Merge pull request #26 from luispater/flash-lite

Add Gemini 2.5 Flash-Lite Model

.dockerignore

@@ -0,0 +1,25 @@
+# Git and GitHub folders
+.git
+.github
+
+# Docker and CI/CD related files
+docker-compose.yml
+.dockerignore
+.gitignore
+.goreleaser.yml
+Dockerfile
+
+# Documentation and license
+README.md
+README_CN.md
+MANAGEMENT_API.md
+MANAGEMENT_API_CN.md
+LICENSE
+
+# Example configuration
+config.example.yaml
+
+# Runtime data folders (should be mounted as volumes)
+auths
+logs
+config.yaml

.gitignore

@@ -1,3 +1,5 @@
 config.yaml
-docs/
+docs/*
-logs/
+logs/*
+auths/*
+!auths/.gitkeep

README.md

@@ -486,6 +486,31 @@ Run the following command to start the server:
 docker run --rm -p 8317:8317 -v /path/to/your/config.yaml:/CLIProxyAPI/config.yaml -v /path/to/your/auth-dir:/root/.cli-proxy-api eceasy/cli-proxy-api:latest
 ```
 
+## Run with Docker Compose
+
+1.  Create a `config.yaml` from `config.example.yaml` and customize it.
+
+2.  Build and start the services using Docker Compose:
+    ```bash
+    docker compose up -d --build
+    ```
+
+3.  To authenticate with providers, run the login command inside the container:
+    - **Gemini**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --login`
+    - **OpenAI (Codex)**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --codex-login`
+    - **Claude**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --claude-login`
+    - **Qwen**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --qwen-login`
+
+4.  To view the server logs:
+    ```bash
+    docker compose logs -f
+    ```
+
+5.  To stop the application:
+    ```bash
+    docker compose down
+    ```
+
 ## Management API
 
 see [MANAGEMENT_API.md](MANAGEMENT_API.md)

README_CN.md

@@ -499,6 +499,31 @@ docker run -it -rm -v /path/to/your/config.yaml:/CLIProxyAPI/config.yaml -v /pat
 docker run --rm -p 8317:8317 -v /path/to/your/config.yaml:/CLIProxyAPI/config.yaml -v /path/to/your/auth-dir:/root/.cli-proxy-api eceasy/cli-proxy-api:latest
 ```
 
+## 使用 Docker Compose 运行
+
+1.  从 `config.example.yaml` 创建一个 `config.yaml` 文件并进行自定义。
+
+2.  使用 Docker Compose 构建并启动服务：
+    ```bash
+    docker compose up -d --build
+    ```
+
+3.  要在容器内运行登录命令进行身份验证：
+    - **Gemini**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --login`
+    - **OpenAI (Codex)**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --codex-login`
+    - **Claude**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --claude-login`
+    - **Qwen**: `docker compose exec cli-proxy-api /CLIProxyAPI/CLIProxyAPI -no-browser --qwen-login`
+
+4.  查看服务器日志：
+    ```bash
+    docker compose logs -f
+    ```
+
+5.  停止应用程序：
+    ```bash
+    docker compose down
+    ```
+
 ## 管理 API 文档
 
 请参见 [MANAGEMENT_API_CN.md](MANAGEMENT_API_CN.md)

cmd/server/main.go

@@ -8,7 +8,7 @@ import (
 	"flag"
 	"fmt"
 	"os"
-	"path"
+	"path/filepath"
 	"strings"
 
 	"github.com/luispater/CLIProxyAPI/internal/cmd"
@@ -36,7 +36,7 @@ func (m *LogFormatter) Format(entry *log.Entry) ([]byte, error) {
 	timestamp := entry.Time.Format("2006-01-02 15:04:05")
 	var newLog string
 	// Customize the log format to include timestamp, level, caller file/line, and message.
-	newLog = fmt.Sprintf("[%s] [%s] [%s:%d] %s\n", timestamp, entry.Level, path.Base(entry.Caller.File), entry.Caller.Line, entry.Message)
+	newLog = fmt.Sprintf("[%s] [%s] [%s:%d] %s\n", timestamp, entry.Level, filepath.Base(entry.Caller.File), entry.Caller.Line, entry.Message)
 
