Compare commits

...

14 Commits

Author SHA1 Message Date
Luis Pater
0d89a22aa0 feat: add handling for function call finish reasons in OpenAI response conversion 2025-10-17 00:19:32 +08:00
hkfires
9319602812 UPDATE README 2025-10-16 22:57:44 +08:00
Chén Mù
8e95c5e0a8 Merge pull request #134 from router-for-me/hg
feat(managementasset): add MANAGEMENT_STATIC_PATH override
2025-10-16 22:25:05 +08:00
hkfires
93f0e65cef docs: document MANAGEMENT_STATIC_PATH for management.html location 2025-10-16 22:15:17 +08:00
hkfires
c75e524fe5 feat(managementasset): add MANAGEMENT_STATIC_PATH override 2025-10-16 21:52:59 +08:00
Chén Mù
f58d0faf8c Merge pull request #130 from router-for-me/log
feat(management): add log retrieval and cleanup endpoints
2025-10-16 12:39:06 +08:00
hkfires
df3b00621a fix(logs): ignore ENOENT when truncating default log file 2025-10-16 12:35:29 +08:00
hkfires
72cb2689e8 feat(management): add log retrieval and cleanup endpoints 2025-10-16 11:55:58 +08:00
Luis Pater
ade279d1f2 Feature: #103
feat(gemini): add Gemini thinking configuration support and metadata normalization

- Introduced logic to parse and apply `thinkingBudget` and `include_thoughts` configurations from metadata.
- Enhanced request handling to include normalized Gemini model metadata, preserving the original model identifier.
- Updated Gemini and Gemini-CLI executors to apply thinking configuration based on metadata overrides.
- Refactored handlers to support metadata extraction and cloning during request preparation.
2025-10-16 11:31:18 +08:00
Luis Pater
9c5ac2927a fix(request_logging): update logging conditions to include only /v1 paths 2025-10-16 09:57:27 +08:00
Luis Pater
7980f055fa fix(iflow): streamline authentication callback handling and improve error reporting 2025-10-16 09:44:36 +08:00
Luis Pater
eb2549a782 fix(gemini): update response template to omit finishReason until known 2025-10-16 06:41:04 +08:00
Luis Pater
c419264a70 fix(responses): handle empty and invalid rawJSON in ConvertOpenAIChatCompletionsResponseToOpenAIResponses 2025-10-16 06:34:00 +08:00
Luis Pater
6b23e2da74 feat(claude): add Claude 4.5 Haiku model definition 2025-10-16 04:53:07 +08:00
17 changed files with 724 additions and 149 deletions

View File

@@ -82,6 +82,8 @@ A web-based management center for CLIProxyAPI.
Set `remote-management.disable-control-panel` to `true` if you prefer to host the management UI elsewhere; the server will skip downloading `management.html` and `/management.html` will return 404.
You can set the `MANAGEMENT_STATIC_PATH` environment variable to choose the directory where `management.html` is stored.
### Authentication
You can authenticate for Gemini, OpenAI, Claude, Qwen, and/or iFlow. All can coexist in the same `auth-dir` and will be load balanced.
@@ -464,6 +466,7 @@ An S3-compatible object storage service can host configuration and authenticatio
| Variable | Required | Default | Description |
|--------------------------|----------|--------------------------------|--------------------------------------------------------------------------------------------------------------------------|
| `MANAGEMENT_PASSWORD` | Yes | | Password for the management web UI (required when remote management is enabled). |
| `OBJECTSTORE_ENDPOINT` | Yes | | Object storage endpoint. Include `http://` or `https://` to force the protocol (omitted scheme → HTTPS). |
| `OBJECTSTORE_BUCKET` | Yes | | Bucket that stores `config/config.yaml` and `auths/*.json`. |
| `OBJECTSTORE_ACCESS_KEY` | Yes | | Access key ID for the object storage account. |
@@ -529,21 +532,6 @@ And you can always use Gemini CLI with `CODE_ASSIST_ENDPOINT` set to `http://127
The `auth-dir` parameter specifies where authentication tokens are stored. When you run the login command, the application will create JSON files in this directory containing the authentication tokens for your Google accounts. Multiple accounts can be used for load balancing.
### Request Authentication Providers
Configure inbound authentication through the `auth.providers` section. The built-in `config-api-key` provider works with inline keys:
```
auth:
providers:
- name: default
type: config-api-key
api-keys:
- your-api-key-1
```
Clients should send requests with an `Authorization: Bearer your-api-key-1` header (or `X-Goog-Api-Key`, `X-Api-Key`, or `?key=` as before). The legacy top-level `api-keys` array is still accepted and automatically synced to the default provider for backwards compatibility.
### Official Generative Language API
The `generative-language-api-key` parameter allows you to define a list of API keys that can be used to authenticate requests to the official Generative Language API.

