claw-code 대비 AX Agent 품질 향상 계획 구체화

- claw-code 소스 구조와 AX Agent 구조를 다시 대조해 추가 품질 향상 계획 수립
- transcript renderer 분리, permission presentation catalog, tool result taxonomy, plan approval inline 마감, runtime summary 계층화, regression prompt ritual 고정 계획 문서화
- 런타임 핵심 설정과 개발자 전용 이동 후보 설정을 구분해 정리
- README 및 DEVELOPMENT 문서에 2026-04-06 00:22 (KST) 기준 이력 반영
- dotnet build src/AxCopilot/AxCopilot.csproj -c Release -v minimal -p:OutputPath=bin\verify\ -p:IntermediateOutputPath=obj\verify\ 경고 0 오류 0 확인

README.md

@@ -1072,3 +1072,5 @@ MIT License
   - 등록 모델 리스트의 `선택 / 편집 / 삭제` 액션은 기본 버튼 대신 팝업 친화적인 클릭 row 스타일로 바꿔 내부 설정 오버레이에서도 더 안정적으로 동작하게 맞췄다.
 - 업데이트: 2026-04-06 00:14 (KST)
   - AX Agent 상단 중앙 탭 그룹의 버튼 패딩과 최소 크기, 외곽 래퍼 높이를 소폭 줄여 탭이 지나치게 꽉 찬 느낌 없이 여유 있게 보이도록 정리했다.
+- 업데이트: 2026-04-06 00:22 (KST)
+  - `claw-code`와 AX Agent 소스 구조를 다시 대조해 transcript renderer 분리, permission presentation catalog, tool result taxonomy, plan approval inline 마감, runtime summary 계층화, regression prompt ritual 고정까지 포함한 품질 향상 계획을 문서에 구체화했다.

docs/DEVELOPMENT.md

@@ -4827,3 +4827,6 @@ ow + toggle ?쒓컖 ?몄뼱濡??ㅼ떆 ?뺣젹?덈떎.
   - 같은 파일의 `BuildOverlayRegisteredModelsPanel(...)` 에서는 `선택 / 편집 / 삭제` 액션을 기본 `Button` 대신 `Border + MouseLeftButtonUp` 기반 클릭 row로 교체했다. 이로써 AX Agent 내부 설정 오버레이 안에서도 액션 클릭이 더 안정적으로 반응하고, 등록 모델 관리 UI가 리스트 중심 구조로 일관되게 유지된다.
 - 업데이트: 2026-04-06 00:14 (KST)
   - [ChatWindow.xaml](/E:/AX%20Copilot%20-%20Codex/src/AxCopilot/Views/ChatWindow.xaml) 의 상단 `채팅 / Cowork / 코드` 탭 그룹에서 각 버튼의 margin, padding, 최소 크기와 바깥 래퍼 높이/padding을 소폭 줄였다. 이제 탭 그룹이 지나치게 넓고 꽉 차 보이지 않고, 레퍼런스처럼 좀 더 여유 있는 pill 세그먼트 느낌으로 보인다.
+- 업데이트: 2026-04-06 00:22 (KST)
+  - [docs/claw-code-parity-plan.md](/E:/AX%20Copilot%20-%20Codex/docs/claw-code-parity-plan.md) 에 `claw-code` 대비 추가 품질 향상 계획을 구체화했다. 이번 계획은 transcript renderer 분리, permission presentation catalog 도입, tool result 메시지 분화, plan approval inline 마감, runtime summary 전용 계층화, regression prompt ritual 고정까지 포함한다.
+  - 설정/로직 검토 기준도 함께 정리해 `FreeTierDelaySeconds`, `MaxAgentIterations`, `MaxRetryOnError`는 개발자 전용 후보로, `OperationMode`, `MaxContextTokens`, `ContextCompactTriggerPercent`, 검증 토글류는 유지해야 할 핵심 런타임 설정으로 구분했다.

