Merge 'integration_2025-03-06_779226727170' into 'master'

merge branch integration_2025-03-06_779226727170 into master

See merge request: !405

Author: volc-sdk-team

README.md

@@ -54,7 +54,7 @@
     <dependency>
       <groupId>com.volcengine</groupId>
 	  <artifactId>volcengine-java-sdk-bom</artifactId>
-       <version>0.1.154</version>
+       <version>0.1.155</version>
 	  <type>pom</type>
       <scope>import</scope>
     </dependency>
@@ -70,12 +70,12 @@
   <dependency>
     <groupId>com.volcengine</groupId>
     <artifactId>volcengine-java-sdk-vpc</artifactId>
-   <version>0.1.154</version>
+   <version>0.1.155</version>
   </dependency>
   <dependency>
     <groupId>com.volcengine</groupId>
     <artifactId>volcengine-java-sdk-ecs</artifactId>
-   <version>0.1.154</version>
+   <version>0.1.155</version>
   </dependency>
 </dependencies>
 ```

meta.json

@@ -1,4 +1,4 @@
 {
-	"lasted": "0.1.154",
-	"meta_commit": "807488f9af9ba500791689bb532d1048dc429cbe"
+	"lasted": "0.1.155",
+	"meta_commit": "5443d820ac3de24907db8fa7e5ef1298babb09b3"
 }

pom.xml

@@ -4,7 +4,7 @@
     <groupId>com.volcengine</groupId>
     <artifactId>volcengine-java-sdk</artifactId>
     <packaging>pom</packaging>
-    <version>0.1.154</version>
+    <version>0.1.155</version>
     <name>volcengine-java-sdk</name>
     <url>https://open.volcengineapi.com</url>
     <description>The Java SDK For Volcengine</description>

volcengine-java-sdk-advdefence/pom.xml

@@ -3,7 +3,7 @@
     <parent>
         <artifactId>volcengine-java-sdk</artifactId>
         <groupId>com.volcengine</groupId>
-        <version>0.1.154</version>
+        <version>0.1.155</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
     <modelVersion>4.0.0</modelVersion>

volcengine-java-sdk-advdefence20230308/pom.xml

@@ -3,7 +3,7 @@
     <parent>
         <artifactId>volcengine-java-sdk</artifactId>
         <groupId>com.volcengine</groupId>
-        <version>0.1.154</version>
+        <version>0.1.155</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
     <modelVersion>4.0.0</modelVersion>

volcengine-java-sdk-alb/pom.xml

@@ -3,7 +3,7 @@
     <parent>
         <artifactId>volcengine-java-sdk</artifactId>
         <groupId>com.volcengine</groupId>
-        <version>0.1.154</version>
+        <version>0.1.155</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
     <modelVersion>4.0.0</modelVersion>

volcengine-java-sdk-ark-runtime/pom.xml

@@ -3,7 +3,7 @@
     <parent>
         <artifactId>volcengine-java-sdk</artifactId>
         <groupId>com.volcengine</groupId>
-        <version>0.1.154</version>
+        <version>0.1.155</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
     <build>

volcengine-java-sdk-ark-runtime/src/main/java/com/volcengine/ark/runtime/model/completion/chat/ChatCompletionChunk.java

@@ -1,5 +1,6 @@
 package com.volcengine.ark.runtime.model.completion.chat;
 
+import com.fasterxml.jackson.annotation.JsonAlias;
 import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
 import com.volcengine.ark.runtime.model.Usage;
 
@@ -27,6 +28,26 @@ public class ChatCompletionChunk {
      */
     String model;
 
+    /**
+     * Specifies the latency tier to use for processing the request.
+     *
+     *     This parameter is relevant for customers subscribed to the scale tier service:
+     *
+     *     - If set to 'auto', and the endpoint is Scale tier enabled, the system will
+     *       utilize scale tier credits until they are exhausted.
+     *     - If set to 'auto', and the endpoint is not Scale tier enabled, the request will
+     *       be processed using the default service tier with a lower uptime SLA and no
+     *       latency guarentee.
+     *     - If set to 'default', the request will be processed using the default service
+     *       tier with a lower uptime SLA and no latency guarentee.
+     *     - When not set, the default behavior is 'auto'.
+     *
+     *     When this parameter is set, the response body will include the `service_tier`
+     *     utilized.
+     */
+    @JsonAlias("service_tier")
+    String serviceTier;
+
     /**
      * A list of all generated completions.
      */
@@ -69,6 +90,14 @@ public void setModel(String model) {
