mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-06-10 08:13:22 +08:00
959067edfb
- Replaced `NewUsageReporter` with `NewExecutorUsageReporter` to include executor type in usage records. - Updated all executors to use the new reporter implementation. - Extended `UsageReporter` to track and publish executor type. - Added tests to validate proper executor type recording and handling. - Enhanced RedisQueue plugin and payload schema with executor type support.
318 lines
11 KiB
Go
318 lines
11 KiB
Go
package helps
|
|
|
|
import (
|
|
"context"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/router-for-me/CLIProxyAPI/v7/sdk/cliproxy/usage"
|
|
)
|
|
|
|
func TestParseOpenAIUsageChatCompletions(t *testing.T) {
|
|
data := []byte(`{"usage":{"prompt_tokens":1,"completion_tokens":2,"total_tokens":3,"prompt_tokens_details":{"cached_tokens":4},"completion_tokens_details":{"reasoning_tokens":5}}}`)
|
|
detail := ParseOpenAIUsage(data)
|
|
if detail.InputTokens != 1 {
|
|
t.Fatalf("input tokens = %d, want %d", detail.InputTokens, 1)
|
|
}
|
|
if detail.OutputTokens != 2 {
|
|
t.Fatalf("output tokens = %d, want %d", detail.OutputTokens, 2)
|
|
}
|
|
if detail.TotalTokens != 3 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 3)
|
|
}
|
|
if detail.CachedTokens != 4 {
|
|
t.Fatalf("cached tokens = %d, want %d", detail.CachedTokens, 4)
|
|
}
|
|
if detail.ReasoningTokens != 5 {
|
|
t.Fatalf("reasoning tokens = %d, want %d", detail.ReasoningTokens, 5)
|
|
}
|
|
}
|
|
|
|
func TestParseOpenAIUsageResponses(t *testing.T) {
|
|
data := []byte(`{"usage":{"input_tokens":10,"output_tokens":20,"total_tokens":30,"input_tokens_details":{"cached_tokens":7},"output_tokens_details":{"reasoning_tokens":9}}}`)
|
|
detail := ParseOpenAIUsage(data)
|
|
if detail.InputTokens != 10 {
|
|
t.Fatalf("input tokens = %d, want %d", detail.InputTokens, 10)
|
|
}
|
|
if detail.OutputTokens != 20 {
|
|
t.Fatalf("output tokens = %d, want %d", detail.OutputTokens, 20)
|
|
}
|
|
if detail.TotalTokens != 30 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 30)
|
|
}
|
|
if detail.CachedTokens != 7 {
|
|
t.Fatalf("cached tokens = %d, want %d", detail.CachedTokens, 7)
|
|
}
|
|
if detail.ReasoningTokens != 9 {
|
|
t.Fatalf("reasoning tokens = %d, want %d", detail.ReasoningTokens, 9)
|
|
}
|
|
}
|
|
|
|
func TestParseOpenAIUsageIgnoresNullUsage(t *testing.T) {
|
|
data := []byte(`{"usage":null}`)
|
|
detail := ParseOpenAIUsage(data)
|
|
if detail != (usage.Detail{}) {
|
|
t.Fatalf("detail = %+v, want zero detail", detail)
|
|
}
|
|
}
|
|
|
|
func TestParseOpenAIStreamUsageIgnoresNullUsage(t *testing.T) {
|
|
line := []byte(`data: {"id":"chunk_1","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"hi"},"finish_reason":null}],"usage":null}`)
|
|
if detail, ok := ParseOpenAIStreamUsage(line); ok {
|
|
t.Fatalf("ParseOpenAIStreamUsage() = (%+v, true), want false for null usage", detail)
|
|
}
|
|
}
|
|
|
|
func TestParseOpenAIStreamUsageResponsesFields(t *testing.T) {
|
|
line := []byte(`data: {"id":"chunk_1","object":"chat.completion.chunk","choices":[],"usage":{"input_tokens":8,"output_tokens":5,"total_tokens":13,"input_tokens_details":{"cached_tokens":3},"output_tokens_details":{"reasoning_tokens":2}}}`)
