fix(executor): only apply thinking config to supported models

internal/runtime/executor/aistudio_executor.go

@@ -256,10 +256,14 @@ func (e *AIStudioExecutor) translateRequest(req cliproxyexecutor.Request, opts c
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
-	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		payload = util.ApplyGeminiThinkingConfig(payload, budgetOverride, includeOverride)
 	}
-	payload = disableGeminiThinkingConfig(payload, req.Model)
+	payload = util.StripThinkingConfigIfUnsupported(req.Model, payload)
 	payload = fixGeminiImageAspectRatio(req.Model, payload)
 	metadataAction := "generateContent"
 	if req.Metadata != nil {

internal/runtime/executor/gemini_cli_executor.go

@@ -63,7 +63,11 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 	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 {
+	if hasOverride && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
 	}
 	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -101,7 +105,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 			payload = setJSONField(payload, "project", projectID)
 			payload = setJSONField(payload, "model", attemptModel)
 		}
-		payload = disableGeminiThinkingConfig(payload, attemptModel)
+		payload = util.StripThinkingConfigIfUnsupported(attemptModel, payload)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -196,7 +200,11 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 	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 {
+	if hasOverride && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
 	}
 	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -223,7 +231,7 @@ 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)
+		payload = util.StripThinkingConfigIfUnsupported(attemptModel, payload)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -393,12 +401,16 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
 	budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
 	for _, attemptModel := range models {
 		payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
-		if hasOverride {
+		if hasOverride && util.ModelSupportsThinking(attemptModel) {
+			if budgetOverride != nil {
+				norm := util.NormalizeThinkingBudget(attemptModel, *budgetOverride)
+				budgetOverride = &norm
+			}
 			payload = util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)
 		}
 		payload = deleteJSONField(payload, "project")
 		payload = deleteJSONField(payload, "model")
-		payload = disableGeminiThinkingConfig(payload, attemptModel)
+		payload = util.StripThinkingConfigIfUnsupported(attemptModel, payload)
 		payload = fixGeminiCLIImageAspectRatio(attemptModel, payload)
 
 		tok, errTok := tokenSource.Token()
@@ -623,29 +635,6 @@ 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", "gemini-2.5-flash-image"} {
-		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

@@ -78,10 +78,14 @@ 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 {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
 	}
-	body = disableGeminiThinkingConfig(body, req.Model)
+	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
 	body = fixGeminiImageAspectRatio(req.Model, body)
 
 	action := "generateContent"
@@ -166,10 +170,14 @@ 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 {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
 	}
-	body = disableGeminiThinkingConfig(body, req.Model)
+	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
 	body = fixGeminiImageAspectRatio(req.Model, body)
 
 	url := fmt.Sprintf("%s/%s/models/%s:%s", glEndpoint, glAPIVersion, req.Model, "streamGenerateContent")
@@ -269,10 +277,14 @@ 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 {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		translatedReq = util.ApplyGeminiThinkingConfig(translatedReq, budgetOverride, includeOverride)
 	}
-	translatedReq = disableGeminiThinkingConfig(translatedReq, req.Model)
+	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
 	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")

internal/util/gemini_thinking.go

@@ -179,3 +179,19 @@ func GeminiThinkingFromMetadata(metadata map[string]any) (*int, *bool, bool) {
 	}
 	return budgetPtr, includePtr, matched
 }
+
+// StripThinkingConfigIfUnsupported removes thinkingConfig from the request body
+// when the target model does not advertise Thinking capability. It cleans both
+// standard Gemini and Gemini CLI JSON envelopes. This acts as a final safety net
+// in case upstream injected thinking for an unsupported model.
+func StripThinkingConfigIfUnsupported(model string, body []byte) []byte {
+	if ModelSupportsThinking(model) || len(body) == 0 {
+		return body
+	}
+	updated := body
+	// Gemini CLI path
+	updated, _ = sjson.DeleteBytes(updated, "request.generationConfig.thinkingConfig")
+	// Standard Gemini path
+	updated, _ = sjson.DeleteBytes(updated, "generationConfig.thinkingConfig")
+	return updated
+}