Merge remote-tracking branch 'upstream/main'

Author: Xiting Zhang

.vscode/cspell.json

@@ -1173,7 +1173,12 @@
         "nbconvert",
         "rollupby",
         "milli",
-        "resourceid"
+        "resourceid",
+        "Exceps",
+        "processiorate",
+        "processiobytessec",
+        "iowait",
+        "softirq"
       ]
     },
     {
@@ -1193,7 +1198,8 @@
         "psutil",
         "psycopg",
         "uninstrument",
-        "uninstrumented"
+        "uninstrumented",
+        "scputimes"
       ]
     },
     {

eng/common/testproxy/target_version.txt

@@ -1 +1 @@
-1.0.0-dev.20250922.2
+1.0.0-dev.20250930.1

sdk/ai/azure-ai-voicelive/CHANGELOG.md

@@ -1,5 +1,51 @@
 # Release History
 
+## 1.0.0 (2025-10-01)
+
+### Features Added
+
+- **Enhanced WebSocket Connection Options**: Significantly improved WebSocket connection configuration with transport-agnostic design:
+  - Added new timeout configuration options: `receive_timeout`, `close_timeout`, and `handshake_timeout` for fine-grained control
+  - Enhanced `compression` parameter to support both boolean and integer types for advanced zlib window configuration
+  - Added `vendor_options` parameter for implementation-specific options passthrough (escape hatch for advanced users)
+  - Improved documentation with clearer descriptions for all connection parameters
+  - Better support for common aliases from other WebSocket ecosystems (`max_size`, `ping_interval`, etc.)
+  - More robust option mapping with proper type conversion and safety checks
+- **Enhanced Type Safety**: Improved type safety for content parts with proper enum usage:
+  - `InputAudioContentPart`, `InputTextContentPart`, and `OutputTextContentPart` now use `ContentPartType` enum values instead of string literals
+  - Better IntelliSense support and compile-time type checking for content part discriminators
+
+### Breaking Changes
+
+- **Improved Naming Conventions**: Updated model and enum names for better clarity and consistency:
+  - `OAIVoice` enum renamed to `OpenAIVoiceName` for more descriptive naming
+  - `ToolChoiceObject` model renamed to `ToolChoiceSelection` for better semantic meaning
+  - `ToolChoiceFunctionObject` model renamed to `ToolChoiceFunctionSelection` for consistency
+  - Updated type unions and imports to reflect the new naming conventions
+  - Cross-language package mappings updated to maintain compatibility across SDKs
+- **Session Model Architecture**: Separated `ResponseSession` and `RequestSession` models for better design clarity:
+  - `ResponseSession` no longer inherits from `RequestSession` and now inherits directly from `_Model`
+  - All session configuration fields are now explicitly defined in `ResponseSession` instead of being inherited
+  - This provides clearer separation of concerns between request and response session configurations
+  - May affect type checking and code that relied on the previous inheritance relationship
+- **Model Cleanup**: Removed unused `AgentConfig` model and related fields from the public API:
+  - `AgentConfig` class has been completely removed from imports and exports
+  - `agent` field removed from `ResponseSession` model (including constructor parameter)
+  - Updated cross-language package mappings to reflect the removal
+- **Model Naming Convention Update**: Renamed `EOUDetection` to `EouDetection` for better naming consistency:
+  - Class name changed from `EOUDetection` to `EouDetection` 
+  - All inheritance relationships updated: `AzureSemanticDetection`, `AzureSemanticDetectionEn`, and `AzureSemanticDetectionMultilingual` now inherit from `EouDetection`
+  - Type annotations updated in `AzureSemanticVad`, `AzureSemanticVadEn`, `AzureSemanticVadMultilingual`, and `ServerVad` classes
+  - Import statements and exports updated to reflect the new naming
+- **Enhanced Content Part Type Safety**: Content part discriminators now use enum values instead of string literals:
+  - `InputAudioContentPart.type` now uses `ContentPartType.INPUT_AUDIO` instead of `"input_audio"`
+  - `InputTextContentPart.type` now uses `ContentPartType.INPUT_TEXT` instead of `"input_text"`  
+  - `OutputTextContentPart.type` now uses `ContentPartType.TEXT` instead of `"text"`
+
+### Other Changes
+
+- Initial GA release
+
 ## 1.0.0b5 (2025-09-26)
 
 ### Features Added

sdk/ai/azure-ai-voicelive/README.md

@@ -5,9 +5,9 @@ This package provides a **real-time, speech-to-speech** client for Azure AI Voic
 It opens a WebSocket session to stream microphone audio to the service and receive
 typed server events (including audio) for responsive, interruptible conversations.
 
-> **Status:** Preview. APIs are subject to change.
+> **Status:** General Availability (GA). This is a stable release suitable for production use.
 
-> **Important:** As of version 1.0.0b5, this SDK is **async-only**. The synchronous API has been removed to focus exclusively on async patterns. All examples and samples use `async`/`await` syntax.
+> **Important:** As of version 1.0.0, this SDK is **async-only**. The synchronous API has been removed to focus exclusively on async patterns. All examples and samples use `async`/`await` syntax.
 
 ---
 
@@ -23,6 +23,8 @@ Getting started
 
 ### Install
 
+Install the stable GA version:
+
 ```bash
 # Base install (core client only)
 python -m pip install azure-ai-voicelive
@@ -34,7 +36,7 @@ python -m pip install "azure-ai-voicelive[aiohttp]"
 python -m pip install azure-ai-voicelive[aiohttp] pyaudio python-dotenv
 ```
 
-The SDK now exclusively provides async-only WebSocket connections using `aiohttp`.
+The SDK provides async-only WebSocket connections using `aiohttp` for optimal performance and reliability.
 
