Add GLM-4.7 Flash model to recommended models list for Z.ai provider #5214
Conversation
🦋 Changeset detectedLatest commit: 4d5298f The changes in this PR will be included in the next version bump. Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
Code Review SummaryStatus: 3 Issues Found | Recommendation: Address before merge Overview
Fix these issues in Kilo Cloud Issue Details (click to expand)WARNING
SUGGESTION
Other Observations (not in diff)Issues found in unchanged code that cannot receive inline comments: None. Files Reviewed (2 files)
|
|
Would this be a duplicate of some other PR? |
|
@timoteo7 - sorry it should not have been closed. 4.7 was added already but not 4.7-flash. This needs kilocode_change markers though. There is also a broader PR over at Roo that may be good to pick instead. RooCodeInc/Roo-Code#10860, once it is merged. |
|
Added the markers and will merge this one. We'll pull the from Roo on top of this |
![kiloconnect[bot]](https://avatars.githubusercontent.com/in/2193792?s=60&v=4){kind=small}
| cacheReadsPrice: 0.11, | ||
| description: | ||
| "GLM-4.7 is Zhipu's latest model with built-in thinking capabilities enabled by default. It provides enhanced reasoning for complex tasks while maintaining fast response times.", | ||
| preferredIndex: 1, |
There was a problem hiding this comment.
WARNING: Missing kilocode_change marker for Kilo-specific change
This updates upstream-shared model metadata without a kilocode_change marker. Adding a marker here helps reduce merge conflicts during upstream sync.
| preferredIndex: 1, | |
| preferredIndex: 1, // kilocode_change |
| cacheWritesPrice: 0, | ||
| cacheReadsPrice: 0, | ||
| description: | ||
| "GLM-4.7-Flash is a free, high-speed model with built-in thinking capabilities, excellent for reasoning, coding, and agentic tasks.", |
There was a problem hiding this comment.
SUGGESTION: Consider aligning reasoning metadata with glm-4.7
glm-4.7 sets supportsReasoningEffort, reasoningEffort, and preserveReasoning. If glm-4.7-flash supports the same reasoning controls/behavior, adding those fields would keep UI/tooling consistent.
| cacheReadsPrice: 0.057, | ||
| description: | ||
| "GLM-4.7 is Zhipu's latest model with built-in thinking capabilities enabled by default. It provides enhanced reasoning for complex tasks while maintaining fast response times.", | ||
| preferredIndex: 1, |
There was a problem hiding this comment.
WARNING: Missing kilocode_change marker for Kilo-specific change
Same as the international list: this adds Kilo-specific metadata in an upstream-shared file without a kilocode_change marker.
| preferredIndex: 1, | |
| preferredIndex: 1, // kilocode_change |
3 participants
Adds the GLM-4.7 Flash model to the recommended models list for the Z.ai provider. The model is placed right after GLM-4.7 in the recommended list.
Changes made:
The model is free (input/output prices set to 0) and includes built-in thinking capabilities.
Built for josh by Kilo for Slack