fix(frontend): track playback completion and meaningful inactivity
This commit is contained in:
@@ -9,6 +9,9 @@ the implementation at the recorded date; current operating instructions live in
|
||||
|
||||
### Fixed
|
||||
|
||||
- Keep the voice UI speaking until buffered playback finishes, flush short final audio chunks,
|
||||
and exclude response processing from the user inactivity timeout.
|
||||
|
||||
- Make frontend configuration failures retryable, bound startup requests, and
|
||||
load optional reports independently while waiting for caller context before
|
||||
starting a session. Cancel superseded external reasoning and reject stale
|
||||
|
||||
Reference in New Issue
Block a user