5b4c05316a
[03-Developer] #311 LLM warm-up + concurrent guard + quickCheck
...
ChatScreen 마운트 시 백그라운드 native init 으로 첫 send 시점에 native
load 지연을 안 보이게 한다. 12개 AC + UX-Reviewer 의 6개 권고 모두 코드
반영.
핵심 변경:
- `chat_warmup_provider.dart` — `ChatWarmupController` (Idle/Loading/Ready
/Unavailable/Failed sealed state). fast path (`llm.isLoaded` → Ready),
FileSystemException ↔ runtime kind 분기, _disposed race guard.
- `model_lifecycle.dart` — `quickCheck()`: 2.4GB SHA-256 hashing 없이
meta_kv + 파일 존재만 보고 ready 추정 (R4 UX 권고).
- `gemma_llm_service.dart` + `llm_service.dart` — `_loadingFuture` 동시
호출 가드. 두 caller 가 동시에 load() 해도 native init 은 1 회만.
- `chat_screen.dart` — initState postFrameCallback 에서 warmup.start().
warmup 상태에 따라 hintText / spinner / 실패 banner 분기.
AC coverage (12개):
- AC1~AC8: ChatWarmupController unit (chat_warmup_test.dart 8 tests).
- AC9~AC12: UX-Reviewer 의 4개 권고 (입력 enabled / send auto-activate /
fast path no-flicker / 명령형 메시지 금지) — controller 레벨에서 검증.
테스트: 167 passed (1 pre-existing skip). `flutter analyze` clean.
Refs #311
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-06-15 12:52:50 +09:00
b9f5674f51
[03-Developer] #260 round 2: AC-9 + AC-10 보강
...
QA round 1 환송 노트 (#260 카테고리 63 환송) 의 두 결함 수정.
AC-9 — tool result 2KB 가드 runtime 연결
- chat_providers.dart userTurn: result.toJson() → encodeToolResult 통과
후 jsonDecode 한 Map 을 LlmChatSession.sendToolResult 로 전달.
- encodeToolResult 가 더 이상 dead code 가 아니다. ADR-0005 / OQ-2
의 2KB hard cap 이 실 경로에서 적용됨.
- 회귀: chat_session_controller_test.dart 신규 'AC-9 대용량 → cap'
케이스 — 인위 huge_dump tool 로 _truncated:true + _hint 검증.
AC-10 — widget E2E 신규
- app/test/ui/chat_screen_test.dart 신규 (2 testWidgets):
1) add_habit tool call → ConfirmDialog '수행' → habits +1 + 모델 마무리.
2) ConfirmDialog '취소' → habits 무변화 + 'tool 취소됨' 라벨.
- ProviderScope overrides: appDatabaseProvider / llmServiceProvider /
bootstrapProvider / toolDepsProvider.
회귀
- 신규 3 (cap 1 + widget 2) → 151 → 154 passed (1 skip)
- flutter analyze: clean
Refs #260
2026-06-15 10:54:53 +09:00
b1bed4d5ca
[03-Developer] #260 in-app tool calling (Gemma 4 multi-turn)
...
ADR-0005 in-process tool runtime — 6 tools (catalog 2 + tracker 2 +
habit 2), ToolDispatcher with JSON-schema validation + modal ConfirmGate
for destructive ops, multi-turn LlmChatSession abstraction wired to
flutter_gemma 0.16.5 (ToolChoice.auto), ChatSessionController with
MAX_TURNS=4 safety + 8-turn history hint, ChatScreen entry behind AI
opt-in. R3/R7/R8 enforced inside handlers. 41 new tests (envelope,
catalog/tracker/habit tools, dispatcher, controller loop) — 151 total
passing.
Refs #260
2026-06-15 10:42:43 +09:00
321d3af53b
[03-Developer] #226 Catalog Gallery 구현
...
- Drift schema v2: Protocols.category CHECK 6→7 (light_circadian/sleep/movement/
nutrition/focus_cognition/recovery_stress/emotion_relationship). schemaVersion
1→2 + onUpgrade migrateV1ToV2 (DROP+CREATE+reseed flag 클리어).
- protocols.json 34 항목 v2 재분류 (1차 효과 기준). emotion_relationship 0 매핑.
- 도메인: DisplayCategory enum (8) + CatalogItem sealed (Protocol/Break/Diet).
- 데이터: CatalogRepository.all/byId/referencesByIds (3 source 통합).
- 상태: catalog_providers.dart (catalogItems / groupedByCategory / refsByIds).
- UI: ProtocolGalleryScreen (카테고리 칩 + 카드 그리드) + ProtocolPreviewScreen
(모든 필드 + reference 펼치기 + "내 습관으로" disabled placeholder) +
CatalogCard / CategoryChipRow / ReferenceExpandCard. HabitListScreen 빈
상태 CTA + AppBar 액션.
- 테스트: migration_v1_to_v2 3건 + display_category 5건 + catalog_repository
9건 + gallery widget 3건 + preview widget 3건 = 23 신규. 기존 88 회귀 0,
flutter analyze 0 issues. 110 passed / 1 skipped.
설계서: docs/design/226-catalog-gallery/{README, fn-catalog_repository,
fn-migration_v1_to_v2}.md + ADR-0004.
Refs #226
2026-06-12 17:20:13 +09:00
f71d132fa3
[03-Developer] #218 Dev round 2 — AC-6 RAM 4GB gate + AC-10 docs cleanup
...
