Google Realtime plugin silently swallows empty Gemini responses (port of agents#4249)

[dbloembe]

Bug Description

The @livekit/agents-plugin-google Realtime plugin silently ignores empty server content from Gemini, causing the agent to enter speaking state with no audio output. This is the JS equivalent of the bug fixed in the Python SDK by livekit/agents#4249.

Current Behavior

In realtime_api.ts (line ~1132), when Gemini returns a response with no meaningful server content, the plugin silently drops it:

if (!hasServerContent) {
  response.serverContent = undefined;
  if (LK_GOOGLE_DEBUG) {
    this.#logger.debug('ignoring empty server content');
  }
}

When Gemini sends turnComplete with empty content (a known server-side bug), the generation is marked done but no audio was produced — the agent "speaks" silence.

Expected Behavior

Match the Python SDK fix (PR #4249): raise an APIStatusError on empty responses so the SDK's retry/fallback mechanisms can recover, rather than silently accepting a failed turn.

Impact

In production phone ordering calls using gemini-3.1-flash-live-preview, we observe ~50% of deployed calls experiencing at least one silent stall. The agent enters speaking state but produces no audio. The WebSocket stays open, no error events fire. Our application-level stall recovery (realtime text nudge after 8s) catches most of these, but the plugin should handle this at the source.

• Zero stalls locally (shorter conversations, fewer tool calls)
• High stall rate on deployed agents handling real calls (longer contexts, more tool calls — conditions that worsen the Gemini bug per Bug Report: Gemini Live API Native Audio Premature turnComplete Causes Mid-Sentence Audio Truncation googleapis/python-genai#2117)

Environment

• @livekit/agents-plugin-google: 1.3.4 (also verified in 1.4.0 — still present)
• @livekit/agents: 1.3.4
• Model: gemini-3.1-flash-live-preview
• Runtime: Node.js on LiveKit Cloud (us-east)

Related Issues

• fix(google): handle content blocking and generation failures agents#4249 — Python SDK fix for this exact issue
• Handle Gemini empty responses agents#4066 — Original bug report (Python)
• Bug Report: Gemini Live API Native Audio Premature turnComplete Causes Mid-Sentence Audio Truncation googleapis/python-genai#2117 — Gemini server-side root cause (~40 confirmations)
• Gemini Live API responses cut off prematurely with turnComplete despite incomplete content googleapis/js-genai#707 — Same premature turnComplete in JS SDK
• Gemini 2.5 Flash returns empty streaming responses intermittently , error generating content no response generated agents#4706 — Gemini empty streaming responses (~50% intermittent rate)
• Gemini Native Audio Model Stops Midway While Speaking google-gemini/live-api-web-console#117 — Google acknowledged as "known issue"