From 3c92ea7df99227e5abce5c49627aa96637c85192 Mon Sep 17 00:00:00 2001 From: ogt Date: Fri, 10 Jul 2026 11:32:30 +0800 Subject: [PATCH] feat(ai): add PixelRAG marketplace adapter dry run --- config.py | 2 +- docs/AI_INTELLIGENCE_MODULE_SOT.md | 4 +- .../ai_automation_mainline_work_items.md | 3 +- docs/guides/browse_sh_crawler_playbook.md | 4 + routes/system_public_routes.py | 37 ++ ...etplace_source_contract_adapter_dry_run.py | 77 +++ services/ai_automation_smoke_service.py | 141 +++++ ...source_contract_adapter_dry_run_service.py | 539 ++++++++++++++++++ tests/test_ai_automation_smoke_service.py | 38 +- ...source_contract_adapter_dry_run_service.py | 259 +++++++++ 10 files changed, 1097 insertions(+), 7 deletions(-) create mode 100755 scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py create mode 100644 services/pixelrag_marketplace_source_contract_adapter_dry_run_service.py create mode 100644 tests/test_pixelrag_marketplace_source_contract_adapter_dry_run_service.py diff --git a/config.py b/config.py index 9ee2139..9fced18 100644 --- a/config.py +++ b/config.py @@ -402,7 +402,7 @@ YOUTUBE_API_KEY = os.getenv('YOUTUBE_API_KEY', '') # ========================================== # 系統版本與路徑 # ========================================== -SYSTEM_VERSION = "V10.765" +SYSTEM_VERSION = "V10.766" LOG_FILE_PATH = os.path.join(BASE_DIR, 'logs/system.log') public_url = PUBLIC_URL # 用於模板顯示 diff --git a/docs/AI_INTELLIGENCE_MODULE_SOT.md b/docs/AI_INTELLIGENCE_MODULE_SOT.md index 5fd8f4d..3fe2ef2 100644 --- a/docs/AI_INTELLIGENCE_MODULE_SOT.md +++ b/docs/AI_INTELLIGENCE_MODULE_SOT.md @@ -2,7 +2,7 @@ > **最後更新**: 2026-07-10 (台北時間) > **狀態**: 🟢 四 AI Agent 自動化閉環已落地；LLM 路由紅線升級為 Ollama-first 三主機級聯；PChome 後台業績匯入韌性已補強；產品定位正名為「PChome 業績成長自動化作戰系統」；外部市場來源正規化層、自動同步、作戰清單與價格參考表優先讀取、CSV 備援預檢、前台操作入口、高可見頁面繁中化守門、比價/作戰 UI 工作台化、AI 密集工作台文字密度守門、跨平台來源治理、商品身份 UI 契約、sitewide visual QA runtime readback、external MCP/RAG integration monitoring、PixelRAG RAG candidate replay monitoring、PixelRAG OCR/VLM replay contract monitoring、PixelRAG application portfolio、PChome auto-policy authorization guard monitoring、decision preflight machine evidence monitoring、decision closeout monitoring、authorization issuer gate monitoring、signing decision preflight monitoring、signing decision closeout monitoring、signing issuer guard monitoring、signing issuer closeout monitoring、signing execution preflight monitoring、signing execution closeout monitoring、signed receipt preflight monitoring、signed receipt closeout monitoring、signed receipt evidence intake monitoring、detached verification evidence validation monitoring、verifier receipt closeout monitoring、authorization evidence execution preflight monitoring、authorization evidence execution closeout monitoring、controlled apply final preflight monitoring、controlled dry-run package monitoring 與 controlled dry-run receipt closeout monitoring 已建立，GCP embedding 熔斷延後處理、110 proxy rescue 與 direct host health skip 已建立 -> **適用版本**: V10.765 +> **適用版本**: V10.766 --- @@ -121,6 +121,7 @@ - 2026-07-10 起 PixelRAG platform probe 必須把 blocked / interstitial receipt 轉成機器可執行下一步：`/api/ai-automation/pixelrag-platform-probe` 與 `scripts/ops/report_pixelrag_platform_probe.py` 需讀取 capture receipts 與 VLM replay receipts，辨識 Shopee language / region / generic marketplace slogan / traffic verification 與 Coupang 403 / access denied，輸出 public browser context probe、structured source fallback、platform backoff、blocked page not product data 與 no-write 邊界；`/api/ai-automation/smoke` 需包含 `PixelRAG platform probe readiness`，`/api/ai-automation/scheduled-health-summary` 需輸出 `pixelrag_platform_probe` family。此 readback 不抓外站、不讀 secret/cookie/session、不寫 DB、不寫 `ai_insights`、不寫正式價格表；capture worker 可消化 `public_browser_context` 的 locale/timezone/Accept-Language，但必須濾掉 Cookie、Authorization、token/secret/key 類 header。 - 2026-07-10 起 PixelRAG platform probe 必須有 controlled worker：`/api/ai-automation/pixelrag-platform-probe-worker` 與 `scripts/ops/run_pixelrag_platform_probe_worker.py` 預設 dry-run，`execute=true&write_receipt=true` 才會對 Shopee language / traffic / generic landing 執行 public empty-context capture，並對 Coupang 403 / access denied 自動產生 structured-source/backoff artifact receipt；`/api/ai-automation/smoke` 需包含 `PixelRAG platform probe worker`，`/api/ai-automation/scheduled-health-summary` 需輸出 `pixelrag_platform_probe_worker` family。此 worker 不登入、不讀 cookie/session/secret、不寫 DB、不寫 `ai_insights`、不寫正式價格表；capture 成功後下一步固定為 RAG candidate replay，structured fallback 只產生機器可讀 package，不把 blocked page 當商品資料。 - 2026-07-10 起 PixelRAG platform probe worker 必須自動處理 capture runtime gap：若 production app 容器缺 Playwright，`execute=true&write_receipt=true` 不得退回人工審核或 critical dead-end；worker 必須寫 `capture_runtime_unavailable_structured_fallback_package` artifact receipt，標記 `network_call=false`、`writes_database=false`、`primary_human_gate_count=0`，並把下一步改為 `run_structured_source_or_install_pixelrag_capture_runtime`。 +- 2026-07-10 起 PixelRAG marketplace source-contract adapter dry-run 必須是正式 smoke/scheduled family：`/api/ai-automation/pixelrag-marketplace-source-contract-adapter-dry-run` 與 `scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py` 預設只讀 adapter preflight receipts 並做 deterministic mapping readiness；`execute=true&write_receipt=true` 只寫 `marketplace_adapter_dry_run_receipt.json` artifact，輸出 field contracts、offer candidate contracts、identity matcher / PromotionGate / embedding signature gates 與 no-write 邊界。此 worker 不抓外站、不呼叫模型、不讀 secret/cookie/session、不寫 DB、不寫 `ai_insights`、不寫正式價格表；dry-run receipt 只允許進 identity matcher replay，不得直接進價格表或候選知識層。 - 2026-07-02 起 `/ai_intelligence` 商品明細與單品作戰詳情的四格價格證據必須可測：PChome 價格、MOMO 參考價、差距、可信度需以 `data-evidence` 固定，並以 `aria-label="價格證據"` 對應可掃描區塊；候選待確認或缺資料只能顯示「候選待確認 / 待補」，不得捏造價格或讓使用者打開 raw payload 才知道判斷依據。 - 2026-07-02 起 `/ai_intelligence` 必須是密集 AI 工作台，不得退回大段文字說明頁：首屏與明細可見內容只保留短狀態、數字、四格證據與下一步按鈕；KPI note、benchmark detail、alert 副句、策略說明、decision copy、來源長句與單品 reason list 不得佔用第一層視覺。`tests/test_ai_intelligence_text_density_guardrails.py` 必須鎖住 `data-density-guardrail="compact-ai-workbench"`、短任務文案、detail meta 與 hidden explanatory copy。 - 2026-07-02 起 `/observability/overview` 也必須採密集 AI 觀測工作台：首屏以 `data-density-guardrail="compact-observability-workbench"`、`AI 觀測 / 風險優先 / 下一步` 與 golden signals 先呈現狀態、數字與操作入口；hero lede、signal note、route desc、host meta 與資料來源長句不得佔用第一層視覺。`tests/test_observability_text_density_guardrails.py` 必須鎖住 compact marker 與 hidden explanatory copy。 @@ -898,6 +899,7 @@ POSTGRES_HOST=momo-db | 2026-07-10 | PixelRAG RAG replay 下一步不得隱藏並行主線 | V10.763 起若同一批 PixelRAG replay 同時存在 ready visual receipt 與 platform probe worker `source_contract_fallback` receipt，`next_machine_action` 必須輸出 `run_ocr_vlm_replay_and_source_contract_replay`，避免只顯示 OCR/VLM 而把 marketplace source-contract 自動化 lane 藏在 summary 裡。 | | 2026-07-10 | PixelRAG source-contract fallback 必須有 controlled replay worker | V10.764 起 `/api/ai-automation/pixelrag-source-contract-replay-worker`、`scripts/ops/run_pixelrag_source_contract_replay_worker.py`、`/api/ai-automation/smoke` 與 `/api/ai-automation/scheduled-health-summary` 必須輸出 PixelRAG source-contract replay worker / `pixelrag_source_contract_replay_worker` family；worker 只讀 platform probe worker `source_contract_fallback` receipts，驗證 structured package、source count、no-DB、network-deferred、blocked-page-not-product-data、source receipt provenance，execute 模式只寫 `source_contract_replay_receipt.json` artifact。