diff --git a/Dockerfile b/Dockerfile index 3584ff85..98d98c4e 100644 --- a/Dockerfile +++ b/Dockerfile @@ -58,6 +58,7 @@ RUN go mod download COPY server/ ./ RUN CGO_ENABLED=0 go build -o /opt/cosmic-clash/game-server-supervisor ./cmd/game-server-supervisor RUN CGO_ENABLED=0 go build -o /opt/cosmic-clash/testkit-api ./cmd/testkit-api +RUN CGO_ENABLED=0 go build -o /opt/cosmic-clash/matcher ./cmd/matcher # Agones-allocated fleet image: the same dedicated-server export as `server` # (unchanged above; make verify-phase6 exercises that target exactly as @@ -78,3 +79,9 @@ COPY --from=supervisor-build /opt/cosmic-clash/testkit-api /opt/cosmic-clash/tes COPY server/migrations /opt/cosmic-clash/migrations RUN chmod 0755 /opt/cosmic-clash/testkit-api ENTRYPOINT ["/opt/cosmic-clash/testkit-api"] + +FROM server AS matcher +COPY --from=supervisor-build /opt/cosmic-clash/matcher /opt/cosmic-clash/matcher +COPY server/migrations /opt/cosmic-clash/migrations +RUN chmod 0755 /opt/cosmic-clash/matcher +ENTRYPOINT ["/opt/cosmic-clash/matcher"] diff --git a/compose.allocated-smoke.yml b/compose.allocated-smoke.yml index 73b550ed..408913f2 100644 --- a/compose.allocated-smoke.yml +++ b/compose.allocated-smoke.yml @@ -25,6 +25,17 @@ services: ports: - "18080:8080" + matcher: + build: + context: . + target: matcher + environment: + COSMIC_CLASH_POSTGRES_DSN: postgres://cosmic_clash_test:cosmic_clash_test@database:5432/cosmic_clash_test?sslmode=disable + command: ["--dsn=postgres://cosmic_clash_test:cosmic_clash_test@database:5432/cosmic_clash_test?sslmode=disable", "--migrations=/opt/cosmic-clash/migrations", "--playlist=casual", "--size=6", "--interval=1s"] + depends_on: + database: + condition: service_healthy + game-server: build: context: . diff --git a/multiplayer-next.md b/multiplayer-next.md index 5c00092e..57279e20 100644 --- a/multiplayer-next.md +++ b/multiplayer-next.md @@ -1246,7 +1246,7 @@ the local/CI/community transport, not a silent production fallback. | 8.44 `[D:8.3,8.4,8.28,8.31]` | **LOCAL COMPLETE; PRODUCTION GATE OPEN.** Go observability package encodes queue/proposal/match/server IDs and lifecycle stage while recursively redacting auth/relay tokens and credentials. `Service.Log` is wired to mutation and read routes at every outcome, and `cmd/control-plane` writes those events as JSON lines to stderr | `server/observability/` covers correlation fields, nested secret redaction, content-aware credential canaries and unnamed-event rejection; API tests cover lifecycle event wiring without logging error text. A production metrics/traces backend and dashboard/alert routing remain open; the local logger is intentionally stderr-only | | 8.45 `[D:8.2,8.44]` | **LOCAL COMPLETE; PRODUCTION GATE OPEN.** Go observability package turns the documented RTT, allocation/connect latency, result-success, API-latency and tick/headroom thresholds into executable window checks; the API exporter emits a bounded cumulative latency histogram suitable for querying the documented p95 API SLO | `server/observability/slo.go`, `metrics.go`, `deploy/observability/prometheus-rules.yaml` and adversarial tests cover healthy/violating/empty windows, fixed operation/status labels, cumulative bucket boundaries, arbitrary-path cardinality safety, and optional API p95/5xx alerts. Production scrape configuration, alert routing, wait/MMR/proposal/flood/cost series and runbooks remain | | 8.46 `[D:8.5,8.7,8.9,8.10,8.14,8.18,8.21,8.23,8.25]` | **IN PROGRESS.** Go unit/race coverage spans the current domain/store/supervisor policies, and fuzz targets now exercise queue input, result payload hashing and revision events | `server/domain/*_test.go`, `server/store/*_test.go`, `server/supervisor/*_test.go`, `server/migrations/*_test.go` and `server/domain/fuzz_test.go` pass normal/race suites; `go test -race ./...` passes across API, domain, migrations, observability, store, supervisor and testkit; `go vet ./...