gstack/bin/gstack-slug

#!/usr/bin/env bash
# gstack-slug — output project slug and sanitized branch name
# Usage: eval "$(gstack-slug)"  → sets SLUG and BRANCH variables
# Or:    gstack-slug            → prints SLUG=... and BRANCH=... lines
#        gstack-slug --get NAME → print one raw value (SLUG, BRANCH or an
#                                  --identity field); skill bash blocks
#                                  use this form (#2763: worktree-isolated Claude
#                                  Code sessions refuse eval/source)
# Modes (not on the hot path; see `gstack-slug --help`):
#   --identity                 also print PROJECT_REMOTE, PROJECT_ROOT, LEGACY_SLUG
#   --stamp-checkpoint <file>  write remote:/project_root: into a checkpoint's frontmatter
#   --classify-checkpoints     read checkpoint paths on stdin, print "<status>\t<path>"
#   --adopt-legacy [--copy <relpath>...]  review/copy files from the pre-#3003 bucket
#
# Nested-group remotes (#3003): a hosted remote with 3+ path segments
# (gitlab.com/a/product/repo) files under "<last-two>-<16 hex>" instead of the
# last two segments alone, so projects in different groups stop sharing one
# bucket. 2-segment remotes (all of GitHub) and local paths are unchanged. The
# canonical-remote and slug rules live in bin/gstack-remote-identity.sh (twin of
# lib/remote-identity.ts). Earlier data stays in the old bucket until the user
# copies it with --adopt-legacy; nothing moves automatically. ssh host aliases
# (git@work-gitlab:…) are a different canonical host than the https spelling;
# pin those with GSTACK_PROJECT_SLUG.
#
# Cache format: entries are versioned ("v2:<slug>"). An unversioned entry from
# an older gstack is recomputed once (one git spawn) and rewritten as v2; it
# keeps its value unless it is exactly the pre-#3003 last-two slug of a
# 3+-segment remote, so #2212 sticky identity survives the upgrade and later
# cache hits stay git-free.
#
# Resolution order (highest precedence first):
#   0. $GSTACK_PROJECT_SLUG env override (documented escape hatch)
#   1. Walk UP from $(pwd) to the OUTERMOST ancestor containing a canonical
#      project-identity marker (.git, .project.yaml, package.json, pyproject.toml,
#      Cargo.toml, Gemfile, go.mod). Use that ancestor as the "project root".
#      Build/deploy artifacts (.vercel, .next, dist, node_modules, etc.) are
#      DELIBERATELY NOT markers — they're tooling output, not project identity.
#      Without this walk-up, running gstack-slug from a subdir whose only
#      "marker" is a deploy artifact silently resolves to the subdir's basename,
#      misfiling all session state under a phantom slug. (2026-05-25 bug fix.)
#   2. Derive the slug from the canonical git remote: the OUTERMOST ancestor
#      that is an actual git repo (`.git` directory, or `.git` FILE for
#      worktrees/submodules) with an `origin` remote wins. The slug is
#      `owner-repo`, parsed EXACTLY like browse/bin/remote-slug so the two
#      bins can never disagree on a canonical-remote repo. Marker-only
#      ancestors that are NOT remote-bearing repos (a stray empty ~/.git,
#      a stray package.json in $HOME) still anchor the basename FALLBACK,
#      but they can no longer shadow a real remote. (2026-08-17 bug fix:
#      a stray empty ~/.git made the walk-up pick $HOME as project root;
#      $HOME has no origin, so EVERY repo under it degraded to
#      SLUG=<username> — one shared bucket for all projects.)
#   3. Otherwise use the basename of the resolved project root.
#   4. If no project root was found anywhere on the chain, fall back to the
#      basename of $(pwd) (preserves prior behavior for plain folders).
#
# MIGRATION NOTE (2026-08-17): sessions run BEFORE the remote-first fix above,
# in repos below a stray marker-bearing ancestor, filed their session state
# (decisions / timeline / ceo-plans / learnings) under the DEGRADED slug —
# ~/.gstack/projects/<ancestor-basename>/ (e.g. `garrytan`) instead of the
# canonical ~/.gstack/projects/<owner-repo>/. The slug cache self-heals on the
# next invocation (see 1b), but already-written store data does NOT move.
# Whether/how to merge those stores is tracked in TODOS.md — do not add data
# migration code here.
#
# Caching is self-healing: a cache entry for the literal pwd that differs from
# the freshly-computed slug gets opportunistically rewritten (single-shot, key-
# local — never sweeps other entries). This lets pre-existing poisoned caches
# clean themselves up without a manual `rm -rf ~/.gstack/slug-cache/`.
#
# Security: output is sanitized to [a-zA-Z0-9._-] only, preventing shell
# injection when consumed via source or eval.
# Bash 5.2+ can feed a heredoc body >=512B through a pipe with no reader
# yet, which hangs --help forever; compat level 50 restores the tempfile path
# (same guard as bin/gstack-artifacts-init). Not exported.
BASH_COMPAT=50

