41457ab96e
[08-Documenter] #311 설계서 Approved + reference + 사용자 가이드 FAQ
...
- docs/design/311-llm-warmup/ 3파일 상태 Draft → Approved (v0.4.1)
- docs/reference/311-llm-warmup.md 신규 (상태 머신, API, UI binding,
마이크로카피, 테스트)
- docs/guides/ai-chat-using.md 헤더 + FAQ 2건 추가 (warmup 인지/회복)
Refs #311
2026-06-15 13:25:38 +09:00
44d571f4ee
[08-Documenter] #260 reference + user guide for v0.4.0 in-app tool calling
...
- docs/reference/260-in-app-tool-calling.md — 구현 후 동기화. 11 섹션 (모듈 지도 / 6 tool 표 / R 규칙 enforce / multi-turn 루프 / dispatcher / ConfirmGate / 2KB cap / LlmChatSession 두 구현 / UI 진입점 / 테스트 / known limitations).
- docs/guides/ai-chat-using.md — 사용자 대상 how-to. 진입(🤖 ) / 대화 예시 / 확인 게이트 / 안전장치 / FAQ.
- 후속 4건 Redmine 이슈 발행: #306 koreanLabel 필드 / #307 blank confirm skip / #308 category case-insensitive / #309 KGP deprecation.
Refs #260
2026-06-15 11:19:57 +09:00
25be18063e
[08-Documenter] #218 docs marked Approved + v0.3.0 sync
...
- 설계서 218-gemma-real-integration/README.md → Approved + AC 체크박스 채움 + 실제 구현/테스트 파일 경로 추적성 갱신
- fn-gemma_llm_service.md → Approved (v2)
- reference/215-ai-frame-suggest.md → v0.3.0 (commit da60dd1#218
2026-06-12 16:22:40 +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
ed340839a0
[Documenter] #215 Reference + guide + design Approved
...
- docs/reference/215-ai-frame-suggest.md — v0.2.0 모듈/함수/Riverpod/meta_kv 사양
- docs/guides/ai-help-onboarding.md — AI 도움 켜기/끄기 사용자 가이드
- docs/design/215-gemma-frame-suggest/{README,fn-suggest_frame,fn-model_lifecycle}
상태 Draft → Approved, 추적성 헤더에 실제 구현 파일/테스트 경로 + 레퍼런스/가이드 cross-link
- docs/README.md — 현재 발행된 문서 인덱스 섹션 추가
Refs #215
2026-06-12 13:32:29 +09:00
