Add Requesty as a built-in model provider#353
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This adds Requesty (https://requesty.ai), an OpenAI-compatible LLM gateway, as a built-in model provider. The wiring mirrors the existing OpenRouter provider.
Like OpenRouter, Requesty exposes an OpenAI-compatible API and uses the same
publisher/modelnaming convention (e.g.openai/gpt-4.1,google/gemini-2.5-flash), so it slots into the existing provider model with no new abstractions.Changes:
app/shared/ai_models_providers.go: add therequestyprovider constant, theREQUESTY_API_KEYenv var, thehttps://router.requesty.ai/v1base URL, the entry inAllModelProviders, and theBuiltInModelProviderConfigsregistration (base URL + API key env var), mirroring the OpenRouter entry.app/shared/ai_models_available.go: add Requesty as an additional provider option on a small set of models where the Requesty model name matches the existing OpenRouter model name exactly:openai/gpt-4.1,openai/gpt-4.1-mini,google/gemini-2.5-flash,google/gemini-2.5-pro.app/cli/schema/json-schemas/definitions/model-providers.schema.json: addrequestyto the provider enum.docs/docs/models/model-providers.md: add a Requesty section under Built-In Providers.I kept this minimal rather than wiring Requesty onto every model: I only added it to models whose name maps 1:1 to a Requesty model I verified routes successfully. Anthropic models were intentionally left out for now because Requesty's current naming (e.g.
anthropic/claude-sonnet-4-5) doesn't line up exactly with Plandex's existinganthropic/claude-sonnet-4model name, and I didn't want to introduce an incorrect mapping. Happy to extend coverage if maintainers prefer.Testing:
go build ./...passes inapp/shared,app/cli, andapp/server.go vet ./...passes inapp/shared.gofmtclean on the changed Go files.https://router.requesty.ai/v1/chat/completionsreturned HTTP 200 for each model added:openai/gpt-4.1,openai/gpt-4.1-mini,google/gemini-2.5-flash, andgoogle/gemini-2.5-pro.Disclosure: I work at Requesty. This mirrors the existing OpenRouter provider; happy to adjust wording/placement or close if it's not a fit.