pi-devbox/entrypoint-user.sh

#!/usr/bin/env bash
set -euo pipefail

# ── Startup banner: which pi-devbox build is this? ─────────────────
# Printed FIRST, before the setup noise below, so it's the first thing
# visible when the container starts (CMD is `bash -l`, tty:true in compose,
# so this reaches the same stream as the interactive shell the user lands
# in). Reads the ground-truth manifest baked in Dockerfile.variant; a no-op
# with a short stderr notice on images built before it existed.
# `--no-skills`: this runs FIRST, before the baked skill links are created
# below and long before the skillset deploy + devbox-skill-reconcile run at the
# end of this script, so the skill-source section would report a pre-reconcile
# state that is about to change. Wrong-but-plausible is worse than absent.
command -v pi-devbox-version >/dev/null 2>&1 && pi-devbox-version --no-skills || true

# ── SSH ControlMaster socket dir ────────────────────────────────
# Companion to /etc/ssh/ssh_config.d/00-devbox-controlmaster.conf in the
# base image — that file declares ControlPath=/tmp/sshcm/%r@%h:%p; this
# creates the directory with the right permissions on every container
# start. /tmp is per-container so the dir doesn't survive recreation;
# baking it into a Dockerfile layer would be wrong.
# Mode 700 is required — OpenSSH refuses to use a ControlPath dir that
# others can write to.
mkdir -p /tmp/sshcm
chmod 700 /tmp/sshcm

# ── LAN access + writable SSH sidecar: host-OS-agnostic helper ──────
# Generates the writable ~/.ssh-local/config on EVERY host OS: a `Host *`
# ControlPath redirect into ~/.ssh-local/cm (so `ssh -F` / dssh / dscp work
# even when ~/.ssh is bind-mounted read-only) plus `Include ~/.ssh/config`. On
# VM-backed hosts (macOS OrbStack / Docker Desktop) it ALSO adds an
# SSH-jump-via-host block so the container can reach the host's
# directly-attached LAN peers; on native Linux (LAN reachable directly) the
# jump block is omitted but the sidecar is still rendered. Controlled by
# DEVBOX_LAN_ACCESS (auto|jump|off) + HOST_SSH_USER. Always non-fatal. See the
# script header.
if [ -r /usr/local/lib/pi-devbox/setup-lan-access.sh ]; then
  bash /usr/local/lib/pi-devbox/setup-lan-access.sh || true
fi

# ── Shell defaults: copy baked files from /etc/skel-devbox/ if absent
# Respects host bind-mounts and user customizations — existing files
# are never overwritten. To restore defaults: rm ~/.bash_aliases (or
# .inputrc) and recreate the container, or cp from /etc/skel-devbox/
# directly.
SKEL_DIR="/etc/skel-devbox"
if [ -d "$SKEL_DIR" ]; then
  for f in .bash_aliases .inputrc .gitignore_global; do
    if [ -f "$SKEL_DIR/$f" ] && [ ! -e "$HOME/$f" ]; then
      cp "$SKEL_DIR/$f" "$HOME/$f"
    fi
  done
fi

