feat: improve resume optimization and import reliability

backend/app/llm_services.py

@@ -203,6 +203,8 @@ class OpenAICompatibleStructuredClient:
         schema_name: str,
         system_prompt: str,
         payload: dict[str, Any],
+        timeout_seconds: float | None = None,
+        max_attempts: int | None = None,
     ) -> SchemaT:
         trace_id = f"ai_{uuid4().hex}"
         response_format: dict[str, Any]
@@ -226,13 +228,22 @@ class OpenAICompatibleStructuredClient:
                 "input": request_payload,
                 "output_json_schema": schema.model_json_schema(),
             }
+        if max_attempts is not None and max_attempts < 1:
+            raise ValueError("max_attempts must be positive")
+        attempts = max_attempts if max_attempts is not None else self.settings.structured_output_retries + 1
+        request_timeout = timeout_seconds if timeout_seconds is not None else self.settings.openai_timeout_seconds
+        request_client = self.client
+        if timeout_seconds is not None or max_attempts is not None:
+            with_options = getattr(request_client, "with_options", None)
+            if callable(with_options):
+                request_client = with_options(timeout=request_timeout, max_retries=0)
         failure_summary = "unknown_error"
         failure_reason = "llm_unknown_error"
         total_started = time.perf_counter()
-        for attempt in range(1, self.settings.structured_output_retries + 2):
+        for attempt in range(1, attempts + 1):
             attempt_started = time.perf_counter()
             try:
-                response = self.client.chat.completions.create(
+                response = request_client.chat.completions.create(
                     model=self.settings.openai_model,
                     messages=[
                         {"role": "system", "content": request_system_prompt},
@@ -242,7 +253,7 @@ class OpenAICompatibleStructuredClient:
                         },
                     ],
                     response_format=response_format,
-                    timeout=self.settings.openai_timeout_seconds,
+                    timeout=request_timeout,
                 )
                 if not getattr(response, "choices", None):
                     raise LLMServiceError(
@@ -296,7 +307,7 @@ class OpenAICompatibleStructuredClient:
             trace_id=trace_id,
             schema=schema_name,
             model=self.settings.openai_model,
-            attempts=self.settings.structured_output_retries + 1,
+            attempts=attempts,
             reason_code=failure_reason,
             duration_ms=round((time.perf_counter() - total_started) * 1000),
             exception=failure_summary,