fleetd/scripts/config-edit.sh

#!/usr/bin/env bash
#
# The one auditable way to edit the live fleetd.yaml.
#
# fleetd ticket #635 — why this exists at all: fleetd.yaml is gitignored and holds the live
# fleet's settings. A bad raw edit reaches a daemon that is already serving, so a direct `Edit`
# on it is refused by policy. This script is the allow-listed alternative, and it is not just
# convenience — it is the thing a raw file write can never give you: a backup, a parse check
# BEFORE the file is installed, and the daemon's own reload verdict read back afterwards. An
# edit to a live config is not finished when the bytes are written. It is finished when the
# daemon has said what it did with them.
#
# What the daemon says, and how this script finds it — measured against `ConfigRef.java` on
# fleetd commit 158a2a8, 2026-10-01:
#
#   1. `ConfigRef` re-reads fleetd.yaml only when the WATCHER sees the mtime move (every 10s by
#      default — read the real interval out of the daemon's own startup line, "config watch: ...
#      re-read when it changes (every Ns)"). So a verdict never appears before the next tick.
#   2. `ConfigRef.Outcome.summary()` logs exactly one of five strings (ConfigRef.java:371-391):
#        config reload refused — <error message>
#        config reload refused — these keys cannot change under a running daemon: <keys>. ...
#        config reloaded
#        config reloaded; these changes need a restart to take effect: <keys>
#        config reloaded; partially live — <key: detail | ...>
#      A parse/validation failure logs a DIFFERENT line instead, before any summary ever runs
#      (ConfigRef.java:425): "config reload from <path> refused, keeping the running config:
#      <message>". This script recognises both shapes of refusal.
#   3. The em dash in those strings is a real multi-byte character — match the stable prefix
#      "config reload refused" (or "...refused, keeping the running config" for the parse-failure
#      shape), never the dash itself.
#   4. A cold-key change (bind/herdrSocket/memberHerdrSocket/broker/auth) throws away the WHOLE
#      reload — the running config keeps every old value, not only the cold one.
#   5. A deferred/split change IS applied (current.set(fresh) runs) — "needs a restart" is a
#      SUCCESS with a follow-up, never a failure.
#
# Four outcomes, and they stay four (see the exit code table below). The one most likely to be
# gotten wrong is "cannot tell" (exit 5): the daemon may be down, or the watcher may be stalled,
# and folding that into either "refused" or "applied" is worse than never checking at all,
# because a caller then acts on a verdict nobody actually read. So exit 5 never restores — a
# visible, recoverable edit beats an invisible revert of a GOOD edit.
#
# Usage:
#   scripts/config-edit.sh --check
#   scripts/config-edit.sh --set <yq-path>=<value> [--set ...]
#   scripts/config-edit.sh --from <candidate.yaml>
#   scripts/config-edit.sh --dry-run --set <yq-path>=<value>
#   scripts/config-edit.sh --restore
#
# `--set .a.b=` (an empty value — a forgotten typo) is REFUSED, not accepted as "clear the
# field": a null value falls back to its default rather than erroring, which is silent, not
# safe. To clear a key on purpose, write a literal null: `--set .a.b=null`. Every other value
# is always written as a YAML string (via yq's strenv(), never spliced into the expression), so
# there is currently no --set spelling for the literal three-character STRING "null" itself — use
# --from for that rare case.
#
# Overrides (so this is drivable with no daemon — see scripts/test-config-edit.sh):
#   --config <path>        default: fleetd/fleetd.yaml
#   --log <path>           default: fleetd/fleetd.out
#   --wait-seconds <n>     default: 4x the watch interval this script reads out of --log (10 -> 40)
#
# Exit codes (the --check/--restore/usage-error paths are reported separately, see below):
#   0  applied; verdict read; clean
#   3  applied; verdict read; needs a restart (deferred or split keys named)
#   4  REFUSED by the daemon; backup restored (and the restore's own verdict reported if seen)
#   5  CANNOT TELL — no verdict line inside the wait window. Nothing is restored.
#
# Never prints a secret. fleetd.yaml keeps credentials out by indirection (broker.uriEnv,
# gitTokenEnv) but this script does not rely on that staying true: every diff it prints is piped
# through `redact`, which (a) blanks the userinfo of any `scheme://user:pass@host` and (b) masks
# the whole value on any line whose key looks like a credential. See `redact` below.

