Merge pull request #90 from router-for-me/dethink

Dethink

README.md

@@ -258,6 +258,7 @@ console.log(await claudeResponse.json());
 - gemini-2.5-pro
 - gemini-2.5-flash
 - gemini-2.5-flash-lite
+- gemini-2.5-flash-image-preview
 - gpt-5
 - gpt-5-codex
 - claude-opus-4-1-20250805
@@ -719,6 +720,17 @@ Contributions are welcome! Please feel free to submit a Pull Request.
 4. Push to the branch (`git push origin feature/amazing-feature`)
 5. Open a Pull Request
 
+## Who is with us?
+
+Those projects are based on CLIProxyAPI:
+
+### [vibeproxy](https://github.com/automazeio/vibeproxy)
+
+Native macOS menu bar app to use your Claude Code & ChatGPT subscriptions with AI coding tools - no API keys needed
+
+> [!NOTE]  
+> If you developed a project based on CLIProxyAPI, please open a PR to add it to this list.
+
 ## License
 
 This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

README_CN.md

@@ -270,6 +270,7 @@ console.log(await claudeResponse.json());
 - gemini-2.5-pro
 - gemini-2.5-flash
 - gemini-2.5-flash-lite
+- gemini-2.5-flash-image-preview
 - gpt-5
 - gpt-5-codex
 - claude-opus-4-1-20250805
@@ -728,6 +729,18 @@ docker run --rm -p 8317:8317 -v /path/to/your/config.yaml:/CLIProxyAPI/config.ya
 4. 推送到分支（`git push origin feature/amazing-feature`）
 5. 打开 Pull Request
 
+## 谁与我们在一起？
+
+这些项目基于 CLIProxyAPI:
+
+### [vibeproxy](https://github.com/automazeio/vibeproxy)
+
+一个原生 macOS 菜单栏应用，让您可以使用 Claude Code & ChatGPT 订阅服务和 AI 编程工具，无需 API 密钥。
+
+> [!NOTE]  
+> 如果你开发了基于 CLIProxyAPI 的项目，请提交一个 PR（拉取请求）将其添加到此列表中。
+
+
 ## 许可证
 
 此项目根据 MIT 许可证授权 - 有关详细信息，请参阅 [LICENSE](LICENSE) 文件。

cmd/server/main.go

@@ -21,9 +21,10 @@ import (
 )
 
 var (
-	Version   = "dev"
-	Commit    = "none"
-	BuildDate = "unknown"
+	Version           = "dev"
+	Commit            = "none"
+	BuildDate         = "unknown"
+	DefaultConfigPath = ""
 )
 
 // init initializes the shared logger setup.
@@ -58,7 +59,7 @@ func main() {
 	flag.BoolVar(&geminiWebAuth, "gemini-web-auth", false, "Auth Gemini Web using cookies")
 	flag.BoolVar(&noBrowser, "no-browser", false, "Don't open browser automatically for OAuth")
 	flag.StringVar(&projectID, "project_id", "", "Project ID (Gemini only, not required)")
-	flag.StringVar(&configPath, "config", "", "Configure File Path")
+	flag.StringVar(&configPath, "config", DefaultConfigPath, "Configure File Path")
 	flag.StringVar(&password, "password", "", "")
 
 	flag.CommandLine.Usage = func() {

internal/registry/model_definitions.go

@@ -152,6 +152,20 @@ func GetGeminiCLIModels() []*ModelInfo {
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
 		},
+		{
+			ID:                         "gemini-2.5-flash-image-preview",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-2.5-flash-image-preview",
+			Version:                    "2.5",
+			DisplayName:                "Gemini 2.5 Flash Image Preview",
+			Description:                "State-of-the-art image generation and editing model.",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           8192,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+		},
 	}
 }
 

internal/runtime/executor/claude_executor.go

@@ -144,8 +144,8 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 		defer close(out)
 		defer func() { _ = resp.Body.Close() }()
 		scanner := bufio.NewScanner(resp.Body)
-		buf := make([]byte, 1024*1024)
-		scanner.Buffer(buf, 1024*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()

internal/runtime/executor/codex_executor.go

@@ -189,8 +189,8 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 		defer close(out)
 		defer func() { _ = resp.Body.Close() }()
 		scanner := bufio.NewScanner(resp.Body)
-		buf := make([]byte, 1024*1024)
-		scanner.Buffer(buf, 1024*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()

