R-861: narrow the agent's root grants — exact sudo patterns, felhom-priv-apply content checker, fixed hook/parent files in the bundle, signed self-update verified as root, escrow root reads pinned

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

internal/selfupdate/executor.go

@@ -3,6 +3,7 @@ package selfupdate
 import (
 	"context"
 	"crypto/sha256"
+	"encoding/base64"
 	"encoding/hex"
 	"encoding/json"
 	"fmt"
@@ -11,6 +12,7 @@ import (
 	"net/http"
 	"os"
 	"path/filepath"
+	"strings"
 	"time"
 
 	"gitea.dooplex.hu/admin/felhom-agent/internal/signedjobs"
@@ -47,6 +49,7 @@ type Executor struct {
 	username    string
 	token       string
 	stateDir    string
+	planDir     string // felhom-os-apply's plan dir; "" = defaultPlanDir (tests set a temp dir)
 	runner      WrapperRunner
 	httpClient  *http.Client
 	logger      *slog.Logger
@@ -126,18 +129,70 @@ func (e *Executor) Execute(ctx context.Context, op string, params json.RawMessag
 		return fmt.Errorf("agent_update: chmod staged: %w", err)
 	}
 
-	// Hand off to the root wrapper. It re-verifies the sha, flips A/B, writes the pending marker,
-	// and schedules the detached restart. After this the new binary starts; the commit is the
-	// Manager's job once it has dwelled cleanly.
-	e.logger.Warn("agent_update: handing staged binary to the guarded wrapper", "staged", staged, "version", p.Version)
-	stdout, stderr, err := e.runner.Run(ctx, wrapperPath, "apply", staged, p.SHA256)
-	if err != nil {
-		return fmt.Errorf("agent_update: wrapper apply failed: %w (stderr: %s)", err, string(stderr))
+	// R-861 (v0.146.0): hand the SIGNED job to the root wrapper felhom-os-apply (mode agent_update). It verifies the
+	// operator's signature itself (root-owned signers file, this host, the window, the nonce), re-hashes the staged
+	// file against the SIGNED sha, and only then runs the A/B flip (felhom-selfupdate-guarded apply, no longer in the
+	// agent's sudoers). Until v0.146.0 the agent passed the sha to the flip itself, so a compromised agent could
+	// install any binary — and the binary is what the escrow ceremony and the guest hook run as root.
+	so, ok := signedjobs.SignedOpFrom(ctx)
+	if !ok {
+		return fmt.Errorf("agent_update: no signed envelope in the context — the root wrapper could not verify it")
 	}
-	e.logger.Warn("agent_update: apply handed off; restart scheduled", "version", p.Version, "wrapper", trim(stdout))
+	planDir := e.planDir
+	if planDir == "" {
+		planDir = defaultPlanDir
+	}
+	if err := os.MkdirAll(planDir, 0o700); err != nil {
+		return fmt.Errorf("agent_update: plan dir: %w", err)
+	}
+	plan, _ := json.Marshal(map[string]any{"release_id": "agent-" + p.Version, "layer": "host", "mode": "agent_update",
+		"staged": staged, "signed": map[string]string{"blob_b64": base64.StdEncoding.EncodeToString(so.Blob), "sig": string(so.Sig)}})
+	planPath := filepath.Join(planDir, "plan-agentupdate-"+p.Version+".json")
+	if err := os.WriteFile(planPath, plan, 0o600); err != nil {
+		return fmt.Errorf("agent_update: write plan: %w", err)
+	}
+	defer os.Remove(planPath)
+	e.logger.Warn("agent_update: handing the signed job to the root wrapper (felhom-os-apply agent_update)", "staged", staged, "version", p.Version)
+	stdout, stderr, err := e.runner.Run(ctx, osApplyPath, "--plan", planPath)
+	rep := parseOSApplyReport(stdout)
+	var r struct {
+		Refused     json.RawMessage `json:"refused"`
+		Failed      json.RawMessage `json:"failed"`
+		AgentUpdate json.RawMessage `json:"agent_update"`
+	}
+	jerr := json.Unmarshal([]byte(rep), &r)
+	refused := len(r.Refused) > 0 && string(r.Refused) != "null"
+	if err != nil || jerr != nil || refused || len(r.Failed) > 0 || len(r.AgentUpdate) == 0 {
+		return fmt.Errorf("agent_update: the root wrapper did not apply it: %v (report: %s; stderr: %s)", err, trimStr(rep), trim(stderr))
+	}
+	e.logger.Warn("agent_update: signed update verified as root and handed off; restart scheduled", "version", p.Version, "report", trimStr(rep))
 	return nil
 }
 
