fix(multiplayer): requeue every participant after a proposal times out

The timeout sibling of the previous commit's decline fix: a proposal
that simply times out (the 10s window elapses with no unanimous
response) hits ProposalExpireSQL/ProposalParticipantExpireSQL, and
neither of those -- same as the decline path -- ever touched
queue_tickets. Same severe consequence: every participant still
holding a PROPOSED ticket, response pending or already accepted, is
left stranded (invisible to the matcher, blocking a fresh
queue_create, renewable forever by heartbeat) with no automatic way
back into matchmaking. This path is reached from both GetProposal
(the recovery/read boundary -- a client that missed the expiry event
entirely) and RespondToProposal (a response arriving after the
window), so both needed the fix.

ProposalExpireRequeueSQL mirrors ProposalDeclineRequeueSQL, guarded on
state = 'EXPIRED' so it's safe to call unconditionally right after
ProposalExpireSQL: a no-op on a proposal that's still OPEN, and a
no-op on a proposal that was already EXPIRED on a prior pass (nothing
left at PROPOSED to requeue a second time).

Covered by a real PostgreSQL integration test via GetProposal (nobody
ever responds; recovering the proposal well after its window expires
it and must requeue both participants), confirming both tickets land
back at QUEUED with a refreshed expiry and are visible again to
ListQueuedCandidates. Clean across 5 runs, plus the full integration
and unit suites.
This commit is contained in:
Josh Creek
2026-09-01 14:36:34 +01:00
parent c8c363e667
commit 4627dd58fb
3 changed files with 94 additions and 0 deletions
+71
View File
@@ -570,6 +570,77 @@ func TestPostgreSQLProposalDeclineRequeuesEveryParticipant(t *testing.T) {
}
}
// TestPostgreSQLProposalTimeoutRequeuesEveryParticipant is the timeout
// sibling of the decline test above: a proposal that simply times out (no
// explicit decline, nobody ever responds) hits the exact same
// ProposalExpireSQL/ProposalParticipantExpireSQL path with the exact same
// gap -- neither ever touched queue_tickets, so this is the same severe
// stranding bug reached a different way. Uses GetProposal (the recovery/read
// path) rather than RespondToProposal, since a real client that just missed
// the expiry event and comes back later to check on it is exactly the
// scenario this path exists for.
func TestPostgreSQLProposalTimeoutRequeuesEveryParticipant(t *testing.T) {
db := openIntegrationPostgres(t)
applyIntegrationMigrations(t, db)
now := time.Now().UTC().Truncate(time.Microsecond)
ctx := context.Background()
for _, player := range []string{"timeout-player-a", "timeout-player-b"} {
if _, err := db.ExecContext(ctx, `INSERT INTO identities (player_id, steam_id) VALUES ($1, $1)`, player); err != nil {
t.Fatal(err)
}
}
for i, player := range []string{"timeout-player-a", "timeout-player-b"} {
if _, err := db.ExecContext(ctx, `INSERT INTO queue_tickets (ticket_id, player_id, playlist, state, client_build, protocol_version, enqueued_at, expires_at) VALUES ($1, $2, 'casual', 'QUEUED', 'integration-build', 1, $3, $4)`, fmt.Sprintf("timeout-ticket-%d", i), player, now, now.Add(time.Minute)); err != nil {
t.Fatal(err)
}
}
proposal, err := domain.NewProposal("timeout-proposal", domain.Casual, []string{"timeout-player-a", "timeout-player-b"}, now)
if err != nil {
t.Fatal(err)
}
if err := CreateProposal(ctx, db, proposal, map[string]string{"timeout-player-a": "timeout-ticket-0", "timeout-player-b": "timeout-ticket-1"}, now); err != nil {
t.Fatalf("create proposal: %v", err)
}
// Nobody ever responds; recover the proposal well after its 10s window,
// exactly as a client reconnecting after missing the expiry event would.
afterExpiry := now.Add(domain.ProposalWindow + time.Second)
recovered, err := GetProposal(ctx, db, "timeout-player-a", proposal.ProposalID, afterExpiry)
if err != nil {
t.Fatalf("recover expired proposal: %v", err)
}
if recovered.State != domain.Expired {
t.Fatalf("proposal did not expire: %+v", recovered)
}
var stateA, stateB string
var expiresB time.Time
if err := db.QueryRow(`SELECT state FROM queue_tickets WHERE ticket_id = 'timeout-ticket-0'`).Scan(&stateA); err != nil {
t.Fatal(err)
}
if err := db.QueryRow(`SELECT state, expires_at FROM queue_tickets WHERE ticket_id = 'timeout-ticket-1'`).Scan(&stateB, &expiresB); err != nil {
t.Fatal(err)
}
if stateA != "QUEUED" || stateB != "QUEUED" {
t.Fatalf("timed-out participants left stranded: a=%s b=%s", stateA, stateB)
}
if !expiresB.After(afterExpiry) {
t.Fatalf("requeued ticket expiry %v was not refreshed forward from %v", expiresB, afterExpiry)
}
candidates, err := ListQueuedCandidates(ctx, db, domain.Casual, afterExpiry, 10)
if err != nil {
t.Fatalf("list queued candidates: %v", err)
}
found := map[string]bool{}
for _, candidate := range candidates {
found[candidate.PlayerID] = true
}
if !found["timeout-player-a"] || !found["timeout-player-b"] {
t.Fatalf("requeued players are not visible to the matcher: %+v", candidates)
}
}
func TestPostgreSQLProposalCreationRollsBackPartialClaims(t *testing.T) {
db := openIntegrationPostgres(t)
applyIntegrationMigrations(t, db)