原则
|
||||
- 修改 Tenant、Policy、Approval 或 Task Lifecycle 权威边界
|
||||
- 绕过 GitOps 直接修改生产
|
||||
- 直接 push main 或创建生产 Tag
|
||||
- 提交 Token、密码、私钥、API Key 或签名材料
|
||||
- 在没有复现测试和文档更新时扩大修复范围
|
||||
- 对架构问题自行做不可逆决策
|
||||
lowRiskFixScope:
|
||||
- systemd 单元和文件权限
|
||||
- Dockerfile、Compose 和健康检查
|
||||
- 环境变量、路径和启动参数
|
||||
- 日志、错误消息和超时边界
|
||||
- Runtime Adapter 的小型兼容性缺陷
|
||||
- 测试、部署或文档中的明确错误
|
||||
escalation:
|
||||
architectureChange: Codex 监督任务
|
||||
controlPlaneChange: Codex 监督任务
|
||||
tenantIsolationIssue: Codex 监督任务和 AIOS Owner
|
||||
secretOrSecurityIssue: 立即停止并升级 AIOS Owner
|
||||
productionApproval: AIOS Owner
|
||||
evidenceRequired:
|
||||
claim:
|
||||
fields: [task_id, executor, branch, candidate_commit, claimed_at]
|
||||
heartbeat:
|
||||
intervalSeconds: 300
|
||||
fields: [status, current_step, progress, last_commit, heartbeat_at]
|
||||
blocker:
|
||||
fields: [blocker_id, severity, description, reproduction, owner, exit_condition]
|
||||
result:
|
||||
fields:
|
||||
- final_status
|
||||
- branch
|
||||
- commit
|
||||
- changed_files
|
||||
- test_commands
|
||||
- test_exit_codes
|
||||
- passed
|
||||
- failed
|
||||
- healthcheck
|
||||
- deployment_status
|
||||
- rollback_status
|
||||
- documentation_sync_status
|
||||
- remaining_risks
|
||||
acceptanceCommands:
|
||||
- python3 tools/aios_v2_docs_code_check.py --base-ref integration/aios-v2r1-cto-production-candidate-20260720
|
||||
- python3 -m unittest discover -s tests/aios_v2_candidate -p 'test_*.py' -v
|
||||
- bash deploy/aios-v2/acceptance/run-all.sh
|
||||
- bash deploy/aios-v2/healthcheck/check.sh
|
||||
completionCriteria:
|
||||
- 文档—代码检查通过
|
||||
- 候选自动测试通过
|
||||
- systemd 或 Docker 预发布部署成功
|
||||
- OpenClaw 与 Hermes 真实联调完成
|
||||
- 重启恢复和回滚演练完成
|
||||
- 所有缺陷、阻塞、提交和测试证据已回写
|
||||
- Codex 输出可进入下一 Gate 的监督结论
|
||||
@@ -0,0 +1,419 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import stat
|
||||
import sys
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
APP_ROOT = REPO_ROOT / "active-runtime" / "app"
|
||||
if str(APP_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(APP_ROOT))
|
||||
|
||||
from aios_hermes import HermesAdapter, HermesJobState, HermesWorker
|
||||
from aios_openclaw import (
|
||||
CommandState,
|
||||
Ed25519CommandSigner,
|
||||
InProcessRuntimeTransport,
|
||||
OpenClawAdapter,
|
||||
)
|
||||
from aios_v2 import (
|
||||
ControlPlaneService,
|
||||
ExecutionEvidence,
|
||||
ExecutionOrchestrator,
|
||||
ExecutionTracker,
|
||||
RequestContext,
|
||||
TaskState,
|
||||
TenantIsolationError,
|
||||
)
|
||||
from aios_v2.dispatch_store import DispatchState, SQLiteDispatchRepository
|
||||
from aios_v2.gateway import GatewayApplication
|
||||
from aios_v2.app import build_application
|
||||
from aios_v2.persistence import DurableControlPlaneService, SQLiteSnapshotRepository
|
||||
|
||||
|
||||
OPENCLAW_KEY_ID = "candidate-test-ed25519"
|
||||
OPENCLAW_PRIVATE_SEED = bytes(range(32))
|
||||
|
||||
|
||||
def context(
|
||||
tenant_id: str,
|
||||
principal: str,
|
||||
*roles: str,
|
||||
) -> RequestContext:
|
||||
return RequestContext.create(
|
||||
tenant_id=tenant_id,
|
||||
principal_id=principal,
|
||||
roles=roles,
|
||||
trace_id=f"trace-{tenant_id}-{principal}",
|
||||
)
|
||||
|
||||
|
||||
def bootstrap(service: ControlPlaneService, tenant_id: str = "tenant-a"):
|
||||
platform = context(tenant_id, "platform", "platform_admin")
|
||||
service.register_tenant(
|
||||
platform,
|
||||
tenant_id=tenant_id,
|
||||
display_name=tenant_id,
|
||||
)
|
||||
operator = context(
|
||||
tenant_id,
|
||||
"operator",
|
||||
"tenant_admin",
|
||||
"operator",
|
||||
"approver",
|
||||
"auditor",
|
||||
"runtime",
|
||||
)
|
||||
return platform, operator
|
||||
|
||||
|
||||
class CandidateFlowTests(unittest.TestCase):
|
||||
def test_rollback_entrypoints_are_executable_in_release_archive(self) -> None:
|
||||
for relative in (
|
||||
"deploy/aios-v2/rollback/rollback.sh",
|
||||
"deploy/aios-v2/healthcheck/check.sh",
|
||||
):
|
||||
mode = (REPO_ROOT / relative).stat().st_mode
|
||||
self.assertTrue(mode & stat.S_IXUSR, relative)
|
||||
|
||||
def test_rollback_waits_for_bounded_service_readiness(self) -> None:
|
||||
script = (REPO_ROOT / "deploy/aios-v2/rollback/rollback.sh").read_text()
|
||||
self.assertIn("AIOS_V2_ROLLBACK_HEALTH_RETRIES", script)
|
||||
self.assertIn("run_healthcheck", script)
|
||||
self.assertIn("HEALTH_RETRY_DELAY", script)
|
||||
|
||||
def test_build_application_propagates_openclaw_signing_key_id(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
material_path = Path(temp_dir) / "signing-material.bin"
|
||||
material_path.write_bytes(OPENCLAW_PRIVATE_SEED)
|
||||
material_path.chmod(0o600)
|
||||
values = {
|
||||
"AIOS_V2_STATE_DIR": temp_dir,
|
||||
"AIOS_OPENCLAW_URL": "http://127.0.0.1:18789",
|
||||
"AIOS_OPENCLAW_SIGNING_MATERIAL_FILE": str(material_path),
|
||||
"AIOS_OPENCLAW_SIGNING_KEY_ID": "openclaw-v2r1-candidate-ed25519",
|
||||
"AIOS_OPENCLAW_CREDENTIAL_REF": "secretref:test",
|
||||
}
|
||||
previous = {key: os.environ.get(key) for key in values}
|
||||
try:
|
||||
os.environ.update(values)
|
||||
application = build_application()
|
||||
finally:
|
||||
for key, value in previous.items():
|
||||
if value is None:
|
||||
os.environ.pop(key, None)
|
||||
else:
|
||||
os.environ[key] = value
|
||||
self.assertEqual(
|
||||
application.orchestrator.openclaw_key_id,
|
||||
"openclaw-v2r1-candidate-ed25519",
|
||||
)
|
||||
|
||||
def test_http_identity_headers_are_case_insensitive(self) -> None:
|
||||
request_context = GatewayApplication.context_from_headers(
|
||||
{
|
||||
"X-Aios-Authenticated": "true",
|
||||
"x-aios-tenant-id": "tenant-a",
|
||||
"X-AIOS-PRINCIPAL-ID": "operator-a",
|
||||
"X-Aios-Roles": "operator,auditor",
|
||||
"x-aios-trace-id": "trace-http-header-case",
|
||||
}
|
||||
)
|
||||
self.assertEqual(request_context.tenant_id, "tenant-a")
|
||||
self.assertEqual(request_context.principal_id, "operator-a")
|
||||
self.assertEqual(request_context.trace_id, "trace-http-header-case")
|
||||
self.assertEqual(
|
||||
request_context.roles, frozenset({"operator", "auditor"})
|
||||
)
|
||||
|
||||
def test_openclaw_full_flow_reconciles_completed_task(self) -> None:
|
||||
service = ControlPlaneService()
|
||||
_, operator = bootstrap(service)
|
||||
agent = service.register_agent(
|
||||
operator,
|
||||
agent_id="openclaw-agent",
|
||||
display_name="OpenClaw",
|
||||
runtime="openclaw",
|
||||
capabilities=("echo",),
|
||||
)
|
||||
task = service.create_task(
|
||||
operator,
|
||||
agent_id=agent.agent_id,
|
||||
action="echo",
|
||||
payload={"message": "hello"},
|
||||
idempotency_key="openclaw-flow-1",
|
||||
)
|
||||
approved = service.transition_task(
|
||||
operator,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.APPROVED,
|
||||
expected_revision=task.revision,
|
||||
)
|
||||
|
||||
signer = Ed25519CommandSigner.from_bytes(
|
||||
OPENCLAW_PRIVATE_SEED,
|
||||
key_id=OPENCLAW_KEY_ID,
|
||||
)
|
||||
transport = InProcessRuntimeTransport(
|
||||
lambda command: {
|
||||
"state": CommandState.COMPLETED.value,
|
||||
"output": {"echo": command.payload["message"]},
|
||||
}
|
||||
)
|
||||
adapter = OpenClawAdapter(
|
||||
transport,
|
||||
lambda tenant_id, key_id: signer.verifier(),
|
||||
)
|
||||
orchestrator = ExecutionOrchestrator(
|
||||
service,
|
||||
openclaw=adapter,
|
||||
openclaw_signing_material_resolver=(
|
||||
lambda tenant_id, key_id: signer
|
||||
),
|
||||
openclaw_key_id=OPENCLAW_KEY_ID,
|
||||
)
|
||||
|
||||
dispatch = orchestrator.dispatch(operator, task_id=approved.task_id)
|
||||
completed = service.get_task(operator, task.task_id)
|
||||
|
||||
self.assertEqual(dispatch.runtime, "openclaw")
|
||||
self.assertEqual(dispatch.state, DispatchState.COMPLETED)
|
||||
self.assertEqual(dispatch.principal_id, operator.principal_id)
|
||||
self.assertEqual(completed.state, TaskState.COMPLETED)
|
||||
self.assertEqual(completed.result, {"echo": "hello"})
|
||||
|
||||
def test_hermes_full_flow_reconciles_worker_result(self) -> None:
|
||||
service = ControlPlaneService()
|
||||
_, operator = bootstrap(service)
|
||||
agent = service.register_agent(
