feat(governance): 新增 AI Agent 專業任務擴展

docs/LOGBOOK.md

@@ -83,6 +83,39 @@
 - S4.9 owner response、source-control owner acceptance、Nginx reload、host restart、firewall change、active scan、secret collection、runtime execution、action button 全部維持 `0 / false`。
 - 本輪未 SSH、未讀 live conf、未改主機、未重啟 Docker / Nginx、未修改 firewall / iptables、未收 secrets 明文、未執行 active scan、未 force push。
 
+## 2026-06-15｜AI Agent 專業任務擴展與 Telegram Runtime Bridge 只讀契約
+
+**背景**：統帥要求繼續盤點 AI Agent 還可以承接哪些專業工作，並質疑 Telegram 群組 / TG Bot 尚未整合到 AI Agent 報表、告警、審核與自動化作業鏈。既有 12-Agent War Room 已定義 OpenClaw / Hermes / NemoTron / SRE / Security / DevOps / Data / Supply Chain / Product / QA / Market / Telegram Ops 分工，但仍需要一份可由 API 讀回、可測試、可被 guard 阻擋誤啟用的專業任務擴展契約。
+
+**完成項目**：
+- 新增 `ai_agent_professional_task_expansion_v1` schema、committed snapshot、API loader 與 `GET /api/v1/agents/agent-professional-task-expansion`。
+- `/zh-TW/governance?tab=automation-inventory` 已接入 P2-405A 卡片，顯示 24 類專業任務、8 個領域、5 段 Telegram bridge、6 種訊息、需批准 19、高風險 / critical 11 與 live / send / write = 0。
+- 新增 `docs/ai/AI_AGENT_PROFESSIONAL_TASK_EXPANSION_2026-06-15.md`，把 AI Agent 可承接的專業工作固定成 24 類任務、8 個領域、MCP/RAG 需求、風險層級、Telegram policy 與 blocked actions。
+- Telegram Runtime Bridge 已拆成 5 段：no-send preview、queue preview readback、approved canary、日報 / 週報 / 月報 digest、action-required digest。
+- 任務 rollup 固定：professional task `24`、domain `8`、Telegram stage `5`、message type `6`、需批准 `19`、low / medium / high / critical = `3 / 10 / 6 / 5`。
+- 邊界固定：Gateway queue write、Telegram send、Bot API call、delivery receipt write、production write、secret read、paid API、host write、kubectl action 全部 `0 / false`。
+
+**完成度與狀態**：
+- P2-405A 專業任務擴展契約：`82%`。
+- 專業任務定義 / MCP-RAG / 風險分層：`100%`。
+- Telegram no-send bridge contract：`100%`。
+- Telegram 實發、Gateway queue 寫入、Bot API call、delivery receipt E2E：`0%`，全部仍需後續批准包與 canary gate。
+- 下一步：P2-405B 只允許把完整 no-send message preview、dedup key、receipt expectation 與 canary approval package 顯示到治理頁；本輪卡片只顯示 bridge / rollup，不代表 Telegram 實發。
+
+**本地驗證**：
+- `python3 -m json.tool docs/evaluations/ai_agent_professional_task_expansion_2026-06-15.json` 通過。
+- `python3 -m json.tool docs/schemas/ai_agent_professional_task_expansion_v1.schema.json` 通過。
+- `python3 -m json.tool apps/web/messages/zh-TW.json` 與 `python3 -m json.tool apps/web/messages/en.json` 通過。
+- `python3 -m py_compile apps/api/src/services/ai_agent_professional_task_expansion.py apps/api/src/api/v1/agents.py` 通過。
+- `DATABASE_URL=postgresql+asyncpg://test:test@localhost/test pytest -q apps/api/tests/test_ai_agent_professional_task_expansion.py apps/api/tests/test_ai_agent_professional_task_expansion_api.py` → `7 passed`。
+- `pnpm --filter @awoooi/web typecheck` 通過。
+- `NEXT_PUBLIC_API_URL=https://awoooi.wooo.work pnpm --filter @awoooi/web build` 通過；`/zh-TW/governance` First Load JS `451 kB`。
+- `python3 scripts/security/security-mirror-progress-guard.py --root .` → `SECURITY_MIRROR_PROGRESS_GUARD_OK`。
+- `python3 scripts/ops/doc-secrets-sanity-check.py docs .gitea apps/web/messages/zh-TW.json apps/web/messages/en.json 'apps/web/src/app/[locale]/governance/tabs/automation-inventory-tab.tsx' apps/web/src/lib/api-client.ts` → `DOC_SECRET_SANITY_OK scanned_files=872`。
+- `git diff --check` 通過。
+
+**邊界**：本輪未 SSH、未讀 live conf、未改主機、未修改 Telegram Bot、未發 Telegram、未寫 Gateway queue、未呼叫 Bot API、未讀 secret、未啟用 paid API、未跑 kubectl、未做 production write，也沒有把工作視窗對話內容放到前端。
+
 ## 2026-06-15｜Monitoring / Alerting / Observability owner response acceptance 只讀帳本
 
 **背景**：Monitoring / Alerting / Observability 已有 repo-only 清冊與 owner request draft，但仍缺少「owner 回覆收件後如何驗收、哪些欄位必填、哪些證據可接受、哪些動作必須阻擋」的固定帳本。這會讓 Prometheus / Alertmanager / Grafana / SigNoz / Sentry / Langfuse / OTEL / Telegram 告警鏈路在後續收件時，可能被誤判成 reload、receiver route change、silence change、Telegram send 或 alert chain smoke 授權。

docs/ai/AI_AGENT_12_AGENT_WAR_ROOM_2026-06-14.md

@@ -184,5 +184,5 @@ Telegram Ops 工位負責 Telegram Gateway、Channel Hub、日報/週報/月報
 狀態變更：12 位 Agent 只讀審查全部回收並彙整；已建立 `ai_agent_12_agent_war_room_v1` schema / committed snapshot / API / tests / governance UI 區塊。
 證據：`docs/schemas/ai_agent_12_agent_war_room_v1.schema.json`、`docs/evaluations/ai_agent_12_agent_war_room_2026-06-14.json`、`GET /api/v1/agents/agent-12-agent-war-room`、治理頁 12-Agent War Room 區塊、12 位 Agent 只讀回饋。
 阻擋：runtime writer、Telegram send、Bot API、production write、SDK 安裝、付費 API、shadow/canary、host update、DB migration、restore 仍未批准。
-下一步：本地驗證、推送 Gitea CD、production API readback 與 desktop / mobile Browser smoke；P2-143 承接 report receipt / 月報 / Agent 工作量 runtime data model。
+下一步：P2-405B 承接 Telegram no-send preview UI；讓統帥先看見 TG 訊息、dedup、receipt 與風險標籤長相。P2-146 owner response receipt preview 仍屬另一條 release gate 主線；兩者都不得直接打開 Gateway queue、Telegram send、Bot API 或 production write。
 ```

docs/ai/AI_AGENT_AUTOMATION_WORKLIST_2026-06-04.md

@@ -15,6 +15,7 @@
 | OpenClaw / Hermes / NemoTron 主動溝通、學習與成長證據 | 100% | P2-401A 到 P2-144 已完成只讀證據面、runtime / report / result-capture gates、no-write readback、promotion review、writer implementation review、writer dry-run fixture、writer dry-run readback、owner promotion execution gate、owner-approved execution rehearsal、owner acceptance / maintenance window gate、owner acceptance readback / preflight hold、owner-approved preflight release package、owner-approved release readiness readback、owner release approval gate、post-release verifier / rollback gate、final release candidate readback、release authorization hold / readback gate、release verifier preflight / owner review packet、release decision hold / readback、release decision next handoff、release decision input prep、12-Agent War Room、owner response 預檢與 owner response 回讀；P2-141 基線與 S4.9 owner release packet 補強皆已正式驗證，P2-142 12-Agent War Room 已完成 production readback 與 desktop / mobile smoke，P2-143 owner response 預檢已完成 production readback 與 in-app browser smoke，P2-144 owner response 回讀已完成 production API readback 與 desktop / mobile smoke。runtime worker、DB migration、production Redis consumer group、canonical runtime readback、live query、runtime score、result capture write、Telegram 實發、delivery receipt E2E、live report delivery、reviewer queue write、Gateway queue write、AI analysis runtime、中低風險 auto worker、KM / LOGBOOK / audit DB / timeline / PlayBook trust 寫入、SDK / 付費服務仍未開 gate | `ai_agent_result_capture_release_decision_owner_response_readback_v1`、`GET /api/v1/agents/agent-result-capture-release-decision-owner-response-readback`、`docs/evaluations/ai_agent_result_capture_release_decision_owner_response_readback_2026-06-14.json`、feature commit `8795f100`、deploy marker `ac938037`、Gitea code-review `2965` / CD `2964` success、5 個回覆讀回 lane、18 個 owner 必填欄位、6 個 readback validation check、6 個 rejection guard、5 個 operator action、等待外部回覆 `5`、未收件 lane `5`、正式寫入 / 發送 `0`；P2-142 feature commit `5de4b3f3`、deploy marker `1a2c9e36`、Gitea CD run `4232` success、production API readback、desktop / mobile in-app browser smoke；P2-143 feature commit `755b0a8d`、deploy marker `667d6329`、Gitea code-review `2961` / CD `2960` success、production API readback、desktop / mobile in-app browser smoke；MASTER §3.2.1b / §3.2.1d / §3.4.3 |
