mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-14 19:02:17 +03:00
opencode-go's static model registry was missing a gpt-5.6-luna entry, so getModelTargetFormat() returned null and resolveOpencodeTargetFormat() fell back to "openai", making OpencodeExecutor.buildUrl() post to /chat/completions -- which the Go upstream 500s on for this model (it only serves gpt-5.6-luna via /responses). The github provider already declares targetFormat:"openai-responses" for the same model id, and opencode-go itself already does the same for deepseek-v4-pro/flash. Adds the missing registry entry mirroring those siblings.