#!/usr/bin/env bash
# Tarball everything about THIS workstation that git does not have.
#
# The repo itself is pushed to Gitea and needs no backup. What has no other
# copy is the ignored/untracked state around it -- and docs/incidents.md #5
# records what happens when that is lost: `git clean -fdx` took router.db,
# .env, .venv and config/config.local.yaml in one command, and recovery was
# luck.
#
# INCLUDED (irreplaceable or expensive to recreate):
#   router.db                 measurement history; cannot be regenerated
#   .env                      provider API key
#   config/config.local.yaml  operator tariff and local overrides
#   .omo/                     plans, evidence ledger, boulder state
#   ~/.config/systemd/user    tuned units (the graceful-shutdown fix etc.)
#   ~/.config/opencode        agent plugins incl. session-registry.js
#   ~/.claude/.../memory      cross-session memory for this project
#
# EXCLUDED on purpose:
#   .venv          rebuildable: python -m venv .venv && pip install -r requirements.txt
#   node_modules   rebuildable
#   ollama models  ~30GB and re-pullable; Modelfile recipes are in docs/local-models.md
#   .git           the remote has it
set -euo pipefail

REPO="${REPO:-$HOME/Sources/6krrt}"
DEST="${LLM_ROUTER_BACKUP_DIR:-$HOME/.local/share/6krrt-backups}"
KEEP="${WORKSTATION_BACKUP_KEEP:-7}"

mkdir -p "$DEST"
stamp=$(date +%Y%m%d-%H%M%S)
out="$DEST/workstation-$stamp.tar.gz"
staging=$(mktemp -d)
trap 'rm -rf "$staging"' EXIT

# Snapshot the DB properly rather than tarring a live file: `cp`/`tar` on an
# open SQLite database can capture a torn page set that still looks valid.
sqlite3 "$REPO/router.db" ".backup '$staging/router.db'"

mkdir -p "$staging/repo/config"
[ -f "$REPO/.env" ] && cp -f "$REPO/.env" "$staging/repo/.env"
[ -f "$REPO/config/config.local.yaml" ] && cp -f "$REPO/config/config.local.yaml" "$staging/repo/config/"
[ -d "$REPO/.omo" ] && cp -a "$REPO/.omo" "$staging/repo/.omo"

mkdir -p "$staging/home"
[ -d "$HOME/.config/systemd/user" ] && cp -a "$HOME/.config/systemd/user" "$staging/home/systemd-user"
[ -d "$HOME/.config/opencode" ] && cp -a "$HOME/.config/opencode" "$staging/home/opencode"
mem="$HOME/.claude/projects/-home-alee-Sources-6krrt/memory"
[ -d "$mem" ] && cp -a "$mem" "$staging/home/claude-memory"

cat > "$staging/RESTORE.md" <<'INNER'
# Restoring this workstation

The repo comes from Gitea; this tarball has only what git does not.

    git clone ssh://git@git.adlee.work:2222/alee/6krrt.git
    cd 6krrt
    python3 -m venv .venv && .venv/bin/pip install -r requirements.txt

Then from this archive:

    cp router.db            <repo>/router.db
    cp repo/.env            <repo>/.env      && chmod 600 <repo>/.env
    cp repo/config/config.local.yaml <repo>/config/
    cp -a repo/.omo         <repo>/.omo
    cp -a home/systemd-user/* ~/.config/systemd/user/ && systemctl --user daemon-reload
    cp -a home/opencode     ~/.config/opencode

Ollama models are not here. Re-pull and re-tag per docs/local-models.md:
    ollama pull qwen2.5-coder:14b && ollama pull qwen3-vl:4b
    (then the Modelfile num_ctx tags documented there)

Verify:
    sqlite3 <repo>/router.db "select integrity_check from pragma_integrity_check limit 1;"
    systemctl --user restart llm-router.service && curl -s localhost:8080/health
INNER

tar -czf "$out" -C "$staging" .

# Verify the archive reads back before rotating anything away.
tar -tzf "$out" >/dev/null || { rm -f "$out"; echo "archive FAILED to verify; discarded" >&2; exit 1; }

# shellcheck disable=SC2012
ls -1t "$DEST"/workstation-*.tar.gz 2>/dev/null | tail -n +$((KEEP + 1)) | xargs -r rm -f

echo "workstation backup ok: $out ($(du -h "$out" | cut -f1)), keeping $KEEP"