 | AI Agent 主動營運委派與版本生命週期 | 100% | P2-402A / P2-402B / P2-402C / P2-402D / P2-402E / P2-402F / P2-402G 已完成；已建立 repo-only 版本新鮮度快照、工具採用批准包、Telegram action-required digest policy、Gitea PR 草案 lane、host / K3s / stateful 版本只讀盤點、API 與 governance UI。定期排程、外部版本查詢、工具安裝、CI 變更、套件升級、主機更新、container pull、實際 PR creation、auto merge、Telegram 實發、SSH、kubectl、重啟仍未開 gate | `ai_agent_proactive_operations_contract_v1`、`ai_agent_version_freshness_snapshot_v1`、`ai_agent_tool_adoption_approval_package_v1`、`ai_agent_telegram_action_required_digest_policy_v1`、`ai_agent_gitea_pr_draft_lane_v1`、`ai_agent_host_stateful_version_inventory_v1`、`GET /api/v1/agents/agent-proactive-operations-contract`、`GET /api/v1/agents/agent-version-freshness-snapshot`、`GET /api/v1/agents/agent-tool-adoption-approval-package`、`GET /api/v1/agents/agent-telegram-action-required-digest-policy`、`GET /api/v1/agents/agent-gitea-pr-draft-lane`、`GET /api/v1/agents/agent-host-stateful-version-inventory`、`/zh-TW/governance?tab=automation-inventory`、MASTER §3.2.1c |
 | 12-Agent War Room 編組 | 72% | 12 個邏輯工位與分批派工規則已正式部署；OpenClaw / Hermes / NemoTron / SRE / Security / DevOps / Data/DR / Supply Chain / Product/UI / QA / Market / Telegram 共 12 份只讀審查已回收；schema / committed snapshot / API / tests / governance UI 區塊 / production API readback / desktop + mobile in-app browser smoke 已完成；runtime writer、Telegram send、Bot API、production write 仍未批准 | `ai_agent_12_agent_war_room_v1`、`docs/evaluations/ai_agent_12_agent_war_room_2026-06-14.json`、`GET /api/v1/agents/agent-12-agent-war-room`、feature commit `5de4b3f3`、deploy marker `1a2c9e36`、Gitea CD run `4232` success、`/zh-TW/governance?tab=automation-inventory`、12 份 Codex sub-agent 只讀回饋 |
+| AI Agent 專業任務擴展與 Telegram Runtime Bridge | 84% | P2-405A 已完成本地只讀契約與治理頁 P2-405A 卡片；24 類專業任務、8 個領域、5 段 Telegram bridge、6 種訊息類型、MCP/RAG stack、日報 / 週報 / 月報 / action-required 報告契約已固定；Telegram 實發、Gateway queue、Bot API、delivery receipt、production write、secret read、paid API、host write、kubectl action 仍全部關閉 | `ai_agent_professional_task_expansion_v1`、`docs/evaluations/ai_agent_professional_task_expansion_2026-06-15.json`、`GET /api/v1/agents/agent-professional-task-expansion`、`/zh-TW/governance?tab=automation-inventory`、`docs/ai/AI_AGENT_PROFESSIONAL_TASK_EXPANSION_2026-06-15.md`、需批准任務 `19`、low / medium / high / critical = `3 / 10 / 6 / 5`；下一步 P2-405B 完整 no-send message preview / canary approval package |
 | Owner response 預檢與拒收邊界 | 100% | P2-143 已完成正式部署與 production readback；承接 P2-141 input prep 與 P2-142 War Room，只建立 owner / verifier / rollback / maintenance / live-apply 五類外部回覆的 intake 預檢、必填欄位與拒收規則；正式 owner response 尚未收到、未接受、未寫入 | `ai_agent_result_capture_release_decision_owner_response_preflight_v1`、`GET /api/v1/agents/agent-result-capture-release-decision-owner-response-preflight`、feature commit `755b0a8d`、deploy marker `667d6329`、Gitea code-review `2961` / CD `2960` success、5 個 response intake lane、18 個 required owner field、6 個 validation check、6 個 rejection guard、5 個 operator action；owner response received / accepted / redacted payload / reviewer queue / Gateway / Telegram / Bot API / production write / secret read / destructive operation 全為 `0` |
 | Owner response 回讀狀態 | 100% | P2-144 已完成正式部署與 production readback；承接 P2-143 preflight，只讀回五類外部回覆仍未收到、未接受、未拒絕、未保存 | `ai_agent_result_capture_release_decision_owner_response_readback_v1`、`GET /api/v1/agents/agent-result-capture-release-decision-owner-response-readback`、feature commit `8795f100`、deploy marker `ac938037`、Gitea code-review `2965` / CD `2964` success、5 個 response readback lane、18 個 required owner field、6 個 readback validation check、6 個 readback rejection guard、5 個 operator action、waiting external response `5`、no external response received `5`；owner response received / accepted / redacted payload / reviewer queue / Gateway / Telegram / Bot API / production write / secret read / destructive operation 全為 `0` |
 | 本工作清單與分析報告 | 100% | 已完成 | 本 MD 文件 |
@@ -1416,7 +1417,8 @@ UI：
 ## 13. 立即執行順序
 
 1. P2-004：依賴 / 供應鏈漂移監控，保持只讀觀察與批准包邊界。
-2. P3-001：外部 Agent / SDK / API 相關能力仍需證據、費用批准與 shadow / canary 關卡。
+2. P2-405B：AI Agent Telegram 完整 no-send message preview / canary approval package，先讓統帥看見未來 TG 訊息、dedup、receipt 與風險標籤長相；仍不得實發。
+3. P3-001：外部 Agent / SDK / API 相關能力仍需證據、費用批准與 shadow / canary 關卡。
 
 ## 14. 目前風險
 

docs/ai/AI_AGENT_PROFESSIONAL_TASK_EXPANSION_2026-06-15.md

@@ -0,0 +1,78 @@
+# AI Agent 專業任務擴展與 Telegram Runtime Bridge 工作報告
+
+> 日期：2026-06-15（台北時間）
+> 狀態：P2-405A 已完成只讀契約、snapshot、API、測試與治理頁卡片；Telegram 實發仍未啟用。
+> 事實來源：`ai_agent_professional_task_expansion_v1`
+
+## 1. 結論
+
+本輪把「AI Agent 還能處理哪些專業工作」正式產品化成 24 類專業任務，並把 Telegram 群組 / TG Bot 整合拆成 5 段啟動前閘門。
+
+這不是直接讓 AI Agent 發 Telegram 或改 production；目前只允許 no-send preview、queue preview readback、owner review 與批准包。真正送到 **AwoooI SRE 戰情室** 必須先通過 approved canary、dedup、receipt、redaction、OpenClaw 仲裁、Security gate 與 QA verifier。
+
+## 2. 完成度
+
+| 範圍 | 完成度 | 狀態 |
+|---|---:|---|
+| 專業任務擴展契約 | 100% | 24 類任務已定義 owner、風險、MCP、RAG、Telegram policy 與 blocked actions |
+| Telegram Runtime Bridge 契約 | 100% | no-send preview、queue preview、approved canary、日週月報、action-required digest 已分段 |
+| API / loader | 100% | `GET /api/v1/agents/agent-professional-task-expansion` 只讀輸出 |
+| 治理頁可視化 | 100% | `/zh-TW/governance?tab=automation-inventory` 顯示任務、風險、TG bridge 與 live/send/write=0 |
+| Telegram 實發 | 0% | `telegram_send_count=0`、`bot_api_call_count=0`、`gateway_queue_write_count=0` |
+| Runtime 自動優化 | 0% | production write、host write、kubectl、paid API、secret read 全部維持 0 |
+
+## 3. Telegram Bridge
+
+| 階段 | 狀態 | 可做 | 不可做 |
+|---|---|---|---|
+| no-send preview | ready for owner review | 產生脫敏 TG 訊息預覽、dedup key、風險層級 | 不送 Telegram、不寫 queue |
+| queue preview readback | ready for owner review | 讀回 queue envelope hash、receipt expectation | 不寫 production queue |
+| approved canary | blocked until approval | 單一 canary 訊息與 receipt 驗證 | 未批准不得 Bot API send |
+| 日週月報 digest | blocked until canary receipt | Agent 工作量、完成度、阻擋項、圖表摘要 | 不洗版、不發成功噪音 |
+| action-required digest | blocked until dual gate | 高風險審核卡、failure-only escalation | 不取代 runtime authorization |
+
+## 4. 專業任務總覽
+
+| 領域 | 任務數 | 代表任務 | 主責 |
+|---|---:|---|---|
+| SRE / Observability | 4 | incident correlation、告警降噪、synthetic check、DB slow query triage | SRE Sentinel / QA |
+| Security / IwoooS | 3 | public bundle redaction、secret metadata parity、owner response completeness | Security Sentinel |
+| DevOps / Release | 4 | image digest pin、GitOps diff、gateway route impact、candidate PR draft | DevOps Commander |
+| Data / Backup / DR | 3 | backup readiness、escrow evidence、data freshness | Data DR / Hermes |
+| Supply Chain | 2 | CVE triage、SBOM/license drift | Supply Chain Scout |
