#!/usr/bin/env bash
#
# launch-upgrader.sh — spin up the cc-ci UPGRADER agent in tmux under remote-control.
#
# The Upgrader is a ONE-SHOT job agent (not a perpetual loop like the Builder/Adversary): it runs the
# weekly recipe-upgrade sequence — the /upgrade-all skill in DEFAULT mode — to completion, then STOPS
# and stays idle (it does NOT self-terminate) so the run + summary remain viewable/steerable at
# claude.ai/code exactly like the Builder, instead of being buried in headless cron output. The next
# weekly run starts a fresh session: `start` leaves an in-flight run alone but clears a finished/idle
# (or wedged) session and starts clean. The weekly cron (Sat 03:00 UTC, once cc-ci is built — see
# [[cc-ci-upgrade-all-cron]]) invokes `launch-upgrader.sh start`.
#
# Naming: tmux session AND remote-control name are both "cc-ci-upgrader" (matching
# cc-ci-builder / cc-ci-adv / cc-ci-watchdog / cc-ci-orchestrator).
#
# Usage:
#   ./launch-upgrader.sh start          # use-or-create: if a run is actively in flight leave it,
#                                        #   else (no session / idle-stale) kill any stale + start fresh
#   ./launch-upgrader.sh fresh          # always kill any existing + start a fresh run
#   ./launch-upgrader.sh status | attach | stop
#
# Env:
#   UPGRADER_ARGS=""   passthrough args to /upgrade-all (e.g. "--dry-run", "ghost n8n"); default none
#                      = full default fleet run. NEVER pass --with-tests here (the cron must not
#                      auto-edit tests; that's the operator's per-recipe opt-in).
set -euo pipefail

SESSION="${UPGRADER_SESSION:-cc-ci-upgrader}"        # tmux session name == remote-control name
WORKDIR="${UPGRADER_DIR:-/srv/cc-ci}"                # cwd: where .claude/skills/ + .testenv live

# Backend selection — mirrors launch.sh. LOOP_BACKEND overrides for consistency.
UPGRADER_BACKEND="${LOOP_BACKEND:-${UPGRADER_BACKEND:-claude}}"  # "claude" or "opencode"
# Model: LOOP_MODEL > UPGRADER_MODEL > backend default (sonnet for claude, provider/model for opencode).
UPGRADER_MODEL="${LOOP_MODEL:-${UPGRADER_MODEL:-sonnet}}"

CLAUDE_BIN="${CLAUDE_BIN:-claude}"
CLAUDE_FLAGS="${CLAUDE_FLAGS:---dangerously-skip-permissions}"
OPENCODE_BIN="${OPENCODE_BIN:-/home/loops/.local/bin/opencode}"
OPENCODE_SERVER="${OPENCODE_SERVER:-http://127.0.0.1:4096}"
REMOTE_CONTROL="${REMOTE_CONTROL:-1}"                # 1 => --remote-control / opencode web
LOG_DIR="${LOG_DIR:-/srv/cc-ci/.cc-ci-logs}"
UPGRADER_ARGS="${UPGRADER_ARGS:-}"

log()  { printf '[upgrader %(%H:%M:%S)T] %s\n' -1 "$*"; }
die()  { log "ERROR: $*"; exit 1; }
session_alive() { tmux has-session -t "$SESSION" 2>/dev/null; }
# "actively working" = claude shows interrupt hint; opencode shows spinner/Running tool.
session_busy() { tmux capture-pane -pt "$SESSION" 2>/dev/null | grep -qE 'esc to interrupt|⠋|⠙|⠹|⠸|⠼|⠴|⠦|⠧|⠇|⠏|Running tool'; }

preflight() {
  command -v tmux >/dev/null 2>&1 || die "missing dependency: tmux"
  case "$UPGRADER_BACKEND" in
    claude)   command -v "$CLAUDE_BIN"   >/dev/null 2>&1 || die "claude CLI not found (set CLAUDE_BIN)" ;;
    opencode) command -v "$OPENCODE_BIN" >/dev/null 2>&1 || die "opencode not found (set OPENCODE_BIN)"
              [[ -n "$OPENCODE_HOST" ]] || die "could not detect tailscale IP for OPENCODE_HOST" ;;
    *) die "unknown UPGRADER_BACKEND '$UPGRADER_BACKEND' — use 'claude' or 'opencode'" ;;
  esac
  [[ -d "$WORKDIR" ]] || die "workdir not found: $WORKDIR"
  [[ -d "$WORKDIR/.claude/skills/upgrade-all" ]] || die "upgrade-all skill not found under $WORKDIR/.claude/skills"
  mkdir -p "$LOG_DIR"
}

write_kickoff() {
  local kf="$LOG_DIR/.kickoff-$SESSION.txt"
  cat > "$kf" <<KICK
*** cc-ci UPGRADER — weekly recipe-upgrade job ***
You are the cc-ci Upgrader: a ONE-SHOT job agent, NOT a perpetual loop. Run the recipe-upgrade
sequence to completion, then STOP. Your cwd is ${WORKDIR}; reach the CI server with \`ssh cc-ci\`;
creds are in ${WORKDIR}/.testenv; the skills live in ${WORKDIR}/.claude/skills/.

