feat: add Requesty as an OpenAI-compatible LLM provider

[Thibaultjaigu]

What this adds

Adds a requesty provider entry mirroring the existing openrouter entry:

• OpenAI-compatible base URL: https://router.requesty.ai/v1
• API key env var: REQUESTY_API_KEY
• provider/model naming (e.g. openai/gpt-4o-mini), same convention as OpenRouter

Changes

• sdk/src/openagents/config/llm_configs.py
  • REQUESTY = "requesty" added to the LLMProviderType enum next to OPENROUTER
  • A requesty entry added to MODEL_CONFIGS with provider: generic, the base URL, and API_KEY_ENV_VAR
  • "requesty" added to the generic-provider list so its predefined api_base is used
• README.md — added requesty to the accepted AIDER_PROVIDER values and a table row
• llms.txt — added a requesty provider table row

Testing

Ran a live chat completion against https://router.requesty.ai/v1/chat/completions with model openai/gpt-4o-mini and got an HTTP 200 with a valid completion. Also imported the modified module and confirmed LLMProviderType.REQUESTY and MODEL_CONFIGS["requesty"] resolve as expected.

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.

[vercel]

@Thibaultjaigu is attempting to deploy a commit to the Raphael's projects Team on Vercel.

A member of the Team first needs to authorize it.