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

# Fails a push when a skill changed without its SKILL.md `metadata.version`
# being bumped. ADR-0022 makes the field mandatory and the bump the rule; this
# is the gate that holds the rule, since skill-size-check only checks presence
# and shape.
#
# Baseline: `git merge-base <main> <pushed commit>`, where <main> is origin/main
# when it resolves and the local `main` branch otherwise. Readers install
# skills from main, so "changed" means changed relative to what main ships, not
# relative to the remote branch's current tip. Diffing from PRE_COMMIT_FROM_REF
# would let the second push of a feature branch excuse a change the first push
# already carried unbumped. The check runs on every push whatever the target
# branch — nothing here reads PRE_COMMIT_REMOTE_BRANCH — so it also runs under
# a manual `pre-commit run --hook-stage pre-push` (against HEAD, since no
# PRE_COMMIT_TO_REF is set). A missing bump is cheapest to fix on the branch,
# before review.
#
# Pushing main itself: with origin/main as the baseline, a push of main diffs
# the new commits against what the remote already has, so it is covered. A
# pushed commit that is already an ancestor of origin/main (merge-base equals
# the pushed commit) changes nothing relative to main and passes. With only the
# local `main` fallback, pushing main makes the merge-base the pushed commit
# itself — the diff is empty by construction, not because nothing changed — so
# that combination FAILS closed rather than passing unchecked.
#
# Scope: every skill directory plugins/<plugin>/.apm/skills/<skill>/, bin
# included. Anything under <skill>/tests/ is ignored — no agent ever loads it,
# so a test-only change ships nothing to a reader. A skill counts as changed
# when any other file under its directory differs between baseline and pushed
# commit. Paths are read NUL-delimited (`git diff -z`), so core.quotePath never
# hides a non-ASCII path. Renames are diffed as delete + add (--no-renames), so:
#   - a skill absent at the baseline (new, renamed-to, merged-into) is exempt;
#     it has no prior version to exceed.
#   - a skill directory absent at the pushed commit (deleted, renamed-from) is
#     exempt; there is nothing left to version. A directory that survives
#     without its SKILL.md is NOT exempt: it fails as "SKILL.md missing".
# A changed skill present at both refs must carry a three-part semver
# `metadata.version` at the pushed commit that is numerically greater than the
# baseline's. The shape rule follows skill-size-check.sh (str()-coerce, strip
# whitespace and quotes, three dot-separated numbers, so `1.0` and `1.0.0-rc1`
# are rejected) but is deliberately stricter: ASCII digits only (Python's `\d`
# also matches e.g. U+FF11) and at most 9 digits per part, so every part fits
# bash arithmetic. A baseline with no valid version (a skill predating
# ADR-0022) accepts any valid version. Versions are read from git objects,
# never the working tree.
#
# Fails closed: if neither origin/main nor main resolves, if no merge-base
# exists (shallow clone, unrelated history), if the pushed ref does not resolve
# to a commit, if python3 or PyYAML is unavailable, or if a SKILL.md cannot be
# read. Passing in any of those would make that environment the one place the
# rule is silently off.
#
# Known gaps:
#   - Only the first pushed ref is gated. pre-commit (4.x, hook_impl.py
#     `_pre_push_ns`) consumes the pre-push stdin itself and builds the
#     environment from the first ref line that is not a delete and has commits
#     the remote lacks; every later ref in the same `git push` (e.g.
#     `git push origin a b`, `--all`, `--tags`) is never seen. When that first
#     ref's unpushed history reaches a root commit, pre-commit runs with
#     all_files and sets no PRE_COMMIT_TO_REF at all, so this script checks
#     HEAD — which is the pushed ref only if it happens to be checked out. The
#     script cannot recover either case: the ref list is gone by the time it
#     runs. Push refs one at a time to be sure each is checked.
#   - A PR merged via Gitea's merge button runs no local hook at all (the same
#     gap check-release-needed has). Closing it requires a server-side CI job,
#     which this repo does not have yet.

