conflict

rui-ren · rui-ren · commit 4a103e584a73 · 2026-05-27T15:03:57.000-07:00
diff --git a/samples/cpp/live-audio-transcription/main.cpp b/samples/cpp/live-audio-transcription/main.cpp
@@ -155,7 +155,7 @@ int main(int argc, char* argv[]) {
         session->Settings().sample_rate = 16000;
         session->Settings().channels = 1;
         session->Settings().bits_per_sample = 16;
-        session->Settings().language = "en";
+        session->Settings().language = "en";                  // English (default)
         // Multi-lingual examples:
         // session->Settings().language = "de";     // German
         // session->Settings().language = "zh-CN";  // Chinese (Simplified)
diff --git a/samples/cs/embeddings/Program.cs b/samples/cs/embeddings/Program.cs
@@ -20,7 +20,7 @@
 var catalog = await mgr.GetCatalogAsync();
 
 // Get an embedding model
-var model = await catalog.GetModelAsync("qwen3-0.6b-embedding") ?? throw new Exception("Embedding model not found");
+var model = await catalog.GetModelAsync("qwen3-embedding-0.6b") ?? throw new Exception("Embedding model not found");
 
 // Download the model (the method skips download if already cached)
 await model.DownloadAsync(progress =>
diff --git a/samples/cs/live-audio-transcription/Program.cs b/samples/cs/live-audio-transcription/Program.cs
@@ -25,9 +25,11 @@
 var catalog = await mgr.GetCatalogAsync();
 
 // English-only:
-var model = await catalog.GetModelAsync("nemotron-speech-streaming-en-0.6b") ?? throw new Exception("Model \"nemotron-speech-streaming-en-0.6b\" not found in catalog");
+var modelAlias = "nemotron-speech-streaming-en-0.6b";
 // Multi-lingual (supports 30+ languages including auto-detect):
-// var model = await catalog.GetModelAsync("nvidia-nemotron-3.5-asr-streaming-multilingual-0.6b") ?? throw new Exception("Model \"nvidia-nemotron-3.5-asr-streaming-multilingual-0.6b\" not found in catalog");
+// var modelAlias = "nvidia-nemotron-3.5-asr-streaming-multilingual-0.6b";
+
+var model = await catalog.GetModelAsync(modelAlias) ?? throw new Exception($"Model \"{modelAlias}\" not found in catalog");
 
 await model.DownloadAsync(progress =>
 {
@@ -46,7 +48,7 @@ await model.DownloadAsync(progress =>
 var session = audioClient.CreateLiveTranscriptionSession();
 session.Settings.SampleRate = 16000;  // Default is 16000; shown here to match the NAudio WaveFormat below
 session.Settings.Channels = 1;
-session.Settings.Language = "en";
+session.Settings.Language = "en";                  // English (default)
 // Multi-lingual examples:
 // session.Settings.Language = "de";     // German
 // session.Settings.Language = "zh-CN";  // Chinese (Simplified)
diff --git a/samples/js/embeddings/app.js b/samples/js/embeddings/app.js
@@ -16,7 +16,7 @@ console.log('✓ SDK initialized successfully');
 
 // <model_setup>
 // Get an embedding model
-const modelAlias = 'qwen3-0.6b-embedding';
+const modelAlias = 'qwen3-embedding-0.6b';
 const model = await manager.catalog.getModel(modelAlias);
 
 // Download the model
diff --git a/samples/js/live-audio-transcription/app.js b/samples/js/live-audio-transcription/app.js
@@ -49,7 +49,7 @@ const session = audioClient.createLiveTranscriptionSession();
 session.settings.sampleRate = 16000;  // Default is 16000; shown here for clarity
 session.settings.channels = 1;
 session.settings.bitsPerSample = 16;
-session.settings.language = 'en';
+session.settings.language = 'en';                  // English (default)
 // Multi-lingual examples:
 // session.settings.language = 'de';     // German
 // session.settings.language = 'zh-CN';  // Chinese (Simplified)
diff --git a/samples/python/embeddings/src/app.py b/samples/python/embeddings/src/app.py
@@ -12,7 +12,7 @@ def main():
     manager = FoundryLocalManager.instance
 
