Agent-Intent/intent/recognizer_test.go

package intent

import (
	"context"
	"errors"
	"os"
	"reflect"
	"strings"
	"testing"
)

// buildDemoRegistry 按消费方典型形态组装：守卫内容 Go 内置（受保护域），
// 业务意图来自 JSON 配置目录。
func buildDemoRegistry(t *testing.T) (*Registry, *Snapshot) {
	t.Helper()
	b := newTestBuilder()
	if err := b.Register(demoGuardSpec()); err != nil {
		t.Fatal(err)
	}
	reg, err := b.BuildFS(context.Background(), os.DirFS("testdata"), "specs")
	if err != nil {
		t.Fatalf("build: %v", err)
	}
	return reg, reg.Snapshot()
}

func TestRecognizeGuardHit(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	res, err := rec.Recognize(context.Background(), "帮我改一下系统网关地址", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchGuardHit || res.Top == nil || res.Top.ID != "guard.config_change" {
		t.Fatalf("guard result: %+v", res)
	}
	if res.Top.Risk != RiskHigh || res.Top.Handler != "refuse.and_guide" {
		t.Fatalf("guard candidate: %+v", res.Top)
	}
	if len(res.Candidates) == 0 || res.Candidates[0].ID != "guard.config_change" {
		t.Fatalf("guard candidates: %+v", res.Candidates)
	}
}

func TestRecognizeMatchedWithSlot(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	res, err := rec.Recognize(context.Background(), "查询任务 42 的进度", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchMatched || res.Top == nil || res.Top.ID != "demo.run.status_query" {
		t.Fatalf("matched result: %+v", res)
	}
	if res.Top.Slots["run_id"] != "42" {
		t.Fatalf("slots: %+v", res.Top.Slots)
	}
	if res.Top.Handler != "taskrun.query_status" || res.Top.Risk != RiskLow {
		t.Fatalf("candidate metadata: %+v", res.Top)
	}
	if res.Top.Reason == "" {
		t.Fatal("reason empty")
	}
}

func TestRecognizeExcludedTermFallsBack(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	// 硬负例：否定写 + 只读式提问不得误触（含"配置"排除词，也不是守卫词）。
	res, err := rec.Recognize(context.Background(), "怎么配置查询进度", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchFallback || res.Top != nil {
		t.Fatalf("expected fallback, got %+v", res)
	}
}

func TestRecognizePatternBonus(t *testing.T) {
	b := NewRegistryBuilder(Options{})
	if err := b.Register(IntentSpec{
		ID:      "demo.deploy.check",
		Domain:  "demo",
		Version: 1,
		Matcher: MatchSpec{
			IncludesAny: []string{"部署"},
			Patterns:    []string{"(?:执行|跑).{0,4}部署"},
		},
		Confidence: ConfidenceSpec{Base: 0.7, PatternBonus: 0.2, Threshold: 0.75},
	}); err != nil {
		t.Fatal(err)
	}
	reg, err := b.Build()
	if err != nil {
		t.Fatal(err)
	}
	rec := NewRecognizer(Options{}, nil, nil)

	// 仅词条命中：base 0.7 < threshold 0.75，不过阈。
	res, _ := rec.Recognize(context.Background(), "部署", reg.Snapshot())
	if res.Branch != BranchFallback {
		t.Fatalf("term-only should stay below threshold: %+v", res)
	}
	// 词条 + 模式命中：0.7 + 0.2 = 0.9 过阈。
	res, _ = rec.Recognize(context.Background(), "帮我执行一下部署", reg.Snapshot())
	if res.Branch != BranchMatched || res.Top.ID != "demo.deploy.check" {
		t.Fatalf("pattern bonus should pass threshold: %+v", res)
	}
	if res.Top.Confidence != 0.9 {
		t.Fatalf("confidence: %v", res.Top.Confidence)
	}
}