# Byte-wise regex matching and messages: path bytes are matched against
# SKILL_PATH_RE below and must not depend on the caller's locale.
export LC_ALL=C

# PRE_COMMIT_TO_REF is the local object actually being pushed, which is only
# HEAD for the common case. For a tag push it is the tag object, so it is
# peeled to a commit below before use.
PUSHED_REF="${PRE_COMMIT_TO_REF:-HEAD}"

# All-zeros sha: the push deletes a branch. Nothing ships; bail out.
if [[ "$PUSHED_REF" =~ ^0+$ ]]; then
  exit 0
fi

REPO_ROOT="$(git rev-parse --show-toplevel)"
cd "$REPO_ROOT"

if ! command -v python3 > /dev/null 2>&1; then
  echo "FAIL: python3 is required to read SKILL.md metadata.version but was not found on PATH." >&2
  echo "  Fix: install python3 (pre-commit itself is a Python application, so it is almost certainly already present)." >&2
  exit 1
fi

if ! python3 -c 'import yaml' > /dev/null 2>&1; then
  echo "FAIL: PyYAML is required to read SKILL.md metadata.version but is not importable by python3." >&2
  echo "  Fix: python3 -m pip install PyYAML   (or your distro's python3-yaml package)." >&2
  exit 1
fi

if ! PUSHED_COMMIT="$(git rev-parse --verify -q "$PUSHED_REF^{commit}")"; then
  echo "FAIL: pushed ref $PUSHED_REF does not resolve to a commit." >&2
  exit 1
fi

MAIN_REF=""
for candidate in origin/main main; do
  if git rev-parse --verify -q "$candidate^{commit}" > /dev/null; then
    MAIN_REF="$candidate"
    break
  fi
done

if [[ -z "$MAIN_REF" ]]; then
  echo "FAIL: neither origin/main nor main resolves, so there is no baseline to compare skill versions against." >&2
  echo "  Fix: git fetch origin main (or create a local main) and retry." >&2
  exit 1
fi

if ! BASELINE="$(git merge-base "$MAIN_REF" "$PUSHED_COMMIT" 2>/dev/null)"; then
  echo "FAIL: no merge-base between $MAIN_REF and $PUSHED_REF, so there is no baseline to compare skill versions against." >&2
  echo "  Fix: ensure full history is available (e.g. git fetch --unshallow) and retry." >&2
  exit 1
fi

if [[ "$MAIN_REF" == "main" && "$BASELINE" == "$PUSHED_COMMIT" ]]; then
  echo "FAIL: origin/main does not resolve and $PUSHED_REF is already contained in local main, so local main cannot serve as an independent baseline — the diff would be empty by construction." >&2
  echo "  Fix: git fetch origin main and retry." >&2
  exit 1
fi

CHANGED_FILE="$(mktemp)"
trap 'rm -f "$CHANGED_FILE"' EXIT

if ! git diff -z --no-renames --name-only "$BASELINE" "$PUSHED_COMMIT" -- plugins > "$CHANGED_FILE"; then
  echo "FAIL: could not diff $BASELINE..$PUSHED_REF (see git error above)." >&2
  exit 1
fi

SKILL_PATH_RE='^(plugins/[^/]+/\.apm/skills/[^/]+)/(.+)$'
SKILL_DIRS=()
while IFS= read -r -d '' path; do
  [[ "$path" =~ $SKILL_PATH_RE ]] || continue
  [[ "${BASH_REMATCH[2]}" == tests/* ]] && continue
  dir="${BASH_REMATCH[1]}"
  seen=false
  for existing in ${SKILL_DIRS[@]+"${SKILL_DIRS[@]}"}; do
    [[ "$existing" == "$dir" ]] && { seen=true; break; }
  done
  $seen || SKILL_DIRS+=("$dir")
done < "$CHANGED_FILE"

