feat(registry, executor, util): add support for gemini-2.5-flash-image-preview and improve aspect ratio handling

- Introduced `gemini-2.5-flash-image-preview` model to the registry with updated definitions.
- Enhanced Gemini CLI and API executors to handle image aspect ratio adjustments for the new model.
- Added utility function to create base64 white image placeholders based on aspect ratio configurations.

.github/workflows/homebrew.yml

@@ -1,16 +0,0 @@
-name: Bump Homebrew formula
-
-on:
-  release:
-    types: [ released ]
-
-jobs:
-  homebrew:
-    name: Bump Homebrew formula
-    runs-on: ubuntu-latest
-    steps:
-      - name: Update Homebrew Formula
-        uses: dawidd6/action-homebrew-bump-formula@v5
-        with:
-          token: ${{ secrets.HOMEBREW_TOKEN }}
-          formula: cliproxyapi

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
 - gemini-2.5-flash-image-preview
 - gpt-5
 - gpt-5-codex
@@ -277,6 +278,7 @@ console.log(await claudeResponse.json());
 - deepseek-v3
 - kimi-k2
 - glm-4.5
+- glm-4.6
 - tstars2.0
 - And other iFlow-supported models
 - Gemini models auto-switch to preview variants when needed
@@ -355,6 +357,11 @@ remote-management:
 # Authentication directory (supports ~ for home directory). If you use Windows, please set the directory like this: `C:/cli-proxy-api/`
 auth-dir: "~/.cli-proxy-api"
 
+# API keys for authentication
+api-keys:
+  - "your-api-key-1"
+  - "your-api-key-2"
+
 # Enable debug logging
 debug: false
 

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
 - gemini-2.5-flash-image-preview
 - gpt-5
 - gpt-5-codex
@@ -289,6 +290,7 @@ console.log(await claudeResponse.json());
 - deepseek-v3
 - kimi-k2
 - glm-4.5
+- glm-4.6
 - tstars2.0
 - 以及其他 iFlow 支持的模型
 - Gemini 模型在需要时自动切换到对应的 preview 版本
@@ -366,6 +368,11 @@ remote-management:
 # 身份验证目录（支持 ~ 表示主目录）。如果你使用Windows，建议设置成`C:/cli-proxy-api/`。
 auth-dir: "~/.cli-proxy-api"
 
+# 请求认证使用的API密钥
+api-keys:
+  - "your-api-key-1"
+  - "your-api-key-2"
+
 # 启用调试日志
 debug: false
 

internal/access/reconcile.go

@@ -51,9 +51,10 @@ func ReconcileProviders(oldCfg, newCfg *config.Config, existing []sdkaccess.Prov
 			continue
 		}
 
+		forceRebuild := strings.EqualFold(strings.TrimSpace(providerCfg.Type), sdkConfig.AccessProviderTypeConfigAPIKey)
 		if oldCfgProvider, ok := oldCfgMap[key]; ok {
 			isAliased := oldCfgProvider == providerCfg
-			if !isAliased && providerConfigEqual(oldCfgProvider, providerCfg) {
+			if !forceRebuild && !isAliased && providerConfigEqual(oldCfgProvider, providerCfg) {
 				if existingProvider, okExisting := existingMap[key]; okExisting {
 					result = append(result, existingProvider)
 					finalIDs[key] = struct{}{}

internal/api/middleware/request_logging.go

@@ -6,6 +6,7 @@ package middleware
 import (
 	"bytes"
 	"io"
+	"strings"
 
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
@@ -17,6 +18,12 @@ import (
 // logger, the middleware has minimal overhead.
 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" {
+			c.Next()
+			return
+		}
+
 		// Early return if logging is disabled (zero overhead)
 		if !logger.IsEnabled() {
 			c.Next()

internal/registry/model_definitions.go

@@ -104,6 +104,34 @@ func GetGeminiModels() []*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"},
+		},
+		{
+			ID:                         "gemini-2.5-flash-image",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-2.5-flash-image",
+			Version:                    "2.5",
+			DisplayName:                "Gemini 2.5 Flash Image",
+			Description:                "State-of-the-art image generation and editing model.",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           8192,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+		},
 	}
 }
 
