Add default models for provider quick options#17
Conversation
- Add provider quick flags (--kimi, --deepseek, --glm, --qwen) for faster profile setup - Support base_url=URL and --base-url URL overrides in both main command and profile add - Implement auto-profile creation when using provider flags without existing profile - Add providers.js module with predefined provider configurations - Refactor CLAUDE.md to reference separate Agents.md documentation - Update CLI help text to include new provider syntax options - Improve base URL resolution priority: explicit override > profile > provider default 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add defaultModel field to provider configurations (kimi, deepseek, glm, qwen) - Automatically set model when creating profiles via provider flags - Improve provider flag handling to respect user-provided model preferences 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
|
Claude encountered an error —— View job I'll analyze this and get back to you. |
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
Codex Review: Here are some suggestions.
Reply with @codex fix comments to fix any unresolved comments.
About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you open a pull request for review, mark a draft as ready, or comment "@codex review". If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex fix this CI failure" or "@codex address that feedback".
| // Default model if not provided | ||
| if (!model && p && p.defaultModel) model = p.defaultModel; |
There was a problem hiding this comment.
[P2] Preserve existing model when overwriting provider profile
When a provider flag is used with kimicc profile add, this block injects the provider’s defaultModel whenever the caller didn’t pass --model. The overwrite path later passes model to addProfile, so running kimicc profile add --kimi <token> to rotate a key will reset any custom model that was already configured on that profile. Users who previously selected a different model lose that setting unexpectedly. Consider only applying the default model when creating a new profile or when --model is explicitly supplied.
Useful? React with 👍 / 👎.
1 participant
Summary
• Added default model configuration for provider quick options (kimi, deepseek, glm, qwen)
• Enhanced provider selection to automatically set appropriate model when creating profiles
• Improved user experience by eliminating need to manually specify common models
Test plan
🤖 Generated with Claude Code