doctate

T

Brummel 44bcc076b4 Defer oneliner regeneration until batch end

Avoid redundant LLM calls by waiting until all recordings in a batch
have been processed before regenerating the oneliner. This change
introduces a helper function `has_pending_recordings` to check for any
`.m4a` files without a corresponding transcript, and the
`update_oneliner` logic now only proceeds if no pending recordings are
found.

2026-04-16 21:10:55 +02:00

docs

Update LLM URL and warn if LLM not configured

2026-04-15 21:12:22 +02:00

scripts

Refactor case listing and silent recording handling

2026-04-16 01:10:52 +02:00

server

Defer oneliner regeneration until batch end

2026-04-16 21:10:55 +02:00

tests/fixtures/dictations

Add per-user whisper settings for hotwords and initial prompt