Merge branch 'router-for-me:main' into main

internal/runtime/executor/aistudio_executor.go

@@ -322,7 +322,7 @@ 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)
-	payload = applyThinkingMetadata(payload, req.Metadata, req.Model)
+	payload = ApplyThinkingMetadata(payload, req.Metadata, req.Model)
 	payload = util.ApplyDefaultThinkingIfNeeded(req.Model, payload)
 	payload = util.ConvertThinkingLevelToBudget(payload)
 	payload = util.NormalizeGeminiThinkingBudget(req.Model, payload)
@@ -384,8 +384,16 @@ func ensureColonSpacedJSON(payload []byte) []byte {
 
 	for i := 0; i < len(indented); i++ {
 		ch := indented[i]
-		if ch == '"' && (i == 0 || indented[i-1] != '\\') {
-			inString = !inString
+		if ch == '"' {
+			// A quote is escaped only when preceded by an odd number of consecutive backslashes.
+			// For example: "\\\"" keeps the quote inside the string, but "\\\\" closes the string.
+			backslashes := 0
+			for j := i - 1; j >= 0 && indented[j] == '\\'; j-- {
+				backslashes++
+			}
+			if backslashes%2 == 0 {
+				inString = !inString
+			}
 		}
 
 		if !inString {

internal/runtime/executor/codex_executor.go

@@ -54,9 +54,9 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("codex")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body = normalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -152,9 +152,9 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	to := sdktranslator.FromString("codex")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body = normalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -254,7 +254,7 @@ func (e *CodexExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth
 
 	modelForCounting := req.Model
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
 	body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
 	body, _ = sjson.SetBytes(body, "stream", false)

internal/runtime/executor/gemini_executor.go

@@ -83,7 +83,7 @@ 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 = applyThinkingMetadata(body, req.Metadata, req.Model)
+	body = ApplyThinkingMetadata(body, req.Metadata, req.Model)
 	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
 	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
 	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
@@ -178,7 +178,7 @@ 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 = applyThinkingMetadata(body, req.Metadata, req.Model)
+	body = ApplyThinkingMetadata(body, req.Metadata, req.Model)
 	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
 	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
 	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
@@ -290,7 +290,7 @@ 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 = applyThinkingMetadata(translatedReq, req.Metadata, req.Model)
+	translatedReq = ApplyThinkingMetadata(translatedReq, req.Metadata, req.Model)
 	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
 	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)

internal/runtime/executor/iflow_executor.go

@@ -57,13 +57,13 @@ func (e *IFlowExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -148,13 +148,13 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	// Ensure tools array exists to avoid provider quirks similar to Qwen's behaviour.

internal/runtime/executor/openai_compat_executor.go

@@ -60,13 +60,13 @@ func (e *OpenAICompatExecutor) Execute(ctx context.Context, auth *cliproxyauth.A
 	}
 	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, to.String(), "", translated)
 	allowCompat := e.allowCompatReasoningEffort(req.Model, auth)
-	translated = applyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
+	translated = ApplyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" && modelOverride == "" {
 		translated, _ = sjson.SetBytes(translated, "model", upstreamModel)
 	}
-	translated = normalizeThinkingConfig(translated, upstreamModel, allowCompat)
-	if errValidate := validateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
+	if errValidate := ValidateThinkingConfig(translated, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 
@@ -156,13 +156,13 @@ func (e *OpenAICompatExecutor) ExecuteStream(ctx context.Context, auth *cliproxy
 	}
 	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, to.String(), "", translated)
 	allowCompat := e.allowCompatReasoningEffort(req.Model, auth)
-	translated = applyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
+	translated = ApplyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" && modelOverride == "" {
 		translated, _ = sjson.SetBytes(translated, "model", upstreamModel)
 	}
-	translated = normalizeThinkingConfig(translated, upstreamModel, allowCompat)
-	if errValidate := validateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
+	if errValidate := ValidateThinkingConfig(translated, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 

internal/runtime/executor/payload_helpers.go

@@ -11,9 +11,9 @@ import (
 	"github.com/tidwall/sjson"
 )
 
-// applyThinkingMetadata applies thinking config from model suffix metadata (e.g., (high), (8192))
+// ApplyThinkingMetadata applies thinking config from model suffix metadata (e.g., (high), (8192))
 // for standard Gemini format payloads. It normalizes the budget when the model supports thinking.
-func applyThinkingMetadata(payload []byte, metadata map[string]any, model string) []byte {
+func ApplyThinkingMetadata(payload []byte, metadata map[string]any, model string) []byte {
 	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
 	if !ok || (budgetOverride == nil && includeOverride == nil) {
 		return payload
@@ -45,10 +45,10 @@ func applyThinkingMetadataCLI(payload []byte, metadata map[string]any, model str
 	return util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)
 }
 
