Expanded support for self-hosted LLMs

As of Sourcegraph 6.4, customers using self-hosted models through the openaicompatible provider can now configure:

• Custom headers: Add authentication keys or other custom HTTP headers to LLM requests
• Non-legacy completions: Use /chat/completions instead of the older /completions endpoint for Cody's autocomplete queries

These updates make Cody compatible with a wider range of LLM gateways and inference servers, giving customers more flexibility to use their preferred infrastructure.

Learn more about model support in our docs.