     # Select and load an embedding model from the catalog
-    model = manager.catalog.get_model("qwen3-0.6b-embedding")
+    model = manager.catalog.get_model("qwen3-embedding-0.6b")
     model.download(
         lambda progress: print(
             f"\rDownloading model: {progress:.2f}%",
diff --git a/samples/python/live-audio-transcription/src/app.py b/samples/python/live-audio-transcription/src/app.py
@@ -49,7 +49,7 @@
 session = audio_client.create_live_transcription_session()
 session.settings.sample_rate = 16000
 session.settings.channels = 1
-session.settings.language = "en"
+session.settings.language = "en"                  # English (default)
 # Multi-lingual examples:
 # session.settings.language = "de"     # German
 # session.settings.language = "zh-CN"  # Chinese (Simplified)
diff --git a/samples/rust/embeddings/src/main.rs b/samples/rust/embeddings/src/main.rs
@@ -6,7 +6,7 @@
 use foundry_local_sdk::{FoundryLocalConfig, FoundryLocalManager};
 // </imports>
 
-const ALIAS: &str = "qwen3-0.6b-embedding";
+const ALIAS: &str = "qwen3-embedding-0.6b";
 
 #[tokio::main]
 async fn main() -> Result<(), Box<dyn std::error::Error>> {
diff --git a/samples/rust/live-audio-transcription/src/main.rs b/samples/rust/live-audio-transcription/src/main.rs
@@ -60,11 +60,11 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
     println!("✓ Model loaded\n");
 
     let audio_client = model.create_audio_client();
-    let session = audio_client.create_live_transcription_session();
-    // session.settings.language = Some("en".into());    // English (default)
+    let mut session = audio_client.create_live_transcription_session();
+    session.settings.language = Some("en".into());    // English (default)
     // session.settings.language = Some("de".into());    // German
     // session.settings.language = Some("zh-CN".into()); // Chinese (Simplified)
-    // session.settings.language = Some("auto".into());  // Auto-detect
+    // session.settings.language = Some("auto".into());  // Auto-detect language
     let session = Arc::new(session);
     session.start(None).await?;
     println!("✓ Session started\n");
diff --git a/sdk/cpp/CMakeLists.txt b/sdk/cpp/CMakeLists.txt
@@ -81,9 +81,9 @@ endif()
 # -----------------------------
 if(WIN32)
 
-set(FL_CORE_VERSION "1.1.0" CACHE STRING "Microsoft.AI.Foundry.Local.Core NuGet version")
-set(FL_ORT_VERSION "1.25.1" CACHE STRING "Microsoft.ML.OnnxRuntime.Foundry NuGet version")
-set(FL_ORTGENAI_VERSION "0.13.2" CACHE STRING "Microsoft.ML.OnnxRuntimeGenAI.Foundry NuGet version")
+set(FL_CORE_VERSION "1.2.0" CACHE STRING "Microsoft.AI.Foundry.Local.Core NuGet version")
+set(FL_ORT_VERSION "1.26.0" CACHE STRING "Microsoft.ML.OnnxRuntime.Foundry NuGet version")
+set(FL_ORTGENAI_VERSION "0.14.0" CACHE STRING "Microsoft.ML.OnnxRuntimeGenAI.Foundry NuGet version")
 set(FL_NATIVE_DEPS_DIR "${CMAKE_CURRENT_BINARY_DIR}/_native_deps")
 
 function(fl_ensure_nuget_package PKG_NAME PKG_VERSION)
diff --git a/sdk/cpp/README.md b/sdk/cpp/README.md
@@ -61,9 +61,9 @@ This uses the `x64-debug` preset which:
 - Resolves C++ dependencies via **vcpkg** (`nlohmann-json`, `ms-gsl`, `gtest`)
 - Builds with the `x64-windows-static-md` triplet
 - Auto-downloads native runtime DLLs via **NuGet**:
-  - `Microsoft.AI.Foundry.Local.Core` (1.1.0) — Foundry Local core runtime
-  - `Microsoft.ML.OnnxRuntime.Foundry` (1.25.1) — ONNX Runtime
-  - `Microsoft.ML.OnnxRuntimeGenAI.Foundry` (0.13.2) — ONNX Runtime GenAI
+  - `Microsoft.AI.Foundry.Local.Core` (1.2.0) — Foundry Local core runtime
+  - `Microsoft.ML.OnnxRuntime.Foundry` (1.26.0) — ONNX Runtime
+  - `Microsoft.ML.OnnxRuntimeGenAI.Foundry` (0.14.0) — ONNX Runtime GenAI
 