@@ -166,6 +194,20 @@ func GetGeminiCLIModels() []*ModelInfo {
 			OutputTokenLimit:           8192,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
 		},
+		{
+			ID:                         "gemini-2.5-flash-image",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-2.5-flash-image",
+			Version:                    "2.5",
+			DisplayName:                "Gemini 2.5 Flash Image",
+			Description:                "State-of-the-art image generation and editing model.",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           8192,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+		},
 	}
 }
 
@@ -354,6 +396,7 @@ func GetIFlowModels() []*ModelInfo {
 		{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build"},
 		{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905"},
 		{ID: "glm-4.5", DisplayName: "GLM-4.5", Description: "Zhipu GLM 4.5 general model"},
+		{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model"},
 		{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model"},
 		{ID: "deepseek-v3.2", DisplayName: "DeepSeek-V3.2-Exp", Description: "DeepSeek V3.2 experimental"},
 		{ID: "deepseek-v3.1", DisplayName: "DeepSeek-V3.1-Terminus", Description: "DeepSeek V3.1 Terminus"},

internal/runtime/executor/gemini_cli_executor.go

@@ -14,6 +14,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/misc"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
 	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
@@ -51,7 +52,7 @@ func (e *GeminiCLIExecutor) Identifier() string { return "gemini-cli" }
 func (e *GeminiCLIExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error { return nil }
 
 func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
-	tokenSource, baseTokenData, err := prepareGeminiCLITokenSource(ctx, auth)
+	tokenSource, baseTokenData, err := prepareGeminiCLITokenSource(ctx, e.cfg, auth)
 	if err != nil {
 		return cliproxyexecutor.Response{}, err
 	}
@@ -60,6 +61,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini-cli")
 	basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
+	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
 
 	action := "generateContent"
 	if req.Metadata != nil {
@@ -139,7 +141,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 }
 
 func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (<-chan cliproxyexecutor.StreamChunk, error) {
-	tokenSource, baseTokenData, err := prepareGeminiCLITokenSource(ctx, auth)
+	tokenSource, baseTokenData, err := prepareGeminiCLITokenSource(ctx, e.cfg, auth)
 	if err != nil {
 		return nil, err
 	}
@@ -148,6 +150,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini-cli")
 	basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
+	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
 
 	projectID := strings.TrimSpace(stringValue(auth.Metadata, "project_id"))
 
@@ -270,7 +273,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 }
 
 func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
-	tokenSource, baseTokenData, err := prepareGeminiCLITokenSource(ctx, auth)
+	tokenSource, baseTokenData, err := prepareGeminiCLITokenSource(ctx, e.cfg, auth)
 	if err != nil {
 		return cliproxyexecutor.Response{}, err
 	}
@@ -294,6 +297,7 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
 		payload = deleteJSONField(payload, "project")
 		payload = deleteJSONField(payload, "model")
 		payload = disableGeminiThinkingConfig(payload, attemptModel)
+		payload = fixGeminiCLIImageAspectRatio(attemptModel, payload)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -351,7 +355,7 @@ func (e *GeminiCLIExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth
 	return auth, nil
 }
 
-func prepareGeminiCLITokenSource(ctx context.Context, auth *cliproxyauth.Auth) (oauth2.TokenSource, map[string]any, error) {
+func prepareGeminiCLITokenSource(ctx context.Context, cfg *config.Config, auth *cliproxyauth.Auth) (oauth2.TokenSource, map[string]any, error) {
 	if auth == nil || auth.Metadata == nil {
 		return nil, nil, fmt.Errorf("gemini-cli auth metadata missing")
 	}
@@ -395,8 +399,8 @@ func prepareGeminiCLITokenSource(ctx context.Context, auth *cliproxyauth.Auth) (
 	}
 
 	ctxToken := ctx
-	if rt, ok := ctx.Value("cliproxy.roundtripper").(http.RoundTripper); ok && rt != nil {
-		ctxToken = context.WithValue(ctxToken, oauth2.HTTPClient, &http.Client{Transport: rt})
+	if httpClient := newProxyAwareHTTPClient(ctx, cfg, auth, 0); httpClient != nil {
+		ctxToken = context.WithValue(ctxToken, oauth2.HTTPClient, httpClient)
 	}
 
