Files
felhom.eu/hub/internal/store/pbsdr_test.go
T
admin c484aa204e hub: R-39 core — stamp a secret GENERATION into the pbs_dr descriptor
The fleet half of R-39. An ep0 credential re-issue re-keys the SECRET of an existing
token, so token_id, fingerprint, datastore and namespace all come back byte-identical.
The agent re-applies on the descriptor's CONTENT HASH, so a re-issue was invisible to a
converged box: it short-circuited, never consumed the fresh secret, and served a revoked
credential while reporting `applied` — the N100 failure of 2026-07-18.

host_pbs_secrets gains a monotonic per-host `generation`, advanced by every fresh MINT and
by nothing else, stamped into the descriptor as `secret_generation`. That is now the only
field a re-key moves, and it is what re-arms the agent.

DEVIATION FROM SPEC, deliberate: the brief said to return "the new row's id (int64) …
no schema change". There is no row id — host_pbs_secrets is keyed by host_id and UPSERTed
last-write-wins, so a new row never exists, and created_at collides for two mints in the
same second. An additive counter column is the only monotonic source; it uses the repo's
existing idempotent ALTER-TABLE idiom.

RestageHostPBSSecret deliberately does NOT advance it: a re-stage re-arms the SAME secret,
the descriptor content genuinely has not changed, and a bump would cause a pointless agent
refetch loop (that method's own contract says so).

Also corrects a comment that asserted the re-issue refreshes the descriptor "with the NEW
token_id/fingerprint". That is false for a re-key, and believing it is why the descriptor
was never expected to be identical in the first place.

omitempty is load-bearing: a zero generation must not start emitting a new key into every
pre-existing descriptor, which would itself be a fleet-wide spurious re-apply.

Compatibility: agents below 0.91.0 drop the unknown JSON key and behave exactly as today —
inert, not breaking (Scenario C).

Tests: store-level monotonicity + per-host isolation + restage-leaves-it-alone; descriptor
byte-change, omitempty, and sibling-key round-trip; and a FLOW-level test driving
ReissuePBSDR against a fake that models a real re-key. Red-proof run at the assertion
level (not the compiler): commenting out the stamp makes the flow test fail with both
byte-identical blocks printed.
2026-07-21 09:52:04 +02:00

