Function create_chat_completion

app/server/chat.py:1757–1934

(
    request: ChatCompletionRequest,
    raw_request: Request,
    api_key: str = Depends(verify_api_key),
    tmp_dir: Path = Depends(get_temp_dir),
    image_store: Path = Depends(get_image_store_dir),
)

@router.post("/v1/chat/completions")
async def create_chat_completion(
    request: ChatCompletionRequest,
    raw_request: Request,
    api_key: str = Depends(verify_api_key),
    tmp_dir: Path = Depends(get_temp_dir),
    image_store: Path = Depends(get_image_store_dir),
):
    base_url = str(raw_request.base_url)
    pool, db = GeminiClientPool(), LMDBConversationStore()
    try:
        model = _get_model_by_name(request.model)
    except ValueError as exc:
        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(exc)) from exc
    if not request.messages:
        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Messages required.")

    structured_requirement = _build_structured_requirement(request.response_format)
    extra_instr = [structured_requirement.instruction] if structured_requirement else None

    # This ensures that server-injected system instructions are part of the history
    msgs = _prepare_messages_for_model(
        request.messages,
        request.tools,
        request.tool_choice,
        extra_instr,
    )

    session, client, remain = await _find_reusable_session(db, pool, model, msgs)
    reused_session = session is not None
    use_google_temporary_mode = g_config.gemini.chat_mode == ChatMode.TEMPORARY

    if session:
        if not remain:
            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="No new messages.")

        # For reused sessions, we only need to process the remaining messages.
        # We don't re-inject system defaults to avoid duplicating instructions already in history.
        input_msgs = _prepare_messages_for_model(
            remain,
            request.tools,
            request.tool_choice,
            extra_instr,
            False,
        )
        m_input, files = await _process_conversation_with_compaction(
            input_msgs,
            tmp_dir,
            allow_summary_compaction=use_google_temporary_mode and (g_config.gemini.oversized_context_strategy == OversizedContextStrategy.COMPACTION),
            reason="temporary session replay",
        )

        logger.debug(
            f"Reused session {reprlib.repr(session.metadata)} - sending {len(input_msgs)} prepared messages."
        )
    else:
        try:
            client = await pool.acquire()
            session = client.start_chat(model=model)