View File

@@ -96,6 +96,8 @@ CLIProxyAPI 的基于 Web 的管理中心。
如果希望自行托管管理页面,可在配置中将 `remote-management.disable-control-panel` 设为 `true`,服务器将停止下载 `management.html`,并让 `/management.html` 返回 404。
可以通过设置环境变量 `MANAGEMENT_STATIC_PATH` 来指定 `management.html` 的存储目录。
### 身份验证
您可以分别为 Gemini、OpenAI、Claude、Qwen 和 iFlow 进行身份验证,它们可同时存在于同一个 `auth-dir` 中并参与负载均衡。
@@ -436,7 +438,7 @@ openai-compatibility:
| 变量 | 必需 | 默认值 | 描述 |
|-------------------------|----|--------|----------------------------------------------------|
| `MANAGEMENT_PASSWORD` | 是 | | 控制面板密码 |
| `MANAGEMENT_PASSWORD` | 是 | | 管理面板密码 |
| `GITSTORE_GIT_URL` | 是 | | 要使用的 Git 仓库的 HTTPS URL。 |
| `GITSTORE_LOCAL_PATH` | 否 | 当前工作目录 | 将克隆 Git 仓库的本地路径。在 Docker 内部,此路径默认为 `/CLIProxyAPI`。 |
| `GITSTORE_GIT_USERNAME` | 否 | | 用于 Git 身份验证的用户名。 |
@@ -477,6 +479,7 @@ openai-compatibility:
| 变量 | 是否必填 | 默认值 | 说明 |
|--------------------------|----------|--------------------|--------------------------------------------------------------------------------------------------------------------------|
| `MANAGEMENT_PASSWORD` | 是 | | 管理面板密码(启用远程管理时必需)。 |
| `OBJECTSTORE_ENDPOINT` | 是 | | 对象存储访问端点。可带 `http://` 或 `https://` 前缀指定协议(省略则默认 HTTPS。 |
| `OBJECTSTORE_BUCKET` | 是 | | 用于存放 `config/config.yaml` 与 `auths/*.json` 的 Bucket 名称。 |
| `OBJECTSTORE_ACCESS_KEY` | 是 | | 对象存储账号的访问密钥 ID。 |
@@ -537,21 +540,6 @@ openai-compatibility:
`auth-dir` 参数指定身份验证令牌的存储位置。当您运行登录命令时,应用程序将在此目录中创建包含 Google 账户身份验证令牌的 JSON 文件。多个账户可用于轮询。
### 请求鉴权提供方
通过 `auth.providers` 配置接入请求鉴权。内置的 `config-api-key` 提供方支持内联密钥:
```
auth:
providers:
- name: default
type: config-api-key
api-keys:
- your-api-key-1
```
调用时可在 `Authorization` 标头中携带密钥(或继续使用 `X-Goog-Api-Key`、`X-Api-Key`、查询参数 `key`)。为了兼容旧版本,顶层的 `api-keys` 字段仍然可用,并会自动同步到默认的 `config-api-key` 提供方。
### 官方生成式语言 API
`generative-language-api-key` 参数允许您定义可用于验证对官方 AIStudio Gemini API 请求的 API 密钥列表。

