Operator actions in the report reply (D1, R-314/R-279/R-177, decision 185)

The hub may ask the running controller for a CLOSED list of actions,
carried in the report ACK (operator_actions) and answered on the next
report (operator_action_results): offsite_backup_now, abandon_stop,
abandon_extend (1-30 days), run_job (fill-watch, offsite-integrity,
offsite-proof, disk-health-check). Unknown action/job/argument -> refused,
nothing called. Once per id (in memory; every action is safe to repeat).

- internal/report/opactions.go: the executor; results re-sent until the
  hub stops listing the id.
- scheduler.RunNow: refuses unknown / already-running jobs; OnDemand(ctx)
  makes an operator's offsite-integrity run even when not due.
- ExtendAbandon never shortens the countdown and refuses in the hub phase;
  StopAbandon reports failure when the hub cancel failed (it said success).
- Report ACK read cap 4 KiB -> 64 KiB (an ACK over the cap dropped every
  field in it).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

controller/cmd/controller/main.go

@@ -1077,6 +1077,15 @@ func main() {
 			RecordEscrowKeyHash: sett.SetHubEscrowKeySHA256,
 			Logger:              logger,
 		}
+		// R-314/R-279/R-177 (`09` §3 decision 185): the operator's closed list of actions, carried in the
+		// report reply and run in THIS process (opactions_wiring.go). The result rides the next report;
+		// a finished result fires an out-of-cycle report through the trigger once it exists.
+		opActions := report.NewOperatorActions(ctx, operatorActionHandlers(backupMgr, sched, func() {
+			if f, ok := opActionReportFire.Load().(func()); ok && f != nil {
+				f()
+			}
+		}, logger), logger)
+		report.SetOperatorActions(opActions)
 		// Wire hub verification: update settings when hub reports customer status
 		hubPusher.OnPushResponse = func(resp *report.PushResponse) {
 			if resp.CustomerBlocked {
@@ -1120,6 +1129,8 @@ func main() {
 			// generation). The web gate reads it on the next request — no restart needed.
 			claimSync := &report.ClaimSync{Settings: sett, Logger: logger}
 			claimSync.Reconcile(resp.Claim)
+			// Decision 185: the operator's pending actions (each acted on once per id).
+			opActions.Reconcile(resp.OperatorActions)
 		}
 		// Wire hub push status into alert manager for dashboard alerts
 		alertMgr.SetHubPushStatus(func() web.HubPushStatusData {
@@ -1496,7 +1507,9 @@ func main() {
 		// collision costs one skipped day, not a missed check, because due-ness makes tomorrow try
 		// again. What would be a real defect is a slot that collides EVERY night; this is not one.
 		sched.Daily("offsite-integrity", "06:00", func(ctx context.Context) error {
-			runOffsiteIntegrityCheck(ctx, backupMgr, notifier, logger, false)
+			// Decision 185: an operator's run_job runs the check even when it is not due — the operator
+			// asked for a check, not for „is a check due". The schedule still checks due-ness.
+			runOffsiteIntegrityCheck(ctx, backupMgr, notifier, logger, scheduler.OnDemand(ctx))
 			return nil
 		})
 
@@ -1811,6 +1824,7 @@ func main() {
 		}
 		reportTrigger = report.NewTrigger(fireReport, logger)
 		go reportTrigger.Run(ctx)
+		opActionReportFire.Store(reportTrigger.Fire)
 
 		// Direction-2 immediate-sync (v0.140.0): hold a hanging GET against the hub's wait channel
 		// and fire the trigger the instant operator intent moves — so an operator save round-trips in

