From 1a8161027c3927859fa40df317dd9353228b3de9 Mon Sep 17 00:00:00 2001 From: Toutsu Date: Tue, 2 Jun 2026 07:57:30 +0300 Subject: [PATCH] fix(data): reject stale reschedule snapshots --- .../2026-05-30-completed-game-portfolio.md | 16 +++- ...6-05-30-completed-game-portfolio-design.md | 4 +- ..._completed_game_portfolios_and_reviews.sql | 6 ++ .../Web/PortfolioMigrationPostgresTests.cs | 75 +++++++++++++++++++ .../Web/PortfolioMigrationTests.cs | 1 + 5 files changed, 97 insertions(+), 5 deletions(-) diff --git a/docs/superpowers/plans/2026-05-30-completed-game-portfolio.md b/docs/superpowers/plans/2026-05-30-completed-game-portfolio.md index a7e9a24..4dd33dd 100644 --- a/docs/superpowers/plans/2026-05-30-completed-game-portfolio.md +++ b/docs/superpowers/plans/2026-05-30-completed-game-portfolio.md @@ -80,6 +80,7 @@ - `d762ecc` `fix(data): serialize portfolio future reschedules` - `1d62f69` `fix(data): lock racing portfolio publications` - `ea71448` `fix(data): serialize new-link publication races` +- Current fix cycle: `fix(data): reject stale reschedule snapshots` **Files:** - Create: `tests/GmRelay.Bot.Tests/Web/PortfolioMigrationTests.cs` @@ -271,6 +272,9 @@ public async Task ConcurrentPublishAndFutureReschedule_ShouldNotDeadlockOrCommit [Fact] public async Task ConcurrentNewLinkPublishAndFutureReschedule_ShouldNotCommitInvalidPublicCard() +[Fact] +public async Task RepeatableReadStaleSnapshotFutureReschedule_ShouldBeRejectedWithoutInvalidPublicCard() + [Theory] [InlineData("portfolio_game_sessions")] [InlineData("portfolio_game_masters")] @@ -285,7 +289,7 @@ public async Task RequiredParentCascadeDelete_ShouldFailCommitForPublishedCard(s public async Task ParentCardAndGroupCascadeDeletes_ShouldCommit() ``` -The direct-delete, moved-link, invalid publication, and direct parent-cascade scenarios must expect PostgreSQL `23514` at commit. Every selected linked session must be completed with `scheduled_at < now()`: one future link among multiple selected sessions rejects publication. A final future reschedule must atomically unpublish linked public cards while preserving their first `published_at`; `past -> future -> past` in one transaction must leave the card public. Opposing-order batch reschedules must use an advisory test gate plus `pg_blocking_pids` observation with bounded timeouts, complete without card deadlock, and leave both cards private; do not rely on `pg_sleep` timing. The `READ COMMITTED` concurrency scenarios must launch bounded tasks together, cover both publish/delete lock orders, and prove there is no deadlock, write-skew, or invalid public commit. A session-delete versus future-reschedule race must use the common `sessions` then `portfolio_games` lock order, cover both first-session-lock orders through real blocking transactions, and finish with the card private and session deleted. The publish/reschedule races must finish with the future session committed and the card private, including a new-link draft publication forced behind the post-row-lock advisory gate. The `REPEATABLE READ` scenarios must reject triggered portfolio writes with `0A000`, including both draft-link deletion versus publication commit orders, because a stale snapshot after lock acquisition cannot safely validate the invariant. The parent-card and owning-group cascade scenarios must commit successfully. +The direct-delete, moved-link, invalid publication, and direct parent-cascade scenarios must expect PostgreSQL `23514` at commit. Every selected linked session must be completed with `scheduled_at < now()`: one future link among multiple selected sessions rejects publication. A final future reschedule must atomically unpublish linked public cards while preserving their first `published_at`; `past -> future -> past` in one transaction must leave the card public. Opposing-order batch reschedules must use an advisory test gate plus `pg_blocking_pids` observation with bounded timeouts, complete without card deadlock, and leave both cards private; do not rely on `pg_sleep` timing. The `READ COMMITTED` concurrency scenarios must launch bounded tasks together, cover both publish/delete lock orders, and prove there is no deadlock, write-skew, or invalid public commit. A session-delete versus future-reschedule race must use the common `sessions` then `portfolio_games` lock order, cover both first-session-lock orders through real blocking transactions, and finish with the card private and session deleted. The publish/reschedule races must finish with the future session committed and the card private, including a new-link draft publication forced behind the post-row-lock advisory gate. The `REPEATABLE READ` scenarios must reject triggered portfolio writes with `0A000`, including both draft-link deletion versus publication commit orders and