#!/usr/bin/env bash
#
# start-fleet.example.sh — reference launcher for a multi-product local fleet.
#
# Starts one detached `agent-queue.sh run` daemon (a "factory") per product, each
# routing work through the platform-service fleet coordinator. This is the tracked,
# parameterized version of the operational `_start_fleet.sh` people keep in their
# local sandbox — copy it, adjust the env vars, and run.
#
# Prereqs:
#   - platform-service running on $AQ_FLEET_API (see scripts/deploy-gigafactory.sh)
#   - a factory token in $FLEET_TOKEN_FILE (an admin/factory JWT for the fleet API)
#   - tmux + the `longrun` helper (sourced below) for detached, logged daemons
#
# Env overrides (all optional):
#   SB                 sandbox/state root (per-product queues live in $SB/q_<product>)
#   AQ                 path to agent-queue.sh
#   AQ_FLEET_API       coordinator base URL (default http://localhost:4003/api)
#   FLEET_TOKEN_FILE   file holding the bearer token (default $SB/.token)
#   PRODUCTS           space-separated product ids (default: the ecosystem set)
#   AGENT_QUEUE_MAX    per-factory concurrency (default 3)
#
# Docs: ../docs/GIGAFACTORY/GIGAFACTORY_SYSTEM_OVERVIEW.md (§9 API, §14 gotchas) and
#       ../docs/GIGAFACTORY/FLEET_DISPATCH_REDESIGN.md (the M0 RU gate).
set -uo pipefail

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SB="${SB:-$PWD/.fleet-sandbox}"
AQ="${AQ:-$HERE/../agent-queue.sh}"
AQ_FLEET_API="${AQ_FLEET_API:-http://localhost:4003/api}"
FLEET_TOKEN_FILE="${FLEET_TOKEN_FILE:-$SB/.token}"
PRODUCTS="${PRODUCTS:-lysnrai chronomind mindlyst nomgap}"
AGENT_QUEUE_MAX="${AGENT_QUEUE_MAX:-3}"
LONGRUN_ALIAS="${LONGRUN_ALIAS:-$HERE/../../aliases/_longrun.alias}"

[ -f "$AQ" ] || { echo "agent-queue.sh not found at $AQ (set AQ=)"; exit 1; }
[ -s "$FLEET_TOKEN_FILE" ] || { echo "fleet token not found at $FLEET_TOKEN_FILE (set FLEET_TOKEN_FILE=)"; exit 1; }
TOK="$(cat "$FLEET_TOKEN_FILE")"

mkdir -p "$SB"
export LONGRUN_LOG_DIR="$SB"
# shellcheck disable=SC1090
source "$LONGRUN_ALIAS"

for p in $PRODUCTS; do
  ROOT="$SB/q_$p"
  longrun "gigafactory-$p" env \
    AGENT_QUEUE_ROOT="$ROOT" \
    AGENT_QUEUE_ENGINE=devin \
    AGENT_QUEUE_MAX="$AGENT_QUEUE_MAX" \
    AQ_FLEET=1 AQ_FLEET_ROUTE=1 \
    AQ_FLEET_API="$AQ_FLEET_API" \
    AQ_FLEET_TOKEN="$TOK" \
    AQ_PRODUCT_ID="$p" \
    AQ_FACTORY_ID="mac-$p" \
    AQ_FLEET_GATE=1 \
    AQ_FLEET_LEASE_RENEW_SEC=30 \
    "$AQ" run
  echo "----"
done

# Why these two matter (both verified on a live fleet):
#   AQ_FLEET_GATE=1            §M0 RU gate — the run loop point-reads the cheap
#                             per-product queue version (GET /fleet/queue-state) and
#                             SKIPS the claim while nothing changed, slashing idle
#                             Cosmos RU. Default OFF; safe (fails open). See
#                             FLEET_DISPATCH_REDESIGN.md §8/§12.
#   AQ_FLEET_LEASE_RENEW_SEC=30  heartbeat/renew cadence. MUST stay well under the
#                             coordinator's 90s stale threshold, or a healthy
#                             factory flaps to "stale"/"no live factory" between
#                             beats (the 300s default caused exactly that).
#
# Stop a factory:  tmux kill-session -t gigafactory-<product>
# Tail a factory:  tail -f "$SB"/longrun-gigafactory-<product>-*.log