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/claude/gemini_claude_response.go

@@ -370,3 +370,7 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 	}
 	return string(encoded)
 }
+
+func ClaudeTokenCount(ctx context.Context, count int64) string {
+	return fmt.Sprintf(`{"input_tokens":%d}`, count)
+}

internal/translator/gemini/claude/init.go

@@ -12,8 +12,9 @@ func init() {
 		Gemini,
 		ConvertClaudeRequestToGemini,
 		interfaces.TranslateResponse{
-			Stream:    ConvertGeminiResponseToClaude,
-			NonStream: ConvertGeminiResponseToClaudeNonStream,
+			Stream:     ConvertGeminiResponseToClaude,
+			NonStream:  ConvertGeminiResponseToClaudeNonStream,
+			TokenCount: ClaudeTokenCount,
 		},
 	)
 }