#!/usr/bin/env bash
# Isolated live smoke of the Codex backend, driven entirely through agents.py.
# It starts one uniquely-named tmux session, verifies Remote Control and a daemon-connected Codex
# TUI, then removes only that session. The shared Remote Control daemon intentionally remains
# available.
set -uo pipefail

HERE="$(cd "$(dirname "$0")" && pwd)"
REPO="$(cd "$HERE/.." && pwd)"
CODEX_BIN="${CODEX_BIN:-$(command -v codex 2>/dev/null || echo "$HOME/.local/bin/codex")}" 
MODEL="${AOTEST_CODEX_MODEL:-}"
PREFIX="aotest-x-$$-"
SANDBOX="$(mktemp -d)"
CFG="$SANDBOX/agents.toml"
FAILED=0

pass(){ echo "  PASS: $*"; }
fail(){ echo "  FAIL: $*"; FAILED=1; }

cleanup(){
  local rc=$?
  python3 "$REPO/agents.py" --config "$CFG" down probe >/dev/null 2>&1 || true
  if command -v tmux >/dev/null 2>&1; then
    tmux ls 2>/dev/null | sed 's/:.*//' | grep "^${PREFIX}" | while read -r s; do
      tmux kill-session -t "=$s" 2>/dev/null || true
    done || true
  fi
  rm -rf "$SANDBOX"
  exit "$rc"
}
trap cleanup EXIT INT TERM

echo "=== codex backend smoke (isolated: prefix=${PREFIX}) ==="
command -v tmux >/dev/null 2>&1 || { echo "SKIP: tmux not on PATH"; exit 0; }
[ -x "$CODEX_BIN" ] || command -v "$CODEX_BIN" >/dev/null 2>&1 \
  || { echo "SKIP: codex binary not found ($CODEX_BIN)"; exit 0; }
"$CODEX_BIN" login status >/dev/null 2>&1 \
  || { echo "SKIP: Codex is not logged in"; exit 0; }
remote_status="$("$CODEX_BIN" remote-control start --json 2>&1)"
echo "$remote_status" | grep -q '"status":"connected"' \
  || { echo "SKIP: Codex Remote Control is not connected: $remote_status"; exit 0; }
pass "Codex Remote Control reports connected"

model_line=""
[ -n "$MODEL" ] && model_line="model = \"$MODEL\""
cat > "$CFG" <<EOF
[defaults]
project_dir    = "$REPO"
session_prefix = "$PREFIX"
log_dir        = "$SANDBOX/state"
backend        = "codex"
$model_line
watch          = "none"

[backend.codex]
bin             = "$CODEX_BIN"
preamble        = "{bin} remote-control start --json >/dev/null"
remote_addr     = "unix://"
flags           = "--dangerously-bypass-approvals-and-sandbox --dangerously-bypass-hook-trust --no-alt-screen"
supports_resume = false
prompt_delivery = "arg"
process_name    = "codex"
footer_ui       = true
log_grace       = 180
submit_key      = "Enter"
startup_prompt_re       = "Trusting the directory|Do you trust"
startup_prompt_response = "1"
startup_prompt_delay    = 2
stall_idle      = 300
active_re       = "esc to interrupt|working|thinking|running|searching"
limit_re        = "usage limit|limit reached"

[[agent]]
name   = "probe"
kind   = "persistent"
prompt = "You are a harness self-test. Reply exactly CODEX_BACKEND_READY and then wait silently. Do not use tools or modify files."
EOF

python3 "$REPO/agents.py" --config "$CFG" up probe \
  || { fail "agents.py up probe errored"; echo "=== CODEX BACKEND SMOKE: FAIL ==="; exit 1; }

sleep 12
if tmux has-session -t "=${PREFIX}probe" 2>/dev/null; then
  cmd="$(tmux display-message -p -t "=${PREFIX}probe:" '#{pane_current_command}')"
  pass "session ${PREFIX}probe created via agents.py (pane command: ${cmd})"
else
  fail "${PREFIX}probe session was not created"
  echo "=== CODEX BACKEND SMOKE: FAIL ==="
  exit 1
fi

pane="$(tmux capture-pane -p -t "=${PREFIX}probe:" -S -200 2>/dev/null)"
if [ "$cmd" = "codex" ] && echo "$pane" | grep -q "CODEX_BACKEND_READY"; then
  pass "Codex TUI attached and completed the probe"
else
  fail "Codex probe did not complete (cmd=${cmd}); tail: $(echo "$pane" | grep -vE '^\s*$' | tail -5)"
fi

if python3 "$REPO/agents.py" --config "$CFG" status \
    | grep -E '^\s*probe\b' | grep -q RUNNING; then
  pass "agents.py status reports probe RUNNING"
else
  fail "agents.py status did not report probe RUNNING"
fi

python3 "$REPO/agents.py" --config "$CFG" down probe >/dev/null 2>&1
sleep 2
if tmux has-session -t "=${PREFIX}probe" 2>/dev/null; then
  fail "${PREFIX}probe still alive after agents.py down"
else
  pass "agents.py down cleanly removed the session"
fi

if [ "$FAILED" = 0 ]; then echo "=== CODEX BACKEND SMOKE: PASS ==="; exit 0
else echo "=== CODEX BACKEND SMOKE: FAIL ==="; exit 1; fi