View File

@@ -1150,126 +1150,50 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
c.JSON(http.StatusInternalServerError, gin.H{"status": "error", "error": "failed to start callback server"})
return
}
go func() {
defer stopCallbackForwarder(iflowauth.CallbackPort)
fmt.Println("Waiting for authentication...")
waitFile := filepath.Join(h.cfg.AuthDir, fmt.Sprintf(".oauth-iflow-%s.oauth", state))
deadline := time.Now().Add(5 * time.Minute)
var resultMap map[string]string
for {
if time.Now().After(deadline) {
oauthStatus[state] = "Authentication failed"
fmt.Println("Authentication failed: timeout waiting for callback")
return
}
if data, errR := os.ReadFile(waitFile); errR == nil {
_ = os.Remove(waitFile)
_ = json.Unmarshal(data, &resultMap)
break
}
time.Sleep(500 * time.Millisecond)
}
if errStr := strings.TrimSpace(resultMap["error"]); errStr != "" {
oauthStatus[state] = "Authentication failed"
fmt.Printf("Authentication failed: %s\n", errStr)
return
}
if resultState := strings.TrimSpace(resultMap["state"]); resultState != state {
oauthStatus[state] = "Authentication failed"
fmt.Println("Authentication failed: state mismatch")
return
}
code := strings.TrimSpace(resultMap["code"])
if code == "" {
oauthStatus[state] = "Authentication failed"
fmt.Println("Authentication failed: code missing")
return
}
tokenData, errExchange := authSvc.ExchangeCodeForTokens(ctx, code, redirectURI)
if errExchange != nil {
oauthStatus[state] = "Authentication failed"
fmt.Printf("Authentication failed: %v\n", errExchange)
return
}
tokenStorage := authSvc.CreateTokenStorage(tokenData)
identifier := strings.TrimSpace(tokenStorage.Email)
if identifier == "" {
identifier = fmt.Sprintf("iflow-%d", time.Now().UnixMilli())
tokenStorage.Email = identifier
}
record := &coreauth.Auth{
ID: fmt.Sprintf("iflow-%s.json", identifier),
Provider: "iflow",
FileName: fmt.Sprintf("iflow-%s.json", identifier),
Storage: tokenStorage,
Metadata: map[string]any{"email": identifier, "api_key": tokenStorage.APIKey},
Attributes: map[string]string{"api_key": tokenStorage.APIKey},
}
savedPath, errSave := h.saveTokenRecord(ctx, record)
if errSave != nil {
oauthStatus[state] = "Failed to save authentication tokens"
log.Fatalf("Failed to save authentication tokens: %v", errSave)
return
}
fmt.Printf("Authentication successful! Token saved to %s\n", savedPath)
if tokenStorage.APIKey != "" {
fmt.Println("API key obtained and saved")
}
fmt.Println("You can now use iFlow services through this CLI")
delete(oauthStatus, state)
}()
oauthStatus[state] = ""
c.JSON(http.StatusOK, gin.H{"status": "ok", "url": authURL, "state": state})
return
}
oauthServer := iflowauth.NewOAuthServer(iflowauth.CallbackPort)
if err := oauthServer.Start(); err != nil {
oauthStatus[state] = "Failed to start authentication server"
log.Errorf("Failed to start iFlow OAuth server: %v", err)
c.JSON(http.StatusInternalServerError, gin.H{"status": "error", "error": "failed to start local oauth server"})
return
}
go func() {
if isWebUI {
defer stopCallbackForwarder(iflowauth.CallbackPort)
}
fmt.Println("Waiting for authentication...")
defer func() {
stopCtx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
defer cancel()
if err := oauthServer.Stop(stopCtx); err != nil {
log.Warnf("Failed to stop iFlow OAuth server: %v", err)
waitFile := filepath.Join(h.cfg.AuthDir, fmt.Sprintf(".oauth-iflow-%s.oauth", state))
deadline := time.Now().Add(5 * time.Minute)
var resultMap map[string]string
for {
if time.Now().After(deadline) {
oauthStatus[state] = "Authentication failed"
fmt.Println("Authentication failed: timeout waiting for callback")
return
}
}()
result, err := oauthServer.WaitForCallback(5 * time.Minute)
if err != nil {
oauthStatus[state] = "Authentication failed"
fmt.Printf("Authentication failed: %v\n", err)
return
if data, errR := os.ReadFile(waitFile); errR == nil {
_ = os.Remove(waitFile)
_ = json.Unmarshal(data, &resultMap)
break
}
time.Sleep(500 * time.Millisecond)
}
if result.Error != "" {
if errStr := strings.TrimSpace(resultMap["error"]); errStr != "" {
oauthStatus[state] = "Authentication failed"
fmt.Printf("Authentication failed: %s\n", result.Error)
fmt.Printf("Authentication failed: %s\n", errStr)
return
}
if result.State != state {
if resultState := strings.TrimSpace(resultMap["state"]); resultState != state {
oauthStatus[state] = "Authentication failed"
fmt.Println("Authentication failed: state mismatch")
return
}
tokenData, errExchange := authSvc.ExchangeCodeForTokens(ctx, result.Code, redirectURI)
code := strings.TrimSpace(resultMap["code"])
if code == "" {
oauthStatus[state] = "Authentication failed"
fmt.Println("Authentication failed: code missing")
return
}
tokenData, errExchange := authSvc.ExchangeCodeForTokens(ctx, code, redirectURI)
if errExchange != nil {
oauthStatus[state] = "Authentication failed"
fmt.Printf("Authentication failed: %v\n", errExchange)

View File

@@ -7,6 +7,7 @@ import (
"fmt"
"net/http"
"os"
"path/filepath"
"strings"
"sync"
"time"
@@ -37,6 +38,7 @@ type Handler struct {
localPassword string
allowRemoteOverride bool
envSecret string
logDir string
}
// NewHandler creates a new management handler instance.
@@ -68,6 +70,19 @@ func (h *Handler) SetUsageStatistics(stats *usage.RequestStatistics) { h.usageSt
// SetLocalPassword configures the runtime-local password accepted for localhost requests.
func (h *Handler) SetLocalPassword(password string) { h.localPassword = password }
// SetLogDirectory updates the directory where main.log should be looked up.
func (h *Handler) SetLogDirectory(dir string) {
if dir == "" {
return
}
if !filepath.IsAbs(dir) {
if abs, err := filepath.Abs(dir); err == nil {
dir = abs
}
}
h.logDir = dir
}
// Middleware enforces access control for management endpoints.
// All requests (local and remote) require a valid management key.
// Additionally, remote access requires allow-remote-management=true.

View File

@@ -0,0 +1,344 @@
package management
import (
"bufio"
"fmt"
"math"
"net/http"
"os"
"path/filepath"
"sort"
"strconv"
"strings"
"time"
"github.com/gin-gonic/gin"
)
const (
defaultLogFileName = "main.log"
logScannerInitialBuffer = 64 * 1024
logScannerMaxBuffer = 8 * 1024 * 1024
)
// GetLogs returns log lines with optional incremental loading.
func (h *Handler) GetLogs(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
}
if !h.cfg.LoggingToFile {
c.JSON(http.StatusBadRequest, gin.H{"error": "logging to file disabled"})
return
}
logDir := h.logDirectory()
if strings.TrimSpace(logDir) == "" {
c.JSON(http.StatusInternalServerError, gin.H{"error": "log directory not configured"})
return
}
files, err := h.collectLogFiles(logDir)
if err != nil {
if os.IsNotExist(err) {
cutoff := parseCutoff(c.Query("after"))
c.JSON(http.StatusOK, gin.H{
"lines": []string{},
"line-count": 0,
"latest-timestamp": cutoff,
})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to list log files: %v", err)})
return
}
cutoff := parseCutoff(c.Query("after"))
acc := newLogAccumulator(cutoff)
for i := range files {
if errProcess := acc.consumeFile(files[i]); errProcess != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to read log file %s: %v", files[i], errProcess)})
return
}
}
lines, total, latest := acc.result()
if latest == 0 || latest < cutoff {
latest = cutoff
}
c.JSON(http.StatusOK, gin.H{
"lines": lines,
"line-count": total,
"latest-timestamp": latest,
})
}
// DeleteLogs removes all rotated log files and truncates the active log.
func (h *Handler) DeleteLogs(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
}
if !h.cfg.LoggingToFile {
c.JSON(http.StatusBadRequest, gin.H{"error": "logging to file disabled"})
return
}
dir := h.logDirectory()
if strings.TrimSpace(dir) == "" {
c.JSON(http.StatusInternalServerError, gin.H{"error": "log directory not configured"})
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
}
removed := 0
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
fullPath := filepath.Join(dir, name)
if name == defaultLogFileName {
if errTrunc := os.Truncate(fullPath, 0); errTrunc != nil && !os.IsNotExist(errTrunc) {
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to truncate log file: %v", errTrunc)})
return
}
continue
}
if isRotatedLogFile(name) {
if errRemove := os.Remove(fullPath); errRemove != nil && !os.IsNotExist(errRemove) {
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to remove %s: %v", name, errRemove)})
return
}
removed++
}
}
c.JSON(http.StatusOK, gin.H{
"success": true,
"message": "Logs cleared successfully",
"removed": removed,
})
}
func (h *Handler) logDirectory() string {
if h == nil {
return ""
}
if h.logDir != "" {
return h.logDir
}
if h.configFilePath != "" {
dir := filepath.Dir(h.configFilePath)
if dir != "" && dir != "." {
return filepath.Join(dir, "logs")
}
}
return "logs"
}
func (h *Handler) collectLogFiles(dir string) ([]string, error) {
entries, err := os.ReadDir(dir)
if err != nil {
return nil, err
}
type candidate struct {
path string
order int64
}
cands := make([]candidate, 0, len(entries))
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
if name == defaultLogFileName {
cands = append(cands, candidate{path: filepath.Join(dir, name), order: 0})
continue
}
if order, ok := rotationOrder(name); ok {
cands = append(cands, candidate{path: filepath.Join(dir, name), order: order})
}
}
if len(cands) == 0 {
return []string{}, nil
}
sort.Slice(cands, func(i, j int) bool { return cands[i].order < cands[j].order })
paths := make([]string, 0, len(cands))
for i := len(cands) - 1; i >= 0; i-- {
paths = append(paths, cands[i].path)
}
return paths, nil
}
type logAccumulator struct {
cutoff int64
lines []string
total int
latest int64
include bool
}
func newLogAccumulator(cutoff int64) *logAccumulator {
return &logAccumulator{
cutoff: cutoff,
lines: make([]string, 0, 256),
}
}
func (acc *logAccumulator) consumeFile(path string) error {
file, err := os.Open(path)
if err != nil {
if os.IsNotExist(err) {
return nil
}
return err
}
defer file.Close()
scanner := bufio.NewScanner(file)
buf := make([]byte, 0, logScannerInitialBuffer)
scanner.Buffer(buf, logScannerMaxBuffer)
for scanner.Scan() {
acc.addLine(scanner.Text())
}
if errScan := scanner.Err(); errScan != nil {
return errScan
}
return nil
}
func (acc *logAccumulator) addLine(raw string) {
line := strings.TrimRight(raw, "\r")
acc.total++
ts := parseTimestamp(line)
if ts > acc.latest {
acc.latest = ts
}
if ts > 0 {
acc.include = acc.cutoff == 0 || ts > acc.cutoff
if acc.cutoff == 0 || acc.include {
acc.lines = append(acc.lines, line)
}
return
}
if acc.cutoff == 0 || acc.include {
acc.lines = append(acc.lines, line)
}
}
func (acc *logAccumulator) result() ([]string, int, int64) {
if acc.lines == nil {
acc.lines = []string{}
}
return acc.lines, acc.total, acc.latest
}
func parseCutoff(raw string) int64 {
value := strings.TrimSpace(raw)
if value == "" {
return 0
}
ts, err := strconv.ParseInt(value, 10, 64)
if err != nil || ts <= 0 {
return 0
}
return ts
}
func parseTimestamp(line string) int64 {
if strings.HasPrefix(line, "[") {
line = line[1:]
}
if len(line) < 19 {
return 0
}
candidate := line[:19]
t, err := time.ParseInLocation("2006-01-02 15:04:05", candidate, time.Local)
if err != nil {
return 0
}
return t.Unix()
}
func isRotatedLogFile(name string) bool {
if _, ok := rotationOrder(name); ok {
return true
}
return false
}
func rotationOrder(name string) (int64, bool) {
if order, ok := numericRotationOrder(name); ok {
return order, true
}
if order, ok := timestampRotationOrder(name); ok {
return order, true
}
return 0, false
}
func numericRotationOrder(name string) (int64, bool) {
if !strings.HasPrefix(name, defaultLogFileName+".") {
return 0, false
}
suffix := strings.TrimPrefix(name, defaultLogFileName+".")
if suffix == "" {
return 0, false
}
n, err := strconv.Atoi(suffix)
if err != nil {
return 0, false
}
return int64(n), true
}
func timestampRotationOrder(name string) (int64, bool) {
ext := filepath.Ext(defaultLogFileName)
base := strings.TrimSuffix(defaultLogFileName, ext)
if base == "" {
return 0, false
}
prefix := base + "-"
if !strings.HasPrefix(name, prefix) {
return 0, false
}
clean := strings.TrimPrefix(name, prefix)
if strings.HasSuffix(clean, ".gz") {
clean = strings.TrimSuffix(clean, ".gz")
}
if ext != "" {
if !strings.HasSuffix(clean, ext) {
return 0, false
}
clean = strings.TrimSuffix(clean, ext)
}
if clean == "" {
return 0, false
}
if idx := strings.IndexByte(clean, '.'); idx != -1 {
clean = clean[:idx]
}
parsed, err := time.ParseInLocation("2006-01-02T15-04-05", clean, time.Local)
if err != nil {
return 0, false
}
return math.MaxInt64 - parsed.Unix(), true
}

