rogee/superpowers
1
0
Fork 0
mirror of https://github.com/obra/superpowers.git synced 2026-05-16 22:19:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Tighten cross-platform tool references

Browse Source
This commit is contained in:
Drew Ritter
2026-05-13 17:29:04 -07:00
committed by Drew Ritter
parent 01034bcf8f
commit d4d99117f2
17 changed files with 79 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/claude-code/test-subagent-driven-development-integration.sh
View File

@@ -7,8 +7,8 @@
# and is stricter on that axis. This bash test additionally asserts:
# - >=3 git commits (initial + per-task commits, exercising SDD's
# commit-per-task workflow shape)
# - >=2 Agent/Task subagent dispatches (drill only asserts >=1)
# - TodoWrite usage (drill makes no assertion)
# - >=2 Claude Code subagent dispatches via Agent or Task (drill only asserts >=1)
# - Claude Code task-tracking tool usage (drill makes no assertion)
# - test/math.test.js exists (drill relies on `npm test` succeeding)
# - analyze-token-usage.py token-budget telemetry
# Kept until those assertions are added to drill or explicitly retired.
@@ -224,13 +224,13 @@ else
fi
echo ""
# Test 3: TodoWrite was used for tracking
# Test 3: Claude Code task-tracking tool was used
echo "Test 3: Task tracking..."
todo_count=$(grep -c '"name":"TodoWrite"' "$SESSION_FILE" || echo "0")
todo_count=$(grep -cE '"name":"(TodoWrite|TaskCreate|TaskUpdate|TaskList|TaskGet)"' "$SESSION_FILE" || echo "0")
if [ "$todo_count" -ge 1 ]; then
echo " [PASS] TodoWrite used $todo_count time(s) for task tracking"
echo " [PASS] Task tracking used $todo_count time(s)"
else
echo " [FAIL] TodoWrite not used"
echo " [FAIL] No Claude Code task-tracking tool used"
FAILED=$((FAILED + 1))
fi
echo ""

2
tests/explicit-skill-requests/run-multiturn-test.sh
View File

@@ -109,7 +109,7 @@ if [ -n "$FIRST_SKILL_LINE" ]; then
PREMATURE_TOOLS=$(head -n "$FIRST_SKILL_LINE" "$TURN3_LOG" | \
grep '"type":"tool_use"' | \
grep -v '"name":"Skill"' | \
grep -v '"name":"TodoWrite"' || true)
grep -vE '"name":"(TodoWrite|TaskCreate|TaskUpdate|TaskList|TaskGet)"' || true)
if [ -n "$PREMATURE_TOOLS" ]; then
echo "WARNING: Tools invoked BEFORE Skill tool in Turn 3:"
echo "$PREMATURE_TOOLS" | head -5

4
tests/explicit-skill-requests/run-test.sh
View File

@@ -103,11 +103,11 @@ echo "Checking for premature action..."
FIRST_SKILL_LINE=$(grep -n '"name":"Skill"' "$LOG_FILE" | head -1 | cut -d: -f1)
if [ -n "$FIRST_SKILL_LINE" ]; then
# Check if any non-Skill, non-system tools were invoked before the first Skill invocation
# Filter out system messages, TodoWrite (planning is ok), and other non-action tools
# Filter out task tracking tools (planning is ok) and other non-action tools
PREMATURE_TOOLS=$(head -n "$FIRST_SKILL_LINE" "$LOG_FILE" | \
grep '"type":"tool_use"' | \
grep -v '"name":"Skill"' | \
grep -v '"name":"TodoWrite"' || true)
grep -vE '"name":"(TodoWrite|TaskCreate|TaskUpdate|TaskList|TaskGet)"' || true)
if [ -n "$PREMATURE_TOOLS" ]; then
echo "WARNING: Tools invoked BEFORE Skill tool:"
echo "$PREMATURE_TOOLS" | head -5

22
tests/opencode/test-bootstrap-caching.mjs
View File

@@ -44,6 +44,10 @@ const result = {
scenario,
firstBootstrapParts: countBootstrapParts(firstOutput),
secondBootstrapParts: countBootstrapParts(secondOutput),
staleMentionMapping: bootstrapText(firstOutput).includes('@mention'),
staleTaskMapping: bootstrapText(firstOutput).includes('`Task` tool with subagents'),
mapsSubagentToTask: bootstrapText(firstOutput).includes('`task` with `subagent_type: "general"`'),
mapsMutationToApplyPatch: bootstrapText(firstOutput).includes('`apply_patch`'),
firstReadCount: afterFirst.readCount,
secondReadCount: afterSecond.readCount,
firstExistsCount: afterFirst.existsCount,
@@ -83,6 +87,12 @@ function countBootstrapParts(output) {
).length;
}
function bootstrapText(output) {
return output.messages[0].parts.find(
(part) => part.type === 'text' && part.text.includes('EXTREMELY_IMPORTANT')
)?.text || '';
}
function assertPresentBootstrap(result) {
const failures = [];
if (result.firstBootstrapParts !== 1) {
@@ -100,6 +110,18 @@ function assertPresentBootstrap(result) {
if (result.secondExistsCount !== result.firstExistsCount) {
failures.push(`expected cached second transform to do no additional exists checks, got ${result.secondExistsCount - result.firstExistsCount}`);
}
if (result.staleMentionMapping) {
failures.push('expected OpenCode bootstrap not to teach @mention subagent syntax');
}
if (result.staleTaskMapping) {
failures.push('expected OpenCode bootstrap not to teach stale Task-tool mapping');
}
if (!result.mapsSubagentToTask) {
failures.push('expected OpenCode bootstrap to map general-purpose subagents to task with subagent_type');
}
if (!result.mapsMutationToApplyPatch) {
failures.push('expected OpenCode bootstrap to map file mutation to apply_patch');
}
return failures;
}