fix(dcode): consume released Nemotron Ultra profile#6416
Merged
Conversation
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Contributor
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughAdds Nemotron Ultra patch and validation scripts, wires them into the image build and e2e checks, and updates Deep Agents Code to 0.1.34 with matching package paths, fixtures, docs, and version expectations. ChangesNemotron 3 Ultra profile backport
Deep Agents Code 0.1.34 upgrade
Estimated code review effort: 4 (Complex) | ~60 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
Code Coverage OverviewLanguages: TypeScript TypeScript / code-coverage/pluginThe overall coverage in the branch is 96%. Coverage data for the branch is not yet available. Show a code coverage summary of the most covered files.
TypeScript / code-coverage/cliThe overall coverage in the branch is 76%. Coverage data for the branch is not yet available. Show a code coverage summary of the most covered files.
Updated |
Contributor
|
🌿 Preview your docs: https://nvidia-preview-pr-6416.docs.buildwithfern.com/nemoclaw |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
![github-code-quality[bot]](https://avatars.githubusercontent.com/u/9919?s=60&v=4){kind=small}
Contributor
E2E Advisor RecommendationRequired E2E: Full advisor summaryE2E Recommendation AdvisorBase: Required E2E
Optional E2E
New E2E recommendations
|
Contributor
E2E Target RecommendationRequired E2E targets: Dispatch required E2E targets:
Full E2E target advisor summaryE2E Target AdvisorBase: Required E2E targets
Optional E2E targets
Relevant changed files
|
Contributor
PR Review Advisor — Changes requestedMerge posture: Do not merge yet Action checklist
Findings index
Review findings by urgency: 0 required fixes, 2 items to resolve/justify, 0 in-scope improvements
|
Contributor
PR Review Advisor (Nemotron Ultra) — Changes requestedMerge posture: Do not merge yet Action checklist
Findings index
🚨 Required before mergeAddress these before merging unless a maintainer explicitly overrides the advisor with rationale.
|
Contributor
E2E Target Results —
|
| Job | Result |
|---|---|
| live |
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Contributor
E2E Target Results —
|
| Job | Result |
|---|---|
| live |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (2)
agents/langchain-deepagents-code/validate-nemotron-ultra-profile.py (1)
52-57: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueUse direct attribute access instead of
getattrwith a constant name.Ruff (B009) flags this:
getattr(profile, "extra_middleware")is equivalent to and no safer thanprofile.extra_middleware.🧹 Suggested fix
def middleware_names(profile: object) -> tuple[str, ...]: - middleware = getattr(profile, "extra_middleware") + middleware = profile.extra_middleware if callable(middleware): </details> <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.In
@agents/langchain-deepagents-code/validate-nemotron-ultra-profile.pyaround
lines 52 - 57, The middleware_names helper is using getattr with a constant
attribute name, which Ruff flags as unnecessary. Update middleware_names to
access extra_middleware directly on the profile object instead of calling
getattr, while keeping the existing callable handling and tuple conversion logic
unchanged.</details> <!-- cr-comment:v1:367ce7f6ddd94b10915a06b8 --> _Source: Linters/SAST tools_ </blockquote></details> <details> <summary>test/e2e/support/platform-parity-cloud-experimental.test.ts (1)</summary><blockquote> `153-168`: _📐 Maintainability & Code Quality_ | _🔵 Trivial_ | _⚡ Quick win_ **Source-text assertions on shell/Python literals rather than observable behavior.** This test asserts on exact substrings of the embedded Python source (import lines, model-ID literals, variable names) instead of exercising the script's actual contract. It will break on harmless refactors of the check script (renames, reformatting, reordering) without any real regression, and it doesn't prove the profile contract holds at runtime — that verification only happens when the E2E check actually runs in a sandbox. Consider narrowing this to a lighter registration/ordering check (as in the `137-137` assertion) and letting the live E2E check own verification of the profile contract's actual behavior, rather than re-asserting its internals as text. Based on path instructions for `**/*.test.{ts,js,mts,mjs,cts,cjs}`: "Prefer observable outcomes through the public boundary over source-text, private-shape, or mock-call assertions." <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.In
@test/e2e/support/platform-parity-cloud-experimental.test.tsaround lines 153
- 168, The test in platform-parity-cloud-experimental.test.ts is asserting on
embedded shell/Python source text instead of observable behavior, making it
brittle to harmless refactors. Update the profile check around
DEEPAGENTS_CLOUD_EXPERIMENTAL_CHECKS[0] / profileCheck to only verify
registration or ordering at this boundary, and remove the exact substring checks