 	b.WriteString(newLog)
 	return b.Bytes(), nil
@@ -96,7 +96,7 @@ func main() {
 		if err != nil {
 			log.Fatalf("failed to get working directory: %v", err)
 		}
-		configFilePath = path.Join(wd, "config.yaml")
+		configFilePath = filepath.Join(wd, "config.yaml")
 		cfg, err = config.LoadConfig(configFilePath)
 	}
 	if err != nil {
@@ -120,7 +120,7 @@ func main() {
 		parts := strings.Split(cfg.AuthDir, string(os.PathSeparator))
 		if len(parts) > 1 {
 			parts[0] = home
-			cfg.AuthDir = path.Join(parts...)
+			cfg.AuthDir = filepath.Join(parts...)
 		} else {
 			// If the path is just "~", set it to the home directory.
 			cfg.AuthDir = home

docker-compose.yml

@@ -0,0 +1,17 @@
+services:
+  cli-proxy-api:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    image: cli-proxy-api:latest
+    container_name: cli-proxy-api
+    ports:
+      - "8317:8317"
+      - "8085:8085"
+      - "1455:1455"
+      - "54545:54545"
+    volumes:
+      - ./config.yaml:/CLIProxyAPI/config.yaml
+      - ./auths:/root/.cli-proxy-api
+      - ./logs:/CLIProxyAPI/logs
+    restart: unless-stopped

internal/auth/claude/token.go

@@ -7,7 +7,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"os"
-	"path"
+	"path/filepath"
 )
 
 // ClaudeTokenStorage stores OAuth2 token information for Anthropic Claude API authentication.
@@ -49,7 +49,7 @@ func (ts *ClaudeTokenStorage) SaveTokenToFile(authFilePath string) error {
 	ts.Type = "claude"
 
 	// Create directory structure if it doesn't exist
-	if err := os.MkdirAll(path.Dir(authFilePath), 0700); err != nil {
+	if err := os.MkdirAll(filepath.Dir(authFilePath), 0700); err != nil {
 		return fmt.Errorf("failed to create directory: %v", err)
 	}
 

internal/auth/codex/token.go

@@ -7,7 +7,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"os"
-	"path"
+	"path/filepath"
 )
 
 // CodexTokenStorage stores OAuth2 token information for OpenAI Codex API authentication.
@@ -43,7 +43,7 @@ type CodexTokenStorage struct {
 //   - error: An error if the operation fails, nil otherwise
 func (ts *CodexTokenStorage) SaveTokenToFile(authFilePath string) error {
 	ts.Type = "codex"
-	if err := os.MkdirAll(path.Dir(authFilePath), 0700); err != nil {
+	if err := os.MkdirAll(filepath.Dir(authFilePath), 0700); err != nil {
 		return fmt.Errorf("failed to create directory: %v", err)
 	}
 

internal/auth/gemini/gemini_token.go

@@ -7,7 +7,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"os"
-	"path"
+	"path/filepath"
 
 	log "github.com/sirupsen/logrus"
 )
@@ -46,7 +46,7 @@ type GeminiTokenStorage struct {
 //   - error: An error if the operation fails, nil otherwise
 func (ts *GeminiTokenStorage) SaveTokenToFile(authFilePath string) error {
 	ts.Type = "gemini"
-	if err := os.MkdirAll(path.Dir(authFilePath), 0700); err != nil {
+	if err := os.MkdirAll(filepath.Dir(authFilePath), 0700); err != nil {
 		return fmt.Errorf("failed to create directory: %v", err)
 	}
 

internal/auth/qwen/qwen_token.go

@@ -7,7 +7,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"os"
-	"path"
+	"path/filepath"
 )
 
