Repository navigation
feat: add requesty and cheaper inference providers - #589
Merged
di-sukharev merged 8 commits intoNov 13, 2026
Merged
Conversation
Signed-off-by: binyangzhu000-sudo <224954946+binyangzhu000-sudo@users.noreply.github.com>
Requesty is an OpenAI-compatible gateway, so RequestyEngine reuses OpenAiEngine with the Requesty base URL (https://router.requesty.ai/v1) by default while still allowing OCO_API_URL to override it (for example the EU endpoint). Registered alongside OpenRouter and OrcaRouter in the provider enum, config validators, model list, key and billing URLs, recommended model, engine factory, setup picker and model cache. Model discovery merges the managed policies list with the full catalog, fetching each on its own. Includes unit tests, README docs and the rebuilt bundle.
Owner
|
fresh setup fails in migration 00. please fix this path and add a cli test. |
Setup and 'oco config set OCO_AI_PROVIDER=atlascloud' were rejected because the validator kept its own hard-coded provider list. Derive it from OCO_AI_PROVIDER_ENUM so new providers (and mlx, which was also missing) cannot drift again, update the error messages, and add regression tests. Signed-off-by: binyangzhu000-sudo <224954946+binyangzhu000-sudo@users.noreply.github.com>
di-sukharev
approved these changes
Nov 13, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
adds requesty and cheaper inference as optional openai-compatible providers, with model discovery and configurable inference endpoints. fresh global setups skip the legacy provider-key migration, and setup examples include an explicit model.
model discovery excludes non-chat models and cheaper inference models that only support the responses api.
includes the original requesty commits from #588.
validation:
regression coverage includes the first commit with no migration records and chat endpoint compatibility.