+| Product / UI / QA | 1 | mobile overflow、console、a11y regression | Product UI / QA |
+| AI Governance / Replay / Market | 4 | market watch、NemoTron replay、cost forecast、runbook/postmortem | OpenClaw / NemoTron / Hermes |
+| Telegram / Reports / Receipts | 3 | digest preview、report truth gate、post-action verifier | Telegram Ops / Hermes / OpenClaw |
+
+## 5. 專業能力層級
+
+| 層級 | AI Agent 可自動做 | Gate |
+|---|---|---|
+| 低風險 | 文件、報表、UI smoke、只讀摘要、truth gate | guard 後自動摘要 |
+| 中風險 | proposal、no-write dry-run、PR 草案、Telegram preview | QA + OpenClaw 或 owner review |
+| 高風險 | 只產批准包、rollback plan、failure-only digest 草案 | 統帥批准 |
+| Critical | production write、kubectl、ArgoCD sync、Telegram 實發、secret、restore、host write | 預設 blocked |
+
+## 6. MCP / RAG
+
+首批 MCP：Gitea、Browser、Observability、Telegram Gateway、Package Registry、Database Readonly、Backup Status、ArgoCD Readonly、HTTP Probe、Fixture Store。
+
+首批 RAG：LOGBOOK chunks、HARD_RULES / ADR chunks、Runbook chunks、Incident / alert traces、Agent market evidence、Owner response templates。
+
+成長指標：KM entries、PlayBook updates、recommendations、replay score delta、blocked action prevented count、receipt missing count。
+
+## 7. 邊界
+
+- 不直接發 Telegram。
+- 不寫 Telegram Gateway queue。
+- 不呼叫 Bot API。
+- 不讀 `TELEGRAM_BOT_TOKEN` 或任何機密明文。
+- 不把工作視窗對話、未遮罩提示、私人推理或未遮罩 runtime payload 放進前端或 Telegram。
+- 不做 production write、host write、kubectl、ArgoCD sync、restore、rollback、paid API、SDK install。
+
+## 8. 下一步
+
+1. P2-405B：把完整 no-send message preview、dedup key、receipt expectation 與 canary approval package 顯示到治理頁，讓統帥先看 TG 訊息會長什麼樣。
+2. P2-405C：產生 approved canary approval package，明確列出發送時間窗、目標群組、dedup、receipt 與 rollback / mute plan。
+3. P2-405D：canary 通過後才開日報 / 週報 / 月報 digest delivery。
+4. P2-405E：Action-required digest 只對 failure / high-risk / approval-required 事件開啟。

docs/evaluations/ai_agent_professional_task_expansion_2026-06-15.json

@@ -0,0 +1,244 @@
+{
+  "schema_version": "ai_agent_professional_task_expansion_v1",
+  "generated_at": "2026-06-15T10:40:00+08:00",
+  "program_status": {
+    "current_priority": "P2",
+    "current_task_id": "P2-405A",
+    "next_task_id": "P2-405B",
+    "overall_completion_percent": 82,
+    "read_only_mode": true,
+    "runtime_authority": "professional_task_expansion_and_telegram_bridge_read_only_no_send",
+    "status_note": "AI Agent 專業任務擴展與 Telegram Runtime Bridge 已產品化為只讀契約；目前只允許 no-send preview、queue preview readback 與 owner review，不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不讀 secret、不做 production write。"
+  },
+  "source_refs": [
+    "docs/ai/AI_AGENT_12_AGENT_WAR_ROOM_2026-06-14.md",
+    "docs/ai/AI_AGENT_PROACTIVE_OPERATIONS_2026-06-11.md",
+    "docs/ai/AI_AGENT_INTERACTION_LEARNING_PROOF_2026-06-11.md",
+    "docs/ai/AI_AGENT_TELEGRAM_ACTION_REQUIRED_DIGEST_POLICY_2026-06-11.md",
+    "docs/ai/AI_AGENT_DEPLOYMENT_LAYOUT_2026-06-11.md",
+    "docs/security/MONITORING-OWNER-RESPONSE-ACCEPTANCE.md",
+    "apps/api/src/services/telegram_gateway.py",
+    ".gitea/workflows/cd.yaml",
+    ".gitea/workflows/code-review.yaml"
+  ],
+  "telegram_runtime_bridge": {
+    "canonical_room": "AwoooI SRE 戰情室",
+    "canonical_room_env": "SRE_GROUP_CHAT_ID",
+    "gateway_required": true,
+    "gateway_owner": "telegram_ops_liaison",
+    "arbiter": "openclaw",
+    "receipt_owner": "hermes",
+    "replay_owner": "nemotron",
+    "no_send_preview_ready": true,
+    "queue_preview_readback_ready": true,
+    "approved_canary_required": true,
+    "direct_bot_api_allowed": false,
+    "bot_api_call_enabled": false,
+    "gateway_queue_write_enabled": false,
+    "telegram_send_enabled": false,
+    "delivery_receipt_write_enabled": false,
+    "stages": [
+      {
+        "stage_id": "tg_bridge_01_no_send_preview",
+        "title": "Telegram no-send preview",
+        "status": "ready_for_owner_review",
+        "allowed_output": "脫敏訊息預覽、dedup key、目標群組 metadata、風險層級、需審核選項",
+        "live_send_enabled": false,
+        "exit_condition": "OpenClaw + Security + QA 確認不含 secret、raw payload、工作視窗內容與誤導性執行按鈕。"
+      },
+      {
+        "stage_id": "tg_bridge_02_queue_preview_readback",
+        "title": "Gateway queue preview readback",
+        "status": "ready_for_owner_review",
+        "allowed_output": "queue envelope hash、message type、receipt expectation、rate-limit / dedup plan",
+        "live_send_enabled": false,
+        "exit_condition": "Hermes 讀回 preview hash，QA 確認不會寫入 production queue。"
+      },
+      {
+        "stage_id": "tg_bridge_03_approved_canary",
+        "title": "Approved canary delivery",
+        "status": "blocked_until_explicit_approval",
+        "allowed_output": "單一 approved canary 訊息與 receipt 驗證",
+        "live_send_enabled": false,
+        "exit_condition": "統帥明確批准 canary、指定時間窗與 rollback / mute plan。"
+      },
+      {
+        "stage_id": "tg_bridge_04_daily_weekly_monthly_digest",
+        "title": "日報 / 週報 / 月報 digest delivery",
+        "status": "blocked_until_canary_receipt",
+        "allowed_output": "Agent 工作量、完成度、阻擋項、圖表摘要與 low-noise digest",
+        "live_send_enabled": false,
+        "exit_condition": "canary receipt 正常、dedup 有效、成功訊息壓制策略通過。"
+      },
+      {
+        "stage_id": "tg_bridge_05_action_required_digest",
+        "title": "Action-required / high-risk approval digest",
+        "status": "blocked_until_dual_gate",
+        "allowed_output": "高風險審核卡、owner response 缺口、failure-only escalation",
+        "live_send_enabled": false,
+        "exit_condition": "OpenClaw 仲裁、Security gate、QA verifier 與 Telegram receipt 全通過。"
+      }
+    ],
+    "message_types": [
+      {
+        "message_type": "daily_agent_workload_digest",
+        "cadence": "daily",
+        "risk_tier": "low",
+        "owner_agent": "hermes",
+        "send_policy": "send_after_canary_and_dedup_gate"
+      },
+      {
+        "message_type": "weekly_governance_summary",
+        "cadence": "weekly",
+        "risk_tier": "medium",
+        "owner_agent": "hermes",
+        "send_policy": "send_after_canary_and_truth_gate"
+      },
+      {
+        "message_type": "monthly_growth_report",
+        "cadence": "monthly",
+        "risk_tier": "medium",
+        "owner_agent": "hermes",
+        "send_policy": "send_after_owner_review"
+      },
+      {
+        "message_type": "high_risk_approval_card",
+        "cadence": "event",
+        "risk_tier": "high",
+        "owner_agent": "openclaw",
+        "send_policy": "approval_required_before_send"
+      },
+      {
+        "message_type": "failure_only_escalation",
+        "cadence": "event",
+        "risk_tier": "critical",
+        "owner_agent": "sre_sentinel",
+        "send_policy": "failure_only_after_route_lock"
+      },
+      {
+        "message_type": "report_receipt_gap_alert",
+        "cadence": "event",
+        "risk_tier": "medium",
+        "owner_agent": "telegram_ops_liaison",
