Fix: Enabled descriptive AI error reporting in Dashboard and generator (Phase 9 Debug)

backend/routers/generator.py

@@ -83,7 +83,7 @@ async def generate_project(
         
         # Use llama3-70b-8192 as a more stable fallback/default
         model_name = provider_config.get("default_model") or "llama3-70b-8192"
-        logger.info("Calling Groq with model: %s", model_name)
+        logger.info("Calling Groq with model: %s (Key: %s...)", model_name, api_key[:8] if api_key else "None")
 
         response = await client.chat.completions.create(
             model=model_name,
@@ -92,20 +92,17 @@ async def generate_project(
                 {"role": "user", "content": user_message}
             ],
             temperature=0.3,
-            max_tokens=2048,
-            # Note: Not all Groq models support json_object mode perfectly yet
-            response_format={"type": "json_object"}
+            max_tokens=2048
+            # response_format={"type": "json_object"} # Disabled for stability testing
         )
         
         response_text = response.choices[0].message.content
-        logger.debug("Groq raw response: %s", response_text)
+        logger.info("Groq raw response received (%d chars)", len(response_text) if response_text else 0)
         data = _parse_json_output(response_text)
         return data
         
     except Exception as e:
         logger.exception("Project generation failed")
+        error_type = type(e).__name__
         error_msg = str(e)
-        # Handle specific Groq errors if possible
-        if "api_key" in error_msg.lower():
-            error_msg = "Invalid or missing API Key"
-        raise HTTPException(status_code=500, detail=f"AI Generation failed: {error_msg}")
+        raise HTTPException(status_code=500, detail=f"AI Error ({error_type}): {error_msg}")

frontend/src/components/Dashboard.tsx

@@ -111,9 +111,9 @@ const Dashboard: React.FC<DashboardProps> = ({ onNewProject, onOpenProject }) =>
         body: formData
       });
 
-      if (!response.ok) throw new Error('AI Generation failed');
-      
       const data = await response.json();
+      if (!response.ok) throw new Error(data.detail || 'AI Generation failed');
+      
       onNewProject(data); // Open NewProject wizard with pre-filled data
       setAiPrompt('');
       setMagicFiles([]);