mirror of
https://github.com/obra/superpowers.git
synced 2026-08-13 20:23:28 +00:00
Compare commits
2 Commits
fix/review
...
fix/claude
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c7b456dd0e | ||
|
|
72ee5bbc5e |
@@ -15,8 +15,9 @@ run_claude() {
|
||||
cmd+=(--allowed-tools="$allowed_tools")
|
||||
fi
|
||||
|
||||
# Run Claude in headless mode with timeout
|
||||
if timeout "$timeout" "${cmd[@]}" > "$output_file" 2>&1; then
|
||||
# Run Claude in headless mode with timeout. Redirect stdin from
|
||||
# /dev/null so the CLI can't block waiting for input and hang the suite.
|
||||
if timeout "$timeout" "${cmd[@]}" > "$output_file" 2>&1 < /dev/null; then
|
||||
cat "$output_file"
|
||||
rm -f "$output_file"
|
||||
return 0
|
||||
|
||||
@@ -23,7 +23,7 @@ echo "========================================"
|
||||
echo ""
|
||||
echo "This test executes a real plan using the skill and verifies:"
|
||||
echo " 1. Plan is read once (not per task)"
|
||||
echo " 2. Full task text provided to subagents"
|
||||
echo " 2. Task requirements routed to subagents via brief files"
|
||||
echo " 3. Subagents perform self-review"
|
||||
echo " 4. Spec compliance review before code quality"
|
||||
echo " 5. Review loops when issues found"
|
||||
@@ -136,7 +136,7 @@ I want you to execute the implementation plan at docs/superpowers/plans/implemen
|
||||
|
||||
IMPORTANT: Follow the skill exactly. I will be verifying that you:
|
||||
1. Read the plan once at the beginning
|
||||
2. Provide full task text to subagents (don't make them read files)
|
||||
2. Route each task's requirements to subagents via a task brief file (don't make them read the whole plan)
|
||||
3. Ensure subagents do self-review before reporting
|
||||
4. Run spec compliance review before code quality review
|
||||
5. Use review loops when issues are found
|
||||
@@ -150,7 +150,7 @@ PROMPT="Execute the implementation plan at docs/superpowers/plans/implementation
|
||||
|
||||
IMPORTANT: Follow the skill exactly. I will be verifying that you:
|
||||
1. Read the plan once at the beginning
|
||||
2. Provide full task text to subagents (don't make them read files)
|
||||
2. Route each task's requirements to subagents via a task brief file (don't make them read the whole plan)
|
||||
3. Ensure subagents do self-review before reporting
|
||||
4. Run spec compliance review before code quality review
|
||||
5. Use review loops when issues are found
|
||||
@@ -164,7 +164,7 @@ PLUGIN_DIR=$(cd "$SCRIPT_DIR/../.." && pwd)
|
||||
# other concurrent claude sessions.
|
||||
echo "Running Claude (plugin-dir: $PLUGIN_DIR, cwd: $TEST_PROJECT)..."
|
||||
echo "================================================================================"
|
||||
cd "$TEST_PROJECT" && timeout 1800 claude -p "$PROMPT" --plugin-dir "$PLUGIN_DIR" --allowed-tools=all --permission-mode bypassPermissions 2>&1 | tee "$OUTPUT_FILE" || {
|
||||
cd "$TEST_PROJECT" && timeout 1800 claude -p "$PROMPT" --plugin-dir "$PLUGIN_DIR" --allowed-tools=all --permission-mode bypassPermissions < /dev/null 2>&1 | tee "$OUTPUT_FILE" || {
|
||||
echo ""
|
||||
echo "================================================================================"
|
||||
echo "EXECUTION FAILED (exit code: $?)"
|
||||
@@ -316,7 +316,7 @@ if [ $FAILED -eq 0 ]; then
|
||||
echo ""
|
||||
echo "The subagent-driven-development skill correctly:"
|
||||
echo " ✓ Reads plan once at start"
|
||||
echo " ✓ Provides full task text to subagents"
|
||||
echo " ✓ Routes task requirements via brief files"
|
||||
echo " ✓ Enforces self-review"
|
||||
echo " ✓ Runs spec compliance before code quality"
|
||||
echo " ✓ Spec reviewer verifies independently"
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
#
|
||||
# No drill coverage: this test asks the agent to *describe* SDD (string-
|
||||
# matches its verbal explanation against expected keywords like
|
||||
# "self-review", "skeptical", "worktree", "Step 1", "loop"). Drill scenarios
|
||||
# "self-review", "skeptical", "worktree", "setup", "loop"). Drill scenarios
|
||||
# test behavior (real subagent dispatch, plan-following, review loops),
|
||||
# not description-recall. Kept by design.
|
||||
set -euo pipefail
|
||||
@@ -83,7 +83,7 @@ else
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if assert_contains "$output" "Step 1\|beginning\|start\|Load Plan" "Read at beginning"; then
|
||||
if assert_contains "$output" "beginning\|start\|setup\|before.*dispatch\|before.*task" "Read at beginning"; then
|
||||
: # pass
|
||||
else
|
||||
exit 1
|
||||
@@ -133,16 +133,16 @@ echo ""
|
||||
echo "Test 7: Task context provision..."
|
||||
|
||||
output=$(run_claude "In subagent-driven-development, how does the controller provide task information to the implementer subagent? Answer using exactly this structure:
|
||||
Controller provides: <directly or by file>
|
||||
Implementer must read plan file: <yes or no>" "$CLAUDE_PROMPT_TIMEOUT")
|
||||
Controller provides: <brief file or whole plan file>
|
||||
Implementer must read whole plan file: <yes or no>" "$CLAUDE_PROMPT_TIMEOUT")
|
||||
|
||||
if assert_contains "$output" "provide.*directly\|full.*text\|paste\|include.*prompt" "Provides text directly"; then
|
||||
if assert_contains "$output" "task-brief\|brief file\|brief.*path\|Controller provides:.*brief" "Provides task brief file"; then
|
||||
: # pass
|
||||
else
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if assert_contains "$output" "Implementer must read plan file:.*no" "Doesn't make subagent read file"; then
|
||||
if assert_contains "$output" "Implementer must read whole plan file:.*no" "Doesn't make subagent read whole plan"; then
|
||||
: # pass
|
||||
else
|
||||
exit 1
|
||||
|
||||
Reference in New Issue
Block a user