feat(governance): 新增 matched PlayBook 學習缺口
This commit is contained in:
Your Name
@@ -634,13 +634,14 @@ Alert / Sentry / SigNoz / Gitea / Market Watch / Operator
|
||||
| `docs/evaluations/ai_agent_communication_learning_contract_2026-06-11.json` | 2026-06-11 committed snapshot；完成度 `35%`，runtime worker / DB migration / Telegram direct send 全部 false |
|
||||
| `apps/api/src/services/ai_agent_communication_learning_contract.py` | 只讀 loader；強制驗證 runtime / migration / Telegram / SDK / route 權限都未開 |
|
||||
| `GET /api/v1/agents/agent-communication-learning-contract` | 治理 API；只回傳 committed contract，不啟動 worker、不碰 DB/Redis、不呼叫外部服務 |
|
||||
| `docs/evaluations/ai_agent_interaction_learning_proof_2026-06-11.json` + `GET /api/v1/agents/agent-interaction-learning-proof` | P2-403A / P2-403B / P2-403C / P2-403D / P2-403E / P2-403F / P2-403G / P2-403H / P2-403I / P2-403J / P2-403L / P2-403M / P2-403N / P2-404 互動、接手、學習、成長、read model gate、Redis dry-run gate、learning writeback approval package、Telegram receipt approval package、owner-approved learning dry-run、fixture dry-run、runtime write gate review、post-write verifier package、runtime verifier evidence review、報表真相、日週月報、Agent 工作量、圖表化報告、風險自動化政策、報表 runtime readiness、no-write dry-run、fixture/readback/verifier dry-run 與 shadow/no-write execution 證據面；目前 live session、message、handoff、learning write、Gateway queue、Telegram send、report delivery、auto optimization、shadow worker、verifier execution 全部 `0`，由 P2-101 / P2-102 / P2-103 權限模型、候選 dry-run 證據與結果稽核軌跡承接下一步 |
|
||||
| `docs/evaluations/ai_agent_interaction_learning_proof_2026-06-11.json` + `GET /api/v1/agents/agent-interaction-learning-proof` | P2-403A / P2-403B / P2-403C / P2-403D / P2-403E / P2-403F / P2-403G / P2-403H / P2-403I / P2-403J / P2-403L / P2-403M / P2-403N / P2-404 互動、接手、學習、成長、read model gate、Redis dry-run gate、learning writeback approval package、Telegram receipt approval package、owner-approved learning dry-run、fixture dry-run、runtime write gate review、post-write verifier package、runtime verifier evidence review、報表真相、日週月報、Agent 工作量、圖表化報告、風險自動化政策、報表 runtime readiness、no-write dry-run、fixture/readback/verifier dry-run 與 shadow/no-write execution 證據面；目前 live session、message、handoff、learning write、Gateway queue、Telegram send、report delivery、auto optimization、shadow worker、verifier execution 全部 `0`，由 P2-101 / P2-102 / P2-103 / P2-104 權限模型、候選 dry-run 證據、結果稽核軌跡與 PlayBook 學習缺口證據承接下一步 |
|
||||
| `docs/evaluations/ai_agent_report_runtime_dry_run_2026-06-12.json` + `GET /api/v1/agents/agent-report-runtime-dry-run` | P2-403M 報表 runtime no-write dry-run 證據包；建立 5 個 dry-run artifact、3 個 SRE 戰情室 queue digest 草案、4 個 readback verifier case、3 個 Agent dry-run role 與 6 個 operator checkpoint；不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不寫 delivery receipt、不啟動 worker、不跑 verifier live readback、不讀 secret，已由 P2-403N fixture readback 承接 |
|
||||
| `docs/evaluations/ai_agent_report_runtime_fixture_readback_2026-06-12.json` + `GET /api/v1/agents/agent-report-runtime-fixture-readback` | P2-403N fixture smoke / queue preview readback / verifier dry-run 證據包；建立 5 個 fixture smoke、3 個 SRE 戰情室 queue preview readback、4 個 verifier dry-run case、3 個 Agent fixture role 與 5 個 operator checkpoint；不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不寫 delivery receipt、不啟動 worker、不跑 verifier live readback、不讀 secret，下一步 P2-404 |
|
||||
| `docs/evaluations/ai_agent_runtime_worker_shadow_gate_2026-06-12.json` + `GET /api/v1/agents/agent-runtime-worker-shadow-gate` | P2-404 runtime worker shadow / no-write execution evidence gate；建立 5 個 shadow candidate、4 個 no-write replay、4 個 verifier shadow case、3 個 Agent shadow role 與 6 個 operator checkpoint；shadow live worker、Gateway queue write、Telegram send、Bot API、delivery receipt、auto worker、verifier live readback、production write 與 secret read 全部 `0 / false`，下一步 P2-101 |
|
||||
