update

backend/qa.py

@@ -294,6 +294,24 @@ async def _llm_verdicts(template: str, topic: str, key: str, items: list[str]) -
 
 # ── Report ──────────────────────────────────────────────────────────────────────────
 
+def freispruch_pfad(topic: str) -> Path:
+    return QA_DIR / topic / "freispruch.json"
+
+
+def _paar_key(a: str, b: str) -> str:
+    return "||".join(sorted((_norm_title(a), _norm_title(b))))
+
+
+def lade_freispruch(topic: str) -> dict[str, list[str]]:
+    """Persistierte 2:1-Freisprüche des Repair-Stichentscheids (repair._mit_stichentscheid):
+    mehrheitlich als „behalten" geurteilte Befunde zählen nicht mehr in die Note — sonst
+    pendelte sie dauerhaft unter 10 ohne Fix-Pfad (gemessen: kanban-smoke 9.4, aak 9.2).
+    Die Detektoren bleiben unverändert; ein Freispruch ist ein persistiertes Urteil,
+    kein Detektor-Tuning. Freigesprochene bleiben im Report sichtbar."""
+    d = _json_file(freispruch_pfad(topic))
+    return d if isinstance(d, dict) else {}
+
+
 async def qa_report(topic: str, llm: bool = False) -> dict | None:
     cards = await db.kanban_cards(topic, board="inventory", stage="done_block")
     if not cards:
@@ -317,6 +335,11 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
     hy = hygiene(blocks)
     n_sections = sum(len(_sections(t)) for t in corpus.values()) or 1
 
+    frei = lade_freispruch(topic)
+    frei_fremd = set(frei.get("fremd") or [])
+    fremd_frei = [t for t in fr if _norm_title(t) in frei_fremd]
+    fr = [t for t in fr if _norm_title(t) not in frei_fremd]
+
     if llm and d:
         v = await _llm_verdicts("QA-Dubletten", topic, "dubletten",
                                 [f"A: {p['a']}\nB: {p['b']}" for p in d[:LLM_SAMPLE]])
@@ -334,6 +357,10 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
                                     [f"A: {p['a']}\nB: {p['b']}" for p in chunk])
             for k, p in enumerate(chunk, 1):
                 p["llm"] = v.get(k, "?")
+        frei_sub = set(frei.get("sub_dubletten") or [])
+        for p in sd:
+            if p.get("llm") == "ja" and _paar_key(p["a"], p["b"]) in frei_sub:
+                p["freispruch"] = True  # 2:1-Urteil „behalten" — sichtbar, aber notenfrei
     unecht: list[str] | None = None
     if llm and blocks:
         verdacht = []
@@ -350,6 +377,8 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
             v2 = await _llm_verdicts("QA-Bausteine", topic, "bausteine-b2",
                                      [f"{b['title']} — {b['description'] or '(ohne Beschreibung)'}" for b in verdacht])
             unecht = [b["title"] for k, b in enumerate(verdacht, 1) if v2.get(k) == "nein"]
+        frei_unecht = set(frei.get("unecht") or [])
+        unecht = [t for t in unecht if _norm_title(t) not in frei_unecht]
 
     art_rows = [dict(r) for r in await db.get_sub_artefakte(topic)]
     fragen = [dict(r) for r in await db.list_question_pattern(topic)]
@@ -362,8 +391,10 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
     n_cons = sum(1 for r in sub_rows if r["status"] == "consensus")
     if n_cons:
         quoten_art["sub_dubletten_verdacht"] = round(len(sd) / n_cons, 3)
-        if llm:  # confirmed pairs only — the bare candidate list is suspicion, not damage
+        if llm:  # confirmed pairs only — the bare candidate list is suspicion, not damage;
-            quoten_art["sub_dubletten"] = round(sum(1 for p in sd if p.get("llm") == "ja") / n_cons, 3)
+            # freigesprochene (2:1 „behalten") zählen nicht mehr
+            quoten_art["sub_dubletten"] = round(
+                sum(1 for p in sd if p.get("llm") == "ja" and not p.get("freispruch")) / n_cons, 3)
     summary = _json_file(arbeit_dir(topic) / "lauf-summary.json") or {}
     report = {
         "topic": topic, "erstellt": datetime.now(timezone.utc).isoformat(),
@@ -377,6 +408,7 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
         },
         "quoten_artefakte": quoten_art,
         **({"unecht": unecht} if unecht is not None else {}),
+        **({"fremd_freigesprochen": fremd_frei} if fremd_frei else {}),
         "dubletten": d, "sub_dubletten": sd, "luecken": lk, "fremd": fr, "beleg": bl, "hygiene": hy,
         "artefakte": art,
         "lauf": summary,

backend/repair.py

@@ -38,8 +38,8 @@ async def repair_befunde(topic: str) -> dict:
 
     hygiene = await _fix_hygiene(topic, report, by_norm, files)
     merges = await _merge_dubletten(topic, report, by_norm, files)
-    sub_merges = await _merge_sub_dubletten(topic, report, files)
+    sub_merges, frei_subs = await _merge_sub_dubletten(topic, report, files)
-    entfernt = await _entferne_fremd_unecht(topic, report, by_norm, files)
+    entfernt, frei_bloecke = await _entferne_fremd_unecht(topic, report, by_norm, files)
     aufgeraeumt = await _raeume_waisen(topic)
 
