mirror of
https://github.com/obra/superpowers.git
synced 2026-05-11 19:49:05 +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:
28
evals/scenarios/decomposing-into-waves-dependency-chain.yaml
Normal file
28
evals/scenarios/decomposing-into-waves-dependency-chain.yaml
Normal file
@@ -0,0 +1,28 @@
|
||||
scenario: decomposing-into-waves-dependency-chain
|
||||
description: "Agent detects semantic import-based dependencies, not just file overlap"
|
||||
user_posture: spec-aware
|
||||
|
||||
setup:
|
||||
helpers:
|
||||
- create_dependency_chain_repo
|
||||
assertions:
|
||||
- "test -f docs/superpowers/plans/test-plan.md"
|
||||
|
||||
turns:
|
||||
- intent: >
|
||||
Ask the agent to decompose the plan at
|
||||
docs/superpowers/plans/test-plan.md into waves. Task 1 creates
|
||||
src/types/auth.ts. Task 3 imports from src/types/auth.ts but
|
||||
does not modify it. Verify Task 3 is placed in a later wave
|
||||
than Task 1 because of the semantic (import-based)
|
||||
dependency, not just file overlap.
|
||||
|
||||
limits:
|
||||
max_turns: 10
|
||||
turn_timeout: 120
|
||||
|
||||
verify:
|
||||
criteria:
|
||||
- "Task that imports another task's output is in a later wave"
|
||||
- "Agent identified the semantic dependency beyond file overlap (mentioned in terminal output)"
|
||||
observe: true
|
||||
Reference in New Issue
Block a user