NODEDC_PLATFORM/infra/scripts/check-ai-workspace-topology.sh

237 lines
7.2 KiB
Bash
Executable File

#!/usr/bin/env sh
set -eu
SCRIPT_DIR=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
INFRA_DIR=$(CDPATH= cd -- "$SCRIPT_DIR/.." && pwd)
PLATFORM_ENV="${PLATFORM_ENV:-$INFRA_DIR/.env}"
ASSISTANT_URL="${ASSISTANT_URL:-http://127.0.0.1:18082}"
HUB_URL="${HUB_URL:-http://127.0.0.1:18081}"
GATEWAY_URL="${GATEWAY_URL:-http://127.0.0.1:4100}"
TASK_URL="${TASK_URL:-http://task.local.nodedc/}"
ENGINE_URL="${ENGINE_URL:-http://127.0.0.1:5300/}"
read_env() {
file="$1"
key="$2"
if [ ! -f "$file" ]; then
return 0
fi
awk -F= -v key="$key" '
$0 ~ "^[[:space:]]*#" { next }
$1 == key {
value = substr($0, index($0, "=") + 1)
gsub(/^[[:space:]]+|[[:space:]]+$/, "", value)
gsub(/^"|"$/, "", value)
print value
exit
}
' "$file"
}
http_status() {
url="$1"
curl -k -sS -o /dev/null -w "%{http_code}" --max-time 3 "$url" 2>/dev/null || true
}
http_body() {
url="$1"
curl -k -sS --max-time 3 "$url" 2>/dev/null || true
}
ok_status() {
code="$1"
case "$code" in
2*|3*) printf true ;;
*) printf false ;;
esac
}
json_number() {
key="$1"
sed -n "s/.*\"$key\"[[:space:]]*:[[:space:]]*\\([0-9][0-9]*\\).*/\\1/p" | head -n 1
}
url_kind() {
value="$1"
case "$value" in
"")
printf missing
;;
*127.0.0.1*|*localhost*|*host.docker.internal*|*".local.nodedc"*|*ai-workspace-hub*|*agent-gateway*)
printf local
;;
*100.[6-9][0-9].*|*100.1[01][0-9].*|*100.12[0-7].*|*.ts.net*)
printf tailscale
;;
*172.22.0.222*|*".nas.nodedc"*)
printf synology-lan
;;
*ai-hub.nodedc.ru*|*ops-agents.nodedc.ru*|*hub.nodedc.ru*|*ops.nodedc.ru*)
printf prod-public
;;
http://172.*|http://192.168.*|http://10.*)
printf lan
;;
*)
printf custom
;;
esac
}
bool_and() {
left="$1"
right="$2"
if [ "$left" = true ] && [ "$right" = true ]; then
printf true
else
printf false
fi
}
assistant_code=$(http_status "$ASSISTANT_URL/healthz")
gateway_code=$(http_status "$GATEWAY_URL/readyz")
task_code=$(http_status "$TASK_URL")
engine_code=$(http_status "$ENGINE_URL")
assistant_ok=$(ok_status "$assistant_code")
gateway_ok=$(ok_status "$gateway_code")
task_ok=$(ok_status "$task_code")
engine_ok=$(ok_status "$engine_code")
profile=$(read_env "$PLATFORM_ENV" NODEDC_ENV || true)
case "$profile" in
"") profile=local ;;
esac
hub_public=$(read_env "$PLATFORM_ENV" AI_WORKSPACE_HUB_PUBLIC_URL || true)
hub_internal=$(read_env "$PLATFORM_ENV" AI_WORKSPACE_HUB_INTERNAL_URL || true)
ops_entitlement=$(read_env "$PLATFORM_ENV" AI_WORKSPACE_OPS_ENTITLEMENT_URL || true)
action_relay_enabled=$(read_env "$PLATFORM_ENV" AI_WORKSPACE_ASSISTANT_ACTION_RELAY_ENABLED || true)
action_relay_id=$(read_env "$PLATFORM_ENV" AI_WORKSPACE_ASSISTANT_ACTION_RELAY_ID || true)
case "$action_relay_enabled" in
1|true|TRUE|yes|YES|on|ON) action_relay_enabled=true ;;
*) action_relay_enabled=false ;;
esac
hub_public_kind=$(url_kind "$hub_public")
hub_internal_kind=$(url_kind "$hub_internal")
ops_entitlement_kind=$(url_kind "$ops_entitlement")
local_hub_body=$(http_body "$HUB_URL/healthz")
local_hub_code=000
if [ -n "$local_hub_body" ]; then
local_hub_code=$(http_status "$HUB_URL/healthz")
fi
local_hub_ok=$(ok_status "$local_hub_code")
relay_health_code=000
relay_health_ok=false
if [ -n "$hub_internal" ]; then
relay_health_code=$(http_status "$(printf "%s" "$hub_internal" | sed 's#/*$##')/healthz")
relay_health_ok=$(ok_status "$relay_health_code")
fi
agents_online=$(printf "%s" "$local_hub_body" | json_number agentsOnline)
case "$agents_online" in
""|*[!0-9]*) agents_online=0 ;;
esac
