feat: add Requesty as an OpenAI-compatible provider

[Thibaultjaigu]

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

Requesty is an OpenAI-compatible LLM gateway using provider/model naming, so it slots into the provider selector and model list the same way OpenRouter does.

Changes:

• src/autocoder/utils/model_provider_selector.py: add a requesty entry to PROVIDER_INFO_LIST (endpoint https://router.requesty.ai/v1) and to the provider radiolist.
• src/autocoder/common/auto_coder_lang.py: add the model_provider_requesty label and API-key prompt (en + zh).
• src/autocoder/models.py: add a default Requesty model entry (saas/openai type, base URL https://router.requesty.ai/v1).

Model ids use the ones Requesty actually serves: deepseek/deepseek-chat and deepseek/deepseek-reasoner.

Verification: I tested the endpoint live before opening this. GET https://router.requesty.ai/v1/models returned 200, and chat completions for deepseek/deepseek-chat and deepseek/deepseek-reasoner 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 or close it if it is not a fit.