Docker engine slow lane (live-restore once by reload; ring-0 pending-docker under a root-owned ring-0 mark; ring 1 and undo only by a signed os_docker_step the wrapper re-verifies against a root-owned signers file; same-container-id health), the version report (facts mode -> host report system stanza, R-852), guest restart scan every pass (R-849), the crash guard (kernel.panic=10, the 3rd unclean stop in 60 min stays off, 24 h re-arm)
gates / gates (push) Successful in 19s

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
This commit is contained in:
2026-10-04 16:14:36 +02:00
parent 2e2e8f56b8
commit b1746c25af
17 changed files with 1780 additions and 135 deletions
+39
View File
@@ -4,10 +4,12 @@ import (
"context"
"crypto/sha256"
"encoding/hex"
"encoding/json"
"fmt"
"io"
"log/slog"
"os"
"strings"
"time"
"gitea.dooplex.hu/admin/felhom-agent/internal/capability"
@@ -108,6 +110,7 @@ type Collector struct {
selfUpdate SelfUpdateReporter // D1: agent self-update pending status (nil → false)
mgmtPlane MgmtPlaneReporter // G1: management-plane health (nil → stanza omitted)
oob OOBReporter // H1: operator-access health (nil → stanza omitted)
system SystemReporter // R-852: the box versions (nil → API fields only)
backupTarget func() ConfiguredBackupTarget // R-109: primary backup tier id (nil → recipe records unknown)
hostID string
agentVersion string
@@ -248,6 +251,41 @@ type OOBReporter interface {
}
// SetOOBReporter wires the operator-access health source (H1; nil-safe → stanza omitted).
// SystemReporter reads the box's versions (R-852): the customer guest's vmid and the wrapper's raw facts.
type SystemReporter interface {
SystemFacts(ctx context.Context) (vmid int, facts json.RawMessage, err error)
}
// SetSystemReporter wires the facts read (agent v0.142.0). Without it the stanza carries the Proxmox API fields only.
func (c *Collector) SetSystemReporter(r SystemReporter) *Collector {
c.system = r
return c
}
func unknownIfEmpty(s string) string {
if strings.TrimSpace(s) == "" {
return "unknown"
}
return s
}
// systemInfo builds the `system` stanza. Never fatal: a failed facts read is FactsError, the API fields stay.
func (c *Collector) systemInfo(ctx context.Context, ns proxmox.NodeStatus) *SystemInfo {
si := &SystemInfo{PVEVersion: unknownIfEmpty(ns.PVEVersion), KernelVersion: unknownIfEmpty(ns.KVersion),
ReadAt: c.now().Format(time.RFC3339)}
if c.system == nil {
si.FactsError = "no facts reader wired"
return si
}
vmid, f, err := c.system.SystemFacts(ctx)
si.VMID, si.Facts = vmid, f
if err != nil {
si.FactsError = err.Error()
c.logger.Debug("hub: system facts unavailable", "err", err)
}
return si
}
func (c *Collector) SetOOBReporter(o OOBReporter) *Collector {
c.oob = o
return c
@@ -284,6 +322,7 @@ func (c *Collector) Collect(ctx context.Context) (*HostReport, error) {
Capabilities: c.capabilities(ctx),
LeafFingerprint: c.leafFP,
Addresses: c.collectAddresses(),
System: c.systemInfo(ctx, ns),
}
// DR recipe host-half — derived from the just-collected guest/storage/PBS facts (no new reads).
// Secret-free by construction (identifiers/intents/sizes/coordinates only).
+16
View File
@@ -89,6 +89,12 @@ type HostReport struct {
// hub-schema change and are absent when the reporter is not wired.
MgmtPlane *MgmtPlaneStatus `json:"mgmt_plane,omitempty"`
// System is the box's versions for the hub's System page (agent v0.142.0, R-852, `09` decision 89): Proxmox and the
// running kernel from the Proxmox API, and the wrapper's read-only facts (host Debian, next-boot kernel, held
// packages, taint, the crash guard; guest Debian, Docker engine, containerd, live-restore). A value nobody could
// read is "unknown", never empty and never guessed. The hub v0.132.0 consumes it (hosts + System pages).
System *SystemInfo `json:"system,omitempty"`
// PBSDR is the PBS-DR-tier bridge status stanza (slice 2). Present only when the pbsdr
// consumer is wired. `consumed_failed` is the LOUD persistent state: the one-time token
// secret was consumed but the apply failed afterwards — the secret is burned, the bridge
@@ -241,6 +247,16 @@ type WireguardStatus struct {
AssignedIP string `json:"assigned_ip,omitempty"` // from the marker, e.g. "10.77.0.2/32"
}
// SystemInfo is the `system` stanza (see HostReport.System).
type SystemInfo struct {
PVEVersion string `json:"pve_version"` // GET /nodes/{node}/status pveversion
KernelVersion string `json:"kernel_version"` // GET /nodes/{node}/status kversion
VMID int `json:"vmid,omitempty"` // the customer guest the facts read
Facts json.RawMessage `json:"facts,omitempty"`
FactsError string `json:"facts_error,omitempty"`
ReadAt string `json:"read_at"`
}
// HostMetrics is the host block, sourced from proxmox NodeStatus.
type HostMetrics struct {
Node string `json:"node"`