feat: kit-busrouter v2.0 — complete Synology + GL fleet router platform

Includes:
- package/ GL-XE3000 kit-busrouter (opkg)
- scripts/provision.sh (GL) and provision-synology.sh (Synology)
- syno-balance/ — new WAN balancer replacing aiwanbal (SmartWAN adapter)
- kit-connect/ — unified connectivity SPK (Tailscale + reverse SSH)
- docs/deployment/synology-rt2600ac-checklist.md — 62-point checklist
- docs/provisioning/device-identity.md — fleet identity spec
- docs/pilot/checklist.md — field pilot validation
- x4078_20260721.dss — reference config backup

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-22 00:07:14 +00:00
commit f15ac69925
41 changed files with 5083 additions and 0 deletions
@@ -0,0 +1,337 @@
#!/bin/sh
# telemetry-synology.sh — Synology SRM telemetry payload builder for fleet hub.
#
# Reads aiwanbal state files from /tmp/aiwanbal/ and optionally queries the
# Eyeride Eyenet (OpenWrt ubus) for GPS position. Posts JSON to the fleet hub
# over Tailscale with disk-buffered retry on failure.
#
# Config (environment variables):
# TELEMETRY_HUB POST endpoint (default: http://10.88.0.1:8080/api/telemetry)
# TELEMETRY_BUFFER_DIR disk buffer for failed POSTs (default: /tmp/busrouter/telemetry-buf)
# AIWANBAL_STATE_DIR aiwanbal runtime state (default: /tmp/aiwanbal)
# EYERIDE_IP Eyeride OpenWrt IP for GPS (default: 192.168.10.1)
# EYERIDE_PORT Eyeride ubus port (default: 8080)
# EYERIDE_USER Eyeride SSH/ubus username (default: root)
# EYERIDE_PASSWORD Eyeride password (required for GPS)
#
# Public API:
# eyeride_gps query GPS from Eyeride ubus; echo 'lat lon fix';
# exit 1 if unavailable
# telemetry_synology_collect emit JSON payload to stdout from aiwanbal state files
# telemetry_synology_flush retry all buffered payloads; return 1 if hub still down
# telemetry_synology_send collect + flush + post; buffer on failure
#
# Cron mode: runs telemetry_synology_send when executed directly.
LIB_DIR="${LIB_DIR:-/usr/lib/busrouter}"
: "${TELEMETRY_HUB:=http://10.88.0.1:8080/api/telemetry}"
: "${TELEMETRY_BUFFER_DIR:=/tmp/busrouter/telemetry-buf}"
: "${AIWANBAL_STATE_DIR:=/tmp/aiwanbal}"
: "${EYERIDE_IP:=192.168.10.1}"
: "${EYERIDE_PORT:=8080}"
: "${EYERIDE_USER:=root}"
_TELEM_SEQ=0
# ── Helpers ─────────────────────────────────────────────────────────────────────
# Escape a string value for JSON (backslash and double-quote only).
_json_str() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g'; }
# Read an aiwanbal state file, return empty string if missing.
_aiwanbal_val() {
local key="$1"
cat "${AIWANBAL_STATE_DIR}/${key}" 2>/dev/null || true
}
# ── Eyeride GPS (ubus JSON-RPC) ─────────────────────────────────────────────────
#
# The Eyeride Eyenet is an OpenWrt device at 192.168.10.1:8080 with ubus
# JSON-RPC. GPS data may be available through:
# 1. ubus call gps status (if gps service is running)
# 2. ubus call location status (alternative service name)
# 3. /tmp/gps/last_fix on the Eyeride (mounted via NFS/SMB or scraped)
#
# This function tries option 1 first, then falls back gracefully.
# Authenticate to Eyeride ubus, return session token on stdout.
_eyeride_login() {
local _pass="${EYERIDE_PASSWORD:-}"
[ -n "$_pass" ] || return 1
local _login_body _login_resp _session
_login_body="{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"call\",\"params\":[\"00000000000000000000000000000000\",\"session\",\"login\",{\"username\":\"${EYERIDE_USER}\",\"password\":\"${_pass}\"}]}"
_login_resp=$(curl -s --connect-timeout 5 -X POST \
-H 'Content-Type: application/json' \
-d "$_login_body" \
"http://${EYERIDE_IP}:${EYERIDE_PORT}/ubus" 2>/dev/null) || return 1
# Check for auth failure: ubus returns [6] for permission denied
if [ -z "$_login_resp" ] || echo "$_login_resp" | grep -q '"result":\[6\]'; then
return 1
fi
_session=$(echo "$_login_resp" | sed 's/.*"ubus_rpc_session":"\([^"]*\)".*/\1/')
[ -n "$_session" ] && [ "$_session" != "$_login_resp" ] || return 1
printf '%s\n' "$_session"