controller/cmd/controller/opactions_wiring.go

@@ -0,0 +1,60 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"log"
+	"sync/atomic"
+	"time"
+
+	"gitea.dooplex.hu/admin/felhom-controller/internal/backup"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/report"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/scheduler"
+)
+
+// opActionReportFire holds the out-of-cycle report trigger once main has built it (func()). The
+// executor is built earlier than the trigger, so it reads it through this holder.
+var opActionReportFire atomic.Value
+
+// operatorActionHandlers wires the four operator actions (R-314/R-279/R-177, `09` §3 decision 185)
+// to the running process. ONE wiring site, called from main and from the wiring test, so the test
+// exercises the doors production uses (the seam-built-but-never-wired trap).
+//
+// offsite_backup_now makes the SAME four checks as the household's „back up now"
+// (offboxRunHandler) and then runs the same call, so an operator press can never do what the
+// household's own press cannot.
+func operatorActionHandlers(backupMgr *backup.Manager, sched *scheduler.Scheduler, resultReady func(), logger *log.Logger) report.OperatorActionHandlers {
+	h := report.OperatorActionHandlers{ResultReady: resultReady}
+	if sched != nil {
+		h.RunJob = sched.RunNow
+	}
+	if backupMgr == nil {
+		return h
+	}
+	h.OffsiteBackupNow = func() (string, func(ctx context.Context) error) {
+		switch {
+		case !backupMgr.OffboxConfigured():
+			return "no off-site target is set on this box", nil
+		case !backupMgr.OffboxRunnable():
+			return "the off-site key step (escrow) is not done yet — the run is refused until it is", nil
+		case backupMgr.OffboxOrphaned():
+			return "the off-site store is orphaned (written with an older key) — a run cannot write to it", nil
+		case backupMgr.IsRunning():
+			return "a backup run is already in flight", nil
+		}
+		return "", func(ctx context.Context) error {
+			if logger != nil {
+				logger.Printf("[INFO] [opaction] off-site backup started at the operator's request")
+			}
+			err := backupMgr.RunOffboxBackupWithProgress(ctx)
+			if errors.Is(err, backup.ErrOffboxRunInFlight) {
+				return fmt.Errorf("%w: %v", report.ErrActionRefused, err)
+			}
+			return err
+		}
+	}
+	h.AbandonStop = backupMgr.StopAbandon
+	h.AbandonExtend = func(days int) (time.Time, error) { return backupMgr.ExtendAbandon(days) }
+	return h
+}

