-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Support OpenScience (@synsci/openscience) as a client integration #4854
Copy link
Copy link
Open
Labels
enhancementNew feature or requestNew feature or requestpriority: P3Low: new provider/client integration, large or experimental feature (>2000 LOC or >50 files), RFC/roLow: new provider/client integration, large or experimental feature (>2000 LOC or >50 files), RFC/roproviderProvider adapters, OpenAI-compat presets, upstream API quirksProvider adapters, OpenAI-compat presets, upstream API quirks
Description
Activity
Metadata
Metadata
Assignees
Labels
enhancementNew feature or requestNew feature or requestpriority: P3Low: new provider/client integration, large or experimental feature (>2000 LOC or >50 files), RFC/roLow: new provider/client integration, large or experimental feature (>2000 LOC or >50 files), RFC/roproviderProvider adapters, OpenAI-compat presets, upstream API quirksProvider adapters, OpenAI-compat presets, upstream API quirks
Area
Multiple areas
What are you trying to accomplish?
I want to use OpenScience (synthetic-sciences/openscience, npm:
@synsci/openscience) with models routed through OpenCodex (Gemini, Claude, DeepSeek, Kimi, GLM, etc.), with automatic configuration similar to how OpenCodex currently supports Codex, Claude Code, and Claude Desktop.What prevents this today?
Currently,
ocx startand auto-injection support Codex, Claude Code, and Claude Desktop. To use OpenCodex with OpenScience, users must manually configure an OpenAI-compatible custom provider endpoint viaopenscience local addpointing tohttp://127.0.0.1:10100/v1.What should OpenCodex do?
ocx inject openscience).ocx doctorchecks.Example usage or interface
Alternatives or workarounds
Manually adding a local OpenAI-compatible provider in OpenScience pointing to
http://127.0.0.1:10100/v1.Additional context
Checks