diff --git a/app/ai/client.py b/app/ai/client.py
index 887c7ff..3c278a0 100644
--- a/app/ai/client.py
+++ b/app/ai/client.py
@@ -346,6 +346,10 @@ class AIClient:
                 payload["temperature"] = model_config.temperature
             if model_config.top_p is not None:
                 payload["top_p"] = model_config.top_p
+            if model_config.repetition_penalty is not None:
+                payload["repetition_penalty"] = model_config.repetition_penalty
+            if model_config.top_k is not None:
+                payload["top_k"] = model_config.top_k
             response = await self._http.post(
                 model_config.endpoint,
                 json=payload,
diff --git a/app/core/config.py b/app/core/config.py
index 5f70fb6..c37e1c4 100644
--- a/app/core/config.py
+++ b/app/core/config.py
@@ -30,6 +30,11 @@ class AIModelConfig(BaseModel):
     # None = MLX/OpenAI server default. Anthropic branch 는 미적용 (별 plan 범위).
     temperature: float | None = None
     top_p: float | None = None
+    # mlx 네이티브 샘플링 — 한국어 장문 코드스위칭(CJK/라틴 누수)·반복루프 억제용.
+    # Qwen3 권장: top_k=20, repetition_penalty 1.05~1.1. None = 서버 기본값(주입 안 함).
+    # OpenAI 호환 분기(mlx)만 적용 — Anthropic 분기는 미적용(별 범위).
+    repetition_penalty: float | None = None
+    top_k: int | None = None
 
 
 class DeepSummaryBacklogConfig(BaseModel):