Repository navigation
feat: default MiniMax requests to M3.1 Flash - #818
octo-patch wants to merge 2 commits into
Conversation
- Set MiniMax-M3 as default in src/config.ts and src/providers/index.ts - Update onboarding label to MiniMax-M3 - Update .env.example sample to MINIMAX_MODEL=MiniMax-M3 - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as supported alternatives - Refresh provider docstring to describe M3 support (up to 128K output) - Update unit tests to use MiniMax-M3 Signed-off-by: octo-patch <octo-patch@github.com>
|
Someone is attempting to deploy a commit to the rohitg00's projects Team on Vercel. A member of the Team first needs to authorize it. |
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info
📝 Walkthrough
Merge Risk: ⚪ Minimal · up to
|
| Check name | Status | Explanation | Resolution |
|---|---|---|---|
| Docstring Coverage |  |
Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 3 functions across 6 files. (2 skipped: 2 … | Write docstrings for the functions missing them to satisfy the coverage threshold. |
-
Check name Status Explanation Title check The title clearly and concisely describes the main change: MiniMax requests now use MiniMax-M3.1-Flash by default. 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. Description Check Check skipped - CodeRabbit’s high-level summary is enabled.
Full details: Docstring Coverage
-
Explanation
Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 3 functions across 6 files. (2 skipped: 2 unsupported.)
Resolution
Write docstrings for the functions missing them to satisfy the coverage threshold.
- Fix all pre-merge checks with AI
✨ Finishing Touches: 💡 1
-
🛠️ Fix failing CI checks: 💡
-
- Commit to this branch
- Create a new PR
🧪 Generate unit tests (beta)
-
- Create a new PR
-
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.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@src/providers/minimax.ts`:
- Line 14: Update the docblock in src/providers/minimax.ts that documents
MAX_TOKENS so the default shown matches runtime/config defaults (4096); change
the text "MAX_TOKENS — max output tokens (default: 800; ...)" to "MAX_TOKENS —
max output tokens (default: 4096; MiniMax-M2.7 needs ≤800, MiniMax-M3 supports
up to 128K)" so it aligns with src/config.ts and .env.example.
🪄 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: defaults
Review profile: CHILL
Plan: Pro
Run ID: 2d40a252-9704-43b3-84ed-3cc3bfe2941f
📒 Files selected for processing (8)
.env.examplesrc/cli/onboarding.tssrc/config.tssrc/providers/index.tssrc/providers/minimax.tstest/fallback-model-resolution.test.tstest/fetch-timeout.test.tstest/minimax-provider.test.ts
| * MINIMAX_MODEL — model name (default: MiniMax-M2.7) | ||
| * MAX_TOKENS — max output tokens (default: 800; MiniMax-M2.7 needs ≤800) | ||
| * MINIMAX_MODEL — model name (default: MiniMax-M3; MiniMax-M2.7 / MiniMax-M2.7-highspeed also supported) | ||
| * MAX_TOKENS — max output tokens (default: 800; MiniMax-M2.7 needs ≤800, MiniMax-M3 supports up to 128K) |
There was a problem hiding this comment.
Fix the MAX_TOKENS default in the provider docblock.
Line 14 says default is 800, but runtime/config defaults are 4096 (see src/config.ts and .env.example). This can mislead operators during setup.
Proposed patch
- * MAX_TOKENS — max output tokens (default: 800; MiniMax-M2.7 needs ≤800, MiniMax-M3 supports up to 128K)
+ * MAX_TOKENS — max output tokens (default: 4096; MiniMax-M2.7 needs ≤800, MiniMax-M3 supports up to 128K)📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| * MAX_TOKENS — max output tokens (default: 800; MiniMax-M2.7 needs ≤800, MiniMax-M3 supports up to 128K) | |
| * MAX_TOKENS — max output tokens (default: 4096; MiniMax-M2.7 needs ≤800, MiniMax-M3 supports up to 128K) |
🤖 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 `@src/providers/minimax.ts` at line 14, Update the docblock in
src/providers/minimax.ts that documents MAX_TOKENS so the default shown matches
runtime/config defaults (4096); change the text "MAX_TOKENS — max output tokens
(default: 800; ...)" to "MAX_TOKENS — max output tokens (default: 4096;
MiniMax-M2.7 needs ≤800, MiniMax-M3 supports up to 128K)" so it aligns with
src/config.ts and .env.example.
Signed-off-by: octo-patch <266937838+octo-patch@users.noreply.github.com>
octo-patch
changed the title
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
There was a problem hiding this comment.
🔍 Devin Review: 1 flag
Not posted on this PR by your GitHub settings — view it in Devin Review. (Configure)
Reason: Make MiniMax-M3.1-Flash the default for new MiniMax configurations and fallback requests while preserving explicitly configured models.
Summary
Validation
npm test -- test/minimax-provider.test.ts test/fallback-model-resolution.test.ts test/fetch-timeout.test.ts --maxWorkers=2— 48 tests across 3 files.npm run skills:gen,npm run skills:check(17 skills), andgit diff --check.npm run docs:sync; no generated changes remain. Its test-count calculation is incomplete because the full suite cannot be collected with the available dependencies.npm run buildcannot start becausetsdownis unavailable. Full-suite collection fails on missingiii-sdkand other uncached dependencies;npm run docs:checkconsequently cannot compute the test count. Full tests and build are not claimed as passing. New heavy setup is paused by the shared resource gate (approximately 60.5 GiB available versus the required 110 GiB). The queued light install was canceled before it started after compatible focused-test caches were located.2b6d240b37ba07855f4980518b4f0f560785efb1, upstream CI and Release gate reportaction_required. Vercel reports a team-authorization failure. These external gates have not validated the patch.The request shape keeps thinking and effort unset on the native MiniMax path, allowing the documented Flash defaults. The existing single-turn text provider interface is unchanged.
Reference: https://platform.minimax.io/docs/api-reference/text-anthropic-api.md
Summary by CodeRabbit
New Features
MiniMax-M3.1-Flashas the default model.MiniMax-M3, remain supported.Documentation
Tests