set -euo pipefail

REPO="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
SELF="$REPO/scripts/config-edit.sh"

CONFIG="$REPO/fleetd/fleetd.yaml"
LOG="$REPO/fleetd/fleetd.out"
WAIT_SECONDS_OVERRIDE=""
FALLBACK_PORT=8765

MODE=""
DRY_RUN=0
SETS=()
FROM_FILE=""

# fleetd #635 follow-up — a signal (or any early exit while a candidate is still uninstalled) must
# not leave a `.config-edit.XXXXXX` file sitting beside the live config forever. CAND is global
# (never a function-local) on purpose: this ONE trap, set once, covers every path that ever
# creates a candidate — run_edit and dry_run_diff both assign it, and clear it back to "" once the
# file is consumed (installed, or explicitly removed), so a later, unrelated exit never retries a
# path that already served its purpose.
CAND=""
cleanup_candidate() { [ -n "$CAND" ] && rm -f "$CAND" 2>/dev/null; return 0; }
trap cleanup_candidate EXIT INT TERM

say()  { printf '\n\033[1m== %s\033[0m\n' "$*"; }
ok()   { printf '   ok    %s\n' "$*"; }
warn() { printf '   WARN  %s\n' "$*"; }
die()  { printf '\n   FAIL  %s\n\n' "$*" >&2; exit 1; }

set_mode() {
  local new="$1"
  if [ -n "$MODE" ] && [ "$MODE" != "$new" ]; then
    die "cannot combine --$MODE and --$new in one invocation"
  fi
  MODE="$new"
}

while [ $# -gt 0 ]; do
  case "$1" in
    --check)   set_mode check; shift ;;
    --restore) set_mode restore; shift ;;
    --set)
      [ $# -ge 2 ] || die "--set requires <yq-path>=<value>"
      set_mode set
      SETS+=("$2")
      shift 2 ;;
    --from)
      [ $# -ge 2 ] || die "--from requires a candidate file path"
      set_mode from
      FROM_FILE="$2"
      shift 2 ;;
    --dry-run) DRY_RUN=1; shift ;;
    --config)
      [ $# -ge 2 ] || die "--config requires a path"
      CONFIG="$2"; shift 2 ;;
    --log)
      [ $# -ge 2 ] || die "--log requires a path"
      LOG="$2"; shift 2 ;;
    --wait-seconds)
      [ $# -ge 2 ] || die "--wait-seconds requires a number of seconds"
      WAIT_SECONDS_OVERRIDE="$2"; shift 2 ;;
    -h|--help) sed -n '3,70p' "$SELF"; exit 0 ;;
    *) echo "unknown option: $1 (try --help)" >&2; exit 2 ;;
  esac
done

[ -n "$MODE" ] || die "no action given — use --check, --set, --from, or --restore (see --help)"

