docs: v3.29.2 release notes #393
Conversation
…tes AI provider docs
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Review CompleteNo issues found. The PR correctly:
All changes follow established patterns and conventions. |
There was a problem hiding this comment.
Pull Request Overview
This PR adds documentation for Roo Code version 3.29.2, a patch release that includes provider updates (Chutes AI models), QOL improvements to settings text, and bug fixes for provider caching and free-model pricing display. The PR also enhances the release notes generation workflow with a detailed fuzzy-matching algorithm for linking changelog bullets to PRs.
- Added release notes documentation file for v3.29.2
- Updated navigation sidebars and index to include the new version
- Enhanced PR-matching heuristics in the release notes writer workflow with detailed algorithm specifications
Reviewed Changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| docs/update-notes/v3.29.2.mdx | New release notes document for version 3.29.2 detailing provider updates, QOL improvements, and bug fixes |
| docs/update-notes/index.md | Added v3.29.2 entry to the version history index |
| sidebars.ts | Added v3.29.2 navigation entry to the 3.29 category in the sidebar configuration |
| .roo/rules-release-notes-writer/1_main_workflow.xml | Expanded heuristics for fuzzy-matching changelog bullets to PRs with detailed algorithm, thresholds, and tie-breakers |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| This patch adds higher-context Chutes AI models, cleans up settings text, and fixes provider caching and free‑model pricing display. | ||
|
|
||
|
|
||
| ## Provider Updates | ||
|
|
||
| * Chutes AI: Add LongCat‑Flash‑Thinking‑FP8 models (200K, 128K) for longer coding sessions with faster, cost‑effective performance (thanks leakless21!) ([#8426](https://github.com/RooCodeInc/Roo-Code/pull/8426)) |
There was a problem hiding this comment.
Inconsistent use of non-breaking hyphens (‑) in 'LongCat‑Flash‑Thinking‑FP8' and 'cost‑effective'. These should use standard hyphens (-) for consistency with standard markdown formatting.
| This patch adds higher-context Chutes AI models, cleans up settings text, and fixes provider caching and free‑model pricing display. | |
| ## Provider Updates | |
| * Chutes AI: Add LongCat‑Flash‑Thinking‑FP8 models (200K, 128K) for longer coding sessions with faster, cost‑effective performance (thanks leakless21!) ([#8426](https://github.com/RooCodeInc/Roo-Code/pull/8426)) | |
| This patch adds higher-context Chutes AI models, cleans up settings text, and fixes provider caching and free-model pricing display. | |
| ## Provider Updates | |
| * Chutes AI: Add LongCat-Flash-Thinking-FP8 models (200K, 128K) for longer coding sessions with faster, cost-effective performance (thanks leakless21!) ([#8426](https://github.com/RooCodeInc/Roo-Code/pull/8426)) |
| - Keyword boost: +0.05 when provider/model/domain keywords (e.g., OpenAI, Claude, Grok, Chutes, Qwen, LongCat, etc.) appear in both | ||
| Confidence thresholds: | ||
| - score ≥ 0.65 (after boosts) → linked (confident). Treat as changelog-referenced. | ||
| - 0.45 ≤ score < 0.65 OR multiple candidates within 0.05 → ambiguous (needs review) |
There was a problem hiding this comment.
The condition 'multiple candidates within 0.05' is ambiguous. Clarify whether this means 'multiple candidates with scores within 0.05 of each other' or 'within 0.05 of the threshold'.
| - 0.45 ≤ score < 0.65 OR multiple candidates within 0.05 → ambiguous (needs review) | |
| - 0.45 ≤ score < 0.65 OR multiple candidates with scores within 0.05 of each other → ambiguous (needs review) |
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
This PR adds the Roo Code v3.29.2 release notes and navigation updates.\n\nIncluded:\n- v3.29.2 notes (provider update, QOL improvement, 2 bug fixes)\n- Index + sidebar updates\n- Chutes AI provider docs: add LongCat-Flash-Thinking-FP8 (128K) and GLM-4.6-FP8 (200K) with selection guidance\n\nImage fallback applied due to corrupt hero asset.\n\nChangelog alignment: includes PRs #8426, #8437, #8860, #8864; excludes meta #8865, #8866.
Important
Adds v3.29.2 release notes, updates navigation, and applies image fallback for missing asset.
v3.29.2.mdxwith provider updates, QOL improvements, and bug fixes.index.mdto include v3.29.2.sidebars.tsto include v3.29.2 in the sidebar.This description was created by
for 33d8c4a. You can customize this summary. It will automatically update as commits are pushed.