local_services_ok=$(bool_and "$assistant_ok" "$(bool_and "$gateway_ok" "$task_ok")")
worker_on_local_hub=false
if [ "$agents_online" -gt 0 ]; then
worker_on_local_hub=true
fi
action_relay_configured=false
if [ "$action_relay_enabled" = true ] && [ -n "$action_relay_id" ]; then
action_relay_configured=true
fi
hub_runtime_kind=custom
case "$hub_public_kind:$hub_internal_kind" in
local:local|local:missing|missing:local) hub_runtime_kind=local ;;
tailscale:local|tailscale:tailscale|tailscale:missing) hub_runtime_kind=tailscale ;;
prod-public:prod-public|prod-public:missing|missing:prod-public) hub_runtime_kind=prod-public ;;
*) hub_runtime_kind=mixed ;;
esac
classification=contract-only
if [ "$local_services_ok" = true ]; then
if [ "$engine_ok" = true ] \
&& [ "$action_relay_configured" = true ] \
&& [ "$hub_runtime_kind" = prod-public ]; then
classification=local-remote-worker-relay
elif [ "$engine_ok" = true ] \
&& [ "$worker_on_local_hub" = true ] \
&& [ "$ops_entitlement_kind" = local ] \
&& [ "$hub_runtime_kind" = local ]; then
classification=true-local-e2e
elif [ "$engine_ok" = true ] \
&& [ "$worker_on_local_hub" = true ] \
&& { [ "$ops_entitlement_kind" = tailscale ] || [ "$hub_runtime_kind" = tailscale ]; }; then
classification=tunnel-local-e2e
elif [ "$hub_runtime_kind" = prod-public ] || [ "$worker_on_local_hub" = false ]; then
classification=hybrid-prod-bridge
else
classification=local-ops-vertical
fi
elif [ "$gateway_ok" = true ] && [ "$task_ok" = true ]; then
classification=local-ops-vertical
elif [ "$task_ok" = true ] || [ "$engine_ok" = true ]; then
classification=local-ui-only
fi
cat <<EOF
classification=$classification
profile=$profile
platform_env=$PLATFORM_ENV
assistant_health=$assistant_ok status=$assistant_code url=$ASSISTANT_URL/healthz
local_hub_health=$local_hub_ok status=$local_hub_code url=$HUB_URL/healthz agents_online=$agents_online
relay_health=$relay_health_ok status=$relay_health_code url=${hub_internal%/}/healthz
gateway_health=$gateway_ok status=$gateway_code url=$GATEWAY_URL/readyz
task_health=$task_ok status=$task_code url=$TASK_URL
engine_health=$engine_ok status=$engine_code url=$ENGINE_URL
hub_public_kind=$hub_public_kind
hub_internal_kind=$hub_internal_kind
hub_runtime_kind=$hub_runtime_kind
ops_entitlement_kind=$ops_entitlement_kind
assistant_action_relay_enabled=${action_relay_enabled:-missing}
assistant_action_relay_id=${action_relay_id:-missing}
assistant_action_relay_configured=$action_relay_configured
EOF
case "$classification" in
true-local-e2e|tunnel-local-e2e)
echo "meaning=local write-path e2e can be interpreted if the worker can reach returned MCP URLs"
;;
local-remote-worker-relay)
echo "meaning=local apps are the downstream target; deployed AI Hub is used only as remote worker relay and assistant actions route back to local Assistant"
;;
hybrid-prod-bridge)
echo "meaning=do not treat UI dialog as local write-path proof; topology is mixed or assistant action relay is not configured"
;;
local-ops-vertical)
echo "meaning=Gateway and Tasker local vertical checks are valid, but no live Codex worker e2e is proven"
;;
local-ui-only)
echo "meaning=local UI/proxy is reachable, but AI Workspace write path is not proven"
;;
*)
echo "meaning=contract tests only; no runtime topology is proven"
;;
esac
if [ "${REQUIRE_TRUE_E2E:-0}" = "1" ]; then
case "$classification" in
true-local-e2e|tunnel-local-e2e) exit 0 ;;
*) exit 2 ;;
esac
fi
if [ "${REQUIRE_LOCAL_REMOTE_WORKER_RELAY:-0}" = "1" ]; then
case "$classification" in
local-remote-worker-relay) exit 0 ;;
*) exit 2 ;;
esac
fi