feat(session): 会话存储体系实现 & Chat多Agent路由

- 新增诊断会话(diagnosis_session/agent_step/tool_invocation)三表
- AgentLoggingHook 持久化 agent_step,记录决策链和耗时
- LookupKnowledgeTool 写入 tool_invocation,记录L0/L1检索质量
- TokenTrackingChatModel 捕获真实token用量
- Chat接口支持意图路由:简单问题单Agent,复杂问题多Agent(Planner+Executor)
- Prompt外置到 src/main/resources/prompts/
- 删除旧 diagnosis_record 表及相关文件
- 新增SessionContextHolder(ThreadLocal传递sessionId)
- QuestionComplexity 复杂度判断工具
- 测试覆盖三张新表的Repository
This commit is contained in:
zhuyongxin
2026-06-26 16:22:05 +08:00
parent a74ccea5be
commit 0d9cce75f9
33 changed files with 1941 additions and 470 deletions
@@ -0,0 +1,45 @@
package com.superbiz.agent.hook;
import org.springframework.ai.chat.model.ChatModel;
import org.springframework.ai.chat.model.ChatResponse;
import org.springframework.ai.chat.prompt.Prompt;
import reactor.core.publisher.Flux;
/**
* ChatModel 包装器 — 捕获每次模型调用的实际 token 用量
* 通过 TokenUsageHolder 传递给 AgentLoggingHook
*/
public class TokenTrackingChatModel implements ChatModel {
private final ChatModel delegate;
public TokenTrackingChatModel(ChatModel delegate) {
this.delegate = delegate;
}
@Override
public ChatResponse call(Prompt prompt) {
ChatResponse response = delegate.call(prompt);
captureTokenUsage(response);
return response;
}
@Override
public Flux<ChatResponse> stream(Prompt prompt) {
return delegate.stream(prompt);
}
private void captureTokenUsage(ChatResponse response) {
try {
if (response.getMetadata() != null && response.getMetadata().getUsage() != null) {
var usage = response.getMetadata().getUsage();
Integer total = usage.getTotalTokens();
if (total != null && total > 0) {
TokenUsageHolder.set(total);
}
}
} catch (Exception e) {
// 不中断模型调用
}
}
}