 ### Authenticate
 

sdk/ai/azure-ai-voicelive/apiview-properties.json

@@ -1,7 +1,6 @@
 {
-    "CrossLanguagePackageId": "VoiceLive.WebSocket",
+    "CrossLanguagePackageId": "VoiceLive",
     "CrossLanguageDefinitionId": {
-        "azure.ai.voicelive.models.AgentConfig": "VoiceLive.AgentConfig",
         "azure.ai.voicelive.models.Animation": "VoiceLive.Animation",
         "azure.ai.voicelive.models.ConversationRequestItem": "VoiceLive.ConversationRequestItem",
         "azure.ai.voicelive.models.MessageItem": "VoiceLive.MessageItem",
@@ -13,7 +12,7 @@
         "azure.ai.voicelive.models.AzureVoice": "VoiceLive.AzureVoice",
         "azure.ai.voicelive.models.AzureCustomVoice": "VoiceLive.AzureCustomVoice",
         "azure.ai.voicelive.models.AzurePersonalVoice": "VoiceLive.AzurePersonalVoice",
-        "azure.ai.voicelive.models.EOUDetection": "VoiceLive.EOUDetection",
+        "azure.ai.voicelive.models.EouDetection": "VoiceLive.EouDetection",
         "azure.ai.voicelive.models.AzureSemanticDetection": "VoiceLive.AzureSemanticDetection",
         "azure.ai.voicelive.models.AzureSemanticDetectionEn": "VoiceLive.AzureSemanticDetectionEn",
         "azure.ai.voicelive.models.AzureSemanticDetectionMultilingual": "VoiceLive.AzureSemanticDetectionMultilingual",
@@ -114,8 +113,8 @@
         "azure.ai.voicelive.models.SessionBase": "VoiceLive.SessionBase",
         "azure.ai.voicelive.models.SystemMessageItem": "VoiceLive.SystemMessageItem",
         "azure.ai.voicelive.models.TokenUsage": "VoiceLive.TokenUsage",
-        "azure.ai.voicelive.models.ToolChoiceObject": "VoiceLive.ToolChoiceObject",
-        "azure.ai.voicelive.models.ToolChoiceFunctionObject": "VoiceLive.ToolChoiceFunctionObject",
+        "azure.ai.voicelive.models.ToolChoiceSelection": "VoiceLive.ToolChoiceObject",
+        "azure.ai.voicelive.models.ToolChoiceFunctionSelection": "VoiceLive.ToolChoiceFunctionObject",
         "azure.ai.voicelive.models.UserMessageItem": "VoiceLive.UserMessageItem",
         "azure.ai.voicelive.models.VideoCrop": "VoiceLive.VideoCrop",
         "azure.ai.voicelive.models.VideoParams": "VoiceLive.VideoParams",
@@ -125,8 +124,9 @@
         "azure.ai.voicelive.models.ItemType": "VoiceLive.ItemType",
         "azure.ai.voicelive.models.ItemParamStatus": "VoiceLive.ItemParamStatus",
         "azure.ai.voicelive.models.MessageRole": "VoiceLive.MessageRole",
+        "azure.ai.voicelive.models.ContentPartType": "VoiceLive.ContentPartType",
         "azure.ai.voicelive.models.Modality": "VoiceLive.Modality",
-        "azure.ai.voicelive.models.OAIVoice": "VoiceLive.OAIVoice",
+        "azure.ai.voicelive.models.OpenAIVoiceName": "VoiceLive.OAIVoice",
         "azure.ai.voicelive.models.AzureVoiceType": "VoiceLive.AzureVoiceType",
         "azure.ai.voicelive.models.PersonalVoiceModels": "VoiceLive.PersonalVoiceModels",
         "azure.ai.voicelive.models.OutputAudioFormat": "VoiceLive.OutputAudioFormat",
@@ -139,7 +139,6 @@
         "azure.ai.voicelive.models.ToolChoiceLiteral": "VoiceLive.ToolChoiceLiteral",
         "azure.ai.voicelive.models.ResponseStatus": "VoiceLive.ResponseStatus",
         "azure.ai.voicelive.models.ResponseItemStatus": "VoiceLive.ResponseItemStatus",
-        "azure.ai.voicelive.models.ContentPartType": "VoiceLive.ContentPartType",
         "azure.ai.voicelive.models.ServerEventType": "VoiceLive.ServerEventType"
     }
 }

sdk/ai/azure-ai-voicelive/azure/ai/voicelive/_types.py

@@ -10,5 +10,5 @@
 
 if TYPE_CHECKING:
     from . import models as _models
-Voice = Union[str, "_models.OAIVoice", "_models.OpenAIVoice", "_models.AzureVoice"]
-ToolChoice = Union[str, "_models.ToolChoiceLiteral", "_models.ToolChoiceObject"]
+Voice = Union[str, "_models.OpenAIVoiceName", "_models.OpenAIVoice", "_models.AzureVoice"]
+ToolChoice = Union[str, "_models.ToolChoiceLiteral", "_models.ToolChoiceSelection"]

sdk/ai/azure-ai-voicelive/azure/ai/voicelive/_version.py

@@ -6,4 +6,4 @@
 # Changes may cause incorrect behavior and will be lost if the code is regenerated.
 # --------------------------------------------------------------------------
 
-VERSION = "1.0.0b5"
+VERSION = "1.0.0"