stale-snapshot final-future reschedules after a newly linked publication, because a stale snapshot after lock acquisition cannot safely validate the invariant. The parent-card and owning-group cascade scenarios must commit successfully. - [ ] **Step 3: Run the Task 1 tests to verify RED** @@ -427,6 +431,12 @@ BEGIN WHERE s.id = NEW.id; IF final_scheduled_at >= now() THEN + IF current_setting('transaction_isolation') <> 'read committed' THEN + RAISE EXCEPTION + 'portfolio future reschedule requires read committed isolation' + USING ERRCODE = '0A000'; + END IF; + PERFORM pg.id FROM portfolio_games pg WHERE EXISTS ( @@ -514,7 +524,7 @@ CREATE INDEX ix_portfolio_game_reviews_pending WHERE moderation_status = 'Pending'; ``` -The deferred constraint triggers retain the link-table `ON DELETE CASCADE` behavior. At transaction commit validators acquire the same transaction-level advisory lock and reject a surviving published card when either required link set is empty or any linked session has `scheduled_at >= now()`. The intentionally global lock is appropriate for low-volume portfolio publication writes: under the application default `READ COMMITTED` isolation level it serializes validation, prevents write-skew across distinct child links, and gives multi-card transactions one lock order. PostgreSQL retains stale snapshots under `REPEATABLE READ` and `SERIALIZABLE`, so the guard rejects every triggered portfolio write at those isolation levels with `0A000`. The deferred future-reschedule trigger re-reads the final session row, skips intermediate future values that end in the past, and for a final future value locks all cards linked to any final-future session in `portfolio_games.id` order. It then acquires the publication advisory lock and runs one guarded public-card unpublish update with a fresh `READ COMMITTED` statement snapshot. The row-lock phase deliberately includes committed drafts so a concurrent draft-to-public publication cannot pass validation against the pre-reschedule session snapshot and commit afterward; the post-row-lock advisory phase also serializes a previously invisible concurrent link-add publication without moving the advisory lock above card locks. At `READ COMMITTED`, draft edits, explicit unpublishing, future reschedules, and card or club cascade deletion remain valid. Normal session-deletion handlers use the same `sessions` then `portfolio_games` lock order: explicitly lock the target session row, unpublish linked cards, then delete the session. +The deferred constraint triggers retain the link-table `ON DELETE CASCADE` behavior. At transaction commit validators acquire the same transaction-level advisory lock and reject a surviving published card when either required link set is empty or any linked session has `scheduled_at >= now()`. The intentionally global lock is appropriate for low-volume portfolio publication writes: under the application default `READ COMMITTED` isolation level it serializes validation, prevents write-skew across distinct child links, and gives multi-card transactions one lock order. PostgreSQL retains stale snapshots under `REPEATABLE READ` and `SERIALIZABLE`, so the guard rejects every triggered portfolio write at those isolation levels with `0A000`. The deferred future-reschedule trigger re-reads the final session row, skips intermediate future values that end in the past, and rejects final-future reschedules outside `READ COMMITTED` with `0A000`. Under `READ COMMITTED`, it locks all cards linked to any final-future session in `portfolio_games.id` order. It then acquires the publication advisory lock and runs one guarded public-card unpublish update with a fresh statement snapshot. The row-lock phase deliberately includes committed drafts so a concurrent draft-to-public publication cannot pass validation against the pre-reschedule session snapshot and commit afterward; the post-row-lock advisory phase also serializes a previously invisible concurrent link-add publication without moving the advisory lock above card locks. At `READ COMMITTED`, draft edits, explicit unpublishing, future reschedules, and card or club cascade deletion remain valid. Normal session-deletion handlers use the same `sessions` then `portfolio_games` lock order: explicitly lock the target session row, unpublish linked cards, then delete the session. - [ ] **Step 5: Lock sessions before explicitly unpublishing linked cards in both session-deletion handlers** @@ -560,7 +570,7 @@ Run: dotnet test tests/GmRelay.Bot.Tests/GmRelay.Bot.Tests.csproj --filter "FullyQualifiedName~PortfolioMigrationTests|FullyQualifiedName~PortfolioMigrationPostgresTests|FullyQualifiedName~PortfolioSessionDeletionSourceTests|FullyQualifiedName~PortfolioSchemaGateSourceTests" ``` -Expected: PASS, including PostgreSQL 17 migration