Merge pull request #100 from cnblogs/adds-thinking-option

feat: support reasoning switch for qwen3 models

Author: ikesnowy

README.md

@@ -123,19 +123,6 @@ var completion = await client.GetQWenCompletionAsync(QWenLlm.QWenMax, prompt);
 Console.WriteLine(completion.Output.Text);
 ```
 
-## Reasoning
-
-Use `completion.Output.Choices![0].Message.ReasoningContent` to access the reasoning content from model.
-
-```csharp
-var history = new List<ChatMessage>
-{
-    ChatMessage.User("Calculate 1+1")
-};
-var completion = await client.GetDeepSeekChatCompletionAsync(DeepSeekLlm.DeepSeekR1, history);
-Console.WriteLine(completion.Output.Choices[0]!.Message.ReasoningContent);
-```
-
 ## Multi-round chat
 
 ```csharp
@@ -153,6 +140,36 @@ var completion = await client.GetQWenChatCompletionAsync(QWenLlm.QWenMax, histor
 Console.WriteLine(completion.Output.Choices[0].Message.Content); // The number is 42
 ```
 
+## Reasoning
+
+Use `completion.Output.Choices![0].Message.ReasoningContent` to access the thoughts from reasoning model.
+
+```csharp
+var history = new List<ChatMessage>
+{
+    ChatMessage.User("Calculate 1+1")
+};
+var completion = await client.GetDeepSeekChatCompletionAsync(DeepSeekLlm.DeepSeekR1, history);
+Console.WriteLine(completion.Output.Choices[0]!.Message.ReasoningContent);
+```
+
+### QWen3
+
+Use `TextGenerationParameters.EnableThinking` to toggle reasoning.
+
+```csharp
+var stream = dashScopeClient
+            .GetQWenChatStreamAsync(
+                QWenLlm.QWenPlusLatest,
+                history,
+                new TextGenerationParameters
+                {
+                    IncrementalOutput = true,
+                    ResultFormat = ResultFormats.Message,
+                    EnableThinking = true
+                });
+```
+
 ## Function Call
 
 Creates a function with parameters
@@ -182,7 +199,7 @@ public enum TemperatureUnit
 }
 ```
 
-Append tool information to chat messages.
+Append tool information to chat messages (Here we use `JsonSchema.NET` to generate JSON Schema).
 
 ```csharp
 var tools = new List<ToolDefinition>()

README.zh-Hans.md

@@ -157,6 +157,23 @@ var completion = await client.GetDeepSeekChatCompletionAsync(DeepSeekLlm.DeepSee
 Console.WriteLine(completion.Output.Choices[0]!.Message.ReasoningContent);
 ```
 
+### QWen3
+
+使用 `TextGenerationParameters.EnableThinking` 决定是否使用模型的推理能力。
+
+```csharp
+var stream = dashScopeClient
+            .GetQWenChatStreamAsync(
+                QWenLlm.QWenPlusLatest,
+                history,
+                new TextGenerationParameters
+                {
+                    IncrementalOutput = true,
+                    ResultFormat = ResultFormats.Message,
+                    EnableThinking = true
+                });
+```
+
 ## 工具调用
 
 创建一个可供模型使用的方法。
@@ -182,7 +199,7 @@ public enum TemperatureUnit
 }
 ```
 
-对话时带上方法的名称、描述和参数列表，参数列表以 JSON Schema 的形式提供。
+对话时带上方法的名称、描述和参数列表，参数列表以 JSON Schema 的形式提供（这里使用 `JsonSchema.Net` 库，您也可以使用其它具有类似功能的库）。
 
