pi-devbox/scripts/smoke-test.sh

#!/usr/bin/env bash
# smoke-test.sh — basic sanity checks for the pi-devbox image
#
# Usage: ./scripts/smoke-test.sh <image>
#
# Verifies:
#   - pi binary present and returns a version
#   - pi-toolkit cloned at /opt/pi-toolkit
#   - pi-extensions cloned at /opt/pi-extensions
#   - entrypoint deploys pi-toolkit keybindings symlink
#   - entrypoint deploys ≥4 extensions
#   - mempalace bridge symlink present
#   - settings.json bootstrapped
#   - image size within threshold

set -euo pipefail

IMAGE="${1:?usage: $0 <image>}"
PASS=0; FAIL=0
# Since the refactor to FROM opencode-devbox:latest-pi-only, this image equals
# the pi-only variant (pi + companions + fork/recall node_modules, NO opencode),
# so the threshold tracks pi-only's (2750 MB), not the old standalone 2200 MB.
SIZE_THRESHOLD_MB=2750

run() {
  local label="$1"; local cmd="$2"
  if docker run --rm --entrypoint="" "$IMAGE" sh -c "$cmd" >/dev/null 2>&1; then
    printf "  ✅  %s\n" "$label"; PASS=$((PASS+1))
  else
    printf "  ❌  %s\n" "$label"; FAIL=$((FAIL+1))
  fi
}

# Stricter version of `run` that also asserts an expected substring in stdout.
# Used for catching the "image bytes silently identical to previous release"
# class of regression (Docker layer cache hit on `npm install -g <pkg>` because
# the bare command string is identical across builds, even when `latest` would
# resolve differently). Discovered 2026-05-23 — every pi-devbox release v0.74.0
# through v0.75.5 had been shipping the same image bytes.
run_expect() {
  local label="$1"; local cmd="$2"; local expect="$3"
  local out
  out=$(docker run --rm --entrypoint="" "$IMAGE" sh -c "$cmd" 2>&1) || true
  if echo "$out" | grep -Fq "$expect"; then
    printf "  ✅  %s (got %s)\n" "$label" "$expect"; PASS=$((PASS+1))
  else
    printf "  ❌  %s — expected substring %q, got: %s\n" "$label" "$expect" "$out"; FAIL=$((FAIL+1))
  fi
}

echo "=== pi-devbox smoke test: $IMAGE ==="
echo ""

# ── Basic binary checks ───────────────────────────────────────────────
echo "── Binaries ──"
if [ -n "${EXPECTED_PI_VERSION:-}" ]; then
  run_expect "pi version matches build arg" "pi --version" "$EXPECTED_PI_VERSION"
else
  run "pi"              "pi --version"
fi
run "node"            "node --version"
run "git"             "git --version"
run "aws"             "aws --version"
run "uv"              "uv --version"
run "nvim"            "nvim --version"
run "mempalace-mcp"   "mempalace-mcp --help"

# ── Repo clones ───────────────────────────────────────────────────────
echo ""
echo "── Repo clones ──"
run "pi-toolkit clone"    "test -d /opt/pi-toolkit && git -C /opt/pi-toolkit rev-parse --short HEAD"
run "pi-extensions clone" "test -d /opt/pi-extensions && git -C /opt/pi-extensions rev-parse --short HEAD"
# pi-fork (fork tool) + pi-observational-memory (recall tool) — inherited from
# the pi-only base, cloned to /opt with node_modules baked at build time.
run "pi-fork clone + node_modules" \
    "test -f /opt/pi-fork/package.json && test -d /opt/pi-fork/node_modules"
run "pi-observational-memory clone + node_modules" \
    "test -f /opt/pi-observational-memory/package.json && test -d /opt/pi-observational-memory/node_modules"

# ── Runtime deployment (needs entrypoint to run) ──────────────────────
echo ""
echo "── Runtime deployment ──"
# Spin up a long-running container WITHOUT overriding the entrypoint, so
# the baked entrypoint chain (entrypoint.sh → entrypoint-user.sh) runs and
# deploys pi-toolkit + pi-extensions to ~/.pi/agent/. Override CMD to
# tail -f /dev/null so the container stays alive while we docker-exec.
CID=$(docker run -d --rm "$IMAGE" tail -f /dev/null)
cleanup() { docker rm -f "$CID" >/dev/null 2>&1 || true; }
trap cleanup EXIT

# Wait for entrypoint-user.sh to finish deploying pi-toolkit + extensions
for i in $(seq 1 30); do
  if docker exec "$CID" test -L /home/developer/.pi/agent/keybindings.json 2>/dev/null; then
    break
  fi
  sleep 1
done

exec_test() {
  local label="$1"; local cmd="$2"
  if docker exec -u developer "$CID" sh -c "$cmd" >/dev/null 2>&1; then
    printf "  ✅  %s\n" "$label"; PASS=$((PASS+1))
  else
    printf "  ❌  %s\n" "$label"; FAIL=$((FAIL+1))
  fi
}

exec_test "keybindings.json (pi-toolkit)"         'test -L $HOME/.pi/agent/keybindings.json && echo ok'
exec_test "extensions ≥ 4 (pi-extensions)"        'count=$(ls -1 $HOME/.pi/agent/extensions/*.ts 2>/dev/null | wc -l); [ $count -ge 4 ] && echo "$count extensions"'
exec_test "mempalace.ts bridge"                    'test -L $HOME/.pi/agent/extensions/mempalace.ts && echo ok'
exec_test "settings.json bootstrapped"             'test -f $HOME/.pi/agent/settings.json && echo ok'

# pi-fork + pi-observational-memory are registered by entrypoint-user.sh via
# `pi install /opt/<pkg>`, which runs slightly after the keybindings marker.
for i in $(seq 1 15); do
  if docker exec "$CID" grep -q pi-observational-memory \
       /home/developer/.pi/agent/settings.json 2>/dev/null; then
    break
  fi
  sleep 1
done
exec_test "pi-fork registered (fork tool)"         'grep -q pi-fork $HOME/.pi/agent/settings.json && echo ok'
exec_test "pi-observational-memory registered (recall tool)" 'grep -q pi-observational-memory $HOME/.pi/agent/settings.json && echo ok'

# ── Image size ────────────────────────────────────────────────────────
echo ""
echo "── Image size ──"
SIZE_MB=$(docker image inspect "$IMAGE" --format='{{.Size}}' | awk '{printf "%d", $1/1048576}')
if [ "$SIZE_MB" -le "$SIZE_THRESHOLD_MB" ]; then
  printf "  ✅  size: %d MB (threshold %d MB)\n" "$SIZE_MB" "$SIZE_THRESHOLD_MB"; PASS=$((PASS+1))
else
  printf "  ❌  size: %d MB exceeds threshold %d MB\n" "$SIZE_MB" "$SIZE_THRESHOLD_MB"; FAIL=$((FAIL+1))
fi

# ── Summary ───────────────────────────────────────────────────────────
echo ""
echo "=== Results: ${PASS} passed, ${FAIL} failed ==="
[ "$FAIL" -eq 0 ]