Files
ewoooc/tests/test_pixelrag_rag_candidate_replay_service.py

309 lines
11 KiB
Python

import json
import subprocess
import sys
from datetime import datetime, timezone
def _write_receipt(root, *, platform, manifest_id, title, url, http_status=200):
receipt_dir = root / platform / manifest_id
tiles_dir = receipt_dir / "tiles"
tiles_dir.mkdir(parents=True)
screenshot = receipt_dir / "screenshot.png"
screenshot.write_bytes(b"png")
files = [{"kind": "screenshot", "path": str(screenshot)}]
for index in range(4):
tile = tiles_dir / f"tile-{index}.png"
tile.write_bytes(b"tile")
files.append({"kind": "tile", "path": str(tile)})
receipt = {
"generated_at": datetime.now(timezone.utc).isoformat(),
"status": "captured",
"manifest_id": manifest_id,
"http_status": http_status,
"capture_target": {
"platform": platform,
"url": url,
"crawler": "PixelRAGMarketplaceSearch.visual_fallback",
},
"page_metrics": {
"title": title,
"final_url": url,
},
"tile_plan": {
"planned_tile_count": 4,
"emitted_tile_count": 4,
},
"files": files,
}
path = receipt_dir / "capture_receipt.json"
path.write_text(json.dumps(receipt, ensure_ascii=False), encoding="utf-8")
return path
def _write_platform_probe_worker_receipt(
root,
*,
platform,
manifest_id,
worker_status="executed_structured_source_fallback_package",
barrier_type="access_denied",
capture_runtime_unavailable=False,
):
receipt_dir = root / platform / manifest_id
receipt_dir.mkdir(parents=True)
payload = {
"platform": platform,
"manifest_id": manifest_id,
"source_type": "capture_receipt",
"source_receipt_path": f"runtime_artifacts/pixelrag_visual_evidence/{platform}/{manifest_id}/capture_receipt.json",
"worker_status": worker_status,
"probe_status": "structured_source_or_backoff_required",
"barrier_type": barrier_type,
"network_call_performed": False,
"artifact_write_performed": True,
"writes_database": False,
"next_machine_action": "run_structured_source_or_platform_backoff_policy",
"structured_source_package": {
"adapter_code": platform.replace("_tw", ""),
"available": True,
"source_count": 2,
"network_request_allowed": False,
"database_write_allowed": False,
"dry_run_only": True,
"blocked_page_not_product_data": True,
"capture_runtime_unavailable": capture_runtime_unavailable,
},
}
path = receipt_dir / "platform_probe_worker_receipt.json"
path.write_text(json.dumps(payload, ensure_ascii=False), encoding="utf-8")
return path
def test_pixelrag_rag_candidate_replay_splits_eligible_and_blocked_receipts(tmp_path):
from services.pixelrag_rag_candidate_replay_service import (
POLICY,
build_pixelrag_rag_candidate_replay_readback,
)
_write_receipt(
tmp_path,
platform="shopee_tw",
manifest_id="shopee-ok",
title="Shopee 防曬乳",
url="https://shopee.tw/search?keyword=%E9%98%B2%E6%9B%AC%E4%B9%B3",
)
_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 = build_pixelrag_rag_candidate_replay_readback(
artifact_root=tmp_path,
platform_probe_worker_receipt_root=tmp_path / "worker_empty",
)
by_platform = {item["platform"]: item for item in payload["candidates"]}
assert payload["policy"] == POLICY
assert payload["status"] == "warning"
assert payload["summary"]["receipt_count"] == 2
assert payload["summary"]["eligible_count"] == 1
assert payload["summary"]["blocked_count"] == 1
assert payload["summary"]["visual_barrier_count"] == 1
assert by_platform["shopee_tw"]["eligible_for_rag_candidate_replay"] is True
assert by_platform["shopee_tw"]["promotion_boundary"]["direct_ai_insights_write_allowed"] is False
assert "Shopee 防曬乳" in by_platform["shopee_tw"]["rag_candidate_text"]
assert by_platform["coupang_tw"]["eligible_for_rag_candidate_replay"] is False
assert by_platform["coupang_tw"]["visual_barrier_reason"] == "http_status_403"
assert by_platform["coupang_tw"]["next_machine_action"] == "run_platform_probe_or_use_structured_api"
assert payload["replay_contract"]["blocked_pages_are_not_product_data"] is True
assert payload["controlled_apply"]["db_write"] is False
def test_pixelrag_rag_candidate_replay_reads_platform_probe_worker_receipts(tmp_path):
from services.pixelrag_rag_candidate_replay_service import (
build_pixelrag_rag_candidate_replay_readback,
)
worker_root = tmp_path / "worker"
_write_platform_probe_worker_receipt(
worker_root,
platform="coupang_tw",
manifest_id="coupang-403",
barrier_type="access_denied",
)
_write_platform_probe_worker_receipt(
worker_root,
platform="shopee_tw",
manifest_id="shopee-runtime-gap",
worker_status="capture_runtime_unavailable_structured_fallback_package",
barrier_type="traffic_verification_interstitial",
