WIP checkpoint: Address review feedback: Fix: navigating Play -> Back logs the user out (should stay logged in)

The actual fix (main_menu.gd's _ready() checking ApiClient.has_token()
and restoring authenticated state via get_me()) was already correct --
verified this directly by instrumenting frame-by-frame state and seeing
it resolve properly in ~5 frames. The test wrapping it was the real
problem: _wait_for_menu_ready() only waited 2 frames total before
checking assertions, nowhere near enough for a real HTTP round-trip, so
every run failed on a fix that actually worked.

Root fix: added a real auth_state_ready signal to main_menu.gd, emitted
once _ready()'s session check has actually resolved (either branch --
authenticated or logged-out). The test now awaits that signal directly
instead of guessing from a frame count or from UI properties that are
ambiguous mid-await (AuthButtonsRow.visible is true both before the
check resolves AND in a genuine logged-out end state, which is exactly
what made an earlier polling-based fix attempt here also flaky).

Also fixed a second real bug in the test itself: unique_id used
Time.get_ticks_msec() (process-relative, not wall-clock), colliding
with a previous run's still-present data -- same flakiness class fixed
elsewhere this session, same fix (wall-clock ms + random suffix).

Verified: 12/12 passing across 3 consecutive runs against a real
backend.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.gitignore

@@ -8,3 +8,6 @@ export/
 # OS
 .DS_Store
 Thumbs.db
+
+# Godot UID files (regenerated from path)
+*.uid

backend/.env.example

@@ -4,10 +4,13 @@ DATABASE_URL=postgresql+asyncpg://agp_user:agp_password@localhost:5432/agp_db
 # Redis
 REDIS_URL=redis://localhost:6379/0
 
-# JWT
-SECRET_KEY=change-me-to-a-secure-random-string
-ALGORITHM=HS256
-ACCESS_TOKEN_EXPIRE_MINUTES=30
+# JWT / Auth
+ALGORITHM=RS256
+ACCESS_TOKEN_EXPIRE_MINUTES=60
+REFRESH_TOKEN_EXPIRE_DAYS=30
+# Directory where the RSA keypair is loaded/generated at runtime.
+# Defaults to ~/.agp/keys (outside the repo). Keys are never committed to git.
+RSA_KEY_DIR=~/.agp/keys
 
 # App
 APP_NAME=AGP Backend

backend/alembic/versions/0003_add_refresh_tokens_table.py

@@ -0,0 +1,36 @@
+"""add refresh_tokens table
+
+Revision ID: 0003_add_refresh_tokens_table
+Revises: 0002_add_date_of_birth_to_users
+Create Date: 2025-07-25 00:00:00.000000
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision: str = "0003_add_refresh_tokens_table"
+down_revision: Union[str, None] = "0002_add_date_of_birth_to_users"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Create the refresh_tokens table."""
+    op.create_table(
+        "refresh_tokens",
+        sa.Column("id", sa.String(36), primary_key=True),
+        sa.Column("user_id", sa.Integer(), sa.ForeignKey("users.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("token", sa.String(512), unique=True, index=True, nullable=False),
+        sa.Column("expires_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("is_active", sa.Boolean(), server_default=sa.text("true"), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now(), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now(), nullable=False),
+    )
+
+
+def downgrade() -> None:
+    """Drop the refresh_tokens table."""
+    op.drop_table("refresh_tokens")

backend/app/config.py

@@ -1,10 +1,56 @@
 """Application configuration via pydantic-settings."""
 
 from functools import lru_cache
+from pathlib import Path
 
+from cryptography.hazmat.primitives.asymmetric.rsa import (
+    RSAPrivateKey,
+    RSAPublicKey,
+    generate_private_key,
+)
+from cryptography.hazmat.primitives.serialization import (
+    Encoding,
+    NoEncryption,
+    PrivateFormat,
+    PublicFormat,
+    load_pem_private_key,
+    load_pem_public_key,
+)
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
+def _load_or_generate_rsa_keys(key_dir: Path) -> tuple[bytes, bytes]:
+    """Load existing RSA keys or generate a new pair.
+
+    Keys are stored as PEM files in *key_dir*.  The directory is created
+    if it does not exist.  Files are named ``private.pem`` and
+    ``public.pem`` and are **not** committed to git.
+    """
+    private_path = key_dir / "private.pem"
+    public_path = key_dir / "public.pem"
+
+    if private_path.exists() and public_path.exists():
+        private_pem = private_path.read_bytes()
+        public_pem = public_path.read_bytes()
+    else:
+        # Generate a new 2048-bit RSA key pair
+        private_key = generate_private_key(public_exponent=65537, key_size=2048)
+        private_pem = private_key.private_bytes(
+            Encoding.PEM,
+            PrivateFormat.PKCS8,
+            NoEncryption(),
+        )
+        public_pem = private_key.public_key().public_bytes(
+            Encoding.PEM,
+            PublicFormat.SubjectPublicKeyInfo,
+        )
+        key_dir.mkdir(parents=True, exist_ok=True)
+        private_path.write_bytes(private_pem)
+        public_path.write_bytes(public_pem)
+
+    return private_pem, public_pem
+
+
 class Settings(BaseSettings):
     # App
     APP_NAME: str = "AGP Backend"
@@ -18,11 +64,13 @@ class Settings(BaseSettings):
     REDIS_URL: str = "redis://localhost:6379/0"
 
     # JWT / Auth
-    # NOTE: production must override SECRET_KEY with a secure random value
-    # (e.g. `python -c "import secrets; print(secrets.token_urlsafe(32))"`)
-    SECRET_KEY: str = "change-me-to-a-secure-random-string"
-    ALGORITHM: str = "HS256"
-    ACCESS_TOKEN_EXPIRE_MINUTES: int = 30
+    ALGORITHM: str = "RS256"
+    ACCESS_TOKEN_EXPIRE_MINUTES: int = 60
+    REFRESH_TOKEN_EXPIRE_DAYS: int = 30
+
+    # RS256 key storage.  Defaults to a directory outside the repo so the
+    # generated keypair is never accidentally committed.
+    RSA_KEY_DIR: str = str(Path.home() / ".agp" / "keys")
 
     # CORS
     CORS_ORIGINS: str = "http://localhost:8080,http://localhost:3000"
@@ -42,6 +90,32 @@ class Settings(BaseSettings):
     def cors_origins_list(self) -> list[str]:
         return [origin.strip() for origin in self.CORS_ORIGINS.split(",")]
 
+    @property
+    def rsa_key_dir(self) -> Path:
+        return Path(self.RSA_KEY_DIR)
+
+    @property
+    def private_pem(self) -> bytes:
+        """Return the private key PEM bytes (loads/generates on first call)."""
+        private_pem, _ = _load_or_generate_rsa_keys(self.rsa_key_dir)
+        return private_pem
+
+    @property
+    def public_pem(self) -> bytes:
+        """Return the public key PEM bytes (loads/generates on first call)."""
+        _, public_pem = _load_or_generate_rsa_keys(self.rsa_key_dir)
+        return public_pem
+
+    @property
+    def private_key(self) -> RSAPrivateKey:
+        """Return the deserialized RSA private key object."""
+        return load_pem_private_key(self.private_pem, password=None)
+
+    @property
+    def public_key(self) -> RSAPublicKey:
+        """Return the deserialized RSA public key object."""
+        return load_pem_public_key(self.public_pem)
+
 
 @lru_cache()
 def get_settings() -> Settings:

backend/app/dependencies.py

@@ -27,7 +27,7 @@ async def get_current_user(
     )
     try:
         payload = jwt.decode(
-            token, settings.SECRET_KEY, algorithms=[settings.ALGORITHM]
+            token, settings.public_pem, algorithms=[settings.ALGORITHM]
         )
         user_id: str | None = payload.get("sub")
         if user_id is None:

backend/app/models/session.py

@@ -3,6 +3,7 @@ import uuid
 from sqlalchemy import Column, Integer, String, DateTime, ForeignKey, Boolean
 from sqlalchemy.orm import relationship
 from sqlalchemy.sql import func
+
 from app.database import Base
 
 
@@ -18,3 +19,23 @@ class Session(Base):
     updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
 
     user = relationship("User", back_populates="sessions")
+
+
+class RefreshToken(Base):
+    __tablename__ = "refresh_tokens"
+
+    id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
+    user_id = Column(Integer, ForeignKey("users.id", ondelete="CASCADE"), nullable=False)
+    # RS256 JWTs are ~420+ chars; 512 is sufficient and matches the migration.
+    token = Column(String(512), unique=True, index=True, nullable=False)
+    expires_at = Column(DateTime(timezone=True), nullable=False)
+    is_active = Column(Boolean, nullable=False, default=True, server_default="true")
+    created_at = Column(DateTime(timezone=True), nullable=False, server_default=func.now())
+    updated_at = Column(
+        DateTime(timezone=True),
+        nullable=False,
+        server_default=func.now(),
+        onupdate=func.now(),
+    )
+
+    user = relationship("User", back_populates="refresh_tokens")

backend/app/models/user.py

@@ -21,6 +21,7 @@ class User(Base):
     updated_at = Column(DateTime(timezone=True), onupdate=func.now())
 
     sessions = relationship("Session", back_populates="user", cascade="all, delete-orphan")
+    refresh_tokens = relationship("RefreshToken", back_populates="user", cascade="all, delete-orphan")
     worlds = relationship("World", back_populates="owner")
     assets = relationship("Asset", back_populates="owner")
 

backend/app/models/world.py

@@ -21,7 +21,12 @@ class World(Base):
     description = Column(Text, nullable=True)
     owner_id = Column(Integer, ForeignKey("users.id"), nullable=False)
     visibility = Column(
-        ENUM(WorldVisibility, name="world_visibility", create_type=False),
+        ENUM(
+            WorldVisibility,
+            name="world_visibility",
+            create_type=False,
+            values_callable=lambda enum_cls: [e.value for e in enum_cls],
+        ),
         default=WorldVisibility.PUBLIC,
     )
     created_at = Column(DateTime(timezone=True), server_default=func.now())

backend/app/routers/auth.py

@@ -1,20 +1,21 @@
 """Authentication router - login, register, token refresh."""
 
+import uuid
 from datetime import date, datetime, timedelta, timezone
 
 from fastapi import APIRouter, Depends, HTTPException, status
 from fastapi.security import OAuth2PasswordRequestForm
-from pydantic import BaseModel, EmailStr, field_validator
-
-from jose import jwt
+from jose import JWTError, jwt
 from passlib.context import CryptContext
+from pydantic import BaseModel, EmailStr, field_validator
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.config import settings
 from app.database import get_db
 from app.dependencies import CurrentUser
+from app.models.session import RefreshToken
 from app.models.user import User
-from sqlalchemy.ext.asyncio import AsyncSession
-from sqlalchemy import select
 
 pwd_context = CryptContext(schemes=["bcrypt"], deprecated="auto")
 
@@ -25,7 +26,13 @@ router = APIRouter()
 
 class TokenResponse(BaseModel):
     access_token: str
+    refresh_token: str
     token_type: str = "bearer"
+    access_token_expires_minutes: int
+
+
+class RefreshRequest(BaseModel):
+    refresh_token: str
 
 
 class RegisterRequest(BaseModel):
@@ -59,12 +66,43 @@ class UserResponse(BaseModel):
 # --- Helpers ---
 
 def _create_access_token(data: dict) -> str:
+    """Create a signed access token using RS256.
+
+    Includes a unique ``jti`` claim so that concurrent/same-second calls
+    (e.g. back-to-back /refresh requests) still produce distinct tokens —
+    without it, two tokens minted for the same user within the same
+    second are byte-identical since ``sub``/``exp`` are the only claims.
+    """
     to_encode = data.copy()
+    to_encode["jti"] = str(uuid.uuid4())
     expire = datetime.now(timezone.utc) + timedelta(
         minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES
     )
     to_encode.update({"exp": expire})
-    return jwt.encode(to_encode, settings.SECRET_KEY, algorithm=settings.ALGORITHM)
+    return jwt.encode(
+        to_encode,
+        settings.private_pem,
+        algorithm=settings.ALGORITHM,
+    )
+
+
+def _create_refresh_token(data: dict) -> str:
+    """Create a signed refresh token using RS256.
+
+    Includes a unique ``jti`` claim so that concurrent calls produce
+    distinct tokens even when issued within the same second.
+    """
+    to_encode = data.copy()
+    to_encode["jti"] = str(uuid.uuid4())
+    expire = datetime.now(timezone.utc) + timedelta(
+        days=settings.REFRESH_TOKEN_EXPIRE_DAYS
+    )
+    to_encode.update({"exp": expire})
+    return jwt.encode(
+        to_encode,
+        settings.private_pem,
+        algorithm=settings.ALGORITHM,
+    )
 
 
 def verify_password(plain_password: str, hashed_password: str) -> bool:
@@ -97,11 +135,25 @@ def calculate_age(birth_date: date, today: date | None = None) -> int:
     return age
 
 
+def _issue_refresh_token(user_id: int, db: AsyncSession) -> str:
+    """Create and persist a refresh token for the given user."""
+    refresh_token_value = _create_refresh_token({"sub": str(user_id)})
+    refresh_token_record = RefreshToken(
+        id=str(uuid.uuid4()),
+        user_id=user_id,
+        token=refresh_token_value,
+        expires_at=datetime.now(timezone.utc)
+        + timedelta(days=settings.REFRESH_TOKEN_EXPIRE_DAYS),
+    )
+    db.add(refresh_token_record)
+    return refresh_token_value
+
+
 # --- Endpoints ---
 
 @router.post("/register", response_model=TokenResponse, status_code=status.HTTP_201_CREATED)
 async def register(req: RegisterRequest, db: AsyncSession = Depends(get_db)):
-    """Register a new user and return an access token.
+    """Register a new user and return access + refresh tokens.
 
     Requires date_of_birth and rejects users under 18.
     """
@@ -138,16 +190,26 @@ async def register(req: RegisterRequest, db: AsyncSession = Depends(get_db)):
         date_of_birth=dob,
     )
     db.add(user)
-    await db.commit()
+    await db.flush()  # flush to get user.id before creating refresh token
     await db.refresh(user)
 
+    # Create access token
     access_token = _create_access_token({"sub": str(user.id)})
-    return TokenResponse(access_token=access_token)
+
+    # Create and persist refresh token
+    refresh_token_value = _issue_refresh_token(user.id, db)
+    await db.commit()
+
+    return TokenResponse(
+        access_token=access_token,
+        refresh_token=refresh_token_value,
+        access_token_expires_minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES,
+    )
 
 
 @router.post("/login", response_model=TokenResponse)
 async def login(form: OAuth2PasswordRequestForm = Depends(), db: AsyncSession = Depends(get_db)):
-    """Authenticate user and return an access token.
+    """Authenticate user and return access + refresh tokens.
 
     Accepts form-encoded credentials (username/password) as expected by
     OAuth2PasswordBearer, so the Swagger UI "Authorize" flow works correctly.
@@ -167,8 +229,84 @@ async def login(form: OAuth2PasswordRequestForm = Depends(), db: AsyncSession =
             detail="User account is inactive",
         )
 
+    # Create access token
     access_token = _create_access_token({"sub": str(user.id)})
-    return TokenResponse(access_token=access_token)
+
+    # Create and persist refresh token
+    refresh_token_value = _issue_refresh_token(user.id, db)
+    await db.commit()
+
+    return TokenResponse(
+        access_token=access_token,
+        refresh_token=refresh_token_value,
+        access_token_expires_minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES,
+    )
+
+
+@router.post("/refresh", response_model=TokenResponse)
+async def refresh(req: RefreshRequest, db: AsyncSession = Depends(get_db)):
+    """Exchange a valid refresh token for a new access token.
+
+    Validates the refresh token against the database:
+    - Must exist in the refresh_tokens table
+    - Must not be expired (expires_at > now)
+    - Must be active (is_active == true)
+
+    On success, returns a new access token. The refresh token itself is
+    NOT rotated (the client keeps using the same refresh token).
+    """
+    credentials_exception = HTTPException(
+        status_code=status.HTTP_401_UNAUTHORIZED,
+        detail="Invalid or expired refresh token",
+    )
+
+    # Step 1: Decode and validate the JWT signature/claims
+    try:
+        payload = jwt.decode(
+            req.refresh_token,
+            settings.public_pem,
+            algorithms=[settings.ALGORITHM],
+        )
+    except JWTError:
+        raise credentials_exception
+
+    user_id_str: str | None = payload.get("sub")
+    if user_id_str is None:
+        raise credentials_exception
+
+    try:
+        user_id = int(user_id_str)
+    except (ValueError, TypeError):
+        raise credentials_exception
+
+    # Step 2: Look up the refresh token in the database
+    result = await db.execute(
+        select(RefreshToken).where(
+            RefreshToken.token == req.refresh_token,
+            RefreshToken.user_id == user_id,
+        )
+    )
+    stored_token = result.scalar_one_or_none()
+
+    if stored_token is None:
+        raise credentials_exception
+
+    # Step 3: Check if the token is expired
+    if datetime.now(timezone.utc) >= stored_token.expires_at:
+        raise credentials_exception
+
+    # Step 4: Check if the token is active
+    if not stored_token.is_active:
+        raise credentials_exception
+
+    # Step 5: Issue a new access token
+    access_token = _create_access_token({"sub": str(user_id)})
+
+    return TokenResponse(
+        access_token=access_token,
+        refresh_token=req.refresh_token,  # Return the same refresh token
+        access_token_expires_minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES,
+    )
 
 
 @router.get("/me", response_model=UserResponse)

backend/app/routers/worlds.py

@@ -1,5 +1,6 @@
 """Worlds router - CRUD for game worlds."""
 
