feat(D1): models.json 集中化 — ADR-067 五大 Ollama 應用 hardcode 消除

- models.json v1.3.0: providers.ollama.models 新增 9 個 purpose keys
  (drift_summary/drift_intent/log_anomaly/nemoclaw/playbook_draft/
   code_review/embedding/rag_generate/image_analysis)
- drift_narrator_service: NARRATOR_MODEL → get_model("ollama","drift_summary")
- drift_interpreter: MODEL → get_model("ollama","drift_intent")
- log_summary_service: SUMMARY_MODEL → get_model("ollama","log_anomaly")
- local_code_review_service: _MODEL_OLLAMA → get_model("ollama","code_review")
- image_analysis_service: _MODEL → get_model("ollama","image_analysis")
- decision_manager: nemoclaw + playbook_draft 兩處 → get_model()
- embedding_service: get_embedding_service() factory → get_model("ollama","embedding")
- knowledge_service: OllamaEmbeddingService(model=...) → get_model()

所有模型名稱現在統一由 models.json 管理，修改模型只需改一個檔案。
LOGBOOK 更新：D1 完成 + B2 已完成確認

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

apps/api/src/services/image_analysis_service.py

@@ -30,6 +30,7 @@ import httpx
 import structlog
 
 from src.core.config import get_settings
+from src.services.model_registry import get_model
 
 if TYPE_CHECKING:
     pass
@@ -37,7 +38,8 @@ if TYPE_CHECKING:
 logger = structlog.get_logger(__name__)
 settings = get_settings()
 
-_MODEL = "llava:latest"
+# D1 集中化 2026-04-11: 從 models.json providers.ollama.models.image_analysis 讀取
+_MODEL = get_model("ollama", "image_analysis")
 _TIMEOUT_S = 120.0
 _MAX_SIZE_BYTES = 5 * 1024 * 1024  # 5MB
 _ALLOWED_MIME = {"image/jpeg", "image/png", "image/webp", "image/gif"}