R-349: the host report carries the sha256 of the RUNNING agent binary

A hand-built proof binary and the published artifact share a version string but not their bytes, so no version check could see the divergence. The agent now reports agent_sha256 (hash of /proc/self/exe, once per process; empty = unknown) beside agent_version, the same mechanism as host.wrapper_sha256. The hub half (compare against the vouched agent_sha256, surface drift) is owed in the hub repo. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
2026-10-05 21:10:43 +02:00
parent 208fac8027
commit 64f704d0f7
3 changed files with 100 additions and 2 deletions
@@ -10,6 +10,7 @@ import (
 	"log/slog"
 	"os"
 	"strings"
+	"sync"
 	"time"

 	"gitea.dooplex.hu/admin/felhom-agent/internal/capability"
@@ -115,6 +116,7 @@ type Collector struct {
 	backupTarget     func() ConfiguredBackupTarget                 // R-109: primary backup tier id (nil → recipe records unknown)
 	hostID           string
 	agentVersion     string
+	selfSHA          func() string // R-349: sha256 of the running binary; default runningBinarySHA256
 	logger           *slog.Logger
 	now              func() time.Time
 }
@@ -135,6 +137,7 @@ func NewCollector(px proxmoxReader, cf CloudflaredProber, storage StorageObserve
 		temp:         SysfsTempReader{}, // slice 9: real sysfs reader by default; tests inject a fake
 		hostID:       hostID,
 		agentVersion: agentVersion,
+		selfSHA:      runningBinarySHA256,
 		logger:       logger,
 		now:          func() time.Time { return time.Now().UTC() },
 	}
@@ -337,6 +340,7 @@ func (c *Collector) Collect(ctx context.Context) (*HostReport, error) {
 		HostID:       c.hostID,
 		ReportedAt:   c.now().Format(time.RFC3339),
 		AgentVersion: c.agentVersion,
+		AgentSHA256:  c.agentSHA256(),
 		Host:         host,
 		Guests:       c.collectGuests(ctx),
 		// storage_targets populated this slice (slice 5) via the observer; the rest stay
@@ -431,8 +435,28 @@ const pbsWrapperPath = "/usr/local/sbin/felhom-pbs-apply"
 // unreadable file yields "", which the hub reads as UNKNOWN rather than as drift — a host that
 // legitimately has no DR wrapper must not light up amber. The file is 0755, so no privilege is
 // needed to read it.
-func pbsWrapperSHA256() string {
-	f, err := os.Open(pbsWrapperPath)
+func pbsWrapperSHA256() string { return fileSHA256(pbsWrapperPath) }
+
+// selfExePath is the running binary as the kernel holds it. /proc/self/exe, not the installed path:
+// after an A/B flip the file at /usr/local/bin/felhom-agent may already be the NEXT binary while this
+// process still runs the old one, and the report must describe what runs (R-349). Test seam.
+var selfExePath = "/proc/self/exe"
+
+// runningBinarySHA256 hashes the running binary ONCE per process — the bytes cannot change under a
+// running process, and re-hashing ~20 MB every report cycle buys nothing. A failed read is cached as
+// "" (UNKNOWN); it never fails the report.
+var runningBinarySHA256 = sync.OnceValue(func() string { return fileSHA256(selfExePath) })
+
+func (c *Collector) agentSHA256() string {
+	if c.selfSHA == nil {
+		return ""
+	}
+	return c.selfSHA()
+}
+
+// fileSHA256 is the hex sha256 of a file's bytes, or "" when it cannot be read.
+func fileSHA256(path string) string {
+	f, err := os.Open(path)
 	if err != nil {
 		return ""
 	}
@@ -0,0 +1,64 @@
+package hub
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// R-349: the report carries the sha256 of the binary that is RUNNING, so the hub can tell a
+// hand-built proof binary from the vouched artifact of the same version string. The consequence
+// asserted: the wire field equals the hash of this very test binary's bytes (read independently via
+// os.Executable, a different channel from /proc/self/exe), and it is on the wire as agent_sha256.
+func TestCollect_AgentSHA256IsTheRunningBinary(t *testing.T) {
+	exe, err := os.Executable()
+	if err != nil {
+		t.Skipf("os.Executable: %v", err)
+	}
+	raw, err := os.ReadFile(exe)
+	if err != nil {
+		t.Fatalf("read own binary: %v", err)
+	}
+	sum := sha256.Sum256(raw)
+	want := hex.EncodeToString(sum[:])
+
+	px := &fakePx{node: "n", ns: newTestNodeStatus()}
+	c := NewCollector(px, fakeProber{status: "running"}, nil, nil, nil, nil, "h", "0.3.0", quietLogger())
+	r, err := c.Collect(context.Background())
+	if err != nil {
+		t.Fatalf("Collect: %v", err)
+	}
+	if r.AgentSHA256 != want {
+		t.Fatalf("agent_sha256 = %q, want the running binary's %q", r.AgentSHA256, want)
+	}
+	b, err := json.Marshal(r)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !strings.Contains(string(b), `"agent_sha256":"`+want+`"`) {
+		t.Fatalf("agent_sha256 not on the wire: %s", b)
+	}
+}
+
+// An unreadable binary is UNKNOWN (empty, omitted) — never a made-up hash, never a failed report.
+func TestFileSHA256_UnreadableIsEmpty(t *testing.T) {
+	if got := fileSHA256(filepath.Join(t.TempDir(), "absent")); got != "" {
+		t.Fatalf("absent file hashed to %q, want empty", got)
+	}
+	px := &fakePx{node: "n", ns: newTestNodeStatus()}
+	c := NewCollector(px, fakeProber{status: "running"}, nil, nil, nil, nil, "h", "0.3.0", quietLogger())
+	c.selfSHA = func() string { return "" }
+	r, err := c.Collect(context.Background())
+	if err != nil {
+		t.Fatalf("Collect must not fail on an unreadable binary: %v", err)
+	}
+	b, _ := json.Marshal(r)
+	if strings.Contains(string(b), "agent_sha256") {
+		t.Fatalf("empty agent_sha256 must be omitted: %s", b)
+	}
+}
@@ -18,6 +18,16 @@ type HostReport struct {
 	HostID       string `json:"host_id"`     // echoes config.Hub.HostID
 	ReportedAt   string `json:"reported_at"` // RFC3339, agent clock
 	AgentVersion string `json:"agent_version"`
+	// AgentSHA256 is the sha256 of the binary this process is RUNNING (read through /proc/self/exe,
+	// once per process), R-349. The version string cannot tell a hand-built proof binary from the
+	// published, vouched artifact of the same version — same source, different bytes (`-trimpath
+	// -buildvcs=false` in release-agent.sh) — so self-update sees "already installed" and never
+	// corrects it. Reporting the bytes lets the hub compare against the vouched agent_sha256, the
+	// same mechanism host.wrapper_sha256 is for the PBS wrapper (R-50b(a)).
+	//
+	// Empty = unreadable, which the hub must treat as UNKNOWN, never as drift. Pinned by
+	// TestCollect_AgentSHA256IsTheRunningBinary.
+	AgentSHA256 string `json:"agent_sha256,omitempty"`

 	Host   HostMetrics `json:"host"`
 	Guests []Guest     `json:"guests"`