|
||||
operator,
|
||||
agent_id="hermes-agent",
|
||||
display_name="Hermes",
|
||||
runtime="hermes",
|
||||
capabilities=("transform",),
|
||||
metadata={"cell_id": "cell-a", "profile_id": "profile-a"},
|
||||
)
|
||||
task = service.create_task(
|
||||
operator,
|
||||
agent_id=agent.agent_id,
|
||||
action="transform",
|
||||
payload={"value": 7},
|
||||
idempotency_key="hermes-flow-1",
|
||||
)
|
||||
approved = service.transition_task(
|
||||
operator,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.APPROVED,
|
||||
expected_revision=task.revision,
|
||||
)
|
||||
|
||||
hermes = HermesAdapter(default_lease_seconds=10)
|
||||
orchestrator = ExecutionOrchestrator(service, hermes=hermes)
|
||||
dispatch = orchestrator.dispatch(operator, task_id=approved.task_id)
|
||||
self.assertEqual(dispatch.runtime, "hermes")
|
||||
self.assertEqual(dispatch.state, DispatchState.QUEUED)
|
||||
|
||||
worker = HermesWorker(
|
||||
hermes,
|
||||
lambda job: {"transformed": int(job.payload["value"]) * 2},
|
||||
worker_id="worker-a",
|
||||
tenant_id="tenant-a",
|
||||
cell_id="cell-a",
|
||||
profile_id="profile-a",
|
||||
heartbeat_seconds=0.05,
|
||||
)
|
||||
run = worker.run_once()
|
||||
self.assertTrue(run.claimed)
|
||||
self.assertEqual(run.state, HermesJobState.COMPLETED.value)
|
||||
|
||||
result = hermes.result(dispatch.runtime_execution_id, tenant_id="tenant-a")
|
||||
completed = orchestrator.reconcile_hermes(
|
||||
operator,
|
||||
result,
|
||||
dispatch_id=dispatch.dispatch_id,
|
||||
provenance_id=dispatch.provenance_id,
|
||||
run_id=dispatch.run_id,
|
||||
)
|
||||
self.assertEqual(completed.state, TaskState.COMPLETED)
|
||||
self.assertEqual(completed.result, {"transformed": 14})
|
||||
|
||||
def test_dispatch_and_control_plane_recover_before_hermes_reconcile(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as temporary:
|
||||
root = Path(temporary)
|
||||
control_path = root / "control-plane.sqlite3"
|
||||
dispatch_path = root / "dispatches.sqlite3"
|
||||
service = DurableControlPlaneService(SQLiteSnapshotRepository(control_path))
|
||||
_, operator = bootstrap(service)
|
||||
agent = service.register_agent(
|
||||
operator,
|
||||
agent_id="recoverable-hermes-agent",
|
||||
display_name="Recoverable Hermes",
|
||||
runtime="hermes",
|
||||
capabilities=("transform",),
|
||||
metadata={"cell_id": "cell-a", "profile_id": "profile-a"},
|
||||
)
|
||||
task = service.create_task(
|
||||
operator,
|
||||
agent_id=agent.agent_id,
|
||||
action="transform",
|
||||
payload={"value": 11},
|
||||
idempotency_key="dispatch-recovery-1",
|
||||
)
|
||||
approved = service.transition_task(
|
||||
operator,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.APPROVED,
|
||||
expected_revision=task.revision,
|
||||
)
|
||||
hermes = HermesAdapter(default_lease_seconds=10)
|
||||
first = ExecutionOrchestrator(
|
||||
service,
|
||||
hermes=hermes,
|
||||
dispatch_repository=SQLiteDispatchRepository(dispatch_path),
|
||||
)
|
||||
dispatch = first.dispatch(operator, task_id=approved.task_id)
|
||||
|
||||
worker = HermesWorker(
|
||||
hermes,
|
||||
lambda job: {"transformed": int(job.payload["value"]) * 3},
|
||||
worker_id="worker-recovery",
|
||||
tenant_id="tenant-a",
|
||||
cell_id="cell-a",
|
||||
profile_id="profile-a",
|
||||
heartbeat_seconds=0.05,
|
||||
)
|
||||
run = worker.run_once()
|
||||
self.assertTrue(run.claimed)
|
||||
|
||||
recovered_service = DurableControlPlaneService(
|
||||
SQLiteSnapshotRepository(control_path)
|
||||
)
|
||||
recovered_repository = SQLiteDispatchRepository(dispatch_path)
|
||||
restored_dispatch = recovered_repository.get(
|
||||
dispatch.dispatch_id,
|
||||
tenant_id="tenant-a",
|
||||
)
|
||||
self.assertEqual(restored_dispatch.runtime_execution_id, dispatch.runtime_execution_id)
|
||||
self.assertEqual(restored_dispatch.principal_id, operator.principal_id)
|
||||
|
||||
recovered = ExecutionOrchestrator(
|
||||
recovered_service,
|
||||
hermes=hermes,
|
||||
dispatch_repository=recovered_repository,
|
||||
)
|
||||
result = hermes.result(dispatch.runtime_execution_id, tenant_id="tenant-a")
|
||||
completed = recovered.reconcile_hermes(
|
||||
operator,
|
||||
result,
|
||||
dispatch_id=dispatch.dispatch_id,
|
||||
provenance_id=dispatch.provenance_id,
|
||||
run_id=dispatch.run_id,
|
||||
)
|
||||
self.assertEqual(completed.state, TaskState.COMPLETED)
|
||||
self.assertEqual(completed.result, {"transformed": 33})
|
||||
self.assertEqual(
|
||||
recovered_repository.get(
|
||||
dispatch.dispatch_id,
|
||||
tenant_id="tenant-a",
|
||||
).state,
|
||||
DispatchState.COMPLETED,
|
||||
)
|
||||
|
||||
def test_cross_tenant_task_read_is_denied(self) -> None:
|
||||
service = ControlPlaneService()
|
||||
_, tenant_a = bootstrap(service, "tenant-a")
|
||||
platform_b = context("tenant-b", "platform", "platform_admin")
|
||||
service.register_tenant(
|
||||
platform_b,
|
||||
tenant_id="tenant-b",
|
||||
display_name="Tenant B",
|
||||
)
|
||||
tenant_b = context("tenant-b", "auditor", "auditor")
|
||||
|
||||
agent = service.register_agent(
|
||||
tenant_a,
|
||||
agent_id="agent-a",
|
||||
display_name="Agent A",
|
||||
runtime="hermes",
|
||||
capabilities=("work",),
|
||||
)
|
||||
task = service.create_task(
|
||||
tenant_a,
|
||||
agent_id=agent.agent_id,
|
||||
action="work",
|
||||
payload={},
|
||||
idempotency_key="tenant-isolation-1",
|
||||
)
|
||||
|
||||
with self.assertRaises(TenantIsolationError):
|
||||
service.get_task(tenant_b, task.task_id)
|
||||
|
||||
def test_durable_service_recovers_state_after_restart(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as temporary:
|
||||
path = Path(temporary) / "state.sqlite3"
|
||||
service = DurableControlPlaneService(SQLiteSnapshotRepository(path))
|
||||
_, operator = bootstrap(service)
|
||||
agent = service.register_agent(
|
||||
operator,
|
||||
agent_id="persistent-agent",
|
||||
display_name="Persistent",
|
||||
runtime="hermes",
|
||||
capabilities=("persist",),
|
||||
)
|
||||
task = service.create_task(
|
||||
operator,
|
||||
agent_id=agent.agent_id,
|
||||
action="persist",
|
||||
payload={"ok": True},
|
||||
idempotency_key="persist-1",
|
||||
)
|
||||
|
||||
recovered = DurableControlPlaneService(SQLiteSnapshotRepository(path))
|
||||
restored_task = recovered.get_task(operator, task.task_id)
|
||||
self.assertEqual(restored_task.payload, {"ok": True})
|
||||
self.assertEqual(restored_task.state, TaskState.CREATED)
|
||||
|
||||
def test_execution_tracking_persists_claim_heartbeat_and_result(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as temporary:
|
||||
tracker = ExecutionTracker(temporary)
|
||||
claimed = tracker.claim(
|
||||
ExecutionEvidence(
|
||||
execution_id="exec-1",
|
||||
tenant_id="tenant-a",
|
||||
task_id="task-1",
|
||||
agent_id="agent-1",
|
||||
executor="codex",
|
||||
branch="task/codex/example",
|
||||
progress_total=3,
|
||||
)
|
||||
)
|
||||
self.assertEqual(claimed.status, "claimed")
|
||||
tracker.heartbeat(
|
||||
tenant_id="tenant-a",
|
||||
execution_id="exec-1",
|
||||
status="running",
|
||||
current_step="tests",
|
||||
progress_completed=2,
|
||||
last_commit="abc123",
|
||||
)
|
||||
tracker.complete(
|
||||
tenant_id="tenant-a",
|
||||
execution_id="exec-1",
|
||||
status="complete",
|
||||
test_status="passed",
|
||||
test_summary={"passed": 5, "failed": 0},
|
||||
)
|
||||
restored = ExecutionTracker(temporary).get(
|
||||
tenant_id="tenant-a",
|
||||
execution_id="exec-1",
|
||||
)
|
||||
self.assertEqual(restored.status, "complete")
|
||||
self.assertEqual(restored.progress_completed, 3)
|
||||
self.assertEqual(restored.test_summary["passed"], 5)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,440 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
import unittest
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
APP_ROOT = REPO_ROOT / "active-runtime" / "app"
|
||||
if str(APP_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(APP_ROOT))
|
||||
|
||||
from aios_v2.app import CandidateHTTPServer, build_application
|
||||
|
||||
|
||||
class HermesLiveLifecycleTests(unittest.TestCase):
|
||||
"""Exercise the real HTTP, SQLite dispatch and Hermes lifecycle boundary."""
