Files
felhom.eu/hub/internal/store/customer_reset.go
T
admin 9b3381be0a feat(hub): v0.70.0 — a deleted customer actually disappears (residue leg + ghost cleanup)
Found validating v0.69.0 against the live hub. demo-vm-felhom was deleted
on 07-18 and was still on the Customers list AND still raising offsite_stale
(10 events, latest 07-21 17:34, operator email at 19:34) — because
GetCustomers() is report-derived and no lifecycle tier ever deleted a report.

New leg 3 (residue), before the record purge: reports, app_telemetry,
app_log_tails, log_tail_requests, customer_notifications, plus the
credential-bearing appliance_registrations and selfbind_tokens. Audit
(events, notification_log) and F-14 provenance still survive.

Ghost customers are now deletable: 404 means "nothing here", not "no config
row". With no config row the offsite descriptor is unknowable, so the Hetzner
and descriptor legs record skipped_no_config rather than a bare "skipped".

Two more red-proofs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J55BQE1gE2V4ffud5jweGS
2026-07-21 20:28:06 +02:00

182 lines
6.6 KiB
Go

package store
import (
"database/sql"
"encoding/json"
"fmt"
"time"
)
// Customer RESET (v0.61.0) — the middle lifecycle tier (host delete < RESET < customer delete). The
// journal is F-14-style provenance: one row per attempt, per-leg status, resumable. External teardown
// runs FIRST and the DB-purge runs LAST (publish-last) so a re-run reads the journal to know what still
// needs tearing down. Provenance/events are NEVER wiped — audit outlives every tier.
// CustomerReset is one reset provenance/journal record.
type CustomerReset struct {
ID int64
CustomerID string
StartedAt time.Time
CompletedAt *time.Time
EscrowAcked bool
Legs map[string]string // hetzner | pbs | db_purge → pending|ok|failed|manual
}
// ResetInventory is the live count of what a RESET would destroy (the confirm surface, ruling 4).
// Sub-account name + PBS namespace are added by the web layer from the external clients.
type ResetInventory struct {
HostCount int // ruling 3: RESET refuses while any host row exists
SupersededBlobs int // M — retained recovery-key custody destroyed (ack-gated)
DRRecipePresent bool
OneTimeSecretPresent bool
ClaimPresent bool
}
// CustomerResetInventory builds the hub-DB side of the confirm inventory.
func (s *Store) CustomerResetInventory(customerID string) (*ResetInventory, error) {
inv := &ResetInventory{}
hosts, err := s.ListHostsByCustomer(customerID)
if err != nil {
return nil, err
}
inv.HostCount = len(hosts)
queries := []struct {
dst *int
q string
arg string
}{
{&inv.SupersededBlobs, `SELECT COUNT(*) FROM host_escrow_superseded WHERE host_id IN (SELECT host_id FROM host_deletions WHERE customer_id = ? UNION SELECT host_id FROM hosts WHERE customer_id = ?)`, customerID},
}
for _, qq := range queries {
if err := s.db.QueryRow(qq.q, qq.arg, customerID).Scan(qq.dst); err != nil {
return nil, err
}
}
present := func(q string) (bool, error) {
var n int
err := s.db.QueryRow(q, customerID).Scan(&n)
return n > 0, err
}
if inv.DRRecipePresent, err = present(`SELECT COUNT(*) FROM dr_recipe WHERE customer_id = ?`); err != nil {
return nil, err
}
if inv.OneTimeSecretPresent, err = present(`SELECT COUNT(*) FROM one_time_secrets WHERE customer_id = ?`); err != nil {
return nil, err
}
if inv.ClaimPresent, err = present(`SELECT COUNT(*) FROM customer_claims WHERE customer_id = ?`); err != nil {
return nil, err
}
return inv, nil
}
// StartCustomerReset opens a reset journal row and returns its id.
func (s *Store) StartCustomerReset(customerID string, escrowAcked bool) (int64, error) {
acked := 0
if escrowAcked {
acked = 1
}
res, err := s.db.Exec(`INSERT INTO customer_resets (customer_id, escrow_acked, legs_json) VALUES (?, ?, '{}')`, customerID, acked)
if err != nil {