application, rejected direct required-link deletes, rejected moved links and session/player cascades, rejected publication with any future linked session, automatic unpublish with preserved `published_at` after final future reschedule, preserved public state after `past -> future -> past`, opposing-order batch reschedules without card deadlock, bounded `READ COMMITTED` publish/delete in both commit orders, existing-link and new-link publish/reschedule races, session-delete/reschedule serialization in both first-lock orders, and distinct-link deletion without deadlock, write-skew, or invalid public commit, rejected `REPEATABLE READ` triggered writes including both draft-delete versus publish commit orders, successful parent-card and owning-group cascades, Discord identity scoping, and Compose/Aspire HTTP health gating with a non-proxied bot endpoint and matching `gmrelaydb` resource name. +Expected: PASS, including PostgreSQL 17 migration application, rejected direct required-link deletes, rejected moved links and session/player cascades, rejected publication with any future linked session, automatic unpublish with preserved `published_at` after final future reschedule, preserved public state after `past -> future -> past`, opposing-order batch reschedules without card deadlock, bounded `READ COMMITTED` publish/delete in both commit orders, existing-link and new-link publish/reschedule races, session-delete/reschedule serialization in both first-lock orders, and distinct-link deletion without deadlock, write-skew, or invalid public commit, rejected `REPEATABLE READ` triggered writes including both draft-delete versus publish commit orders and stale-snapshot final-future reschedules, successful parent-card and owning-group cascades, Discord identity scoping, and Compose/Aspire HTTP health gating with a non-proxied bot endpoint and matching `gmrelaydb` resource name. - [ ] **Step 7: Commit** diff --git a/docs/superpowers/specs/2026-05-30-completed-game-portfolio-design.md b/docs/superpowers/specs/2026-05-30-completed-game-portfolio-design.md index f964ff8..083627f 100644 --- a/docs/superpowers/specs/2026-05-30-completed-game-portfolio-design.md +++ b/docs/superpowers/specs/2026-05-30-completed-game-portfolio-design.md @@ -81,7 +81,7 @@ Application validation additionally requires at least one linked session, every Deferred database constraint triggers validate the same invariant at transaction commit after a card transitions to public, a session link is inserted, deleted, moved, or repointed, or a required master link is deleted or moved. They raise a check-violation error if a published card would commit without both required link sets or with any linked session where `scheduled_at >= now()`. Before checking state, each validator acquires the same transaction-level PostgreSQL advisory lock, `pg_advisory_xact_lock(20260530, 108)`. Portfolio publication writes are low volume, so this intentionally global lock serializes invariant validation with one lock order, prevents write-skew under the application default `READ COMMITTED` isolation level, and avoids multi-card deadlocks. PostgreSQL keeps a stale snapshot after waiting under `REPEATABLE READ` or `SERIALIZABLE`, so the guard rejects every triggered portfolio write at those levels; callers must use `READ COMMITTED` for portfolio mutations. -A deferred `sessions.scheduled_at` trigger atomically unpublishes linked public cards when a completed session is finally rescheduled into the future, preserving the first `published_at`. Because deferred row triggers retain their event-time `NEW`, the trigger re-reads the final `sessions.scheduled_at` before acting. For a final future value it takes row locks for all cards linked to any final-future session in `portfolio_games.id` order, including committed drafts. It then acquires the publication advisory lock and unpublishes matching public cards in a guarded update with a fresh `READ COMMITTED` statement snapshot. Including drafts prevents a concurrent draft-to-public publication from validating against the pre-reschedule session snapshot and committing afterward. Taking the shared advisory lock after card rows, but before the guarded update, also serializes a previously invisible concurrent link-add publication without reintroducing the card/advisory lock inversion. Session mutation paths use `sessions` before linked `portfolio_games`; normal session-deletion handlers explicitly lock the target session row, unpublish linked cards in the same transaction, and only then delete the session. The link foreign keys retain `ON DELETE CASCADE`; when the card itself or its owning club is deleted at `READ COMMITTED`, deferred validation sees no surviving published card and remains harmless. +A deferred `sessions.scheduled_at` trigger atomically