PC3 Phase 3.1: hermetic backend tests + fresh-clone boot check + CI workflow

- backend/tests/conftest.py: pytest_configure brings up an ephemeral
  Postgres via docker compose + runs migrations when DATABASE_URL isn't
  already reachable, and tears it down after. `cd backend && pytest` now
  works from a clean checkout with zero manual setup (72 passed in ~28s);
  no docker and no DB -> the whole suite skips with a clear message instead
  of erroring 60+ times.
- scripts/verify_fresh_clone.sh: exports a pristine tree (git archive, so no
  .godot), imports from scratch, headless-boots the main menu + game scene,
  fails on any SCRIPT ERROR / failed autoload. Catches the stale-class-cache
  class of bug. PASS.
- run_checkpoint_tests.py runs both the 2p multiplayer test and the
  fresh-clone check.
- .forgejo/workflows/checkpoint.yml + docs/ci.md: the CI workflow (runs the
  checkpoint suite on push/PR) and how to enable it -- it needs a Forgejo
  Actions `host` runner registered on the AGP box, a one-time operator step.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015jtxAiu5dAW4WxCNdGkrkJ
This commit is contained in:
2026-09-05 22:11:53 +00:00
parent 50c6a31c25
commit 855311e731
5 changed files with 238 additions and 16 deletions
+103 -16
View File
@@ -1,17 +1,25 @@
"""Shared pytest fixtures.
"""Shared pytest fixtures + hermetic-DB bootstrap.
The auth integration tests hit the *real* Postgres database (per
``DATABASE_URL``), so they persist data between runs. Without cleanup a
second run of the suite fails with 409 conflicts because the users it
registered on the first run already exist. The session-scoped fixture below
truncates all application tables once before the first test, making the suite
re-runnable.
The integration tests hit a real Postgres (Postgres-specific types: JSONB,
native ENUMs). To make ``cd backend && pytest`` work from a clean checkout
with no manual setup, ``pytest_configure`` below brings up an ephemeral
Postgres via docker compose and runs the migrations IF ``DATABASE_URL`` is
not already pointing at a reachable database. When it is (dev loop, or the
checkpoint runner which stands the DB up itself), that path is skipped and
the existing database is reused.
Truncation order doesn't strictly matter because ``CASCADE`` follows foreign
keys, but the tables are listed explicitly for clarity.
If Docker isn't available and no DB is reachable, the whole DB-backed suite
is skipped with a clear message rather than erroring out 60+ times.
"""
import asyncio
import os
import socket
import subprocess
import sys
import time
from pathlib import Path
from urllib.parse import urlsplit
import pytest
from sqlalchemy import text
@@ -24,17 +32,100 @@ from app.main import app
TEST_TABLES = ("avatar_loadouts", "assets", "worlds", "sessions", "refresh_tokens", "users")
BACKEND_DIR = Path(__file__).resolve().parents[1]
_COMPOSE_PROJECT = "agp-pytest"
_EPHEMERAL_PG_PORT = 25432
# Set by _ensure_database() when it starts a container it owns; torn down in
# pytest_unconfigure.
_started_container = False
_db_unavailable_reason: str | None = None
def _port_open(host: str, port: int, timeout: float = 1.0) -> bool:
try:
with socket.create_connection((host, port), timeout=timeout):
return True
except OSError:
return False
def _db_reachable(url: str) -> bool:
parts = urlsplit(url)
return _port_open(parts.hostname or "localhost", parts.port or 5432)
def _run(cmd: list[str], **kw) -> subprocess.CompletedProcess:
return subprocess.run(cmd, cwd=BACKEND_DIR, capture_output=True, text=True, **kw)
def pytest_configure(config):
global _started_container, _db_unavailable_reason
if _db_reachable(settings.DATABASE_URL):
return # dev loop / checkpoint runner already provided one
if not _run(["docker", "--version"]).returncode == 0:
_db_unavailable_reason = (
"no reachable DATABASE_URL and docker is unavailable -- run the "
"checkpoint suite (scripts/run_checkpoint_tests.py) or start Postgres "
"manually"
)
return
env = os.environ.copy()
env["COMPOSE_PROJECT_NAME"] = _COMPOSE_PROJECT
env["POSTGRES_HOST_PORT"] = str(_EPHEMERAL_PG_PORT)
env["POSTGRES_PORT"] = str(_EPHEMERAL_PG_PORT)
up = _run(["docker", "compose", "up", "-d", "postgres"], env=env)
if up.returncode != 0:
_db_unavailable_reason = f"docker compose up postgres failed:\n{up.stderr[-800:]}"
return
_started_container = True
for _ in range(30):
r = _run(
["docker", "compose", "exec", "-T", "postgres",
"pg_isready", "-U", "agp_user", "-d", "agp_db"],
env=env,
)
if r.returncode == 0:
break
time.sleep(1)
else:
_db_unavailable_reason = "ephemeral Postgres never became ready"
return
url = f"postgresql+asyncpg://agp_user:agp_password@localhost:{_EPHEMERAL_PG_PORT}/agp_db"
os.environ["DATABASE_URL"] = url
settings.DATABASE_URL = url
mig = _run([sys.executable, "-m", "alembic", "upgrade", "head"],
env={**os.environ, "DATABASE_URL": url})
if mig.returncode != 0:
_db_unavailable_reason = f"alembic upgrade head failed:\n{mig.stderr[-800:]}"
def pytest_unconfigure(config):
if not _started_container:
return
env = os.environ.copy()
env["COMPOSE_PROJECT_NAME"] = _COMPOSE_PROJECT
env["POSTGRES_HOST_PORT"] = str(_EPHEMERAL_PG_PORT)
env["POSTGRES_PORT"] = str(_EPHEMERAL_PG_PORT)
_run(["docker", "compose", "down", "-v"], env=env)
@pytest.fixture(scope="session", autouse=True)
def _reset_database():
"""Truncate all application tables once per test session."""
if _db_unavailable_reason:
pytest.skip(_db_unavailable_reason, allow_module_level=True)
async def _truncate() -> None:
engine = create_async_engine(settings.DATABASE_URL)
async with engine.begin() as conn:
await conn.execute(
text(f"TRUNCATE TABLE {', '.join(TEST_TABLES)} CASCADE")
)
await conn.execute(text(f"TRUNCATE TABLE {', '.join(TEST_TABLES)} CASCADE"))
await engine.dispose()
asyncio.run(_truncate())
@@ -52,10 +143,6 @@ def _override_db():
reusing one from the shared pool across requests raises "attached to a
different loop" the moment a test makes more than one request. NullPool
sidesteps it: every checkout is a brand-new connection.
This lived (identically) in three separate test files before it was
lifted here; any file still defining its own local `_override_db`
simply shadows this one with the same behaviour.
"""
test_engine = create_async_engine(settings.DATABASE_URL, poolclass=NullPool)
test_session_factory = async_sessionmaker(test_engine, expire_on_commit=False)