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-cli/claude/gemini-cli_claude_response.go

@@ -376,3 +376,7 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 	}
 	return string(encoded)
 }
+
+func ClaudeTokenCount(ctx context.Context, count int64) string {
+	return fmt.Sprintf(`{"input_tokens":%d}`, count)
+}

internal/translator/gemini-cli/claude/init.go

@@ -12,8 +12,9 @@ func init() {
 		GeminiCLI,
 		ConvertClaudeRequestToCLI,
 		interfaces.TranslateResponse{
-			Stream:    ConvertGeminiCLIResponseToClaude,
-			NonStream: ConvertGeminiCLIResponseToClaudeNonStream,
+			Stream:     ConvertGeminiCLIResponseToClaude,
+			NonStream:  ConvertGeminiCLIResponseToClaudeNonStream,
+			TokenCount: ClaudeTokenCount,
 		},
 	)
 }