Files
admin 588fed2aa9 slice 10B: operator-signed destructive completion (offline key + signing CLI) (v0.16.0)
A destructive op runs ONLY on a pinned-key-verified, nonce-fresh, in-window,
host-bound, durable-id-bound operator signature. New cmd/felhom-opsign signs
canonical OpBlobs offline via ssh-keygen -Y sign (hardware-ready); the signing
key is never in the hub or agent. New internal/signedjobs runner verifies each
queued blob through the gate and only on all-pass runs the WipeExecutor, which
re-resolves the DURABLE device id + re-inspects (8C) before mkfs — closing the
8C data-bearing-wipe pending_signature gap. New storage durable-device
resolution; authz.CanonicalBlob promoted to production. Real-crypto tests assert
valid executes and forged/replay/expired/retarget/non-pinned are rejected
(executor never called).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-10 20:14:16 +02:00

112 lines
4.7 KiB
Go

package signedjobs
import (
"context"
"encoding/json"
"fmt"
"log/slog"
"gitea.dooplex.hu/admin/felhom-agent/internal/storage"
)
// opStorageWipe is the op class this executor serves (mirrors reconcile.ClassStorageWipe; the
// literal avoids importing reconcile here just for the string).
const opStorageWipe = "storage_wipe"
// WipeOps is the privileged storage surface the wipe executor needs (a subset of storage.HostOps).
type WipeOps interface {
InspectDevice(ctx context.Context, device string) (storage.DeviceProbe, error)
Format(ctx context.Context, device, fstype string) error
}
// wipeParams is the verified params of a storage_wipe op. The device is named by a DURABLE id
// (never a mutable /dev path), so execution re-resolves it to the exact physical device.
type wipeParams struct {
DurableID string `json:"durable_id"`
FSType string `json:"fstype"`
}
// WipeExecutor is the slice-10B storage-wipe consumer — it CLOSES the 8C data-bearing-format
// `pending_signature` gap. Given a gate-VERIFIED+bound storage_wipe op, it:
// 1. resolves the op's DURABLE device id → the current /dev path (vanished/replaced → refuse);
// 2. re-derives that device's durable id and requires it to MATCH the signed id (resource-level
// anti-retarget — "wipe device X" wipes exactly X, not whatever is at /dev/sdb now);
// 3. re-inspects (8C classifier) to confirm it is STILL the data-bearing target;
// 4. mkfs.
//
// A path-only binding, a device that vanished/changed, or a target that is no longer data-bearing
// is refused EVEN WITH a valid signature. The gate has already burned the nonce durably before we
// run, so an interrupted wipe can't be re-authorized by replaying the blob.
type WipeExecutor struct {
ops WipeOps
resolve func(durableID string) (string, error)
derive func(device string) (string, error)
logger *slog.Logger
}
// NewWipeExecutor wires the production durable resolver/deriver (storage package).
func NewWipeExecutor(ops WipeOps, logger *slog.Logger) *WipeExecutor {
if logger == nil {
logger = slog.Default()
}
return &WipeExecutor{
ops: ops,
resolve: storage.ResolveDurableDevice,
derive: storage.DeviceDurableID,
logger: logger,
}
}
// Execute implements signedjobs.Executor for the storage_wipe op class.
func (w *WipeExecutor) Execute(ctx context.Context, op string, params json.RawMessage) error {
if op != opStorageWipe {
return ErrNoExecutor // not ours — the runner leaves it queued for the owning slice
}
var p wipeParams
if err := json.Unmarshal(params, &p); err != nil {
return fmt.Errorf("wipe: bad params: %w", err)
}
if p.DurableID == "" {
// The whole point of the durable binding: a path-only op is refused (anti-retarget).
return fmt.Errorf("wipe: op has no durable_id — refusing a path-only wipe binding")
}
// 1. Resolve the durable id → current device (gone/replaced → refuse).
device, err := w.resolve(p.DurableID)
if err != nil {
return fmt.Errorf("wipe: durable id %q no longer resolves (device removed/replaced?) — refusing: %w", p.DurableID, err)
}
// 2. Anti-retarget: re-derive the resolved device's durable id; it MUST equal the signed id.
got, err := w.derive(device)
if err != nil {
return fmt.Errorf("wipe: cannot re-derive durable id for %s — refusing: %w", device, err)
}
if got != p.DurableID {
return fmt.Errorf("wipe: durable-id mismatch — %s now has id %q, signed id was %q — refusing", device, got, p.DurableID)
}
// 3. Re-inspect (8C classifier) — confirm the resolved device is STILL the data-bearing target.
probe, err := w.ops.InspectDevice(ctx, device)
if err != nil {
return fmt.Errorf("wipe: re-inspect %s failed — refusing: %w", device, err)
}
if !probe.Probed {
return fmt.Errorf("wipe: %s did not probe cleanly at execution — refusing", device)
}
if !probe.DataBearing() {
// The signed op authorized wiping a DATA-BEARING device; if it is now blank, the target
// changed since signing — refuse rather than wipe the wrong (or an unexpected) device.
return fmt.Errorf("wipe: %s is no longer data-bearing (target changed since signing) — refusing", device)
}
// 4. Execute. The nonce was durably burned by the gate's Verify BEFORE this point (crash-safety:
// a replay after an interrupted wipe is rejected). This log line is the audit trail of a
// destructive, operator-authorized wipe actually running.
w.logger.Warn("wipe: executing operator-signed data-bearing wipe",
"device", device, "durable_id", p.DurableID, "fstype", p.FSType, "data_reason", probe.Reason())
if err := w.ops.Format(ctx, device, p.FSType); err != nil {
return fmt.Errorf("wipe: mkfs %s %s: %w", p.FSType, device, err)
}
w.logger.Warn("wipe: operator-signed wipe complete", "device", device, "durable_id", p.DurableID)
return nil
}