 hyungi
|
f6bb830c8e
|
fix(ai-fabric): LocalMLX 라이브 fixture 캡처 + 모델명 정정 (mac-mini-default)
맥미니 GUI 로그인 복구(GPU 점프 경유 Screen Sharing) 후 llm-router :8890 라이브 캡처 → S2-2a 완료.
- llm-router-chat.{request,response}.json: PROVISIONAL_SYNTHETIC → CAPTURED_LIVE (2026-06-05)
- 모델명 'gemma-macmini'(= DS backend 이름, llm-router 모델 ID 아님) → 'mac-mini-default'
(/v1/models 실측 확인, 별칭 → mlx-community/gemma-4-26b-a4b-it-8bit resolve)
- LocalMLXProvider/AIProviderConfiguration 기본 모델 + 관련 테스트 갱신
- testLiveLocalMLXIfReachable 추가(실 :8890 e2e, offline 시 skip). 47 tests PASS.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-05 07:01:29 +09:00 |
|
|
hyungi
|
5383a93f98
|
feat(ai-fabric): S2 LLM 패브릭 4 provider 결선 + 컴포지션 루트
risk-first 채움(RemoteDS→LocalMLX→OnDevice→Specialized) + makeDefaultRouter 컴포지션 루트.
동결 인터페이스(AIProvider/AIRouter/MockAIProvider) 무변경. SPM AIFabric 단독 빌드·테스트(46 PASS).
- RemoteDS: DSAskClient seam + AskResponse(ask.json) 매핑 + backend exhaustive switch(qwen/cloud TODO)
- LocalMLX: GET /v1/models probe + OpenAI /v1/chat/completions system/user call-shape + non-200 backendError
- OnDevice: FoundationModels 라이브(M5 Max) availability + respond() + GenerationError 9-case 매핑 + stateless/prewarm
- Specialized: scaffold-only(명시 unavailable, vision 폴백 가시화), cloud='claude-cloud' 503
- config 단일소스(env override) + 타임아웃/취소(URLSession 자동 honor, OnDevice 협조적)
실측 동결(S2-3a, M5 Max): availability=available · 취소=COOPERATIVE(~33ms) · 오버플로=exceededContextWindowSize
· GenerationError 9-case(refusal·concurrentRequests 추가 발견, plan 정정).
한계: LocalMLX fixture=PROVISIONAL_SYNTHETIC(맥미니 offline → 라이브 재캡처 S2-Ff 대기).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-04 17:20:10 +09:00 |
|