|
||||
|
||||
tenant_id = "tenant-hermes-live"
|
||||
principal_id = "operator-hermes-live"
|
||||
trace_id = "trace-hermes-live"
|
||||
provenance_id = "provenance-hermes-live"
|
||||
run_id = "run-hermes-live"
|
||||
cell_id = "cell-hermes-live"
|
||||
profile_id = "profile-hermes-live"
|
||||
|
||||
def setUp(self) -> None:
|
||||
self.temporary = tempfile.TemporaryDirectory()
|
||||
self._saved_environment = {
|
||||
name: os.environ.get(name)
|
||||
for name in (
|
||||
"AIOS_V2_STATE_DIR",
|
||||
"AIOS_HERMES_LIFECYCLE_API_ENABLED",
|
||||
"AIOS_REQUIRE_RUN_PROVENANCE",
|
||||
"AIOS_OPENCLAW_URL",
|
||||
"AIOS_OPENCLAW_SIGNING_MATERIAL_FILE",
|
||||
)
|
||||
}
|
||||
os.environ["AIOS_V2_STATE_DIR"] = self.temporary.name
|
||||
os.environ["AIOS_HERMES_LIFECYCLE_API_ENABLED"] = "1"
|
||||
os.environ["AIOS_REQUIRE_RUN_PROVENANCE"] = "0"
|
||||
os.environ.pop("AIOS_OPENCLAW_URL", None)
|
||||
os.environ.pop("AIOS_OPENCLAW_SIGNING_MATERIAL_FILE", None)
|
||||
self._start_server()
|
||||
self._bootstrap()
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._stop_server()
|
||||
for name, value in self._saved_environment.items():
|
||||
if value is None:
|
||||
os.environ.pop(name, None)
|
||||
else:
|
||||
os.environ[name] = value
|
||||
self.temporary.cleanup()
|
||||
|
||||
def _start_server(self) -> None:
|
||||
self.application = build_application()
|
||||
self.server = CandidateHTTPServer(("127.0.0.1", 0), self.application)
|
||||
self.port = int(self.server.server_address[1])
|
||||
self.thread = threading.Thread(target=self.server.serve_forever, daemon=True)
|
||||
self.thread.start()
|
||||
|
||||
def _stop_server(self) -> None:
|
||||
if getattr(self, "server", None) is None:
|
||||
return
|
||||
self.server.shutdown()
|
||||
self.server.server_close()
|
||||
self.thread.join(timeout=5)
|
||||
self.server = None
|
||||
|
||||
def _restart_server(self) -> None:
|
||||
self._stop_server()
|
||||
self._start_server()
|
||||
|
||||
def _headers(self, **overrides: str) -> dict[str, str]:
|
||||
values = {
|
||||
"X-AIOS-Authenticated": "true",
|
||||
"X-AIOS-Tenant-ID": self.tenant_id,
|
||||
"X-AIOS-Principal-ID": self.principal_id,
|
||||
"X-AIOS-Trace-ID": self.trace_id,
|
||||
"X-AIOS-Roles": (
|
||||
"platform_admin,tenant_admin,operator,approver,auditor,runtime"
|
||||
),
|
||||
"X-AIOS-Provenance-ID": self.provenance_id,
|
||||
"X-AIOS-Run-ID": self.run_id,
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
values.update(overrides)
|
||||
return values
|
||||
|
||||
def _request(
|
||||
self,
|
||||
method: str,
|
||||
path: str,
|
||||
body: dict[str, object] | None = None,
|
||||
*,
|
||||
headers: dict[str, str] | None = None,
|
||||
) -> tuple[int, dict[str, object]]:
|
||||
encoded = json.dumps(body or {}, separators=(",", ":")).encode("utf-8")
|
||||
request = urllib.request.Request(
|
||||
f"http://127.0.0.1:{self.port}{path}",
|
||||
data=encoded if method == "POST" else None,
|
||||
method=method,
|
||||
headers=headers or self._headers(),
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=5) as response:
|
||||
return response.status, json.loads(response.read())
|
||||
except urllib.error.HTTPError as exc:
|
||||
return exc.code, json.loads(exc.read())
|
||||
|
||||
def _bootstrap(self) -> None:
|
||||
status, _ = self._request(
|
||||
"POST",
|
||||
"/api/v2/tenants",
|
||||
{"tenant_id": self.tenant_id, "display_name": "Hermes Live"},
|
||||
)
|
||||
self.assertEqual(status, 201)
|
||||
status, _ = self._request(
|
||||
"POST",
|
||||
"/api/v2/agents",
|
||||
{
|
||||
"agent_id": "hermes-live-agent",
|
||||
"display_name": "Hermes Live",
|
||||
"runtime": "hermes",
|
||||
"capabilities": ["transform"],
|
||||
"metadata": {
|
||||
"cell_id": self.cell_id,
|
||||
"profile_id": self.profile_id,
|
||||
},
|
||||
},
|
||||
)
|
||||
self.assertEqual(status, 201)
|
||||
|
||||
def _dispatch(self, suffix: str) -> dict[str, object]:
|
||||
status, created = self._request(
|
||||
"POST",
|
||||
"/api/v2/tasks",
|
||||
{
|
||||
"agent_id": "hermes-live-agent",
|
||||
"action": "transform",
|
||||
"payload": {"value": suffix},
|
||||
"idempotency_key": f"hermes-live-{suffix}",
|
||||
},
|
||||
)
|
||||
self.assertEqual(status, 201)
|
||||
task = created["task"]
|
||||
assert isinstance(task, dict)
|
||||
task_id = str(task["task_id"])
|
||||
status, approved = self._request(
|
||||
"POST",
|
||||
f"/api/v2/tasks/{task_id}/approve",
|
||||
{"expected_revision": task["revision"]},
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
approved_task = approved["task"]
|
||||
assert isinstance(approved_task, dict)
|
||||
status, response = self._request(
|
||||
"POST",
|
||||
f"/api/v2/tasks/{task_id}/dispatch",
|
||||
{
|
||||
"provenance_id": self.provenance_id,
|
||||
"run_id": self.run_id,
|
||||
},
|
||||
)
|
||||
self.assertEqual(status, 202)
|
||||
dispatch = response["dispatch"]
|
||||
assert isinstance(dispatch, dict)
|
||||
return dispatch
|
||||
|
||||
def _identity(self, dispatch: dict[str, object]) -> dict[str, object]:
|
||||
return {
|
||||
"dispatch_id": dispatch["dispatch_id"],
|
||||
"job_id": dispatch["runtime_execution_id"],
|
||||
"tenant_id": self.tenant_id,
|
||||
"task_id": dispatch["task_id"],
|
||||
"trace_id": self.trace_id,
|
||||
"principal_id": self.principal_id,
|
||||
"provenance_id": self.provenance_id,
|
||||
"run_id": self.run_id,
|
||||
"cell_id": self.cell_id,
|
||||
"profile_id": self.profile_id,
|
||||
}
|
||||
|
||||
def _lifecycle(
|
||||
self,
|
||||
action: str,
|
||||
identity: dict[str, object],
|
||||
**values: object,
|
||||
) -> tuple[int, dict[str, object]]:
|
||||
body = dict(identity)
|
||||
body.update(values)
|
||||
return self._request(
|
||||
"POST",
|
||||
f"/api/v2/internal/runtime/hermes/lifecycle/{action}",
|
||||
body,
|
||||
)
|
||||
|
||||
def _claim_start(self, suffix: str, worker_id: str = "worker-a"):
|
||||
dispatch = self._dispatch(suffix)
|
||||
identity = self._identity(dispatch)
|
||||
status, claimed = self._lifecycle(
|
||||
"claim", identity, worker_id=worker_id, lease_seconds=5
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
job = claimed["job"]
|
||||
assert isinstance(job, dict)
|
||||
status, started = self._lifecycle(
|
||||
"start",
|
||||
identity,
|
||||
worker_id=worker_id,
|
||||
expected_revision=job["revision"],
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
return dispatch, identity, started["job"]
|
||||
|
||||
def test_01_claim(self) -> None:
|
||||
dispatch = self._dispatch("claim")
|
||||
status, payload = self._lifecycle(
|
||||
"claim", self._identity(dispatch), worker_id="worker-claim"
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["job"]["state"], "CLAIMED")
|
||||
self.assertEqual(payload["dispatch"]["expected_worker_id"], "worker-claim")
|
||||
|
||||
def test_02_start(self) -> None:
|
||||
_, _, job = self._claim_start("start")
|
||||
self.assertEqual(job["state"], "RUNNING")
|
||||
|
||||
def test_03_heartbeat(self) -> None:
|
||||
_, identity, job = self._claim_start("heartbeat")
|
||||
status, payload = self._lifecycle(
|
||||
"heartbeat", identity, worker_id="worker-a", lease_seconds=5
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertGreater(payload["job"]["revision"], job["revision"])
|
||||
|
||||
def test_04_complete(self) -> None:
|
||||
_, identity, _ = self._claim_start("complete")
|
||||
status, payload = self._lifecycle(
|
||||
"complete", identity, worker_id="worker-a", output={"ok": True}
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["task"]["state"], "COMPLETED")
|
||||
self.assertEqual(payload["dispatch"]["state"], "COMPLETED")
|
||||
|
||||
def test_05_fail(self) -> None:
|
||||
_, identity, _ = self._claim_start("fail")
|
||||
status, payload = self._lifecycle(
|
||||
"fail", identity, worker_id="worker-a", error={"code": "expected"}
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["task"]["state"], "FAILED")
|
||||
|
||||
def test_06_cancel(self) -> None:
|
||||
dispatch = self._dispatch("cancel")
|
||||
identity = self._identity(dispatch)
