fc02eb5538
An agent chat used to open with the model knowing the name of a machine and nothing about what was on it, so the first two rounds of every reply went on finding out. It now gets a listing: one read-only command, `git ls-files` where that works and `find` otherwise, falling back to an SFTP walk that always does. git first because a repository already carries somebody's considered list of what is not part of the project, and reproducing it by hand is how an index ends up mostly build output. The listing is budgeted rather than dumped. A tree of a thousand files is worse than no tree -- it costs the window on every request forever and buries the four names that mattered -- so directories that will not fit are shown as a count and the model is told to open one itself. Collapsing picks the deepest and largest first: by saving alone it would take `src/` before `src/web/static/vendor/`, because it contains it, and lose every name worth having. Read from a cache and never fetched. `harness.context_variables` is synchronous and sits on the request path; the walk happens in the generation setup, which is async and already doing network work, with a short wait. A chat whose first reply outruns its first walk simply has no listing that turn and the fragment disappears rather than appearing as an empty heading. Then `@`, over the same index and over the library, and `/` for commands with an Alt-based keyboard for the same jobs. A mentioned file arrives as contents, not a reference -- a small model asked to call file_read often does not bother -- and it arrives with its absolute path and the machine it came from, because a model handed `main.py` cannot tell which of four it is and cannot name it back when asked to change something. The rule that matters for `/`: a message that merely starts with a slash still sends. `//` escapes and an unrecognised command is posted as written. Swallowing somebody's message is a much worse failure than an unknown command. Two exceptions to Manual mode now, not one. Browsing and indexing are a person acting, not a model, so neither passes through policy.py -- the same argument the terminal panel rests on. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
225 lines
7.1 KiB
Python
225 lines
7.1 KiB
Python
"""Test fixtures.
|
|
|
|
Every test runs against a throwaway SQLite file in a tmp_path, never the real
|
|
data directory. The environment has to be set before lembas.config is imported,
|
|
because Settings is a cached singleton read at import time.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import tempfile
|
|
from collections.abc import Iterator
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
# Must happen before any lembas import.
|
|
_TMP = tempfile.mkdtemp(prefix="lembas-tests-")
|
|
os.environ.update(
|
|
{
|
|
"LEMBAS_SECRET_KEY": "test-secret-key-not-for-real-use",
|
|
"LEMBAS_DATA_DIR": _TMP,
|
|
"LEMBAS_ALLOW_SIGNUP": "true",
|
|
"LEMBAS_LOG_LEVEL": "warning",
|
|
}
|
|
)
|
|
|
|
from fastapi.testclient import TestClient # noqa: E402
|
|
from sqlalchemy.orm import Session # noqa: E402
|
|
|
|
from lembas.config import settings # noqa: E402
|
|
from lembas.db.base import Base # noqa: E402
|
|
from lembas.db.session import get_engine, get_session_factory, reset_engine # noqa: E402
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def fresh_database(tmp_path: Path) -> Iterator[None]:
|
|
"""Point the engine at a per-test database and build the schema.
|
|
|
|
reset_engine() is essential: the engine is a module-level singleton, so
|
|
without it every test after the first would share the first one's file.
|
|
"""
|
|
settings.data_dir = tmp_path
|
|
reset_engine()
|
|
settings.ensure_dirs()
|
|
|
|
import lembas.db.models # noqa: F401 (registers the tables)
|
|
|
|
# sync_schema rather than create_all: it is what startup runs, and it also
|
|
# builds the full-text indexes, which are not SQLAlchemy models and so are
|
|
# invisible to create_all. Tests were otherwise running against a schema
|
|
# production does not have.
|
|
from lembas.db.migrations import sync_schema
|
|
|
|
Base.metadata.create_all(bind=get_engine())
|
|
sync_schema(get_engine())
|
|
yield
|
|
reset_engine()
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def fresh_generation_registry() -> Iterator[None]:
|
|
"""Empty the in-flight reply registry between tests.
|
|
|
|
`_RUNNING` and `_TASKS` are module-level dicts, so a test that starts a
|
|
reply and does not wait for it leaves an entry behind for the rest of the
|
|
session -- holding a Generation, and a Task belonging to an event loop that
|
|
has since closed. `_prune()` will not clear it either: it only drops
|
|
generations that have finished, and it runs on every `ensure()`.
|
|
|
|
Cheap, and it keeps a test that posts a message from meeting the leftovers
|
|
of one that asked a question.
|
|
"""
|
|
from lembas.services import generation as generation_service
|
|
|
|
generation_service._RUNNING.clear()
|
|
generation_service._TASKS.clear()
|
|
yield
|
|
generation_service._RUNNING.clear()
|
|
generation_service._TASKS.clear()
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def fresh_terminal_registry() -> Iterator[None]:
|
|
"""Empty the open-shell registry between tests, for the same reason.
