Add Requesty as an OpenAI-compatible LLM provider#102
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a dedicated
requestyprovider mirroring the existing OpenRouter provider.What this does
RequestyProvider(src/caal/llm/providers/requesty_provider.py) subclassesOpenAICompatibleProviderwith base URLhttps://router.requesty.ai/v1. Auth isAuthorization: Bearer <key>, plus the sameHTTP-Referer/X-Titleattribution headers the OpenRouter provider sets.src/caal/llm/providers/__init__.py:create_provider("requesty", ...)andcreate_provider_from_settings(...)(api_key fromrequesty_api_keysetting orREQUESTY_API_KEYenv; model fromrequesty_model, defaultopenai/gpt-4o-mini). Supported-provider strings in docstrings and bothValueErrormessages updated.provider/model(same convention as OpenRouter), e.g.openai/gpt-4o-mini,anthropic/claude-sonnet-4-5.Config sites mirrored (every place OpenRouter appears for config)
src/caal/llm/providers/requesty_provider.py(new)src/caal/llm/providers/__init__.py(imports,__all__, both factories, docstrings, error messages)src/caal/settings.py(requesty_api_key/requesty_modeldefaults)voice_agent.py(runtime config block + startup log line)src/caal/chat/api.py(runtime config block + reload model resolution).env.example(LLM_PROVIDER=requestychoice + Requesty block)README.md(provider mentions + acknowledgements list)Live test
Tested live against
https://router.requesty.ai/v1: a real chat completion withopenai/gpt-4o-mini(the same request shapeRequestyProviderproduces — bearer auth + the attribution headers) returned HTTP 200 with a valid completion.Notes
This intentionally does not touch the frontend setup wizard / settings UI, the
webhooks.py/setup/test-*endpoint, or the i18n message JSONs (frontend/messages/*.json, mobile l10n). Those can follow in a separate change if wanted.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 wording/placement or close it if it's not a fit.