diff --git a/Game/scripts/control_plane_client.gd b/Game/scripts/control_plane_client.gd index fd9f05f8..7973406e 100644 --- a/Game/scripts/control_plane_client.gd +++ b/Game/scripts/control_plane_client.gd @@ -308,6 +308,7 @@ func _on_request_completed(result: HTTPRequest.Result, response_code: int, _head return if response_code < 200 or response_code >= 300: var detail := String(parsed.get("error", "request rejected")) + var recover_proposal_after_conflict := response_code == HTTPClient.RESPONSE_CONFLICT and (operation == "proposal_accept" or operation == "proposal_decline") and not state.proposal_id.is_empty() if response_code == HTTPClient.RESPONSE_UNAUTHORIZED: access_token = "" auth_expired = true @@ -328,6 +329,9 @@ func _on_request_completed(result: HTTPRequest.Result, response_code: int, _head else: state.set_notice(detail) request_failed.emit(operation, response_code, detail) + if recover_proposal_after_conflict: + _pending_resync_resource_id = state.proposal_id + call_deferred("_run_pending_resync") return var payload: Dictionary = parsed if operation == "steam_session": diff --git a/Game/tests/control_plane_proposal_smoke.gd b/Game/tests/control_plane_proposal_smoke.gd index ea58de4a..610ca19a 100644 --- a/Game/tests/control_plane_proposal_smoke.gd +++ b/Game/tests/control_plane_proposal_smoke.gd @@ -119,12 +119,8 @@ func _send_accept() -> void: func _on_request_failed(operation: String, http_code: int, detail: String) -> void: if _finished: return - if operation == "proposal_accept" and http_code == 409 and not ControlPlaneClient.state.proposal_id.is_empty(): - print("SMOKE[%s]: concurrent accept conflicted at an old revision; recovering the authoritative proposal..." % _role) - _accept_sent = false - var err := ControlPlaneClient.recover_proposal(ControlPlaneClient.state.proposal_id) - if err != OK and err != ERR_BUSY: - _finish(false, "proposal recovery after concurrent accept failed to start: %s" % error_string(err)) + if operation == "proposal_accept" and http_code == HTTPClient.RESPONSE_CONFLICT: + print("SMOKE[%s]: concurrent accept conflicted; ControlPlaneClient is recovering the authoritative proposal..." % _role) return _finish(false, "%s failed: http=%d detail=%s" % [operation, http_code, detail]) diff --git a/multiplayer-next.md b/multiplayer-next.md index 0b0e0c2b..34522028 100644 --- a/multiplayer-next.md +++ b/multiplayer-next.md @@ -1237,7 +1237,7 @@ the local/CI/community transport, not a silent production fallback. | 8.40 `[D:8.3,8.14]` | **IN PROGRESS.** Pure Go revisioned replica reducer rejects gaps for REST resync, makes duplicate/out-of-order events idempotent, and resumes from the authoritative snapshot revision; authenticated queue-ticket recovery now has an owner-checked REST read; Godot client projection persists non-secret ticket/proposal state, forces authoritative recovery after restart, and can replay a lost queue-create response with the original ticket/idempotency key; the Go API now exposes an authenticated `/v1/events` WebSocket with bounded per-player queues, strict upgrade/vocabulary validation and REST-resync-safe slow-client failure; Godot `ControlPlaneClient` can connect to the stream using Godot 4.7's handshake-header API, consume validated events, automatically reconnect with bounded backoff, and trigger REST recovery on projection gaps and stream return, including a deferred recovery when an event arrives during an in-flight HTTP mutation; `OutboxDispatcher` now provides ordered at-least-once delivery after durable commit; assignment recovery events carry the durable assignment revision without leaking it into REST JSON; prediction startup now distinguishes the sequence-0 warm-up acknowledgement from genuine missing/evicted history, preventing a false hard-snap during a live match; proposal creation now writes one durable targeted `proposal_changed` outbox event per proposal aggregate revision, and both production `cmd/control-plane` and the test-only API harness dispatch only that event type to authenticated participants, leaving result events for their separate consumer | `server/domain/sync.go`, `server/api/events.go`, `server/api/outbox.go`, `server/api/service.go`, `server/store/outbox.go`, `server/store/proposal_sql.go`, `server/cmd/control-plane`, `server/cmd/testkit-api`, `service_test.go`, `outbox_test.go`, `matchmaking_state.gd`, `control_plane_client.gd`, `local_prediction_history.gd`, `net_ship_predictor.gd` and tests cover gap, snapshot, replay, same-revision conflict, owner-only ticket recovery, expired-ticket terminal handling, malformed restart snapshots, API-level duplicate-create replay/conflict, authenticated handshake/key rejection, targeted event delivery, exactly-once slow-subscriber closure, invalid-event rejection, delivery-before-ack failure ordering, assignment event/response revision separation, prediction warm-up/hard-resync separation, deferred proposal recovery and proposal outbox filtering/delivery failures; Godot 4.7.1 headless project parse and 150-test unit harness pass with compatibility rendering, and a two-process ENet authoritative match smoke passes spawn, movement, prediction, 0% snapshot loss and 0 hard snaps; `cmd/control-plane` provides a signal-bound API role, `cmd/matcher` now supports casual and explicitly enabled ranked roles with durable identity lookup, and `cmd/maintenance` provides bounded season maintenance. **Live multi-process control-plane/game verification now exists**: `scripts/verify_control_plane_integration.sh` runs a real `postgres:17-alpine`, the real `api.Service` (via the new test-only `server/cmd/testkit-api`, wired identically to `cmd/control-plane` except for a fake Steam login — see §8.7), and a real headless Godot client (`control_plane_smoke.gd`) round-tripping login → `fetch_ranked_profile` (expect 404, §8.22) → `queue_create` → heartbeat → `cancel_queue` over an actual network connection — the first time this boundary was exercised end to end rather than against a mock on either side. **The two-player proposal extension now also passes**: `scripts/verify_control_plane_proposal_integration.sh` starts isolated PostgreSQL, the real matcher and testkit API, launches two headless Godot clients, seeds deterministic RTT projections, observes the real WebSocket `OPEN` proposal, accepts from both clients, and verifies both durable tickets plus the proposal reach `ACCEPTED` (including authoritative recovery when the concurrent revision advances). Allocator and Redis fan-out live verification remain | | 8.41 `[D:7.8,8.9,8.31,8.40]` | **IN PROGRESS.