wooo/ewoooc
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat(ai): 建立 PixelRAG VLM replay worker

Browse Source
This commit is contained in:
ogt
2026-07-09 23:30:43 +08:00
parent e34c9d777b
commit 55ce12e6b0
12 changed files with 1012 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
tests/test_ai_automation_smoke_service.py
View File

@@ -1434,11 +1434,12 @@ def test_collect_ai_automation_smoke_uses_worst_status(monkeypatch):
monkeypatch.setattr(smoke, "_external_mcp_rag_integration_check", lambda: smoke._check("external mcp rag", "ok", "ok"))
monkeypatch.setattr(smoke, "_pixelrag_rag_candidate_replay_check", lambda: smoke._check("pixelrag replay", "ok", "ok"))
monkeypatch.setattr(smoke, "_pixelrag_ocr_vlm_replay_check", lambda: smoke._check("pixelrag ocr vlm", "ok", "ok"))
monkeypatch.setattr(smoke, "_pixelrag_vlm_replay_worker_check", lambda: smoke._check("pixelrag vlm worker", "ok", "ok"))
result = smoke.collect_ai_automation_smoke(record_history=False)
assert result["status"] == "critical"
assert result["summary"] == {"ok": 32, "warning": 1, "critical": 1, "total": 34}
assert result["summary"] == {"ok": 33, "warning": 1, "critical": 1, "total": 35}
def test_pchome_controlled_apply_drift_monitor_reports_verified_zero_drift(monkeypatch):
@@ -3968,6 +3969,7 @@ def test_collect_ai_automation_smoke_persists_recent_history(tmp_path, monkeypat
monkeypatch.setattr(smoke, "_external_mcp_rag_integration_check", lambda: smoke._check("external mcp rag", "ok", "ok"))
monkeypatch.setattr(smoke, "_pixelrag_rag_candidate_replay_check", lambda: smoke._check("pixelrag replay", "ok", "ok"))
monkeypatch.setattr(smoke, "_pixelrag_ocr_vlm_replay_check", lambda: smoke._check("pixelrag ocr vlm", "ok", "ok"))
monkeypatch.setattr(smoke, "_pixelrag_vlm_replay_worker_check", lambda: smoke._check("pixelrag vlm worker", "ok", "ok"))
first = smoke.collect_ai_automation_smoke(history_limit=5)
second = smoke.collect_ai_automation_smoke(history_limit=5)
@@ -4023,7 +4025,7 @@ def test_scheduled_automation_health_summary_reads_history_without_side_effects(
json.dumps({
"generated_at": datetime.now().isoformat(timespec="seconds"),
"status": "ok",
"summary": {"ok": 34, "warning": 0, "critical": 0, "total": 34},
"summary": {"ok": 35, "warning": 0, "critical": 0, "total": 35},
"checks": [
{
"name": "PChome 受控落地 drift monitor",
@@ -4148,6 +4150,27 @@ def test_scheduled_automation_health_summary_reads_history_without_side_effects(
"blocked_pages_are_not_product_data": True,
"next_machine_action": "run_ollama_first_vlm_replay_worker",
},
},
{
"name": "PixelRAG VLM replay worker",
"status": "ok",
"summary": "PixelRAG VLM replay worker receipts=1, ready=1, dry_run=1, skipped=0, executed=0",
"details": {
"policy": "controlled_pixelrag_ollama_vlm_replay_worker_v1",
"receipt_count": 1,
"ready_count": 1,
"skipped_count": 0,
"dry_run_count": 1,
"executed_count": 0,
"executed_ok_count": 0,
"executed_warning_count": 0,
"model_error_count": 0,
"parse_error_count": 0,
"receipt_written_count": 0,
"model_call_performed": False,
"artifact_write_performed": False,
"next_machine_action": "run_pixelrag_vlm_replay_worker_execute",
},
}
],
}, ensure_ascii=False) + "\n",
@@ -4166,7 +4189,7 @@ 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"] == 31
assert summary["summary"]["total"] == 32
assert summary["summary"]["primary_human_gate_count"] == 0
