diff --git a/TODO_NEXT_STEPS.txt b/TODO_NEXT_STEPS.txt index 478de4e..677ff4f 100644 --- a/TODO_NEXT_STEPS.txt +++ b/TODO_NEXT_STEPS.txt @@ -9,7 +9,7 @@ python scripts/ops/check_production_version_truth.py 目前最新版本仍以 production `https://mo.wooo.work/health` readback 為準。 -本輪 source target 為 `V10.753`；部署完成前不得宣稱正式環境已是 `V10.753`。 +本輪 source target 為 `V10.754`；部署完成前不得宣稱正式環境已是 `V10.754`。 舊 iCloud checkout 不是 Gitea dev worktree，不得拿來當最新版本真相。 ================================================================================ diff --git a/config.py b/config.py index 4a2c7ff..408f795 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 = "V10.753" +SYSTEM_VERSION = "V10.754" 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 bc75415..871c52f 100644 --- a/docs/AI_INTELLIGENCE_MODULE_SOT.md +++ b/docs/AI_INTELLIGENCE_MODULE_SOT.md @@ -883,6 +883,7 @@ POSTGRES_HOST=momo-db | 2026-07-09 | PixelRAG Ollama-first VLM replay worker 必須有 runtime monitoring | V10.751 起 `/api/ai-automation/pixelrag-vlm-replay-worker`、`scripts/ops/run_pixelrag_vlm_replay_worker.py`、`/api/ai-automation/smoke` 與 `/api/ai-automation/scheduled-health-summary` 必須輸出 controlled VLM replay worker / `pixelrag_vlm_replay_worker` family；readback 預設 dry-run，不呼叫模型、不寫 artifact，execute 模式只讀 saved tiles、呼叫 approved Ollama VLM route、驗證 JSON field confidence/evidence refs，並只寫 artifact receipt；model_error 也必須寫 failure artifact receipt，receipt 檔內需自證 `artifact_write_performed=true` 與 `receipt_path`。此 worker 明確標記 `writes_database=false`、`writes_ai_insights=false`、`writes_price_tables=false`、`secret_read=false`、`primary_human_gate_count=0`；blocked page 不得輸出商品欄位，ready VLM 結果仍需 identity matcher replay 與 PromotionGate。 | | 2026-07-09 | PixelRAG VLM route readiness 必須有 runtime monitoring 與 execute 前自動選模 | V10.752 起 `/api/ai-automation/pixelrag-vlm-route-readiness`、`scripts/ops/report_pixelrag_vlm_route_readiness.py`、`/api/ai-automation/smoke` 與 `/api/ai-automation/scheduled-health-summary` 必須輸出 read-only approved Ollama route/model readiness / `pixelrag_vlm_route_readiness` family；readback 只打 `/api/tags`，不呼叫 `/api/generate`，輸出 reachable host、configured model available count、candidate model、candidate host、model_route_ready 與 next machine action。`run_pixelrag_vlm_replay_worker.py --execute` 預設必須使用此 readback 自動選擇已安裝候選模型；完全沒有候選時寫 `model_route_not_ready` artifact receipt，不得盲打 missing model。 | | 2026-07-10 | PixelRAG VLM execute preflight 必須驗證 generate route | V10.753 起 `/api/ai-automation/pixelrag-vlm-route-readiness?probe_generate=true` 與 `scripts/ops/report_pixelrag_vlm_route_readiness.py --probe-generate` 可對已安裝候選模型執行極小 `/api/generate` preflight；smoke 預設仍不呼叫模型。`run_pixelrag_vlm_replay_worker.py --execute` 預設先執行 generate preflight，若 GCP-A direct / 110 proxy timeout、GCP-B candidate 雖安裝但 generate 不健康，worker 必須在送入 screenshot tiles 前寫 `model_route_not_ready` artifact receipt，輸出 `tag_model_route_ready`、`generate_route_ready`、`route_model_call_performed` 與 `tile_model_call_performed=false`，下一步固定為 `repair_ollama_vlm_generate_runtime_or_proxy_timeout`；不得把 tags 可見誤當 VLM 可執行。 | +| 2026-07-10 | PixelRAG VLM tile generate 必須綁定 preflight 選出的 host / exact model | V10.754 起 `run_pixelrag_vlm_replay_worker.py --execute` 若 route readiness 已輸出 `candidate_host`，tile VLM generate 必須使用該 approved host 與 exact `candidate_model` 直呼 `/api/generate`，不得重新進入全域 Ollama resolver、不得因 111 fallback 規則把 VLM 模型降級成文字模型、不得再出現 preflight 選 111 但 tile generate tried GCP-B/GCP-A/111 的 route drift。receipt 必須輸出 `route_candidate_host`，模型錯誤時下一步為 `repair_ollama_vlm_generate_runtime_or_proxy_timeout`，仍然不寫 DB、不寫正式價格表。 | | 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/services/pixelrag_vlm_replay_worker_service.py b/services/pixelrag_vlm_replay_worker_service.py index aee70ea..d8d2306 100644 --- a/services/pixelrag_vlm_replay_worker_service.py +++ b/services/pixelrag_vlm_replay_worker_service.py @@ -16,7 +16,15 @@ from datetime import datetime, timezone from pathlib import Path from typing import Any, Mapping -from services.ollama_service import OllamaService, get_host_label, get_provider_tag +import requests + +from services.ollama_service import ( + OllamaResponse, + OllamaService, + get_host_label, + get_provider_tag, + is_approved_ollama_host, +) from services.pixelrag_crawler_integration_service import ( DEFAULT_ARTIFACT_MAX_AGE_HOURS, DEFAULT_ARTIFACT_ROOT, @@ -223,6 +231,78 @@ def _validate_model_payload( } +def _generate_exact_host( + prompt: str, + *, + host: str, + model: str, + temperature: float, + timeout: int, + options: Mapping[str, Any] | None, + images: list[str], +) -> OllamaResponse: + """Call the route-readiness selected host without fallback or model downgrade.""" + clean_host = str(host or "").rstrip("/") + if not is_approved_ollama_host(clean_host): + return OllamaResponse( + success=False, + content="", + model=model, + error=f"unapproved_pixelrag_vlm_candidate_host: {clean_host}", + host=clean_host or "unknown", + ) + payload: dict[str, Any] = { + "model": model, + "prompt": prompt, + "stream": False, + "options": {"temperature": temperature}, + } + if options: + payload["options"].update(dict(options)) + if images: + payload["images"] = images + try: + response = requests.post( + f"{clean_host}/api/generate", + json=payload, + timeout=max(1, int(timeout or DEFAULT_TIMEOUT_SECONDS)), + ) + if response.status_code != 200: + return OllamaResponse( + success=False, + content="", + model=model, + error=f"HTTP {response.status_code}: {response.text[:RAW_EXCERPT_LIMIT]}", + host=clean_host, + ) + data = response.json() + return OllamaResponse( + success=True, + content=data.get("response", ""), + model=model, + total_duration=(data.get("total_duration", 0) or 0) / 1e9, + host=clean_host, + input_tokens=int(data.get("prompt_eval_count", 0) or 0), + output_tokens=int(data.get("eval_count", 0) or 0), + ) + except requests.Timeout: + return OllamaResponse( + success=False, + content="", + model=model, + error=f"timeout ({max(1, int(timeout or DEFAULT_TIMEOUT_SECONDS))}s)", + host=clean_host, + ) + except Exception as exc: + return OllamaResponse( + success=False, + content="", + model=model, + error=f"{type(exc).__name__}: {str(exc)[:RAW_EXCERPT_LIMIT]}", + host=clean_host, + ) + + def _write_replay_receipt( *, output_root: Path, @@ -324,6 +404,7 @@ def _execute_item( root: Path, output_root: Path, model: str, + route_host: str | None, timeout: int, tile_limit: int, write_receipt: bool, @@ -335,6 +416,7 @@ def _execute_item( "source_receipt_path": item.get("source_receipt_path"), "worker_status": "executing", "model": model, + "route_candidate_host": str(route_host or ""), "tile_evidence": tile_evidence, "tile_image_count": len(images), "model_call_performed": bool(images), @@ -348,14 +430,27 @@ def _execute_item( }) return base - response = OllamaService(model=model).generate( - _prompt_for_item(item), - model=model, - temperature=0.1, - timeout=max(10, int(timeout or DEFAULT_TIMEOUT_SECONDS)), - options={"num_predict": 700, "num_ctx": 4096}, - images=images, - ) + prompt = _prompt_for_item(item) + options = {"num_predict": 700, "num_ctx": 4096} + if route_host: + response = _generate_exact_host( + prompt, + host=route_host, + model=model, + temperature=0.1, + timeout=max(10, int(timeout or DEFAULT_TIMEOUT_SECONDS)), + options=options, + images=images, + ) + else: + response = OllamaService(model=model).generate( + prompt, + model=model, + temperature=0.1, + timeout=max(10, int(timeout or DEFAULT_TIMEOUT_SECONDS)), + options=options, + images=images, + ) base.update({ "host": response.host, "host_label": get_host_label(response.host or ""), @@ -369,7 +464,11 @@ def _execute_item( base.update({ "worker_status": "model_error", "model_error": str(response.error or "")[:RAW_EXCERPT_LIMIT], - "next_machine_action": "repair_ollama_vlm_runtime_or_model_route", + "next_machine_action": ( + "repair_ollama_vlm_generate_runtime_or_proxy_timeout" + if route_host + else "repair_ollama_vlm_runtime_or_model_route" + ), }) if write_receipt: base["receipt_path"] = _write_replay_receipt( @@ -454,6 +553,7 @@ def run_pixelrag_ollama_vlm_replay_worker( item_limit = max(1, min(int(limit or DEFAULT_LIMIT), 250)) tiles = max(1, min(int(tile_limit or DEFAULT_TILE_LIMIT), 12)) selected_model = str(model or DEFAULT_MODEL) + selected_route_host = "" selected_timeout = max(10, int(timeout or DEFAULT_TIMEOUT_SECONDS)) readiness_timeout = max(1, min(int(route_readiness_timeout or 3), 20)) generate_probe_timeout = max( @@ -489,6 +589,7 @@ def run_pixelrag_ollama_vlm_replay_worker( model_route_ready = bool(route_summary.get("model_route_ready")) if candidate_model: selected_model = candidate_model + selected_route_host = str(route_summary.get("candidate_host") or "").strip() worker_items: list[dict[str, Any]] = [] for item in replay_items: @@ -511,6 +612,7 @@ def run_pixelrag_ollama_vlm_replay_worker( root=root, output_root=output, model=selected_model, + route_host=selected_route_host, timeout=selected_timeout, tile_limit=tiles, write_receipt=write_receipt, @@ -607,6 +709,7 @@ def run_pixelrag_ollama_vlm_replay_worker( "tile_limit": tiles, "model": selected_model, "configured_model": str(model or DEFAULT_MODEL), + "route_candidate_host": selected_route_host, "timeout_seconds": selected_timeout, "execute": bool(execute), "write_receipt": bool(write_receipt), diff --git a/tests/test_pixelrag_vlm_replay_worker_service.py b/tests/test_pixelrag_vlm_replay_worker_service.py index 63c6d64..b0179bc 100644 --- a/tests/test_pixelrag_vlm_replay_worker_service.py +++ b/tests/test_pixelrag_vlm_replay_worker_service.py @@ -204,44 +204,41 @@ def test_pixelrag_vlm_replay_worker_auto_selects_installed_candidate(tmp_path, m }, ) - class FakeOllama: - def __init__(self, model): - self.model = model - - def generate(self, *args, **kwargs): - assert kwargs["model"] == "gemma3:4b" - return SimpleNamespace( - success=True, - content=json.dumps({ - "blocked_page_detected": False, - "fields": { - "title": { - "value": "防曬乳 SPF50", - "confidence": 0.92, - "evidence_refs": ["tile:1"], - }, - "price": { - "value": "399", - "confidence": 0.88, - "evidence_refs": ["tile:1"], - }, + def fake_generate_exact_host(prompt, **kwargs): + assert kwargs["host"] == "http://34.21.145.224:11434" + assert kwargs["model"] == "gemma3:4b" + return SimpleNamespace( + success=True, + content=json.dumps({ + "blocked_page_detected": False, + "fields": { + "title": { + "value": "防曬乳 SPF50", + "confidence": 0.92, + "evidence_refs": ["tile:1"], }, - "quality": { - "overall_confidence": 0.90, - "missing_required_fields": [], - "requires_identity_matcher_replay": True, - "requires_promotion_gate": True, + "price": { + "value": "399", + "confidence": 0.88, + "evidence_refs": ["tile:1"], }, - }), - model="gemma3:4b", - error=None, - total_duration=1.0, - host="http://34.21.145.224:11434", - input_tokens=10, - output_tokens=50, - ) + }, + "quality": { + "overall_confidence": 0.90, + "missing_required_fields": [], + "requires_identity_matcher_replay": True, + "requires_promotion_gate": True, + }, + }), + model="gemma3:4b", + error=None, + total_duration=1.0, + host="http://34.21.145.224:11434", + input_tokens=10, + output_tokens=50, + ) - monkeypatch.setattr(service, "OllamaService", FakeOllama) + monkeypatch.setattr(service, "_generate_exact_host", fake_generate_exact_host) payload = service.run_pixelrag_ollama_vlm_replay_worker( artifact_root=tmp_path, platform="shopee_tw", @@ -253,7 +250,9 @@ def test_pixelrag_vlm_replay_worker_auto_selects_installed_candidate(tmp_path, m assert payload["model"] == "gemma3:4b" assert payload["configured_model"] == "minicpm-v:latest" + assert payload["route_candidate_host"] == "http://34.21.145.224:11434" assert payload["route_readiness"]["summary"]["candidate_model"] == "gemma3:4b" + assert payload["worker_items"][0]["route_candidate_host"] == "http://34.21.145.224:11434" assert payload["summary"]["executed_ok_count"] == 1