feat: introduce custom provider example and remove redundant debug logs

- Added `examples/custom-provider/main.go` showcasing custom executor and translator integration using the SDK.
- Removed redundant debug logs from translator modules to enhance code cleanliness.
- Updated SDK documentation with new usage and advanced examples.
- Expanded the management API with new endpoints, including request logging and GPT-5 Codex features.

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

@@ -25,7 +25,6 @@ import (
 // Returns:
 //   - []byte: The transformed request data in Gemini API format
 func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool) []byte {
-	log.Debug("ConvertOpenAIRequestToGemini")
 	rawJSON := bytes.Clone(inputRawJSON)
 	// Base envelope
 	out := []byte(`{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}}`)

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

@@ -37,7 +37,6 @@ type convertGeminiResponseToOpenAIChatParams struct {
 // Returns:
 //   - []string: A slice of strings, each containing an OpenAI-compatible JSON response
 func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, param *any) []string {
-	log.Debug("ConvertGeminiResponseToOpenAI")
 	if *param == nil {
 		*param = &convertGeminiResponseToOpenAIChatParams{
 			UnixTimestamp: 0,
@@ -180,7 +179,6 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 // Returns:
 //   - string: An OpenAI-compatible JSON response containing all message content and metadata
 func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
-	log.Debug("ConvertGeminiResponseToOpenAINonStream")
 	var unixTimestamp int64
 	template := `{"id":"","object":"chat.completion","created":123456,"model":"model","choices":[{"index":0,"message":{"role":"assistant","content":null,"reasoning_content":null,"tool_calls":null},"finish_reason":null,"native_finish_reason":null}]}`
 	if modelVersionResult := gjson.GetBytes(rawJSON, "modelVersion"); modelVersionResult.Exists() {

internal/translator/gemini/openai/responses/gemini_openai-responses_request.go

@@ -10,7 +10,6 @@ import (
 )
 
 func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte, stream bool) []byte {
-	log.Debug("ConvertOpenAIResponsesRequestToGemini")
 	rawJSON := bytes.Clone(inputRawJSON)
 
 	// Note: modelName and stream parameters are part of the fixed method signature

internal/translator/gemini/openai/responses/gemini_openai-responses_response.go

@@ -7,7 +7,6 @@ import (
 	"strings"
 	"time"
 
-	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -44,7 +43,6 @@ func emitEvent(event string, payload string) string {
 
 // ConvertGeminiResponseToOpenAIResponses converts Gemini SSE chunks into OpenAI Responses SSE events.
 func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, param *any) []string {
-	log.Debug("ConvertGeminiResponseToOpenAIResponses")
 	if *param == nil {
 		*param = &geminiToResponsesState{
 			FuncArgsBuf: make(map[int]*strings.Builder),
@@ -424,7 +422,6 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 
 // ConvertGeminiResponseToOpenAIResponsesNonStream aggregates Gemini response JSON into a single OpenAI Responses JSON object.
 func ConvertGeminiResponseToOpenAIResponsesNonStream(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
-	log.Debug("ConvertGeminiResponseToOpenAIResponsesNonStream")
 	root := gjson.ParseBytes(rawJSON)
 
 	// Base response scaffold