222 lines
8.6 KiB
Go

package store
import (
"database/sql"
"testing"
)
// RestageHostPBSSecret re-arms a stored (consumed) secret WITHOUT changing its value, inserting a
// row, or bumping any generation. Returns restaged=false when no row exists.
func TestRestageHostPBSSecret(t *testing.T) {
s := newTestStore(t)
// No row → restaged=false, no error (the caller escalates to Re-issue).
if restaged, err := s.RestageHostPBSSecret("h1"); err != nil || restaged {
t.Fatalf("restage with nothing stored = (%v, %v), want (false, nil)", restaged, err)
}
// Store + consume, then re-stage: the SAME value is served once more.
if _, err := s.SaveHostPBSSecret("h1", "the-secret"); err != nil {
t.Fatalf("save: %v", err)
}
if _, err := s.ConsumeHostPBSSecret("h1"); err != nil {
t.Fatalf("first consume: %v", err)
}
if _, err := s.ConsumeHostPBSSecret("h1"); err != sql.ErrNoRows {
t.Fatalf("pre-restage second consume = %v, want ErrNoRows", err)
}
restaged, err := s.RestageHostPBSSecret("h1")
if err != nil || !restaged {
t.Fatalf("restage of a stored secret = (%v, %v), want (true, nil)", restaged, err)
}
// Red-proof: dropping the `SET consumed_at = NULL` makes this consume return ErrNoRows.
got, err := s.ConsumeHostPBSSecret("h1")
if err != nil || got != "the-secret" {
t.Fatalf("post-restage consume = (%q, %v), want (the-secret, nil) — same value, re-armed", got, err)
}
}
// A-gen guard: a re-stage touches ONLY host_pbs_secrets — never the host generation (a bump would
// trigger an agent desired-state refetch loop). Red-proof: adding a SetHostDesired/gen bump to
// RestageHostPBSSecret makes this assert fail.
func TestRestageHostPBSSecret_NoGenerationBump(t *testing.T) {
s := newTestStore(t)
if err := s.UpsertHost(&Host{HostID: "h1", CustomerID: "c1", APIKey: "k"}); err != nil {
t.Fatalf("host: %v", err)
}
genBefore, err := s.SetHostDesired("h1", []byte(`{"pbs_dr":{"enabled":true,"namespace":"c1"}}`))
if err != nil {
t.Fatalf("set desired: %v", err)
}
if _, err := s.SaveHostPBSSecret("h1", "s"); err != nil {
t.Fatalf("save secret: %v", err)
}
if _, err := s.RestageHostPBSSecret("h1"); err != nil {
t.Fatalf("restage: %v", err)
}
h, err := s.GetHost("h1")
if err != nil {
t.Fatalf("get host: %v", err)
}
if h.DesiredGeneration != genBefore {
t.Fatalf("generation changed by a re-stage: %d -> %d (a re-stage must never bump)", genBefore, h.DesiredGeneration)
}
}
// PBSDRHealStates joins each host's descriptor (enabled/provisioned) to its LATEST report's
// pbs_dr.state + report id.
func TestPBSDRHealStates(t *testing.T) {
s := newTestStore(t)
// Host A: enabled + provisioned, latest report waiting_secret (after an older applied report).
mustHost(t, s, "hA", "cA", `{"pbs_dr":{"enabled":true,"namespace":"cA","storage_id":"felhom-pbs"}}`)
mustReport(t, s, "hA", "cA", `{"pbs_dr":{"state":"applied"}}`)
mustReport(t, s, "hA", "cA", `{"pbs_dr":{"state":"waiting_secret"}}`) // newer → wins
// Host B: descriptor disabled.
mustHost(t, s, "hB", "cB", `{"pbs_dr":{"enabled":false,"namespace":"cB"}}`)
mustReport(t, s, "hB", "cB", `{"pbs_dr":{"state":"disabled"}}`)
// Host C: enabled but NOT provisioned (namespace empty); no report.
mustHost(t, s, "hC", "cC", `{"pbs_dr":{"enabled":true}}`)
rows, err := s.PBSDRHealStates()
if err != nil {
t.Fatalf("PBSDRHealStates: %v", err)
}
byHost := map[string]PBSDRHealRow{}
for _, r := range rows {
byHost[r.HostID] = r
}
a := byHost["hA"]
if !a.DescriptorEnabled || !a.DescriptorProvisioned || a.ReportedState != "waiting_secret" || a.ReportID == 0 {
t.Errorf("hA = %+v, want enabled+provisioned+waiting_secret+reportID>0", a)
}
b := byHost["hB"]
if b.DescriptorEnabled || b.ReportedState != "disabled" {
t.Errorf("hB = %+v, want disabled descriptor + state disabled", b)
}
c := byHost["hC"]
if !c.DescriptorEnabled || c.DescriptorProvisioned || c.ReportedState != "" || c.ReportID != 0 {
t.Errorf("hC = %+v, want enabled+unprovisioned+no-report", c)
}
}
func mustHost(t *testing.T, s *Store, hostID, customerID, desiredJSON string) {
t.Helper()
if err := s.UpsertHost(&Host{HostID: hostID, CustomerID: customerID, APIKey: "k-" + hostID}); err != nil {
t.Fatalf("UpsertHost %s: %v", hostID, err)
}
if _, err := s.SetHostDesired(hostID, []byte(desiredJSON)); err != nil {
t.Fatalf("SetHostDesired %s: %v", hostID, err)
}
}
