#!/usr/bin/env bash
set -euo pipefail

# 2026-05-05 ogt + Codex
# Find or stop stale Gitea/act job containers on the 110 host.
#
# Default is dry-run:
#   bash scripts/ops/stop-stale-gitea-actions-jobs.sh
#
# Apply after reviewing candidates:
#   bash scripts/ops/stop-stale-gitea-actions-jobs.sh --apply
#
# Safety rules:
# - Only touches Docker containers named GITEA-ACTIONS-* or repo-scoped
#   Gitea job containers such as awoooi-cd-5901-1-e2e-smoke.
# - Defaults to containers older than 20 minutes.
# - Known long-running workflows get a higher stop threshold than the alert threshold.
# - Skips containers with recent log output unless --force is provided.

MIN_AGE_SECONDS=1200
APPLY=0
FORCE=0

threshold_for_name() {
  local name="$1"

  case "$name" in
    *WORKFLOW-CD-Pipeline_JOB-deploy*|*-cd-*-deploy*)
      # .gitea/workflows/cd.yaml deploy job timeout is 60m. Give act/Gitea
      # cleanup a buffer before treating the container as abandoned.
      echo 4500
      ;;
    *WORKFLOW-CD-Pipeline_JOB-tests*|*WORKFLOW-CD-Pipeline_JOB-post-deploy-checks*|*-cd-*-tests*|*-cd-*-post-deploy*)
      echo 2400
      ;;
    *WORKFLOW-Code-Review_JOB-ai-code-review*|*-code-review-*)
      echo 720
      ;;
    *-cd-*-e2e-smoke*|*-cd-*-source-link-smoke*)
      echo 900
      ;;
    *WORKFLOW-Deploy-Alert-Rules_JOB-deploy-alerts*)
      echo 900
      ;;
    *)
      echo "$MIN_AGE_SECONDS"
      ;;
  esac
}

while [[ $# -gt 0 ]]; do
  case "$1" in
    --apply)
      APPLY=1
      shift
      ;;
    --force)
      FORCE=1
      shift
      ;;
    --min-age-seconds)
      MIN_AGE_SECONDS="${2:?--min-age-seconds requires a value}"
      shift 2
      ;;
    *)
      echo "Unknown argument: $1" >&2
      exit 2
      ;;
  esac
done

now="$(date +%s)"
found=0

while read -r name; do
  [[ -n "$name" ]] || continue
  started_raw="$(docker inspect "$name" --format '{{.State.StartedAt}}')"
  started="$(date -u -d "$started_raw" +%s 2>/dev/null || echo 0)"
  age=$((now - started))
  stop_threshold="$(threshold_for_name "$name")"
  [[ "$stop_threshold" -ge "$MIN_AGE_SECONDS" ]] || stop_threshold="$MIN_AGE_SECONDS"
  [[ "$age" -ge "$stop_threshold" ]] || continue

  found=1
  log_tail="$(docker logs --since 5m --tail 5 "$name" 2>&1 || true)"
  has_recent_logs=0
  if [[ -n "$log_tail" ]]; then
    has_recent_logs=1
  fi

  printf 'candidate name=%s age_seconds=%s stop_threshold_seconds=%s recent_logs=%s\n' \
    "$name" "$age" "$stop_threshold" "$has_recent_logs"
  if [[ "$has_recent_logs" == "1" ]]; then
    printf '%s\n' "$log_tail" | sed 's/^/  log: /'
  fi

  if [[ "$APPLY" == "1" ]]; then
    if [[ "$has_recent_logs" == "1" && "$FORCE" != "1" ]]; then
      echo "skip $name: recent logs exist; use --force only after manual review"
      continue
    fi
    docker stop "$name"
  fi
done < <(docker ps --format '{{.Names}}' | grep -E '^(GITEA-ACTIONS-|[A-Za-z0-9][A-Za-z0-9_.-]*-(cd|code-review)-[0-9]+-)' || true)

if [[ "$found" == "0" ]]; then
  echo "No stale Gitea Actions containers older than policy threshold (minimum ${MIN_AGE_SECONDS}s)."
fi