generate_thread_name(
model_spec: str,
messages: Sequence[BaseMessage],
*,
thread_id: str| Name | Type | Description |
|---|---|---|
model_spec* | str | Configured provider/model specification. |
messages* | Sequence[BaseMessage] | Conversation to name; only user and assistant text is sent. |
thread_id | str | None | Default: NoneThread that owns the request's usage for cost accounting. |
model_params | dict[str, object] | None | Default: None |
initialization_lock | asyncio.Lock | None | Default: None |
Generate a safe name using the selected model without conversation callbacks.
Cancellation waits for model initialization, which can update process-wide provider settings, even if the generation timeout has expired.
Active conversation model overrides when inheriting its model,
including connection settings such as base_url.
Excludes environment mutations while the model factory runs, including cancellation cleanup. Released before the model request.