此路徑不抓外站、不呼叫模型、不讀 secret/cookie/session、不寫 DB、不寫 `ai_insights`、不寫正式價格表，下一步只允許進 marketplace source-contract adapter replay preflight。 | | 2026-07-10 | PixelRAG marketplace source-contract adapter 必須先有 no-write preflight | V10.765 起 `/api/ai-automation/pixelrag-marketplace-source-contract-adapter-preflight`、`scripts/ops/run_pixelrag_marketplace_source_contract_adapter_preflight.py`、`/api/ai-automation/smoke` 與 `/api/ai-automation/scheduled-health-summary` 必須輸出 PixelRAG marketplace adapter preflight / `pixelrag_marketplace_adapter_preflight` family；preflight 只讀 `source_contract_replay_receipt.json`，驗證 replay ready、source contract version、adapter code、source count、source checks all passed、blocked page not product data、no-DB、network-deferred、public source boundary、rate-limit contract、provenance contract、identity/promotion gates 與 canonical offer fields。execute 模式只寫 `marketplace_adapter_preflight_receipt.json` artifact，不抓外站、不呼叫模型、不讀 secret/cookie/session、不寫 DB、不寫 `ai_insights`、不寫正式價格表，下一步只允許進 marketplace source-contract adapter dry-run。 | +| 2026-07-10 | PixelRAG marketplace adapter dry-run 必須先產生 no-write mapping receipt | V10.766 起 `/api/ai-automation/pixelrag-marketplace-source-contract-adapter-dry-run`、`scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py`、`/api/ai-automation/smoke` 與 `/api/ai-automation/scheduled-health-summary` 必須輸出 PixelRAG marketplace adapter dry-run / `pixelrag_marketplace_adapter_dry_run` family；dry-run 只讀 `marketplace_adapter_preflight_receipt.json`，驗證 preflight ready、canonical offer fields、required gates、no-DB/no-network/no-model、blocked page not product data 與 price-write blocked。execute 模式只寫 `marketplace_adapter_dry_run_receipt.json` artifact，產生 deterministic field contracts / offer candidate contracts，不抓外站、不呼叫模型、不寫 DB、不寫 `ai_insights`、不寫正式價格表，下一步只允許進 identity matcher replay。 | | 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` 與 `/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。 | diff --git a/docs/guides/ai_automation_mainline_work_items.md b/docs/guides/ai_automation_mainline_work_items.md index 7c77f95..d18ce4c 100644 --- a/docs/guides/ai_automation_mainline_work_items.md +++ b/docs/guides/ai_automation_mainline_work_items.md @@ -19,11 +19,12 @@ | 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 marketplace source-contract adapter preflight | `/api/ai-automation/pixelrag-marketplace-source-contract-adapter-preflight` and `scripts/ops/run_pixelrag_marketplace_source_contract_adapter_preflight.py` validate source-contract replay receipts for adapter readiness, canonical offer fields, provenance/rate-limit/public-boundary requirements, and no-write promotion gates. | +| Completed | PixelRAG marketplace adapter dry-run | `/api/ai-automation/pixelrag-marketplace-source-contract-adapter-dry-run` and `scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py` turn adapter preflight receipts into deterministic no-write field contracts and offer candidate contracts, with price writes blocked until identity matcher replay and PromotionGate. | | 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 | 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, PixelRAG platform probe worker, source-contract replay, adapter preflight, and adapter dry-run 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 diff --git a/docs/guides/browse_sh_crawler_playbook.md b/docs/guides/browse_sh_crawler_playbook.md index 6a87483..77b7d3b 100644 --- a/docs/guides/browse_sh_crawler_playbook.md +++ b/docs/guides/browse_sh_crawler_playbook.md @@ -200,6 +200,8 @@ python scripts/ops/run_pixelrag_source_contract_replay_worker.py --platform shop python scripts/ops/run_pixelrag_source_contract_replay_worker.py --platform coupang_tw --execute --write-receipt --limit 1 python scripts/ops/run_pixelrag_marketplace_source_contract_adapter_preflight.py --platform shopee_tw --platform coupang_tw python scripts/ops/run_pixelrag_marketplace_source_contract_adapter_preflight.py --platform coupang_tw --execute --write-receipt --limit 1 +python scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py --platform shopee_tw --platform coupang_tw +python scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py --platform coupang_tw --execute --write-receipt --limit 1 ``` API readback: `/api/ai-automation/pixelrag-vlm-route-readiness` 與 `/api/ai-automation/pixelrag-vlm-replay-worker?platform=shopee_tw`。worker 預設為 dry-run，不呼叫模型、不寫 artifact；`execute=true&write_receipt=true` 才呼叫 Ollama VLM 並寫 artifact receipt。execute 前會自動讀 approved Ollama `/api/tags` 選擇已安裝候選模型；若完全沒有候選，會寫 `model_route_not_ready` artifact receipt，不盲打 generate。即使 execute，結果仍只是 candidate evidence；不得直接寫 `ai_insights`、正式價格表或競品價格歷史，且 missing confidence/evidence 會留在 replay / probe lane。 @@ -210,6 +212,8 @@ Source-contract replay worker API readback: `/api/ai-automation/pixelrag-source- Marketplace adapter preflight API readback: `/api/ai-automation/pixelrag-marketplace-source-contract-adapter-preflight?platform=coupang_tw`。preflight 預設為 dry-run，不抓外站、不呼叫模型、不寫 artifact；`execute=true&write_receipt=true` 才把 source-contract replay receipt 轉成 adapter preflight artifact。artifact 只證明 adapter dry-run 條件齊備，不得直接寫 `ai_insights`、正式價格表或競品價格歷史。 +Marketplace adapter dry-run API readback: `/api/ai-automation/pixelrag-marketplace-source-contract-adapter-dry-run?platform=coupang_tw`。dry-run 預設只讀 adapter preflight receipts 並建立 deterministic field contracts；`execute=true&write_receipt=true` 只寫 adapter dry-run artifact receipt，不抓外站、不呼叫模型、不寫 DB、不寫 `ai_insights`、不寫正式價格表。dry-run artifact 下一步只能進 identity matcher replay 與 PromotionGate，不得直接變成價格資料。 + Application portfolio： ```bash diff --git a/routes/system_public_routes.py b/routes/system_public_routes.py index 3ea71ff..db9b7a0 100644 --- a/routes/system_public_routes.py +++ b/routes/system_public_routes.py @@ -979,6 +979,43 @@ def ai_automation_pixelrag_marketplace_source_contract_adapter_preflight_api(): )) +@system_public_bp.route('/api/ai-automation/pixelrag-marketplace-source-contract-adapter-dry-run') +@login_required +def ai_automation_pixelrag_marketplace_source_contract_adapter_dry_run_api(): + """Controlled PixelRAG marketplace source-contract adapter dry-run readback.""" + from services.pixelrag_marketplace_source_contract_adapter_dry_run_service import ( + run_pixelrag_marketplace_source_contract_adapter_dry_run, + ) + + platforms = tuple( + str(item or '').strip() + for item in request.args.getlist('platform') + if str(item or '').strip() + ) + execute = str(request.args.get('execute') or '').strip().lower() in { + '1', + 'true', + 'yes', + } + write_receipt = str(request.args.get('write_receipt') or '').strip().lower() in { + '1', + 'true', + 'yes', + } + max_age_hours = request.args.get('max_age_hours', 168, type=int) + limit = request.args.get('limit', 25, type=int) + return jsonify(run_pixelrag_marketplace_source_contract_adapter_dry_run( + adapter_preflight_receipt_root=str( + request.args.get('adapter_preflight_receipt_root') or '' + ).strip() or None, + platform=platforms, + max_age_hours=max(1, min(max_age_hours or 168, 720)), + limit=max(1, min(limit or 25, 250)), + execute=execute, + write_receipt=bool(execute and write_receipt), + )) + + @system_public_bp.route('/api/ai-automation/external-mcp-rag-integration') @login_required def ai_automation_external_mcp_rag_integration_api(): diff --git a/scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py b/scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py new file mode 100755 index 0000000..f423fc1 --- /dev/null +++ b/scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py @@ -0,0 +1,77 @@ +#!