-// applyReasoningEffortMetadata applies reasoning effort overrides from metadata to the given JSON path.
+// ApplyReasoningEffortMetadata applies reasoning effort overrides from metadata to the given JSON path.
 // Metadata values take precedence over any existing field when the model supports thinking, intentionally
 // overwriting caller-provided values to honor suffix/default metadata priority.
-func applyReasoningEffortMetadata(payload []byte, metadata map[string]any, model, field string, allowCompat bool) []byte {
+func ApplyReasoningEffortMetadata(payload []byte, metadata map[string]any, model, field string, allowCompat bool) []byte {
 	if len(metadata) == 0 {
 		return payload
 	}
@@ -73,6 +73,12 @@ func applyReasoningEffortMetadata(payload []byte, metadata map[string]any, model
 	if util.ModelUsesThinkingLevels(baseModel) || allowCompat {
 		if budget, _, _, matched := util.ThinkingFromMetadata(metadata); matched && budget != nil {
 			if effort, ok := util.OpenAIThinkingBudgetToEffort(baseModel, *budget); ok && effort != "" {
+				if *budget == 0 && effort == "none" && util.ModelUsesThinkingLevels(baseModel) {
+					if _, supported := util.NormalizeReasoningEffortLevel(baseModel, effort); !supported {
+						return StripThinkingFields(payload, false)
+					}
+				}
+
 				if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
 					return updated
 				}
@@ -232,12 +238,12 @@ func matchModelPattern(pattern, model string) bool {
 	return pi == len(pattern)
 }
 
-// normalizeThinkingConfig normalizes thinking-related fields in the payload
+// NormalizeThinkingConfig normalizes thinking-related fields in the payload
 // based on model capabilities. For models without thinking support, it strips
 // reasoning fields. For models with level-based thinking, it validates and
 // normalizes the reasoning effort level. For models with numeric budget thinking,
 // it strips the effort string fields.
-func normalizeThinkingConfig(payload []byte, model string, allowCompat bool) []byte {
+func NormalizeThinkingConfig(payload []byte, model string, allowCompat bool) []byte {
 	if len(payload) == 0 || model == "" {
 		return payload
 	}
@@ -246,22 +252,22 @@ func normalizeThinkingConfig(payload []byte, model string, allowCompat bool) []b
 		if allowCompat {
 			return payload
 		}
-		return stripThinkingFields(payload, false)
+		return StripThinkingFields(payload, false)
 	}
 
 	if util.ModelUsesThinkingLevels(model) {
-		return normalizeReasoningEffortLevel(payload, model)
+		return NormalizeReasoningEffortLevel(payload, model)
 	}
 
 	// Model supports thinking but uses numeric budgets, not levels.
 	// Strip effort string fields since they are not applicable.
-	return stripThinkingFields(payload, true)
+	return StripThinkingFields(payload, true)
 }
 
-// stripThinkingFields removes thinking-related fields from the payload for
+// StripThinkingFields removes thinking-related fields from the payload for
 // models that do not support thinking. If effortOnly is true, only removes
 // effort string fields (for models using numeric budgets).
-func stripThinkingFields(payload []byte, effortOnly bool) []byte {
+func StripThinkingFields(payload []byte, effortOnly bool) []byte {
 	fieldsToRemove := []string{
 		"reasoning_effort",
 		"reasoning.effort",
@@ -278,9 +284,9 @@ func stripThinkingFields(payload []byte, effortOnly bool) []byte {
 	return out
 }
 
-// normalizeReasoningEffortLevel validates and normalizes the reasoning_effort
+// NormalizeReasoningEffortLevel validates and normalizes the reasoning_effort
 // or reasoning.effort field for level-based thinking models.
-func normalizeReasoningEffortLevel(payload []byte, model string) []byte {
+func NormalizeReasoningEffortLevel(payload []byte, model string) []byte {
 	out := payload
 
 	if effort := gjson.GetBytes(out, "reasoning_effort"); effort.Exists() {
@@ -298,10 +304,10 @@ func normalizeReasoningEffortLevel(payload []byte, model string) []byte {
 	return out
 }
 
-// validateThinkingConfig checks for unsupported reasoning levels on level-based models.
+// ValidateThinkingConfig checks for unsupported reasoning levels on level-based models.
 // Returns a statusErr with 400 when an unsupported level is supplied to avoid silently
 // downgrading requests.
-func validateThinkingConfig(payload []byte, model string) error {
+func ValidateThinkingConfig(payload []byte, model string) error {
 	if len(payload) == 0 || model == "" {
 		return nil
 	}

internal/runtime/executor/qwen_executor.go

@@ -51,13 +51,13 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -131,13 +131,13 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	toolsResult := gjson.GetBytes(body, "tools")