Per model api wire type and custom Responses providers
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 19.9k
- Forks
- 2.3k
- Avg merge
- 2d 7h
- Merged PRs (30d)
- 30
Description
Some names providers have three of the following api formats:
OpenAI Responses,
OpenAI Chat Completions,
Anthropic Messages
For example, qwen3.7-max on OpenCode Go supports only Anthropic endpoint, whereas another model like glm-5.2 works with OpenAI Chat Completions. Ollama works with both OpenAI Responses and OpenAI Chat Completions - however perhaps with the Responses cache hit will be better. SuperGrok or some other providers works better with Responses API because of built in server side tool calling functionality.
Currently named providers only support "OpenAI Chat Completions" format, it is not possible to create custom OpenAI Responses provider or model.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing how named providers and models select the current OpenAI Chat Completions wire format and where custom providers are configured. Define the supported choices for OpenAI Responses, OpenAI Chat Completions, and Anthropic Messages, then verify that a custom provider or model can select each required format.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- ai, api, cli
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100