#!/usr/bin/env bash
#
# scripts/smoke.sh — end-to-end smoke suite for banger.
#
# Drives a real create → start → ssh → exec → delete cycle against
# real Firecracker + real KVM on the host. Intended as a pre-release
# gate: the Go unit + integration tests don't and can't cover the
# post-machine.Start path (socket ownership, guest boot, vsock agent
# wait, guest SSH, workspace prepare). If this suite fails, don't
# ship.
#
# State lives under $BANGER_SMOKE_XDG_DIR (set by `make smoke`,
# defaults to build/smoke/xdg). It's ISOLATED from the invoking
# user's real banger install via XDG_{CONFIG,STATE,CACHE,RUNTIME}
# overrides, but PERSISTED across runs — so the first smoke pulls
# the golden image, subsequent smokes reuse it. `make smoke-clean`
# wipes it.
#
# Invoked via `make smoke`, which sets the three env vars below.
# Don't run this directly unless you know they're set.

set -euo pipefail

log() { printf '[smoke] %s\n' "$*" >&2; }
die() { printf '[smoke] FAIL: %s\n' "$*" >&2; exit 1; }

# wait_for_ssh polls `vm ssh <vm> -- true` until it succeeds or the
# timeout expires. `vm ssh` — unlike `vm run` — does not itself wait
# for guest sshd, so scenarios that call `vm create` / `vm start`
# back-to-back with `vm ssh` need this shim. 60s matches
# vmRunSSHTimeout.
wait_for_ssh() {
  local vm="$1"
  local deadline=$(( $(date +%s) + 60 ))
  while (( $(date +%s) < deadline )); do
    if "$BANGER" vm ssh "$vm" -- true >/dev/null 2>&1; then
      return 0
    fi
    sleep 1
  done
  return 1
}

: "${BANGER_SMOKE_BIN_DIR:?must point at the instrumented binary dir, set by make smoke}"
: "${BANGER_SMOKE_COVER_DIR:?must point at the coverage dir, set by make smoke}"
: "${BANGER_SMOKE_XDG_DIR:?must point at the isolated XDG root, set by make smoke}"

BANGER="$BANGER_SMOKE_BIN_DIR/banger"
BANGERD="$BANGER_SMOKE_BIN_DIR/bangerd"
VSOCK_AGENT="$BANGER_SMOKE_BIN_DIR/banger-vsock-agent"

for bin in "$BANGER" "$BANGERD" "$VSOCK_AGENT"; do
  [[ -x "$bin" ]] || die "binary missing or not executable: $bin"
done

# Persistent XDG dirs (state, cache, config) so repeated smoke
# runs reuse the pulled golden image instead of re-downloading
# ~300MB each time. Runtime dir needs to be fresh per-run because
# it holds sockets the daemon cleans up on stop and refuses to
# reuse if any are stale.
mkdir -p \
  "$BANGER_SMOKE_XDG_DIR/config" \
  "$BANGER_SMOKE_XDG_DIR/state" \
  "$BANGER_SMOKE_XDG_DIR/cache"
runtime_dir="$(mktemp -d -t banger-smoke-runtime-XXXXXX)"
# shellcheck disable=SC2064
trap "rm -rf '$runtime_dir'" EXIT
chmod 0700 "$runtime_dir"

export XDG_CONFIG_HOME="$BANGER_SMOKE_XDG_DIR/config"
export XDG_STATE_HOME="$BANGER_SMOKE_XDG_DIR/state"
export XDG_CACHE_HOME="$BANGER_SMOKE_XDG_DIR/cache"
export XDG_RUNTIME_DIR="$runtime_dir"

# Point banger at its companion binaries inside the smoke build.
export BANGER_DAEMON_BIN="$BANGERD"
export BANGER_VSOCK_AGENT_BIN="$VSOCK_AGENT"

# Instrumented binaries dump coverage here on clean exit.
export GOCOVERDIR="$BANGER_SMOKE_COVER_DIR"
mkdir -p "$GOCOVERDIR"

# Any smoke daemon left behind from a prior run that crashed mid-
# scenario would reuse the stale socket path and confuse
# ensureDaemon. Best-effort stop; ignore if nothing is running.
"$BANGER" daemon stop >/dev/null 2>&1 || true