}
# Call a ubus method on the Eyeride with an active session token.
# Usage: _eyeride_ubus_call <session> <service> <method> [params_json]
_eyeride_ubus_call() {
local _session="$1" _svc="$2" _method="$3" _params="${4:-{}}"
local _body
_body="{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"call\",\"params\":[\"${_session}\",\"${_svc}\",\"${_method}\",${_params}]}"
curl -s --connect-timeout 5 -X POST \
-H 'Content-Type: application/json' \
-d "$_body" \
"http://${EYERIDE_IP}:${EYERIDE_PORT}/ubus" 2>/dev/null
}
# Query GPS position from Eyeride.
# Emits 'lat lon fix_quality' on success; exit 1 on failure or no fix.
eyeride_gps() {
local _session _resp _lat _lon _fix
_session=$(_eyeride_login) || return 1
# Try 'gps' service first (common OpenWrt gpsd ubus binding)
_resp=$(_eyeride_ubus_call "$_session" "gps" "status") 2>/dev/null
if [ -z "$_resp" ] || echo "$_resp" | grep -q '"result":\[2\]'; then
# gps service not found — try 'location' service
_resp=$(_eyeride_ubus_call "$_session" "location" "status") 2>/dev/null
fi
# Try to extract lat/lon from ubus response JSON
_lat=$(echo "$_resp" | sed 's/.*"latitude":\([0-9.-]*\).*/\1/' 2>/dev/null)
_lon=$(echo "$_resp" | sed 's/.*"longitude":\([0-9.-]*\).*/\1/' 2>/dev/null)
# Also try snake_case variants
[ "$_lat" = "$_resp" ] && _lat=$(echo "$_resp" | sed 's/.*"lat":\([0-9.-]*\).*/\1/' 2>/dev/null)
[ "$_lon" = "$_resp" ] && _lon=$(echo "$_resp" | sed 's/.*"lon":\([0-9.-]*\).*/\1/' 2>/dev/null)
# Alt spelling
[ "$_lat" = "$_resp" ] && _lat=$(echo "$_resp" | sed 's/.*"lat_deg":\([0-9.-]*\).*/\1/' 2>/dev/null)
[ "$_lon" = "$_resp" ] && _lon=$(echo "$_resp" | sed 's/.*"lon_deg":\([0-9.-]*\).*/\1/' 2>/dev/null)
# Sanitize: if sed didn't match, the field equals the full response
[ "$_lat" = "$_resp" ] && _lat=""
[ "$_lon" = "$_resp" ] && _lon=""
if [ -n "$_lat" ] && [ -n "$_lon" ]; then
_fix=2 # assume 2D fix if we got coordinates
[ -n "$_fix" ] || _fix=2
logger -t busrouter -p daemon.debug "eyeride_gps: ${_lat} ${_lon} fix=${_fix}"
printf '%s %s %s\n' "$_lat" "$_lon" "$_fix"
return 0
fi
logger -t busrouter "eyeride_gps: no fix from Eyeride"