docs/claw-code-parity-plan.md

@@ -237,7 +237,128 @@
 2. Plan / approval rendering parity
 - `claw-code` reference: `src/components/messages/PlanApprovalMessage.tsx`
 - AX gap:
-  - 기본 transcript에서는 compact pill 위주로 줄였지만, 승인/계획 결과 표현이 아직 `Popup/Window + WPF 카드`와 섞여 있습니다.
+- 기본 transcript에서는 compact pill 위주로 줄였지만, 승인/계획 결과 표현이 아직 `Popup/Window + WPF 카드`와 섞여 있습니다.
+
+## Quality Uplift Plan
+- Updated: 2026-04-06 00:22 (KST)
+- Goal: move AX Agent from parity-oriented stability into `claw-code`-grade maintainability and transcript quality, without copying implementation expression.
+
+### Track 1. Transcript Renderer Decomposition
+- `claw-code` references:
+  - `src/components/Messages.tsx`
+  - `src/components/MessageRow.tsx`
+  - `src/components/messages/AssistantToolUseMessage.tsx`
+  - `src/components/messages/PlanApprovalMessage.tsx`
+- AX apply targets:
+  - `src/AxCopilot/Views/ChatWindow.xaml.cs`
+  - new partial/helper files under `src/AxCopilot/Views/`
+- Completion criteria:
+  - `plan / permission / ask / tool-result / task-summary` rendering no longer lives as one large block inside `ChatWindow.xaml.cs`
+  - each transcript concern has a dedicated helper/partial/class boundary
+- Quality criteria:
+  - render changes for one message type do not regress unrelated timeline behavior
+  - transcript behavior remains stable after reopen / retry / regenerate
+
+### Track 2. Permission Presentation Catalog
+- `claw-code` references:
+  - `src/components/permissions/PermissionRequest.tsx`
+  - `src/components/permissions/PermissionDialog.tsx`
+  - tool-specific permission request components under `src/components/permissions/*`
+- AX apply targets:
+  - `src/AxCopilot/Services/Agent/PermissionModeCatalog.cs`
+  - new `src/AxCopilot/Services/Agent/PermissionRequestPresentationCatalog.cs`
+  - `src/AxCopilot/Views/ChatWindow.xaml.cs`
+- Completion criteria:
+  - permission request title, subtitle, icon, severity, and choice set are resolved by tool/request type
+  - file edit / shell / skill / ask-user / web-like permission requests use distinct presentation metadata
+- Quality criteria:
+  - permission prompts feel explicit and predictable
+  - user can distinguish request type without reading raw tool names or payload
+
+### Track 3. Tool Result Message Taxonomy
+- `claw-code` references:
+  - `src/components/messages/UserToolResultMessage/UserToolSuccessMessage.tsx`
+  - `src/components/messages/UserToolResultMessage/UserToolErrorMessage.tsx`
+  - `src/components/messages/UserToolResultMessage/UserToolRejectMessage.tsx`
+  - `src/components/messages/UserToolResultMessage/UserToolCanceledMessage.tsx`
+- AX apply targets:
+  - new `src/AxCopilot/Services/Agent/ToolResultPresentationCatalog.cs`
+  - `src/AxCopilot/Views/ChatWindow.TranscriptPolicy.cs`
+  - `src/AxCopilot/Views/ChatWindow.xaml.cs`
+- Completion criteria:
+  - transcript display rules differ for `success / error / reject / cancel`
+  - tool-result badges and summaries are resolved from presentation metadata instead of inline ad-hoc branches
+- Quality criteria:
+  - result cards read as stable UX language, not raw execution logs
+  - failed and rejected tool runs are visually distinct without increasing noise
+
+### Track 4. Plan Approval Transcript-Only Flow
+- `claw-code` references:
+  - `src/components/messages/PlanApprovalMessage.tsx`
+  - `src/components/messages/UserPlanMessage.tsx`
+- AX apply targets:
+  - `src/AxCopilot/Views/ChatWindow.xaml.cs`
+  - `src/AxCopilot/Views/PlanViewerWindow.cs`
+- Completion criteria:
+  - default approval / reject / revise flow completes inline in transcript
+  - `PlanViewerWindow` is detail-only and never required for primary approval flow
+- Quality criteria:
+  - planning feels like part of the conversation, not a modal interruption
+  - approval history is replayable from persisted conversation state
+
+### Track 5. Runtime Summary Layer
+- `claw-code` references:
+  - `src/components/StatusLine.tsx`
+  - `src/components/PromptInput/PromptInputFooter.tsx`
+  - `src/bootstrap/state.ts`
+- AX apply targets:
+  - `src/AxCopilot/Services/AppStateService.cs`
+  - `src/AxCopilot/Views/ChatWindow.xaml.cs`
+- Completion criteria:
+  - one runtime/status summary model feeds the status line, queue summary, runtime badge, and completion hint
+  - status rendering no longer depends on scattered imperative refresh branches
+- Quality criteria:
+  - no contradictory or stale runtime badges
+  - long-running Cowork/Code sessions stay visually calm
+
+### Track 6. Regression Prompt Ritual
+- `claw-code` references:
+  - runtime validation scenarios implied by `sessionRunner`, `Messages`, `StatusLine`, and permission components
+- AX apply targets:
+  - `docs/AX_AGENT_REGRESSION_PROMPTS.md`
+  - `docs/claw-code-parity-plan.md`
+  - developer workflow / release checklist
+- Completion criteria:
+  - Chat / Cowork / Code prompt set is treated as mandatory regression for runtime-affecting changes
+  - each prompt is mapped to a failure class (`blank reply`, `duplicate banner`, `bad approval flow`, `queue drift`, `restore drift`)
+- Quality criteria:
+  - parity claims are based on repeatable checks instead of visual spot-checks
+  - regressions are easier to catch before release
+
+## Recommended Execution Order
+1. Transcript renderer decomposition
+2. Permission presentation catalog
+3. Tool result taxonomy
+4. Plan approval transcript-only flow
+5. Runtime summary layer
+6. Regression prompt ritual hardening
+
+## Settings and Logic Review
+- Updated: 2026-04-06 00:22 (KST)
+- Candidate to move to developer-only:
+  - `FreeTierDelaySeconds`
+  - `MaxAgentIterations`
+  - `MaxRetryOnError`
+- Keep as runtime-critical user settings:
+  - `OperationMode`
+  - `MaxContextTokens`
+  - `ContextCompactTriggerPercent`
+  - `EnableProactiveContextCompact`
+  - `EnableCoworkVerification`
+  - `EnableCodeVerification`
+  - code tool exposure toggles
+- Rule:
+  - if a setting changes the main execution route or recovery semantics without representing a stable real-world user choice, move it out of default user-facing surfaces
   - 목표는 “본문 우선 + 필요 시 열기” 기준으로 더 단일한 timeline 언어로 수렴시키는 것입니다.
 
 3. Status line / composer parity