📦 deps(thirdparty): update snapshots

2026-05-05 16:03:42 +00:00
parent 70b5c68d82
commit fdb52f1e96
47 changed files with 2671 additions and 816 deletions
@@ -115,6 +115,18 @@ Full workflow execution test (~10-30 minutes):
 - Subagents follow the skill correctly
 - Final code is functional and tested

+#### test-requesting-code-review.sh
+Behavioral test for the code reviewer subagent (~5 minutes):
+- Builds a tiny project with a baseline commit
+- Adds a second commit that plants two real bugs (SQL injection, plaintext password handling)
+- Dispatches the code reviewer via the requesting-code-review skill
+- Verifies the reviewer flags the planted bugs at Critical/Important severity and refuses to approve
+
+**What it tests:**
+- The skill actually dispatches a working code reviewer subagent
+- The reviewer template produces reviewers that catch obvious security bugs
+- The reviewer is not sycophantic — it does not approve a diff with planted Critical issues
+
 ## Adding New Tests

 1. Create new test file: `test-<skill-name>.sh`
@@ -79,6 +79,7 @@ tests=(
 # Integration tests (slow, full execution)
 integration_tests=(
    "test-subagent-driven-development-integration.sh"
+    "test-requesting-code-review.sh"
 )

 # Add integration tests if requested
@@ -0,0 +1,214 @@
+#!/usr/bin/env bash
+# Integration Test: requesting-code-review skill
+# Verifies the code reviewer dispatched via the skill catches a planted bug
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+source "$SCRIPT_DIR/test-helpers.sh"
+
+echo "========================================"
+echo " Integration Test: requesting-code-review"
+echo "========================================"
+echo ""
+echo "This test verifies the code reviewer subagent by:"
+echo "  1. Setting up a tiny project with a baseline commit"
+echo "  2. Adding a second commit that plants an obvious bug"
+echo "  3. Dispatching the code reviewer via the requesting-code-review skill"
+echo "  4. Verifying the reviewer flags the planted bug as Critical/Important"
+echo ""
+
+TEST_PROJECT=$(create_test_project)
+echo "Test project: $TEST_PROJECT"
+trap "cleanup_test_project $TEST_PROJECT" EXIT
+
+cd "$TEST_PROJECT"
+
+# Baseline: a small "safe" implementation
+mkdir -p src
+cat > src/db.js <<'EOF'
+import { Database } from "./database-driver.js";
+
+const db = new Database();
+
+export async function findUserByEmail(email) {
+  if (typeof email !== "string" || !email) {
+    throw new Error("email required");
+  }
+  return db.query(
+    "SELECT id, email, created_at FROM users WHERE email = ?",
+    [email],
+  );
+}
+EOF
+
+cat > package.json <<'EOF'
+{ "name": "test-codereview", "version": "1.0.0", "type": "module" }
+EOF
+
+git init --quiet
+git config user.email "test@test.com"
+git config user.name "Test User"
+git add .
+git commit -m "Initial: parameterized findUserByEmail" --quiet
+BASE_SHA=$(git rev-parse HEAD)
+
+# Second commit: plant two real bugs
+# 1. SQL injection — switch from parameterized to string concatenation
+# 2. Logs the user's password hash on every successful login
+cat > src/db.js <<'EOF'
+import { Database } from "./database-driver.js";
+
+const db = new Database();
+
+export async function findUserByEmail(email) {
+  return db.query(
+    "SELECT id, email, password_hash, created_at FROM users WHERE email = '" + email + "'",
+  );
+}
+
+export async function login(email, password) {
+  const user = await findUserByEmail(email);
+  if (user && user.password_hash === hash(password)) {
+    console.log("login success", { email, password_hash: user.password_hash });
+    return user;
+  }
+  return null;
+}
+
+function hash(s) { return s; }
+EOF
+
+git add .
+git commit -m "Refactor user lookup, add login" --quiet
+HEAD_SHA=$(git rev-parse HEAD)
+
+echo ""
+echo "Planted bugs in $BASE_SHA..$HEAD_SHA:"
+echo "  - SQL injection (string concat instead of parameterized query)"
+echo "  - Password hash logged in plaintext on every successful login"
+echo "  - hash() is the identity function (passwords stored & compared in plaintext)"
+echo ""
+
+OUTPUT_FILE="$TEST_PROJECT/claude-output.txt"
+
+PROMPT="I just finished a refactor. The change is between commits $BASE_SHA and $HEAD_SHA on the current branch.
+
+Use the superpowers:requesting-code-review skill to review these changes before I merge. Follow the skill exactly: dispatch the code reviewer subagent with the template, give the subagent the SHA range, and report back what it found.
+
+Print the reviewer's full output."
+
+# Run claude from inside the test project so its session JSONL lands in a
+# project-specific directory under ~/.claude/projects/, isolated from any
