TimeoutError: Timeout (60.00999999999663 secs): rate limit for key: ('client', 'gpt-5.2-2025-12-11')

llm_openai = "gpt-5.2-2025-12-11"
settings = Settings(
    llm=llm_openai,
    llm_config={
        "model_list": [
            {
                "model_name": llm_openai,
                "litellm_params": {
                    "model": llm_openai,
                    "temperature": 0.1,
                    "max_tokens": 4096,
                },
            }
        ],
        "rate_limit": {
            llm_openai: "100000 per 1 minute",
        },
    },
    summary_llm=llm_openai,
    summary_llm_config={
        "rate_limit": {
            llm_openai: "100000 per 1 minute",
        },
    },
    embedding="text-embedding-3-small",
    embedding_config={},
    temperature=0.1,
    batch_size=1,
    verbosity=1,
    answer=AnswerSettings(
        evidence_k=10,
        evidence_retrieval=True,
        evidence_summary_length="about 200 words",
        evidence_skip_summary=False,
        answer_max_sources=10,
        max_answer_attempts=None,
        answer_length="must not exceed approximately 1000 words",
        max_concurrent_requests=10,
    ),
    parsing=ParsingSettings(
        reader_config={"chunk_chars": 7000, "overlap": 250},
        citation_prompt=citation_prompt,
        structured_citation_prompt=structured_citation_prompt,
    ),
    prompts=PromptSettings(
        summary=summary_prompt,
        qa=qa_prompt,
        select=select_paper_prompt,
        pre=None,
        post=None,
        system=default_system_prompt,
        use_json=True,
        summary_json=summary_json_prompt,
        summary_json_system=summary_json_system_prompt,
        context_outer=CONTEXT_OUTER_PROMPT,
        context_inner=CONTEXT_INNER_PROMPT,
    ),
    agent=AgentSettings(
        agent_llm=llm_openai,
        agent_llm_config={
            "model_list": [
                {
                    "model_name": llm_openai,
                    "litellm_params": {
                        "model": llm_openai,
                    },
                }
            ],
            "rate_limit": {
                llm_openai: "100000 per 1 minute",
            },
        },
        agent_prompt=env_reset_prompt,
        agent_system_prompt=env_system_prompt,
        search_count=8,
        index=IndexSettings(
            paper_directory=pathlib.Path.cwd().joinpath("papers"),
            manifest_file=None,
            index_directory=pathlib.Path.cwd().joinpath("papers/index"),
        ),
        timeout=10000
    ),
)

python3
session = await docs.aquery(q, settings=settings)

File ~/.venv/lib/python3.13/site-packages/lmi/llms.py:536, in rate_limited.<locals>.wrapper(self, *args, **kwargs)
    533 else:
    534     token_count = 0  # Default if method is unknown
--> 536 await self.check_rate_limit(token_count)
    538 # If wrapping a generator, count the tokens for each
    539 # portion before yielding
    540 if isasyncgenfunction(func):

File ~/.venv/lib/python3.13/site-packages/lmi/llms.py:865, in LiteLLMModel.check_rate_limit(self, token_count, **kwargs)
    863 async def check_rate_limit(self, token_count: float, **kwargs) -> None:
    864     if "rate_limit" in self.config:
--> 865         await GLOBAL_LIMITER.try_acquire(
    866             ("client", self.name),
    867             self.config["rate_limit"].get(self.name, None),
    868             weight=max(int(token_count), 1),
    869             **kwargs,
    870         )

File ~/.venv/lib/python3.13/site-packages/lmi/rate_limiter.py:416, in GlobalRateLimiter.try_acquire(self, namespace_and_key, rate_limit, machine_id, acquire_timeout, weight, raise_impossible_limits)
    414     elapsed += self.WAIT_INCREMENT
    415 if elapsed >= acquire_timeout:
--> 416     raise TimeoutError(
    417         f"Timeout ({elapsed} secs): rate limit for key: {namespace_and_key}"
    418     )
    420 # If the rate limit hit is False, then we're violating the limit, so we
    421 # need to wait again. This can happen in race conditions.
    422 if await self.rate_limiter.hit(
    423     rate_limit,
    424     new_namespace,
   (...)    427 ):
    428     # we need to keep trying when we have an "impossible" limit

TimeoutError: Timeout (60.00999999999663 secs): rate limit for key: ('client', 'gpt-5.2-2025-12-11')