v0.3.0

Coordinated 0.3.0 release across all @ariontalk packages. Headline change: Gemini Live engine migrated from gemini-2.5-flash-native-audio-preview-12-2025 to gemini-3.1-flash-live-preview.

Engine-Gemini 0.3.0

• Migrate to gemini-3.1-flash-live-preview. Default model updated.
• Synchronous tool calls. The model now pauses output until a FunctionResponse arrives. NON_BLOCKING and SILENT scheduling are removed.
• Greeting trigger uses sendRealtimeInput({ text }) instead of sendClientContent text turns (the latter is rejected by 3.1).
• sessionResumption only attached on reconnect when a saved handle exists.
• Listening-state transitions on either generationComplete or turnComplete (3.1 emits these as separate signals; previously stuck on "speaking" if only turnComplete was watched).
• Bumps @google/genai to ^1.50.1.

Token-Server 0.3.0

• Migrate to gemini-3.1-flash-live-preview.
• Drop Behavior.NON_BLOCKING from the highlight tool config.
• Add thinkingConfig.thinkingLevel = LOW for low-latency voice responses.
• Bumps @google/genai to ^1.50.1.
• Private package, not published to npm.

Widget 0.3.0

Version aligned with the rest of the @ariontalk package set. Picks up the new engine via the workspace lockfile. No widget-level API changes.

Core 0.3.0

Version aligned. No functional changes.

Plugin-Silero-VAD 0.3.0

Version aligned. No functional changes.

Upgrading

• If you self-host the token-server, redeploy it (or pull this release) so it stops sending NON_BLOCKING in tool declarations. 3.1 Flash Live closes the WebSocket with code 1008 ("Operation is not implemented") if NON_BLOCKING is present.
• If you pinned gemini-model="gemini-2.5-flash-native-audio-preview-12-2025" explicitly, switch to gemini-3.1-flash-live-preview. The default has changed.
• Custom tool integrations: synchronous tool calls now require sending a FunctionResponse for every tool call, including unhandled ones, otherwise the model stays paused. The bundled engine-gemini already handles this for highlight_and_scroll.

Install

pnpm add @ariontalk/widget
# or via CDN:
# https://cdn.jsdelivr.net/npm/@ariontalk/widget@0.3.0/dist/ariontalk.js

v0.2.0

Widget 0.2.0

Simpler snippet. Using the ArionTalk cloud service now requires just a site key:

<ariontalk-widget site-key="YOUR_SITE_KEY" interactive-highlights></ariontalk-widget>
<script type="module" src="https://cdn.jsdelivr.net/npm/@ariontalk/widget@0.2.0/dist/ariontalk.js" async></script>

engine="gemini" resolves automatically when site-key is present, and the widget points at the cloud service by default.

New FAB customization. label, variant (default / compact), icon (mic / wave).

Minimize state. Sessions can collapse into a compact indicator with status-aware icons (listening / speaking / muted) without ending.

Engine-Gemini 0.2.0

• Scripted session greeting delivered via system instruction.
• Tool responses scheduled with SILENT.
• Page content delivered as context rather than a user-turn instruction.

Core 0.2.0

• SessionTimer.format(seconds, padMinutes?) now accepts an optional second argument. Default behavior changed: minutes are no longer zero-padded. Pass padMinutes: true to restore "01:30" formatting.

Plugin-Silero-VAD 0.2.0

Version alignment across all @ariontalk packages: they now ship at matched versions. No functional changes.

Upgrading

• If you were using token-server="..." + engine="gemini" manually, that still works. New recommended form is site-key="..." alone.
• Removed FAB icon="shield". Use "mic" or "wave".
• @ariontalk/core: direct consumers of SessionTimer.format() will see "1:30" where they previously saw "01:30". Pass padMinutes: true as the second arg to restore the old output.

Install

pnpm add @ariontalk/widget
# or via CDN:
# https://cdn.jsdelivr.net/npm/@ariontalk/widget@0.2.0/dist/ariontalk.js

v0.1.0

Initial public release