 	src := conf.TokenSource(ctxToken, &token)
@@ -518,7 +522,7 @@ func geminiModelDisallowsThinking(model string) bool {
 		return false
 	}
 	lower := strings.ToLower(model)
-	for _, marker := range []string{"gemini-2.5-flash-image-preview"} {
+	for _, marker := range []string{"gemini-2.5-flash-image-preview", "gemini-2.5-flash-image"} {
 		if strings.Contains(lower, marker) {
 			return true
 		}
@@ -549,3 +553,45 @@ func deleteJSONField(body []byte, key string) []byte {
 	}
 	return updated
 }
+
+func fixGeminiCLIImageAspectRatio(modelName string, rawJSON []byte) []byte {
+	if modelName == "gemini-2.5-flash-image-preview" {
+		aspectRatioResult := gjson.GetBytes(rawJSON, "request.generationConfig.imageConfig.aspectRatio")
+		if aspectRatioResult.Exists() {
+			contents := gjson.GetBytes(rawJSON, "request.contents")
+			contentArray := contents.Array()
+			if len(contentArray) > 0 {
+				hasInlineData := false
+			loopContent:
+				for i := 0; i < len(contentArray); i++ {
+					parts := contentArray[i].Get("parts").Array()
+					for j := 0; j < len(parts); j++ {
+						if parts[j].Get("inlineData").Exists() {
+							hasInlineData = true
+							break loopContent
+						}
+					}
+				}
+
+				if !hasInlineData {
+					emptyImageBase64ed, _ := util.CreateWhiteImageBase64(aspectRatioResult.String())
+					emptyImagePart := `{"inlineData":{"mime_type":"image/png","data":""}}`
+					emptyImagePart, _ = sjson.Set(emptyImagePart, "inlineData.data", emptyImageBase64ed)
+					newPartsJson := `[]`
+					newPartsJson, _ = sjson.SetRaw(newPartsJson, "-1", `{"text": "Based on the following requirements, create an image within the uploaded picture. The new content *MUST* completely cover the entire area of the original picture, maintaining its exact proportions, and *NO* blank areas should appear."}`)
+					newPartsJson, _ = sjson.SetRaw(newPartsJson, "-1", emptyImagePart)
+
+					parts := contentArray[0].Get("parts").Array()
+					for j := 0; j < len(parts); j++ {
+						newPartsJson, _ = sjson.SetRaw(newPartsJson, "-1", parts[j].Raw)
+					}
+
+					rawJSON, _ = sjson.SetRawBytes(rawJSON, "request.contents.0.parts", []byte(newPartsJson))
+					rawJSON, _ = sjson.SetRawBytes(rawJSON, "request.generationConfig.responseModalities", []byte(`["Image", "Text"]`))
+				}
+			}
+			rawJSON, _ = sjson.DeleteBytes(rawJSON, "request.generationConfig.imageConfig")
+		}
+	}
+	return rawJSON
+}

internal/runtime/executor/gemini_executor.go

@@ -78,6 +78,7 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	to := sdktranslator.FromString("gemini")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
 	body = disableGeminiThinkingConfig(body, req.Model)
+	body = fixGeminiImageAspectRatio(req.Model, body)
 
 	action := "generateContent"
 	if req.Metadata != nil {
@@ -136,6 +137,7 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	to := sdktranslator.FromString("gemini")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 	body = disableGeminiThinkingConfig(body, req.Model)
+	body = fixGeminiImageAspectRatio(req.Model, body)
 