|
||||
runtime_only = self._headers(**{"X-AIOS-Roles": "runtime"})
|
||||
status, _ = self._request(
|
||||
"POST",
|
||||
"/api/v2/internal/runtime/hermes/lifecycle/cancel",
|
||||
{**identity, "cancellation_source": "aios-control-plane"},
|
||||
headers=runtime_only,
|
||||
)
|
||||
self.assertEqual(status, 401)
|
||||
status, _ = self._lifecycle(
|
||||
"cancel",
|
||||
identity,
|
||||
worker_id="worker-must-not-cancel",
|
||||
cancellation_source="aios-control-plane",
|
||||
)
|
||||
self.assertEqual(status, 401)
|
||||
status, payload = self._lifecycle(
|
||||
"cancel", identity, cancellation_source="aios-control-plane"
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["task"]["state"], "CANCELLED")
|
||||
|
||||
def test_07_lease_expiry(self) -> None:
|
||||
dispatch = self._dispatch("expiry")
|
||||
identity = self._identity(dispatch)
|
||||
status, _ = self._lifecycle(
|
||||
"claim", identity, worker_id="worker-expired", lease_seconds=5
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
time.sleep(5.1)
|
||||
status, payload = self._lifecycle("status", identity)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["job"]["state"], "QUEUED")
|
||||
self.assertIsNone(payload["job"]["assigned_worker_id"])
|
||||
|
||||
def test_08_requeue_to_new_worker(self) -> None:
|
||||
dispatch = self._dispatch("requeue")
|
||||
identity = self._identity(dispatch)
|
||||
self.assertEqual(
|
||||
self._lifecycle(
|
||||
"claim", identity, worker_id="worker-old", lease_seconds=5
|
||||
)[0],
|
||||
200,
|
||||
)
|
||||
time.sleep(5.1)
|
||||
status, payload = self._lifecycle(
|
||||
"claim", identity, worker_id="worker-new", lease_seconds=5
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["job"]["assigned_worker_id"], "worker-new")
|
||||
self.assertEqual(payload["dispatch"]["expected_worker_id"], "worker-new")
|
||||
|
||||
def test_09_crash_recovery_preserves_running_job(self) -> None:
|
||||
_, identity, _ = self._claim_start("crash")
|
||||
self._restart_server()
|
||||
status, payload = self._lifecycle("status", identity)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["job"]["state"], "RUNNING")
|
||||
self.assertEqual(payload["dispatch"]["state"], "QUEUED")
|
||||
self.assertEqual(payload["task"]["state"], "RUNNING")
|
||||
|
||||
def test_10_cell_and_profile_isolation(self) -> None:
|
||||
dispatch = self._dispatch("isolation")
|
||||
identity = self._identity(dispatch)
|
||||
for field in ("cell_id", "profile_id"):
|
||||
bad = dict(identity)
|
||||
bad[field] = f"wrong-{field}"
|
||||
with self.subTest(field=field):
|
||||
self.assertEqual(
|
||||
self._lifecycle("claim", bad, worker_id="worker-a")[0], 400
|
||||
)
|
||||
self.assertEqual(self._lifecycle("status", identity)[1]["job"]["state"], "QUEUED")
|
||||
|
||||
def test_11_wrong_lease_owner(self) -> None:
|
||||
dispatch = self._dispatch("wrong-owner")
|
||||
identity = self._identity(dispatch)
|
||||
self.assertEqual(
|
||||
self._lifecycle("claim", identity, worker_id="worker-owner")[0], 200
|
||||
)
|
||||
status, _ = self._lifecycle("start", identity, worker_id="worker-other")
|
||||
self.assertEqual(status, 409)
|
||||
|
||||
def test_12_mismatched_identity_tuple(self) -> None:
|
||||
dispatch = self._dispatch("identity")
|
||||
identity = self._identity(dispatch)
|
||||
for field in (
|
||||
"tenant_id",
|
||||
"task_id",
|
||||
"trace_id",
|
||||
"principal_id",
|
||||
"provenance_id",
|
||||
"run_id",
|
||||
"dispatch_id",
|
||||
"job_id",
|
||||
):
|
||||
bad = dict(identity)
|
||||
bad[field] = f"wrong-{field}"
|
||||
with self.subTest(field=field):
|
||||
status, _ = self._lifecycle("status", bad)
|
||||
self.assertIn(status, {400, 404, 409})
|
||||
|
||||
def test_13_same_terminal_result_is_idempotent(self) -> None:
|
||||
_, identity, _ = self._claim_start("same-terminal")
|
||||
values = {"worker_id": "worker-a", "output": {"stable": True}}
|
||||
first = self._lifecycle("complete", identity, **values)
|
||||
second = self._lifecycle("complete", identity, **values)
|
||||
self.assertEqual(first[0], 200)
|
||||
self.assertEqual(second[0], 200)
|
||||
self.assertEqual(first[1]["result"], second[1]["result"])
|
||||
|
||||
def test_14_different_terminal_result_conflicts(self) -> None:
|
||||
_, identity, _ = self._claim_start("different-terminal")
|
||||
self.assertEqual(
|
||||
self._lifecycle(
|
||||
"complete", identity, worker_id="worker-a", output={"v": 1}
|
||||
)[0],
|
||||
200,
|
||||
)
|
||||
status, _ = self._lifecycle(
|
||||
"fail", identity, worker_id="worker-a", error={"code": "different"}
|
||||
)
|
||||
self.assertEqual(status, 409)
|
||||
|
||||
def test_15_full_state_consistency(self) -> None:
|
||||
_, identity, _ = self._claim_start("consistency")
|
||||
self.assertEqual(
|
||||
self._lifecycle(
|
||||
"complete", identity, worker_id="worker-a", output={"ok": True}
|
||||
)[0],
|
||||
200,
|
||||
)
|
||||
status, payload = self._lifecycle("status", identity)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["job"]["state"], "COMPLETED")
|
||||
self.assertEqual(payload["dispatch"]["state"], "COMPLETED")
|
||||
self.assertEqual(payload["task"]["state"], "COMPLETED")
|
||||
self.assertEqual(payload["result"]["state"], "COMPLETED")
|
||||
status, executions = self._request("GET", "/api/v2/executions")
|
||||
self.assertEqual(status, 200)
|
||||
matching = [
|
||||
item
|
||||
for item in executions["executions"]
|
||||
if item["execution_id"] == identity["job_id"]
|
||||
]
|
||||
self.assertEqual(len(matching), 1)
|
||||
self.assertEqual(matching[0]["status"], "completed")
|
||||
self.assertEqual(matching[0]["provenance_id"], self.provenance_id)
|
||||
self.assertEqual(matching[0]["run_id"], self.run_id)
|
||||
status, audit = self._request("GET", "/api/v2/audit")
|
||||
self.assertEqual(status, 200)
|
||||
actions = {
|
||||
item["action"]
|
||||
for item in audit["events"]
|
||||
if item["resource_id"] == identity["job_id"]
|
||||
}
|
||||
self.assertTrue({"HERMES_CLAIM", "HERMES_START", "HERMES_COMPLETE"} <= actions)
|
||||
|
||||
def test_16_restart_then_reconcile(self) -> None:
|
||||
_, identity, _ = self._claim_start("restart-reconcile")
|
||||
self._restart_server()
|
||||
status, payload = self._lifecycle(
|
||||
"complete", identity, worker_id="worker-a", output={"recovered": True}
|
||||
)
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(payload["task"]["state"], "COMPLETED")
|
||||
|
||||
def test_17_lifecycle_api_disabled_fail_closed(self) -> None:
|
||||
dispatch = self._dispatch("disabled")
|
||||
identity = self._identity(dispatch)
|
||||
self._stop_server()
|
||||
os.environ["AIOS_HERMES_LIFECYCLE_API_ENABLED"] = "0"
|
||||
self._start_server()
|
||||
status, _ = self._lifecycle("status", identity)
|
||||
self.assertEqual(status, 404)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,383 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
import tempfile
|
||||
import unittest
|
||||
from dataclasses import replace
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
|
||||
APP_ROOT = Path(__file__).resolve().parents[2] / "active-runtime" / "app"
|
||||
if str(APP_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(APP_ROOT))
|
||||
|
||||
from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
|
||||
|
||||
from aios_hermes import HermesAdapter
|
||||
from aios_v2 import (
|
||||
ControlPlaneService,
|
||||
Ed25519PrivateKeySigner,
|
||||
ExecutionEvidence,
|
||||
ExecutionOrchestrator,
|
||||
ExecutionPath,
|
||||
ExecutionTracker,
|
||||
GitExecutionContext,
|
||||
GitOperation,
|
||||
OperationContext,
|
||||
OrchestrationError,
|
||||
PRODUCTION_POLICY_VERSION,
|
||||
ProvenanceControlledWriter,
|
||||
ProvenanceDenied,
|
||||
ProvenanceExpired,
|
||||
ProvenanceGitError,
|
||||
ProvenanceGitWriter,
|
||||
ProvenanceIssuer,
|
||||
ProvenanceOperationGate,
|
||||
ProvenanceReplay,
|
||||
ProvenanceRevoked,
|
||||
ProvenanceSignatureError,
|
||||
ProvenanceStatus,
|
||||
ProvenanceVerifier,
|
||||
RequestContext,
|
||||
RunProvenance,
|
||||
SQLiteProvenanceStore,
