feat: add Requesty as a config-driven provider#629
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
Requesty is an OpenAI-compatible LLM gateway that uses the same provider/model naming convention as OpenRouter, so this mirrors the existing OpenRouter provider. - configs/providers/requesty.yaml mirroring openrouter.yaml (base URL https://router.requesty.ai/v1, REQUESTY_API_KEY, provider/model ids) - RequestyProvider in adapters/models/factory.py (OpenAILike + attribution headers) registered in the provider factory - requesty added to the config.yaml provider registry and the manager preferred_order - REQUESTY_API_KEY in .env.example and Requesty documented in CONFIGURATION_GUIDE.md - config-loading tests validating requesty.yaml loads via the same loader path Signed-off-by: Thibault Jaigu <thibault.jaigu@gmail.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 as a config-driven provider, mirroring the existing OpenRouter provider. Requesty is an OpenAI-compatible LLM gateway that uses the same
provider/modelid convention (e.g.openai/gpt-4o-mini,anthropic/claude-sonnet-4-5).Changes:
python/configs/providers/requesty.yaml— mirrorsopenrouter.yamlstructure exactly (base URLhttps://router.requesty.ai/v1,REQUESTY_API_KEY, provider/model ids).python/valuecell/adapters/models/factory.py— newRequestyProvider(OpenAI-compatible viaOpenAILike, forwardsHTTP-Referer/X-Titleattribution headers) registered in the provider factory_providersmap.python/configs/config.yaml—requestyadded to the provider registry;python/valuecell/config/manager.py— added to the auto-selectpreferred_order..env.example—REQUESTY_API_KEY;docs/CONFIGURATION_GUIDE.md— Requesty documented in the provider table, file-tree, registry example, and priority-order list.python/valuecell/config/tests/test_provider_config.py— tests validatingrequesty.yamlloads via the same loader/manager path as OpenRouter, resolves the env key, and registers in the factory.Testing: config-loading tests pass (4 passed). Verified a live chat/completions round-trip against
https://router.requesty.ai/v1usingprovider/modelnaming and the attribution headers.Note: the frontend provider→icon map (
frontend/src/constants/icons.ts) was not edited because adding arequestyentry requires a logo asset I don't have — happy to add it if you can point me at the icon convention.Docs: https://requesty.ai · https://docs.requesty.ai · https://app.requesty.ai/api-keys · https://app.requesty.ai/router/list
I work at Requesty. This mirrors the existing OpenRouter provider as closely as possible. Happy to adjust or close it if it's not a fit.