refactor(thinking): export thinking helpers

Expose thinking/effort normalization helpers from the executor package
so conversion tests use production code and stay aligned with runtime
validation behavior.

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)

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 = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body = normalizeThinkingConfig(body, upstreamModel, false)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	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 = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body = normalizeThinkingConfig(body, upstreamModel, false)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	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)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	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)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	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)
+	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
-	if errValidate := validateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	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)
+	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
-	if errValidate := validateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	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
 	}
@@ -75,7 +75,7 @@ func applyReasoningEffortMetadata(payload []byte, metadata map[string]any, model
 			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)
+						return StripThinkingFields(payload, false)
 					}
 				}
 
@@ -238,12 +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
 	}
@@ -252,22 +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",
@@ -284,9 +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() {
@@ -304,10 +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)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	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)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	toolsResult := gjson.GetBytes(body, "tools")

test/thinking_conversion_test.go

@@ -2,7 +2,6 @@ package test
 
 import (
 	"fmt"
-	"net/http"
 	"strings"
 	"testing"
 	"time"
@@ -10,20 +9,13 @@ import (
 	_ "github.com/router-for-me/CLIProxyAPI/v6/internal/translator"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/runtime/executor"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
 
-// statusErr mirrors executor.statusErr to keep validation behavior aligned.
-type statusErr struct {
-	code int
-	msg  string
-}
-
-func (e statusErr) Error() string { return e.msg }
-
 // isOpenAICompatModel returns true if the model is configured as an OpenAI-compatible
 // model that should have reasoning effort passed through even if not in registry.
 // This simulates the allowCompat behavior from OpenAICompatExecutor.
@@ -108,159 +100,10 @@ func buildRawPayload(fromProtocol, modelWithSuffix string) []byte {
 	}
 }
 
