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
#
# 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.
set -euo pipefail

# GSTACK_HOME-aware, matching lib/bin-context.ts's native port (#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).
CACHE_DIR="${GSTACK_HOME:-$HOME/.gstack}/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._-')
  # 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.
if [[ -z "$SLUG" && -f "$CACHE_FILE" ]]; then
  _CACHED=$(cat "$CACHE_FILE" 2>/dev/null | 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" != "$PROJECT_ROOT" ]]; }; then
      : # degraded-ancestor (stray-repo) shape — recompute below and self-heal the cache
    else
      SLUG="$_CACHED"
    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. Parse kept byte-identical to
#    browse/bin/remote-slug (strip trailing .git, then owner/repo → owner-repo)
#    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
    RAW_SLUG=$(printf '%s' "${REMOTE_URL%.git}" | sed -E 's#.*[:/]([^/]+)/([^/]+)$#\1-\2#')
    SLUG=$(printf '%s' "$RAW_SLUG" | tr -cd 'a-zA-Z0-9._-')
    # Dot-only / degenerate guard: a hostile origin like `url = ..` (git
    # accepts it) passes sed unchanged and would become SLUG=".." — filing
    # state one level ABOVE ~/.gstack/projects/. Reject empty/"."/".."/
    # slash-bearing slugs and fall through to the basename fallback below.
    # (tr -cd already deletes "/", so */* is belt-and-braces.)
    case "$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" != "$SLUG" ]]; then
    mkdir -p "$CACHE_DIR" 2>/dev/null || true
    CACHE_TMP=$(mktemp "$CACHE_DIR/.slug-XXXXXX" 2>/dev/null) || CACHE_TMP=""
    if [[ -n "$CACHE_TMP" ]]; then
      printf '%s' "$SLUG" > "$CACHE_TMP" && mv "$CACHE_TMP" "$CACHE_FILE" 2>/dev/null || rm -f "$CACHE_TMP" 2>/dev/null
    fi
  fi
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}"
echo "SLUG=$SLUG"
echo "BRANCH=$BRANCH"