feat: improve UX for Ollama 404 errors (missing model)

- src/ollama-client.ts: Detect HTTP 404 on /api/chat and throw a descriptive
  ApiError with the model name and the exact ollama pull command needed.

- src/error-handler.ts: For API_ERROR type, return the error message directly
  instead of prefixing with 'API error: ', so the user-friendly 404 message
  is shown cleanly in the Obsidian notice.

- tests/ollama-client.test.ts: Update 404 assertions to match the new
  descriptive error message.

tests/ollama-client.test.ts

@@ -214,7 +214,7 @@ describe('OllamaClient', () => {
       mockFetch.mockResolvedValue({ ok: false, status: 404 });
 
       await expect(client.streamChatAsPromise(mockMessages, mockTools)).rejects.toThrow(
-        'Ollama API error: 404'
+        'Model "llama3" not found. Run \`ollama pull llama3\` first.'
       );
     });
 
@@ -418,7 +418,7 @@ describe('OllamaClient', () => {
             /* consume */
           }
         })()
-      ).rejects.toThrow('Ollama API error: 404');
+      ).rejects.toThrow('Model "llama3" not found. Run \`ollama pull llama3\` first.');
     });
   });