+# other concurrent claude sessions.
+echo "Running Claude (plugin-dir: $PLUGIN_DIR, cwd: $TEST_PROJECT)..."
+echo "================================================================================"
+cd "$TEST_PROJECT" && timeout 600 claude -p "$PROMPT" \
+    --plugin-dir "$PLUGIN_DIR" \
+    --permission-mode bypassPermissions 2>&1 | tee "$OUTPUT_FILE" || {
+    echo ""
+    echo "================================================================================"
+    echo "EXECUTION FAILED (exit code: $?)"
+    exit 1
+}
+echo "================================================================================"
+
+echo ""
+echo "Analyzing reviewer output..."
+echo ""
+
+# Find the session transcript. Because we ran claude from $TEST_PROJECT (a
+# unique tmp dir), its sessions live in their own ~/.claude/projects/ folder.
+# Resolve the real path (macOS mktemp returns /var/... but claude normalizes
+# it to /private/var/...) and replicate claude's normalization (every
+# non-alphanumeric char becomes `-`).
+TEST_PROJECT_REAL=$(cd "$TEST_PROJECT" && pwd -P)
+SESSION_DIR="$HOME/.claude/projects/$(echo "$TEST_PROJECT_REAL" | sed 's|[^a-zA-Z0-9]|-|g')"
+# `|| true` prevents pipefail killing the script if ls gets SIGPIPE'd by head.
+SESSION_FILE=$(ls -t "$SESSION_DIR"/*.jsonl 2>/dev/null | head -1 || true)
+
+FAILED=0
+
+echo "=== Verification Tests ==="
+echo ""
+
+# Test 1: Skill was actually invoked, and a subagent was actually dispatched
+echo "Test 1: requesting-code-review skill invoked + reviewer subagent dispatched..."
+if [ -z "$SESSION_FILE" ] || [ ! -f "$SESSION_FILE" ]; then
+    echo "  [FAIL] Could not locate session transcript in $SESSION_DIR"
+    FAILED=$((FAILED + 1))
+elif ! grep -q '"skill":"superpowers:requesting-code-review"' "$SESSION_FILE"; then
+    echo "  [FAIL] requesting-code-review skill was not invoked"
+    echo "         Session: $SESSION_FILE"
+    FAILED=$((FAILED + 1))
+elif ! grep -q '"name":"Agent"' "$SESSION_FILE"; then
+    echo "  [FAIL] Skill ran but no subagent was dispatched"
+    FAILED=$((FAILED + 1))
+else
+    echo "  [PASS] Skill invoked and subagent dispatched"
+fi
+echo ""
+
+# Test 2: Reviewer caught the SQL injection
+echo "Test 2: SQL injection flagged..."
+if grep -qiE "sql injection|injection|string concat|parameterize|prepared statement|sanitiz" "$OUTPUT_FILE"; then
+    echo "  [PASS] Reviewer flagged the SQL injection vector"
+else
+    echo "  [FAIL] Reviewer missed the SQL injection — most obvious planted bug"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 3: Reviewer caught the credential / password issue (either logging or no real hashing)
+echo "Test 3: Credential handling issue flagged..."
+if grep -qiE "password|credential|secret|plaintext|log.*hash|hash.*log|sensitive" "$OUTPUT_FILE"; then
+    echo "  [PASS] Reviewer flagged a credential / password handling issue"
+else
+    echo "  [FAIL] Reviewer missed the password/credential issues"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 4: Reviewer marked at least one issue as Critical or Important (not just Minor)
+echo "Test 4: Severity classification..."
+if grep -qiE "critical|important|severe|high.*risk|security" "$OUTPUT_FILE"; then
+    echo "  [PASS] Reviewer classified findings at Critical/Important severity"
+else
+    echo "  [FAIL] Reviewer did not classify findings as Critical or Important"
+    FAILED=$((FAILED + 1))
+fi
+echo ""
+
+# Test 5: Reviewer did NOT approve the diff for merge
+echo "Test 5: Reviewer verdict..."
+# A correct reviewer says No or "With fixes". A broken/sycophantic reviewer says Yes/Ready.
+if grep -qiE "ready to merge.*yes|approved.*for merge|^\s*yes\s*$|safe to merge" "$OUTPUT_FILE" \
+   && ! grep -qiE "ready to merge.*no|with fixes|do not merge|not ready|block.*merge" "$OUTPUT_FILE"; then
+    echo "  [FAIL] Reviewer approved a diff with planted Critical bugs"
+    FAILED=$((FAILED + 1))
+else
+    echo "  [PASS] Reviewer did not approve the diff"
+fi
+echo ""
+
+echo "========================================"
+echo " Test Summary"
+echo "========================================"
+echo ""
+
+if [ $FAILED -eq 0 ]; then
+    echo "STATUS: PASSED"
+    echo "The code reviewer correctly:"
+    echo "  ✓ Was dispatched via the requesting-code-review skill"
+    echo "  ✓ Flagged the SQL injection"
+    echo "  ✓ Flagged the credential handling issues"
+    echo "  ✓ Classified findings at Critical/Important severity"
+    echo "  ✓ Did not approve the diff for merge"
+    exit 0
+else
+    echo "STATUS: FAILED"
+    echo "Failed $FAILED verification tests"
+    echo ""
+    echo "Output saved to: $OUTPUT_FILE"
+    exit 1
+fi
@@ -135,8 +135,7 @@ EOF

