llm_nudge()

Register an LLM-powered advisory nudge.

Usage

Source

llm_nudge(
    prompt,
    *,
    message,
    response_model=NudgeVerdict,
    verdict=lambda r: r.fire,
    signals=None,
    when=None,
    only_if=(),
    skip_if=(),
    events=None,
    max_fires=None,
    tests=None,
    async_=False,
    max_context=2000,
    specialty="review",
    model="small",
    agent=True,
    transcript=True
)

Defaults are tuned for the common case: agent=True and transcript=True so the nudge has tool access and full transcript context. Pass agent=False, transcript=False for cheap, stateless yes/no checks.

Example

llm_nudge(“Is the agent speculating instead of observing?”, … message=“Observe, don’t infer – check traces first”, … signals=Signals([Signal(r”should contain”, weight=2)], threshold=3))