# ------------------------------------------------------------------------------------- redaction
#
# Two independent passes, applied to every diff this script ever prints:
#   1. `scheme://user:pass@host` -> `scheme://<redacted>@host`, globally (the `g` flag matters —
#      a line can carry more than one URI).
#   2. Any line whose key looks like TOKEN|SECRET|PASSWORD|PASSWD|PASSPHRASE|CREDENTIAL|URI|_KEY,
#      matched case-insensitively against the key text (uriEnv, gitTokenEnv, ... are camelCase,
#      not SCREAMING_CASE) has its whole value blanked, diff marker and indentation kept so the
#      shape of the change is still visible. Deliberately conservative: a false-positive
#      redaction on an unrelated line costs nothing, an unredacted secret is a security defect
#      (acceptance criterion 7).
#
# fleetd #635 follow-up (ticket comment 17670, defect 7) — a masked key line is not the whole
# story: a YAML block scalar (`|`, `|-`, `>`, `>-`, ...) puts the VALUE on the lines that follow
# the key, each indented deeper than it. The key-name match above only ever sees the key line
# itself, so those continuation lines used to flow straight through unredacted while the key line
# right above them printed a reassuring "<redacted>" — an incomplete redactor that looks complete
# is worse than one that visibly does nothing, because it stops a reviewer from looking further.
# The fix is structural, not another name to match: once a key line is masked, every following
# line indented STRICTLY DEEPER than that key is masked too, by indentation alone, until the
# indentation returns to the key's own level or shallower. This needs no knowledge of the key's
# name and so protects a block scalar under any masked key, present or future.
#
# `redact` is always fed `diff -u` output, and every line of a unified diff starts with exactly
# one of ' ', '+', '-' (the three body markers; '@'/'-'/'+' for the three header-line kinds too).
# That one leading character is NOT part of the YAML indentation, and must be stripped before
# indentation is measured or a key is matched — otherwise a changed ('+' or '-') line reads one
# column shallower than it really is, and either wrongly escapes a continuation mask or wrongly
# ends one early. Tabs are out of scope: YAML forbids them for indentation, and this is a bounded
# fix, not a YAML parser.
redact() {
  local line prefix content indent lead key
  local masked=0 masked_indent=0 saved_nocasematch=0
  shopt -q nocasematch && saved_nocasematch=1
  shopt -s nocasematch
  sed -E 's#://[^@]*@#://<redacted>@#g' | while IFS= read -r line || [ -n "$line" ]; do
    case "$line" in
      [\ +-]*) prefix="${line:0:1}"; content="${line:1}" ;;
      *)       prefix="";            content="$line" ;;
    esac

    indent=0
    while [ "${content:$indent:1}" = " " ]; do indent=$((indent + 1)); done

    if [ "$masked" = 1 ] && [ "$indent" -gt "$masked_indent" ]; then
      printf '%s%*s<redacted>\n' "$prefix" "$indent" ""
      continue
    fi
    masked=0

    if [[ "$content" =~ ^([[:space:]]*)([A-Za-z0-9_.-]+:) ]]; then
      lead="${BASH_REMATCH[1]}"
      key="${BASH_REMATCH[2]}"
      if [[ "$key" =~ (TOKEN|SECRET|PASSWORD|PASSWD|PASSPHRASE|CREDENTIAL|URI|_KEY) ]]; then
        printf '%s%s%s <redacted>\n' "$prefix" "$lead" "$key"
        masked=1
        masked_indent="$indent"
        continue
      fi
    fi
    printf '%s\n' "$line"
  done
  [ "$saved_nocasematch" = 1 ] || shopt -u nocasematch
}

# ------------------------------------------------------------------------------------- the probe
#
# Probe the SOCKET, never `pgrep`/`ps -f` — both print argv, and argv holds `NAME=value`, making
# either a credential channel. The port comes from the config's own `bind.port`; 8765 is only a
# fallback when that key is absent or the file does not parse yet.
resolve_port() {
  local file="$1" port
  if [ -f "$file" ] && command -v yq >/dev/null 2>&1; then
    port="$(yq eval '.bind.port' "$file" 2>/dev/null || true)"
  else
    port=""
  fi
  case "$port" in
    ''|null) echo "$FALLBACK_PORT" ;;
    *) echo "$port" ;;
  esac
}

daemon_listening() {
  local port="$1"
  if command -v nc >/dev/null 2>&1; then
    nc -z -w1 127.0.0.1 "$port" 2>/dev/null
  else
    ( exec 3<>"/dev/tcp/127.0.0.1/$port" ) 2>/dev/null
  fi
}