internal/runtime/executor/gemini_cli_executor.go

@@ -89,6 +89,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 			payload = setJSONField(payload, "project", projectID)
 			payload = setJSONField(payload, "model", attemptModel)
 		}
+		payload = disableGeminiThinkingConfig(payload, attemptModel)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -165,6 +166,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 		payload := append([]byte(nil), basePayload...)
 		payload = setJSONField(payload, "project", projectID)
 		payload = setJSONField(payload, "model", attemptModel)
+		payload = disableGeminiThinkingConfig(payload, attemptModel)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -212,8 +214,8 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 			defer func() { _ = resp.Body.Close() }()
 			if opts.Alt == "" {
 				scanner := bufio.NewScanner(resp.Body)
-				buf := make([]byte, 1024*1024)
-				scanner.Buffer(buf, 1024*1024)
+				buf := make([]byte, 20_971_520)
+				scanner.Buffer(buf, 20_971_520)
 				var param any
 				for scanner.Scan() {
 					line := scanner.Bytes()
@@ -291,6 +293,7 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
 		payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
 		payload = deleteJSONField(payload, "project")
 		payload = deleteJSONField(payload, "model")
+		payload = disableGeminiThinkingConfig(payload, attemptModel)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -500,6 +503,29 @@ func cliPreviewFallbackOrder(model string) []string {
 	}
 }
 
+func disableGeminiThinkingConfig(body []byte, model string) []byte {
+	if !geminiModelDisallowsThinking(model) {
+		return body
+	}
+
+	updated := deleteJSONField(body, "request.generationConfig.thinkingConfig")
+	updated = deleteJSONField(updated, "generationConfig.thinkingConfig")
+	return updated
+}
+
+func geminiModelDisallowsThinking(model string) bool {
+	if model == "" {
+		return false
+	}
+	lower := strings.ToLower(model)
+	for _, marker := range []string{"gemini-2.5-flash-image-preview"} {
+		if strings.Contains(lower, marker) {
+			return true
+		}
+	}
+	return false
+}
+
 // setJSONField sets a top-level JSON field on a byte slice payload via sjson.
 func setJSONField(body []byte, key, value string) []byte {
 	if key == "" {

internal/runtime/executor/gemini_executor.go

@@ -77,6 +77,7 @@ 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)
+	body = disableGeminiThinkingConfig(body, req.Model)
 
 	action := "generateContent"
 	if req.Metadata != nil {
@@ -134,6 +135,7 @@ 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)
+	body = disableGeminiThinkingConfig(body, req.Model)
 
 	url := fmt.Sprintf("%s/%s/models/%s:%s", glEndpoint, glAPIVersion, req.Model, "streamGenerateContent")
 	if opts.Alt == "" {
@@ -173,8 +175,8 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 		defer close(out)
 		defer func() { _ = resp.Body.Close() }()
 		scanner := bufio.NewScanner(resp.Body)
-		buf := make([]byte, 1024*1024)
-		scanner.Buffer(buf, 1024*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()
@@ -204,6 +206,7 @@ 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)
+	translatedReq = disableGeminiThinkingConfig(translatedReq, req.Model)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "generationConfig")

internal/runtime/executor/iflow_executor.go

@@ -141,8 +141,8 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 		defer func() { _ = resp.Body.Close() }()
 
 		scanner := bufio.NewScanner(resp.Body)
-		buf := make([]byte, 1024*1024)
-		scanner.Buffer(buf, 1024*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()

internal/runtime/executor/openai_compat_executor.go

@@ -133,8 +133,8 @@ func (e *OpenAICompatExecutor) ExecuteStream(ctx context.Context, auth *cliproxy
 		defer close(out)
 		defer func() { _ = resp.Body.Close() }()
 		scanner := bufio.NewScanner(resp.Body)
-		buf := make([]byte, 1024*1024)
-		scanner.Buffer(buf, 1024*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()

internal/runtime/executor/qwen_executor.go

@@ -126,8 +126,8 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
 		defer close(out)
 		defer func() { _ = resp.Body.Close() }()
 		scanner := bufio.NewScanner(resp.Body)
-		buf := make([]byte, 1024*1024)
-		scanner.Buffer(buf, 1024*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()

internal/translator/claude/gemini/claude_gemini_response.go

@@ -331,8 +331,8 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 	streamingEvents := make([][]byte, 0)
 
 	scanner := bufio.NewScanner(bytes.NewReader(rawJSON))
-	buffer := make([]byte, 10240*1024)
-	scanner.Buffer(buffer, 10240*1024)
+	buffer := make([]byte, 20_971_520)
+	scanner.Buffer(buffer, 20_971_520)
 	for scanner.Scan() {
 		line := scanner.Bytes()
 		// log.Debug(string(line))

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

@@ -445,8 +445,8 @@ func ConvertClaudeResponseToOpenAIResponsesNonStream(_ context.Context, _ string
 		// Use a simple scanner to iterate through raw bytes
 		// Note: extremely large responses may require increasing the buffer
 		scanner := bufio.NewScanner(bytes.NewReader(rawJSON))
-		buf := make([]byte, 10240*1024)
-		scanner.Buffer(buf, 10240*1024)
+		buf := make([]byte, 20_971_520)
+		scanner.Buffer(buf, 20_971_520)
 		for scanner.Scan() {
 			line := scanner.Bytes()
 			if !bytes.HasPrefix(line, dataTag) {

