#!/bin/bash
#===============================================================================
# hostinstall-mode-harness.sh — GL-2 test harness for felhom-host-install.sh's
# --mode appliance|byo install profile (spec: TASK GL-2; pattern precedent:
# felhom-agent/scripts/mkfs-guarded-harness.sh).
#
# Two tiers, PASS/FAIL per case, nonzero exit on any FAIL:
#
#   STATIC tier (runs anywhere with bash + python3 — incl. a Windows Git Bash):
#     bash -n; shellcheck (if present); the argument-refusal matrix C1-C4
#     (exit nonzero + the exact die message, asserted BEFORE any host access);
#     the C6 gate's presence; grep-invariants (exactly one GATED
#     step_break_glass call site, chpasswd unreachable outside its body,
#     --mode in usage).
#
#   PVE tier (only on a PVE host as root; skips itself cleanly elsewhere):
#     C5 (byo dies naming a bogus --acl-storages entry — read-only, dies in
#     preflight before any hub contact) and the Scenario A/B dry-run transcript
#     checks. A/B need a real customer + retrieval passphrase — provide them
#     via FELHOM_TEST_CUSTOMER + FELHOM_TEST_PASSFILE (a 0600 passphrase file,
#     the script's EXISTING non-interactive path); unset -> those cases SKIP.
#
# STATE SAFETY (spec §9 rule 9): every invocation of the script under test runs
# with FELHOM_INSTALL_STATE_DIR pointed at a throwaway temp dir, so NO case can
# ever touch a live install's /var/lib/felhom-install/state.json. (Dry-run
# state helpers are additionally no-ops — this is the belt on top.)
#
# Red-proofs (spec Part 4): run the harness against a MUTATED COPY of the
# script (gate removed / requirement dropped) and watch the matching case FAIL:
#   RP-1  un-gate the step_break_glass call site  -> "break-glass call site gated" FAILs
#   RP-2  drop the byo --cores/--memory requirement -> C1 FAILs
#   RP-3  drop the resume mode-mismatch check       -> C4 FAILs
#
# Usage: hostinstall-mode-harness.sh [path-to-felhom-host-install.sh]
#===============================================================================
set -euo pipefail

SCRIPT="${1:-$(dirname "$0")/felhom-host-install.sh}"
[[ -r "$SCRIPT" ]] || { echo "no script under test at $SCRIPT" >&2; exit 2; }
command -v python3 >/dev/null || { echo "python3 required (the script's state helpers use it)" >&2; exit 2; }

pass=0; fail=0; skip=0
verdict() { # PASS|FAIL|SKIP <name> [detail]
    local v="$1" name="$2" detail="${3:-}"
    case "$v" in
        PASS) pass=$((pass+1)) ;;
        FAIL) fail=$((fail+1)) ;;
        SKIP) skip=$((skip+1)) ;;
    esac
    printf '%-4s %s\n' "$v" "$name"
    [[ -n "$detail" ]] && printf '     %s\n' "$detail"
    return 0
}

# Throwaway state dir for EVERY run of the script under test (never the live one). On Git Bash the
# script's python3 may be a native Windows build — hand it a Windows-syntax path via cygpath -m.
WORK="$(mktemp -d "${TMPDIR:-/tmp}/hostinstall-harness.XXXXXX")"
trap 'rm -rf "$WORK"' EXIT
STATE_OVERRIDE="$WORK/state"
mkdir -p "$STATE_OVERRIDE"
if command -v cygpath >/dev/null 2>&1; then
    STATE_OVERRIDE_ENV="$(cygpath -m "$STATE_OVERRIDE")"
else
    STATE_OVERRIDE_ENV="$STATE_OVERRIDE"
fi

# run_script <args...> — run the script under test with the state override; captures stdout+stderr
# into $out and the exit code into $rc. Never lets a nonzero rc kill the harness.
out=""; rc=0
run_script() {
    set +e
    out=$(FELHOM_INSTALL_STATE_DIR="$STATE_OVERRIDE_ENV" bash "$SCRIPT" "$@" 2>&1)
    rc=$?
    set -e
}