/usr/bin/env python3 +"""Run or dry-run PixelRAG marketplace source-contract adapter dry-run.""" + +from __future__ import annotations + +import argparse +import json +import sys +from pathlib import Path + + +ROOT = Path(__file__).resolve().parents[2] +if str(ROOT) not in sys.path: + sys.path.insert(0, str(ROOT)) + +from services.pixelrag_marketplace_source_contract_adapter_dry_run_service import ( # noqa: E402 + run_pixelrag_marketplace_source_contract_adapter_dry_run, +) + + +def main() -> int: + parser = argparse.ArgumentParser( + description="執行或 dry-run PixelRAG marketplace source-contract adapter dry-run。" + ) + parser.add_argument( + "--adapter-preflight-receipt-root", + help="Marketplace adapter preflight receipt root；預設使用 production/container 設定。", + ) + parser.add_argument( + "--output-root", + help="Marketplace adapter dry-run artifact receipt output root。", + ) + parser.add_argument( + "--platform", + action="append", + dest="platforms", + help="限制平台，可重複指定，例如 --platform shopee_tw --platform coupang_tw。", + ) + parser.add_argument( + "--max-age-hours", + type=int, + default=168, + help="receipt 最大新鮮度小時數。", + ) + parser.add_argument( + "--limit", + type=int, + default=25, + help="最多處理 adapter preflight receipt 數。", + ) + parser.add_argument( + "--execute", + action="store_true", + help="執行 adapter dry-run；未指定時只做 no-write dry-run readiness。", + ) + parser.add_argument( + "--write-receipt", + action="store_true", + help="execute 後寫入 adapter dry-run artifact receipt；不寫 DB。", + ) + args = parser.parse_args() + + payload = run_pixelrag_marketplace_source_contract_adapter_dry_run( + adapter_preflight_receipt_root=args.adapter_preflight_receipt_root, + output_root=args.output_root, + platform=tuple(args.platforms or ()), + max_age_hours=args.max_age_hours, + limit=args.limit, + execute=args.execute, + write_receipt=bool(args.write_receipt and args.execute), + ) + print(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True)) + return 0 if payload.get("success") else 1 + + +if __name__ == "__main__": + raise SystemExit(main()) diff --git a/services/ai_automation_smoke_service.py b/services/ai_automation_smoke_service.py index e99fb0b..cddb2e4 100644 --- a/services/ai_automation_smoke_service.py +++ b/services/ai_automation_smoke_service.py @@ -552,6 +552,23 @@ def build_scheduled_automation_health_summary( pixelrag_marketplace_adapter_preflight_details = ( pixelrag_marketplace_adapter_preflight.get("details") or {} ) + pixelrag_marketplace_adapter_dry_run = _find_check( + source_result, + "PixelRAG marketplace adapter dry-run", + ) + pixelrag_marketplace_adapter_dry_run_details = ( + pixelrag_marketplace_adapter_dry_run.get("details") or {} + ) + if ( + not pixelrag_marketplace_adapter_dry_run + or not pixelrag_marketplace_adapter_dry_run_details + ): + pixelrag_marketplace_adapter_dry_run = ( + _pixelrag_marketplace_adapter_dry_run_check() + ) + pixelrag_marketplace_adapter_dry_run_details = ( + pixelrag_marketplace_adapter_dry_run.get("details") or {} + ) pixelrag_ocr_vlm_replay = _find_check(source_result, "PixelRAG OCR/VLM replay contract") pixelrag_ocr_vlm_replay_details = pixelrag_ocr_vlm_replay.get("details") or {} if not pixelrag_ocr_vlm_replay or not pixelrag_ocr_vlm_replay_details: @@ -4712,6 +4729,61 @@ def build_scheduled_automation_health_summary( "primary_human_gate_count": 0, }, }, + { + "key": "pixelrag_marketplace_adapter_dry_run", + "label": "PixelRAG marketplace adapter dry-run", + "status": pixelrag_marketplace_adapter_dry_run.get("status") or "warning", + "summary": ( + pixelrag_marketplace_adapter_dry_run.get("summary") + or "PixelRAG marketplace adapter dry-run has no latest readback." + ), + "next_machine_action": pixelrag_marketplace_adapter_dry_run_details.get( + "next_machine_action" + ) + or "run_pixelrag_marketplace_adapter_dry_run", + "details": { + "policy": pixelrag_marketplace_adapter_dry_run_details.get("policy"), + "candidate_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("candidate_count") or 0 + ), + "ready_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("ready_count") or 0 + ), + "blocked_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("blocked_count") or 0 + ), + "dry_run_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("dry_run_count") or 0 + ), + "executed_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("executed_count") or 0 + ), + "receipt_written_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("receipt_written_count") or 0 + ), + "capture_runtime_gap_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("capture_runtime_gap_count") or 0 + ), + "field_contract_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("field_contract_count") or 0 + ), + "dry_run_output_contract_count": int( + pixelrag_marketplace_adapter_dry_run_details.get("dry_run_output_contract_count") or 0 + ), + "network_call_performed": bool( + pixelrag_marketplace_adapter_dry_run_details.get("network_call_performed") + ), + "model_call_performed": bool( + pixelrag_marketplace_adapter_dry_run_details.get("model_call_performed") + ), + "artifact_write_performed": bool( + pixelrag_marketplace_adapter_dry_run_details.get("artifact_write_performed") + ), + "writes_database": False, + "writes_database_count": 0, + "primary_human_gate_count": 0, + }, + }, { "key": "pixelrag_ocr_vlm_replay", "label": "PixelRAG OCR/VLM replay contract", @@ -13066,6 +13138,74 @@ def _pixelrag_marketplace_adapter_preflight_check() -> Dict[str, Any]: ) +def _pixelrag_marketplace_adapter_dry_run_check() -> Dict[str, Any]: + """Dry-run sentinel for PixelRAG marketplace adapter deterministic mapping.""" + try: + from services.pixelrag_marketplace_source_contract_adapter_dry_run_service import ( + run_pixelrag_marketplace_source_contract_adapter_dry_run, + ) + + readback = run_pixelrag_marketplace_source_contract_adapter_dry_run( + execute=False, + ) + summary = readback.get("summary") or {} + candidate_count = int(summary.get("candidate_count") or 0) + ready_count = int(summary.get("ready_count") or 0) + blocked_count = int(summary.get("blocked_count") or 0) + dry_run_count = int(summary.get("dry_run_count") or 0) + executed_count = int(summary.get("executed_count") or 0) + receipt_written_count = int(summary.get("receipt_written_count") or 0) + field_contract_count = int(summary.get("field_contract_count") or 