# ── Image-baked skills: link into ~/.agents/skills ───────────────────
# Skills shipped IN the image (under /usr/local/share/pi-devbox/skills/) are
# made available regardless of whether a skillset repo is mounted. Done EARLY
# — before the pi-toolkit/extensions deploy below — so the symlinks exist by
# the time anything gates on "container ready": the smoke-test readiness probe
# waits on pi-deploy markers (keybindings.json, mempalace.ts) that only land
# AFTER this point, so linking here closes a sample-too-early race that failed
# the runtime skill-link assertion. Pointing at the image path (/usr/local/...)
# keeps the skill fresh from the image and surviving volume recreate (unlike
# anything baked under a home dir, which a named volume would shadow). Created
# only when absent, so a user override is never clobbered.
#
# NB: "created only when absent" does NOT hand a same-named skillset skill
# priority — the opposite. The skillset deploy runs at the end of this script
# and classifies these links as foreign, so through v1.8.4 the BAKED copy
# always won and an edit pushed to a skillset-owned skill was invisible until
# the next image build. The links below are therefore the FALLBACK only;
# devbox-skill-reconcile (invoked right after the skillset deploy) hands the
# skillset-OWNED skills back to the live clone. Ownership is per-skill, listed
# in skills/skillset-owned.txt — see VENDORED.md for why pi-extensions must
# keep losing to the baked copy.
DEVBOX_SKILLS_SRC=/usr/local/share/pi-devbox/skills
if [ -d "$DEVBOX_SKILLS_SRC" ]; then
  mkdir -p "$HOME/.agents/skills"
  for _sk in "$DEVBOX_SKILLS_SRC"/*/; do
    [ -d "$_sk" ] || continue
    _skname=$(basename "$_sk")
    if [ ! -e "$HOME/.agents/skills/$_skname" ]; then
      # -sfn, not -s: `[ ! -e ]` is TRUE for a DANGLING symlink (-e follows the
      # link), and since v1.8.5 these links can point into /workspace/skillset
      # (see devbox-skill-reconcile, invoked after the skillset deploy). If that
      # mount vanishes while the writable layer survives — a `docker restart` or
      # a host reboot under restart: unless-stopped, as opposed to a recreate —
      # plain `ln -s` fails with "File exists" and, under `set -e`, aborts
      # container start before `exec "$@"`. With -f the broken link heals back to
      # the baked fallback, and the reconciler re-points it in the same boot if
      # the clone is back.
      ln -sfn "${_sk%/}" "$HOME/.agents/skills/$_skname"
    fi
  done
fi

# ── MemPalace: initialize palace for the workspace if mempalace is installed
# Creates the palace directory structure on first run. Idempotent — skips
# if palace already exists, so upgrades from older versions preserve
# existing data. `--yes` auto-accepts detected entities so the init is
# non-interactive.
if command -v mempalace &>/dev/null && [ -d /workspace ]; then
  PALACE_DIR="${HOME}/.mempalace"
  if [ ! -d "$PALACE_DIR/palace" ]; then
    echo "Initializing MemPalace for workspace (non-interactive)..."
    # </dev/null: mempalace init has an interactive "Mine this directory
    # now? [Y/n]" prompt that --yes does not auto-answer in all paths.
    # Without redirected stdin, the process blocks here forever when run
    # from `docker run -it` (the TTY keeps stdin open). EOF on stdin
    # makes the prompt fall through to its default (skip).
    mempalace init --yes /workspace </dev/null >/dev/null 2>&1 || true
  fi
fi

# ── MemPalace: pi transcript feeder ─────────────────────────────────
# mempalace-toolkit ships `mempalace-pi-session`, which mines pi's own JSONL
# session transcripts into the palace. pi's mempalace extension drives it on
# session_shutdown and on a debounced agent_settled; this is the catch-up for
# the one case no handler can cover — a hard kill (docker kill, OOM, host
# reboot) runs nothing at all, so without this the previous life's transcripts
# are never mined.
#
# No MEMPALACE_PI_STAGE override here on purpose: the feeder stages next to the
# palace it feeds (<palace-root>/pi-stage), so the stage and the dedup keys
# referencing it share one lifetime — whatever persistence the palace has, the
# stage inherits. Pinning it elsewhere (e.g. into the ~/.pi volume) would
# re-introduce the very split that design prevents: palace volume kept, stage
# volume dropped, and `mempalace sync` then prunes every conversation drawer.
#
# Backgrounded: a cold mine can take tens of seconds and must never delay the
# shell. Contention with a live session is handled by the tool itself (it exits
# 0 and lets the palace holder do the mine).

# Self-heal onto PATH for images whose base predates the toolkit symlink.
# ~/.local/bin is already ahead of /usr/local/bin on PATH (Dockerfile.base sets
# it in ENV PATH) and is writable by this (non-root) user, unlike /usr/local/bin.
if [ -x /opt/mempalace-toolkit/bin/mempalace-pi-session ] && \
   ! command -v mempalace-pi-session >/dev/null 2>&1; then
  mkdir -p "$HOME/.local/bin"
  ln -sf /opt/mempalace-toolkit/bin/mempalace-pi-session "$HOME/.local/bin/mempalace-pi-session"
fi

