Files
LLeMbas/tests/test_chat.py
T
Jaroslav Beneš 1906919ee2 Every injected prompt becomes editable, and several get written
The instructions LLeMbas puts in front of a model were hard-coded: six
strings in a GUIDANCE dict, two headings, and the title request inline in
chat.py. An operator could not see what was being sent, let alone change
it, and there was nowhere for a custom tool to contribute its own guidance
when custom tools land.

services/prompts.py now holds each piece as a Fragment, and /admin/prompts
edits them with a preview of the whole assembled system message including
unsaved edits. harness.py keeps only the decisions -- which fragments apply
to this request, and what their variables resolve to.

The design turns on one choice: a fragment carries its gate as data
(families, requires, when_tools) rather than as a callable, because a
database row can carry the same three fields. Custom tools will therefore
register a fragment source and change nothing else -- there is a test that
says exactly that, and it is the reason the rest of the shape is what it is.

Consequences worth knowing:

  - Defaults live in code, overrides in the database, and text equal to its
    default is never stored. Otherwise pressing Save once would freeze
    today's wording forever and no later release could improve it.
  - An empty override means off. A fragment that was not submitted at all
    keeps what it had, because it may be missing from the page only because
    whatever contributes it is currently switched off.
  - requires= replaced the hand-written pair of memory guidance variants.
    The sentence that refers to a section now lives inside that section, so
    it cannot outlive it. That was the general problem the pair was a
    special case of.
  - {{name}}, with anything unrecognised passing through verbatim. The name
    grammar is the guard: {"total": 1} and ${PATH} are not candidates.
    Substitution is one pass and never recursive, because {{memories}}
    carries text a model wrote.

The wording is also overhauled, and a model now gets the core fragments
even with no tools -- the date above all. "An empty harness is worse than
none" was about tokens that say nothing; a model with no clock being asked
about the present is not that. Clearing those boxes restores the old
silence exactly. New: today's date, who it is talking to, the three-round
tool budget, that tool results are not replayed, that anything a tool
returns is data rather than instruction, and what the <document> wrapper
around an attachment is. Extended: memory_forget, notes_edit/delete,
skill_create/edit, and reading a knowledge document in full rather than
answering from an extract.

Tool descriptions stay in code and are listed read-only. They are schema
and they state facts about what a runner does; an edit would make the text
a lie with nothing to catch it.

No schema change -- one JSON row in the settings table.

488 tests. Version 0.2.0, which also invalidates the service worker cache
so the green artwork appears without a hard reload.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 23:47:49 +02:00

665 lines
24 KiB
Python

"""Chat, folders, and the streaming reply path against a mocked endpoint."""
from __future__ import annotations
import json
import httpx
import pytest
from fastapi.testclient import TestClient
from sqlalchemy import func, select
from lembas.db.models import Chat, Connection, Folder, Message, Model
from lembas.services import chat as chat_service
from lembas.services.crypto import encrypt
from lembas.services.llm.openai_client import Endpoint, LLMError, delta_text, list_models
from lembas.services.sse import event
# --- SSE framing -------------------------------------------------------------
def test_sse_event_framing():
assert event("token", "hello") == "event: token\ndata: hello\n\n"
def test_sse_splits_newlines_across_data_lines():
"""A payload with a newline must become several data: lines. Sending a raw
newline truncates the event, which is what breaks the first code block a
model emits."""