# banger's vmDNS binds 127.0.0.1:42069 (UDP) hard. If the user's
# real (non-smoke) daemon is running, its listener holds the port
# and the smoke daemon's Open() fails before any scenario runs.
# Fail fast with an actionable message — don't guess whether to
# stop the user's daemon for them.
if command -v ss >/dev/null 2>&1 && ss -Huln 2>/dev/null | awk '{print $4}' | grep -q '[:.]42069$'; then
  die 'port 127.0.0.1:42069 is already bound (likely your real banger daemon); stop it with `banger daemon stop` and re-run `make smoke`'
fi

# --- doctor -----------------------------------------------------------
log 'doctor: checking host readiness'
if ! "$BANGER" doctor; then
  die 'doctor reported failures; fix the host before running smoke'
fi

# --- bare vm run ------------------------------------------------------
log "bare vm run: create + start + ssh + exec 'echo smoke-bare-ok' + --rm"
bare_out="$("$BANGER" vm run --rm -- echo smoke-bare-ok)" || die "bare vm run exit $?"
grep -q 'smoke-bare-ok' <<<"$bare_out" || die "bare vm run stdout missing marker: $bare_out"

# --- workspace vm run -------------------------------------------------
log 'workspace vm run: preparing a throwaway git repo'
repodir="$runtime_dir/fake-repo"
mkdir -p "$repodir"
(
  cd "$repodir"
  git init -q -b main
  git config commit.gpgsign false
  git config user.name smoke
  git config user.email smoke@smoke
  echo 'smoke-workspace-marker' > smoke-file.txt
  git add .
  git commit -q -m init
)

log "workspace vm run: create + start + workspace prepare + cat guest file + --rm"
ws_out="$("$BANGER" vm run --rm "$repodir" -- cat /root/repo/smoke-file.txt)" || die "workspace vm run exit $?"
grep -q 'smoke-workspace-marker' <<<"$ws_out" || die "workspace vm run didn't ship smoke-file.txt: $ws_out"

# --- command exit-code propagation ------------------------------------
# A non-zero exit from the guest command must surface as banger's own
# exit code. Regressions here are hard to catch any other way — the
# local Go tests don't cross the SSH boundary, and users expect their
# CI scripts that wrap `banger vm run` to fail when the thing inside
# the VM failed.
log 'exit-code propagation: guest `sh -c "exit 42"` must produce rc=42'
set +e
"$BANGER" vm run --rm -- sh -c 'exit 42'
rc=$?
set -e
[[ "$rc" -eq 42 ]] || die "exit-code propagation: got rc=$rc, want 42"

# --- workspace dry-run (no VM) ----------------------------------------
# Pure CLI-side path — no VM, no sudo, just the local git inspection
# against d.repoInspector. Fast; catches regressions in the preview
# output (file list shape, mode line) that the Go tests already pin
# but that could still be broken by a client-side wiring change.
log 'workspace dry-run: list tracked files without creating a VM'
dry_out="$("$BANGER" vm run --dry-run "$repodir")" || die "dry-run exit $?"
grep -q 'smoke-file.txt' <<<"$dry_out" || die "dry-run didn't list smoke-file.txt: $dry_out"
grep -q 'mode: tracked only' <<<"$dry_out" || die "dry-run mode line missing or wrong: $dry_out"

# --- workspace --include-untracked -----------------------------------
# The default is tracked-only (review cycle 4). Opt-in must ship
# untracked files too. Write one, run with --include-untracked, verify
# it reaches the guest.
log 'workspace --include-untracked: opt-in ships files outside the git index'
echo 'untracked-marker' > "$repodir/smoke-untracked.txt"
inc_out="$("$BANGER" vm run --rm --include-untracked "$repodir" -- cat /root/repo/smoke-untracked.txt)" || die "include-untracked vm run exit $?"
grep -q 'untracked-marker' <<<"$inc_out" || die "--include-untracked didn't ship the untracked file: $inc_out"
# Restore repo to tracked-only state for any later scenarios.
rm -f "$repodir/smoke-untracked.txt"

# --- workspace export round-trip --------------------------------------
# Exercises ExportVMWorkspace: create a VM, prepare the workspace,
# write a new file inside the guest, then export and assert the
# emitted patch sees the guest-side change. If the export pipeline
# (temp-index, git add -A, diff --binary) ever stops capturing
# guest-side changes, this scenario catches it.
log 'workspace export: create + prepare + guest edit + export + assert marker'
export_vm='smoke-export'
cleanup_export_vm() {
  "$BANGER" vm delete "$export_vm" >/dev/null 2>&1 || true
}
# Chain the VM cleanup with the existing runtime_dir trap so a mid-
# scenario failure still tears the VM down before the script exits.
# shellcheck disable=SC2064
trap "cleanup_export_vm; rm -rf '$runtime_dir'" EXIT

