SurfSense/surfsense_backend/app/tasks/chat/streaming/flows
CREDO23 885d4acda9 refactor(chat): add streaming/flows/resume_chat/ per-concern leaf modules
Three focused modules used by the upcoming resume-chat orchestrator:

* runtime_context: build_resume_chat_runtime_context assembles the
  SurfSenseContextSchema for a resume turn (handles empty mention
  lists, since resume requests do not carry fresh @-mentions).
* assistant_shell: persist_resume_assistant_shell writes a fresh
  assistant row for the resumed turn so the post-stream finalize
  has a target.
* resume_routing: build_resume_routing collects the pending
  interrupts across paused subagents and slices the flat list of
  ResumeDecision[] into the correct (thread, subagent) buckets so
  LangGraph routes each decision back to the right paused tool call.

Add-only; no orchestrator yet (next commit).
2026-05-25 21:50:03 +02:00
..
new_chat refactor(chat): add streaming/flows/new_chat/orchestrator.stream_new_chat 2026-05-25 21:49:55 +02:00
resume_chat refactor(chat): add streaming/flows/resume_chat/ per-concern leaf modules 2026-05-25 21:50:03 +02:00
shared refactor(chat): add streaming/flows/shared/assistant_finalize.py 2026-05-25 21:49:31 +02:00