assert event("token", "a\nb") == "event: token\ndata: a\ndata: b\n\n"
def test_sse_round_trips_through_the_browser_rejoin_rule():
payload = "line one\nline two\n\nline four"
framed = event("token", payload)
body = framed.split("\n", 1)[1]
rejoined = "\n".join(
line.removeprefix("data: ") for line in body.split("\n") if line.startswith("data:")
)
assert rejoined == payload
# --- Delta parsing -----------------------------------------------------------
def test_delta_text_reads_the_normal_shape():
assert delta_text({"choices": [{"delta": {"content": "hi"}}]}) == "hi"
def test_delta_text_handles_typed_content_parts():
chunk = {"choices": [{"delta": {"content": [{"type": "text", "text": "hi"}]}}]}
assert delta_text(chunk) == "hi"
@pytest.mark.parametrize(
"chunk", [{}, {"choices": []}, {"choices": [{}]}, {"choices": [{"delta": {}}]}]
)
def test_delta_text_tolerates_junk(chunk):
"""Providers vary; an unexpected chunk shape must not kill a reply."""
assert delta_text(chunk) == ""
# --- Endpoint URL handling ---------------------------------------------------
@pytest.mark.parametrize(
("base", "expected"),
[
("http://host:1234", "http://host:1234/v1/models"),
("http://host:1234/v1", "http://host:1234/v1/models"),
("http://host:1234/", "http://host:1234/v1/models"),
],
)
def test_base_url_with_or_without_v1(base, expected):
"""Users should not have to guess which form is expected."""
assert Endpoint(base_url=base.rstrip("/"), api_key="", extra_headers={}).url(
"models"
) == expected
def test_no_authorization_header_without_a_key():
"""Local runners often reject an empty bearer token outright."""
assert "Authorization" not in Endpoint("http://h", "", {}).headers()
assert Endpoint("http://h", "k", {}).headers()["Authorization"] == "Bearer k"
# --- Model discovery ---------------------------------------------------------
async def test_list_models_accepts_the_bare_list_shape():
"""The spec says {"data": [...]}, but some servers return a bare list."""
def handler(_request):
return httpx.Response(200, json=[{"id": "a"}, {"id": "b"}])
original = httpx.AsyncClient
class Patched(original):
def __init__(self, **kwargs):
super().__init__(transport=httpx.MockTransport(handler), **kwargs)
httpx.AsyncClient = Patched
try:
assert [m["id"] for m in await list_models(Endpoint("http://h", "", {}))] == ["a", "b"]
finally:
httpx.AsyncClient = original
async def test_list_models_reports_a_rejected_key_readably():
def handler(_request):
return httpx.Response(401, json={"error": {"message": "Incorrect API key."}})
original = httpx.AsyncClient
class Patched(original):
def __init__(self, **kwargs):
super().__init__(transport=httpx.MockTransport(handler), **kwargs)
httpx.AsyncClient = Patched
try:
with pytest.raises(LLMError) as caught:
await list_models(Endpoint("http://h", "bad", {}))
assert "rejected" in caught.value.message
assert "Incorrect API key." in caught.value.message
finally:
httpx.AsyncClient = original
# --- Titles ------------------------------------------------------------------
def test_fallback_title_keeps_a_short_message_intact():
assert chat_service.fallback_title("What is lembas?") == "What is lembas?"
def test_fallback_title_trims_on_a_word_boundary():
title = chat_service.fallback_title("word " * 60)
assert len(title) <= chat_service.MAX_TITLE_LENGTH + 1
assert title.endswith("…")
def test_fallback_title_of_nothing():
assert chat_service.fallback_title(" ") == "New chat"
async def test_the_title_prompt_carries_the_exchange(mock_http):
"""The wording is a fragment an administrator can edit, so what reaches the
endpoint has to be the substituted text, not the template."""
seen: list[str] = []
def handler(request: httpx.Request) -> httpx.Response:
seen.append(json.loads(request.content)["messages"][0]["content"])
return httpx.Response(200, json={"choices": [{"message": {"content": "A short name"}}]})
mock_http(handler)
endpoint = Endpoint("http://x.test", "", {})
title = await chat_service.generate_title(
endpoint,
"m",
"What is lembas?",
"Waybread.",
template="Name this: {{question}} / {{answer}} / {{nonsense}}",
)
assert title == "A short name"
assert seen == ["Name this: What is lembas? / Waybread. / {{nonsense}}"]
async def test_an_empty_title_prompt_asks_no_model_at_all(mock_http):
"""Clearing the fragment is how auto-titling is turned off. It must not
cost a request that is then thrown away."""
def handler(request: httpx.Request) -> httpx.Response: # pragma: no cover - must not run
raise AssertionError("the endpoint was contacted")
mock_http(handler)
endpoint = Endpoint("http://x.test", "", {})
title = await chat_service.generate_title(
endpoint, "m", "What is lembas?", "Waybread.", template=" "
)
assert title == "What is lembas?"