 ```csharp
 var tools = new List<ToolDefinition>()

sample/Cnblogs.DashScope.Sample/Program.cs

@@ -32,12 +32,12 @@
 switch (type)
 {
     case SampleType.TextCompletion:
-        Console.WriteLine("Prompt > ");
+        Console.Write("Prompt > ");
         userInput = Console.ReadLine()!;
         await TextCompletionAsync(userInput);
         break;
     case SampleType.TextCompletionSse:
-        Console.WriteLine("Prompt > ");
+        Console.Write("Prompt > ");
         userInput = Console.ReadLine()!;
         await TextCompletionStreamAsync(userInput);
         break;
@@ -97,9 +97,14 @@ async Task ChatStreamAsync()
         history.Add(TextChatMessage.User(input));
         var stream = dashScopeClient
             .GetQWenChatStreamAsync(
-                QWenLlm.QWenMax,
+                QWenLlm.QWenPlusLatest,
                 history,
-                new TextGenerationParameters { IncrementalOutput = true, ResultFormat = ResultFormats.Message });
+                new TextGenerationParameters
+                {
+                    IncrementalOutput = true,
+                    ResultFormat = ResultFormats.Message,
+                    EnableThinking = true
+                });
         var role = string.Empty;
         var message = new StringBuilder();
         await foreach (var modelResponse in stream)
@@ -112,7 +117,10 @@ async Task ChatStreamAsync()
             }
 
             message.Append(chunk.Message.Content);
-            Console.Write(chunk.Message.Content);
+            var write = string.IsNullOrEmpty(chunk.Message.ReasoningContent)
+                ? chunk.Message.Content
+                : chunk.Message.ReasoningContent;
+            Console.Write(write);
         }
 
         Console.WriteLine();

src/Cnblogs.DashScope.Core/ITextGenerationParameters.cs

@@ -40,6 +40,11 @@ public interface ITextGenerationParameters
     /// </summary>
     public bool? EnableSearch { get; }
 
+    /// <summary>
+    /// Thinking option. Valid for supported models.(e.g. qwen3)
+    /// </summary>
+    public bool? EnableThinking { get; }
+
     /// <summary>
     /// Available tools for model to call.
     /// </summary>

src/Cnblogs.DashScope.Core/TextGenerationOutputTokenDetails.cs

@@ -0,0 +1,7 @@
+namespace Cnblogs.DashScope.Core;
+
+/// <summary>
+/// Output details for text generation api.
+/// </summary>
+/// <param name="ReasoningTokens">Token count of reasoning content.</param>
+public record TextGenerationOutputTokenDetails(int ReasoningTokens);

src/Cnblogs.DashScope.Core/TextGenerationParameters.cs

@@ -38,6 +38,9 @@ public class TextGenerationParameters : ITextGenerationParameters
     /// <inheritdoc />
     public bool? EnableSearch { get; set; }
 
+    /// <inheritdoc />
+    public bool? EnableThinking { get; set; }
+
     /// <inheritdoc />
     public IEnumerable<ToolDefinition>? Tools { get; set; }
 

src/Cnblogs.DashScope.Core/TextGenerationPromptTokenDetails.cs

@@ -0,0 +1,7 @@
+namespace Cnblogs.DashScope.Core;
+
+/// <summary>
+/// Token usage details.
+/// </summary>
+/// <param name="CachedTokens">Token count of cached input.</param>
+public record TextGenerationPromptTokenDetails(int CachedTokens);

src/Cnblogs.DashScope.Core/TextGenerationTokenDetails.cs

@@ -14,7 +14,12 @@ public class TextGenerationTokenUsage
     /// <summary>
     /// Input token details.
     /// </summary>
-    public TextGenerationTokenDetails? PromptTokensDetails { get; set; }
+    public TextGenerationPromptTokenDetails? PromptTokensDetails { get; set; }
+
+    /// <summary>
+    /// Output token details.
+    /// </summary>
+    public TextGenerationOutputTokenDetails? OutputTokensDetails { get; set; }
 
     /// <summary>
     /// The number of output token.

src/Cnblogs.DashScope.Core/TextGenerationTokenUsage.cs

@@ -9,6 +9,7 @@
     ]
   },
   "parameters": {
-    "incremental_output": false
+    "incremental_output": false,
+    "result_format": "message"
   }
 }

test/Cnblogs.DashScope.Tests.Shared/RawHttpData/single-generation-message-reasoning-nosse.request.body.json

@@ -1,5 +1,5 @@
 {
-  "model": "deepseek-r1",
+  "model": "qwen-plus-latest",
   "input": {
     "messages": [
       {
@@ -9,6 +9,8 @@
     ]
   },
   "parameters": {
-    "incremental_output": true
+    "incremental_output": true,
+    "result_format": "message",
+    "enable_thinking": true
   }
 }