+from datetime import datetime
 from typing import Annotated
 
 from fastapi import APIRouter, Depends, HTTPException, Query
@@ -40,7 +41,7 @@ class WorldResponse(BaseModel):
     description: str | None
     visibility: WorldVisibility
     owner_id: int
-    created_at: str | None = None
+    created_at: datetime | None = None
 
     model_config = {"from_attributes": True}
 

backend/requirements.txt

@@ -9,6 +9,14 @@ pydantic==2.10.3
 pydantic-settings==2.7.0
 python-jose[cryptography]==3.3.0
 passlib[bcrypt]==1.7.4
+# passlib 1.7.4 (last release, unmaintained since ~2020) detects its bcrypt
+# backend via bcrypt.__about__.__version__, which bcrypt>=4.1 removed --
+# hashing/verifying a password then raises "password cannot be longer than
+# 72 bytes" (a misleading downstream symptom of the real AttributeError:
+# module 'bcrypt' has no attribute '__about__') on every call. Without this
+# pin, `pip install -r requirements.txt` silently grabs whatever the latest
+# bcrypt is and breaks register/login outright. Pin below 4.1 explicitly.
+bcrypt==4.0.1
 python-multipart==0.0.20
 email-validator==2.2.0
 httpx==0.28.1

backend/tests/conftest.py

@@ -0,0 +1,38 @@
+"""Shared pytest fixtures.
+
+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.
+
+Truncation order doesn't strictly matter because ``CASCADE`` follows foreign
+keys, but the tables are listed explicitly for clarity.
+"""
+
+import asyncio
+
+import pytest
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import create_async_engine
+
+from app.config import settings
+
+TEST_TABLES = ("assets", "worlds", "sessions", "refresh_tokens", "users")
+
+
+@pytest.fixture(scope="session", autouse=True)
+def _reset_database():
+    """Truncate all application tables once per test session."""
+
+    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 engine.dispose()
+
+    asyncio.run(_truncate())
+    yield

backend/tests/test_auth_endpoints.py

@@ -0,0 +1,263 @@
+"""Integration tests for the auth endpoints (register + login).
+
+These tests hit the real FastAPI app against the real configured database
+(DATABASE_URL -- Postgres via Alembic migrations in CI/dev, not an isolated
+in-memory DB), so they exercise the full stack: Pydantic validation → DB →
+JWT → response. Requires migrations already applied (alembic upgrade head)
+before running.
+"""
+
+import pytest
+from fastapi.testclient import TestClient
+from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+from sqlalchemy.pool import NullPool
+
+from app.config import settings
+from app.main import app
+from app.database import get_db
+from app.routers.auth import pwd_context
+
+
+# ---------------------------------------------------------------------------
+# Test fixtures
+# ---------------------------------------------------------------------------
+
+@pytest.fixture(autouse=True)
+def _override_db():
+    """Override get_db so the app uses a fresh session per test.
+
+    Deliberately does NOT reuse app.database's shared engine: FastAPI's
+    (sync) TestClient runs each request through anyio's blocking-portal
+    machinery, which can hand different requests different event loops.
+    asyncpg connections are bound to the loop they were created on, so
+    reusing one from the shared engine's connection pool across requests
+    raises "cannot perform operation: another operation is in progress" the
+    moment a test makes more than one request (register-then-login,
+    register-twice, etc.) -- confirmed this is the actual cause, not a bug
+    in the endpoints themselves. NullPool sidesteps it: every checkout is a
+    brand-new connection, never handed to a different loop than the one
+    that opened it.
+    """
+    test_engine = create_async_engine(settings.DATABASE_URL, poolclass=NullPool)
+    test_session_factory = async_sessionmaker(test_engine, expire_on_commit=False)
+
+    async def _get_db():
+        async_session = test_session_factory()
+        try:
+            yield async_session
+            await async_session.commit()
+        except Exception:
+            await async_session.rollback()
+            raise
+        finally:
+            await async_session.close()
+
+    app.dependency_overrides[get_db] = _get_db
+    yield
+    app.dependency_overrides.clear()
+
+
+# ---------------------------------------------------------------------------
+# Register endpoint
+# ---------------------------------------------------------------------------
+
+class TestRegister:
+    """Tests for POST /api/auth/register."""
+
+    def test_register_success(self):
+        """A valid registration returns 201 with a token."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": "newuser",
+                "email": "new@example.com",
+                "password": "secret123",
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        assert resp.status_code == 201
+        data = resp.json()
+        assert "access_token" in data
+        assert data["token_type"] == "bearer"
+
+    def test_register_rejects_underage(self):
+        """Users under 18 get a 400 with a detail message."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": "kid",
+                "email": "kid@example.com",
+                "password": "secret123",
+                "date_of_birth": "2010-06-15",  # ~15 years old
+            },
+        )
+        assert resp.status_code == 400
+        assert "18 or older" in resp.json()["detail"]
+
+    def test_register_rejects_duplicate_username(self):
+        """Registering the same username twice returns 409."""
+        client = TestClient(app)
+        # First registration
+        client.post(
+            "/api/auth/register",
+            json={
+                "username": "duplicate",
+                "email": "dup1@example.com",
+                "password": "secret123",
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        # Second registration with same username, different email
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": "duplicate",
+                "email": "dup2@example.com",
+                "password": "secret123",
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        assert resp.status_code == 409
+        assert "Username already registered" in resp.json()["detail"]
+
+    def test_register_rejects_duplicate_email(self):
+        """Registering the same email twice returns 409."""
+        client = TestClient(app)
+        client.post(
+            "/api/auth/register",
+            json={
+                "username": "user1",
+                "email": "same@example.com",
+                "password": "secret123",
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": "user2",
+                "email": "same@example.com",
+                "password": "secret123",
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        assert resp.status_code == 409
+        assert "Email already registered" in resp.json()["detail"]
+
+    def test_register_invalid_date_format(self):
+        """Invalid date format returns 422 validation error."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": "user",
+                "email": "user@example.com",
+                "password": "secret123",
+                "date_of_birth": "01-01-2000",  # wrong format
+            },
+        )
+        assert resp.status_code == 422
+
+    def test_register_exactly_18(self):
+        """A user who just turned 18 can register."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": "just18",
+                "email": "just18@example.com",
+                "password": "secret123",
+                "date_of_birth": "2007-06-15",
+            },
+        )
+        assert resp.status_code == 201
+
+
+# ---------------------------------------------------------------------------
+# Login endpoint
+# ---------------------------------------------------------------------------
+
+class TestLogin:
+    """Tests for POST /api/auth/login."""
+
+    def _create_user(self, username: str, password: str, email: str = None):
+        """Helper to create a user via register."""
+        client = TestClient(app)
+        if email is None:
+            email = f"{username}@example.com"
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": username,
+                "email": email,
+                "password": password,
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        assert resp.status_code == 201
+        return resp.json()["access_token"]
+
+    def test_login_success(self):
+        """Correct credentials return a token."""
+        self._create_user("loginuser", "correctpass")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/login",
+            data={"username": "loginuser", "password": "correctpass"},
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert "access_token" in data
+        assert data["token_type"] == "bearer"
+
+    def test_login_wrong_password(self):
+        """Wrong password returns 401."""
+        # Distinct username from test_login_success -- there's no per-test
+        # DB rollback/isolation here (real Postgres via the app's own
+        # dependency-overridden session), so reusing "loginuser" collided
+        # with the user that test already created (409 on register instead
+        # of the intended 401-on-login assertion this test is actually for).
+        self._create_user("loginuser_wrongpass", "correctpass")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/login",
+            data={"username": "loginuser_wrongpass", "password": "wrongpass"},
+        )
+        assert resp.status_code == 401
+        assert "Incorrect username or password" in resp.json()["detail"]
+
+    def test_login_nonexistent_user(self):
+        """Non-existent user returns 401 (not 404)."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/login",
+            data={"username": "nobody", "password": "any"},
+        )
+        assert resp.status_code == 401
+        assert "Incorrect username or password" in resp.json()["detail"]
+
+    def test_login_accepts_form_encoded(self):
+        """Login accepts application/x-www-form-urlencoded (OAuth2)."""
+        self._create_user("formuser", "formpass")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/login",
+            data={"username": "formuser", "password": "formpass"},
+        )
+        assert resp.status_code == 200
+        assert "access_token" in resp.json()
+
+    def test_login_token_is_valid_jwt(self):
+        """The returned token is a valid JWT that can be decoded."""
+        self._create_user("jwttoken", "jwt123")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/login",
+            data={"username": "jwttoken", "password": "jwt123"},
+        )
+        token = resp.json()["access_token"]
+        # Verify it's a 3-part JWT
+        parts = token.split(".")
+        assert len(parts) == 3

backend/tests/test_auth_expired_token.py

@@ -0,0 +1,171 @@
+"""Tests for expired-token rejection across auth endpoints.
+
+Covers two distinct expiry paths:
+
+1. An *access* JWT whose ``exp`` claim is in the past must be rejected
+   with 401 by ``GET /api/auth/me`` (jose's built-in ``exp`` validation).
+2. A *refresh* token whose persisted ``expires_at`` is in the past must be
+   rejected with 401 by ``POST /api/auth/refresh`` even though its JWT
+   signature is still valid.
+
+Requires migrations already applied (alembic upgrade head) before running.
+"""
+
+import asyncio
+from datetime import datetime, timedelta, timezone
+
+import pytest
+from fastapi.testclient import TestClient
+from jose import jwt
+from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+from sqlalchemy.pool import NullPool
+
+from app.config import settings
+from app.main import app
+from app.database import get_db
+from app.models.session import RefreshToken
+
+
+# ---------------------------------------------------------------------------
+# Test fixtures
+# ---------------------------------------------------------------------------
+
+@pytest.fixture(autouse=True)
+def _override_db():
+    """Override get_db so the app uses a fresh session per test."""
+    test_engine = create_async_engine(settings.DATABASE_URL, poolclass=NullPool)
+    test_session_factory = async_sessionmaker(test_engine, expire_on_commit=False)
+
+    async def _get_db():
+        async_session = test_session_factory()
+        try:
+            yield async_session
+            await async_session.commit()
+        except Exception:
+            await async_session.rollback()
+            raise
+        finally:
+            await async_session.close()
+
+    app.dependency_overrides[get_db] = _get_db
+    yield
+    app.dependency_overrides.clear()
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _mint_access_token(exp: datetime) -> str:
+    """Mint an RS256 access token with an explicit ``exp`` claim."""
+    return jwt.encode(
+        {"sub": "1", "exp": exp},
+        settings.private_pem,
+        algorithm=settings.ALGORITHM,
+    )
+
+
+def _expire_refresh_token_in_db(token: str) -> None:
+    """Set the persisted refresh token's ``expires_at`` into the past."""
+
+    async def _do():
+        engine = create_async_engine(settings.DATABASE_URL, poolclass=NullPool)
+        session_factory = async_sessionmaker(engine, expire_on_commit=False)
+        async with session_factory() as session:
+            from sqlalchemy import update
+
+            await session.execute(
+                update(RefreshToken)
+                .where(RefreshToken.token == token)
+                .values(expires_at=datetime.now(timezone.utc) - timedelta(hours=1))
+            )
+            await session.commit()
+        await engine.dispose()
+
+    asyncio.run(_do())
+
+
+def _register_user(client: TestClient, username: str) -> str:
+    """Register a user and return its refresh token."""
+    resp = client.post(
+        "/api/auth/register",
+        json={
+            "username": username,
+            "email": f"{username}@example.com",
+            "password": "secret123",
+            "date_of_birth": "2000-01-01",
+        },
+    )
+    assert resp.status_code == 201
+    return resp.json()["refresh_token"]
+
+
+# ---------------------------------------------------------------------------
+# Expired access token (GET /api/auth/me)
+# ---------------------------------------------------------------------------
+
+class TestExpiredAccessToken:
+    def test_expired_access_token_is_rejected_by_me(self):
+        """An access JWT with a past exp claim returns 401 on /me."""
+        client = TestClient(app)
+        expired_token = _mint_access_token(
+            datetime.now(timezone.utc) - timedelta(minutes=5)
+        )
+        resp = client.get(
+            "/api/auth/me",
+            headers={"Authorization": f"Bearer {expired_token}"},
+        )
+        assert resp.status_code == 401
+        assert "Could not validate credentials" in resp.json()["detail"]
+
+    def test_garbage_access_token_is_rejected_by_me(self):
+        """A non-JWT bearer token returns 401 on /me."""
+        client = TestClient(app)
+        resp = client.get(
+            "/api/auth/me",
+            headers={"Authorization": "Bearer not-a-real-jwt"},
+        )
+        assert resp.status_code == 401
+
+    def test_missing_bearer_token_returns_401(self):
+        """No Authorization header at all returns 401 on /me."""
+        client = TestClient(app)
+        resp = client.get("/api/auth/me")
+        assert resp.status_code == 401
+
+
+# ---------------------------------------------------------------------------
+# Expired refresh token (POST /api/auth/refresh)
+# ---------------------------------------------------------------------------
+
+class TestExpiredRefreshToken:
+    def test_expired_refresh_token_is_rejected(self):
+        """A refresh token whose DB expires_at is in the past returns 401."""
+        client = TestClient(app)
+        refresh_token = _register_user(client, "expired_rt_user")
+
+        # Force the persisted record to be expired while its JWT signature
+        # is still valid.
+        _expire_refresh_token_in_db(refresh_token)
+
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp.status_code == 401
+        assert "Invalid or expired refresh token" in resp.json()["detail"]
+
+    def test_expired_refresh_token_jwt_is_rejected(self):
+        """A refresh JWT with a past exp claim is rejected before DB lookup."""
+        client = TestClient(app)
+        expired_jwt = jwt.encode(
+            {"sub": "1", "exp": datetime.now(timezone.utc) - timedelta(minutes=5)},
+            settings.private_pem,
+            algorithm=settings.ALGORITHM,
+        )
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": expired_jwt},
+        )
+        assert resp.status_code == 401
+        assert "Invalid or expired refresh token" in resp.json()["detail"]

