gstack/bin/gstack-jsonl-merge

#!/usr/bin/env bash
# gstack-jsonl-merge — git merge driver for append-only JSONL files.
#
# Usage (called by git, not by users):
#   gstack-jsonl-merge <base> <ours> <theirs>
#
# Registered in local git config by bin/gstack-brain-init and
# bin/gstack-brain-restore:
#   git config merge.jsonl-append.driver \
#       "$GSTACK_BIN/gstack-jsonl-merge %O %A %B"
#
# Behavior:
#   Concatenate base + ours + theirs, dedup exact-duplicate lines, sort by
#   ISO "ts" field when present, fall back to SHA-256 of the line for
#   deterministic order. Write result to <ours> (the %A file per the git
#   merge-driver contract).
#
#   Two machines appending to the same JSONL file between pushes produces
#   a same-line conflict at the file tail. This driver resolves it cleanly:
#   both appends survive, ordered by wall-clock timestamp where available,
#   content hash otherwise.
#
# Exit codes:
#   0 — merge succeeded, result written to <ours>
#   1 — error; git treats as conflict and stops the merge

set -uo pipefail

if [ "$#" -lt 3 ]; then
  echo "gstack-jsonl-merge: expected 3 args (base ours theirs), got $#" >&2
  exit 1
fi

BASE="$1"
OURS="$2"
THEIRS="$3"

TMP=$(mktemp /tmp/gstack-jsonl-merge.XXXXXX) || exit 1
trap 'rm -f "$TMP" 2>/dev/null || true' EXIT

python3 - "$BASE" "$OURS" "$THEIRS" > "$TMP" <<'PYEOF'
import sys, json, hashlib

paths = sys.argv[1:4]  # base, ours, theirs
seen = {}  # line content -> sort_key

for path in paths:
    try:
        with open(path, 'r', encoding='utf-8') as f:
            for line in f:
                line = line.rstrip('\n')
                if not line:
                    continue
                if line in seen:
                    continue
                # Prefer ISO ts field for sort; fall back to SHA-256.
                sort_key = None
                try:
                    obj = json.loads(line)
                    ts = obj.get('ts') or obj.get('timestamp')
                    if isinstance(ts, str):
                        sort_key = (0, ts)
                except (json.JSONDecodeError, ValueError, TypeError):
                    pass
                if sort_key is None:
                    h = hashlib.sha256(line.encode('utf-8')).hexdigest()
                    sort_key = (1, h)
                seen[line] = sort_key
    except FileNotFoundError:
        # Absent base / absent ours / absent theirs are all valid.
        continue
    except OSError:
        # Permission / IO errors are fatal — caller sees non-zero exit.
        sys.exit(1)

# Timestamp-ordered entries first (group 0), then hash-ordered (group 1).
for line, _ in sorted(seen.items(), key=lambda item: item[1]):
    print(line)
PYEOF

_PYEXIT=$?
if [ "$_PYEXIT" != "0" ]; then
  exit 1
fi

mv "$TMP" "$OURS" || exit 1
trap - EXIT
exit 0