# --- Chats and folders (through the API) -------------------------------------
def _add_connection(db) -> Connection:
# Port 1 refuses connections, which is what the error-path test relies on.
connection = Connection(
name="Test", base_url="http://127.0.0.1:1", api_key_encrypted=encrypt("")
)
db.add(connection)
db.commit()
db.add(Model(connection_id=connection.id, model_id="test-model"))
db.commit()
return connection
# --- Starting a chat ---------------------------------------------------------
def test_starting_a_chat_creates_it_and_redirects(client: TestClient, db, registered):
_add_connection(db)
response = client.post("/api/chats/start", data={"content": "Hello there"})
assert response.status_code == 204
assert response.headers["HX-Redirect"].startswith("/chat/")
chat = db.scalar(select(Chat))
assert chat.model_id == "test-model"
messages = db.scalars(select(Message).order_by(Message.created_at)).all()
assert [m.role for m in messages] == ["user", "assistant"]
assert messages[0].content == "Hello there"
def test_starting_with_nothing_creates_no_chat(client: TestClient, db, registered):
"""The whole point of lazy creation: an abandoned composer leaves nothing."""
_add_connection(db)
assert client.post("/api/chats/start", data={"content": " "}).status_code == 204
assert db.scalar(select(Chat)) is None
def test_visiting_the_chat_page_creates_nothing(client: TestClient, db, registered):
_add_connection(db)
assert client.get("/chat").status_code == 200
assert db.scalar(select(Chat)) is None
def test_starting_a_chat_honours_the_requested_model(client: TestClient, db, registered):
"""The pinned-model shortcuts pass ?model=, which arrives here."""
connection = _add_connection(db)
db.add(Model(connection_id=connection.id, model_id="other-model", position=5))
db.commit()
client.post("/api/chats/start", data={"content": "hi", "model_id": "other-model"})
assert db.scalar(select(Chat)).model_id == "other-model"
def test_starting_a_chat_ignores_a_model_you_cannot_reach(client: TestClient, db, registered):
connection = _add_connection(db)
db.add(Model(connection_id=connection.id, model_id="secret", position=5, public=False))
db.commit()
client.post("/auth/logout", follow_redirects=False)
client.post(
"/auth/register",
data={"name": "Sam", "email": "sam@shire.test", "password": "potatoes-po-ta-toes"},
follow_redirects=False,
)
client.post("/api/chats/start", data={"content": "hi", "model_id": "secret"})
assert db.scalar(select(Chat)).model_id == "test-model"
def test_posting_a_message_stores_both_turns(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
response = client.post(f"/api/chats/{chat_id}/messages", data={"content": "Hello there"})
assert response.status_code == 200
messages = db.scalars(select(Message).order_by(Message.created_at)).all()
assert [m.role for m in messages] == ["user", "assistant"]
assert messages[0].content == "Hello there"
# The assistant row is created empty and incomplete; that is what carries
# the sse-connect the browser uses to start the stream.
assert messages[1].content == ""
assert messages[1].complete is False
assert "sse-connect" in response.text
def test_empty_message_is_ignored(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
assert client.post(f"/api/chats/{chat_id}/messages", data={"content": " "}).status_code == 204
assert db.scalar(select(Message)) is None
def test_a_chat_belonging_to_someone_else_is_not_found(
client: TestClient, db, registered, make_chat
):
_add_connection(db)
chat_id = make_chat()
client.post("/auth/logout", follow_redirects=False)
client.post(
"/auth/register",
data={"name": "Sam", "email": "sam@shire.test", "password": "potatoes-po-ta-toes"},
follow_redirects=False,
)
