Skip to content

fix: remove broken qwen endpoint picker entry#1269

Merged
ericksoa merged 7 commits intomainfrom
fix/remove-broken-qwen-endpoint-model
Apr 2, 2026
Merged

fix: remove broken qwen endpoint picker entry#1269
ericksoa merged 7 commits intomainfrom
fix/remove-broken-qwen-endpoint-model

Conversation

@kjw3
Copy link
Copy Markdown
Contributor

@kjw3 kjw3 commented Apr 1, 2026

Summary

  • remove Qwen3.5 397B A17B from the curated NVIDIA Endpoints cloud model picker
  • keep the rest of the routed inference model handling unchanged

Why

QA has been using Qwen3.5 397B A17B as the default validation target for NVIDIA Endpoints onboarding, but the endpoint team has confirmed that this model is currently not working.

This PR does not claim that the rest of the NVIDIA Endpoints catalog is broken. It only removes the specific known-bad curated picker entry so onboarding defaults and manual QA runs stop selecting it from the built-in list.

Related #1161

Validation

npx vitest run test/inference-config.test.js
npx eslint bin/lib/inference-config.js test/inference-config.test.js
npx tsc -p jsconfig.json --noEmit

Signed-off-by: Kevin Jones kejones@nvidia.com

Summary by CodeRabbit

  • Bug Fixes
    • Removed Qwen3.5 397B A17B model from available cloud model options.

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented Apr 1, 2026

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: b24b5877-252c-4b24-933e-842132488a2e

📥 Commits

Reviewing files that changed from the base of the PR and between 7ff2718 and 4532ec0.

📒 Files selected for processing (2)
  • src/lib/inference-config.test.ts
  • src/lib/inference-config.ts
💤 Files with no reviewable changes (2)
  • src/lib/inference-config.ts
  • src/lib/inference-config.test.ts

📝 Walkthrough

Walkthrough

A Qwen model option (qwen/qwen3.5-397b-a17b) was removed from the CLOUD_MODEL_OPTIONS configuration array, with corresponding test expectations updated to reflect this removal.

Changes

Cohort / File(s) Summary
Model Configuration Cleanup
src/lib/inference-config.ts, src/lib/inference-config.test.ts
Removed the qwen/qwen3.5-397b-a17b model entry from the CLOUD_MODEL_OPTIONS array and updated test expectations accordingly.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Poem

Hop, hop—a model bids farewell,
Qwen3.5 leaves with a gentle spell,
Config and tests now align so clean,
One option gone from the scene! 🐰✨

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately describes the main change: removing a broken Qwen model endpoint entry from the cloud model picker options.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ 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 fix/remove-broken-qwen-endpoint-model

Comment @coderabbitai help to get the list of available commands and usage tips.

@wscurran wscurran added status: triage For new items that haven't been reviewed yet. bug Something isn't working NemoClaw CLI Use this label to identify issues with the NemoClaw command-line interface (CLI). and removed status: triage For new items that haven't been reviewed yet. labels Apr 1, 2026
kjw3 and others added 5 commits April 1, 2026 19:45
The inference-config migration (#1265) moved the implementation to
src/lib/inference-config.ts. Resolve the merge conflict by keeping the
thin shim in bin/lib/ and applying the qwen removal to the new TS
source file.

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Copy link
Copy Markdown
Contributor

@ericksoa ericksoa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Resolved merge conflict with TS migration and applied qwen removal to the new source file.

@ericksoa ericksoa merged commit c3fd887 into main Apr 2, 2026
8 checks passed
@kjw3 kjw3 deleted the fix/remove-broken-qwen-endpoint-model branch April 2, 2026 00:44
laitingsheng pushed a commit that referenced this pull request Apr 2, 2026
## Summary
- remove `Qwen3.5 397B A17B` from the curated NVIDIA Endpoints cloud
model picker
- keep the rest of the routed inference model handling unchanged

## Why
QA has been using `Qwen3.5 397B A17B` as the default validation target
for NVIDIA Endpoints onboarding, but the endpoint team has confirmed
that this model is currently not working.

This PR does **not** claim that the rest of the NVIDIA Endpoints catalog
is broken. It only removes the specific known-bad curated picker entry
so onboarding defaults and manual QA runs stop selecting it from the
built-in list.

Related #1161

## Validation
```bash
npx vitest run test/inference-config.test.js
npx eslint bin/lib/inference-config.js test/inference-config.test.js
npx tsc -p jsconfig.json --noEmit
```

Signed-off-by: Kevin Jones <kejones@nvidia.com>


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Bug Fixes**
  * Removed Qwen3.5 397B A17B model from available cloud model options.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Co-authored-by: Aaron Erickson <aerickson@nvidia.com>
lakamsani pushed a commit to lakamsani/NemoClaw that referenced this pull request Apr 4, 2026
## Summary
- remove `Qwen3.5 397B A17B` from the curated NVIDIA Endpoints cloud
model picker
- keep the rest of the routed inference model handling unchanged

## Why
QA has been using `Qwen3.5 397B A17B` as the default validation target
for NVIDIA Endpoints onboarding, but the endpoint team has confirmed
that this model is currently not working.

This PR does **not** claim that the rest of the NVIDIA Endpoints catalog
is broken. It only removes the specific known-bad curated picker entry
so onboarding defaults and manual QA runs stop selecting it from the
built-in list.

Related NVIDIA#1161

## Validation
```bash
npx vitest run test/inference-config.test.js
npx eslint bin/lib/inference-config.js test/inference-config.test.js
npx tsc -p jsconfig.json --noEmit
```

Signed-off-by: Kevin Jones <kejones@nvidia.com>


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Bug Fixes**
  * Removed Qwen3.5 397B A17B model from available cloud model options.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Co-authored-by: Aaron Erickson <aerickson@nvidia.com>
gemini2026 pushed a commit to gemini2026/NemoClaw that referenced this pull request Apr 14, 2026
## Summary
- remove `Qwen3.5 397B A17B` from the curated NVIDIA Endpoints cloud
model picker
- keep the rest of the routed inference model handling unchanged

## Why
QA has been using `Qwen3.5 397B A17B` as the default validation target
for NVIDIA Endpoints onboarding, but the endpoint team has confirmed
that this model is currently not working.

This PR does **not** claim that the rest of the NVIDIA Endpoints catalog
is broken. It only removes the specific known-bad curated picker entry
so onboarding defaults and manual QA runs stop selecting it from the
built-in list.

Related NVIDIA#1161

## Validation
```bash
npx vitest run test/inference-config.test.js
npx eslint bin/lib/inference-config.js test/inference-config.test.js
npx tsc -p jsconfig.json --noEmit
```

Signed-off-by: Kevin Jones <kejones@nvidia.com>


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Bug Fixes**
  * Removed Qwen3.5 397B A17B model from available cloud model options.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Co-authored-by: Aaron Erickson <aerickson@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working NemoClaw CLI Use this label to identify issues with the NemoClaw command-line interface (CLI).

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants