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

usage() {
  cat <<EOF
Usage: validate-drift.sh <repo-root>

Check every AGENTS.md file in a repo (root and nested) for drift: package
manager scripts and file paths referenced in the text that no longer exist
in the repo. Catches the failure mode that matters most in practice — an
agent running a documented command that was renamed or deleted.

Arguments:
  repo-root  Path to the repository root to scan.

Exit codes:
  0  No FAIL findings (INFO may still be printed, e.g. no package.json found)
  1  One or more FAIL findings
EOF
}

if [[ "${1:-}" == "--help" || "${1:-}" == "-h" ]]; then
  usage
  exit 0
fi

if [[ $# -lt 1 ]]; then
  echo "Error: repo-root is required." >&2
  echo "" >&2
  usage >&2
  exit 1
fi

python3 -u - "$1" <<'PYTHON'
import sys
import os
import re
import json

repo_root = os.path.abspath(sys.argv[1])
if not os.path.isdir(repo_root):
    print(f"Error: '{repo_root}' is not a directory.", file=sys.stderr)
    sys.exit(1)

EXCLUDE_DIRS = {".git", "node_modules", "vendor", ".venv", "venv", "dist", "build"}

def find_agents_md(root):
    results = []
    for dirpath, dirnames, filenames in os.walk(root):
        dirnames[:] = [d for d in dirnames if d not in EXCLUDE_DIRS and not d.startswith(".")]
        for fname in filenames:
            if fname == "AGENTS.md":
                results.append(os.path.join(dirpath, fname))
    return sorted(results)

def load_package_scripts(root):
    pkg_path = os.path.join(root, "package.json")
    if not os.path.isfile(pkg_path):
        return None
    try:
        with open(pkg_path, encoding="utf-8") as f:
            data = json.load(f)
    except (json.JSONDecodeError, OSError):
        return None
    return set(data.get("scripts", {}).keys())

def load_make_targets(root):
    make_path = os.path.join(root, "Makefile")
    if not os.path.isfile(make_path):
        return None
    with open(make_path, encoding="utf-8", errors="replace") as f:
        content = f.read()
    return set(re.findall(r'(?m)^([a-zA-Z0-9_-]+)\s*:(?!=)', content))

NPM_RUN_RE = re.compile(r'\b(?:npm|pnpm|yarn)\s+run\s+([a-zA-Z0-9:_-]+)')
MAKE_RE = re.compile(r'\bmake\s+([a-zA-Z0-9_-]+)')

# Backticked relative file paths, e.g. `scripts/bootstrap.sh`, `src/index.ts`.
# Requires a path separator and file extension to avoid matching bare commands/words.
PATH_RE = re.compile(r'`([A-Za-z0-9_.\-]+(?:/[A-Za-z0-9_.\-]+)+\.[A-Za-z0-9]+)`')

has_fail = False

package_scripts = load_package_scripts(repo_root)
make_targets = load_make_targets(repo_root)

for fpath in find_agents_md(repo_root):
    rel = os.path.relpath(fpath, repo_root)
    with open(fpath, encoding="utf-8", errors="replace") as f:
        content = f.read()

    for m in NPM_RUN_RE.finditer(content):
        script_name = m.group(1)
        if package_scripts is None:
            print(f"INFO  Cannot verify referenced script '{script_name}' — {rel}")
            print(f"      Note: AGENTS.md references an npm/pnpm/yarn script, but no package.json was found at the repo root to check it against.")
            print()
        elif script_name not in package_scripts:
            has_fail = True
            print(f"FAIL  Referenced script '{script_name}' not found in package.json — {rel}")
            print(f"      Why: AGENTS.md tells agents to run '{script_name}', but package.json has no matching \"scripts\" entry — the command will fail.")
            print(f"      Fix: Update AGENTS.md to reference an existing script, or add '{script_name}' to package.json's scripts.")
            print()

    for m in MAKE_RE.finditer(content):
        target_name = m.group(1)
        if make_targets is None:
            print(f"INFO  Cannot verify referenced make target '{target_name}' — {rel}")
            print(f"      Note: AGENTS.md references a make target, but no Makefile was found at the repo root to check it against.")
            print()
        elif target_name not in make_targets:
            has_fail = True
            print(f"FAIL  Referenced make target '{target_name}' not found in Makefile — {rel}")
            print(f"      Why: AGENTS.md tells agents to run 'make {target_name}', but the Makefile has no matching target — the command will fail.")
            print(f"      Fix: Update AGENTS.md to reference an existing target, or add '{target_name}' to the Makefile.")
            print()

    file_dir = os.path.dirname(fpath)
    for m in PATH_RE.finditer(content):
        candidate = m.group(1)
        resolved = (
            os.path.isfile(os.path.join(repo_root, candidate))
            or os.path.isfile(os.path.join(file_dir, candidate))
            or os.path.isdir(os.path.join(repo_root, candidate))
            or os.path.isdir(os.path.join(file_dir, candidate))
        )
        if not resolved:
            has_fail = True
            print(f"FAIL  Referenced path '{candidate}' does not exist — {rel}")
            print(f"      Why: AGENTS.md points agents to '{candidate}', but it isn't present in the repo (checked relative to repo root and to the AGENTS.md's own directory).")
            print(f"      Fix: Update AGENTS.md to reference the correct path, or restore/create '{candidate}'.")
            print()

if has_fail:
    sys.exit(1)
sys.exit(0)
PYTHON