 	url := fmt.Sprintf("%s/%s/models/%s:%s", glEndpoint, glAPIVersion, req.Model, "streamGenerateContent")
 	if opts.Alt == "" {
@@ -207,6 +209,7 @@ func (e *GeminiExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
 	to := sdktranslator.FromString("gemini")
 	translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
 	translatedReq = disableGeminiThinkingConfig(translatedReq, req.Model)
+	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "generationConfig")
@@ -374,3 +377,45 @@ func geminiCreds(a *cliproxyauth.Auth) (apiKey, bearer string) {
 	}
 	return
 }
+
+func fixGeminiImageAspectRatio(modelName string, rawJSON []byte) []byte {
+	if modelName == "gemini-2.5-flash-image-preview" {
+		aspectRatioResult := gjson.GetBytes(rawJSON, "generationConfig.imageConfig.aspectRatio")
+		if aspectRatioResult.Exists() {
+			contents := gjson.GetBytes(rawJSON, "contents")
+			contentArray := contents.Array()
+			if len(contentArray) > 0 {
+				hasInlineData := false
+			loopContent:
+				for i := 0; i < len(contentArray); i++ {
+					parts := contentArray[i].Get("parts").Array()
+					for j := 0; j < len(parts); j++ {
+						if parts[j].Get("inlineData").Exists() {
+							hasInlineData = true
+							break loopContent
+						}
+					}
+				}
+
+				if !hasInlineData {
+					emptyImageBase64ed, _ := util.CreateWhiteImageBase64(aspectRatioResult.String())
+					emptyImagePart := `{"inlineData":{"mime_type":"image/png","data":""}}`
+					emptyImagePart, _ = sjson.Set(emptyImagePart, "inlineData.data", emptyImageBase64ed)
+					newPartsJson := `[]`
+					newPartsJson, _ = sjson.SetRaw(newPartsJson, "-1", `{"text": "Based on the following requirements, create an image within the uploaded picture. The new content *MUST* completely cover the entire area of the original picture, maintaining its exact proportions, and *NO* blank areas should appear."}`)
+					newPartsJson, _ = sjson.SetRaw(newPartsJson, "-1", emptyImagePart)
+
+					parts := contentArray[0].Get("parts").Array()
+					for j := 0; j < len(parts); j++ {
+						newPartsJson, _ = sjson.SetRaw(newPartsJson, "-1", parts[j].Raw)
+					}
+
+					rawJSON, _ = sjson.SetRawBytes(rawJSON, "contents.0.parts", []byte(newPartsJson))
+					rawJSON, _ = sjson.SetRawBytes(rawJSON, "generationConfig.responseModalities", []byte(`["Image", "Text"]`))
+				}
+			}
+			rawJSON, _ = sjson.DeleteBytes(rawJSON, "generationConfig.imageConfig")
+		}
+	}
+	return rawJSON
+}

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

@@ -26,6 +26,20 @@ import (
 //   - []byte: The transformed request data in Gemini CLI API format
 func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
+	var pathsToDelete []string
+	root := gjson.ParseBytes(rawJSON)
+	util.Walk(root, "", "additionalProperties", &pathsToDelete)
+	util.Walk(root, "", "$schema", &pathsToDelete)
+	util.Walk(root, "", "ref", &pathsToDelete)
+
+	var err error
+	for _, p := range pathsToDelete {
+		rawJSON, err = sjson.DeleteBytes(rawJSON, p)
+		if err != nil {
+			continue
+		}
+	}
+
 	// Base envelope
 	out := []byte(`{"project":"","request":{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}},"model":"gemini-2.5-pro"}`)
 
@@ -65,6 +79,31 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 		out, _ = sjson.SetBytes(out, "request.generationConfig.topK", tkr.Num)
 	}
 
+	// Map OpenAI modalities -> Gemini CLI request.generationConfig.responseModalities
+	// e.g. "modalities": ["image", "text"] -> ["Image", "Text"]
+	if mods := gjson.GetBytes(rawJSON, "modalities"); mods.Exists() && mods.IsArray() {
+		var responseMods []string
+		for _, m := range mods.Array() {
+			switch strings.ToLower(m.String()) {
+			case "text":
+				responseMods = append(responseMods, "Text")
+			case "image":
+				responseMods = append(responseMods, "Image")
+			}
+		}
+		if len(responseMods) > 0 {
+			out, _ = sjson.SetBytes(out, "request.generationConfig.responseModalities", responseMods)
+		}
+	}
+
+	// OpenRouter-style image_config support
+	// If the input uses top-level image_config.aspect_ratio, map it into request.generationConfig.imageConfig.aspectRatio.
+	if imgCfg := gjson.GetBytes(rawJSON, "image_config"); imgCfg.Exists() && imgCfg.IsObject() {
+		if ar := imgCfg.Get("aspect_ratio"); ar.Exists() && ar.Type == gjson.String {
+			out, _ = sjson.SetBytes(out, "request.generationConfig.imageConfig.aspectRatio", ar.Str)
+		}
+	}
+
 	// messages -> systemInstruction + contents
 	messages := gjson.GetBytes(rawJSON, "messages")
 	if messages.IsArray() {
@@ -232,7 +271,7 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 	}
 
 	var pathsToType []string
-	root := gjson.ParseBytes(out)
+	root = gjson.ParseBytes(out)
 	util.Walk(root, "", "type", &pathsToType)
 	for _, p := range pathsToType {
 		typeResult := gjson.GetBytes(out, p)

