oclaw/platform/llm
oliver a3365b77fa fix(chat): persist reasoning for Responses stream and WS final snapshot
- 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>
2026-05-12 20:18:15 +08:00
..
transports fix(chat): persist reasoning for Responses stream and WS final snapshot 2026-05-12 20:18:15 +08:00
__init__.py 初始化:独立 oclaw 仓库首提交 2026-04-24 22:31:22 +08:00
chat_models.py 重构仓库目录为统一的 runtime 分层并清理历史 openclaw 残留。 2026-04-25 01:24:23 +08:00
image_http_common.py feat(chat): image specialist legacy lane, Responses fixes, ACL + UI attachments 2026-05-10 07:06:05 +08:00
image_legacy_client.py feat(chat): image specialist session image fallback and WS UX 2026-05-10 11:25:21 +08:00
image_ocr_client.py feat: multimodal image clients, workspaces, Tushare skill, test fixes 2026-05-10 04:41:42 +08:00
MIT_LICENSE.txt 重构仓库目录为统一的 runtime 分层并清理历史 openclaw 残留。 2026-04-25 01:24:23 +08:00
replay_policy.py 重构仓库目录为统一的 runtime 分层并清理历史 openclaw 残留。 2026-04-25 01:24:23 +08:00
tool_call_id.py 重构仓库目录为统一的 runtime 分层并清理历史 openclaw 残留。 2026-04-25 01:24:23 +08:00
tool_schema.py feat: multimodal image clients, workspaces, Tushare skill, test fixes 2026-05-10 04:41:42 +08:00
tool_wire_policy.py feat: multimodal image clients, workspaces, Tushare skill, test fixes 2026-05-10 04:41:42 +08:00
video_generation_client.py feat(video): DashScope video specialist with correct i2v request bodies 2026-05-10 16:20:43 +08:00