update

backend/block_calls.py

@@ -0,0 +1,686 @@
+"""Board 2, verschmolzene Call-Struktur: 3 Bausteine pro Block statt ~20 serieller Segmente.
+
+Die alte Stage-Treppe (Finder-Runden → Facts find/erg/check → Konsolidierung → Lücken →
+Nachfass → Levels → Relevanz → Fragen → Kritik → Flashcards → Beispiele → Check) kostete
+pro Block 35–55 Calls und ~14 min Wandzeit — bei p50 20–50 s pro Call zählt NUR die Zahl
+der seriellen Segmente. Hier: Generate(∥2) → Verify(∥2, + Fix-Tail) → Artefakte(Gen+Check)
+= 4–5 Segmente, 6–9 Calls. Unabhängigkeit bleibt: Generatoren und Prüfer sind getrennte
+Agenten, Konsens (≥2 unabhängige Nennungen) und Einstimmigkeits-Faltung wie zuvor.
+
+Output-Kontrakt unverändert (finalize/QA/Guide/Übungssystem lesen dieselben Strukturen):
+raw {block: [sub]}, facts {block: {sub_norm: 5-Felder}}, sidecar {block: [{title, level,
+relevance, facts}]}, pattern {block: [{subblock, question}]}, artefacts {flashcard/example}."""
+
+import asyncio
+import hashlib
+import json
+import logging
+
+import database as db
+import embedding
+from blocks import (
+    _SOURCE_TEMPLATE, _FACTS_FIELDS, _agreed_cliques, _cited_evidence, _dedup_subblocks,
+    _evidence_pack, _facts_lines, _facts_union, _luecken_schnitt, _neg_set, _pairs_of,
+    _sink_json, _sub_tokens, _subs_hash, _variant_clusters, load_source, material_folder,
+    source_folder,
+)
+from config import (ART_SPLIT_SUBS, EMBEDDING_AKTIV, GEN_PANEL, SEED_COVER_COS,
+                    VERIFY_PANEL)
+from jsonio import read_json_file as _json_file
+from pipeline import FAILED, GenContext, _extra, _log, _prompt, _race, _timeout, run_single_slot
+from textkit import _norm_title, clean_title
+
+log = logging.getLogger("creator.block_calls")
+
+_STUFEN = ("beginner", "advanced", "expert")
+_RELEVANZ = ("relevant", "peripheral")
+
+
+def _h8(*parts: str) -> str:
+    return hashlib.md5("|".join(parts).encode("utf-8")).hexdigest()[:8]
+
+
+# ── Schemas ─────────────────────────────────────────────────────────────────────────
+
+def _gen_schema(data) -> list[dict] | None:
+    """{"subs": [{title, level, relevance, …facts}]} → normalisierte Liste · sonst None.
+    Feld-Normalisierung wie _facts_schema; ungültiges level/relevance fällt auf ""
+    (die Stimme entfällt im Vote, der Sub bleibt)."""
+    if not isinstance(data, dict) or not isinstance(data.get("subs"), list):
+        return None
+    out = []
+    for e in data["subs"]:
+        if not isinstance(e, dict) or not str(e.get("title", "")).strip():
+            continue
+        bf = [{"text": t, "source": str(f.get("source", "")).strip()}
+              for f in (e.get("cited_facts") or []) if isinstance(f, dict) and (t := str(f.get("text", "")).strip())]
+        lv = str(e.get("level", "")).strip().casefold()
+        rv = str(e.get("relevance", "")).strip().casefold()
+        out.append({
+            "title": clean_title(str(e["title"]).strip()),
+            "level": lv if lv in _STUFEN else "",
+            "relevance": rv if rv in _RELEVANZ else "",
+            "key_points": [k for x in (e.get("key_points") or []) if (k := str(x).strip())],
+            "prerequisites": str(e.get("prerequisites", "")).strip(),
+            "hurdles": str(e.get("hurdles", "")).strip(),
+            "cited_facts": bf,
+            "example_idea": str(e.get("example_idea", "")).strip(),
+        })
+    return out or None
+
+
+def _vid(x, n: int) -> int | None:
+    """Prüfer-Nummer → int in 1..n, else None (bools sind keine ids)."""
+    if isinstance(x, bool):
+        return None
+    if isinstance(x, str) and x.isdigit():
+        x = int(x)
+    return x if isinstance(x, int) and 1 <= x <= n else None
+
+
+def _verify_schema(data, n: int) -> dict | None:
+    """Prüfer-Output → normalisiertes Verdikt · None wenn kaputt. Alle Felder optional
+    außer der Grundform (dict) — ein leeres Verdikt {"gruppen": []} heißt „alles ok"."""