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

@@ -20,6 +20,7 @@ import (
 // convertCliResponseToOpenAIChatParams holds parameters for response conversion.
 type convertCliResponseToOpenAIChatParams struct {
 	UnixTimestamp int64
+	FunctionIndex int
 }
 
 // ConvertCliResponseToOpenAI translates a single chunk of a streaming response from the
@@ -40,6 +41,7 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 	if *param == nil {
 		*param = &convertCliResponseToOpenAIChatParams{
 			UnixTimestamp: 0,
+			FunctionIndex: 0,
 		}
 	}
 
@@ -117,13 +119,18 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 			} else if functionCallResult.Exists() {
 				// Handle function call content.
 				toolCallsResult := gjson.Get(template, "choices.0.delta.tool_calls")
-				if !toolCallsResult.Exists() || !toolCallsResult.IsArray() {
+				functionCallIndex := (*param).(*convertCliResponseToOpenAIChatParams).FunctionIndex
+				(*param).(*convertCliResponseToOpenAIChatParams).FunctionIndex++
+				if toolCallsResult.Exists() && toolCallsResult.IsArray() {
+					functionCallIndex = len(toolCallsResult.Array())
+				} else {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.tool_calls", `[]`)
 				}
 
-				functionCallTemplate := `{"id": "","type": "function","function": {"name": "","arguments": ""}}`
+				functionCallTemplate := `{"id": "","index": 0,"type": "function","function": {"name": "","arguments": ""}}`
 				fcName := functionCallResult.Get("name").String()
 				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "id", fmt.Sprintf("%s-%d", fcName, time.Now().UnixNano()))
+				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "index", functionCallIndex)
 				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "function.name", fcName)
 				if fcArgsResult := functionCallResult.Get("args"); fcArgsResult.Exists() {
 					functionCallTemplate, _ = sjson.Set(functionCallTemplate, "function.arguments", fcArgsResult.Raw)

internal/translator/gemini/openai/chat-completions/gemini_openai_request.go

@@ -26,6 +26,20 @@ import (
 //   - []byte: The transformed request data in Gemini API format
 func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
+	var pathsToDelete []string
+	root := gjson.ParseBytes(rawJSON)
+	util.Walk(root, "", "additionalProperties", &pathsToDelete)
+	util.Walk(root, "", "$schema", &pathsToDelete)
+	util.Walk(root, "", "ref", &pathsToDelete)
+
+	var err error
+	for _, p := range pathsToDelete {
+		rawJSON, err = sjson.DeleteBytes(rawJSON, p)
+		if err != nil {
+			continue
+		}
+	}
+
 	// Base envelope
 	out := []byte(`{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}}`)
 
@@ -65,6 +79,31 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 		out, _ = sjson.SetBytes(out, "generationConfig.topK", tkr.Num)
 	}
 
+	// Map OpenAI modalities -> Gemini generationConfig.responseModalities
+	// e.g. "modalities": ["image", "text"] -> ["Image", "Text"]
+	if mods := gjson.GetBytes(rawJSON, "modalities"); mods.Exists() && mods.IsArray() {
+		var responseMods []string
+		for _, m := range mods.Array() {
+			switch strings.ToLower(m.String()) {
+			case "text":
+				responseMods = append(responseMods, "Text")
+			case "image":
+				responseMods = append(responseMods, "Image")
+			}
+		}
+		if len(responseMods) > 0 {
+			out, _ = sjson.SetBytes(out, "generationConfig.responseModalities", responseMods)
+		}
+	}
+
+	// OpenRouter-style image_config support
+	// If the input uses top-level image_config.aspect_ratio, map it into generationConfig.imageConfig.aspectRatio.
+	if imgCfg := gjson.GetBytes(rawJSON, "image_config"); imgCfg.Exists() && imgCfg.IsObject() {
+		if ar := imgCfg.Get("aspect_ratio"); ar.Exists() && ar.Type == gjson.String {
+			out, _ = sjson.SetBytes(out, "generationConfig.imageConfig.aspectRatio", ar.Str)
+		}
+	}
+
 	// messages -> systemInstruction + contents
 	messages := gjson.GetBytes(rawJSON, "messages")
 	if messages.IsArray() {
@@ -257,7 +296,7 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 	}
 
