Ubuntu 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

..

brains

feat: persist photos and enrich conversation history

2026-08-05 16:14:03 +08:00

pipecat

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

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

tools

feat(mcp): enhance MCP transport support and add server management UI

2026-07-19 12:04:11 +08:00

workflow

feat: add realtime workflow vision tools

2026-08-05 13:35:00 +08:00

__init__.py

Initial commit: AI Video Assistant fullstack platform.

2026-06-08 13:51:28 +08:00

action_runtime.py

feat: add prompt startup actions and shared vision config

2026-08-01 23:31:14 +08:00

action_stage.py

feat: add deterministic message interaction stages

2026-08-03 07:10:41 +08:00

auth.py

Add workflow support and enhance runtime configuration in models and services

2026-07-13 16:13:27 +08:00

client_tools.py

feat: persist photos and enrich conversation history

2026-08-05 16:14:03 +08:00

config_resolver.py

refactor: unify system tools as resources

2026-08-04 17:05:26 +08:00

conversation_history.py

Improve image upload in debug drawer

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

fixed_speech.py

fix(workflow): prevent fixed speech continuation

2026-08-03 13:02:31 +08:00

input_assets.py

feat: support uploaded images in debug voice preview

2026-08-05 19:52:37 +08:00

interface_catalog.py

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

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

knowledge.py

feat: persist photos and enrich conversation history

2026-08-05 16:14:03 +08:00

masking.py

Refactor backend to support interface-definition driven model resources

2026-06-14 19:36:12 +08:00

message_policy.py

feat(workflow): enhance message stages and image routing

2026-08-03 12:38:02 +08:00

message_stage.py

feat: add prompt opening behavior modes

2026-08-04 13:29:21 +08:00

model_resource_tester.py

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

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

node_specs.py

feat: add realtime workflow vision tools

2026-08-05 13:35:00 +08:00

object_storage.py

feat: persist photos and enrich conversation history

2026-08-05 16:14:03 +08:00

runtime_variables.py

feat: add session updates and message dialogs

2026-07-31 00:01:01 +08:00

system_tools.py

refactor: unify system tools as resources

2026-08-04 17:05:26 +08:00

tool_executor.py

feat: add session-scoped client tool waits

2026-07-31 23:53:47 +08:00

tool_policy.py

feat: add session-scoped client tool waits

2026-07-31 23:53:47 +08:00

tool_resources.py

feat: add MCP tool integration

2026-07-18 00:00:06 +08:00

vision.py

feat: support uploaded images in debug voice preview

2026-08-05 19:52:37 +08:00

webrtc_ice.py

Configure self-hosted STUN for remote WebRTC

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

workflow_engine.py

feat(workflow): add edge-tool routing and realtime runtime

2026-08-04 22:29:04 +08:00

workflow_router.py

feat: route workflow image inputs natively

2026-08-03 10:55:57 +08:00