knowledge-genome-orchestrator/skills/ingest/scripts/open-pr.sh

#!/usr/bin/env bash
# =============================================================================
# skills/ingest/scripts/open-pr.sh
# Branch, commit (conventional), push, and open a Forgejo PR for the wiki/ changes.
# Mirrors the API conventions of providers/forgejo.sh (token auth + http_code).
# Runs inside the genome checkout (cwd = genome root). Never touches main.
#
#   open-pr.sh --slug <slug> --title "feat: ingest <slug>" --body-file <path> \
#       [--base main] [--label CONFLICT]
#
# Requires env: FORGEJO_URL, FORGEJO_USER, FORGEJO_TOKEN.
# =============================================================================
set -euo pipefail

: "${FORGEJO_URL:?missing FORGEJO_URL}"
: "${FORGEJO_USER:?missing FORGEJO_USER}"
: "${FORGEJO_TOKEN:?missing FORGEJO_TOKEN}"

slug="" title="" body_file="" base="main" label="" branch=""
while [[ $# -gt 0 ]]; do
  case "$1" in
    --slug)      slug="$2";      shift 2 ;;
    --branch)    branch="$2";    shift 2 ;;
    --title)     title="$2";     shift 2 ;;
    --body-file) body_file="$2"; shift 2 ;;
    --base)      base="$2";      shift 2 ;;
    --label)     label="$2";     shift 2 ;;
    *) echo "open-pr: unknown arg: $1" >&2; exit 1 ;;
  esac
done

: "${title:?--title required}"
: "${body_file:?--body-file required}"
[[ -f "$body_file" ]] || { echo "open-pr: body file not found: $body_file" >&2; exit 1; }

# --branch overrides the default; otherwise derive the ingest branch from --slug.
# (run-prune passes its own chore/prune-orphans-* branch; run-ingest passes --slug.)
if [[ -z "$branch" ]]; then
  : "${slug:?--slug or --branch required}"
  branch="feat/ai-ingest-${slug}"
fi
repo="$(basename -s .git "$(git config --get remote.origin.url)")"

# 1. Branch + commit + push (AGENTS.md rule 5: never commit to main)
# Rolling PR: -C force-resets the branch label to the current base (we are on it after
# clean_start) and CARRIES the freshly-written wiki/ changes, so a re-ingest of the same
# source rebuilds the branch cleanly instead of hitting a dirty-switch refusal.
git switch -C "$branch"
git add wiki/
# Scope BOTH the emptiness check and the commit to wiki/ — never commit anything that
# happened to be staged outside wiki/ (a stray hook, an aborted prior run, etc.).
if git diff --cached --quiet -- wiki/; then
  echo "open-pr: nothing staged under wiki/ — aborting" >&2
  exit 1
fi
git commit -m "$title" -- wiki/
# Try a normal push (new branch / fast-forward). If the branch was rebuilt from base and
# diverged, force-with-lease updates the open PR in place — the lease refuses to clobber if
# origin moved unexpectedly since our fetch, so concurrent work is never lost.
git push -u origin "$branch" 2>/dev/null || git push -u --force-with-lease origin "$branch"

# DRY_RUN: local git work done; skip the Forgejo API (offline tests).
if [[ -n "${DRY_RUN:-}" ]]; then
  echo "PR opened: DRY-RUN ${branch} -> ${base}"
  exit 0
fi

# 2. Open the PR via Forgejo API (jq builds the JSON safely)
# TODO: Forgejo-only. When registry.sh/globals.env sets PROVIDER=github, branch on
# $PROVIDER here and delegate to providers/github.sh (same token + http_code contract).
body="$(cat "$body_file")"
payload="$(jq -n --arg head "$branch" --arg base "$base" \
                 --arg title "$title" --arg body "$body" \
                 '{head:$head, base:$base, title:$title, body:$body}')"

resp="$(curl --max-time 30 -s -w '\n%{http_code}' \
  -H "Authorization: token ${FORGEJO_TOKEN}" \
  -H "Content-Type: application/json" \
  -X POST "${FORGEJO_URL}/api/v1/repos/${FORGEJO_USER}/${repo}/pulls" \
  -d "$payload")"

# curl -w appends '\n<code>' AFTER the body, so the code is always the final line and the
# body is everything before it. Parameter expansion (no subshells), robust to multi-line JSON.
code="${resp##*$'\n'}"
json="${resp%$'\n'*}"

case "$code" in
  201)
    url="$(printf '%s' "$json" | jq -r '.html_url')"
    number="$(printf '%s' "$json" | jq -r '.number')"
    echo "PR opened: ${url}"
    ;;
  409)
    # PR already exists — fetch it so the orchestrator still gets the URL.
    existing="$(curl --max-time 15 -s -H "Authorization: token ${FORGEJO_TOKEN}" \
      "${FORGEJO_URL}/api/v1/repos/${FORGEJO_USER}/${repo}/pulls?state=open" \
      | jq -r --arg b "$branch" '.[] | select(.head.ref==$b) | .html_url' | head -n1)"
    if [[ -n "$existing" && "$existing" != "null" ]]; then
      echo "PR opened: ${existing}"
    else
      echo "open-pr: a PR for '${branch}' already exists (push updated the branch)." >&2
    fi
    exit 0
    ;;
  401)
    echo "open-pr: unauthorized — check FORGEJO_TOKEN (n8n-bot)." >&2
    exit 1
    ;;
  *)
    echo "open-pr: Forgejo API HTTP ${code}: ${json}" >&2
    exit 1
    ;;
esac

# 3. Optional label (e.g. CONFLICT). Best-effort; non-fatal.
if [[ -n "$label" && -n "${number:-}" ]]; then
  label_id="$(curl --max-time 15 -s -H "Authorization: token ${FORGEJO_TOKEN}" \
    "${FORGEJO_URL}/api/v1/repos/${FORGEJO_USER}/${repo}/labels" \
    | jq -r --arg n "$label" '.[] | select(.name==$n) | .id' | head -n1)"
  if [[ -n "$label_id" && "$label_id" != "null" ]]; then
    curl --max-time 15 -s -o /dev/null \
      -H "Authorization: token ${FORGEJO_TOKEN}" -H "Content-Type: application/json" \
      -X POST "${FORGEJO_URL}/api/v1/repos/${FORGEJO_USER}/${repo}/issues/${number}/labels" \
      -d "{\"labels\":[${label_id}]}" \
      && echo "label '${label}' applied" >&2
  else
    echo "open-pr: label '${label}' not found in repo — skipped." >&2
  fi
fi