for imports, model IDs, variable names, and middleware internals; let the actual
E2E check script validate the runtime profile contract.</details> <!-- cr-comment:v1:761d44d205ca9aaddef97c14 --> _Source: Path instructions_ </blockquote></details> </blockquote></details> <details> <summary>🤖 Prompt for all review comments with AI agents</summary>Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.Nitpick comments:
In@agents/langchain-deepagents-code/validate-nemotron-ultra-profile.py:
- Around line 52-57: The middleware_names helper is using getattr with a
constant attribute name, which Ruff flags as unnecessary. Update
middleware_names to access extra_middleware directly on the profile object
instead of calling getattr, while keeping the existing callable handling and
tuple conversion logic unchanged.In
@test/e2e/support/platform-parity-cloud-experimental.test.ts:
- Around line 153-168: The test in platform-parity-cloud-experimental.test.ts is
asserting on embedded shell/Python source text instead of observable behavior,
making it brittle to harmless refactors. Update the profile check around
DEEPAGENTS_CLOUD_EXPERIMENTAL_CHECKS[0] / profileCheck to only verify
registration or ordering at this boundary, and remove the exact substring checks
for imports, model IDs, variable names, and middleware internals; let the actual
E2E check script validate the runtime profile contract.</details> --- <details> <summary>ℹ️ Review info</summary> <details> <summary>⚙️ Run configuration</summary> **Configuration used**: Path: .coderabbit.yaml **Review profile**: CHILL **Plan**: Enterprise **Run ID**: `b9c2e63c-ff77-403a-ba3e-b038d2c64950` </details> <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 5b8e437fdcb2685825b24e8ee3a8ee28850b2133 and 66c7895aa255119e7f00bafc22bfa42c25364166. </details> <details> <summary>📒 Files selected for processing (12)</summary> * `agents/langchain-deepagents-code/Dockerfile` * `agents/langchain-deepagents-code/LICENSE.langchain-deepagents` * `agents/langchain-deepagents-code/dependency-review.md` * `agents/langchain-deepagents-code/nemotron-ultra-harness-profile.py` * `agents/langchain-deepagents-code/patch-nemotron-ultra-profile.py` * `agents/langchain-deepagents-code/validate-nemotron-ultra-profile.py` * `docs/get-started/quickstart-langchain-deepagents-code.mdx` * `test/e2e/e2e-cloud-experimental/checks/03-deepagents-code-nemotron-ultra-profile.sh` * `test/e2e/live/cloud-experimental-check-list.ts` * `test/e2e/support/platform-parity-cloud-experimental.test.ts` * `test/langchain-deepagents-code-image.test.ts` * `test/langchain-deepagents-code-nemotron-profile-patch.test.ts` </details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
21 tasks
Contributor
E2E Target Results — ✅ All selected jobs passedRun: 28892803126
|
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Contributor
E2E Target Results — ✅ All selected jobs passedRun: 28893172137
|
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
ericksoa
added
integration: dcode
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
test/e2e/e2e-cloud-experimental/checks/10-deepagents-code-tui-startup.sh (1)
216-220: 🩺 Stability & Availability | 🔵 Trivial | 💤 Low value
elsepath sends/helpafter a fixedafter 1000with no readiness gate.The pending path deliberately waits for the name prompt before typing (per the comment at Lines 179-181, to avoid sending keystrokes while first paint is in flight). The complete path instead sends
/helpafter a fixed 1s. There's no name field to corrupt here, so worst case is/helptyped before the prompt has input focus, which surfaces later as a readiness timeout (exit 20) — a potential flake rather than a correctness bug. If the TUI exposes any stable "prompt ready" line on the complete path, gating on it (with a bounded timeout fallback) would be more robust than a fixed sleep.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@test/e2e/e2e-cloud-experimental/checks/10-deepagents-code-tui-startup.sh` around lines 216 - 220, The complete-path flow in 10-deepagents-code-tui-startup.sh is using a fixed sleep before sending /help, which can race with TUI readiness and cause flaky timeouts. Update the else branch around the existing after/send sequence to wait for a stable “prompt ready” signal from the TUI before typing, using the same style of readiness gating already used in the pending path, and keep a bounded fallback timeout so the test still fails deterministically if the prompt never appears.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@test/deepagents-code-tui-startup-check.test.ts`:
- Around line 217-237: The onboarding-predicate test is overfitting to copied
shell logic and source-text checks instead of verifying real behavior. Replace
the inline hand-rolled `case` snippet with the actual probe logic used by
`runTuiStartupCheckHelper` or sourced from the startup check script, and drive
it through observable outcomes rather than duplicating production mappings.
