feat: Browser-Matrix C2 + B11 AI-Retention + Impressum-Specialist-Agent + B1 Mobile Playwright
Task #15 Stage 1.c-e — Browser-Matrix Backend-Integration: - _phase_c2_browser_matrix.py: ruft consent-tester /scan-matrix wenn env BROWSER_MATRIX=true, fuellt state["browser_matrix"] + state["browser_aggregate"] + state["browser_matrix_html"] - V2-Mail-Block: 🌐 Browser-Matrix Tabelle (Profile · Score · Sub-Scores PC/RR/BD · Bewertung) mit Worst-of-Header - Orchestrator ruft run_phase_c2 nach run_phase_c KNOWN: Stage 1.b (consent_scanner browser_profile-Param) bleibt zurueckgestellt (Datei in loc-exception, Hook-Patch verweigert). Stage 1.a-Shim laeuft im consent-tester — alle Profile aktuell auf Chromium, echte Engine-Diversitaet kommt mit 1.b. Task #17 TH-RETENTION-002 als B11 ai_retention_granularity_check: - Erkennt AI-Provider-Kontext (vertex/openai/anthropic/etc) - In +-800-char-Window: prueft ≥2 Datenkategorien aus Standard-Liste (Texteingaben/IP/Geraet/Session/Fehlerprotokoll/Zeitstempel) - Wenn 1 pauschale Speicherdauer + ≥2 Kategorien aber kein per-Kategorie-Differential → LOW - Smoke: Elli-Mock-DSE trifft LOW "AI-Speicherdauer pauschal" Task #18 Specialist-Agents Phase-1-Prototyp: - compliance/services/specialist_agents/__init__.py mit Architektur-Doku - impressum_agent.py: 9 Pflichtangaben § 5 TMG + § 1 DL-InfoV als Pattern-Registry (Name, Email, Telefon, HR, USt-IdNr, Vertretungsberechtigt, Aufsichtsbehoerde, Berufsangaben, OS-Link) - business_scope-aware (OS-Link nur fuer ecommerce, Aufsichtsbehoerde nur fuer regulated_profession/financial/insurance) - Phase-1 ist Pattern-Match-only (kein LLM), demonstriert die Schnittstelle. Phase 2 ersetzt Pattern durch System-Prompt + KB. - Smoke: minimal-Impressum triggert 4 Findings korrekt Task #7 B1 Playwright Mobile-Verifikation: - consent-tester/services/mobile_reachability_scanner.py: echte WebKit-launch + p.devices['iPhone 15'] preset + de-DE locale + Europe/Berlin timezone - Footer-Anchor-Suche via locator("footer >> text=/.../i") fuer 13 Reopen-Phrasen - Tap-Target-Boundingbox-Messung (Apple HIG / WCAG ≥44x44) - Click-Behavior: DOM-Modal-Snapshot vor/nach, erkennt CMP-Open - Output: has_anchor, anchor_text, tap_target_px, click_opens_cmp, engine_meta, screenshot_b64 (Footer-Crop wenn kein Anchor) - consent-tester/routes_mobile.py POST /scan-mobile-reachability - Backend _b1_wiring erweitert: ruft Mobile-Endpoint zuerst, Fallback auf statischen HTTP-Fetch. Mobile-Daten enrichen finding.mobile_playwright + Severity-Bump bei tap-target<44 / click-doesnt-open-CMP. KNOWN: WebKit-System-Libs sind im Dockerfile ergaenzt (Stage 1.a- Commit), greifen aber erst nach CI/CD-Rebuild des consent-tester. Bis dahin faellt B1 sauber auf statischen Fetch zurueck. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
@@ -0,0 +1,163 @@
|
||||
"""B1 Mobile Reachability — echter Playwright-Scan auf iPhone-Emulation.
|
||||
|
||||
Ersetzt den statischen HTTP-Fetch im Backend-B1-Wiring durch eine
|
||||
echte WebKit-Browser-Session mit `devices['iPhone 15']`-Preset. Misst:
|
||||
|
||||
- hat Footer einen Reopen-Anchor (Text/aria-label/onclick)?
|
||||
- Tap-Target-Größe (boundingBox in px) — Apple HIG 44pt = ≥44 px
|
||||
- Click-Behavior: öffnet sich der CMP direkt? (DOM-Mutation +
|
||||
Modal-Detection nach 2s)
|
||||
|
||||
Output schema (für Backend-B1 ersetzbar mit statischer Logik):
|
||||
|
||||
{
|
||||
"url": str,
|
||||
"has_anchor": bool,
|
||||
"anchor_text": str,
|
||||
"tap_target_px": {"w": int, "h": int} | None,
|
||||
"click_opens_cmp": bool,
|
||||
"modal_selector": str | None,
|
||||
"screenshot_b64": str (initial Footer-Crop),
|
||||
"engine_meta": {"engine": "webkit", "device": "iPhone 15",
|
||||
"user_agent": str, "viewport": str},
|
||||
}
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Phrasen für Footer-Anchor-Suche (mirror des Backend-Service)
|
||||
_REOPEN_PHRASES = (
|
||||
"cookie-einstellungen", "cookie einstellungen",
|
||||
"cookie-präferenzen", "cookie-praeferenzen",
|
||||
"cookie-einwilligung",
|
||||
"einwilligung verwalten",
|
||||
"consent manager", "consent settings", "consent-einstellungen",
|
||||
"datenschutz-einstellungen", "datenschutzeinstellungen",
|
||||
"cookies verwalten", "manage cookies", "manage preferences",
|
||||
"privacy settings", "privacy preferences",
|
||||
"tracking-einstellungen",
|
||||
)
|
||||
|
||||
|
||||
async def scan_mobile_reachability(url: str) -> dict[str, Any]:
|
||||
"""Run Mobile-Safari emulation + footer reachability check."""
