# AI Automation Mainline Work Items

> Updated: 2026-07-10
> Scope: EwoooC / MOMO Pro System AI automation, PixelRAG, MCP/RAG, production UX.

## Source Of Truth

- Production readback stays authoritative after deploy: `/health`, container health, AI automation API readback, and smoke.
- Gitea is the only source-control truth. GitHub remains frozen and must not be used.
- Runtime truth must stay separate from source truth: a green test or registry does not mean MCP/RAG runtime is enabled.
- PixelRAG visual receipts are evidence, not formal price truth. They cannot write `competitor_prices`, `competitor_price_history`, or `ai_insights` without replay and promotion gates.

## P0

| Status | Work item | Evidence / next machine action |
|---|---|---|
| Completed | Multi-commerce PixelRAG visual evidence lane for momo, pchome, shopee_tw, coupang_tw, yahoo_shopping_tw, etmall_tw, friday_tw, rakuten_tw | API and CLI can emit expansion plans and marketplace manifests; PChome parser failures can queue manifests. |
| Completed | External MCP/RAG capability inventory absorbed into internal governance readback | `/api/ai-automation/external-mcp-rag-integration` and `scripts/ops/report_external_mcp_rag_integration.py` expose 9 capabilities, absorbed/unresolved counts, and runtime flags. |
| Completed | PixelRAG receipts to internal RAG candidate replay | `/api/ai-automation/pixelrag-rag-candidate-replay` and `scripts/ops/report_pixelrag_rag_candidate_replay.py` read visual capture receipts and platform probe worker receipts, split eligible / blocked / source-contract-fallback candidates, and expose combined OCR/VLM + source-contract next actions before identity matching and PromotionGate knowledge writes. |
| Completed | PixelRAG source-contract replay worker | `/api/ai-automation/pixelrag-source-contract-replay-worker` and `scripts/ops/run_pixelrag_source_contract_replay_worker.py` turn platform probe worker `source_contract_fallback` receipts into replayable source-contract artifact receipts with provenance, public-boundary, no-DB, and blocked-page-not-product-data guards. |
| Completed | PixelRAG application portfolio and integration lanes | `/api/ai-automation/pixelrag-application-portfolio` and `scripts/ops/report_pixelrag_application_portfolio.py` expose commerce, RAG, UX, ops, marketing, and governance uses with priority, status, next machine action, and forbidden guardrails. |
| Completed | PixelRAG Ollama-first VLM replay worker | `/api/ai-automation/pixelrag-vlm-replay-worker` and `scripts/ops/run_pixelrag_vlm_replay_worker.py` dry-run or execute ready visual receipts against approved Ollama VLM routes, emit evidence-bound artifact receipts, and keep blocked pages out of product data. |
| Completed | PixelRAG VLM route readiness and auto model select | `/api/ai-automation/pixelrag-vlm-route-readiness` and `scripts/ops/report_pixelrag_vlm_route_readiness.py` read approved Ollama `/api/tags`, expose configured/candidate model readiness, and let execute mode avoid missing-model blind generate calls. |
| Completed | PixelRAG platform probe worker | `/api/ai-automation/pixelrag-platform-probe-worker` and `scripts/ops/run_pixelrag_platform_probe_worker.py` turn platform probe plans into dry-run/execute automation: Shopee interstitials go to public empty-context capture when runtime is available, missing Playwright auto-falls back to structured-source/backoff receipt, and Coupang 403/access denied goes to structured-source/backoff artifact receipts. |
| In progress | MCP/RAG runtime health in AI automation smoke | `/api/ai-automation/smoke` and `/api/ai-automation/scheduled-health-summary` include external MCP/RAG integration, PixelRAG RAG candidate replay, PixelRAG OCR/VLM replay contract, PixelRAG VLM route readiness, PixelRAG VLM replay worker, PixelRAG platform probe, and PixelRAG platform probe worker families. |
| In progress | Formal production deploy/readback discipline | Every mainline change must update version, push Gitea main/dev, deploy to 188 without touching `momo-db`, and read back `/health` plus new endpoints. |

## P1

| Status | Work item | Evidence / next machine action |
|---|---|---|
| Completed | OCR/VLM replay contract for visual fields | `/api/ai-automation/pixelrag-ocr-vlm-replay` and `scripts/ops/report_pixelrag_ocr_vlm_replay.py` turn saved tiles into no-write field contracts, output schemas, validation rules, and Ollama-first worker actions. |
| Completed | Ollama-first OCR/VLM extraction worker | `run_pixelrag_vlm_replay_worker.py --execute --write-receipt` executes the replay contract against approved Ollama multimodal routes and emits confidence/evidence artifact receipts without writing formal price truth. |
| Not started | Ollama-first multimodal embedding benchmark | Verify local Qwen3-VL or equivalent visual embedding on GCP-A -> GCP-B -> 111 before any visual vector retrieval. |
| Not started | pgvector-compatible visual evidence metadata | Design metadata-first retrieval without FAISS in production unless ADR approves a different store. |
| In progress | Coupang platform probe / structured API strategy | Treat 403 as platform barrier; `run_pixelrag_platform_probe_worker.py --execute --write-receipt` now emits structured-source/backoff receipts without network, DB writes, or product-data promotion. |
| In progress | Marketplace source contracts beyond MOMO/PChome | Platform probe worker receipts now enter source-contract replay as artifact receipts; next machine action is marketplace source-contract adapter replay preflight for stable Shopee/Coupang/Yahoo/ETMall/friday/Rakuten contracts after provenance, rate-limit, public boundary, and replay evidence. |
| In progress | Professional product website UI/UX text reduction | Continue compact AI surfaces, visual QA, and user-facing copy guardrails; avoid engineering logs or work-session prose in the UI. |

## Always Enforced

- Manual review is exception-only for low-risk, machine-verifiable controlled apply.
- Break-glass still applies to secrets, destructive DB actions, force pushes, production provider switchovers, raw runtime volumes, and unverified core model replacement.
- AI automation smoke must expose health honestly: `MCP_ROUTER_ENABLED=false` or `RAG_ENABLED=false` is a runtime gap, not a source-code failure.