QA round 1 (commit 9a9eb2a#221 corpus 평가. §9 다음 단계 =
#219~#222 follow-up 목록. 신규 테스트 합계 41 / 전체 88 통과.
테스트: device_capabilities_test.dart 7 신규 (kAiMinRamBytes 동등,
null/0/3.9GB/4GB-1/4GB/8GB 경계). flutter analyze 무이슈, 전체 88 통과
(71 기존 + 10 gemma + 7 RAM gate).
Architect 설계서 §4 의 "RAM 4GB 차단 = AC-9 재활용" 문구는 사실 #215
미구현 사항이라 본 라운드에서 신규 추가했음을 README 에 명기.
Refs #218
2026-06-12 15:45:14 +09:00
9a9eb2abd5
[Developer] #218 Real Gemma 4 E2B integration via flutter_gemma 0.16.5
...
Implements the OQ-1 follow-up to #215 v0.2.0: replace the placeholder
GemmaLlmService stub with a real flutter_gemma 0.16.5 backend driving
Gemma 4 E2B (litert-community/gemma-4-E2B-it-litert-lm, 2.41GB).
Highlights:
- GemmaLlmService.load → FlutterGemma.initialize + installModel.fromFile +
getActiveModel; idempotent + FileSystemException on missing file.
- generateStructured uses Gemma 4 native function calling via
createChat(tools: [Tool(...)], toolChoice: required). Stream parsed by
collectFunctionCall — first FCR wins, ParallelFCR first-call wins,
TextResponse/ThinkingResponse skipped, errors sanitized to prevent
prompt leakage.
- main.dart wires _LazyLlmService adapter that resolves to GemmaLlmService
when ModelLifecycle reports ready, MockLlmService otherwise.
- ai_providers.dart pins real model URL + SHA-256 (181938...39a63c).
- F2 hardening: ModelLifecycle.purge wraps each delete + meta remove in
try/catch so a single OS-level flake cannot block opt-out.
- Android: INTERNET / FOREGROUND_SERVICE / POST_NOTIFICATIONS permissions
+ R8 proguard-rules.pro keeping MediaPipe / LiteRT / TFLite / protobuf
JNI entry points (release builds otherwise crash on first inference).
Design-First: fn-gemma_llm_service.md updated to v2 — §C
(_appendSchemaInstruction) deprecated after reading flutter_gemma
0.16.5 source (Gemma 4 SDK injects tool declarations via template;
prompt-side append would double-wrap).
Tests:
- 10 new unit tests for collectFunctionCall covering all 8 fn-spec
cases + 2 ParallelFunctionCallResponse paths.
- All 81 existing tests still pass.
- flutter analyze: 0 issues.
Refs #218
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-06-12 15:18:08 +09:00
1e019c6dc7
[Developer] #215 AC2/AC4/AC6 fixes after QA reject
...
QA 1차 (커밋 6ab4c0d#215
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-06-12 12:30:16 +09:00
6ab4c0da7d
[Developer] #215 AI frame-suggest vertical slice (mock LlmService)
...
설계서대로 구현. flutter_gemma 실제 통합은 OQ-1 (모델 URL+SHA) 확정 후.
v1은 LlmService 추상 + ModelLifecycle (다운로드/SHA/purge) + Riverpod
providers + 다이얼로그 + Settings 화면까지. main.dart 가 MockLlmService 를
override 해 모든 경로가 graceful (suggest 결과는 빈 리스트).
추가:
- lib/data/ai/{llm_service,gemma_llm_service,model_lifecycle}.dart
- lib/domain/ai/{frame_candidate,few_shot_builder,parse_response,suggest_frame}.dart
- lib/state/ai_providers.dart (aiSettings + modelAvailability + frameSuggestions)
- lib/ui/screens/settings_screen.dart (opt-in 토글 + 모델 상태 표시)
- lib/ui/widgets/frame_suggestion_dialog.dart (후보 3개 카드 + 다시 시도)
- HabitCreateScreen: "AI 제안" 버튼 (opt-in + ready 일 때만 노출)
- MetaDao.remove(key) 추가 (purge 용)
테스트 31개 신규 추가 (총 62개 통과):
- test/domain/ai/{suggest_frame, few_shot_builder, parse_response}_test.dart
- test/data/ai/model_lifecycle_test.dart (download/SHA/purge/availability)
flutter analyze 0 issue, flutter build apk --debug 통과.
Refs #215
2026-06-12 12:08:25 +09:00
8fe6a8f378
[Developer] #204 Phase 1 MVP — Flutter app skeleton complete
...
- Drift 21 tables (8 catalog + 11 user + habit_dose_variants + meta_kv)
with R1~R10 CHECK constraints and 19 indexes
- 8 hand-crafted seed JSON catalogs in app/assets/seed/
(refs 84, protocols 34, methodologies 21, frame_patterns 30,
reward_menu_items 30, break_protocols 8, common_frames 5, diet_patterns 5)
- 6 domain functions: recommend_variant, compute_streak,
validate_frame_level, active_habit_quota, weekly_minimum_ratio,
seed_importer (transactional, idempotent)
- 4 vertical-slice Riverpod screens: HabitList, HabitCreate, CheckIn, Streak
- 31 unit tests passing; flutter analyze clean
- OQ-5 streak semantics: missing entry ≠ explicit blank
(missing = end of history; only TrackerValue.blank triggers Never-miss-twice)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-06-12 10:33:03 +09:00
