mirror of
https://github.com/hansjone/oclaw.git
synced 2026-10-09 03:30:48 +08:00
- Forward reasoning_content and non-stream reasoning to on_token in OpenAI chat completions; Gemini thought parts to on_token. - Stream bubble: always render session.tool panels; format tool_use_call payloads and title as call · tool_name. - Emit tool_use_call via on_tool_ui before tool execution so WS shows invoke cards before tool_use_result. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| assets/fonts | ||
| admin-theme.js | ||
| app.js | ||
| chat.html | ||
| chat.js | ||
| default-user-avatar.svg | ||
| index.html | ||
| oliver.svg | ||
| styles.css | ||
| theme-deepseek.css | ||
| theme-presets.css | ||