feat: add Requesty as an OpenAI-compatible LLM provider

[Thibaultjaigu]

Summary

Adds Requesty as a native, OpenAI-compatible LLM provider, mirroring the existing OpenRouter integration as closely as possible.

Requesty is an OpenAI-compatible LLM gateway:

• Base URL: https://router.requesty.ai/v1
• Auth: Authorization: Bearer <REQUESTY_API_KEY>
• Model naming: provider/model (e.g. openai/gpt-4o-mini), same convention as OpenRouter

Wiring sites (parallel to openrouter)

• packages/core/src/constants/models/providers.ts — new requesty entry in the providers map (name: 'Requesty', baseURL: 'https://router.requesty.ai/v1'), placed right after openrouter.
• packages/config/src/schema.ts — added 'requesty' to the provider union.
• packages/config/src/modelYaml.ts — env resolver now maps requesty → REQUESTY_API_KEY.
• packages/config/src/models/gpt5.ts — requesty added to the expected-providers list and to the GPT-5 baseURL repair branch (https://router.requesty.ai/v1).
• apps/cli/src/ui/components/ModelSelector/useModelSelectorMenus.ts — requesty added to the ranked provider list so it appears in the /model selector.
• docs/develop/configuration.md — added a Requesty config example block and the REQUESTY_API_KEY env var, parallel to the OpenRouter section.
• .env.example — documented REQUESTY_API_KEY.

Verification

• bun run typecheck (tsc --noEmit) passes clean.
• Pre-commit hook (format:check + typecheck) passes.
• Live check: a real chat completion against https://router.requesty.ai/v1/chat/completions with model openai/gpt-4o-mini returned HTTP 200 with a valid completion.

Links

• https://requesty.ai
• https://docs.requesty.ai

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.