# expect_die <name> <msg-substr> -- <args...> — the script must exit nonzero AND print msg-substr.
expect_die() {
    local name="$1" msg="$2"; shift 2
    [[ "${1:-}" == "--" ]] && shift
    run_script "$@"
    if [[ $rc -ne 0 && "$out" == *"$msg"* ]]; then
        verdict PASS "$name"
    else
        verdict FAIL "$name" "rc=$rc; wanted substring: '$msg'; got: $(echo "$out" | tail -3 | tr '\n' ' ')"
    fi
}

echo "=== hostinstall-mode-harness — script under test: $SCRIPT ==="
echo ""
echo "--- STATIC tier ---"

# S1: syntax
if bash -n "$SCRIPT" 2>"$WORK/bashn.err"; then
    verdict PASS "bash -n"
else
    verdict FAIL "bash -n" "$(cat "$WORK/bashn.err")"
fi

# S2: shellcheck (best-effort — required by the green gate, but the harness itself degrades)
if command -v shellcheck >/dev/null 2>&1; then
    if shellcheck --shell=bash --severity=warning "$SCRIPT" >"$WORK/sc.out" 2>&1; then
        verdict PASS "shellcheck (severity>=warning)"
    else
        verdict FAIL "shellcheck (severity>=warning)" "$(head -5 "$WORK/sc.out")"
    fi
else
    verdict SKIP "shellcheck" "not installed here — run it on the build server (green gate still requires it)"
fi

# C1: byo without --cores/--memory refuses (both missing, and each alone)
expect_die "C1  byo without caps refused" \
    "byo mode requires explicit --cores and --memory" \
    -- --customer-id t --mode byo
expect_die "C1b byo with only --cores refused" \
    "byo mode requires explicit --cores and --memory" \
    -- --customer-id t --mode byo --cores 4
expect_die "C1c byo with only --memory refused" \
    "byo mode requires explicit --cores and --memory" \
    -- --customer-id t --mode byo --memory 8192

# C2: byo refuses --enable-oob / --rotate-recovery, naming the flag
expect_die "C2a byo --enable-oob refused" \
    "--enable-oob is not allowed in byo mode" \
    -- --customer-id t --mode byo --cores 4 --memory 8192 --enable-oob
expect_die "C2b byo --rotate-recovery refused" \
    "--rotate-recovery is not allowed in byo mode" \
    -- --customer-id t --mode byo --cores 4 --memory 8192 --rotate-recovery

# C3: fresh install without --mode refuses, naming both modes
expect_die "C3  fresh install without --mode refused" \
    "--mode is required: pass --mode appliance" \
    -- --customer-id t
expect_die "C3b unknown --mode refused" \
    "Unknown --mode: bogus (appliance|byo)" \
    -- --customer-id t --mode bogus
expect_die "C3c retired --mode provision refused" \
    "--mode provision was retired" \
    -- --customer-id t --mode provision

# C4: --resume with a state.json recording the OTHER mode refuses
printf '{"completed":["preflight"],"customer_id":"t","mode":"appliance"}\n' > "$STATE_OVERRIDE/state.json"
expect_die "C4  resume mode-mismatch refused" \
    "install started as appliance; resume with --mode appliance or start over" \
    -- --customer-id t --mode byo --cores 4 --memory 8192 --resume
rm -f "$STATE_OVERRIDE/state.json"

# C6 (static shape): the byo PVE-major gate + its message exist (a non-9.x host isn't available)
if grep -q 'byo mode is validated on PVE 9.x only' "$SCRIPT" \
   && grep -B3 'byo mode is validated on PVE 9.x only' "$SCRIPT" | grep -q 'MODE" == "byo"'; then
    verdict PASS "C6  byo PVE-major gate present (static grep)"
else
    verdict FAIL "C6  byo PVE-major gate present (static grep)"
fi

# INV-1: exactly ONE step_break_glass invocation, and it is gated on MODE == appliance.
#        (Comment lines and the function definition itself don't count.)
inv_calls=$(grep -n 'step_break_glass' "$SCRIPT" \
    | grep -v -E '^[0-9]+:[[:space:]]*#' \
    | grep -v 'step_break_glass()' || true)
inv_count=$(echo "$inv_calls" | grep -c 'step_break_glass' || true)
if [[ "$inv_count" == "1" ]] \
   && echo "$inv_calls" | grep -q 'should_skip break_glass' \
   && grep -B4 'should_skip break_glass' "$SCRIPT" | grep -q 'MODE" == "appliance"'; then
    verdict PASS "INV-1 break-glass call site: exactly one, appliance-gated"
else
    verdict FAIL "INV-1 break-glass call site: exactly one, appliance-gated" "count=$inv_count; calls: $(echo "$inv_calls" | tr '\n' ' ')"
fi