 NuGet packages are cached in `out/build/<preset>/_native_deps/` and only downloaded on first configure. Runtime DLLs are automatically copied next to executables via post-build steps.
 
diff --git a/sdk/cs/src/OpenAI/LiveAudioTypes.cs b/sdk/cs/src/OpenAI/LiveAudioTypes.cs
@@ -36,6 +36,10 @@ public class LiveAudioTranscriptionResponse : ConversationItem
     [JsonPropertyName("end_time")]
     public double? EndTime { get; init; }
 
+    /// <summary>BCP-47 language code detected by the model (e.g. "zh-CN", "en-US"), or null if not detected.</summary>
+    [JsonPropertyName("language")]
+    public string? Language { get; init; }
+
     internal static LiveAudioTranscriptionResponse FromJson(string json)
     {
         var raw = JsonSerializer.Deserialize(json,
@@ -50,6 +54,7 @@ internal static LiveAudioTranscriptionResponse FromJson(string json)
             IsFinal = raw.IsFinal,
             StartTime = raw.StartTime,
             EndTime = raw.EndTime,
+            Language = raw.Language,
             Content =
             [
                 new ContentPart
@@ -79,6 +84,9 @@ internal record LiveAudioTranscriptionRaw
 
     [JsonPropertyName("end_time")]
     public double? EndTime { get; init; }
+
+    [JsonPropertyName("language")]
+    public string? Language { get; init; }
 }
 
 internal record CoreErrorResponse
diff --git a/sdk/cs/test/FoundryLocal.Tests/ChatCompletionsTests.cs b/sdk/cs/test/FoundryLocal.Tests/ChatCompletionsTests.cs
@@ -99,6 +99,11 @@ public async Task DirectChat_Streaming_Succeeds()
             await Assert.That(message.Role).IsEqualTo("assistant");
             await Assert.That(message.Content).IsNotNull();
             responseMessage.Append(message.Content);
+
+            if (response.Choices[0].FinishReason == "stop")
+            {
+                break; // test doesn't handle the usage response
+            }
         }
 
         var fullResponse = responseMessage.ToString();
@@ -123,6 +128,11 @@ public async Task DirectChat_Streaming_Succeeds()
             await Assert.That(message.Role).IsEqualTo("assistant");
             await Assert.That(message.Content).IsNotNull();
             responseMessage.Append(message.Content);
+
+            if (response.Choices[0].FinishReason == "stop")
+            {
+                break; // test doesn't handle the usage response
+            }
         }
 
         fullResponse = responseMessage.ToString();
@@ -270,15 +280,21 @@ public async Task DirectTool_Streaming_Succeeds()
             var content = response.Choices[0].Message.Content;
             await Assert.That(content).IsNotNull();
             Console.WriteLine($"Content in streaming: {content}, Finish reason: {response.Choices[0].FinishReason}");
+
             if (!string.IsNullOrEmpty(content))
             {
                 responseMessage.Append(content);
                 numTokens += 1;
             }
+
             if (response.Choices[0].FinishReason == "tool_calls")
             {
                 toolCallResponse = response;
             }
+            else if (response.Choices[0].FinishReason == "stop")
+            {
+                break; // test doesn't handle the usage response
+            }
         }
 
         // Check that the full response contains the expected tool call and that the tool call information is correct
@@ -329,6 +345,11 @@ public async Task DirectTool_Streaming_Succeeds()
             {
                 responseMessage.Append(content);
             }
+
+            if (response.Choices[0].FinishReason == "stop")
+            {
+                break; // test doesn't handle the usage response
+            }
         }
 
         // Check that the conversation continued
diff --git a/sdk/cs/test/FoundryLocal.Tests/EmbeddingClientTests.cs b/sdk/cs/test/FoundryLocal.Tests/EmbeddingClientTests.cs
@@ -1,4 +1,4 @@
-// --------------------------------------------------------------------------------------------------------------------
+﻿// --------------------------------------------------------------------------------------------------------------------
 // <copyright company="Microsoft">
 //   Copyright (c) Microsoft. All rights reserved.
 // </copyright>
@@ -21,10 +21,10 @@ public static async Task Setup()
         // Reduce max_length in the embedding model's genai_config.json to avoid OOM
         // when allocating the KV cache. Embedding models only need a single forward pass
         // so a large max_length is unnecessary.
-        Utils.PatchModelMaxLength("qwen3-0.6b-embedding-generic-cpu-1", "v1");
+        Utils.PatchModelMaxLength("qwen3-embedding-0.6b-generic-cpu-1", "v1");
 