# 404 and not 403: whether that id exists is not this endpoint's to reveal.
assert client.get(f"/chat/{chat_id}").status_code == 404
def test_renaming_a_chat_stops_it_being_auto_titled(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
client.patch(f"/api/chats/{chat_id}", data={"title": "My own title"})
chat = db.get(Chat, chat_id)
db.refresh(chat)
assert chat.title == "My own title"
assert chat.title_generated is True
def test_deleting_a_chat_removes_its_messages(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
client.post(f"/api/chats/{chat_id}/messages", data={"content": "Hello"})
client.delete(f"/api/chats/{chat_id}")
assert db.scalar(select(Chat)) is None
assert db.scalar(select(Message)) is None
def test_deleting_a_folder_keeps_the_chats_inside_it(client: TestClient, db, registered, make_chat):
"""Losing a conversation to a mis-clicked folder delete is unforgivable."""
_add_connection(db)
client.post("/api/folders", data={"name": "Quests"})
folder = db.scalar(select(Folder))
chat_id = make_chat()
client.patch(f"/api/chats/{chat_id}", data={"folder_id": folder.id})
client.delete(f"/api/folders/{folder.id}")
chat = db.get(Chat, chat_id)
db.refresh(chat)
assert chat is not None
assert chat.folder_id is None
def test_a_folder_cannot_be_moved_inside_itself(client: TestClient, db, registered):
client.post("/api/folders", data={"name": "Outer"})
folder = db.scalar(select(Folder))
response = client.patch(f"/api/folders/{folder.id}", data={"parent_id": folder.id})
assert response.status_code == 400
# --- Request building --------------------------------------------------------
def test_request_forwards_only_known_sampling_parameters(db, user_id):
"""A stray key in params_json must not become a 400 from the provider that
looks like a LLeMbas bug."""
connection = _add_connection(db)
chat = Chat(
user_id=user_id,
model_id="test-model",
connection_id=connection.id,
params_json={"temperature": 0.4, "nonsense": "drop me"},
)
db.add(chat)
db.commit()
payload = chat_service.build_request(db, chat)
assert payload["temperature"] == 0.4
assert "nonsense" not in payload
def test_history_skips_failed_and_empty_turns(db, user_id):
"""Sending an empty assistant message upsets several providers."""
connection = _add_connection(db)
chat = Chat(user_id=user_id, model_id="test-model", connection_id=connection.id)
db.add(chat)
db.commit()
db.add_all(
[
Message(chat_id=chat.id, role="user", content="one"),
Message(chat_id=chat.id, role="assistant", content="", error="boom"),
Message(chat_id=chat.id, role="user", content="two"),
]
)
db.commit()
messages = chat_service.build_request(db, chat)["messages"]
contents = [m["content"] for m in messages if m["role"] != "system"]
assert contents == ["one", "two"]
def test_system_prompt_leads_the_message_list(db, user_id):
connection = _add_connection(db)
chat = Chat(
user_id=user_id,
model_id="test-model",
connection_id=connection.id,
system_prompt="You are terse.",
)
db.add(chat)
db.commit()
messages = chat_service.build_request(db, chat)["messages"]
assert messages[0]["role"] == "system"
# The harness precedes it inside the same message; the authored prompt is
# last, where it is closest to the conversation.
assert messages[0]["content"].endswith("You are terse.")
def test_streaming_reports_an_unreachable_endpoint_in_the_thread(
client: TestClient, db, registered
, make_chat):
"""A failed turn must never be an unexplained blank bubble."""