controller/cmd/controller/opactions_wiring_test.go

@@ -0,0 +1,169 @@
+package main
+
+import (
+	"context"
+	"go/ast"
+	"go/parser"
+	"go/token"
+	"io"
+	"log"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"gitea.dooplex.hu/admin/felhom-controller/internal/backup"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/config"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/report"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/scheduler"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/settings"
+)
+
+// `09` §3 decision 185 (D1), the design's red test (1): a reply carrying abandon_stop during a
+// countdown stops it IN THE RUNNING MANAGER — and settings.json on disk agrees. This is the reason
+// the action rides the report reply instead of the CLI lever: the CLI runs a SECOND process, whose
+// write the running controller can overwrite (the lost update, main.go's R-241 block).
+func TestD1_AbandonStopActsOnTheRunningManagerAndDisk(t *testing.T) {
+	logger := log.New(io.Discard, "", 0)
+	dir := t.TempDir()
+	settingsPath := filepath.Join(dir, "settings.json")
+	sett, err := settings.Load(settingsPath, logger)
+	if err != nil {
+		t.Fatal(err)
+	}
+	cfg := &config.Config{}
+	cfg.Paths.DataDir = dir
+	cfg.Paths.SystemDataPath = filepath.Join(dir, "sys")
+	mgr := backup.NewManager(cfg, sett, logger)
+	// No test reaches a real ssh or restic (R-488 / R-650).
+	mgr.SetOffboxSSH(func(context.Context, string, string, int, string, string, string) ([]byte, error) {
+		t.Fatal("abandon_stop must issue no remote command")
+		return nil, nil
+	})
+	mgr.SetOffboxRunner(func(context.Context, []string, ...string) ([]byte, error) {
+		t.Fatal("abandon_stop must run no restic")
+		return nil, nil
+	})
+	due := time.Now().Add(10 * 24 * time.Hour).UTC()
+	if err := sett.SetOffboxTarget(&settings.OffboxTarget{
+		Enabled: true, Host: "nas.local", Port: 22, User: "felhom", RepoPath: "/srv/repo", Schedule: "daily",
+		EscrowState:      "escrowed",
+		AbandonRepoPath:  "/srv/repo.orphaned-20261001",
+		AbandonStartedAt: time.Now().Add(-4 * 24 * time.Hour).UTC().Format(time.RFC3339),
+		AbandonAt:        due.Format(time.RFC3339),
+	}); err != nil {
+		t.Fatal(err)
+	}
+	if !mgr.AbandonStatus().Active {
+		t.Fatal("fixture: a countdown must be running")
+	}
+
+	o := report.NewOperatorActions(context.Background(), operatorActionHandlers(mgr, nil, nil, logger), logger)
+	o.Reconcile([]report.OperatorAction{{ID: 1, Action: report.OpAbandonStop}})
+
+	if mgr.AbandonStatus().Active {
+		t.Fatal("the running manager still counts down after abandon_stop")
+	}
+	onDisk, err := settings.Load(settingsPath, logger)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if tg := onDisk.GetOffboxTarget(); tg == nil || tg.AbandonAt != "" || tg.AbandonRepoPath == "" {
+		t.Fatalf("settings.json disagrees: %+v (want no due date, the set-aside path kept)", tg)
+	}
+	rs := o.Results()
+	if len(rs) != 1 || rs[0].Outcome != report.OutcomeDone {
+		t.Fatalf("result = %+v", rs)
+	}
+
+	// Control: the same countdown, a second press → nothing to stop, reported as such (not „done").
+	o.Reconcile([]report.OperatorAction{{ID: 2, Action: report.OpAbandonStop}})
+	if r := o.Results(); len(r) != 1 || r[0].ID != 2 || r[0].Outcome != report.OutcomeFailed {
+		t.Fatalf("second stop: %+v", r)
+	}
+}
+
+// offsite_backup_now refuses exactly where the household's „back up now" refuses: no target here.
+func TestD1_OffsiteBackupNowRefusesWithoutATarget(t *testing.T) {
+	logger := log.New(io.Discard, "", 0)
+	dir := t.TempDir()
+	sett, err := settings.Load(filepath.Join(dir, "settings.json"), logger)
+	if err != nil {
+		t.Fatal(err)
+	}
+	cfg := &config.Config{}
+	cfg.Paths.DataDir = dir
+	mgr := backup.NewManager(cfg, sett, logger)
+	mgr.SetOffboxRunner(func(context.Context, []string, ...string) ([]byte, error) {
+		t.Fatal("no restic may run")
+		return nil, nil
+	})
+	o := report.NewOperatorActions(context.Background(), operatorActionHandlers(mgr, nil, nil, logger), logger)
+	o.Reconcile([]report.OperatorAction{{ID: 9, Action: report.OpOffsiteBackupNow}})
+	if r := o.Results(); len(r) != 1 || r[0].Outcome != report.OutcomeRefused {
+		t.Fatalf("result = %+v", r)
+	}
+}
+
+// run_job reaches the scheduler's RunNow: a registered job runs; a job not registered on this box is
+// refused.
+func TestD1_RunJobUsesTheScheduler(t *testing.T) {
+	logger := log.New(io.Discard, "", 0)
+	sched := scheduler.New(logger)
+	ran := make(chan bool, 1)
+	sched.Daily("fill-watch", "03:30", func(ctx context.Context) error { ran <- scheduler.OnDemand(ctx); return nil })
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	sched.Start(ctx)
+	defer sched.Stop()
+	o := report.NewOperatorActions(ctx, operatorActionHandlers(nil, sched, nil, logger), logger)
+	o.Reconcile([]report.OperatorAction{{ID: 1, Action: report.OpRunJob, Arg: "fill-watch"}, {ID: 2, Action: report.OpRunJob, Arg: "offsite-proof"}})
+	select {
+	case od := <-ran:
+		if !od {
+			t.Fatal("the job did not see itself as on-demand")
+		}
+	case <-time.After(5 * time.Second):
+		t.Fatal("fill-watch never ran")
+	}
+	deadline := time.Now().Add(5 * time.Second)
+	for len(o.Results()) < 2 && time.Now().Before(deadline) {
+		time.Sleep(10 * time.Millisecond)
+	}
+	got := map[int64]string{}
+	for _, r := range o.Results() {
+		got[r.ID] = r.Outcome
+	}
+	if got[1] != report.OutcomeDone || got[2] != report.OutcomeRefused {
+		t.Fatalf("outcomes = %v, want 1:done 2:refused (offsite-proof not registered here)", got)
+	}
+}
+
+// main.go hands the reply's list to the executor and the trigger to its holder — one call each
+// (the seam-built-but-never-wired trap: a green executor that main never calls proves nothing).
+func TestD1_MainWiresTheExecutor(t *testing.T) {
+	f, err := parser.ParseFile(token.NewFileSet(), "main.go", nil, 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+	found := map[string]int{}
+	ast.Inspect(f, func(n ast.Node) bool {
+		call, ok := n.(*ast.CallExpr)
+		if !ok {
+			return true
+		}
+		switch fn := call.Fun.(type) {
+		case *ast.SelectorExpr:
+			if x, ok := fn.X.(*ast.Ident); ok {
+				found[x.Name+"."+fn.Sel.Name]++
+			}
+		case *ast.Ident:
+			found[fn.Name]++
+		}
+		return true
+	})
+	for _, want := range []string{"opActions.Reconcile", "report.SetOperatorActions", "operatorActionHandlers", "opActionReportFire.Store"} {
+		if found[want] != 1 {
+			t.Errorf("main.go calls %s %d time(s), want exactly 1", want, found[want])
+		}
+	}
+}