` passes; each of the three declared domain fuzz targets passes a bounded 4-second run; PostgreSQL live migration execution now runs clean (§8.5), and four real-concurrency cases are covered against a live database with `-race`: §8.14's queue-heartbeat revision race, §8.18's two-matcher contested-ticket race, §8.30's cross-allocator-replica capacity race, and §8.21/§8.25's concurrent identical-result-submission race; the "lost Redis" fixture is covered live against a real server (§8.14: real TTL expiry, repair-after-`FLUSHALL`; fake Steam/allocator fixtures are §8.47's testkit, already done). Further transaction fixtures (e.g. concurrent proposal-recovery expiry races, live Redis failover mid-write under load) remain | -| 8.47 `[D:8.7,8.30]` | **IN PROGRESS.** Offline testkit provides deterministic fake Steam verification and fake allocation with forced failure injection; the independent Compose runner now also drives fake-Steam session issuance and the real HTTP queue create/heartbeat/cancel boundary with an idempotency-conflict check | `server/testkit/` covers verified identity/replay, unknown identity, wrong App ID, expiry, no capacity, compatibility-key conflict, idempotent allocation replay and cloud-free forced allocation failure; the Compose API slice is wired into CI, while live exhaustive matrix and production Steam remain | +| 8.47 `[D:8.7,8.30]` | **IN PROGRESS.** Offline testkit provides deterministic fake Steam verification and fake allocation with forced failure injection; the independent Compose runner drives fake-Steam session issuance, real HTTP queue create/heartbeat/cancel, matcher-backed six-player proposal formation/acceptance, and idempotency-conflict checks | `server/testkit/` covers verified identity/replay, unknown identity, wrong App ID, expiry, no capacity, compatibility-key conflict, idempotent allocation replay and cloud-free forced allocation failure; the Compose API/matcher slice is wired into CI, while live exhaustive matrix and production Steam remain | | 8.48 `[D:8.10,8.14,8.17,8.18,8.27,8.31,8.35,8.47]` | **IN PROGRESS.** Offline testkit exercises verified queue projection → ranked six-player proposal → ENet allocation → assignment-ready manifest → certified durable result receipt; `compose.allocated-smoke.yml` independently runs the real testkit API against PostgreSQL and the real game-server supervisor with a generated signed roster, verifying authenticated result, idempotent retry, shutdown acknowledgment, durable receipt/audit rows, and SIGTERM-driven game-process drain | `.github/workflows/allocated-compose.yml` runs `make verify-allocated-compose`. Full queue/proposal/allocation orchestration over HTTP, live Docker evidence from this workspace, and legacy fixture non-regression remain open | | 8.49 `[D:8.25,8.26,8.28,8.29,8.30,8.31,8.35,8.36]` | **IN PROGRESS.** `scripts/verify_kind_agones.sh` creates a disposable kind cluster, installs pinned Agones, loads the real `game-server` image, applies the Fleet in an explicitly separate Agones-only supervisor/UDP readiness mode, and verifies readiness plus allocation of a dynamic UDP endpoint; `.github/workflows/agones-integration.yml` runs it for infrastructure changes and on demand | The cloud-free runner is committed and fails clearly when Docker/kind/Helm are unavailable. CI/live evidence for production control-plane registration, roster/no-show, both readiness stages, races, multi-match node, result-pending reconciliation, drain, and rollback remains open | | 8.50 `[D:8.25,8.37,8.43,8.49]` | Network/chaos suite: 100 ms RTT, jitter/loss, client/API/matcher restart, game-pod death, node drain, Redis failover and control-plane loss | System recovers to a defined state; infrastructure-caused cases cannot penalise affected players | diff --git a/scripts/verify_allocated_compose.sh b/scripts/verify_allocated_compose.sh index 791b61ee..9743bf05 100755 --- a/scripts/verify_allocated_compose.sh +++ b/scripts/verify_allocated_compose.sh @@ -94,6 +94,49 @@ curl -fsS -o /dev/null -X POST "$api_url/v1/queue/compose-queue-ticket/cancel" \ -H 'Idempotency-Key: compose-cancel-key-123456' \ -H "If-Match-Revision: $heartbeat_revision" +# Drive six independent authenticated players through the real queue boundary; +# the matcher service consumes the durable rows below and creates the proposal. +match_tokens=() +for player in 1 2 3 4 5 6; do + player_session="$(curl -fsS -X POST "$api_url/v1/session/steam" \ + -H 'Content-Type: application/json' -d "{\"web_api_ticket\":\"compose-match-player-${player}\"}")" + match_tokens+=("$(python3 -c 'import json,sys; print(json.load(sys.stdin)["access_token"])' <<<"$player_session")") + curl -fsS -o /dev/null -X POST "$api_url/v1/queue" \ + -H "Authorization: Bearer ${match_tokens[$((player - 1))]}" \ + -H "Idempotency-Key: compose-match-queue-key-${player}-123456" \ + -H 'Content-Type: application/json' \ + -d "{\"ticket_id\":\"compose-match-ticket-${player}\",\"playlist\":\"casual\",\"client_build\":\"build-1\",\"protocol_version\":1}" +done +"${compose[@]}" exec -T database psql -v ON_ERROR_STOP=1 -U cosmic_clash_test -d cosmic_clash_test -c \ + "UPDATE queue_tickets SET predicted_rtt = '{\"EU\":30}'::jsonb WHERE ticket_id LIKE 'compose-match-ticket-%'" >/dev/null + +proposal_id="" +for attempt in $(seq 1 30); do + proposal_id="$("${compose[@]}" exec -T database psql -At -U cosmic_clash_test -d cosmic_clash_test -c "SELECT proposal_id FROM proposals WHERE state = 'OPEN' ORDER BY created_at DESC LIMIT 1" | tr -d '\r')" + if [[ -n "$proposal_id" ]]; then break; fi + [[ "$attempt" == 30 ]] && { echo "matcher did not create a proposal" >&2; exit 1; } + sleep 1 +done +proposal_json="$(curl -fsS -H "Authorization: Bearer ${match_tokens[0]}" "$api_url/v1/proposals/$proposal_id")" +python3 - "$proposal_json" <<'PY' +import json, sys +proposal = json.loads(sys.argv[1]) +assert proposal["state"] == "OPEN" +assert len(proposal["participants"]) == 6 +print("proposal formation check passed") +PY + +proposal_revision=0 +for player in 1 2 3 4 5 6; do + proposal_json="$(curl -fsS -X POST "$api_url/v1/proposals/$proposal_id/accept" \ + -H "Authorization: Bearer ${match_tokens[$((player - 1))]}" \ + -H "Idempotency-Key: compose-proposal-accept-${player}-123456" \ + -H "If-Match-Revision: $proposal_revision")" + proposal_revision="$(python3 -c 'import json,sys; print(json.load(sys.stdin)["revision"])' <<<"$proposal_json")" +done +[[ "$("${compose[@]}" exec -T database psql -At -U cosmic_clash_test -d cosmic_clash_test -c "SELECT state FROM proposals WHERE proposal_id = '$proposal_id'" | tr -d '\r')" == ACCEPTED ]] +[[ "$("${compose[@]}" exec -T database psql -At -U cosmic_clash_test -d cosmic_clash_test -c "SELECT count(*) FROM matches WHERE state = 'ALLOCATING'" | tr -d '\r')" == 1 ]] + # Model the durable state produced by the allocator, then use the real HTTP # workload authentication and mutation boundaries for every action below. "${compose[@]}" exec -T database psql -v ON_ERROR_STOP=1 -U cosmic_clash_test -d cosmic_clash_test <<'SQL' diff --git a/server/security/test_compose_manifests.py b/server/security/test_compose_manifests.py index 1c204300..c1cf68a0 100644 --- a/server/security/test_compose_manifests.py +++ b/server/security/test_compose_manifests.py @@ -20,6 +20,7 @@ class ComposeManifestTest(unittest.TestCase): def test_allocated_runner_checks_durable_retry_and_shutdown(self): runner = (ROOT / "scripts/verify_allocated_compose.sh").read_text() + allocated = (ROOT / "compose.allocated-smoke.yml").read_text() for marker in ( "/v1/servers/compose-server/result", "compose-result-key-123456", @@ -29,9 +30,12 @@ class ComposeManifestTest(unittest.TestCase): "/v1/session/steam", "compose-queue-key-123456", "/v1/queue/compose-queue-ticket/heartbeat", + "/v1/proposals/$proposal_id/accept", + "compose-match-ticket-", "down --volumes --remove-orphans", ): self.assertIn(marker, runner) + self.assertIn("target: matcher", allocated) if __name__ == "__main__":