pi-devbox/scripts/smoke-test.sh

#!/usr/bin/env bash
# smoke-test.sh — sanity checks for the pi-devbox image
#
# Usage: ./scripts/smoke-test.sh <image>
#
# Verifies:
#   - pi binary present and (if EXPECTED_PI_VERSION set) matches CI's resolved version
#   - mempalace core matches the audited pin (if EXPECTED_MEMPALACE_VERSION set)
#   - new v1.0.0 base additions (pandoc, graphviz, imagemagick, yq, tealdeer)
#   - typst PDF engine for pandoc (v1.4.0) — `pandoc --pdf-engine=typst`
#   - non-modal editors nano + micro (alongside nvim)
#   - terminfo for modern emulators: xterm-kitty, xterm-ghostty, wezterm,
#     alacritty, foot (kitty-terminfo + ncurses-term + compiled ghostty alias)
#   - tmux 0-indexing baked in /etc/tmux.conf (required for pi-studio variants)
#   - pi-toolkit cloned at /opt/pi-toolkit
#   - pi-extensions cloned at /opt/pi-extensions
#   - pi-atelier vendored at /opt/pi-atelier, registered from /opt (not npm:),
#     and >= the version floor pi's TUI requires (see the floor test)
#   - pi-fork + pi-observational-memory cloned with node_modules baked
#   - entrypoint deploys pi-toolkit keybindings symlink
#   - entrypoint deploys ≥4 extensions
#   - mempalace bridge symlink present
#   - settings.json bootstrapped
#   - pi-fork + pi-observational-memory registered in settings.json packages[]
#     via `pi install`
#   - pi-devbox-version command present + wraps the build manifest correctly
#     (human, --json, --quiet)
#   - (studio variant only, auto-detected) pi-studio cloned + prebuilt
#     client bundle present + registered via `pi install`
#   - image size within threshold

set -euo pipefail

IMAGE="${1:?usage: $0 <image>}"
PASS=0; FAIL=0
# pi-devbox v1.0.0 (decoupled from opencode-devbox) added pandoc, graphviz,
# imagemagick, yq, tealdeer, a baked /etc/tmux.conf, and the non-modal
# editors nano + micro (~15 MB combined). v1.6.0 baked in agent-browser +
# Playwright Chromium (~291 MB net after dropping the unused headless-shell
# build), which lifted the baseline. CI amd64 actuals observed on run 512
# (v1.6.1): 3411 MB non-studio, 3574 MB studio. Threshold below carries
# ~225 MB margin above the studio number to absorb minor arch/build-cache
# differences and small future growth without false reds, while still
# catching an unexpected +GB regression.
SIZE_THRESHOLD_MB=3800

# On failure, surface the last few lines the command produced. This used to
# discard output entirely (`>/dev/null 2>&1`), which made a red ❌ carry zero
# diagnostic weight: explaining the single v1.8.0 stage-default failure took a
# full CI-log dig plus a registry-config inspection, when the container had
# already printed the answer and thrown it away. Assertions that want a
# diagnostic just echo it to stderr — it stays hidden while they pass.
run() {
  local label="$1"; local cmd="$2"
  local out
  if out=$(docker run --rm --entrypoint="" "$IMAGE" sh -c "$cmd" 2>&1); then
    printf "  ✅  %s\n" "$label"; PASS=$((PASS+1))
  else
    printf "  ❌  %s\n" "$label"; FAIL=$((FAIL+1))
    # `if`, not `&&` — a trailing false under `set -e` would abort the script.
    if [ -n "$out" ]; then
      printf "        └─ %s\n" "$(printf '%s' "$out" | tail -3 | tr '\n' ' ' | cut -c1-300)"
    fi
  fi
}

# Stricter version of `run` that asserts an expected substring in stdout.
# Catches 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..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 ""

