fix(ai): stabilize GCP Ollama alert lane
This commit is contained in:
@@ -520,6 +520,14 @@ class Settings(BaseSettings):
|
||||
"then local 111 before cloud backup providers such as Gemini."
|
||||
),
|
||||
)
|
||||
ALERT_OLLAMA_MODEL: str = Field(
|
||||
default="gemma3:4b",
|
||||
description=(
|
||||
"Ollama model used for incident/alert diagnosis. Keep this separate "
|
||||
"from the general RCA model so alert cards stay on the fast local "
|
||||
"lane before Gemini backup is considered."
|
||||
),
|
||||
)
|
||||
# 2026-03-29 ogt: ADR-036 Nemotron Tool Calling 整合
|
||||
NVIDIA_API_KEY: str = Field(
|
||||
default="",
|
||||
|
||||
Reference in New Issue
Block a user