set -euo pipefail

# State-root aware (bin/gstack-state-root.sh), matching lib/bin-context.ts (#2561): the
# bash writer and the TS reader must key the SAME cache, and a test running
# with GSTACK_HOME=<temp> must write its cache junk there, not into the real
# home (observed: 2,528 stale temp-cwd entries accumulated in ~/.gstack).
. "$(dirname "$0")/gstack-state-root.sh" 2>/dev/null || { echo "$0: cannot resolve the gstack state root: $(dirname "$0")/gstack-state-root.sh is missing. fix: reinstall with ./setup or /gstack-upgrade (docs/state-root.md)" >&2; exit 1; }
gstack_state_root_select; GSTACK_STATE_ROOT="$_gstack_sr_root"
. "$(dirname "$0")/gstack-remote-identity.sh" 2>/dev/null || { echo "$0: $(dirname "$0")/gstack-remote-identity.sh is missing. fix: reinstall with ./setup or /gstack-upgrade" >&2; exit 1; }

MODE=default
MODE_ARG=""
COPY_PATHS=()
case "${1:-}" in
  "") ;;
  --identity) MODE=identity ;;
  --get) MODE=get; MODE_ARG="${2:-}"
    case "$MODE_ARG" in SLUG|BRANCH|PROJECT_REMOTE|PROJECT_ROOT|LEGACY_SLUG) ;;
      *) echo "usage: gstack-slug --get SLUG|BRANCH|PROJECT_REMOTE|PROJECT_ROOT|LEGACY_SLUG" >&2; exit 2 ;;
    esac ;;
  --stamp-checkpoint) MODE=stamp; MODE_ARG="${2:-}"
    [[ -n "$MODE_ARG" ]] || { echo "usage: gstack-slug --stamp-checkpoint <file>" >&2; exit 2; } ;;
  --classify-checkpoints) MODE=classify ;;
  --adopt-legacy) MODE=adopt; shift
    if [[ "${1:-}" == "--copy" ]]; then
      shift
      [[ $# -gt 0 ]] || { echo "usage: gstack-slug --adopt-legacy --copy <relpath>..." >&2; exit 2; }
      COPY_PATHS=("$@")
    elif [[ -n "${1:-}" ]]; then
      echo "usage: gstack-slug --adopt-legacy [--copy <relpath>...]" >&2; exit 2
    fi ;;
  -h|--help)
    cat <<'USAGE'
gstack-slug — print SLUG=<project slug> and BRANCH=<branch> for the current directory.
  eval "$(gstack-slug)"                 set SLUG and BRANCH
  SLUG=$(gstack-slug --get SLUG)        print one raw value (SLUG, BRANCH, or an --identity
                                        field); no eval needed
  gstack-slug --identity                also print PROJECT_REMOTE (canonical, credential-free),
                                        PROJECT_ROOT and LEGACY_SLUG (pre-#3003 bucket, if different)
  gstack-slug --stamp-checkpoint FILE   write remote:/project_root: into FILE's frontmatter
  gstack-slug --classify-checkpoints    read checkpoint paths on stdin; print "<status><TAB><path>",
                                        status = match | match-root | foreign | unstamped
  gstack-slug --adopt-legacy            list the old bucket's files (checkpoints marked
                                        matching/foreign/unknown); asks per file on a terminal
  gstack-slug --adopt-legacy --copy P…  copy the named files (paths relative to the old bucket)
Env: GSTACK_PROJECT_SLUG pins the slug (ssh host aliases, vendored sub-repos); never cached.
USAGE
    exit 0 ;;
  *) echo "gstack-slug: unknown argument: $1 (try --help)" >&2; exit 2 ;;
esac
CACHE_DIR="$GSTACK_STATE_ROOT/slug-cache"
PROJECT_DIR="$(pwd)"
# Encode absolute path as cache key: /Users/j/foo → _Users_j_foo
CACHE_KEY=$(printf '%s' "$PROJECT_DIR" | tr '/' '_')
CACHE_FILE="${CACHE_DIR}/${CACHE_KEY}"

