docs: Q1c GREEN — reboot survival automatic since agent 0.84.0 (feature doc + audit §7 + CONTEXT + REPORT)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PSK5g6qYLknKj8u3QAFEr6
This commit is contained in:
2026-07-11 21:25:14 +02:00
parent ae950e5933
commit 146d165c26
11 changed files with 743 additions and 40 deletions
+108
View File
@@ -3,6 +3,7 @@ package store
import (
"database/sql"
"encoding/json"
"errors"
"fmt"
"log"
"strconv"
@@ -1636,6 +1637,113 @@ func (s *Store) ListHosts() ([]Host, error) {
return hosts, rows.Err()
}
// ErrHostEscrowPresent is returned by DeleteHost when the host still has a key-escrow row
// and the caller did not explicitly acknowledge deleting it (fail-safe-to-refuse — an escrow
// blob may be the ONLY remaining path to a customer's backup keys).
var ErrHostEscrowPresent = errors.New("host has key escrow; deletion requires the explicit escrow acknowledgement")
// HostArtifacts summarizes what a host deletion would remove — counts/booleans ONLY (the
// impact preview must never carry a secret or blob).
type HostArtifacts struct {
Guests int
Reports int
LogBundles int // log_bundles rows with scope_id == host_id (the agent channel ONLY)
EscrowPresent bool
WGPeerBound bool
PBSSecretPresent bool
RecoveryPresent bool
}
// CountHostArtifacts reports the per-table blast radius of deleting a host (v0.47.0 stale
// host removal). LogBundles counts ONLY host-scoped rows — customer-scoped bundles (the
// controller channel, scope_id == customer_id) belong to the customer and are never touched.
func (s *Store) CountHostArtifacts(hostID string) (HostArtifacts, error) {
var a HostArtifacts
counts := []struct {
dst *int
query string
}{
{&a.Guests, `SELECT COUNT(*) FROM guests WHERE host_id = ?`},
{&a.Reports, `SELECT COUNT(*) FROM host_reports WHERE host_id = ?`},
{&a.LogBundles, `SELECT COUNT(*) FROM log_bundles WHERE scope_id = ?`},
}
for _, c := range counts {
if err := s.db.QueryRow(c.query, hostID).Scan(c.dst); err != nil {
return a, err
}
}
flags := []struct {
dst *bool
query string
}{
{&a.EscrowPresent, `SELECT EXISTS(SELECT 1 FROM host_escrow WHERE host_id = ?)`},
{&a.WGPeerBound, `SELECT EXISTS(SELECT 1 FROM wg_peers WHERE host_id = ?)`},
{&a.PBSSecretPresent, `SELECT EXISTS(SELECT 1 FROM host_pbs_secrets WHERE host_id = ?)`},
{&a.RecoveryPresent, `SELECT EXISTS(SELECT 1 FROM host_recovery WHERE host_id = ?)`},
}
for _, f := range flags {
var n int
if err := s.db.QueryRow(f.query, hostID).Scan(&n); err != nil {
return a, err
}
*f.dst = n != 0
}
return a, nil
}
// DeleteHost removes a host and every host-scoped artifact in ONE transaction (v0.47.0
// stale host removal). The online-gate lives in the web handler — the store deletes what
// it is told to. Guards:
// - empty hostID → refused (would DELETE the '' scope rows);
// - escrow present without deleteEscrow → ErrHostEscrowPresent, the tx never starts.
//
// The wg_peers delete is INSIDE the tx on purpose — a crash between a host delete and a
// separate peer delete would strand a bound peer the reconciler keeps pushing. The wgsync
// reconciler's 5-minute declarative full-list push converges the endpoint after the row
// disappears — no bump, no reconciler change. log_bundle rows die by scope_id == host_id
// (agent channel); customer-scoped bundles (scope_id == customer_id) are NOT touched.
func (s *Store) DeleteHost(hostID string, deleteEscrow bool) error {
if hostID == "" {
return fmt.Errorf("DeleteHost: empty host_id")
}
if !deleteEscrow {
var n int
if err := s.db.QueryRow(`SELECT EXISTS(SELECT 1 FROM host_escrow WHERE host_id = ?)`, hostID).Scan(&n); err != nil {
return fmt.Errorf("DeleteHost %s: escrow check: %w", hostID, err)
}
if n != 0 {
return ErrHostEscrowPresent
}
}
tx, err := s.db.Begin()
if err != nil {
return fmt.Errorf("DeleteHost %s: begin: %w", hostID, err)
}
defer tx.Rollback()
stmts := []string{
`DELETE FROM guests WHERE host_id = ?`,
`DELETE FROM host_reports WHERE host_id = ?`,
`DELETE FROM signed_jobs WHERE host_id = ?`,
`DELETE FROM host_recovery WHERE host_id = ?`,
`DELETE FROM host_pbs_secrets WHERE host_id = ?`,
`DELETE FROM log_bundle_requests WHERE scope_id = ?`,
`DELETE FROM log_bundles WHERE scope_id = ?`,
`DELETE FROM wg_peers WHERE host_id = ?`,
}
if deleteEscrow {
stmts = append(stmts, `DELETE FROM host_escrow WHERE host_id = ?`)
}
stmts = append(stmts, `DELETE FROM hosts WHERE host_id = ?`)
for _, q := range stmts {
if _, err := tx.Exec(q, hostID); err != nil {
return fmt.Errorf("DeleteHost %s: %q: %w", hostID, q, err)
}
}
return tx.Commit()
}
// UpsertHost creates or updates a host identity (used by the admin mint). On
// conflict it updates only operator-settable identity fields + updated_at; it does
// NOT touch the reality columns (agent_version/last_report_at) or the inert intent