#!/bin/bash

# Re-weave host-local upstream overrides (method disables etc.) into the freshly
# pushed configs BEFORE signaling dshackle - makes /root/rpc-local/dshackle-overrides.yaml
# survive every configure-drpc regeneration. See apply-dshackle-overrides.py.
[ -f /root/rpc/apply-dshackle-overrides.py ] && python3 /root/rpc/apply-dshackle-overrides.py

# 1:1 invariant (2026-07-15): refuse to ACTIVATE a dshackle config routing >1 node for the same
# chain — we can't attribute traffic to multiple nodes behind one proxy (no per-upstream request
# metric; conn-seconds biases it), and the attribution model + planner assume 1:1. The validator
# reads /root/rpc/main_configs/*.yaml; on violation it exits 1 and we keep the live config.
# See /root/proxy-1to1-invariant-plan.md + rpc/validate-dshackle-1to1.py.
if [ -f /root/rpc/validate-dshackle-1to1.py ]; then
  python3 /root/rpc/validate-dshackle-1to1.py /root/rpc/main_configs || {
    echo "reload_dshackle.sh: REFUSING reload — 1:1 invariant violated (above); keeping live config" >&2
    exit 1
  }
fi

# Signal dshackle to reload, then VERIFY the reload applied. dshackle's SIGHUP reload is
# unreliable for upstream REMOVALS (and method-set changes, same remove+add path): it can
# throw internally, log "Config is not reloaded, cause - ...", and SILENTLY keep serving the
# old config (in-memory config updated, runtime selectors stale = drift). Note
# "Reloading config has been completed" is NOT success — it's a finally-block and prints even
# when a processor threw. There is no runtime admin API to mutate upstreams, so a container
# restart is the only way to actually apply such changes.
# Per container: SIGHUP, check the post-SIGHUP logs for a failure/drop marker, restart on
# failure. Exit 0 when the config ends up applied (via SIGHUP or restart); non-zero only if a
# needed restart failed or the container didn't come back (so the deploy fails loudly instead
# of silently drifting).
set -u
FAIL_MARK='Config is not reloaded, cause -'   # a reload processor threw (removal/method bug)
DROP_MARK='Reloading is in progress'          # a concurrent HUP was dropped (reload skipped)
SETTLE=3                                      # seconds for the SIGHUP handler to run + log
RC=0

for CID in $(docker ps -q -f "name=dshackle"); do
  NAME=$(docker inspect -f '{{.Name}}' "$CID" 2>/dev/null | sed 's|^/||')
  [ -n "$NAME" ] || NAME="$CID"
  T0=$(date +%s)
  if ! docker kill --signal=HUP "$CID" >/dev/null 2>&1; then
    echo "reload_dshackle: WARNING: failed to SIGHUP $NAME" >&2
    RC=1
    continue
  fi
  sleep "$SETTLE"
  LOGS=$(docker logs --since "$T0" "$CID" 2>&1)
  REASON=""
  if echo "$LOGS" | grep -qF "$FAIL_MARK"; then
    REASON=$(echo "$LOGS" | grep -F "$FAIL_MARK" | head -1)
  elif echo "$LOGS" | grep -qF "$DROP_MARK"; then
    REASON="concurrent HUP dropped (reload skipped)"
  fi
  [ -z "$REASON" ] && continue                  # SIGHUP applied the config — done
  echo "reload_dshackle: $NAME reload did NOT apply ($REASON) — restarting to load config fresh" >&2
  if ! docker restart "$CID" >/dev/null 2>&1; then
    echo "reload_dshackle: ERROR: restart failed for $NAME — config NOT applied, manual intervention" >&2
    RC=1
    continue
  fi
  UP=""
  for _ in $(seq 1 30); do
    if docker inspect -f '{{.State.Running}}' "$CID" 2>/dev/null | grep -q true; then UP=1; break; fi
    sleep 2
  done
  if [ -n "$UP" ]; then
    echo "reload_dshackle: $NAME restarted, config applied on clean start" >&2
  else
    echo "reload_dshackle: ERROR: $NAME not running after restart — manual intervention" >&2
    RC=1
  fi
done

exit $RC