SLUG=""

# 0. Explicit env override — wins over everything. Escape hatch for vendored
#    sub-repos and other genuine "subdir IS its own project" edge cases.
SLUG_FROM_ENV=0
if [[ -n "${GSTACK_PROJECT_SLUG:-}" ]]; then
  SLUG=$(printf '%s' "$GSTACK_PROJECT_SLUG" | tr -cd 'a-zA-Z0-9._-')
  # A pin of "." or ".." would file state outside projects/; ignore it.
  case "$SLUG" in .|..) SLUG="" ;; esac
  # Per-invocation escape hatch, never a durable identity: persisting it
  # would rebind THIS cwd's slug for every later env-less run (observed: a
  # test exporting GSTACK_PROJECT_SLUG from the repo root rebound the whole
  # repo's session state to the test's slug).
  SLUG_FROM_ENV=1
fi

# 1. Walk up from pwd, tracking the OUTERMOST ancestor with a canonical
#    project-identity marker. The walk stops at "/" so we never escape the
#    filesystem root. Markers are an allow-list (not a blacklist) so new
#    build/deploy tools cannot silently establish phantom project roots.
#
#    Markers: .git can be a directory (normal repo) or a file (worktree /
#    submodule pointer). Everything else is a file at the directory's top
#    level.
#    Two tiers of markers:
#    - STRONG markers (canonical version-control / language project files):
#      .git, .project.yaml, package.json, pyproject.toml, Cargo.toml, Gemfile,
#      go.mod. These signal "this directory is a real project of its own."
#    - WEAK markers (content-only project signals): README.md, README, LICENSE.
#      These catch content folders (markdown bundles, asset collections, AJ's
#      loadout-style folders) that have no programming-language project files
#      but ARE the user's project root.
#    Rule: outermost STRONG marker wins. If no strong marker exists anywhere on
#    the chain, outermost WEAK marker wins. This means a vendored sub-repo
#    (e.g. `loadout/starter-pack/.git`) correctly keeps its own slug even when
#    a weak-marker parent (`loadout/README.md`) is higher up — the sub-repo IS
#    its own project. But a deploy-artifact-only subdir (`loadout/site/.vercel`)
#    correctly folds into the content-project parent (`loadout/README.md`),
#    because `.vercel` is not a marker at all.
_outermost_project_root() {
  local dir="$1"
  local outermost_strong=""
  local outermost_weak=""
  local parent="" depth=0
  # Terminate on dirname's FIXED POINT, not on a literal "/": under git-bash
  # on Windows a mixed-form path walks C:/Users -> C: -> . -> . forever, which
  # hung every bin that evals gstack-slug (caught by windows-free-tests CI).
  # The depth cap is belt-and-braces for exotic path forms (UNC, //server).
  while [[ -n "$dir" && "$dir" != "/" && $depth -lt 64 ]]; do
    if [[ -e "$dir/.git" \
       || -f "$dir/.project.yaml" \
       || -f "$dir/package.json" \
       || -f "$dir/pyproject.toml" \
       || -f "$dir/Cargo.toml" \
       || -f "$dir/Gemfile" \
       || -f "$dir/go.mod" ]]; then
      outermost_strong="$dir"
    elif [[ -f "$dir/README.md" \
         || -f "$dir/README" \
         || -f "$dir/README.rst" \
         || -f "$dir/LICENSE" \
         || -f "$dir/LICENSE.md" ]]; then
      outermost_weak="$dir"
    fi
    parent=$(dirname "$dir")
    [[ "$parent" == "$dir" ]] && break # dirname fixed point (C:/, ., //srv)
    dir="$parent"
    depth=$((depth + 1))
  done
  # Strong markers win over weak; either wins over nothing.
  if [[ -n "$outermost_strong" ]]; then
    printf '%s' "$outermost_strong"
  else
    printf '%s' "$outermost_weak"
  fi
}