+    if not isinstance(data, dict):
+        return None
+    pflicht = ("gruppen", "kataloge", "fremd", "luecken", "uebernehmen", "facts_probleme",
+               "levels", "relevanz")
+    if not any(k in data for k in pflicht):
+        return None
+
+    def _ids(lst):
+        return sorted({i for x in (lst or []) if (i := _vid(x, n)) is not None})
+
+    gruppen = []
+    for g in data.get("gruppen") or []:
+        if not isinstance(g, dict):
+            continue
+        haupt = _vid(g.get("haupt"), n)
+        ids = _ids(([haupt] if haupt else []) + list(g.get("weitere") or []))
+        if len(ids) >= 2:
+            gruppen.append({"haupt": haupt if haupt in ids else None, "ids": ids})
+    kataloge = []
+    for k in data.get("kataloge") or []:
+        if not isinstance(k, dict):
+            continue
+        ids = _ids(k.get("mitglieder"))
+        titel = str(k.get("titel") or "").strip()
+        if len(ids) >= 2 and titel:
+            kataloge.append({"titel": titel, "ids": ids})
+    uebernehmen = {}
+    for k, v in (data.get("uebernehmen") or {}).items() if isinstance(data.get("uebernehmen"), dict) else []:
+        if (i := _vid(k, n)) is not None:
+            uebernehmen[i] = str(v).strip().casefold()
+    probleme = []
+    for p in data.get("facts_probleme") or []:
+        if isinstance(p, dict) and (i := _vid(p.get("nr"), n)) is not None:
+            probleme.append({"nr": i, "discard": bool(p.get("discard")),
+                             "hinweis": str(p.get("hinweis", "")).strip()})
+    def _enum_map(key, allowed):
+        out = {}
+        raw = data.get(key)
+        for k, v in (raw.items() if isinstance(raw, dict) else []):
+            if (i := _vid(k, n)) is not None and str(v).strip().casefold() in allowed:
+                out[i] = str(v).strip().casefold()
+        return out
+    return {"gruppen": gruppen, "kataloge": kataloge, "fremd": set(_ids(data.get("fremd"))),
+            "luecken": [s.strip() for s in data.get("luecken") or [] if isinstance(s, str) and s.strip()],
+            "uebernehmen": uebernehmen, "facts_probleme": probleme,
+            "levels": _enum_map("levels", _STUFEN), "relevanz": _enum_map("relevanz", _RELEVANZ)}
+
+
+def _pattern_liste(lst) -> list[dict]:
+    out = []
+    for e in lst or []:
+        if isinstance(e, dict):
+            blk, sub, q = (str(e.get(k, "")).strip() for k in ("block", "subblock", "question"))
+            if blk and sub and q:
+                out.append({"block": blk, "subblock": sub, "question": q})
+    return out
+
+
+def _art_gen_schema(data) -> dict | None:
+    """{"pattern": […], "cards": […], "examples": […]} → normalisiert · None wenn kaputt.
+    pattern ist Pflicht (Leitner hängt an Fragen), cards/examples best-effort."""
+    if not isinstance(data, dict):
+        return None
+    pattern = _pattern_liste(data.get("pattern"))
+    if not pattern:
+        return None
+    cards = []
+    for e in data.get("cards") or []:
+        if isinstance(e, dict):
+            blk, sub, q, a = (str(e.get(k, "")).strip() for k in ("block", "subblock", "question", "answer"))
+            if blk and sub and q and a:
+                cards.append({"block": blk, "subblock": sub, "question": q, "answer": a})
+    examples = []
+    for e in data.get("examples") or []:
+        if isinstance(e, dict):
+            blk, sub, pr, res = (str(e.get(k, "")).strip() for k in ("block", "subblock", "problem", "result"))
+            steps = [s for x in (e.get("steps") or []) if (s := str(x).strip())]
+            if blk and sub and pr and steps:
+                examples.append({"block": blk, "subblock": sub, "problem": pr, "steps": steps, "result": res})
+    return {"pattern": pattern, "cards": cards, "examples": examples}
+
+
+def _art_check_schema(data) -> dict | None:
+    """{"ok": true} → leeres Verdikt · sonst pattern (bereinigt) + pattern_ergaenzt +
+    examples_probleme (1-basierte Indizes)."""
+    if not isinstance(data, dict):
+        return None
+    if data.get("ok") is True:
+        return {"pattern": [], "pattern_ergaenzt": [], "examples_probleme": set()}
+    if not any(k in data for k in ("pattern", "pattern_ergaenzt", "examples_probleme")):
+        return None
+    probleme = set()
+    for p in data.get("examples_probleme") or []:
+        i = p.get("index") if isinstance(p, dict) else p
+        if isinstance(i, str) and i.isdigit():
+            i = int(i)
+        if isinstance(i, int) and not isinstance(i, bool) and i >= 1:
+            probleme.add(i)
+    return {"pattern": _pattern_liste(data.get("pattern")),
+            "pattern_ergaenzt": _pattern_liste(data.get("pattern_ergaenzt")),
+            "examples_probleme": probleme}
+
+
+# ── Gemeinsames ─────────────────────────────────────────────────────────────────────
+
+def _inline_source(topic: str, sources: list[str] | None, queries: list[str]) -> tuple[str, str]:
+    """→ (source-Slot, capabilities). Korpus-Auszüge inline (uni/projekt/link oder
+    thema-Research-Material); ohne Treffer fail-open auf die alte Selbst-Recherche."""