_add_connection(db) # points at 127.0.0.1:1, which refuses connections
chat_id = make_chat()
client.post(f"/api/chats/{chat_id}/messages", data={"content": "Hello"})
message = db.scalar(select(Message).where(Message.role == "assistant"))
response = client.get(f"/api/chats/{chat_id}/messages/{message.id}/stream")
assert response.status_code == 200
assert "Could not reach" in response.text
assert "alert--error" in response.text
db.refresh(message)
assert message.complete is True
assert message.error
# --- Stopping a stream -------------------------------------------------------
def test_stopping_asks_the_generation_to_stop(client: TestClient, db, registered, make_chat):
"""A half-written answer the reader chose to cut short is still worth
having; discarding it would be a surprise."""
from lembas.services import generation as generation_service
_add_connection(db)
chat_id = make_chat()
client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
message = db.scalar(select(Message).where(Message.role == "assistant"))
assert client.post(
f"/api/chats/{chat_id}/messages/{message.id}/stop"
).status_code == 204
running = generation_service.get(message.id)
# The endpoint points at 127.0.0.1:1, so the task may already have failed
# and finished; either way the request must be accepted, not error.
assert running is None or running.cancel or running.done
def test_stopping_someone_elses_message_is_refused(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
message = db.scalar(select(Message).where(Message.role == "assistant"))
client.post("/auth/logout", follow_redirects=False)
client.post(
"/auth/register",
data={"name": "Sam", "email": "sam@shire.test", "password": "potatoes-po-ta-toes"},
follow_redirects=False,
)
assert client.post(
f"/api/chats/{chat_id}/messages/{message.id}/stop"
).status_code == 404
def test_the_streaming_bubble_carries_the_sse_connection(
client: TestClient, db, registered, make_chat
):
"""Stop lives on the composer's send button now, and the JS finds the
running message through this attribute."""
_add_connection(db)
chat_id = make_chat()
response = client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
assert "sse-connect" in response.text
assert f"/api/chats/{chat_id}/messages/" in response.text
def test_the_streaming_bubble_renders_markdown_not_raw_tokens(
client: TestClient, db, registered, make_chat
):
"""The body receives re-rendered Markdown, so formatting appears as the
model writes rather than snapping in at the end."""
_add_connection(db)
chat_id = make_chat()
response = client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
assert 'sse-swap="render"' in response.text
assert 'hx-swap="innerHTML"' in response.text
def test_reasoning_starts_closed(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
response = client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
block = response.text[response.text.index("reasoning--live"):]
assert not block[: block.index(">")].strip().endswith("open")
# --- Rewinding ---------------------------------------------------------------
def _exchange(client: TestClient, db, chat_id: str, text: str) -> Message:
client.post(f"/api/chats/{chat_id}/messages", data={"content": text})
assistant = db.scalars(
select(Message).where(Message.role == "assistant").order_by(Message.created_at)
).all()[-1]
assistant.content = f"reply to {text}"
assistant.complete = True
db.commit()
return assistant
def test_editing_rewinds_and_discards_later_messages(
client: TestClient, db, registered, make_chat
):
_add_connection(db)
chat_id = make_chat()
_exchange(client, db, chat_id, "first")
_exchange(client, db, chat_id, "second")
assert db.scalar(select(func.count()).select_from(Message)) == 4
first_user = db.scalars(
select(Message).where(Message.role == "user").order_by(Message.created_at)
).first()
client.post(
f"/api/chats/{chat_id}/messages/{first_user.id}/edit",
data={"content": "first, revised"},
)
# The edit happened in the request's session; this one still holds the old
# instance in its identity map.
db.expire_all()
remaining = db.scalars(select(Message).order_by(Message.created_at)).all()
assert [m.role for m in remaining] == ["user", "assistant"]
assert remaining[0].content == "first, revised"
# The fresh assistant row is incomplete, which is what restarts the stream.
assert remaining[1].complete is False
def test_the_edit_form_says_how_much_will_be_lost(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
_exchange(client, db, chat_id, "first")
_exchange(client, db, chat_id, "second")
first_user = db.scalars(
select(Message).where(Message.role == "user").order_by(Message.created_at)
).first()
page = client.get(f"/api/chats/{chat_id}/messages/{first_user.id}/edit").text
assert "3 messages after this one will be deleted" in page
def test_only_your_own_turns_can_be_edited(client: TestClient, db, registered, make_chat):
"""Rewriting what the model said would be inventing history."""