capture_runtime_unavailable=True,
)
payload = build_pixelrag_rag_candidate_replay_readback(
artifact_root=tmp_path / "visual_empty",
platform_probe_worker_receipt_root=worker_root,
platform=("coupang_tw", "shopee_tw"),
)
by_platform = {item["platform"]: item for item in payload["candidates"]}
assert payload["status"] == "ok"
assert payload["summary"]["receipt_count"] == 2
assert payload["summary"]["visual_receipt_count"] == 0
assert payload["summary"]["platform_probe_worker_receipt_count"] == 2
assert payload["summary"]["source_contract_fallback_count"] == 2
assert payload["summary"]["capture_runtime_gap_count"] == 1
assert payload["next_machine_action"] == (
"run_source_contract_replay_for_platform_probe_worker_receipts"
)
assert by_platform["coupang_tw"]["candidate_status"] == "source_contract_fallback"
assert by_platform["coupang_tw"]["eligible_for_source_contract_replay"] is True
assert by_platform["coupang_tw"]["eligible_for_rag_candidate_replay"] is False
assert by_platform["coupang_tw"]["promotion_boundary"][
"requires_source_contract_before_knowledge_write"
] is True
assert by_platform["shopee_tw"]["platform_probe_worker"][
"structured_source_package"
]["capture_runtime_unavailable"] is True
assert payload["replay_contract"][
"platform_probe_worker_receipts_are_source_contract_candidates"
] is True
assert payload["controlled_apply"]["db_write"] is False
def test_pixelrag_rag_candidate_replay_prefers_worker_source_contract_handoff(tmp_path):
from services.pixelrag_rag_candidate_replay_service import (
build_pixelrag_rag_candidate_replay_readback,
)
visual_root = tmp_path / "visual"
worker_root = tmp_path / "worker"
_write_receipt(
visual_root,
platform="coupang_tw",
manifest_id="coupang-403",
title="Access Denied",
url="https://www.tw.coupang.com/search?q=iphone",
http_status=403,
)
_write_platform_probe_worker_receipt(
worker_root,
platform="coupang_tw",
manifest_id="coupang-403",
barrier_type="access_denied",
)
payload = build_pixelrag_rag_candidate_replay_readback(
artifact_root=visual_root,
platform_probe_worker_receipt_root=worker_root,
platform="coupang_tw",
)
assert payload["summary"]["visual_barrier_count"] == 1
assert payload["summary"]["source_contract_fallback_count"] == 1
assert payload["next_machine_action"] == (
"run_source_contract_replay_for_platform_probe_worker_receipts"
)
def test_pixelrag_rag_candidate_replay_combines_ready_and_source_contract_actions(tmp_path):
from services.pixelrag_rag_candidate_replay_service import (
build_pixelrag_rag_candidate_replay_readback,
)
visual_root = tmp_path / "visual"
worker_root = tmp_path / "worker"
_write_receipt(
visual_root,
platform="shopee_tw",
manifest_id="shopee-ok",
title="Shopee 防曬乳",
url="https://shopee.tw/search?keyword=sunscreen",
)
_write_platform_probe_worker_receipt(
worker_root,
platform="coupang_tw",
manifest_id="coupang-403",
barrier_type="access_denied",
)
payload = build_pixelrag_rag_candidate_replay_readback(
artifact_root=visual_root,
platform_probe_worker_receipt_root=worker_root,
platform=("shopee_tw", "coupang_tw"),
)
assert payload["summary"]["eligible_count"] == 1
assert payload["summary"]["source_contract_fallback_count"] == 1
assert payload["next_machine_action"] == (
"run_ocr_vlm_replay_and_source_contract_replay"
)
def test_pixelrag_rag_candidate_replay_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/report_pixelrag_rag_candidate_replay.py",
"--artifact-root",
str(tmp_path),
"--platform",
"shopee_tw",
"--platform-probe-worker-receipt-root",
str(tmp_path / "worker_empty"),
],
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"]["eligible_count"] == 1
assert payload["candidates"][0]["platform"] == "shopee_tw"
def test_pixelrag_rag_candidate_replay_route_returns_readback(tmp_path, monkeypatch):
from flask import Flask
from routes import system_public_routes as routes
from services import pixelrag_rag_candidate_replay_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))
monkeypatch.setattr(
service,
"DEFAULT_PLATFORM_PROBE_WORKER_RECEIPT_ROOT",
str(tmp_path / "worker_empty"),
)
app = Flask(__name__)
with app.test_request_context(
"/api/ai-automation/pixelrag-rag-candidate-replay?platform=shopee_tw"
):
response = routes.ai_automation_pixelrag_rag_candidate_replay_api.__wrapped__()
payload = response.get_json()
assert payload["policy"] == "read_only_pixelrag_rag_candidate_replay_v1"
assert payload["summary"]["receipt_count"] == 1
assert payload["summary"]["eligible_count"] == 1
assert payload["replay_contract"]["writes_database"] is False