+    mat = material_folder(topic)
+    ev = _evidence_pack(mat, sources, queries) if mat else ""
+    if ev:
+        return _prompt("Blocks-Source-Inline", excerpts=ev), "none"
+    _type = load_source(topic).get("type", "thema")
+    folder = source_folder(topic)
+    if _type in _SOURCE_TEMPLATE:
+        return _prompt(_SOURCE_TEMPLATE[_type], project=folder), ("files" if folder else "full")
+    return _prompt("Blocks-Source-Thema", topic=topic), "full"
+
+
+async def _sims_of(titles: list[str]):
+    """Ähnlichkeitsmatrix fürs Variant-Clustering; ohne Modell exakte Norm-Gleichheit."""
+    if EMBEDDING_AKTIV and await asyncio.to_thread(embedding.available):
+        sims = await asyncio.to_thread(embedding.embed_sims, titles)
+        if sims is not None:
+            return sims
+    norms = [_norm_title(t) for t in titles]
+    return [[1.0 if norms[i] == norms[j] else 0.0 for j in range(len(titles))]
+            for i in range(len(titles))]
+
+
+def _fk_of(e: dict) -> dict:
+    return {k: e.get(k) for k in _FACTS_FIELDS}
+
+
+# ── Generate ────────────────────────────────────────────────────────────────────────
+
+async def _generate_block(ctx: GenContext, files: dict, title: str, description: str,
+                          instructions: str = "", ns: str = "", lbl: str = "",
+                          sources: list[str] | None = None,
+                          seeds: list[str] | None = None) -> dict | None:
+    """GEN_PANEL unabhängige Generatoren liefern je Subs+Facts+Level/Relevanz in EINEM Call;
+    Konsens im Code (Variant-Cluster über beide Ausgaben, ≥2 unabhängige Generatoren =
+    consensus). Einzelnennungen und ungedeckte Seeds werden „unsicher" — der Prüfer
+    entscheidet mit Material (ersetzt Sättigungsrunden + Clarify-Panel). Degraded: liefert
+    nur EIN Generator, wird alles unsicher. → {raw, facts, unsicher, votes} | None."""
+    topic, provider = ctx.topic, ctx.provider
+    work_dir = files["arbeit"]
+    bnorm = _norm_title(title)
+    source, caps = await asyncio.to_thread(
+        _inline_source, topic, sources, [f"{title} {description}"])
+    seeds_txt = ""
+    if seeds:
+        seeds_txt = ("\nAlready identified sub-point CANDIDATES of this block (verify against "
+                     "the material; if backed AND not already covered by another entry, include "
+                     "them — rephrased as a standalone statement):\n"
+                     + "\n".join(f"- {s}" for s in dict.fromkeys(seeds) if s) + "\n")
+    h = _h8(title, description, "gen")
+    paths = [work_dir / f"gen-{h}-g{g}.json" for g in range(1, GEN_PANEL + 1)]
+    prompt = _prompt("Subblock-Generate", topic=topic,
+                     block=f"{title} — {description}" if description else title,
+                     source=source, seeds=seeds_txt, extra=_extra(instructions))
+    pending = [(g, p) for g, p in enumerate(paths, 1) if _gen_schema(_json_file(p)) is None]
+    if pending:
+        slots = [{
+            "key": f"blocks-{topic}-{ns}sb-gen-{h}-g{g}",
+            "prompt": prompt, "role": "quick", "capabilities": caps,
+            "payload": (lambda result, p=p: _sink_json(result, p, _gen_schema)),
+        } for g, p in pending]
+        await _race(topic, f"{lbl}Generate", slots, len(slots),
+                    _timeout("generate", 10), provider, cancelled=ctx.is_cancelled)
+    if ctx.is_cancelled():
+        return None
+    outs = [o for p in paths if (o := _gen_schema(_json_file(p))) is not None]
+    if not outs:
+        return None
+    if len(outs) < len(paths):
+        _log(topic, f"Generate {title}: nur {len(outs)}/{len(paths)} Generatoren — alles unsicher, Prüfer entscheidet")
+
+    # Mentions in die DB (QA-Beleg-Signal), Karten-Re-Spawn darf nicht kumulieren
+    await db.delete_subblocks(topic, bnorm)
+    alle: list[tuple[dict, int]] = []  # (sub-Eintrag, Generator-Index)
+    for gi, subs in enumerate(outs):
+        seen: set[str] = set()
+        for e in subs:
