factor_agent.llm.anthropic.AnthropicBackend#

class AnthropicBackend(model, max_tokens=16000, effort=None, base_url=None, timeout_seconds=600.0)[source]#

Complete a request with one Messages API call.

Parameters:

modelstr: The model of every call.
max_tokensint: The max_tokens of every call.
effortstr, optional: The output_config.effort of every call; the model’s default if None.
base_urlstr, optional: Another endpoint than Anthropic’s.
timeout_secondsfloat: Seconds a call may take.

Methods#

`AnthropicBackend.complete`	Send `request`'s prompt as one user message.
`AnthropicBackend.from_config`	Build from a role's config: `model` and optionally `max_tokens`, `effort`, `base_url`, `timeout_seconds`.

AnthropicBackend.OPTIONS = ('max_tokens', 'effort', 'base_url', 'timeout_seconds')#: The options a role’s config may give besides backend and model.