+        "send_policy": "no_send_preview_until_receipt_contract"
+      }
+    ]
+  },
+  "professional_task_domains": [
+    {"domain_id": "sre_observability", "label": "SRE / Observability", "owner_agent": "sre_sentinel"},
+    {"domain_id": "security_iwooos", "label": "Security / IwoooS", "owner_agent": "security_sentinel"},
+    {"domain_id": "devops_release", "label": "DevOps / Release", "owner_agent": "devops_commander"},
+    {"domain_id": "data_dr", "label": "Data / Backup / DR", "owner_agent": "data_dr_guardian"},
+    {"domain_id": "supply_chain", "label": "Supply Chain / Versions", "owner_agent": "supply_chain_scout"},
+    {"domain_id": "product_quality", "label": "Product / UI / QA", "owner_agent": "product_ui_curator"},
+    {"domain_id": "ai_governance", "label": "AI Governance / Replay / Market", "owner_agent": "openclaw"},
+    {"domain_id": "telegram_reporting", "label": "Telegram / Reports / Receipts", "owner_agent": "telegram_ops_liaison"}
+  ],
+  "professional_tasks": [
+    {"task_id": "pro_task_001_incident_correlation", "title": "跨來源 incident correlation 與根因候選排序", "domain_id": "sre_observability", "owner_agent": "sre_sentinel", "supporting_agents": ["openclaw", "hermes"], "risk_tier": "medium", "automation_mode": "no_write_dry_run", "telegram_policy": "action_required_preview", "required_mcp": ["observability", "gitea", "browser"], "required_rag": ["incident_traces", "runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["alert_rule_change", "silence_change", "restart_service"]},
+    {"task_id": "pro_task_002_alert_noise_budget", "title": "告警噪音預算與降噪提案", "domain_id": "sre_observability", "owner_agent": "sre_sentinel", "supporting_agents": ["hermes", "openclaw"], "risk_tier": "medium", "automation_mode": "proposal_only", "telegram_policy": "weekly_digest", "required_mcp": ["prometheus", "alertmanager"], "required_rag": ["alert_traces", "runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["receiver_route_change", "silence_policy_change", "prometheus_reload"]},
+    {"task_id": "pro_task_003_synthetic_check_plan", "title": "公開路由 synthetic check 與失敗分類計畫", "domain_id": "sre_observability", "owner_agent": "qa_verifier", "supporting_agents": ["product_ui_curator", "sre_sentinel"], "risk_tier": "low", "automation_mode": "auto_summary_after_guard", "telegram_policy": "daily_digest", "required_mcp": ["browser", "http_probe"], "required_rag": ["route_runbooks"], "approval_required": false, "current_live_count_24h": 0, "blocked_actions": ["active_scan", "production_write"]},
+    {"task_id": "pro_task_004_backup_restore_readiness", "title": "備份 freshness、restore drill 與 DR readiness 報告", "domain_id": "data_dr", "owner_agent": "data_dr_guardian", "supporting_agents": ["hermes", "openclaw"], "risk_tier": "high", "automation_mode": "approval_required_before_execution", "telegram_policy": "action_required_preview", "required_mcp": ["backup_status", "gitea"], "required_rag": ["dr_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["restore_run", "offsite_sync", "credential_escrow_marker_write"]},
+    {"task_id": "pro_task_005_non_secret_escrow_evidence", "title": "credential escrow 非敏感證據補件路由", "domain_id": "data_dr", "owner_agent": "data_dr_guardian", "supporting_agents": ["security_sentinel", "hermes"], "risk_tier": "critical", "automation_mode": "blocked_until_owner_response", "telegram_policy": "action_required_preview", "required_mcp": ["gitea"], "required_rag": ["dr_runbooks", "hard_rules"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["secret_value_collection", "credential_read", "marker_write_without_owner"]},
+    {"task_id": "pro_task_006_dependency_cve_triage", "title": "依賴 CVE / EOL / license 風險分流", "domain_id": "supply_chain", "owner_agent": "supply_chain_scout", "supporting_agents": ["openclaw", "security_sentinel"], "risk_tier": "medium", "automation_mode": "proposal_only", "telegram_policy": "weekly_digest", "required_mcp": ["package_registry", "osv"], "required_rag": ["dependency_policy"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["package_upgrade", "lockfile_write", "external_scan_without_approval"]},
+    {"task_id": "pro_task_007_sbom_license_drift", "title": "SBOM / license / Docker surface drift 批准包", "domain_id": "supply_chain", "owner_agent": "supply_chain_scout", "supporting_agents": ["hermes", "security_sentinel"], "risk_tier": "medium", "automation_mode": "proposal_only", "telegram_policy": "weekly_digest", "required_mcp": ["syft", "trivy"], "required_rag": ["supply_chain_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["tool_install", "image_pull", "sbom_upload"]},
+    {"task_id": "pro_task_008_image_digest_pin_plan", "title": "Docker image digest pinning 與 rollback 計畫", "domain_id": "supply_chain", "owner_agent": "devops_commander", "supporting_agents": ["supply_chain_scout", "qa_verifier"], "risk_tier": "high", "automation_mode": "approval_required_before_execution", "telegram_policy": "action_required_preview", "required_mcp": ["registry", "gitea"], "required_rag": ["release_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["image_pull", "image_push", "kustomization_write_without_review"]},
+    {"task_id": "pro_task_009_gitops_diff_review", "title": "K8s / ArgoCD manifest diff 與 blast-radius review", "domain_id": "devops_release", "owner_agent": "devops_commander", "supporting_agents": ["openclaw", "qa_verifier"], "risk_tier": "critical", "automation_mode": "approval_required_before_execution", "telegram_policy": "action_required_preview", "required_mcp": ["gitea", "argocd"], "required_rag": ["gitops_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["argocd_sync", "kubectl_apply", "helm_upgrade"]},
+    {"task_id": "pro_task_010_gateway_route_impact", "title": "Nginx / public gateway route impact analysis", "domain_id": "devops_release", "owner_agent": "devops_commander", "supporting_agents": ["security_sentinel", "qa_verifier"], "risk_tier": "critical", "automation_mode": "approval_required_before_execution", "telegram_policy": "action_required_preview", "required_mcp": ["gitea", "browser"], "required_rag": ["gateway_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["nginx_reload", "route_change", "certbot_renew"]},
+    {"task_id": "pro_task_011_public_bundle_redaction", "title": "前台 bundle / DOM / i18n 敏感資訊防洩漏掃描", "domain_id": "security_iwooos", "owner_agent": "security_sentinel", "supporting_agents": ["product_ui_curator", "qa_verifier"], "risk_tier": "medium", "automation_mode": "no_write_dry_run", "telegram_policy": "daily_digest", "required_mcp": ["browser", "gitea"], "required_rag": ["hard_rules"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["frontend_deploy_without_smoke", "secret_storage"]},