     # llm=True: gleiche Messlatte wie QA-Button/Abschluss-QA — der llm=False-Report
@@ -48,7 +48,8 @@ async def repair_befunde(topic: str) -> dict:
     if neu:
         await qa.write_report(neu)
     return {"hygiene": hygiene, "merges": merges, "sub_merges": sub_merges, "entfernt": entfernt,
-            "aufgeraeumt": aufgeraeumt, "braucht_research": len(report.get("luecken", []))}
+            "aufgeraeumt": aufgeraeumt, "freigesprochen": frei_subs + frei_bloecke,
+            "braucht_research": len(report.get("luecken", []))}
 
 
 async def _judge(template: str, topic: str, key: str, slot: str, items: list[str]) -> dict[int, str]:
@@ -69,22 +70,42 @@ async def _judge(template: str, topic: str, key: str, slot: str, items: list[str
     return verdicts
 
 
+def _speichere_freispruch(topic: str, kategorie: str, keys: list[str]) -> None:
+    d = qa.lade_freispruch(topic)
+    alt = set(d.get(kategorie) or [])
+    d[kategorie] = sorted(alt | set(keys))
+    qa.freispruch_pfad(topic).parent.mkdir(parents=True, exist_ok=True)
+    atomic_write_json(qa.freispruch_pfad(topic), d, indent=1)
+
+
 async def _mit_stichentscheid(template: str, topic: str, key: str, slot: str,
-                              lines: list[str], befund: str) -> dict[int, str]:
+                              lines: list[str], befund: str, kategorie: str = "",
+                              ids: list[str] | None = None) -> tuple[dict[int, str], list[str]]:
     """Zweitmeinung + Stichentscheid: Der Repair-Judge kann den QA-Befund kippen — bei
     Dissens (QA sagt Befund, Judge sagt behalten) entscheidet ein DRITTER Judge nur über
     die strittigen Items, Mehrheit 2/3 (Muster Crossblock-Tiebreaker). Ohne ihn pendelte
     die Note dauerhaft unter 10 ohne Fix-Pfad (gemessen: aak-fremd 9.2, kanban-smoke-
-    Dublette 9.4 — „keine behebbaren Befunde" trotz Befund). j3 „behalten" oder Ausfall
+    Dublette 9.4 — „keine behebbaren Befunde" trotz Befund).
-    → Item bleibt (fail-open)."""
+    Explizites 2:1-„behalten" wird als FREISPRUCH persistiert (kategorie+ids) — die QA
+    zählt das Item ab dann nicht mehr (qa.lade_freispruch). j3-AUSFALL persistiert nicht
+    (fail-open ist kein Urteil). → (verdicts, freigesprochene Zeilen)."""
     v = await _judge(template, topic, key, slot, lines)
     strittig = [i for i in range(1, len(lines) + 1) if v.get(i) != befund]
+    frei: list[str] = []
     if strittig:
         v3 = await _judge(template, topic, f"{key}-st", slot, [lines[i - 1] for i in strittig])
+        gegen = "nein" if befund == "ja" else "ja"
+        frei_keys: list[str] = []
         for pos, i in enumerate(strittig, 1):
             if v3.get(pos) == befund:
                 v[i] = befund  # 2:1 für den QA-Befund → handeln
-    return v
+            elif v3.get(pos) == gegen and kategorie and ids:
+                frei_keys.append(ids[i - 1])
+                frei.append(lines[i - 1].splitlines()[0][:80])
+        if frei_keys:
+            _speichere_freispruch(topic, kategorie, frei_keys)
+            log.info("[%s] Repair %s: %d Befund(e) per 2:1 freigesprochen", topic, kategorie, len(frei_keys))
+    return v, frei
 
