fix: add current Z.AI GLM models#426
Open
devatnull wants to merge 1 commit into
Open
Conversation
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Updates Z.AI/GLM model support to include GLM-5.2 and GLM-5 across runtime config, UI copy, tests, and docs, plus adds a Codex Desktop setup guide.
Changes:
- Add GLM-5.2 and GLM-5 to default Z.AI model list and validate via spec.
- Update Settings UI help text and documentation to reference newer GLM models.
- Add new
CODEX_DESKTOP_SETUP.mdguide and link it from the README.
Reviewed changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| src/Verification/ConfigComposerSpec.swift | Adds an assertion that managed Z.AI provider includes the expected GLM aliases. |
| src/Sources/SettingsView.swift | Updates Z.AI provider help text to mention GLM-5.2/GLM-5. |
| src/Sources/ConfigComposer.swift | Extends default Z.AI models with GLM-5.2 and GLM-5. |
| README.md | Updates “latest models supported” text and adds link to Codex Desktop setup. |
| FACTORY_SETUP.md | Adds GLM-5.2 to example config and documents it in the model list. |
| CODEX_DESKTOP_SETUP.md | Introduces a new setup guide for using VibeProxy with Codex Desktop. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+248
to
+253
| expectEqual( | ||
| modelAliases(in: zai ?? [:]), | ||
| ["glm-5.2", "glm-5", "glm-4.7", "glm-4-plus", "glm-4-air", "glm-4-flash"], | ||
| "managed zai provider should include current GLM aliases", | ||
| recorder: recorder | ||
| ) |
| ```toml | ||
| model = "gpt-5.5" | ||
| model_provider = "vibeproxy" | ||
| model_catalog_json = "/Users/YOU/.codex/model_catalog_vibeproxy.json" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
glm-5.2andglm-5to the managed Z.AI provider defaultsVerification
swift testswiftc src/Sources/ConfigComposer.swift src/Sources/ProviderCatalog.swift src/Sources/CustomProviders.swift src/Verification/ConfigComposerSpec.swift -o /tmp/vibeproxy-config-composer-spec && /tmp/vibeproxy-config-composer-speccurl http://localhost:8317/v1/modelsincludesglm-5.2,glm-5, and existing OpenAI/Codex modelsPOST /v1/responseswithglm-5.2returns a completed response with final textcodex exec --model glm-5.2routes through providervibeproxyand returns the expected outputNote
The local OpenAI/Codex smoke route reached VibeProxy correctly but the connected Codex credential was in usage-limit cooldown, so the PR validation focuses on model exposure and GLM routing.