|
||||
TaskState,
|
||||
digest_payload,
|
||||
)
|
||||
|
||||
|
||||
class ProvenanceTestCase(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.temp = tempfile.TemporaryDirectory()
|
||||
self.root = Path(self.temp.name)
|
||||
self.store_path = self.root / "provenance.sqlite3"
|
||||
self.store = SQLiteProvenanceStore(self.store_path)
|
||||
self.signer = Ed25519PrivateKeySigner(
|
||||
Ed25519PrivateKey.generate(),
|
||||
key_id="owner-ed25519-test",
|
||||
)
|
||||
self.verifier = self.signer.public_verifier()
|
||||
self.issuer = ProvenanceIssuer(self.signer, self.store)
|
||||
self.writer = ProvenanceControlledWriter(
|
||||
ProvenanceVerifier(self.store, {self.verifier.key_id: self.verifier}),
|
||||
self.root / "receipts",
|
||||
)
|
||||
self.context = OperationContext(
|
||||
provenance_id="placeholder",
|
||||
run_id="run-001",
|
||||
tenant_id="tenant-a",
|
||||
task_id="task-001",
|
||||
agent_id="agent-001",
|
||||
principal_id="owner-001",
|
||||
)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
try:
|
||||
self.store.close()
|
||||
finally:
|
||||
self.temp.cleanup()
|
||||
|
||||
def issue(
|
||||
self,
|
||||
*,
|
||||
ttl_seconds: int = 3600,
|
||||
now: datetime | None = None,
|
||||
allowed_git_operations: tuple[str, ...] | None = None,
|
||||
) -> RunProvenance:
|
||||
provenance = self.issuer.issue(
|
||||
run_id=self.context.run_id,
|
||||
issuer="aios-owner",
|
||||
tenant_id=self.context.tenant_id,
|
||||
task_id=self.context.task_id,
|
||||
agent_id=self.context.agent_id,
|
||||
principal_id=self.context.principal_id,
|
||||
allowed_git_operations=(
|
||||
allowed_git_operations
|
||||
if allowed_git_operations is not None
|
||||
else tuple(item.value for item in GitOperation)
|
||||
),
|
||||
ttl_seconds=ttl_seconds,
|
||||
now=now,
|
||||
)
|
||||
self.context = replace(self.context, provenance_id=provenance.provenance_id)
|
||||
return provenance
|
||||
|
||||
def authorization_values(self, request: dict[str, object]) -> dict[str, str]:
|
||||
return {
|
||||
"provenance_id": self.context.provenance_id,
|
||||
"run_id": self.context.run_id,
|
||||
"tenant_id": self.context.tenant_id,
|
||||
"task_id": self.context.task_id,
|
||||
"agent_id": self.context.agent_id,
|
||||
"principal_id": self.context.principal_id,
|
||||
"request_digest": digest_payload(request),
|
||||
}
|
||||
|
||||
def test_issue_verify_use_and_restart_recovery(self) -> None:
|
||||
provenance = self.issue()
|
||||
self.assertEqual(
|
||||
self.store.status(provenance.provenance_id), ProvenanceStatus.ISSUED
|
||||
)
|
||||
receipt = ProvenanceOperationGate(self.writer).authorize(
|
||||
self.context,
|
||||
execution_path=ExecutionPath.DEPLOYMENT.value,
|
||||
operation="candidate-deploy",
|
||||
request={"release": "v2r1-candidate", "target": "staging"},
|
||||
)
|
||||
self.assertTrue(receipt.authorization_id.startswith("pauth_"))
|
||||
self.assertEqual(
|
||||
self.store.status(provenance.provenance_id), ProvenanceStatus.USED
|
||||
)
|
||||
self.assertEqual(self.store.authorization_count(provenance.provenance_id), 1)
|
||||
self.store.close()
|
||||
self.store = SQLiteProvenanceStore(self.store_path)
|
||||
self.assertEqual(
|
||||
self.store.status(provenance.provenance_id), ProvenanceStatus.USED
|
||||
)
|
||||
self.assertEqual(self.store.authorization_count(provenance.provenance_id), 1)
|
||||
event_types = [
|
||||
item["event_type"] for item in self.store.events(provenance.provenance_id)
|
||||
]
|
||||
self.assertIn("issued", event_types)
|
||||
self.assertIn("verified", event_types)
|
||||
self.assertIn("used", event_types)
|
||||
|
||||
def test_tampered_payload_is_rejected(self) -> None:
|
||||
provenance = self.issue()
|
||||
tampered = replace(
|
||||
provenance,
|
||||
provenance_id="prov_tampered",
|
||||
tenant_id="tenant-b",
|
||||
)
|
||||
self.store.save_issued(tampered)
|
||||
with self.assertRaises(ProvenanceSignatureError):
|
||||
self.writer.authorize_deployment(
|
||||
provenance_id=tampered.provenance_id,
|
||||
run_id=tampered.run_id,
|
||||
tenant_id=tampered.tenant_id,
|
||||
task_id=tampered.task_id,
|
||||
agent_id=tampered.agent_id,
|
||||
principal_id=tampered.principal_id,
|
||||
request_digest=digest_payload({"operation": "tamper-test"}),
|
||||
)
|
||||
|
||||
def test_expired_provenance_is_marked_and_rejected(self) -> None:
|
||||
issued_at = datetime(2026, 7, 20, tzinfo=timezone.utc)
|
||||
provenance = self.issue(ttl_seconds=1, now=issued_at)
|
||||
verifier = ProvenanceVerifier(
|
||||
self.store, {self.verifier.key_id: self.verifier}
|
||||
)
|
||||
with self.assertRaises(ProvenanceExpired):
|
||||
verifier.authorize(
|
||||
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=ExecutionPath.DEPLOYMENT.value,
|
||||
request_digest=digest_payload({"operation": "expired"}),
|
||||
now=issued_at + timedelta(seconds=2),
|
||||
)
|
||||
self.assertEqual(
|
||||
self.store.status(provenance.provenance_id), ProvenanceStatus.EXPIRED
|
||||
)
|
||||
|
||||
def test_revoked_provenance_is_rejected(self) -> None:
|
||||
provenance = self.issue()
|
||||
self.store.revoke(
|
||||
provenance.provenance_id,
|
||||
reason="owner emergency stop",
|
||||
principal_id=self.context.principal_id,
|
||||
)
|
||||
with self.assertRaises(ProvenanceRevoked):
|
||||
self.writer.authorize_rollback(
|
||||
**self.authorization_values({"operation": "rollback"})
|
||||
)
|
||||
self.assertEqual(
|
||||
self.store.status(provenance.provenance_id), ProvenanceStatus.REVOKED
|
||||
)
|
||||
|
||||
def test_identical_authorization_replay_is_rejected(self) -> None:
|
||||
self.issue()
|
||||
values = self.authorization_values({"operation": "deploy", "release": "r1"})
|
||||
self.writer.authorize_deployment(**values)
|
||||
with self.assertRaises(ProvenanceReplay):
|
||||
self.writer.authorize_deployment(**values)
|
||||
|
||||
def test_production_policy_requires_all_seven_paths(self) -> None:
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
self.issuer.issue(
|
||||
run_id=self.context.run_id,
|
||||
issuer="aios-owner",
|
||||
tenant_id=self.context.tenant_id,
|
||||
task_id=self.context.task_id,
|
||||
agent_id=self.context.agent_id,
|
||||
principal_id=self.context.principal_id,
|
||||
allowed_paths=(ExecutionPath.RUNTIME_EXECUTE.value,),
|
||||
allowed_git_operations=(),
|
||||
policy_version=PRODUCTION_POLICY_VERSION,
|
||||
)
|
||||
|
||||
def test_context_mismatch_is_rejected(self) -> None:
|
||||
self.issue()
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
self.writer.authorize_runtime_execute(
|
||||
provenance_id=self.context.provenance_id,
|
||||
run_id=self.context.run_id,
|
||||
tenant_id="tenant-b",
|
||||
task_id=self.context.task_id,
|
||||
agent_id=self.context.agent_id,
|
||||
principal_id=self.context.principal_id,
|
||||
request_digest=digest_payload({"operation": "runtime"}),
|
||||
)
|
||||
|
||||
def test_evidence_requires_provenance_and_persists_receipt(self) -> None:
|
||||
self.issue()
|
||||
tracker = ExecutionTracker(
|
||||
self.root / "evidence",
|
||||
provenance_writer=self.writer,
|
||||
require_provenance=True,
|
||||
)
|
||||
evidence = ExecutionEvidence(
|
||||
execution_id="exec-001",
|
||||
tenant_id=self.context.tenant_id,
|
||||
task_id=self.context.task_id,
|
||||
agent_id=self.context.agent_id,
|
||||
executor="openclaw",
|
||||
branch="task/openclaw/provenance-test",
|
||||
provenance_id=self.context.provenance_id,
|
||||
run_id=self.context.run_id,
|
||||
)
|
||||
with self.assertRaises(RuntimeError):
|
||||
tracker.claim(evidence)
|
||||
claimed = tracker.claim(
|
||||
evidence,
|
||||
principal_id=self.context.principal_id,
|
||||
)
|
||||
self.assertIsNotNone(claimed.last_authorization_id)
|
||||
heartbeat = tracker.heartbeat(
|
||||
tenant_id=self.context.tenant_id,
|
||||
execution_id=evidence.execution_id,
|
||||
status="running",
|
||||
current_step="test",
|
||||
progress_completed=1,
|
||||
progress_total=2,
|
||||
principal_id=self.context.principal_id,
|
||||
)
|
||||
self.assertEqual(heartbeat.status, "running")
|