# Resolve the feeder explicitly rather than trusting PATH: this runs before any
# login shell, and a silently-skipped catch-up is exactly the failure we are
# here to prevent.
MEMPALACE_FEEDER=""
if command -v mempalace-pi-session >/dev/null 2>&1; then
  MEMPALACE_FEEDER="mempalace-pi-session"
elif [ -x /opt/mempalace-toolkit/bin/mempalace-pi-session ]; then
  MEMPALACE_FEEDER="/opt/mempalace-toolkit/bin/mempalace-pi-session"
fi

if [ "${MEMPALACE_FEED:-1}" != "0" ] && [ -n "$MEMPALACE_FEEDER" ]; then
  if [ -n "${MEMPALACE_REMOTE_URL:-}" ] && [ -z "${MEMPALACE_PI_SSH_TARGET:-}" ]; then
    # Remote palace, but no inbox to ship transcripts to — the feeder genuinely
    # cannot do anything here, so skipping is right. Saying so is the point:
    # this branch used to be a bare `:`, and the skip happens *before* the
    # subshell below that writes mempalace-catchup.log, so a container in this
    # state contributed nothing to the palace and left no artifact at all — not
    # even an empty log — to explain why. That is indistinguishable from a
    # healthy run that simply had nothing to file. `tee` puts the notice both in
    # the container's start output (docker logs) and at the path anyone
    # debugging "why is nothing from this container in the palace?" looks first.
    # This is an entrypoint: a notice must never be able to stop a container
    # from starting. An unwritable ~/.pi (root-owned volume — a classic Docker
    # permission accident) makes `mkdir -p` fail, and under `set -e` that would
    # abort startup entirely: a brand-new failure mode in precisely the branch
    # that used to do nothing at all. Degrade to stdout-only instead.
    _mp_log="$HOME/.pi/agent/mempalace-catchup.log"
    mkdir -p "$HOME/.pi/agent" 2>/dev/null || _mp_log=/dev/null
    {
      echo "MemPalace catch-up skipped: remote palace with no transcript inbox."
      echo "  MEMPALACE_REMOTE_URL is set (${MEMPALACE_REMOTE_URL})"
      echo "  but MEMPALACE_PI_SSH_TARGET is not, so there is nowhere to ship this"
      echo "  container's staged sessions. MCP tools still read and write the shared"
      echo "  palace — but this container's own conversations are mined nowhere."
      echo "  Fix: set MEMPALACE_PI_SSH_TARGET (and MEMPALACE_PI_DEVICE) in .env,"
      echo "  or unset MEMPALACE_REMOTE_URL to keep the palace local."
      echo "  Deliberate? MEMPALACE_FEED=0 turns the feed off and silences this."
    } | tee "$_mp_log" 2>/dev/null || true
    unset _mp_log
  else
    mkdir -p "$HOME/.pi/agent"
    (
      "$MEMPALACE_FEEDER" --reason container-start \
        >"$HOME/.pi/agent/mempalace-catchup.log" 2>&1 || true
    ) &
  fi
fi

# ── Git config defaults ──────────────────────────────────────────────
if [ -n "${GIT_USER_NAME:-}" ] && ! git config --global user.name &>/dev/null; then
  git config --global user.name "$GIT_USER_NAME"
fi
if [ -n "${GIT_USER_EMAIL:-}" ] && ! git config --global user.email &>/dev/null; then
  git config --global user.email "$GIT_USER_EMAIL"
fi
# Global gitignore for personal/tooling artifacts (*.bak, *~, *.orig, ...).
# Seeded above into $HOME/.gitignore_global from /etc/skel-devbox. Point git at
# it only if the user has not already set their own core.excludesFile.
if [ -f "$HOME/.gitignore_global" ] && ! git config --global core.excludesFile &>/dev/null; then
  git config --global core.excludesFile "$HOME/.gitignore_global"
fi