|
|
detail, ok := ParseOpenAIStreamUsage(line)
|
|
if !ok {
|
|
t.Fatal("ParseOpenAIStreamUsage() ok = false, want true")
|
|
}
|
|
if detail.InputTokens != 8 {
|
|
t.Fatalf("input tokens = %d, want %d", detail.InputTokens, 8)
|
|
}
|
|
if detail.OutputTokens != 5 {
|
|
t.Fatalf("output tokens = %d, want %d", detail.OutputTokens, 5)
|
|
}
|
|
if detail.TotalTokens != 13 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 13)
|
|
}
|
|
if detail.CachedTokens != 3 {
|
|
t.Fatalf("cached tokens = %d, want %d", detail.CachedTokens, 3)
|
|
}
|
|
if detail.ReasoningTokens != 2 {
|
|
t.Fatalf("reasoning tokens = %d, want %d", detail.ReasoningTokens, 2)
|
|
}
|
|
}
|
|
|
|
func TestParseClaudeUsageIncludesCacheTokensInTotal(t *testing.T) {
|
|
data := []byte(`{"usage":{"input_tokens":3085,"output_tokens":253,"cache_read_input_tokens":7,"cache_creation_input_tokens":19514}}`)
|
|
detail := ParseClaudeUsage(data)
|
|
if detail.InputTokens != 3085 {
|
|
t.Fatalf("input tokens = %d, want %d", detail.InputTokens, 3085)
|
|
}
|
|
if detail.OutputTokens != 253 {
|
|
t.Fatalf("output tokens = %d, want %d", detail.OutputTokens, 253)
|
|
}
|
|
if detail.CacheReadTokens != 7 {
|
|
t.Fatalf("cache read tokens = %d, want %d", detail.CacheReadTokens, 7)
|
|
}
|
|
if detail.CacheCreationTokens != 19514 {
|
|
t.Fatalf("cache creation tokens = %d, want %d", detail.CacheCreationTokens, 19514)
|
|
}
|
|
if detail.CachedTokens != 7 {
|
|
t.Fatalf("cached tokens = %d, want %d", detail.CachedTokens, 7)
|
|
}
|
|
if detail.TotalTokens != 22859 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 22859)
|
|
}
|
|
}
|
|
|
|
func TestParseClaudeUsageFallsBackCachedTokensToCacheCreation(t *testing.T) {
|
|
data := []byte(`{"usage":{"input_tokens":3085,"output_tokens":253,"cache_creation_input_tokens":19514}}`)
|
|
detail := ParseClaudeUsage(data)
|
|
if detail.CachedTokens != 19514 {
|
|
t.Fatalf("cached tokens = %d, want %d", detail.CachedTokens, 19514)
|
|
}
|
|
if detail.TotalTokens != 22852 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 22852)
|
|
}
|
|
}
|
|
|
|
func TestParseGeminiCLIUsage_TopLevelUsageMetadata(t *testing.T) {
|
|
data := []byte(`{"usageMetadata":{"promptTokenCount":11,"candidatesTokenCount":7,"thoughtsTokenCount":3,"totalTokenCount":21,"cachedContentTokenCount":5}}`)
|
|
detail := ParseGeminiCLIUsage(data)
|
|
if detail.InputTokens != 11 {
|
|
t.Fatalf("input tokens = %d, want %d", detail.InputTokens, 11)
|
|
}
|
|
if detail.OutputTokens != 7 {
|
|
t.Fatalf("output tokens = %d, want %d", detail.OutputTokens, 7)
|
|
}
|
|
if detail.ReasoningTokens != 3 {
|
|
t.Fatalf("reasoning tokens = %d, want %d", detail.ReasoningTokens, 3)
|
|
}
|
|
if detail.TotalTokens != 21 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 21)
|
|
}
|
|
if detail.CachedTokens != 5 {
|
|
t.Fatalf("cached tokens = %d, want %d", detail.CachedTokens, 5)
|
|
}
|
|
}
|
|
|
|
func TestParseGeminiCLIStreamUsage_ResponseSnakeCaseUsageMetadata(t *testing.T) {
|
|
line := []byte(`data: {"response":{"usage_metadata":{"promptTokenCount":13,"candidatesTokenCount":2,"totalTokenCount":15}}}`)
|
|
