fix: backend_model_id 매핑 추가 — MLX 모델 ID 불일치 해결

MLX 서버 모델 ID(mlx-community/Qwen3.5-35B-A3B-4bit)와
사용자 노출 ID(qwen3.5:35b-a3b)가 달라 500 에러 발생.
registry에 backend_model_id 필드 추가하여 프록시 시 변환.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hyungi Ahn
2026-03-31 15:14:55 +09:00
parent 7b28252d4f
commit 2dab682e21
3 changed files with 10 additions and 5 deletions

View File

@@ -17,6 +17,7 @@ class ModelInfo:
id: str
capabilities: list[str]
priority: int = 1
backend_model_id: str = "" # actual model ID sent to backend (if different from id)
@dataclass
@@ -68,6 +69,7 @@ class Registry:
id=m["id"],
capabilities=m.get("capabilities", ["chat"]),
priority=m.get("priority", 1),
backend_model_id=m.get("backend_model_id", ""),
)
for m in entry.get("models", [])
]