# ── pi: deploy toolkit + extensions + mempalace bridge ─────────────
# pi is always installed in pi-devbox; no INSTALL_PI guard needed.
# Each install.sh is idempotent and backs up real files before linking,
# so re-running across container restarts is safe.
#
# Order: pi-toolkit first (creates ~/.pi/agent/keybindings.json symlink
# and writes the AWS env loader), then pi-extensions (symlinks our
# extensions), then settings.json bootstrap from the toolkit template,
# then the mempalace bridge symlink (one-liner; mempalace-toolkit's
# install_skill is intentionally skipped to avoid racing with skillset
# auto-deploy below).
if command -v pi &>/dev/null; then
  if [ -d /opt/pi-toolkit ]; then
    (cd /opt/pi-toolkit && ./install.sh --yes) || \
      echo "WARN: pi-toolkit install.sh failed (continuing)"
  fi

  if [ -d /opt/pi-extensions ]; then
    (cd /opt/pi-extensions && ./install.sh --yes) || \
      echo "WARN: pi-extensions install.sh failed (continuing)"
  fi

  # Bootstrap settings.json from template if absent (pi rewrites this
  # file at runtime — lastChangelogVersion, etc — so we can't symlink it).
  _pi_settings="$HOME/.pi/agent/settings.json"
  _pi_template=/opt/pi-toolkit/settings.example.json
  if [ ! -f "$_pi_settings" ] && [ -f "$_pi_template" ]; then
    cp "$_pi_template" "$_pi_settings"
    echo "pi settings.json bootstrapped from template"
  elif [ -f "$_pi_settings" ] && [ -f "$_pi_template" ] && \
       [ "${PI_SETTINGS_MERGE:-1}" != "0" ] && command -v jq >/dev/null 2>&1; then
    # Non-destructive merge: a settings.json on a PRESERVED volume never
    # otherwise sees new template keys (the bootstrap above only fires when
    # the file is absent), so config added in an image upgrade — e.g. the
    # observational-memory / pi-fork blocks or a newly-enabled model — never
    # reaches existing users. Deep-merge with the template FIRST and the
    # live file SECOND ('.[0] * .[1]') so the user's values always win and
    # only keys MISSING from the live file are filled in from the template.
    # Arrays are treated as leaves (the user's array is kept verbatim, so a
    # model they deliberately removed is not re-added). Only rewrite when the
    # merge actually changes something, and back up the original first.
    # Set PI_SETTINGS_MERGE=0 to disable. Invalid JSON on either side → skip,
    # never clobber.
    if _pi_merged=$(jq -s '.[0] * .[1]' "$_pi_template" "$_pi_settings" 2>/dev/null); then
      if [ -n "$_pi_merged" ] && \
         ! printf '%s' "$_pi_merged" | jq -e --slurpfile cur "$_pi_settings" '. == $cur[0]' >/dev/null 2>&1; then
        cp "$_pi_settings" "${_pi_settings}.bak.$(date +%Y%m%d-%H%M%S)"
        printf '%s\n' "$_pi_merged" > "$_pi_settings"
        echo "pi settings.json: merged new template keys from settings.example.json (backup saved)"
      fi
    else
      echo "WARN: pi settings.json merge skipped (jq could not parse template or live file; left untouched)"
    fi
  fi

  # pi↔mempalace MCP bridge — single extension symlink.
  if [ -f /opt/mempalace-toolkit/extensions/pi/mempalace.ts ] && \
     command -v mempalace &>/dev/null && \
     [ ! -L "$HOME/.pi/agent/extensions/mempalace.ts" ]; then
    ln -sf /opt/mempalace-toolkit/extensions/pi/mempalace.ts \
           "$HOME/.pi/agent/extensions/mempalace.ts"
  fi

