Gemini on Vertex AI and Dome

1. 01

   Add the connection

   The provider id is google. Pass the service account's JSON key as the credential; location defaults to us-central1.

   $ dome models add gemini-flash \
     --provider google \
     --model gemini-3.8-flash \
     --provider-config '{"project":"acme-agents","location":"us-central1"}' \
     --api-key "$(cat vertex-sa.json)" \
     --attributes '{"tier":"flash"}' \
     --gateway prod-gateway

2. 02

   Point your agent at the Gateway

   Any OpenAI-compatible client works. Dome translates each request to Gemini's format and back.

   from openai import OpenAI
    
   client = OpenAI(base_url=f"{GATEWAY_URL}/v1", api_key=DOME_AGENT_KEY)
   client.chat.completions.create(
       model="gemini-flash",
       messages=[{"role": "user", "content": "Summarize this support thread."}],
   )

Commands and rules tested against a Dome workspace on October 1, 2026. For anything about Google Gemini itself, see Google Cloud's documentation.

forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)
when {
  resource has tier && resource.tier == "pro" &&
  principal has act_as &&
  principal.act_as.groups.contains("support")
};