** Authenticated `GET /v1/assignments/{matchId}` now exposes only a validated, player-scoped assignment view including the hosted endpoint; Godot `AssignmentState`/`ControlPlaneClient.fetch_assignment()` bind the response to the authenticated player, recheck expiry, validate and retain the endpoint, and `connect_to_assignment()` now starts only the validated ENet/Steam transport after assignment readiness; the opaque join authorisation is carried in the MatchNet hello payload rather than the endpoint URL; allocated Godot servers now fail closed unless an operator-mounted JSON roster of control-plane signed envelopes and an HMAC-SHA256 key are present, and MatchNet verifies the canonical Go claim bytes, checks exact token membership plus match/server/protocol/slot/expiry claims before admitting a peer, rejects concurrent reuse of an active token, tracks server-owned reconnect generations across the 60-second reclaim window, fences expired reclaims and invalidates old peers; migration 0002 and the Go store adapter now persist/recover the complete player-scoped assignment projection with conflict-safe identical replay; `AssignmentProviderFromStore` wires that durable projection into the API injection point; `SaveAssignments` publishes a complete signed roster atomically instead of allowing partial player visibility; `SaveVerifiedAssignmentRoster` rechecks signed claims before deriving player rows; live authenticated Godot/PostgreSQL assignment verification now exists via `scripts/verify_assignment_integration.sh`, which seeds a durable player-scoped `ASSIGNMENT_READY` row behind the real testkit API and verifies the returned endpoint/join authorisation over HTTP/JSON (including the live numeric-decoding boundary) | `server/api/service.go`, `store_adapters.go`, `service_test.go`, `assignment_state.gd`, `control_plane_client.gd`, `match_net.gd`, `server_boot.gd`, `server_config.gd`, `test_assignment_state.gd`, `test_control_plane_client.gd`, `test_match_net.gd`, `server/contracts/v1/openapi.json`, `server/migrations/0002_assignments.sql` and `server/store/assignment_sql.go` cover participant/identity/expiry/shape/transport/endpoint boundaries, player-scoped schema keys, expiry-filtered reads, assignment upsert conflict handling, atomic batch validation, signed-claim binding, strict endpoint splitting, allowlisted claim rejection, canonical HMAC interoperability, forged-signature rejection, duplicate active-token rejection, reclaim generation/expiry behavior and 150-test Godot compatibility coverage; the three-process disconnect/reclaim smoke passes ship retention, replacement drive and old-peer invalidation; SDR relay-ticket installation and live allocated-token process integration remain | | 8.42 `[D:8.22,8.23,8.24,8.40]` | **IN PROGRESS.** `RankedProfileState` and `ControlPlaneClient.fetch_ranked_profile()` expose the backend-authoritative rating/RD/volatility/games/tier/provisional/season view; matchmaking UI displays provisional/tier status without client-side rating math; runnable API binaries now wire the backend-owned default tier policy; live authenticated profile verification now exists via `scripts/verify_ranked_profile_integration.sh`, which seeds a durable rating and verifies the populated profile over real PostgreSQL, Go HTTP, and Godot JSON | `test_control_plane_client.gd` validates profile shape, numeric safety and provisional display; the real populated profile path now covers durable rating/games/tier/provisional decoding and caught the missing runtime tier-policy wiring; committed revision after reconnect, abandon status and season countdown remain dependent on live auth/backend events and Godot runtime verification | -| 8.43 `[D:8.39,8.40,8.41]` | **IN PROGRESS.** Matchmaking client now distinguishes expired queue recovery, session expiry, missing records and retryable control-plane outages; a 401 clears the in-memory token, emits `session_expired` and disables retry until a new session is configured; terminal messages remain visible and active searches are not falsely failed on transient errors | `MatchmakingState` and `ControlPlaneClient` tests cover explicit expiry and the existing terminal/retry-safe state paths; decline, version mismatch, regional outage retry UI, failed reconnect, duplicate-action recovery and live Godot verification remain | +| 8.43 `[D:8.39,8.40,8.41]` | **IN PROGRESS.** Matchmaking client now distinguishes expired queue recovery, session expiry, missing records and retryable control-plane outages; a 401 clears the in-memory token, emits `session_expired` and disables retry until a new session is configured; terminal messages remain visible and active searches are not falsely failed on transient errors; stale proposal accept/decline conflicts now automatically schedule an authoritative proposal recovery instead of requiring each UI caller to implement 409 handling | `MatchmakingState` and `ControlPlaneClient` tests cover explicit expiry and the existing terminal/retry-safe state paths; the real two-player proposal smoke now exercises the client-owned conflict-recovery path; decline, version mismatch, regional outage retry UI, failed reconnect, duplicate-action recovery beyond proposals and broader live Godot verification remain | #### 8F — Observability, verification, cost and rollout