@mastra/voice-google-gemini-live 0.14.0-alpha.0 → 0.14.0

package/CHANGELOG.md

@@ -1,5 +1,41 @@
 # @mastra/voice-google-gemini-live
 
+## 0.14.0
+
+### Minor Changes
+
+- Added `sendContext()` method to `GeminiLiveVoice` for seeding conversation history into a fresh voice session without triggering a model response. This lets apps replay prior turns from Mastra Memory (or any external store) on a cold connect so the model has full context before the user speaks — enabling seamless handoff between text chat and voice on a shared thread. ([#18286](https://github.com/mastra-ai/mastra/pull/18286))
+
+  **Usage:**
+
+  ```ts
+  await voice.connect();
+
+  await voice.sendContext([
+    { role: 'user', content: 'What is the weather?' },
+    { role: 'assistant', content: 'It is 72°F in San Francisco.' },
+  ]);
+
+  // Model stays silent until the user actually speaks
+  await voice.send(micStream);
+  ```
+
+### Patch Changes
+
+- Fix resumeSession() always timing out. Session resumption now works end-to-end: new sessions request server-issued tokens, inbound handles are stored and emitted, and resuming reconnects with the correct handle in the setup frame. ([#18190](https://github.com/mastra-ai/mastra/pull/18190))
+
+- Fix sendContext() being rejected (WS 1007) on gemini-3.1-flash-live-preview by emitting `history_config: { initial_history_in_client_content: true }` in the setup frame. Also exposes `initialHistoryInClientContent` on `GeminiSessionConfig` so callers can opt out explicitly. ([#18368](https://github.com/mastra-ai/mastra/pull/18368))
+
+- Fixed realtime audio streaming being immediately rejected by the Gemini Live API. Audio frames now use the current API format, replacing a deprecated payload shape that caused the connection to close on the first frame. ([#18291](https://github.com/mastra-ai/mastra/pull/18291))
+
+  The `session` event for disconnections now includes `code` and `reason` fields, so consumers can see why the server closed the connection.
+
+## 0.14.0-alpha.1
+
+### Patch Changes
+
+- Fix sendContext() being rejected (WS 1007) on gemini-3.1-flash-live-preview by emitting `history_config: { initial_history_in_client_content: true }` in the setup frame. Also exposes `initialHistoryInClientContent` on `GeminiSessionConfig` so callers can opt out explicitly. ([#18368](https://github.com/mastra-ai/mastra/pull/18368))
+
 ## 0.14.0-alpha.0
 
 ### Minor Changes

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-voice-google-gemini-live
 description: Documentation for @mastra/voice-google-gemini-live. Use when working with @mastra/voice-google-gemini-live APIs, configuration, or implementation.
 metadata:
   package: "@mastra/voice-google-gemini-live"
-  version: "0.14.0-alpha.0"
+  version: "0.14.0"
 ---
 
 ## When to use

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.14.0-alpha.0",
+  "version": "0.14.0",
   "package": "@mastra/voice-google-gemini-live",
   "exports": {},
   "modules": {}

package/dist/index.cjs

@@ -2853,6 +2853,17 @@ var GeminiLiveVoice = class _GeminiLiveVoice extends MastraVoice {
         // { handle } resumes a previous session. Only included when enableResumption is set.
         ...this.options.sessionConfig?.enableResumption && {
           session_resumption: this.isResuming && this.sessionHandle ? { handle: this.sessionHandle } : {}
+        },
+        // history_config opts the session into send_client_content-based history seeding.
+        // Required by gemini-3.1-flash-live-preview (and later 3.x models) for sendContext() to
+        // succeed — without this field in the setup frame the server closes the WebSocket with
+        // code 1007 ("Request contains an invalid argument."). Defaults to true so that
+        // sendContext() works out of the box; set initialHistoryInClientContent: false on
+        // sessionConfig to opt out explicitly.
+        ...this.options.sessionConfig?.initialHistoryInClientContent !== false && {
+          history_config: {
+            initial_history_in_client_content: true
+          }
         }
       }
     };