# 1a. Outermost REMOTE-BEARING repo root: walk the same ancestor chain and
#     track the outermost dir that has a `.git` entry (directory for normal
#     clones, FILE for git-worktrees/submodules — `git -C` resolves a
#     worktree's remote through its main clone) AND whose `origin` remote
#     resolves. This is the canonical-identity walk: a marker-only ancestor
#     with no resolvable origin (stray empty ~/.git, stray package.json)
#     cannot win here, so it cannot hijack remote-derived identity the way
#     it can hijack the marker walk above. Nested-repo semantics preserved:
#     an inner repo under an outer canonical-remote repo still resolves to
#     the OUTER repo's remote (outermost wins), same as before.
#     Note: git spawns only at `.git`-bearing ancestors — typically one.
_outermost_remote_repo() {
  local dir="$1"
  local outermost="" parent="" depth=0
  while [[ -n "$dir" && "$dir" != "/" && $depth -lt 64 ]]; do
    if [[ -e "$dir/.git" ]] && git -C "$dir" remote get-url origin >/dev/null 2>&1; then
      outermost="$dir"
    fi
    parent=$(dirname "$dir")
    [[ "$parent" == "$dir" ]] && break # dirname fixed point (C:/, ., //srv)
    dir="$parent"
    depth=$((depth + 1))
  done
  printf '%s' "$outermost"
}

# Only compute the project root if we don't already have a slug (env override
# took precedence). The walk is cheap (~10 stats on the deepest realistic cwd).
PROJECT_ROOT=""
if [[ -z "$SLUG" ]]; then
  PROJECT_ROOT=$(_outermost_project_root "$PROJECT_DIR")
fi

# Lazy, memoized remote discovery. Needed on exactly two paths: fresh
# resolution (no usable cache) and the degraded-ancestor heal check below.
# Gating it keeps ordinary cache hits git-spawn-free.
REMOTE_ROOT=""
REMOTE_URL=""
_REMOTE_RESOLVED=0
_resolve_remote() {
  if [[ "$_REMOTE_RESOLVED" -eq 1 ]]; then return 0; fi
  _REMOTE_RESOLVED=1
  REMOTE_ROOT=$(_outermost_remote_repo "$PROJECT_DIR")
  if [[ -n "$REMOTE_ROOT" ]]; then
    REMOTE_URL=$(git -C "$REMOTE_ROOT" remote get-url origin 2>/dev/null) || REMOTE_URL=""
  fi
  return 0
}

