#!/bin/zsh
# Push perfcheck to the m4mini watchdog, where the nightly godcheck cron runs it.
#
# Idempotent — re-run it whenever bench.py or run_fleet.py changes, otherwise the fleet keeps
# being measured by the old benchmark. Accumulated state (history/baselines/pending) is NEVER
# overwritten: on the first deploy the local history is seeded across so the baselines carry
# over, and after that the m4mini's copy is authoritative.
#
# Lives beside godcheck (~/godcheck/perfcheck) rather than in ~/MODELBEAST, to match how
# godcheck itself is a standalone script and to keep the cron independent of the repo state.
set -u
W=m4mini@100.124.220.31
DEST=godcheck/perfcheck
HERE=${0:A:h}

echo "==> deploying perfcheck to $W:~/$DEST"
ssh -o ConnectTimeout=10 -o BatchMode=yes "$W" "mkdir -p ~/$DEST"
scp -q "$HERE/bench.py" "$HERE/run_fleet.py" "$W:$DEST/"
ssh -o ConnectTimeout=10 -o BatchMode=yes "$W" "chmod +x ~/$DEST/run_fleet.py"

# Seed history only if the watchdog has none, so a redeploy never clobbers real history.
#
# Tested on OUTPUT, never on ssh's exit status: the m4mini is the one node in the fleet with
# Tailscale SSH enabled (`RunSSH: true`), and tailscaled handles the session itself rather than
# sshd — it does not propagate the remote exit code. `ssh m4mini "exit 7"` returns 0, so every
# `if ssh m4mini test ...` silently succeeds. Every other node propagates correctly. (godcheck
# is output-based throughout and is unaffected.)
have=$(ssh -o ConnectTimeout=10 -o BatchMode=yes "$W" "test -s ~/$DEST/history.jsonl && echo YES")
if [ "$have" = "YES" ]; then
  echo "==> watchdog already has history — left untouched"
elif [ -s "$HERE/history.jsonl" ]; then
  echo "==> seeding history.jsonl (first deploy)"
  scp -q "$HERE/history.jsonl" "$W:$DEST/"
fi

echo "==> smoke test (one node)"
ssh -o ConnectTimeout=10 -o BatchMode=yes "$W" "cd ~/$DEST && /usr/bin/python3 run_fleet.py --only m4mini --quiet"
echo "==> done"