feat(translators): add token counting support for Claude and Gemini responses

- Implemented `TokenCount` transform method across translators to calculate token usage.
- Integrated token counting logic into executor pipelines for Claude, Gemini, and CLI translators.
- Added corresponding API endpoints and handlers (`/messages/count_tokens`) for token usage retrieval.
- Enhanced translation registry to support `TokenCount` functionality alongside existing response types.

internal/translator/gemini/gemini/gemini_gemini_response.go

@@ -3,6 +3,7 @@ package gemini
 import (
 	"bytes"
 	"context"
+	"fmt"
 )
 
 // PassthroughGeminiResponseStream forwards Gemini responses unchanged.
@@ -22,3 +23,7 @@ func PassthroughGeminiResponseStream(_ context.Context, _ string, originalReques
 func PassthroughGeminiResponseNonStream(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
 	return string(rawJSON)
 }
+
+func GeminiTokenCount(ctx context.Context, count int64) string {
+	return fmt.Sprintf(`{"totalTokens":%d,"promptTokensDetails":[{"modality":"TEXT","tokenCount":%d}]}`, count, count)
+}

internal/translator/gemini/gemini/init.go

@@ -14,8 +14,9 @@ func init() {
 		Gemini,
 		ConvertGeminiRequestToGemini,
 		interfaces.TranslateResponse{
-			Stream:    PassthroughGeminiResponseStream,
-			NonStream: PassthroughGeminiResponseNonStream,
+			Stream:     PassthroughGeminiResponseStream,
+			NonStream:  PassthroughGeminiResponseNonStream,
+			TokenCount: GeminiTokenCount,
 		},
 	)
 }