Configure Inference Timeouts

View as Markdown

NemoClaw uses separate time budgets for agent requests, local provider validation, and sandbox readiness. Change the budget that matches the phase that times out.

Choose the Timeout

Use the error location to select the correct setting.

SettingApplies toDefault
NEMOCLAW_AGENT_TIMEOUTOpenClaw per-request inference600 seconds
NEMOCLAW_LOCAL_INFERENCE_TIMEOUTOllama, vLLM, NIM, and compatible-endpoint validation during onboarding180 seconds
NEMOCLAW_SANDBOX_READY_TIMEOUTImage build, gateway upload, and in-sandbox boot after sandbox creation180 seconds

The readiness timeout does not govern inference requests or provider validation.

Increase the OpenClaw Request Timeout

Hermes does not consume the OpenClaw-only NEMOCLAW_AGENT_TIMEOUT setting.

Increase the Local Validation Timeout

Raise NEMOCLAW_LOCAL_INFERENCE_TIMEOUT when the inference-server validation probe needs more than 180 seconds. Large prompts, cold local model loads, and slower hardware can require a larger budget.

$export NEMOCLAW_LOCAL_INFERENCE_TIMEOUT=300
$nemohermes onboard

Local Ollama setup treats host-side curl timeouts as retryable probe failures and retries with a larger timeout before reporting validation failure. This variable does not extend the later sandbox-readiness wait.

Increase the Sandbox Readiness Timeout

Raise NEMOCLAW_SANDBOX_READY_TIMEOUT when onboarding creates the sandbox but image build, upload, or boot exceeds 180 seconds. This can occur during a first run with cold caches or on a remote VM over a slow link.

$export NEMOCLAW_SANDBOX_READY_TIMEOUT=600
$nemohermes onboard

Raise both onboarding budgets when the provider probe and the later sandbox creation phase are slow.

$export NEMOCLAW_LOCAL_INFERENCE_TIMEOUT=300
$export NEMOCLAW_SANDBOX_READY_TIMEOUT=600
$nemohermes onboard

Apply Build-Time Changes

Recreate an existing sandbox when you change a timeout that NemoClaw bakes into its image.

$nemohermes onboard --fresh --name <sandbox-name> --recreate-sandbox