func mustReport(t *testing.T, s *Store, hostID, customerID, reportJSON string) {
t.Helper()
if err := s.SaveHostReport(hostID, customerID, []byte(reportJSON), HostReportDenorm{AgentVersion: "0.88.0"}); err != nil {
t.Fatalf("SaveHostReport %s: %v", hostID, err)
}
}
// The host-scoped consume-once contract (PBS DR SLICE 1): exactly one read per stored value,
// a re-save resets the consumed flag (re-issue supersedes), absence is sql.ErrNoRows.
func TestHostPBSSecret_ConsumeOnce(t *testing.T) {
s := newTestStore(t)
if _, err := s.ConsumeHostPBSSecret("h1"); err != sql.ErrNoRows {
t.Fatalf("consume with nothing stored = %v, want sql.ErrNoRows", err)
}
if _, err := s.SaveHostPBSSecret("h1", "secret-1"); err != nil {
t.Fatalf("save: %v", err)
}
got, err := s.ConsumeHostPBSSecret("h1")
if err != nil || got != "secret-1" {
t.Fatalf("first consume = (%q, %v), want (secret-1, nil)", got, err)
}
// Single use: the second consume MUST be ErrNoRows (red-proof: dropping the consumed_at
// UPDATE in ConsumeHostPBSSecret makes this assert fail with the value returned again).
if got, err := s.ConsumeHostPBSSecret("h1"); err != sql.ErrNoRows {
t.Fatalf("second consume = (%q, %v), want sql.ErrNoRows — consume-once broken", got, err)
}
// Re-issue path: a fresh save resets consumption and serves the NEW value once.
if _, err := s.SaveHostPBSSecret("h1", "secret-2"); err != nil {
t.Fatalf("re-save: %v", err)
}
got, err = s.ConsumeHostPBSSecret("h1")
if err != nil || got != "secret-2" {
t.Fatalf("post-reissue consume = (%q, %v), want (secret-2, nil)", got, err)
}
// Host isolation: h2 never sees h1's rows.
if _, err := s.ConsumeHostPBSSecret("h2"); err != sql.ErrNoRows {
t.Fatalf("foreign host consume = %v, want sql.ErrNoRows", err)
}
}
// R-39 — the secret GENERATION is what makes a re-key visible to the agent.
//
// A re-issue rotates only the side-table secret: token_id, fingerprint, datastore and namespace all
// come back byte-identical, so without this counter the descriptor never moves, the converged agent
// short-circuits on its content hash, and the fresh secret is never consumed. That is the 2026-07-18
// N100 failure. These assertions are the store half of the guarantee.
func TestSaveHostPBSSecret_GenerationIsMonotonicPerMint(t *testing.T) {
s := newTestStore(t)
// No secret ever stored → generation 0 (not an error).
if g, err := s.HostPBSSecretGeneration("h1"); err != nil || g != 0 {
t.Fatalf("generation with nothing stored = (%d, %v), want (0, nil)", g, err)
}
g1, err := s.SaveHostPBSSecret("h1", "secret-1")
if err != nil {
t.Fatalf("first mint: %v", err)
}
if g1 != 1 {
t.Fatalf("first mint generation = %d, want 1", g1)
}
// THE FIX: a re-key with an identical descriptor still advances the generation.
g2, err := s.SaveHostPBSSecret("h1", "secret-2")
if err != nil {
t.Fatalf("re-key mint: %v", err)
}
if g2 != 2 {
t.Fatalf("re-key generation = %d, want 2 — a re-issue MUST advance it or the agent never re-applies", g2)
}
if g2 <= g1 {
t.Fatalf("generation went backwards or stalled: %d -> %d", g1, g2)
}
if got, err := s.HostPBSSecretGeneration("h1"); err != nil || got != g2 {
t.Fatalf("read-back generation = (%d, %v), want (%d, nil)", got, err, g2)
}
// Per-host, not global: another host starts at 1.
if g, err := s.SaveHostPBSSecret("h2", "other"); err != nil || g != 1 {
t.Fatalf("second host first mint = (%d, %v), want (1, nil) — the counter is per-host", g, err)
}
}
// A RE-STAGE must NOT advance the generation: it re-arms the SAME secret, so the descriptor content
// genuinely has not changed and a bump would cause a pointless agent refetch loop. This is the
// counterpart to TestRestageHostPBSSecret_NoGenerationBump, one level down.
func TestRestageHostPBSSecret_LeavesSecretGenerationAlone(t *testing.T) {
s := newTestStore(t)
g1, err := s.SaveHostPBSSecret("h1", "secret-1")
if err != nil {
t.Fatalf("mint: %v", err)
}
if _, err := s.ConsumeHostPBSSecret("h1"); err != nil {
t.Fatalf("consume: %v", err)
}
if restaged, err := s.RestageHostPBSSecret("h1"); err != nil || !restaged {
t.Fatalf("restage = (%v, %v), want (true, nil)", restaged, err)
}
g2, err := s.HostPBSSecretGeneration("h1")
if err != nil {
t.Fatalf("read generation: %v", err)
}
if g2 != g1 {
t.Fatalf("restage moved the secret generation %d -> %d; a re-stage changes no descriptor content", g1, g2)
}
}