heavy-duty-watcher/scripts/discover.sh

#!/usr/bin/env bash
# Org-wide discovery of actionable PRs/issues for the bot.
# Supports FORGE_BACKEND=github (default) or forgejo.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# shellcheck source=lib/common.sh
source "${SCRIPT_DIR}/lib/common.sh"

FORMAT="${FORMAT:-json}" # json | summary
LIMIT="${LIMIT:-50}"

discover_github() {
  require_cmd gh jq

  local tmp
  tmp="$(mktemp -d)"
  # shellcheck disable=SC2064
  trap "rm -rf '${tmp}'" EXIT

  gh search prs --owner "${ORG}" --review-requested=@me --state open \
    --json number,title,url,updatedAt,author,assignees,repository --limit "${LIMIT}" \
    > "${tmp}/pr_rr.json" 2>/dev/null || echo '[]' > "${tmp}/pr_rr.json"

  gh search prs --owner "${ORG}" --assignee=@me --state open \
    --json number,title,url,updatedAt,author,assignees,repository --limit "${LIMIT}" \
    > "${tmp}/pr_as.json" 2>/dev/null || echo '[]' > "${tmp}/pr_as.json"

  gh search issues --owner "${ORG}" --assignee=@me --state open \
    --json number,title,url,updatedAt,author,assignees,repository --limit "${LIMIT}" \
    > "${tmp}/issues.json" 2>/dev/null || echo '[]' > "${tmp}/issues.json"

  # Normalize empty/null files
  for f in pr_rr pr_as issues; do
    if [[ ! -s "${tmp}/${f}.json" ]] || ! jq empty "${tmp}/${f}.json" 2>/dev/null; then
      echo '[]' > "${tmp}/${f}.json"
    fi
  done

  jq -n \
    --arg org "${ORG}" \
    --arg bot "${BOT_LOGIN}" \
    --slurpfile rr "${tmp}/pr_rr.json" \
    --slurpfile as "${tmp}/pr_as.json" \
    --slurpfile iss "${tmp}/issues.json" \
    '
    def repo_name:
      .repository.nameWithOwner // .repository.full_name // "unknown/unknown";
    def pr_key:
      (repo_name) + "#pr:" + (.number|tostring);

    ($rr[0] // []) as $rr |
    ($as[0] // []) as $as |
    ($iss[0] // []) as $iss |

    # set of assignee PR keys
    ([$as[] | pr_key] | unique) as $as_keys |
    ([$rr[] | pr_key] | unique) as $rr_keys |

    (
      [
        $rr[] |
        . + {
          kind: "pr",
          role: (if ([pr_key] | inside($as_keys)) then "reviewer+assignee" else "reviewer" end)
        }
      ]
      + [
        $as[] |
        select(([pr_key] | inside($rr_keys)) | not) |
        . + { kind: "pr", role: "assignee" }
      ]
    ) as $prs |

    (
      [ $iss[] | . + { kind: "issue", role: "assignee" } ]
    ) as $issues |

    {
      backend: "github",
      org: $org,
      bot: $bot,
      generated_at: (now | strftime("%Y-%m-%dT%H:%M:%SZ")),
      counts: {
        prs: ($prs | length),
        issues: ($issues | length),
        total: (($prs | length) + ($issues | length))
      },
      prs: $prs,
      issues: $issues
    }
    '
}

discover_forgejo() {
  require_cmd jq curl

  local cfg token url tmp page batch n owner repo full
  cfg="${STOKE_CONFIG_FILE:-${XDG_CONFIG_HOME:-$HOME/.config}/stoke/config.json}"
  if [[ ! -f "${cfg}" ]]; then
    echo "error: stoke config not found at ${cfg} (run: stoke auth login)" >&2
    return 1
  fi
  token="$(jq -r '.token // empty' "${cfg}")"
  url="$(jq -r '.url // empty' "${cfg}")"
  url="${url:-$FORGEJO_URL}"
  url="${url%/}"
  if [[ -z "${token}" ]]; then
    echo "error: no token in ${cfg}" >&2
    return 1
  fi

  tmp="$(mktemp -d)"
  # shellcheck disable=SC2064
  trap "rm -rf '${tmp}'" EXIT

  api() {
    curl -fsS -H "Authorization: token ${token}" -H "Accept: application/json" "$@"
  }

