fix(ai): detect PixelRAG marketplace interstitials

This commit is contained in:
ogt
2026-07-10 00:49:54 +08:00
parent c491723961
commit 83f6d2e255
5 changed files with 124 additions and 3 deletions

View File

@@ -887,6 +887,7 @@ POSTGRES_HOST=momo-db
| 2026-07-10 | PixelRAG VLM no-probe 監控不得把 unknown 顯示成 failed | V10.755 起 smoke / scheduled-health 的 `pixelrag_vlm_route_readiness.details.generate_route_ready``generate_probe_performed=false` 時必須保留為 `null`,表示尚未做 `/api/generate` preflight不得把未探測狀態轉成 `false`,避免 UI 或監控把 tags-only readiness 誤讀為 generate failure。 |
| 2026-07-10 | PixelRAG VLM 空欄位與 Shopee language interstitial 必須自動轉 platform probe | V10.756 起 VLM prompt 明確把 language / region / app-download / landing / loading / logo-only / cookie consent pages 視為非商品卡;若 VLM 回傳所有 offer fields 皆空且 required title / price 缺失worker 會標記 `non_product_or_interstitial_detected=true`receipt 下一步改為 `run_platform_probe_or_use_structured_api`,不得反覆要求人工審核或無限 rerun VLM。 |
| 2026-07-10 | PixelRAG VLM worker preflight 必須容納 111 VLM 冷啟延遲 | V10.757 起 `run_pixelrag_vlm_replay_worker.py --execute` 與對應 API 的 `route_generate_probe_timeout` 預設為 20 秒111 `minicpm-v` 在正式環境可於約 4 到 20 秒間完成小型 `/api/generate` probe8 秒容易造成假陰性。若 VLM receipt 已判定 `run_platform_probe_or_use_structured_api`run-level `next_machine_action` 也必須同樣輸出 platform probe不得停留在 rerun VLM 摘要。 |
| 2026-07-10 | PixelRAG VLM language note / generic marketplace slogan 必須視為 interstitial | V10.758 起若 VLM notes 或 title 顯示 `Language selection page`、語言/地區選擇,或只抽到 Shopee `蝦皮購物 | 花得更少買得更好` 這類網站 slogan 且 price/shop 缺失worker validation 會標記 `interstitial_signal_detected` / `generic_marketplace_title_detected``non_product_or_interstitial_detected=true`run-level 與 item-level 下一步都輸出 `run_platform_probe_or_use_structured_api`。 |
| 2026-06-29 | PChome DB apply 授權 lane 必須先通過 no-write guard / decision preflight / decision closeout / issuer gate / signing-decision preflight / signing-decision closeout / signing-issuer guard | V10.725 的 PChome mapping backlog auto-policy 已新增 `/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-lane-guard``/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-decision-preflight``/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-decision-closeout``/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-issuer-gate``/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-signing-decision-preflight``/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-signing-decision-closeout``/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-signing-issuer-guard`;這些 endpoint 只驗證 final exact request package、same-run production truth requirement、secret rejection、rollback boundary、lane entry requirements、decision input requirements、rejection policy、post-apply verifier、future authorization decision package、final nonsecret authorization envelope、signing decision preflight inputs、unsigned signing decision package 與 signable request boundary不讀 secret、不執行 shell/SQL、不寫 DB也不簽發 database apply authorization。 |
| 2026-06-29 | PChome DB apply 授權簽署發行者 lane 必須先產出 final signable request package | V10.725 的 PChome mapping backlog auto-policy 新增 `/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-signing-issuer-closeout`;此 endpoint 只把 signing-issuer guard 的 signable request boundary 收斂成 final signable request package 與 closeout contract確認 fresh production truth、post-apply verifier、migration hash、secret boundary 與 no-side-effect checks不讀 secret、不簽發 authorization、不執行 shell/SQL、不寫 DB也不代表正式 DB apply 已授權。 |
| 2026-06-29 | PChome DB apply 授權簽署執行 lane 必須先通過 operator-held secret boundary preflight | V10.725 的 PChome mapping backlog auto-policy 新增 `/api/ai/pchome-growth/mapping-backlog/auto-policy-db-apply-authorization-signing-execution-preflight`;此 endpoint 只把 final signable request package 轉成 future signing execution preflight package、operator-held secret boundary contract、nonsecret signing inputs、command-shape preview、rollback boundary 與 abort conditions不讀 secret、不接受 plaintext secret、不簽發 authorization、不執行 shell/SQL、不寫 DB也不代表正式 DB apply 已授權。 |