apiVersion: lumbridge/v1
kind: EvalSuite
metadata:
  name: smoke
  version: 1
  description: "Fast correctness and serving-health gate for every new model."
  tags: [smoke, ci]
defaults:
  max_tokens: 96
  temperature: 0.0
  repeat: 1
  system: "Follow the requested output format exactly. Do not explain unless asked."
cases:
  - id: exact-instruction
    category: instruction
    prompt: "Reply with exactly: lumbridge ready"
    assertions:
      - type: exact
        value: "lumbridge ready"
  - id: arithmetic
    category: reasoning
    prompt: "A box has 121 GB. The OS reserves 21 GB and models use 75 GB. Reply with only the remaining number."
    assertions:
      - type: exact
        value: "25"
  - id: concise-voice
    category: voice
    prompt: "In at most twelve words, say that risk limits are operating normally. No markdown."
    assertions:
      - type: max_words
        value: 12
      - type: not_contains
        value: "**"