Repository navigation
feat(vscode-lm): port six Copilot model entries - #2032
Conversation
Port simurg79/Roo-Code#13 at 922db52fdf24fd102fbf4056f33b0136b60ea0ee without its version bump or PR Zoo-Code-Org#14 changes. Preserve advertised unverified Opus 5 and Gemini 3.6 Flash limits and cover exact rows, ordering, and exclusions.
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info
📜 Recent review details
📝 Summary
Merge Risk: ⚪ Minimal · up to The catalog additions have focused coverage, and no concrete user-facing risk is identified. The change appears ready for normal merge checks. Pre-merge checks ·
  |
| Check name | Status | Explanation | Resolution |
|---|---|---|---|
| Description check |  |
The description explains the implementation and validation steps, but it does not satisfy the required issue-link section or complete the template checklist. It explicitly states that no approved Zoo … | Link this PR to an approved Zoo Code GitHub issue by replacing the placeholder with Closes: #<issue-number>. Complete the required template sections and checklist, including the test procedure and contribution-guidelines confirmation. |
-
Check name Status Explanation Linked Issues check Check skipped because no linked issues were found for this pull request. Out of Scope Changes check Check skipped because no linked issues were found for this pull request. Regression Evidence The PR changes only the VS Code LM catalog and its focused unit test. The new test asserts the complete metadata object and token limits for all six added rows, verifies each required ordering group, … Security Boundaries No changed path meets a security failure condition. packages/types/src/providers/vscode-llm.tsadds only static model identifiers and numeric metadata. `packages/types/src/tests/vscode-llm.spec.…Persistence Integrity The pull request changes only a static VS Code LM catalog and its tests. The catalog adds in-memory metadata rows; it does not perform persistence, file writes, asynchronous operations, rollback, or p… Lifecycle Resource Cleanup PASS. The pull request changes only static VS Code model metadata and unit tests. The changed code adds object-literal entries and assertions; it does not add listeners, watchers, timers, tasks, provi… Title check The title clearly summarizes the main change: adding six VS Code LM Copilot model entries.
Full details: Description check
-
Explanation
The description explains the implementation and validation steps, but it does not satisfy the required issue-link section or complete the template checklist. It explicitly states that no approved Zoo Code issue was supplied.
- Fix all pre-merge checks with AI
✨ Finishing Touches
-
🧪 Generate unit tests (beta)
-
- Create a new PR
-
- Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
Comment @coderabbitai help to get the list of available commands.
Review statusThanks for contributing. This comment tracks the review sequence and the next action. Current step: Awaiting fresh human maintainer or CODEOWNER approval. Automated review is complete for the latest commit but does not replace human approval. Review-state labels are managed by this workflow; do not edit them manually. |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
github-actions
Bot
added
coderabbit-review-active
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
github-actions
Bot
added
awaiting-maintainer
edelauna
left a comment
edelauna
left a comment
There was a problem hiding this comment.
approving - with a comment if you wanted to update in a future PR
| version: "claude-opus-5", | ||
| name: "Claude Opus 5", | ||
| supportsToolCalling: true, | ||
| maxInputTokens: 935793, |
There was a problem hiding this comment.
maxInputTokens here (and for gemini-3.6-flash at line 250) comes from the advertised picker cache and is marked unverified in the header. Since the condense gate reads this field, would a too-high ceiling mean we never condense before the API rejects the request? Is it worth verifying these two with the same binary search used for sonnet-5 and gpt-5.6, or keeping them lower until measured?
2 participants
Summary
Port simurg79/Roo-Code#13 into Zoo Code from upstream head
922db52fdf24fd102fbf4056f33b0136b60ea0ee.mainat839fd6c03, not on the previous streaming feature branch.This expands model coverage while retaining the existing default and model-limit semantics.
I have used this code for multiple months without any hiccup. I will have more PRs coming in to add newer model support for vscode-lm.
Validation
Rerun in the isolated publication worktree:
pnpm --dir packages/types exec vitest run src/__tests__/vscode-llm.spec.ts— 15 tests passed.pnpm --dir packages/types check-types— passed.pnpm --dir packages/types exec eslint --max-warnings=0 src/providers/vscode-llm.ts src/__tests__/vscode-llm.spec.ts— passed; suppression pruning also found no suppressions.git diff --checkand staged diff check — passed.Validation reused the existing Windows dependency installation (Vitest reported 4.1.9; the package manifest declares 4.1.11), rather than performing a fresh lockfile installation. The prior implementation was independently reviewed, per the publication handoff. Publication and verification were AI-assisted.
Related issue and documentation
No approved Zoo Code issue was supplied or identified for this exact port; the source PR is linked above. No issue is claimed closed by this PR.
No separate documentation or visual snapshot changes: this is a catalog-data and regression-test port, with the limit provenance recorded beside the catalog.