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/openai/openai/chat-completions/openai_openai_request.go

@@ -4,8 +4,6 @@ package chat_completions
 
 import (
 	"bytes"
-
-	log "github.com/sirupsen/logrus"
 )
 
 // ConvertOpenAIRequestToOpenAI converts an OpenAI Chat Completions request (raw JSON)
@@ -19,6 +17,5 @@ import (
 // Returns:
 //   - []byte: The transformed request data in Gemini CLI API format
 func ConvertOpenAIRequestToOpenAI(modelName string, inputRawJSON []byte, _ bool) []byte {
-	log.Debug("ConvertOpenAIRequestToOpenAI")
 	return bytes.Clone(inputRawJSON)
 }

internal/translator/openai/openai/chat-completions/openai_openai_response.go

@@ -27,7 +27,6 @@ import (
 // Returns:
 //   - []string: A slice of strings, each containing an OpenAI-compatible JSON response
 func ConvertOpenAIResponseToOpenAI(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, param *any) []string {
-	log.Debug("ConvertOpenAIResponseToOpenAI")
 	if bytes.HasPrefix(rawJSON, []byte("data:")) {
 		rawJSON = bytes.TrimSpace(rawJSON[5:])
 	}
@@ -51,6 +50,5 @@ func ConvertOpenAIResponseToOpenAI(_ context.Context, _ string, originalRequestR
 // Returns:
 //   - string: An OpenAI-compatible JSON response containing all message content and metadata
 func ConvertOpenAIResponseToOpenAINonStream(ctx context.Context, modelName string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, param *any) string {
-	log.Debug("ConvertOpenAIResponseToOpenAINonStream")
 	return string(rawJSON)
 }

internal/translator/openai/openai/responses/openai_openai-responses_request.go

@@ -28,7 +28,6 @@ import (
 // Returns:
 //   - []byte: The transformed request data in OpenAI chat completions format
 func ConvertOpenAIResponsesRequestToOpenAIChatCompletions(modelName string, inputRawJSON []byte, stream bool) []byte {
-	log.Debug("ConvertOpenAIResponsesRequestToOpenAIChatCompletions")
 	rawJSON := bytes.Clone(inputRawJSON)
 	// Base OpenAI chat completions template with default values
 	out := `{"model":"","messages":[],"stream":false}`

internal/translator/openai/openai/responses/openai_openai-responses_response.go

@@ -7,7 +7,6 @@ import (
 	"strings"
 	"time"
 
-	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -42,7 +41,6 @@ func emitRespEvent(event string, payload string) string {
 // ConvertOpenAIChatCompletionsResponseToOpenAIResponses converts OpenAI Chat Completions streaming chunks
 // to OpenAI Responses SSE events (response.*).
 func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context, modelName string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, param *any) []string {
-	log.Debug("ConvertOpenAIChatCompletionsResponseToOpenAIResponses")
 	if *param == nil {
 		*param = &oaiToResponsesState{
 			FuncArgsBuf:     make(map[int]*strings.Builder),
@@ -518,7 +516,6 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 // ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream builds a single Responses JSON
 // from a non-streaming OpenAI Chat Completions response.
 func ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
-	log.Debug("ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream")
 	root := gjson.ParseBytes(rawJSON)
 
 	// Basic response scaffold