+            sn = _norm_title(e["title"])
+            if not sn or sn in seen:
+                continue
+            seen.add(sn)
+            alle.append((e, gi))
+            await db.upsert_subblock(topic, bnorm, sn, title, e["title"])
+    if not alle:
+        return {"raw": {title: []}, "facts": {title: {}}, "unsicher": [], "votes": {}}
+
+    sims = await _sims_of([e["title"] for e, _ in alle])
+    raw: list[str] = []
+    facts: dict[str, dict] = {}
+    votes: dict[str, dict] = {}
+    unsicher: list[dict] = []
+    for c in _variant_clusters([e["title"] for e, _ in alle], [1] * len(alle), sims):
+        rep = alle[c["rep"]][0]
+        sn = _norm_title(rep["title"])
+        fk = _fk_of(rep)
+        for m in c["members"]:
+            if m != c["rep"]:
+                _facts_union(fk, _fk_of(alle[m][0]))
+                await db.set_subblock_fields(topic, bnorm, _norm_title(alle[m][0]["title"]),
+                                             status="variant")
+        votes[sn] = {"level": [v for m in c["members"] if (v := alle[m][0]["level"])],
+                     "relevance": [v for m in c["members"] if (v := alle[m][0]["relevance"])]}
+        gens = {alle[m][1] for m in c["members"]}
+        # degraded (1 Generator): kein Konsens möglich — alles unsicher, Prüfer entscheidet
+        if len(gens) >= 2 and len(outs) >= 2:
+            raw.append(rep["title"])
+            facts[sn] = fk
+            await db.set_subblock_fields(topic, bnorm, sn, status="consensus")
+        else:
+            unsicher.append({**rep, **fk})
+
+    # Seed-Garantie: ungedeckte Seeds gehen als unsicher zum Prüfer (der ist das Beleg-Gate)
+    for seed in dict.fromkeys(s for s in (seeds or []) if s):
+        st = _sub_tokens(seed)
+        gedeckt = [t for t in raw + [u["title"] for u in unsicher]]
+        if not st or any(st <= _sub_tokens(t) for t in gedeckt):
+            continue
+        if gedeckt and EMBEDDING_AKTIV and await asyncio.to_thread(embedding.available):
+            sims = await asyncio.to_thread(embedding.embed_sims, [seed] + gedeckt)
+            if sims is not None and max(float(sims[0][j]) for j in range(1, len(gedeckt) + 1)) >= SEED_COVER_COS:
+                continue
+        unsicher.append({"title": seed, "level": "", "relevance": "", "key_points": [],
+                         "prerequisites": "", "hurdles": "", "cited_facts": [], "example_idea": ""})
+
+    raw_map = {title: raw}
+    await _dedup_subblocks(topic, raw_map)  # deterministischer Near-Dup-Filter
+    facts = {sn: fk for sn, fk in facts.items()
+             if sn in {_norm_title(s) for s in raw_map[title]}}
+    return {"raw": raw_map, "facts": {title: facts}, "unsicher": unsicher, "votes": votes}
+
+
+# ── Verify (+ Fix-Tail) ─────────────────────────────────────────────────────────────
+
+def _default_vote(stimmen: list[str], default: str) -> str:
+    """Mehrheit über die Stimmen (Gen-Vorschläge + implizite/explizite Prüfer-Stimmen);
+    Patt oder leer → default."""
+    counter: dict[str, int] = {}
+    for s in stimmen:
+        if s:
+            counter[s] = counter.get(s, 0) + 1
+    best = max(counter.values(), default=0)
+    winners = [s for s, v in counter.items() if v == best]
+    return winners[0] if len(winners) == 1 and best else default
+
+
+async def _verify_block(ctx: GenContext, files: dict, title: str, gen: dict, q: dict,
+                        instructions: str = "", ns: str = "", lbl: str = "",
+                        sources: list[str] | None = None) -> dict | None:
+    """VERIFY_PANEL unabhängige Prüfer auditieren den Block in EINEM Call (MECE-Faltung,
+    Fremd, Lücken, Unsicher-Übernahme, Facts-Korrektheit, Level/Relevanz). Auswertung mit
+    Schnittmengen-Semantik pro Befundklasse (Faltung/Fremd/Übernahme einstimmig, Discard
+    2/2, Korrektur ≥1 Stimme); Fix-Tail ist EIN Call für Korrekturen + belegte Lücken.
+    → {raw, facts, sidecar} | None (nur bei Cancel)."""