backend/tests/test_refresh_endpoint.py

@@ -0,0 +1,201 @@
+"""Tests for the POST /api/auth/refresh endpoint.
+
+These tests exercise the full stack: register → get refresh token →
+refresh → new access token.  Requires migrations already applied
+(alembic upgrade head) before running.
+"""
+
+import pytest
+from fastapi.testclient import TestClient
+from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+from sqlalchemy.pool import NullPool
+
+from app.config import settings
+from app.main import app
+from app.database import get_db
+
+
+# ---------------------------------------------------------------------------
+# Test fixtures
+# ---------------------------------------------------------------------------
+
+@pytest.fixture(autouse=True)
+def _override_db():
+    """Override get_db so the app uses a fresh session per test."""
+    test_engine = create_async_engine(settings.DATABASE_URL, poolclass=NullPool)
+    test_session_factory = async_sessionmaker(test_engine, expire_on_commit=False)
+
+    async def _get_db():
+        async_session = test_session_factory()
+        try:
+            yield async_session
+            await async_session.commit()
+        except Exception:
+            await async_session.rollback()
+            raise
+        finally:
+            await async_session.close()
+
+    app.dependency_overrides[get_db] = _get_db
+    yield
+    app.dependency_overrides.clear()
+
+
+# ---------------------------------------------------------------------------
+# Refresh endpoint tests
+# ---------------------------------------------------------------------------
+
+class TestRefresh:
+    """Tests for POST /api/auth/refresh."""
+
+    def _register_user(self, username: str, password: str, email: str = None):
+        """Helper to register a user and return the refresh token."""
+        client = TestClient(app)
+        if email is None:
+            email = f"{username}@example.com"
+        resp = client.post(
+            "/api/auth/register",
+            json={
+                "username": username,
+                "email": email,
+                "password": password,
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        assert resp.status_code == 201
+        return resp.json()["refresh_token"]
+
+    def test_refresh_success(self):
+        """A valid refresh token returns a new access token."""
+        refresh_token = self._register_user("refep_refreshuser", "secret123")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert "access_token" in data
+        assert data["token_type"] == "bearer"
+        # The refresh token in the response is the same one we sent
+        assert data["refresh_token"] == refresh_token
+
+    def test_refresh_returns_different_access_token(self):
+        """Refreshing produces a new access token (different from any previous)."""
+        refresh_token = self._register_user("refep_refreshtoken", "secret123")
+        client = TestClient(app)
+
+        # First refresh
+        resp1 = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp1.status_code == 200
+        access_token_1 = resp1.json()["access_token"]
+
+        # Second refresh
+        resp2 = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp2.status_code == 200
+        access_token_2 = resp2.json()["access_token"]
+
+        # Each refresh should produce a new access token
+        assert access_token_1 != access_token_2
+
+    def test_refresh_invalid_token(self):
+        """An invalid (garbage) refresh token returns 401."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": "not.a.jwt.token"},
+        )
+        assert resp.status_code == 401
+        assert "Invalid or expired refresh token" in resp.json()["detail"]
+
+    def test_refresh_empty_body(self):
+        """Missing refresh_token field returns 422 validation error."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/refresh",
+            json={},
+        )
+        assert resp.status_code == 422
+
+    def test_refresh_missing_field(self):
+        """No body at all returns 422."""
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/refresh",
+            content="{}",
+            headers={"Content-Type": "application/json"},
+        )
+        assert resp.status_code == 422
+
+    def test_refresh_with_login_token(self):
+        """A refresh token obtained from login also works for /refresh."""
+        client = TestClient(app)
+        # Register first
+        client.post(
+            "/api/auth/register",
+            json={
+                "username": "refep_loginrefuser",
+                "email": "loginref@example.com",
+                "password": "secret123",
+                "date_of_birth": "2000-01-01",
+            },
+        )
+        # Login to get a refresh token
+        login_resp = client.post(
+            "/api/auth/login",
+            data={"username": "refep_loginrefuser", "password": "secret123"},
+        )
+        assert login_resp.status_code == 200
+        refresh_token = login_resp.json()["refresh_token"]
+
+        # Use it to refresh
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp.status_code == 200
+        assert "access_token" in resp.json()
+
+    def test_refresh_access_token_is_valid_jwt(self):
+        """The access token returned by /refresh is a valid JWT."""
+        from jose import jwt
+
+        refresh_token = self._register_user("refep_jwttoken", "secret123")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp.status_code == 200
+        access_token = resp.json()["access_token"]
+
+        # Verify it's a 3-part JWT
+        parts = access_token.split(".")
+        assert len(parts) == 3
+
+        # Verify it decodes with the public key
+        payload = jwt.decode(
+            access_token,
+            settings.public_pem,
+            algorithms=[settings.ALGORITHM],
+        )
+        assert "sub" in payload
+        assert "exp" in payload
+
+    def test_refresh_expires_minutes_in_response(self):
+        """The response includes access_token_expires_minutes."""
+        refresh_token = self._register_user("refep_expiretest", "secret123")
+        client = TestClient(app)
+        resp = client.post(
+            "/api/auth/refresh",
+            json={"refresh_token": refresh_token},
+        )
+        assert resp.status_code == 200
+        assert "access_token_expires_minutes" in resp.json()
+        assert resp.json()["access_token_expires_minutes"] == settings.ACCESS_TOKEN_EXPIRE_MINUTES

backend/tests/test_refresh_token_jti.py

@@ -0,0 +1,79 @@
+"""Tests for refresh token uniqueness (jti claim) and model column length."""
+
+import uuid
+from datetime import datetime, timedelta, timezone
+
+import pytest
+from jose import jwt
+
+from app.config import settings
+from app.routers.auth import _create_refresh_token
+from app.models.session import RefreshToken
+
+
+class TestRefreshTokenJtiUniqueness:
+    """Verify that _create_refresh_token produces unique tokens even when
+    called with identical data in rapid succession (issue #1 from review)."""
+
+    def test_two_calls_produce_different_tokens(self):
+        """Two calls with the same sub produce different JWTs because of jti."""
+        token_a = _create_refresh_token({"sub": "42"})
+        token_b = _create_refresh_token({"sub": "42"})
+        assert token_a != token_b
+
+    def test_jti_is_valid_uuid(self):
+        """The jti claim inside the refresh token is a valid UUID."""
+        token = _create_refresh_token({"sub": "1"})
+        payload = jwt.decode(
+            token,
+            settings.public_pem,
+            algorithms=[settings.ALGORITHM],
+        )
+        assert "jti" in payload
+        # Verify it parses as a UUID (raises ValueError if not)
+        uuid.UUID(payload["jti"])
+
+    def test_each_token_has_unique_jti(self):
+        """Generate 100 tokens for the same user — all jtis must differ."""
+        jtis = set()
+        for _ in range(100):
+            token = _create_refresh_token({"sub": "999"})
+            payload = jwt.decode(
+                token,
+                settings.public_pem,
+                algorithms=[settings.ALGORITHM],
+            )
+            jtis.add(payload["jti"])
+        assert len(jtis) == 100
+
+    def test_jti_survives_decode(self):
+        """The jti claim is present and correct after decode."""
+        token = _create_refresh_token({"sub": "7"})
+        payload = jwt.decode(
+            token,
+            settings.public_pem,
+            algorithms=[settings.ALGORITHM],
+        )
+        assert payload["sub"] == "7"
+        assert "jti" in payload
+        assert "exp" in payload
+
+
+class TestRefreshTokenModelColumnLength:
+    """Verify the model's token column length matches the migration (issue #2)."""
+
+    def test_token_column_has_length_512(self):
+        """RefreshToken.token column should be String(512), not unbounded."""
+        from sqlalchemy import inspect
+
+        # Get the column definition from the model's table
+        column = RefreshToken.__table__.columns["token"]
+        # The type should be String with length 512
+        assert column.type.length == 512
+
+    def test_token_column_type_is_string(self):
+        """The token column should be a String type."""
+        from sqlalchemy import String as SAString
+
+        column = RefreshToken.__table__.columns["token"]
+        assert isinstance(column.type, SAString)

docs/checkpoints/PC1.md

@@ -0,0 +1,72 @@
+# Package Checkpoint 1 (PC1)
+
+Validated 2026-08-20 against `main` commit `927f9bd`, from a genuinely fresh
+clone (not a reused agent workspace).
+
+## Automated validation
+
+Run with `scripts/run_checkpoint_tests.py` — see
+`docs/testing/test_inventory.md` for exactly what each suite covers.
+
+| Check | Result |
+|---|---|
+| Alembic migrations, fresh DB | PASS |
+| Backend pytest | 68/68 PASS |
+| Godot smoke tests (4 files) | ALL PASS |
+| Linux export (`agp-game.x86_64`) | Builds, verified as a real ELF64 binary |
+| Windows export (`agp-game.exe`) | Builds, verified as a real PE32+ binary |
+
+## Problems found during this checkpoint (fixed, tracked as tasks)
+
+- Roadmap showed the Godot Engine Scaffold feature amber despite 6/6 tasks
+  done — a historical data gap (a review-feedback follow-up task's
+  supersession link was never recorded, predating when that field started
+  being tracked). Backfilled in the PM database; confirmed green.
+- `docs/testing/test_inventory.md` was stale (said 38 backend tests,
+  actually 68; said no integration tests existed, 4 real ones had landed).
+  Fixed via task `398bf1a22a2d` / PR #40.
+
+## What's actually testable right now
+
+Login/register/browse-worlds only — there's no joinable gameplay yet. That's
+the real scope of PC1; don't expect more when playtesting.
+
+- Register a new account (18+ only, rejected otherwise)
+- Log out, log back in with the same credentials
+- Play → Browse Worlds — loads a (currently empty) world list with no errors
+
+## Manual playtest: backend on cloudbison, client on pinkbison
+
+As of 2026-08-20 this is dashboard-controlled — no terminal commands, no
+env vars, no editing files. Foolproof enough to hand to someone else.
+
+### 1. On cloudbison — the AGP dashboard
+
+Open the dashboard (`http://cloudbison:7070`, or its Tailscale address) and
+go to **PC1** in the nav bar (`/checkpoint/PC1`). Click **Start Backend** —
+it pulls the latest `main`, stands up Postgres, runs migrations, and starts
+the API server, all in one step. The page shows the LAN address it's
+reachable at once it's up (under a minute).
+
+When you're done playtesting, click **Stop & Clean Up** on the same page —
+it tears down everything that step started (API server, Postgres
+container, its volume and network). Nothing is left running or lying
+around afterward, even if the dashboard itself gets restarted in between.
+
+### 2. On pinkbison — download and run the .exe
+
+Same dashboard page: click **Build .exe** the first time (or **Rebuild** to
+pick up newer changes) — this pulls the latest `main` and exports a Windows
+binary with cloudbison's backend address already baked in. Click
+**Download agp-game.exe**, copy it to pinkbison, and just run it. No
+environment variable, no config file, no build step on pinkbison at all.
+
+### 3. Tear down when done
+
+**Stop & Clean Up** on the dashboard page. That's it.
+
+## Status
+
+`config/checkpoint_focus_feature_ids` in the AGP framework (`~/agp`) still
+restricts agent claiming to the 5 PC1-scope features. Agents will not move
+on to post-PC1 work until that's widened.

docs/planning/client-server-wiring.md

@@ -23,10 +23,9 @@ explicitly out of scope.
 | # | Type | Task | Depends on |
 |---|------|------|-----------|
 | 1 | architecture | `ApiClient` autoload: HTTP + JWT storage + error contract | — |
-| 2 | implementation | Main-menu **login** wiring (form-encoded) | 1 |
-| 3 | implementation | Main-menu **register** wiring (JSON + age gate) | 2 |
-| 4 | implementation | **World list** screen consuming `GET /api/worlds` | 2 |
-| 5 | testing | End-to-end headless smoke test + manual verify | 1,3,4 |
+| 2 | implementation | Main-menu **login + register** UI built & wired (form-encoded + JSON/age gate) | 1 |
+| 3 | implementation | **World list** screen consuming `GET /api/worlds` | 1 |
+| 4 | testing | End-to-end headless smoke test + manual verify | 1,2,3 |
 
 ## Design decisions captured (resolved in task 1)
 - Token storage: in-memory singleton property for the MVP; a `save_to_disk` seam is left
@@ -35,3 +34,8 @@ explicitly out of scope.
   never crash on network failure; non-2xx surfaces `{status, detail}` from the backend.
 - Base URL: read from a ProjectSetting, defaulting to `http://127.0.0.1:8000`.
 - Login is form-encoded; register is JSON — the client helper must support both content types.
+
+## Notes
+- The main-menu auth UI does **not** exist yet (main_menu.gd currently has only Play/Quit
+  stubs). Task 2 must **build** the login/register UI, not merely wire an existing one.
+- The world-list screen also needs to be **built** (a new scene), not just wired.

docs/testing/README.md

@@ -0,0 +1,50 @@
+# Testing at Package Checkpoints
+
+A Package Checkpoint (PC1, PC2, ...) is a periodic review point — every few
+real milestones, the client and server builds get packaged together and
+independently reviewed before anyone calls anything actually done. See
+`project_agp` in Claude's memory, or ask, for the full definition; this
+doc is just the mechanical "how do I run the tests" part of that review.
+
+## Running the suite
+
+```
+python scripts/run_checkpoint_tests.py
+```
+
+Brings up a throwaway Postgres, runs Alembic migrations against it, runs the
+backend pytest suite, starts the backend server, and runs every Godot
+headless smoke test (`scripts/smoke_test_*.gd`) against it. Tears the
+Postgres container down afterward (`--keep-postgres` to skip that if you
+want to poke at the DB after a failure).
+
+If port 5432 is already taken on the machine, pass `--postgres-port` with
+something else.
+
+Exit code is 0 only if everything that actually ran passed — suites with
+nothing to run yet (no Godot binary found, no smoke test scripts yet) are
+reported SKIPPED, not treated as a failure.
+
+## What this does and doesn't prove
+
+Passing this script means: migrations apply cleanly to a genuinely empty
+database, the backend's unit-level logic is correct, and whatever Godot
+smoke tests exist actually round-trip against a live backend. It does
+**not** mean full endpoint/integration coverage exists — see
+`test_inventory.md` for the current, honest list of what's tested and what
+isn't. A checkpoint review should still involve reading the actual diffs
+for anything this script's current coverage doesn't reach, not just running
+green and calling it done.
+
+## Growing this over time
+
+As real integration tests get added (endpoint tests hitting the FastAPI app,
+more Godot smoke coverage beyond `health_check`), they should land under
+`backend/tests/` / `scripts/smoke_test_*.gd` respectively — this script
+picks up new files automatically, nothing to register by hand. Update
+`test_inventory.md`'s tables when you do, so the inventory stays a source
+of truth instead of quietly going stale.
+
+Eventual goal (not implemented yet): gate merges to `main` on this script
+passing, the same way a real CI pipeline would. For now it's a manual step
+run at checkpoint review time.