         // Load the specific cached model variant directly
-        var model = await catalog.GetModelVariantAsync("qwen3-0.6b-embedding-generic-cpu:1").ConfigureAwait(false);
+        var model = await catalog.GetModelVariantAsync("qwen3-embedding-0.6b-generic-cpu:1").ConfigureAwait(false);
         await Assert.That(model).IsNotNull();
 
         await model!.LoadAsync().ConfigureAwait(false);
@@ -52,7 +52,7 @@ public async Task Embedding_BasicRequest_Succeeds()
                                              .ConfigureAwait(false);
 
         await Assert.That(response).IsNotNull();
-        await Assert.That(response.Model).IsEqualTo("qwen3-0.6b-embedding-generic-cpu:1");
+        await Assert.That(response.Model).IsEqualTo("qwen3-embedding-0.6b-generic-cpu:1");
         await Assert.That(response.Data).IsNotNull().And.IsNotEmpty();
         await Assert.That(response.Data[0].Embedding).IsNotNull();
         await Assert.That(response.Data[0].Embedding.Count).IsEqualTo(1024);
@@ -177,7 +177,7 @@ public async Task Embedding_KnownValues_CapitalOfFrance()
 
         // Use tolerance for float32 model outputs which may vary across hardware
         const double tolerance = 2e-3;
-        await Assert.That(Math.Abs(embedding[0] - (-0.02815740555524826))).IsLessThanOrEqualTo(tolerance);
+        await Assert.That(Math.Abs(embedding[0] - (-0.035993535071611404))).IsLessThanOrEqualTo(tolerance);
         await Assert.That(Math.Abs(embedding[1023] - (-0.00887922290712595))).IsLessThanOrEqualTo(tolerance);
     }
 
diff --git a/sdk/cs/test/FoundryLocal.Tests/Utils.cs b/sdk/cs/test/FoundryLocal.Tests/Utils.cs
@@ -244,7 +244,7 @@ private static List<ModelInfo> BuildTestCatalog(bool includeCuda = true)
                     PromptTemplate = common.PromptTemplate,
                     Publisher = common.Publisher, Task = common.Task,
                     FileSizeMb = common.FileSizeMb - 10,  // smaller so default chosen in test that sorts on this
-                    ModelSettings = common.ModelSettings, 
+                    ModelSettings = common.ModelSettings,
                     SupportsToolCalling = common.SupportsToolCalling,
                     License = common.License,
                     LicenseDescription = common.LicenseDescription,
diff --git a/sdk/deps_versions.json b/sdk/deps_versions.json
@@ -1,7 +1,7 @@
 {
   "foundry-local-core": {
-    "nuget": "1.1.0",
-    "python": "1.1.0"
+    "nuget": "1.2.0",
+    "python": "1.2.0"
   },
   "onnxruntime": {
     "version": "1.26.0"
diff --git a/sdk/deps_versions_winml.json b/sdk/deps_versions_winml.json
@@ -1,7 +1,7 @@
 {
   "foundry-local-core": {
-    "nuget": "1.1.0",
-    "python": "1.1.0"
+    "nuget": "1.2.0",
+    "python": "1.2.0"
   },
   "windows-ai-machinelearning": {
     "version": "2.1.1"
diff --git a/sdk/js/test/openai/embeddingClient.test.ts b/sdk/js/test/openai/embeddingClient.test.ts
@@ -13,7 +13,7 @@ describe('Embedding Client Tests', () => {
         expect(cachedModels.length).to.be.greaterThan(0);
 
         const cachedVariant = cachedModels.find(m => m.alias === EMBEDDING_MODEL_ALIAS);
-        expect(cachedVariant, 'qwen3-0.6b-embedding-generic-cpu should be cached').to.not.be.undefined;
+        expect(cachedVariant, `${EMBEDDING_MODEL_ALIAS} should be cached`).to.not.be.undefined;
 
