oliver 398d85ba06 fix(chat): complete streaming for reasoning, tools, and tool calls ... - 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>		2026-05-10 14:02:14 +08:00
..
__init__.py	初始化：独立 oclaw 仓库首提交	2026-04-24 22:31:22 +08:00
anthropic_messages.py	初始化：独立 oclaw 仓库首提交	2026-04-24 22:31:22 +08:00
base.py	初始化：独立 oclaw 仓库首提交	2026-04-24 22:31:22 +08:00
google_gemini_sse.py	fix(chat): complete streaming for reasoning, tools, and tool calls	2026-05-10 14:02:14 +08:00
openai_chat_completions.py	fix(chat): complete streaming for reasoning, tools, and tool calls	2026-05-10 14:02:14 +08:00
openai_responses.py	feat(chat): image specialist legacy lane, Responses fixes, ACL + UI attachments	2026-05-10 07:06:05 +08:00
simple.py	初始化：独立 oclaw 仓库首提交	2026-04-24 22:31:22 +08:00