View File

@@ -19,7 +19,12 @@ import (
func RequestLoggingMiddleware(logger logging.RequestLogger) gin.HandlerFunc {
return func(c *gin.Context) {
path := c.Request.URL.Path
if strings.HasPrefix(path, "/v0/management") || path == "/keep-alive" {
shouldLog := false
if strings.HasPrefix(path, "/v1") {
shouldLog = true
}
if !shouldLog {
c.Next()
return
}

View File

@@ -233,6 +233,7 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
if optionState.localPassword != "" {
s.mgmt.SetLocalPassword(optionState.localPassword)
}
s.mgmt.SetLogDirectory(filepath.Join(s.currentPath, "logs"))
s.localPassword = optionState.localPassword
// Setup routes
@@ -411,6 +412,8 @@ func (s *Server) registerManagementRoutes() {
mgmt.PATCH("/generative-language-api-key", s.mgmt.PatchGlKeys)
mgmt.DELETE("/generative-language-api-key", s.mgmt.DeleteGlKeys)
mgmt.GET("/logs", s.mgmt.GetLogs)
mgmt.DELETE("/logs", s.mgmt.DeleteLogs)
mgmt.GET("/request-log", s.mgmt.GetRequestLog)
mgmt.PUT("/request-log", s.mgmt.PutRequestLog)
mgmt.PATCH("/request-log", s.mgmt.PutRequestLog)

View File

@@ -56,6 +56,14 @@ type releaseResponse struct {
// StaticDir resolves the directory that stores the management control panel asset.
func StaticDir(configFilePath string) string {
if override := strings.TrimSpace(os.Getenv("MANAGEMENT_STATIC_PATH")); override != "" {
cleaned := filepath.Clean(override)
if strings.EqualFold(filepath.Base(cleaned), managementAssetName) {
return filepath.Dir(cleaned)
}
return cleaned
}
configFilePath = strings.TrimSpace(configFilePath)
if configFilePath == "" {
return ""
@@ -74,6 +82,14 @@ func StaticDir(configFilePath string) string {
// FilePath resolves the absolute path to the management control panel asset.
func FilePath(configFilePath string) string {
if override := strings.TrimSpace(os.Getenv("MANAGEMENT_STATIC_PATH")); override != "" {
cleaned := filepath.Clean(override)
if strings.EqualFold(filepath.Base(cleaned), managementAssetName) {
return cleaned
}
return filepath.Join(cleaned, ManagementFileName)
}
dir := StaticDir(configFilePath)
if dir == "" {
return ""

View File

@@ -8,6 +8,15 @@ import "time"
// GetClaudeModels returns the standard Claude model definitions
func GetClaudeModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "claude-haiku-4-5-20251001",
Object: "model",
Created: 1759276800, // 2025-10-01
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Haiku",
},
{
ID: "claude-sonnet-4-5-20250929",
Object: "model",

View File

@@ -60,7 +60,11 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
from := opts.SourceFormat
to := sdktranslator.FromString("gemini-cli")
budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
if hasOverride {
basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
}
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
action := "generateContent"
@@ -149,7 +153,11 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
from := opts.SourceFormat
to := sdktranslator.FromString("gemini-cli")
budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
if hasOverride {
basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
}
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
projectID := strings.TrimSpace(stringValue(auth.Metadata, "project_id"))
@@ -292,8 +300,12 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
var lastStatus int
var lastBody []byte
budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
for _, attemptModel := range models {
payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
if hasOverride {
payload = util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)
}
payload = deleteJSONField(payload, "project")
payload = deleteJSONField(payload, "model")
payload = disableGeminiThinkingConfig(payload, attemptModel)

