Add precision and recall metrics to the multi-turn evaluation

Why: I2 acceptance - the evaluator must emit metrics over a
multiturn fixture no smaller than the existing corpus, not just
print branch names.

Evidence: go vet clean; full suite ok; intentctl eval prints
precision=1.000 recall=1.000 (TP=12 FP=0 FN=0) over the 11-case
multiturn fixture; MetricsOf unit test pins TP/FP/FN counting
including wrong-match counting as both.

Impact: CorpusMetrics + MetricsOf (expectation_hit counts as a
hit); intentctl eval prints the metrics line after the summary;
corpus_multiturn.json expanded to 11 cases (chained expectation,
tie-break, ambiguous, fallback, handler action, clarify paths).

Refs: Documents proposal 2026-10-07-agent-stack-n1q1i1-plans.md I2

cmd/intentctl/main.go

@@ -340,6 +340,22 @@ func cmdEval(args []string) error {
 		fmt.Printf("PASS %-28s %s\n", tc.Name, res.Branch)
 	}
 	fmt.Printf("总计 %d 用例：%d 通过，%d 失败\n", len(corpus.Cases), len(corpus.Cases)-failed, failed)
+	// I2：指标输出（precision/recall 按意图标签计；确定性重跑，不计入通过判定）。
+	var results []intent.CaseResult
+	for _, tc := range corpus.Cases {
+		results = append(results, intent.RunCorpusCase(context.Background(), snap, tc))
+	}
+	metrics := intent.MetricsOf(corpus.Cases, results)
+	p, pok := metrics.Precision()
+	r, rok := metrics.Recall()
+	ps, rs := "-", "-"
+	if pok {
+		ps = fmt.Sprintf("%.3f", p)
+	}
+	if rok {
+		rs = fmt.Sprintf("%.3f", r)
+	}
+	fmt.Printf("指标: precision=%s recall=%s（TP=%d FP=%d FN=%d）\n", ps, rs, metrics.TP, metrics.FP, metrics.FN)
 	if failed > 0 {
 		return fmt.Errorf("%d/%d 用例失败", failed, len(corpus.Cases))
 	}