fix: improve error handling for AI service responses

- Add defensive check for response.body existence to prevent undefined property access
- Include x-ms-error-code header in error messages for better debugging
- Provide clearer error messages for different failure scenarios
- Fix 'Cannot read properties of undefined (reading 'error')' runtime error

This improves the debugging experience when AI service requests fail due to
network issues, authentication errors, or unexpected response formats.

Author: ainoya

src/main.ts

@@ -82,14 +82,27 @@ export async function run(): Promise<void> {
     })
 
     if (isUnexpected(response)) {
-      if (response.body.error) {
+      // Extract x-ms-error-code from headers if available
+      const errorCode = response.headers['x-ms-error-code']
+      const errorCodeMsg = errorCode ? ` (error code: ${errorCode})` : ''
+      
+      // Check if response body exists and contains error details
+      if (response.body && response.body.error) {
         throw response.body.error
       }
+      
+      // Handle case where response body is missing
+      if (!response.body) {
+        throw new Error(
+          `Failed to get response from AI service (status: ${response.status})${errorCodeMsg}. ` +
+          'Please check network connection and endpoint configuration.'
+        )
+      }
+      
+      // Handle other error cases
       throw new Error(
-        'An error occurred while fetching the response (' +
-          response.status +
-          '): ' +
-          response.body
+        `AI service returned error response (status: ${response.status})${errorCodeMsg}: ` +
+        (typeof response.body === 'string' ? response.body : JSON.stringify(response.body))
       )
     }