# ── Binaries ─────────────────────────────────────────────────────────
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 "nano"            "nano --version"
run "micro"           "micro --version"
run "kitty-terminfo"  "infocmp -x xterm-kitty >/dev/null 2>&1"
run "terminfo: modern emulators (ncurses-term)" 'for t in wezterm alacritty foot ghostty st-256color; do infocmp -x "$t" >/dev/null 2>&1 || exit 1; done'
run "terminfo: xterm-ghostty alias (tic)" "infocmp -x xterm-ghostty >/dev/null 2>&1"
run "nvim true-colour default (sysinit.vim)" "nvim --headless -c 'lua os.exit(vim.o.termguicolors and 0 or 1)'"
run "mempalace-mcp"   "mempalace-mcp --help"
run "mempalace-pi-session on PATH" "mempalace-pi-session --help"
# The staging dir must sit next to the palace, not in a disposable cache: the
# palace keys per-source dedup on the STAGED path, so a stage that can be wiped
# while the palace survives lets `mempalace sync` prune every drawer mined from
# it. Assert the resolved default, not an env var — the guarantee is "stage
# shares the palace's lifetime", which an ENV pin would quietly break.
# NOTE: --sessions-dir gets an EMPTY temp dir, never /tmp. The stage banner is
# printed before any export, so nothing needs to be found — and pointing a
# default-staged run at a populated dir would export whatever transcripts it
# finds into the real stage, which is how a synthetic test session ends up
# staged for mining as if it were a real conversation.
#
# Asserted $HOME-RELATIVE, not against a literal /home/developer. `run` invokes
# `docker run --entrypoint=""`, and neither Dockerfile sets USER or ENV HOME
# (HOME is set by entrypoint-user.sh, which --entrypoint="" deliberately skips),
# so these assertions execute as root with HOME=/root. The original literal
# /home/developer form could therefore never match and failed the v1.8.0
# release — a test bug, not a product one: the stage resolution was correct all
# along, it just follows $HOME. The invariant under test ("the stage sits beside
# the palace, sharing its lifetime") is user-independent, so pinning the user
# was never part of it. A cache-dir default still fails the pattern below, which
# is the regression this guards.
#
# It went unnoticed for three days because this workflow only triggers on
# `push: tags: v*` — the assertion was added on a main push, so v1.8.0 was its
# first execution ever. Use the `smoke_only` workflow_dispatch input to run
# smoke against HEAD without cutting a tag.
run "pi stage defaults next to the palace (not a cache dir)" '
  out=$(mempalace-pi-session --dry-run --reason smoke --sessions-dir "$(mktemp -d)" 2>&1) || true
  stage=$(echo "$out" | grep -oE "stage=[^ ]+" | head -1)
  echo "resolved ${stage:-<no stage= line>} with HOME=$HOME" >&2
  case "$stage" in
    "stage=$HOME/.mempalace/pi-stage/"*) exit 0 ;;
    *) exit 1 ;;
  esac
'
# Companion to the above: the deployment-specific case the literal assertion was
# reaching for, done properly by supplying the HOME the container actually runs
# with instead of assuming it.
run "pi stage is palace-adjacent for the developer user" '
  out=$(HOME=/home/developer mempalace-pi-session --dry-run --reason smoke --sessions-dir "$(mktemp -d)" 2>&1) || true
  echo "$out" | grep -oE "stage=[^ ]+" | head -1 >&2
  echo "$out" | grep -q "stage=/home/developer/.mempalace/pi-stage/"
'
run "pi stage follows MEMPALACE_PALACE_PATH" '
  out=$(MEMPALACE_PALACE_PATH=/tmp/alt/.mempalace/palace \
        mempalace-pi-session --dry-run --reason smoke --sessions-dir "$(mktemp -d)" 2>&1) || true
  echo "$out" | grep -q "stage=/tmp/alt/.mempalace/pi-stage/"
'
# The feeder's --agent default is WHO a drawer is attributed to. mempalace core
# records neither the machine nor the harness on a write, and one shared bearer
# token means the server cannot tell clients apart, so toolkit c64ffa1 changed
# this default from $USER to pi@$MEMPALACE_PI_DEVICE — the one string that makes
# a write attributable to both. Nothing ever PRINTED the resolved value (the
# banner shows mode= and stage= only), so an image built from a pre-c64ffa1
# toolkit ref would ship unattributed writes with every check still green.
#
# `--help` assigns AGENT (script top) before it parses args, then exits 0 with
# no side effects — so `bash -x` observes the REAL resolution, env interpolation
# and fallback included, rather than grepping the source for a literal line that
# any reformat would break. Two-sided on purpose: device set => pi@<device>;
# device UNSET => must not be pi@anything. The second half is what fails against
# the old unconditional $USER default, which ignored the device entirely.
#
# Probes the PATH entry (a symlink into the /opt clone) rather than that clone
# path directly: this is the invocation the systemd/launchd timers and
# entrypoint-user.sh actually use, so it is the default that reaches the palace.
run "feeder resolves --agent to pi@<device> (drawer attribution)" '
  f=$(command -v mempalace-pi-session) || { echo "feeder not on PATH" >&2; exit 1; }
  with=$(MEMPALACE_PI_DEVICE=smoke-device bash -x $f --help 2>&1 | sed -n "s/^+* *AGENT=//p" | tail -n1)
  without=$(env -u MEMPALACE_PI_DEVICE bash -x $f --help 2>&1 | sed -n "s/^+* *AGENT=//p" | tail -n1)
  echo "resolved with-device=[$with] without-device=[$without]" >&2
  [ "$with" = "pi@smoke-device" ] || exit 1
  case "$without" in pi@*) exit 1 ;; esac
  echo ok
'
# Regression guard for the pi transcript exporter. If pi ever changes its
# session JSONL shape, the exporter stops recognising sessions and the palace
# silently gets nothing (or, worse, raw JSON chunked as prose). Feed it a
# synthetic session and assert it is actually exported. Uses --dry-run so no
# palace is touched, and a temp stage so nothing real is written.
run "pi transcript exporter recognises a pi session" '
  set -e
  d=$(mktemp -d); s="$d/sessions/--workspace--"; mkdir -p "$s"
  {
    printf "%s\n" "{\"type\":\"session\",\"version\":1,\"id\":\"smoke\",\"cwd\":\"/workspace\",\"timestamp\":\"2026-01-01T00:00:00Z\"}"
