supermemory/apps
Ishaan Gupta 0e604c8384 fix(livekit): keep memory scoped to the caller and bound capture writes
From review of 5b2a435e:

- Captured turns now keep the container tag and document id they were
  spoken under. Rebinding the instance used to flush earlier turns into
  the new caller's scope. Turns captured before any bind still go to the
  first caller bound.
- Recall strips earlier injected memory before it runs, so a failed or
  empty recall can no longer leave another caller's memory in context.
  For the same caller, a slow or failed recall falls back to the profile
  loaded by preload.
- The recall cache is keyed on the user message, not its text, so a
  later turn with the same words recalls again.
- Capture writes time out after 10s and keep their turns for retry,
  including on cancellation. Large calls are written in chunks of at
  most 100k characters, and the buffer is capped.
- remember falls back to the default processing schedule when the
  organization has no balance for instant processing (HTTP 402).
- Docs state the measured delays: about a minute for remember, 10 to 20
  minutes for captured calls on the default dynamic schedule.
2026-10-02 00:35:38 +05:30
..
docs fix(livekit): keep memory scoped to the caller and bound capture writes 2026-10-02 00:35:38 +05:30
mcp fix(mcp): treat full-scope read grants as read-only 2026-09-22 18:22:26 -07:00
memory-graph-playground fix(deps): bump next to 16.3.3 in chatapp, sdk-playground, and memory-graph-playground (#1655) 2026-09-09 23:01:32 -07:00
raycast-extension fix(mcp): bound tool inputs and scope get_document to the active space (#1593) 2026-08-24 21:36:04 +00:00
sdk-playground fix(deps): bump next to 16.3.3 in chatapp, sdk-playground, and memory-graph-playground (#1655) 2026-09-09 23:01:32 -07:00
web chore(web): reduce the app to a redirect shell, drop the browser extension (#1651) 2026-09-07 19:56:46 +00:00