mirror of
https://github.com/hansjone/oclaw.git
synced 2026-10-09 03:13:19 +08:00
oliver
a3365b77fa
- Parse reasoning_summary_text (and related) SSE events in OpenAI Responses streaming; forward deltas to on_token and return reasoning_content on LLMResponse so thinking-mode rows get event_payload in the store. - When emitting chat/final from turn_runner, include event_type/event_payload and merge reasoning_content from earlier assistant rows in the same turn_uuid so the collapsed reasoning fold matches what streamed. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| config | ||
| embeddings | ||
| files | ||
| integrations | ||
| llm | ||
| persistence | ||
| __init__.py | ||