||||
completed = tracker.complete(
|
||||
tenant_id=self.context.tenant_id,
|
||||
execution_id=evidence.execution_id,
|
||||
status="complete",
|
||||
test_status="passed",
|
||||
test_summary={"passed": 1, "failed": 0},
|
||||
result_summary={"result": "ok"},
|
||||
principal_id=self.context.principal_id,
|
||||
)
|
||||
self.assertEqual(completed.status, "complete")
|
||||
self.assertEqual(completed.progress_completed, completed.progress_total)
|
||||
|
||||
def test_runtime_dispatch_without_provenance_is_denied_before_running(self) -> None:
|
||||
self.issue()
|
||||
service = ControlPlaneService()
|
||||
request = RequestContext(
|
||||
tenant_id=self.context.tenant_id,
|
||||
principal_id=self.context.principal_id,
|
||||
roles=frozenset({"platform_admin", "tenant_admin", "operator", "approver"}),
|
||||
trace_id="trace-prov-runtime",
|
||||
session_id="session-prov-runtime",
|
||||
policy_version="policy-v1",
|
||||
)
|
||||
service.register_tenant(
|
||||
request,
|
||||
tenant_id=self.context.tenant_id,
|
||||
display_name="Tenant A",
|
||||
)
|
||||
agent = service.register_agent(
|
||||
request,
|
||||
agent_id=self.context.agent_id,
|
||||
display_name="Hermes Agent",
|
||||
runtime="hermes",
|
||||
capabilities=("build",),
|
||||
metadata={"cell_id": "cell-a", "profile_id": "profile-a"},
|
||||
)
|
||||
task = service.create_task(
|
||||
request,
|
||||
agent_id=agent.agent_id,
|
||||
action="build",
|
||||
payload={"target": "candidate"},
|
||||
idempotency_key="prov-runtime-001",
|
||||
)
|
||||
task = service.transition_task(
|
||||
request,
|
||||
task_id=task.task_id,
|
||||
target_state=TaskState.APPROVED,
|
||||
expected_revision=task.revision,
|
||||
)
|
||||
orchestrator = ExecutionOrchestrator(
|
||||
service,
|
||||
hermes=HermesAdapter(),
|
||||
provenance_writer=self.writer,
|
||||
require_provenance=True,
|
||||
)
|
||||
with self.assertRaises(OrchestrationError):
|
||||
orchestrator.dispatch(request, task_id=task.task_id)
|
||||
self.assertEqual(service.get_task(request, task.task_id).state.value, "APPROVED")
|
||||
|
||||
def test_git_writer_rejects_main_fetch_to_local_branch_and_unallowed_operation(self) -> None:
|
||||
self.issue(allowed_git_operations=(GitOperation.READ_REF.value,))
|
||||
repo = self.root / "repo"
|
||||
repo.mkdir()
|
||||
import subprocess
|
||||
|
||||
subprocess.run(["git", "init", str(repo)], check=True, capture_output=True)
|
||||
subprocess.run(
|
||||
["git", "-C", str(repo), "config", "user.name", "AIOS Test"],
|
||||
check=True,
|
||||
)
|
||||
subprocess.run(
|
||||
["git", "-C", str(repo), "config", "user.email", "aios@example.invalid"],
|
||||
check=True,
|
||||
)
|
||||
(repo / "README.md").write_text("test\n", encoding="utf-8")
|
||||
subprocess.run(["git", "-C", str(repo), "add", "README.md"], check=True)
|
||||
subprocess.run(
|
||||
["git", "-C", str(repo), "commit", "-m", "initial"], check=True,
|
||||
capture_output=True,
|
||||
)
|
||||
writer = ProvenanceGitWriter(repo, self.writer)
|
||||
git_context = GitExecutionContext(**self.context.as_dict())
|
||||
with self.assertRaises(ProvenanceGitError):
|
||||
writer.push(git_context, remote="origin", branch="main")
|
||||
with self.assertRaises(ProvenanceGitError):
|
||||
writer.fetch(
|
||||
git_context,
|
||||
remote="origin",
|
||||
refspecs=("+refs/heads/x:refs/heads/x",),
|
||||
)
|
||||
with self.assertRaises(ProvenanceGitError):
|
||||
writer.create_branch(git_context, branch="patch/test", start_point="HEAD")
|
||||
|
||||
def test_deployment_and_rollback_are_separate_authorizations(self) -> None:
|
||||
self.issue()
|
||||
gate = ProvenanceOperationGate(self.writer)
|
||||
deployment = gate.authorize(
|
||||
self.context,
|
||||
execution_path=ExecutionPath.DEPLOYMENT.value,
|
||||
operation="systemd-restart",
|
||||
request={"service": "aios-v2"},
|
||||
)
|
||||
rollback = gate.authorize(
|
||||
self.context,
|
||||
execution_path=ExecutionPath.ROLLBACK.value,
|
||||
operation="release-rollback",
|
||||
request={"target": "previous"},
|
||||
)
|
||||
self.assertNotEqual(deployment.authorization_id, rollback.authorization_id)
|
||||
self.assertEqual(deployment.execution_path, ExecutionPath.DEPLOYMENT.value)
|
||||
self.assertEqual(rollback.execution_path, ExecutionPath.ROLLBACK.value)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,281 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
import tempfile
|
||||
import unittest
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
|
||||
APP_ROOT = Path(__file__).resolve().parents[2] / "active-runtime" / "app"
|
||||
if str(APP_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(APP_ROOT))
|
||||
|
||||
from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
|
||||
|
||||
from aios_v2.provenance import (
|
||||
Ed25519PrivateKeySigner,
|
||||
ExecutionPath,
|
||||
GitOperation,
|
||||
ProvenanceDenied,
|
||||
ProvenanceExpired,
|
||||
ProvenanceReplay,
|
||||
ProvenanceRevoked,
|
||||
ProvenanceVerifier,
|
||||
SQLiteProvenanceStore,
|
||||
digest_payload,
|
||||
)
|
||||
from aios_v2.provenance_grants import (
|
||||
GrantIssuer,
|
||||
GrantType,
|
||||
GrantVerifier,
|
||||
SQLiteGrantStore,
|
||||
WorkflowProvenanceIssuer,
|
||||
)
|
||||
from aios_v2.provenance_scoped import ScopedLeastPrivilegeProvenanceWriter
|
||||
|
||||
|
||||
class ProvenanceGrantIsolationTests(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.temporary = tempfile.TemporaryDirectory()
|
||||
self.root = Path(self.temporary.name)
|
||||
self.store_file = self.root / "provenance.sqlite3"
|
||||
self.parent_store = SQLiteProvenanceStore(self.store_file)
|
||||
self.grant_store = SQLiteGrantStore(self.store_file)
|
||||
self.signer = Ed25519PrivateKeySigner(
|
||||
Ed25519PrivateKey.generate(),
|
||||
key_id="grant-isolation-key",
|
||||
)
|
||||
self.public_verifier = self.signer.public_verifier()
|
||||
self.workflow = WorkflowProvenanceIssuer(
|
||||
self.signer,
|
||||
self.parent_store,
|
||||
).issue(
|
||||
run_id="run-grant-001",
|
||||
issuer="aios-owner",
|
||||
tenant_id="tenant-a",
|
||||
task_id="task-a",
|
||||
agent_id="agent-a",
|
||||
principal_id="owner-a",
|
||||
ttl_seconds=3600,
|
||||
)
|
||||
self.grant_issuer = GrantIssuer(
|
||||
self.signer,
|
||||
self.parent_store,
|
||||
self.grant_store,
|
||||
)
|
||||
self.grant_verifier = GrantVerifier(
|
||||
self.parent_store,
|
||||
self.grant_store,
|
||||
{self.public_verifier.key_id: self.public_verifier},
|
||||
)
|
||||
self.values = {
|
||||
"provenance_id": self.workflow.provenance_id,
|
||||
"run_id": self.workflow.run_id,
|
||||
"tenant_id": self.workflow.tenant_id,
|
||||
"task_id": self.workflow.task_id,
|
||||
"agent_id": self.workflow.agent_id,
|
||||
"principal_id": self.workflow.principal_id,
|
||||
}
|
||||
|
||||
def tearDown(self) -> None:
|
||||
try:
|
||||
self.grant_store.close()
|
||||
finally:
|
||||
try:
|
||||
self.parent_store.close()
|
||||
finally:
|
||||
self.temporary.cleanup()
|
||||
|
||||
def issue_grant(
|
||||
self,
|
||||
grant_type: GrantType,
|
||||
*,
|
||||
ttl_seconds: int = 900,
|
||||
allowed_git_operations: tuple[str, ...] = (),
|
||||
now: datetime | None = None,
|
||||
):
|
||||
return self.grant_issuer.issue(
|
||||
parent_provenance_id=self.workflow.provenance_id,
|
||||
grant_type=grant_type,
|
||||
ttl_seconds=ttl_seconds,
|
||||
allowed_git_operations=allowed_git_operations,
|
||||
now=now,
|
||||
)
|
||||
|
||||
def writer(self, path: ExecutionPath, grant_id: str):
|
||||
return ScopedLeastPrivilegeProvenanceWriter(
|
||||
self.grant_verifier,
|
||||
self.root / "receipts",
|
||||
{path.value: grant_id},
|
||||
required_paths=(path.value,),
|
||||
writer_id=f"test-{path.value}-writer",
|
||||
)
|
||||
|
||||
def authorization_values(self, label: str) -> dict[str, str]:
|
||||
return {
|
||||
**self.values,
|
||||
"request_digest": digest_payload({"operation": label}),
|
||||
}
|
||||
|
||||
def test_parent_workflow_has_no_operational_rights(self) -> None:
|
||||
verifier = ProvenanceVerifier(
|
||||
self.parent_store,
|
