mirror of
https://gitcode.com/JianFeeeee/HomeAgent.git
synced 2026-09-23 10:28:06 +00:00
e273924511
★ 上次修复误判了成因。真实根因（本次运行日志 34/34 同形）：
{"command": "…完好的长命令…", "timeout": 20s}
command 一字节没错，只是 timeout 值少了引号 —— cmd_run 的 schema 把 timeout
声明成 string、示例写着 "10s, 1m, 30s"，模型照抄格式却忘了引号。
finish_reason=length 出现 0 次 ⇒ 上次那条"截断"分支从不生效。
旧行为把**整个参数**丢掉，模型只看到 "command is required"，看不出坏在 timeout，
只能原样重试。实测本次运行 cmd_run 失败率 35%（34 败 / 71 成），
12 分钟的任务里更是 48% 时间耗在这上面 —— 每次失败都付一次完整 LLM 往返。
三处改动：
1. repairToolArgsJSON：解析失败时先试窄修复 —— 只给"值位置上未加引号的带单位
数字"补引号，且修完必须真能解析成功才接受。不碰合法 JSON、不动正文里的 20s、
不会把真截断"修好"。
2. 修复仍失败时不再静默降级成空 map，改为带 __arg_error 交给模型，并按成因
分流文案：截断→拆小参数；JSON 写坏→提醒带单位的值要加引号。
3. 统一键名 __arg_error（原 __truncated_error 只覆盖截断，语义过窄）。
同一缺陷面不止 cmd：agentcli/healthcheck/timer 都有 string 类型却以
"5m, 1h" 作示例的参数，此修复一并覆盖。
回归测试：真实日志样本修复、保守性（不碰合法/正文/截断）、
端到端（修复后 timeout 仍能被 time.ParseDuration 接受）。
100 lines
2.3 KiB
Go
100 lines
2.3 KiB
Go
package core
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"gitcode.com/JianFeeeee/HomeAgent/internal/memory/document"
|
|
)
|
|
|
|
func TestEntitySimilarity(t *testing.T) {
|
|
tests := []struct {
|
|
a, b string
|
|
want float64
|
|
}{
|
|
{"", "", 0}, // empty → 0
|
|
{"a", "b", 0}, // single char → 0
|
|
{"张三", "张三", 1.0}, // identical → 1.0
|
|
{"张三", "李四", 0}, // no common bigrams
|
|
{"iPhone", "iPhone 15", 0.625}, // partial overlap
|
|
}
|
|
for _, tt := range tests {
|
|
got := entitySimilarity(tt.a, tt.b)
|
|
if got != tt.want {
|
|
t.Errorf("entitySimilarity(%q, %q) = %.3f, want %.3f", tt.a, tt.b, got, tt.want)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestDocToTriples(t *testing.T) {
|
|
doc := &document.Doc{
|
|
Summary: "用户喜欢编程",
|
|
Content: "用户提到喜欢Go和Python",
|
|
Source: "context",
|
|
}
|
|
|
|
triples := docToTriples(doc, nil)
|
|
|
|
foundSummary := false
|
|
foundSource := false
|
|
for _, tr := range triples {
|
|
switch {
|
|
case tr.Subject == "文档" && tr.Relation == "主题":
|
|
foundSummary = true
|
|
case tr.Subject == "文档" && tr.Relation == "来源":
|
|
foundSource = true
|
|
}
|
|
}
|
|
|
|
if !foundSummary {
|
|
t.Error("missing '主题' triple")
|
|
}
|
|
if !foundSource {
|
|
t.Error("missing '来源' triple")
|
|
}
|
|
}
|
|
|
|
func TestDocToTriplesNil(t *testing.T) {
|
|
triples := docToTriples(nil, nil)
|
|
if len(triples) != 0 {
|
|
t.Errorf("expected empty for nil doc, got %d", len(triples))
|
|
}
|
|
}
|
|
|
|
func TestDocToTriplesNoSource(t *testing.T) {
|
|
doc := &document.Doc{
|
|
Summary: "无来源文档",
|
|
Content: "content",
|
|
}
|
|
triples := docToTriples(doc, nil)
|
|
for _, tr := range triples {
|
|
if tr.Relation == "来源" {
|
|
t.Error("should not have source triple when Source is empty")
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestDocToTriplesTypes(t *testing.T) {
|
|
doc := &document.Doc{
|
|
Summary: "测试三元组类型",
|
|
Content: "用于验证 SubjectType 和 ObjectType",
|
|
Source: "test",
|
|
}
|
|
|
|
triples := docToTriples(doc, nil)
|
|
|
|
for _, tr := range triples {
|
|
if tr.Subject == "文档" {
|
|
if tr.SubjectType != "Concept" {
|
|
t.Errorf("文档 subject_type should be Concept, got %q", tr.SubjectType)
|
|
}
|
|
if tr.Confidence != 1.0 {
|
|
t.Errorf("文档 triple confidence should be 1.0, got %f", tr.Confidence)
|
|
}
|
|
}
|
|
// all should have SubjectType/ObjectType set
|
|
if tr.SubjectType == "" || tr.ObjectType == "" {
|
|
t.Errorf("triple %+v missing SubjectType or ObjectType", tr)
|
|
}
|
|
}
|
|
}
|