 	var pathsToType []string
-	root := gjson.ParseBytes(out)
+	root = gjson.ParseBytes(out)
 	util.Walk(root, "", "type", &pathsToType)
 	for _, p := range pathsToType {
 		typeResult := gjson.GetBytes(out, p)

internal/translator/gemini/openai/chat-completions/gemini_openai_response.go

@@ -19,6 +19,7 @@ import (
 // convertGeminiResponseToOpenAIChatParams holds parameters for response conversion.
 type convertGeminiResponseToOpenAIChatParams struct {
 	UnixTimestamp int64
+	FunctionIndex int
 }
 
 // ConvertGeminiResponseToOpenAI translates a single chunk of a streaming response from the
@@ -39,6 +40,7 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 	if *param == nil {
 		*param = &convertGeminiResponseToOpenAIChatParams{
 			UnixTimestamp: 0,
+			FunctionIndex: 0,
 		}
 	}
 
@@ -120,13 +122,18 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 			} else if functionCallResult.Exists() {
 				// Handle function call content.
 				toolCallsResult := gjson.Get(template, "choices.0.delta.tool_calls")
-				if !toolCallsResult.Exists() || !toolCallsResult.IsArray() {
+				functionCallIndex := (*param).(*convertGeminiResponseToOpenAIChatParams).FunctionIndex
+				(*param).(*convertGeminiResponseToOpenAIChatParams).FunctionIndex++
+				if toolCallsResult.Exists() && toolCallsResult.IsArray() {
+					functionCallIndex = len(toolCallsResult.Array())
+				} else {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.tool_calls", `[]`)
 				}
 
-				functionCallTemplate := `{"id": "","type": "function","function": {"name": "","arguments": ""}}`
+				functionCallTemplate := `{"id": "","index": 0,"type": "function","function": {"name": "","arguments": ""}}`
 				fcName := functionCallResult.Get("name").String()
 				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "id", fmt.Sprintf("%s-%d", fcName, time.Now().UnixNano()))
+				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "index", functionCallIndex)
 				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "function.name", fcName)
 				if fcArgsResult := functionCallResult.Get("args"); fcArgsResult.Exists() {
 					functionCallTemplate, _ = sjson.Set(functionCallTemplate, "function.arguments", fcArgsResult.Raw)

internal/util/image.go

@@ -0,0 +1,59 @@
+package util
+
+import (
+	"bytes"
+	"encoding/base64"
+	"image"
+	"image/draw"
+	"image/png"
+)
+
+func CreateWhiteImageBase64(aspectRatio string) (string, error) {
+	width := 1024
+	height := 1024
+
+	switch aspectRatio {
+	case "1:1":
+		width = 1024
+		height = 1024
+	case "2:3":
+		width = 832
+		height = 1248
+	case "3:2":
+		width = 1248
+		height = 832
+	case "3:4":
+		width = 864
+		height = 1184
+	case "4:3":
+		width = 1184
+		height = 864
+	case "4:5":
+		width = 896
+		height = 1152
+	case "5:4":
+		width = 1152
+		height = 896
+	case "9:16":
+		width = 768
+		height = 1344
+	case "16:9":
+		width = 1344
+		height = 768
+	case "21:9":
+		width = 1536
+		height = 672
+	}
+
+	img := image.NewRGBA(image.Rect(0, 0, width, height))
+	draw.Draw(img, img.Bounds(), image.White, image.Point{}, draw.Src)
+
+	var buf bytes.Buffer
+
+	if err := png.Encode(&buf, img); err != nil {
+		return "", err
+	}
+
+	base64String := base64.StdEncoding.EncodeToString(buf.Bytes())
+	return base64String, nil
+}