# 1b. Cached identity is STICKY (#2212): a project that used gstack before it
#     adopted a git remote keeps its pre-origin slug — recomputing from the
#     remote here would rename the project mid-life and orphan everything
#     under ~/.gstack/projects/<slug>/. TWO provable bug shapes are exempt
#     and fall through to recompute (self-heal):
#     - Old-bug shape (#1125): the pre-walk-up resolver cached basename(pwd)
#       for a SUBDIRECTORY of the real project — cached == pwd basename while
#       the walk-up says pwd is NOT the project root.
#     - Degraded-ancestor shape (2026-08-17), STRAY-REPO shape ONLY: the
#       pre-remote-first resolver cached basename(PROJECT_ROOT) for an
#       ancestor anchored by a .git entry whose origin does NOT resolve (the
#       stray empty ~/.git live bug) while a remote-bearing repo BELOW it
#       exists. A marker root anchored by package.json / pyproject etc. with
#       NO .git is legit #2212 sticky identity (a monorepo wrapper that used
#       gstack before its inner dir grew a remote) and must NOT be healed.
#       Legit remote-adopting stickiness is safe too: there the repo that
#       adopted the remote IS the marker root (REMOTE_ROOT == PROJECT_ROOT),
#       so the heal never fires.
_CACHE_V2=0
LEGACY_NOTICE_SLUG=""
if [[ -z "$SLUG" && -f "$CACHE_FILE" ]]; then
  _RAW_CACHE=$(cat "$CACHE_FILE" 2>/dev/null || true)
  if [[ "$_RAW_CACHE" == v2:* ]]; then
    _CACHE_V2=1
    _RAW_CACHE="${_RAW_CACHE#v2:}"
  fi
  _CACHED=$(printf '%s' "$_RAW_CACHE" | tr -cd 'a-zA-Z0-9._-')
  if [[ -n "$_CACHED" ]]; then
    _PWD_BASE=$(basename "$PROJECT_DIR" | tr -cd 'a-zA-Z0-9._-')
    _ROOT_BASE=""
    if [[ -n "$PROJECT_ROOT" ]]; then
      _ROOT_BASE=$(basename "$PROJECT_ROOT" | tr -cd 'a-zA-Z0-9._-')
    fi
    if [[ "$_CACHED" == "$_PWD_BASE" && -n "$PROJECT_ROOT" && "$PROJECT_ROOT" != "$PROJECT_DIR" ]]; then
      : # old-bug shape — recompute below and self-heal the cache
    elif [[ -n "$PROJECT_ROOT" && "$_CACHED" == "$_ROOT_BASE" && -e "$PROJECT_ROOT/.git" ]] \
      && ! git -C "$PROJECT_ROOT" remote get-url origin >/dev/null 2>&1 \
      && { _resolve_remote; [[ -n "$REMOTE_URL" && "$REMOTE_ROOT" != "$PROJECT_ROOT" ]]; }; then
      : # degraded-ancestor (stray-repo) shape — recompute below and self-heal the cache
    elif [[ "$_CACHE_V2" -eq 1 ]]; then
      SLUG="$_CACHED"
    else
      # Unversioned (pre-#3003) entry: recompute once. Keep the sticky value
      # unless it is exactly the old last-two slug of a 3+-segment remote.
      SLUG="$_CACHED"
      _resolve_remote
      if [[ -n "$REMOTE_URL" ]]; then
        gstack_remote_slug "$REMOTE_URL"
        if [[ -n "$_gri_slug" && "$_gri_slug" != "$_gri_legacy_slug" && "$_CACHED" == "$_gri_legacy_slug" ]]; then
          SLUG="$_gri_slug"
          LEGACY_NOTICE_SLUG="$_gri_legacy_slug"
        fi
      fi
    fi
  fi
fi

# 2. Canonical remote-derived slug. Sourced from the outermost remote-bearing
#    repo (see 1a) — NOT from PROJECT_ROOT, which may be a marker-only
#    ancestor with no remote. The slug rule (legacy owner-repo for 2-segment
#    and local remotes, "<last-two>-<16 hex>" for 3+-segment hosted remotes)
#    is shared with browse/bin/remote-slug through gstack-remote-identity.sh,
#    so the two bins agree on every canonical-remote repo, worktrees included.
#    Parity pinned by test/gstack-slug-parity.test.ts.
if [[ -z "$SLUG" ]]; then
  _resolve_remote
  if [[ -n "$REMOTE_URL" ]]; then
    gstack_remote_slug "$REMOTE_URL"
    SLUG="$_gri_slug"
    if [[ -n "$SLUG" && "$_gri_slug" != "$_gri_legacy_slug" ]]; then
      LEGACY_NOTICE_SLUG="$_gri_legacy_slug"
    fi
    # Dot-only / degenerate guard: a hostile origin like `url = ..` (git
    # accepts it) passes sed unchanged and would become SLUG=".." — filing
    # state one level ABOVE ~/.gstack/projects/. Reject empty/"."/".."/
    # slash-bearing slugs and fall through to the basename fallback below.
    # (tr -cd already deletes "/", so */* is belt-and-braces.)
    case "$SLUG" in ""|.|..|*/*) SLUG="" ;; esac
  fi
fi