return 0, err
}
return res.LastInsertId()
}
// UpdateResetLeg merges one leg's status into the journal (read-modify-write; the reset is single-flight
// per customer at the handler, so no lock contention).
func (s *Store) UpdateResetLeg(resetID int64, leg, status string) error {
var raw string
if err := s.db.QueryRow(`SELECT legs_json FROM customer_resets WHERE id = ?`, resetID).Scan(&raw); err != nil {
return err
}
legs := map[string]string{}
if raw != "" {
_ = json.Unmarshal([]byte(raw), &legs)
}
legs[leg] = status
out, err := json.Marshal(legs)
if err != nil {
return err
}
_, err = s.db.Exec(`UPDATE customer_resets SET legs_json = ? WHERE id = ?`, string(out), resetID)
return err
}
// FinishCustomerReset stamps completion.
func (s *Store) FinishCustomerReset(resetID int64) error {
_, err := s.db.Exec(`UPDATE customer_resets SET completed_at = datetime('now') WHERE id = ?`, resetID)
return err
}
// LatestCustomerReset returns the customer's most recent reset record (nil = never).
func (s *Store) LatestCustomerReset(customerID string) (*CustomerReset, error) {
var (
cr CustomerReset
startedAt string
completedAt sql.NullString
acked int
legs string
)
err := s.db.QueryRow(`
SELECT id, customer_id, started_at, completed_at, escrow_acked, legs_json
FROM customer_resets WHERE customer_id = ? ORDER BY id DESC LIMIT 1`, customerID).
Scan(&cr.ID, &cr.CustomerID, &startedAt, &completedAt, &acked, &legs)
if err == sql.ErrNoRows {
return nil, nil
}
if err != nil {
return nil, err
}
cr.StartedAt = parseSQLiteTime(startedAt)
if completedAt.Valid && completedAt.String != "" {
t := parseSQLiteTime(completedAt.String)
cr.CompletedAt = &t
}
cr.EscrowAcked = acked != 0
cr.Legs = map[string]string{}
_ = json.Unmarshal([]byte(legs), &cr.Legs)
return &cr, nil
}
// PurgeCustomerResetDBState is the DB-purge phase — runs LAST, after the external teardown legs. In one
// tx it removes the customer-scoped operational state a RESET destroys: retained escrow custody
// (ack-gated), the one-time repo password, the DR recipe, and customer-scoped log bundles. It does NOT
// touch customer_configs identity/config (SURVIVES), provenance (host_deletions/customer_resets), or
// events (audit). The claim reset rides the claim engine separately; the offsite descriptor clear rides
// the offsite package (config_json). Idempotent — a re-run deletes nothing extra.
func (s *Store) PurgeCustomerResetDBState(customerID string, escrowAcked bool) error {
tx, err := s.db.Begin()
if err != nil {
return err
}
defer tx.Rollback()
if escrowAcked {
// Retained (superseded) blobs — the hosts are gone by the RESET precondition, so they are found
// only via the F-14 host_deletions provenance (UNION current hosts as a belt-and-suspenders).
if _, err := tx.Exec(`DELETE FROM host_escrow_superseded WHERE host_id IN (
SELECT host_id FROM host_deletions WHERE customer_id = ?
UNION SELECT host_id FROM hosts WHERE customer_id = ?)`, customerID, customerID); err != nil {
return fmt.Errorf("purge superseded escrow: %w", err)
}
}
for _, q := range []string{
`DELETE FROM one_time_secrets WHERE customer_id = ?`,
`DELETE FROM dr_recipe WHERE customer_id = ?`,
`DELETE FROM log_bundles WHERE scope_id = ?`,
`DELETE FROM log_bundle_requests WHERE scope_id = ?`,
} {
if _, err := tx.Exec(q, customerID); err != nil {
return fmt.Errorf("reset purge %q: %w", q, err)
}
}
return tx.Commit()
}
// DeleteClaim removes a customer's claim row (RESET → unclaimed / pre-first-install). The claim ENGINE
// re-mints a fresh code via EnsureIssued on the next onboarding — this is the store primitive the
// engine's ResetToUnclaimed rides (no parallel claimed-flag mechanism).
func (s *Store) DeleteClaim(customerID string) error {
_, err := s.db.Exec(`DELETE FROM customer_claims WHERE customer_id = ?`, customerID)
return err
}