"$BANGER" vm create --name "$export_vm" --image debian-bookworm >/dev/null \
  || die "export: vm create exit $?"
"$BANGER" vm workspace prepare "$export_vm" "$repodir" >/dev/null \
  || die "export: workspace prepare exit $?"
"$BANGER" vm ssh "$export_vm" -- sh -c 'echo guest-edit > /root/repo/new-guest-file.txt' \
  || die "export: guest-side file write exit $?"
export_patch="$runtime_dir/smoke-export.diff"
"$BANGER" vm workspace export "$export_vm" --output "$export_patch" \
  || die "export: workspace export exit $?"
[[ -s "$export_patch" ]] || die "export: patch file empty at $export_patch"
grep -q 'new-guest-file.txt' "$export_patch" \
  || die "export: patch missing new-guest-file.txt marker (head: $(head -c 400 "$export_patch"))"

cleanup_export_vm
# shellcheck disable=SC2064
trap "rm -rf '$runtime_dir'" EXIT

# --- concurrent vm runs -----------------------------------------------
# Stresses per-VM lock scoping, the tap pool warm-up path, and
# createVMMu's narrow reservation window. Two `vm run --rm` invocations
# that actually overlap should both succeed. A regression that
# serialises create path too aggressively would make this slow but
# still pass; a regression that breaks tap allocation or name
# uniqueness would fail one of them.
log 'concurrent vm runs: two --rm invocations must both succeed'
tmpA="$runtime_dir/concurrent-a.out"
tmpB="$runtime_dir/concurrent-b.out"
"$BANGER" vm run --rm -- echo smoke-concurrent-a > "$tmpA" 2>&1 &
pidA=$!
"$BANGER" vm run --rm -- echo smoke-concurrent-b > "$tmpB" 2>&1 &
pidB=$!
wait "$pidA" || die "concurrent VM A exited non-zero: $(cat "$tmpA")"
wait "$pidB" || die "concurrent VM B exited non-zero: $(cat "$tmpB")"
grep -q 'smoke-concurrent-a' "$tmpA" || die "concurrent VM A missing marker: $(cat "$tmpA")"
grep -q 'smoke-concurrent-b' "$tmpB" || die "concurrent VM B missing marker: $(cat "$tmpB")"

# --- vm lifecycle (create → stop → start → delete) --------------------
# Exercises lifecycle verbs directly instead of the --rm convenience
# path. The critical assertion is the second `vm ssh` AFTER stop/start:
# that path (a) rebuilds the handle cache via rediscoverHandles,
# (b) runs the e2fsck-snapshot sanitize step before patchRootOverlay
# on the dirty COW, and (c) shouldn't die from the SDK's
# ctx-SIGTERM-on-RPC-close goroutine. All three were bugs at one
# point; this scenario guards all three at once.
log 'vm lifecycle: explicit create / stop / start / ssh / delete'
lifecycle_name=smoke-lifecycle
# shellcheck disable=SC2064
trap "\"$BANGER\" vm delete $lifecycle_name >/dev/null 2>&1 || true; rm -rf '$runtime_dir'" EXIT

"$BANGER" vm create --name "$lifecycle_name" >/dev/null || die "vm create $lifecycle_name failed"
show_out="$("$BANGER" vm show "$lifecycle_name")" || die "vm show after create failed"
grep -q '"state": "running"' <<<"$show_out" || die "post-create state not running: $show_out"

wait_for_ssh "$lifecycle_name" || die 'vm lifecycle: ssh did not come up after create'
ssh_out="$("$BANGER" vm ssh "$lifecycle_name" -- echo hello-1)" || die "vm ssh #1 failed"
grep -q 'hello-1' <<<"$ssh_out" || die "vm ssh #1 missing marker: $ssh_out"

"$BANGER" vm stop "$lifecycle_name" >/dev/null || die "vm stop failed"
show_out="$("$BANGER" vm show "$lifecycle_name")" || die "vm show after stop failed"
grep -q '"state": "stopped"' <<<"$show_out" || die "post-stop state not stopped: $show_out"

