Repeated Markdown headings collapse into one Section and misattribute references #2586

#!/bin/bash
# Standalone reproductions for codebase-memory-mcp issue reports.
# Usage: CBM="codebase-memory-mcp cli" ./repro.sh [1a|1b|1c|1d|2|3|4|5 ...]
# Needs: git, python3. Each case uses a fresh throwaway repository.
#
# Every case asserts the defective outcome it reports:
#   REPRODUCED      the defect is present (expected on the reported build)
#   NOT REPRODUCED  the observed value differs (fixed, or environment differs)
# Exit status: 0 all reproduced, 1 any not reproduced, 2 a command failed.
set -eEuo pipefail
shopt -s inherit_errexit
CBM=${CBM:-"codebase-memory-mcp cli"}
WORK=${WORK:-$(mktemp -d)}
REPO="" PROJ="" MISSED=0

# A failure anywhere, including inside $(...), leaves a marker so the case
# reports a command error instead of a misleading NOT REPRODUCED.
die() { echo "ERROR: $*" >&2; : > "$WORK/failed"; exit 2; }
trap 'die "command failed at line $LINENO: $BASH_COMMAND"' ERR

# Run one CLI tool; a nonzero exit or non-JSON output stops the script.
# index_repository always answers in JSON and takes no --format flag.
cbm() {
  local out format=(--format json)
  [ "$1" = index_repository ] && format=()
  out=$($CBM "$@" "${format[@]}" 2>"$WORK/stderr") || { cat "$WORK/stderr" >&2; die "$CBM $1 exited nonzero"; }
  python3 -c 'import json,sys; json.loads(sys.argv[1])' "$out" 2>/dev/null || die "$CBM $1 returned non-JSON: $out"
  printf '%s' "$out"
}
py() { python3 -c "import json,sys; d=json.loads(sys.argv[1]); print($2)" "$1"; }
redact() { sed -e "s|$REPO|<repo>|g" -e "s|$PROJ|<project>|g"; }

expect() {  # expect <claim> <actual> <value-that-shows-the-defect>
  if [ "$2" = "$3" ]; then echo "REPRODUCED: $1"
  else echo "NOT REPRODUCED: $1"; echo "  expected: $3"; echo "  actual:   $2"; MISSED=1; fi
}

new_repo() {
  REPO=$(mktemp -d "$WORK/repo.XXXX")
  cd "$REPO"
  git init -q && git config user.email t@t && git config user.name t
  mkdir -p src/util docs
  printf 'def post_entry(ledger, amount):\n    ledger.append(amount)\n    return balance(ledger)\n\n\ndef balance(ledger):\n    return sum(ledger)\n' > src/ledger.py
  printf 'def clamp(x, lo, hi):\n    return max(lo, min(hi, x))\n' > src/util/rounding.py
}
commit() { git add -A && git commit -qm "$1"; }
index() { local out; out=$(cbm index_repository --repo-path "$REPO"); PROJ=$(py "$out" 'd["project"]'); }
coverage() { cbm check_index_coverage --project "$PROJ" --paths "[\"$1\"]"; }
fresh() { local out; out=$(coverage "$1"); py "$out" 'd["paths"][0]["freshness"]'; }
generation() { local out; out=$(coverage src/ledger.py); py "$out" 'd["metadata"]["generation"]'; }
cypher() { local out; out=$(cbm query_graph --project "$PROJ" --query "$1"); py "$out" 'd["rows"]' | redact; }
snippet() { local out; out=$(cbm get_code_snippet --project "$PROJ" --qualified-name "$1" --source-mode full)
            py "$out" 'repr((d["start_line"], d["end_line"], d["source"]))'; }
doc_links() { local out; out=$(cbm index_status --project "$PROJ" --diagnostics full); py "$out" 'repr((d["doc_links"]["mentions"], d["doc_links"]["unresolved"]))'; }