# --------------------------------------------------------------------------------- the log marker
#
# Take the log's line count BEFORE touching anything. Every later read of "what did the daemon
# say" starts strictly after this mark, so a refusal from hours ago can never be mistaken for
# this edit's verdict. Same approach as scripts/redeploy-fleetd.sh's RESTART_MARK.
log_mark() {
  local file="$1"
  if [ -f "$file" ]; then
    wc -l < "$file" 2>/dev/null || echo 0
  else
    echo 0
  fi
}

read_verdict_after_marker() {
  local file="$1" mark="$2"
  [ -f "$file" ] || return 0
  tail -n "+$((mark + 1))" "$file" 2>/dev/null || true
}

# Classifies one log LINE. Echoes one of: refused | clean | needs-restart | none. Always
# succeeds (every branch ends in `echo`), so it is safe to call from inside `$( )`.
classify_verdict_line() {
  local line="$1"
  case "$line" in
    *'config reload refused'*) echo refused ;;
    *'config reload from '*'refused, keeping the running config'*) echo refused ;;
    *'config reloaded'*)
      case "$line" in
        *'need a restart'*|*'partially live'*) echo needs-restart ;;
        *) echo clean ;;
      esac ;;
    *) echo none ;;
  esac
  return 0
}

scan_region_for_verdict() {
  local region="$1" line kind
  [ -n "$region" ] || return 1
  while IFS= read -r line || [ -n "$line" ]; do
    kind="$(classify_verdict_line "$line")"
    if [ "$kind" != "none" ]; then
      VERDICT_KIND="$kind"
      VERDICT_LINE="$line"
      return 0
    fi
  done <<< "$region"
  return 1
}

# Sets VERDICT_KIND/VERDICT_LINE and returns 0 on the first verdict line found after $mark;
# returns 1 (VERDICT_KIND=none) if none appeared inside $wait_s seconds. Checks once before each
# sleep AND once more after the last sleep, the same boundary idiom
# scripts/redeploy-fleetd.sh's wait_for_daemon_exit/wait_for_new_pid already use.
wait_for_verdict() {
  local log="$1" mark="$2" wait_s="$3" _i region
  VERDICT_KIND="none"
  VERDICT_LINE=""
  for _i in $(seq "$wait_s"); do
    region="$(read_verdict_after_marker "$log" "$mark")"
    scan_region_for_verdict "$region" && return 0
    sleep 1
  done
  region="$(read_verdict_after_marker "$log" "$mark")"
  scan_region_for_verdict "$region" && return 0
  return 1
}

last_verdict_line() {
  local file="$1" line out=""
  [ -f "$file" ] || return 0
  while IFS= read -r line || [ -n "$line" ]; do
    if [ "$(classify_verdict_line "$line")" != "none" ]; then
      out="$line"
    fi
  done < "$file"
  printf '%s' "$out"
}

default_wait_seconds() {
  local log="$1" interval=""
  if [ -f "$log" ]; then
    interval="$(grep -F 'config watch:' "$log" 2>/dev/null | tail -1 \
      | sed -E 's/.*\(every ([0-9]+)s\).*/\1/' || true)"
  fi
  case "$interval" in
    ''|*[!0-9]*) interval=10 ;;
  esac
  echo $((interval * 4))
}

# ----------------------------------------------------------------------------------- the backup
#
# Timestamped, never pruned — "keep backups" per the ticket. A pid suffix avoids a same-second
# collision between two invocations.
#
# fleetd #635 follow-up — lands under a DEDICATED, gitignored directory beside the config
# (<dir>/.config-backups/), never beside the config file itself. The whole reason fleetd.yaml is
# gitignored is that it must never be committed, and a backup of it inherits that requirement — a
# bare `fleetd.yaml.bak.*` next to a tracked directory is one `git add -A`/`git add .` away from
# committing the live config. A directory beats a glob on its own: the glob only protects today's
# naming, a location keeps working even if the naming changes later. (See .gitignore for the glob
# kept anyway, as a backstop for a stray backup written the old way.)
BACKUP_DIRNAME=".config-backups"