"$BANGER" vm start "$lifecycle_name" >/dev/null || die "vm start (from stopped) failed"
show_out="$("$BANGER" vm show "$lifecycle_name")" || die "vm show after start failed"
grep -q '"state": "running"' <<<"$show_out" || die "post-start state not running: $show_out"

wait_for_ssh "$lifecycle_name" || die 'vm lifecycle: ssh did not come up after restart'
ssh_out="$("$BANGER" vm ssh "$lifecycle_name" -- echo hello-2)" || die "vm ssh #2 (post-restart) failed"
grep -q 'hello-2' <<<"$ssh_out" || die "vm ssh #2 missing marker: $ssh_out"

"$BANGER" vm delete "$lifecycle_name" >/dev/null || die "vm delete failed"
set +e
"$BANGER" vm show "$lifecycle_name" >/dev/null 2>&1
rc=$?
set -e
[[ "$rc" -ne 0 ]] || die "vm show still finds $lifecycle_name after delete"
# shellcheck disable=SC2064
trap "rm -rf '$runtime_dir'" EXIT

# --- vm set reconfiguration (vcpu change + restart) -------------------
# Exercises SetVM + configChangeCapability. Create with --vcpu 2,
# stop, `vm set --vcpu 4`, restart, confirm the guest sees the new
# count. Regression guard: a restart that reuses the pre-change spec
# would leave nproc at 2.
log 'vm set: create --vcpu 2 → stop → set --vcpu 4 → restart → nproc=4'
# shellcheck disable=SC2064
trap "\"$BANGER\" vm delete smoke-set >/dev/null 2>&1 || true; rm -rf '$runtime_dir'" EXIT

"$BANGER" vm create --name smoke-set --vcpu 2 >/dev/null || die 'vm set: create failed'
wait_for_ssh smoke-set || die 'vm set: initial ssh did not come up'

set +e
nproc_before="$("$BANGER" vm ssh smoke-set -- nproc 2>/dev/null)"
rc=$?
set -e
[[ "$rc" -eq 0 ]] || die "vm set: initial nproc ssh exit $rc"
[[ "$(printf '%s' "$nproc_before" | tr -d '[:space:]')" == "2" ]] \
  || die "vm set: initial nproc got '$nproc_before', want 2"

"$BANGER" vm stop smoke-set >/dev/null || die 'vm set: stop failed'
"$BANGER" vm set smoke-set --vcpu 4 >/dev/null || die 'vm set: reconfigure failed'
"$BANGER" vm start smoke-set >/dev/null || die 'vm set: restart failed'
wait_for_ssh smoke-set || die 'vm set: post-reconfig ssh did not come up'

set +e
nproc_after="$("$BANGER" vm ssh smoke-set -- nproc 2>/dev/null)"
rc=$?
set -e
[[ "$rc" -eq 0 ]] || die "vm set: post-reconfig nproc ssh exit $rc"
[[ "$(printf '%s' "$nproc_after" | tr -d '[:space:]')" == "4" ]] \
  || die "vm set: post-reconfig nproc got '$nproc_after', want 4 (spec change didn't land)"

"$BANGER" vm delete smoke-set >/dev/null || die 'vm set: delete failed'
# shellcheck disable=SC2064
trap "rm -rf '$runtime_dir'" EXIT

# --- invalid spec rejection + no artifact leak ------------------------
# Tests the negative-path create flow: a blatantly invalid VM spec
# must fail before any VM row is persisted. The review cycle flagged
# "cleanup on partial failure" as under-tested; this scenario pins
# that a rejected create doesn't leak a reservation we then have to
# clean up by hand.
log 'invalid spec rejection: --vcpu 0 must fail and leave no VM behind'
pre_vms="$("$BANGER" vm list --all 2>/dev/null | wc -l)"
set +e
"$BANGER" vm run --rm --vcpu 0 -- echo unused >/dev/null 2>&1
rc=$?
set -e
[[ "$rc" -ne 0 ]] || die 'invalid spec: vm run succeeded despite --vcpu 0'
post_vms="$("$BANGER" vm list --all 2>/dev/null | wc -l)"
[[ "$pre_vms" == "$post_vms" ]] || die "invalid spec leaked a VM row: pre=$pre_vms, post=$post_vms"

# --- daemon stop (flushes coverage) -----------------------------------
log 'stopping daemon so instrumented binaries flush coverage'
"$BANGER" daemon stop >/dev/null 2>&1 || true
# Give the daemon a moment to write its covdata pod before the trap
# tears down runtime_dir.
sleep 0.5

log 'all scenarios passed'