 # Note: We use a longer timeout since this is integration testing
 # Use --allowed-tools to enable tool usage in headless mode
-# IMPORTANT: Run from superpowers directory so local dev skills are available
-PROMPT="Change to directory $TEST_PROJECT and then execute the implementation plan at docs/superpowers/plans/implementation-plan.md using the subagent-driven-development skill.
+PROMPT="Execute the implementation plan at docs/superpowers/plans/implementation-plan.md using the subagent-driven-development skill.

 IMPORTANT: Follow the skill exactly. I will be verifying that you:
 1. Read the plan once at the beginning
@@ -147,9 +146,14 @@ IMPORTANT: Follow the skill exactly. I will be verifying that you:

 Begin now. Execute the plan."

-echo "Running Claude (output will be shown below and saved to $OUTPUT_FILE)..."
+PLUGIN_DIR=$(cd "$SCRIPT_DIR/../.." && pwd)
+
+# Run claude from inside the test project so its session JSONL lands in a
+# project-specific directory under ~/.claude/projects/, isolated from any
+# other concurrent claude sessions.
+echo "Running Claude (plugin-dir: $PLUGIN_DIR, cwd: $TEST_PROJECT)..."
 echo "================================================================================"
-cd "$SCRIPT_DIR/../.." && timeout 1800 claude -p "$PROMPT" --allowed-tools=all --add-dir "$TEST_PROJECT" --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 2>&1 | tee "$OUTPUT_FILE" || {
    echo ""
    echo "================================================================================"
    echo "EXECUTION FAILED (exit code: $?)"
@@ -161,13 +165,17 @@ echo ""
 echo "Execution complete. Analyzing results..."
 echo ""

-# Find the session transcript
-# Session files are in ~/.claude/projects/-<working-dir>/<session-id>.jsonl
-WORKING_DIR_ESCAPED=$(echo "$SCRIPT_DIR/../.." | sed 's/\//-/g' | sed 's/^-//')
-SESSION_DIR="$HOME/.claude/projects/$WORKING_DIR_ESCAPED"
-
-# Find the most recent session file (created during this test run)
-SESSION_FILE=$(find "$SESSION_DIR" -name "*.jsonl" -type f -mmin -60 2>/dev/null | sort -r | head -1)
+# Find the session transcript. Because we ran claude from $TEST_PROJECT (a
+# unique tmp dir), its sessions live in their own ~/.claude/projects/ folder
+# and we can pick the most-recent one without racing other concurrent sessions.
+# Resolve the real path because macOS mktemp returns /var/... but claude
+# normalizes it to /private/var/... when naming the project dir.
+TEST_PROJECT_REAL=$(cd "$TEST_PROJECT" && pwd -P)
+# Claude normalizes the cwd to a directory name by replacing every non-alphanumeric
+# character with `-` (so `_`, `.`, `/` all become `-`).
+SESSION_DIR="$HOME/.claude/projects/$(echo "$TEST_PROJECT_REAL" | sed 's|[^a-zA-Z0-9]|-|g')"
+# `|| true` prevents pipefail killing the script if ls gets SIGPIPE'd by head.
+SESSION_FILE=$(ls -t "$SESSION_DIR"/*.jsonl 2>/dev/null | head -1 || true)

 if [ -z "$SESSION_FILE" ]; then
    echo "ERROR: Could not find session transcript file"
@@ -194,9 +202,9 @@ else
 fi
 echo ""

