improvise/scripts/fmt-workspaces.sh

#!/usr/bin/env bash
# Format-checks every Cargo workspace root in the repo, from any directory.
# `cargo fmt --all` reaches only ONE of them. Reasoning: context/test-evidence/
# tooling.md, "The two-workspace fmt gate" -- including why `-p` scoped by `--manifest-path` is the only
# spelling that is neither blind nor boundary-crossing (improvise-b4ks).
set -uo pipefail

usage() {
  cat >&2 <<'EOF'
usage: fmt-workspaces.sh [--list] [--fix] [repo-root]

  repo-root   the tree to scan; defaults to the directory above this script
  --list      print each workspace root and its members, then exit
  --fix       rewrite the offending files instead of reporting them

exit 0  every workspace root is formatted
exit 1  rustfmt did not certify a root clean: a file differs from rustfmt's
        output, or rustfmt refused to parse one. Either way a FILE IS NAMED
        and the tree is what is wrong.
exit 2  the gate did not run: usage error, no cargo, no rustfmt, cargo
        metadata failed, no [workspace] root found, or a [package] that no
        root has as a member. NO verdict was produced. No SOURCE file is
        named; the unreached-package case names its Cargo.toml.

The split is "did the gate run", not "is every exit-1 cause a diff". That is
narrower than it sounds and it is deliberate -- see the note on rc=1 below.

Exit 2 exists because `cargo fmt -p opfs-contract -- --check` from the repo
root exits 1 with `not a member of the workspace`, having checked nothing and
named nothing, which a caller reading $? cannot tell from a real failure.
Never collapse 2 into 1.
EOF
}

# `[workspace]` at the start of a line, in a Cargo.toml that is not vendored
# build output. `harness/opfs-contract` carries an empty one, so it is its own
# root and the outer `--all` never reaches it.
#
# The find is RELATIVE to the tree being scanned: an absolute `-path` filter
# matches the ancestors too, and this repo is itself checked out under
# `.claude/worktrees/` in every agent worktree, where that excluded everything.
manifests_with() {
  local root="$1" section="$2"
  ( cd "$root" && find . -name Cargo.toml \
       -not -path './target/*' -not -path '*/target/*' \
       -not -path './.git/*' \
       -not -path '*/node_modules/*' \
       -not -path './.claude/*' ) \
    | sort \
    | while IFS= read -r rel; do
        if grep -q "^\\[$section\\]" "$root/${rel#./}"; then
          printf '%s\n' "$root/${rel#./}"
        fi
      done
}
workspace_roots() { manifests_with "$1" workspace; }

# The members of ONE workspace, named by cargo rather than parsed out of the
# manifest: a `members = [...]` list may carry globs and path dependencies.
members_of() {
  local manifest="$1" meta
  meta="$(cargo metadata --manifest-path "$manifest" --no-deps --format-version 1 2>/dev/null)" || return 1
  printf '%s' "$meta" | python3 -c '
import json, sys
doc = json.load(sys.stdin)
rows = [p["name"] + "\t" + p["manifest_path"] for p in doc["packages"]]
if not rows:
    sys.exit(1)
print("\n".join(rows))
' || return 1
}

main() {
  local list=0 mode=--check root=""
  while [ $# -gt 0 ]; do
    case "$1" in
      --list) list=1 ;;
      --fix) mode=--fix ;;
      -h|--help) usage; return 2 ;;
      -*) printf 'fmt-workspaces: unknown option %s\n' "$1" >&2; usage; return 2 ;;
      *)
        if [ -n "$root" ]; then
          printf 'fmt-workspaces: at most one repo-root, got %s and %s\n' "$root" "$1" >&2
          return 2
        fi
        root="$1" ;;
    esac
    shift
  done

  if [ -z "$root" ]; then root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"; fi
  if [ ! -d "$root" ]; then
    printf 'fmt-workspaces: not a directory: %s\n' "$root" >&2
    return 2
  fi
  command -v cargo >/dev/null 2>&1 || {
    echo 'fmt-workspaces: cargo is not on PATH' >&2; return 2; }
  # Without this, a missing rustfmt component exits 1 from `cargo fmt` and
  # reads as "your code is misformatted" -- the very confusion this exists for.
  cargo fmt --version >/dev/null 2>&1 || {
    echo 'fmt-workspaces: cargo fmt is unavailable (rustfmt component missing?)' >&2
    return 2; }

  local -a roots=()
  while IFS= read -r m; do [ -n "$m" ] && roots+=("$m"); done < <(workspace_roots "$root")
  if [ ${#roots[@]} -eq 0 ]; then
    printf 'fmt-workspaces: no [workspace] root under %s\n' "$root" >&2
    return 2
  fi

  # Pass 1: every root's members, before anything is formatted, so that a
  # package NO root reaches is exit 2 rather than silently never checked.
  local rc=0 manifest member i m
  local -a members=() covered=()
  for i in "${!roots[@]}"; do
    local rows
    rows="$(members_of "${roots[$i]}")" || rows=""
    if [ -z "$rows" ]; then
      printf 'fmt-workspaces: cargo metadata failed for %s\n' "${roots[$i]}" >&2
      return 2
    fi
    members[$i]="$(printf '%s\n' "$rows" | cut -f1 | tr '\n' ' ')"
    while IFS= read -r m; do covered+=("$m"); done < <(printf '%s\n' "$rows" | cut -f2)
  done
  local orphans
  orphans="$(manifests_with "$root" package | python3 -c '
import os, sys
covered = {os.path.realpath(p) for p in sys.argv[1:]}
for line in sys.stdin:
    m = line.rstrip("\n")
    if m and os.path.realpath(m) not in covered:
        print(m)
' "${covered[@]}")"
  if [ -n "$orphans" ]; then
    printf 'fmt-workspaces: no workspace root reaches these packages, so nothing checks them:\n%s\n' \
      "$orphans" >&2
    return 2
  fi

  for i in "${!roots[@]}"; do
    manifest="${roots[$i]}"
    local -a pkgs=()
    read -r -a pkgs <<< "${members[$i]}"

    if [ "$list" = 1 ]; then
      printf '%s: %s\n' "$manifest" "${pkgs[*]}"
      continue
    fi

    # `-p` for every member, scoped by this root's own manifest. NOT `--all`,
    # which walks PAST a nested workspace boundary and reports the outer tree's
    # files under the inner root's name; and not the bare manifest-path form,
    # which silently checks only the root package and misses every member.
    # `|| rc=1` deliberately does NOT try to separate a diff from a source
    # rustfmt could not parse: both exit 1 and both NAME A FILE, so both are
    # facts about the tree. Measured: an unclosed delimiter exits 1, and an
    # unknown rustfmt.toml option is only a warning (exit 0). What exit 2 is
    # reserved for is "the gate did not run", and every such cause is checked
    # ABOVE this loop. Reasoning: context/test-evidence/tooling.md.
    local -a flags=()
    for member in "${pkgs[@]}"; do flags+=(-p "$member"); done
    if [ "$mode" = --fix ]; then
      cargo fmt --manifest-path "$manifest" "${flags[@]}" || rc=1
    else
      cargo fmt --manifest-path "$manifest" "${flags[@]}" -- --check || rc=1
    fi
  done
  return $rc
}

main "$@"