  : > "${tmp}/repos.txt"
  page=1
  while (( page <= 40 )); do
    batch="$(api "${url}/api/v1/orgs/${ORG}/repos?limit=50&page=${page}" 2>/dev/null || echo '[]')"
    n="$(echo "${batch}" | jq 'length')"
    (( n == 0 )) && break
    echo "${batch}" | jq -r '.[].full_name // empty' >> "${tmp}/repos.txt"
    (( n < 50 )) && break
    page=$((page + 1))
  done

  : > "${tmp}/prs.ndjson"
  : > "${tmp}/issues.ndjson"

  while read -r full; do
    [[ -z "${full}" ]] && continue
    owner="${full%%/*}"
    repo="${full#*/}"

    api "${url}/api/v1/repos/${owner}/${repo}/pulls?state=open&limit=50" 2>/dev/null \
      | jq -c --arg full "${full}" --arg bot "${BOT_LOGIN}" '
          .[]? |
          (
            ((.requested_reviewers // []) | map(.login) | index($bot) != null)
          ) as $is_rev |
          (
            (.assignee.login == $bot)
            or (((.assignees // []) | map(.login) | index($bot)) != null)
          ) as $is_as |
          select($is_rev or $is_as) |
          {
            kind: "pr",
            number,
            title,
            url: .html_url,
            updatedAt: .updated_at,
            author: (.user.login // null),
            head_sha: (.head.sha // null),
            repository: { nameWithOwner: $full },
            role: (
              if $is_rev and $is_as then "reviewer+assignee"
              elif $is_rev then "reviewer"
              else "assignee"
              end
            )
          }
        ' >> "${tmp}/prs.ndjson" 2>/dev/null || true

    api "${url}/api/v1/repos/${owner}/${repo}/issues?state=open&type=issues&limit=50" 2>/dev/null \
      | jq -c --arg full "${full}" --arg bot "${BOT_LOGIN}" '
          .[]? |
          select(.pull_request == null) |
          select(
            (.assignee.login == $bot)
            or (((.assignees // []) | map(.login) | index($bot)) != null)
          ) |
          {
            kind: "issue",
            number,
            title,
            url: .html_url,
            updatedAt: .updated_at,
            author: (.user.login // null),
            repository: { nameWithOwner: $full },
            role: "assignee"
          }
        ' >> "${tmp}/issues.ndjson" 2>/dev/null || true
  done < "${tmp}/repos.txt"

  local prs_json issues_json
  if [[ -s "${tmp}/prs.ndjson" ]]; then
    prs_json="$(jq -s '.' "${tmp}/prs.ndjson")"
  else
    prs_json='[]'
  fi
  if [[ -s "${tmp}/issues.ndjson" ]]; then
    issues_json="$(jq -s '.' "${tmp}/issues.ndjson")"
  else
    issues_json='[]'
  fi

  jq -n \
    --arg org "${ORG}" \
    --arg bot "${BOT_LOGIN}" \
    --arg url "${url}" \
    --argjson prs "${prs_json}" \
    --argjson issues "${issues_json}" \
    '{
      backend: "forgejo",
      forge_url: $url,
      org: $org,
      bot: $bot,
      generated_at: (now | strftime("%Y-%m-%dT%H:%M:%SZ")),
      counts: {
        prs: ($prs | length),
        issues: ($issues | length),
        total: (($prs | length) + ($issues | length))
      },
      prs: $prs,
      issues: $issues
    }'
}

print_summary() {
  jq -r '
    "backend=\(.backend) org=\(.org) bot=\(.bot)",
    "counts: prs=\(.counts.prs) issues=\(.counts.issues) total=\(.counts.total)",
    "",
    (if (.prs|length)>0 then "PRs:" else empty end),
    (.prs[]? | "  [\(.role)] \(.repository.nameWithOwner // "unknown")!\(.number) — \(.title)"),
    (if (.issues|length)>0 then "Issues:" else empty end),
    (.issues[]? | "  [\(.role)] \(.repository.nameWithOwner // "unknown")#\(.number) — \(.title)"),
    (if .counts.total == 0 then "(no actionable items)" else empty end)
  '
}

main() {
  local payload
  case "${FORGE_BACKEND}" in
    github) payload="$(discover_github)" ;;
    forgejo) payload="$(discover_forgejo)" ;;
    *)
      echo "error: unknown FORGE_BACKEND=${FORGE_BACKEND} (use github or forgejo)" >&2
      exit 2
      ;;
  esac

  case "${FORMAT}" in
    json) echo "${payload}" | jq . ;;
    summary) echo "${payload}" | print_summary ;;
    *) echo "error: FORMAT must be json or summary" >&2; exit 2 ;;
  esac
}

main "$@"