UbuntuandClaude 8bd781242a fix(workflow): prevent untracked BotStoppedSpeakingFrame from consuming end-node tracked-speech counter ...

The CallEndCoordinator.observe() decremented _tracked_speeches on every
BotStoppedSpeakingFrame, not just the one corresponding to tracked
(end-node) speech.  When a preceding LLM utterance finished between
track_speech() and the actual fixed-speech playback, the counter was
consumed prematurely, ending the call before the end-node message played.

Gate the decrement behind a _current_speech_is_tracked flag that is set
only when BotStartedSpeakingFrame follows a pending tracked-speech start.

Co-Authored-By: Claude <noreply@anthropic.com>

2026-08-05 22:35:06 +08:00

.claude

Add support for Xfyun ASR and TTS services in the backend

2026-06-11 10:51:08 +08:00

backend

fix(workflow): prevent untracked BotStoppedSpeakingFrame from consuming end-node tracked-speech counter

2026-08-05 22:35:06 +08:00

deploy

Configure self-hosted STUN for remote WebRTC

2026-08-05 14:05:22 +08:00

docs

Configure self-hosted STUN for remote WebRTC

2026-08-05 14:05:22 +08:00

frontend

Improve image upload in debug drawer

2026-08-05 21:28:51 +08:00

scripts

Improve Element2 copilot WebRTC tooling and enlarge the audio probe panel.

2026-07-13 12:12:04 +08:00

.DS_Store

Refactor backend configuration management and update environment settings

2026-07-09 21:40:29 +08:00

.env

Add support for image input in model resources and enhance related configurations

2026-07-07 19:41:45 +08:00

.env.example

Configure self-hosted STUN for remote WebRTC

2026-08-05 14:05:22 +08:00

.gitignore

Enhance knowledge base functionality and integrate S3 storage support

2026-07-12 13:58:47 +08:00

AGENTS.md

Update AGENTS.md

2026-08-03 10:56:30 +08:00

docker-compose.yaml

Configure self-hosted STUN for remote WebRTC

2026-08-05 14:05:22 +08:00

Makefile

Implement Alembic for database migrations and update FastAPI initialization

2026-07-09 16:29:10 +08:00

package-lock.json

feat(qwen-audio): add Alibaba Cloud Qwen-Audio Realtime service integration

2026-07-21 15:57:43 +08:00

S

Description

No description provided

2.5 MiB

Languages

Python 53.6%

TypeScript 36.6%

JavaScript 6.4%

MDX 2.9%

CSS 0.3%

Other 0.1%