+    topic = ctx.topic
+    work_dir = files["arbeit"]
+    bnorm = _norm_title(title)
+    subs = list(gen["raw"].get(title) or [])
+    bfacts: dict[str, dict] = dict(gen["facts"].get(title) or {})
+    unsicher: list[dict] = list(gen.get("unsicher") or [])
+    votes: dict[str, dict] = gen.get("votes") or {}
+    nummern = subs + [u["title"] for u in unsicher]  # 1-basiert: consensus, dann unsicher
+    n = len(nummern)
+
+    def _kp(t: str) -> list:
+        fk = bfacts.get(_norm_title(t)) or next(
+            (u for u in unsicher if u["title"] == t), {})
+        return (fk.get("key_points") or [])[:3]
+
+    verdicts: list[dict] = []
+    if n:
+        zeilen = "\n".join(f"{k}. {t}" + "".join(f"\n   - {p}" for p in _kp(t))
+                           for k, t in enumerate(nummern, 1))
+        u_txt = ""
+        if unsicher:
+            erste = len(subs) + 1
+            u_txt = (f"\nUNSICHER — entries {erste}–{n} were named by only ONE generator "
+                     "(or are seed candidates). Judge their adoption under `uebernehmen`.\n")
+        cites = [bf.get("source", "") for fk in bfacts.values() for bf in fk.get("cited_facts", [])]
+        mat = material_folder(topic)
+        ev = _cited_evidence(mat, sources, cites, [title] + nummern) if mat else ""
+        if ev:
+            source = _prompt("Blocks-Source-Inline", excerpts=ev)
+        else:
+            source, _caps = await asyncio.to_thread(_inline_source, topic, sources, [title] + nummern)
+        sh = _subs_hash({title: nummern})
+        pfade = {j: work_dir / f"verify-{sh}-j{j}.json" for j in (*range(1, VERIFY_PANEL + 1), "E")}
+
+        async def _judge(j):
+            if _verify_schema(_json_file(pfade[j]), n) is not None:
+                return  # resume
+            status, _v = await run_single_slot(
+                ctx, f"{lbl}Verify j{j}", key=f"blocks-{topic}-{ns}sb-verify-{sh}-j{j}",
+                prompt=_prompt("Subblock-Verify", topic=topic, block=title, subs=zeilen,
+                               unsicher=u_txt, source=source, extra=_extra(instructions)),
+                role="judge", capabilities="none",
+                payload=lambda result, p=pfade[j]: _sink_json(result, p, lambda d: _verify_schema(d, n)),
+                timeout=_timeout("verify", n))
+            if status == FAILED:
+                _log(topic, f"Verify {title} j{j} ohne Ergebnis — fail-open")
+
+        await asyncio.gather(*[_judge(j) for j in range(1, VERIFY_PANEL + 1)])
+        if ctx.is_cancelled():
+            return None
+        verdicts = [v for j in range(1, VERIFY_PANEL + 1)
+                    if (v := _verify_schema(_json_file(pfade[j]), n)) is not None]
+        if len(verdicts) == 1 and VERIFY_PANEL >= 2:  # Ersatz-Richter statt fail-open
+            await _judge("E")
+            if ctx.is_cancelled():
+                return None
+            verdicts = [v for j in (*range(1, VERIFY_PANEL + 1), "E")
+                        if (v := _verify_schema(_json_file(pfade[j]), n)) is not None][:2]
+
+    einstimmig = len(verdicts) >= 2
+    if n and not einstimmig:
+        _log(topic, f"Verify {title}: nur {len(verdicts)}/2 Prüfer — fail-open, unsicher verworfen")
+    negs = [_neg_set(t) for t in nummern]
+    gone: set[int] = set()
+    keep = list(subs)
+    korrekturen: list[dict] = []   # {titel, hinweis}
+    luecken: list[str] = []
+
+    def _titel(k: int) -> str:
+        return nummern[k - 1]
+
+    async def _fold(k: int, wf: dict | None):
+        t = _titel(k)
+        lf = bfacts.pop(_norm_title(t), None) or {}
+        if wf is not None:
+            _facts_union(wf, lf)
+        await db.set_subblock_fields(topic, bnorm, _norm_title(t), status="variant")
+        if t in keep:
+            keep.remove(t)
+        gone.add(k)
+
+    if einstimmig:
+        v1, v2 = verdicts[0], verdicts[1]
+        # 1. Fremd (einstimmig): fürs THEMA fremde Aussagen → discarded
+        for k in sorted(v1["fremd"] & v2["fremd"]):
+            t = _titel(k)
+            bfacts.pop(_norm_title(t), None)
+            await db.set_subblock_fields(topic, bnorm, _norm_title(t), status="discarded")
+            if t in keep:
+                keep.remove(t)
+            gone.add(k)
+        # 2. Unsicher-Übernahme (2/2 „ja"): wird consensus samt Generator-Facts
+        for k in range(len(subs) + 1, n + 1):
+            if k in gone:
+                continue
+            u = unsicher[k - len(subs) - 1]
