코드탭 query/history 조립 구조를 단계형 서비스로 분리

- AgentLoopQueryAssemblyService를 추가해 session learning refresh, queued command/query window 준비, code working set supplemental context 부착을 단계형으로 정리함

- AgentLoopService는 orchestration 중심으로 단순화하고 claw-code의 staged query/history 흐름과 비슷하게 책임을 재배치함

- AgentLoopQueryAssemblyServiceTests를 추가하고 SessionLearningCollectorTests를 영어 기준으로 정리했으며 dotnet build 및 targeted dotnet test(56 통과, 경고/오류 0)로 검증함

docs/CODE_CONTEXT_RELIABILITY_PLAN.md

@@ -288,3 +288,18 @@ Updated: 2026-04-16 01:57 (KST)
 - Remaining follow-up:
   - measure whether `tool_trace_repair` counts keep trending down in long Code runs after this preflight normalization
   - continue replacing older mojibake strings outside the active Code execution path
+
+Updated: 2026-04-16 02:05 (KST)
+
+- Delivered in this pass:
+  - structural alignment step:
+    - `AgentLoopQueryAssemblyService.cs` now owns the staged query/history assembly path.
+    - `PrepareHistory(...)` handles session-learning refresh plus queued-command/query-window preparation.
+    - `PrepareRequest(...)` handles Code working-set supplemental context and request-message assembly before dispatch.
+    - `AgentLoopService.cs` now delegates those responsibilities instead of manually stitching them together inline.
+  - test and encoding hygiene step:
+    - `AgentLoopQueryAssemblyServiceTests.cs` locks the new staged assembly behavior.
+    - `SessionLearningCollectorTests.cs` was rewritten to English-only comments and assertions to match the new repository rule.
+- Remaining follow-up:
+  - keep extracting more inline AgentLoop responsibilities into smaller staged services where it improves observability or retry correctness
+  - continue measuring long Code runs against claw-code-style continuity scenarios