DO THIS:
1. Invoke the **/upgrade-all** skill in DEFAULT mode${UPGRADER_ARGS:+ with arguments: ${UPGRADER_ARGS}}
   (read ${WORKDIR}/.claude/skills/upgrade-all/SKILL.md for the full procedure). It surveys every
   enrolled recipe and, for each upgradeable one, runs /recipe-upgrade in DEFAULT mode — recipe PR
   only, verified by posting \`!testme\` on the PR (results visible in the PR, iterate up to 3x). A
   genuinely stale test gets an explanatory PR COMMENT, never a test edit.
2. Process recipes via per-recipe SUBAGENTS (as the skill specifies) so your own context stays light.
   If your context usage climbs (~80%), run /compact before continuing.
3. Write + push the weekly summary (the PR list is the actionable output for the operator).
4. WHEN THE RUN IS COMPLETE: STOP. Print the final summary (lead with the PR list) and an
   \`UPGRADE RUN COMPLETE\` line, then go idle. Do NOT loop, do NOT re-run, and do NOT kill your own
   session — leave it up so the operator can review your output + the summary in the web UI
   (claude.ai/code). Next week's run starts a fresh session (the launcher clears this idle one).

GUARDRAILS: NEVER merge any PR. NEVER weaken a test. DEFAULT mode only — do NOT pass --with-tests
(updating cc-ci tests is the operator's per-recipe opt-in). Single-writer: dedicated branches +
separate clones, never push main, never touch the build loops' /cc-ci /cc-ci-adv clones. The shared
Swarm is stateful — go sequentially and tear down what you deploy.
KICK
  echo "$kf"
}

start() {
  local mode="${1:-use-or-create}"
  preflight
  if session_alive; then
    if [[ "$mode" == "use-or-create" ]] && session_busy; then
      log "$SESSION already running a job (busy) — leaving it"; return 0
    fi
    log "$SESSION exists but idle/stale (or fresh requested) — killing it first"
    tmux kill-session -t "$SESSION" 2>/dev/null || true; sleep 1
  fi
  local kf
  kf="$(write_kickoff)"
  log "starting $SESSION (backend=$UPGRADER_BACKEND, model=$UPGRADER_MODEL, args='${UPGRADER_ARGS:-<none>}')"
  case "$UPGRADER_BACKEND" in
    claude)
      local rc=""
      [[ "$REMOTE_CONTROL" == "1" ]] && rc="--remote-control '$SESSION'"
      tmux new-session -d -s "$SESSION" -c "$WORKDIR" \
        "$CLAUDE_BIN $rc --model '$UPGRADER_MODEL' $CLAUDE_FLAGS \"\$(cat '$kf')\""
      ;;
    opencode)
      tmux new-session -d -s "$SESSION" -c "$WORKDIR" \
        "set -a; . /srv/cc-ci/.testenv; set +a; $OPENCODE_BIN --model '$UPGRADER_MODEL' run --attach '$OPENCODE_SERVER' --title '$SESSION' \"\$(cat '$kf')\""
      log "$SESSION visible in web UI at http://oc.commoninternet.net (tailnet only)"
      ;;
  esac
  tmux pipe-pane -o -t "$SESSION" "cat >> '$LOG_DIR/$SESSION.log'"
  log "started. status: $0 status | attach: tmux attach -t $SESSION | log: $LOG_DIR/$SESSION.log"
}

case "${1:-start}" in
  start)  start use-or-create ;;
  fresh)  start fresh ;;
  stop)   if session_alive; then log "killing $SESSION"; tmux kill-session -t "$SESSION" || true; else log "$SESSION not running"; fi ;;
  status)
    if session_alive; then
      log "$SESSION: RUNNING $(session_busy && echo '(busy)' || echo '(idle/finishing)')"
      ps -eo pid,etime,args | grep "[r]emote-control $SESSION" || true
    else log "$SESSION: stopped"; fi ;;
  attach) exec tmux attach -t "$SESSION" ;;
  *)
    cat <<EOF
cc-ci upgrader launcher — one-shot weekly recipe-upgrade job agent (remote-control)

  $0 start    use-or-create: leave an in-flight run alone, else (re)start fresh (DEFAULT; what the cron calls)
  $0 fresh    always kill any existing + start a fresh run
  $0 status   show tmux + remote-control state
  $0 attach   tmux attach to the session
  $0 stop     kill the session

Env: UPGRADER_BACKEND=$UPGRADER_BACKEND  UPGRADER_MODEL=$UPGRADER_MODEL  UPGRADER_ARGS='${UPGRADER_ARGS:-<none>}'
     claude:   CLAUDE_BIN=$CLAUDE_BIN  REMOTE_CONTROL=$REMOTE_CONTROL
     opencode: OPENCODE_BIN=$OPENCODE_BIN  OPENCODE_SERVER=$OPENCODE_SERVER  web=http://oc.commoninternet.net
     (LOOP_BACKEND / LOOP_MODEL override UPGRADER_BACKEND / UPGRADER_MODEL for unified control)
The agent runs /upgrade-all (DEFAULT mode) to completion, then STOPS and stays idle (viewable in the
web UI). It does NOT self-terminate; the next weekly `start` clears the idle session and runs fresh.
EOF
    ;;
esac