internal/translator/codex/claude/codex_claude_response.go

@@ -181,8 +181,8 @@ func ConvertCodexResponseToClaude(_ context.Context, _ string, originalRequestRa
 //   - string: A Claude Code-compatible JSON response containing all message content and metadata
 func ConvertCodexResponseToClaudeNonStream(_ context.Context, _ string, originalRequestRawJSON, _ []byte, rawJSON []byte, _ *any) string {
 	scanner := bufio.NewScanner(bytes.NewReader(rawJSON))
-	buffer := make([]byte, 10240*1024)
-	scanner.Buffer(buffer, 10240*1024)
+	buffer := make([]byte, 20_971_520)
+	scanner.Buffer(buffer, 20_971_520)
 	revNames := buildReverseMapFromClaudeOriginalShortToOriginal(originalRequestRawJSON)
 
 	for scanner.Scan() {

internal/translator/codex/gemini/codex_gemini_response.go

@@ -153,8 +153,8 @@ func ConvertCodexResponseToGemini(_ context.Context, modelName string, originalR
 //   - string: A Gemini-compatible JSON response containing all message content and metadata
 func ConvertCodexResponseToGeminiNonStream(_ context.Context, modelName string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
 	scanner := bufio.NewScanner(bytes.NewReader(rawJSON))
-	buffer := make([]byte, 10240*1024)
-	scanner.Buffer(buffer, 10240*1024)
+	buffer := make([]byte, 20_971_520)
+	scanner.Buffer(buffer, 20_971_520)
 	for scanner.Scan() {
 		line := scanner.Bytes()
 		// log.Debug(string(line))

internal/translator/codex/openai/responses/codex_openai-responses_request.go

@@ -34,9 +34,17 @@ func ConvertOpenAIResponsesRequestToCodex(modelName string, inputRawJSON []byte,
 	}
 
 	inputResult := gjson.GetBytes(rawJSON, "input")
-	inputResults := []gjson.Result{}
-	if inputResult.Exists() && inputResult.IsArray() {
-		inputResults = inputResult.Array()
+	var inputResults []gjson.Result
+	if inputResult.Exists() {
+		if inputResult.IsArray() {
+			inputResults = inputResult.Array()
+		} else if inputResult.Type == gjson.String {
+			newInput := `[{"type":"message","role":"user","content":[{"type":"input_text","text":""}]}]`
+			newInput, _ = sjson.Set(newInput, "0.content.0.text", inputResult.String())
+			inputResults = gjson.Parse(newInput).Array()
+		}
+	} else {
+		inputResults = []gjson.Result{}
 	}
 
 	extractedSystemInstructions := false

internal/translator/codex/openai/responses/codex_openai-responses_response.go

@@ -30,8 +30,8 @@ func ConvertCodexResponseToOpenAIResponses(ctx context.Context, modelName string
 // from a non-streaming OpenAI Chat Completions response.
 func ConvertCodexResponseToOpenAIResponsesNonStream(_ context.Context, modelName string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
 	scanner := bufio.NewScanner(bytes.NewReader(rawJSON))
-	buffer := make([]byte, 10240*1024)
-	scanner.Buffer(buffer, 10240*1024)
+	buffer := make([]byte, 20_971_520)
+	scanner.Buffer(buffer, 20_971_520)
 	dataTag := []byte("data:")
 	for scanner.Scan() {
 		line := scanner.Bytes()

internal/translator/gemini-cli/openai/chat-completions/cli_openai_response.go

@@ -8,6 +8,7 @@ package chat_completions
 import (
 	"bytes"
 	"context"
+	"encoding/json"
 	"fmt"
 	"time"
 
@@ -100,6 +101,10 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 			partResult := partResults[i]
 			partTextResult := partResult.Get("text")
 			functionCallResult := partResult.Get("functionCall")
+			inlineDataResult := partResult.Get("inlineData")
+			if !inlineDataResult.Exists() {
+				inlineDataResult = partResult.Get("inline_data")
+			}
 
 			if partTextResult.Exists() {
 				// Handle text content, distinguishing between regular content and reasoning/thoughts.
@@ -125,6 +130,34 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 				}
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
 				template, _ = sjson.SetRaw(template, "choices.0.delta.tool_calls.-1", functionCallTemplate)
+			} else if inlineDataResult.Exists() {
+				data := inlineDataResult.Get("data").String()
+				if data == "" {
+					continue
+				}
+				mimeType := inlineDataResult.Get("mimeType").String()
+				if mimeType == "" {
+					mimeType = inlineDataResult.Get("mime_type").String()
+				}
+				if mimeType == "" {
+					mimeType = "image/png"
+				}
+				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
+				imagePayload, err := json.Marshal(map[string]any{
+					"type": "image_url",
+					"image_url": map[string]string{
+						"url": imageURL,
+					},
+				})
+				if err != nil {
+					continue
+				}
+				imagesResult := gjson.Get(template, "choices.0.delta.images")
+				if !imagesResult.Exists() || !imagesResult.IsArray() {
+					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
+				}
+				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
+				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", string(imagePayload))
 			}
 		}
 	}