detail, ok := ParseGeminiCLIStreamUsage(line)
|
|
if !ok {
|
|
t.Fatal("ParseGeminiCLIStreamUsage() ok = false, want true")
|
|
}
|
|
if detail.InputTokens != 13 {
|
|
t.Fatalf("input tokens = %d, want %d", detail.InputTokens, 13)
|
|
}
|
|
if detail.OutputTokens != 2 {
|
|
t.Fatalf("output tokens = %d, want %d", detail.OutputTokens, 2)
|
|
}
|
|
if detail.TotalTokens != 15 {
|
|
t.Fatalf("total tokens = %d, want %d", detail.TotalTokens, 15)
|
|
}
|
|
}
|
|
|
|
func TestParseGeminiCLIStreamUsage_IgnoresTrafficTypeOnlyUsageMetadata(t *testing.T) {
|
|
line := []byte(`data: {"response":{"usageMetadata":{"trafficType":"ON_DEMAND"}}}`)
|
|
if detail, ok := ParseGeminiCLIStreamUsage(line); ok {
|
|
t.Fatalf("ParseGeminiCLIStreamUsage() = (%+v, true), want false for traffic-only usage metadata", detail)
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterBuildRecordIncludesLatency(t *testing.T) {
|
|
reporter := &UsageReporter{
|
|
provider: "openai",
|
|
model: "gpt-5.4",
|
|
requestedAt: time.Now().Add(-1500 * time.Millisecond),
|
|
}
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.Latency < time.Second {
|
|
t.Fatalf("latency = %v, want >= 1s", record.Latency)
|
|
}
|
|
if record.Latency > 3*time.Second {
|
|
t.Fatalf("latency = %v, want <= 3s", record.Latency)
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterTrackHTTPClientStartsTTFTBeforeRoundTrip(t *testing.T) {
|
|
delay := 40 * time.Millisecond
|
|
reporter := NewUsageReporter(context.Background(), "openai", "gpt-5.4", nil)
|
|
client := reporter.TrackHTTPClient(&http.Client{
|
|
Transport: roundTripFunc(func(req *http.Request) (*http.Response, error) {
|
|
time.Sleep(delay)
|
|
return &http.Response{
|
|
StatusCode: http.StatusOK,
|
|
Status: "200 OK",
|
|
Header: make(http.Header),
|
|
Body: io.NopCloser(strings.NewReader("ok")),
|
|
Request: req,
|
|
}, nil
|
|
}),
|
|
})
|
|
|
|
req, errNewRequest := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://example.invalid/v1/chat/completions", strings.NewReader("{}"))
|
|
if errNewRequest != nil {
|
|
t.Fatalf("NewRequestWithContext() error = %v", errNewRequest)
|
|
}
|
|
resp, errDo := client.Do(req)
|
|
if errDo != nil {
|
|
t.Fatalf("Do() error = %v", errDo)
|
|
}
|
|
if _, errRead := io.ReadAll(resp.Body); errRead != nil {
|
|
t.Fatalf("ReadAll() error = %v", errRead)
|
|
}
|
|
if errClose := resp.Body.Close(); errClose != nil {
|
|
t.Fatalf("response body close error = %v", errClose)
|
|
}
|
|
if got := reporter.ttftDuration(); got < delay {
|
|
t.Fatalf("ttft = %v, want >= %v", got, delay)
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterBuildRecordIncludesRequestedModelAlias(t *testing.T) {
|
|
ctx := usage.WithRequestedModelAlias(context.Background(), "client-gpt")
|
|
reporter := NewUsageReporter(ctx, "openai", "gpt-5.4", nil)
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.Model != "gpt-5.4" {
|
|
t.Fatalf("model = %q, want %q", record.Model, "gpt-5.4")
|
|
}
|
|
if record.Alias != "client-gpt" {
|
|
t.Fatalf("alias = %q, want %q", record.Alias, "client-gpt")
|
|
}
|
|
}
|
|
|
|
func TestNewExecutorUsageReporterIncludesExecutorType(t *testing.T) {
|
|
reporter := NewExecutorUsageReporter(context.Background(), &TestUsageExecutor{}, "gpt-5.4", nil)
