What's Changed

Added image/vision input modalities to GPT and Claude models that were previously missing this configuration. This enables image input support when using these models through ProxyPal.

Fixes

• agents.rs: Expanded multimodal detection to include GPT-4o, GPT-4.1, GPT-5.x, o1/o3/o4, Claude, and Copilot GPT models
• opencode.json: Added modalities: { input: ["text", "image"], output: ["text"] } to 37 models (17 GPT + 20 Claude)

Fixes #168

Full Changelog: https://github.com/heyhuynhgiabuu/proxypal/compare/v0.4.1...v0.4.2