Add Z.AI provider support for GLM-5

[reidliu41]

Summary

• add a minimal zai registry provider using the existing OpenAI-compatible chat completions path
• configure default Z.AI endpoint, API key env vars, default model, and setup wizard key URL
• add a config regression test covering bigmodel alias resolution and canonical backend normalization
• update FEATURE_PARITY.md to mark GLM-5 as supported via the new provider

Value:

• makes GLM-5 a first-class provider instead of requiring manual openai_compatible setup
• keeps the implementation low-risk by reusing the existing provider registry and adapter path
• improves onboarding and discoverability for Z.AI users with no behavioral changes to other providers

Change Type

• Bug fix
• New feature
• Refactor
• Documentation
• CI/Infrastructure
• Security
• Dependencies

Linked Issue

None

Validation

• cargo fmt
• cargo clippy --all --benches --tests --examples --all-features
• Relevant tests pass:
• Manual testing:

Security Impact

None

Database Impact

None

Blast Radius

Rollback Plan

---

Review track:

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates Z.AI's GLM-5 model as a native provider, streamlining its configuration and usage within the system. By reusing the established OpenAI-compatible chat completions infrastructure, it offers a low-risk implementation that enhances user experience for Z.AI users by making GLM-5 easily discoverable and accessible without requiring manual setup.

Highlights

• New Provider Integration: Added a new zai registry provider for Z.AI GLM-5, utilizing the existing OpenAI-compatible chat completions path.
• Configuration Details: Configured default Z.AI endpoint, API key environment variables, default model, and setup wizard key URL.
• New Test Case: Included a new regression test to ensure correct resolution of the bigmodel alias to the zai provider.
• Documentation Update: Updated FEATURE_PARITY.md to reflect GLM-5's support through the new Z.AI provider.

Changelog

• FEATURE_PARITY.md
  • Marked GLM-5 as supported via the new Z.AI provider.
• providers.json
  • Added a new provider entry for zai, including its ID, bigmodel alias, open_ai_completions protocol, default base URL, API key environment variable (ZAI_API_KEY), default model (glm-5), and setup wizard details.
• src/config/llm.rs
  • Introduced a new test registry_provider_alias_resolves_zai to validate the correct resolution of the bigmodel alias to the zai provider and its associated configuration.

Activity

• No human activity has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds support for the Z.AI provider for GLM-5 models. The changes include updating the feature parity documentation, adding the provider definition to providers.json, and including a new regression test. The implementation is clean and follows existing patterns. I have one suggestion to improve the robustness of the new test case to better guard against future regressions in the provider's default configuration.

[gemini-code-assist]

This test is intended to verify the configuration resolution for the new zai provider, including its alias. However, by explicitly setting selected_model to "glm-5", the test doesn't verify that the default_model from providers.json is correctly configured. If the default_model in providers.json were to change or have a typo, this test would still pass, making it less effective as a regression test for the provider's default configuration.

To make the test more robust and ensure it validates the default configuration from the provider definition, I suggest removing the selected_model field. This will cause the configuration resolution to fall back to the default_model specified in providers.json, which is what we want to test for a new provider's default setup.

A similar test, registry_provider_resolves_tinfoil, already follows this pattern.

        let settings = Settings {
            llm_backend: Some("bigmodel".to_string()),
            ..Default::default()
        };

[reidliu41]

Could you review this when you get a chance? @zmanian

[zmanian]

Review: Add Z.AI provider support for GLM-5

Clean, minimal addition. Reuses the existing OpenAI-compatible provider path, which is the right approach.

• providers.json entry is well-structured with alias (bigmodel), correct protocol, and setup config
• Test covers alias resolution and canonical backend normalization, following existing test patterns
• FEATURE_PARITY.md updated accurately
• Trailing newline fix on providers.json is a nice cleanup

No concerns. LGTM.