new·Earn with mozg — 20% of every monthSend somebody here and take a fifth of every plan payment they make, for as long as they keep paying — not a bounty on the first invoice. Your handle is the link, the window is thirty days, and the commission lands on your balance the second they pay. Free to join: if you have signed in, you already have the link. mozg.sh/earnall news →
mozg.beta
Sign in

LangChain & LangGraph · all subjects

models and messages

6 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Model parameter format for direct provider calls

Set the model parameter to a 'provider:model' string such as 'openai:gpt-5.5', 'anthropic:claude-sonnet-4-6', or 'google_genai:gemini-3.6-flash'. The provider's API key must be added to .env for the model to work locally and in deployment.

LLM Gateway model routing syntax

To use LLM Gateway, prefix the gateway model ID with 'langsmith:' and use the format 'langsmith:provider/model-name'. Gateway model IDs use a slash between provider and model, while direct provider calls use a colon. LangChain-hosted models like 'langsmith:moonshotai/kimi-k3' require no provider secret and draw on Gateway Credits. Provider-specific models like 'langsmith:anthropic/claude-opus-5' use the provider secret and bill to the provider account.

LangChain model instance for parameter configuration

Pass a LangChain chat model instance instead of a provider string when you need to configure model parameters in code.

Model reference requirements in documentation

Always use latest generally available (GA) models when referencing LLMs in docstrings and illustrative code snippets. Avoid preview or beta identifiers unless no GA equivalent exists. Verify current model IDs against provider's official docs before writing or updating—do not rely on memorized or cached model names as they go stale quickly.

A2A messageId mapped to LangChain message IDs

A2A messageId is now mapped to LangChain message IDs for proper message tracking across protocols.

messages-tuple streaming mode tool_call_chunks fix

A bug in messages-tuple streaming mode was fixed where tool_call_chunks contained args_json instead of args, preventing message reconstruction.

Give your agent this brain