 // QwenTokenStorage stores OAuth2 token information for Alibaba Qwen API authentication.
@@ -41,7 +41,7 @@ type QwenTokenStorage struct {
 //   - error: An error if the operation fails, nil otherwise
 func (ts *QwenTokenStorage) SaveTokenToFile(authFilePath string) error {
 	ts.Type = "qwen"
-	if err := os.MkdirAll(path.Dir(authFilePath), 0700); err != nil {
+	if err := os.MkdirAll(filepath.Dir(authFilePath), 0700); err != nil {
 		return fmt.Errorf("failed to create directory: %v", err)
 	}
 

internal/client/gemini-cli_client.go

@@ -38,8 +38,9 @@ const (
 
 var (
 	previewModels = map[string][]string{
-		"gemini-2.5-pro":   {"gemini-2.5-pro-preview-05-06", "gemini-2.5-pro-preview-06-05"},
+		"gemini-2.5-pro":        {"gemini-2.5-pro-preview-05-06", "gemini-2.5-pro-preview-06-05"},
-		"gemini-2.5-flash": {"gemini-2.5-flash-preview-04-17", "gemini-2.5-flash-preview-05-20"},
+		"gemini-2.5-flash":      {"gemini-2.5-flash-preview-04-17", "gemini-2.5-flash-preview-05-20"},
+		"gemini-2.5-flash-lite": {"gemini-2.5-flash-lite-preview-06-17"},
 	}
 )
 
@@ -99,6 +100,7 @@ func (c *GeminiCLIClient) CanProvideModel(modelName string) bool {
 	models := []string{
 		"gemini-2.5-pro",
 		"gemini-2.5-flash",
+		"gemini-2.5-flash-lite",
 	}
 	return util.InArray(models, modelName)
 }

internal/registry/model_definitions.go

@@ -130,6 +130,20 @@ func GetGeminiCLIModels() []*ModelInfo {
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
 		},
+		{
+			ID:                         "gemini-2.5-flash-lite",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-2.5-flash-lite",
+			Version:                    "2.5",
+			DisplayName:                "Gemini 2.5 Flash Lite",
+			Description:                "Our smallest and most cost effective model, built for at scale usage.",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           65536,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+		},
 	}
 }
 

internal/translator/claude/gemini/claude_gemini_request.go

@@ -89,6 +89,17 @@ func ConvertGeminiRequestToClaude(modelName string, inputRawJSON []byte, stream
 				out, _ = sjson.Set(out, "stop_sequences", stopSequences)
 			}
 		}
+		// Include thoughts configuration for reasoning process visibility
+		if thinkingConfig := genConfig.Get("thinkingConfig"); thinkingConfig.Exists() && thinkingConfig.IsObject() {
+			if includeThoughts := thinkingConfig.Get("include_thoughts"); includeThoughts.Exists() {
+				if includeThoughts.Type == gjson.True {
+					out, _ = sjson.Set(out, "thinking.type", "enabled")
+					if thinkingBudget := thinkingConfig.Get("thinkingBudget"); thinkingBudget.Exists() {
+						out, _ = sjson.Set(out, "thinking.budget_tokens", thinkingBudget.Int())
+					}
+				}
+			}
+		}
 	}
 
 	// System instruction conversion to Claude Code format

internal/translator/claude/gemini/claude_gemini_response.go

@@ -128,7 +128,7 @@ func ConvertClaudeResponseToGemini(_ context.Context, modelName string, original
 				}
 			case "thinking_delta":
 				// Thinking/reasoning content delta for models with reasoning capabilities
-				if text := delta.Get("text"); text.Exists() && text.String() != "" {
+				if text := delta.Get("thinking"); text.Exists() && text.String() != "" {
 					thinkingPart := `{"thought":true,"text":""}`
 					thinkingPart, _ = sjson.Set(thinkingPart, "text", text.String())
 					template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", thinkingPart)
@@ -411,7 +411,7 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 					}
 				case "thinking_delta":
 					// Process reasoning/thinking content
-					if text := delta.Get("text"); text.Exists() && text.String() != "" {
+					if text := delta.Get("thinking"); text.Exists() && text.String() != "" {
 						partJSON := `{"thought":true,"text":""}`
 						partJSON, _ = sjson.Set(partJSON, "text", text.String())
 						part := gjson.Parse(partJSON).Value().(map[string]interface{})

internal/translator/claude/openai/chat-completions/claude_openai_request.go

@@ -41,6 +41,21 @@ func ConvertOpenAIRequestToClaude(modelName string, inputRawJSON []byte, stream
 
 	root := gjson.ParseBytes(rawJSON)
 
