feat(providers): add OrcaRouter preset - #89
Open
Marc-oss-hub wants to merge 1 commit into
Open
Conversation
Collaborator
|
Thanks for the contribution! We will take a look and run it through the same verification every built-in preset goes through (each preset URL is live-checked end to end before it ships), and get back to you here. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Change
Adds OrcaRouter as a named preset in the provider wizard, mirroring the existing Groq/DeepSeek/Together presets. The operator now picks "OrcaRouter" by name instead of typing a base URL, and the API key lands in its own
ORCAROUTER_API_KEYenv var — each preset gets its own variable so connecting a second service cannot overwrite the first one's key.OrcaRouter is an OpenAI-compatible gateway: one key routes to 160+ models across all major model families, with
orcarouter/autoas a smart default router. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.Like every other preset, this one resolves to the existing
openai-compatiblekind withbaseUrlfilled in (https://api.orcarouter.ai, stored without the/v1suffix per the repo convention — call sites append/v1/...). Model lists still come from the server's own/v1/models, so nothing here needs updating when a vendor ships a new model. OrcaRouter serves that endpoint without credentials, solistsModelsWithoutKeyis set: the operator can browse the model catalog before pasting a key.Testing
findProviderPreset("orcarouter")→baseUrlhttps://api.orcarouter.ai,envVarORCAROUTER_API_KEY,listsModelsWithoutKeytrue. New test added; existing presence/uniqueness/no-/v1-suffix tests all still pass.npm run lint(tsc --noEmit) clean;npm run buildclean.https://api.orcarouter.aithrough the repo's own code path (fetchOpenAiCompatModels+ theopenai-compatibleprovider): model list returned 189 ids, 10orcarouter/-namespaced includingorcarouter/auto, and a chat completion returned normally.mainwithout this change.I'm an engineer on the OrcaRouter team.