feat(database): store gameplay replays in compact form
Build and Push Docker Container / build-and-push (push) Successful in 3m52s

- Add compact storage package: codec, records, hydrate, replay blobs, cache.
- Running games write game_turns and snake_states keyed by integer ids.
- Encode moves as 1-byte codes and bodies as head plus step codes.
- Store food and hazards only when they changed since the previous turn.
- Strip reasoning fields that duplicate stored values and restore on read.
- Pack finished games into one zstd blob per game in game_replays.
- Merge late turns into packed blobs during the stale-game sweep.
- Extract SQLite and PostgreSQL schemas into dedicated modules.
- Add read/import game bundle and list_game_ids to the backend template.
- Add legacy readers and converter for the old turns/snake_turns layout.
- Add migrate_gameplay_to_compact.py with in-place or cross-DB migration.
- Verify every migrated game and keep legacy rows on failure.
- Support --since, --minimum-quality and guarded --drop-legacy.
- Add just recipe migrate-gameplay-postgres.
- Rewrite merge script to copy game by game via backend bundles.
- Move benchmark state loading into benchmark_states for both backends.
- Update PostgreSQL cleanup script to the new replay tables.
- Drop sqlite-zstd build stages from the Dockerfile.
- Remove old migration scripts, normalized_turn and their tests.
- Add tests for compact storage, schema, legacy migration and PostgreSQL.
- Document the compact layout and migration workflow in the README.
This commit is contained in:
2026-11-05 00:02:56 +01:00
parent 4403978537
commit 39a7a53873
41 changed files with 2779 additions and 2493 deletions
+20 -14
View File
@@ -21,20 +21,20 @@ async def cleanup(dsn: str, older_than_days: int, dry_run: bool, vacuum: bool) -
AND COALESCE(ended_at, started_at) < $1
""", cutoff))
rows = await connection.fetchrow("""
WITH candidates AS (
SELECT game_id, gid FROM games
WHERE has_replay
AND quality_status = 'low_quality'
AND COALESCE(ended_at, started_at) < $1
)
SELECT
(SELECT count(*) FROM turns t JOIN games g USING (game_id)
WHERE g.has_replay AND g.quality_status = 'low_quality'
AND COALESCE(g.ended_at, g.started_at) < $1) AS turns,
(SELECT count(*) FROM snake_turns t JOIN games g USING (game_id)
WHERE g.has_replay AND g.quality_status = 'low_quality'
AND COALESCE(g.ended_at, g.started_at) < $1) AS snake_turns,
(SELECT count(*) FROM game_snakes t JOIN games g USING (game_id)
WHERE g.has_replay AND g.quality_status = 'low_quality'
AND COALESCE(g.ended_at, g.started_at) < $1) AS game_snakes
(SELECT count(*) FROM game_replays r JOIN candidates c USING (gid)) AS replays,
(SELECT count(*) FROM game_turns t JOIN candidates c USING (gid)) AS turns,
(SELECT count(*) FROM game_snakes s JOIN candidates c USING (game_id)) AS game_snakes
""", cutoff)
print(
f"candidates before {cutoff.isoformat()}: games={candidates:,}, "
f"turns={rows['turns']:,}, snake_turns={rows['snake_turns']:,}, "
f"replays={rows['replays']:,}, running turns={rows['turns']:,}, "
f"game_snakes={rows['game_snakes']:,}"
)
if dry_run or candidates == 0:
@@ -50,8 +50,13 @@ async def cleanup(dsn: str, older_than_days: int, dry_run: bool, vacuum: bool) -
FOR UPDATE
""", cutoff)
ids = [row["game_id"] for row in game_ids]
await connection.execute("DELETE FROM snake_turns WHERE game_id = ANY($1::text[])", ids)
await connection.execute("DELETE FROM turns WHERE game_id = ANY($1::text[])", ids)
# snake_states rows cascade from game_snakes.
await connection.execute("""
DELETE FROM game_replays WHERE gid IN (SELECT gid FROM games WHERE game_id = ANY($1::text[]))
""", ids)
await connection.execute("""
DELETE FROM game_turns WHERE gid IN (SELECT gid FROM games WHERE game_id = ANY($1::text[]))
""", ids)
await connection.execute("DELETE FROM game_snakes WHERE game_id = ANY($1::text[])", ids)
await connection.execute("""
UPDATE games
@@ -62,8 +67,9 @@ async def cleanup(dsn: str, older_than_days: int, dry_run: bool, vacuum: bool) -
if vacuum:
await connection.execute("VACUUM (ANALYZE) games")
await connection.execute("VACUUM (ANALYZE) game_snakes")
await connection.execute("VACUUM (ANALYZE) turns")
await connection.execute("VACUUM (ANALYZE) snake_turns")
await connection.execute("VACUUM (ANALYZE) game_replays")
await connection.execute("VACUUM (ANALYZE) game_turns")
await connection.execute("VACUUM (ANALYZE) snake_states")
print("vacuum/analyze complete")
finally:
await connection.close()