unpublishes linked public cards when a completed session is finally rescheduled into the future, preserving the first `published_at`. Because deferred row triggers retain their event-time `NEW`, the trigger re-reads the final `sessions.scheduled_at` before acting. It rejects final-future reschedules outside `READ COMMITTED` with `0A000`, because the unpublish pass requires fresh statement snapshots. Under `READ COMMITTED`, it takes row locks for all cards linked to any final-future session in `portfolio_games.id` order, including committed drafts. It then acquires the publication advisory lock and unpublishes matching public cards in a guarded update with a fresh statement snapshot. Including drafts prevents a concurrent draft-to-public publication from validating against the pre-reschedule session snapshot and committing afterward. Taking the shared advisory lock after card rows, but before the guarded update, also serializes a previously invisible concurrent link-add publication without reintroducing the card/advisory lock inversion. Session mutation paths use `sessions` before linked `portfolio_games`; normal session-deletion handlers explicitly lock the target session row, unpublish linked cards in the same transaction, and only then delete the session. The link foreign keys retain `ON DELETE CASCADE`; when the card itself or its owning club is deleted at `READ COMMITTED`, deferred validation sees no surviving published card and remains harmless. ### `portfolio_game_sessions` @@ -356,7 +356,7 @@ Follow TDD for production changes. ### Schema And Contracts - Migration source-contract tests assert the four new tables, format constraint, publication guard, case-insensitive slug uniqueness, group and GM-profile indexes, card-oriented pending-review index, completed-session validator, deferred future-reschedule unpublish trigger, session-first deletion locks, and the AppHost HTTP health gate. -- PostgreSQL integration tests apply migrations V001 through V029 to `postgres:17-alpine` and cover direct invalid link removal, moved links, direct session/player cascades, explicit session-lock then unpublish then session deletion, delete/reschedule lock ordering in both first-lock orders, rejection of publication when any linked session is future, automatic unpublish with preserved `published_at` after future reschedule, `past -> future -> past` final-state handling, opposing-order batch future reschedules without card deadlock using an observed advisory test gate instead of timing sleeps, existing-link and new-link draft publication/reschedule races, both bounded publish/delete commit orders, concurrent removal of distinct required links without write-skew or deadlock under `READ COMMITTED`, rejection of equivalent `REPEATABLE READ` writes including both draft-delete versus publish commit orders, and parent/card cascade deletion. +- PostgreSQL integration tests apply migrations V001 through V029 to `postgres:17-alpine` and cover direct invalid link removal, moved links, direct session/player cascades, explicit session-lock then unpublish then session deletion, delete/reschedule lock ordering in both first-lock orders, rejection of publication when any linked session is future, automatic unpublish with preserved `published_at` after future reschedule, `past -> future -> past` final-state handling, opposing-order batch future reschedules without card deadlock using an observed advisory test gate instead of timing sleeps, existing-link and new-link draft publication/reschedule races, both bounded publish/delete commit orders, concurrent removal of distinct required links without write-skew or deadlock under `READ COMMITTED`, rejection of equivalent `REPEATABLE READ` writes including both draft-delete versus publish commit orders and stale-snapshot final-future reschedules, and parent/card cascade deletion. - Public DTO reflection/source tests assert that private identifiers and physical storage paths are absent. - Existing showcase tests continue to assert the future-session catalog boundary. diff --git a/src/GmRelay.Bot/Migrations/V029__add_completed_game_portfolios_and_reviews.sql b/src/GmRelay.Bot/Migrations/V029__add_completed_game_portfolios_and_reviews.sql index 4eab31f..7e6334d 100644 --- a/src/GmRelay.Bot/Migrations/V029__add_completed_game_portfolios_and_reviews.sql +++ b/src/GmRelay.Bot/Migrations/V029__add_completed_game_portfolios_and_reviews.sql @@ -128,6 +128,12 @@ BEGIN WHERE s.id = NEW.id; IF final_scheduled_at >= now() THEN + IF current_setting('transaction_isolation') <> 'read committed' THEN + RAISE EXCEPTION + 'portfolio future reschedule requires read committed isolation' + USING ERRCODE = '0A000'; + END IF; + PERFORM pg.id FROM portfolio_games pg WHERE EXISTS ( diff --git a/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationPostgresTests.cs