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/routers/health.py

@@ -3,7 +3,7 @@
 from fastapi import APIRouter
 
 from config import VERSION
-from services import llamaswap
+from services import gateway, llamaswap
 
 router = APIRouter(prefix="/api")
 
@@ -14,4 +14,5 @@ def health() -> dict:
         "status": "ok",
         "version": VERSION,
         "engine_reachable": llamaswap.engine_reachable(),
+        "gateway_reachable": gateway.gateway_reachable(),
     }

backend/routers/models.py

@@ -1,13 +1,81 @@
-"""Modelle-Endpoint (Phase 0: read-only Liste aus der llama-swap config.yaml)."""
+"""Modelle-Endpoints: Liste (mit Caps), Discover, Fit, Register, Groups."""
 
-from fastapi import APIRouter
+import psutil
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
 
-from services import llamaswap
+from services import discover, llamaswap
+from services.fit import evaluate_fit, max_ctx_for
 
 router = APIRouter(prefix="/api")
 
 
+def _ram_gb() -> float:
+    return psutil.virtual_memory().total / (1024 ** 3)
+
+
 @router.get("/models")
 def models() -> dict:
     items = llamaswap.list_models()
     return {"models": items, "count": len(items)}
+
+
+@router.get("/discover")
+def discover_models(force: bool = False) -> dict:
+    ram = _ram_gb()
+    data = discover.refresh_discover(ram) if force else discover.safe_discover(ram)
+    if not data:
+        raise HTTPException(502, "Modell-Quellen gerade nicht erreichbar — später erneut.")
+    return {**data, "sys_ram_gb": round(ram, 1)}
+
+
+@router.get("/fit")
+def fit(params_b: float, quant: str = "Q4_K_M", ctx: int = 8192, name: str = "") -> dict:
+    ram = _ram_gb()
+    return {
+        "fit": evaluate_fit(params_b, quant, ctx, ram, name=name),
+        "optimal_ctx": max_ctx_for(params_b, quant, ram),
+        "sys_ram_gb": round(ram, 1),
+    }
+
+
+class RegisterReq(BaseModel):
+    model_path: str
+    role: str | None = None
+    ctx: int = 8192
+    ttl: int | None = None
+    mmproj_path: str | None = None
+    jinja: bool = False
+
+
+@router.post("/models/register")
+def register(req: RegisterReq) -> dict:
+    try:
+        model_id = llamaswap.register_model(
+            req.model_path, role=req.role, ctx=req.ctx, ttl=req.ttl,
+            mmproj_path=req.mmproj_path, jinja=req.jinja,
+        )
+    except PermissionError as exc:
+        raise HTTPException(500, str(exc))
+    return {"ok": True, "model_id": model_id}
+
+
+@router.get("/groups")
+def groups() -> dict:
+    return {"groups": llamaswap.list_groups()}
+
+
+class GroupReq(BaseModel):
+    group: str
+    members: list[str]
+    swap: bool = False
+    persist: bool = False
+
+
+@router.put("/groups")
+def set_group(req: GroupReq) -> dict:
+    try:
+        llamaswap.set_group(req.group, req.members, swap=req.swap, persist=req.persist)
+    except PermissionError as exc:
+        raise HTTPException(500, str(exc))
+    return {"ok": True}

backend/routers/routing.py

@@ -0,0 +1,28 @@
+"""Routing-Endpoints: Gateway-Übersicht (welcher Alias = fast/heavy/…) + Mapping setzen."""
+
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
+
+from services import gateway
+
+router = APIRouter(prefix="/api")
+
+
+@router.get("/routing")
+def routing() -> dict:
+    return {**gateway.routing_summary(), "gateway_reachable": gateway.gateway_reachable()}
+
+
+class RouteReq(BaseModel):
+    name: str          # Gateway-Modellname, z.B. "fast" / "heavy" / "vision" / "coder"
+    target_alias: str  # llama-swap-Alias, der bedient wird
+    api_base: str = "http://127.0.0.1:8080/v1"
+
+
+@router.put("/routing/route")
+def set_route(req: RouteReq) -> dict:
+    try:
+        gateway.set_route(req.name, req.target_alias, api_base=req.api_base)
+    except Exception as exc:  # noqa: BLE001
+        raise HTTPException(500, str(exc))
+    return {"ok": True}