mirror of
https://github.com/hansjone/oclaw.git
synced 2026-10-09 05:50:44 +08:00
- 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> |
||
|---|---|---|
| .. | ||
| transports | ||
| __init__.py | ||
| chat_models.py | ||
| image_http_common.py | ||
| image_legacy_client.py | ||
| image_ocr_client.py | ||
| MIT_LICENSE.txt | ||
| replay_policy.py | ||
| tool_call_id.py | ||
| tool_schema.py | ||
| tool_wire_policy.py | ||
| video_generation_client.py | ||