Compare commits

..

22 Commits

Author SHA1 Message Date
Luis Pater
cf8b2dcc85 Merge pull request #67 from router-for-me/plus
v6.6.54
2025-12-25 21:07:45 +08:00
Luis Pater
8e24d9dc34 Merge branch 'main' into plus 2025-12-25 21:07:37 +08:00
Luis Pater
443c4538bb feat(config): add commercial-mode to optimize HTTP middleware for lower memory usage 2025-12-25 21:05:01 +08:00
Luis Pater
8e749ac22d docs(readme): update GLM model version from 4.6 to 4.7 in README and README_CN 2025-12-24 23:59:48 +08:00
Luis Pater
69e09d9bc7 docs(readme): update GLM model version from 4.6 to 4.7 in README and README_CN 2025-12-24 23:46:27 +08:00
Luis Pater
ed57d82bc1 Merge branch 'router-for-me:main' into main 2025-12-24 23:31:09 +08:00
Luis Pater
06ad527e8c Fixed: #696
fix(translators): adjust prompt token calculation by subtracting cached tokens across Gemini, OpenAI, and Claude handlers
2025-12-24 23:29:18 +08:00
Luis Pater
7af5a90a0b Merge pull request #65 from router-for-me/plus
v6.6.52
2025-12-24 22:28:45 +08:00
Luis Pater
7551faff79 Merge branch 'main' into plus 2025-12-24 22:27:12 +08:00
Luis Pater
b7409dd2de Merge pull request #706 from router-for-me/log
Log
2025-12-24 22:24:39 +08:00
hkfires
5ba325a8fc refactor(logging): standardize request id formatting and layout 2025-12-24 22:03:07 +08:00
Luis Pater
d502840f91 Merge pull request #695 from NguyenSiTrung/main
feat: add cached token parsing for Gemini , Antigravity API responses
2025-12-24 21:58:55 +08:00
hkfires
99238a4b59 fix(logging): normalize warning level to warn 2025-12-24 21:11:37 +08:00
hkfires
6d43a2ff9a refactor(logging): inline request id in log output 2025-12-24 21:07:18 +08:00
Luis Pater
cdb9c2e6e8 Merge remote-tracking branch 'origin/main' into router-for-me/main 2025-12-24 20:18:53 +08:00
Luis Pater
3faa1ca9af Merge pull request #700 from router-for-me/log
refactor(sdk/auth): rename manager.go to conductor.go
2025-12-24 19:36:24 +08:00
Luis Pater
9d975e0375 feat(models): add support for GLM-4.7 and MiniMax-M2.1 2025-12-24 19:30:57 +08:00
hkfires
2a6d8b78d4 feat(api): add endpoint to retrieve request logs by ID 2025-12-24 19:24:51 +08:00
hkfires
26fbb77901 refactor(sdk/auth): rename manager.go to conductor.go 2025-12-24 15:21:03 +08:00
NguyenSiTrung
a277302262 Merge remote-tracking branch 'upstream/main' 2025-12-24 10:54:09 +07:00
NguyenSiTrung
969c1a5b72 refactor: extract parseGeminiFamilyUsageDetail helper to reduce duplication 2025-12-24 10:22:31 +07:00
NguyenSiTrung
872339bceb feat: add cached token parsing for Gemini API responses 2025-12-24 10:20:11 +07:00
12 changed files with 144 additions and 90 deletions

View File

@@ -39,6 +39,9 @@ api-keys:
# Enable debug logging
debug: false
# When true, disable high-overhead HTTP middleware features to reduce per-request memory usage under high concurrency.
commercial-mode: false
# Open OAuth URLs in incognito/private browser mode.
# Useful when you want to login with a different account without logging out from your current session.
# Default: false (but Kiro auth defaults to true for multi-account support)