backup_dir_for() {
  local src="$1"
  printf '%s/%s' "$(dirname "$src")" "$BACKUP_DIRNAME"
}

backup_config() {
  local src="$1" ts backup dir base
  dir="$(backup_dir_for "$src")"
  mkdir -p "$dir" \
    || die "could not create the backup directory $dir — refusing to edit without a backup. The live config at $src was NOT touched."
  ts="$(date -u +%Y%m%dT%H%M%S)Z"
  base="$(basename "$src")"
  backup="${dir}/${base}.bak.${ts}.$$"
  cp "$src" "$backup" \
    || die "could not create a backup at $backup — refusing to edit without one. The live config at $src was NOT touched."
  printf '%s' "$backup"
}

newest_backup() {
  local cfg="$1" dir base
  dir="$(backup_dir_for "$cfg")"
  base="$(basename "$cfg")"
  ls -t "${dir}/${base}".bak.* 2>/dev/null | head -1 || true
}

# ------------------------------------------------------------------------------------ the file mode
#
# fleetd #635 follow-up — `mv` from a mktemp candidate carries mktemp's 0600 onto the live path
# forever (measured: 644 -> 600 after one --set), and a restore does not undo it either, because
# `cp` onto an EXISTING file keeps the DESTINATION's mode, not the source's. Capture the live
# file's mode before anything touches it, and reapply it to whatever lands on that path
# afterwards — the candidate before install, and the config again after a restore — so an edit
# changes the file's CONTENT only, never its permissions. BSD `stat -f '%Lp'` first (matches this
# project's dev machine), GNU `stat -c '%a'` as the fallback. Prints nothing when the file does
# not exist yet, so apply_mode then does nothing and a first-ever edit falls back to the normal
# umask default rather than inventing a number.
file_mode() {
  local file="$1"
  [ -f "$file" ] || return 0
  stat -f '%Lp' "$file" 2>/dev/null || stat -c '%a' "$file" 2>/dev/null || true
}

apply_mode() {
  local file="$1" mode="$2"
  [ -n "$mode" ] || return 0
  chmod "$mode" "$file" 2>/dev/null || true
}

# --------------------------------------------------------------------------- candidate builders
#
# Never edit the live file in place. Each builder fills $1 (a temp file already sitting in the
# SAME directory as the live config, so the later `mv` install is a rename, not a cross-device
# copy — see run_edit).
# fleetd #635 follow-up — a forgotten value (`--set .a.b=`, a plausible typo) must never be
# accepted as "clear the field". `*=*` alone cannot tell "--set .a.b=" from "--set .a.b=7" apart
# — both contain an `=` — so the guard has to look at the VALUE, not the shape of the argument.
# An empty value refuses outright: nothing is installed, and the message names the likely cause
# AND the two ways to actually mean it (clear on purpose, or an intentional empty string via
# --from). Measured against the real daemon loader: a quoted empty string reads back as a null
# field (`quoted empty -> OK int=null`), and a null numeric field FALLS BACK TO ITS DEFAULT rather
# than erroring — so this is not a cosmetic nit, it is the one shape of edit that widens capacity
# silently instead of failing loudly, which is exactly what this script exists to catch.
#
# A deliberate clear needs its own spelling, because `""` and YAML `null` are NOT the same value
# to the loader (`""` is a valid empty String; `null` means absent, and an Integer field reads
# either the same way — null — but a String field would keep `""` as a real value). `--set
# .a.b=null` is that spelling: it writes a literal, unquoted `null` via yq, never the string
# "null" through strenv(). One consequence worth knowing: there is currently no --set spelling
# for the three-character STRING "null" itself (it collides with the clear spelling) — use
# --from for that rare case.
apply_set_pairs() {
  local cand="$1" kv path value
  shift
  for kv in "$@"; do
    case "$kv" in
      *=*) : ;;
      *) die "--set expects <yq-path>=<value>, got: '$kv'" ;;
    esac
    path="${kv%%=*}"
    path="${path#.}"
    value="${kv#*=}"
    if [ -z "$value" ]; then
      die "--set '$kv' has an EMPTY value — refusing. Nothing was installed. A forgotten value
          would NULL the field, and a null value falls back to its default rather than erroring —
          silent, not safe. Did you mean --set .${path}=null to clear it on purpose, or --from a
          file if you need a genuinely empty string?"
    fi
    # fleetd #635 follow-up (ticket comment 17673, defect 8) — these two failure messages used to
    # echo the full "$kv" (path=value, exactly as the operator typed it), unredacted. The operator
    # already has the value, so a terminal is not where this leaks — the risk is where the output
    # goes NEXT: this fleet pastes command output into tickets, PRs and fleet_reply bodies, and a
    # failure is exactly when someone copies it to ask for help. Print the PATH, which is what's
    # needed to fix the command, and never the value. $kv is not key:value-shaped YAML, so piping
    # it through redact would just pass it straight through — a false sense of coverage, the same
    # mistake as defect 7.
    if [ "$value" = "null" ]; then
      yq eval -i ".${path} = null" "$cand" \
        || die "yq could not clear --set '.${path}=null' — nothing was installed. The live config is unchanged."
      continue
    fi
    CONFIG_EDIT_SET_VALUE="$value" yq eval -i ".${path} = strenv(CONFIG_EDIT_SET_VALUE)" "$cand" \
      || die "yq could not apply --set '.${path}=<value>' — nothing was installed. The live config is unchanged."
  done
}

