feat: simplify Discover view into socket cards & backend upgrades

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):