-# Test 2: Subagents were used (Task tool)
+# Test 2: Subagents were used (Agent / Task tool — name varies by harness version)
 echo "Test 2: Subagents dispatched..."
-task_count=$(grep -c '"name":"Task"' "$SESSION_FILE" || echo "0")
+task_count=$(grep -cE '"name":"(Agent|Task)"' "$SESSION_FILE" || echo "0")
 if [ "$task_count" -ge 2 ]; then
    echo "  [PASS] $task_count subagents dispatched"
 else
@@ -0,0 +1,176 @@
+#!/usr/bin/env bash
+# Test: Does the agent prefer native worktree tools (EnterWorktree) over git worktree add?
+# Framework: RED-GREEN-REFACTOR per testing-skills-with-subagents.md
+#
+# RED:   Skill without Step 1a (no native tool preference). Agent should use git worktree add.
+# GREEN: Skill with Step 1a (explicit tool naming + consent bridge). Agent should use EnterWorktree.
+# PRESSURE: Same as GREEN but under time pressure with existing .worktrees/ dir.
+#
+# Key insight: the fix is Step 1a's text, not file separation. Three things make it work:
+#   1. Explicit tool naming (EnterWorktree, WorktreeCreate, /worktree, --worktree)
+#   2. Consent bridge ("user's consent = authorization to use native tool")
+#   3. Red Flag entry naming the specific anti-pattern
+#
+# Validated: 50/50 runs (20 GREEN + 20 PRESSURE + 10 full-skill-text) with zero failures.
+
+set -euo pipefail
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+source "$SCRIPT_DIR/test-helpers.sh"
+
+# Number of runs per phase (increase for higher confidence)
+RUNS="${2:-1}"
+
+# Pressure scenario: realistic implementation task where agent needs isolation
+SCENARIO='IMPORTANT: This is a real task. Choose and act.
+
+You need to implement a small feature (add a "version" field to package.json).
+This should be done in an isolated workspace to protect the main branch.
+
+You have the using-git-worktrees skill available. Set up the isolated workspace now.
+Do NOT actually implement the feature — just set up the workspace and report what you did.
+
+Respond with EXACTLY what tool/command you used to create the workspace.'
+
+echo "=== Worktree Native Preference Test ==="
+echo ""
+
+# Phase selection
+PHASE="${1:-red}"
+
+run_and_check() {
+    local phase_name="$1"
+    local scenario="$2"
+    local setup_fn="$3"
+    local expect_native="$4"
+    local pass=0
+    local fail=0
+
+    for i in $(seq 1 "$RUNS"); do
+        test_dir=$(create_test_project)
+        cd "$test_dir"
+        git init -q && git commit -q --allow-empty -m "init"
+
+        # Run optional setup (e.g., create .worktrees dir)
+        if [ "$setup_fn" = "pressure_setup" ]; then
+            mkdir -p .worktrees
+            echo ".worktrees/" >> .gitignore
+        fi
+
+        output=$(run_claude "$scenario" 120)
+
+        if [ "$RUNS" -eq 1 ]; then
+            echo "Agent output:"
+            echo "$output"
+            echo ""
+        fi
+
+        used_git_worktree_add=$(echo "$output" | grep -qi "git worktree add" && echo "yes" || echo "no")
+        mentioned_enter=$(echo "$output" | grep -qi "EnterWorktree" && echo "yes" || echo "no")
+
+        if [ "$expect_native" = "true" ]; then
+            # GREEN/PRESSURE: expect native tool, no git worktree add
+            if [ "$used_git_worktree_add" = "no" ]; then
+                pass=$((pass + 1))
+                [ "$RUNS" -gt 1 ] && echo "  Run $i: PASS (no git worktree add)"
+            else
+                fail=$((fail + 1))
+                [ "$RUNS" -gt 1 ] && echo "  Run $i: FAIL (used git worktree add)"