build_from_set() {
  local cand="$1"
  cp "$CONFIG" "$cand"
  apply_set_pairs "$cand" "${SETS[@]}"
}

build_from_file() {
  local cand="$1"
  [ -f "$FROM_FILE" ] || die "--from file not found: $FROM_FILE"
  cp "$FROM_FILE" "$cand"
}

parse_check() {
  yq eval '.' "$1" >/dev/null 2>&1
}

install_candidate() {
  local cand="$1" live="$2"
  mv -f "$cand" "$live"
}

# -------------------------------------------------------------------------------- the report path
#
# Prints the literal command the operator (or a test) can run to restore the backup by hand — the
# absolute path to THIS script plus the overrides actually in force, so it works from any cwd.
restore_command_line() {
  printf '%q --restore --config %q --log %q --wait-seconds %q' "$SELF" "$CONFIG" "$LOG" "$WAIT_SECONDS"
}

# State 4 only: restore the pre-edit backup, then wait for a SECOND verdict confirming the
# restore itself reloaded cleanly. Never claims a restore it did not observe — if the second wait
# also times out, it says so plainly rather than reporting "restored" as though confirmed.
restore_and_confirm() {
  local backup="$1" mark2 orig_mode
  orig_mode="$(file_mode "$CONFIG")"
  mark2="$(log_mark "$LOG")"
  cp "$backup" "$CONFIG" \
    || die "could not restore $backup onto $CONFIG — the live config is left as the REFUSED edit. Fix this by hand immediately: cp \"$backup\" \"$CONFIG\""
  apply_mode "$CONFIG" "$orig_mode"
  ok "restored from $backup"
  if wait_for_verdict "$LOG" "$mark2" "$WAIT_SECONDS"; then
    case "$VERDICT_KIND" in
      refused) warn "the RESTORE was also refused by the daemon: $VERDICT_LINE" ;;
      *)       ok "restore confirmed: $VERDICT_LINE" ;;
    esac
  else
    warn "the restore is on disk, but no confirming verdict line appeared within ${WAIT_SECONDS}s"
    warn "cannot confirm the restore reloaded cleanly — check $LOG by hand"
  fi
  return 0
}

