Ask a question to get started
Enter to send•Shift+Enter new line
Runtime context passed via context= to the LangGraph graph.
context=
Carries per-invocation overrides that ConfigurableModelMiddleware reads from request.runtime.context.
ConfigurableModelMiddleware
request.runtime.context
CLIContext()
TypedDict
Model spec to swap at runtime (e.g. 'openai:gpt-4o').
'openai:gpt-4o'
Invocation params (e.g. temperature, max_tokens) to merge into model_settings.
temperature
max_tokens
model_settings
