- Fix streaming to work even when tools are present (was forcing JSON mode)
- Fix response format: use empty list [] instead of null for tool_calls
- Add exclude_none config to ChatMessage model to match OpenAI format
- Remove tool instructions from prompt (were confusing 3B model)
- Fix tool call parsing to handle markdown code blocks properly
- Change default instances from 3 to 1 for faster debugging
- Allow 1 instance minimum in interactive config (was 2 on Mac)
- Add debug logging to track requests and responses
Fixes infinite loop issue where opencode would retry requests repeatedly
sleepy
d30eedaa63