 
 async def _fix_hygiene(topic: str, report: dict, by_norm: dict, files: dict) -> list[str]:
@@ -116,8 +137,8 @@ async def _merge_dubletten(topic: str, report: dict, by_norm: dict, files: dict)
              and _norm_title(p.get("a", "")) in by_norm and _norm_title(p.get("b", "")) in by_norm]
     if not paare:
         return []
-    v = await _mit_stichentscheid("QA-Dubletten", topic, "dubletten", "pairs",
+    v, _frei = await _mit_stichentscheid("QA-Dubletten", topic, "dubletten", "pairs",
-                                  [f"A: {p['a']}\nB: {p['b']}" for p in paare], "ja")
+                                         [f"A: {p['a']}\nB: {p['b']}" for p in paare], "ja")
     merged = []
     for i, p in enumerate(paare, 1):
         a, b = by_norm.get(_norm_title(p["a"])), by_norm.get(_norm_title(p["b"]))
@@ -177,7 +198,7 @@ async def falte_sub(topic: str, files: dict, win: dict, lose: dict) -> None:
     _entferne_sub_in_files(files, lose["block_norm"], lose["sub_norm"])
 
 
-async def _merge_sub_dubletten(topic: str, report: dict, files: dict) -> list[str]:
+async def _merge_sub_dubletten(topic: str, report: dict, files: dict) -> tuple[list[str], list[str]]:
     """QA-bestätigte Sub-Paare (llm=ja) nach Zweitmeinung falten: Verlierer → variant,
     seine Fragen/Artefakte wandern zum Gewinner (oder fallen weg, wenn er den Typ hat).
     Repair hatte dafür keinen Handler — die Paare überlebten jeden Repair-Zyklus."""
@@ -192,10 +213,13 @@ async def _merge_sub_dubletten(topic: str, report: dict, files: dict) -> list[st
              and (a := _row(p.get("a"))) and (b := _row(p.get("b")))
              and (a["block_norm"], a["sub_norm"]) != (b["block_norm"], b["sub_norm"])]
     if not paare:
-        return []
+        return [], []
-    v = await _mit_stichentscheid("QA-Sub-Dubletten", topic, "sub-dubletten", "pairs",
+    v, frei = await _mit_stichentscheid(
-                                  [f"A: [{a['block']}] {a['sub_title']}\nB: [{b['block']}] {b['sub_title']}"
+        "QA-Sub-Dubletten", topic, "sub-dubletten", "pairs",
-                                   for a, b in paare], "ja")
+        [f"A: [{a['block']}] {a['sub_title']}\nB: [{b['block']}] {b['sub_title']}" for a, b in paare],
+        "ja", kategorie="sub_dubletten",
+        ids=[qa._paar_key(f"[{a['block']}] {a['sub_title']}", f"[{b['block']}] {b['sub_title']}")
+             for a, b in paare])
     merged: list[str] = []
     gone: set[tuple] = set()
     for i, (a, b) in enumerate(paare, 1):
@@ -206,7 +230,7 @@ async def _merge_sub_dubletten(topic: str, report: dict, files: dict) -> list[st
         await falte_sub(topic, files, win, lose)
         gone.add(lk)
         merged.append(f"{lose['sub_title'][:40]} → {win['sub_title'][:40]}")
-    return merged
+    return merged, frei
 
 
 def _entferne_sub_in_files(files: dict, bnorm: str, sub_norm: str) -> None:
@@ -237,8 +261,9 @@ def _entferne_sub_in_files(files: dict, bnorm: str, sub_norm: str) -> None:
             atomic_write_json(files["artefakte"], neu, indent=1)
 
 
-async def _entferne_fremd_unecht(topic: str, report: dict, by_norm: dict, files: dict) -> list[str]:
+async def _entferne_fremd_unecht(topic: str, report: dict, by_norm: dict, files: dict) -> tuple[list[str], list[str]]:
     out = []
+    frei_alle: list[str] = []
     fremd = [t for t in report.get("fremd", []) if _norm_title(t) in by_norm]
     if fremd:
         folder = source_folder(topic)
@@ -247,7 +272,10 @@ async def _entferne_fremd_unecht(topic: str, report: dict, by_norm: dict, files:
             srcs = by_norm[_norm_title(t)]["payload"].get("sources") or None
             ev = _evidence_pack(folder, srcs, [t], budget=EVIDENCE_PER_BLOCK) if folder else ""
             lines.append(f"{t}\n{ev or '(keine Treffer im Material)'}")
-        v = await _mit_stichentscheid("QA-Repair-Beleg", topic, "fremd", "blocks", lines, "nein")
+        v, frei = await _mit_stichentscheid("QA-Repair-Beleg", topic, "fremd", "blocks", lines,
+                                            "nein", kategorie="fremd",
+                                            ids=[_norm_title(t) for t in fremd])
+        frei_alle += frei
         for i, t in enumerate(fremd, 1):
             if v.get(i) == "nein":
                 await _reject(topic, t, by_norm, files, "qa-fremd")
@@ -256,12 +284,15 @@ async def _entferne_fremd_unecht(topic: str, report: dict, by_norm: dict, files:
     if unecht:
         lines = [f"{t} — {by_norm[_norm_title(t)]['payload'].get('description') or '(ohne Beschreibung)'}"
                  for t in unecht]
-        v = await _mit_stichentscheid("QA-Bausteine", topic, "unecht", "blocks", lines, "nein")
+        v, frei = await _mit_stichentscheid("QA-Bausteine", topic, "unecht", "blocks", lines,
+                                            "nein", kategorie="unecht",
+                                            ids=[_norm_title(t) for t in unecht])
+        frei_alle += frei
         for i, t in enumerate(unecht, 1):
             if v.get(i) == "nein":
                 await _reject(topic, t, by_norm, files, "qa-unecht")
                 out.append(t)
-    return out
+    return out, frei_alle
 