    printf "%s\n" "{\"type\":\"message\",\"message\":{\"role\":\"user\",\"content\":\"question one\"}}"
    a=$(printf "a%.0s" $(seq 1 1200))
    printf "%s\n" "{\"type\":\"message\",\"message\":{\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"$a\"}]}}"
    printf "%s\n" "{\"type\":\"message\",\"message\":{\"role\":\"user\",\"content\":\"question two\"}}"
    printf "%s\n" "{\"type\":\"message\",\"message\":{\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"short reply\"}]}}"
  } > "$s/2026-01-01T00-00-00-000Z_smoke.jsonl"
  out=$(mempalace-pi-session --dry-run --sessions-dir "$d/sessions" --stage "$d/stage" 2>&1)
  echo "$out" | grep -q "Exported 1 session"
'
# The same guard from the other side: a session with no real assistant output
# (an abandoned prompt, whose bulk is injected skill text) must NOT be filed.
run "pi transcript exporter rejects an abandoned session" '
  set -e
  d=$(mktemp -d); s="$d/sessions/--workspace--"; mkdir -p "$s"
  {
    printf "%s\n" "{\"type\":\"session\",\"version\":1,\"id\":\"smoke2\",\"cwd\":\"/workspace\",\"timestamp\":\"2026-01-01T00:00:00Z\"}"
    u=$(printf "u%.0s" $(seq 1 13000))
    printf "%s\n" "{\"type\":\"message\",\"message\":{\"role\":\"user\",\"content\":\"$u\"}}"
    printf "%s\n" "{\"type\":\"message\",\"message\":{\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"Ready. What would you like to work on?\"}]}}"
  } > "$s/2026-01-01T00-00-00-000Z_smoke2.jsonl"
  out=$(mempalace-pi-session --dry-run --sessions-dir "$d/sessions" --stage "$d/stage" 2>&1)
  echo "$out" | grep -q "no sessions qualified"
'
# The remote-palace-without-inbox skip must ANNOUNCE itself, not vanish. This
# branch of entrypoint-user.sh runs at container start (not reachable from a
# `docker run` one-shot), so assert against the entrypoint that actually shipped
# in the image. Guards a silent regression back to the bare `:` no-op, which
# left a container contributing nothing to the palace with no artifact saying
# why — the log it would normally leave is written by the other branch.
run_expect "remote-palace-without-inbox skip is announced, not silent" \
    "grep -o 'MemPalace catch-up skipped' /usr/local/bin/entrypoint-user.sh | head -1" \
    "MemPalace catch-up skipped"
run "...and the skip notice names the variable that fixes it" \
    "grep -A6 'MemPalace catch-up skipped' /usr/local/bin/entrypoint-user.sh | grep -q 'MEMPALACE_PI_SSH_TARGET'"
# A remote mine that FAILS must not report success. MCP answers a hard tool
# failure with HTTP 200 and the tool's own JSON escaped inside
# result.content[].text, so the feeder's old `'\"error\"' in body` check could
# never see it: on 2026-08-15 a mine that died with "source directory not found:
# '/data/feed/...'" logged "Done. Wing updated." and exited 0, and this
# container's transcripts were filed nowhere for a whole session. The feeder
# carries fixtures for that exact body; run them against the baked toolkit so a
# stale/reverted toolkit ref can't reintroduce a silent feed.
run "baked feeder detects a failed remote mine (no silent false success)" \
    "mempalace-pi-session --self-test"
# v1.0.0 base additions — verify presence and basic functionality.
run "pandoc"          "pandoc --version"
run "typst"           "typst --version"
run "pandoc+typst PDF engine" "printf '# hi\n' | pandoc --pdf-engine=typst -o /tmp/_smoke.pdf - && test -s /tmp/_smoke.pdf; rm -f /tmp/_smoke.pdf"
run "graphviz (dot)"  "dot -V"
run "imagemagick"     "magick --version"
run "yq (mikefarah v4)" "yq --version | grep -qE 'mikefarah.*version v4'"
run "tldr (tealdeer)" "tldr --version"
run "socat"           "socat -V"
run "studio-expose helper" "test -x /usr/local/bin/studio-expose"
run "image-baked pi-devbox-environment skill" \
    "test -f /usr/local/share/pi-devbox/skills/pi-devbox-environment/SKILL.md"
run "image-baked credential-incident-response skill" \
    "test -f /usr/local/share/pi-devbox/skills/credential-incident-response/SKILL.md"
run "global-AGENTS append snippet present" \
    "test -f /usr/local/share/pi-devbox/pi-global-AGENTS.append.md"
run "pi-devbox block merged into pi-global-AGENTS.md" \
    "grep -q 'pi-devbox:managed-block' /opt/pi-toolkit/pi-global-AGENTS.md"
run "mempalace session-start pointer merged into global AGENTS.md" \
    "grep -q 'load the mempalace skill' /opt/pi-toolkit/pi-global-AGENTS.md"
# Vendored fallback skills (so a no-skillset container still resolves the
# AGENTS.md 'read the pi-extensions skill' pointer).
run "image-baked pi-extensions fallback skill" \
    "test -f /usr/local/share/pi-devbox/skills/pi-extensions/SKILL.md"
run "pi-extensions skill ships its helper" \
    "test -f /usr/local/share/pi-devbox/skills/pi-extensions/evaluate-extension-usage.py"
run "image-baked mempalace fallback skill" \
    "test -f /usr/local/share/pi-devbox/skills/mempalace/SKILL.md"
# Layered freshness: when the pinned pi-extensions clone carries the skill, the
# baked copy must be the fresh package copy (Option 1), not the stale snapshot.
run "pi-extensions skill refreshed from package when present" \
    "if [ -f /opt/pi-extensions/skill/SKILL.md ]; then cmp -s /opt/pi-extensions/skill/SKILL.md /usr/local/share/pi-devbox/skills/pi-extensions/SKILL.md; else true; fi"
# Runtime ownership handover (v1.8.5): the baked links are a FALLBACK, and
# skillset-OWNED skills must be repointed at the live clone when one is mounted.
# The list is data, so assert its content, not just its presence: mempalace in,
# pi-extensions deliberately out (its skillset copy is a lagging duplicate).
run "devbox-skill-reconcile helper present + executable" \
    "test -x /usr/local/bin/devbox-skill-reconcile"
run "skillset-owned list ships and names mempalace" \
    "grep -qx 'mempalace' /usr/local/share/pi-devbox/skills/skillset-owned.txt"
run "skillset-owned list excludes pi-extensions (ownership)" \
    "! grep -qx 'pi-extensions' /usr/local/share/pi-devbox/skills/skillset-owned.txt"

