docs+feat(platform): Pruefer-Matrix-Foundation einfrieren (Evidenz, Mapping, Checker-Library, AGB-Kalibrierung)

Know-how-Freeze der Website-Compliance-Runde (DSE/Cookie/Impressum/AGB). docs: platform_evidence_v1 (Evidenz-/Qualitaetsnachweis, echte Zahlen), nutzungsbedingungen_mapping (neues Modul = Mapping, empirisch belegt), platform_checker_matrix (Meta-Modell verification_method x decision_method), verification_method, platform_validation_v1. code: checkers/ (reusable Pruefer-Library base+reference+embedding+llm, im Container validiert), agb/ (decision_method-Routing + Checker-Prototypen, 71% FP -> ~0 validiert). Dev-only, kein Prod-Push; Benchmark-GTs/Korpora im internen Archiv (data-retention). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-21 09:23:21 +02:00
parent 6b9c7984b4
commit 9d79cf1576
14 changed files with 900 additions and 0 deletions
@@ -0,0 +1,73 @@
+"""CONTENT/CONTRACTUAL-Pruefer / decision_method=LLM.
+
+present/absent ueber die LLM-Kaskade (`call_with_cascade`; prod: OVH-120b zuerst).
+Retrieval = GANZE Paragraph-Abschnitte zum Topic (nicht Top-k-Chunks — das war in
+der AGB-Validierung der Schluessel). KEIN DEFECT — Korrektheits-/Defekt-Pruefung
+ist ein separater Modus. present=None bei Fehler (fail-safe: Aufrufer behaelt
+Keyword-Ergebnis). (Validiert an AGB delivery/warranty.)
+"""
+from __future__ import annotations
+
+import json
+import logging
+import re
+
+from .base import CheckResult, ControlSpec, DocContext, VerificationMethod
+
+logger = logging.getLogger(__name__)
+
+_SECTION = re.compile(r"(?m)(?=^\s*(?:§\s*)?\d+[\.\)]\s)")
+_SYS = (
+    "Du bist deutscher Compliance-Rechtsexperte. Entscheide, ob die genannte "
+    "Pflicht in den vorgelegten Abschnitten vorhanden ist. NUR die Abschnitte "
+    'zaehlen. Antworte NUR JSON: {"verdict":"ERFUELLT|FEHLT","zitat":"woertlich '
+    'oder leer","begruendung":"1 Satz"}.'
+)
+
+
+def _sections(text: str) -> list[str]:
+    return [s.strip() for s in _SECTION.split(text) if s.strip()]
+
+
+def _parse(txt: str) -> dict:
+    out = (txt or "").strip()
+    if out.startswith("```"):
+        out = out.split("```", 2)[1]
+        out = out[4:] if out.startswith("json") else out
+    a, b = out.find("{"), out.rfind("}")
+    return json.loads(out[a:b + 1] if 0 <= a < b else out)
+
+
+class LLMChecker:
+    verification_method = VerificationMethod.CONTENT
+
+    async def check(self, ctrl: ControlSpec, doc: DocContext) -> CheckResult:
+        text = doc.text or ""
+        if len(text) < 50:
+            return CheckResult(present=None, source="llm")
+        secs = _sections(text)
+        if ctrl.topic_regex:
+            rel = [s for s in secs if re.search(ctrl.topic_regex, s, re.I)][:6] or secs[:6]
+        else:
+            rel = secs[:6]
+        question = ctrl.question or f"Ist die Pflicht '{ctrl.label}' im Text vorhanden?"
+        try:
+            from compliance.services.llm_cascade import call_with_cascade
+            r = await call_with_cascade(
+                _SYS,
+                json.dumps({"frage": question, "abschnitte": rel}, ensure_ascii=False),
+                min_confidence=0.6, max_tokens=500,
+            )
+            obj = _parse(r.get("text"))
+            verdict = obj.get("verdict")
+            zitat = (obj.get("zitat") or "")[:120]
+            if verdict not in ("ERFUELLT", "FEHLT"):
+                return CheckResult(present=None, evidence=zitat, source=r.get("source", "?"))
+            return CheckResult(
+                present=verdict == "ERFUELLT", evidence=zitat,
+                confidence=float(r.get("confidence") or 0.0),
+                source=r.get("source", "llm"),
+            )
+        except Exception as e:
+            logger.info("llm checker fail %s: %s", ctrl.control_id, str(e)[:80])
+            return CheckResult(present=None, source="error")