0) + output_contract_count = int(summary.get("dry_run_output_contract_count") or 0) + status = readback.get("status") or "warning" + summary_text = ( + f"PixelRAG marketplace adapter dry-run candidates={candidate_count}, " + f"ready={ready_count}, blocked={blocked_count}, dry_run={dry_run_count}, " + f"executed={executed_count}, receipts={receipt_written_count}, " + f"fields={field_contract_count}, outputs={output_contract_count}" + ) + return _check( + "PixelRAG marketplace adapter dry-run", + status, + summary_text, + { + "policy": readback.get("policy"), + "candidate_count": candidate_count, + "ready_count": ready_count, + "blocked_count": blocked_count, + "dry_run_count": dry_run_count, + "executed_count": executed_count, + "receipt_written_count": receipt_written_count, + "capture_runtime_gap_count": int( + summary.get("capture_runtime_gap_count") or 0 + ), + "guard_failed_count": int(summary.get("guard_failed_count") or 0), + "field_contract_count": field_contract_count, + "dry_run_output_contract_count": output_contract_count, + "network_call_performed": bool(summary.get("network_call_performed")), + "model_call_performed": bool(summary.get("model_call_performed")), + "artifact_write_performed": bool( + summary.get("artifact_write_performed") + ), + "next_machine_action": readback.get("next_machine_action"), + "writes_database": False, + "writes_database_count": 0, + "primary_human_gate_count": 0, + }, + ) + except Exception as exc: + return _check( + "PixelRAG marketplace adapter dry-run", + "critical", + f"PixelRAG marketplace adapter dry-run 無法執行 dry-run：{exc}", + { + "writes_database": False, + "writes_database_count": 0, + "primary_human_gate_count": 0, + }, + ) + + def _pixelrag_ocr_vlm_replay_check() -> Dict[str, Any]: """Read-only sentinel for PixelRAG receipts becoming OCR/VLM replay contracts.""" try: @@ -13399,6 +13539,7 @@ def collect_ai_automation_smoke(*, record_history: bool = True, history_limit: i _pixelrag_rag_candidate_replay_check(), _pixelrag_source_contract_replay_worker_check(), _pixelrag_marketplace_adapter_preflight_check(), + _pixelrag_marketplace_adapter_dry_run_check(), _pixelrag_ocr_vlm_replay_check(), _pixelrag_vlm_route_readiness_check(), _pixelrag_vlm_replay_worker_check(), diff --git a/services/pixelrag_marketplace_source_contract_adapter_dry_run_service.py b/services/pixelrag_marketplace_source_contract_adapter_dry_run_service.py new file mode 100644 index 0000000..7e47c1c --- /dev/null +++ b/services/pixelrag_marketplace_source_contract_adapter_dry_run_service.py @@ -0,0 +1,539 @@ +"""Controlled PixelRAG marketplace adapter dry-run worker. + +This worker turns marketplace adapter preflight receipts into deterministic +adapter dry-run receipts. It does not fetch marketplace pages, call models, +write databases, or promote candidate prices into production truth. +""" + +from __future__ import annotations + +import json +import os +import re +from datetime import datetime, timezone +from pathlib import Path +from typing import Any, Mapping + +from services.pixelrag_crawler_integration_service import DEFAULT_ARTIFACT_MAX_AGE_HOURS +from services.pixelrag_marketplace_source_contract_adapter_preflight_service import ( + ADAPTER_PREFLIGHT_VERSION, + DEFAULT_OUTPUT_ROOT as DEFAULT_ADAPTER_PREFLIGHT_RECEIPT_ROOT, +) +from services.pixelrag_source_contract_replay_worker_service import SOURCE_CONTRACT_VERSION + + +POLICY = "controlled_pixelrag_marketplace_source_contract_adapter_dry_run_v1" +ADAPTER_DRY_RUN_VERSION = "pixelrag_marketplace_adapter_dry_run_v1" +DEFAULT_LIMIT = 25 +DEFAULT_OUTPUT_ROOT = os.getenv( + "PIXELRAG_MARKETPLACE_ADAPTER_DRY_RUN_RECEIPT_ROOT", + "/app/data/ai_automation/pixelrag_marketplace_adapter_dry_run_receipts" + if Path("/app/data").exists() + else "runtime_artifacts/pixelrag_marketplace_adapter_dry_run_receipts", +) + +CANONICAL_OFFER_FIELDS = { + "platform", + "platform_product_id", + "title", + "url", + "image_url", + "price", + "currency", + "availability", + "seller", + "promotion_badges", + "shipping_badges", + "evidence_time", + "source_method", + "confidence", +} +REQUIRED_PROMOTION_GATES = { + "public_source_boundary", + "rate_limit_contract", + "provenance_contract", + "identity_matcher_replay", + "promotion_gate", + "embedding_signature_guard", +} + + +def _normalise_platforms( + platform: str | tuple[str, ...] | list[str] | None, +) -> tuple[str, ...]: + if isinstance(platform, str): + value = platform.strip().lower() + return (value,) if value else () + return tuple( + str(item or "").strip().lower() + for item in (platform or ()) + if str(item or "").strip() + ) + + +def _safe_segment(value: Any) -> str: + text = str(value or "unknown").strip().lower() + text = re.sub(r"[^a-z0-9._-]+", "-", text) + return text.strip("-") or "unknown" + + +def _parse_iso_datetime(value: Any) -> datetime | None: + if not value: + return None + try: + return datetime.fromisoformat(str(value).replace("Z", "+00:00")) + except ValueError: + return None + + +def _receipt_candidates( + root: Path, + *, + platforms: tuple[str, ...], + limit: int, +) -> list[Path]: + if not root.exists(): + return [] + candidates: list[Path] = [] + if platforms: + for platform in platforms: + candidates.extend( + (root / platform).glob("*/marketplace_adapter_preflight_receipt.json") + ) + else: + candidates.extend(root.glob("*/*/marketplace_adapter_preflight_receipt.json")) + return sorted(candidates, key=lambda path: path.stat().st_mtime, reverse=True)[:limit] + + +def _load_receipt(path: Path) -> tuple[dict[str, Any], list[str]]: + try: + return json.loads(path.read_text(encoding="utf-8")), [] + except (OSError, json.JSONDecodeError) as exc: + return {}, [str(exc)[:300]] + + +def _field_source_path(field: str) -> str: + return { + "platform": "literal.platform", + "platform_product_id": "source.product_id_or_url_identity", + "title": "source.title_text", + "url": "source.public_product_url", + "image_url": "source.public_image_url", + "price": "source.price_text_or_amount", + "currency": "source.currency_text_or_locale_default", + "availability": "source.availability_text", + "seller": "source.seller_text", + "promotion_badges": "source.promotion_badges[]", + "shipping_badges": "source.shipping_badges[]", + "evidence_time": "receipt.generated_at", + "source_method": "source_contract.source_method", + "confidence": "adapter.confidence_contract", + }.get(field, f"source.