|
|
|
|
A leaked entry holds an asyncssh connection belonging to an event loop that
|
|
has since closed, and the reaper task is module-level too -- one left
|
|
running would wake up inside the next test's loop.
|
|
"""
|
|
from lembas.services.agent import terminal as terminal_service
|
|
|
|
def _clear() -> None:
|
|
reaper = terminal_service._REAPER
|
|
if reaper is not None:
|
|
reaper.cancel()
|
|
terminal_service._REAPER = None
|
|
terminal_service._SESSIONS.clear()
|
|
|
|
_clear()
|
|
yield
|
|
_clear()
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def fresh_project_index() -> Iterator[None]:
|
|
"""Empty the directory-listing cache between tests, for the third time.
|
|
|
|
Keyed on (profile, directory) and both are recycled freely by fixtures, so
|
|
without this a test asserting "the listing said X" can be answered by the
|
|
previous test's walk of an entirely different tmp_path.
|
|
"""
|
|
from lembas.services.agent import index as index_service
|
|
|
|
index_service.clear()
|
|
yield
|
|
index_service.clear()
|
|
|
|
|
|
@pytest.fixture
|
|
def db() -> Iterator[Session]:
|
|
session = get_session_factory()()
|
|
try:
|
|
yield session
|
|
finally:
|
|
session.close()
|
|
|
|
|
|
@pytest.fixture
|
|
def client() -> Iterator[TestClient]:
|
|
from lembas.main import app
|
|
|
|
# raise_server_exceptions=False so error-handler behaviour is exercised
|
|
# rather than the exception propagating into the test.
|
|
with TestClient(app, raise_server_exceptions=False) as test_client:
|
|
yield test_client
|
|
|
|
|
|
@pytest.fixture
|
|
def registered(client: TestClient) -> dict[str, str]:
|
|
"""Register the first account. It becomes the administrator."""
|
|
credentials = {
|
|
"name": "Frodo",
|
|
"email": "frodo@shire.test",
|
|
"password": "speak-friend-and-enter",
|
|
}
|
|
response = client.post("/auth/register", data=credentials, follow_redirects=False)
|
|
assert response.status_code == 303, response.text
|
|
return credentials
|
|
|
|
|
|
@pytest.fixture
|
|
def make_chat(db: Session):
|
|
"""Create a chat row directly, as scaffolding for other tests.
|
|
|
|
Chats are normally created by POST /api/chats/start along with their first
|
|
exchange -- there is deliberately no endpoint that makes an empty one. Most
|
|
tests want a chat to act on, not that flow, so they get one straight from
|
|
the database rather than having to subtract an opening turn from every
|
|
assertion. The flow itself is covered in test_chat.py.
|
|
"""
|
|
from sqlalchemy import select
|
|
|
|
from lembas.db.models import Chat, Model, User
|
|
|
|
def _create(email: str | None = None, model_id: str | None = None) -> str:
|
|
user = (
|
|
db.scalar(select(User).where(User.email == email))
|
|
if email
|
|
else db.scalars(select(User).order_by(User.created_at)).first()
|
|
)
|
|
model = (
|
|
db.scalar(select(Model).where(Model.model_id == model_id))
|
|
if model_id
|
|
else db.scalars(select(Model).order_by(Model.position)).first()
|
|
)
|
|
chat = Chat(
|
|
user_id=user.id,
|
|
model_id=model.model_id if model else "",
|
|
connection_id=model.connection_id if model else None,
|
|
)
|
|
db.add(chat)
|
|
db.commit()
|
|
return chat.id
|
|
|
|
return _create
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_http():
|
|
"""Answer every outgoing httpx request with a handler of the test's choosing.
|
|
|
|
The services build their own AsyncClient because each needs its own timeout,
|
|
so there is no client to inject; patching the class is what reaches them.
|
|
Returns a callable that installs a handler and is undone on teardown.
|
|
"""
|
|
import httpx
|
|
|
|
original = httpx.AsyncClient
|
|
|
|
def install(handler):
|
|
class Patched(original):
|
|
def __init__(self, **kwargs):
|
|
super().__init__(transport=httpx.MockTransport(handler), **kwargs)
|
|
|
|
httpx.AsyncClient = Patched
|
|
|
|
yield install
|
|
httpx.AsyncClient = original
|
|
|
|
|
|
@pytest.fixture
|
|
def user_id(db: Session, registered: dict[str, str]) -> str:
|
|
"""The registered user's id.
|
|
|
|
Chats have a real foreign key to users and SQLite enforces it (the
|
|
connect-time PRAGMA in db/session.py turns that on), so tests that build a
|
|
Chat directly need a user that actually exists.
|
|
"""
|
|
from sqlalchemy import select
|
|
|
|
from lembas.db.models import User
|
|
|
|
return db.scalar(select(User).where(User.email == registered["email"])).id
|