+// osApplyPath is the root wrapper that verifies the signed agent_update (R-861). Fixed, never config-overridable.
+const osApplyPath = "/usr/local/sbin/felhom-os-apply"
+
+// defaultPlanDir is felhom-os-apply's ONLY plan directory (PLAN_DIR there; osupdate.DefaultPlanDir here).
+const defaultPlanDir = "/var/lib/felhom-agent/os"
+
+// parseOSApplyReport returns the JSON after the wrapper's last "OSAPPLY-REPORT " line ("" when there is none).
+func parseOSApplyReport(stdout []byte) string {
+	rep := ""
+	for _, line := range strings.Split(string(stdout), "\n") {
+		if strings.HasPrefix(line, "OSAPPLY-REPORT ") {
+			rep = strings.TrimPrefix(line, "OSAPPLY-REPORT ")
+		}
+	}
+	return rep
+}
+
+func trimStr(s string) string {
+	if len(s) > 400 {
+		return s[:400] + "…"
+	}
+	return s
+}
+
 // download streams url → dest (0644, fsync'd) and returns the lowercase-hex sha256 of the bytes.
 func (e *Executor) download(ctx context.Context, url, dest string) (string, error) {
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)

internal/selfupdate/executor_test.go

@@ -15,34 +15,56 @@ import (
 	"sync"
 	"testing"
 
+	"gitea.dooplex.hu/admin/felhom-agent/internal/reconcile"
 	"gitea.dooplex.hu/admin/felhom-agent/internal/signedjobs"
 )
 
-// fakeWrapper records the verbs the executor/manager shell out, and returns a configurable error.
+// fakeWrapper records the verbs the executor/manager shell out, and returns a configurable error. For the os-apply
+// call it snapshots the plan file at call time (the executor removes it afterwards) and answers with report.
 type fakeWrapper struct {
-	mu    sync.Mutex
-	calls [][]string
-	err   error
+	mu     sync.Mutex
+	calls  [][]string
+	err    error
+	plans  []map[string]any
+	report string // the OSAPPLY-REPORT JSON; "" = a successful agent_update
 }
 
 func (f *fakeWrapper) Run(_ context.Context, name string, args ...string) ([]byte, []byte, error) {
 	f.mu.Lock()
 	defer f.mu.Unlock()
 	f.calls = append(f.calls, append([]string{name}, args...))
+	if name == osApplyPath && len(args) == 2 && args[0] == "--plan" {
+		var p map[string]any
+		b, _ := os.ReadFile(args[1])
+		_ = json.Unmarshal(b, &p)
+		f.plans = append(f.plans, p)
+		rep := f.report
+		if rep == "" {
+			rep = `{"agent_update": {"version": "x", "wrapper_rc": 0}, "mode": "agent_update", "refused": null}`
+		}
+		return []byte("OSAPPLY-REPORT " + rep + "\n"), nil, f.err
+	}
 	return []byte("ok"), nil, f.err
 }
+
+// applyCalls are the hand-offs to the root wrapper (felhom-os-apply --plan …). Since v0.146.0 the agent never calls
+// `felhom-selfupdate-guarded apply` itself.
 func (f *fakeWrapper) applyCalls() [][]string {
 	f.mu.Lock()
 	defer f.mu.Unlock()
 	var out [][]string
 	for _, c := range f.calls {
-		if len(c) >= 2 && c[1] == "apply" {
+		if c[0] == osApplyPath || (len(c) >= 2 && c[1] == "apply") {
 			out = append(out, c)
 		}
 	}
 	return out
 }
 
+func signedCtx() context.Context {
+	return signedjobs.WithSignedOp(context.Background(), &reconcile.SignedOp{Blob: []byte(`{"op":"agent_update"}`), Sig: []byte("SIG")})
+}
+
 func sha256Of(b []byte) string {
 	h := sha256.Sum256(b)
 	return hex.EncodeToString(h[:])
@@ -65,6 +87,7 @@ func newExec(t *testing.T, srv *httptest.Server, wrap WrapperRunner) (*Executor,
 		Runner:      wrap,
 		Logger:      slog.New(slog.NewTextHandler(io.Discard, nil)),
 	})
+	e.planDir = t.TempDir()
 	return e, stateDir
 }
 