# INV-2: chpasswd is unreachable outside step_break_glass's body (non-comment occurrences only).
body=$(awk '/^step_break_glass\(\)/{s=NR} s && /^\}/{print s, NR; exit}' "$SCRIPT")
bstart=${body% *}; bend=${body#* }
inv2_ok=true
while IFS=: read -r ln _; do
    [[ -z "$ln" ]] && continue
    if [[ "$ln" -lt "$bstart" || "$ln" -gt "$bend" ]]; then inv2_ok=false; fi
done < <(grep -n 'chpasswd' "$SCRIPT" | grep -v -E '^[0-9]+:[[:space:]]*#' || true)
if [[ -n "$bstart" && -n "$bend" ]] && $inv2_ok; then
    verdict PASS "INV-2 chpasswd unreachable outside step_break_glass ($bstart-$bend)"
else
    verdict FAIL "INV-2 chpasswd unreachable outside step_break_glass" "body=$bstart-$bend"
fi

# INV-3: --mode is documented in usage (run the real -h path)
run_script -h
if [[ $rc -eq 0 && "$out" == *"--mode appliance|byo"* ]]; then
    verdict PASS "INV-3 usage documents --mode appliance|byo"
else
    verdict FAIL "INV-3 usage documents --mode appliance|byo" "rc=$rc"
fi

echo ""
echo "--- GL-4 static tier (key-pin + uninstall parity) ---"

# GL4-C3: --operator-pubkey-file refusals (each dies at argv-validation, before any host access).
GOODKEY="ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFakeFakeFakeFakeFakeFakeFakeFakeFakeFakeFake felhom-op-1"
printf 'signer %s\n' "$GOODKEY" > "$WORK/keys-badrole"
expect_die "GL4-C3a key file: unknown role refused" \
    "unknown role 'signer' (want operational|recovery)" \
    -- --customer-id t --mode appliance --operator-pubkey-file "$WORK/keys-badrole"
printf 'operational not-a-key-at-all\n' > "$WORK/keys-badline"
expect_die "GL4-C3b key file: non-authorized_keys line refused" \
    "not an authorized_keys line" \
    -- --customer-id t --mode appliance --operator-pubkey-file "$WORK/keys-badline"
printf 'operational ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFakeFakeFake\n' > "$WORK/keys-nocomment"
expect_die "GL4-C3c key file: missing key_id comment refused" \
    "no comment field" \
    -- --customer-id t --mode appliance --operator-pubkey-file "$WORK/keys-nocomment"
printf '# only a comment\n\n' > "$WORK/keys-empty"
expect_die "GL4-C3d key file: empty file refused" \
    "has no key lines" \
    -- --customer-id t --mode appliance --operator-pubkey-file "$WORK/keys-empty"
expect_die "GL4-C3e key file: missing file refused" \
    "--operator-pubkey-file not found" \
    -- --customer-id t --mode appliance --operator-pubkey-file "$WORK/keys-nonexistent"

# GL4-C2 (positive shape, runtime): a VALID key file passes resolution — the script must die LATER
# (root/pveum/hub preflight, machine-dependent) and NEVER with a key-file error.
printf 'operational %s\nrecovery ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFakeFakeRecovery felhom-rec-1\n' "$GOODKEY" > "$WORK/keys-good"
run_script --customer-id t --mode appliance --operator-pubkey-file "$WORK/keys-good" --hub-url https://127.0.0.1:9
if [[ $rc -ne 0 && "$out" != *"--operator-pubkey-file"*  && "$out" != *"authorized_keys line"* && "$out" != *"unknown role"* ]]; then
    verdict PASS "GL4-C2  valid key file accepted (dies later, not at key parse)"
else
    verdict FAIL "GL4-C2  valid key file accepted" "rc=$rc; $(echo "$out" | tail -2 | tr '\n' ' ')"
fi

