AX Agent 계획 승인 흐름과 상태선 표현 계층 정리

- 계획 승인 기본 흐름을 transcript inline 우선 구조로 더 정리하고, 계획 버튼은 저장된 계획을 여는 상세 보기 성격으로 분리했습니다.

- OperationalStatusPresentationState를 확장해 runtime badge, compact strip, quick strip의 문구·강조색·노출 여부를 한 번에 계산하도록 통합했습니다.

- ChatWindow 상태선/quick strip/status token 로직을 StatusPresentation partial로 분리해 메인 창 코드의 직접 분기와 렌더 책임을 줄였습니다.

- 문서 이력(README, DEVELOPMENT)을 2026-04-06 01:37 KST 기준으로 갱신했습니다.

- 검증: dotnet build src/AxCopilot/AxCopilot.csproj -c Release -v minimal -p:OutputPath=bin\\verify\\ -p:IntermediateOutputPath=obj\\verify\\ (경고 0 / 오류 0)

docs/DEVELOPMENT.md

@@ -1,5 +1,8 @@
 # AX Copilot - 媛쒕컻 臾몄꽌
 
+- Document update: 2026-04-06 01:37 (KST) - Reworked AX Agent plan approval toward a more transcript-native flow. The inline decision card remains the primary approval path, while the `계획` affordance now opens the stored plan as a detail-only surface instead of acting like a required popup step.
+- Document update: 2026-04-06 01:37 (KST) - Expanded `OperationalStatusPresentationState` so runtime badge, compact strip, and quick-strip labels/colors/visibility are calculated together. `ChatWindow` now consumes a richer presentation model instead of branching on strip kinds and quick-strip counters independently.
+
 - Document update: 2026-04-05 19:04 (KST) - Added transcript-facing tool/skill display normalization in `ChatWindow.xaml.cs`. Tool and skill events now use role-first badges (`도구`, `도구 결과`, `스킬`) with human-readable item labels such as `파일 읽기`, `빌드/실행`, `Git`, or `/skill-name`, instead of exposing raw snake_case names as the primary visual label.
 - Document update: 2026-04-05 19:04 (KST) - Reduced task-summary observability noise by limiting permission/background observability sections to debug-level sessions. Default AX Agent runtime UX now stays closer to `claw-code`, where transcript reading flow remains primary and diagnostics stay secondary.