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.Provider != "test-provider" {
|
|
t.Fatalf("provider = %q, want %q", record.Provider, "test-provider")
|
|
}
|
|
if record.ExecutorType != "TestUsageExecutor" {
|
|
t.Fatalf("executor type = %q, want %q", record.ExecutorType, "TestUsageExecutor")
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterBuildRecordIncludesReasoningEffort(t *testing.T) {
|
|
ctx := usage.WithReasoningEffort(context.Background(), "medium")
|
|
reporter := NewUsageReporter(ctx, "openai", "gpt-5.4", nil)
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.ReasoningEffort != "medium" {
|
|
t.Fatalf("reasoning effort = %q, want %q", record.ReasoningEffort, "medium")
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterBuildRecordIncludesServiceTier(t *testing.T) {
|
|
ctx := usage.WithServiceTier(context.Background(), "priority")
|
|
reporter := NewUsageReporter(ctx, "openai", "gpt-5.4", nil)
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.ServiceTier != "priority" {
|
|
t.Fatalf("service tier = %q, want %q", record.ServiceTier, "priority")
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterSetTranslatedReasoningEffortUpdatesServiceTier(t *testing.T) {
|
|
reporter := NewUsageReporter(context.Background(), "openai", "gpt-5.4", nil)
|
|
|
|
reporter.SetTranslatedReasoningEffort([]byte(`{"service_tier":"priority"}`), "openai")
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.ServiceTier != "priority" {
|
|
t.Fatalf("service tier = %q, want %q", record.ServiceTier, "priority")
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterSetTranslatedReasoningEffortDefaultsServiceTierWhenRemoved(t *testing.T) {
|
|
ctx := usage.WithServiceTier(context.Background(), "priority")
|
|
reporter := NewUsageReporter(ctx, "openai", "gpt-5.4", nil)
|
|
|
|
reporter.SetTranslatedReasoningEffort([]byte(`{"model":"gpt-5.4"}`), "openai")
|
|
|
|
record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
|
|
if record.ServiceTier != usage.DefaultServiceTier {
|
|
t.Fatalf("service tier = %q, want %q", record.ServiceTier, usage.DefaultServiceTier)
|
|
}
|
|
}
|
|
|
|
func TestUsageReporterBuildAdditionalModelRecordSkipsZeroTokens(t *testing.T) {
|
|
reporter := &UsageReporter{
|
|
provider: "codex",
|
|
model: "gpt-5.4",
|
|
requestedAt: time.Now(),
|
|
}
|
|
|
|
if _, ok := reporter.buildAdditionalModelRecord("gpt-image-2", usage.Detail{}); ok {
|
|
t.Fatalf("expected all-zero token usage to be skipped")
|
|
}
|
|
if _, ok := reporter.buildAdditionalModelRecord("gpt-image-2", usage.Detail{InputTokens: 2}); !ok {
|
|
t.Fatalf("expected non-zero input token usage to be recorded")
|
|
}
|
|
if _, ok := reporter.buildAdditionalModelRecord("gpt-image-2", usage.Detail{CachedTokens: 2}); !ok {
|
|
t.Fatalf("expected non-zero cached token usage to be recorded")
|
|
}
|
|
}
|
|
|
|
type roundTripFunc func(*http.Request) (*http.Response, error)
|
|
|
|
func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) {
|
|
return f(req)
|
|
}
|
|
|
|
type TestUsageExecutor struct{}
|
|
|
|
func (TestUsageExecutor) Identifier() string {
|
|
return "test-provider"
|
|
}
|