Remove the direct `tuiStartupCheckSource`/`tuiExpectProgram` string assertions
and validate the behavior via `runTuiExpectStateMachine` or equivalent
public-boundary checks in `deepagents-code-tui-startup-check.test.ts`.
---
Nitpick comments:
In `@test/e2e/e2e-cloud-experimental/checks/10-deepagents-code-tui-startup.sh`:
- Around line 216-220: The complete-path flow in
10-deepagents-code-tui-startup.sh is using a fixed sleep before sending /help,
which can race with TUI readiness and cause flaky timeouts. Update the else
branch around the existing after/send sequence to wait for a stable “prompt
ready” signal from the TUI before typing, using the same style of readiness
gating already used in the pending path, and keep a bounded fallback timeout so
the test still fails deterministically if the prompt never appears.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 31d5e173-7791-434c-a7f2-40edec0e9d91
📒 Files selected for processing (2)
test/deepagents-code-tui-startup-check.test.tstest/e2e/e2e-cloud-experimental/checks/10-deepagents-code-tui-startup.sh
Contributor
E2E Target Results — ❌ Some jobs failedRun: 28906215693
|
Collaborator
|
Diagnosis from the failed typed-target artifact in run 28906215693: the Enter submission does leave the optional-name screen and reach the main composer. The sanitized capture then shows Use an exact known command as the stable readiness probe instead: submit |
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Collaborator
|
Correction after checking the pinned 0.1.34 wheel: The deterministic live probe is therefore to send the exact |
Contributor
E2E Target Results —
|
| Job | Result |
|---|---|
| live |
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Contributor
E2E Target Results —
|
| Job | Result |
|---|---|
| live |
Contributor
E2E Target Results — ✅ All selected jobs passedRun: 28906853666
|
Contributor
E2E Target Results —
|
| Job | Result |
|---|---|
| mcp-bridge |
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Contributor
E2E Target Results — ❌ Some jobs failedRun: 28907098766
|
Contributor
E2E Target Results — ✅ All selected jobs passedRun: 28907500822
|
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Collaborator
|
Maintainer disposition for exact head This clears the remaining advisor-required accountability item; approval still waits on final-head CI and the required live E2E evidence. |
Contributor
E2E Target Results — ✅ All selected jobs passedRun: 28907835011
|
Collaborator
|
Maintainer disposition for the remaining trusted-apt warning on exact head The suggested extra rationale-marker regression is therefore not required for this release; the existing workflow-boundary tests cover the security-relevant executable contract. |
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Contributor
E2E Target Results — ✅ All selected jobs passedRun: 28908698325
|
cv
approved these changes
Jul 8, 2026
Collaborator
|
Blocker resolution summary:
Local conflict-sensitive verification also passed (161 tests passed, 1 platform-only skip), along with |
This was referenced Jul 8, 2026
21 tasks
apurvvkumaria
added a commit
that referenced
this pull request
Jul 8, 2026
<!-- markdownlint-disable MD041 --> ## Summary Prepares the user-facing documentation for NemoClaw v0.0.76 and closes the release-prep documentation gate. It adds the release highlights, documents the arm64 Local NIM warning and expanded image cleanup behavior, and fixes agent-specific command headings in generated guides. ## Changes - Add the v0.0.76 release-notes section and move the shared-gateway route containment entry out of the v0.0.74 history where it was incorrectly placed. - Document the advisory Linux arm64 Local NIM manifest warning in the canonical platform matrix and local-inference guidance. - Document that `gc` scans both gateway-built and locally prebuilt sandbox image repositories. - Keep OpenClaw and Hermes session headings out of the generated Deep Agents command guide. - Add a focused variant regression test for the agent-specific session headings. ### Source summary | Merged sources | Documentation coverage | | --- | --- | | [#6414](#6414), [#6418](#6418), [#6416](#6416), [#6344](#6344) | v0.0.76 release notes and the Deep Agents quickstart/inference routes | | [#6340](#6340) | v0.0.76 release notes and existing Deep Agents observability guidance | | [#6338](#6338), [#6378](#6378), [#6297](#6297) | v0.0.76 