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

fix(ai): classify empty PixelRAG VLM offers as platform barriers

Browse Source
This commit is contained in:
ogt
2026-07-10 00:41:39 +08:00
parent 2059ab3cc2
commit 9c7eb6f895
5 changed files with 87 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
services/pixelrag_vlm_replay_worker_service.py
View File

@@ -153,6 +153,8 @@ def _prompt_for_item(item: Mapping[str, Any]) -> str:
"Use only visible tile evidence and cite evidence_refs like tile:1.\n"
"If the tile is access denied, captcha, login, traffic verification, or not a product/search card, "
"set blocked_page_detected=true and leave product fields empty.\n"
"Language selection, region selection, app-download, landing, loading, logo-only, or cookie consent "
"pages are not product/search cards; set blocked_page_detected=true for them.\n"
"Required JSON schema:\n"
"{\n"
' "blocked_page_detected": false,\n'
@@ -183,6 +185,7 @@ def _validate_model_payload(
missing_required: list[str] = []
field_evidence_missing: list[str] = []
low_confidence_fields: list[str] = []
present_field_count = 0
blocked_detected = bool(parsed.get("blocked_page_detected"))
for contract in list(item.get("field_contract") or []):
@@ -198,6 +201,8 @@ def _validate_model_payload(
confidence = 0.0
min_confidence = float(contract.get("min_confidence") or DEFAULT_CONFIDENCE_THRESHOLD)
present = _field_value_present(value)
if present:
present_field_count += 1
if present and not evidence_refs:
field_evidence_missing.append(field_name)
if present and confidence < min_confidence:
@@ -213,14 +218,22 @@ def _validate_model_payload(
for field in declared_missing:
if field not in missing_required:
missing_required.append(field)
non_product_or_interstitial_detected = (
not blocked_detected
and present_field_count == 0
and bool(missing_required)
)
return {
"blocked_page_detected": blocked_detected,
"non_product_or_interstitial_detected": non_product_or_interstitial_detected,
"present_field_count": present_field_count,
"missing_required_fields": missing_required,
"field_evidence_missing": field_evidence_missing,
"low_confidence_fields": low_confidence_fields,
"valid_for_identity_matcher_replay": (
not blocked_detected
and not non_product_or_interstitial_detected
and not missing_required
and not field_evidence_missing
),
@@ -501,9 +514,12 @@ def _execute_item(
missing_required = list(validation.get("missing_required_fields") or [])
evidence_missing = list(validation.get("field_evidence_missing") or [])
blocked_detected = bool(validation.get("blocked_page_detected"))
non_product_or_interstitial = bool(
validation.get("non_product_or_interstitial_detected")
)
status = "executed_ok"
next_action = "run_identity_matcher_replay_then_promotion_gate"
if blocked_detected:
if blocked_detected or non_product_or_interstitial:
status = "executed_warning"
next_action = "run_platform_probe_or_use_structured_api"
elif missing_required or evidence_missing: