From 86ccf2c47a4eb471ea56985441af44132e9dea52 Mon Sep 17 00:00:00 2001
From: Michal Pemcak <m.pemcak@gmail.com>
Date: Mon, 19 Oct 2026 18:39:31 +0200
Subject: [PATCH] build: add commit hooks

---
 .githooks/check-large-files.sh | 14 ++++++++++++++
 .githooks/commit-msg-check.sh  | 27 +++++++++++++++++++++++++++
 lefthook.yml                   | 22 ++++++++++++++++++++++
 3 files changed, 63 insertions(+)
 create mode 100755 .githooks/check-large-files.sh
 create mode 100755 .githooks/commit-msg-check.sh
 create mode 100644 lefthook.yml

diff --git a/.githooks/check-large-files.sh b/.githooks/check-large-files.sh
new file mode 100755
index 0000000..94502de
--- /dev/null
+++ b/.githooks/check-large-files.sh
@@ -0,0 +1,14 @@
+#!/bin/sh
+# Block staged files over the limit: checkpoints, datasets and binaries stay out of git.
+# Called by lefthook as: check-large-files.sh {staged_files}
+limit_mb="${MAX_FILE_MB:-5}"
+limit=$((limit_mb * 1024 * 1024))
+status=0
+for file in "$@"; do
+  size=$(git cat-file -s ":$file" 2>/dev/null) || continue
+  if [ "$size" -gt "$limit" ]; then
+    echo "large file: $file is $((size / 1024 / 1024)) MB (limit ${limit_mb} MB). Add it to .gitignore." >&2
+    status=1
+  fi
+done
+exit $status
diff --git a/.githooks/commit-msg-check.sh b/.githooks/commit-msg-check.sh
new file mode 100755
index 0000000..129be43
--- /dev/null
+++ b/.githooks/commit-msg-check.sh
@@ -0,0 +1,27 @@
+#!/bin/sh
+# Conventional Commits with a short subject; no AI attribution.
+# Called by lefthook as: commit-msg-check.sh <message-file>
+msg_file="$1"
+subject=$(sed -n '1p' "$msg_file")
+
+case "$subject" in
+  Merge\ * | Revert\ * | fixup!\ * | squash!\ * | amend!\ *) exit 0 ;;
+esac
+
+types='feat|fix|refactor|perf|docs|test|build|ci|chore|style|revert|exp'
+if ! printf '%s\n' "$subject" | grep -Eq "^($types)(\([a-z0-9._/-]+\))?!?: [^ ].*$"; then
+  echo "commit-msg: subject must be '<type>(<scope>): <summary>'" >&2
+  echo "  types: ${types}" >&2
+  echo "  got:   $subject" >&2
+  exit 1
+fi
+
+if [ "${#subject}" -gt 72 ]; then
+  echo "commit-msg: subject is ${#subject} chars, keep it at 72 or less (aim for ~50)" >&2
+  exit 1
+fi
+
+if grep -Eiq 'co-authored-by:[[:space:]]*claude|noreply@anthropic\.com|generated with \[?claude code' "$msg_file"; then
+  echo "commit-msg: no AI attribution lines in commit messages" >&2
+  exit 1
+fi
diff --git a/lefthook.yml b/lefthook.yml
new file mode 100644
index 0000000..9c94bfa
--- /dev/null
+++ b/lefthook.yml
@@ -0,0 +1,22 @@
+# Commit checks. Generated by project-bootstrap; coding agents may not edit it.
+# Remove the sections for languages the project doesn't use.
+# Formatter (biome) intentionally not enforced repo-wide: the codebase is
+# pre-existing, unformatted (spaces), and has no config — it gets formatted
+# file by file as files are touched, not in a mass reformat.
+pre-commit:
+  parallel: true
+  commands:
+    gitleaks:
+      run: gitleaks git --pre-commit --staged --no-banner --redact
+    large-files:
+      run: .githooks/check-large-files.sh {staged_files}
+
+    # --- shell ---
+    shellcheck:
+      glob: "*.sh"
+      run: shellcheck {staged_files}
+
+commit-msg:
+  commands:
+    conventional:
+      run: .githooks/commit-msg-check.sh {1}