| `docs/evaluations/ai_agent_operation_permission_model_2026-06-12.json` + `GET /api/v1/agents/agent-operation-permission-model` | P2-101 操作類別權限模型；建立 5 條 permission lane、13 類 operation category、3 個 Agent permission role、8 個 gate transition 與 5 個 operator decision template；runtime execution、Gateway queue write、Telegram send、Bot API、delivery receipt、auto worker、verifier live readback、production write、secret / paid provider、host command 與 destructive action 全部 `0 / false`，已由 P2-102 承接 |
|
||||
| `docs/evaluations/ai_agent_candidate_operation_dry_run_evidence_2026-06-12.json` + `GET /api/v1/agents/agent-candidate-operation-dry-run-evidence` | P2-102 候選操作 dry-run 證據；13 類候選操作全部具備 input / output evidence hash、side-effect count、verifier plan、rollback/no-op plan 與人工 handoff；6 個 verifier plan、7 個 gate evidence requirement、5 個 operator handoff；runtime、Gateway queue、Telegram、production write、secret / paid provider 與 destructive action 全部 `0 / false`，已由 P2-103 承接 |
|
||||
| `docs/evaluations/ai_agent_task_result_audit_trail_2026-06-13.json` + `GET /api/v1/agents/agent-task-result-audit-trail` | P2-103 任務結果稽核軌跡；8 條 result route、6 個 writeback contract、7 個 audit checkpoint、5 個 operator handoff；把 diagnostic-only、repair candidate、execution failed、provider unmatched、report zero-signal 等結果固定到 KM 草稿、LOGBOOK 證據、audit trail、timeline 與人工下一步；KM / LOGBOOK / audit DB / timeline / PlayBook trust / Gateway queue / Telegram 寫入全為 `0 / false`，下一步 P2-104 |
|
||||
| `docs/evaluations/ai_agent_matched_playbook_learning_gap_2026-06-13.json` + `GET /api/v1/agents/agent-matched-playbook-learning-gap` | P2-104 `matched_playbook_id` 學習缺口；7 個 learning checkpoint、4 個 gap、5 個測試契約、3 個 owner gate；repo 內來源、approval record 序列化、learning_service EWMA 與 await learning 契約可查；live DB read、PlayBook trust write、KM / timeline / Gateway / Telegram 寫入全為 `0 / false`，下一步 P2-105 |
|
||||
| `docs/evaluations/ai_agent_live_read_model_gate_2026-06-11.json` + `GET /api/v1/agents/agent-live-read-model-gate` | P2-403B AgentSession / Redis Streams live read model gate；定義 safe fields、Redis envelope、worker gate、rollback plan 與 no-write smoke，不連 DB、不讀寫 Redis、不啟動 worker |
|
||||
|
||||
#### 3.2.1c 2026-06-11 AI Agent 主動營運委派與版本生命週期契約
|
||||
@@ -733,6 +734,7 @@ Repo / registry / release notes / K8s / host / observability / backup evidence
|
||||
22. 定義操作類別權限模型。✅ P2-101 已完成；permission lane `5`、operation category `13`、Agent permission role `3`、gate transition `8`、operator decision template `5`，runtime execution、Gateway queue write、Telegram send、Bot API、delivery receipt、AI runtime worker、中低風險 auto worker、verifier live readback、production write、secret / paid provider、host command 與 destructive action 仍為 `0 / false`。已由 P2-102 承接。
|
||||
23. 建立候選操作 dry-run 證據。✅ P2-102 已完成；candidate operation `13`、dry-run evidence `13`、verifier plan `6`、gate evidence requirement `7`、operator handoff `5`，side-effect、runtime execution、Gateway queue write、Telegram send、production write、secret value read、paid provider call、host / cluster command 與 destructive action 仍為 `0 / false`。已由 P2-103 承接。
|
||||
24. 把任務結果接回 KM / LOGBOOK / 稽核軌跡。✅ P2-103 已完成；result route `8`、writeback contract `6`、audit checkpoint `7`、operator handoff `5`，KM write、LOGBOOK runtime append、audit DB write、timeline write、PlayBook trust write、Gateway queue write、Telegram send 與 production write 仍為 `0 / false`。下一步 P2-104 修復 `matched_playbook_id` 學習缺口。
|
||||
25. 修復 `matched_playbook_id` 學習缺口。✅ P2-104 已完成；learning checkpoint `7`、gap `4`、test contract `5`、owner gate `3`，repo 內 matched_playbook_id 來源、approval record、learning_service、await learning 與 E2E 測試契約可查；live DB read、PlayBook trust write、KM / timeline / Gateway / Telegram 寫入仍為 `0 / false`。下一步 P2-105 加入 critic / reviewer 評分。
|
||||
|
||||
#### 3.2.1d 2026-06-11 Agent 互動、學習與成長證據面
|
||||
|
||||
@@ -765,6 +767,7 @@ Repo / registry / release notes / K8s / host / observability / backup evidence
