feat(ai): automate agent integration truth and RAG canary

docs/guides/ai_automation_mainline_work_items.md

@@ -1,6 +1,6 @@
 # AI Automation Mainline Work Items
 
-> Updated: 2026-07-16 16:08 Asia/Taipei
+> Updated: 2026-07-17 01:25 Asia/Taipei
 > Governance: `global_product_governance_v2` + ADR-038
 > Current P0: `GROWTH-P0-001 comparison coverage truth + autonomous refresh`
 
@@ -23,7 +23,7 @@
 | 5 | `SUPPLY-P0-001` | In progress | Gitea-only secure software supply chain | Gitea-native checkout, secret-safe `.dockerignore`, commit-bound source receipt and governance gate are active. Exit: exact dependency lock, internal SAST/SCA/secret scan, SBOM, image digest/provenance, vulnerability SLA and production digest readback. |
 | 6 | `GOV-P0-001` | In progress | Canonical full asset graph + runtime reconciliation | `governance/ewoooc_asset_inventory.json` seeds hosts, services, data, AI, routes, supply chain, observability and recovery. Exit: same-run probe receipt for every asset; drift auto-creates work items. |
 | 7 | `GOV-P0-002` | Not started | Unified controlled-apply envelope | Introduce one `trace_id/run_id/work_item_id` across sensor, identity, SOT diff, decision, risk, dry-run, execution, verifier, rollback/retry and learning acknowledgement. Start with EventRouter + AutoHeal. |
-| 8 | `RAG-P0-001` | Not started | Internal RAG candidate canary | V10.770 stops at candidate preview. Exit: bounded pgvector candidate canary, signature/readback/feedback receipt, no price write and no premature `ai_insights` promotion. Next: `run_internal_rag_candidate_canary`. |
+| 8 | `RAG-P0-001` | In progress (`scheduled_source_ready_runtime_unproven`) | Internal RAG candidate canary | V10.811 source adds `internal_rag_candidate_canary_service`, read-only authenticated API, CLI, smoke adapter and a default-enabled daily 04:45 scheduler run. The bounded executor processes at most one candidate, requires both GCP-A/GCP-B, runs pgvector similarity inside `SET TRANSACTION READ ONLY`, always rolls back, writes only a canary artifact/scheduler receipt and records Telegram acknowledgement; it cannot write `ai_insights` or price tables. Exit still requires production candidate/executed receipts, immutable model reference, controlled `RAG_ENABLED` shadow activation, query/hit telemetry and feedback readback. Source/test readiness is not runtime closure. |
 | 9 | `MCP-P0-001` | In progress (`federation_source_ready`) | MCP/RAG production runtime closure | V10.796 source adds a strict public aggregate receipt for canonical `ewoooc` and `momo-pro-system` identities without opening authenticated internal APIs or exposing endpoint/tool payload data. Exit still requires V10.796 production `/health`, two fresh AWOOOI durable receipts with fingerprint recompute, live MCP servers/router/RAG, approved caller/tool boundary and production query canary. Current source readiness must not be reported as runtime closure. |
 | 10 | `SEC-P0-004` | Not started | Security operations lifecycle and metrics | Add durable security incident state and publish MTTA, MTTR, recurrence, false positive, human intervention, verifier pass, rollback and freshness. Exit: detect-to-learn production receipt. |
 | 11 | `REL-P0-001` | In progress (`runtime_verified_cd_degraded`) | Formal deploy and visible proof discipline | Production V10.810 runs exact Gitea object `911393190ded015e384e438c26b68faf50ec260c`; dev merge `e56c613399affb5cf0134eea44b7f78aa8134943` carries the same source. Host 110 still exposes only paused `vibework-dedicated-runner`, with no matching EwoooC runner, so this release has no formal CD execution receipt. The controlled fallback archive SHA-256 is `cd0607d593fd16c8281b5f01839d20d7eba493f49d363cb197c30966c25be5ee`; archive, checksum manifest and rollback (`02e73678125ee0c8908a42be8fff479287180fa2c06f6efe7dce70c2ce7339a4`) are retained at `/home/ollama/momo-deploy-backups/analytics-ui-20260716T080302Z-9113931`. Internal/external `/health` is healthy at V10.810; only `momo-app` was recreated, while scheduler ID `9af8e31fd0eb90f74ce5894af1ae1fbc511362ec90df142fde6442cf737d1181`, Telegram bot ID `1d4bd922f6ad1252177ba40f16ea172dcd5eb1de1b4c999c00f4a3141bd06ca5` and `momo-db` immutable ID `cd092451cb5fd555d0ffff70642e109f3b742882c418beeab631793d1e9dc55d` did not change. Runner recovery remains a release-governance gap and is not replaced by fallback evidence. |
@@ -38,6 +38,17 @@ These lanes are one ordered current P0, not optional side work. They must advanc
 | B. Verified same-item evidence | In progress | TOP50 fixed cohort: `25` verified, `1` candidate/source validation, `24` unmatched. Count coverage is `50%`; revenue-weighted coverage is `NT$211,667 / NT$354,062 = 59.782%`. V10.810 preserves fingerprint `7b74504fcc1e1801c2ca2b42`; run `34999f5314054f09909663b46fc42ee2` added one independently verified offer (`+2.0pp` count, `+1.89pp` revenue), while run `e1508ec3a49241d1965bc99d428b0325` correctly ended no-write. Their durable artifact SHA-256 values are `994beba6dfa70ef8c50031f130916ee155657dd77ac8a2f59b6530b491d45d1e` and `e58be7bb07599871a8f318ad63885bd868c786b0144b81ba0980ae80cf556541`. | Retry unresolved candidates only after fresh evidence arrives, preserve deterministic identity/unit/variant gates, and publish count/revenue deltas against the same fingerprint per run. |
 | C. Platform runtime coverage | In progress (`runtime_canary_activated`) | V10.810 is live. Yahoo is durably active and exact-offer canary readback remains valid; an already-active canary now returns `already_active_verified`, `state_changed=false` and `writes_database_count=0`, while latest no-write receipts no longer erase durable activation truth. Formal runtime is `2/15`; PixelRAG remains evidence-only. | Continue bounded refresh on schedule, monitor expiry/recurrence/rollback signals, then implement the next approved structured source contract for Shopee, Coupang, ETMall, Friday or Rakuten without treating blocked pages as product data. |
 