# ── tmux 0-indexing (required for pi-studio variants) ─────────────────
echo ""
echo "── tmux config ──"
run_expect "/etc/tmux.conf has base-index 0" \
  "cat /etc/tmux.conf" "set -g base-index 0"
run_expect "/etc/tmux.conf has pane-base-index 0" \
  "cat /etc/tmux.conf" "set -g pane-base-index 0"

# ── 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"
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"
# ...and that the clone carries the AUTH FIX, not merely that it exists. om's
# pre-flight hasUsableAuth() check silently disabled `recall` for ~8 weeks once
# pi moved to request-time SigV4 signing and stopped exposing a static Bedrock
# key; upstream fixed it in ce9fc98, adopted in v1.8.4. PI_OBSMEM_REF tracks
# master, so an upstream revert or force-push would ship a dead `recall` with
# the clone assertion above still green — the exact gap flagged as open in the
# v1.8.5 changelog.
#
# Pin the markers to src/runtime.ts, the fix SITE, rather than grepping the
# repo: two of these three strings also appear under tests/, so a repo-wide
# grep stays green with runtime.ts itself reverted. That is a false green of the
# same family as the old skill-snapshot canary.
run "pi-observational-memory carries the ce9fc98 auth fix (recall stays alive)" '
  f=/opt/pi-observational-memory/src/runtime.ts
  test -f "$f" || { echo "fix site missing: $f" >&2; exit 1; }
  for m in availability_recheck providerCredentialConfigured hasConfiguredAuth; do
    grep -q "$m" "$f" || { echo "marker absent from runtime.ts: $m" >&2; exit 1; }
  done
  echo ok
'
# pi-atelier: deliberately NO node_modules assertion, unlike its siblings —
# it declares zero runtime dependencies (only peerDeps, satisfied by the baked
# pi) and has no build step, so Dockerfile.variant skips `npm install` for it.
# Assert what pi actually loads instead: the entry point named by its
# package.json `pi.extensions` key.
run "pi-atelier clone + entry point" \
    "test -f /opt/pi-atelier/package.json && test -f /opt/pi-atelier/extensions/index.ts"

# ── pi <-> pi-atelier compatibility floor (executable, not a comment) ──
# pi-atelier < 0.7.1 wraps pi's PRIVATE TUI renderer in a way that recurses
# under pi >= 0.84: pi hangs at startup burning CPU, with no error. Upstream
# fixed it in 0.7.1/0.7.2, but atelier's peerDependencies still say
# `>=0.80.7`, so neither npm nor pi can warn about the real floor. Both
# versions are pinned in Dockerfile.variant; this makes a bad PAIRING fail the
# build instead of publishing an image whose TUI never starts.
run_expect "pi-atelier >= 0.7.1 floor for pi >= 0.84 (startup-hang guard)" \
    'ge() { [ "$(printf "%s\n%s\n" "$1" "$2" | sort -V | head -n1)" = "$2" ]; }; AV=$(jq -r ".version // empty" /opt/pi-atelier/package.json 2>/dev/null); PV=$(pi --version 2>/dev/null | grep -oE "[0-9]+\.[0-9]+\.[0-9]+" | head -n1); if [ -z "$AV" ] || [ -z "$PV" ]; then echo "unreadable versions (atelier=$AV pi=$PV)"; elif ge "$PV" 0.84.0 && ! ge "$AV" 0.7.1; then echo "VIOLATION: pi $PV with pi-atelier $AV"; else echo "compatible: pi $PV + pi-atelier $AV"; fi' \
    "compatible:"

# pi-studio is present only in the :latest-studio variant. Auto-detect by
# probing /opt/pi-studio so this one script covers both variants.
if docker run --rm --entrypoint="" "$IMAGE" sh -c 'test -d /opt/pi-studio' >/dev/null 2>&1; then
  STUDIO_VARIANT=1
  echo "  ℹ️   pi-studio detected — running studio assertions"
  run "pi-studio clone + node_modules" \
      "test -f /opt/pi-studio/package.json && test -d /opt/pi-studio/node_modules"
  run "pi-studio prebuilt client bundle" \
      "test -f /opt/pi-studio/client/studio-client.js"
else
  STUDIO_VARIANT=0
  echo "  ℹ️   pi-studio not present (non-studio variant) — skipping studio clone checks"
fi

