Cyrene_v2/internal/runtime/loop/thinking_gate_test.go

package loop

import (
	"context"
	"testing"

	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
)

// thinkingAdapter 发出一个完整的思考分段，后接一个文本分段，
// 并记录它收到的每个请求，使测试能断言循环的
// 推理旋钮确实到达了模型调用。
type thinkingAdapter struct {
	reqs []model.Request
}

func (a *thinkingAdapter) Name() string { return "thinking-mock" }

func (a *thinkingAdapter) Chat(_ context.Context, req model.Request, _ model.Options) (model.Response, error) {
	a.reqs = append(a.reqs, req)
	return model.Response{Content: "Hello"}, nil
}

func (a *thinkingAdapter) ChatStream(_ context.Context, req model.Request, on func(model.StreamEvent)) (model.Response, error) {
	a.reqs = append(a.reqs, req)
	events := []model.StreamEvent{
		{Kind: model.StreamKindThinkingStart},
		{Kind: model.StreamKindThinkingDelta, Delta: "let me think"},
		{Kind: model.StreamKindThinkingEnd},
		{Kind: model.StreamKindTextStart},
		{Kind: model.StreamKindTextDelta, Delta: "Hello"},
		{Kind: model.StreamKindTextEnd},
	}
	for _, ev := range events {
		if on != nil {
			on(ev)
		}
	}
	return model.Response{Content: "Hello"}, nil
}

// kindsOf 把事件 kind 作为集合返回，便于紧凑断言。
func kindsOf(events []model.StreamEvent) map[model.StreamKind]int {
	out := make(map[model.StreamKind]int, len(events))
	for _, ev := range events {
		out[ev.Kind]++
	}
	return out
}

// runThinkingTurn 用给定广播开关配置的循环驱动一个流式 turn，
// 并返回 OnStream 见过的事件。
func runThinkingTurn(t *testing.T, show *bool) ([]model.StreamEvent, *thinkingAdapter) {
	t.Helper()
	ad := &thinkingAdapter{}
	onStream, streams := collectStream()
	l := New(Options{
		Agent:              newTestAgent(t, ad, nil),
		OnStream:           onStream,
		MaxRounds:          8,
		ThinkingShowToUser: show,
	})
	if _, err := l.Run(context.Background(), "web", []model.Message{model.TextMessage(model.RoleUser, "hi")}); err != nil {
		t.Fatalf("Run: %v", err)
	}
	return streams(), ad
}

// TestRun_ThinkingShowToUserFalseWithholdsThinkingFrames 是 showToUser=false
// 的契约：思考帧绝不抵达客户端回调，而正文本
// 分段原样投递（展示被门控，答案不受影响）。
func TestRun_ThinkingShowToUserFalseWithholdsThinkingFrames(t *testing.T) {
	t.Parallel()

	show := false
	events, _ := runThinkingTurn(t, &show)
	kinds := kindsOf(events)
	for _, k := range []model.StreamKind{model.StreamKindThinkingStart, model.StreamKindThinkingDelta, model.StreamKindThinkingEnd} {
		if n := kinds[k]; n != 0 {
			t.Fatalf("event kind %q emitted %d time(s) with showToUser=false", k, n)
		}
	}
	for _, k := range []model.StreamKind{model.StreamKindTextStart, model.StreamKindTextDelta, model.StreamKindTextEnd} {
		if kinds[k] != 1 {
			t.Fatalf("event kind %q emitted %d time(s), want 1 (body must be unaffected)", k, kinds[k])
		}
	}
	if len(events) != 3 {
		t.Fatalf("events = %d, want only the 3 text frames", len(events))
	}
}

// TestRun_ThinkingShowToUserDefaultBroadcastsThinking 在选项未设置
// （nil）时保持既有行为：思考帧被推送。
func TestRun_ThinkingShowToUserDefaultBroadcastsThinking(t *testing.T) {
	t.Parallel()

	events, _ := runThinkingTurn(t, nil)
	kinds := kindsOf(events)
	if kinds[model.StreamKindThinkingDelta] != 1 || kinds[model.StreamKindThinkingStart] != 1 || kinds[model.StreamKindThinkingEnd] != 1 {
		t.Fatalf("thinking frames = %v, want start/delta/end each once with the option unset", kinds)
	}
	if len(events) != 6 {
		t.Fatalf("events = %d, want all 6 frames", len(events))
	}
}

// TestRun_ThinkingShowToUserTrueBroadcastsThinking 断言显式 true
// 的行为与默认值一致。
func TestRun_ThinkingShowToUserTrueBroadcastsThinking(t *testing.T) {
	t.Parallel()

	show := true
	events, _ := runThinkingTurn(t, &show)
	if kinds := kindsOf(events); kinds[model.StreamKindThinkingDelta] != 1 {
		t.Fatalf("thinking delta frames = %d, want 1 with showToUser=true", kinds[model.StreamKindThinkingDelta])
	}
}

// TestRun_RequestCarriesThinkingKnobs 断言循环把它配置的推理
// 选项注入它构建的每个模型请求，使某人格的思考配置
// 真正被应用，而不是校验后被忽略。
func TestRun_RequestCarriesThinkingKnobs(t *testing.T) {
	t.Parallel()

	ad := &thinkingAdapter{}
	onStream, _ := collectStream()
	want := &model.Thinking{BudgetTokens: 4096}
	l := New(Options{
		Agent:           newTestAgent(t, ad, nil),
		OnStream:        onStream,
		MaxRounds:       8,
		Thinking:        want,
		ReasoningEffort: "low",
	})
	if _, err := l.Run(context.Background(), "web", []model.Message{model.TextMessage(model.RoleUser, "hi")}); err != nil {
		t.Fatalf("Run: %v", err)
	}
	if len(ad.reqs) == 0 {
		t.Fatal("no model request was recorded")
	}
	got := ad.reqs[0]
	if got.Thinking != want {
		t.Fatalf("request.Thinking = %+v, want %+v", got.Thinking, want)
	}
	if got.Thinking.BudgetTokens != 4096 {
		t.Fatalf("request.Thinking.BudgetTokens = %d, want 4096", got.Thinking.BudgetTokens)
	}
	if got.ReasoningEffort != "low" {
		t.Fatalf("request.ReasoningEffort = %q, want low", got.ReasoningEffort)
	}
}