|
||||
try:
|
||||
from playwright.async_api import async_playwright
|
||||
except Exception as e:
|
||||
logger.warning("playwright not available: %s", e)
|
||||
return {"url": url, "error": "playwright missing"}
|
||||
|
||||
async with async_playwright() as p:
|
||||
device_preset = p.devices.get("iPhone 15") or {}
|
||||
browser = await p.webkit.launch(headless=True)
|
||||
try:
|
||||
context = await browser.new_context(
|
||||
**device_preset,
|
||||
locale="de-DE",
|
||||
timezone_id="Europe/Berlin",
|
||||
)
|
||||
page = await context.new_page()
|
||||
try:
|
||||
await page.goto(url, wait_until="domcontentloaded",
|
||||
timeout=30000)
|
||||
except Exception as e:
|
||||
return {"url": url, "error": f"goto failed: {e}"[:200]}
|
||||
try:
|
||||
await page.wait_for_timeout(1500)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
ua = await page.evaluate("() => navigator.userAgent")
|
||||
viewport = page.viewport_size or {}
|
||||
engine_meta = {
|
||||
"engine": "webkit",
|
||||
"device": "iPhone 15",
|
||||
"user_agent": ua,
|
||||
"viewport": f"{viewport.get('width','?')}x{viewport.get('height','?')}",
|
||||
}
|
||||
|
||||
# Find footer reopen anchor by text matching
|
||||
anchor_loc = None
|
||||
for phrase in _REOPEN_PHRASES:
|
||||
try:
|
||||
candidate = page.locator(
|
||||
f"footer >> text=/{phrase}/i"
|
||||
).first
|
||||
if await candidate.count() > 0:
|
||||
anchor_loc = candidate
|
||||
anchor_text = phrase
|
||||
break
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
result: dict[str, Any] = {
|
||||
"url": url,
|
||||
"has_anchor": False,
|
||||
"anchor_text": "",
|
||||
"tap_target_px": None,
|
||||
"click_opens_cmp": False,
|
||||
"modal_selector": None,
|
||||
"engine_meta": engine_meta,
|
||||
}
|
||||
|
||||
if anchor_loc is None:
|
||||
# Capture footer crop
|
||||
try:
|
||||
footer = page.locator("footer").first
|
||||
if await footer.count() > 0:
|
||||
png = await footer.screenshot()
|
||||
result["screenshot_b64"] = base64.b64encode(
|
||||
png,
|
||||
).decode("ascii")[:120000]
|
||||
except Exception:
|
||||
pass
|
||||
return result
|
||||
|
||||
result["has_anchor"] = True
|
||||
result["anchor_text"] = anchor_text
|
||||
|
||||
try:
|
||||
box = await anchor_loc.bounding_box()
|
||||
if box:
|
||||
result["tap_target_px"] = {
|
||||
"w": int(box["width"]), "h": int(box["height"]),
|
||||
}
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# DOM-Modal-Snapshot vorher
|
||||
try:
|
||||
before_modals = await page.evaluate(
|
||||
"() => Array.from(document.querySelectorAll("
|
||||
"'[role=dialog],[aria-modal=true],.cmp-modal,"
|
||||
".ot-sdk-container,#usercentrics-cmp')).length"
|
||||
)
|
||||
except Exception:
|
||||
before_modals = 0
|
||||
|
||||
# Klick + warten
|
||||
try:
|
||||
await anchor_loc.click(timeout=5000)
|
||||
await page.wait_for_timeout(2000)
|
||||
after_modals = await page.evaluate(
|
||||
"() => Array.from(document.querySelectorAll("
|
||||
"'[role=dialog],[aria-modal=true],.cmp-modal,"
|
||||
".ot-sdk-container,#usercentrics-cmp')).length"
|
||||
)
|
||||
if after_modals > before_modals:
|
||||
result["click_opens_cmp"] = True
|
||||
result["modal_selector"] = (
|
||||
"[role=dialog] | [aria-modal=true] | cmp-modal"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.info("anchor click skipped: %s", e)
|
||||
|
||||
return result
|
||||
finally:
|
||||
await browser.close()
|
||||
Reference in New Issue
Block a user