hotfix: Prefer NVIDIA NIM models in OpenCode review pool - #680
Conversation
OpenCode skipped usable reviews on fast-mlsirm PR #290+. Add an OpenAI-compatible nvidia-nim provider, prioritize Nemotron/Llama NIM candidates in OPENCODE_MODEL_CANDIDATES, skip when NVIDIA_API_KEY is unset, and document the temporary hotfix bypass (no permanent security gate weaken).
|
Warning Review limit reached
Next review available in: 29 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughOpenCode에 NVIDIA NIM 제공자와 모델을 추가했습니다. 워크플로가 ChangesNVIDIA NIM OpenCode 통합
Estimated code review effort: 3 (Moderate) | ~20 minutes Possibly related issues
Possibly related PRs
Sequence Diagram(s)sequenceDiagram
participant GitHubActions
participant ModelPool
participant NVIDIA_NIM
GitHubActions->>ModelPool: NVIDIA_API_KEY 및 모델 후보 전달
ModelPool->>ModelPool: NVIDIA NIM 후보 확인
alt 키가 설정됨
ModelPool->>NVIDIA_NIM: 선택한 모델로 OpenCode 검토 실행
NVIDIA_NIM-->>ModelPool: 검토 결과 반환
else 키가 설정되지 않음
ModelPool->>ModelPool: NVIDIA NIM 후보 건너뛰기
end
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 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 @.github/workflows/opencode-review-dispatch.yml:
- Line 3962: Update the Prepare isolated OpenCode review workspace step so its
generated opencode.jsonc reuses the canonical nvidia-nim provider definition and
includes all six configured NIM models in enabled_providers. Add a fast
validation gate that fails when the generated configuration lacks nvidia-nim,
and avoid maintaining a separate provider definition in the workflow.
In `@opencode.jsonc`:
- Around line 3-4: Update the default-model assertions in
test_strix_quick_gate.sh to expect the NVIDIA NIM values configured by the model
and small_model settings in opencode.jsonc, replacing the previous github-models
expectations. Run bash scripts/ci/test_strix_quick_gate.sh to verify the quick
gate passes.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 6e7fb3de-5969-4506-a7d4-ac30775e08a8
📒 Files selected for processing (5)
.github/workflows/opencode-review-dispatch.ymldocs/nvidia-nim-opencode-hotfix.mdopencode.jsoncscripts/ci/run_opencode_review_model_pool.shscripts/ci/test_strix_quick_gate.sh
Hotfix landing noteOpenCode failed to produce a usable review on ContextualWisdomLab/fast-mlsirm#290 ( Authorized temporary bypass: merge-aid for this hotfix only. Does not weaken Security Scan / trivy / osv. Org secret required after merge: |
Include the NIM provider in the generated isolated opencode.jsonc used by the model pool (not only OPENCODE_MODEL_CANDIDATES), prefer NIM defaults, fail fast if the generated config lacks NIM, and update quick-gate asserts.
1 participant
Summary
opencode-reviewskipped; no opencode-agent review body).https://integrate.api.nvidia.com/v1,NVIDIA_API_KEY).OPENCODE_MODEL_CANDIDATES.nvidia-nim/*whenNVIDIA_API_KEYis unset (same pattern as OpenRouter).Test plan
opencode.jsoncbrace-balanced; candidates string includesnvidia-nim/...is_nvidia_nim_candidate+ NVIDIA skip pathNVIDIA_API_KEYconfigured on ContextualWisdomLabHotfix note
Temporary permission bypass authorized for landing this central-repo recovery; permanent gate weaken is out of scope.
Summary by CodeRabbit
새 기능
문서
개선 사항