Skip to content

Add first-class Qwen preset#42

Merged
yuanhao merged 1 commit into
mainfrom
feat/issue-38-qwen-provider
May 26, 2026
Merged

Add first-class Qwen preset#42
yuanhao merged 1 commit into
mainfrom
feat/issue-38-qwen-provider

Conversation

@yuanhao

@yuanhao yuanhao commented May 26, 2026

Copy link
Copy Markdown
Collaborator

Closes #38.

Summary

  • Add first-class hosted Qwen / DashScope support via ModelConfig::qwen(...).
  • Add OpenAiCompat::qwen() for Qwen reasoning-content parsing and OpenAI-compatible max-token behavior.
  • Add ModelConfig::openai_compat(...) for local/custom deployments that need explicit model-family compat flags.
  • Document hosted Qwen, local Qwen, regional DashScope URLs, and combined Qwen-on-Ollama compat.

Impact

  • Additive public API only.
  • Existing provider behavior is unchanged.
  • CLI now supports --provider qwen, and DASHSCOPE_API_KEY is only preferred for Qwen.

Validation

  • cargo fmt --check
  • cargo check --examples
  • cargo test provider::model
  • cargo test provider::openai_compat
  • cargo test

@yuanhao yuanhao merged commit 5f04585 into main May 26, 2026
1 check passed
@yuanhao yuanhao deleted the feat/issue-38-qwen-provider branch May 26, 2026 16:19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add first-class Qwen/DashScope OpenAI-compatible preset

1 participant