fix(inference): propagate OpenClaw provider timeout

[jyaunches]

Summary

OpenClaw configs currently apply NEMOCLAW_AGENT_TIMEOUT to the whole agent run while leaving the provider request watchdog at OpenClaw's shorter default. This change applies the configured timeout to both layers so slow local inference can continue up to the agent deadline.

Related Issue

Related to #8468. This PR addresses the independently reproduced timeout gap; the reported sandbox-readiness transition still needs the QA harness and lifecycle evidence requested on the issue.

Changes

• Write NEMOCLAW_AGENT_TIMEOUT to models.providers.<provider-id>.timeoutSeconds as well as agents.defaults.timeoutSeconds.
• Cover both generated timeout fields in the OpenClaw configuration regression test.
• Document the two timeout consumers in the Dockerfile and inference/command references.

Type of Change

• Code change (feature, bug fix, or refactor)
• Code change with doc updates
• Doc only (prose changes, no code sample modifications)
• Doc only (includes code sample changes)

Quality Gates

• Tests added or updated for changed behavior
• Existing tests cover changed behavior — justification:
• Tests not applicable — justification:
• Docs updated for user-facing behavior changes
• Docs not applicable — justification:
• Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging)
• Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification:
• Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue:

Documentation Writer Review

• Documentation writer subagent reviewed the completed changes
• Result: docs-updated
• Evidence: docs/inference/configure-inference-timeouts.mdx, docs/reference/commands.mdx
• Agent: Codex Desktop

DGX Station Hardware Evidence

• Tested on DGX Station
• Tested commit:
• Station profile/scenario:
• Result:
• Supporting evidence:

Verification

• PR description includes a Signed-off-by: line and every commit appears as Verified in GitHub
• Normal pre-commit, commit-msg, and pre-push hooks passed, or npm run validate:pr passed after refreshing origin/main when hooks were skipped or unavailable
• Targeted behavior tests pass for the current change set, or tests are marked not applicable above — npm exec -- vitest run --project integration test/generate-openclaw-config.test.ts -t 'propagates the agent timeout to the run and provider request|rejects invalid agent timeout values' (2 passed)
• Applicable broad gate passed — npm test for broad runtime/test-harness changes; npm run check for repo-wide validation/coverage changes — command/result:
• Quality Gates section completed with required justifications or waivers
• No secrets, API keys, or credentials committed
• npm run docs builds without warnings (doc changes only)
• Doc pages follow the style guide (doc changes only)
• New doc pages include SPDX header and frontmatter (new pages only)

npm run docs completed with 0 Fern errors and 2 non-blocking warnings.

---

Signed-off-by: Julie Yaunches jyaunches@nvidia.com

Summary by CodeRabbit

• New Features

  • Agent timeout settings now apply consistently to both agent runs and provider requests.
  • Generated configurations automatically include the configured provider request timeout.

• Documentation

  • Clarified timeout behavior across setup instructions, command references, and build-time configuration guidance.

• Tests

  • Added coverage confirming that the configured timeout is propagated to both agent and provider timeout settings.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 94be8d7f-1382-4faf-a035-da9a80d2177d

📥 Commits

Reviewing files that changed from the base of the PR and between 5429cec and ac48733.

📒 Files selected for processing (6)

• Dockerfile
• docs/inference/configure-inference-timeouts.mdx
• docs/reference/commands.mdx
• scripts/generate-openclaw-config.mts
• src/lib/onboard/dockerfile-patch.ts
• test/generate-openclaw-config.test.ts

🚧 Files skipped from review as they are similar to previous changes (6)

• docs/reference/commands.mdx
• scripts/generate-openclaw-config.mts
• src/lib/onboard/dockerfile-patch.ts
• docs/inference/configure-inference-timeouts.mdx
• Dockerfile
• test/generate-openclaw-config.test.ts

---

📝 Walkthrough

Walkthrough

NEMOCLAW_AGENT_TIMEOUT now configures both the default agent timeout and the selected provider timeout. The generator, test, Dockerfile comments, and documentation reflect this behavior.

Changes

Agent timeout propagation

Layer / File(s)	Summary
Provider timeout configuration and validation scripts/generate-openclaw-config.mts, test/generate-openclaw-config.test.ts	The generator writes agentTimeout to the provider’s timeoutSeconds. The test verifies both agent-default and provider timeout fields.
Timeout behavior documentation Dockerfile, src/lib/onboard/dockerfile-patch.ts, docs/inference/configure-inference-timeouts.mdx, docs/reference/commands.mdx	Comments and documentation state that NEMOCLAW_AGENT_TIMEOUT applies to agent and provider request timeouts.

Estimated code review effort: 1 (Trivial) | ~5 minutes

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and concisely describes propagating the OpenClaw provider timeout, which is the main change in the pull request.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch codex/issue-8468-provider-timeout

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

🌿 Preview your docs: https://nvidia-preview-pr-8569.docs.buildwithfern.com/nemoclaw

[github-code-quality]

Code Coverage Overview

Languages: TypeScript

TypeScript / code-coverage/plugin

The overall coverage in commit 2c0eff9 in the codex/issue-8468-pro... branch remains at 96%, unchanged from commit 7d1c24e in the main branch.

TypeScript / code-coverage/cli

The overall coverage in commit 2c0eff9 in the codex/issue-8468-pro... branch remains at 81%, unchanged from commit 7d1c24e in the main branch.

---

_{Updated August 09, 2026 07:33 UTC}

[github-actions]

PR Review Advisor — No blocking findings reported

Advisor assessment: No blocking advisor findings reported
Next action: No advisor follow-up needed.
Findings: 0 blockers · 0 warnings · 0 suggestions

Model lanes

• GPT-5.6 Terra (primary): Completed · high confidence · 0 blockers · 0 warnings · 0 suggestions
• Nemotron 3 Ultra (second opinion): Completed · high confidence · 0 blockers · 0 warnings · 0 suggestions
• Model comparison: normalized findings match; normalized terminology decisions differ; normalized E2E selections differ; severity counts match.

2 additional E2E selections from the second opinion

Advisory only. The primary lane did not select these E2E jobs or targets.

• openclaw-inference-switch: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• inference-routing: The completed second-opinion lane identified E2E coverage that the primary lane omitted.

Second-opinion terminology and E2E selections are advisory. Live E2E does not run automatically for pull requests.

2 semantic terminology decisions

Terminology decisions are advisory. They affect the assessment only when a separate finding identifies concrete semantic impact.

• justified — provider-request at src/lib/onboard/dockerfile-patch.ts:394: Use provider-request when the provider-side timeout is distinguished from the agent-run timeout.
• established — provider-request at test/generate-openclaw-config.test.ts:763: Retain provider request for the request concept in the test title.

E2E guidance

Advisory only. A maintainer can dispatch the default E2E suite against this exact revision.

Recommended E2E: cloud-onboard, full-e2e, managed-image-multiarch-startup, onboard-repair, onboard-resume

Workflow run details

This automated review informs maintainers. Warnings and suggestions do not require a response. A maintainer decides whether to merge.

[coderabbitai]

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

[cv]

Reviewed all six changed files and relevant timeout-generation context. The change preserves the accepted #2281 build-time timeout contract, adds the pinned OpenClaw 2026.7.1 provider field correctly, retains positive-integer validation and sandbox config immutability, and documents both consumers. No competing PR, unresolved finding, compatibility blocker, security finding, or missing documentation impact was found. The PR is open, mergeable, current with main, and has no submitted maintainer review.