M1+M2: RAG-Pipeline mit verbindlichem Grounding

agent/-Paket: Ingest (601 Layer-2-Eintraege -> 3005 Chunks, FTS5-BM25 +
Vektoren-Cache), Hybrid-Retrieval (RRF, Stand-Boost, cross_ref-Erweiterung),
Ollama-Client (embed/chat, think-Flag-Fallback, kurzes Connect-Budget),
Systemprompt mit Zitierpflicht, Post-Validierung (zitierte IDs gemaess
Retrieved-Set, 1x Regenerierung, dann Verweigerung), FastAPI (/ask, /health,
/reindex), CLI, Goldset (31 Fragen, IDs gegen kb.json verifiziert, inkl.
ATZ-Konfliktfall + 4 Verweigerungsfaelle), Eval-Suite, Test-Chat.

41 Offline-Tests gruen. Baseline BM25-only: Hit-Rate 0,871 / Recall@8 0,855 /
MRR 0,476. Hybrid-Messung, Antwortmodus-Eval und Modell-Bake-off (M3) auf
dem Host ausstaendig (Ollama aus der Zed-Sandbox nicht erreichbar).

MEMORY.md und planung.md Umsetzungsstand aktualisiert.

tests/test_kb.py

@@ -0,0 +1,74 @@
+"""Tests: Layer-2-Parsing, Sektionen, Cross-Ref-Integrität, kb.json-Gate."""
+import json
+from pathlib import Path
+
+import pytest
+
+from agent.kb import KbValidationError, load_entry, load_kb, parse_frontmatter, split_sections
+from tests.conftest import DOC_ATZ, MIN_IDS, write_mini_kb
+
+
+def test_parse_frontmatter_and_sections():
+    meta, body = parse_frontmatter(DOC_ATZ)
+    assert meta["id"] == "lb-min-01"
+    assert meta["stand"] == "2026-01"
+    sections = split_sections(body)
+    titles = [s.title for s in sections]
+    assert "Zusammenfassung" in titles
+    assert titles[1].startswith("Kernwerte & Fristen")
+    assert all(s.text for s in sections)
+
+
+def test_split_sections_ignores_h1_and_intro():
+    sections = split_sections("# Titel\n\n*Quellzeile*\n\n## A\n\nText A\n\n## B\n\nText B")
+    assert [s.title for s in sections] == ["A", "B"]
+    assert sections[0].text == "Text A"
+
+
+def test_load_entry_minimal_doc(tmp_path):
+    p = tmp_path / "doc.md"
+    p.write_text(DOC_ATZ, encoding="utf-8")
+    e = load_entry(p)
+    assert e.id == "lb-min-01"
+    assert e.tags == ["altersteilzeit", "lohnausgleich"]
+    assert e.cross_refs == ["lb-min-02"]
+    assert len(e.sections) >= 3
+
+
+def test_gate_rejects_out_of_sync_registry(tmp_path):
+    root = write_mini_kb(tmp_path / "kb")
+    kb = json.loads((root / "kb.json").read_text(encoding="utf-8"))
+    kb["entries"].append({"id": "lb-min-99"})
+    (root / "kb.json").write_text(json.dumps(kb), encoding="utf-8")
+    with pytest.raises(KbValidationError, match="out of sync"):
+        load_kb(root)
+
+
+def test_gate_rejects_dangling_cross_refs(tmp_path):
+    root = write_mini_kb(tmp_path / "kb")
+    doc = root / "dokumente" / "altersteilzeit_uberblick.md"
+    doc.write_text(
+        DOC_ATZ.replace('cross_refs: ["lb-min-02"]', 'cross_refs: ["lb-min-42"]'),
+        encoding="utf-8",
+    )
+    with pytest.raises(KbValidationError, match="dangling cross_refs"):
+        load_kb(root)
+
+
+def test_gate_rejects_invalid_stand(tmp_path):
+    root = write_mini_kb(tmp_path / "kb")
+    doc = root / "dokumente" / "altersteilzeit_uberblick.md"
+    doc.write_text(DOC_ATZ.replace("stand: 2026-01", "stand: Jänner 2026"), encoding="utf-8")
+    with pytest.raises(KbValidationError, match="not YYYY-MM"):
+        load_kb(root)
+
+
+def test_real_corpus_loads_and_matches_registry():
+    """Integrationstest gegen die echte Wissensbasis (Gate inklusive)."""
+    entries = load_kb("wissensbasis", verify_registry=True)
+    ids = {e.id for e in entries}
+    assert len(entries) == 601
+    assert "lb-atz-07" in ids and "wk-akt-01" in ids
+    atz = [e for e in entries if e.id == "lb-atz-07"][0]
+    assert atz.topic == "altersteilzeit"
+    assert any(s.title.startswith("Kernwerte") for s in atz.sections)