fix: 缓存 token 计费按上游协议区分口径

- 新增 ComputeCost：OpenAI 系 prompt 含缓存读需扣减（异常数据钳制为 0）； Anthropic input_tokens 不含缓存，按原值计费，缓存写按输入价 ×1.25（原实现误用输出价） - recordUsage 传入上游协议（用量语义跟随解析它的上游响应，而非客户端协议） - 补充单元测试覆盖两种协议口径与边界情况
2026-09-02 02:36:28 +08:00
parent 0628d5050f
commit ca4dc4b3b7
3 changed files with 116 additions and 12 deletions
@@ -0,0 +1,75 @@
+package proxy
+
+import "testing"
+
+func TestComputeCost(t *testing.T) {
+	// 标准三价：输入 0.5 / 输出 1.5 / 缓存读 0.05（$/M）
+	const (
+		inPrice  = 0.5
+		outPrice = 1.5
+		cchPrice = 0.05
+	)
+
+	tests := []struct {
+		name          string
+		upstreamProto string
+		input         int
+		output        int
+		cacheRead     int
+		cacheCreation int
+		inP           float64
+		outP          float64
+		cchP          float64
+		want          float64
+	}{
+		{
+			// OpenAI：prompt 含缓存读，需扣减：(11000−10000)×0.5 + 10000×0.05 + 500×1.5
+			name:          "openai prompt includes cache read",
+			upstreamProto: "chat",
+			input:         11000, output: 500, cacheRead: 10000,
+			inP: inPrice, outP: outPrice, cchP: cchPrice,
+			want: (1000*inPrice + 10000*cchPrice + 500*outPrice) / 1e6,
+		},
+		{
+			// Anthropic：input 不含缓存；缓存写按输入价 ×1.25
+			name:          "anthropic cache write at 1.25x input price",
+			upstreamProto: "messages",
+			input:         1000, output: 500, cacheRead: 10000, cacheCreation: 2000,
+			inP: inPrice, outP: outPrice, cchP: cchPrice,
+			want: (1000*inPrice + 10000*cchPrice + 2000*inPrice*1.25 + 500*outPrice) / 1e6,
+		},
+		{
+			// Anthropic 口径不得扣减缓存读（否则这里非缓存输入会算成负数）
+			name:          "anthropic does not subtract cache read",
+			upstreamProto: "messages",
+			input:         100, output: 0, cacheRead: 1000,
+			inP: inPrice, outP: outPrice, cchP: cchPrice,
+			want: (100*inPrice + 1000*cchPrice) / 1e6,
+		},
+		{
+			// OpenAI 异常数据：cached > prompt 时非缓存输入钳制为 0，不出现负费用
+			name:          "openai clamps negative uncached input",
+			upstreamProto: "responses",
+			input:         100, output: 0, cacheRead: 5000,
+			inP: inPrice, outP: outPrice, cchP: cchPrice,
+			want: (5000 * cchPrice) / 1e6,
+		},
+		{
+			// 未配置价格时费用为 0
+			name:          "no prices no cost",
+			upstreamProto: "messages",
+			input:         1000, output: 1000, cacheRead: 1000, cacheCreation: 1000,
+			want: 0,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ComputeCost(tt.upstreamProto, tt.input, tt.output, tt.cacheRead, tt.cacheCreation, tt.inP, tt.outP, tt.cchP)
+			if diff := got - tt.want; diff > 1e-12 || diff < -1e-12 {
+				t.Fatalf("ComputeCost(%q, in=%d, out=%d, cr=%d, cw=%d) = %v, want %v",
+					tt.upstreamProto, tt.input, tt.output, tt.cacheRead, tt.cacheCreation, got, tt.want)
+			}
+		})
+	}
+}