mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-15 18:01:22 +00:00
- Extract and display reasoning tokens from both Chat Completions and Responses APIs
- Add smart preflight detection to check reasoning support per model/API (cached per agent)
- Support both reasoning_text (o1/o3) and summary_text (gpt-5) formats
- Display reasoning tokens with ⚡ symbol in console and TUI renderers
- Only send reasoning parameters to models that support them
- Fix event type from "thinking" to "reasoning" for consistency
Note: Chat Completions API only returns reasoning token counts, not content (by design).
Only Responses API exposes actual thinking/reasoning events.
408 B
408 B
- When receiving the first user message, you MUST read the following files in full, in parallel:
- README.md
- packages/tui/README.md
- packages/agent/README.md
- packages/pods/README.md
- We must NEVER have type any anywhere, unless absolutely, positively necessary.
- If you are working with an external API, check node_modules for the type definitions as needed instead of assuming things.