ModelRouter/internal/gateway/thinking_test.go

package gateway

import (
	"encoding/json"
	"testing"

	"llmsproxy/internal/types"
)

// TestThinkingFromClient 把「客户端措辞 → 中立语义」这条翻译链钉死。
//
// v1 的问题：disable_thinking 是内核私有字段，被序列化进交给适配器的 body，
// 于是 10 个适配器各自写 req.disable_thinking = nil 来清理它。v2 把它换成
// 双方都认可的 thinking 字段，这条测试确保翻译只发生一次、且在适配器之前。
func TestThinkingFromClient(t *testing.T) {
	cases := []struct {
		name string
		req  chatRequest
		want *types.ThinkingConfig
	}{
		{
			name: "无任何字段 → 不带 thinking（上游用自己默认）",
			req:  chatRequest{},
			want: nil,
		},
		{
			name: "disable_thinking=true → enabled=false",
			req:  chatRequest{DisableThinking: true},
			want: &types.ThinkingConfig{Enabled: boolPtr(false)},
		},
		{
			name: "中立 thinking 显式给出 → 原样透传",
			req:  chatRequest{Thinking: &types.ThinkingConfig{Enabled: boolPtr(true), BudgetTokens: 4096}},
			want: &types.ThinkingConfig{Enabled: boolPtr(true), BudgetTokens: 4096},
		},
		{
			name: "两者冲突时，中立的 thinking 优先（它带预算，布尔表达不了）",
			req: chatRequest{
				DisableThinking: true,
				Thinking:        &types.ThinkingConfig{Enabled: boolPtr(true), BudgetTokens: 1024},
			},
			want: &types.ThinkingConfig{Enabled: boolPtr(true), BudgetTokens: 1024},
		},
	}
	for _, c := range cases {
		t.Run(c.name, func(t *testing.T) {
			got := c.req.thinkingFromClient()
			if c.want == nil {
				if got != nil {
					t.Fatalf("want nil, got %+v", got)
				}
				return
			}
			if got == nil {
				t.Fatal("want non-nil thinking, got nil")
			}
			if (got.Enabled == nil) != (c.want.Enabled == nil) {
				t.Fatalf("Enabled presence mismatch: got %v want %v", got.Enabled, c.want.Enabled)
			}
			if got.Enabled != nil && *got.Enabled != *c.want.Enabled {
				t.Errorf("Enabled = %v, want %v", *got.Enabled, *c.want.Enabled)
			}
			if got.BudgetTokens != c.want.BudgetTokens {
				t.Errorf("BudgetTokens = %d, want %d", got.BudgetTokens, c.want.BudgetTokens)
			}
		})
	}
}

// TestDisableThinkingNeverReachesAdapterBody 是那条泄漏的回归测试：内核私有
// 字段不得出现在交给适配器的 body 里。
func TestDisableThinkingNeverReachesAdapterBody(t *testing.T) {
	var r chatRequest
	if err := json.Unmarshal([]byte(`{"model":"m","messages":[],"disable_thinking":true}`), &r); err != nil {
		t.Fatal(err)
	}
	inner := &types.ChatRequest{
		Model:         "m",
		Thinking:      r.thinkingFromClient(),
		Tools:         r.rawTools(),
		ToolChoice:    r.rawToolChoice(),
		ExtraBody:     r.ExtraBody,
		ClientSession: "",
	}
	body, err := json.Marshal(inner)
	if err != nil {
		t.Fatal(err)
	}
	var m map[string]json.RawMessage
	if err := json.Unmarshal(body, &m); err != nil {
		t.Fatal(err)
	}
	if _, leaked := m["disable_thinking"]; leaked {
		t.Errorf("内核私有字段 disable_thinking 泄漏进适配器 body（v1 回归）: %s", body)
	}
	if _, ok := m["thinking"]; !ok {
		t.Errorf("中立 thinking 字段缺失: %s", body)
	}
}

// TestToolsPassthroughRaw 确认 tools/tool_choice 以原始形状交给适配器：
// 内核不解释工具 schema，那是适配器的职责。
func TestToolsPassthroughRaw(t *testing.T) {
	var r chatRequest
	body := `{"model":"m","messages":[],"tools":[{"type":"function","function":{"name":"f","parameters":{"type":"object"}}}],"tool_choice":"auto"}`
	if err := json.Unmarshal([]byte(body), &r); err != nil {
		t.Fatal(err)
	}
	tools := r.rawTools()
	if len(tools) == 0 {
		t.Fatal("tools 未透传")
	}
	var decoded []map[string]interface{}
	if err := json.Unmarshal(tools, &decoded); err != nil {
		t.Fatalf("tools 不是合法 JSON: %v (%s)", err, tools)
	}
	if len(decoded) != 1 || decoded[0]["type"] != "function" {
		t.Errorf("tools 形状被内核改写: %s", tools)
	}
	if tc := string(r.rawToolChoice()); tc != `"auto"` {
		t.Errorf("tool_choice = %s, want \"auto\"", tc)
	}
	// 空值不应变成 "null" 出现在 body 里
	var empty chatRequest
	if got := empty.rawTools(); got != nil {
		t.Errorf("无 tools 时应返回 nil, got %s", got)
	}
	if got := empty.rawToolChoice(); got != nil {
		t.Errorf("无 tool_choice 时应返回 nil, got %s", got)
	}
}

func boolPtr(v bool) *bool { return &v }