fix(ops): keep Ollama health checks on alert fast model

2026-05-05 23:16:15 +08:00
parent 83daeb3f87
commit 1cc215ec30
3 changed files with 6 additions and 2 deletions
--- a/apps/api/src/core/config.py
+++ b/apps/api/src/core/config.py
@@ -370,9 +370,10 @@ class Settings(BaseSettings):
            )
        return v

-    # 2026-04-25 Claude Engineer-C (P1.1): Ollama 健康檢測推理測試模型
+    # 2026-05-05 Codex: health inference must stay on alert-fast model; qwen2.5
+    # keeps reloading a 7B model on CPU-only GCP and slows incident fallback.
    OLLAMA_HEALTH_CHECK_MODEL: str = Field(
-        default="qwen2.5:7b-instruct",
+        default="gemma3:4b",
        description="OllamaHealthMonitor 推理測試使用模型（P1.1）",
    )
    # 2026-04-12 ogt: 心跳必須確認載入的 Ollama 模型清單