skill-gitea/scripts/pr-create.sh

#!/usr/bin/env bash
# gitea skill — crear un PR.
#
# Uso:
#   pr-create.sh <owner>/<repo> --head <branch> [--base main] --title "..." \
#                (--body "..." | --body-file <path>) [--draft]
#
# Garantías:
#   - Body en UTF-8 puro (vía Python json.dumps + curl --data-binary @file)
#   - Anti-AI-attribution guard sobre title + body (rechaza si encuentra
#     "Co-Authored-By: Claude", "🤖", "Generated with Claude", "Anthropic" en
#     contexto de atribución)
#   - Trap EXIT borra el temp dir con el body al terminar

set -euo pipefail

# Forzar UTF-8 en stdout de Python. Windows defaultea a cp1252 y crashea
# con literales no-ASCII (e.g. el `OK`/`->` aquí abajo o un PR title con ñ).
# Ver memoria feedback_api_utf8_encoding.md.
export PYTHONIOENCODING=utf-8

SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
QUERY="$SKILL_DIR/scripts/query.sh"

repo_arg=""
head=""
base="main"
title=""
body=""
body_file=""
draft=0

while [[ $# -gt 0 ]]; do
  case "$1" in
    --head) head="$2"; shift 2 ;;
    --base) base="$2"; shift 2 ;;
    --title) title="$2"; shift 2 ;;
    --body) body="$2"; shift 2 ;;
    --body-file) body_file="$2"; shift 2 ;;
    --draft) draft=1; shift ;;
    -h|--help)
      cat <<EOF
Uso: pr-create.sh <owner>/<repo> --head <branch> [--base main] \\
                  --title "..." (--body "..." | --body-file <path>) [--draft]

Ejemplos:
  pr-create.sh NucleOS/nucleo-infra --head fix/foo --title "fix(x): ..." \\
    --body-file /tmp/pr-body.md

  pr-create.sh nucleo-infra --head feat/y --title "..." --body "linea 1"
EOF
      exit 0
      ;;
    -*) echo "ERROR: flag desconocida: $1" >&2; exit 2 ;;
    *)  repo_arg="$1"; shift ;;
  esac
done

if [[ -z "$repo_arg" || -z "$head" || -z "$title" ]]; then
  echo "ERROR: faltan args. Necesitás: <owner>/<repo> --head <branch> --title \"...\"" >&2
  exit 2
fi

# Resolver owner/repo
if [[ "$repo_arg" == */* ]]; then
  owner="${repo_arg%%/*}"
  repo="${repo_arg##*/}"
else
  set -a; source "$SKILL_DIR/.env"; set +a
  owner="${GITEA_DEFAULT_OWNER:?owner no especificado y GITEA_DEFAULT_OWNER vacío}"
  repo="$repo_arg"
fi

# Cargar body desde archivo si corresponde
if [[ -n "$body_file" ]]; then
  if [[ -n "$body" ]]; then
    echo "ERROR: pasá --body o --body-file, no ambos." >&2
    exit 2
  fi
  if [[ ! -f "$body_file" ]]; then
    echo "ERROR: --body-file '$body_file' no existe." >&2
    exit 2
  fi
  body="$(cat "$body_file")"
fi

# ─── Anti-AI-attribution guard ──────────────────────────────────────────
# Regla dura. Ver memoria feedback_no_ai_attribution.md.
combined="$title
$body"

ai_patterns=(
  "Co-Authored-By:[[:space:]]*Claude"
  "Co-Authored-By:[[:space:]]*Anthropic"
  "🤖"
  "Generated with[[:space:]]*\[?Claude"
  "Generated with[[:space:]]*Anthropic"
  "Created with[[:space:]]*\[?Claude"
  "Powered by[[:space:]]*Claude"
  "Made with[[:space:]]*Claude"
)

for pat in "${ai_patterns[@]}"; do
  if echo "$combined" | grep -iqE "$pat"; then
    cat >&2 <<EOF
ERROR: el title o body contiene marker de AI attribution:
  pattern: $pat

Esta skill bloquea esos markers (regla dura, ver memoria
feedback_no_ai_attribution.md). El usuario considera deshonesto darle crédito
a Claude/Anthropic por trabajo del usuario. Removelos y volvé a correr.

Líneas que matchean:
EOF
    echo "$combined" | grep -inE "$pat" | head -5 >&2
    exit 4
  fi
done

# ─── Build body JSON con Python (UTF-8 safe) ────────────────────────────
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "$TMP_DIR"' EXIT

BODY_JSON="$TMP_DIR/body.json"

PY_TITLE="$title" PY_BODY="$body" PY_HEAD="$head" PY_BASE="$base" PY_DRAFT="$draft" \
  python -c '
import json, os
data = {
    "title": os.environ["PY_TITLE"],
    "body": os.environ["PY_BODY"],
    "head": os.environ["PY_HEAD"],
    "base": os.environ["PY_BASE"],
}
if os.environ.get("PY_DRAFT") == "1":
    # Gitea no tiene draft API field, pero podés prefijar el title
    data["title"] = "[WIP] " + data["title"]
# json.dumps con ensure_ascii=True (default) escapa todo non-ASCII a \uXXXX,
# eliminando cualquier riesgo de encoding raro en transit.
print(json.dumps(data))
' > "$BODY_JSON"

# Sanity check
if [[ ! -s "$BODY_JSON" ]]; then
  echo "ERROR: body JSON vacío después de python. Bug del script." >&2
  exit 5
fi

echo "→ POST /repos/${owner}/${repo}/pulls" >&2
echo "  head: $head → base: $base" >&2
echo "  title: $title" >&2
echo "  body: ${#body} chars" >&2

resp="$("$QUERY" -X POST \
  -H 'Content-Type: application/json; charset=utf-8' \
  --data-binary @"$BODY_JSON" \
  "/repos/${owner}/${repo}/pulls")"

echo "$resp" | python -c "
import json, sys
d = json.load(sys.stdin)
if d.get('number'):
    print(f'✓ PR #{d[\"number\"]} creado')
    print(f'  url: {d.get(\"html_url\")}')
else:
    print('ERROR:', d.get('message') or d, file=sys.stderr)
    sys.exit(1)
"