# ── Build provenance (manifest + OCI labels) ─────────────────────────
echo ""
echo "── Build provenance ──"
run "/etc/pi-devbox/build-manifest.json present" \
    "test -f /etc/pi-devbox/build-manifest.json"
# These next checks replace three that grepped the manifest for the FIELD NAME
# and never looked at the value:
#
#     run_expect "manifest records pi_version" "cat …manifest.json" '"pi_version"'
#
# which passes on {"pi_version": ""} and on {"pi_version": null}. The tell was
# visible in its own passing output — `✅ manifest records pi_version (got
# "pi_version")` echoes the key back as the thing it claims to have found.
# Two failure modes were therefore invisible: a key that survives with an empty
# or garbage value, and a key that vanishes from the manifest while every
# remaining value still looks fine.
#
# Those two need SEPARATE assertions, and the reason is a trap worth keeping in
# writing: an "every component value is a valid SHA" loop passes VACUOUSLY on
# components:{} — jq's all() over an empty list is true — so the value check
# alone would go green on a manifest that lost every component. Mutation-tested
# 2026-08-25 across nine fabricated manifests (empty map, deleted key, "",
# null, "unknown", 12-hex truncation, 40 non-hex chars, legit null pi-studio).
run "manifest declares every required component key" '
  req="pi-toolkit pi-extensions pi-fork pi-observational-memory pi-atelier mempalace-toolkit pi-studio"
  for k in $req; do
    jq -e --arg k "$k" "(.components|has(\$k))" /etc/pi-devbox/build-manifest.json >/dev/null \
      || { echo "manifest lost component key: $k" >&2; exit 1; }
  done
'
# Subsumes the old `! grep -q \"unknown\"` check ("unknown" is not 40-hex), and
# also catches "", null and truncated SHAs, which that grep let through. null is
# legitimate for pi-studio alone: the non-studio variant has no such clone.
run "manifest component values are resolved 40-hex commits" '
  jq -e "
    .components
    | to_entries
    | all(if .key == \"pi-studio\" and .value == null then true
           else (.value|type) == \"string\" and (.value|test(\"^[0-9a-f]{40}\$\")) end)
  " /etc/pi-devbox/build-manifest.json >/dev/null
'
# pi_version against ground truth, same shape as the mempalace check below.
# Chains with the "pi version matches build arg" assertion earlier in this file:
# together they tie build arg -> installed binary -> recorded manifest, so a
# manifest written from a stale variable cannot pass by agreeing with itself.
run "manifest pi_version matches the installed pi" '
  m=$(jq -r ".pi_version // empty" /etc/pi-devbox/build-manifest.json)
  b=$(pi --version 2>/dev/null | head -n1 | tr -d "\r")
  echo "manifest=[$m] installed=[$b]" >&2
  [ -n "$m" ] && [ "$m" = "$b" ]
'
# Top-level provenance fields: assert the SHAPE of each value, and only when the
# field is populated. source_revision and build_date legitimately default to
# empty (Dockerfile.variant ARGs) on a plain local `docker build`, so demanding
# them would fail honest local smoke runs; a populated-but-malformed value is
# the actual defect. release_tag defaults to "dev", so empty means a broken write.
run "manifest top-level fields are well-formed, not merely present" '
  j=/etc/pi-devbox/build-manifest.json
  t=$(jq -r ".release_tag // empty" $j)
  r=$(jq -r ".source_revision // empty" $j)
  d=$(jq -r ".build_date // empty" $j)
  echo "release_tag=[$t] source_revision=[$r] build_date=[$d]" >&2
  [ -n "$t" ] || { echo "release_tag empty (ARG default is dev)" >&2; exit 1; }
  if [ -n "$r" ]; then
    printf "%s" "$r" | grep -qxE "[0-9a-f]{40}" || { echo "source_revision not a 40-hex commit" >&2; exit 1; }
  fi
  if [ -n "$d" ]; then
    printf "%s" "$d" | grep -qE "^[0-9]{4}-[0-9]{2}-[0-9]{2}T" || { echo "build_date not ISO-8601" >&2; exit 1; }
  fi
'
# mempalace CORE was absent from the manifest through v1.8.5: the toolkit SHA
# was recorded but the palace version behind the MCP tools was not, so a palace
# bug could not be correlated to an image version. Assert the field exists AND
# equals the installed binary — recording it from ARG MEMPALACE_VERSION instead
# would look identical here yet drift silently the first time an install
# resolved to something other than the pin, which is the whole reason this file
# is built from ground truth. `// empty` matters: jq -r prints the 4-char
# string "null" for a JSON null, which would satisfy a naive -n test.
run "manifest mempalace_version matches the installed core" '
  m=$(jq -r ".mempalace_version // empty" /etc/pi-devbox/build-manifest.json)
  b=$(mempalace --version 2>/dev/null | head -n1 | tr -d "\r"); b=${b##* }
  echo "manifest=[$m] installed=[$b]" >&2
  [ -n "$m" ] && [ "$m" = "$b" ]
'
