feat: add Requesty as an OpenAI-compatible provider#23
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
Requesty (https://requesty.ai) is an OpenAI-compatible LLM gateway. This adds it as a named provider in the AutoFigure SDK, mirroring the existing OpenRouter wiring 1:1: - config.py: add a 'requesty' branch to _get_default_base_url (https://router.requesty.ai/v1), _get_default_model (openai/gpt-4o-mini), and _get_default_enhancement_model; update provider comments/docstrings. - llm_client.py: list Requesty among supported OpenAI-compatible providers (no special-casing needed; it uses the same openai SDK path as OpenRouter). - README.md: add Requesty to the provider list and a one-line factual note. Tested against the live endpoint: POST /v1/chat/completions with model openai/gpt-4o-mini returned HTTP 200 and a valid completion.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds Requesty as a named, OpenAI-compatible LLM provider in the AutoFigure SDK, mirroring the existing OpenRouter wiring 1:1.
autofigure/config.py: add a"requesty"branch to_get_default_base_url(https://router.requesty.ai/v1),_get_default_model(openai/gpt-4o-mini), and_get_default_enhancement_model; update the provider comments andfrom_envdocstring.autofigure/utils/llm_client.py: list Requesty among the supported OpenAI-compatible providers. No special-casing is required — Requesty uses the exact sameopenaiSDK path as OpenRouter.autofigure/README.md: add Requesty to the provider feature list and thegeneration_provideroptions, plus one factual line on the default base URL.Why
Requesty is an OpenAI-compatible LLM gateway. Model naming (
provider/model) and theAuthorization: Bearerauth header are identical to OpenRouter, so it slots into the existing provider abstraction with no behavioral changes for other providers.Tested against the live endpoint
A
POSTtohttps://router.requesty.ai/v1/chat/completionswithmodel=openai/gpt-4o-minireturned HTTP 200 and a valid completion. I also verified thatConfig(generation_provider="requesty")resolves the expected base URL (https://router.requesty.ai/v1) and default model (openai/gpt-4o-mini).Scope / compliance
Code-level provider entry plus a single factual row in the existing provider list — no new dependencies, no changes to other providers' defaults. The frontend Vercel-AI-SDK provider layer is intentionally untouched to keep this change focused on the SDK.
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.