+            if v1["uebernehmen"].get(k) == "ja" and v2["uebernehmen"].get(k) == "ja":
+                sn = _norm_title(u["title"])
+                bfacts[sn] = _fk_of(u)
+                keep.append(u["title"])
+                await db.set_subblock_fields(topic, bnorm, sn, status="consensus")
+            else:
+                await db.set_subblock_fields(topic, bnorm, _norm_title(u["title"]), status="discarded")
+                gone.add(k)
+        # 3. Gruppen (einstimmige Paare): haupt-Votum, sonst key_points/Länge
+        haupt_votes: dict[int, int] = {}
+        for v in (v1, v2):
+            for g in v["gruppen"]:
+                if g["haupt"]:
+                    haupt_votes[g["haupt"]] = haupt_votes.get(g["haupt"], 0) + 1
+        for g in _agreed_cliques([_pairs_of([x["ids"] for x in v["gruppen"]]) for v in (v1, v2)], negs, n):
+            g = [k for k in g if k not in gone]
+            if len(g) < 2:
+                continue
+            win = max(g, key=lambda k: (haupt_votes.get(k, 0), len(_kp(_titel(k))), len(_titel(k)), -k))
+            wf = bfacts.setdefault(_norm_title(_titel(win)), {})
+            for k in g:
+                if k != win:
+                    await _fold(k, wf)
+        # 4. Kataloge: Aufzählungszeilen → EIN neuer benannter Sub (Facts-Union)
+        for g in _agreed_cliques([_pairs_of([x["ids"] for x in v["kataloge"]]) for v in (v1, v2)], negs, n):
+            g = [k for k in g if k not in gone]
+            if len(g) < 2:
+                continue
+            titel = next((clean_title(x["titel"]) for x in v1["kataloge"] + v2["kataloge"]
+                          if set(x["ids"]) & set(g) and clean_title(x["titel"])), "")
+            kn = _norm_title(titel)
+            if not kn or kn in {_norm_title(s) for s in keep}:
+                continue
+            kf: dict = {}
+            for k in g:
+                await _fold(k, kf)
+            bfacts[kn] = kf
+            keep.append(titel)
+            await db.put_subblock(topic, bnorm, kn, title, titel, status="consensus")
+        # 5. Facts-Probleme: discard nur 2/2 (irreversibel), Korrektur ab 1 Stimme
+        d1 = {p["nr"] for p in v1["facts_probleme"] if p["discard"]}
+        d2 = {p["nr"] for p in v2["facts_probleme"] if p["discard"]}
+        for k in sorted(d1 & d2):
+            if k in gone:
+                continue
+            t = _titel(k)
+            bfacts.pop(_norm_title(t), None)
+            await db.set_subblock_fields(topic, bnorm, _norm_title(t), status="discarded")
+            if t in keep:
+                keep.remove(t)
+            gone.add(k)
+        for p in v1["facts_probleme"] + v2["facts_probleme"]:
+            k = p["nr"]
+            if k in gone or not p["hinweis"]:
+                continue
+            t = _titel(k)
+            if t in keep and all(x["titel"] != t for x in korrekturen):
+                korrekturen.append({"titel": t, "hinweis": p["hinweis"]})
+        # 6. Lücken (Schnitt beider Prüfer, Cap)
+        luecken = _luecken_schnitt(v1["luecken"], v2["luecken"])
+    else:
+        # fail-open: consensus bleibt, unsicher wird verworfen (wie heutiges Clarify-Aus)
+        for u in unsicher:
+            await db.set_subblock_fields(topic, bnorm, _norm_title(u["title"]), status="discarded")
+
+    # 7. Level/Relevanz: Stimmen = Generatoren + Prüfer (explizite Korrektur schlägt
+    #    die implizite Zustimmung); Patt → advanced/relevant (heutige Defaults)
+    sidecar_subs = []
+    for t in keep:
+        sn = _norm_title(t)
+        try:
+            k = nummern.index(t) + 1
+        except ValueError:
+            k = 0  # Katalog-/Fix-Neuzugänge haben keine Nummer
+        stimmen_l = list((votes.get(sn) or {}).get("level") or [])
+        stimmen_r = list((votes.get(sn) or {}).get("relevance") or [])
+        for v in verdicts[:2]:
+            if k and k in v["levels"]:
+                stimmen_l += [v["levels"][k]] * 2  # explizite Korrektur wiegt doppelt
+            if k and k in v["relevanz"]:
+                stimmen_r += [v["relevanz"][k]] * 2
+        fk = bfacts.get(sn) or {}
+        sidecar_subs.append({"title": t, "level": _default_vote(stimmen_l, "advanced"),
+                             "relevance": _default_vote(stimmen_r, "relevant"), "facts": fk})
+
+    # 8. Fix-Tail (0–1 Call): Korrekturen + belegte Lücken
+    if (korrekturen or luecken) and not ctx.is_cancelled():
