@tencent-ai/agent-sdk 0.3.142 → 0.3.144

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/cli/CHANGELOG.md CHANGED
@@ -7,6 +7,23 @@ CodeBuddy Code 的所有重要更新都会记录在这里。
7
7
 
8
8
  ## [未发布]
9
9
 
10
+ ## [2.94.3] - 2026-04-29
11
+
12
+ ### 🔧 功能改进
13
+
14
+ - **模型兼容适配匹配增强**:模型兼容适配器的模型 ID 匹配新增"分段边界子串"兜底规则,覆盖 `org/xxx-model` 这类带命名空间前缀的自定义模型 ID;同时保留精确/前缀匹配优先级并通过边界限制避免短标识误伤
15
+
16
+ ### 🐛 问题修复
17
+
18
+ - **DeepSeek V4+ 思考模式兼容**:修复自定义 DeepSeek V4 模型(如 `deepseek-v4-flash`)在多轮对话中报 `The reasoning_content in the thinking mode must be passed back to the API` 400 错误的问题。现在即使当前轮未显式启用思考模式,只要历史消息中存在推理字段,也会正确补齐回传
19
+ - **错误信息解析**:兼容 OpenAI 格式(`{error: {message, code, type}}`)的上游错误响应,使自定义模型返回的具体报错可在界面中展示,不再被统一替换为 "Server error" 占位文案;解析失败时也会保留原始响应体而非丢弃
20
+
21
+ ## [2.94.2] - 2026-04-28
22
+
23
+ ### 🐛 问题修复
24
+
25
+ - **私有化部署检测**:移除通过企业端点配置推断 Self-Hosted 部署类型的逻辑,避免在配置了企业端点但实际为云托管场景时错误地将部署类型标记为 Self-Hosted
26
+
10
27
  ## [2.94.1] - 2026-04-28
11
28
 
12
29
  ### 🐛 问题修复