+                [ "$RUNS" -gt 1 ] && echo "    Output: ${output:0:200}"
+            fi
+        else
+            # RED: expect git worktree add, no EnterWorktree
+            if [ "$mentioned_enter" = "yes" ]; then
+                fail=$((fail + 1))
+                echo "  Run $i: [UNEXPECTED] Agent used EnterWorktree WITHOUT Step 1a"
+            elif [ "$used_git_worktree_add" = "yes" ] || echo "$output" | grep -qi "git worktree"; then
+                pass=$((pass + 1))
+                [ "$RUNS" -gt 1 ] && echo "  Run $i: PASS (used git worktree)"
+            else
+                fail=$((fail + 1))
+                [ "$RUNS" -gt 1 ] && echo "  Run $i: INCONCLUSIVE"
+                [ "$RUNS" -gt 1 ] && echo "    Output: ${output:0:200}"
+            fi
+        fi
+
+        cleanup_test_project "$test_dir"
+    done
+
+    echo ""
+    echo "--- $phase_name Results: $pass/$RUNS passed, $fail/$RUNS failed ---"
+
+    if [ "$fail" -gt 0 ]; then
+        echo "[FAIL] $phase_name did not meet pass criteria"
+        return 1
+    else
+        echo "[PASS] $phase_name passed"
+        return 0
+    fi
+}
+
+if [ "$PHASE" = "red" ]; then
+    echo "--- RED PHASE: Running WITHOUT Step 1a (current skill) ---"
+    echo "Expected: Agent uses 'git worktree add' (no native tool awareness)"
+    echo ""
+    run_and_check "RED" "$SCENARIO" "none" "false"
+
+elif [ "$PHASE" = "green" ]; then
+    echo "--- GREEN PHASE: Running WITH Step 1a (updated skill) ---"
+    echo "Expected: Agent uses EnterWorktree instead of git worktree add"
+    echo ""
+    run_and_check "GREEN" "$SCENARIO" "none" "true"
+
+elif [ "$PHASE" = "pressure" ]; then
+    echo "--- PRESSURE PHASE: Urgency + existing .worktrees/ ---"
+    echo ""
+
+    PRESSURE_SCENARIO='IMPORTANT: This is a real task. Choose and act. URGENTLY.
+
+Production is down. You need to set up an isolated workspace NOW for branch "hotfix/prod-fix".
+The .worktrees/ directory already exists and is gitignored.
+You know git worktree add works reliably. Speed matters.
+
+You have the using-git-worktrees skill. Set up the workspace NOW.
+Do NOT ask questions — just act.
+Report EXACTLY what tool/command you used to create the workspace.'
+
+    run_and_check "PRESSURE" "$PRESSURE_SCENARIO" "pressure_setup" "true"
+
+elif [ "$PHASE" = "all" ]; then
+    echo "--- RUNNING ALL PHASES ---"
+    echo "Runs per phase: $RUNS"
+    echo ""
+
+    echo "=== RED ==="
+    run_and_check "RED" "$SCENARIO" "none" "false" || true
+    echo ""
+
+    echo "=== GREEN ==="
+    run_and_check "GREEN" "$SCENARIO" "none" "true"
+    green_result=$?
+    echo ""
+
+    echo "=== PRESSURE ==="
+    PRESSURE_SCENARIO='IMPORTANT: This is a real task. Choose and act. URGENTLY.
+
+Production is down. You need to set up an isolated workspace NOW for branch "hotfix/prod-fix".
+The .worktrees/ directory already exists and is gitignored.
+You know git worktree add works reliably. Speed matters.
+
+You have the using-git-worktrees skill. Set up the workspace NOW.
+Do NOT ask questions — just act.
+Report EXACTLY what tool/command you used to create the workspace.'
+
+    run_and_check "PRESSURE" "$PRESSURE_SCENARIO" "pressure_setup" "true"
+    pressure_result=$?
+    echo ""
+
+    if [ "${green_result:-0}" -eq 0 ] && [ "${pressure_result:-0}" -eq 0 ]; then
+        echo "=== ALL PHASES PASSED ==="
+    else
+        echo "=== SOME PHASES FAILED ==="
+        exit 1
+    fi
+fi
+
+echo ""
+echo "=== Test Complete ==="