+	if v := root.Get("reasoning_effort"); v.Exists() {
+		out, _ = sjson.Set(out, "thinking.type", "enabled")
+
+		switch v.String() {
+		case "none":
+			out, _ = sjson.Set(out, "thinking.type", "disabled")
+		case "low":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 1024)
+		case "medium":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 8192)
+		case "high":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 24576)
+		}
+	}
+
 	// Helper for generating tool call IDs in the form: toolu_<alphanum>
 	// This ensures unique identifiers for tool calls in the Claude Code format
 	genToolCallID := func() string {

internal/translator/claude/openai/chat-completions/claude_openai_response.go

@@ -128,10 +128,11 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
 				return []string{}
 			}
 		}
-		return []string{template}
+		return []string{}
 
 	case "content_block_delta":
 		// Handle content delta (text, tool use arguments, or reasoning content)
+		hasContent := false
 		if delta := root.Get("delta"); delta.Exists() {
 			deltaType := delta.Get("type").String()
 
@@ -140,8 +141,14 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
 				// Text content delta - send incremental text updates
 				if text := delta.Get("text"); text.Exists() {
 					template, _ = sjson.Set(template, "choices.0.delta.content", text.String())
+					hasContent = true
+				}
+			case "thinking_delta":
+				// Accumulate reasoning/thinking content
+				if thinking := delta.Get("thinking"); thinking.Exists() {
+					template, _ = sjson.Set(template, "choices.0.delta.reasoning_content", thinking.String())
+					hasContent = true
 				}
-
 			case "input_json_delta":
 				// Tool use input delta - accumulate arguments for tool calls
 				if partialJSON := delta.Get("partial_json"); partialJSON.Exists() {
@@ -156,7 +163,11 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
 				return []string{}
 			}
 		}
-		return []string{template}
+		if hasContent {
+			return []string{template}
+		} else {
+			return []string{}
+		}
 
 	case "content_block_stop":
 		// End of content block - output complete tool call if it's a tool_use block

internal/translator/claude/openai/responses/claude_openai-responses_request.go

@@ -28,6 +28,23 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
 
 	root := gjson.ParseBytes(rawJSON)
 
+	if v := root.Get("reasoning.effort"); v.Exists() {
+		out, _ = sjson.Set(out, "thinking.type", "enabled")
+
+		switch v.String() {
+		case "none":
+			out, _ = sjson.Set(out, "thinking.type", "disabled")
+		case "minimal":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 1024)
+		case "low":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 4096)
+		case "medium":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 8192)
+		case "high":
+			out, _ = sjson.Set(out, "thinking.budget_tokens", 24576)
+		}
+	}
+
 	// Helper for generating tool call IDs when missing
 	genToolCallID := func() string {
 		const letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"

internal/watcher/watcher.go

@@ -39,6 +39,8 @@ type Watcher struct {
 	clientsMutex   sync.RWMutex
 	reloadCallback func(map[string]interfaces.Client, *config.Config)
 	watcher        *fsnotify.Watcher
+	eventTimes     map[string]time.Time
+	eventMutex     sync.Mutex
 }
 
 // NewWatcher creates a new file watcher instance
@@ -54,6 +56,7 @@ func NewWatcher(configPath, authDir string, reloadCallback func(map[string]inter
 		reloadCallback: reloadCallback,
 		watcher:        watcher,
 		clients:        make(map[string]interfaces.Client),
+		eventTimes:     make(map[string]time.Time),
 	}, nil
 }
 
@@ -123,6 +126,16 @@ func (w *Watcher) handleEvent(event fsnotify.Event) {
 	now := time.Now()
 	log.Debugf("file system event detected: %s %s", event.Op.String(), event.Name)
 
+	// Debounce logic to prevent rapid reloads
+	w.eventMutex.Lock()
+	if lastTime, ok := w.eventTimes[event.Name]; ok && now.Sub(lastTime) < 500*time.Millisecond {
+		log.Debugf("debouncing event for %s", event.Name)
+		w.eventMutex.Unlock()
+		return
+	}
+	w.eventTimes[event.Name] = now
+	w.eventMutex.Unlock()
+
 	// Handle config file changes
 	if event.Name == w.configPath && (event.Op&fsnotify.Write == fsnotify.Write || event.Op&fsnotify.Create == fsnotify.Create) {
 		log.Infof("config file changed, reloading: %s", w.configPath)