@mobileai/react-native 0.5.4 → 0.5.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +0 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -34,8 +34,6 @@ Wrap your navigation with `<AIAgent>`. The AI automatically understands your ent
|
|
|
34
34
|
### 🎤 Voice Mode (Live Agent)
|
|
35
35
|
- 🗣️ **Real-time voice chat** — Bidirectional audio with Gemini Live API. Speak naturally, the agent responds with voice.
|
|
36
36
|
- 🔄 **Screen change detection** — The agent automatically detects when the screen changes (e.g., loading finishes) and updates its context — no polling tool needed.
|
|
37
|
-
- 🛡️ **Tool-first protocol** — Tool calls are emitted before speech to prevent server crashes (Gemini Live API limitation).
|
|
38
|
-
- 🔇 **Audio gating** — Mic is automatically paused during tool execution and resumed after, preventing race conditions.
|
|
39
37
|
- 🚫 **Auto-navigation guard** — Code-level gate rejects tool calls before the user speaks, preventing the model from acting on screen context alone.
|
|
40
38
|
|
|
41
39
|
### Security & Production
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mobileai/react-native",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.5",
|
|
4
4
|
"description": "Build autonomous AI agents for React Native and Expo apps. Provides AI-native UI traversal, tool calling, and structured reasoning.",
|
|
5
5
|
"main": "./lib/module/index.js",
|
|
6
6
|
"source": "./src/index.ts",
|