docs: add EvoLink custom endpoint example

[EvoLinkAI]

Summary

• Add EvoLink to the OpenAI-compatible custom endpoint examples.
• Include a minimal config.yaml snippet using https://direct.evolink.ai/v1.
• Point users to the /v1/models catalog for model ids.

Validation

• git diff --check
• Verified GET https://direct.evolink.ai/v1/models returns HTTP 200 with an EvoLink API key.
• Verified POST https://direct.evolink.ai/v1/chat/completions with model=gpt-5.2 returns HTTP 200.

[gemini-code-assist]

Code Review

This pull request adds EvoLink as an OpenAI-compatible custom endpoint provider in the integrations documentation, including a configuration example. The feedback suggests replacing the non-existent model gpt-5.2 in the example with a placeholder like your-model-id to avoid confusion.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

Using gpt-5.2 as the default model in the example is misleading because it is a non-existent model. It is better to use a placeholder like your-model-id to align with the instruction below to use a model ID returned by the /v1/models endpoint.

Suggested change

	default: gpt-5.2
	default: your-model-id