# ... and, when CI supplies it, that the installed core is the version CI
# actually AUDITED (published + not yanked on PyPI, in resolve-versions). This
# does NOT duplicate the check above, which compares two properties of one
# image and so cannot notice that BOTH are the wrong version. The live failure
# mode it covers: the variant builds `FROM` a base tag chosen by base-decide's
# content hash, so a bug in that hashing (the reason scripts/check-base-hash.sh
# exists) could reuse a cached base built from an OLDER MEMPALACE_VERSION pin —
# internally consistent, silently stale, invisible to every other assertion.
if [ -n "${EXPECTED_MEMPALACE_VERSION:-}" ]; then
  run "installed mempalace matches CI's audited pin (${EXPECTED_MEMPALACE_VERSION})" "
    b=\$(mempalace --version 2>/dev/null | head -n1 | tr -d '\r'); b=\${b##* }
    echo \"installed=[\$b] audited_pin=[${EXPECTED_MEMPALACE_VERSION}]\" >&2
    [ \"\$b\" = \"${EXPECTED_MEMPALACE_VERSION}\" ]
  "
fi
# Every component must be a resolved commit (or null for pi-studio in the
# non-studio variant) — now enforced by the 40-hex value check above, which
# strictly subsumes the old whole-file grep for '"unknown"'. Only rev() ever
# emits "unknown" and rev() feeds components only, so nothing is lost.
# pi-devbox-version wraps the manifest into a human-first command; verify the
# binary is present, executable, and that all three output modes work.
run "pi-devbox-version binary present + executable" \
    "test -x /usr/local/bin/pi-devbox-version"
run_expect "pi-devbox-version human output shows release tag" \
    "pi-devbox-version" "pi-devbox "
# --json is a verbatim `cat` of the manifest, so "round-trips" is assertable
# literally. The old form grepped the output for the string "release_tag" — the
# key name again — which would pass on a truncated or re-serialised dump.
run "pi-devbox-version --json round-trips the manifest byte-for-byte" '
  a=$(cat /etc/pi-devbox/build-manifest.json)
  b=$(pi-devbox-version --json)
  [ "$a" = "$b" ] || { echo "--json output differs from the manifest on disk" >&2; exit 1; }
'
run_expect "pi-devbox-version --quiet is a compact one-liner" \
    "pi-devbox-version --quiet | wc -l" "1"
# ── Vendored skill snapshot provenance ─────────────────────────────────
# The vendored mempalace skill is the one baked artefact with no /opt clone
# behind it (private upstream — see VENDORED.md), so until now the manifest
# could not say which skillset commit it came from. Two fields now travel with
# it: the CLAIMED ref (ARG default in Dockerfile.variant) and the MEASURED
# sha256 of the shipped bytes. Assert both are well-formed, and — separately —
# that the measurement still describes the file in the image.
#
# Kept as two assertions for the same reason the component checks are: one
# proves the fields are not empty/garbage, the other proves they are not merely
# self-consistent. A single combined check could pass on a manifest whose hash
# was computed from a file that was later overwritten (the pi-extensions skill
# copy at Dockerfile.variant:165 does exactly that kind of overwrite, one stage
# earlier), which is the failure this second one exists to catch.
run "manifest records the vendored skill snapshot provenance" '
  j=/etc/pi-devbox/build-manifest.json
  r=$(jq -r ".skillset_snapshot_ref // empty" $j)
  s=$(jq -r ".skillset_snapshot_tree_sha256 // empty" $j)
  echo "ref=[$r] tree_sha256=[$s]" >&2
  printf "%s" "$r" | grep -qxE "[0-9a-f]{40}" \
    || { echo "skillset_snapshot_ref is not a 40-hex commit" >&2; exit 1; }
  printf "%s" "$s" | grep -qxE "[0-9a-f]{64}" \
    || { echo "skillset_snapshot_tree_sha256 is not a 64-hex digest" >&2; exit 1; }
'
# Recomputes over the whole DIRECTORY with the same tree_sha256() pipeline
# Dockerfile.variant used to measure it, not a plain `sha256sum SKILL.md` —
# a file-only compare here would pass even if the manifest recorded a
# fingerprint over a directory that has since grown a second file (this is
# not hypothetical: pi-extensions already ships two files for its skill).
run "manifest skill fingerprint matches the baked snapshot" '
  j=/etc/pi-devbox/build-manifest.json
  d=/usr/local/share/pi-devbox/skills/mempalace
  m=$(jq -r ".skillset_snapshot_tree_sha256 // empty" $j)
  a=$( (cd "$d" && find . -type f -print | LC_ALL=C sort | xargs -r sha256sum) | sha256sum | cut -d" " -f1)
  echo "manifest=[$m] actual=[$a]" >&2
  [ -n "$m" ] && [ "$m" = "$a" ]
'
# OCI labels live in the image config, not the container fs — inspect them
# from the host docker rather than via `docker run`.
LBL=$(docker inspect --format '{{ index .Config.Labels "se.jordbo.pi-devbox.pi-extensions-ref" }}' "$IMAGE" 2>/dev/null || true)
if [ -n "$LBL" ] && [ "$LBL" != "<no value>" ]; then
  printf "  ✅  OCI label se.jordbo.pi-devbox.pi-extensions-ref=%s\n" "$LBL"; PASS=$((PASS+1))
else
  printf "  ❌  OCI label se.jordbo.pi-devbox.pi-extensions-ref missing or empty\n"; FAIL=$((FAIL+1))
fi