||||
{self.public_verifier.key_id: self.public_verifier},
|
||||
)
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
verifier.authorize(
|
||||
provenance_id=self.workflow.provenance_id,
|
||||
run_id=self.workflow.run_id,
|
||||
tenant_id=self.workflow.tenant_id,
|
||||
task_id=self.workflow.task_id,
|
||||
agent_id=self.workflow.agent_id,
|
||||
principal_id=self.workflow.principal_id,
|
||||
execution_path=ExecutionPath.RUNTIME_EXECUTE.value,
|
||||
request_digest=digest_payload({"operation": "parent-runtime"}),
|
||||
)
|
||||
|
||||
def test_runtime_scope_allows_runtime_and_denies_deployment(self) -> None:
|
||||
grant = self.issue_grant(GrantType.RUNTIME)
|
||||
writer = self.writer(ExecutionPath.RUNTIME_EXECUTE, grant.grant_id)
|
||||
|
||||
authorization = writer.authorize_runtime_execute(
|
||||
**self.authorization_values("runtime-dispatch")
|
||||
)
|
||||
self.assertEqual(authorization.grant_id, grant.grant_id)
|
||||
self.assertEqual(
|
||||
authorization.execution_path,
|
||||
ExecutionPath.RUNTIME_EXECUTE.value,
|
||||
)
|
||||
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
writer.authorize_deployment(
|
||||
**self.authorization_values("forbidden-deploy")
|
||||
)
|
||||
|
||||
def test_evidence_scope_cannot_authorize_runtime(self) -> None:
|
||||
grant = self.issue_grant(GrantType.EVIDENCE)
|
||||
writer = self.writer(ExecutionPath.EVIDENCE_WRITE, grant.grant_id)
|
||||
writer.authorize_evidence_write(
|
||||
**self.authorization_values("evidence-write")
|
||||
)
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
writer.authorize_runtime_execute(
|
||||
**self.authorization_values("forbidden-runtime")
|
||||
)
|
||||
|
||||
def test_deployment_scope_cannot_authorize_rollback(self) -> None:
|
||||
grant = self.issue_grant(GrantType.DEPLOYMENT)
|
||||
writer = self.writer(ExecutionPath.DEPLOYMENT, grant.grant_id)
|
||||
writer.authorize_deployment(
|
||||
**self.authorization_values("deploy-release")
|
||||
)
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
writer.authorize_rollback(
|
||||
**self.authorization_values("forbidden-rollback")
|
||||
)
|
||||
|
||||
def test_git_grant_limits_individual_git_operations(self) -> None:
|
||||
grant = self.issue_grant(
|
||||
GrantType.GIT,
|
||||
allowed_git_operations=(GitOperation.READ_REF.value,),
|
||||
)
|
||||
writer = self.writer(ExecutionPath.GIT_OPERATION, grant.grant_id)
|
||||
authorization = writer.authorize_git_operation(
|
||||
git_operation=GitOperation.READ_REF.value,
|
||||
**self.authorization_values("git-read-ref"),
|
||||
)
|
||||
self.assertEqual(authorization.git_operation, GitOperation.READ_REF.value)
|
||||
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
writer.authorize_git_operation(
|
||||
git_operation=GitOperation.PUSH.value,
|
||||
**self.authorization_values("forbidden-git-push"),
|
||||
)
|
||||
|
||||
def test_context_mismatch_is_rejected(self) -> None:
|
||||
grant = self.issue_grant(GrantType.RUNTIME)
|
||||
with self.assertRaises(ProvenanceDenied):
|
||||
self.grant_verifier.authorize(
|
||||
grant_id=grant.grant_id,
|
||||
parent_provenance_id=self.workflow.provenance_id,
|
||||
run_id=self.workflow.run_id,
|
||||
tenant_id="tenant-b",
|
||||
task_id=self.workflow.task_id,
|
||||
agent_id=self.workflow.agent_id,
|
||||
principal_id=self.workflow.principal_id,
|
||||
execution_path=ExecutionPath.RUNTIME_EXECUTE.value,
|
||||
request_digest=digest_payload({"operation": "tenant-mismatch"}),
|
||||
)
|
||||
|
||||
def test_identical_grant_authorization_is_replay_protected(self) -> None:
|
||||
grant = self.issue_grant(GrantType.RUNTIME)
|
||||
writer = self.writer(ExecutionPath.RUNTIME_EXECUTE, grant.grant_id)
|
||||
values = self.authorization_values("same-runtime-request")
|
||||
writer.authorize_runtime_execute(**values)
|
||||
with self.assertRaises(ProvenanceReplay):
|
||||
writer.authorize_runtime_execute(**values)
|
||||
|
||||
def test_revoked_child_grant_is_rejected(self) -> None:
|
||||
grant = self.issue_grant(GrantType.RUNTIME)
|
||||
self.grant_store.revoke(
|
||||
grant.grant_id,
|
||||
reason="runtime emergency stop",
|
||||
principal_id=self.workflow.principal_id,
|
||||
)
|
||||
writer = self.writer(ExecutionPath.RUNTIME_EXECUTE, grant.grant_id)
|
||||
with self.assertRaises(ProvenanceRevoked):
|
||||
writer.authorize_runtime_execute(
|
||||
**self.authorization_values("revoked-runtime")
|
||||
)
|
||||
|
||||
def test_revoked_parent_blocks_all_child_grants(self) -> None:
|
||||
grant = self.issue_grant(GrantType.RUNTIME)
|
||||
self.parent_store.revoke(
|
||||
self.workflow.provenance_id,
|
||||
reason="workflow cancelled",
|
||||
principal_id=self.workflow.principal_id,
|
||||
)
|
||||
writer = self.writer(ExecutionPath.RUNTIME_EXECUTE, grant.grant_id)
|
||||
with self.assertRaises(ProvenanceRevoked):
|
||||
writer.authorize_runtime_execute(
|
||||
**self.authorization_values("parent-revoked")
|
||||
)
|
||||
|
||||
def test_expired_child_grant_is_rejected(self) -> None:
|
||||
issued = datetime.now(timezone.utc)
|
||||
grant = self.issue_grant(
|
||||
GrantType.RUNTIME,
|
||||
ttl_seconds=1,
|
||||
now=issued,
|
||||
)
|
||||
with self.assertRaises(ProvenanceExpired):
|
||||
self.grant_verifier.authorize(
|
||||
grant_id=grant.grant_id,
|
||||
parent_provenance_id=self.workflow.provenance_id,
|
||||
run_id=self.workflow.run_id,
|
||||
tenant_id=self.workflow.tenant_id,
|
||||
task_id=self.workflow.task_id,
|
||||
agent_id=self.workflow.agent_id,
|
||||
principal_id=self.workflow.principal_id,
|
||||
execution_path=ExecutionPath.RUNTIME_EXECUTE.value,
|
||||
request_digest=digest_payload({"operation": "expired-runtime"}),
|
||||
now=issued + timedelta(seconds=2),
|
||||
)
|
||||
|
||||
def test_scoped_writer_rejects_unnecessary_grant_mapping(self) -> None:
|
||||
runtime = self.issue_grant(GrantType.RUNTIME)
|
||||
deployment = self.issue_grant(GrantType.DEPLOYMENT)
|
||||
with self.assertRaises(ValueError):
|
||||
ScopedLeastPrivilegeProvenanceWriter(
|
||||
self.grant_verifier,
|
||||
self.root / "receipts-extra",
|
||||
{
|
||||
ExecutionPath.RUNTIME_EXECUTE.value: runtime.grant_id,
|
||||
ExecutionPath.DEPLOYMENT.value: deployment.grant_id,
|
||||
},
|
||||
required_paths=(ExecutionPath.RUNTIME_EXECUTE.value,),
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,271 @@
|
||||
#!/usr/bin/env python3
|
||||
"""AIOS V2 文档—代码匹配门禁。
|
||||
|
||||
仅使用 Python 标准库,可由本地、Gitea Actions、Codex 监督任务或发布验收脚本调用。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Iterable
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CheckResult:
|
||||
level: str
|
||||
message: str
|
||||
|
||||
|
||||
REQUIRED_DOCUMENTS = (
|
||||
"docs/aios-v2/README.md",
|
||||
"docs/aios-v2/01-USER-REQUIREMENTS.md",
|
||||
"docs/aios-v2/02-TARGET-ARCHITECTURE.md",
|
||||
"docs/aios-v2/03-MIGRATION-AND-DELIVERY.md",
|
||||
"docs/aios-v2/04-MODULE-CONTRACTS.md",
|
||||
"docs/aios-v2/05-TRACEABILITY-MATRIX.md",
|
||||
"docs/aios-v2/06-DOCUMENT-GOVERNANCE.md",
|
||||
"docs/aios-v2/adr/README.md",
|
||||
"docs/aios-v2/adr/ADR-001-single-control-plane.md",
|
||||
"docs/aios-v2/adr/ADR-002-openclaw-hermes-decoupling.md",
|
||||
"docs/aios-v2/adr/ADR-003-gitops-only-change-flow.md",
|
||||
"docs/aios-v2/adr/ADR-004-multi-tenant-isolation.md",
|
||||
"docs/aios-v2/adr/ADR-005-document-code-sync-gate.md",
|
||||
"docs/aios-v2/adr/ADR-006-candidate-persistence-strategy.md",
|
||||
)
|
||||
|
||||
REQUIRED_CODE_PATHS = (
|
||||
"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",
|
||||
"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",
|
||||
"active-runtime/app/aios_hermes/contract.py",
|
||||
"active-runtime/app/aios_hermes/adapter.py",
|
||||
"active-runtime/app/aios_hermes/worker.py",
|
||||
"tests/aios_v2_candidate/test_candidate_flow.py",
|
||||
"deploy/aios-v2/systemd/aios-v2.service",
|
||||
"deploy/aios-v2/docker/Dockerfile",
|
||||
"deploy/aios-v2/docker/compose.yaml",
|
||||
"deploy/aios-v2/healthcheck/check.sh",
|
||||
"deploy/aios-v2/rollback/rollback.sh",
|
||||
"tasks/openclaw-production-deploy-task.yaml",
