Method _finalize_output

backend/python/mlx/backend.py:605–667

Build a ChatDelta + token counts + logprobs from accumulated output. Returns ``(content, reasoning_content, tool_calls_proto, prompt_token_count, completion_token_count, logprobs_bytes)``.

(self, request, generated_text, last_response)

        )

    def _finalize_output(self, request, generated_text, last_response):
        """Build a ChatDelta + token counts + logprobs from accumulated output.

        Returns ``(content, reasoning_content, tool_calls_proto,
        prompt_token_count, completion_token_count, logprobs_bytes)``.
        """
        content = generated_text
        reasoning_content = ""

        if getattr(self.tokenizer, "has_thinking", False):
            think_start = getattr(self.tokenizer, "think_start", "") or ""
            think_end = getattr(self.tokenizer, "think_end", "") or ""
            reasoning_content, content = split_reasoning(content, think_start, think_end)

        tool_calls_proto: List[backend_pb2.ToolCallDelta] = []
        tool_module = None
        if getattr(self.tokenizer, "has_tool_calling", False):
            tool_module = self._tool_module_from_tokenizer()
        if tool_module is not None:
            parsed_tools = None
            if request.Tools:
                try:
                    parsed_tools = json.loads(request.Tools)
                except json.JSONDecodeError:
                    parsed_tools = None
            calls, content = parse_tool_calls(content, tool_module, parsed_tools)
            for c in calls:
                tool_calls_proto.append(
                    backend_pb2.ToolCallDelta(
                        index=c["index"],
                        id=c["id"],
                        name=c["name"],
                        arguments=c["arguments"],
                    )
                )

        prompt_token_count = int(getattr(last_response, "prompt_tokens", 0) or 0) if last_response else 0
        completion_token_count = int(getattr(last_response, "generation_tokens", 0) or 0) if last_response else 0

        logprobs_bytes = b""
        # Logprobs extraction — only when the request asked for them.
        if last_response is not None and int(getattr(request, "Logprobs", 0) or 0) > 0:
            try:
                lp = getattr(last_response, "logprobs", None)
                if lp is not None:
                    # GenerationResponse.logprobs on the last chunk is the
                    # logprob distribution of the final token. Without a
                    # per-token history we at minimum surface the last token's
                    # top-1 logprob so clients get a non-empty field.
                    token_id = int(getattr(last_response, "token", 0) or 0)
                    token_text = self.tokenizer.decode([token_id]) if token_id else ""
                    top_logprob = float(lp[token_id]) if hasattr(lp, "__getitem__") else 0.0
                    logprobs_bytes = json.dumps(
                        {
                            "content": [
                                {"token": token_text, "logprob": top_logprob}
                            ]
                        }