feat(checkers): platform router + Haiku sufficiency tier; cookie is first consumer

Generalise "Embedding finds, Claude decides" into the shared Pruefer-Library:
- router.route_and_check dispatches control -> sensor_classification -> Checker.
- build_spec reads sensor_classification (CONTENT/LLM -> judge=haiku, the
  validated sufficiency tier; the Qwen-first cascade is disproven for sufficiency).
- LLMChecker gains a Haiku-direct tier (reuses the validated deep_check prompt).
- Cookie Layer-3 now routes through route_and_check instead of bespoke code, so
  cookie is the first real router consumer -- proves the architecture end-to-end.

Reproduces the validated result via the shared path: FN 159->14, recall
0.13->0.92, precision 0.89 (vs bespoke 12/0.93/0.90 -- within Haiku noise).
Tests: 10/10 (router dispatch + build_spec + haiku tier + cookie rewire).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend-compliance/tests/test_checker_router.py

@@ -0,0 +1,51 @@
+"""Prüfer-Router: build_spec aus sensor_classification + method-agnostischer
+Dispatch. CONTENT/LLM -> Haiku-Sufficiency-Tier (validiert), unbekannte
+decision_methods -> fail-safe present=None."""
+import pytest
+from unittest.mock import AsyncMock, patch
+
+from compliance.services.checkers.base import DocContext
+from compliance.services.checkers.router import build_spec, route_and_check
+
+_ANTHROPIC = "compliance.services.llm_cascade._call_anthropic"
+
+
+def test_build_spec_content_llm_uses_haiku():
+    s = build_spec("X", {"verification_method": "CONTENT", "decision_method": "LLM"},
+                   label="L", criteria=["a", "b"])
+    assert s.verification_method == "CONTENT" and s.decision_method == "LLM"
+    assert s.extra.get("judge") == "haiku"
+    assert s.paraphrases == ["a", "b"]
+
+
+def test_build_spec_embedding_no_haiku():
+    s = build_spec("X", {"verification_method": "CONTENT", "decision_method": "EMBEDDING"})
+    assert s.extra.get("judge") is None
+
+
+@pytest.mark.asyncio
+async def test_route_unknown_decision_is_failsafe():
+    s = build_spec("X", {"verification_method": "BEHAVIOR", "decision_method": "PLAYWRIGHT"})
+    r = await route_and_check(s, DocContext(text="x" * 200))
+    assert r.present is None and "no_checker" in r.source
+
+
+@pytest.mark.asyncio
+async def test_route_content_llm_haiku_fehlt():
+    s = build_spec("X", {"verification_method": "CONTENT", "decision_method": "LLM"},
+                   label="Speicherdauer", criteria=["Höchstdauer pro Kategorie"])
+    fake = AsyncMock(return_value='{"erfuellt": false, "confidence": 0.9, "begruendung": "fehlt"}')
+    with patch(_ANTHROPIC, new=fake):
+        r = await route_and_check(s, DocContext(text="Wir nutzen Cookies. " * 30))
+    assert r.present is False and r.source == "haiku"
+    assert fake.call_count >= 1
+
+
+@pytest.mark.asyncio
+async def test_route_content_llm_haiku_erfuellt():
+    s = build_spec("X", {"verification_method": "CONTENT", "decision_method": "LLM"},
+                   label="L", criteria=["x"])
+    fake = AsyncMock(return_value='{"erfuellt": true, "confidence": 0.8}')
+    with patch(_ANTHROPIC, new=fake):
+        r = await route_and_check(s, DocContext(text="text " * 40))
+    assert r.present is True

backend-compliance/tests/test_cookie_sufficiency_judge.py

@@ -8,6 +8,7 @@ from compliance.services.specialist_agents.cookie_policy._sufficiency_judge impo
 )
 
 _ANTHROPIC = "compliance.services.llm_cascade._call_anthropic"
+_DOC = "Volltext der Cookie-Richtlinie mit ausreichend Inhalt. " * 4
 
 
 def _r(cid, source, passed=True):
@@ -20,7 +21,7 @@ async def test_rescued_unpassed_when_judge_fehlt():
     results = [_r("A", "keyword+embedding")]
     fake = AsyncMock(return_value='{"erfuellt": false, "confidence": 0.9, "begruendung": "fehlt"}')
     with patch(_ANTHROPIC, new=fake):
-        n = await judge_rescued("text", results)
+        n = await judge_rescued(_DOC, results)
     assert n == 1
     assert results[0]["passed"] is False
     assert "+llm_failed" in results[0]["source"]
@@ -31,7 +32,7 @@ async def test_rescued_kept_when_judge_erfuellt():
     results = [_r("A", "keyword+embedding")]
     fake = AsyncMock(return_value='{"erfuellt": true, "confidence": 0.9}')
     with patch(_ANTHROPIC, new=fake):
-        n = await judge_rescued("text", results)
+        n = await judge_rescued(_DOC, results)
     assert n == 0
     assert results[0]["passed"] is True
 
@@ -42,7 +43,7 @@ async def test_keyword_pass_not_judged():
     results = [_r("A", "keyword")]
     fake = AsyncMock(return_value='{"erfuellt": false}')
     with patch(_ANTHROPIC, new=fake):
-        n = await judge_rescued("text", results)
+        n = await judge_rescued(_DOC, results)
     assert n == 0
     assert results[0]["passed"] is True
     assert fake.call_count == 0
@@ -53,7 +54,7 @@ async def test_boost_rescue_is_judged():
     results = [_r("A", "keyword+regex_boost")]
     fake = AsyncMock(return_value='{"erfuellt": false}')
     with patch(_ANTHROPIC, new=fake):
-        n = await judge_rescued("text", results)
+        n = await judge_rescued(_DOC, results)
     assert n == 1 and results[0]["passed"] is False
 
 
@@ -63,5 +64,5 @@ async def test_failed_controls_ignored():
     results = [_r("A", "keyword+embedding", passed=False)]
     fake = AsyncMock(return_value='{"erfuellt": false}')
     with patch(_ANTHROPIC, new=fake):
-        n = await judge_rescued("text", results)
+        n = await judge_rescued(_DOC, results)
     assert n == 0 and fake.call_count == 0