Inference

Configure Model Limits

View as Markdown

Set Pi Model Metadata

Pi accepts an explicit context window, maximum output-token count, and reasoning flag.

VariableValuesDefault
NEMOCLAW_CONTEXT_WINDOWPositive integer up to 4194304 tokensUnset; Pi uses the model default
NEMOCLAW_MAX_TOKENSInteger from 1 to 1000000000 tokensUnset; Pi uses the model default
NEMOCLAW_REASONINGtrue or falseUnset; Pi uses the model default

Export the values before onboarding.

export NEMOCLAW_CONTEXT_WINDOW=65536
export NEMOCLAW_MAX_TOKENS=8192
export NEMOCLAW_REASONING=true
nemoclaw onboard --agent pi --name <sandbox-name>

NemoClaw validates each supplied value and writes it to /sandbox/.pi/agent/models.json through the managed startup profile. An invalid value fails before Pi starts. Pi does not support NEMOCLAW_REASONING_EFFORT.

Recreate a Pi Sandbox

A normal Pi rebuild replays the recorded context window, maximum output-token count, and reasoning flag. Changing those values requires a fresh replacement. Keep an independent copy first when you need an extra recovery point, then export the new values and recreate the sandbox.

nemoclaw onboard --agent pi --name <sandbox-name> --fresh --recreate-sandbox

Pi has no runtime inference set configuration path. Use the same fresh replacement flow to change its provider or model.