release notes and existing inference/troubleshooting guidance | | [#6362](#6362) | v0.0.76 release notes and existing lifecycle, command, and credential guidance | | [#6330](#6330), [#6307](#6307), [#6008](#6008) | v0.0.76 release notes and existing security, troubleshooting, and command guidance | | [#6382](#6382) | v0.0.76 release notes and existing MCP/command guidance | | [#6326](#6326), [#5868](#5868), [#5539](#5539) | v0.0.76 release notes, platform matrix, inference options, and local-inference guidance | | [#6396](#6396), [#6390](#6390), [#6007](#6007) | v0.0.76 release notes and existing messaging guidance | | [#5388](#5388), [#6249](#6249), [#6303](#6303), [#6306](#6306) | v0.0.76 release notes and command/lifecycle guidance | ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [x] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Quality Gates - [x] Tests added or updated for changed behavior - [ ] Existing tests cover changed behavior — justification: - [ ] Tests not applicable — justification: - [x] 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: ## Verification - [x] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or `npm run check:diff` passed when hooks were skipped or unavailable - [x] Targeted behavior tests pass for the current change set, or tests are marked not applicable above — `npx vitest run --project integration test/generate-platform-docs.test.ts test/agent-variant-docs.test.ts test/sync-agent-variant-docs.test.ts` (3 files, 29 tests passed) - [ ] Applicable broad gate passed — `npm test` for broad runtime/test-harness changes; `npm run check` for repo-wide validation/coverage changes — command/result: - [x] Quality Gates section completed with required justifications or waivers - [x] No secrets, API keys, or credentials committed - [ ] `npm run docs` builds without warnings (doc changes only) — completed with 0 errors and 2 pre-existing Fern warnings - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) --- Signed-off-by: Apurv Kumaria <akumaria@nvidia.com> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Documentation** * Added v0.0.76 release notes content, and removed an older conflicting bullet from the surrounding release history. * Expanded Local NVIDIA NIM guidance across inference/provider docs, including an advisory for Linux arm64 DGX Spark/DGX Station hosts when a matching `linux/arm64` image manifest is unavailable. * Updated the command reference for correct session-section rendering and clarified `gc` image cleanup sources. * **Tests** * Added coverage ensuring Deep Agents omits sessions headings while Hermes includes them. * **CI** * Refreshed Local NVIDIA NIM provider notes used in the platform matrix. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Apurv Kumaria <akumaria@nvidia.com>
21 tasks
Hadar301
pushed a commit
to Hadar301/NemoClaw-OpenShift
that referenced
this pull request
Jul 12, 2026
## Summary Consume the official Nemotron 3 Ultra profile from `deepagents-code[nvidia]==0.1.34`, which pins `deepagents==0.7.0a6`. This keeps the managed model IDs and public behavior unchanged while preserving the optional first-run name prompt and suppressed dependency/model pickers from NVIDIA#6410 and NVIDIA#6418. ## Changes - Pin `deepagents-code[nvidia]==0.1.34` and `deepagents==0.7.0a6`; regenerate the hash-locked dependency set with only `langchain-google-genai` moving from `4.2.6` to `4.2.7`. - Remove the temporary profile source and license wiring, then retain an atomic, idempotent, fail-closed alias bridge for `openai:nvidia/nemotron-3-ultra-550b-a55b` and `openai:nvidia/nvidia/nemotron-3-ultra`. - Bind removal of that bridge to its exact DCode/Deep Agents version-and-hash gate in `dependency-review.md`; this PR intentionally does not create a separate follow-up issue. - Port the managed DCode hardening patch to the `0.1.34` package layout and direct-return MCP loader while preserving JSON diagnostics and the NVIDIA#6418 launch overrides. - Validate the official wheels, all 12 native middleware entries, unrelated-model isolation, complete graph compilation, and equivalent single-dispatch behavior for parser-repaired and native `execute` calls. - Update the DCode documentation and cloud acceptance checks for the released versions, native profile, TUI startup behavior, and direct/login-shell inference. ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [x] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Quality Gates - [x] Tests added or updated for changed behavior - [ ] Existing tests cover changed behavior — justification: - [ ] Tests not applicable — justification: - [x] Docs updated for user-facing behavior changes - [ ] Docs not applicable — justification: - [x] Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging) - [x] Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification: [cv's deterministic TUI contract](NVIDIA#6416 (comment)) is implemented and passed exact-head server acceptance; cv also [waived a separate bridge-removal issue](NVIDIA#6416 (comment)) and [accepted the trusted-apt warning as nonblocking](NVIDIA#6416 (comment)) - [ ] Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue: ## Verification - [x] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or `npm run check:diff` passed when hooks were skipped or unavailable — normal hooks and `npm run check:diff` passed - [x] Targeted behavior tests pass for the current change set, or tests are marked not applicable above — official-wheel hash-locked validators passed; profile patch 12/12, direct module 34 passed/1 Linux-only skip, progressive disclosure 13/13, image 75/75, TUI 19/19, independent DCode image/TUI 94/94, platform parity 10/10, managed entrypoints 24/24, workflow boundary 39/39, and updated CLI/onboarding fixtures passed; repository checks, typecheck, test-size, and `pip-audit` passed - [x] Applicable broad gate passed — `npm test` for broad runtime/test-harness changes; `npm run check` for repo-wide validation/coverage changes — all exact-head Linux CI and [`ubuntu-repo-cloud-langchain-deepagents-code`](https://github.com/NVIDIA/NemoClaw/actions/runs/28907835011) passed for `928b50626b303b2008d35f844408a1f83a43a404` - [x] Quality Gates section completed with required justifications or waivers — 42 applicable exact-head checks passed; cv recorded the two advisor dispositions linked above - [x] No secrets, API keys, or credentials committed - [ ] `npm run docs` builds without warnings (doc changes only) — passed with 0 errors and 2 existing repository warnings - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only); `npm run docs:sync-agent-variants` passed - [ ] New doc pages include SPDX header and frontmatter (new pages only) --- Signed-off-by: Aaron Erickson <aerickson@nvidia.com> --------- Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Hadar301
pushed a commit
to Hadar301/NemoClaw-OpenShift
that referenced
this pull request
Jul 12, 2026
<!-- markdownlint-disable MD041 --> ## Summary Prepares the user-facing documentation for NemoClaw v0.0.76 and closes the release-prep documentation gate. It adds the release highlights, documents the arm64 Local NIM warning and expanded image cleanup behavior, and fixes agent-specific command headings in generated guides. ## Changes - Add the v0.0.76 release-notes section and move the shared-gateway route containment entry out of the v0.0.74 history where it was incorrectly placed. - Document the advisory Linux arm64 Local NIM manifest warning in the canonical platform matrix and local-inference guidance. - Document that `gc` scans both gateway-built and locally prebuilt sandbox image repositories. - Keep OpenClaw and Hermes session headings out of the generated Deep Agents command guide. - Add a focused variant regression test for the agent-specific session headings. ### Source summary | Merged sources | Documentation coverage | | --- | --- | | [NVIDIA#6414](NVIDIA#6414), [NVIDIA#6418](NVIDIA#6418), [NVIDIA#6416](NVIDIA#6416), [NVIDIA#6344](NVIDIA#6344) | v0.0.76 release notes and the Deep Agents quickstart/inference routes | | [NVIDIA#6340](NVIDIA#6340) | v0.0.76 release notes and existing Deep Agents observability guidance | | [NVIDIA#6338](NVIDIA#6338), [NVIDIA#6378](NVIDIA#6378), [NVIDIA#6297](NVIDIA#6297) | v0.0.76 release notes and existing inference/troubleshooting guidance | | [NVIDIA#6362](NVIDIA#6362) | v0.0.76 release notes and existing lifecycle, command, and credential guidance | | [NVIDIA#6330](NVIDIA#6330), [NVIDIA#6307](NVIDIA#6307), [NVIDIA#6008](NVIDIA#6008) | v0.0.76 release notes and existing security, troubleshooting, and command guidance | | [NVIDIA#6382](NVIDIA#6382) | v0.0.76 release notes and existing MCP/command guidance | | [NVIDIA#6326](NVIDIA#6326), [NVIDIA#5868](NVIDIA#5868), [NVIDIA#5539](NVIDIA#5539) | v0.0.76 release notes, platform matrix, inference options, and local-inference guidance | | [NVIDIA#6396](NVIDIA#6396), [NVIDIA#6390](NVIDIA#6390), [NVIDIA#6007](NVIDIA#6007) | v0.0.76 release notes and existing messaging guidance | | [NVIDIA#5388](NVIDIA#5388), [NVIDIA#6249](NVIDIA#6249), [NVIDIA#6303](NVIDIA#6303), [NVIDIA#6306](NVIDIA#6306) | v0.0.76 release notes and command/lifecycle guidance | ## Type of Change - [ ] Code change (feature, bug fix, or refactor) - [x] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Quality Gates - [x] Tests added or updated for changed behavior - [ ] Existing tests cover changed behavior — justification: - [ ] Tests not applicable — justification: - [x] 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: ## Verification - [x] PR description includes the DCO sign-off declaration and every commit appears as `Verified` in GitHub - [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or `npm run check:diff` passed when hooks were skipped or unavailable - [x] Targeted behavior tests pass for the current change set, or tests are marked not applicable above — `npx vitest run --project integration test/generate-platform-docs.test.ts test/agent-variant-docs.test.ts test/sync-agent-variant-docs.test.ts` (3 files, 29 tests passed) - [ ] Applicable broad gate passed — `npm test` for broad runtime/test-harness changes; `npm run check` for repo-wide validation/coverage changes — command/result: - [x] Quality Gates section completed with required justifications or waivers - [x] No secrets, API keys, or credentials committed - [ ] `npm run docs` builds without warnings (doc changes only) — completed with 0 errors and 2 pre-existing Fern warnings - [x] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) --- Signed-off-by: Apurv Kumaria <akumaria@nvidia.com> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Documentation** * Added v0.0.76 release notes content, and removed an older conflicting bullet from the surrounding release history. * Expanded Local NVIDIA NIM guidance across inference/provider docs, including an advisory for Linux arm64 DGX Spark/DGX Station hosts when a matching `linux/arm64` image manifest is unavailable. * Updated the command reference for correct session-section rendering and clarified `gc` image cleanup sources. * **Tests** * Added coverage ensuring Deep Agents omits sessions headings while Hermes includes them. * **CI** * Refreshed Local NVIDIA NIM provider notes used in the platform matrix. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Apurv Kumaria <akumaria@nvidia.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Consume the official Nemotron 3 Ultra profile from
deepagents-code[nvidia]==0.1.34, which pinsdeepagents==0.7.0a6. This keeps the managed model IDs and public behavior unchanged while preserving the optional first-run name prompt and suppressed dependency/model pickers from #6410 and #6418.Changes
deepagents-code[nvidia]==0.1.34anddeepagents==0.7.0a6; regenerate the hash-locked dependency set with onlylangchain-google-genaimoving from4.2.6to4.2.7.openai:nvidia/nemotron-3-ultra-550b-a55bandopenai:nvidia/nvidia/nemotron-3-ultra.dependency-review.md; this PR intentionally does not create a separate follow-up issue.0.1.34package layout and direct-return MCP loader while preserving JSON diagnostics and the fix(dcode): allow first-run name prompt while suppressing model picker #6418 launch overrides.main's backend-neutral Relay observability middleware and validation while composing it with the released DCode layout and Ultra profile.executecalls.Type of Change
Quality Gates
mainmergeVerification
Verifiedin GitHubpre-commit,commit-msg, andpre-pushhooks passed, ornpm run check:diffpassed when hooks were skipped or unavailable — normal hooks andnpm run check:diffpassedpip-auditpassednpm testfor broad runtime/test-harness changes;npm run checkfor repo-wide validation/coverage changes — all exact-head Linux CI andubuntu-repo-cloud-langchain-deepagents-codepassed for439ffb41271a7d73d7299991a381f45fa94454f8; server checks passed Ultra 1/1, inference 10/10, TUI 4/4, and OTLP observability/containment 11/11npm run docsbuilds without warnings (doc changes only) — passed with 0 errors and 2 existing repository warningsnpm run docs:sync-agent-variantspassedSigned-off-by: Aaron Erickson aerickson@nvidia.com