lacvet/AX-Copilot-Codex
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

권한·도구 결과 transcript 안내 강화
Some checks failed
Release Gate / gate (push) Has been cancelled
Details

Browse Source 
권한 요청과 도구 결과 metadata를 실제 transcript 카드에 반영했습니다.

ActionHint, Severity, RequiresPreview, FollowUpHint, NeedsAttention, StatusKind를 이용해 보조 문구와 주의 chip을 표시하도록 정리했습니다.

README와 DEVELOPMENT 문서를 갱신했고 dotnet build 기준 경고 0 / 오류 0을 확인했습니다.
This commit is contained in:
lacvet
2026-04-06 13:03:18 +09:00
parent e747032501
commit 7fd4d1ae5a
3 changed files with 116 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/DEVELOPMENT.md
View File

@@ -4944,3 +4944,5 @@ ow + toggle ?쒓컖 ?몄뼱濡??ㅼ떆 ?뺣젹?덈떎.
- Document update: 2026-04-06 11:52 (KST) - Expanded `PermissionRequestPresentationCatalog.cs` into an action-level permission taxonomy (`bash`, `powershell`, `command`, `web_fetch`, `mcp`, `skill`, `question`, `file_edit`, `file_write`, `git`, `document`, `filesystem`) and added `ActionHint`, `Severity`, `RequiresPreview` metadata for later renderer refinement.
- Document update: 2026-04-06 11:52 (KST) - Expanded `ToolResultPresentationCatalog.cs` with richer result taxonomy and post-result guidance. AX now distinguishes `approval_required` and `partial` in addition to `success / error / reject / cancel`, and each result carries `FollowUpHint` and `NeedsAttention`.
- Document update: 2026-04-06 11:52 (KST) - Extended `SkillGalleryWindow.xaml.cs` to expose runtime-policy metadata (`model`, `effort`, `execution context`, `agent`, `disable model invocation`, `when to use`) so AX skills are easier to inspect and maintain like `claw-code` bundled skills.
- Document update: 2026-04-06 13:01 (KST) - Wired the new permission/result metadata into transcript rendering. `ChatWindow.AgentEventRendering.cs` now appends action-level guidance and attention chips to permission/tool-result event banners instead of using badge labels alone.
- Document update: 2026-04-06 13:01 (KST) - Permission events now surface `ActionHint`, `Severity`, and `RequiresPreview` through inline cues such as `미리보기 권장`, `주의 필요`, and `검토 권장`, while tool-result events surface `FollowUpHint`, `NeedsAttention`, and `StatusKind` through cues such as `확인 필요`, `승인 후 계속`, and `후속 점검`.