  # pi-fork (fork tool) + pi-observational-memory (recall tool) + pi-atelier
  # (TUI sidebar panels/split-pane) + (in the :latest-studio variant only)
  # pi-studio (/studio command + studio_* tools + theme). These are pi packages (not symlink-style extensions):
  # they're cloned to /opt with node_modules baked at BUILD time, then
  # registered here via `pi install <local-path>`. A local-path install is
  # instant + in-place (pi loads the extension directly from /opt) +
  # idempotent (no duplicate package entry on re-run), and stores a relative
  # path that resolves into the image-layer /opt so it survives volume
  # recreate. The tools/command register on the NEXT pi start (extensions
  # bind at startup) or on `/reload`. Guard on settings.json so we only
  # install once per volume. /opt/pi-studio is present only in the studio
  # variant; the `[ -d ]` test makes this a no-op everywhere else.
  #
  # The guard MUST inspect the `packages` ARRAY, not merely grep the whole
  # file for the package name. settings.example.json ships a top-level
  # "pi-fork" CONFIG block (the fork effort profiles, pi-toolkit adb6907,
  # 2026-06-17), so a whole-file substring grep matches on any settings.json
  # that was bootstrapped from — or template-merged with — that template.
  # Worse, the merge above runs FIRST, so it plants the matching string in the
  # same startup that the loop then reads: `pi install /opt/pi-fork` was
  # skipped forever and the `fork` tool never registered (v1.0.0 → v1.6.3).
  # Its siblings escaped only by luck — the template key is
  # "observational-memory" (no pi- prefix) and there is no studio block.
  # jq reads the array; the grep fallback matches the stored relative-path
  # form ("…/opt/<name>\""), which a config KEY can never produce.
  _pi_pkg_registered() {
    _pi_reg_settings="$HOME/.pi/agent/settings.json"
    [ -f "$_pi_reg_settings" ] || return 1
    if command -v jq >/dev/null 2>&1; then
      jq -e --arg n "$1" \
        '(.packages // []) | any((type == "string") and (. == "npm:" + $n or endswith("/" + $n)))' \
        "$_pi_reg_settings" >/dev/null 2>&1
    else
      grep -q "opt/$1\"" "$_pi_reg_settings"
    fi
  }

  # ── pi-atelier: retire a stale `npm:pi-atelier`, plus an opt-out ──────
  # The image now vendors pi-atelier at a pinned, audited tag (PI_ATELIER_REF
  # in Dockerfile.variant). A leftover `npm:pi-atelier` entry from a
  # hand-install resolves through ~/.pi/npm-global, which lives on the
  # devbox-pi-config VOLUME — so it survives image upgrades and keeps whatever
  # version was installed by hand, unpinned and unaudited. That is not
  # academic: pi-atelier < 0.7.1 makes pi >= 0.84 hang at startup with
  # sustained CPU, so leaving it in place turns a pi bump into a TUI that will
  # not start. And `_pi_pkg_registered` deliberately counts `npm:<name>` as
  # registered (it respects a user's own npm install), so the loop below would
  # never replace it.
  #
  # We only DELETE the exact `npm:pi-atelier` string; the loop then registers
  # /opt/pi-atelier in pi's own canonical serialization, so this code never has
  # to guess the stored relative-path form. Idempotent — after the rewrite
  # there is no npm entry left to match.
  #
  # DEVBOX_ATELIER=0 goes further and removes pi-atelier from `packages`
  # altogether. That escape hatch lives HERE, in the entrypoint, precisely
  # because this component's known failure mode is "pi will not start" — which
  # you cannot repair with `pi uninstall`.
  _pi_atelier_drop() {
    # $1 = jq predicate over one `packages` entry, selecting what to REMOVE.
    # Returns 0 only when the file was actually rewritten (caller logs), 1 for
    # "nothing to do" — including missing jq or unparseable JSON, which must
    # never clobber user settings. Backs up first, same convention as the
    # template merge above.
    _ad_settings="$HOME/.pi/agent/settings.json"
    [ -f "$_ad_settings" ] || return 1
    command -v jq >/dev/null 2>&1 || return 1
    _ad_new=$(jq "(.packages // []) |= map(select(($1) | not))" "$_ad_settings" 2>/dev/null) || return 1
    [ -n "$_ad_new" ] || return 1
    if printf '%s' "$_ad_new" | jq -e --slurpfile cur "$_ad_settings" '. == $cur[0]' >/dev/null 2>&1; then
      return 1
    fi
    # `.bak.atelier.` rather than the merge's plain `.bak.` prefix: both can
    # fire in the same startup, and a bare seconds-resolution timestamp would
    # make the second cp overwrite the first one's backup.
    cp "$_ad_settings" "${_ad_settings}.bak.atelier.$(date +%Y%m%d-%H%M%S)"
    printf '%s\n' "$_ad_new" > "$_ad_settings"
    return 0
  }
  if [ "${DEVBOX_ATELIER:-1}" = "0" ]; then
    if _pi_atelier_drop '(. == "npm:pi-atelier") or ((type == "string") and endswith("/pi-atelier"))'; then
      echo "pi-atelier: unregistered per DEVBOX_ATELIER=0 (settings backup saved)"
    fi
  elif [ -d /opt/pi-atelier ]; then
    if _pi_atelier_drop '. == "npm:pi-atelier"'; then
      echo "pi-atelier: dropped stale npm: registration — the pinned /opt copy takes over (settings backup saved)"
    fi
  fi

