Update Z.AI default model to GLM-4.7 #90
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughTwo exported constants in the ZAI types file are updated from model version ChangesZAI Model Version Update
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Warning There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure. 🔧 ESLint
packages/types/src/providers/zai.tsOops! Something went wrong! :( ESLint: 9.28.0 ESLint couldn't find an eslint.config.(js|mjs|cjs) file. From ESLint v9.0.0, the default configuration file is now eslint.config.js. https://eslint.org/docs/latest/use/configure/migration-guide If you still have problems after following the migration guide, please stop by 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 |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
Honestly it should be changed to latest, 5.1 |
|
Follow-up reverted after checking Z.AI docs more closely. The extra |
There was a problem hiding this comment.
Thanks for updating this! Read up on the zAI docs, and it does look like the decision to default to 4.7 is correct - with 5.1 being opt-in.
(Also used this PR as a test ground to see if Roomote could update forked PRs)
Approving and will merge once CI passes.
Nobody really buys z.ai for GLM 4.7, but it doesn't really matter much anyway. |
|
Personally I use GLM 5.1 daily and rarely hit the prompt limit. That said I think the best practice should be token-efficient defaults rather than SOTA models - particularly when the docs have a recommended default. |
Related GitHub Issue
#89
Closes: #
Roo Code Task Context (Optional)
Description
Updates default Z.AI model from GLM-4.6 -> GLM-4.7 per recommendation on Z.AI Docs
Test Procedure
Have not tested yet
Pre-Submission Checklist
Screenshots / Videos
Documentation Updates
Additional Notes
Get in Touch
Summary by CodeRabbit