# 3. No git remote (or no remote at all) — use the project root's basename.
if [[ -z "$SLUG" && -n "$PROJECT_ROOT" ]]; then
  SLUG=$(basename "$PROJECT_ROOT" | tr -cd 'a-zA-Z0-9._-')
fi

# 4. Final fallback: no project root found anywhere on the chain. Use pwd's
#    basename (preserves the old behavior for plain non-project folders).
SLUG="${SLUG:-$(basename "$PROJECT_DIR" | tr -cd 'a-zA-Z0-9._-')}"

# Cache compare/evict/write — self-healing. Compute the cache decision AFTER
# fresh resolution so a stale cached value gets corrected on next invocation
# rather than perpetuated. Single-shot: we only ever touch the cache entry for
# the literal current pwd's key, never sweep others.
# 3b. Re-sanitize unconditionally before the value is echoed into `eval`/`source`
#     output — honors the [a-zA-Z0-9._-] invariant promised in the header on
#     every path (the fresh-compute design already prevents poisoned-cache
#     injection, but the invariant should not depend on that reasoning).
SLUG=$(printf '%s' "$SLUG" | tr -cd 'a-zA-Z0-9._-')

if [[ -n "$SLUG" && "$SLUG_FROM_ENV" -eq 0 ]]; then
  CURRENT_CACHE=""
  if [[ -f "$CACHE_FILE" ]]; then
    CURRENT_CACHE=$(cat "$CACHE_FILE" 2>/dev/null || true)
  fi
  if [[ "$CURRENT_CACHE" != "v2:$SLUG" ]]; then
    mkdir -p "$CACHE_DIR" 2>/dev/null || true
    CACHE_TMP=$(mktemp "$CACHE_DIR/.slug-XXXXXX" 2>/dev/null) || CACHE_TMP=""
    if [[ -n "$CACHE_TMP" ]]; then
      printf 'v2:%s' "$SLUG" > "$CACHE_TMP" && mv "$CACHE_TMP" "$CACHE_FILE" 2>/dev/null || rm -f "$CACHE_TMP" 2>/dev/null
    fi
  fi
fi

# One notice on the resolve that first files this project under its new
# nested-group slug while the old shared bucket still exists (stderr only, so
# eval consumers are unaffected; later runs are v2 cache hits and stay quiet).
if [[ -n "$LEGACY_NOTICE_SLUG" && "$SLUG" != "$LEGACY_NOTICE_SLUG" && -d "$GSTACK_STATE_ROOT/projects/$LEGACY_NOTICE_SLUG" ]]; then
  echo "gstack now files this project under projects/$SLUG; earlier data is still in projects/$LEGACY_NOTICE_SLUG (review and copy it with: gstack-slug --adopt-legacy)" >&2
fi

RAW_BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null) || RAW_BRANCH=""
BRANCH=$(printf '%s' "${RAW_BRANCH:-}" | tr '/' '-' | tr -cd 'a-zA-Z0-9._-')
BRANCH="${BRANCH:-unknown}"

if [[ "$MODE" == "get" && ( "$MODE_ARG" == SLUG || "$MODE_ARG" == BRANCH ) ]]; then
  if [[ "$MODE_ARG" == SLUG ]]; then printf '%s\n' "$SLUG"; else printf '%s\n' "$BRANCH"; fi
  exit 0
fi
if [[ "$MODE" == "default" ]]; then
  echo "SLUG=$SLUG"
  echo "BRANCH=$BRANCH"
  exit 0
fi

# ── Project identity (#3003) ─────────────────────────────────────────────────
# Identity = canonical remote; the root is identity only when there is no
# remote. Roots are physical (pwd -P) so a symlinked spelling compares equal.
ID_REMOTE=""
ID_ROOT=""
ID_LEGACY=""
_resolve_identity() {
  _resolve_remote
  if [[ -n "$REMOTE_URL" ]]; then
    gstack_remote_slug "$REMOTE_URL"
    ID_REMOTE="$_gri_canon"
    ID_ROOT="$REMOTE_ROOT"
    if [[ -n "$_gri_legacy_slug" && "$_gri_slug" != "$_gri_legacy_slug" && "$_gri_legacy_slug" != "$SLUG" ]]; then
      ID_LEGACY="$_gri_legacy_slug"
    fi
  else
    ID_ROOT="${PROJECT_ROOT:-$(_outermost_project_root "$PROJECT_DIR")}"
    ID_ROOT="${ID_ROOT:-$PROJECT_DIR}"
  fi
  ID_ROOT=$(cd "$ID_ROOT" 2>/dev/null && pwd -P) || ID_ROOT="$PROJECT_DIR"
}

# Prints "<remote>\037<project_root>" from the file's leading frontmatter only.
_checkpoint_fields() {
  awk 'NR == 1 { if ($0 != "---") exit; next }
       $0 == "---" { exit }
       /^remote:/ && !r { v = $0; sub(/^remote:[ \t]*/, "", v); sub(/[ \t\r]+$/, "", v); rem = v; r = 1 }
       /^project_root:/ && !p { v = $0; sub(/^project_root:[ \t]*/, "", v); sub(/[ \t\r]+$/, "", v); root = v; p = 1 }
       END { printf "%s\037%s\n", rem, root }' "$1" 2>/dev/null || true
}

# Sets _ck_status: match | match-root (same remote, different root: info only)
# | foreign | unstamped (checkpoint written before identity stamping existed).
_classify_checkpoint() {
  local fields r root
  fields=$(_checkpoint_fields "$1")
  r="${fields%%$'\037'*}"
  root="${fields#*$'\037'}"
  if [[ -n "$ID_REMOTE" && -n "$r" ]]; then
    if [[ "$r" != "$ID_REMOTE" ]]; then _ck_status=foreign
    elif [[ -n "$root" && "$root" != "$ID_ROOT" ]]; then _ck_status=match-root
    else _ck_status=match
    fi
  elif [[ -n "$root" ]]; then
    if [[ "$root" == "$ID_ROOT" ]]; then _ck_status=match; else _ck_status=foreign; fi
  elif [[ -n "$r" ]]; then
    _ck_status=foreign
  else
    _ck_status=unstamped
  fi
}

_resolve_identity

case "$MODE" in
  get)
    case "$MODE_ARG" in
      PROJECT_REMOTE) printf '%s\n' "$ID_REMOTE" ;;
      PROJECT_ROOT) printf '%s\n' "$ID_ROOT" ;;
      LEGACY_SLUG) printf '%s\n' "$ID_LEGACY" ;;
    esac
    ;;

  identity)
    echo "SLUG=$SLUG"
    echo "BRANCH=$BRANCH"
    printf 'PROJECT_REMOTE=%q\n' "$ID_REMOTE"
    printf 'PROJECT_ROOT=%q\n' "$ID_ROOT"
    echo "LEGACY_SLUG=$ID_LEGACY"
    ;;

  stamp)
    [[ -f "$MODE_ARG" ]] || { echo "gstack-slug: no such checkpoint file: $MODE_ARG" >&2; exit 1; }
    STAMP_TMP=$(mktemp "${MODE_ARG}.stamp-XXXXXX") || exit 1
    if GRI_REMOTE="$ID_REMOTE" GRI_ROOT="$ID_ROOT" awk '
      function ids() { if (ENVIRON["GRI_REMOTE"] != "") print "remote: " ENVIRON["GRI_REMOTE"]; print "project_root: " ENVIRON["GRI_ROOT"] }
      NR == 1 { if ($0 == "---") { infm = 1; print; next } print "---"; ids(); print "---" }
      infm && $0 == "---" { ids(); print; infm = 0; next }
      infm && (/^remote:/ || /^project_root:/) { next }
      { print }
      END { if (NR == 0) { print "---"; ids(); print "---" } }' "$MODE_ARG" > "$STAMP_TMP"; then
      mv "$STAMP_TMP" "$MODE_ARG"
    else
      rm -f "$STAMP_TMP"
      exit 1
    fi
    ;;

  classify)
    while IFS= read -r ck_file || [[ -n "$ck_file" ]]; do
      [[ -n "$ck_file" ]] || continue
      _classify_checkpoint "$ck_file"
      printf '%s\t%s\n' "$_ck_status" "$ck_file"
    done
    ;;

  adopt)
    if [[ -z "$ID_LEGACY" ]]; then
      echo "Nothing to adopt: this project's slug ($SLUG) did not change."
      exit 0
    fi
    OLD_BUCKET="$GSTACK_STATE_ROOT/projects/$ID_LEGACY"
    NEW_BUCKET="$GSTACK_STATE_ROOT/projects/$SLUG"
    if [[ ! -d "$OLD_BUCKET" ]]; then
      echo "Nothing to adopt: no earlier bucket at $OLD_BUCKET."
      exit 0
    fi
    OLD_REAL=$(cd "$OLD_BUCKET" && pwd -P)