+    {"task_id": "pro_task_012_secret_metadata_parity", "title": "Secret name parity、injection route 與 redaction gate", "domain_id": "security_iwooos", "owner_agent": "security_sentinel", "supporting_agents": ["devops_commander", "openclaw"], "risk_tier": "critical", "automation_mode": "blocked_until_owner_response", "telegram_policy": "action_required_preview", "required_mcp": ["gitea"], "required_rag": ["secret_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["secret_value_read", "secret_rotation", "workflow_modification"]},
+    {"task_id": "pro_task_013_telegram_digest_preview", "title": "AI Agent 日週月報 Telegram no-send preview", "domain_id": "telegram_reporting", "owner_agent": "telegram_ops_liaison", "supporting_agents": ["hermes", "qa_verifier"], "risk_tier": "medium", "automation_mode": "no_write_dry_run", "telegram_policy": "no_direct_telegram", "required_mcp": ["telegram_gateway"], "required_rag": ["logbook_chunks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["telegram_send", "bot_api_call", "gateway_queue_write"]},
+    {"task_id": "pro_task_014_report_truth_gate", "title": "日報 / 週報 / 月報 truth gate 與可處置性審查", "domain_id": "telegram_reporting", "owner_agent": "hermes", "supporting_agents": ["openclaw", "sre_sentinel"], "risk_tier": "medium", "automation_mode": "auto_summary_after_guard", "telegram_policy": "weekly_digest", "required_mcp": ["gitea", "observability"], "required_rag": ["logbook_chunks", "incident_traces"], "approval_required": false, "current_live_count_24h": 0, "blocked_actions": ["false_green_report", "report_send_without_truth_gate"]},
+    {"task_id": "pro_task_015_agent_market_watch", "title": "主流 AI Agent / SDK / 模型版本市場雷達", "domain_id": "ai_governance", "owner_agent": "market_scout", "supporting_agents": ["openclaw", "nemotron"], "risk_tier": "medium", "automation_mode": "proposal_only", "telegram_policy": "weekly_digest", "required_mcp": ["web_primary_sources", "gitea"], "required_rag": ["agent_market_evidence"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["sdk_install", "paid_api_call", "production_route_change"]},
+    {"task_id": "pro_task_016_model_replay_scorecard", "title": "NemoTron / 候選模型 replay scorecard 與 failure mode 分析", "domain_id": "ai_governance", "owner_agent": "nemotron", "supporting_agents": ["openclaw", "qa_verifier"], "risk_tier": "high", "automation_mode": "no_write_dry_run", "telegram_policy": "action_required_preview", "required_mcp": ["fixture_store", "gitea"], "required_rag": ["replay_fixtures"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["shadow_route", "canary_route", "full_replay_without_approval"]},
+    {"task_id": "pro_task_017_cost_capacity_forecast", "title": "AI provider、主機、K3s 與外部服務成本 / 容量預測", "domain_id": "ai_governance", "owner_agent": "openclaw", "supporting_agents": ["supply_chain_scout", "sre_sentinel"], "risk_tier": "high", "automation_mode": "proposal_only", "telegram_policy": "monthly_digest", "required_mcp": ["observability", "billing_metadata"], "required_rag": ["cost_policy"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["paid_provider_switch", "limit_increase", "paid_api_call"]},
+    {"task_id": "pro_task_018_db_query_triage", "title": "PostgreSQL 慢查詢、索引與資料新鮮度異常 triage", "domain_id": "sre_observability", "owner_agent": "sre_sentinel", "supporting_agents": ["data_dr_guardian", "openclaw"], "risk_tier": "high", "automation_mode": "proposal_only", "telegram_policy": "action_required_preview", "required_mcp": ["database_readonly", "observability"], "required_rag": ["db_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["migration", "reindex", "write_query"]},
+    {"task_id": "pro_task_019_data_freshness_source_reliability", "title": "資料來源新鮮度、fallback 與來源可信度監控", "domain_id": "data_dr", "owner_agent": "hermes", "supporting_agents": ["sre_sentinel", "qa_verifier"], "risk_tier": "medium", "automation_mode": "auto_summary_after_guard", "telegram_policy": "daily_digest", "required_mcp": ["http_probe", "database_readonly"], "required_rag": ["data_quality_runbooks"], "approval_required": false, "current_live_count_24h": 0, "blocked_actions": ["source_switch_without_owner", "data_write"]},
+    {"task_id": "pro_task_020_ui_accessibility_regression", "title": "前後台 mobile overflow、console error、可讀性與 a11y regression", "domain_id": "product_quality", "owner_agent": "product_ui_curator", "supporting_agents": ["qa_verifier", "security_sentinel"], "risk_tier": "low", "automation_mode": "auto_summary_after_guard", "telegram_policy": "daily_digest", "required_mcp": ["browser"], "required_rag": ["frontend_guidelines"], "approval_required": false, "current_live_count_24h": 0, "blocked_actions": ["unrelated_redesign", "public_secret_display"]},
+    {"task_id": "pro_task_021_runbook_postmortem_draft", "title": "Runbook、postmortem 與 owner handoff 草稿", "domain_id": "ai_governance", "owner_agent": "hermes", "supporting_agents": ["openclaw", "sre_sentinel"], "risk_tier": "low", "automation_mode": "auto_summary_after_guard", "telegram_policy": "weekly_digest", "required_mcp": ["gitea"], "required_rag": ["logbook_chunks", "runbooks"], "approval_required": false, "current_live_count_24h": 0, "blocked_actions": ["canonical_km_write_without_review", "secret_in_doc"]},
+    {"task_id": "pro_task_022_owner_response_completeness", "title": "Owner response 欄位完整性、補件與拒收分流", "domain_id": "security_iwooos", "owner_agent": "security_sentinel", "supporting_agents": ["hermes", "openclaw"], "risk_tier": "high", "automation_mode": "proposal_only", "telegram_policy": "action_required_preview", "required_mcp": ["gitea"], "required_rag": ["owner_response_templates"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["mark_accepted_without_reviewer", "runtime_gate_open"]},
+    {"task_id": "pro_task_023_candidate_pr_draft_packaging", "title": "低 / 中風險候選 PR 草案、測試與 rollback 封包", "domain_id": "devops_release", "owner_agent": "devops_commander", "supporting_agents": ["qa_verifier", "openclaw"], "risk_tier": "medium", "automation_mode": "proposal_only", "telegram_policy": "action_required_preview", "required_mcp": ["gitea"], "required_rag": ["release_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["branch_push_without_approval", "auto_merge", "workflow_trigger"]},
+    {"task_id": "pro_task_024_post_action_verifier", "title": "Post-action verifier、rollback trigger 與 receipt reconciliation", "domain_id": "telegram_reporting", "owner_agent": "openclaw", "supporting_agents": ["telegram_ops_liaison", "qa_verifier"], "risk_tier": "critical", "automation_mode": "approval_required_before_execution", "telegram_policy": "failure_only_preview", "required_mcp": ["telegram_gateway", "observability", "gitea"], "required_rag": ["verification_runbooks"], "approval_required": true, "current_live_count_24h": 0, "blocked_actions": ["verifier_live_readback_without_gate", "rollback_without_owner", "telegram_send_without_receipt"] }
+  ],
+  "mcp_rag_stack": {
+    "mcp_connectors": [
+      "gitea",
+      "browser",
