fix(agent): recall_lessons tokenizer keeps single CJK runes

cloudAgentLessonSearchTokens dropped any token shorter than 2 runes.
That filter was copied from English stop-word logic (a / I), but a single
Han rune such as the ones meaning hook, gag or twist is already a complete
semantic unit in Chinese. When the whole keyword consisted of such runes,
tokens came back empty and cloudAgentSearchLessons silently fell back to
"list the first N lessons" - the user thinks a search happened but gets an
arbitrary list.

Fix: keep a token when it is exactly one Han rune (unicode.Han); single
ASCII/digit runes and empty strings are still dropped as before.

Test: TestLessonSearchTokensKeepsSingleCJKRune fails on the old logic
(got [反转 钩子], want [反转 钩子 梗 钩]) and passes after the fix.
The isomorphic copy in skill_search (cloud_agent_tools.go) is fixed
separately on the #580 branch and deliberately not included here.

Gates: go build ./... and go vet EXIT=0; gofmt clean on LF content; the 3
go-sqlite3 cgo-stub failures in internal/app are pre-existing and unrelated.

backend/internal/app/cloud_agent_lessons.go

@@ -545,7 +545,12 @@ func cloudAgentLessonSearchTokens(keyword string) []string {
 	seen := map[string]bool{}
 	for _, raw := range strings.FieldsFunc(keyword, cloudAgentLessonTokenSeparator) {
 		token := strings.ToLower(strings.TrimSpace(raw))
-		if utf8.RuneCountInString(token) < 2 || seen[token] {
+		// 单字停用词过滤照搬的是英文逻辑（a / I）；汉字单字「梗」「钩」「戏」本身是完整
+		// 语义的最小单位。一刀切丢掉后 tokens 为空，检索会静默回落为「列前 N 条」。
+		// 这里只放行单个汉字的 token，英文/数字单字与空串仍按停用词丢掉。
+		first, size := utf8.DecodeRuneInString(token)
+		singleHan := size == len(token) && unicode.Is(unicode.Han, first)
+		if (!singleHan && utf8.RuneCountInString(token) < 2) || seen[token] {
 			continue
 		}
 		seen[token] = true

backend/internal/app/cloud_agent_lessons_test.go

@@ -414,6 +414,28 @@ func TestLessonSearchTokensAreCapped(t *testing.T) {
 	}
 }
 
+func TestLessonSearchTokensKeepsSingleCJKRune(t *testing.T) {
+	// 单字停用词过滤照搬的是英文逻辑（a / I）；中文单字「梗」「钩」「戏」本身就是完整语义的最小单位，
+	// 被 < 2 一刀切后 tokens 为空，cloudAgentSearchLessons 会静默回落为「列前 N 条」——
+	// 用户以为搜过了，拿到的却是任意清单。
+	got := cloudAgentLessonSearchTokens("反转 钩子 梗 钩")
+	want := []string{"反转", "钩子", "梗", "钩"}
+	if len(got) != len(want) {
+		t.Fatalf("切词结果 %v，期望 %v", got, want)
+	}
+	for index := range want {
+		if got[index] != want[index] {
+			t.Fatalf("切词结果 %v，期望 %v", got, want)
+		}
+	}
+	// 只放行汉字单字：英文/数字单字与空串仍按停用词处理。
+	for _, keyword := range []string{"a", "I", "7", "", "，、。；"} {
+		if tokens := cloudAgentLessonSearchTokens(keyword); len(tokens) != 0 {
+			t.Fatalf("%q 应无候选词，得到 %v", keyword, tokens)
+		}
+	}
+}
+
 func TestLessonMatchScoreRanksByHit(t *testing.T) {
 	tokens := cloudAgentLessonSearchTokens("视频 合并 拼接")
 	strong := model.AgentLesson{Topic: "video.merge-concat-not-a-feature", Situation: "用户要把多条镜头视频合并成一条成片"}