fix(agent): harden live diagnosis skill observability

This commit is contained in:
aruo
2026-07-07 00:20:34 +08:00
parent 64adb998cf
commit b3315ead52
20 changed files with 792 additions and 26 deletions
@@ -86,10 +86,61 @@ class ChatServiceSequentialAgentTest {
"sequential-low-confidence-session"
);
assertTrue(result.answer().contains("EXECUTOR_FINAL_ANSWER"));
assertTrue(result.answer().startsWith("以下结论基于当前已获取证据"));
assertFalse(result.answer().contains("EXECUTOR_FINAL_ANSWER"));
assertTrue(result.answer().contains("当前缺口"));
assertEquals(List.of("chat_planner", "chat_executor", "chat_verifier"), chatModel.agentCalls);
}
@Test
void executeChatComplexLowConfidenceConfirmedFactsOnlyUseDirectEvidence() throws Exception {
ChatService chatService = createChatService();
ScriptedChatModel chatModel = new ScriptedChatModel("""
{
"verdict": "LOW_CONFID",
"groundedness_score": 0.37,
"critical_fact_count": 3,
"facts_checked": [
{
"fact": "连接池耗尽 active=50/50",
"is_critical": true,
"verification": "direct_evidence",
"detail": "log evidence",
"evidence_refs": []
},
{
"fact": "临时扩容连接池到 80",
"is_critical": true,
"verification": "indirect_support",
"detail": "suggestion inferred from evidence",
"evidence_refs": []
},
{
"fact": "OOM 导致连接泄漏",
"is_critical": true,
"verification": "no_evidence",
"detail": "missing OOM log",
"evidence_refs": []
}
],
"rationale": "scripted low confidence"
}
""");
ChatService.ChatResult result = chatService.executeChatComplex(
chatModel,
new ToolCallback[0],
"请分析 MySQL 连接池耗尽",
List.of(),
"sequential-low-confid-direct-only-session"
);
assertTrue(result.answer().contains("已确认信息:\n- 连接池耗尽 active=50/50"));
assertFalse(result.answer().contains("临时扩容连接池到 80"));
assertTrue(result.answer().contains("当前缺口:\n- OOM 导致连接泄漏:missing OOM log"));
assertFalse(result.answer().contains("EXECUTOR_FINAL_ANSWER"));
}
@Test
void executeChatComplexFallsBackToLowConfidenceWhenVerifierOutputMissing() throws Exception {
ChatService chatService = createChatService();
@@ -243,6 +294,7 @@ class ChatServiceSequentialAgentTest {
assertTrue(chatModel.executorPromptText.contains("## Skills System"));
assertTrue(chatModel.executorPromptText.contains("diagnose-mysql-connection-pool"));
assertTrue(chatModel.executorPromptText.contains("read_skill"));
assertTrue(chatModel.executorPromptText.contains("只允许对该 skill 调用一次 read_skill"));
assertFalse(chatModel.verifierPromptText.contains("diagnose-mysql-connection-pool"));
assertFalse(chatModel.verifierPromptText.contains("read_skill"));
}