         this.model = model;
     }
 
+    public String getServiceTier() {
+        return serviceTier;
+    }
+
+    public void setServiceTier(String serviceTier) {
+        this.serviceTier = serviceTier;
+    }
+
     public List<ChatCompletionChoice> getChoices() {
         return choices;
     }
@@ -92,6 +121,7 @@ public String toString() {
                 ", object='" + object + '\'' +
                 ", created=" + created +
                 ", model='" + model + '\'' +
+                ", service_tier='" + serviceTier + '\'' +
                 ", choices=" + choices +
                 ", usage=" + usage +
                 '}';

volcengine-java-sdk-ark-runtime/src/main/java/com/volcengine/ark/runtime/model/completion/chat/ChatCompletionRequest.java

@@ -48,6 +48,26 @@ public class ChatCompletionRequest {
     @JsonProperty("stream_options")
     ChatCompletionRequestStreamOptions streamOptions;
 
+    /**
+     * Specifies the latency tier to use for processing the request.
+     *
+     *     This parameter is relevant for customers subscribed to the scale tier service:
+     *
+     *     - If set to 'auto', and the endpoint is Scale tier enabled, the system will
+     *       utilize scale tier credits until they are exhausted.
+     *     - If set to 'auto', and the endpoint is not Scale tier enabled, the request will
+     *       be processed using the default service tier with a lower uptime SLA and no
+     *       latency guarentee.
+     *     - If set to 'default', the request will be processed using the default service
+     *       tier with a lower uptime SLA and no latency guarentee.
+     *     - When not set, the default behavior is 'auto'.
+     *
+     *     When this parameter is set, the response body will include the `service_tier`
+     *     utilized.
+     */
+    @JsonProperty("service_tier")
+    String serviceTier;
+
     /**
      * Up to 4 sequences where the API will stop generating further tokens.
      */
@@ -120,6 +140,11 @@ public class ChatCompletionRequest {
      */
     Integer n;
 
+    /**
+     * Whether to enable parallel function calling during tool use.
+     */
+    Boolean parallelToolCalls;
+
     @JsonProperty("tool_choice")
     Object toolChoice;
 
@@ -181,6 +206,14 @@ public void setStreamOptions(ChatCompletionRequestStreamOptions streamOptions) {
         this.streamOptions = streamOptions;
     }
 
+    public String getServiceTier() {
+        return serviceTier;
+    }
+
+    public void setServiceTier(String serviceTier) {
+        this.serviceTier = serviceTier;
+    }
+
     public List<String> getStop() {
         return stop;
     }
@@ -277,6 +310,14 @@ public void setN(Integer n) {
         this.n = n;
     }
 
+    public Boolean getParallelToolCalls() {
+        return parallelToolCalls;
+    }
+
+    public void setParallelToolCalls(Boolean parallelToolCalls) {
+        this.parallelToolCalls = parallelToolCalls;
+    }
+
     public Object getToolChoice() {
         return toolChoice;
     }
@@ -302,6 +343,7 @@ public String toString() {
                 ", topP=" + topP +
                 ", stream=" + stream +
                 ", streamOptions=" + streamOptions +
+                ", serviceTier=" + serviceTier +
                 ", stop=" + stop +
                 ", maxTokens=" + maxTokens +
                 ", presencePenalty=" + presencePenalty +
@@ -314,6 +356,7 @@ public String toString() {
                 ", topLogprobs=" + topLogprobs +
                 ", repetitionPenalty=" + repetitionPenalty +
                 ", n=" + n +
+                ", parallelToolCalls=" + parallelToolCalls +
                 ", toolChoice=" + toolChoice +
                 ", responseFormat=" + responseFormat +
                 '}';
@@ -444,6 +487,7 @@ public static class Builder {
         private Double topP;
         private Boolean stream;
         private ChatCompletionRequestStreamOptions streamOptions;
+        private String serviceTier;
         private List<String> stop;
         private Integer maxTokens;
         private Double presencePenalty;
@@ -456,6 +500,7 @@ public static class Builder {
         private Integer topLogprobs;
         private Double repetitionPenalty;