+        neu = await _fix_befunde(ctx, files, title, korrekturen, luecken,
+                                 [s["title"] for s in sidecar_subs], instructions, ns, lbl, sources)
+        for e in neu or []:
+            sn = _norm_title(e["title"])
+            vorhanden = next((s for s in sidecar_subs if _norm_title(s["title"]) == sn), None)
+            if vorhanden is not None:  # Korrektur: Facts ersetzen, Einstufung bleibt
+                vorhanden["facts"] = _fk_of(e)
+                bfacts[sn] = vorhanden["facts"]
+            else:  # Lücken-Fund: neuer consensus-Sub
+                bfacts[sn] = _fk_of(e)
+                keep.append(e["title"])
+                sidecar_subs.append({"title": e["title"],
+                                     "level": e["level"] or "advanced",
+                                     "relevance": e["relevance"] or "relevant",
+                                     "facts": bfacts[sn]})
+                await db.put_subblock(topic, bnorm, sn, title, e["title"], status="consensus")
+
+    if len(keep) != len(subs):
+        _log(topic, f"Verify {title}: {len(subs)} consensus + {len(unsicher)} unsicher → {len(keep)}")
+    return {"raw": {title: [s["title"] for s in sidecar_subs]},
+            "facts": {title: bfacts},
+            "sidecar": {title: sidecar_subs}}
+
+
+async def _fix_befunde(ctx: GenContext, files: dict, title: str, korrekturen: list[dict],
+                       luecken: list[str], vorhanden: list[str], instructions: str,
+                       ns: str, lbl: str, sources: list[str] | None) -> list[dict]:
+    """EIN Call korrigiert beanstandete Facts und füllt gemeldete Lücken. Hartes Beleg-Gate
+    für Neuzugänge (key_points/cited_facts nicht leer) + Dedup gegen den Bestand — ein
+    unbelegter Lücken-„Fund" flutet sonst das Fakten-Gate des Guides."""
+    topic = ctx.topic
+    work_dir = files["arbeit"]
+    auftraege = [f"- KORRIGIEREN: „{k['titel']}“ — {k['hinweis']}" for k in korrekturen]
+    auftraege += [f"- LÜCKE (neuer Subbaustein, nur wenn belegbar): {l}" for l in luecken]
+    source, caps = await asyncio.to_thread(
+        _inline_source, topic, sources,
+        [title] + [k["titel"] for k in korrekturen] + list(luecken))
+    sh = _h8(title, *sorted(a for a in auftraege))
+    pfad = work_dir / f"fix-{sh}.json"
+    if _gen_schema(_json_file(pfad)) is None:
+        status, _v = await run_single_slot(
+            ctx, f"{lbl}Fix", key=f"blocks-{topic}-{ns}sb-fix-{sh}",
+            prompt=_prompt("Subblock-Fix", topic=topic, block=title, source=source,
+                           auftraege="\n".join(auftraege), extra=_extra(instructions)),
+            role="quick", capabilities=caps,
+            payload=lambda result, p=pfad: _sink_json(result, p, _gen_schema),
+            timeout=_timeout("fix", len(auftraege)))
+        if status == FAILED:
+            _log(topic, f"Fix {title} ohne Ergebnis — Befunde bleiben offen")
+            return []
+    out = _gen_schema(_json_file(pfad)) or []
+    korrektur_norms = {_norm_title(k["titel"]) for k in korrekturen}
+    have_norms = {_norm_title(t) for t in vorhanden}
+    angenommen = []
+    for e in out:
+        sn = _norm_title(e["title"])
+        if sn in korrektur_norms:
+            angenommen.append(e)
+            continue
+        if sn in have_norms or not (e["key_points"] or e["cited_facts"]):
+            continue  # unbelegt oder Dublette → verfällt
+        st = _sub_tokens(e["title"])
+        if any(st <= _sub_tokens(t) or _sub_tokens(t) <= st for t in vorhanden):
+            continue
+        angenommen.append(e)
+        have_norms.add(sn)
+    return angenommen
+
+
+# ── Artefakte ───────────────────────────────────────────────────────────────────────
+
+def _subs_text(title: str, sidecar_subs: list[dict]) -> str:
+    return f"BLOCK: {title}\n" + "\n".join(
+        f"- {s['title']}\n" + "\n".join(f"  {z}" for z in _facts_lines(s.get("facts") or {}).splitlines())
+        for s in sidecar_subs)
+
+
+async def _artefakte_block(ctx: GenContext, files: dict, title: str,
+                           sidecar_subs: list[dict], instructions: str = "",
+                           ns: str = "", lbl: str = "") -> dict | None:
+    """EIN Generator-Call liefert Fragen + Flashcards + Beispiele (Split in 2 parallele
+    Calls bei > ART_SPLIT_SUBS Subs), EIN Prüfer-Call verifiziert Beispiele, bereinigt
+    die Fragen und ergänzt fehlende. → {pattern, artefacts} | None (nur Cancel)."""