+      "observability",
+      "telegram_gateway",
+      "package_registry",
+      "database_readonly",
+      "backup_status",
+      "argocd_readonly",
+      "http_probe",
+      "fixture_store"
+    ],
+    "rag_sources": [
+      "LOGBOOK chunks",
+      "HARD_RULES / ADR chunks",
+      "runbook chunks",
+      "incident / alert traces",
+      "agent market evidence",
+      "owner response templates"
+    ],
+    "growth_metrics": [
+      "km_entries_created",
+      "playbook_updates",
+      "recommendations_created",
+      "replay_score_delta",
+      "blocked_action_prevented_count",
+      "receipt_missing_count"
+    ]
+  },
+  "risk_policy": {
+    "low": "文件、報表、UI smoke 與只讀摘要可在 guard 後自動處理並進每日 digest。",
+    "medium": "中風險只能先產 proposal、no-write dry-run 或 PR 草案；涉及設定、外部服務、成本、路由或未知狀態時升級審核。",
+    "high": "高風險必須 OpenClaw 仲裁、QA / Security gate 與統帥批准；不得自動執行。",
+    "critical": "production write、kubectl、ArgoCD sync、Telegram 實發、secret、付費 API、restore、rollback、host write 均維持 blocked until explicit approval。"
+  },
+  "reporting_contract": {
+    "daily": {"required": true, "owner_agent": "hermes", "telegram_stage": "tg_bridge_04_daily_weekly_monthly_digest"},
+    "weekly": {"required": true, "owner_agent": "hermes", "telegram_stage": "tg_bridge_04_daily_weekly_monthly_digest"},
+    "monthly": {"required": true, "owner_agent": "hermes", "telegram_stage": "tg_bridge_04_daily_weekly_monthly_digest"},
+    "action_required": {"required": true, "owner_agent": "openclaw", "telegram_stage": "tg_bridge_05_action_required_digest"}
+  },
+  "redaction_contract": {
+    "redaction_required": true,
+    "conversation_transcript_display_allowed": false,
+    "raw_prompt_display_allowed": false,
+    "private_reasoning_display_allowed": false,
+    "secret_value_display_allowed": false,
+    "raw_runtime_payload_display_allowed": false,
+    "telegram_message_must_be_sanitized": true,
+    "forbidden_terms": [
+      "work_window_transcript",
+      "raw prompt",
+      "private reasoning",
+      "chain-of-thought",
+      "telegram token",
+      "authorization header",
+      "secret value"
+    ]
+  },
+  "rollups": {
+    "professional_task_count": 24,
+    "domain_count": 8,
+    "telegram_stage_count": 5,
+    "telegram_message_type_count": 6,
+    "approval_required_count": 19,
+    "low_risk_task_count": 3,
+    "medium_risk_task_count": 10,
+    "high_risk_task_count": 6,
+    "critical_risk_task_count": 5,
+    "current_live_count": 0,
+    "gateway_queue_write_count": 0,
+    "telegram_send_count": 0,
+    "bot_api_call_count": 0,
+    "delivery_receipt_write_count": 0,
+    "production_write_count": 0,
+    "secret_read_count": 0,
+    "paid_api_call_count": 0,
+    "host_write_count": 0,
+    "kubectl_action_count": 0
+  }
+}

docs/schemas/ai_agent_professional_task_expansion_v1.schema.json

@@ -0,0 +1,329 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://awoooi.wooo.work/schemas/ai_agent_professional_task_expansion_v1.schema.json",
+  "title": "AI Agent Professional Task Expansion And Telegram Runtime Bridge",
+  "type": "object",
+  "required": [
+    "schema_version",
+    "generated_at",
+    "program_status",
+    "source_refs",
+    "telegram_runtime_bridge",
+    "professional_task_domains",
+    "professional_tasks",
+    "mcp_rag_stack",
+    "risk_policy",
+    "reporting_contract",
+    "redaction_contract",
+    "rollups"
+  ],
+  "properties": {
+    "schema_version": {
+      "const": "ai_agent_professional_task_expansion_v1"
+    },
+    "generated_at": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "program_status": {
+      "type": "object",
+      "required": [
+        "current_priority",
+        "current_task_id",
+        "next_task_id",
+        "overall_completion_percent",
+        "read_only_mode",
+        "runtime_authority",
+        "status_note"
+      ],
+      "properties": {
+        "current_priority": {
+          "enum": ["P0", "P1", "P2", "P3"]
+        },
+        "current_task_id": {
+          "const": "P2-405A"
+        },
+        "next_task_id": {
+          "const": "P2-405B"
+        },
+        "overall_completion_percent": {
+          "type": "integer",
+          "minimum": 0,
+          "maximum": 100
+        },
+        "read_only_mode": {
+          "const": true
+        },
+        "runtime_authority": {
+          "const": "professional_task_expansion_and_telegram_bridge_read_only_no_send"
+        },
+        "status_note": {
+          "type": "string",
+          "minLength": 1
+        }
+      },
+      "additionalProperties": true
+    },
+    "source_refs": {
+      "type": "array",
+      "minItems": 1,
+      "items": {
+        "type": "string"
+      }
+    },
+    "telegram_runtime_bridge": {
+      "type": "object",
+      "required": [
+        "canonical_room",
+        "canonical_room_env",
+        "gateway_required",
+        "no_send_preview_ready",
+        "queue_preview_readback_ready",
+        "approved_canary_required",
+        "direct_bot_api_allowed",
+        "bot_api_call_enabled",
+        "gateway_queue_write_enabled",
+        "telegram_send_enabled",
+        "delivery_receipt_write_enabled",
+        "stages",
+        "message_types"
+      ],
+      "properties": {
+        "canonical_room": {
+          "const": "AwoooI SRE 戰情室"
+        },
+        "canonical_room_env": {
+          "const": "SRE_GROUP_CHAT_ID"
+        },
+        "gateway_required": {
+          "const": true
+        },
+        "no_send_preview_ready": {
+          "const": true
+        },
+        "queue_preview_readback_ready": {
+          "const": true
+        },
+        "approved_canary_required": {
+          "const": true
+        },
+        "direct_bot_api_allowed": {
+          "const": false
+        },
+        "bot_api_call_enabled": {
+          "const": false
+        },
+        "gateway_queue_write_enabled": {
+          "const": false
+        },
+        "telegram_send_enabled": {
+          "const": false
+        },
+        "delivery_receipt_write_enabled": {
+          "const": false
+        },
+        "stages": {
+          "type": "array",
+          "minItems": 5,
+          "items": {
+            "type": "object"
+          }
+        },
+        "message_types": {
+          "type": "array",
+          "minItems": 6,
+          "items": {
+            "type": "object"
+          }
+        }
+      },
+      "additionalProperties": true
+    },
+    "professional_task_domains": {
+      "type": "array",
+      "minItems": 8,
+      "items": {
+        "type": "object"
+      }
+    },
+    "professional_tasks": {
+      "type": "array",
+      "minItems": 24,
+      "items": {
+        "type": "object",
+        "required": [
+          "task_id",
+          "title",
+          "domain_id",
+          "owner_agent",