         private Integer n;
+        private Boolean parallelToolCalls;
         private Object toolChoice;
         private ChatCompletionRequestResponseFormat responseFormat;
 
@@ -489,6 +534,11 @@ public ChatCompletionRequest.Builder streamOptions(ChatCompletionRequestStreamOp
             return this;
         }
 
+        public ChatCompletionRequest.Builder serviceTier(String serviceTier) {
+            this.serviceTier = serviceTier;
+            return this;
+        }
+
         public ChatCompletionRequest.Builder stop(List<String> stop) {
             this.stop = stop;
             return this;
@@ -549,6 +599,11 @@ public ChatCompletionRequest.Builder n(Integer n) {
             return this;
         }
 
+        public ChatCompletionRequest.Builder parallelToolCalls(Boolean parallelToolCalls) {
+            this.parallelToolCalls = parallelToolCalls;
+            return this;
+        }
+
         public ChatCompletionRequest.Builder toolChoice(String toolChoice) {
             this.toolChoice = toolChoice;
             return this;
@@ -572,6 +627,7 @@ public ChatCompletionRequest build() {
             chatCompletionRequest.setTopP(topP);
             chatCompletionRequest.setStream(stream);
             chatCompletionRequest.setStreamOptions(streamOptions);
+            chatCompletionRequest.setServiceTier(serviceTier);
             chatCompletionRequest.setStop(stop);
             chatCompletionRequest.setMaxTokens(maxTokens);
             chatCompletionRequest.setPresencePenalty(presencePenalty);
@@ -584,6 +640,7 @@ public ChatCompletionRequest build() {
             chatCompletionRequest.setTopLogprobs(topLogprobs);
             chatCompletionRequest.setRepetitionPenalty(repetitionPenalty);
             chatCompletionRequest.setN(n);
+            chatCompletionRequest.setParallelToolCalls(parallelToolCalls);
             chatCompletionRequest.setToolChoice(toolChoice);
             chatCompletionRequest.setResponseFormat(responseFormat);
             return chatCompletionRequest;

volcengine-java-sdk-ark-runtime/src/main/java/com/volcengine/ark/runtime/model/completion/chat/ChatCompletionResult.java

@@ -1,5 +1,6 @@
 package com.volcengine.ark.runtime.model.completion.chat;
 
+import com.fasterxml.jackson.annotation.JsonAlias;
 import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
 import com.volcengine.ark.runtime.model.Usage;
 
@@ -28,6 +29,26 @@ public class ChatCompletionResult {
      */
     String model;
 
+    /**
+     * Specifies the latency tier to use for processing the request.
+     *
+     *     This parameter is relevant for customers subscribed to the scale tier service:
+     *
+     *     - If set to 'auto', and the endpoint is Scale tier enabled, the system will
+     *       utilize scale tier credits until they are exhausted.
+     *     - If set to 'auto', and the endpoint is not Scale tier enabled, the request will
+     *       be processed using the default service tier with a lower uptime SLA and no
+     *       latency guarentee.
+     *     - If set to 'default', the request will be processed using the default service
+     *       tier with a lower uptime SLA and no latency guarentee.
+     *     - When not set, the default behavior is 'auto'.
+     *
+     *     When this parameter is set, the response body will include the `service_tier`
+     *     utilized.
+     */
+    @JsonAlias("service_tier")
+    String serviceTier;
+
     /**
      * A list of all generated completions.
      */
@@ -70,6 +91,14 @@ public void setModel(String model) {
         this.model = model;
     }
 
+    public String getServiceTier() {
+        return serviceTier;
+    }
+
+    public void setServiceTier(String serviceTier) {
+        this.serviceTier = serviceTier;
+    }
+
     public List<ChatCompletionChoice> getChoices() {
         return choices;
     }
@@ -93,6 +122,7 @@ public String toString() {
                 ", object='" + object + '\'' +
                 ", created=" + created +
                 ", model='" + model + '\'' +
+                ", service_tier='" + serviceTier + '\'' +
                 ", choices=" + choices +
                 ", usage=" + usage +
                 '}';