View File

@@ -77,6 +77,9 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
}
body = disableGeminiThinkingConfig(body, req.Model)
body = fixGeminiImageAspectRatio(req.Model, body)
@@ -136,6 +139,9 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
}
body = disableGeminiThinkingConfig(body, req.Model)
body = fixGeminiImageAspectRatio(req.Model, body)
@@ -208,6 +214,9 @@ func (e *GeminiExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
translatedReq = util.ApplyGeminiThinkingConfig(translatedReq, budgetOverride, includeOverride)
}
translatedReq = disableGeminiThinkingConfig(translatedReq, req.Model)
translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
respCtx := context.WithValue(ctx, "alt", opts.Alt)

View File

@@ -97,6 +97,7 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
// Process the main content part of the response.
partsResult := gjson.GetBytes(rawJSON, "response.candidates.0.content.parts")
hasFunctionCall := false
if partsResult.IsArray() {
partResults := partsResult.Array()
for i := 0; i < len(partResults); i++ {
@@ -118,6 +119,7 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
} else if functionCallResult.Exists() {
// Handle function call content.
hasFunctionCall = true
toolCallsResult := gjson.Get(template, "choices.0.delta.tool_calls")
functionCallIndex := (*param).(*convertCliResponseToOpenAIChatParams).FunctionIndex
(*param).(*convertCliResponseToOpenAIChatParams).FunctionIndex++
@@ -169,6 +171,11 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
}
}
if hasFunctionCall {
template, _ = sjson.Set(template, "choices.0.finish_reason", "tool_calls")
template, _ = sjson.Set(template, "choices.0.native_finish_reason", "tool_calls")
}
return []string{template}
}

View File

@@ -100,6 +100,7 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
// Process the main content part of the response.
partsResult := gjson.GetBytes(rawJSON, "candidates.0.content.parts")
hasFunctionCall := false
if partsResult.IsArray() {
partResults := partsResult.Array()
for i := 0; i < len(partResults); i++ {
@@ -121,6 +122,7 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
} else if functionCallResult.Exists() {
// Handle function call content.
hasFunctionCall = true
toolCallsResult := gjson.Get(template, "choices.0.delta.tool_calls")
functionCallIndex := (*param).(*convertGeminiResponseToOpenAIChatParams).FunctionIndex
(*param).(*convertGeminiResponseToOpenAIChatParams).FunctionIndex++
@@ -172,6 +174,11 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
}
}
if hasFunctionCall {
template, _ = sjson.Set(template, "choices.0.finish_reason", "tool_calls")
template, _ = sjson.Set(template, "choices.0.native_finish_reason", "tool_calls")
}
return []string{template}
}
@@ -231,6 +238,7 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
// Process the main content part of the response.
partsResult := gjson.GetBytes(rawJSON, "candidates.0.content.parts")
hasFunctionCall := false
if partsResult.IsArray() {
partsResults := partsResult.Array()
for i := 0; i < len(partsResults); i++ {
@@ -252,6 +260,7 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
template, _ = sjson.Set(template, "choices.0.message.role", "assistant")
} else if functionCallResult.Exists() {
// Append function call content to the tool_calls array.
hasFunctionCall = true
toolCallsResult := gjson.Get(template, "choices.0.message.tool_calls")
if !toolCallsResult.Exists() || !toolCallsResult.IsArray() {
template, _ = sjson.SetRaw(template, "choices.0.message.tool_calls", `[]`)
@@ -297,5 +306,10 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
}
}
if hasFunctionCall {
template, _ = sjson.Set(template, "choices.0.finish_reason", "tool_calls")
template, _ = sjson.Set(template, "choices.0.native_finish_reason", "tool_calls")
}
return template
}

View File

@@ -97,8 +97,8 @@ func ConvertOpenAIResponseToGemini(_ context.Context, _ string, originalRequestR
var results []string
choices.ForEach(func(choiceIndex, choice gjson.Result) bool {
// Base Gemini response template
template := `{"candidates":[{"content":{"parts":[],"role":"model"},"finishReason":"STOP","index":0}]}`
// Base Gemini response template without finishReason; set when known
template := `{"candidates":[{"content":{"parts":[],"role":"model"},"index":0}]}`
// Set model if available
if model := root.Get("model"); model.Exists() {
@@ -514,8 +514,8 @@ func tryParseNumber(s string) (interface{}, bool) {
func ConvertOpenAIResponseToGeminiNonStream(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
root := gjson.ParseBytes(rawJSON)
// Base Gemini response template
out := `{"candidates":[{"content":{"parts":[],"role":"model"},"finishReason":"STOP","index":0}]}`
// Base Gemini response template without finishReason; set when known
out := `{"candidates":[{"content":{"parts":[],"role":"model"},"index":0}]}`
// Set model if available
if model := root.Get("model"); model.Exists() {