+          "risk_tier",
+          "automation_mode",
+          "telegram_policy",
+          "required_mcp",
+          "required_rag",
+          "approval_required",
+          "current_live_count_24h",
+          "blocked_actions"
+        ],
+        "properties": {
+          "task_id": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "domain_id": {
+            "type": "string"
+          },
+          "owner_agent": {
+            "type": "string"
+          },
+          "risk_tier": {
+            "enum": ["low", "medium", "high", "critical"]
+          },
+          "automation_mode": {
+            "enum": [
+              "auto_summary_after_guard",
+              "no_write_dry_run",
+              "proposal_only",
+              "approval_required_before_execution",
+              "blocked_until_owner_response"
+            ]
+          },
+          "telegram_policy": {
+            "enum": [
+              "daily_digest",
+              "weekly_digest",
+              "monthly_digest",
+              "action_required_preview",
+              "failure_only_preview",
+              "no_direct_telegram"
+            ]
+          },
+          "required_mcp": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          },
+          "required_rag": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          },
+          "approval_required": {
+            "type": "boolean"
+          },
+          "current_live_count_24h": {
+            "const": 0
+          },
+          "blocked_actions": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          }
+        },
+        "additionalProperties": true
+      }
+    },
+    "mcp_rag_stack": {
+      "type": "object"
+    },
+    "risk_policy": {
+      "type": "object"
+    },
+    "reporting_contract": {
+      "type": "object"
+    },
+    "redaction_contract": {
+      "type": "object"
+    },
+    "rollups": {
+      "type": "object",
+      "required": [
+        "professional_task_count",
+        "domain_count",
+        "telegram_stage_count",
+        "telegram_message_type_count",
+        "approval_required_count",
+        "low_risk_task_count",
+        "medium_risk_task_count",
+        "high_risk_task_count",
+        "critical_risk_task_count",
+        "current_live_count",
+        "gateway_queue_write_count",
+        "telegram_send_count",
+        "bot_api_call_count",
+        "delivery_receipt_write_count",
+        "production_write_count",
+        "secret_read_count",
+        "paid_api_call_count",
+        "host_write_count",
+        "kubectl_action_count"
+      ],
+      "properties": {
+        "professional_task_count": {
+          "const": 24
+        },
+        "domain_count": {
+          "const": 8
+        },
+        "telegram_stage_count": {
+          "const": 5
+        },
+        "telegram_message_type_count": {
+          "const": 6
+        },
+        "approval_required_count": {
+          "const": 19
+        },
+        "low_risk_task_count": {
+          "const": 3
+        },
+        "medium_risk_task_count": {
+          "const": 10
+        },
+        "high_risk_task_count": {
+          "const": 6
+        },
+        "critical_risk_task_count": {
+          "const": 5
+        },
+        "current_live_count": {
+          "const": 0
+        },
+        "gateway_queue_write_count": {
+          "const": 0
+        },
+        "telegram_send_count": {
+          "const": 0
+        },
+        "bot_api_call_count": {
+          "const": 0
+        },
+        "delivery_receipt_write_count": {
+          "const": 0
+        },
+        "production_write_count": {
+          "const": 0
+        },
+        "secret_read_count": {
+          "const": 0
+        },
+        "paid_api_call_count": {
+          "const": 0
+        },
+        "host_write_count": {
+          "const": 0
+        },
+        "kubectl_action_count": {
+          "const": 0
+        }
+      },
+      "additionalProperties": true
+    }
+  },
+  "additionalProperties": true
+}

docs/superpowers/specs/2026-04-15-MASTER-ai-autonomous-flywheel-v2.md

@@ -638,6 +638,7 @@ Alert / Sentry / SigNoz / Gitea / Market Watch / Operator
 | `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_professional_task_expansion_2026-06-15.json` + `GET /api/v1/agents/agent-professional-task-expansion` | P2-405A AI Agent 專業任務擴展與 Telegram Runtime Bridge；承接 12-Agent War Room、P2-403 report/runtime 鏈與 monitoring owner response acceptance，固定 24 類專業任務、8 個任務領域、5 段 Telegram bridge、6 種訊息類型、MCP/RAG stack、日報 / 週報 / 月報 / action-required 報告契約，並接入 governance automation inventory 卡片；需批准任務 `19`、low / medium / high / critical = `3 / 10 / 6 / 5`；Gateway queue write、Telegram send、Bot API、delivery receipt、production write、secret read、paid API、host write 與 kubectl action 全部 `0 / false`，下一步 P2-405B 完整 no-send message preview / canary approval package |
 | `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`，已由 P2-104 承接 |
@@ -840,6 +841,7 @@ Repo / registry / release notes / K8s / host / observability / backup evidence
 64. 建立 owner response preflight 與拒收邊界。✅ P2-143 已完成正式驗證；承接 P2-141 decision input prep 與 P2-142 War Room 基線，固定 response intake lane `5`、required owner field `18`、intake validation check `6`、rejection guard `6`、operator action `5`、waiting external response `5`；owner response received / accepted / rejected、redacted payload ingested、reviewer queue write、Gateway queue write、Telegram send、Bot API、result capture、learning、PlayBook trust、production write、secret read、destructive operation 仍為 `0 / false`；feature commit `755b0a8d`、deploy marker `667d6329`、Gitea code-review `2961` / CD `2960` success、本地 P2-142 War Room + P2-139 至 P2-143 regression `37 passed`、JSON parse、Python compile、Web typecheck、guard、doc secret sanity、禁用外露值掃描、production API readback 與 desktop / mobile smoke 通過。下一步 P2-144 owner response readback。
 65. 建立 owner response readback。✅ P2-144 已完成正式驗證；承接 P2-143 preflight，固定 response readback lane `5`、required owner field `18`、readback validation check `6`、readback rejection guard `6`、operator action `5`、waiting external response `5`、no external response received lane `5`；owner response received / accepted / rejected、redacted payload ingested、reviewer queue write、Gateway queue write、Telegram send、Bot API、result capture、learning、PlayBook trust、production write、secret read、destructive operation 仍為 `0 / false`；feature commit `8795f100`、deploy marker `ac938037`、Gitea code-review `2965` / CD `2964` success；本地 P2-139 至 P2-144 regression `45 passed`，rebase 後含 tenants regression 的推送前回歸 `47 passed`、JSON parse、Python compile、Web typecheck、guard、doc secret sanity、value-only 禁用外露值掃描、i18n key parity 與 diff check 通過；production API readback、desktop / mobile smoke、水平溢位 `0`、危險控制 `0`、工作溝通片語命中 `0` 已完成。下一步 P2-145 owner response acceptance gate。
