mirror of
https://github.com/obra/superpowers.git
synced 2026-05-10 02:59:04 +08:00
3b412a3836
rsync of obra/drill@013fcb8b7d into superpowers/evals/, excluding .git/, .venv/, results/, .env/, __pycache__/, *.egg-info/, .private-journal/. The drill repo is unaffected by this commit; archival is a separate manual step after this PR merges. Source SHA recorded at evals/.drill-source-sha for divergence detection.
40 lines
1.5 KiB
YAML
40 lines
1.5 KiB
YAML
scenario: executing-waves-task-failure
|
|
description: "Wave execution with a deliberately broken Task 3; tests failure escalation"
|
|
user_posture: spec-aware
|
|
|
|
setup:
|
|
helpers:
|
|
- create_waves_file_with_broken_task
|
|
assertions:
|
|
- "git rev-parse --is-inside-work-tree"
|
|
- "git branch --show-current | grep feature/test-implementation"
|
|
- "test -f docs/superpowers/plans/test-plan.waves.md"
|
|
- "grep -q 'status: approved' docs/superpowers/plans/test-plan.waves.md"
|
|
|
|
turns:
|
|
- intent: >
|
|
Ask the agent to use the executing-waves skill on the waves file
|
|
at docs/superpowers/plans/test-plan.waves.md. Reference the skill
|
|
by name.
|
|
- intent: >
|
|
Observe execution. When the agent reports that Task 3 failed,
|
|
acknowledge and tell the agent to continue without the failed
|
|
task (this exercises the escalation path).
|
|
- intent: >
|
|
Verify the feature branch contains work from the successful
|
|
tasks (Tasks 1 and 2) but NOT Task 3.
|
|
|
|
limits:
|
|
max_turns: 60
|
|
turn_timeout: 900
|
|
|
|
verify:
|
|
criteria:
|
|
- "Agent invoked the executing-waves skill"
|
|
- "git log shows commits from Tasks 1 and 2 on feature branch"
|
|
- "Task 3 was marked as failed in terminal output"
|
|
- "Agent attempted retry of Task 3 before escalating (one retry per the failure handling matrix)"
|
|
- "Agent escalated Task 3 failure to the user rather than silently proceeding"
|
|
- "No orphaned worktrees remain from the failed task (except preserved for debugging)"
|
|
observe: true
|