fix(gemini): Disable thinking config for incompatible models

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 {
@@ -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 == "" {
@@ -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")