|
||||
"tasks/codex-production-supervisor-task.yaml",
|
||||
)
|
||||
|
||||
REQUIRED_APIS = (
|
||||
"/api/v2/health",
|
||||
"/api/v2/tenants",
|
||||
"/api/v2/agents",
|
||||
"/api/v2/tasks",
|
||||
"/api/v2/audit",
|
||||
"/api/v2/runtime",
|
||||
"/api/v2/executions",
|
||||
"/api/v2/gitops",
|
||||
"/api/v2/hermes/results/reconcile",
|
||||
)
|
||||
|
||||
REQUIRED_MODELS = (
|
||||
"RequestContext",
|
||||
"TenantRecord",
|
||||
"AgentRecord",
|
||||
"TaskRecord",
|
||||
"TaskState",
|
||||
"AuditEvent",
|
||||
"OpenClawCommand",
|
||||
"OpenClawResult",
|
||||
"RuntimeHealth",
|
||||
"HermesJob",
|
||||
"HermesResult",
|
||||
"HermesHealth",
|
||||
"ExecutionEvidence",
|
||||
)
|
||||
|
||||
CODE_CHANGE_PREFIXES = (
|
||||
"active-runtime/app/aios_v2/",
|
||||
"active-runtime/app/aios_openclaw/",
|
||||
"active-runtime/app/aios_hermes/",
|
||||
"deploy/aios-v2/",
|
||||
"tests/aios_v2_candidate/",
|
||||
"tasks/",
|
||||
)
|
||||
|
||||
CONFLICT_MARKERS = ("<<<<<<<", "=======", ">>>>>>>")
|
||||
|
||||
|
||||
def run_git(repo: Path, *args: str) -> tuple[int, str]:
|
||||
process = subprocess.run(
|
||||
["git", "-C", str(repo), *args],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
timeout=20,
|
||||
)
|
||||
return process.returncode, process.stdout.strip()
|
||||
|
||||
|
||||
def chinese_ratio(text: str) -> float:
|
||||
chinese = len(re.findall(r"[\u3400-\u9fff]", text))
|
||||
latin = len(re.findall(r"[A-Za-z]", text))
|
||||
denominator = chinese + latin
|
||||
return chinese / denominator if denominator else 0.0
|
||||
|
||||
|
||||
def all_text(paths: Iterable[Path]) -> str:
|
||||
return "\n".join(path.read_text(encoding="utf-8") for path in paths)
|
||||
|
||||
|
||||
def check_required_files(repo: Path, results: list[CheckResult]) -> list[Path]:
|
||||
document_paths: list[Path] = []
|
||||
for relative in REQUIRED_DOCUMENTS:
|
||||
path = repo / relative
|
||||
if not path.is_file():
|
||||
results.append(CheckResult("错误", f"缺少必需文档:{relative}"))
|
||||
continue
|
||||
size = path.stat().st_size
|
||||
if size < 500:
|
||||
results.append(CheckResult("错误", f"文档正文过短:{relative}({size} 字节)"))
|
||||
else:
|
||||
document_paths.append(path)
|
||||
for relative in REQUIRED_CODE_PATHS:
|
||||
if not (repo / relative).is_file():
|
||||
results.append(CheckResult("错误", f"文档引用的实现路径不存在:{relative}"))
|
||||
return document_paths
|
||||
|
||||
|
||||
def check_document_quality(paths: list[Path], results: list[CheckResult]) -> None:
|
||||
for path in paths:
|
||||
text = path.read_text(encoding="utf-8")
|
||||
relative = path.as_posix()
|
||||
if any(marker in text for marker in CONFLICT_MARKERS):
|
||||
results.append(CheckResult("错误", f"文档存在未解决 Git 冲突标记:{relative}"))
|
||||
ratio = chinese_ratio(text)
|
||||
if ratio < 0.18:
|
||||
results.append(
|
||||
CheckResult(
|
||||
"错误",
|
||||
f"文档中文正文比例过低:{relative}({ratio:.1%})",
|
||||
)
|
||||
)
|
||||
headings = re.findall(r"^#{1,6}\s+.+$", text, flags=re.MULTILINE)
|
||||
if len(headings) < 3:
|
||||
results.append(CheckResult("错误", f"文档章节不完整:{relative}"))
|
||||
if re.search(r"(?mi)^\s*(TODO|TBD)\s*$", text):
|
||||
results.append(CheckResult("错误", f"文档包含未完成占位符:{relative}"))
|
||||
|
||||
|
||||
def check_requirements(repo: Path, results: list[CheckResult]) -> None:
|
||||
requirements = (repo / "docs/aios-v2/01-USER-REQUIREMENTS.md").read_text(
|
||||
encoding="utf-8"
|
||||
)
|
||||
matrix = (repo / "docs/aios-v2/05-TRACEABILITY-MATRIX.md").read_text(
|
||||
encoding="utf-8"
|
||||
)
|
||||
for number in range(1, 16):
|
||||
requirement = f"UR-{number:03d}"
|
||||
if requirement not in requirements:
|
||||
results.append(CheckResult("错误", f"需求文档缺少:{requirement}"))
|
||||
if requirement not in matrix:
|
||||
results.append(CheckResult("错误", f"追踪矩阵缺少:{requirement}"))
|
||||
|
||||
|
||||
def check_api_and_models(repo: Path, docs_text: str, results: list[CheckResult]) -> None:
|
||||
code_paths = [repo / path for path in REQUIRED_CODE_PATHS if path.endswith(".py")]
|
||||
code_text = all_text(path for path in code_paths if path.is_file())
|
||||
for api in REQUIRED_APIS:
|
||||
if api not in docs_text:
|
||||
results.append(CheckResult("错误", f"正式文档未覆盖核心 API:{api}"))
|
||||
if api not in code_text:
|
||||
results.append(CheckResult("错误", f"代码中未找到核心 API:{api}"))
|
||||
for model in REQUIRED_MODELS:
|
||||
if model not in docs_text:
|
||||
results.append(CheckResult("错误", f"正式文档未覆盖核心模型:{model}"))
|
||||
if model not in code_text:
|
||||
results.append(CheckResult("错误", f"代码中未找到核心模型:{model}"))
|
||||
|
||||
|
||||
def check_adr_links(repo: Path, results: list[CheckResult]) -> None:
|
||||
index = (repo / "docs/aios-v2/adr/README.md").read_text(encoding="utf-8")
|
||||
linked = re.findall(r"\((ADR-[^)]+\.md)\)", index)
|
||||
if len(set(linked)) < 6:
|
||||
results.append(CheckResult("错误", "ADR 索引未覆盖六项必需决策"))
|
||||
for filename in linked:
|
||||
if not (repo / "docs/aios-v2/adr" / filename).is_file():
|
||||
results.append(CheckResult("错误", f"ADR 索引引用不存在:{filename}"))
|
||||
|
||||
|
||||
def check_changed_docs(
|
||||
repo: Path,
|
||||
base_ref: str | None,
|
||||
results: list[CheckResult],
|
||||
) -> None:
|
||||
if not base_ref:
|
||||
results.append(CheckResult("警告", "未提供基准分支,跳过变更级文档同步检查"))
|
||||
return
|
||||
code, output = run_git(repo, "diff", "--name-only", f"{base_ref}...HEAD")
|
||||
if code != 0:
|
||||
results.append(CheckResult("警告", f"无法读取与 {base_ref} 的变更,跳过变更级检查"))
|
||||
return
|
||||
changed = [line.strip() for line in output.splitlines() if line.strip()]
|
||||
code_changed = any(path.startswith(CODE_CHANGE_PREFIXES) for path in changed)
|
||||
docs_changed = any(path.startswith("docs/aios-v2/") for path in changed)
|
||||
if code_changed and not docs_changed:
|
||||
results.append(
|
||||
CheckResult(
|
||||
"错误",
|
||||
"检测到架构、功能、测试、任务或部署变化,但本交付范围没有 docs/aios-v2/ 变化",
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="AIOS V2 文档—代码匹配检查")
|
||||
parser.add_argument("--repo", default=".", help="仓库根目录")
|
||||
parser.add_argument(
|
||||
"--base-ref",
|
||||
default=None,
|
||||
help="用于检查代码变化是否同步文档的基准引用",
|
||||
)
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
args = parse_args()
|
||||
repo = Path(args.repo).resolve()
|
||||
if not (repo / ".git").exists() and run_git(repo, "rev-parse", "--is-inside-work-tree")[0] != 0:
|
||||
print(f"错误:不是 Git 仓库:{repo}", file=sys.stderr)
|
||||
return 2
|
||||
|
||||
results: list[CheckResult] = []
|
||||
document_paths = check_required_files(repo, results)
|
||||
check_document_quality(document_paths, results)
|
||||
check_requirements(repo, results)
|
||||
docs_text = all_text(document_paths)
|
||||
check_api_and_models(repo, docs_text, results)
|
||||
check_adr_links(repo, results)
|
||||
check_changed_docs(repo, args.base_ref, results)
|
||||
|
||||
errors = [item for item in results if item.level == "错误"]
|
||||
warnings = [item for item in results if item.level == "警告"]
|
||||
for item in results:
|
||||
stream = sys.stderr if item.level == "错误" else sys.stdout
|
||||
print(f"{item.level}:{item.message}", file=stream)
|
||||
|
||||
print(
|
||||
f"文档—代码匹配检查完成:错误 {len(errors)},警告 {len(warnings)},正式文档 {len(document_paths)}。"
|
||||
)
|
||||
return 1 if errors else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"vrc": "V2R1C1",
|
||||
"semver": "2.1.0-rc.1",
|
||||
"product_baseline_oid": "fb739f6e8ff9c031d319221ace68dce157694086",
|
||||
"release_branch": "release/AIOS-V2R1C1-20260721",
|
||||
"old_release_oid": "80c4cbde03a82c30648a09b817bc2f03d5402936",
|
||||
"validated_release_parent_oid": "0778a31ec073e7c90003ef091f1d093c16bf22e5",
|
||||
"openclaw_companion_oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
|
||||
"openclaw_plugin_version": "2.1.0-rc.4",
|
||||
"openclaw_artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671",
|
||||
"validation_status": "PASS",
|
||||
"deployment_status": "NOT_STARTED",
|
||||
"previous_oid": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a"
|
||||
}
|
||||
Reference in New Issue
Block a user