InferenceValidate Inference

Understand Provider Validation

View as Markdown

NemoClaw validates the selected provider and model before it creates a sandbox. The exact request depends on the provider API that the agent uses.

Credential Validation

When credential validation fails, the onboarding wizard lets you re-enter the API key, choose another provider, retry, or exit. NemoClaw retries transient upstream failures before it reports a provider failure.

The nvapi- prefix check applies only to NVIDIA_INFERENCE_API_KEY. OpenRouter keys must be non-empty and begin with sk-or-. Other provider keys use provider-aware validation during the retry flow.

Provider Requests

NemoClaw sends a provider-specific request that exercises the API surface intended for the route.

ProviderValidation request
OpenAITries /responses, then /chat/completions.
NVIDIA EndpointsUses /v1/chat/completions and skips /v1/responses.
OpenRouterUses /v1/chat/completions for catalog, model, and smoke validation.
Google GeminiUses the OpenAI-compatible chat-completions path and skips /v1/responses.
Other OpenAI-compatible endpointTries /v1/responses with tool-calling and streaming checks, then falls back to /v1/chat/completions.
Local NVIDIA NIMUses /v1/chat/completions and skips /v1/responses.

For an OpenAI-compatible endpoint, the runtime defaults to /v1/chat/completions even when the Responses probe succeeds. Set NEMOCLAW_PREFERRED_API=openai-responses before onboarding to select /v1/responses only after the probe verifies the required streaming behavior. Set NEMOCLAW_PREFERRED_API=openai-completions to skip the Responses probe and validate Chat Completions only.

Anthropic-Compatible Requests

For OpenClaw, NemoClaw sends a non-streaming request to /v1/messages, then sends a streaming request to the same path. The streaming check requires exactly one message_start, at least one content_block_delta, and one message_stop event.

Set NEMOCLAW_REASONING=true to skip the streaming check for a reasoning-only endpoint. Agent runs still use streaming, so this setting moves a streaming defect from onboarding to runtime.

Compatible Endpoint Probes

Compatible endpoint validation sends a real inference request because many proxies do not expose /models. For an OpenAI-compatible endpoint, a reasoning model that returns only reasoning content can receive a retry with a larger response budget before NemoClaw reports failure. Route, configuration, and authentication failures still fail immediately.

An endpoint that is reachable only through http://host.openshell.internal:<port> cannot receive the host-side API probe. Verify that route from inside the sandbox after onboarding.