fix(ai): stabilize GCP Ollama alert lane
Some checks failed
Code Review / ai-code-review (push) Successful in 10s
CD Pipeline / build-and-deploy (push) Has been cancelled
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / tests (push) Has been cancelled

This commit is contained in:
Your Name
2026-05-05 22:20:10 +08:00
parent a4e9a04982
commit bf847ad045
7 changed files with 42 additions and 8 deletions

View File

@@ -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="",