feat: load and cache Ollama show data per model with clickable model details

- Add GET /api/v1/models/{model_name}/show endpoint (proxy to Ollama /api/show)
- Worker now fetches show data for each model during model list sync
- Persist show details in localStorage under llm_monitor_models.showByModel
- Make model cards clickable to display cached show details in a dedicated panel
- Keep UI updates incremental without full page reload
- Add tests for show endpoint and OpenAPI path
- Update README and PRD with show-flow and click-card behavior

app/api/models.py

@@ -4,7 +4,7 @@ Models endpoints - Gestione dei modelli Ollama
 
 from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel
-from typing import List, Optional
+from typing import Any, Dict, List, Optional
 from datetime import datetime
 import requests
 import logging
@@ -174,6 +174,58 @@ async def get_model(model_name: str):
             detail="Errore nel recupero del modello"
         )
 
+
+@router.get("/models/{model_name}/show")
+async def get_model_show(model_name: str) -> Dict[str, Any]:
+    """
+    Recupera le informazioni estese di un modello tramite endpoint Ollama /api/show.
+
+    Args:
+        model_name: Nome del modello da interrogare
+
+    Returns:
+        Dict[str, Any]: Dati estesi del modello
+    """
+    try:
+        response = requests.post(
+            f"{settings.OLLAMA_HOST}/api/show",
+            json={"model": model_name},
+            timeout=settings.OLLAMA_TIMEOUT
+        )
+
+        if response.status_code == 404:
+            raise HTTPException(
+                status_code=404,
+                detail=f"Modello '{model_name}' non trovato"
+            )
+
+        if response.status_code != 200:
+            raise HTTPException(
+                status_code=502,
+                detail="Errore durante il recupero dettagli modello"
+            )
+
+        return response.json()
+
+    except requests.exceptions.Timeout:
+        raise HTTPException(
+            status_code=504,
+            detail="Timeout: Ollama non ha risposto in tempo"
+        )
+    except requests.exceptions.ConnectionError:
+        raise HTTPException(
+            status_code=502,
+            detail="Impossible connettersi a Ollama"
+        )
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error fetching model show data: {e}")
+        raise HTTPException(
+            status_code=500,
+            detail="Errore nel recupero dei dettagli modello"
+        )
+
 @router.post(
     "/models/{model_name}/pull",
     include_in_schema=settings.ENABLE_MODEL_RW_API