docs: update v0.0.104 release notes

[cjagwani]

Summary

Updates the canonical v0.0.104 changelog after the experimental managed llama.cpp activation merged while the original release-prep PR was awaiting merge.
The entry keeps the option explicitly experimental and does not claim a supported agent, model, and runtime tuple.

Changes

• #8448 -> docs/changelog/2026-08-06.mdx: record the experimental managed llama.cpp option for DGX Spark, exact GGUF verification, authenticated loopback runtime, and receipt-backed lifecycle.
• #8509 remains excluded because it hardens the hidden experimental portable-profile path rather than adding a release-ready public surface.

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: npx vitest run test/changelog-docs.test.ts passed 6/6 and validates the changelog structure and published links.
• 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/changelog/2026-08-06.mdx; post-prep merge scope, Product Scope Gate wording, experimental status, exact lifecycle claims, links, style, and skip terms reviewed; changelog tests and docs build passed.
• Agent: Codex Desktop

DGX Station Hardware Evidence

• Tested on DGX Station
• Tested commit: Not applicable; no DGX Station host preparation script changed.
• Station profile/scenario: Not applicable.
• Result: Not applicable.
• Supporting evidence: Not applicable.

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 — command/result or justification: npx vitest run test/changelog-docs.test.ts passed 6/6.
• Applicable broad gate passed — npm test for broad runtime/test-harness changes; npm run check for repo-wide validation/coverage changes — command/result: Not applicable to a one-file changelog correction.
• 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)

No new page is added; the existing dated changelog keeps its required parser-safe MDX SPDX header.

---

Signed-off-by: Charan Jagwani cjagwani@nvidia.com

Summary by CodeRabbit

• New Features

  • Added an experimental managed llama.cpp option for DGX Spark using a verified Nemotron model.
  • Added authenticated local runtime support with lifecycle status tracking.
  • Added a Personal network policy tier and support for trusted private endpoints.
  • Added MCP timeout and diagnostics controls.

• Bug Fixes

  • Improved gateway, rebuild, registry, and recovery behavior.
  • Made uninstall safer and strengthened credential isolation.

• Documentation

  • Added installation guidance and documented configuration and state-management behavior.

[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: 80ec366e-2424-43b6-968f-38c5aaf6c531

📥 Commits

Reviewing files that changed from the base of the PR and between 43851b4 and 6bf1509.

📒 Files selected for processing (1)

• docs/changelog/2026-08-06.mdx

---

📝 Walkthrough

Walkthrough

The v0.0.104 changelog entry now documents the experimental DGX Spark managed llama.cpp workflow and related runtime, lifecycle, recovery, configuration, and installation guidance.

Changes

Release documentation

Layer / File(s)	Summary
Managed llama.cpp release entry docs/changelog/2026-08-06.mdx	The changelog documents verified GGUF acquisition, authenticated loopback runtime publication, lifecycle state handling, qualification and activation gates, and related documentation links.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

• NVIDIA/NemoClaw#8510: Both PRs update the v0.0.104 changelog entry.

Suggested reviewers: aasthajh

🚥 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 accurately identifies the documentation change to the v0.0.104 release notes.
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 unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch codex/release-prep-v0.0.104-followup

---

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

[github-actions]

🌿 Preview your docs: https://nvidia-preview-pr-8511.docs.buildwithfern.com/nemoclaw

[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): Failed after a partial review · low confidence · 0 blockers · 0 warnings · 0 suggestions

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

3 semantic terminology decisions

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

• established — managed llama.cpp at docs/changelog/2026-08-06.mdx:8: Keep the established term.
• established — repository-owned at docs/changelog/2026-08-06.mdx:12: Keep the established modifier.
• established — protected qualification and activation gates at docs/changelog/2026-08-06.mdx:14: Keep the established term.

E2E guidance

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

Recommended E2E: None

Workflow run details

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