# The four-outcome decision. Echoed as a function so run_edit/restore_mode share one place that
# can return 0/3/4/5 — never duplicated, never re-worded between the two callers.
report_outcome() {
  local mark="$1" backup="$2" kind line

  say "waiting for the daemon's verdict (up to ${WAIT_SECONDS}s)"
  if wait_for_verdict "$LOG" "$mark" "$WAIT_SECONDS"; then
    kind="$VERDICT_KIND"; line="$VERDICT_LINE"
  else
    kind="none"
  fi

  case "$kind" in
    clean)
      ok "daemon verdict: $line"
      say "result: applied cleanly"
      return 0 ;;
    needs-restart)
      ok "daemon verdict: $line"
      say "result: applied — a restart is needed for the change(s) named above"
      return 3 ;;
    refused)
      warn "daemon verdict: $line"
      say "result: REFUSED — restoring the backup"
      restore_and_confirm "$backup"
      return 4 ;;
    none)
      warn "no verdict line appeared within ${WAIT_SECONDS}s after $LOG line $mark"
      warn "CANNOT TELL whether the daemon applied this edit, refused it, or is simply down."
      warn "Nothing was restored — the edit is still on disk at $CONFIG."
      echo
      echo "   backup: $backup"
      echo "   to restore it by hand:"
      echo "       $(restore_command_line)"
      return 5 ;;
  esac
}

# ------------------------------------------------------------------------------------- the modes
check_mode() {
  say "config-edit --check"
  if [ -f "$CONFIG" ]; then
    if parse_check "$CONFIG"; then
      ok "config parses: $CONFIG"
    else
      warn "config does NOT parse as valid YAML: $CONFIG"
    fi
  else
    warn "no config file at $CONFIG"
  fi

  local port
  port="$(resolve_port "$CONFIG")"
  if daemon_listening "$port"; then
    ok "daemon is listening on 127.0.0.1:$port"
  else
    warn "no daemon detected listening on 127.0.0.1:$port"
  fi

  ok "watch interval assumed: $(( $(default_wait_seconds "$LOG") / 4 ))s (derives --wait-seconds default of $(default_wait_seconds "$LOG")s)"

  local verdict
  verdict="$(last_verdict_line "$LOG")"
  if [ -n "$verdict" ]; then
    ok "last verdict in log: $verdict"
  else
    warn "no reload verdict line found in $LOG"
  fi

  local backup
  backup="$(newest_backup "$CONFIG")"
  if [ -n "$backup" ]; then
    ok "newest backup: $backup"
  else
    warn "no backups found for $CONFIG"
  fi

  if command -v yq >/dev/null 2>&1; then
    ok "yq: $(yq --version 2>&1)"
  else
    warn "yq not found on PATH"
  fi

  return 0
}

# Shared by --set and --from: backup, build, parse-check, redacted diff, install, await verdict.
run_edit() {
  local builder="$1"
  [ -f "$CONFIG" ] || die "no config at $CONFIG — nothing to edit"

  local mark orig_mode
  mark="$(log_mark "$LOG")"
  orig_mode="$(file_mode "$CONFIG")"

  say "probe"
  local port
  port="$(resolve_port "$CONFIG")"
  if daemon_listening "$port"; then
    ok "daemon appears to be listening on 127.0.0.1:$port"
  else
    warn "no daemon detected listening on 127.0.0.1:$port — a verdict may never appear"
  fi

  say "backup"
  local backup
  backup="$(backup_config "$CONFIG")"
  ok "backup: $backup"

  say "candidate"
  local cand
  CAND="$(mktemp "$(dirname "$CONFIG")/.config-edit.XXXXXX")" \
    || die "could not create a candidate temp file next to $CONFIG"
  cand="$CAND"
  if ! "$builder" "$cand"; then
    rm -f "$cand"; CAND=""
    die "could not build the candidate — nothing was installed. The live config at $CONFIG is unchanged."
  fi

  if ! parse_check "$cand"; then
    rm -f "$cand"; CAND=""
    die "candidate does not parse as valid YAML — nothing was installed. The live config at $CONFIG is unchanged."
  fi
  ok "candidate parses"

  apply_mode "$cand" "$orig_mode"

