[Bug]:HarnessAgent Skill加载工具load_skill_through_path提示Error: Tool not found: load_skill_through_path

```java

package com.ieds.ai.agent;

import io.agentscope.core.ReActAgent;
import io.agentscope.core.agent.RuntimeContext;
import io.agentscope.core.formatter.openai.OpenAIChatFormatter;
import io.agentscope.core.message.Msg;
import io.agentscope.core.model.GenerateOptions;
import io.agentscope.core.model.OpenAIChatModel;
import io.agentscope.core.skill.repository.ClasspathSkillRepository;
import io.agentscope.core.studio.StudioManager;
import io.agentscope.core.studio.StudioMessageHook;
import io.agentscope.core.studio.StudioUserAgent;
import io.agentscope.core.tool.Toolkit;
import io.agentscope.harness.agent.HarnessAgent;
import io.agentscope.harness.agent.filesystem.local.LocalFilesystemWithShell;
import io.agentscope.harness.agent.filesystem.sandbox.BaseSandboxFilesystem;
import io.agentscope.harness.agent.filesystem.sandbox.SandboxBackedFilesystem;
import io.agentscope.harness.agent.filesystem.spec.LocalFilesystemSpec;
import io.agentscope.harness.agent.memory.compaction.CompactionConfig;
import io.agentscope.harness.agent.tool.ShellExecuteTool;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

import java.io.IOException;
import java.nio.file.Paths;
import java.util.UUID;

@SpringBootApplication

public class AgentDemoApplication {

public static void main(String[] args) throws IOException {
SpringApplication.run(AgentDemoApplication.class, args);

OpenAIChatModel chatModel = OpenAIChatModel.builder().baseUrl("https://dashscope.aliyuncs.com/compatible-mode/v1")
.apiKey("").modelName("deepseek-v4-flash")
.generateOptions(GenerateOptions.builder().thinkingBudget(0).build())
.formatter(new OpenAIChatFormatter()).build();
StudioManager.init().studioUrl("http://localhost:3000").project("harness-agent").runName(UUID.randomUUID().toString()).initialize().block();
Toolkit toolkit = new Toolkit();
toolkit.registerTool(new ShellExecuteTool(new LocalFilesystemWithShell("/Users/liuyunhao/Desktop/工作/AI/agent-demo/.agentscope")));
HarnessAgent agent = HarnessAgent.builder()
.name("harness-agent")
.sysPrompt("""

""")
.model(chatModel)
.toolkit(toolkit)
.hook(new StudioMessageHook(StudioManager.getClient()))
.workspace(Paths.get(".agentscope/workspace"))
.filesystem(new LocalFilesystemSpec()
.executeTimeoutSeconds(120)
.inheritEnv(true))
.skillRepository(new ClasspathSkillRepository("skills"))
.compaction(CompactionConfig.builder()
.triggerMessages(30)
.keepMessages(10)
.build())
.build();

RuntimeContext ctx = RuntimeContext.builder()
.sessionId("liuyunhao-session")
.userId("liuyunhao")
.build();
StudioUserAgent user = StudioUserAgent.builder()
.name("liuyunhao")
.studioClient(StudioManager.getClient())
.webSocketClient(StudioManager.getWebSocketClient())
.build();

Msg msg = null;
while (true) {
msg = user.call(msg).block();

if (msg == null || "exit".equalsIgnoreCase(msg.getTextContent())) {
break;
}
msg = agent.call(msg,ctx).block();
}
}

}
```

当执行 agent 的时候trace 中提示Error: Tool not found: load_skill_through_path，如下图，但是使用 ReActAgent 的时候正常。