    # Sets _ad_label and _ad_copyable (1/0) for one path relative to OLD_BUCKET.
    _adopt_label() {
      _ad_copyable=1
      case "$1" in
        checkpoints/*.md)
          _classify_checkpoint "$OLD_BUCKET/$1"
          case "$_ck_status" in
            match|match-root) _ad_label="checkpoint: matching this project" ;;
            foreign) _ad_label="checkpoint: another project (not copyable)"; _ad_copyable=0 ;;
            *) _ad_label="checkpoint: unknown project (saved before identity stamps)" ;;
          esac ;;
        *) _ad_label="no project identity: the old bucket may be shared, check before copying" ;;
      esac
      if [[ "$_ad_copyable" -eq 1 && -e "$NEW_BUCKET/$1" ]]; then
        _ad_label="$_ad_label; already in new bucket (skipped)"; _ad_copyable=0
      fi
    }

    _adopt_copy() {
      mkdir -p "$(dirname "$NEW_BUCKET/$1")" && cp -p "$OLD_BUCKET/$1" "$NEW_BUCKET/$1" && echo "COPIED $1"
    }

    if [[ ${#COPY_PATHS[@]} -gt 0 ]]; then
      ADOPT_RC=0
      for rel in "${COPY_PATHS[@]}"; do
        case "/$rel/" in
          */../*|*/./*|//*) echo "REFUSED $rel (must be a plain path relative to $OLD_BUCKET)"; ADOPT_RC=1; continue ;;
        esac
        src="$OLD_BUCKET/$rel"
        src_dir=$(cd "$(dirname "$src")" 2>/dev/null && pwd -P) || src_dir=""
        if [[ ! -f "$src" || -L "$src" || -z "$src_dir" ]] || [[ "$src_dir" != "$OLD_REAL" && "$src_dir" != "$OLD_REAL"/* ]]; then
          echo "REFUSED $rel (not a regular file inside $OLD_BUCKET)"; ADOPT_RC=1; continue
        fi
        _adopt_label "$rel"
        if [[ "$_ad_copyable" -eq 0 ]]; then
          echo "SKIPPED $rel ($_ad_label)"; continue
        fi
        _adopt_copy "$rel" || ADOPT_RC=1
      done
      exit "$ADOPT_RC"
    fi

    echo "gstack now files this project under: $NEW_BUCKET"
    echo "Earlier data (shared nested-group bucket): $OLD_BUCKET"
    echo "Nothing is copied unless you confirm it. Files:"
    ADOPT_FILES=$(cd "$OLD_BUCKET" && find . -type f 2>/dev/null | sed 's#^\./##' | LC_ALL=C sort)
    INTERACTIVE=0
    if [[ -t 0 && -t 1 ]]; then INTERACTIVE=1; fi
    while IFS= read -r rel; do
      [[ -n "$rel" ]] || continue
      _adopt_label "$rel"
      echo "  $rel  [$_ad_label]"
      if [[ "$INTERACTIVE" -eq 1 && "$_ad_copyable" -eq 1 ]]; then
        printf '    copy into the new bucket? [y/N] '
        ans=""
        read -r ans </dev/tty || ans=""
        case "$ans" in y|Y|yes|YES) _adopt_copy "$rel" ;; esac
      fi
    done <<ADOPT_LIST
$ADOPT_FILES
ADOPT_LIST
    if [[ "$INTERACTIVE" -eq 0 ]]; then
      echo "Nothing copied. Copy chosen files with: gstack-slug --adopt-legacy --copy <path> [<path>...]"
    fi
    ;;
esac