feat: simplify Discover view into socket cards & backend upgrades

backend/routers/maintenance.py

@@ -1,6 +1,6 @@
 """Wartungs-Endpoints: Update-Badge, OS-/Engine-Update, Reboot, Restart, Logs."""
 
-from fastapi import APIRouter, HTTPException
+from fastapi import APIRouter, HTTPException, Header
 from pydantic import BaseModel
 
 from services import maintenance
@@ -8,38 +8,46 @@ from services import maintenance
 router = APIRouter(prefix="/api")
 
 
+class SudoReq(BaseModel):
+    sudo_password: str | None = None
+
+
+class RestartReq(BaseModel):
+    service: str
+    sudo_password: str | None = None
+
+
 @router.get("/maintenance/updates")
 def updates() -> dict:
     return maintenance.updates()
 
 
 @router.post("/maintenance/os-update")
-def os_update() -> dict:
-    return {"job_id": maintenance.os_update_job()}
+def os_update(body: SudoReq) -> dict:
+    res = maintenance.os_update_job(body.sudo_password)
+    if isinstance(res, dict) and not res.get("ok", True):
+        return res
+    return res
 
 
 @router.post("/maintenance/engine-update")
-def engine_update() -> dict:
-    job = maintenance.engine_update_job()
-    if not job:
+def engine_update(body: SudoReq) -> dict:
+    res = maintenance.engine_update_job(body.sudo_password)
+    if not res:
         raise HTTPException(400, "Kein Engine-Update-Befehl gesetzt (MC_ENGINE_UPDATE_CMD).")
-    return {"job_id": job}
+    return res
 
 
 @router.post("/maintenance/reboot")
-def reboot() -> dict:
-    return maintenance.reboot()
-
-
-class RestartReq(BaseModel):
-    service: str
+def reboot(body: SudoReq) -> dict:
+    return maintenance.reboot(body.sudo_password)
 
 
 @router.post("/maintenance/restart")
 def restart(body: RestartReq) -> dict:
-    return maintenance.restart_service(body.service)
+    return maintenance.restart_service(body.service, body.sudo_password)
 
 
 @router.get("/maintenance/logs")
-def logs(service: str, lines: int = 200) -> dict:
-    return maintenance.logs(service, lines)
+def logs(service: str, lines: int = 200, x_sudo_password: str | None = Header(None)) -> dict:
+    return maintenance.logs(service, lines, x_sudo_password)

backend/routers/models.py

@@ -158,6 +158,49 @@ def set_model_ctx(model_id: str, body: CtxReq) -> dict:
     return {"ok": True}
 
 
+@router.post("/models/unload")
+def unload_all_models() -> dict:
+    import httpx
+    from config import LLAMA_SWAP_URL
+    try:
+        with httpx.Client(timeout=10.0) as c:
+            r = c.post(f"{LLAMA_SWAP_URL}/api/models/unload")
+            return {"ok": r.status_code == 200}
+    except Exception as exc:
+        raise HTTPException(500, str(exc))
+
+
+@router.post("/models/{model_id}/unload")
+def unload_model(model_id: str) -> dict:
+    import httpx
+    from config import LLAMA_SWAP_URL
+    try:
+        with httpx.Client(timeout=10.0) as c:
+            r = c.post(f"{LLAMA_SWAP_URL}/api/models/unload/{model_id}")
+            return {"ok": r.status_code == 200}
+    except Exception as exc:
+        raise HTTPException(500, str(exc))
+
+
+@router.post("/models/{model_id}/load")
+def load_model(model_id: str) -> dict:
+    import httpx
+    from config import LLAMA_SWAP_URL
+    try:
+        # Trigger load by sending a lightweight completion request.
+        body = {
+            "model": model_id,
+            "messages": [{"role": "user", "content": "ping"}],
+            "max_tokens": 1
+        }
+        # High timeout because model loading might take time
+        with httpx.Client(timeout=60.0) as c:
+            c.post(f"{LLAMA_SWAP_URL}/v1/chat/completions", json=body)
+            return {"ok": True}
+    except Exception as exc:
+        raise HTTPException(500, str(exc))
+
+
 @router.delete("/models/{model_id}")
 def delete(model_id: str) -> dict:
     if not llamaswap.delete_model(model_id):