AgapHost/openai/migrate-adolf-state.sh

#!/bin/bash
# Migration script for kb#219 — move Adolf's runtime state off the named
# Docker volume (openai_adolf-state) onto a host bind mount at
# /mnt/ssd/dbs/adolf/state, matching the convention every other Agap
# service already follows (hindsight, litellm, qdrant, langfuse, ...).
#
# SAFETY MODEL:
#   - COPY ONLY. Never touches or deletes the source volume. The volume
#     stays intact and usable as a rollback source until a human explicitly
#     removes it (see rollback section in the compose-diff writeup /
#     kb#219 report), long after this script has run and the container has
#     been soak-tested on the new mount.
#   - Dry-run by default. Pass --apply to actually copy.
#   - Idempotent. Safe to re-run; re-copying onto an already-populated
#     destination just refreshes it (cp -a overwrite-in-place). It will
#     NOT delete files at the destination that were removed from the
#     source between runs -- if that matters, wipe the dest dir yourself
#     before re-running.
#   - Verifies file counts + a sha256 manifest diff between source and
#     destination before declaring success. Non-zero exit if they disagree.
#   - Uses only `docker run` (alvis is in the `docker` group -- no `sudo`
#     needed for container operations) to read the volume; never reads
#     /var/lib/docker/volumes directly (root-only, 0700).
#   - Does NOT create /mnt/ssd/dbs/adolf itself. That directory tree is
#     root-owned (/mnt/ssd/dbs is 0755 root:root, same as every other
#     service dir under it) and must be created + chowned by a human with
#     sudo first -- see the paste-ready root block in the kb#219 report.
#     This script aborts early with a clear message if the destination
#     parent doesn't exist or isn't writable.
#
# USAGE:
#   ./migrate-adolf-state.sh                 # dry run (default), prints plan
#   ./migrate-adolf-state.sh --apply          # actually copies + verifies
#   ./migrate-adolf-state.sh --apply --dest /path/to/scratch --volume some-test-volume
#                                              # point at a throwaway volume/dest for a trial run
#
# This script is NOT executed against live state as part of kb#219 prep.
# It has been dry-run tested and trial-run tested against a throwaway
# volume with a handful of files (see kb#219 report for the transcript).

set -euo pipefail

SRC_VOLUME="openai_adolf-state"
DEST_DIR="/mnt/ssd/dbs/adolf/state"
APPLY=0

while [ $# -gt 0 ]; do
  case "$1" in
    --apply) APPLY=1; shift ;;
    --dest) DEST_DIR="$2"; shift 2 ;;
    --volume) SRC_VOLUME="$2"; shift 2 ;;
    -h|--help)
      grep '^#' "$0" | sed 's/^#//'
      exit 0
      ;;
    *)
      echo "Unknown argument: $1" >&2
      exit 2
      ;;
  esac
done

echo "== kb#219 adolf-state migration =="
echo "Source volume : $SRC_VOLUME"
echo "Dest dir      : $DEST_DIR"
echo "Mode          : $([ "$APPLY" -eq 1 ] && echo APPLY || echo DRY-RUN)"
echo

# --- 0. sanity: source volume exists ---
if ! docker volume inspect "$SRC_VOLUME" >/dev/null 2>&1; then
  echo "ERROR: source volume '$SRC_VOLUME' does not exist." >&2
  exit 1
fi

# --- 1. sanity: destination parent exists and is writable ---
DEST_PARENT="$(dirname "$DEST_DIR")"
if [ ! -d "$DEST_PARENT" ]; then
  cat >&2 <<EOF
ERROR: $DEST_PARENT does not exist.

/mnt/ssd/dbs is root-owned; this directory must be created by a human
with sudo before this script can run. See the paste-ready root block in
the kb#219 report (creates /mnt/ssd/dbs/adolf/{state,config,personas},
chowned 1000:1000 to match the adolf container's node user).
EOF
  exit 1
fi
if [ ! -w "$DEST_PARENT" ]; then
  echo "ERROR: $DEST_PARENT exists but is not writable by $(whoami). Check ownership (should be chowned to your uid, or 1000:1000)." >&2
  exit 1
fi

mkdir -p "$DEST_DIR"

# --- 2. source manifest (counts + sha256, computed inside a container) ---
echo "-- Computing source manifest (read-only mount of $SRC_VOLUME) --"
SRC_COUNT=$(docker run --rm -v "$SRC_VOLUME":/from:ro alpine sh -c "find /from -type f | wc -l")
echo "Source file count: $SRC_COUNT"

if [ "$APPLY" -eq 0 ]; then
  echo
  echo "[DRY RUN] Would copy $SRC_COUNT files from volume '$SRC_VOLUME' into $DEST_DIR,"
  echo "[DRY RUN] then verify file count + sha256 manifest match."
  echo "[DRY RUN] Re-run with --apply to actually copy."
  exit 0
fi

# --- 3. copy (tar stream preserves ownership/perms across the boundary) ---
echo "-- Copying (tar stream, preserves perms/ownership) --"
docker run --rm \
  -v "$SRC_VOLUME":/from:ro \
  -v "$DEST_DIR":/to \
  alpine sh -c "cd /from && tar cf - . | (cd /to && tar xf -)"

# --- 4. verify: file count ---
DEST_COUNT=$(docker run --rm -v "$DEST_DIR":/to:ro alpine sh -c "find /to -type f | wc -l")
echo "Dest file count: $DEST_COUNT"
if [ "$SRC_COUNT" != "$DEST_COUNT" ]; then
  echo "ERROR: file count mismatch (source=$SRC_COUNT dest=$DEST_COUNT). NOT declaring success." >&2
  exit 1
fi

# --- 5. verify: sha256 manifest diff ---
echo "-- Verifying sha256 manifests match --"
SRC_MANIFEST=$(mktemp)
DEST_MANIFEST=$(mktemp)
trap 'rm -f "$SRC_MANIFEST" "$DEST_MANIFEST"' EXIT

docker run --rm -v "$SRC_VOLUME":/from:ro alpine sh -c \
  "cd /from && find . -type f -exec sha256sum {} \; | sort -k2" > "$SRC_MANIFEST"
docker run --rm -v "$DEST_DIR":/to:ro alpine sh -c \
  "cd /to && find . -type f -exec sha256sum {} \; | sort -k2" > "$DEST_MANIFEST"

if diff -u "$SRC_MANIFEST" "$DEST_MANIFEST" > /tmp/adolf-state-migration.diff; then
  echo "OK: manifests match byte-for-byte ($SRC_COUNT files)."
else
  echo "ERROR: manifest mismatch, see /tmp/adolf-state-migration.diff" >&2
  cat /tmp/adolf-state-migration.diff >&2
  exit 1
fi

echo
echo "== Migration copy verified OK =="
echo "Source volume '$SRC_VOLUME' left untouched (not deleted, not modified)."
echo "Next steps (NOT done by this script -- human-supervised, see kb#219 report):"
echo "  1. Apply the docker-compose.yml bind-mount diff for the 'adolf' service."
echo "  2. docker compose -f openai/docker-compose.yml config -q   # validate"
echo "  3. docker compose -f openai/docker-compose.yml up -d adolf # recreates container on new mount"
echo "  4. Verify: docker inspect adolf shows /mnt/ssd/dbs/adolf/state, not the volume;"
echo "     Matrix session survives (no re-login), memory/config/persona intact."
echo "  5. Only after a soak period: docker volume rm $SRC_VOLUME"