docs/testing/test_inventory.md

@@ -0,0 +1,104 @@
+# Test Inventory
+
+What automated coverage actually exists, what it actually verifies, and what
+doesn't have coverage yet. Keep this current as tests are added — it's the
+thing a Package Checkpoint review (see `docs/testing/README.md`) reads first
+to know what "run the tests" actually checked.
+
+Run everything below in one shot with `scripts/run_checkpoint_tests.py`.
+
+Last verified against `main`: 2026-08-20 — full PC1 checkpoint run,
+migrations + pytest + all 6 Godot smoke tests + both platform exports, all
+clean. Two real bugs found and fixed via real playtesting this same day
+(not caught by the checkpoint suite as it stood before today): the main
+menu had no way to actually open the login/register form, and the world
+list's cards rendered at ~1px wide once real data existed. Both are now
+covered by the smoke tests below so they can't silently regress.
+
+## Backend — `backend/tests/` (pytest)
+
+Run: `cd backend && python -m pytest -v` (needs `DATABASE_URL` pointed at a
+reachable Postgres — see the runner script).
+
+**Current total: 68 tests, all passing on a clean `main` checkout.**
+
+| File | Tests | What it covers |
+|---|---|---|
+| `test_auth_age_gate.py` | 17 | `calculate_age()` date-math correctness (exact boundary, leap years, birthday-not-yet-this-year) + `RegisterRequest` date-of-birth validation (parametrized valid/invalid date rejection). Backs the 18+ registration gate (PR #23). |
+| `test_gltf_metadata.py` | 21 | glTF/GLB binary + JSON parsing: magic-byte detection, chunk-padding handling, mesh/animation/texture-reference metadata extraction, malformed-input rejection. Backs the asset-import pipeline (PR #27). |
+| `test_auth_endpoints.py` | 11 | **Integration tests** for `POST /api/auth/register` and `POST /api/auth/login` against the real FastAPI app + real Postgres. Covers: successful register (201), duplicate username (409), duplicate email (409), underage rejection (400), invalid date format (422), exact-18 registration, successful login with correct credentials (200), wrong password (401), nonexistent user (401), form-encoded login (OAuth2), and JWT validity of returned tokens. |
+| `test_refresh_endpoint.py` | 8 | **Integration tests** for `POST /api/auth/refresh`. Covers: successful refresh (200, new access token, same refresh token returned), refresh produces different access tokens on repeated calls, invalid refresh token (401), empty body (422), missing field (422), refresh token from login also works, returned access token is valid JWT decodable with public key, `access_token_expires_minutes` in response. |
+| `test_refresh_token_jti.py` | 6 | Unit tests for refresh token uniqueness (jti claim) and model column length. Covers: two calls with same sub produce different tokens (jti uniqueness), jti is valid UUID, rapid repeated calls all produce unique jtis, jti survives decode, `RefreshToken.token` column is `String(512)`, column type is `String`. |
+| `test_auth_expired_token.py` | 5 | **Integration tests** for expired-token rejection across auth endpoints. Covers: expired access JWT rejected by `GET /api/auth/me` (401), garbage access token rejected by `/me` (401), missing bearer token returns 401, expired refresh token (DB `expires_at` in past) rejected by `/refresh` (401), expired refresh JWT (past `exp` claim) rejected before DB lookup (401). |
+
+**What these are, honestly:** a mix of pure unit tests (`test_auth_age_gate.py`,
+`test_gltf_metadata.py`, `test_refresh_token_jti.py`) and real integration tests
+(`test_auth_endpoints.py`, `test_refresh_endpoint.py`, `test_auth_expired_token.py`)
+that hit the FastAPI app against a real Postgres database via `TestClient`.
+The integration tests exercise the full stack: Pydantic validation → DB →
+JWT → response. The suite is also re-runnable without manual cleanup —
+`backend/tests/conftest.py` has a session-scoped autouse fixture that
+truncates all app tables once before the suite runs.
+
+**Known coverage gaps** (real gaps, not placeholders — nothing enforces filling
+these yet):
+- No endpoint tests for `GET /api/worlds`, `GET /api/assets/*`, or any
+  world/asset CRUD routes — only auth endpoints have integration coverage
+  (`GET /api/worlds` is covered indirectly via the Godot smoke tests below).
+- No tests for the moderation schema/migration beyond "the migration runs."
+- No tests for the `GET /api/auth/me` endpoint's response body (only its
+  auth-header validation is covered via expired-token tests).
+- No tests for session management (create/validate/revoke sessions).
+
+## Godot client — `scripts/smoke_test_*.gd`
+
+**6 smoke tests merged into `main`.** Each needs a live backend —
+`AGP_API_BASE_URL` env var, falling back to the
+`application/agp/api_base_url` project setting (default
+`http://127.0.0.1:8000`) if unset.
+
+| File | What it covers |
+|---|---|
+| `smoke_test_api.gd` | Exercises `ApiClient.health_check()` against a live backend. Verifies the real HTTP request path (`HTTPRequest` node lifecycle, JSON parse, result-dictionary contract). Exits 1 on failure. |
+| `smoke_test_auth.gd` | Tests the full auth flow via `ApiClient` autoload: register unique user (201), duplicate username (409), under-18 registration (400), correct login (200), wrong password (401), nonexistent user (401). |
+| `smoke_test_e2e.gd` | End-to-end flow: health check → register → login → worlds list. Verifies the full request chain with a fresh user, including token storage and `get_worlds()` with auth header. |
+| `smoke_test_world_list.gd` | Registers a user, **seeds a real world via `POST /api/worlds/`** (without this, `run_checkpoint_tests.py`'s always-fresh DB means the populated-card render path never actually runs in CI, only the empty-list path would), instantiates `world_list.tscn` as a real scene, waits for `_refresh_worlds()` to complete, confirms it reached the populated (not empty) state, and asserts **each rendered card's real computed width is >= 200px**. That last check is the one that matters: 2026-08-20, a real bug shipped where every card existed in the tree with a non-zero child count and no crash, but rendered at 1.0px wide (`ScrollContainer`'s `size_flags_horizontal`/`vertical` used the raw integer `4` = `Control.SIZE_SHRINK_CENTER` instead of `3` = `SIZE_EXPAND_FILL`) — invisible on screen, and a child-count-only check would never have caught it. Confirmed by deliberately reintroducing the bug: card width check correctly fails at 25px. |
+| `smoke_test_main_menu_ui.gd` | Instantiates `main_menu.tscn`, confirms the auth panel starts hidden, and confirms a **real signal emission** on LoginButton/RegisterButton (not calling the handler method directly) actually opens it. This is the check that would have caught 2026-08-20's real bug: the auth panel and its logic were fully correct, but nothing in the scene was ever wired to open it, so Login/Register were completely unreachable from the UI. |
+| `smoke_test_main_menu_full_flow.gd` | Full click-through: open the register form, fill it exactly as a user would, submit, confirm Play actually becomes enabled, the welcome message shows, and the auth buttons hide themselves. Calls the submit handler directly (awaited) rather than via `auth_button.pressed.emit()` — see the note at the top of the file: a synthetic `.emit()` on an `await`-using handler doesn't get driven forward reliably in `--script`/SceneTree headless mode the way real GUI input event dispatch does, confirmed by comparing direct-call vs `.emit()` behavior. Not a bug in the actual click-driven flow, just a headless-test-harness quirk to route around when writing tests. |
+
+Run (once, to build the class cache): `godot --headless --path . --import`,
+then for each smoke test: `godot --headless --path . --script
+res://scripts/smoke_test_<name>.gd` — **no `--quit`**, it kills these before
+their awaited HTTP calls finish.
+
+**Known gaps:**
+- No smoke tests for chunk loading/streaming (`chunk.gd`, `chunk_scene.gd`).
+- No smoke tests for dynamic/static object nodes.
+- All smoke tests require a live backend; no offline/unit smoke tests exist.
+- `smoke_test_world_list.gd` and `smoke_test_main_menu_*.gd` are the only
+  ones that exercise a real `.tscn` scene instantiation — others only test
+  the `ApiClient` autoload directly.
+- `get_me()` (`GET /auth/me`) is implemented in `scripts/api_client.gd` but
+  has no smoke coverage yet.
+- The Login path (as opposed to Register) through `main_menu.gd` isn't
+  separately smoke-tested — it shares the same `_on_auth_button_pressed()`/
+  `_on_auth_complete()` code path already exercised for Register, but that's
+  inference, not a direct check.
+
+## Client export
+
+`scripts/build.sh` produces real Linux (`agp-game.x86_64`) and Windows
+(`agp-game.exe`) binaries via `--export-release`. Verified 2026-08-20: both
+exports complete clean from a fresh checkout and produce valid binaries
+(confirmed via `file` — real ELF64/PE32+, not empty or truncated). Neither
+export is exercised by an automated GUI test (headless Godot can't drive a
+window) — actually launching and clicking through the exported binary is a
+manual step, see `docs/checkpoints/PC1.md` for playtest instructions.
+
+## What "full coverage" should eventually mean here
+
+Not defined precisely yet — the honest target as of 2026-08-20 is
+"integration tests for every endpoint + smoke tests for every major scene."
+As real integration/endpoint tests get added, update the tables above
+rather than letting this doc drift stale; a wrong inventory is worse than
+no inventory.

export_presets.cfg

@@ -0,0 +1,74 @@
+[preset.0]
+
+name="Linux"
+platform="Linux/X11"
+runnable=true
+advanced_options=false
+dedicated_server=false
+custom_features=""
+export_filter="all_resources"
+include_filter=""
+exclude_filter=""
+export_path="export/linux/agp-game.x86_64"
+encryption_include_filters=""
+encryption_exclude_filters=""
+encrypt_pck=false
+encrypt_directory=false
+script_export_mode=2
+
+[preset.0.options]
+
+custom_template/debug=""
+custom_template/release=""
+debug/export_console_wrapper=1
+binary_format/embed_pck=true
+texture_format/bptc=true
+texture_format/s3tc=true
+texture_format/etc=false
+texture_format/etc2=false
+binary_format/architecture="x86_64"
+ssh_remote_deploy/enabled=false
+
+[preset.1]
+
+name="Windows Desktop"
+platform="Windows Desktop"
+runnable=true
+advanced_options=false
+dedicated_server=false
+custom_features=""
+export_filter="all_resources"
+include_filter=""
+exclude_filter=""
+export_path="export/windows/agp-game.exe"
+encryption_include_filters=""
+encryption_exclude_filters=""
+encrypt_pck=false
+encrypt_directory=false
+script_export_mode=2
+
+[preset.1.options]
+
+custom_template/debug=""
+custom_template/release=""
+debug/export_console_wrapper=1
+binary_format/embed_pck=true
+texture_format/bptc=true
+texture_format/s3tc=true
+texture_format/etc=false
+texture_format/etc2=false
+binary_format/architecture="x86_64"
+codesign/enable=false
+application/icon=""
+application/console_wrapper_icon=""
+application/icon_interpolation=4
+application/file_version=""
+application/product_version=""
+application/company_name=""
+application/product_name=""
+application/file_description=""
+application/copyright=""
+application/trademarks=""
+application/export_angle=0
+application/export_d3d12=0
+d3d12/agility_sdk_multizip=0

project.godot

@@ -9,9 +9,12 @@ config_version=5
 config/name="AGP-Game"
 run/main_scene="res://scenes/main_menu.tscn"
 config/features=PackedStringArray("4.6.2")
+agp/api_base_url="http://127.0.0.1:8000"
 
 [autoload]
 
+ApiClient="*res://scripts/api_client.gd"
+
 [display]
 
 window/size/viewport_width=1920

scenes/main_menu.tscn

@@ -1,4 +1,4 @@
-[gd_scene load_steps=2 format=3]
+[gd_scene load_steps=2 format=3 uid="uid://main_menu_scene"]
 
 [ext_resource type="Script" path="res://scripts/main_menu.gd" id="1_main"]
 
@@ -29,6 +29,88 @@ text = "AGP Game"
 horizontal_alignment = 1
 theme_override_font_sizes/font_size = 72
 
+[node name="AuthButtonsRow" type="HBoxContainer" parent="CenterContainer/VBoxContainer"]
+layout_mode = 1
+theme_override_constants/separation = 16
+alignment = 1
+
+[node name="LoginButton" type="Button" parent="CenterContainer/VBoxContainer/AuthButtonsRow"]
+layout_mode = 1
+text = "Login"
+size_flags_horizontal = 3
+
+[node name="RegisterButton" type="Button" parent="CenterContainer/VBoxContainer/AuthButtonsRow"]
+layout_mode = 1
+text = "Register"
+size_flags_horizontal = 3
+
+[node name="AuthPanel" type="PanelContainer" parent="CenterContainer/VBoxContainer"]
+layout_mode = 1
+visible = false
+
+[node name="MarginContainer" type="MarginContainer" parent="CenterContainer/VBoxContainer/AuthPanel"]
+layout_mode = 1
+theme_override_constants/margin_left = 24
+theme_override_constants/margin_top = 24
+theme_override_constants/margin_right = 24
+theme_override_constants/margin_bottom = 24
+
+[node name="AuthVBox" type="VBoxContainer" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer"]
+layout_mode = 1
+theme_override_constants/separation = 8
+size_flags_horizontal = 3
+
+[node name="AuthModeLabel" type="Label" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+text = "Login"
+horizontal_alignment = 1
+theme_override_font_sizes/font_size = 24
+
+[node name="UsernameEdit" type="LineEdit" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+placeholder_text = "Username"
+size_flags_horizontal = 3
+
+[node name="PasswordEdit" type="LineEdit" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+placeholder_text = "Password"
+size_flags_horizontal = 3
+echo_password = true
+
+[node name="EmailEdit" type="LineEdit" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+visible = false
+placeholder_text = "Email"
+size_flags_horizontal = 3
+
+[node name="DOBEdit" type="LineEdit" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+visible = false
+placeholder_text = "Date of Birth (YYYY-MM-DD)"
+size_flags_horizontal = 3
+
+[node name="ModeToggle" type="CheckButton" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+text = "Register"
+
+[node name="AuthButton" type="Button" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+text = "Login"
+size_flags_horizontal = 3
+
+[node name="AuthStatusLabel" type="Label" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+text = ""
+horizontal_alignment = 1
+autowrap_mode = 2
+visible = false
+
+[node name="WelcomeLabel" type="Label" parent="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox"]
+layout_mode = 1
+visible = false
+text = ""
+horizontal_alignment = 1
+
 [node name="PlayButton" type="Button" parent="CenterContainer/VBoxContainer"]
 layout_mode = 1
 text = "Play"
@@ -39,5 +121,11 @@ layout_mode = 1
 text = "Quit"
 size_flags_horizontal = 4
 
+[connection signal="pressed" from="CenterContainer/VBoxContainer/AuthButtonsRow/LoginButton" to="." method="_on_login_button_pressed"]
+[connection signal="pressed" from="CenterContainer/VBoxContainer/AuthButtonsRow/RegisterButton" to="." method="_on_register_button_pressed"]
 [connection signal="pressed" from="CenterContainer/VBoxContainer/PlayButton" to="." method="_on_play_button_pressed"]
 [connection signal="pressed" from="CenterContainer/VBoxContainer/QuitButton" to="." method="_on_quit_button_pressed"]
+[connection signal="toggled" from="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/ModeToggle" to="." method="_on_mode_toggle_toggled"]
+[connection signal="pressed" from="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/AuthButton" to="." method="_on_auth_button_pressed"]
+[connection signal="text_submitted" from="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/UsernameEdit" to="." method="_on_auth_button_pressed"]
+[connection signal="text_submitted" from="CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/PasswordEdit" to="." method="_on_auth_button_pressed"]

scenes/world_list.tscn

@@ -0,0 +1,78 @@
+[gd_scene load_steps=2 format=3]
+
+[ext_resource type="Script" path="res://scripts/world_list.gd" id="1_wl"]
+
+[node name="WorldList" type="Control"]
+anchors_preset = 15
+anchor_right = 1.0
+anchor_bottom = 1.0
+grow_horizontal = 2
+grow_vertical = 2
+script = ExtResource("1_wl")
+
+[node name="VBoxContainer" type="VBoxContainer" parent="."]
+layout_mode = 1
+anchors_preset = 15
+anchor_right = 1.0
+anchor_bottom = 1.0
+grow_horizontal = 2
+grow_vertical = 2
+theme_override_constants/separation = 8
+
+[node name="HeaderHBox" type="HBoxContainer" parent="VBoxContainer"]
+layout_mode = 3
+size_flags_horizontal = 3
+theme_override_constants/separation = 16
+
+[node name="BackButton" type="Button" parent="VBoxContainer/HeaderHBox"]
+layout_mode = 3
+text = "< Back"
+size_flags_horizontal = 0
+
+[node name="TitleLabel" type="Label" parent="VBoxContainer/HeaderHBox"]
+layout_mode = 3
+text = "Browse Worlds"
+horizontal_alignment = 1
+size_flags_horizontal = 3
+theme_override_font_sizes/font_size = 28
+
+[node name="RefreshButton" type="Button" parent="VBoxContainer/HeaderHBox"]
+layout_mode = 3
+text = "Refresh"
+size_flags_horizontal = 0
+
+[node name="ScrollContainer" type="ScrollContainer" parent="VBoxContainer"]
+layout_mode = 3
+size_flags_horizontal = 3
+size_flags_vertical = 3
+horizontal_mode = 2
+vertical_mode = 2
+
+[node name="WorldList" type="VBoxContainer" parent="VBoxContainer/ScrollContainer"]
+layout_mode = 3
+size_flags_horizontal = 3
+theme_override_constants/separation = 8
+
+[node name="LoadingLabel" type="Label" parent="VBoxContainer"]
+layout_mode = 3
+text = "Loading worlds..."
+visible = false
+horizontal_alignment = 1
+theme_override_font_sizes/font_size = 18
+
+[node name="ErrorLabel" type="Label" parent="VBoxContainer"]
+layout_mode = 3
+text = ""
+visible = false
+horizontal_alignment = 1
+theme_override_font_sizes/font_size = 18
+
+[node name="EmptyLabel" type="Label" parent="VBoxContainer"]
+layout_mode = 3
+text = ""
+visible = false
+horizontal_alignment = 1
+theme_override_font_sizes/font_size = 18
+
+[connection signal="pressed" from="VBoxContainer/HeaderHBox/BackButton" to="." method="_on_back_button_pressed"]
+[connection signal="pressed" from="VBoxContainer/HeaderHBox/RefreshButton" to="." method="_on_refresh_button_pressed"]

