src/agents/extensions/models/litellm_model.py [151:206]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            disabled=tracing.is_disabled(),
        ) as span_generation:
            response, stream = await self._fetch_response(
                system_instructions,
                input,
                model_settings,
                tools,
                output_schema,
                handoffs,
                span_generation,
                tracing,
                stream=True,
            )

            final_response: Response | None = None
            async for chunk in ChatCmplStreamHandler.handle_stream(response, stream):
                yield chunk

                if chunk.type == "response.completed":
                    final_response = chunk.response

            if tracing.include_data() and final_response:
                span_generation.span_data.output = [final_response.model_dump()]

            if final_response and final_response.usage:
                span_generation.span_data.usage = {
                    "input_tokens": final_response.usage.input_tokens,
                    "output_tokens": final_response.usage.output_tokens,
                }

    @overload
    async def _fetch_response(
        self,
        system_instructions: str | None,
        input: str | list[TResponseInputItem],
        model_settings: ModelSettings,
        tools: list[Tool],
        output_schema: AgentOutputSchemaBase | None,
        handoffs: list[Handoff],
        span: Span[GenerationSpanData],
        tracing: ModelTracing,
        stream: Literal[True],
    ) -> tuple[Response, AsyncStream[ChatCompletionChunk]]: ...

    @overload
    async def _fetch_response(
        self,
        system_instructions: str | None,
        input: str | list[TResponseInputItem],
        model_settings: ModelSettings,
        tools: list[Tool],
        output_schema: AgentOutputSchemaBase | None,
        handoffs: list[Handoff],
        span: Span[GenerationSpanData],
        tracing: ModelTracing,
        stream: Literal[False],
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/agents/models/openai_chatcompletions.py [123:178]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            disabled=tracing.is_disabled(),
        ) as span_generation:
            response, stream = await self._fetch_response(
                system_instructions,
                input,
                model_settings,
                tools,
                output_schema,
                handoffs,
                span_generation,
                tracing,
                stream=True,
            )

            final_response: Response | None = None
            async for chunk in ChatCmplStreamHandler.handle_stream(response, stream):
                yield chunk

                if chunk.type == "response.completed":
                    final_response = chunk.response

            if tracing.include_data() and final_response:
                span_generation.span_data.output = [final_response.model_dump()]

            if final_response and final_response.usage:
                span_generation.span_data.usage = {
                    "input_tokens": final_response.usage.input_tokens,
                    "output_tokens": final_response.usage.output_tokens,
                }

    @overload
    async def _fetch_response(
        self,
        system_instructions: str | None,
        input: str | list[TResponseInputItem],
        model_settings: ModelSettings,
        tools: list[Tool],
        output_schema: AgentOutputSchemaBase | None,
        handoffs: list[Handoff],
        span: Span[GenerationSpanData],
        tracing: ModelTracing,
        stream: Literal[True],
    ) -> tuple[Response, AsyncStream[ChatCompletionChunk]]: ...

    @overload
    async def _fetch_response(
        self,
        system_instructions: str | None,
        input: str | list[TResponseInputItem],
        model_settings: ModelSettings,
        tools: list[Tool],
        output_schema: AgentOutputSchemaBase | None,
        handoffs: list[Handoff],
        span: Span[GenerationSpanData],
        tracing: ModelTracing,
        stream: Literal[False],
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -