Add Sentry observability to the `agents`. Introduce a dedicated
`observability.py` module. Refactor both agents to use the shared
observability layer and extract task helpers into a new `tasks.py` module,
making task execution easier to instrument and maintain.
The LiveKit integration was still using RoomInputOptions and
RoomOutputOptions, which emit deprecation warnings.
Update the implementation to use the unified RoomOptions API.
Pin urllib3 to >=2.7.0 via uv constraint-dependencies to fix a moderate
severity decompression DoS vulnerability. Affected versions (2.6.0 to
<2.7.0) could fully decode a compressed response body in a single
operation, leading to excessive CPU and memory consumption.
Pin idna to >=3.15 via uv constraint-dependencies to fix a moderate
severity (CVSS 5.3) information disclosure vulnerability. The flaw is
network-exploitable with no authentication required.
Fix two issues. 1: Missmatch between commands in dev and production in
Dockerfile, leading to unexpected behaviors. 2: Naming of
multi-user-transcriber -> multi-user-transcriber-dev for coherence.
Introduce a new user assignment mechanism to for more friendly output
than the current (SPEAKER_0, SPEAKER_1, ...). Use the VAD metadata to
compare speech intervals with those returned by WhisperX. User with the
highest overlap score above a defined threshold is assigned to each segment.
This method allows for multi-speaker scenarios for a single account.
Introduce MetadataCollector and MetadataCollectorService classes to
centralize the collection and storage of user connections, VAD events,
and chat messages. This creates a structured foundation for future speaker
assignment logic based on voice activity detection. Add tests for this new
feature.
Upgrade OpenSSL and related dependencies to address CVE-2025-15467
in meet-agents.
This vulnerability was blocking the image signature workflow, as it
is classified as a critical dependency.
Allow configuring whether a VAD model runs before calling an external ASR API.
Running VAD can save API calls (and costs) when no audible sound is detected,
but comes with the trade-off of additional computational overhead.
The previous attempt to make the Deepgram configuration extensible
introduced unnecessary complexity for a very limited use case and
made it harder to add new STT backends.
Refactor to a deliberately simple and explicit design with minimal
cognitive overhead. Configuration is now fully driven by environment
variables and provides enough flexibility for ops to select and
parameterize the STT backend.
Until a Pull Request is merged with our changes on livekit-agent
to support Kyutai API, we will use a custom and hacky python
library made from Arnaud's researches and published on an
unofficial pypi project page.
Everything is quite "draft" but it allows us to deploy and test
in real situation the work from Arnaud.
Some system dependencies were unexpectedly missing, causing the
LiveKit agent framework to fail at runtime.
Install the required dependencies based on runtime error logs.
This fixes Docker image failures in the remote (staging) environment.
lebaudantoine