feat: add Requesty provider to the catalog - #623
Open
Thibaultjaigu wants to merge 2 commits into
Open
Thibaultjaigu wants to merge 2 commits into
Thibaultjaigu wants to merge 2 commits into
Conversation
Requesty is an OpenAI compatible gateway. Like OpenRouter it ships no built in models and resolves capabilities through the cross provider lookup, reading its key from REQUESTY_API_KEY.
Mirror the OpenRouter entry in the Web UI catalog with a short seed list checked against the live Requesty model list, and accept a Requesty provider without an explicit url like the other catalog providers.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Requesty, an OpenAI compatible gateway, as a catalog provider next to OpenRouter so it can be picked in Settings and configured with just
REQUESTY_API_KEY.Changes
src/model/catalog/providers.ts:requestyentry mirroringopenrouter(https://router.requesty.ai/v1,REQUESTY_API_KEY, no built in models, cross provider lookup).ui/src/shared/catalogProviders.ts: matching Web UI entry with four seed models whose ids, context windows and output caps come from the live/v1/modelslist; the model picker still fetches the full list from the default URL.ui/server/services/pilotdeckConfig.js: default URL so a config withouturlvalidates, as for OpenRouter.parseModelConfig.spec.tsandcatalogProviders.test.ts.Validation
node --import tsx --test "tests/model/**/*.spec.ts" "tests/model/**/*.test.ts": 105 pass.npx vitest runinui/on catalogProviders, config route, onboarding route, pilotdeckConfig, configurationRegression, ModelsSection and ProviderCard: 211 pass. Roottsc --noEmitandeslinton the touched UI files are clean;uitypecheck shows the same 513 JSX type errors as a cleanmaincheckout here, none in these files.openai/gpt-4o-mini:completeandstreamModelthrough the parsed config both replied "pong", andPOST /api/config/modelsforrequestyreturned 733 models keyless and 778 with the env key.Disclosure: I work at Requesty. Happy to adjust anything to match project conventions.