@@ -84,7 +107,7 @@ func TestExecutor_HappyPath(t *testing.T) {
 	e, stateDir := newExec(t, srv, wrap)
 
 	sha := sha256Of(body)
-	if err := e.Execute(context.Background(), "agent_update", updateParamsJSON(t, "0.70.1", sha)); err != nil {
+	if err := e.Execute(signedCtx(), "agent_update", updateParamsJSON(t, "0.70.1", sha)); err != nil {
 		t.Fatalf("execute: %v", err)
 	}
 	staged := filepath.Join(stateDir, "selfupdate", "felhom-agent-0.70.1")
@@ -93,11 +116,46 @@ func TestExecutor_HappyPath(t *testing.T) {
 		t.Fatalf("staged binary missing/mismatch: %v", err)
 	}
 	calls := wrap.applyCalls()
-	if len(calls) != 1 {
-		t.Fatalf("apply invoked %d times, want 1 (%v)", len(calls), wrap.calls)
+	if len(calls) != 1 || calls[0][0] != osApplyPath || calls[0][1] != "--plan" {
+		t.Fatalf("want exactly one hand-off to felhom-os-apply --plan, got %v", wrap.calls)
 	}
-	if calls[0][2] != staged || calls[0][3] != sha {
-		t.Errorf("apply args = %v, want [.. apply %s %s]", calls[0], staged, sha)
+	// R-861: the plan carries the SIGNED envelope and the staged path; the wrapper, not the agent, decides.
+	p := wrap.plans[0]
+	sg, _ := p["signed"].(map[string]any)
+	if p["mode"] != "agent_update" || p["layer"] != "host" || p["staged"] != staged || sg["sig"] != "SIG" || sg["blob_b64"] == "" {
+		t.Errorf("plan = %v, want mode agent_update + the staged path + the signed envelope", p)
+	}
+	if _, err := os.Stat(calls[0][2]); !os.IsNotExist(err) {
+		t.Error("the plan file was left behind")
+	}
+}
+
+// R-861: without the signed envelope nothing reaches the root wrapper.
+// RED-PROOF (audits/hub-safety-2026-10-05/partF/red-proof.txt): call `felhom-selfupdate-guarded apply` directly again
+// → the happy path's "exactly one hand-off to felhom-os-apply" fails.
+func TestExecutor_NoEnvelopeNoHandOff(t *testing.T) {
+	body := []byte("good bytes")
+	srv := artifactServer(t, body)
+	defer srv.Close()
+	wrap := &fakeWrapper{}
+	e, _ := newExec(t, srv, wrap)
+	if err := e.Execute(context.Background(), "agent_update", updateParamsJSON(t, "0.70.1", sha256Of(body))); err == nil {
+		t.Fatal("an update with no signed envelope was handed on")
+	}
+	if len(wrap.applyCalls()) != 0 {
+		t.Fatalf("the root wrapper was called without an envelope: %v", wrap.calls)
+	}
+}
+
+// A refusal in the wrapper's report is a failure, even when its exit code reads 0.
+func TestExecutor_WrapperRefusalSurfaces(t *testing.T) {
+	body := []byte("good bytes")
+	srv := artifactServer(t, body)
+	defer srv.Close()
+	wrap := &fakeWrapper{report: `{"mode": "agent_update", "refused": {"code": "R3", "reason": "the operator signature does not verify"}}`}
+	e, _ := newExec(t, srv, wrap)
+	if err := e.Execute(signedCtx(), "agent_update", updateParamsJSON(t, "0.70.1", sha256Of(body))); err == nil {
+		t.Fatal("a refused signed update read as applied")
 	}
 }
 
@@ -158,7 +216,7 @@ func TestExecutor_WrapperFailureSurfaces(t *testing.T) {
 	defer srv.Close()
 	wrap := &fakeWrapper{err: errors.New("wrapper refused: sha mismatch")}
 	e, _ := newExec(t, srv, wrap)
-	if err := e.Execute(context.Background(), "agent_update", updateParamsJSON(t, "0.70.1", sha256Of(body))); err == nil {
+	if err := e.Execute(signedCtx(), "agent_update", updateParamsJSON(t, "0.70.1", sha256Of(body))); err == nil {
 		t.Fatal("wrapper failure must surface")
 	}
 }