# ── 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.
# Gate on BOTH the keybindings symlink (deployed by pi-toolkit) AND the
# mempalace.ts bridge (deployed last by entrypoint-user.sh) AND ≥4 *.ts
# extensions present. Parallel build load can otherwise sample the *.ts
# count mid-deploy and produce a flake. See opencode-devbox c6f9d11
# (2026-06-08) — same fix transplanted.
for i in $(seq 1 45); do
  if docker exec "$CID" sh -c '
       test -L /home/developer/.pi/agent/keybindings.json && \
       test -L /home/developer/.pi/agent/extensions/mempalace.ts && \
       test -L /home/developer/.agents/skills/pi-devbox-environment && \
       test -L /home/developer/.agents/skills/pi-extensions && \
       test -L /home/developer/.agents/skills/mempalace && \
       count=$(ls -1 /home/developer/.pi/agent/extensions/*.ts 2>/dev/null | wc -l) && \
       [ "$count" -ge 4 ]
     ' >/dev/null 2>&1; 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'
exec_test "pi-devbox-environment skill linked"     'test -L $HOME/.agents/skills/pi-devbox-environment && test -f $HOME/.agents/skills/pi-devbox-environment/SKILL.md && echo ok'
exec_test "pi-extensions skill linked (fallback)"  'test -L $HOME/.agents/skills/pi-extensions && test -f $HOME/.agents/skills/pi-extensions/SKILL.md && echo ok'
exec_test "mempalace skill linked (fallback)"      'test -L $HOME/.agents/skills/mempalace && test -f $HOME/.agents/skills/mempalace/SKILL.md && echo ok'
# The vendored mempalace snapshot is refreshed MANUALLY per release (see
# rootfs/usr/local/share/pi-devbox/skills/VENDORED.md). Through v1.8.4 it also
# silently SHADOWED the live skillset copy, so staleness was invisible — and the
# canary that was supposed to catch it could not: it grepped "Shared palace:
# multiple harnesses", a phrase present in BOTH the stale and the fresh copy.
# A snapshot canary must pin the NEWEST section, so update this string whenever
# the snapshot is refreshed — that is the point of it.
#
# v1.8.7: this fired for real, and on the release that changed the snapshot. The
# pinned phrase was "Attribute what you file yourself", the heading of the
# instruction telling agents to hand-stamp added_by — which that same release
# WITHDREW (RFC 001 §7.3.2 ranks agent-side stamping worst-possible; the bridge
# now does it). So the canary correctly reported "snapshot changed, expectation
# did not", and blocked publication of an otherwise-green build (81 passed, 1
# failed, twice). Two lessons kept in the assertion itself:
#   * it is now BIDIRECTIONAL — the new phrase must be present AND the withdrawn
#     one absent, so a re-vendored stale snapshot fails just as loudly as a
#     forgotten bump. A one-way canary only catches half the drift.
#   * a phrase canary can only ever detect "older than what I remembered to pin",
#     never "older than skillset main".
#
# That structural limit is now addressed, but NOT by the "CI job diffing this
# file against the skillset repo" this comment used to point at (that pointer
# also dangled: it referenced an Unreleased changelog note that had become the
# v1.8.7 heading). A CI diff cannot be done without granting CI a credential
# for the PRIVATE skillset repo, and it would guard a file that on this fleet
# NO host reads — all four compose stacks mount a workspace containing the
# skillset, so devbox-skill-reconcile repoints this link at the live clone and
# the baked copy is a CI/no-mount fallback only. Instead the snapshot now
# carries its provenance (skillset_snapshot_ref + a measured
# skillset_snapshot_sha256 in build-manifest.json, written by
# scripts/vendor-mempalace-skill.sh), which moves the check to where the
# skillset actually IS: `scripts/vendor-mempalace-skill.sh --check` for a
# maintainer, and `pi-devbox-version` for an agent inside any container.
# This assertion is kept because it is orthogonal and free: it pins content,
# not provenance, so it still catches a re-vendored snapshot whose ref was
# bumped correctly but whose bytes came from the wrong place.
exec_test "mempalace skill snapshot is current"    'f=$HOME/.agents/skills/mempalace/SKILL.md; grep -q "Provenance is stamped for you" "$f" && ! grep -q "Attribute what you file yourself" "$f" && echo ok'
# Link TARGETS, not just link existence: with no skillset mounted (as here) the
# baked tree must be what resolves, for all four vendored skills.
exec_test "vendored skills resolve to the baked tree (no skillset mounted)" \
    'for s in mempalace pi-extensions pi-devbox-environment credential-incident-response; do
       case "$(readlink -f $HOME/.agents/skills/$s)" in
         /usr/local/share/pi-devbox/skills/$s) ;;
         *) echo "$s resolves to $(readlink -f $HOME/.agents/skills/$s)" >&2; exit 1 ;;
       esac
     done; echo ok'
# ... and that the tool REPORTS that resolution, which is the half that was
# missing: a stale baked snapshot and a current live clone were
# indistinguishable from inside the container. CI mounts no skillset, so every
# vendored skill must report "baked" here — which also makes this a real test of
# the fallback path rather than of the environment it happens to run in.
exec_test "pi-devbox-version reports skill sources (all baked, no skillset here)" \
    'out=$(pi-devbox-version)
     echo "$out" | grep -q "skills:" || { echo "no skills section" >&2; exit 1; }
     for s in mempalace pi-extensions pi-devbox-environment credential-incident-response; do
       echo "$out" | grep -qE "^    $s +baked$" \
         || { echo "$s not reported as baked" >&2; exit 1; }
     done; echo ok'
# The boot banner must NOT carry the section: entrypoint-user.sh prints the
# version FIRST, before the baked links exist and long before the skillset
# deploy + reconcile run last, so anything it said about skill sources would be
# a pre-reconcile state that is about to change.
# A bare negative (`! grep -q "skills:"`) passes if the tool crashes or
# prints nothing at all — it cannot tell "correctly omitted the section"
# apart from "the binary is broken". Anchor it positively: the command must
# still succeed and still print its normal release-tag line.
exec_test "pi-devbox-version --no-skills omits the skills section" \
    'out=$(pi-devbox-version --no-skills) && echo "$out" | grep -q "^pi-devbox " && ! echo "$out" | grep -q "skills:"'
exec_test "entrypoint prints the version banner with --no-skills" \
    'grep -q "pi-devbox-version --no-skills" /usr/local/bin/entrypoint-user.sh'
# The handover path itself. CI never mounts a skillset, so without this the
# v1.8.5 fix would ship untested: fabricate a skillset + a skills dir holding
# baked-style links, run the reconciler, and assert all three outcomes —
# owned skill repointed, unowned skill left baked, user override untouched.
exec_test "reconciler: owned skill handed to live clone, others untouched" \
    'set -e; t=$(mktemp -d); mkdir -p $t/ss/skills/mempalace $t/ss/skills/pi-extensions $t/skills
     echo LIVE > $t/ss/skills/mempalace/SKILL.md; echo LIVE > $t/ss/skills/pi-extensions/SKILL.md
     ln -s /usr/local/share/pi-devbox/skills/mempalace     $t/skills/mempalace
     ln -s /usr/local/share/pi-devbox/skills/pi-extensions $t/skills/pi-extensions
     mkdir -p $t/skills/mine; echo MINE > $t/skills/mine/SKILL.md
     devbox-skill-reconcile $t/ss $t/skills >/dev/null
     devbox-skill-reconcile $t/ss $t/skills >/dev/null   # idempotent
     [ "$(readlink $t/skills/mempalace)" = "$t/ss/skills/mempalace" ] || { echo "owned skill NOT repointed" >&2; exit 1; }
     [ "$(readlink $t/skills/pi-extensions)" = /usr/local/share/pi-devbox/skills/pi-extensions ] || { echo "unowned skill was repointed" >&2; exit 1; }
     [ "$(cat $t/skills/mine/SKILL.md)" = MINE ] || { echo "user override clobbered" >&2; exit 1; }
     rm -rf $t; echo ok'
# The case above cannot fail if the reconciler stops checking WHERE a link
# points — a mutation test showed all three of its assertions still passing with
# that guard deleted, which is the same false-green shape as the old snapshot
# canary. This one discriminates: an OWNED name (so it is considered) whose link
# is a user override pointing outside the baked tree (so it must be left alone).
exec_test "reconciler: user override on an owned name is left alone" \
    'set -e; t=$(mktemp -d); mkdir -p $t/ss/skills/mempalace $t/skills $t/mine-skill
     echo LIVE > $t/ss/skills/mempalace/SKILL.md; echo USERLINK > $t/mine-skill/SKILL.md
     ln -sfn $t/mine-skill $t/skills/mempalace
     devbox-skill-reconcile $t/ss $t/skills >/dev/null
     [ "$(cat $t/skills/mempalace/SKILL.md)" = USERLINK ] || { echo "user symlink override clobbered" >&2; exit 1; }
     rm -rf $t; echo ok'
# mempalace-census gained a /usr/local/bin symlink in v1.8.3; its three siblings
# had one since they were added, so this asserts the set stays complete.
exec_test "mempalace-census on PATH"               'command -v mempalace-census >/dev/null && mempalace-census --help >/dev/null && 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.
#
# Assert against the `packages` ARRAY, never a whole-file grep: the settings
# template ships a top-level "pi-fork" CONFIG block, so `grep -q pi-fork
# settings.json` passes even when `pi install /opt/pi-fork` never ran. That
# false green is exactly why the missing `fork` tool shipped unnoticed from
# v1.0.0 through v1.6.3.
pkg_registered_cmd() {
  printf "jq -e --arg n %s '(.packages // []) | any((type == \"string\") and (. == \"npm:\" + \$n or endswith(\"/\" + \$n)))' \$HOME/.pi/agent/settings.json" "$1"
}

