feat(2.0): Phase 1 — Engine + Routing (Herzstueck)

Backend-Services: fit/caps/sources (portiert), discover (live HF + Fit +
Caps + ranked recommendation), llama-swap write/register + groups (Ko-
Residenz swap:false), LiteLLM-Gateway-Config + gateway-Service (model:auto +
Fallbacks). Router: discover/fit/register/groups/routing; health zeigt
gateway_reachable. Frontend: Modelle&Routing mit Caps-Chips, Fit-Badges,
Discover-Tab (live), Routing-View.

Lokal verifiziert: Backend-Smoke (alle Endpunkte) + Frontend-Build +
Browser (Shell, Discover, Caps/Fit). Box-Verifikation offen.

Docs: README + docs/STATUS.md (Phasen-Tracker + Resume-Guide).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/services/discover.py

@@ -0,0 +1,133 @@
+"""
+Automatische Modell-Entdeckung ("aktuell beste Modelle"): fragt vertrauenswürdige
+HF-Orgs live ab, kategorisiert per Stichwort, rankt nach Hardware-Fit + Beliebtheit
+und cached. Portiert aus Mission Control v1 (cookbook.py-Discover).
+
+Wichtig (Greenfield-Fix gegen v1): EIN gemeinsamer Ranking-Helfer `rank_runnable`
+ist die Quelle der Wahrheit — sowohl die „beste Empfehlung" je Kategorie als auch
+spätere Auto-Setups nutzen ihn, damit sie nie auseinanderlaufen.
+"""
+
+import json
+import os
+import time
+
+import httpx
+
+from config import DISCOVER_CACHE_PATH, DISCOVER_TTL
+from services.caps import capabilities
+from services.fit import evaluate_fit, extract_params_b, max_ctx_for
+from services.sources import CATEGORIES, SKIP_TOKENS, TRUSTED_AUTHORS
+
+_FIT_ORDER = {"perfect": 0, "marginal": 1, "too_tight": 2}
+
+
+def _categorize(repo_id: str) -> str:
+    low = repo_id.lower()
+    for cat in CATEGORIES:
+        if any(k in low for k in cat["kw"]):
+            return cat["role"]
+    return "scout"
+
+
+def _fetch_author_models(author: str) -> list:
+    url = (f"https://huggingface.co/api/models?author={author}"
+           f"&filter=gguf&sort=downloads&direction=-1&limit=40")
+    try:
+        with httpx.Client(timeout=12.0) as c:
+            data = c.get(url).json()
+        return data if isinstance(data, list) else []
+    except Exception:
+        return []
+
+
+def rank_runnable(models: list[dict]) -> list[dict]:
+    """EINE Quelle der Wahrheit fürs Ranking lauffähiger Modelle:
+    bestes Fit-Level zuerst (perfect < marginal), bei Gleichstand meistgeladen.
+    Zu große Modelle (too_tight) fliegen raus."""
+    return sorted(
+        [m for m in models if m["fit"]["level"] != "too_tight"],
+        key=lambda m: (_FIT_ORDER[m["fit"]["level"]], -int(m.get("downloads") or 0)),
+    )
+
+
+def refresh_discover(ram_gb: float) -> dict:
+    """Quellen live abfragen, kategorisieren, ranken, cachen. Wirft nur, wenn KEINE
+    Quelle erreichbar war."""
+    raw, seen, ok = [], set(), 0
+    for author in TRUSTED_AUTHORS:
+        models = _fetch_author_models(author)
+        if models:
+            ok += 1
+        for m in models:
+            rid = m.get("id")
+            if not rid or rid in seen:
+                continue
+            seen.add(rid)
+            raw.append(m)
+    if ok == 0:
+        raise RuntimeError("Keine Quelle erreichbar.")
+
+    by_cat: dict[str, list] = {c["role"]: [] for c in CATEGORIES}
+    for m in raw:
+        rid = m["id"]
+        low = rid.lower()
+        if any(tok in low for tok in SKIP_TOKENS):
+            continue
+        role = _categorize(rid)
+        params_b = extract_params_b(rid)
+        quant = "Q4_K_M"  # Referenz-Quant für die Fit-Einschätzung
+        fit = evaluate_fit(params_b, quant, 8192, ram_gb, name=rid)
+        tags = [str(t) for t in (m.get("tags") or [])]
+        by_cat[role].append({
+            "name": rid.split("/")[-1], "author": rid.split("/")[0], "repo": rid,
+            "role": role, "params_b": params_b, "quant": quant, "tags": tags,
+            "downloads": int(m.get("downloads") or 0), "likes": int(m.get("likes") or 0),
+            "lastModified": m.get("lastModified"),
+            "fit": fit, "optimal_ctx": max_ctx_for(params_b, quant, ram_gb),
+            "caps": capabilities(name=rid, hf={"tags": tags}),
+        })
+
+    cats = []
+    for c in CATEGORIES:
+        items = by_cat[c["role"]]
+        ranked = rank_runnable(items)
+        # Top 4 je Kategorie (für die Anzeige) — gerankt, dann nach Downloads aufgefüllt.
+        items.sort(key=lambda x: (x["fit"]["level"] != "too_tight", x["downloads"]), reverse=True)
+        top = items[:4]
+        if top:
+            cats.append({
+                "role": c["role"], "title": c["title"], "icon": c["icon"],
+                "models": top,
+                "recommended": ranked[0]["repo"] if ranked else None,
+            })
+
+    data = {"updated": time.time(), "categories": cats}
+    try:
+        DISCOVER_CACHE_PATH.parent.mkdir(parents=True, exist_ok=True)
+        tmp = DISCOVER_CACHE_PATH.with_name(DISCOVER_CACHE_PATH.name + ".tmp")
+        tmp.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
+        os.replace(tmp, DISCOVER_CACHE_PATH)
+    except Exception:
+        pass  # Cache ist nur Beschleunigung
+    return data
+
+
+def load_discover() -> dict | None:
+    try:
+        if DISCOVER_CACHE_PATH.exists():
+            return json.loads(DISCOVER_CACHE_PATH.read_text(encoding="utf-8"))
+    except Exception:
+        pass
+    return None
+
+
+def safe_discover(ram_gb: float) -> dict | None:
+    """Aus Cache (wenn frisch) oder live; wirft nie — None wenn nichts da."""
+    cached = load_discover()
+    if cached and (time.time() - cached.get("updated", 0) < DISCOVER_TTL):
+        return cached
+    try:
+        return refresh_discover(ram_gb)
+    except Exception:
+        return cached