assert summary["summary"]["writes_database_count"] == 0
assert pchome_family["status"] == "ok"
@@ -5849,6 +5872,15 @@ def test_scheduled_automation_health_summary_reads_history_without_side_effects(
assert pixelrag_ocr_vlm_replay_family["status"] == "ok"
assert pixelrag_ocr_vlm_replay_family["details"]["replay_ready_count"] == 1
assert pixelrag_ocr_vlm_replay_family["details"]["extraction_execution_performed"] is False
pixelrag_vlm_replay_worker_family = next(
item for item in summary["families"]
if item["key"] == "pixelrag_vlm_replay_worker"
)
assert pixelrag_vlm_replay_worker_family["status"] == "ok"
assert pixelrag_vlm_replay_worker_family["details"]["ready_count"] == 1
assert pixelrag_vlm_replay_worker_family["details"]["dry_run_count"] == 1
assert pixelrag_vlm_replay_worker_family["details"]["model_call_performed"] is False
assert pixelrag_vlm_replay_worker_family["details"]["writes_database_count"] == 0
assert summary["scheduled_outputs"]["telegram_send_in_preview"] is False
assert summary["scheduled_outputs"]["writes_database"] is False
assert summary["automation_policy"]["primary_flow"] == "ai_controlled"
@@ -6470,6 +6502,11 @@ def test_surface_html_readback_check_is_part_of_ai_smoke(monkeypatch):
"ok",
"pixelrag ocr vlm ok",
))
monkeypatch.setattr(smoke, "_pixelrag_vlm_replay_worker_check", lambda: smoke._check(
"PixelRAG VLM replay worker",
"ok",
"pixelrag vlm worker ok",
))
result = smoke.collect_ai_automation_smoke(record_history=False)
@@ -6485,7 +6522,7 @@ 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"] == 34
assert result["summary"]["total"] == 35
assert surface_check["status"] == "ok"
assert surface_check["details"]["checked_surface_count"] == 10
assert sitewide_check["status"] == "ok"

181
tests/test_pixelrag_vlm_replay_worker_service.py Normal file
View File

@@ -0,0 +1,181 @@
import json
import subprocess
import sys
from types import SimpleNamespace
from tests.test_pixelrag_ocr_vlm_replay_service import _write_receipt
def test_pixelrag_vlm_replay_worker_dry_run_keeps_blocked_pages_out(tmp_path):
from services.pixelrag_vlm_replay_worker_service import (
POLICY,
run_pixelrag_ollama_vlm_replay_worker,
)
_write_receipt(
tmp_path,
platform="shopee_tw",
manifest_id="shopee-ok",
title="Shopee 防曬乳",
url="https://shopee.tw/search?keyword=sunscreen",
)
_write_receipt(
tmp_path,
platform="coupang_tw",
manifest_id="coupang-403",
title="Access Denied",
url="https://www.tw.coupang.com/search?q=iphone",
http_status=403,
)
payload = run_pixelrag_ollama_vlm_replay_worker(
artifact_root=tmp_path,
platform=("shopee_tw", "coupang_tw"),
)
assert payload["policy"] == POLICY
assert payload["status"] == "warning"
assert payload["execute"] is False
assert payload["summary"]["receipt_count"] == 2
assert payload["summary"]["ready_count"] == 1
assert payload["summary"]["dry_run_count"] == 1
assert payload["summary"]["skipped_count"] == 1
assert payload["summary"]["model_call_performed"] is False
assert payload["summary"]["artifact_write_performed"] is False
assert payload["summary"]["writes_database_count"] == 0
assert payload["controlled_apply"]["primary_human_gate_count"] == 0
assert payload["next_machine_action"] == "run_pixelrag_vlm_replay_worker_execute"
by_platform = {item["platform"]: item for item in payload["worker_items"]}
assert by_platform["shopee_tw"]["worker_status"] == "dry_run_ready"