+### AI Agent Product Integration Acceptance
+
+This is an acceptance surface inside the current growth P0; it does not reorder the P0 queue. V10.811 source replaces class/method-presence optimism with a seven-day production telemetry readback.
+
+| Layer | Current status | Exit evidence |
+|---|---|---|
+| Source and scheduler wiring | Source ready (`4/4`) | Hermes, NemoTron, OpenClaw and ElephantAlpha source markers plus scheduler ownership are machine-read and reported separately from runtime. |
+| Agent runtime activity | Production baseline partial (`2/4`) | The pre-release live readback found Hermes `1` call / `1` error, OpenClaw `13` calls / `4` errors, and zero NemoTron/ElephantAlpha calls in seven days. Exit requires all four active and healthy in the bounded window, without treating a configured fallback as activity. |
+| MCP/RAG dependency | Runtime disabled / telemetry empty | Production currently reports `MCP_ROUTER_ENABLED=false`, `RAG_ENABLED=false`, zero `mcp_calls` and zero `rag_query_log` activity. Exit requires enabled approved routes, live health, non-zero agent/product telemetry and the internal RAG candidate canary. |
+| Controlled automation closure | Runtime partial | `/api/ai-automation/agent-product-integration`, CLI and smoke must report Detect -> Normalize -> Correlate -> Decide -> Check -> Controlled Apply -> Verify -> Retry/Rollback -> Learn/Writeback. Completion requires bounded execution, linked outcome/incident verification and durable learning evidence; aggregate source presence is insufficient. |
+
 ### Analytics Period-Linkage Closure
 
 This bounded interruption is closed and control returns to `GROWTH-P0-001` without changing its lane order.
@@ -85,7 +96,8 @@ These are reusable foundations, not proof that the full program is complete.
 | Completed | Marketplace identity matcher replay | Candidate identity only. |
 | Completed | PromotionGate replay | No production write. |
 | Completed | Embedding-signature guard replay | Signature readiness only. |
-| Completed | Candidate knowledge replay | Internal RAG preview only; canary remains P0. |
+| Completed | Candidate knowledge replay | Internal RAG preview only; no DB/model call. |
+| Scheduled source ready | Internal RAG candidate canary | Daily bounded pgvector/Ollama canary exists in V10.811 source with same-run identity, rollback/no-write terminal and Telegram acknowledgement; production execution, model pin and RAG shadow activation remain P0. |
 | Completed | PixelRAG application portfolio | Commerce/RAG/UX/ops/marketing/governance inventory. |
 | Completed | Ollama-first VLM route readiness and replay worker | Evidence-bound artifact output; no direct price write. |
 | Completed | Platform probe worker | Shopee/Coupang barriers become structured fallback/backoff receipts. |