View File

@@ -209,6 +209,94 @@ func (h *Handler) GetRequestErrorLogs(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{"files": files})
}
// GetRequestLogByID finds and downloads a request log file by its request ID.
// The ID is matched against the suffix of log file names (format: *-{requestID}.log).
func (h *Handler) GetRequestLogByID(c *gin.Context) {
if h == nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "handler unavailable"})
return
}
if h.cfg == nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": "configuration unavailable"})
return
}
dir := h.logDirectory()
if strings.TrimSpace(dir) == "" {
c.JSON(http.StatusInternalServerError, gin.H{"error": "log directory not configured"})
return
}
requestID := strings.TrimSpace(c.Param("id"))
if requestID == "" {
requestID = strings.TrimSpace(c.Query("id"))
}
if requestID == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing request ID"})
return
}
if strings.ContainsAny(requestID, "/\\") {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid request ID"})
return
}
entries, err := os.ReadDir(dir)
if err != nil {
if os.IsNotExist(err) {
c.JSON(http.StatusNotFound, gin.H{"error": "log directory not found"})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to list log directory: %v", err)})
return
}
suffix := "-" + requestID + ".log"
var matchedFile string
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
if strings.HasSuffix(name, suffix) {
matchedFile = name
break
}
}
if matchedFile == "" {
c.JSON(http.StatusNotFound, gin.H{"error": "log file not found for the given request ID"})
return
}
dirAbs, errAbs := filepath.Abs(dir)
if errAbs != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to resolve log directory: %v", errAbs)})
return
}
fullPath := filepath.Clean(filepath.Join(dirAbs, matchedFile))
prefix := dirAbs + string(os.PathSeparator)
if !strings.HasPrefix(fullPath, prefix) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid log file path"})
return
}
info, errStat := os.Stat(fullPath)
if errStat != nil {
if os.IsNotExist(errStat) {
c.JSON(http.StatusNotFound, gin.H{"error": "log file not found"})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to read log file: %v", errStat)})
return
}
if info.IsDir() {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid log file"})
return
}
c.FileAttachment(fullPath, matchedFile)
}
// DownloadRequestErrorLog downloads a specific error request log file by name.
func (h *Handler) DownloadRequestErrorLog(c *gin.Context) {
if h == nil {

View File

@@ -209,13 +209,15 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
// Resolve logs directory relative to the configuration file directory.
var requestLogger logging.RequestLogger
var toggle func(bool)
if optionState.requestLoggerFactory != nil {
requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
}
if requestLogger != nil {
engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
toggle = setter.SetEnabled
if !cfg.CommercialMode {
if optionState.requestLoggerFactory != nil {
requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
}
if requestLogger != nil {
engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
toggle = setter.SetEnabled
}
}
}
@@ -538,6 +540,7 @@ func (s *Server) registerManagementRoutes() {
mgmt.DELETE("/logs", s.mgmt.DeleteLogs)
mgmt.GET("/request-error-logs", s.mgmt.GetRequestErrorLogs)
mgmt.GET("/request-error-logs/:name", s.mgmt.DownloadRequestErrorLog)
mgmt.GET("/request-log-by-id/:id", s.mgmt.GetRequestLogByID)
mgmt.GET("/request-log", s.mgmt.GetRequestLog)
mgmt.PUT("/request-log", s.mgmt.PutRequestLog)
mgmt.PATCH("/request-log", s.mgmt.PutRequestLog)

View File

@@ -39,6 +39,9 @@ type Config struct {
// Debug enables or disables debug-level logging and other debug features.
Debug bool `yaml:"debug" json:"debug"`
// CommercialMode disables high-overhead HTTP middleware features to minimize per-request memory usage.
CommercialMode bool `yaml:"commercial-mode" json:"commercial-mode"`
// LoggingToFile controls whether application logs are written to rotating files or stdout.
LoggingToFile bool `yaml:"logging-to-file" json:"logging-to-file"`

View File

@@ -73,17 +73,15 @@ func GinLogrusLogger() gin.HandlerFunc {
method := c.Request.Method
errorMessage := c.Errors.ByType(gin.ErrorTypePrivate).String()
if requestID == "" {
requestID = "--------"
}
logLine := fmt.Sprintf("%3d | %13v | %15s | %-7s \"%s\"", statusCode, latency, clientIP, method, path)
if errorMessage != "" {
logLine = logLine + " | " + errorMessage
}
var entry *log.Entry
if requestID != "" {
entry = log.WithField("request_id", requestID)
} else {
entry = log.WithField("request_id", "--------")
}
entry := log.WithField("request_id", requestID)
switch {
case statusCode >= http.StatusInternalServerError:

View File

@@ -40,25 +40,22 @@ func (m *LogFormatter) Format(entry *log.Entry) ([]byte, error) {
timestamp := entry.Time.Format("2006-01-02 15:04:05")
message := strings.TrimRight(entry.Message, "\r\n")
reqID := ""
reqID := "--------"
if id, ok := entry.Data["request_id"].(string); ok && id != "" {
reqID = id
}
callerFile := "unknown"
callerLine := 0
if entry.Caller != nil {
callerFile = filepath.Base(entry.Caller.File)
callerLine = entry.Caller.Line
level := entry.Level.String()
if level == "warning" {
level = "warn"
}
levelStr := fmt.Sprintf("%-5s", entry.Level.String())
levelStr := fmt.Sprintf("%-5s", level)
var formatted string
if reqID != "" {
formatted = fmt.Sprintf("[%s] [%s] [%s:%d] | %s | %s\n", timestamp, levelStr, callerFile, callerLine, reqID, message)
if entry.Caller != nil {
formatted = fmt.Sprintf("[%s] [%s] [%s] [%s:%d] %s\n", timestamp, reqID, levelStr, filepath.Base(entry.Caller.File), entry.Caller.Line, message)
} else {
formatted = fmt.Sprintf("[%s] [%s] [%s:%d] %s\n", timestamp, levelStr, callerFile, callerLine, message)
formatted = fmt.Sprintf("[%s] [%s] [%s] %s\n", timestamp, reqID, levelStr, message)
}
buffer.WriteString(formatted)