{field}") + + +def _field_contract(field: str) -> dict[str, Any]: + return { + "field": field, + "mapped": True, + "required": field in CANONICAL_OFFER_FIELDS, + "source_path": _field_source_path(field), + "value_materialized": False, + "write_target": None, + "requires_evidence": field in {"price", "title", "url", "evidence_time"}, + "requires_identity_match": field in {"platform_product_id", "title", "url"}, + "requires_promotion_gate": field in { + "price", + "promotion_badges", + "shipping_badges", + "confidence", + }, + } + + +def _preflight_payload(receipt: Mapping[str, Any]) -> Mapping[str, Any]: + payload = receipt.get("adapter_preflight") + return payload if isinstance(payload, Mapping) else {} + + +def _promotion_boundary(receipt: Mapping[str, Any]) -> Mapping[str, Any]: + payload = receipt.get("promotion_boundary") + return payload if isinstance(payload, Mapping) else {} + + +def _expected_fields(preflight: Mapping[str, Any]) -> list[str]: + fields = [str(item) for item in list(preflight.get("expected_offer_fields") or [])] + seen: set[str] = set() + ordered: list[str] = [] + for field in fields + sorted(CANONICAL_OFFER_FIELDS): + if field and field not in seen: + ordered.append(field) + seen.add(field) + return ordered + + +def _adapter_dry_run_payload( + receipt: Mapping[str, Any], + *, + receipt_path: Path, +) -> dict[str, Any]: + preflight = _preflight_payload(receipt) + fields = _expected_fields(preflight) + source_count = int(preflight.get("source_count") or 0) + output_count = max(0, min(source_count, 50)) + field_contracts = [_field_contract(field) for field in fields] + return { + "adapter_dry_run_version": ADAPTER_DRY_RUN_VERSION, + "adapter_preflight_version": preflight.get("adapter_preflight_version"), + "source_contract_version": preflight.get("source_contract_version"), + "adapter_code": preflight.get("adapter_code") or receipt.get("adapter_code"), + "contract_id": preflight.get("contract_id"), + "barrier_type": preflight.get("barrier_type") or receipt.get("barrier_type"), + "capture_runtime_unavailable": bool(preflight.get("capture_runtime_unavailable")), + "input_preflight_receipt_path": str(receipt_path), + "source_contract_replay_receipt_path": receipt.get( + "source_contract_replay_receipt_path" + ), + "source_worker_receipt_path": receipt.get("source_worker_receipt_path"), + "source_receipt_path": receipt.get("source_receipt_path"), + "dry_run_execution_mode": "deterministic_mapping_only_no_network_no_db", + "source_count": source_count, + "dry_run_output_contract_count": output_count, + "expected_offer_fields": fields, + "field_contract_count": len(field_contracts), + "field_contracts": field_contracts, + "offer_candidate_contracts": [ + { + "candidate_index": index, + "candidate_id": ( + f"{receipt.get('platform') or 'unknown'}:" + f"{receipt.get('manifest_id') or 'unknown'}:{index}" + ), + "field_count": len(field_contracts), + "field_contracts_materialized": True, + "values_materialized": False, + "ready_for_identity_matcher_replay": True, + "ready_for_price_table_write": False, + "price_write_blocked_until_promotion_gate": True, + } + for index in range(output_count) + ], + "required_before_data_promotion": list( + preflight.get("required_before_data_promotion") or [] + ), + "allowed_next_step": "run_marketplace_adapter_identity_matcher_replay", + } + + +def _adapter_dry_run_checks( + receipt: Mapping[str, Any], + *, + stale: bool, + errors: list[str], + dry_run_payload: Mapping[str, Any], +) -> dict[str, bool]: + preflight = _preflight_payload(receipt) + boundary = _promotion_boundary(receipt) + preflight_checks = receipt.get("adapter_preflight_checks") + if not isinstance(preflight_checks, Mapping): + preflight_checks = {} + required_before = set( + str(item) for item in list(preflight.get("required_before_data_promotion") or []) + ) + expected_fields = set(str(item) for item in list(preflight.get("expected_offer_fields") or [])) + return { + "receipt_parse_ok": not errors, + "receipt_fresh": not stale, + "adapter_preflight_ready": ( + receipt.get("worker_status") == "executed_adapter_preflight_ready" + ), + "adapter_preflight_version_supported": ( + preflight.get("adapter_preflight_version") == ADAPTER_PREFLIGHT_VERSION + ), + "source_contract_version_supported": ( + preflight.get("source_contract_version") == SOURCE_CONTRACT_VERSION + ), + "adapter_preflight_checks_all_passed": ( + int(receipt.get("adapter_preflight_check_pass_count") or 0) + == int(receipt.get("adapter_preflight_check_count") or -1) + and int(receipt.get("adapter_preflight_check_count") or 0) > 0 + ), + "blocked_page_not_product_data": bool( + preflight_checks.get("blocked_page_not_product_data") + ), + "adapter_code_present": bool(preflight.get("adapter_code") or receipt.get("adapter_code")), + "source_count_positive": int(preflight.get("source_count") or 0) > 0, + "canonical_offer_fields_present": CANONICAL_OFFER_FIELDS.issubset(expected_fields), + "promotion_gates_required": REQUIRED_PROMOTION_GATES.issubset(required_before), + "direct_price_write_disallowed": not bool( + boundary.get("direct_price_write_allowed") + ), + "direct_ai_insights_write_disallowed": not bool( + boundary.get("direct_ai_insights_write_allowed") + ), + "database_write_disallowed": not bool(receipt.get("writes_database")) + and int(receipt.get("writes_database_count") or 0) == 0, + "network_call_disallowed": not bool(receipt.get("network_call_performed")), + "model_call_disallowed": not bool(receipt.get("model_call_performed")), + "dry_run_schema_generated": bool(dry_run_payload.get("field_contracts")), + "dry_run_output_contract_generated": int( + dry_run_payload.get("dry_run_output_contract_count") or 0 + ) + > 0, + "price_write_blocked_until_promotion_gate": all( + bool(item.get("price_write_blocked_until_promotion_gate")) + for item in list(dry_run_payload.get("offer_candidate_contracts") or []) + ), + } + + +def _worker_item( + receipt_path: Path, + *, + now: datetime, + max_age_hours: int, + execute: bool, +) -> dict[str, Any]: + receipt, errors = _load_receipt(receipt_path) + generated_at = _parse_iso_datetime(receipt.get("generated_at")) + if generated_at is None: + try: + generated_at = datetime.fromtimestamp(receipt_path.stat().st_mtime, tz=timezone.utc) + except OSError: + generated_at = None + age_hours = ((now - generated_at).total_seconds() / 3600) if generated_at else None + stale = age_hours is None or age_hours > max_age_hours + dry_run_payload = _adapter_dry_run_payload(receipt, receipt_path=receipt_path) + checks = _adapter_dry_run_checks( + receipt, + stale=stale, + errors=errors, + dry_run_payload=dry_run_payload, + ) + check_count = len(checks) + pass_count = sum(1 for passed in checks.values() if passed) + ready = pass_count == check_count + platform = str(receipt.get("platform") or receipt_path.parent.parent.name).strip().lower() + manifest_id = str(receipt.get("manifest_id") or receipt_path.parent.name).strip() + status = ( + "executed_marketplace_adapter_dry_run_ready" + if execute and ready + else ( + "dry_run_ready_for_marketplace_adapter_dry_run" + if ready + else "skipped_marketplace_adapter_dry_run_guard_failed" + ) + ) + return { + "worker_status": status, + "platform": platform, + "manifest_id": manifest_id, + "source_type": "marketplace_adapter_preflight_receipt", + "adapter_preflight_receipt_path": str(receipt_path), + "source_contract_replay_receipt_path": receipt.get( + "source_contract_replay_receipt_path" + ), + "source_worker_receipt_path": receipt.get("source_worker_receipt_path"), + "source_receipt_path": receipt.get("source_receipt_path"), + "adapter_code": dry_run_payload.get("adapter_code"), + "adapter_dry_run_status": "ready" if ready else "blocked", + "ready_for_execution": ready, + "execute": bool(execute), + "generated_at": generated_at.isoformat() if