Skip to content

Add Requesty as an LLM provider#756

Open
Thibaultjaigu wants to merge 1 commit into
stakpak:mainfrom
Thibaultjaigu:add-requesty-provider
Open

Add Requesty as an LLM provider#756
Thibaultjaigu wants to merge 1 commit into
stakpak:mainfrom
Thibaultjaigu:add-requesty-provider

Conversation

@Thibaultjaigu

Copy link
Copy Markdown

This adds Requesty as a provider, mirroring the existing OpenRouter provider.

Requesty (https://router.requesty.ai/v1) is an OpenAI-compatible LLM router.

Changes:

  • libs/ai/src/providers/requesty/: new provider module (chat + streaming) mirroring openrouter/, default base URL https://router.requesty.ai/v1.
  • libs/shared/src/models/llm.rs: a Requesty ProviderConfig variant handled across all match arms.
  • libs/ai/src/client/{config,builder}.rs, libs/shared/src/models/stakai_adapter.rs: client + dispatch wiring.
  • libs/shared/src/oauth/: a Requesty auth provider + registry entry.
  • cli/src/config/{app,profile}.rs, cli/src/onboarding/*, cli/src/commands/auth/login.rs: REQUESTY_API_KEY, builtin-provider list, onboarding profile, and login support.

Model naming is provider/model. Verified: cargo build succeeds and cargo test -p stakpak-shared passes (342 tests).

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.

Mirror the existing OpenRouter provider to add Requesty (https://router.requesty.ai/v1),
an OpenAI-compatible LLM router. Adds a dedicated requesty provider module, the Requesty
ProviderConfig variant handled across all match arms, client/registry wiring, CLI config
and onboarding entries, and login support.

Signed-off-by: Thibault Jaigu <thibault.jaigu@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant