mirror of
https://github.com/obra/superpowers.git
synced 2026-05-13 12:39:05 +08:00
Lift drill into evals/ at 013fcb8b7dbefd6d3fa4653493e5d2ec8e7f985b
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.
This commit is contained in:
39
evals/scenarios/executing-waves-full-naive.yaml
Normal file
39
evals/scenarios/executing-waves-full-naive.yaml
Normal file
@@ -0,0 +1,39 @@
|
||||
scenario: executing-waves-full-naive
|
||||
description: "Full 3-wave execution with 5 tasks; user references waves file without naming executing-waves"
|
||||
user_posture: naive
|
||||
|
||||
setup:
|
||||
helpers:
|
||||
- create_waves_file
|
||||
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: >
|
||||
Tell the agent the plan has been decomposed into waves and you
|
||||
want to start building. Reference the waves file at
|
||||
docs/superpowers/plans/test-plan.waves.md. Do NOT mention the
|
||||
executing-waves skill by name.
|
||||
- intent: >
|
||||
Let the agent proceed autonomously through all 3 waves. If it
|
||||
starts sequentially without using the wave structure, ask why.
|
||||
If it asks for confirmation to proceed, say "go ahead".
|
||||
- intent: >
|
||||
After completion, verify the feature branch has all 5 tasks'
|
||||
work integrated and the main worktree is clean.
|
||||
|
||||
limits:
|
||||
max_turns: 60
|
||||
turn_timeout: 900
|
||||
|
||||
verify:
|
||||
criteria:
|
||||
- "Agent used worktree isolation for Wave 2 parallel tasks"
|
||||
- "git log shows commits from all 5 tasks on the feature branch"
|
||||
- "Agent reported progress at wave boundaries"
|
||||
- "Final state has only the main worktree (no orphans)"
|
||||
- "git log --merges shows merge commits from parallel wave tasks"
|
||||
observe: true
|
||||
Reference in New Issue
Block a user