[[ ${#SKILL_DIRS[@]} -eq 0 ]] && exit 0

# Reads SKILL.md bytes on stdin and prints exactly one line: `OK <version>`
# when metadata.version is a valid three-part semver, `INVALID` when it is
# missing or malformed (including unparseable frontmatter). Any other outcome —
# python3 crashing, PyYAML failing to import — is a non-zero exit with no OK /
# INVALID line, which the caller reports as a read failure, never as a missing
# version. Bytes are decoded explicitly so the caller's locale cannot turn a
# non-ASCII SKILL.md into a crash; `\s*` before each `\n` absorbs CRLF.
read_version() {
  python3 -c '
import re, sys, yaml
text = sys.stdin.buffer.read().decode("utf-8", errors="replace")
m = re.match(r"---[ \t\r]*\n(.*?)\n---[ \t\r]*(\n|\Z)", text, re.S)
data = None
if m:
    try:
        data = yaml.safe_load(m.group(1))
    except yaml.YAMLError:
        data = None
meta = data.get("metadata") if isinstance(data, dict) else None
ver = meta.get("version") if isinstance(meta, dict) else None
ver = None if ver is None else str(ver).strip().strip("\x27\"")
if ver is not None and re.fullmatch(r"[0-9]{1,9}\.[0-9]{1,9}\.[0-9]{1,9}", ver):
    print("OK " + ver)
else:
    print("INVALID")
'
}

# version_at <commit> <path>: sets VERSION to the valid version or "" when
# invalid. Exits the script on a read failure.
version_at() {
  local out
  if ! out="$(git show "$1:$2" | read_version)" || [[ "$out" != OK\ * && "$out" != INVALID ]]; then
    echo "FAIL: could not read metadata.version from $1:$2 (see error above)." >&2
    exit 1
  fi
  VERSION=""
  [[ "$out" == OK\ * ]] && VERSION="${out#OK }"
  return 0
}

# Exit 0 when $1 > $2, both MAJOR.MINOR.PATCH with parts of at most 9 ASCII
# digits, compared numerically so 1.0.10 > 1.0.9. 10# forces base 10 on a
# leading zero.
semver_gt() {
  local -a a b
  local i
  IFS=. read -ra a <<< "$1"
  IFS=. read -ra b <<< "$2"
  for i in 0 1 2; do
    if (( 10#${a[i]} > 10#${b[i]} )); then return 0; fi
    if (( 10#${a[i]} < 10#${b[i]} )); then return 1; fi
  done
  return 1
}

OFFENDERS=()
for dir in ${SKILL_DIRS[@]+"${SKILL_DIRS[@]}"}; do
  # Absent at baseline: new, renamed-to, or merged-into. Exempt.
  git cat-file -e "$BASELINE:$dir/SKILL.md" 2>/dev/null || continue
  # Directory absent at pushed commit: deleted or renamed-from. Exempt.
  [[ "$(git cat-file -t "$PUSHED_COMMIT:$dir" 2>/dev/null)" == "tree" ]] || continue

  version_at "$BASELINE" "$dir/SKILL.md"
  base_ver="$VERSION"

  if ! git cat-file -e "$PUSHED_COMMIT:$dir/SKILL.md" 2>/dev/null; then
    OFFENDERS+=("$dir: SKILL.md missing at $PUSHED_REF (baseline: ${base_ver:-none})")
    continue
  fi
  version_at "$PUSHED_COMMIT" "$dir/SKILL.md"
  cur_ver="$VERSION"

  if [[ -z "$cur_ver" ]]; then
    OFFENDERS+=("$dir: metadata.version missing or not MAJOR.MINOR.PATCH at $PUSHED_REF (baseline: ${base_ver:-none})")
  elif [[ -n "$base_ver" ]] && ! semver_gt "$cur_ver" "$base_ver"; then
    OFFENDERS+=("$dir: $base_ver -> $cur_ver")
  fi
done

if [[ ${#OFFENDERS[@]} -gt 0 ]]; then
  echo "FAIL: skills changed since merge-base with $MAIN_REF without a metadata.version bump (ADR-0022):" >&2
  printf '    %s\n' ${OFFENDERS[@]+"${OFFENDERS[@]}"} >&2
  echo "  Fix: raise metadata.version in each SKILL.md above the baseline — bump PATCH at minimum." >&2
  exit 1
fi