Topic: Gemini 3.1 Flash Live —

generate_reply

still blocked in v1.5.4 Hi team, I am running a self-hosted LiveKit instance with the Python Agents SDK and I am hitting a hard blocker with proactive greetings. Environment: •

livekit-agents==1.5.4

•

livekit-plugins-google==1.5.4

• Model:

gemini-3.1-flash-live-preview

The Issue: I am trying to make the agent "speak first" immediately after the session starts. However, the

generate_reply

command is being explicitly ignored by the Google plugin. Relevant Logs:

[WARNING] livekit.plugins.google: generate_reply is not compatible with 'gemini-3.1-flash-live-preview' and will be ignored.

[ERROR] livekit.agents: failed to generate a reply: generate_reply is not compatible with 'gemini-3.1-flash-live-preview'

I thought the v1.5.4 update addressed the protocol shift for 3.1. Is there a different method we should be using for assistant-initiated turns (like

push_text

or a specific session setting), or is

generate_reply

still intentionally disabled for this model? Any guidance would be appreciated!

Hi David Paulos, ⚠️ This channel will be deleted soon ⚠️ Please use our new community at https://community.livekit.io for technical discussions and to post technical questions. The Slack community is not going away, but we are migrating technical questions to our new forum. Please see full details here.