feat(daemon): Phase E — production hardening, complete

Exposure: --grpc default flipped from 0.0.0.0 to 127.0.0.1 (the API is
unauthenticated by design; auth belongs to the transport), Unix-domain-
socket support (--grpc unix:///run/secs_gemd/api.sock = zero network
surface), SECURITY.md documents the contract and ch42 gained a "Running it
in production" section (which also documents the HSMS-SS single-session
assumption).

Graceful shutdown: SIGTERM/SIGINT land on an asio::signal_set on the io
thread, which nudges grpc Shutdown with a 2s deadline (cancels open
Subscribe/WatchHealth streams); Wait() returns on the MAIN thread, which
stops the engine (rt->stop() joins the io thread, so it must not run on
it). Exit 0, journal-safe, the in-code TODO is gone. --spool-dir added so
host-bound events survive daemon restarts.

Observability: --metrics serves Prometheus gauges secsgem_link_selected /
secsgem_control_state / secsgem_spool_depth, wired via the Phase-0
add_link_observer/add_control_state_observer hooks + io-thread sampling.

Deployment: deploy/secs_gemd.service — hardened systemd unit (DynamicUser,
ProtectSystem=strict, StateDirectory for the spool, UDS for the API,
TimeoutStopSec aligned with the graceful-shutdown window).

Enforcement: tools/check_daemon_ops.sh proves all three operational claims
(unix-socket gRPC accepts, all gauges present on /metrics, SIGTERM -> exit
0 + clean-stop log) — green; wired into tools/run_interop.sh (now 11
steps) and CI. CI python-interop lane also gained the pyclient and
spool-restart steps, so every harness now runs in CI.

TODO sweep: the shutdown TODO is fixed; the four remaining TODOs (nested
list formats, C2-as-text, U8>2^63, CONNECTED link state) are deliberate
deferred edge cases, each marked in code with context.

Daemon suite re-verified green (175 assertions).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

apps/secs_gemd.cpp

@@ -1,17 +1,30 @@
 // secs_gemd — the SECS/GEM daemon.
 //
 // Runs the GEM engine (EquipmentRuntime + the default handlers) on a background
-// thread, owning the HSMS link to the host, and exposes a small name-based gRPC
+// thread, owning the HSMS link to the host, and exposes the name-based gRPC
 // API (proto/secsgem/v1/equipment.proto) so a tool's software — in any language
 // — can drive the equipment without linking C++ or knowing SEMI.
 //
-// Increment 1: the universal "report state to the host" RPCs (SetVariables,
-// FireEvent) plus control-state visibility. Alarms, GetVariables, and the
-// host->tool Subscribe command stream follow (see docs/DAEMON_ROADMAP.md).
+// Operations (Phase E):
+//   --grpc      defaults to 127.0.0.1:50051 — NEVER expose the unauthenticated
+//               API on the equipment LAN. For same-host tool software prefer a
+//               Unix domain socket: --grpc unix:///run/secs_gemd.sock
+//   --metrics   Prometheus endpoint port (0 = disabled). Gauges: HSMS link
+//               state, control state, spool depth.
+//   SIGTERM/SIGINT: graceful shutdown — gRPC server drains (open streams are
+//               cancelled), then the engine stops cleanly, so a supervised
+//               restart (systemd / docker stop) never kills the spool journal
+//               mid-write. Exit code 0.
+//
+// Deployment recipe: deploy/secs_gemd.service (systemd) and docs/42.
 
 #include <grpcpp/grpcpp.h>
 
+#include <asio.hpp>
+#include <chrono>
+#include <csignal>
 #include <cstdint>
+#include <functional>
 #include <iostream>
 #include <memory>
 #include <string>
@@ -19,8 +32,11 @@
 #include "secsgem/daemon/equipment_service.hpp"
 #include "secsgem/gem/default_handlers.hpp"
 #include "secsgem/gem/runtime.hpp"
+#include "secsgem/metrics/prometheus.hpp"
 
 namespace gem = secsgem::gem;
+namespace metrics = secsgem::metrics;
+using namespace std::chrono_literals;
 
 namespace {
 std::string arg(int argc, char** argv, const std::string& key, const std::string& def) {
@@ -31,9 +47,12 @@ std::string arg(int argc, char** argv, const std::string& key, const std::string
 }  // namespace
 
 int main(int argc, char** argv) {
-  const std::string hsms_port = arg(argc, argv, "--port", "5000");
-  const std::string grpc_addr = arg(argc, argv, "--grpc", "0.0.0.0:50051");
-  const std::string cfgdir    = arg(argc, argv, "--config-dir", "data");
+  const std::string hsms_port    = arg(argc, argv, "--port", "5000");
+  const std::string grpc_addr    = arg(argc, argv, "--grpc", "127.0.0.1:50051");
+  const std::string cfgdir       = arg(argc, argv, "--config-dir", "data");
+  const std::string spool_dir    = arg(argc, argv, "--spool-dir", "");
+  const uint16_t metrics_port    =
+      static_cast<uint16_t>(std::stoi(arg(argc, argv, "--metrics", "0")));
 