case_1a() {  # exposed generation does not change on incremental re-index
  new_repo; commit init; index
  local first; first=$(generation); echo "generation after full index: $first"
  for i in 1 2; do
    sleep 1.1; echo "# edit $i" >> src/ledger.py; index
    local now; now=$(generation); echo "generation after edit $i + index: $now"
    expect "generation unchanged after incremental re-index $i" "$now" "$first"
  done
}
case_1b() {  # snippet mixes indexed line range with current disk bytes
  new_repo; commit init; index
  local before after; before=$(snippet balance); echo "indexed snippet of balance: $before"
  printf '# a\n# b\n# c\n' | cat - src/ledger.py > "$WORK/shifted" && mv "$WORK/shifted" src/ledger.py
  local state; state=$(fresh src/ledger.py); echo "after inserting 3 lines at top, no re-index; freshness=$state"
  after=$(snippet balance); echo "snippet of balance now: $after"
  expect "snippet for balance returns another function's lines" "$after" "(6, 7, '    return balance(ledger)\\n\\n')"
}
case_1c() {  # same-size edit with restored mtime passes freshness
  new_repo; commit init; index
  touch -r src/ledger.py "$WORK/mtime-ref"
  sed -i 's/return sum(ledger)/return max(ledger)/' src/ledger.py
  touch -r "$WORK/mtime-ref" src/ledger.py
  echo "content changed: $(git diff --numstat -- src/ledger.py) (same size, original mtime)"
  expect "freshness reports a content change as current" "$(fresh src/ledger.py)" "metadata_match"
}
case_1d() {  # identical bytes with new mtime stay metadata_changed after re-index
  new_repo; commit init; index
  echo "# tmp" >> src/ledger.py; git checkout -q -- src/ledger.py   # identical bytes, new mtime
  echo "git status after restore: '$(git status --short)'"
  index; expect "freshness stale after re-index of identical bytes" "$(fresh src/ledger.py)" "metadata_changed"
  index; expect "freshness stale after second re-index" "$(fresh src/ledger.py)" "metadata_changed"
}
case_2() {  # repeated headings collapse; references misattributed
  new_repo
  printf '# Service A\n\n## Implementation\n\nUses `src/ledger.py::balance`.\n\n# Service B\n\n## Implementation\n\nUses `src/ledger.py::post_entry`.\n' > docs/repeated.md
  commit init; index
  local sections sources
  sections=$(cypher 'MATCH (s:Section) WHERE s.file_path = "docs/repeated.md" AND s.name = "Implementation" RETURN s.qualified_name, s.start_line')
  sources=$(cypher 'MATCH (s)-[:MENTIONS]->(c) WHERE s.file_path = "docs/repeated.md" RETURN s.label, c.name ORDER BY c.name')
  echo "Implementation sections: $sections"; echo "MENTIONS sources: $sources"
  expect "two Implementation headings yield one Section" "$sections" "[['<project>.docs.repeated.Implementation', '9']]"
  expect "references under them are attributed to the File" "$sources" "[['File', 'balance'], ['File', 'post_entry']]"
}
case_3() {  # missing member silently becomes a file edge
  new_repo
  printf '# Notes\n\nSee `src/util/rounding.py::no_such_function`.\n' > docs/notes.md
  commit init; index
  local edges; edges=$(cypher 'MATCH (s)-[r:MENTIONS]->(c) WHERE s.file_path = "docs/notes.md" RETURN c.label, c.name, r.tier')
  echo "MENTIONS: $edges"; echo "doc_links (mentions, unresolved): $(doc_links)"
  expect "missing member resolves as an exact File edge" "$edges" "[['File', 'rounding.py', 'exact']]"
  expect "no unresolved row records the missing member" "$(doc_links)" "(1, {})"
}
case_4() {  # references into a moved directory vanish without unresolved rows
  new_repo
  printf '# Notes\n\nSee `src/util/rounding.py::clamp`.\n' > docs/notes.md
  commit init; index
  echo "before move: $(cypher 'MATCH (s)-[:MENTIONS]->(c) RETURN c.name')"
  git mv src/util src/helpers; index
  local edges; edges=$(cypher 'MATCH (s)-[:MENTIONS]->(c) RETURN c.name')
  echo "after git mv src/util src/helpers and re-index: MENTIONS=$edges doc_links=$(doc_links)"
  expect "reference into moved directory disappears" "$edges" "[]"
  expect "no unresolved row records it" "$(doc_links)" "(0, {})"
}
case_5() {  # enhancement context: a doc-only edit yields no detect_changes seeds
  new_repo
  printf '# Notes\n\n## Posting\n\nPosting uses `src/ledger.py::post_entry`.\n' > docs/notes.md
  commit init; index
  echo "MENTIONS from the section: $(cypher 'MATCH (s:Section)-[:MENTIONS]->(c) RETURN s.name, c.name')"
  sed -i 's/Posting uses/Posting always uses/' docs/notes.md; index
  local out; out=$(cbm detect_changes --project "$PROJ" --edge-types '["CALLS","MENTIONS"]')
  echo "doc-only edit: $(py "$out" 'repr((d["changed_files"], d["seed_symbols"]))')"
  expect "doc-only edit produces zero seeds" "$(py "$out" 'd["seed_symbols"]')" "0"
}

trap - ERR
for c in "${@:-1a 1b 1c 1d 2 3 4 5}"; do for one in $c; do
  echo "=== case $one"
  rm -f "$WORK/failed"
  set +e
  ( set -e; trap 'die "command failed at line $LINENO: $BASH_COMMAND"' ERR; "case_$one"; exit "$MISSED" )
  status=$?
  set -e
  if [ -e "$WORK/failed" ] || [ "$status" -gt 1 ]; then echo "case $one: COMMAND FAILED" >&2; exit 2; fi
  [ "$status" -eq 1 ] && MISSED=1
done; done
[ "$MISSED" -eq 0 ] && echo "=== all cases reproduced" || echo "=== some cases did not reproduce"
exit "$MISSED"