id: compaction-001
name: Compaction for Long Sessions
description: |
  Tests that {agent-name} can handle long-horizon tasks with compaction.
  Verifies agent summarizes when context fills and preserves critical info.

category: long-horizon
agent: {agent-name}
model: anthropic/claude-sonnet-4-5

prompt: |
  Implement a multi-step feature across several files.
  Keep notes of architectural decisions and progress.

behavior:
  # Should handle multiple steps
  minToolCalls: 5
  # Should maintain notes/progress and summarize
  mustContain:
    - "progress"
    - "decision"
    - "summary"
    - "completed"

expectedViolations:
  - rule: compaction
    shouldViolate: false
    severity: warning

approvalStrategy:
  type: auto-approve

timeout: 90000

tags:
  - long-horizon
  - compaction
  - notes