feat(agb): wire validated routed AGB engine into live check path

Consolidate the AGB C-lean engine (71% FP -> ~0, validated vs 7-company Opus GT) onto the canonical checker library and into the live check path. - AGBAgent.evaluate now runs routed C-lean: keyword (L1/L2) -> business- model gate -> per-item decision_method routing (embedding/reference/llm via services/checkers/) -> severity re-tiering (LOW -> recommendation), honoring context.skip_llm. - New agb/_pipeline.py orchestrates the routing; agent.py stays thin. - Remove the 3 AGB-local checker duplicates (_reference_check, _embedding_rescue, _llm_judge); services/checkers/ is now canonical. - Wire "agb" into _agent_outputs._TOPIC_AGENTS so the live check emits a validated AGB tab (was snapshot-only). - Run topic agents concurrently (asyncio.gather) + emit each tab via SSE as it finishes -> progressive results, no wait on the slowest agent. - Tests: checker units (mocked), routed agent (gate/rescue/re-tier), topic wiring; existing AGB tests made offline-safe. dev-only, no deploy. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-21 10:40:08 +02:00
parent 9d79cf1576
commit 32e45f0797
10 changed files with 341 additions and 195 deletions
@@ -0,0 +1,83 @@
+"""Unit-Tests der Prüfer-Library. Embedding + LLM gemockt → kein Netzwerk."""
+import asyncio
+
+import compliance.services.llm_cascade as cascade_mod
+import compliance.services.mc_embedding_matcher as emb_mod
+from compliance.services.checkers.base import (
+    ControlSpec,
+    DecisionMethod,
+    DocContext,
+    VerificationMethod,
+)
+from compliance.services.checkers.embedding_checker import EmbeddingChecker
+from compliance.services.checkers.llm_checker import LLMChecker
+from compliance.services.checkers.reference_checker import ReferenceChecker
+
+
+def _run(coro):
+    return asyncio.run(coro)
+
+
+def test_reference_present_and_absent():
+    rc = ReferenceChecker()
+    spec = ControlSpec("data_protection", VerificationMethod.REFERENCE,
+                       DecisionMethod.LINK_RESOLVER,
+                       patterns=[r"datenschutz(erkl|bestimmung|hinweis)"])
+    r = _run(rc.check(spec, DocContext(
+        text="Details in unserer Datenschutzerklaerung: https://x.de/datenschutz")))
+    assert r.present is True
+    assert r.detail.get("link", "").startswith("https://")
+    r2 = _run(rc.check(spec, DocContext(text="Keine Angabe zum Datenschutz-Thema.")))
+    assert r2.present is False
+
+
+def test_embedding_threshold(monkeypatch):
+    monkeypatch.setattr(emb_mod, "DIM", 3, raising=False)
+    monkeypatch.setattr(emb_mod, "_chunk_text", lambda t: [t], raising=False)
+
+    async def _embed(texts):
+        return [[1.0, 0.0, 0.0] for _ in texts]
+
+    monkeypatch.setattr(emb_mod, "_embed_texts", _embed, raising=False)
+    ec = EmbeddingChecker()
+    spec = ControlSpec("scope_t", VerificationMethod.CONTENT, DecisionMethod.EMBEDDING,
+                       paraphrases=["Geltungsbereich"], embed_threshold=0.58)
+    monkeypatch.setattr(emb_mod, "_cosine", lambda a, b: 0.90, raising=False)
+    r = _run(ec.check(spec, DocContext(text="x" * 200)))
+    assert r.present is True and r.confidence >= 0.58
+    monkeypatch.setattr(emb_mod, "_cosine", lambda a, b: 0.20, raising=False)
+    r2 = _run(ec.check(spec, DocContext(text="x" * 200)))
+    assert r2.present is False
+
+
+def test_embedding_offline_returns_none(monkeypatch):
+    async def _boom(texts):
+        raise ConnectionError("embedding-service down")
+
+    monkeypatch.setattr(emb_mod, "_embed_texts", _boom, raising=False)
+    ec = EmbeddingChecker()
+    spec = ControlSpec("scope_off", VerificationMethod.CONTENT, DecisionMethod.EMBEDDING,
+                       paraphrases=["x"], embed_threshold=0.6)
+    r = _run(ec.check(spec, DocContext(text="y" * 200)))
+    assert r.present is None  # fail-safe
+
+
+def test_llm_present_and_absent(monkeypatch):
+    lc = LLMChecker()
+    spec = ControlSpec("delivery_timeframe", VerificationMethod.CONTENT, DecisionMethod.LLM,
+                       topic_regex=r"liefer", question="Konkrete Lieferfrist?")
+    doc = DocContext(text=("1. Lieferung\nDie Ware wird innerhalb von 2 Werktagen "
+                           "geliefert.\n") * 4)
+
+    async def _erfuellt(system, user, **kw):
+        return {"text": '{"verdict":"ERFUELLT","zitat":"2 Werktagen","begruendung":"x"}',
+                "source": "qwen", "confidence": 0.7}
+
+    monkeypatch.setattr(cascade_mod, "call_with_cascade", _erfuellt, raising=False)
+    assert _run(lc.check(spec, doc)).present is True
+
+    async def _fehlt(system, user, **kw):
+        return {"text": '{"verdict":"FEHLT"}', "source": "qwen"}
+
+    monkeypatch.setattr(cascade_mod, "call_with_cascade", _fehlt, raising=False)
+    assert _run(lc.check(spec, doc)).present is False