# GL4-C4/C5 (grep shapes): the write-guard + override mechanics exist in the script text.
if grep -q '^if signers:$' "$SCRIPT" && grep -q "replacing %d preserved authz signer" "$SCRIPT"; then
    verdict PASS "GL4-C4  signers-only-when-nonempty guard + preserve/replace notice present"
else
    verdict FAIL "GL4-C4  signers-only-when-nonempty guard + preserve/replace notice present"
fi
if grep -q 'overrides the script.s built-in operator key constants' "$SCRIPT" \
   && grep -q 'RESOLVED_OP_ID=""; RESOLVED_OP_LINE=""; RESOLVED_REC_ID=""; RESOLVED_REC_LINE=""' "$SCRIPT"; then
    verdict PASS "GL4-C5  file-overrides-constants mechanics present (notice + reset)"
else
    verdict FAIL "GL4-C5  file-overrides-constants mechanics present"
fi
if grep -q 'no operator key pinned' "$SCRIPT" && grep -B1 'no operator key pinned' "$SCRIPT" | grep -q 'log_warn'; then
    verdict PASS "GL4-C1  verify dormant path is a WARN (not an error)"
else
    verdict FAIL "GL4-C1  verify dormant path is a WARN (not an error)"
fi

# GL4-D: disclosure↔uninstall parity — every host artifact the byo disclosure names must be covered
# (removed or explicitly KEPT) in the uninstall section (_guest_drive_note.._end of run_uninstall).
ustart=$(grep -n '^_guest_drive_note()' "$SCRIPT" | cut -d: -f1)
uend=$(grep -n '^# run_adopt_pool' "$SCRIPT" | cut -d: -f1)
if [[ -n "$ustart" && -n "$uend" && "$ustart" -lt "$uend" ]]; then
    usect=$(sed -n "${ustart},${uend}p" "$SCRIPT")
    d_missing=""
    for tok in 'felhom-selfupdate-guarded' 'felhom-agent-rollback.service' 'felhom-agent-limits.conf' \
               '.prev' 'felhom-mgmt-watchdog' 'felhom-privsep.conf' 'felhom-mkfs-guarded' \
               'felhom-guest-hook' '/mnt/felhom-drives' 'AGENT_SUDOERS' 'AGENT_STATE_DIR' \
               'remove_scoped_acl' 'pveum user token remove' 'pveum pool delete' 'STATE_FILE'; do
        echo "$usect" | grep -qF "$tok" || d_missing+="$tok "
    done
    if [[ -z "$d_missing" ]]; then
        verdict PASS "GL4-D   disclosure↔uninstall parity (all artifact tokens covered)"
    else
        verdict FAIL "GL4-D   disclosure↔uninstall parity" "uncovered: $d_missing"
    fi
else
    verdict FAIL "GL4-D   disclosure↔uninstall parity" "could not locate the uninstall section"
fi

# GL4-INV: no forced/lazy unmount and no format op on the drives root — REAL invocations only
# (comment lines and log_* guidance strings legitimately SAY "never umount -l/-f").
if ! grep -vE '^[[:space:]]*#|log_(warn|info|dry|error|success|skip)' "$SCRIPT" | grep -E 'umount +-(l|f)' >/dev/null \
   && ! grep -vE '^[[:space:]]*#' "$SCRIPT" | grep -E '(mkfs|wipefs) [^|]*/mnt/felhom-drives' >/dev/null; then
    verdict PASS "GL4-INV no umount -l/-f, no mkfs/wipefs invocation on /mnt/felhom-drives"
else
    verdict FAIL "GL4-INV no umount -l/-f, no mkfs/wipefs invocation on /mnt/felhom-drives"
fi

echo ""
echo "--- PVE tier ---"
if ! command -v pveum >/dev/null 2>&1 || [[ "$(id -u)" != 0 ]]; then
    verdict SKIP "PVE tier (C5 + Scenario A/B dry transcripts)" "needs a PVE host as root — run there"
else
    # C5: byo with a bogus --acl-storages entry dies in preflight NAMING it (read-only: dies before
    # any hub contact/passphrase and before any mutation; state override active).
    expect_die "C5  byo bogus --acl-storages refused, named" \
        "acl storage(s) not found on this box: definitely-not-a-storage" \
        -- --customer-id t --mode byo --cores 4 --memory 8192 \
           --acl-storages "local definitely-not-a-storage" --dry-run

