Add Requesty as an OpenAI-compatible provider

[Thibaultjaigu]

This adds a dedicated requesty provider to the AI provider registry (packages/core/src/config/ai-providers.ts), mirroring the existing OpenRouter entry as closely as possible.

What this does:

• Adds a requesty entry to the AI_PROVIDERS map with host: "https://router.requesty.ai/v1", providerType: "openai", a starter model list, and the keys/docs links. Because AIProviderKey is derived as keyof typeof AI_PROVIDERS, the new id is picked up by the type automatically.
• Adds if (host.includes("requesty.ai")) return "requesty"; to detectProviderFromHost, next to the existing OpenRouter mapping.

Requesty is an OpenAI-compatible LLM gateway, so it routes through the same providerType: "openai" client path as OpenRouter (no new client code needed). Model naming is provider/model, same convention as OpenRouter.

Verification: I tested the endpoint live before opening this. GET https://router.requesty.ai/v1/models returned 200 (572 models), and a chat completion with openai/gpt-4o-mini against https://router.requesty.ai/v1/chat/completions returned 200.

Docs: https://requesty.ai , https://app.requesty.ai/api-keys

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.