for i in $(seq 1 15); do
  if docker exec -u developer "$CID" sh -c "$(pkg_registered_cmd pi-observational-memory)" \
       >/dev/null 2>&1; then
    break
  fi
  sleep 1
done
exec_test "pi-fork registered in packages[] (fork tool)" \
  "$(pkg_registered_cmd pi-fork)"
exec_test "pi-observational-memory registered in packages[] (recall tool)" \
  "$(pkg_registered_cmd pi-observational-memory)"

# pi-studio registration (studio variant only) — registered by the same
# entrypoint-user.sh local-path install loop as fork/obsmem.
if [ "${STUDIO_VARIANT:-0}" = "1" ]; then
  for i in $(seq 1 15); do
    if docker exec -u developer "$CID" sh -c "$(pkg_registered_cmd pi-studio)" \
         >/dev/null 2>&1; then
      break
    fi
    sleep 1
  done
  exec_test "pi-studio registered in packages[] (/studio command + studio_* tools)" \
    "$(pkg_registered_cmd pi-studio)"
fi

# pi-atelier registration. It is LAST in the entrypoint's install loop, so a
# pass here also means that loop ran to completion rather than dying midway.
for i in $(seq 1 15); do
  if docker exec -u developer "$CID" sh -c "$(pkg_registered_cmd pi-atelier)" \
       >/dev/null 2>&1; then
    break
  fi
  sleep 1
done
exec_test "pi-atelier registered in packages[] (TUI sidebar)" \
  "$(pkg_registered_cmd pi-atelier)"
# ...and registered from the vendored /opt copy, NOT as `npm:pi-atelier`: an
# npm: entry resolves through ~/.pi/npm-global on the config VOLUME, which
# outlives image upgrades and would silently keep an old, unaudited atelier —
# exactly the shape that pairs a stale 0.6.x with a new pi and hangs at startup.
exec_test "pi-atelier registered from /opt, not npm: (volume-shadowing guard)" \
  'jq -e "((.packages // []) | any((type == \"string\") and endswith(\"/pi-atelier\"))) and (((.packages // []) | any(. == \"npm:pi-atelier\")) | not)" $HOME/.pi/agent/settings.json'

# agent-browser: the third package hit by ~/.pi/npm-global volume shadowing
# (after pi itself and pi-atelier). This build-time check is deliberately WEAK
# and says so: a `docker run` container has an EMPTY config volume, so it can
# only prove the image ships a sane copy and nothing in the image itself
# shadows it. The check that actually bites lives in
# recreate-sanity-check.sh, which runs where the volume is real — that is
# where a 7-week-old 0.27.0 was caught shadowing 0.35.2 on 2026-09-06.
exec_test "agent-browser resolves under /usr (volume-shadowing guard, build-time half)" '
  p=$(command -v agent-browser) || { echo "agent-browser not on PATH" >&2; exit 1; }
  r=$(readlink -f "$p")
  echo "resolved=[$r] version=[$(agent-browser --version 2>/dev/null | head -n1)]" >&2
  case "$r" in /usr/*) ;; *) exit 1 ;; esac
  test ! -d "$HOME/.pi/npm-global/lib/node_modules/agent-browser" || exit 1
  echo ok
'

# pi-fork capability floor. `extensions: []` makes a fork child run with
# --no-extensions, which is the only MECHANICAL guarantee that a fork cannot
# file drawers or diary entries under the parent's identity — the mempalace
# bridge is an extension, so removing extensions removes the write path.
# Asserted because it is a security-shaped default that a settings merge or a
# hand-edit could silently drop, and its absence is invisible until a fork
# writes to the shared palace as you (measured twice: 2026-09-01, 2026-09-06).
# Deliberately compares to [] and not "is falsy": null means "load normal
# extensions", i.e. exactly the unguarded state this asserts against.
exec_test "pi-fork extensions floor is [] (forks cannot write to the palace)" \
  'jq -e ".[\"pi-fork\"].extensions == []" $HOME/.pi/agent/settings.json'

# ── /tmp/sshcm directory created by entrypoint ────────────────────────
exec_test "/tmp/sshcm dir mode 700 (ssh ControlMaster)" \
  'test -d /tmp/sshcm && [ "$(stat -c %a /tmp/sshcm)" = "700" ] && echo ok'

# ── Image size ────────────────────────────────────────────────────────
echo ""
echo "── Image size ──"
# Sum all layers via `docker history`. Docker's `image inspect --format='{{.Size}}'`
# returns ONLY the variant-unique layer when the base is content-addressed and
# shared (the case in this repo's two-phase build), which understates the
# user-facing image size by 2+ GB. Summing layer sizes from history is the
# metric Hub displays to users and the one we actually want to gate on.
SIZE_MB=$(docker history --format '{{.Size}}' "$IMAGE" | python3 -c '
import sys, re
total=0.0
for line in sys.stdin:
    s=line.strip()
    if s in ("0B", ""): continue
    m=re.match(r"^([0-9.]+)(B|kB|MB|GB)$", s)
    if not m: continue
    v=float(m.group(1)); u=m.group(2)
    mult={"B":1/1048576,"kB":1/1024,"MB":1,"GB":1024}[u]
    total+=v*mult
print(int(total))
')
if [ -z "$SIZE_MB" ] || [ "$SIZE_MB" = "0" ]; then
  printf "  ⚠️   image size: could not parse — skipping check\n"
elif [ "$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 ]