SQL 리뷰 계층과 AgentLoop 응답 분해 helper를 추가해 코드 탭 마감 품질을 높임

- SqlReviewService를 추가해 SQL fallback 결과에 review severity, key findings, review checklist를 붙이고 schema migration, seed/reference data, reporting query마다 다른 검토 포인트를 안내하도록 확장했습니다.
- SqlAnalysisService와 CodeLanguageCatalog를 업데이트해 SQL fallback summary와 workflow summary가 rollback notes, dependency order, row-count guard 같은 리뷰 힌트를 직접 포함하도록 보강했습니다.
- AgentLoopResponseClassificationService를 추가해 LLM 응답에서 text/tool_use 분리, no-tool 연속 카운트 계산, thinking summary 생성을 helper로 분리했고 AgentLoopService 본체는 해당 helper를 사용하도록 정리했습니다.
- README, docs/DEVELOPMENT.md, docs/NEXT_ROADMAP.md에 2026-04-15 11:50 (KST) 기준 이력을 반영했습니다.

검증 결과
- dotnet build src/AxCopilot/AxCopilot.csproj -c Release -v minimal -p:OutputPath=bin\\verify_loop_sql_finalize\\ -p:IntermediateOutputPath=obj\\verify_loop_sql_finalize\\ : 경고 0 / 오류 0
- dotnet test src/AxCopilot.Tests/AxCopilot.Tests.csproj -c Release -v minimal --filter "AgentLoopResponseClassificationServiceTests|AgentLoopLlmRequestPreparationServiceTests|AgentLoopIterationPreparationServiceTests|SqlAnalysisServiceTests|SqlReviewServiceTests|CodeLanguageCatalogTests|WorkspaceContextGeneratorTests" -p:OutputPath=bin\\verify_loop_sql_finalize_tests\\ -p:IntermediateOutputPath=obj\\verify_loop_sql_finalize_tests\\ : 통과 48

src/AxCopilot/Services/Agent/AgentLoopResponseClassificationService.cs

@@ -0,0 +1,52 @@
+using AxCopilot.Services;
+
+namespace AxCopilot.Services.Agent;
+
+internal sealed record AgentLoopResponseClassificationResult(
+    string TextResponse,
+    IReadOnlyList<string> TextParts,
+    List<ContentBlock> ToolCalls,
+    int NextConsecutiveNoToolResponses)
+{
+    public string BuildThinkingSummary(int maxLength = 150)
+    {
+        if (string.IsNullOrEmpty(TextResponse))
+            return string.Empty;
+
+        return TextResponse.Length > maxLength
+            ? TextResponse[..maxLength] + "…"
+            : TextResponse;
+    }
+}
+
+/// <summary>
+/// LLM 응답 블록을 텍스트와 tool_use로 분리하고, 무도구 응답 연속 횟수를 계산한다.
+/// </summary>
+internal static class AgentLoopResponseClassificationService
+{
+    public static AgentLoopResponseClassificationResult Classify(
+        IReadOnlyList<ContentBlock> blocks,
+        int consecutiveNoToolResponses)
+    {
+        var textParts = new List<string>();
+        var toolCalls = new List<ContentBlock>();
+
+        foreach (var block in blocks)
+        {
+            if (block.Type == "text" && !string.IsNullOrWhiteSpace(block.Text))
+                textParts.Add(block.Text);
+            else if (block.Type == "tool_use")
+                toolCalls.Add(block);
+        }
+
+        var nextConsecutiveNoToolResponses = toolCalls.Count == 0
+            ? consecutiveNoToolResponses + 1
+            : 0;
+
+        return new AgentLoopResponseClassificationResult(
+            string.Join("\n", textParts),
+            textParts,
+            toolCalls,
+            nextConsecutiveNoToolResponses);
+    }
+}

src/AxCopilot/Services/Agent/AgentLoopService.cs

@@ -726,21 +726,12 @@ public partial class AgentLoopService
                     return $"⚠ LLM 오류: {ex.Message}";
                 }
 
-                // 응답에서 텍스트와 도구 호출 분리
-                var textParts = new List<string>();
-                var toolCalls = new List<ContentBlock>();
-
-                foreach (var block in blocks)
-                {
-                    if (block.Type == "text" && !string.IsNullOrWhiteSpace(block.Text))
-                        textParts.Add(block.Text);
-                    else if (block.Type == "tool_use")
-                        toolCalls.Add(block);
-                }
-
-                // 텍스트 부분
-                var textResponse = string.Join("\n", textParts);
-                consecutiveNoToolResponses = toolCalls.Count == 0 ? consecutiveNoToolResponses + 1 : 0;
+                var responseClassification = AgentLoopResponseClassificationService.Classify(
+                    blocks,
+                    consecutiveNoToolResponses);
+                var textResponse = responseClassification.TextResponse;
+                var toolCalls = responseClassification.ToolCalls;
+                consecutiveNoToolResponses = responseClassification.NextConsecutiveNoToolResponses;
 
                 // 워크플로우 상세 로그: LLM 응답
                 WorkflowLogService.LogLlmResponse(_conversationId, _currentRunId, iteration,
@@ -804,9 +795,7 @@ public partial class AgentLoopService
                 // Thinking UI: 텍스트 응답 중 도구 호출이 있으면 "사고 과정"으로 표시
                 if (!string.IsNullOrEmpty(textResponse) && toolCalls.Count > 0)
                 {
-                    var thinkingSummary = textResponse.Length > 150
-                        ? textResponse[..150] + "…"
-                        : textResponse;
+                    var thinkingSummary = responseClassification.BuildThinkingSummary();
                     EmitEvent(AgentEventType.Thinking, "", thinkingSummary);
                 }