agent: Add reasoning token support for OpenAI reasoning models

- 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.
This commit is contained in:
Mario Zechner 2025-08-10 00:32:30 +02:00
parent 9157411034
commit 62d9eefc2a
8 changed files with 284 additions and 15 deletions

View file

@ -2,4 +2,6 @@
- README.md
- packages/tui/README.md
- packages/agent/README.md
- packages/pods/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.