func TestRecognizeAmbiguousAndPriorityOrder(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	res, err := rec.Recognize(context.Background(), "你好呀", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchAmbiguous || res.Top != nil {
		t.Fatalf("expected ambiguous without top: %+v", res)
	}
	if len(res.Candidates) < 2 {
		t.Fatalf("expected >=2 candidates: %+v", res.Candidates)
	}
	// 同分按 priority 降序：hello(10) 在 hi(5) 前。
	if res.Candidates[0].ID != "demo.greet.hello" || res.Candidates[1].ID != "demo.greet.hi" {
		t.Fatalf("priority order: %+v", res.Candidates)
	}
}

type stubClassifier struct {
	scores map[string]float64
	err    error
}

func (s stubClassifier) Refine(ctx context.Context, input string, cands []Candidate) ([]Candidate, error) {
	if s.err != nil {
		return nil, s.err
	}
	out := append([]Candidate(nil), cands...)
	for i := range out {
		if v, ok := s.scores[out[i].ID]; ok {
			out[i].Confidence = v
		}
	}
	return out, nil
}

func TestRecognizeClassifierResolvesAmbiguity(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	cls := stubClassifier{scores: map[string]float64{"demo.greet.hello": 0.9, "demo.greet.hi": 0.3}}
	rec := NewRecognizer(Options{}, nil, cls)
	res, err := rec.Recognize(context.Background(), "你好呀", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchMatched || res.Top == nil || res.Top.ID != "demo.greet.hello" {
		t.Fatalf("classifier should resolve: %+v", res)
	}
	if !strings.Contains(res.Top.Reason, "refined_by=classifier") {
		t.Fatalf("reason missing refine marker: %q", res.Top.Reason)
	}
}

func TestRecognizeClassifierFailureKeepsAmbiguous(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, stubClassifier{err: errors.New("llm down")})
	res, err := rec.Recognize(context.Background(), "你好呀", snap)
	if err != nil {
		t.Fatalf("classifier failure must not fail recognition: %v", err)
	}
	if res.Branch != BranchAmbiguous || res.Top != nil {
		t.Fatalf("expected ambiguous kept: %+v", res)
	}
}

type stubExpectation struct {
	pending *PendingExpectation
}

func (s stubExpectation) Pending(ctx context.Context) *PendingExpectation { return s.pending }

func TestRecognizeExpectationHit(t *testing.T) {
	_, snap := buildDemoRegistry(t)

	// 无挂起预期时该输入落在规则歧义（0.8 vs 0.75，差 0.05 < margin 0.1）。
	plain := NewRecognizer(Options{}, nil, nil)
	res, _ := plain.Recognize(context.Background(), "任务重启 进度", snap)
	if res.Branch != BranchAmbiguous {
		t.Fatalf("expected ambiguous without expectation: %+v", res)
	}

	// 宿主声明挂起预期后，同输入确定命中预期意图。
	exp := stubExpectation{pending: &PendingExpectation{IntentIDs: []string{"demo.run.restart"}, Reason: "确认重启"}}
	rec := NewRecognizer(Options{}, exp, nil)
	res, err := rec.Recognize(context.Background(), "任务重启 进度", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchExpectationHit || res.Top == nil || res.Top.ID != "demo.run.restart" {
		t.Fatalf("expectation result: %+v", res)
	}
}

func TestRecognizeRequiredSlotMissing(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	res, err := rec.Recognize(context.Background(), "取消一下", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchMatched || res.Top == nil || res.Top.ID != "demo.run.cancel" {
		t.Fatalf("matched: %+v", res)
	}
	if len(res.Top.MissingRequiredSlots) != 1 || res.Top.MissingRequiredSlots[0] != "run_id" {
		t.Fatalf("missing slots: %+v", res.Top.MissingRequiredSlots)
	}
}

func TestRecognizeCaseFolding(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	res, err := rec.Recognize(context.Background(), "please DEPLOY it", snap)
	if err != nil {
		t.Fatal(err)
	}
	if res.Branch != BranchMatched || res.Top.ID != "demo.misc.deploy" {
		t.Fatalf("case fold: %+v", res)
	}
}

