Benjamin_Boenisch/breakpilot-compliance
1
0
Fork 0
Code Issues 24 Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Scan quality — raise page limit, use full DSI text for checks

Browse Source 
Bug 1: max_pages was hardcoded to 15 in backend call — raised to 50
Bug 2: DSI documents checked against text_preview (500 chars) — now uses
       full_text (10,000 chars) for Art. 13 mandatory field checks
Bug 3: DSE text not found when Playwright misses DSE page — now falls
       back to DSI Discovery full_text as second source
Bug 4: Backend timeout 120s too short for 50 pages — raised to 300s

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-05-04 23:51:03 +02:00
parent f967480cd9
commit a3f7fb93f4
2 changed files with 24 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend-compliance/compliance/api/agent_scan_routes.py
+22 -9
View File
@@ -114,10 +114,10 @@ async def scan_website_endpoint(req: ScanRequest):
# Step 1: Scan website — try Playwright first (JS-rendered), fallback to httpx
playwright_htmls: dict[str, str] = {}
try:
async with httpx.AsyncClient(timeout=120.0) as pw_client:
async with httpx.AsyncClient(timeout=300.0) as pw_client:
pw_resp = await pw_client.post(
"http://bp-compliance-consent-tester:8094/website-scan",
json={"url": req.url, "max_pages": 15, "click_nav": True},
json={"url": req.url, "max_pages": 50, "click_nav": True},
)
if pw_resp.status_code == 200:
pw_data = pw_resp.json()
@@ -172,8 +172,9 @@ async def scan_website_endpoint(req: ScanRequest):
)
for doc in dsi_data.get("documents", []):
doc_type = classify_document_type(doc["title"], doc["url"])
doc_text = doc.get("full_text", "") or doc.get("text_preview", "")
doc_findings = check_document_completeness(
doc.get("text_preview", ""), doc_type, doc["title"], doc["url"],
doc_text, doc_type, doc["title"], doc["url"],
)
# Count completeness
score_finding = next((f for f in doc_findings if "SCORE" in f.get("code", "")), None)
@@ -199,16 +200,28 @@ async def scan_website_endpoint(req: ScanRequest):
except Exception as e:
logger.warning("DSI discovery failed: %s", e)
# Step 2: Fetch privacy policy text (from Playwright HTMLs or httpx)
# Step 2: Fetch privacy policy text
# Priority: 1) Playwright HTMLs, 2) DSI Discovery full_text, 3) httpx fallback
dse_text = ""
for page_url, html in playwright_htmls.items():
if re.search(r"datenschutz|privacy|dsgvo", page_url, re.IGNORECASE):
import re as _re
clean = _re.sub(r"<(script|style)[^>]*>.*?</\1>", "", html, flags=_re.DOTALL | _re.IGNORECASE)
clean = _re.sub(r"<[^>]+>", " ", clean)
clean = _re.sub(r"\s+", " ", clean).strip()
dse_text = clean[:4000]
clean = re.sub(r"<(script|style)[^>]*>.*?</\1>", "", html, flags=re.DOTALL | re.IGNORECASE)
clean = re.sub(r"<[^>]+>", " ", clean)
clean = re.sub(r"\s+", " ", clean).strip()
dse_text = clean[:8000]
break
# Fallback: use DSI discovery texts (combined from all DSE documents found)
if not dse_text and discovered_docs:
try:
dsi_data_local = dsi_resp.json() if 'dsi_resp' in dir() else {}
for doc in dsi_data_local.get("documents", []):
if doc.get("doc_type", "") in ("dse", "privacy", "datenschutz") or \
"datenschutz" in doc.get("title", "").lower():
ft = doc.get("full_text", "")
if ft and len(ft) > len(dse_text):
dse_text = ft[:8000]
except Exception:
pass
if not dse_text:
dse_text = await _fetch_dse_text(req.url, scan.pages_scanned)