generated_at else None, + "age_hours": round(age_hours, 3) if age_hours is not None else None, + "stale": stale, + "network_call_performed": False, + "model_call_performed": False, + "artifact_write_performed": False, + "writes_database": False, + "writes_database_count": 0, + "primary_human_gate_count": 0, + "adapter_dry_run_checks": checks, + "adapter_dry_run_check_count": check_count, + "adapter_dry_run_check_pass_count": pass_count, + "adapter_dry_run": dry_run_payload, + "promotion_boundary": { + "direct_ai_insights_write_allowed": False, + "direct_price_write_allowed": False, + "adapter_dry_run_only": True, + "requires_public_source_boundary": True, + "requires_rate_limit_contract": True, + "requires_provenance_contract": True, + "requires_identity_matcher_replay": True, + "requires_promotion_gate": True, + "requires_embedding_signature_guard": True, + }, + "next_machine_action": ( + "run_marketplace_adapter_identity_matcher_replay" + if execute and ready + else ( + "run_marketplace_source_contract_adapter_dry_run_execute" + if ready + else "repair_marketplace_source_contract_adapter_dry_run_inputs" + ) + ), + } + + +def _write_dry_run_receipt(*, output_root: Path, item: Mapping[str, Any]) -> str: + target = ( + output_root + / _safe_segment(item.get("platform")) + / _safe_segment(item.get("manifest_id")) + / "marketplace_adapter_dry_run_receipt.json" + ) + target.parent.mkdir(parents=True, exist_ok=True) + receipt = dict(item) + receipt["artifact_write_performed"] = True + receipt["receipt_path"] = str(target) + receipt["generated_at"] = datetime.now(timezone.utc).isoformat() + receipt["policy"] = POLICY + target.write_text( + json.dumps(receipt, ensure_ascii=False, indent=2, sort_keys=True), + encoding="utf-8", + ) + return str(target) + + +def run_pixelrag_marketplace_source_contract_adapter_dry_run( + *, + adapter_preflight_receipt_root: str | Path | None = None, + output_root: str | Path | None = None, + platform: str | tuple[str, ...] | list[str] | None = None, + max_age_hours: int | None = None, + limit: int | None = None, + execute: bool = False, + write_receipt: bool = False, +) -> dict[str, Any]: + """Run or dry-run marketplace adapter deterministic mapping.""" + source_root = Path(adapter_preflight_receipt_root or DEFAULT_ADAPTER_PREFLIGHT_RECEIPT_ROOT) + output = Path(output_root or DEFAULT_OUTPUT_ROOT) + platforms = _normalise_platforms(platform) + max_age = max(1, int(max_age_hours or DEFAULT_ARTIFACT_MAX_AGE_HOURS)) + item_limit = max(1, min(int(limit or DEFAULT_LIMIT), 250)) + now = datetime.now(timezone.utc) + receipt_paths = _receipt_candidates(source_root, platforms=platforms, limit=item_limit) + worker_items: list[dict[str, Any]] = [] + for receipt_path in receipt_paths: + item = _worker_item( + receipt_path, + now=now, + max_age_hours=max_age, + execute=execute, + ) + if execute and write_receipt and item.get("ready_for_execution"): + item["receipt_path"] = _write_dry_run_receipt(output_root=output, item=item) + item["artifact_write_performed"] = True + worker_items.append(item) + + ready_count = sum(1 for item in worker_items if item.get("ready_for_execution")) + blocked_count = len(worker_items) - ready_count + dry_run_count = sum( + 1 for item in worker_items if str(item.get("worker_status") or "").startswith("dry_run_") + ) + executed_count = sum( + 1 for item in worker_items if str(item.get("worker_status") or "").startswith("executed_") + ) + receipt_written_count = sum(1 for item in worker_items if item.get("receipt_path")) + guard_failed_count = sum( + 1 for item in worker_items if item.get("adapter_dry_run_status") != "ready" + ) + capture_runtime_gap_count = sum( + 1 + for item in worker_items + if (item.get("adapter_dry_run") or {}).get("capture_runtime_unavailable") + ) + field_contract_count = sum( + int((item.get("adapter_dry_run") or {}).get("field_contract_count") or 0) + for item in worker_items + ) + output_contract_count = sum( + int((item.get("adapter_dry_run") or {}).get("dry_run_output_contract_count") or 0) + for item in worker_items + ) + + if not worker_items: + status = "warning" + elif guard_failed_count: + status = "warning" + else: + status = "ok" + + if not worker_items: + next_action = "run_marketplace_source_contract_adapter_preflight" + elif not execute and ready_count: + next_action = "run_marketplace_source_contract_adapter_dry_run_execute" + elif execute and receipt_written_count: + next_action = "run_marketplace_adapter_identity_matcher_replay" + elif guard_failed_count: + next_action = "repair_marketplace_source_contract_adapter_dry_run_inputs" + else: + next_action = "refresh_marketplace_source_contract_adapter_dry_run_candidates" + + summary = { + "candidate_count": len(worker_items), + "ready_count": ready_count, + "blocked_count": blocked_count, + "dry_run_count": dry_run_count, + "executed_count": executed_count, + "receipt_written_count": receipt_written_count, + "guard_failed_count": guard_failed_count, + "capture_runtime_gap_count": capture_runtime_gap_count, + "field_contract_count": field_contract_count, + "dry_run_output_contract_count": output_contract_count, + "platforms": sorted({str(item.get("platform") or "unknown") for item in worker_items}), + "network_call_performed": False, + "model_call_performed": False, + "artifact_write_performed": bool(receipt_written_count), + "writes_database_count": 0, + "primary_human_gate_count": 0, + } + return { + "success": status != "critical", + "policy": POLICY, + "status": status, + "generated_at": now.isoformat(), + "adapter_dry_run_version": ADAPTER_DRY_RUN_VERSION, + "adapter_preflight_receipt_root": str(source_root), + "output_root": str(output), + "platform_filter": list(platforms), + "max_age_hours": max_age, + "limit": item_limit, + "execute": bool(execute), + "write_receipt": bool(write_receipt and execute), + "summary": summary, + "worker_items": worker_items, + "controlled_apply": { + "network_call": False, + "model_call": False, + "artifact_write": bool(receipt_written_count), + "db_write": False, + "writes_database": False, + "writes_database_count": 0, + "secret_read": False, + "raw_cookie_or_session_read": False, + "credentialed_session_allowed": False, + "login_allowed": False, + "production_price_write": False, + "primary_human_gate_count": 0, + }, + "promotion_boundary": { + "writes_ai_insights": False, + "writes_price_tables": False, + "adapter_dry_run_only": True, + "requires_public_source_boundary": True, + "requires_rate_limit_contract": True, + "requires_provenance_contract": True, + "requires_identity_matcher_replay": True, + "requires_promotion_gate": True, + "requires_embedding_signature_guard": True, + }, + "next_machine_action": next_action, + } + + +__all__ = [ + "ADAPTER_DRY_RUN_VERSION", + "DEFAULT_OUTPUT_ROOT", + "POLICY", + "run_pixelrag_marketplace_source_contract_adapter_dry_run", +] diff --git a/tests/test_ai_automation_smoke_service.py b/tests/test_ai_automation_smoke_service.py index 1927e4a..38624cd 100644 --- a/tests/test_ai_automation_smoke_service.py +++ b/tests/test_ai_automation_smoke_service.py @@ -1312,6 +1312,7 @@ def test_collect_ai_automation_smoke_uses_worst_status(monkeypatch): monkeypatch.setattr(smoke, "_pixelrag_rag_candidate_replay_check", lambda: smoke._check("pixelrag replay", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_source_contract_replay_worker_check", lambda: smoke._check("pixelrag source contract", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_marketplace_adapter_preflight_check", lambda: smoke._check("pixelrag marketplace adapter preflight", "ok", "ok")) + monkeypatch.setattr(smoke, "_pixelrag_marketplace_adapter_dry_run_check", lambda: smoke._check("pixelrag marketplace adapter dry-run", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_ocr_vlm_replay_check", lambda: smoke._check("pixelrag ocr vlm", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_vlm_route_readiness_check", lambda: smoke._check("pixelrag vlm route", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_vlm_replay_worker_check", lambda: smoke._check("pixelrag vlm worker", "ok", "ok")) @@ -1321,7 +1322,7 @@ def test_collect_ai_automation_smoke_uses_worst_status(monkeypatch): result = smoke.collect_ai_automation_smoke(record_history=False) assert result["status"] == "critical" - assert result["summary"] == {"ok": 37, "warning": 1, "critical": 1, "total": 39} + assert result["summary"] == {"ok": 38, "warning": 1, "critical": 1, "total": 40} def test_pchome_controlled_apply_drift_monitor_reports_verified_zero_drift(monkeypatch): @@ -3852,6 +3853,7 @@ def test_collect_ai_automation_smoke_persists_recent_history(tmp_path, monkeypat monkeypatch.setattr(smoke, "_pixelrag_rag_candidate_replay_check", lambda: smoke._check("pixelrag replay", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_source_contract_replay_worker_check", lambda: smoke._check("pixelrag source contract", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_marketplace_adapter_preflight_check", lambda: smoke._check("pixelrag marketplace adapter preflight", "ok", "ok")) + monkeypatch.setattr(smoke, "_pixelrag_marketplace_adapter_dry_run_check", lambda: smoke._check("pixelrag marketplace adapter dry-run", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_ocr_vlm_replay_check", lambda: smoke._check("pixelrag ocr vlm", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_vlm_route_readiness_check", lambda: smoke._check("pixelrag vlm route", "ok", "ok")) monkeypatch.setattr(smoke, "_pixelrag_vlm_replay_worker_check", lambda: smoke._check("pixelrag vlm worker", "ok", "ok")) @@ -3912,7 +3914,7 @@ def test_scheduled_automation_health_summary_reads_history_without_side_effects( json.dumps({ "generated_at": datetime.now().isoformat(timespec="seconds"), "status": "ok", - "summary": {"ok": 39, "warning": 0, "critical": 0, "total": 39}, + "summary": {"ok": 40, "warning": 0, "critical": 0, "total": 40}, "checks": [ { "name": "PChome 受控落地 drift monitor", @@ -4063,6 +4065,29 @@ def test_scheduled_automation_health_summary_reads_history_without_side_effects( "primary_human_gate_count": 0, }, }, + { + "name": "PixelRAG marketplace adapter dry-run", + "status": "ok", + "summary": "PixelRAG marketplace adapter dry-run candidates=1, ready=1, blocked=0, dry_run=1, executed=0, receipts=0, fields=14, outputs=2", + "details": { + "policy": "controlled_pixelrag_marketplace_source_contract_adapter_dry_run_v1", + "candidate_count": 1, + "ready_count": 1, + "blocked_count": 0, + "dry_run_count": 1, + "executed_count": 0, + "receipt_written_count": 0, + "capture_runtime_gap_count": 0, + "field_contract_count": 14, + "dry_run_output_contract_count": 2, + "network_call_performed": False, + "model_call_performed": False, + "artifact_write_performed": False, + "next_machine_action": "run_marketplace_source_contract_adapter_dry_run_execute", + "writes_database_count": 0, + "primary_human_gate_count": 0, + }, + }, { "name": "PixelRAG OCR/VLM replay contract", "status": "ok", @@ -4177,7 +4202,7 @@ def test_scheduled_automation_health_summary_reads_history_without_side_effects( ) assert summary["policy"] == "read_only_ai_automation_scheduled_health_summary" assert summary["status"] == "ok" - assert summary["summary"]["total"] == 36 + assert summary["summary"]["total"] == 37 assert summary["summary"]["primary_human_gate_count"] == 0 assert summary["summary"]["writes_database_count"] == 0 assert pchome_family["status"] == "ok" @@ -6519,6 +6544,11 @@ def test_surface_html_readback_check_is_part_of_ai_smoke(monkeypatch): "ok", "pixelrag marketplace adapter preflight ok", )) + monkeypatch.setattr(smoke, "_pixelrag_marketplace_adapter_dry_run_check", lambda: smoke._check( + "PixelRAG marketplace adapter dry-run", + "ok", + "pixelrag marketplace adapter dry-run ok", + )) monkeypatch.setattr(smoke, "_pixelrag_ocr_vlm_replay_check", lambda: smoke._check( "PixelRAG OCR/VLM replay contract", "ok", @@ -6559,7 +6589,7 @@ def test_surface_html_readback_check_is_part_of_ai_smoke(monkeypatch): item for item in result["checks"] if item["name"] == "Sitewide visual QA readback" ) - assert result["summary"]["total"] == 39 + assert result["summary"]["total"] == 40 assert surface_check["status"] == "ok" assert surface_check["details"]["checked_surface_count"] == 10 assert sitewide_check["status"] == "ok" diff --git a/tests/test_pixelrag_marketplace_source_contract_adapter_dry_run_service.py b/tests/test_pixelrag_marketplace_source_contract_adapter_dry_run_service.py new file mode 100644 index 0000000..b9bdd62 --- /dev/null +++ b/tests/test_pixelrag_marketplace_source_contract_adapter_dry_run_service.py @@ -0,0 +1,259 @@ +import json +import subprocess +import sys +from datetime import datetime, timezone + + +def _write_adapter_preflight_receipt( + root, + *, + platform="coupang_tw", + manifest_id="coupang-403", + adapter_code="coupang", + barrier_type="access_denied", + capture_runtime_unavailable=False, +): + receipt_dir = root / platform / manifest_id + receipt_dir.mkdir(parents=True) + payload = { + "generated_at": datetime.now(timezone.utc).isoformat(), + "policy": "controlled_pixelrag_marketplace_source_contract_adapter_preflight_v1", + "worker_status": "executed_adapter_preflight_ready", + "platform": platform, + "manifest_id": manifest_id, + "adapter_code": adapter_code, + "source_contract_replay_receipt_path": ( + f"runtime_artifacts/pixelrag_source_contract_replay_receipts/" + f"{platform}/{manifest_id}/source_contract_replay_receipt.json" + ), + "source_worker_receipt_path": ( + f"runtime_artifacts/pixelrag_platform_probe_worker_receipts/" + f"{platform}/{manifest_id}/platform_probe_worker_receipt.json" + ), + "source_receipt_path": ( + f"runtime_artifacts/pixelrag_visual_evidence/" + f"{platform}/{manifest_id}/capture_receipt.json" + ), + "adapter_preflight_check_count": 16, + "adapter_preflight_check_pass_count": 