 66. 建立 owner response acceptance gate。✅ P2-145 已完成並正式驗證；承接 P2-144 readback，固定 acceptance gate lane `5`、required owner field `18`、acceptance validation check `6`、acceptance rejection guard `6`、operator action `5`、blocked no external response `5`、no acceptable external response `5`；owner response received / accepted / rejected、redacted payload ingested、reviewer queue write、Gateway queue write、Telegram send、Bot API、result capture、learning、PlayBook trust、production write、secret read、destructive operation 仍為 `0 / false`；feature commit `386dbd07`、deploy marker `36fbfc6b`、Gitea code-review `2969` / CD `2968` success；P2-144 + P2-145 regression `16 passed`、JSON parse、Python compile、Web typecheck、guard、doc secret sanity、顯示值工作視窗污染掃描、i18n key parity、diff check、production API readback、in-app browser smoke、desktop / mobile smoke、水平溢位 `0`、P2-145 卡片操作控制 `0`、工作溝通片語命中 `0` 已完成。下一步 P2-146 acceptance receipt preview，且必須等合格、遮罩、欄位完整、可驗證來源的外部正式回覆後才能建立 receipt preview。
+66a. 建立 AI Agent 專業任務擴展與 Telegram Runtime Bridge。✅ P2-405A 本地完成；承接 12-Agent War Room、P2-403 report/runtime 鏈與 monitoring owner response acceptance，固定 24 類專業任務、8 個領域、5 段 Telegram bridge、6 種訊息類型與 MCP/RAG stack，並接入 governance automation inventory 卡片；需批准任務 `19`、low / medium / high / critical = `3 / 10 / 6 / 5`；Gateway queue write、Telegram send、Bot API、delivery receipt、production write、secret read、paid API、host write、kubectl action 仍為 `0 / false`。下一步 P2-405B 完整 no-send message preview / canary approval package；這不占用 P2-146 owner response receipt preview。
 67. 新增 P0 配置控管優先序前台可視化。✅ 正式驗證完成；`/zh-TW/iwooos` 已集中顯示 Nginx public gateway、DNS / TLS / certbot、K8s / ArgoCD / production manifests、Workflow / runner / secret metadata、Public / admin / API runtime config、agent-bounty runtime / treasury 六類即時風險配置；owner response `0 / 0`、live evidence `0`、執行期 `0`、操作按鈕 `0`；feature commit `e992af89`、deploy marker `ed651a98`、Gitea code-review `2971` / CD `2970` success；本地與正式 in-app browser、desktop `1440x1100`、mobile `390x844` smoke 通過。這不是 Nginx live conf 讀取、`nginx -t`、reload、DNS / TLS probe、certbot renew、ArgoCD sync、kubectl、workflow / secret 修改、public route change、agent-bounty runtime、payout / withdrawal、production write 或 runtime gate。
 68. 補強 P0 高價值配置 Gate path pattern、工作樹 preflight、owner packet 與 coverage snapshot。✅ 本地完成；`k8s/nginx/**`、`scripts/ops/**/*cert*`、`scripts/ops/**/*tls*` 已納入 high-value config classification，Nginx public gateway 與 DNS / TLS / certbot sample 從 `matched=0 / C0=0` 收斂到 `matched=3 / C0=2`；gate snapshot 顯示 `changed_files=6`、`matched=6`、`categories=3`、`c0=2`、`c1=0`；預設模式已可讀取 staged / unstaged / untracked，臨時 `k8s/nginx/*` smoke 命中 C0；owner packet snapshot `packets=3 / c0=2 / runtime_gate=0`；coverage snapshot `categories=14 / c0=8 / avg=67 / runtime_gate=0`；owner evidence 仍 `provided=false / complete=false`，runtime execution 仍 `false`。這不是 live config read、`nginx -t`、reload、certbot renew、DNS / TLS probe、host write、active scan、workflow 修改、secret 收集、production write 或 runtime gate。
 69. 同步高價值配置 Owner Packet 前台 projection。✅ 已完成並正式驗證；`/zh-TW/iwooos` 與 `/zh-TW/awooop` 已顯示 owner packet snapshot `packet=3 / c0=2`、最高命中 `C0 / P0`、Nginx public gateway、DNS / TLS / certbot 與 security tooling 影響範圍；feature commit `e999c16b`、deploy marker `16c6b983`、Gitea code-review `2973` / CD `2972` success；request sent、received、accepted、runtime gate 與 action buttons 仍為 `0`；本地與正式 desktop / mobile / in-app browser smoke 已通過，水平溢位 `0`、卡片內操作控制 `0`、危險連結 `0`、工作溝通片語命中 `0`。不得因此調高 IwoooS headline。
@@ -892,6 +894,7 @@ Repo / registry / release notes / K8s / host / observability / backup evidence
 | `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；5 個 dry-run artifact、3 個 queue digest 草案、4 個 readback verifier case、3 個 Agent dry-run role、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 |
 | `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；5 個 fixture smoke、3 個 queue preview readback、4 個 verifier dry-run case、3 個 Agent fixture role、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 |
 | `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；5 個 shadow candidate、4 個 no-write replay、4 個 verifier shadow case、3 個 Agent shadow role、6 個 operator checkpoint；不啟動 live worker、不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不寫 production target |
+| `docs/evaluations/ai_agent_professional_task_expansion_2026-06-15.json` + `GET /api/v1/agents/agent-professional-task-expansion` | P2-405A AI Agent 專業任務擴展與 Telegram Runtime Bridge；24 類專業任務、8 個領域、5 段 Telegram bridge、6 種訊息類型、MCP/RAG stack、治理頁 P2-405A 卡片；不寫 Gateway queue、不送 Telegram、不呼叫 Bot API、不寫 production target、不讀 secret、不用 paid API |
 | `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 |
@@ -4977,3 +4980,16 @@ Trigger commit `f5cd37b7` 與 deploy marker `0ba92357` 已把 governance UI 的
 - `iwooos-config-control-guard.py`、`security-mirror-progress-guard.py` 與高價值配置 coverage 已鎖住新 artifact；`monitoring_alerting_observability` 只讀治理成熟度 `62% -> 66%`，高價值配置平均只讀治理成熟度 `68% -> 69%`。
 
 **裁決：** 這是 owner response acceptance 只讀帳本，不是 owner response received / accepted / rejected、live evidence、Prometheus reload、Alertmanager reload、Grafana import、SigNoz apply、Sentry deploy、Langfuse config change、OTEL reload、receiver route change、silence change、Telegram send、live alert fire、alert chain smoke、secret collection、host write、production write 或 runtime gate；IwoooS headline 仍維持 `64%`，active runtime gate 仍 `0`。
+
+### 2026-06-15 10:40 (台北) — §3.2 / §5 — 新增 AI Agent 專業任務擴展與 Telegram Runtime Bridge — 把專業委派與 TG 群組整合前置門檻固定成 no-send guard artifact
+
+**觸發**：統帥要求繼續專業評估 AI Agent 還可以承接哪些工作，並指出 Telegram 群組 / TG Bot 需要真正納入整體監控、報表、告警與審核路徑。既有 12-Agent War Room 已定義分工，但還缺一份可由 API 讀回、可測試、可禁止誤啟用的專業任務擴展契約。
+
+**已推進：**
+- 新增 `docs/schemas/ai_agent_professional_task_expansion_v1.schema.json`、`docs/evaluations/ai_agent_professional_task_expansion_2026-06-15.json`、`apps/api/src/services/ai_agent_professional_task_expansion.py` 與 `GET /api/v1/agents/agent-professional-task-expansion`。
+- 新增 `docs/ai/AI_AGENT_PROFESSIONAL_TASK_EXPANSION_2026-06-15.md`，把 24 類專業任務拆成 SRE / Observability、Security / IwoooS、DevOps / Release、Data / Backup / DR、Supply Chain、Product / UI / QA、AI Governance / Replay / Market、Telegram / Reports / Receipts 8 個領域。
+- `/zh-TW/governance?tab=automation-inventory` 新增 P2-405A 卡片，顯示任務數、風險分層、Telegram bridge、脫敏狀態與 live / send / write = 0。
+- Telegram Runtime Bridge 固定 5 段：no-send preview、queue preview readback、approved canary、日週月報 digest、action-required digest；所有 live send / queue write / Bot API call / receipt write 仍為 `0 / false`。
+- 任務風險 rollup 固定：總任務 `24`、需批准 `19`、low / medium / high / critical = `3 / 10 / 6 / 5`；高風險與 critical 任務必須保留 approval gate。
+
+**裁決：** 這是專業任務與 Telegram 整合的只讀擴展契約，不是 Telegram send、Gateway queue write、Bot API call、delivery receipt write、production write、host write、kubectl action、secret read、paid API call 或 runtime authorization；下一步 P2-405B 只能做完整 no-send message preview 與 canary approval package，可讓統帥看到將來 TG 訊息長相，但仍不得實發。