Files
memoryweave/go/internal/storage/split_notuseful_test.go
T
小唯 9b7b969cd3 feat(memoryweave): GA-P0-1 拆分 not_useful_count → human_not_useful_count / dedup_downweight_count
背景:not_useful_count 被两种语义混写——用户人工点「没用」(feedback.go
MarkNotUseful) 与 dedup/合并流程自动降权(core.go Dedup demote) 都写同一字段。
实测 35010 行里 509 条非零但 human useful 仅 21 ⇒ 字段被混写。P2 自适应阈值
要靠它当标签,统计即垃圾。

改法(AC1-5,禁部署):
- LanceDB(arrow_schema) + sqlite(create/alter) 两侧同步新增
  human_not_useful_count / dedup_downweight_count(additive,不删旧列)
- 两个写入点各写各的:feedback.go→IncrementHumanNotUseful;
  core.go dedup→IncrementDedupDownweight
- not_useful_count 保留 deprecated,新代码不再读(读侧仅 Scan/迁移保留)
- 存量迁移工具 cmd/split_notuseful(--dry-run 默认,apply 需终审);
  实测存量无可按来源判定行(M=0)→ 全部归 unknown(K=109 存活行),apply=no-op
- 单测 TestSplitNotUsefulFieldIsolation:两写入点写不同字段,相对增量断言

go build/vet/test + rust build 全绿;rust open() schema 演进在副本上
实测补列 human_not_useful_count/dedup_downweight_count 成功。
2026-10-12 14:17:31 +08:00

63 lines
2.4 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package storage
import "testing"
// TestSplitNotUsefulFieldIsolation — GA-P0-1 (t_718d8707) AC5
//
// 覆盖「两个写入点写不同字段」:
//
// 写入点1(feedback.go MarkNotUseful 人工「没用」)→ IncrementHumanNotUseful
// 写入点2(core.go Dedup 自动降权) → IncrementDedupDownweight
//
// 断言用**相对增量**(绝对值会被其它路径的计数干扰,见 AC5):
//
// 每次调用只 +1 到各自字段,其它两个字段必须原样不变。
func TestSplitNotUsefulFieldIsolation(t *testing.T) {
mlc := NewMemLanceClient(nil)
mlc.mu.Lock()
mlc.memories["mem_split_1"] = &memEntry{ID: "mem_split_1", NotUsefulCount: 3}
mlc.mu.Unlock()
e := mlc.memories["mem_split_1"]
// 写入点1:人工「没用」→ 只加 human_not_useful_count,不动其它两字段
if err := mlc.IncrementHumanNotUseful("mem_split_1"); err != nil {
t.Fatalf("IncrementHumanNotUseful err: %v", err)
}
if e.HumanNotUsefulCount != 1 {
t.Fatalf("human_not_useful_count: 相对增量 +1,want 1 got %d", e.HumanNotUsefulCount)
}
if e.NotUsefulCount != 3 {
t.Fatalf("human 路径不得污染 not_useful_count,want 3 got %d", e.NotUsefulCount)
}
if e.DedupDownweightCount != 0 {
t.Fatalf("human 路径不得污染 dedup_downweight_count,want 0 got %d", e.DedupDownweightCount)
}
// 写入点2:dedup 降权 → 只加 dedup_downweight_count,不动其它两字段
if err := mlc.IncrementDedupDownweight("mem_split_1"); err != nil {
t.Fatalf("IncrementDedupDownweight err: %v", err)
}
if e.DedupDownweightCount != 1 {
t.Fatalf("dedup_downweight_count: 相对增量 +1,want 1 got %d", e.DedupDownweightCount)
}
if e.HumanNotUsefulCount != 1 {
t.Fatalf("dedup 路径不得污染 human_not_useful_count,want 1 got %d", e.HumanNotUsefulCount)
}
if e.NotUsefulCount != 3 {
t.Fatalf("dedup 路径不得污染 not_useful_count,want 3 got %d", e.NotUsefulCount)
}
// AC3:IncrementNotUseful 是 deprecated 历史混写列,仍只动 not_useful_count(向后兼容)
if err := mlc.IncrementNotUseful("mem_split_1"); err != nil {
t.Fatalf("IncrementNotUseful err: %v", err)
}
if e.NotUsefulCount != 4 {
t.Fatalf("not_useful_count(历史列) 相对增量 +1,want 4 got %d", e.NotUsefulCount)
}
if e.HumanNotUsefulCount != 1 || e.DedupDownweightCount != 1 {
t.Fatalf("历史列写入不得污染拆分字段,want human=1 dedup=1 got human=%d dedup=%d",
e.HumanNotUsefulCount, e.DedupDownweightCount)
}
}