   gem::EquipmentRuntime::Config cfg;
   cfg.equipment_yaml     = cfgdir + "/equipment.yaml";
@@ -41,6 +60,7 @@ int main(int argc, char** argv) {
   cfg.process_job_yaml   = cfgdir + "/process_job_state.yaml";
   cfg.control_job_yaml   = cfgdir + "/control_job_state.yaml";
   cfg.port = static_cast<uint16_t>(std::stoi(hsms_port));
+  cfg.spool_dir = spool_dir;
   cfg.log = [](const std::string& m) { std::cout << "[gemd] " << m << std::endl; };
 
   std::unique_ptr<gem::EquipmentRuntime> rt;
@@ -52,9 +72,50 @@ int main(int argc, char** argv) {
   }
   gem::register_default_handlers(*rt);
 
+  // ---- observability (before run_async: observers must land first) -------
+  std::shared_ptr<metrics::Registry> registry;
+  std::shared_ptr<metrics::PrometheusServer> exporter;
+  std::shared_ptr<asio::steady_timer> gauge_timer;
+  if (metrics_port != 0) {
+    registry = std::make_shared<metrics::Registry>();
+    registry->describe("secsgem_link_selected",
+                       "1 when an HSMS session is SELECTED, else 0",
+                       metrics::MetricType::Gauge);
+    registry->describe("secsgem_control_state",
+                       "E30 control state (0=EquipOffline 1=AttemptOnline "
+                       "2=HostOffline 3=OnlineLocal 4=OnlineRemote)",
+                       metrics::MetricType::Gauge);
+    registry->describe("secsgem_spool_depth", "Queued spool messages",
+                       metrics::MetricType::Gauge);
+    rt->add_link_observer([registry](bool selected) {
+      registry->set_gauge("secsgem_link_selected", selected ? 1.0 : 0.0);
+    });
+    rt->add_control_state_observer(
+        [registry](gem::ControlState, gem::ControlState to, gem::ControlEvent) {
+          registry->set_gauge("secsgem_control_state", static_cast<double>(to));
+        });
+    registry->set_gauge("secsgem_link_selected", 0.0);
+    registry->set_gauge("secsgem_control_state",
+                        static_cast<double>(rt->control_state()));
+    // Spool depth: sampled on the io thread (the model's owner).
+    gauge_timer = std::make_shared<asio::steady_timer>(rt->io());
+    auto tick = std::make_shared<std::function<void(std::error_code)>>();
+    *tick = [registry, gauge_timer, tick, raw = rt.get()](std::error_code ec) {
+      if (ec) return;
+      registry->set_gauge("secsgem_spool_depth",
+                          static_cast<double>(raw->model().spool.size()));
+      gauge_timer->expires_after(5s);
+      gauge_timer->async_wait(*tick);
+    };
+    gauge_timer->expires_after(1s);
+    gauge_timer->async_wait(*tick);
+    exporter = std::make_shared<metrics::PrometheusServer>(
+        rt->io(), metrics_port, registry);
+    exporter->start();
+  }
+
   // Construct the service before starting the io thread: its constructor
-  // snapshots the name->id/format maps from the model (see the service's
-  // threading note).
+  // snapshots the name->id/format maps and registers its observers.
   secsgem::daemon::EquipmentService service(*rt);
   rt->run_async();  // engine + HSMS link on a background thread
 
@@ -66,12 +127,26 @@ int main(int argc, char** argv) {
     std::cerr << "[gemd] failed to start gRPC server on " << grpc_addr << std::endl;
     return 1;
   }
+
+  // Graceful shutdown: the signal lands on the io thread, which only nudges
+  // the gRPC server; Wait() then returns on the MAIN thread, which tears the
+  // engine down (rt->stop() joins the io thread — it must not run on it).
+  // The deadline cancels open Subscribe/WatchHealth streams instead of
+  // waiting for clients to hang up.
+  asio::signal_set signals(rt->io(), SIGINT, SIGTERM);
+  signals.async_wait([&server, &rt](std::error_code ec, int signo) {
+    if (ec) return;
+    rt->log("signal " + std::to_string(signo) + ": shutting down");
+    server->Shutdown(std::chrono::system_clock::now() + 2s);
+  });
+
   std::cout << "[gemd] gRPC on " << grpc_addr
+            << (metrics_port ? "; metrics on :" + std::to_string(metrics_port) +
+                                   "/metrics"
+                             : "")
             << "; HSMS equipment on :" << hsms_port << std::endl;
-  // TODO(daemon): graceful shutdown — handle SIGTERM/SIGINT by calling
-  // server->Shutdown() and rt->stop() so in-flight RPCs drain and the spool
-  // journal flushes, instead of dying mid-write when supervised (systemd/
-  // docker stop). See DAEMON_ROADMAP Phase E.
   server->Wait();
+  rt->stop();
+  std::cout << "[gemd] stopped cleanly" << std::endl;
   return 0;
 }