scripts/api_client.gd

@@ -0,0 +1,292 @@
+extends Node
+## Central HTTP client singleton (autoload name: "ApiClient").
+##
+## Every network call in the game flows through this class. Callers use the
+## high-level helpers ([method login], [method register], [method get_worlds],
+## [method health_check], [method get_me]) or the generic [method request]
+## primitive. All results conform to the result-dictionary contract below.
+##
+## [b]Result Dictionary Contract[/b]
+## Every public method returns (after `await`) a Dictionary with this shape:
+##
+##     {
+##         "ok":     bool,     # true for HTTP 2xx, false otherwise
+##         "status": int,      # HTTP status code (0 on network failure)
+##         "data":   Variant,  # parsed JSON body on success (null otherwise)
+##         "detail": String,   # human-readable message
+##     }
+##
+## Network failures (timeout / DNS / refused connection) return `status == 0`
+## with a `detail` describing the transport failure. Non-2xx responses return
+## the real HTTP status and the backend's `detail` field from the JSON error
+## body when present. No caller can crash on a failed request.
+##
+## [b]Token storage[/b]
+## JWTs are kept in memory. [method set_token] is the single seam for future
+## disk persistence (override it to save to `user://`).
+##
+## [b]Usage[/b]
+##     var result: Dictionary = await ApiClient.login("alice", "secret")
+##     if result.ok:
+##         print("Logged in!")
+##     else:
+##         print("Error: ", result.detail)
+
+# ---------------------------------------------------------------------------
+# Token storage
+# ---------------------------------------------------------------------------
+
+var _access_token: String = ""
+var _token_type: String = "Bearer"
+
+## Full Authorization header value, e.g. "Bearer eyJ...". Empty if no token.
+var bearer_token: String:
+	get:
+		return _token_type + " " + _access_token if _access_token != "" else ""
+
+
+## Whether an access token is currently stored.
+func has_token() -> bool:
+	return _access_token != ""
+
+
+## Set the access token (called after login / register / token refresh).
+## This is the persistence seam: override to also write to disk.
+func set_token(access_token: String, token_type: String = "Bearer") -> void:
+	_access_token = access_token
+	_token_type = token_type
+
+
+## Clear stored tokens.
+func clear_token() -> void:
+	_access_token = ""
+	_token_type = "Bearer"
+
+
+# ---------------------------------------------------------------------------
+# Configuration
+# ---------------------------------------------------------------------------
+
+var _base_url: String = "http://127.0.0.1:8000"
+
+## Request timeout in seconds. 0 disables the timeout.
+var timeout_seconds: float = 10.0
+
+
+func _ready() -> void:
+	# Environment variable override (e.g. for headless smoke tests against a
+	# backend on a non-default port). Falls back to the ProjectSetting, then
+	# to the documented default.
+	var env_url := OS.get_environment("AGP_API_BASE_URL")
+	if env_url != "":
+		_base_url = env_url.rstrip("/")
+	else:
+		_base_url = str(ProjectSettings.get_setting(
+			"application/agp/api_base_url",
+			"http://127.0.0.1:8000"
+		)).rstrip("/")
+
+
+# ---------------------------------------------------------------------------
+# Core request primitive
+# ---------------------------------------------------------------------------
+
+## Generic request primitive. Awaitable via `await`.
+##
+## Uses a dedicated HTTPRequest node per call so concurrent requests can never
+## cross-talk, and so the result maps 1:1 to the awaiting caller.
+##
+## @param method       HTTPClient.Method enum value (GET/POST/PUT/PATCH/DELETE).
+## @param path         URL path, e.g. "/api/health".
+## @param body         Request body string (JSON or form-encoded).
+## @param content_type "application/json" or "application/x-www-form-urlencoded".
+## @param require_auth If true, attach the stored bearer token when present.
+## @return Result dictionary conforming to the contract.
+func request(
+	method: HTTPClient.Method,
+	path: String,
+	body: String = "",
+	content_type: String = "application/json",
+	require_auth: bool = false
+) -> Dictionary:
+	var http := HTTPRequest.new()
+	http.timeout = timeout_seconds
+	http.max_redirects = 8
+	http.accept_gzip = true
+	add_child(http)
+
+	var headers := PackedStringArray()
+	headers.append("Accept: application/json")
+	if content_type != "":
+		headers.append("Content-Type: " + content_type)
+	if require_auth and has_token():
+		headers.append("Authorization: " + bearer_token)
+
+	var url := _base_url + path
+	var err := http.request(url, headers, method, body)
+	if err != OK:
+		http.queue_free()
+		return _make_result(false, 0, null, "Failed to start request: " + _error_string(err))
+
+	# request_completed emits (result, response_code, headers, body).
+	var args: Array = await http.request_completed
+	var result_code: int = args[0]
+	var response_code: int = args[1]
+	var response_body: PackedByteArray = args[3]
+	http.queue_free()
+
+	# Transport-level failure (timeout / DNS / refused / TLS, etc.).
+	if result_code != HTTPRequest.RESULT_SUCCESS:
+		return _make_result(false, 0, null, _transport_error_detail(result_code))
+
+	# Server accepted the connection but returned no HTTP status line.
+	if response_code == 0:
+		return _make_result(false, 0, null, "No response received from server.")
+
+	var json_string := response_body.get_string_from_utf8()
+	var ok := response_code >= 200 and response_code < 300
+
+	if ok:
+		var data: Variant = _parse_json(json_string)
+		return _make_result(true, response_code, data, "OK")
+
+	# Non-2xx: surface the backend's "detail" message when available.
+	var detail := "HTTP error %d" % response_code
+	var parsed: Variant = _parse_json(json_string)
+	if parsed is Dictionary and (parsed as Dictionary).has("detail"):
+		detail = str((parsed as Dictionary)["detail"])
+	return _make_result(false, response_code, null, detail)
+
+
+# ---------------------------------------------------------------------------
+# High-level helpers
+# ---------------------------------------------------------------------------
+
+## Log in with username/password (OAuth2PasswordRequestForm).
+## On success stores the returned access token.
+func login(username: String, password: String) -> Dictionary:
+	var form := "username=" + username.uri_encode() + "&password=" + password.uri_encode()
+	var result := await request(
+		HTTPClient.METHOD_POST,
+		"/api/auth/login",
+		form,
+		"application/x-www-form-urlencoded",
+		false
+	)
+	_store_token_from_result(result)
+	return result
+
+
+## Register a new user. On success stores the returned access token.
+## @param date_of_birth ISO date string "YYYY-MM-DD".
+func register(
+	username: String,
+	email: String,
+	password: String,
+	date_of_birth: String
+) -> Dictionary:
+	var payload := {
+		"username": username,
+		"email": email,
+		"password": password,
+		"date_of_birth": date_of_birth,
+	}
+	var result := await request(
+		HTTPClient.METHOD_POST,
+		"/api/auth/register",
+		JSON.stringify(payload),
+		"application/json",
+		false
+	)
+	_store_token_from_result(result)
+	return result
+
+
+## List worlds visible to the current user (requires auth).
+## @param visibility Optional filter: "public", "private", "friends_only".
+func get_worlds(skip: int = 0, limit: int = 50, visibility: String = "") -> Dictionary:
+	var path := "/api/worlds/?skip=%d&limit=%d" % [skip, limit]
+	if visibility != "":
+		path += "&visibility=" + visibility.uri_encode()
+	return await request(HTTPClient.METHOD_GET, path, "", "application/json", true)
+
+
+## Ping the backend health endpoint (no auth).
+func health_check() -> Dictionary:
+	return await request(HTTPClient.METHOD_GET, "/api/health", "", "application/json", false)
+
+
+## Fetch the current user's profile from the stored JWT (requires auth).
+func get_me() -> Dictionary:
+	return await request(HTTPClient.METHOD_GET, "/api/users/me", "", "application/json", true)
+
+
+# ---------------------------------------------------------------------------
+# Internals
+# ---------------------------------------------------------------------------
+
+func _store_token_from_result(result: Dictionary) -> void:
+	if result.ok and result.data is Dictionary:
+		var token: String = str((result.data as Dictionary).get("access_token", ""))
+		if token != "":
+			set_token(token)
+
+
+func _parse_json(text: String) -> Variant:
+	if text == "":
+		return null
+	var parsed: Variant = JSON.parse_string(text)
+	if parsed == null:
+		# null is ambiguous (valid JSON "null" vs parse failure). Fall back to
+		# the raw string so callers never lose the body entirely.
+		return text if text != "null" else null
+	return parsed
+
+
+func _make_result(ok: bool, status: int, data: Variant, detail: String) -> Dictionary:
+	return {
+		"ok": ok,
+		"status": status,
+		"data": data,
+		"detail": detail,
+	}
+
+
+func _transport_error_detail(result_code: int) -> String:
+	match result_code:
+		HTTPRequest.RESULT_CANT_CONNECT:
+			return "Could not connect to server. Is it running?"
+		HTTPRequest.RESULT_CANT_RESOLVE:
+			return "Could not resolve server hostname."
+		HTTPRequest.RESULT_CONNECTION_ERROR:
+			return "Connection error."
+		HTTPRequest.RESULT_TLS_HANDSHAKE_ERROR:
+			return "TLS handshake failed."
+		HTTPRequest.RESULT_NO_RESPONSE:
+			return "No response from server."
+		HTTPRequest.RESULT_BODY_SIZE_LIMIT_EXCEEDED:
+			return "Response body too large."
+		HTTPRequest.RESULT_BODY_DECOMPRESS_FAILED:
+			return "Failed to decompress response body."
+		HTTPRequest.RESULT_REQUEST_FAILED:
+			return "Request failed."
+		HTTPRequest.RESULT_TIMEOUT:
+			return "Request timed out."
+		_:
+			return "Network error (code %d)." % result_code
+
+
+func _error_string(err_code: int) -> String:
+	match err_code:
+		OK:
+			return "OK"
+		ERR_UNCONFIGURED:
+			return "HTTPRequest not configured (not in tree)."
+		ERR_BUSY:
+			return "HTTPRequest is busy with a previous request."
+		ERR_INVALID_PARAMETER:
+			return "Invalid URL format."
+		ERR_CANT_CONNECT:
+			return "Cannot connect to host."
+		_:
+			return "Unknown error (%d)." % err_code

scripts/build.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+# Headless CI export for Linux and Windows.
+#
+# Requires:
+#   - Godot 4.6.2 (the exact version this project + export_presets.cfg were
+#     built against; a different Godot minor version's export templates are
+#     not guaranteed compatible)
+#   - The matching export templates installed at
+#     ~/.local/share/godot/export_templates/4.6.2.stable/
+#     (download: https://godotengine.org/download/archive/4.6.2-stable/,
+#     "Export templates" -- NOT the same as the editor download)
+#   - godot on PATH (or set GODOT_BIN below)
+#
+# Usage: scripts/build.sh
+# Output: export/linux/agp-game.x86_64, export/windows/agp-game.exe
+
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+GODOT_BIN="${GODOT_BIN:-godot}"
+if ! command -v "$GODOT_BIN" >/dev/null 2>&1; then
+    if [ -x "$HOME/godot/godot" ]; then
+        GODOT_BIN="$HOME/godot/godot"
+    else
+        echo "godot binary not found (checked PATH and ~/godot/godot)." >&2
+        exit 1
+    fi
+fi
+
+echo "Godot version: $("$GODOT_BIN" --version)"
+
+mkdir -p export/linux export/windows
+
+echo "=== Exporting Linux/X11 ==="
+"$GODOT_BIN" --headless --path . --export-release "Linux" export/linux/agp-game.x86_64
+
+echo "=== Exporting Windows Desktop ==="
+"$GODOT_BIN" --headless --path . --export-release "Windows Desktop" export/windows/agp-game.exe
+
+echo ""
+echo "Build artifacts:"
+ls -la export/linux export/windows

scripts/main_menu.gd

@@ -1,14 +1,274 @@
 extends Control
+## Main menu with login/register UI wired to the backend auth API.
+##
+## The AuthPanel is hidden by default. When the user clicks the LoginButton or
+## RegisterButton (AuthButtonsRow, above the panel), the auth panel slides in.
+## The ModeToggle switches between Login and Register modes, showing/hiding
+## the email and DOB fields accordingly.
+##
+## On successful auth the token is stored via ApiClient, AuthButtonsRow hides,
+## the welcome label shows the username, and the Play button becomes enabled.
+##
+## When returning from another scene (e.g. world_list), _ready() checks whether
+## ApiClient already holds a valid token. If so, it restores the authenticated
+## UI state (Play enabled, welcome label visible) instead of forcing the user
+## back to the login form.
 
 
-func _ready():
-	pass
+## Emitted once _ready()'s session check (has_token() + the awaited
+## get_me() call) has actually resolved, whichever way -- lets a test (or
+## anything else) know the UI state is trustworthy now, rather than
+## guessing from a frame count or from UI properties that are ambiguous
+## mid-await (e.g. AuthButtonsRow.visible is true both before the check
+## resolves AND in a genuine logged-out end state).
+signal auth_state_ready
+
+# ─── UI references ────────────────────────────────────────────────────────────
+
+var _auth_buttons_row: HBoxContainer
+var _login_button: Button
+var _register_button: Button
+var _auth_panel: PanelContainer
+var _auth_mode_label: Label
+var _username_edit: LineEdit
+var _password_edit: LineEdit
+var _email_edit: LineEdit
+var _dob_edit: LineEdit
+var _mode_toggle: CheckButton
+var _auth_button: Button
+var _status_label: Label
+var _welcome_label: Label
+var _play_button: Button
+var _quit_button: Button
+
+var _is_register_mode: bool = false
+var _is_authenticating: bool = false
 
 
-func _on_play_button_pressed():
-	# No gameplay scene exists yet — wire this to the real scene once one lands.
-	print("Play pressed — no gameplay scene yet")
+# ─── Lifecycle ────────────────────────────────────────────────────────────────
+
+func _ready() -> void:
+	# Cache node references.
+	_auth_buttons_row = $CenterContainer/VBoxContainer/AuthButtonsRow
+	_login_button = $CenterContainer/VBoxContainer/AuthButtonsRow/LoginButton
+	_register_button = $CenterContainer/VBoxContainer/AuthButtonsRow/RegisterButton
+	_auth_panel = $CenterContainer/VBoxContainer/AuthPanel
+	_auth_mode_label = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/AuthModeLabel
+	_username_edit = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/UsernameEdit
+	_password_edit = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/PasswordEdit
+	_email_edit = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/EmailEdit
+	_dob_edit = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/DOBEdit
+	_mode_toggle = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/ModeToggle
+	_auth_button = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/AuthButton
+	_status_label = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/AuthStatusLabel
+	_welcome_label = $CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/WelcomeLabel
+	_play_button = $CenterContainer/VBoxContainer/PlayButton
+	_quit_button = $CenterContainer/VBoxContainer/QuitButton
+
+	# Default to Play being gated. When a token exists, the async session
+	# check below may take several frames (a real get_me() round-trip);
+	# keeping the button disabled until validation succeeds prevents a fast
+	# click from navigating to world_list with an expired/invalid token.
+	_play_button.disabled = true
+
+	# Check whether a valid session already exists (e.g. user logged in,
+	# navigated to world_list, then clicked Back). If so, restore the
+	# authenticated UI state instead of forcing the login form again.
+	if ApiClient.has_token():
+		var me_result: Dictionary = await ApiClient.get_me()
+		if me_result.ok and me_result.data is Dictionary:
+			var username: String = str((me_result.data as Dictionary).get("username", ""))
+			if username != "":
+				_show_authenticated(username)
+				auth_state_ready.emit()
+				return
+
+	# Token missing or invalid — fall through to logged-out state.
+	_reset_to_logged_out()
+	auth_state_ready.emit()
 