-// applyThinkingMetadataLocal mirrors executor.applyThinkingMetadata.
-func applyThinkingMetadataLocal(payload []byte, metadata map[string]any, model string) []byte {
-	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
-	if !ok || (budgetOverride == nil && includeOverride == nil) {
-		return payload
-	}
-	if !util.ModelSupportsThinking(model) {
-		return payload
-	}
-	if budgetOverride != nil {
-		norm := util.NormalizeThinkingBudget(model, *budgetOverride)
-		budgetOverride = &norm
-	}
-	return util.ApplyGeminiThinkingConfig(payload, budgetOverride, includeOverride)
-}
-
-// applyReasoningEffortMetadataLocal mirrors executor.applyReasoningEffortMetadata.
-func applyReasoningEffortMetadataLocal(payload []byte, metadata map[string]any, model, field string, allowCompat bool) []byte {
-	if len(metadata) == 0 {
-		return payload
-	}
-	if field == "" {
-		return payload
-	}
-	baseModel := util.ResolveOriginalModel(model, metadata)
-	if baseModel == "" {
-		baseModel = model
-	}
-	if !util.ModelSupportsThinking(baseModel) && !allowCompat {
-		return payload
-	}
-	if effort, ok := util.ReasoningEffortFromMetadata(metadata); ok && effort != "" {
-		if util.ModelUsesThinkingLevels(baseModel) || allowCompat {
-			if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
-				return updated
-			}
-		}
-	}
-	// Fallback: numeric thinking_budget suffix for level-based (OpenAI-style) models.
-	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 stripThinkingFieldsLocal(payload, false)
-					}
-				}
-
-				if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
-					return updated
-				}
-			}
-		}
-	}
-	return payload
-}
-
-// normalizeThinkingConfigLocal mirrors executor.normalizeThinkingConfig.
-// When allowCompat is true, reasoning fields are preserved even for models
-// without thinking support (simulating openai-compat passthrough behavior).
-func normalizeThinkingConfigLocal(payload []byte, model string, allowCompat bool) []byte {
-	if len(payload) == 0 || model == "" {
-		return payload
-	}
-
-	if !util.ModelSupportsThinking(model) {
-		if allowCompat {
-			return payload
-		}
-		return stripThinkingFieldsLocal(payload, false)
-	}
-
-	if util.ModelUsesThinkingLevels(model) {
-		return normalizeReasoningEffortLevelLocal(payload, model)
-	}
-
-	// Model supports thinking but uses numeric budgets, not levels.
-	// Strip effort string fields since they are not applicable.
-	return stripThinkingFieldsLocal(payload, true)
-}
-
-// stripThinkingFieldsLocal mirrors executor.stripThinkingFields.
-func stripThinkingFieldsLocal(payload []byte, effortOnly bool) []byte {
-	fieldsToRemove := []string{
-		"reasoning_effort",
-		"reasoning.effort",
-	}
-	if !effortOnly {
-		fieldsToRemove = append([]string{"reasoning"}, fieldsToRemove...)
-	}
-	out := payload
-	for _, field := range fieldsToRemove {
-		if gjson.GetBytes(out, field).Exists() {
-			out, _ = sjson.DeleteBytes(out, field)
-		}
-	}
-	return out
-}
-
-// normalizeReasoningEffortLevelLocal mirrors executor.normalizeReasoningEffortLevel.
-func normalizeReasoningEffortLevelLocal(payload []byte, model string) []byte {
-	out := payload
-
-	if effort := gjson.GetBytes(out, "reasoning_effort"); effort.Exists() {
-		if normalized, ok := util.NormalizeReasoningEffortLevel(model, effort.String()); ok {
-			out, _ = sjson.SetBytes(out, "reasoning_effort", normalized)
-		}
-	}
-
-	if effort := gjson.GetBytes(out, "reasoning.effort"); effort.Exists() {
-		if normalized, ok := util.NormalizeReasoningEffortLevel(model, effort.String()); ok {
-			out, _ = sjson.SetBytes(out, "reasoning.effort", normalized)
-		}
-	}
-
-	return out
-}
-
-// validateThinkingConfigLocal mirrors executor.validateThinkingConfig.
-func validateThinkingConfigLocal(payload []byte, model string) error {
-	if len(payload) == 0 || model == "" {
-		return nil
-	}
-	if !util.ModelSupportsThinking(model) || !util.ModelUsesThinkingLevels(model) {
-		return nil
-	}
-
-	levels := util.GetModelThinkingLevels(model)
-	checkField := func(path string) error {
-		if effort := gjson.GetBytes(payload, path); effort.Exists() {
-			if _, ok := util.NormalizeReasoningEffortLevel(model, effort.String()); !ok {
-				return statusErr{
-					code: http.StatusBadRequest,
-					msg:  fmt.Sprintf("unsupported reasoning effort level %q for model %s (supported: %s)", effort.String(), model, strings.Join(levels, ", ")),
-				}
-			}
-		}
-		return nil
-	}
-
-	if err := checkField("reasoning_effort"); err != nil {
-		return err
-	}
-	if err := checkField("reasoning.effort"); err != nil {
-		return err
-	}
-	return nil
-}
-
 // normalizeCodexPayload mirrors codex_executor's reasoning + streaming tweaks.
 func normalizeCodexPayload(body []byte, upstreamModel string, allowCompat bool) ([]byte, error) {
-	body = normalizeThinkingConfigLocal(body, upstreamModel, allowCompat)
+	body = executor.NormalizeThinkingConfig(body, upstreamModel, allowCompat)
-	if err := validateThinkingConfigLocal(body, upstreamModel); err != nil {
+	if err := executor.ValidateThinkingConfig(body, upstreamModel); err != nil {
 		return body, err
 	}
 	body, _ = sjson.SetBytes(body, "model", upstreamModel)
@@ -290,7 +133,7 @@ func buildBodyForProtocol(t *testing.T, fromProtocol, toProtocol, modelWithSuffi
 	allowCompat := isOpenAICompatModel(normalizedModel)
 	switch toProtocol {
 	case "gemini":
-		body = applyThinkingMetadataLocal(body, metadata, normalizedModel)
+		body = executor.ApplyThinkingMetadata(body, metadata, normalizedModel)
 		body = util.ApplyDefaultThinkingIfNeeded(normalizedModel, body)
 		body = util.NormalizeGeminiThinkingBudget(normalizedModel, body)
 		body = util.StripThinkingConfigIfUnsupported(normalizedModel, body)
@@ -299,12 +142,12 @@ func buildBodyForProtocol(t *testing.T, fromProtocol, toProtocol, modelWithSuffi
 			body = util.ApplyClaudeThinkingConfig(body, budget)
 		}
 	case "openai":
-		body = applyReasoningEffortMetadataLocal(body, metadata, normalizedModel, "reasoning_effort", allowCompat)
+		body = executor.ApplyReasoningEffortMetadata(body, metadata, normalizedModel, "reasoning_effort", allowCompat)
-		body = normalizeThinkingConfigLocal(body, upstreamModel, allowCompat)
+		body = executor.NormalizeThinkingConfig(body, upstreamModel, allowCompat)
-		err = validateThinkingConfigLocal(body, upstreamModel)
+		err = executor.ValidateThinkingConfig(body, upstreamModel)
 	case "codex": // OpenAI responses / codex
 		// Codex does not support allowCompat; always use false.
-		body = applyReasoningEffortMetadataLocal(body, metadata, normalizedModel, "reasoning.effort", false)
+		body = executor.ApplyReasoningEffortMetadata(body, metadata, normalizedModel, "reasoning.effort", false)
 		// Mirror CodexExecutor final normalization and model override so tests log the final body.
 		body, err = normalizeCodexPayload(body, upstreamModel, false)
 	default:
@@ -629,8 +472,8 @@ func buildBodyForProtocolWithRawThinking(t *testing.T, fromProtocol, toProtocol,
 		// For raw payload, Claude thinking is passed through by translator
 		// No additional processing needed as thinking is already in body
 	case "openai":
-		body = normalizeThinkingConfigLocal(body, model, allowCompat)
+		body = executor.NormalizeThinkingConfig(body, model, allowCompat)
-		err = validateThinkingConfigLocal(body, model)
+		err = executor.ValidateThinkingConfig(body, model)
 	case "codex":
 		// Codex does not support allowCompat; always use false.
 		body, err = normalizeCodexPayload(body, model, false)