컨텍스트 카드 모델별 사용량 가시화 보강

- AX Agent 하단 컨텍스트 카드에 현재 서비스·모델 기준 오늘 사용량을 함께 표시하고 hover에서 현재 모델 usage·compact 이후 usage·오늘 상위 모델 usage를 확인할 수 있게 함

- UsageStatisticsService에 오늘 통계 스냅샷 API를 추가하고 long-safe 토큰 포맷 경로를 넣어 per-model 집계가 커져도 K/M 단위로 안정적으로 표시되게 함

- README.md와 docs/DEVELOPMENT.md에 2026-04-05 00:34 (KST) 기준 이력을 반영함

- 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 +1,9 @@
 # AX Copilot - 媛쒕컻 臾몄꽌
 
+- Document update: 2026-04-05 00:34 (KST) - Exposed current service/model daily usage directly in the AX Agent context card, and expanded the hover panel to show current-model usage, current-model post-compaction usage, and top model usage for the day using the new per-model daily token buckets.
+- Document update: 2026-04-05 00:34 (KST) - Added a long-safe token formatting path for large per-model aggregates so context usage summaries keep the same K/M style even when daily model totals exceed the older int-based formatting path.
+
+
 - Document update: 2026-04-05 00:17 (KST) - Upgraded the AX Agent loop to track the first post-compaction turn explicitly, mirroring claw-code's post-autocompact turn handling so compact-follow-up state now survives into the next loop turn instead of ending at the condenser call.
 - Document update: 2026-04-05 00:24 (KST) - Added compact-aware tool result trimming for the first post-compaction turn so heavy `process`, `build_run`, `test_loop`, `git_tool`, `http_tool`, and similar outputs are fed back to the loop as head/tail summaries instead of re-expanding the freshly compacted context.
 - Document update: 2026-04-05 00:17 (KST) - Added post-compaction thinking suppression for boilerplate loop events (`LLM request`, prompt submit, free-tier wait) during the first compact-follow-up turn, while still surfacing a compact-specific lightweight pill and compact-noise counts in total stats.