View File

@@ -727,6 +727,7 @@ func GetIFlowModels() []*ModelInfo {
{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build", Created: 1757030400},
{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905", Created: 1757030400},
{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400, Thinking: iFlowThinkingSupport},
{ID: "glm-4.7", DisplayName: "GLM-4.7", Description: "Zhipu GLM 4.7 general model", Created: 1766448000, Thinking: iFlowThinkingSupport},
{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model", Created: 1752192000},
{ID: "kimi-k2-thinking", DisplayName: "Kimi-K2-Thinking", Description: "Moonshot Kimi K2 thinking model", Created: 1762387200},
{ID: "deepseek-v3.2-chat", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2 Chat", Created: 1764576000},
@@ -740,6 +741,7 @@ func GetIFlowModels() []*ModelInfo {
{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000},
{ID: "minimax-m2.1", DisplayName: "MiniMax-M2.1", Description: "MiniMax M2.1", Created: 1766448000},
}
models := make([]*ModelInfo, 0, len(entries))
for _, entry := range entries {

View File

@@ -275,6 +275,20 @@ func parseClaudeStreamUsage(line []byte) (usage.Detail, bool) {
return detail, true
}
func parseGeminiFamilyUsageDetail(node gjson.Result) usage.Detail {
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
CachedTokens: node.Get("cachedContentTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
}
func parseGeminiCLIUsage(data []byte) usage.Detail {
usageNode := gjson.ParseBytes(data)
node := usageNode.Get("response.usageMetadata")
@@ -284,16 +298,7 @@ func parseGeminiCLIUsage(data []byte) usage.Detail {
if !node.Exists() {
return usage.Detail{}
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
return parseGeminiFamilyUsageDetail(node)
}
func parseGeminiUsage(data []byte) usage.Detail {
@@ -305,16 +310,7 @@ func parseGeminiUsage(data []byte) usage.Detail {
if !node.Exists() {
return usage.Detail{}
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
return parseGeminiFamilyUsageDetail(node)
}
func parseGeminiStreamUsage(line []byte) (usage.Detail, bool) {
@@ -329,16 +325,7 @@ func parseGeminiStreamUsage(line []byte) (usage.Detail, bool) {
if !node.Exists() {
return usage.Detail{}, false
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail, true
return parseGeminiFamilyUsageDetail(node), true
}
func parseGeminiCLIStreamUsage(line []byte) (usage.Detail, bool) {
@@ -353,16 +340,7 @@ func parseGeminiCLIStreamUsage(line []byte) (usage.Detail, bool) {
if !node.Exists() {
return usage.Detail{}, false
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail, true
return parseGeminiFamilyUsageDetail(node), true
}
func parseAntigravityUsage(data []byte) usage.Detail {
@@ -377,16 +355,7 @@ func parseAntigravityUsage(data []byte) usage.Detail {
if !node.Exists() {
return usage.Detail{}
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
return parseGeminiFamilyUsageDetail(node)
}
func parseAntigravityStreamUsage(line []byte) (usage.Detail, bool) {
@@ -404,16 +373,7 @@ func parseAntigravityStreamUsage(line []byte) (usage.Detail, bool) {
if !node.Exists() {
return usage.Detail{}, false
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail, true
return parseGeminiFamilyUsageDetail(node), true
}
var stopChunkWithoutUsage sync.Map

View File

@@ -271,11 +271,11 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
params.HasUsageMetadata = true
params.PromptTokenCount = usageResult.Get("promptTokenCount").Int()
params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
params.PromptTokenCount = usageResult.Get("promptTokenCount").Int() - params.CachedTokenCount
params.CandidatesTokenCount = usageResult.Get("candidatesTokenCount").Int()
params.ThoughtsTokenCount = usageResult.Get("thoughtsTokenCount").Int()
params.TotalTokenCount = usageResult.Get("totalTokenCount").Int()
params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
if params.CandidatesTokenCount == 0 && params.TotalTokenCount > 0 {
params.CandidatesTokenCount = params.TotalTokenCount - params.PromptTokenCount - params.ThoughtsTokenCount
if params.CandidatesTokenCount < 0 {

View File

@@ -87,15 +87,15 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
// Extract and set usage metadata (token counts).
if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
}
if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
}
promptTokenCount := usageResult.Get("promptTokenCount").Int()
promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)

View File

@@ -89,15 +89,15 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
// Extract and set usage metadata (token counts).
if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() {
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
}
if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
}
promptTokenCount := usageResult.Get("promptTokenCount").Int()
promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)