Skip to content

Anthropic

The anthropic provider calls Anthropic's Messages API through LangChain's ChatAnthropic.

Settings

Setting Default Notes
core.llm.provider openai Set to anthropic.
core.llm.anthropic.api_key — Required; the provider refuses to build a model without it. Stored encrypted.
core.llm.anthropic.expert_model claude-sonnet-4-20250514 The analysts' model.
core.llm.anthropic.judge_model claude-sonnet-4-20250514 The judge's model. 
core.llm.provider               = anthropic
core.llm.anthropic.api_key      = <your key>
core.llm.anthropic.expert_model = claude-sonnet-4-20250514
core.llm.anthropic.judge_model  = claude-sonnet-4-20250514

How it behaves

  • No endpoint to override. Anthropic is a vendor API here: a per-agent entry on anthropic takes no base_url, and one set is rejected on save.
  • Structured output is used where a caller asks for it.
  • Tool replies. A turn's tool_use blocks are each answered by a tool_result block at the front of the next user turn, as the API requires; a call the history left unanswered gets a reply saying none was recorded.
  • Hosted, so parallel. Under core.llm.parallel_analysts = auto, the Anthropic API counts as hosted, so a stage's analysts run at once.
  • Request timeout. 1800 s until the model's pace is measured, then sized per request.

The probe for this provider asks through /v1/messages. A per-agent entry may put one agent on Anthropic while the rest run elsewhere; see Per-agent models and fallbacks.