OpenAI-compat BASE_URL /v1 with provider openai, not the Gemini origin example
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.3k
- Forks
- 4.3k
- PR merge metrics
- No merged PRs in 30d
Description
Working config (openai provider, BASE_URL /v1)
ChatDev already reads BASE_URL / API_KEY from .env and YAML provider: openai. A Chat Completions host whose public catalog is GET https://api.pzero.studio/v1/models (no key) fits that slot.
BASE_URL=https://api.pzero.studio/v1
API_KEY=<Bearer key for that host>
YAML model node: provider: openai, base_url: ${BASE_URL}, name: a live catalog id, example deepseek-v4-flash.
Do not set provider: gemini. Do not copy the README Gemini example (https://generativelanguage.googleapis.com with no /v1). This host needs the /v1 root. The OpenAI default https://api.openai.com/v1 plus sk-… will not list catalog ids on this host.
Not asking for a first-party provider enum. openai plus a custom BASE_URL is enough.
Contributor guide
No contributing guide indexed for this repository
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 locating the README Gemini example and the surrounding configuration documentation. Update the example to show the openai provider with BASE_URL ending in /v1, API_KEY, and a live catalog model id; done means the README no longer directs users to the Gemini origin or provider for this setup.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- yaml
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 76/100