View File

@@ -67,9 +67,20 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
rawJSON = bytes.TrimSpace(rawJSON[5:])
}
rawJSON = bytes.TrimSpace(rawJSON)
if len(rawJSON) == 0 {
return []string{}
}
if bytes.Equal(rawJSON, []byte("[DONE]")) {
return []string{}
}
root := gjson.ParseBytes(rawJSON)
obj := root.Get("object").String()
if obj != "chat.completion.chunk" {
obj := root.Get("object")
if obj.Exists() && obj.String() != "" && obj.String() != "chat.completion.chunk" {
return []string{}
}
if !root.Get("choices").Exists() || !root.Get("choices").IsArray() {
return []string{}
}

View File

@@ -0,0 +1,181 @@
package util
import (
"encoding/json"
"strconv"
"strings"
"github.com/tidwall/sjson"
)
const (
GeminiThinkingBudgetMetadataKey = "gemini_thinking_budget"
GeminiIncludeThoughtsMetadataKey = "gemini_include_thoughts"
GeminiOriginalModelMetadataKey = "gemini_original_model"
)
func ParseGeminiThinkingSuffix(model string) (string, *int, *bool, bool) {
if model == "" {
return model, nil, nil, false
}
lower := strings.ToLower(model)
if !strings.HasPrefix(lower, "gemini-") {
return model, nil, nil, false
}
if strings.HasSuffix(lower, "-nothinking") {
base := model[:len(model)-len("-nothinking")]
budgetValue := 0
if strings.HasPrefix(lower, "gemini-2.5-pro") {
budgetValue = 128
}
include := false
return base, &budgetValue, &include, true
}
idx := strings.LastIndex(lower, "-thinking-")
if idx == -1 {
return model, nil, nil, false
}
digits := model[idx+len("-thinking-"):]
if digits == "" {
return model, nil, nil, false
}
end := len(digits)
for i := 0; i < len(digits); i++ {
if digits[i] < '0' || digits[i] > '9' {
end = i
break
}
}
if end == 0 {
return model, nil, nil, false
}
valueStr := digits[:end]
value, err := strconv.Atoi(valueStr)
if err != nil {
return model, nil, nil, false
}
base := model[:idx]
budgetValue := value
return base, &budgetValue, nil, true
}
func ApplyGeminiThinkingConfig(body []byte, budget *int, includeThoughts *bool) []byte {
if budget == nil && includeThoughts == nil {
return body
}
updated := body
if budget != nil {
valuePath := "generationConfig.thinkingConfig.thinkingBudget"
rewritten, err := sjson.SetBytes(updated, valuePath, *budget)
if err == nil {
updated = rewritten
}
}
if includeThoughts != nil {
valuePath := "generationConfig.thinkingConfig.include_thoughts"
rewritten, err := sjson.SetBytes(updated, valuePath, *includeThoughts)
if err == nil {
updated = rewritten
}
}
return updated
}
func ApplyGeminiCLIThinkingConfig(body []byte, budget *int, includeThoughts *bool) []byte {
if budget == nil && includeThoughts == nil {
return body
}
updated := body
if budget != nil {
valuePath := "request.generationConfig.thinkingConfig.thinkingBudget"
rewritten, err := sjson.SetBytes(updated, valuePath, *budget)
if err == nil {
updated = rewritten
}
}
if includeThoughts != nil {
valuePath := "request.generationConfig.thinkingConfig.include_thoughts"
rewritten, err := sjson.SetBytes(updated, valuePath, *includeThoughts)
if err == nil {
updated = rewritten
}
}
return updated
}
func GeminiThinkingFromMetadata(metadata map[string]any) (*int, *bool, bool) {
if len(metadata) == 0 {
return nil, nil, false
}
var (
budgetPtr *int
includePtr *bool
matched bool
)
if rawBudget, ok := metadata[GeminiThinkingBudgetMetadataKey]; ok {
switch v := rawBudget.(type) {
case int:
budget := v
budgetPtr = &budget
matched = true
case int32:
budget := int(v)
budgetPtr = &budget
matched = true
case int64:
budget := int(v)
budgetPtr = &budget
matched = true
case float64:
budget := int(v)
budgetPtr = &budget
matched = true
case json.Number:
if val, err := v.Int64(); err == nil {
budget := int(val)
budgetPtr = &budget
matched = true
}
}
}
if rawInclude, ok := metadata[GeminiIncludeThoughtsMetadataKey]; ok {
switch v := rawInclude.(type) {
case bool:
include := v
includePtr = &include
matched = true
case string:
if parsed, err := strconv.ParseBool(v); err == nil {
include := parsed
includePtr = &include
matched = true
}
case json.Number:
if val, err := v.Int64(); err == nil {
include := val != 0
includePtr = &include
matched = true
}
case int:
include := v != 0
includePtr = &include
matched = true
case int32:
include := v != 0
includePtr = &include
matched = true
case int64:
include := v != 0
includePtr = &include
matched = true
case float64:
include := v != 0
includePtr = &include
matched = true
}
}
return budgetPtr, includePtr, matched
}