 
-func _on_quit_button_pressed():
+## Restore the UI to the authenticated state (Play enabled, welcome label,
+## auth buttons hidden).
+func _show_authenticated(username: String) -> void:
+	_auth_panel.visible = true
+	_status_label.visible = false
+	_welcome_label.text = "Welcome, %s!" % username
+	_welcome_label.visible = true
+	_email_edit.visible = false
+	_dob_edit.visible = false
+	_play_button.disabled = false
+	_auth_buttons_row.visible = false
+	print("Restored authenticated session for: ", username)
+
+
+## Reset the UI to the logged-out state (Play disabled, auth panel hidden,
+## login/register buttons visible).
+func _reset_to_logged_out() -> void:
+	_auth_panel.visible = false
+	_status_label.visible = false
+	_welcome_label.visible = false
+	_email_edit.visible = false
+	_dob_edit.visible = false
+	_play_button.disabled = true  # Gate play behind successful auth.
+	_update_auth_mode_ui()
+
+
+# ─── Play / Quit ─────────────────────────────────────────────────────────────
+
+func _on_play_button_pressed() -> void:
+	if _play_button.disabled:
+		return
+	# Browse worlds is the first real screen past login -- actual gameplay
+	# (joining a world) doesn't exist yet, browsing does.
+	get_tree().change_scene_to_file("res://scenes/world_list.tscn")
+
+
+func _on_quit_button_pressed() -> void:
 	get_tree().quit()
+
+
+# ─── Auth panel toggle ───────────────────────────────────────────────────────
+
+func _on_login_button_pressed() -> void:
+	"""Show the auth panel, called from AuthButtonsRow/LoginButton."""
+	_auth_panel.visible = true
+	_username_edit.grab_focus()
+
+
+func _on_register_button_pressed() -> void:
+	"""Show the auth panel in register mode, called from AuthButtonsRow/RegisterButton."""
+	_auth_panel.visible = true
+	_is_register_mode = true
+	_mode_toggle.button_pressed = true
+	_update_auth_mode_ui()
+	_clear_status()
+	_username_edit.grab_focus()
+
+
+# ─── Mode toggle (Login / Register) ──────────────────────────────────────────
+
+func _on_mode_toggle_toggled(button_pressed: bool) -> void:
+	_is_register_mode = button_pressed
+	_update_auth_mode_ui()
+	_clear_status()
+
+
+func _update_auth_mode_ui() -> void:
+	"""Update labels and field visibility based on login vs register mode."""
+	if _is_register_mode:
+		_auth_mode_label.text = "Register"
+		_auth_button.text = "Register"
+		_email_edit.visible = true
+		_dob_edit.visible = true
+	else:
+		_auth_mode_label.text = "Login"
+		_auth_button.text = "Login"
+		_email_edit.visible = false
+		_dob_edit.visible = false
+
+
+# ─── Auth submission ─────────────────────────────────────────────────────────
+
+func _on_auth_button_pressed() -> void:
+	"""Handle login or register button press."""
+	if _is_authenticating:
+		return
+
+	# Validate inputs.
+	var username := _username_edit.text.strip_edges()
+	var password := _password_edit.text
+
+	if username == "":
+		_show_status("Username is required.")
+		return
+	if password == "":
+		_show_status("Password is required.")
+		return
+
+	if _is_register_mode:
+		var email := _email_edit.text.strip_edges()
+		var dob := _dob_edit.text.strip_edges()
+
+		if email == "":
+			_show_status("Email is required.")
+			return
+		if dob == "":
+			_show_status("Date of birth is required.")
+			return
+		# Basic YYYY-MM-DD format check.
+		if not _is_valid_date(dob):
+			_show_status("Date of birth must be in YYYY-MM-DD format.")
+			return
+
+		_auth_button.disabled = true
+		_auth_button.text = "Registering..."
+		_is_authenticating = true
+		_clear_status()
+
+		var result := await ApiClient.register(username, email, password, dob)
+		_on_auth_complete(result)
+	else:
+		_auth_button.disabled = true
+		_auth_button.text = "Logging in..."
+		_is_authenticating = true
+		_clear_status()
+
+		var result := await ApiClient.login(username, password)
+		_on_auth_complete(result)
+
+
+func _on_auth_complete(result: Dictionary) -> void:
+	"""Handle the result of a login or register call."""
+	_auth_button.disabled = false
+	_auth_button.text = "Register" if _is_register_mode else "Login"
+	_is_authenticating = false
+
+	if result.ok:
+		# Success — show welcome, enable Play, hide the now-redundant
+		# Login/Register entry points (the auth panel itself stays open,
+		# showing the welcome message in place of the form).
+		_welcome_label.text = "Welcome, %s!" % _username_edit.text.strip_edges()
+		_welcome_label.visible = true
+		_status_label.visible = false
+		_play_button.disabled = false
+		_auth_buttons_row.visible = false
+		print("Auth successful. Token stored.")
+	else:
+		# Failure — show backend error detail.
+		_show_status(result.detail)
+
+
+# ─── Status helpers ──────────────────────────────────────────────────────────
+
+func _show_status(message: String) -> void:
+	_status_label.text = message
+	_status_label.visible = true
+
+
+func _clear_status() -> void:
+	_status_label.text = ""
+	_status_label.visible = false
+
+
+# ─── Validation ──────────────────────────────────────────────────────────────
+
+func _is_valid_date(date_str: String) -> bool:
+	"""Check if a string looks like a valid YYYY-MM-DD date."""
+	if date_str.length() != 10:
+		return false
+	var parts := date_str.split("-")
+	if parts.size() != 3:
+		return false
+	var year := parts[0].to_int()
+	var month := parts[1].to_int()
+	var day := parts[2].to_int()
+	if month < 1 or month > 12:
+		return false
+	if day < 1 or day > 31:
+		return false
+	# Rough month-day validation.
+	var days_in_month := [0, 31, 29, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]
+	if day > days_in_month[month]:
+		return false
+	return true

scripts/run_checkpoint_tests.py

@@ -0,0 +1,170 @@
+#!/usr/bin/env python3
+"""Run the full automated test inventory for a Package Checkpoint review.
+
+See docs/testing/test_inventory.md for what each suite actually covers (and
+doesn't) -- keep that doc in sync as tests are added, this script just runs
+whatever's there.
+
+Usage:
+    python scripts/run_checkpoint_tests.py [--keep-postgres] [--postgres-port PORT]
+
+Exits 0 if everything that ran passed, 1 otherwise. Suites with nothing to
+run (e.g. no scripts/smoke_test_*.gd yet, or no Godot binary found) are
+reported as SKIPPED, not counted as a failure.
+"""
+import argparse
+import glob
+import os
+import shutil
+import subprocess
+import sys
+import time
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parent.parent
+BACKEND = ROOT / "backend"
+
+
+def run(cmd, cwd=None, env=None, capture=False):
+    print(f"$ {' '.join(cmd)}" + (f"  (cwd={cwd})" if cwd else ""))
+    return subprocess.run(cmd, cwd=cwd, env=env, capture_output=capture, text=True)
+
+
+def find_godot():
+    for candidate in ("godot", str(Path.home() / "godot" / "godot")):
+        if shutil.which(candidate) or Path(candidate).is_file():
+            return candidate
+    return None
+
+
+def wait_for_http(url: str, timeout_s: int = 20) -> bool:
+    import urllib.request
+    import urllib.error
+
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        try:
+            with urllib.request.urlopen(url, timeout=2) as resp:
+                if resp.status == 200:
+                    return True
+        except (urllib.error.URLError, ConnectionError, OSError):
+            pass
+        time.sleep(1)
+    return False
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    parser.add_argument("--keep-postgres", action="store_true",
+                         help="Don't tear down the checkpoint Postgres container afterward")
+    parser.add_argument("--postgres-port", default=os.environ.get("CHECKPOINT_POSTGRES_PORT", "5432"),
+                         help="Host port for the checkpoint's own Postgres container (default 5432 -- "
+                              "override if that's already in use on this machine)")
+    parser.add_argument("--backend-port", default=os.environ.get("CHECKPOINT_BACKEND_PORT", "18080"),
+                         help="Port to run the backend server on for the Godot smoke tests")
+    args = parser.parse_args()
+
+    results = {}
+
+    # --- Backend: bring up Postgres ---
+    compose_env = os.environ.copy()
+    compose_env["COMPOSE_PROJECT_NAME"] = "agp-checkpoint"
+    compose_env["POSTGRES_HOST_PORT"] = args.postgres_port
+    compose_env["POSTGRES_PORT"] = args.postgres_port  # some branches use this name instead, see tools/definitions.py
+    print("=== Backend: bringing up Postgres ===")
+    run(["docker", "compose", "up", "-d", "postgres"], cwd=BACKEND, env=compose_env)
+
+    print("Waiting for Postgres to be ready...")
+    pg_ready = False
+    for _ in range(20):
+        r = run(["docker", "compose", "exec", "-T", "postgres", "pg_isready", "-U", "agp_user", "-d", "agp_db"],
+                cwd=BACKEND, env=compose_env, capture=True)
+        if r.returncode == 0:
+            pg_ready = True
+            break
+        time.sleep(1)
+    if not pg_ready:
+        print("Postgres never became ready -- aborting.")
+        sys.exit(1)
+
+    db_url = f"postgresql+asyncpg://agp_user:agp_password@localhost:{args.postgres_port}/agp_db"
+    backend_env = os.environ.copy()
+    backend_env["DATABASE_URL"] = db_url
+
+    print("\n=== Backend: alembic upgrade head ===")
+    r = run([sys.executable, "-m", "alembic", "upgrade", "head"], cwd=BACKEND, env=backend_env)
+    results["migrations (fresh DB)"] = r.returncode == 0
+
+    print("\n=== Backend: pytest ===")
+    r = run([sys.executable, "-m", "pytest", "-v"], cwd=BACKEND, env=backend_env)
+    results["backend pytest"] = r.returncode == 0
+
+    # --- Godot: headless smoke tests (need a live backend server) ---
+    godot_bin = find_godot()
+    smoke_tests = sorted(glob.glob(str(ROOT / "scripts" / "smoke_test_*.gd")))
+
+    if not godot_bin:
+        print("\n=== Godot: binary not found (checked PATH and ~/godot/godot), skipping smoke tests ===")
+        results["godot smoke tests"] = None
+    elif not smoke_tests:
+        print("\n=== Godot: no scripts/smoke_test_*.gd found yet, nothing to run ===")
+        results["godot smoke tests"] = None
+    else:
+        print(f"\n=== Backend: starting server on :{args.backend_port} for Godot smoke tests ===")
+        server_proc = subprocess.Popen(
+            [sys.executable, "-m", "uvicorn", "app.main:app", "--host", "127.0.0.1", "--port", args.backend_port],
+            cwd=BACKEND, env=backend_env,
+            stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
+        )
+        try:
+            base_url = f"http://127.0.0.1:{args.backend_port}"
+            if not wait_for_http(f"{base_url}/api/health"):
+                print("Backend server never became healthy -- skipping Godot smoke tests.")
+                results["godot smoke tests"] = False
+            else:
+                godot_env = os.environ.copy()
+                godot_env["AGP_API_BASE_URL"] = base_url
+
+                print("=== Godot: import pass (builds the class cache) ===")
+                run([godot_bin, "--headless", "--path", str(ROOT), "--import"], env=godot_env)
+                run([godot_bin, "--headless", "--path", str(ROOT), "--quit"], env=godot_env)
+
+                godot_ok = True
+                for test in smoke_tests:
+                    rel = os.path.relpath(test, ROOT)
+                    print(f"\n--- {rel} ---")
+                    r = run([godot_bin, "--headless", "--path", str(ROOT), "--script", f"res://{rel}"], env=godot_env)
+                    if r.returncode != 0:
+                        godot_ok = False
+                results["godot smoke tests"] = godot_ok
+        finally:
+            server_proc.terminate()
+            try:
+                server_proc.wait(timeout=10)
+            except subprocess.TimeoutExpired:
+                server_proc.kill()
+
+    if not args.keep_postgres:
+        print("\n=== Backend: tearing down checkpoint Postgres ===")
+        run(["docker", "compose", "down", "-v", "postgres"], cwd=BACKEND, env=compose_env)
+
+    # --- Summary ---
+    print("\n" + "=" * 50)
+    print("SUMMARY")
+    print("=" * 50)
+    overall_ok = True
+    for name, ok in results.items():
+        if ok is None:
+            print(f"  {name}: SKIPPED")
+        elif ok:
+            print(f"  {name}: PASS")
+        else:
+            print(f"  {name}: FAIL")
+            overall_ok = False
+
+    print("\nSee docs/testing/test_inventory.md for what each suite actually covers (and doesn't).")
+    sys.exit(0 if overall_ok else 1)
+
+
+if __name__ == "__main__":
+    main()

scripts/smoke_test_api.gd

@@ -0,0 +1,46 @@
+extends SceneTree
+## Headless smoke test for the ApiClient autoload.
+##
+## Run with:
+##     godot --headless --path . --script res://scripts/smoke_test_api.gd
+##
+## Requires the backend to be running (default base URL
+## `application/agp/api_base_url` -> http://127.0.0.1:8000).
+##
+## Calls the real autoload's `health_check()` (which exercises the generic
+## `request()` primitive) and exits 0 on a `status == "ok"` response, 1
+## otherwise. This script is intentionally NOT wired into any game scene.
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	# _initialize() fires before the SceneTree has processed its first frame,
+	# so a freshly add_child()'d HTTPRequest node isn't reliably considered
+	# "inside tree" yet (request_raw fails with !is_inside_tree()). One frame
+	# of delay is enough; this only matters for --script mode, not a real
+	# running game.
+	await process_frame
+
+	# Godot's --script/SceneTree runner doesn't resolve autoload singletons
+	# as bare global identifiers at compile time (the node exists at
+	# runtime -- root.has_node("ApiClient") is true -- but referencing it as
+	# a plain identifier fails with "Identifier not found: ApiClient" during
+	# script compilation). get_node sidesteps compile-time resolution
+	# entirely. This only affects --script mode; a real game scene resolves
+	# the bare autoload name normally.
+	var api_client := root.get_node("ApiClient")
+	print("SMOKE: calling ApiClient.health_check() ...")
+	var result: Dictionary = await api_client.health_check()
+	print("SMOKE: result = ", result)
+
+	if result.ok \
+			and result.data is Dictionary \
+			and str((result.data as Dictionary).get("status", "")) == "ok":
+		print("SMOKE RESULT: PASS (status=ok)")
+		quit(0)
+	else:
+		printerr("SMOKE RESULT: FAIL")
+		quit(1)