func TestRecognizeEmptyInputFallsBack(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	for _, in := range []string{"", "   ", "\t\n"} {
		res, err := rec.Recognize(context.Background(), in, snap)
		if err != nil {
			t.Fatal(err)
		}
		if res.Branch != BranchFallback || res.Top != nil {
			t.Fatalf("input %q: %+v", in, res)
		}
	}
}

func TestRecognizeNilSnapshot(t *testing.T) {
	rec := NewRecognizer(Options{}, nil, nil)
	_, err := rec.Recognize(context.Background(), "x", nil)
	var e *Error
	if !errors.As(err, &e) || e.Code != InvalidArgument {
		t.Fatalf("expected sys.invalid_argument, got %v", err)
	}
}

func TestRecognizeOverlongInput(t *testing.T) {
	// 输入上限随快照构建（阈值类参数在快照内），识别器不单独限制。
	b := NewRegistryBuilder(Options{MaxInputLen: 16})
	reg, err := b.Build()
	if err != nil {
		t.Fatal(err)
	}
	rec := NewRecognizer(Options{}, nil, nil)
	_, err = rec.Recognize(context.Background(), "这一段输入超过了十六字节的长度上限用于验证", reg.Snapshot())
	var e *Error
	if !errors.As(err, &e) || e.Code != InvalidArgument {
		t.Fatalf("expected sys.invalid_argument, got %v", err)
	}
	if e.Fields["max_len"] != 16 {
		t.Fatalf("fields: %v", e.Fields)
	}
}

func TestRecognizeDeterministic(t *testing.T) {
	_, snap := buildDemoRegistry(t)
	rec := NewRecognizer(Options{}, nil, nil)
	for _, in := range []string{"查询任务 42 的进度", "你好呀", "怎么配置查询进度", "帮我改一下系统网关地址"} {
		first, err := rec.Recognize(context.Background(), in, snap)
		if err != nil {
			t.Fatal(err)
		}
		second, err := rec.Recognize(context.Background(), in, snap)
		if err != nil {
			t.Fatal(err)
		}
		if !reflect.DeepEqual(first, second) {
			t.Fatalf("nondeterministic result for %q", in)
		}
		trace1, trace2 := snap.Explain(in), snap.Explain(in)
		if !reflect.DeepEqual(trace1, trace2) {
			t.Fatalf("nondeterministic explain for %q", in)
		}
	}
}

func TestExplainTrace(t *testing.T) {
	_, snap := buildDemoRegistry(t)

	trace := snap.Explain("怎么配置查询进度")
	if trace.Branch != BranchFallback {
		t.Fatalf("branch: %+v", trace)
	}
	found := false
	for _, r := range trace.RulesRejected {
		if r.ID == "demo.run.status_query" && len(r.Reason) > len("excluded_term:") && r.Reason[:len("excluded_term:")] == "excluded_term:" {
			found = true
		}
	}
	if !found {
		t.Fatalf("excluded rejection missing: %+v", trace.RulesRejected)
	}

	trace = snap.Explain("帮我改一下系统网关地址")
	if trace.Branch != BranchGuardHit || trace.TopID != "guard.config_change" || len(trace.Guard) != 1 {
		t.Fatalf("guard trace: %+v", trace)
	}
}

func TestRuleSegmenter(t *testing.T) {
	seg := NewRuleSegmenter()
	got := seg.Segment("查询任务进度，然后把结果发给我。谢谢！")
	want := []string{"查询任务进度", "然后把结果发给我", "谢谢"}
	if !reflect.DeepEqual(got, want) {
		t.Fatalf("segment: %v", got)
	}
	if got := seg.Segment("   "); len(got) != 1 || got[0] != "   " {
		t.Fatalf("blank input should return as-is: %v", got)
	}
}