View File

@@ -133,20 +133,27 @@ func (h *BaseAPIHandler) GetContextWithCancel(handler interfaces.APIHandler, c *
// ExecuteWithAuthManager executes a non-streaming request via the core auth manager.
// This path is the only supported execution route.
func (h *BaseAPIHandler) ExecuteWithAuthManager(ctx context.Context, handlerType, modelName string, rawJSON []byte, alt string) ([]byte, *interfaces.ErrorMessage) {
providers := util.GetProviderName(modelName)
normalizedModel, metadata := normalizeModelMetadata(modelName)
providers := util.GetProviderName(normalizedModel)
if len(providers) == 0 {
return nil, &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
}
req := coreexecutor.Request{
Model: modelName,
Model: normalizedModel,
Payload: cloneBytes(rawJSON),
}
if cloned := cloneMetadata(metadata); cloned != nil {
req.Metadata = cloned
}
opts := coreexecutor.Options{
Stream: false,
Alt: alt,
OriginalRequest: cloneBytes(rawJSON),
SourceFormat: sdktranslator.FromString(handlerType),
}
if cloned := cloneMetadata(metadata); cloned != nil {
opts.Metadata = cloned
}
resp, err := h.AuthManager.Execute(ctx, providers, req, opts)
if err != nil {
return nil, &interfaces.ErrorMessage{StatusCode: http.StatusInternalServerError, Error: err}
@@ -157,20 +164,27 @@ func (h *BaseAPIHandler) ExecuteWithAuthManager(ctx context.Context, handlerType
// ExecuteCountWithAuthManager executes a non-streaming request via the core auth manager.
// This path is the only supported execution route.
func (h *BaseAPIHandler) ExecuteCountWithAuthManager(ctx context.Context, handlerType, modelName string, rawJSON []byte, alt string) ([]byte, *interfaces.ErrorMessage) {
providers := util.GetProviderName(modelName)
normalizedModel, metadata := normalizeModelMetadata(modelName)
providers := util.GetProviderName(normalizedModel)
if len(providers) == 0 {
return nil, &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
}
req := coreexecutor.Request{
Model: modelName,
Model: normalizedModel,
Payload: cloneBytes(rawJSON),
}
if cloned := cloneMetadata(metadata); cloned != nil {
req.Metadata = cloned
}
opts := coreexecutor.Options{
Stream: false,
Alt: alt,
OriginalRequest: cloneBytes(rawJSON),
SourceFormat: sdktranslator.FromString(handlerType),
}
if cloned := cloneMetadata(metadata); cloned != nil {
opts.Metadata = cloned
}
resp, err := h.AuthManager.ExecuteCount(ctx, providers, req, opts)
if err != nil {
return nil, &interfaces.ErrorMessage{StatusCode: http.StatusInternalServerError, Error: err}
@@ -181,7 +195,8 @@ func (h *BaseAPIHandler) ExecuteCountWithAuthManager(ctx context.Context, handle
// ExecuteStreamWithAuthManager executes a streaming request via the core auth manager.
// This path is the only supported execution route.
func (h *BaseAPIHandler) ExecuteStreamWithAuthManager(ctx context.Context, handlerType, modelName string, rawJSON []byte, alt string) (<-chan []byte, <-chan *interfaces.ErrorMessage) {
providers := util.GetProviderName(modelName)
normalizedModel, metadata := normalizeModelMetadata(modelName)
providers := util.GetProviderName(normalizedModel)
if len(providers) == 0 {
errChan := make(chan *interfaces.ErrorMessage, 1)
errChan <- &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
@@ -189,15 +204,21 @@ func (h *BaseAPIHandler) ExecuteStreamWithAuthManager(ctx context.Context, handl
return nil, errChan
}
req := coreexecutor.Request{
Model: modelName,
Model: normalizedModel,
Payload: cloneBytes(rawJSON),
}
if cloned := cloneMetadata(metadata); cloned != nil {
req.Metadata = cloned
}
opts := coreexecutor.Options{
Stream: true,
Alt: alt,
OriginalRequest: cloneBytes(rawJSON),
SourceFormat: sdktranslator.FromString(handlerType),
}
if cloned := cloneMetadata(metadata); cloned != nil {
opts.Metadata = cloned
}
chunks, err := h.AuthManager.ExecuteStream(ctx, providers, req, opts)
if err != nil {
errChan := make(chan *interfaces.ErrorMessage, 1)
@@ -232,6 +253,34 @@ func cloneBytes(src []byte) []byte {
return dst
}
func normalizeModelMetadata(modelName string) (string, map[string]any) {
baseModel, budget, include, matched := util.ParseGeminiThinkingSuffix(modelName)
if !matched {
return baseModel, nil
}
metadata := map[string]any{
util.GeminiOriginalModelMetadataKey: modelName,
}
if budget != nil {
metadata[util.GeminiThinkingBudgetMetadataKey] = *budget
}
if include != nil {
metadata[util.GeminiIncludeThoughtsMetadataKey] = *include
}
return baseModel, metadata
}
func cloneMetadata(src map[string]any) map[string]any {
if len(src) == 0 {
return nil
}
dst := make(map[string]any, len(src))
for k, v := range src {
dst[k] = v
}
return dst
}
// WriteErrorResponse writes an error message to the response writer using the HTTP status embedded in the message.
func (h *BaseAPIHandler) WriteErrorResponse(c *gin.Context, msg *interfaces.ErrorMessage) {
status := http.StatusInternalServerError