         const model = await catalog.getModel(EMBEDDING_MODEL_ALIAS);
         expect(model).to.not.be.undefined;
diff --git a/sdk/js/test/testUtils.ts b/sdk/js/test/testUtils.ts
@@ -43,7 +43,7 @@ export const TEST_CONFIG: FoundryLocalConfig = {
 };
 
 export const TEST_MODEL_ALIAS = 'qwen2.5-0.5b';
-export const EMBEDDING_MODEL_ALIAS = 'qwen3-0.6b-embedding-generic-cpu';
+export const EMBEDDING_MODEL_ALIAS = 'qwen3-embedding-0.6b';
 
 export function getTestManager() {
     return FoundryLocalManager.create(TEST_CONFIG);
diff --git a/sdk/python/requirements-winml.txt b/sdk/python/requirements-winml.txt
@@ -2,6 +2,6 @@ pydantic>=2.0.0
 requests>=2.32.4
 openai>=2.24.0
 # WinML native binary packages from the ORT-Nightly PyPI feed.
-foundry-local-core-winml==1.1.0
-onnxruntime-core==1.23.2.3
-onnxruntime-genai-core==0.13.2
+foundry-local-core-winml==1.2.0
+onnxruntime-core==1.26.0
+onnxruntime-genai-core==0.14.0
diff --git a/sdk/python/requirements.txt b/sdk/python/requirements.txt
@@ -5,7 +5,7 @@ openai>=2.24.0
 # - Linux x86_64:   onnxruntime-gpu / onnxruntime-genai-cuda (CUDA-enabled wheels).
 # - Linux aarch64:  onnxruntime / onnxruntime-genai (the CUDA variants do not ship aarch64 binaries).
 # - Other platforms: onnxruntime-core / onnxruntime-genai-core (cross-platform variants).
-foundry-local-core==1.1.0
+foundry-local-core==1.2.0
 onnxruntime-core==1.26.0; sys_platform != "linux"
 onnxruntime-gpu==1.26.0; sys_platform == "linux" and platform_machine == "x86_64"
 onnxruntime==1.26.0; sys_platform == "linux" and platform_machine == "aarch64"
diff --git a/sdk/python/test/README.md b/sdk/python/test/README.md
@@ -76,4 +76,5 @@ Tests that require the web service are skipped when either `TF_BUILD=true` (Azur
 | Alias | Use | Variant |
 |---|---|---|
 | `qwen2.5-0.5b` | Chat completions | `qwen2.5-0.5b-instruct-generic-cpu:4` |
-| `whisper-tiny` | Audio transcription | `openai-whisper-tiny-generic-cpu:2` |
+| `whisper-tiny` | Audio transcription | `openai-whisper-tiny-generic-cpu:4` |
+| `qwen3-embedding-0.6b` | Embeddings | `qwen3-embedding-0.6b-generic-cpu:1` |
diff --git a/sdk/python/test/conftest.py b/sdk/python/test/conftest.py
@@ -26,7 +26,7 @@
 
 TEST_MODEL_ALIAS = "qwen2.5-0.5b"
 AUDIO_MODEL_ALIAS = "whisper-tiny"
-EMBEDDING_MODEL_ALIAS = "qwen3-0.6b-embedding-generic-cpu"
+EMBEDDING_MODEL_ALIAS = "qwen3-embedding-0.6b"
 
 def get_git_repo_root() -> Path:
     """Walk upward from __file__ until we find a .git directory."""
diff --git a/sdk/rust/tests/integration/common/mod.rs b/sdk/rust/tests/integration/common/mod.rs
@@ -15,7 +15,7 @@ pub const TEST_MODEL_ALIAS: &str = "qwen2.5-0.5b";
 pub const WHISPER_MODEL_ALIAS: &str = "whisper-tiny";
 
 /// Default model alias used for embedding integration tests.
-pub const EMBEDDING_MODEL_ALIAS: &str = "qwen3-0.6b-embedding-generic-cpu";
+pub const EMBEDDING_MODEL_ALIAS: &str = "qwen3-embedding-0.6b";
 
 /// Expected transcription text fragment for the shared audio test file.
 pub const EXPECTED_TRANSCRIPTION_TEXT: &str =