 
 async def _raeume_waisen(topic: str) -> int:

backend/tests/test_repair.py

@@ -230,6 +230,35 @@ async def test_sub_dubletten_stichentscheid_faltet(env, monkeypatch):
     assert rows["sub b"] == "variant" and rows["sub a"] == "consensus"
 
 
+async def test_stichentscheid_behalten_persistiert_freispruch(env, monkeypatch):
+    """2:1 „behalten" (Zweitmeinung + j3 einig gegen den QA-Befund) → Freispruch wird
+    persistiert und der Report des nächsten qa_report zählt das Paar nicht mehr —
+    vorher pendelte die Note dauerhaft unter 10 ohne Fix-Pfad."""
+    import qa as qa_mod
+    db, seed, files, write_report = env
+    await seed("Alpha", "beschr")
+    norm = repair._norm_title("Alpha")
+    await db.put_subblock(TOPIC, norm, "sub a", "Alpha", "Sub A", status="consensus")
+    await db.put_subblock(TOPIC, norm, "sub b", "Alpha", "Sub B", status="consensus")
+    write_report(_report(sub_dubletten=[{"a": "[Alpha] Sub A", "b": "[Alpha] Sub B", "llm": "ja"}]))
+
+    async def fake_agent(key, prompt, timeout, **kw):
+        return 0, '{"relevant": {"1": "nein"}}', ""  # beide Repair-Judges: behalten
+
+    monkeypatch.setattr(repair, "run_agent", fake_agent)
+    res = await repair.repair_befunde(TOPIC)
+    assert res["sub_merges"] == [] and len(res["freigesprochen"]) == 1
+    frei = qa_mod.lade_freispruch(TOPIC)
+    key = qa_mod._paar_key("[Alpha] Sub A", "[Alpha] Sub B")
+    assert key in set(frei.get("sub_dubletten") or [])
+    # QA-Seite: bestätigtes, aber freigesprochenes Paar zählt nicht in die Quote
+    sd = [{"a": "[Alpha] Sub A", "b": "[Alpha] Sub B", "llm": "ja"}]
+    frei_sub = set(frei["sub_dubletten"])
+    zaehlt = sum(1 for p in sd if p.get("llm") == "ja"
+                 and qa_mod._paar_key(p["a"], p["b"]) not in frei_sub)
+    assert zaehlt == 0
+
+
 async def test_fremd_stichentscheid_behalten(env, monkeypatch):
     """Dissens bei fremd, Stichentscheid sagt ebenfalls behalten (ja) → Block bleibt
     (fail-open bei 1:2 gegen den Befund)."""

frontend/src/components/GenerationView.vue

@@ -106,10 +106,10 @@ async function repairClick() {
   try {
     const r = await runRepair(props.topic)
     const n = (r.hygiene || []).length + (r.merges || []).length + (r.sub_merges || []).length
-      + (r.entfernt || []).length + (r.aufgeraeumt || 0)
+      + (r.entfernt || []).length + (r.aufgeraeumt || 0) + (r.freigesprochen || []).length
     repairInfo.value = n === 0
       ? 'keine behebbaren Befunde'
-      : `${(r.hygiene || []).length} Titel · ${(r.merges || []).length} Merges · ${(r.sub_merges || []).length} Sub-Merges · ${(r.entfernt || []).length} entfernt · ${r.aufgeraeumt || 0} aufgeräumt`
+      : `${(r.hygiene || []).length} Titel · ${(r.merges || []).length} Merges · ${(r.sub_merges || []).length} Sub-Merges · ${(r.entfernt || []).length} entfernt · ${r.aufgeraeumt || 0} aufgeräumt · ${(r.freigesprochen || []).length} freigesprochen`
   } catch (e) {
     repairInfo.value = String(e.message || e)
   } finally {