  say "change (redacted)"
  diff -u "$backup" "$cand" | redact || true

  say "install"
  install_candidate "$cand" "$CONFIG" \
    || die "could not install the candidate onto $CONFIG — the live config was NOT changed. The validated candidate is sitting at $cand; investigate before retrying."
  CAND=""
  ok "installed: $CONFIG"

  local rc=0
  report_outcome "$mark" "$backup" || rc=$?
  return "$rc"
}

dry_run_diff() {
  local builder="$1"
  [ -f "$CONFIG" ] || die "no config at $CONFIG — nothing to diff against"
  local cand
  CAND="$(mktemp "$(dirname "$CONFIG")/.config-edit.XXXXXX")" \
    || die "could not create a candidate temp file next to $CONFIG"
  cand="$CAND"
  if ! "$builder" "$cand"; then
    rm -f "$cand"; CAND=""
    die "could not build the candidate — this was a --dry-run, nothing would have been installed either"
  fi
  if ! parse_check "$cand"; then
    rm -f "$cand"; CAND=""
    die "candidate does not parse as valid YAML — this was a --dry-run, nothing would have been installed either"
  fi
  say "dry run — diff (redacted), nothing installed"
  diff -u "$CONFIG" "$cand" | redact || true
  rm -f "$cand"; CAND=""
  return 0
}

restore_mode() {
  [ -f "$CONFIG" ] || die "no config at $CONFIG to restore onto"
  local backup dir base
  backup="$(newest_backup "$CONFIG")"
  if [ -z "$backup" ]; then
    # fleetd #635 follow-up (ticket comment 17664) — this message must name the directory the
    # code actually searches (backup_dir_for, same as newest_backup), not the old beside-the-
    # config glob. A backup written the OLD way is real and NOT searched any more — say so and
    # give the one-line recovery command — but do NOT make the search itself look there; that
    # would be a behaviour change nobody asked for. The message is the only thing being fixed.
    dir="$(backup_dir_for "$CONFIG")"
    base="$(basename "$CONFIG")"
    die "no backup found matching ${dir}/${base}.bak.* — nothing to restore.
        A backup written the OLD way, directly beside the config (${CONFIG}.bak.*), is NOT
        searched — that location was retired so a backup of a file that must never be committed
        cannot sit next to a tracked directory. If one exists there, recover it by hand:
        cp ${CONFIG}.bak.<timestamp>.<pid> $CONFIG"
  fi
  [ -f "$backup" ] || die "backup candidate $backup vanished"

  say "restore"
  ok "restoring $backup onto $CONFIG"
  local mark orig_mode
  mark="$(log_mark "$LOG")"
  orig_mode="$(file_mode "$CONFIG")"
  cp "$backup" "$CONFIG" || die "could not copy $backup onto $CONFIG"
  apply_mode "$CONFIG" "$orig_mode"
  ok "installed: $CONFIG"

  local rc=0
  report_outcome "$mark" "$backup" || rc=$?
  return "$rc"
}

# -------------------------------------------------------------------------------------- dispatch

if [ -n "$WAIT_SECONDS_OVERRIDE" ]; then
  WAIT_SECONDS="$WAIT_SECONDS_OVERRIDE"
else
  WAIT_SECONDS="$(default_wait_seconds "$LOG")"
fi

RC=0
case "$MODE" in
  check)
    check_mode || RC=$?
    ;;
  set)
    [ "${#SETS[@]}" -gt 0 ] || die "--set requires at least one <yq-path>=<value>"
    if [ "$DRY_RUN" = 1 ]; then
      dry_run_diff build_from_set || RC=$?
    else
      run_edit build_from_set || RC=$?
    fi
    ;;
  from)
    [ -n "$FROM_FILE" ] || die "--from requires a candidate file path"
    if [ "$DRY_RUN" = 1 ]; then
      dry_run_diff build_from_file || RC=$?
    else
      run_edit build_from_file || RC=$?
    fi
    ;;
  restore)
    restore_mode || RC=$?
    ;;
esac

exit "$RC"