supermemory

mirror of https://github.com/supermemoryai/supermemory.git synced 2026-09-30 01:51:28 +00:00

History

Ishaan Gupta 2d281f8cbc fix(livekit): recall once per turn in llm_node and remember instantly Found in live LiveKit Cloud voice calls: - Recalling in on_user_turn_completed changed the turn context, so LiveKit discarded its preemptive generation on every turn with memory. SupermemoryAgent now recalls only in llm_node, and uses the turn hook only for realtime models, which skip llm_node. - A turn with no memory recalled twice (hook, then llm_node), and tool follow-ups recalled again. Each user message is now recalled once; retries and follow-ups share the result. - A preloaded profile made llm_node skip recall for the rest of the call. Fresh recall now replaces the earlier injection. - remember used the default dynamic dreaming, so an explicit fact took about 18 minutes to become recallable. It now uses instant (~40s). The call transcript mode is configurable via capture_dreaming. - recall_timeout defaults to 2s; profile calls measured 0.5-1.4s. - Require livekit-agents>=1.3.6: AgentServer (used in the quick start) arrived in 1.3.1, and 1.3.1-1.3.5 no longer import with current opentelemetry-sdk.	2026-09-28 20:56:25 +05:30
..
workflows	fix(livekit): recall once per turn in llm_node and remember instantly	2026-09-28 20:56:25 +05:30

Ishaan Gupta 2d281f8cbc fix(livekit): recall once per turn in llm_node and remember instantly

Found in live LiveKit Cloud voice calls:

- Recalling in on_user_turn_completed changed the turn context, so
  LiveKit discarded its preemptive generation on every turn with memory.
  SupermemoryAgent now recalls only in llm_node, and uses the turn hook
  only for realtime models, which skip llm_node.
- A turn with no memory recalled twice (hook, then llm_node), and tool
  follow-ups recalled again. Each user message is now recalled once;
  retries and follow-ups share the result.
- A preloaded profile made llm_node skip recall for the rest of the
  call. Fresh recall now replaces the earlier injection.
- remember used the default dynamic dreaming, so an explicit fact took
  about 18 minutes to become recallable. It now uses instant (~40s).
  The call transcript mode is configurable via capture_dreaming.
- recall_timeout defaults to 2s; profile calls measured 0.5-1.4s.
- Require livekit-agents>=1.3.6: AgentServer (used in the quick start)
  arrived in 1.3.1, and 1.3.1-1.3.5 no longer import with current
  opentelemetry-sdk.

2026-09-28 20:56:25 +05:30

workflows

fix(livekit): recall once per turn in llm_node and remember instantly

2026-09-28 20:56:25 +05:30