return 1
}
# ── Telemetry Collection ─────────────────────────────────────────────────────────
#
# State files read from AIWANBAL_STATE_DIR (written by aiwanbal daemon each cycle):
# wan1_score_avg, wan2_score_avg integer 0100
# wan1_latency, wan2_latency ms
# wan1_throughput, wan2_throughput B/s (converted to Mbps below)
# wan1_upload, wan2_upload B/s
# wan1_jitter, wan2_jitter ms
# wan1_packet_loss, wan2_packet_loss %
# wan1_rsrp, wan2_rsrp dBm (cellular signal)
# wan1_rsrq, wan2_rsrq dB
# wan1_sinr, wan2_sinr dB
# wan1_technology, wan2_technology e.g. "5G-NR", "LTE"
# wan1_modem_type, wan2_modem_type e.g. "eyeride", "peplink", "none"
# wan0_mode "active" or "failover"
# wan0_starlink_quality quality score (if Starlink connected)
# wan0_starlink_latency ms
# wan0_starlink_obstruction bool-ish
# wan0_starlink_outage bool-ish
# Read one WAN's metrics and emit a JSON object fragment.
# Usage: _synology_wan_json <wan_num>
_synology_wan_json() {
local n="$1"
local score lat dl ul jitter loss rsrp rsrq sinr tech carrier modem
score=$(_aiwanbal_val "wan${n}_score_avg")
lat=$(_aiwanbal_val "wan${n}_latency")
local throughput_bytes
throughput_bytes=$(_aiwanbal_val "wan${n}_throughput")
dl=""
[ -n "$throughput_bytes" ] && dl=$(awk "BEGIN { printf \"%.1f\", ${throughput_bytes} / 125000 }" 2>/dev/null)
[ -z "$dl" ] && dl="0"
local upload_bytes
upload_bytes=$(_aiwanbal_val "wan${n}_upload")
ul=""
[ -n "$upload_bytes" ] && ul=$(awk "BEGIN { printf \"%.1f\", ${upload_bytes} / 125000 }" 2>/dev/null)
[ -z "$ul" ] && ul="0"
jitter=$(_aiwanbal_val "wan${n}_jitter")
loss=$(_aiwanbal_val "wan${n}_packet_loss")
rsrp=$(_aiwanbal_val "wan${n}_rsrp")
rsrq=$(_aiwanbal_val "wan${n}_rsrq")
sinr=$(_aiwanbal_val "wan${n}_sinr")
tech=$(_aiwanbal_val "wan${n}_technology")
modem=$(_aiwanbal_val "wan${n}_modem_type")
# Carrier is not tracked separately by aiwanbal — derive from modem type
carrier=""
case "$modem" in
eyeride) carrier="Eyeride" ;;
peplink) carrier="Peplink" ;;
zte) carrier="ZTE" ;;
mofi) carrier="Mofi" ;;
none|generic|"") carrier="" ;;
*) carrier="$modem" ;;
esac
local esc_tech esc_carrier
esc_tech=$(_json_str "${tech:-unknown}")
esc_carrier=$(_json_str "${carrier:-unknown}")
printf '{"score":%s,"latency_ms":%s,"dl_mbps":%s,"ul_mbps":%s,"jitter_ms":%s,"loss_pct":%s,"rsrp_dbm":%s,"rsrq_db":%s,"sinr_db":%s,"technology":"%s","carrier":"%s"}' \
"${score:-0}" \
"${lat:-null}" \
"${dl:-0}" \
"${ul:-0}" \
"${jitter:-null}" \
"${loss:-null}" \
"${rsrp:-null}" \
"${rsrq:-null}" \
"${sinr:-null}" \
"${esc_tech}" \
"${esc_carrier}"
}
# Build the full telemetry JSON payload from aiwanbal state files.
# Emits JSON on stdout; never fails — uses defaults for all missing fields.
telemetry_synology_collect() {
local now device_id uptime_s version
now=$(date +%s)
device_id=$(cat /etc/busrouter/device-id 2>/dev/null || hostname)
uptime_s=$(awk '{printf "%d", $1}' /proc/uptime 2>/dev/null)
version=$(cat /etc/busrouter/version 2>/dev/null || echo "dev")
# GPS
local gps_lat gps_lon gps_fix
if gps_out=$(eyeride_gps 2>/dev/null); then
read -r gps_lat gps_lon gps_fix <<-EOF
$gps_out
EOF
fi
# WAN 1 + WAN 2
local wan1_json wan2_json
wan1_json=$(_synology_wan_json 1)
wan2_json=$(_synology_wan_json 2)
# Active WAN — which one is currently carrying traffic
local mode sel_primary
mode=$(_aiwanbal_val "wan0_mode")
case "$mode" in
failover)
# In failover, primary is the active one; check which is up
local wan1_state wan2_state