16, + "adapter_preflight_checks": { + "adapter_code_present": True, + "blocked_page_not_product_data": True, + "canonical_offer_fields_present": True, + "database_write_disallowed": True, + "direct_price_write_disallowed": True, + "identity_and_promotion_gates_required": True, + "network_request_deferred": True, + "provenance_contract_required": True, + "public_source_boundary_required": True, + "rate_limit_contract_required": True, + "receipt_fresh": True, + "receipt_parse_ok": True, + "source_contract_checks_all_passed": True, + "source_contract_replay_ready": True, + "source_contract_version_supported": True, + "source_count_positive": True, + }, + "adapter_preflight": { + "adapter_preflight_version": "pixelrag_marketplace_adapter_preflight_v1", + "source_contract_version": "pixelrag_marketplace_source_contract_v1", + "contract_id": f"{platform}:{manifest_id}:{adapter_code}", + "adapter_code": adapter_code, + "barrier_type": barrier_type, + "capture_runtime_unavailable": capture_runtime_unavailable, + "source_count": 2, + "expected_offer_fields": [ + "platform", + "platform_product_id", + "title", + "url", + "image_url", + "price", + "currency", + "availability", + "seller", + "promotion_badges", + "shipping_badges", + "evidence_time", + "source_method", + "confidence", + ], + "required_before_data_promotion": [ + "public_source_boundary", + "rate_limit_contract", + "provenance_contract", + "identity_matcher_replay", + "promotion_gate", + "embedding_signature_guard", + ], + }, + "promotion_boundary": { + "direct_ai_insights_write_allowed": False, + "direct_price_write_allowed": False, + }, + "writes_database": False, + "writes_database_count": 0, + "network_call_performed": False, + "model_call_performed": False, + } + path = receipt_dir / "marketplace_adapter_preflight_receipt.json" + path.write_text(json.dumps(payload, ensure_ascii=False), encoding="utf-8") + return path + + +def test_marketplace_adapter_dry_run_reads_preflight_receipts(tmp_path): + from services.pixelrag_marketplace_source_contract_adapter_dry_run_service import ( + POLICY, + run_pixelrag_marketplace_source_contract_adapter_dry_run, + ) + + preflight_root = tmp_path / "adapter_preflight" + _write_adapter_preflight_receipt(preflight_root) + _write_adapter_preflight_receipt( + preflight_root, + platform="shopee_tw", + manifest_id="shopee-runtime-gap", + adapter_code="shopee", + barrier_type="language_or_region_interstitial", + capture_runtime_unavailable=True, + ) + + payload = run_pixelrag_marketplace_source_contract_adapter_dry_run( + adapter_preflight_receipt_root=preflight_root, + platform=("coupang_tw", "shopee_tw"), + ) + by_platform = {item["platform"]: item for item in payload["worker_items"]} + + assert payload["policy"] == POLICY + assert payload["status"] == "ok" + assert payload["summary"]["candidate_count"] == 2 + assert payload["summary"]["ready_count"] == 2 + assert payload["summary"]["dry_run_count"] == 2 + assert payload["summary"]["capture_runtime_gap_count"] == 1 + assert payload["summary"]["field_contract_count"] == 28 + assert payload["summary"]["dry_run_output_contract_count"] == 4 + assert payload["summary"]["writes_database_count"] == 0 + assert payload["controlled_apply"]["network_call"] is False + assert payload["controlled_apply"]["writes_database"] is False + assert payload["promotion_boundary"]["writes_price_tables"] is False + assert payload["next_machine_action"] == ( + "run_marketplace_source_contract_adapter_dry_run_execute" + ) + assert by_platform["coupang_tw"]["worker_status"] == ( + "dry_run_ready_for_marketplace_adapter_dry_run" + ) + assert by_platform["coupang_tw"]["adapter_dry_run_checks"][ + "price_write_blocked_until_promotion_gate" + ] is True + assert by_platform["coupang_tw"]["adapter_dry_run"]["offer_candidate_contracts"][0][ + "ready_for_price_table_write" + ] is False + assert by_platform["shopee_tw"]["adapter_dry_run"][ + "capture_runtime_unavailable" + ] is True + + +def test_marketplace_adapter_dry_run_execute_writes_receipt(tmp_path): + from services.pixelrag_marketplace_source_contract_adapter_dry_run_service import ( + run_pixelrag_marketplace_source_contract_adapter_dry_run, + ) + + preflight_root = tmp_path / "adapter_preflight" + output_root = tmp_path / "adapter_dry_run" + _write_adapter_preflight_receipt(preflight_root) + + payload = run_pixelrag_marketplace_source_contract_adapter_dry_run( + adapter_preflight_receipt_root=preflight_root, + output_root=output_root, + platform="coupang_tw", + execute=True, + write_receipt=True, + ) + + assert payload["status"] == "ok" + assert payload["summary"]["executed_count"] == 1 + assert payload["summary"]["receipt_written_count"] == 1 + assert payload["controlled_apply"]["artifact_write"] is True + assert payload["controlled_apply"]["writes_database"] is False + assert payload["next_machine_action"] == "run_marketplace_adapter_identity_matcher_replay" + receipt_path = ( + output_root + / "coupang_tw" + / "coupang-403" + / "marketplace_adapter_dry_run_receipt.json" + ) + assert receipt_path.exists() + receipt = json.loads(receipt_path.read_text(encoding="utf-8")) + assert receipt["worker_status"] == "executed_marketplace_adapter_dry_run_ready" + assert receipt["artifact_write_performed"] is True + assert receipt["writes_database"] is False + assert receipt["adapter_dry_run_check_pass_count"] == ( + receipt["adapter_dry_run_check_count"] + ) + assert receipt["adapter_dry_run"]["adapter_dry_run_version"] == ( + "pixelrag_marketplace_adapter_dry_run_v1" + ) + assert receipt["adapter_dry_run"]["allowed_next_step"] == ( + "run_marketplace_adapter_identity_matcher_replay" + ) + + +def test_marketplace_adapter_dry_run_cli_outputs_json(tmp_path): + preflight_root = tmp_path / "adapter_preflight" + _write_adapter_preflight_receipt(preflight_root) + + completed = subprocess.run( + [ + sys.executable, + "scripts/ops/run_pixelrag_marketplace_source_contract_adapter_dry_run.py", + "--adapter-preflight-receipt-root", + str(preflight_root), + "--platform", + "coupang_tw", + ], + capture_output=True, + check=False, + text=True, + ) + + assert completed.returncode == 0 + payload = json.loads(completed.stdout) + assert payload["summary"]["candidate_count"] == 1 + assert payload["summary"]["ready_count"] == 1 + assert payload["summary"]["field_contract_count"] == 14 + assert payload["controlled_apply"]["writes_database"] is False + + +def test_marketplace_adapter_dry_run_route_returns_readback( + tmp_path, + monkeypatch, +): + from flask import Flask + from routes import system_public_routes as routes + from services import pixelrag_marketplace_source_contract_adapter_dry_run_service as service + + preflight_root = tmp_path / "adapter_preflight" + _write_adapter_preflight_receipt(preflight_root) + monkeypatch.setattr( + service, + "DEFAULT_ADAPTER_PREFLIGHT_RECEIPT_ROOT", + str(preflight_root), + ) + + app = Flask(__name__) + with app.test_request_context( + "/api/ai-automation/pixelrag-marketplace-source-contract-adapter-dry-run?platform=coupang_tw" + ): + response = ( + routes + .ai_automation_pixelrag_marketplace_source_contract_adapter_dry_run_api + .__wrapped__() + ) + payload = response.get_json() + + assert payload["policy"] == ( + "controlled_pixelrag_marketplace_source_contract_adapter_dry_run_v1" + ) + assert payload["summary"]["candidate_count"] == 1 + assert payload["summary"]["ready_count"] == 1 + assert payload["controlled_apply"]["writes_database"] is False