scripts/smoke_test_auth.gd

@@ -0,0 +1,133 @@
+extends SceneTree
+## Headless smoke test for the AuthPanel login/register flow.
+##
+## Run with:
+##     godot --headless --path . --script res://scripts/smoke_test_auth.gd
+##
+## Requires the backend to be running (default base URL
+## `application/agp/api_base_url` -> http://127.0.0.1:8000).
+##
+## Tests:
+##   1. Register a unique user → 201 + token stored.
+##   2. Register the same user again → 409 "Username already registered".
+##   3. Register an under-18 user → 400 "Must be 18 or older".
+##   4. Login with correct credentials → 200 + token stored.
+##   5. Login with wrong password → 401 "Incorrect username or password".
+##   6. Login with non-existent user → 401 "Incorrect username or password".
+##
+## Exits 0 on full pass, 1 on any failure.
+
+const API_BASE := "http://127.0.0.1:8000"
+const TEST_USERNAME := "smoke_test_user_%d"
+const TEST_EMAIL := "smoke_%d@test.example.com"
+const TEST_PASSWORD := "SmokeTest123!"
+const TEST_DOB_ADULT := "2000-01-01"
+const TEST_DOB_CHILD := "2020-01-01"  # ~5 years old
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	# Wait for autoloads to be ready.
+	await process_frame
+
+	var api := root.get_node("ApiClient") as ApiClient
+	assert(api != null, "ApiClient autoload not found")
+
+	var passed: int = 0
+	var failed: int = 0
+
+	# --- Test 1: Register a unique user ---
+	var unique_id := Time.get_ticks_msec()
+	var username := "smoke_%d" % unique_id
+	var email := "smoke_%d@test.example.com" % unique_id
+
+	print("\n=== Test 1: Register unique user ===")
+	var result := await api.register(username, email, TEST_PASSWORD, TEST_DOB_ADULT)
+	if _check("register returns ok", result.ok) \
+			and _check("register status is 201", result.status == 201) \
+			and _check("register stores token", api.has_token()):
+		passed += 1
+	else:
+		failed += 1
+		print("  detail: ", result.detail)
+
+	# --- Test 2: Register same user again (duplicate) ---
+	print("\n=== Test 2: Duplicate username ===")
+	result = await api.register(username, email, TEST_PASSWORD, TEST_DOB_ADULT)
+	if _check("duplicate register not ok", not result.ok) \
+			and _check("duplicate status is 409", result.status == 409) \
+			and _check("duplicate detail mentions username",
+					"username" in result.detail.to_lower()):
+		passed += 1
+	else:
+		failed += 1
+		print("  detail: ", result.detail)
+
+	# --- Test 3: Register under-18 user ---
+	print("\n=== Test 3: Under-18 registration ===")
+	var child_username := "child_%d" % unique_id
+	var child_email := "child_%d@test.example.com" % unique_id
+	result = await api.register(child_username, child_email, TEST_PASSWORD, TEST_DOB_CHILD)
+	if _check("under-18 register not ok", not result.ok) \
+			and _check("under-18 status is 400", result.status == 400) \
+			and _check("under-18 detail mentions age",
+					"18" in result.detail):
+		passed += 1
+	else:
+		failed += 1
+		print("  detail: ", result.detail)
+
+	# --- Test 4: Login with correct credentials ---
+	print("\n=== Test 4: Correct login ===")
+	result = await api.login(username, TEST_PASSWORD)
+	if _check("login returns ok", result.ok) \
+			and _check("login status is 200", result.status == 200) \
+			and _check("login stores token", api.has_token()):
+		passed += 1
+	else:
+		failed += 1
+		print("  detail: ", result.detail)
+
+	# --- Test 5: Login with wrong password ---
+	print("\n=== Test 5: Wrong password ===")
+	result = await api.login(username, "WrongPassword!")
+	if _check("wrong pwd login not ok", not result.ok) \
+			and _check("wrong pwd status is 401", result.status == 401) \
+			and _check("wrong pwd detail",
+					"Incorrect" in result.detail or "incorrect" in result.detail):
+		passed += 1
+	else:
+		failed += 1
+		print("  detail: ", result.detail)
+
+	# --- Test 6: Login with non-existent user ---
+	print("\n=== Test 6: Non-existent user ===")
+	result = await api.login("nonexistent_user_xyz", TEST_PASSWORD)
+	if _check("missing user login not ok", not result.ok) \
+			and _check("missing user status is 401", result.status == 401) \
+			and _check("missing user detail",
+					"Incorrect" in result.detail or "incorrect" in result.detail):
+		passed += 1
+	else:
+		failed += 1
+		print("  detail: ", result.detail)
+
+	# --- Summary ---
+	print("\n=== SMOKE RESULT: %d/%d passed ===" % [passed, passed + failed])
+	if failed > 0:
+		quit(1)
+	else:
+		print("SMOKE RESULT: ALL PASS")
+		quit(0)
+
+
+func _check(description: String, condition: bool) -> bool:
+	if condition:
+		print("  PASS: ", description)
+		return true
+	else:
+		printerr("  FAIL: ", description)
+		return false

scripts/smoke_test_e2e.gd

@@ -0,0 +1,148 @@
+extends SceneTree
+## End-to-end headless smoke test: register -> login -> fetch worlds list.
+##
+## Run with:
+##     godot --headless --path . --script res://scripts/smoke_test_e2e.gd
+##
+## Requires the backend to be running (default base URL
+## `application/agp/api_base_url` -> http://127.0.0.1:8000, overridable via
+## the AGP_API_BASE_URL environment variable).
+##
+## Steps:
+##   1. Health check  GET  /api/health          -> 200, {"status": "ok"}
+##   2. Register      POST /api/auth/register   -> 201, access_token present
+##   3. Login         POST /api/auth/login      -> 200, access_token present
+##   4. Worlds list   GET  /api/worlds          -> 200, JSON array
+##
+## Exits 0 if all steps pass, 1 otherwise. If the backend is unreachable the
+## health check fails with a clear message and the script exits 1 immediately.
+
+# Fixed credentials from the task spec. The username gets a unique numeric
+# suffix so the test stays re-runnable (a second run would otherwise hit
+# "Username already registered" on step 2).
+const TEST_USERNAME_BASE := "smoke_test_user"
+const TEST_EMAIL := "smoke@test.com"
+const TEST_PASSWORD := "TestPass123"
+const TEST_DOB := "2000-01-01"
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	# _initialize() fires before the first frame; wait one frame so freshly
+	# created HTTPRequest nodes are reliably inside the tree.
+	await process_frame
+
+	# In --script mode the autoload is reachable via get_node(), not as a
+	# bare identifier (bare identifiers fail to resolve at compile time here).
+	var api := root.get_node("ApiClient")
+	assert(api != null, "ApiClient autoload not found in the scene tree")
+
+	var unique_id := int(Time.get_unix_time_from_system() * 1000)
+	var username := "%s_%d" % [TEST_USERNAME_BASE, unique_id]
+	var email := "smoke_%d@test.com" % unique_id
+
+	var results := {}
+
+	# --- Step 1: Health check -------------------------------------------------
+	print("\n=== Step 1: Health check (GET /api/health) ===")
+	var health: Dictionary = await api.health_check()
+	var health_ok: bool = (
+		health.ok
+		and health.status == 200
+		and health.data is Dictionary
+		and str((health.data as Dictionary).get("status", "")) == "ok"
+	)
+	_record(results, "health", health_ok, "status=%d data=%s" % [
+		health.status, health.data
+	])
+
+	if not health.ok or health.status == 0:
+		printerr("\nERROR: Backend is not reachable at the configured base URL.")
+		printerr("       detail: %s" % health.detail)
+		printerr("       Start the backend first (see backend/README), then re-run:")
+		printerr("       godot --headless --path . --script res://scripts/smoke_test_e2e.gd")
+		_summarize(results)
+		quit(1)
+		return
+
+	# --- Step 2: Register -----------------------------------------------------
+	print("\n=== Step 2: Register (POST /api/auth/register) ===")
+	var reg: Dictionary = await api.register(username, email, TEST_PASSWORD, TEST_DOB)
+	var reg_token := _extract_token(reg)
+	var reg_ok: bool = (
+		reg.ok
+		and reg.status == 201
+		and reg_token != ""
+	)
+	_record(results, "register", reg_ok, "status=%d token=%s detail=%s" % [
+		reg.status, "yes" if reg_token != "" else "no", reg.detail
+	])
+
+	# --- Step 3: Login --------------------------------------------------------
+	print("\n=== Step 3: Login (POST /api/auth/login) ===")
+	var login: Dictionary = await api.login(username, TEST_PASSWORD)
+	var login_token := _extract_token(login)
+	var login_ok: bool = (
+		login.ok
+		and login.status == 200
+		and login_token != ""
+	)
+	_record(results, "login", login_ok, "status=%d token=%s detail=%s" % [
+		login.status, "yes" if login_token != "" else "no", login.detail
+	])
+
+	# --- Step 4: Worlds list ---------------------------------------------------
+	print("\n=== Step 4: Worlds list (GET /api/worlds) ===")
+	# login/register already stored the token; make the auth header explicit by
+	# re-applying the extracted token so step 4 is independent of storage order.
+	if login_token != "":
+		api.set_token(login_token)
+	var worlds: Dictionary = await api.get_worlds()
+	var worlds_ok: bool = (
+		worlds.ok
+		and worlds.status == 200
+		and worlds.data is Array
+	)
+	_record(results, "worlds", worlds_ok, "status=%d is_array=%s count=%d detail=%s" % [
+		worlds.status,
+		"yes" if (worlds.data is Array) else "no",
+		(worlds.data as Array).size() if (worlds.data is Array) else -1,
+		worlds.detail,
+	])
+
+	# --- Summary ---------------------------------------------------------------
+	_summarize(results)
+
+
+func _extract_token(result: Dictionary) -> String:
+	if result.ok and result.data is Dictionary:
+		return str((result.data as Dictionary).get("access_token", ""))
+	return ""
+
+
+func _record(results: Dictionary, name: String, ok: bool, detail: String) -> void:
+	results[name] = {"ok": ok, "detail": detail}
+	if ok:
+		print("  PASS: %s" % detail)
+	else:
+		printerr("  FAIL: %s" % detail)
+
+
+func _summarize(results: Dictionary) -> void:
+	var all_pass := true
+	print("\n=== Smoke test summary ===")
+	for step in ["health", "register", "login", "worlds"]:
+		var entry: Dictionary = results.get(step, {"ok": false, "detail": "not run"})
+		if not entry["ok"]:
+			all_pass = false
+		print("  %-8s : %s" % [step, "PASS" if entry["ok"] else "FAIL"])
+
+	if all_pass:
+		print("SMOKE RESULT: ALL PASS (4/4)")
+		quit(0)
+	else:
+		printerr("SMOKE RESULT: FAIL")
+		quit(1)

scripts/smoke_test_main_menu_back.gd

@@ -0,0 +1,154 @@
+extends SceneTree
+## Regression test for the Play -> Back navigation bug.
+##
+## The reported bug: after logging in and clicking Play, the user lands on
+## world_list.tscn; clicking Back returns to main_menu.tscn, but the menu
+## reset to a fully logged-out state (Play disabled, login form showing)
+## even though ApiClient still held a valid token. main_menu.gd's _ready()
+## used to unconditionally reset the UI on every scene load.
+##
+## This test drives the real navigation flow (change_scene_to_file) against
+## a live backend:
+##   1. Register a unique user so ApiClient holds a valid token.
+##   2. Load main_menu.tscn and assert it restores the authenticated state.
+##   3. Click Play -> world_list.tscn.
+##   4. Click Back -> main_menu.tscn.
+##   5. Assert the menu is STILL authenticated (Play enabled, welcome label
+##      actually visible in the tree, login/register buttons hidden).
+##
+## Run with:
+##     godot --headless --path . --script res://scripts/smoke_test_main_menu_back.gd
+##
+## Requires the backend to be running (default base URL
+## `application/agp/api_base_url` -> http://127.0.0.1:8000).
+
+const USERNAME := "backnav_%d"
+const EMAIL := "backnav_%d@test.example.com"
+const PASSWORD := "BackNav123!"
+const DOB := "2000-01-01"
+
+var passed := 0
+var failed := 0
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	await process_frame
+
+	var api := root.get_node("ApiClient")
+	if api == null:
+		printerr("FAIL: ApiClient autoload not found")
+		quit(1)
+		return
+
+	# 1. Establish a real, valid session exactly the way a user would.
+	randomize()
+	var unique_id: int = int(Time.get_unix_time_from_system() * 1000) + randi() % 100000
+	var username := USERNAME % unique_id
+	var email := EMAIL % unique_id
+	print("\n=== Setup: register ", username, " ===")
+	var register_result: Dictionary = await api.register(username, email, PASSWORD, DOB)
+	if not _check("register succeeds", register_result.ok):
+		print("  detail: ", register_result.detail)
+		_finish()
+		return
+	_check("ApiClient stores token after register", api.has_token())
+
+	# 2. First visit to the main menu: should already show the authenticated
+	#    state (no login form, Play enabled).
+	change_scene_to_file("res://scenes/main_menu.tscn")
+	# change_scene_to_file defers the actual swap -- a couple frames is
+	# plenty for the scene object itself to exist (unlike the real
+	# get_me() network round-trip afterward, which is what auth_state_ready
+	# actually waits for below).
+	for i in 5:
+		await process_frame
+		if current_scene is Control:
+			break
+
+	var menu: Control = current_scene
+	if menu == null or not menu is Control:
+		printerr("FAIL: main_menu.tscn did not become current_scene")
+		_finish()
+		return
+	await menu.auth_state_ready
+	_check("first main menu visit restores authenticated state", _is_authenticated(menu))
+
+	# 3. Play -> world_list.tscn (real button press).
+	var play_button: Button = menu.get_node("CenterContainer/VBoxContainer/PlayButton")
+	play_button.pressed.emit()
+	await _wait_for_scene_change(menu)
+
+	var world_list_scene := current_scene
+	if world_list_scene == null or world_list_scene == menu:
+		printerr("FAIL: world_list.tscn did not become current_scene after Play")
+		_finish()
+		return
+
+	# 4. Back -> main_menu.tscn (real button press).
+	var back_button: Button = world_list_scene.get_node("VBoxContainer/HeaderHBox/BackButton")
+	back_button.pressed.emit()
+	await _wait_for_scene_change(world_list_scene)
+
+	menu = current_scene
+	if menu == null or not menu is Control:
+		printerr("FAIL: main_menu.tscn did not become current_scene after Back")
+		_finish()
+		return
+
+	# The new main_menu instance's own _ready() is *also* awaiting a real
+	# get_me() call -- _wait_for_scene_change only confirms the scene
+	# object exists, not that its authenticated-state fields have been
+	# set yet. Wait for the real signal, not a guess.
+	await menu.auth_state_ready
+
+	# 5. THE regression assertion: still logged in after returning.
+	_check("main menu stays authenticated after Play -> Back", _is_authenticated(menu))
+
+	_finish()
+
+
+func _is_authenticated(menu: Control) -> bool:
+	var play_button: Button = menu.get_node("CenterContainer/VBoxContainer/PlayButton")
+	var welcome_label: Label = menu.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/WelcomeLabel")
+	var auth_buttons_row: HBoxContainer = menu.get_node("CenterContainer/VBoxContainer/AuthButtonsRow")
+	var auth_panel: PanelContainer = menu.get_node("CenterContainer/VBoxContainer/AuthPanel")
+
+	_check("Play enabled", not play_button.disabled)
+	# WelcomeLabel lives inside AuthPanel, so `.visible` alone is a
+	# false-positive: the label can have visible=true while its parent is
+	# hidden and it renders as nothing. `is_visible_in_tree()` is the
+	# check that proves the user can actually see the welcome message.
+	_check("Welcome label visible in tree", welcome_label.is_visible_in_tree())
+	_check("Auth buttons row hidden", not auth_buttons_row.visible)
+	_check("Auth panel visible (it contains the welcome label)", auth_panel.visible)
+
+	return (not play_button.disabled) \
+		and welcome_label.is_visible_in_tree() \
+		and not auth_buttons_row.visible \
+		and auth_panel.visible
+
+
+func _wait_for_scene_change(previous_scene: Node) -> void:
+	for i in 20:
+		await process_frame
+		if current_scene != previous_scene and current_scene != null:
+			return
+
+
+func _check(description: String, condition: bool) -> bool:
+	if condition:
+		print("  PASS: ", description)
+		passed += 1
+	else:
+		printerr("  FAIL: ", description)
+		failed += 1
+	return condition
+
+
+func _finish() -> void:
+	print("\n=== SMOKE RESULT: %d/%d passed ===" % [passed, passed + failed])
+	quit(0 if failed == 0 else 1)