  for _pkg in /opt/pi-fork /opt/pi-observational-memory /opt/pi-studio /opt/pi-atelier; do
    [ -d "$_pkg" ] || continue
    _name=$(basename "$_pkg")
    # DEVBOX_ATELIER=0 → leave pi-atelier unregistered (handled just above).
    if [ "$_name" = "pi-atelier" ] && [ "${DEVBOX_ATELIER:-1}" = "0" ]; then continue; fi
    if ! _pi_pkg_registered "$_name"; then
      pi install "$_pkg" >/dev/null 2>&1 || \
        echo "WARN: pi install $_name failed (continuing)"
    fi
  done
fi

# ── pi-studio: optional loopback bridge (opt-in) ──────────────────────
# pi-studio binds its server to 127.0.0.1 inside the container, which a
# published Docker port cannot reach. When STUDIO_EXPOSE is truthy (set in
# compose), start the `studio-expose` socat bridge in the background so a
# published port + `ssh -L` tunnel can reach Studio once the user runs
# `/studio --port "$STUDIO_PORT"`. Default OFF — Studio stays loopback-only
# (its secure default) unless explicitly opted in. Guarded on the studio
# variant (/opt/pi-studio) so it is a no-op in the plain image.
case "${STUDIO_EXPOSE:-}" in
  1|true|TRUE|yes|on)
    if [ -d /opt/pi-studio ] && command -v studio-expose &>/dev/null && command -v socat &>/dev/null; then
      echo "STUDIO_EXPOSE set — starting studio-expose bridge on port ${STUDIO_PORT:-8765} (background)"
      nohup studio-expose "${STUDIO_PORT:-8765}" >/tmp/studio-expose.log 2>&1 &
    else
      echo "STUDIO_EXPOSE set but studio-expose/socat/pi-studio unavailable — skipping bridge"
    fi
    ;;
esac

# ── Skillset: deploy skills/instructions from mounted skillset repo ──
# When the skillset repo is mounted (at $HOME/skillset or /workspace/skillset),
# run the deploy script to create relative symlinks for skills and instructions.
# This ensures skills resolve correctly inside the container regardless of
# where the repo lives on the host. Idempotent — second run is a no-op.
#
# Detection order:
#   1. SKILLSET_CONTAINER_PATH env var (explicit, for non-standard layouts)
#   2. $HOME/skillset (dedicated volume mount via SKILLSET_PATH in compose)
#   3. /workspace/skillset (skillset is directly inside workspace root)
SKILLSET_DEPLOY=""
if [ -n "${SKILLSET_CONTAINER_PATH:-}" ] && [ -x "${SKILLSET_CONTAINER_PATH}/deploy-skills.sh" ]; then
  SKILLSET_DEPLOY="${SKILLSET_CONTAINER_PATH}/deploy-skills.sh"
elif [ -x "$HOME/skillset/deploy-skills.sh" ]; then
  SKILLSET_DEPLOY="$HOME/skillset/deploy-skills.sh"
elif [ -x /workspace/skillset/deploy-skills.sh ]; then
  SKILLSET_DEPLOY="/workspace/skillset/deploy-skills.sh"
fi
if [ -n "$SKILLSET_DEPLOY" ]; then
  "$SKILLSET_DEPLOY" --bootstrap --prune-stale >/dev/null 2>&1 || true
  # The deploy leaves the early baked links (above) in place as foreign links,
  # which silently shadows the live clone for skills the skillset OWNS. Repoint
  # just those; baked stays the fallback, user overrides still win. `|| true`:
  # a skill-link refinement must never break container start.
  if command -v devbox-skill-reconcile >/dev/null 2>&1; then
    devbox-skill-reconcile "$(dirname "$SKILLSET_DEPLOY")" || true
  fi
fi

# ── Execute command ──────────────────────────────────────────────────
exec "$@"