wan1_state=$(_aiwanbal_val "wan1_state")
wan2_state=$(_aiwanbal_val "wan2_state")
if [ "$wan2_state" = "up" ]; then
sel_primary="wan2"
else
sel_primary="wan1"
fi
;;
*)
# Load-balance mode: both are active; wan1 is primary
sel_primary="wan1"
;;
esac
# Starlink (may be attached to one of the WANs)
local sl_lat sl_dl sl_obs sl_outage
sl_lat=$(_aiwanbal_val "wan0_starlink_latency")
sl_dl=$(_aiwanbal_val "wan0_starlink_quality")
sl_obs=$(_aiwanbal_val "wan0_starlink_obstruction")
sl_outage=$(_aiwanbal_val "wan0_starlink_outage")
# Convert Starlink quality to bps (quality is a score 0100, not bps)
# Store quality as-is; the hub can interpret it
local sl_quality
sl_quality="${sl_dl:-0}"
local esc_id esc_ver esc_sel
esc_id=$(_json_str "$device_id")
esc_ver=$(_json_str "$version")
esc_sel=$(_json_str "$sel_primary")
printf '{"device_id":"%s","timestamp":%d,"uptime":%d,"version":"%s","platform":"synology","sel_primary":"%s","gps":{"lat":%s,"lon":%s,"fix":%s},"wan":{"wan1":%s,"wan2":%s},"starlink":{"quality":%s,"latency_ms":%s,"obstructed":%s,"outage":%s}}\n' \
"${esc_id}" "${now:-0}" "${uptime_s:-0}" "${esc_ver}" "${esc_sel}" \
"${gps_lat:-null}" "${gps_lon:-null}" "${gps_fix:-null}" \
"${wan1_json}" "${wan2_json}" \
"${sl_quality:-0}" "${sl_lat:-null}" "${sl_obs:-0}" "${sl_outage:-0}"
}
# ── Hub POST + Buffering ─────────────────────────────────────────────────────────
# POST a JSON file to the hub. Returns 0 on HTTP 2xx, 1 on any failure.
_telemetry_try_post() {
local file="$1"
local code
code=$(curl -sf -X POST -H "Content-Type: application/json" \
--data-binary @"$file" -o /dev/null -w "%{http_code}" \
--max-time 10 "$TELEMETRY_HUB" 2>/dev/null)
case "$code" in 2*) return 0 ;; *) return 1 ;; esac
}
# Retry all buffered payloads in timestamp order.
# Stops on first failure to avoid hammering a down hub.
telemetry_synology_flush() {
[ -d "$TELEMETRY_BUFFER_DIR" ] || return 0
local f
for f in "$TELEMETRY_BUFFER_DIR"/*.json; do
[ -f "$f" ] || continue
if _telemetry_try_post "$f"; then
rm -f "$f"
logger -t busrouter -p daemon.debug "telemetry_synology_flush: sent $(basename "$f")"
else
logger -t busrouter "telemetry_synology_flush: hub unreachable, stopping"
return 1
fi
done
}
# Collect metrics, flush old buffer, POST current payload.
# On POST failure: saves payload to TELEMETRY_BUFFER_DIR.
# Never blocks the caller on hub downtime.
telemetry_synology_send() {
local payload
payload=$(telemetry_synology_collect)
telemetry_synology_flush 2>/dev/null || true
mkdir -p "$TELEMETRY_BUFFER_DIR"
_TELEM_SEQ=$(( _TELEM_SEQ + 1 ))
local tmpfile="${TELEMETRY_BUFFER_DIR}/$(date +%s)_$$_${_TELEM_SEQ}.json"
# Cap buffer to 60 files to protect tmpfs
local buf_count
buf_count=$(ls "$TELEMETRY_BUFFER_DIR"/*.json 2>/dev/null | wc -l)
if [ "${buf_count:-0}" -ge 60 ]; then
local oldest
oldest=$(ls "$TELEMETRY_BUFFER_DIR"/*.json 2>/dev/null | sort | head -n 1)
[ -f "$oldest" ] && rm -f "$oldest"
fi
printf '%s\n' "$payload" > "$tmpfile"
if _telemetry_try_post "$tmpfile"; then
rm -f "$tmpfile"
logger -t busrouter -p daemon.debug "telemetry_synology_send: posted ok"
else
logger -t busrouter "telemetry_synology_send: hub unreachable, buffered $(basename "$tmpfile")"
fi
}
# ── Entry Point ──────────────────────────────────────────────────────────────────
# When executed directly (e.g. from cron), run a single telemetry cycle.
case "${0##*/}" in
telemetry-synology.sh|telemetry-synology)
telemetry_synology_send
;;
esac