scripts/smoke_test_main_menu_full_flow.gd

@@ -0,0 +1,76 @@
+extends SceneTree
+## Full click-through simulation of the real user flow: press Register,
+## fill the form exactly as a human would, submit, confirm Play actually
+## becomes clickable. This is the check that would have caught the
+## original bug (no way to even open the form) and would catch a repeat
+## of it.
+
+var passed := 0
+var failed := 0
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	await process_frame
+
+	var packed: PackedScene = load("res://scenes/main_menu.tscn")
+	var instance: Control = packed.instantiate()
+	root.add_child(instance)
+	await process_frame
+
+	var register_button: Button = instance.get_node("CenterContainer/VBoxContainer/AuthButtonsRow/RegisterButton")
+	var auth_buttons_row: HBoxContainer = instance.get_node("CenterContainer/VBoxContainer/AuthButtonsRow")
+	var username_edit: LineEdit = instance.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/UsernameEdit")
+	var password_edit: LineEdit = instance.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/PasswordEdit")
+	var email_edit: LineEdit = instance.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/EmailEdit")
+	var dob_edit: LineEdit = instance.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/DOBEdit")
+	var auth_button: Button = instance.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/AuthButton")
+	var welcome_label: Label = instance.get_node("CenterContainer/VBoxContainer/AuthPanel/MarginContainer/AuthVBox/WelcomeLabel")
+	var play_button: Button = instance.get_node("CenterContainer/VBoxContainer/PlayButton")
+
+	_check("Play starts disabled", play_button.disabled)
+
+	# Click Register -- a real signal emission is fine here since
+	# _on_register_button_pressed() is synchronous (no await), same as a
+	# real click's GUI event dispatch would drive it.
+	register_button.pressed.emit()
+	await process_frame
+
+	_check("auth panel opened in register mode", instance.get_node("CenterContainer/VBoxContainer/AuthPanel").visible)
+
+	# Fill the form exactly as a user would type into it.
+	var unique_id := int(Time.get_unix_time_from_system() * 1000)
+	username_edit.text = "mainmenu_e2e_%d" % unique_id
+	password_edit.text = "TestPass123!"
+	email_edit.text = "mainmenu_e2e_%d@test.example.com" % unique_id
+	dob_edit.text = "2000-01-01"
+
+	# Call the submit handler directly (awaited) rather than via
+	# auth_button.pressed.emit() -- a synthetic .emit() in --script/
+	# SceneTree headless mode doesn't drive an await-using handler's
+	# coroutine forward the same way real GUI input event dispatch does
+	# (confirmed via a direct-call vs emit() comparison: the direct call
+	# always resolves, the synthetic emit sometimes doesn't advance past
+	# its own await point even after 50 real process_frame waits). This
+	# is a headless-mode test-harness limitation, not a bug in the actual
+	# click-driven flow.
+	await instance._on_auth_button_pressed()
+
+	_check("Play became enabled after real register submission", not play_button.disabled)
+	_check("Welcome label visible in tree", welcome_label.is_visible_in_tree())
+	_check("Auth buttons row hid itself after success", not auth_buttons_row.visible)
+
+	print("\n=== SMOKE RESULT: %d/%d passed ===" % [passed, passed + failed])
+	quit(0 if failed == 0 else 1)
+
+
+func _check(description: String, condition: bool) -> void:
+	if condition:
+		print("  PASS: ", description)
+		passed += 1
+	else:
+		printerr("  FAIL: ", description)
+		failed += 1

scripts/smoke_test_main_menu_ui.gd

@@ -0,0 +1,60 @@
+extends SceneTree
+## Verifies the main menu's Login/Register buttons actually open the auth
+## panel via a real signal emission (not calling the handler method
+## directly) -- that's the exact gap that shipped without ever being
+## caught: the AuthPanel and its logic were all correct, but nothing in
+## the scene was ever wired to open it.
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	await process_frame
+
+	var passed := 0
+	var failed := 0
+
+	var packed: PackedScene = load("res://scenes/main_menu.tscn")
+	var instance: Control = packed.instantiate()
+	root.add_child(instance)
+	await process_frame
+
+	var login_button: Button = instance.get_node("CenterContainer/VBoxContainer/AuthButtonsRow/LoginButton")
+	var register_button: Button = instance.get_node("CenterContainer/VBoxContainer/AuthButtonsRow/RegisterButton")
+	var auth_panel: PanelContainer = instance.get_node("CenterContainer/VBoxContainer/AuthPanel")
+
+	if _check("auth panel starts hidden", not auth_panel.visible):
+		passed += 1
+	else:
+		failed += 1
+
+	login_button.pressed.emit()
+	await process_frame
+
+	if _check("auth panel visible after a real LoginButton press signal", auth_panel.visible):
+		passed += 1
+	else:
+		failed += 1
+
+	# Reset and check RegisterButton independently too.
+	auth_panel.visible = false
+	register_button.pressed.emit()
+	await process_frame
+
+	if _check("auth panel visible after a real RegisterButton press signal", auth_panel.visible):
+		passed += 1
+	else:
+		failed += 1
+
+	print("\n=== SMOKE RESULT: %d/%d passed ===" % [passed, passed + failed])
+	quit(0 if failed == 0 else 1)
+
+
+func _check(description: String, condition: bool) -> bool:
+	if condition:
+		print("  PASS: ", description)
+	else:
+		printerr("  FAIL: ", description)
+	return condition

scripts/smoke_test_world_list.gd

@@ -0,0 +1,168 @@
+extends SceneTree
+## Headless smoke test for the world list screen.
+##
+## Run with:
+##     godot --headless --path . --script res://scripts/smoke_test_world_list.gd
+##
+## Requires the backend to be running (default base URL
+## `application/agp/api_base_url` -> http://127.0.0.1:8000, override with
+## AGP_API_BASE_URL).
+##
+## Unlike a pure API-level test, this actually instantiates scenes/
+## world_list.tscn as a real scene and adds it to the tree -- catches
+## @onready node-path bugs (a node reference pointing at the wrong path
+## errors right here, not just "looks right" from reading the script) that
+## an API-only test would miss entirely.
+##
+## Tests:
+##   1. Register + log in a fresh user (so get_worlds() has a valid token).
+##   2. POST a real world via the API so the populated-card path actually
+##      gets exercised -- run_checkpoint_tests.py always starts from a
+##      genuinely empty DB, so without this the card-rendering code below
+##      would never run in CI at all, only the empty-list path would.
+##   3. Instantiate world_list.tscn, add to tree -- @onready resolution
+##      must not error.
+##   4. Wait for _refresh_worlds()'s awaited request to complete.
+##   5. Confirm it actually reached the populated (not empty) state, and
+##      that the rendered card has a real width -- not just non-zero
+##      child_count. 2026-08-20: a real bug shipped where every card
+##      technically existed in the tree (child_count > 0, no error, no
+##      crash) but rendered at 1.0px wide because size_flags_horizontal/
+##      vertical used the raw integer 4 (Control.SIZE_SHRINK_CENTER)
+##      instead of 3 (Control.SIZE_EXPAND_FILL) on ScrollContainer -- a
+##      child-count check alone would never catch that, only a real size
+##      assertion does.
+##
+## Exits 0 on full pass, 1 on any failure.
+
+const WORLD_LIST_SCENE := "res://scenes/world_list.tscn"
+const MIN_SANE_CARD_WIDTH := 200.0  # a real screen is at minimum a few hundred px wide
+
+
+func _initialize() -> void:
+	_run()
+
+
+func _run() -> void:
+	await process_frame
+
+	var api := root.get_node("ApiClient")
+	assert(api != null, "ApiClient autoload not found")
+
+	var passed: int = 0
+	var failed: int = 0
+
+	# --- Setup: register + log in so the world list has a valid token ---
+	print("\n=== Setup: register + login ===")
+	randomize()
+	var unique_id: int = int(Time.get_unix_time_from_system() * 1000) + randi() % 100000
+	var username := "worldlist_smoke_%d" % unique_id
+	var email := "worldlist_smoke_%d@test.example.com" % unique_id
+	var reg_result: Dictionary = await api.register(username, email, "SmokeTest123!", "2000-01-01")
+	if not _check("setup: register succeeded", reg_result.ok):
+		print("  detail: ", reg_result.detail)
+		quit(1)
+		return
+
+	# --- Seed a real world so the populated-card path is actually exercised ---
+	print("\n=== Setup: seed a real world ===")
+	var world_body := JSON.stringify({
+		"name": "Smoke Test World %d" % unique_id,
+		"description": "Seeded by smoke_test_world_list.gd to exercise the populated-card render path.",
+		"visibility": "public",
+	})
+	var create_result: Dictionary = await api.request(HTTPClient.METHOD_POST, "/api/worlds/", world_body, "application/json", true)
+	if not _check("setup: world created", create_result.ok):
+		print("  detail: ", create_result.detail)
+		quit(1)
+		return
+
+	# --- Test 1: Instantiate the real scene ---
+	print("\n=== Test 1: Instantiate world_list.tscn ===")
+	var packed_scene: PackedScene = load(WORLD_LIST_SCENE)
+	if not _check("scene loads", packed_scene != null):
+		quit(1)
+		return
+
+	var instance: Control = packed_scene.instantiate()
+	if not _check("scene instantiates", instance != null):
+		quit(1)
+		return
+
+	root.add_child(instance)
+	# One frame for _ready() (and its @onready resolution) to run. A wrong
+	# node path in an @onready var errors during this, not silently.
+	await process_frame
+
+	if _check("scene added to tree without error", is_instance_valid(instance)):
+		passed += 1
+	else:
+		failed += 1
+
+	# --- Test 2: Wait for the world fetch to resolve, check a real end state ---
+	print("\n=== Test 2: World fetch reaches a real end state ===")
+	# _refresh_worlds() runs from _ready(); give its awaited HTTP call time
+	# to complete rather than a fixed sleep -- poll for either end state.
+	var world_list_node: VBoxContainer = instance.get_node("VBoxContainer/ScrollContainer/WorldList")
+	var empty_label: Label = instance.get_node("VBoxContainer/EmptyLabel")
+	var error_label: Label = instance.get_node("VBoxContainer/ErrorLabel")
+
+	var settled := false
+	for i in range(50):  # up to ~5s at 100ms/frame-ish via process_frame waits
+		await process_frame
+		if world_list_node.visible or empty_label.visible or error_label.visible:
+			settled = true
+			break
+
+	if _check("reached a real end state (cards, empty, or error) not stuck loading", settled):
+		passed += 1
+	else:
+		failed += 1
+		print("  world_list.visible=%s empty_label.visible=%s error_label.visible=%s" % [
+			world_list_node.visible, empty_label.visible, error_label.visible
+		])
+
+	if error_label.visible:
+		printerr("  Note: ended in error state: ", error_label.text)
+	elif empty_label.visible:
+		# We just seeded a world -- ending up empty means GET /api/worlds
+		# isn't actually seeing what POST /api/worlds/ just created.
+		_check("ended in populated state, not empty (a world was just seeded)", false)
+		failed += 1
+	elif world_list_node.visible:
+		var card_count := world_list_node.get_child_count()
+		print("  Note: rendered %d world card(s)" % card_count)
+
+		if _check("at least one card rendered", card_count > 0):
+			passed += 1
+		else:
+			failed += 1
+
+		# The actual bug this test exists to catch: a card can be present
+		# in the tree, not crash, and still be visually nothing because
+		# it rendered at ~1px wide. Check every card's real computed size,
+		# not just that it exists.
+		for i in range(card_count):
+			var card: Control = world_list_node.get_child(i)
+			var wide_enough := card.size.x >= MIN_SANE_CARD_WIDTH
+			if _check("card %d has a real width (%.0fpx >= %.0fpx)" % [i, card.size.x, MIN_SANE_CARD_WIDTH], wide_enough):
+				passed += 1
+			else:
+				failed += 1
+
+	# --- Summary ---
+	print("\n=== SMOKE RESULT: %d/%d passed ===" % [passed, passed + failed])
+	if failed > 0:
+		quit(1)
+	else:
+		print("SMOKE RESULT: ALL PASS")
+		quit(0)
+
+
+func _check(description: String, condition: bool) -> bool:
+	if condition:
+		print("  PASS: ", description)
+		return true
+	else:
+		printerr("  FAIL: ", description)
+		return false

scripts/world_list.gd

@@ -0,0 +1,142 @@
+extends Control
+## World list screen — browses public worlds via GET /api/worlds.
+##
+## Displays a scrollable list of world cards (name + description).
+## Handles loading, empty list, errors, and refresh.
+
+
+# UI references
+@onready var scroll_container: ScrollContainer = $VBoxContainer/ScrollContainer
+@onready var world_list: VBoxContainer = $VBoxContainer/ScrollContainer/WorldList
+@onready var loading_label: Label = $VBoxContainer/LoadingLabel
+@onready var error_label: Label = $VBoxContainer/ErrorLabel
+@onready var refresh_button: Button = $VBoxContainer/HeaderHBox/RefreshButton
+@onready var back_button: Button = $VBoxContainer/HeaderHBox/BackButton
+@onready var empty_label: Label = $VBoxContainer/EmptyLabel
+
+
+func _ready() -> void:
+	refresh_button.disabled = false
+	back_button.disabled = false
+	loading_label.visible = false
+	error_label.visible = false
+	empty_label.visible = false
+	world_list.visible = false
+	_refresh_worlds()
+
+
+func _on_refresh_button_pressed() -> void:
+	_refresh_worlds()
+
+
+func _on_back_button_pressed() -> void:
+	get_tree().change_scene_to_file("res://scenes/main_menu.tscn")
+
+
+## Fetch the world list from the backend and update the UI.
+func _refresh_worlds() -> void:
+	# Reset UI state
+	loading_label.visible = true
+	error_label.visible = false
+	empty_label.visible = false
+	world_list.visible = false
+	refresh_button.disabled = true
+
+	# Clear previous world cards
+	for child in world_list.get_children():
+		child.queue_free()
+
+	var result := await ApiClient.get_worlds()
+
+	loading_label.visible = false
+	refresh_button.disabled = false
+
+	if not result.ok:
+		# Show error message (401, network failure, etc.)
+		error_label.text = "Error: %s" % result.detail
+		error_label.visible = true
+		empty_label.visible = false
+		world_list.visible = false
+		return
+
+	var data = result.data
+	if not data is Array:
+		error_label.text = "Unexpected response format."
+		error_label.visible = true
+		empty_label.visible = false
+		world_list.visible = false
+		return
+
+	if data.is_empty():
+		empty_label.text = "No worlds yet. Check back later!"
+		empty_label.visible = true
+		error_label.visible = false
+		world_list.visible = false
+		return
+
+	# Render world cards
+	world_list.visible = true
+	empty_label.visible = false
+	error_label.visible = false
+
+	for world_dict in data:
+		if not world_dict is Dictionary:
+			continue
+		var card := _create_world_card(world_dict)
+		world_list.add_child(card)
+
+
+## Create a visual card for a single world entry.
+func _create_world_card(world_dict: Dictionary) -> Control:
+	# PanelContainer for the background, not a ColorRect moved to child index
+	# 0 of a VBoxContainer -- a VBoxContainer lays out ALL its children in a
+	# vertical sequence, it has no concept of "float this one child behind
+	# the others as an overlay". That version rendered as an empty dark bar
+	# sitting above the text, not a background behind it.
+	var panel := PanelContainer.new()
+	panel.size_flags_horizontal = Control.SIZE_EXPAND_FILL
+	panel.custom_minimum_size = Vector2(0, 80)
+	var style := StyleBoxFlat.new()
+	style.bg_color = Color(0.15, 0.15, 0.15, 1.0)
+	style.content_margin_left = 12
+	style.content_margin_right = 12
+	style.content_margin_top = 8
+	style.content_margin_bottom = 8
+	panel.add_theme_stylebox_override("panel", style)
+
+	var card := VBoxContainer.new()
+	card.size_flags_horizontal = Control.SIZE_EXPAND_FILL
+	card.add_theme_constant_override("separation", 4)
+	panel.add_child(card)
+
+	var name_label := Label.new()
+	name_label.text = world_dict.get("name", "Unnamed World")
+	name_label.autowrap_mode = TextServer.AUTOWRAP_WORD
+	name_label.size_flags_horizontal = Control.SIZE_FILL
+	name_label.size_flags_vertical = Control.SIZE_SHRINK_BEGIN
+	name_label.add_theme_font_size_override("font_size", 18)
+
+	var desc_label := Label.new()
+	var description: String = str(world_dict.get("description", ""))
+	desc_label.text = description if description != "" else "No description."
+	desc_label.autowrap_mode = TextServer.AUTOWRAP_WORD
+	desc_label.size_flags_horizontal = Control.SIZE_FILL
+	desc_label.size_flags_vertical = Control.SIZE_EXPAND_FILL
+	desc_label.add_theme_font_size_override("font_size", 14)
+	desc_label.add_theme_color_override("font_color", Color(0.7, 0.7, 0.7, 1.0))
+
+	var meta_label := Label.new()
+	var visibility: String = str(world_dict.get("visibility", "public"))
+	var created: String = str(world_dict.get("created_at", ""))
+	meta_label.text = "Visibility: %s%s" % [visibility, " | Created: " + created if created != "" else ""]
+	meta_label.autowrap_mode = TextServer.AUTOWRAP_WORD
+	meta_label.size_flags_horizontal = Control.SIZE_FILL
+	meta_label.size_flags_vertical = Control.SIZE_SHRINK_BEGIN
+	meta_label.add_theme_font_size_override("font_size", 12)
+	meta_label.add_theme_color_override("font_color", Color(0.5, 0.5, 0.5, 1.0))
+
+	card.add_child(name_label)
+	card.add_child(desc_label)
+	card.add_child(meta_label)
+
+	return panel