b/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationPostgresTests.cs index 6286fab..2ae9621 100644 --- a/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationPostgresTests.cs +++ b/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationPostgresTests.cs @@ -631,6 +631,81 @@ public sealed class PortfolioMigrationPostgresTests(PortfolioMigrationPostgresFi ])); } + [Fact] + public async Task RepeatableReadStaleSnapshotFutureReschedule_ShouldBeRejectedWithoutInvalidPublicCard() + { + var database = await fixture.CreateMigratedDatabaseAsync(); + await using var seedConnection = await database.OpenConnectionAsync(); + var seed = await SeedCardAsync(seedConnection, isPublic: false); + var rescheduledSessionId = Guid.NewGuid(); + await ExecuteNonQueryAsync( + seedConnection, + """ + INSERT INTO sessions (id, group_id, title, join_link, scheduled_at) + VALUES (@sessionId, @groupId, 'Completed Session', 'https://example.test/session', now() - interval '1 day'); + """, + parameters: + [ + new NpgsqlParameter("sessionId", rescheduledSessionId), + new NpgsqlParameter("groupId", seed.GroupId) + ]); + await using var rescheduleConnection = await database.OpenConnectionAsync(); + await using var publishConnection = await database.OpenConnectionAsync(); + await using var rescheduleTransaction = await rescheduleConnection.BeginTransactionAsync(IsolationLevel.RepeatableRead); + + Assert.Equal(0, await ExecuteScalarAsync( + rescheduleConnection, + """ + SELECT COUNT(*) + FROM portfolio_game_sessions + WHERE portfolio_game_id = @portfolioGameId + AND session_id = @sessionId + """, + rescheduleTransaction, + new NpgsqlParameter("portfolioGameId", seed.PortfolioGameId), + new NpgsqlParameter("sessionId", rescheduledSessionId))); + + await using (var publishTransaction = await publishConnection.BeginTransactionAsync()) + { + await ExecuteNonQueryAsync( + publishConnection, + """ + INSERT INTO portfolio_game_sessions (portfolio_game_id, session_id) + VALUES (@portfolioGameId, @sessionId); + + UPDATE portfolio_games + SET is_public = true, + published_at = COALESCE(published_at, now()), + updated_at = now() + WHERE id = @portfolioGameId + """, + publishTransaction, + new NpgsqlParameter("portfolioGameId", seed.PortfolioGameId), + new NpgsqlParameter("sessionId", rescheduledSessionId)); + await publishTransaction.CommitAsync().WaitAsync(CommandTimeout); + } + + Assert.Equal(1, await RescheduleSessionAsync( + rescheduleConnection, + rescheduleTransaction, + rescheduledSessionId)); + + var exception = await Assert.ThrowsAsync( + () => rescheduleTransaction.CommitAsync().WaitAsync(CommandTimeout)); + + Assert.Equal(PostgresErrorCodes.FeatureNotSupported, exception.SqlState); + + await using var verificationConnection = await database.OpenConnectionAsync(); + Assert.True(await ExecuteScalarAsync( + verificationConnection, + "SELECT is_public FROM portfolio_games WHERE id = @portfolioGameId", + parameters: new NpgsqlParameter("portfolioGameId", seed.PortfolioGameId))); + Assert.False(await ExecuteScalarAsync( + verificationConnection, + "SELECT scheduled_at >= now() FROM sessions WHERE id = @sessionId", + parameters: new NpgsqlParameter("sessionId", rescheduledSessionId))); + } + [Theory] [InlineData(true)] [InlineData(false)] diff --git a/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationTests.cs b/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationTests.cs index d1f9ce5..bd6ad29 100644 --- a/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationTests.cs +++ b/tests/GmRelay.Bot.Tests/Web/PortfolioMigrationTests.cs @@ -48,6 +48,7 @@ public sealed class PortfolioMigrationTests Assert.Contains("CREATE FUNCTION unpublish_public_portfolio_games_for_future_session() RETURNS TRIGGER LANGUAGE plpgsql", normalizedMigration, StringComparison.Ordinal); Assert.Contains("SELECT s.scheduled_at INTO final_scheduled_at FROM sessions s WHERE s.id = NEW.id;", normalizedMigration, StringComparison.Ordinal); Assert.Contains("IF final_scheduled_at >= now() THEN", normalizedMigration, StringComparison.Ordinal); + Assert.Contains("IF final_scheduled_at >= now() THEN IF current_setting('transaction_isolation') <> 'read committed' THEN RAISE EXCEPTION 'portfolio future reschedule requires read committed isolation' USING ERRCODE = '0A000'; END IF; PERFORM pg.id", normalizedMigration, StringComparison.Ordinal); Assert.Contains("PERFORM pg.id FROM portfolio_games pg WHERE EXISTS", normalizedMigration, StringComparison.Ordinal); Assert.Contains("ORDER BY pg.id FOR UPDATE OF pg;", normalizedMigration, StringComparison.Ordinal); Assert.Contains("ORDER BY pg.id FOR UPDATE OF pg; PERFORM pg_advisory_xact_lock(20260530, 108); UPDATE portfolio_games pg SET is_public = false", normalizedMigration, StringComparison.Ordinal);