assert by_platform["coupang_tw"]["worker_status"] == "skipped_blocked_or_not_ready"
def test_pixelrag_vlm_replay_worker_execute_writes_artifact_receipt(tmp_path, monkeypatch):
from services import pixelrag_vlm_replay_worker_service as service
_write_receipt(
tmp_path,
platform="shopee_tw",
manifest_id="shopee-ok",
title="Shopee 防曬乳",
url="https://shopee.tw/search?keyword=sunscreen",
)
class FakeOllama:
def __init__(self, model):
self.model = model
def generate(self, *args, **kwargs):
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:2"],
},
},
"quality": {
"overall_confidence": 0.89,
"missing_required_fields": [],
"requires_identity_matcher_replay": True,
"requires_promotion_gate": True,
},
"notes": [],
}),
model="minicpm-v:latest",
error=None,
total_duration=1.5,
host="http://34.87.90.216:11434",
input_tokens=12,
output_tokens=80,
)
monkeypatch.setattr(service, "OllamaService", FakeOllama)
payload = service.run_pixelrag_ollama_vlm_replay_worker(
artifact_root=tmp_path,
output_root=tmp_path / "receipts",
platform="shopee_tw",
execute=True,
write_receipt=True,
tile_limit=1,
)
assert payload["status"] == "ok"
assert payload["summary"]["executed_count"] == 1
assert payload["summary"]["executed_ok_count"] == 1
assert payload["summary"]["receipt_written_count"] == 1
assert payload["summary"]["writes_database_count"] == 0
item = payload["worker_items"][0]
assert item["worker_status"] == "executed_ok"
assert item["provider"] == "gcp_ollama"
assert item["validation"]["valid_for_identity_matcher_replay"] is True
receipt_path = tmp_path / "receipts" / "shopee_tw" / "shopee-ok" / "vlm_replay_receipt.json"
assert receipt_path.exists()
receipt = json.loads(receipt_path.read_text(encoding="utf-8"))
assert receipt["parsed_output"]["fields"]["title"]["value"] == "防曬乳 SPF50"
def test_pixelrag_vlm_replay_worker_cli_outputs_machine_readable_json(tmp_path):
_write_receipt(
tmp_path,
platform="shopee_tw",
manifest_id="shopee-ok",
title="Shopee 防曬乳",
url="https://shopee.tw/search?keyword=sunscreen",
)
completed = subprocess.run(
[
sys.executable,
"scripts/ops/run_pixelrag_vlm_replay_worker.py",
"--artifact-root",
str(tmp_path),
"--platform",
"shopee_tw",
],
capture_output=True,
check=False,
text=True,
)
assert completed.returncode == 0
payload = json.loads(completed.stdout)
assert payload["summary"]["receipt_count"] == 1
assert payload["summary"]["dry_run_count"] == 1
assert payload["controlled_apply"]["model_call"] is False
assert payload["controlled_apply"]["writes_database"] is False
def test_pixelrag_vlm_replay_worker_route_returns_readback(tmp_path, monkeypatch):
from flask import Flask
from routes import system_public_routes as routes
from services import pixelrag_vlm_replay_worker_service as service
_write_receipt(
tmp_path,
platform="shopee_tw",
manifest_id="shopee-ok",
title="Shopee 防曬乳",
url="https://shopee.tw/search?keyword=sunscreen",
)
monkeypatch.setattr(service, "DEFAULT_ARTIFACT_ROOT", str(tmp_path))
app = Flask(__name__)
with app.test_request_context(
"/api/ai-automation/pixelrag-vlm-replay-worker?platform=shopee_tw"
):
response = routes.ai_automation_pixelrag_vlm_replay_worker_api.__wrapped__()
payload = response.get_json()
assert payload["policy"] == "controlled_pixelrag_ollama_vlm_replay_worker_v1"
assert payload["summary"]["receipt_count"] == 1
assert payload["summary"]["dry_run_count"] == 1
assert payload["controlled_apply"]["model_call"] is False