- The deepen buttons of task rows and Kanban cards open an already linked note (accent colour)
instead of creating another one; the server refuses a second note for a linked task as well.
- "Alle Aufgaben" uses each task's own list columns for the status selector, dot and detail.
- Whisper: send vad_filter (STT_VAD_FILTER, default on) and drop a verbatim repeated tail of
sentences or words from the transcript.
- Task detail: narrower time field, wider date field in the desktop sidebar.
v0.37.2.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- STT_URL switches voice input to an OpenAI-compatible Whisper server
(e.g. speaches); without it the browser's recognition stays. Configured
by environment only, with limits for upload size, parallel jobs, hourly
budget per user and timeout. The demo always uses the browser.
- POST /voice/transcribe forwards recordings and returns the text; nothing
is stored. On startup MindSift waits for the server and asks it to
download the model if missing.
- Admin card shows the active mode and server state, with a test recording.
- docker-compose: optional "whisper" service (speaches 0.8.3 CPU, profile
"whisper", models in ./whisper).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>