    # GL4 H-U: FULL uninstall dry transcript (Scenario A). Read-only: every mutation is dry-printed,
    # the typed confirm takes its dry branch, and the state override keeps the live state.json out.
    # Requires a Felhom guest to target — resolved from felhom_guests-style detection below.
    hu_vmid=$(for id in $( { pct list 2>/dev/null; qm list 2>/dev/null; } | awk "{print \$1}" | grep -E "^[0-9]+$" ); do
        pct config "$id" 2>/dev/null | grep -q "mp=/etc/felhom-bootstrap" && { echo "$id"; break; }
    done)
    if [[ -z "$hu_vmid" ]]; then
        verdict SKIP "GL4 H-U uninstall dry transcript" "no Felhom guest on this host to target"
    else
        run_script --uninstall --vmid "$hu_vmid" --dry-run
        hu_ok=true; hu_why=""
        [[ $rc -eq 0 ]] || { hu_ok=false; hu_why+="rc=$rc "; }
        for want in "felhom-selfupdate-guarded" "kept vs wiped" "NEVER wiped"; do
            [[ "$out" == *"$want"* ]] || { hu_ok=false; hu_why+="missing '$want' "; }
        done
        # MUST NOT: forced/lazy unmounts, or ANY destructive op (mkfs/wipefs/rm) on a drive-data
        # path. Removing the felhom-mkfs-guarded WRAPPER from /usr/local/sbin is legitimate.
        for bad in "umount -l" "umount -f"; do
            [[ "$out" != *"$bad"* ]] || { hu_ok=false; hu_why+="contains '$bad' "; }
        done
        if echo "$out" | grep -E '(mkfs|wipefs|rm |rm -rf).*/mnt/felhom-drives/' >/dev/null; then
            hu_ok=false; hu_why+="destructive op on a /mnt/felhom-drives/ path "
        fi
        # drive umount lines only when child mounts exist — assert conditionally
        if findmnt -rn -o TARGET 2>/dev/null | grep -q '^/mnt/felhom-drives/'; then
            [[ "$out" == *"data stays on the drive"* ]] || { hu_ok=false; hu_why+="missing per-drive umount lines "; }
        fi
        if $hu_ok; then
            verdict PASS "GL4 H-U uninstall dry transcript (guest $hu_vmid; statement + selfupdate removal, no forced ops)"
        else
            verdict FAIL "GL4 H-U uninstall dry transcript" "$hu_why"
        fi
    fi

    if [[ -n "${FELHOM_TEST_CUSTOMER:-}" && -n "${FELHOM_TEST_PASSFILE:-}" && -r "${FELHOM_TEST_PASSFILE:-}" ]]; then
        common=(--customer-id "$FELHOM_TEST_CUSTOMER" --passphrase-file "$FELHOM_TEST_PASSFILE" \
                --vmid 990100 --cores 2 --memory 4096 --dry-run)
        # H-A: appliance dry transcript still walks 4b/8 (regression guard)
        run_script --mode appliance "${common[@]}"
        if [[ $rc -eq 0 && "$out" == *"4b/8"* ]]; then
            verdict PASS "H-A appliance dry transcript contains 4b/8"
        else
            verdict FAIL "H-A appliance dry transcript contains 4b/8" "rc=$rc"
        fi
        # H-B: byo dry transcript — no 4b/8 / chpasswd / recovery-credential; ack + caps + storages present
        run_script --mode byo "${common[@]}"
        hb_ok=true; hb_why=""
        [[ $rc -eq 0 ]] || { hb_ok=false; hb_why+="rc=$rc "; }
        for bad in "4b/8" "chpasswd" "recovery-credential"; do
            [[ "$out" != *"$bad"* ]] || { hb_ok=false; hb_why+="contains '$bad' "; }
        done
        for want in "acknowledge the byo install" "acl storages all present" "-cores 2 -memory 4096" "self-update authority"; do
            [[ "$out" == *"$want"* ]] || { hb_ok=false; hb_why+="missing '$want' "; }
        done
        if $hb_ok; then
            verdict PASS "H-B byo dry transcript (no root@pam path; ack+caps+storages present)"
        else
            verdict FAIL "H-B byo dry transcript" "$hb_why"
        fi
    else
        verdict SKIP "H-A/H-B dry transcripts" "set FELHOM_TEST_CUSTOMER + FELHOM_TEST_PASSFILE (0600 passphrase file) to run"
    fi
fi

echo ""
echo "=== $pass passed, $fail failed, $skip skipped ==="
[[ $fail -eq 0 ]]