|
||||
| `docs/evaluations/ai_agent_operation_permission_model_2026-06-12.json` + `GET /api/v1/agents/agent-operation-permission-model` | P2-101 操作類別權限模型；5 條 permission lane、13 類 operation category、3 個 Agent permission role、8 個 gate transition、5 個 operator decision template；不啟動 runtime worker、不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不寫 production target、不讀 secret |
|
||||
| `docs/evaluations/ai_agent_candidate_operation_dry_run_evidence_2026-06-12.json` + `GET /api/v1/agents/agent-candidate-operation-dry-run-evidence` | P2-102 候選操作 dry-run 證據；13 類候選操作、13 組 dry-run evidence、6 個 verifier plan、7 個 gate evidence requirement、5 個 operator handoff；不啟動 runtime worker、不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不寫 production target、不讀 secret、不執行 destructive action |
|
||||
| `docs/evaluations/ai_agent_task_result_audit_trail_2026-06-13.json` + `GET /api/v1/agents/agent-task-result-audit-trail` | P2-103 任務結果稽核軌跡；8 條 result route、6 個 writeback contract、7 個 audit checkpoint、5 個 operator handoff；不寫 KM、不 runtime append LOGBOOK、不寫 audit DB、不寫 timeline、不更新 PlayBook trust、不寫 Gateway queue、不送 Telegram |
|
||||
| `docs/evaluations/ai_agent_matched_playbook_learning_gap_2026-06-13.json` + `GET /api/v1/agents/agent-matched-playbook-learning-gap` | P2-104 PlayBook 學習缺口證據；7 個 learning checkpoint、4 個 gap、5 個測試契約、3 個 owner gate；不查 live DB、不更新 PlayBook trust、不寫 KM、不寫 timeline、不寫 Gateway queue、不送 Telegram |
|
||||
| `apps/api/src/services/ai_agent_interaction_learning_proof.py` | 只讀 loader；強制 live flags / DB / Redis / Telegram / transcript / 私有推理全部關閉 |
|
||||
| `GET /api/v1/agents/agent-interaction-learning-proof` | 治理 API；只回傳證據面，不啟動 worker、不碰 live DB/Redis、不發 Telegram |
|
||||
| `docs/schemas/ai_agent_live_read_model_gate_v1.schema.json` | P2-403B live read model gate schema；強制 DB / Redis / worker / Telegram / learning writeback 仍需批准 |
|
||||
@@ -1939,6 +1942,13 @@ Phase 6 完成後
|
||||
- 政策裁決：P2-103 只允許結果路由、redacted evidence hash、寫回契約、稽核 checkpoint 與人工下一步；任何 KM write、LOGBOOK runtime append、audit DB write、timeline write、PlayBook trust write、Gateway queue write、Telegram send、production write 或 secret value read 都仍為 `0 / false`。
|
||||
- 本波仍不寫 KM、不 runtime append LOGBOOK、不寫 audit DB、不寫 timeline、不更新 PlayBook trust、不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不啟動 runtime worker、不讀 secret、不回傳內部協作內容；下一步 P2-104 才修復 `matched_playbook_id` 學習缺口。
|
||||
|
||||
### 2026-06-13 10:55 (台北) — §3.2 / §5 — 完成 P2-104 `matched_playbook_id` 學習缺口證據面 — 把 PlayBook trust 斷鏈拆成可驗證 gate
|
||||
|
||||
- 新增 `ai_agent_matched_playbook_learning_gap_v1` schema / committed snapshot / loader / API / 測試，定義 7 個 learning checkpoint、4 個 gap item、5 個測試契約與 3 個 owner gate。
|
||||
- `apps/web/src/app/[locale]/governance/tabs/automation-inventory-tab.tsx` 接入 `GET /api/v1/agents/agent-matched-playbook-learning-gap`，治理頁顯示 proposal RAG 匹配、approval record 序列化、learning_service EWMA、await learning、repair candidate、webhook source correlation 與 live null-rate gate。
|
||||
- 政策裁決：P2-104 只允許 repo committed evidence、測試契約、redacted evidence ref 與 owner gate；任何 live DB read、PlayBook trust write、KM write、timeline write、Gateway queue write、Telegram send、production write 或 secret value read 都仍為 `0 / false`。
|
||||
- 本波仍不查 live DB、不更新 PlayBook trust、不寫 KM、不寫 timeline、不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不啟動 runtime worker、不讀 secret、不回傳內部協作內容；下一步 P2-105 才在批准前加入 critic / reviewer 評分。
|
||||
|
||||
### 2026-06-12 11:55 (台北) — §3.2 / §5 — 完成 P2-403M 報表 runtime no-write dry-run 證據包 — 把 queue / verifier 草案固定成可審核證據
|
||||
|
||||
- 新增 `ai_agent_report_runtime_dry_run_v1` schema / committed snapshot / loader / API / 測試，定義 report_run snapshot preview、Telegram digest payload preview、AI post-report analysis packet、中低風險 no-op plan、post-action verifier readback plan。
|
||||
|
||||
Reference in New Issue
Block a user