+    topic = ctx.topic
+    work_dir = files["arbeit"]
+    if not sidecar_subs:
+        return {"pattern": {title: []}, "artefacts": {"flashcard": [], "example": []}}
+    sh = _subs_hash({title: sidecar_subs})
+    haelften = ([sidecar_subs] if len(sidecar_subs) <= ART_SPLIT_SUBS
+                else [sidecar_subs[:len(sidecar_subs) // 2], sidecar_subs[len(sidecar_subs) // 2:]])
+
+    async def _gen(gi: int, teil: list[dict]):
+        pfad = work_dir / f"art-{sh}-t{gi}.json"
+        if _art_gen_schema(_json_file(pfad)) is not None:
+            return
+        status, _v = await run_single_slot(
+            ctx, f"{lbl}Artefakte {gi}", key=f"blocks-{topic}-{ns}art-gen-{sh}-t{gi}",
+            prompt=_prompt("Artefakt-Generate", topic=topic, blocks=_subs_text(title, teil),
+                           extra=_extra(instructions)),
+            role="quick", capabilities="none",
+            payload=lambda result, p=pfad: _sink_json(result, p, _art_gen_schema),
+            timeout=_timeout("artefakt", len(teil)))
+        if status == FAILED:
+            _log(topic, f"Artefakte {title} Teil {gi} ohne Ergebnis")
+
+    await asyncio.gather(*[_gen(gi, teil) for gi, teil in enumerate(haelften, 1)])
+    if ctx.is_cancelled():
+        return None
+    pattern: list[dict] = []
+    cards: list[dict] = []
+    examples: list[dict] = []
+    for gi in range(1, len(haelften) + 1):
+        o = _art_gen_schema(_json_file(work_dir / f"art-{sh}-t{gi}.json"))
+        if o:
+            pattern += o["pattern"]
+            cards += o["cards"]
+            examples += o["examples"]
+
+    # Prüfer: Beispiele verifizieren, Fragen bereinigen + fehlende ergänzen
+    sub_titles = [s["title"] for s in sidecar_subs]
+    fehlend = [t for t in sub_titles
+               if _norm_title(t) not in {_norm_title(p["subblock"]) for p in pattern}]
+    if pattern or examples:
+        tabelle = "\n".join(f"({p['subblock']}) {p['question']}" for p in pattern) or "(keine)"
+        beisp = "\n\n".join(
+            f"{k}. PROBLEM: {e['problem']}\n   SCHRITTE: " + " | ".join(e["steps"])
+            + (f"\n   ERGEBNIS: {e['result']}" if e.get("result") else "")
+            for k, e in enumerate(examples, 1)) or "(keine)"
+        fehlend_txt = ("\nSUBBLOCKS STILL MISSING A QUESTION:\n"
+                       + "\n".join(f"- {t}" for t in fehlend) + "\n") if fehlend else "\n"
+        pfad = work_dir / f"artcheck-{sh}.json"
+        if _art_check_schema(_json_file(pfad)) is None:
+            status, _v = await run_single_slot(
+                ctx, f"{lbl}Artefakt-Check", key=f"blocks-{topic}-{ns}art-check-{sh}",
+                prompt=_prompt("Artefakt-Check", topic=topic, facts=_subs_text(title, sidecar_subs),
+                               table=tabelle, fehlend=fehlend_txt, examples=beisp,
+                               extra=_extra(instructions)),
+                role="judge", capabilities="none",
+                payload=lambda result, p=pfad: _sink_json(result, p, _art_check_schema),
+                timeout=_timeout("artefakt_check", len(sidecar_subs)))
+            if status == FAILED:
+                _log(topic, f"Artefakt-Check {title} ohne Ergebnis — Rohfassung übernommen")
+        check = _art_check_schema(_json_file(pfad))
+        if check:
+            if check["examples_probleme"]:
+                examples = [e for k, e in enumerate(examples, 1)
+                            if k not in check["examples_probleme"]]
+                _log(topic, f"Artefakt-Check {title}: {len(check['examples_probleme'])} Beispiel(e) verworfen")
+            if check["pattern"]:  # bereinigte Fassung ersetzt die Rohfassung
+                pattern = check["pattern"]
+            pattern += check["pattern_ergaenzt"]
+
+    pattern_map = {title: [{"subblock": p["subblock"], "question": p["question"]}
+                           for p in pattern]}
+    # block-Feld auf den Karten-Block normieren (Ein-Block-Call — Agent-Echos abfangen)
+    for e in cards + examples:
+        e["block"] = title
+    return {"pattern": pattern_map,
+            "artefacts": {"flashcard": [{k: e[k] for k in ("block", "subblock", "question", "answer")} for e in cards],
+                          "example": [{k: e[k] for k in ("block", "subblock", "problem", "steps", "result")} for e in examples]}}