Description

Add custom HTTP headers support for the VLM (Vision Language Model) OpenAI-compatible backend. Users can pass custom request headers (e.g., HTTP-Referer and X-Title required by OpenRouter) via the extra_headers configuration option.

Related Issue

Type of Change

• New feature (non-breaking change that adds functionality)
• Documentation update

Changes Made

1. Core code changes:

   • openviking/models/vlm/base.py: VLMBase extracts extra_headers from config
   • openviking/models/vlm/backends/openai_vlm.py: OpenAIVLM passes extra_headers as default_headers to OpenAI clients (sync/async)
   • openviking_cli/utils/config/vlm_config.py: VLMConfig supports extra_headers in providers configuration

2. Tests:

   • Added tests/models/test_vlm_extra_headers.py with 6 test cases covering sync/async clients, empty config, VLMConfig forwarding, etc.

3. Documentation and config:

   • Updated examples/ov.conf.example with an extra_headers usage example (OpenRouter scenario)
   • Updated docs/zh/guides/01-configuration.md and docs/en/guides/01-configuration.md with extra_headers parameter description and usage examples

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have made corresponding changes to the documentation
• My changes generate no new warnings

Additional Notes

Usage example:

{
  "vlm": {
    "provider": "openai",
    "api_key": "your-api-key",
    "model": "gpt-4o",
    "api_base": "https://openrouter.ai/api/v1",
    "extra_headers": {
      "HTTP-Referer": "https://your-site.com",
      "X-Title": "Your App Name"
    }
  }
}

This feature only takes effect for OpenAI-compatible VLM providers (e.g., openai, litellm, etc.), and does not affect the volcengine provider.