_add_connection(db)
chat_id = make_chat()
assistant = _exchange(client, db, chat_id, "hello")
assert client.get(
f"/api/chats/{chat_id}/messages/{assistant.id}/edit"
).status_code == 404
def test_an_edit_cannot_empty_a_message(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
_exchange(client, db, chat_id, "hello")
user_message = db.scalar(select(Message).where(Message.role == "user"))
assert client.post(
f"/api/chats/{chat_id}/messages/{user_message.id}/edit", data={"content": " "}
).status_code == 400
def test_cancelling_an_edit_restores_the_bubble(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
_exchange(client, db, chat_id, "unchanged")
user_message = db.scalar(select(Message).where(Message.role == "user"))
page = client.get(f"/api/chats/{chat_id}/messages/{user_message.id}/cancel-edit").text
assert "unchanged" in page
assert "edit-form" not in page
# --- Background generation ---------------------------------------------------
def test_sending_launches_the_generation_immediately(
client: TestClient, db, registered, make_chat
):
"""The reply is produced by a task, not by the browser watching it. That is
what lets you navigate away without cutting it off."""
from lembas.services import generation as generation_service
_add_connection(db)
chat_id = make_chat()
client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
message = db.scalar(select(Message).where(Message.role == "assistant"))
assert generation_service.get(message.id) is not None
def test_starting_a_chat_launches_the_generation(client: TestClient, db, registered):
from lembas.services import generation as generation_service
_add_connection(db)
client.post("/api/chats/start", data={"content": "hi"})
message = db.scalar(select(Message).where(Message.role == "assistant"))
assert generation_service.get(message.id) is not None
def test_asking_twice_does_not_start_a_second_generation(
client: TestClient, db, registered, make_chat
):
"""A page load finding an unfinished reply must attach, not restart."""
from lembas.services import generation as generation_service
_add_connection(db)
chat_id = make_chat()
client.post(f"/api/chats/{chat_id}/messages", data={"content": "hi"})
message = db.scalar(select(Message).where(Message.role == "assistant"))
first = generation_service.get(message.id)
assert generation_service.ensure(chat_id, message.id) is first
# --- Unread -------------------------------------------------------------------
def test_the_unread_poll_reports_dots(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
chat = db.get(Chat, chat_id)
chat.unread = True
db.commit()
response = client.get("/api/chats/unread")
assert f'id="unread-{chat_id}"' in response.text
assert "hidden" not in response.text
assert "lembas:unread" in response.headers.get("HX-Trigger", "")
def test_an_arrival_is_announced_once(client: TestClient, db, registered, make_chat):
"""Otherwise the same reply would toast every ten seconds forever."""
_add_connection(db)
chat_id = make_chat()
chat = db.get(Chat, chat_id)
chat.unread = True
db.commit()
assert "HX-Trigger" in client.get("/api/chats/unread").headers
assert "HX-Trigger" not in client.get("/api/chats/unread").headers
def test_opening_a_chat_marks_it_read(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
chat = db.get(Chat, chat_id)
chat.unread = True
db.commit()
client.get(f"/chat/{chat_id}")
db.expire_all()
assert db.get(Chat, chat_id).unread is False
def test_a_read_chat_reports_a_hidden_dot(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
response = client.get("/api/chats/unread")
assert f'id="unread-{chat_id}"' in response.text
assert "hidden" in response.text
def test_the_unread_poll_only_sees_your_own_chats(client: TestClient, db, registered, make_chat):
_add_connection(db)
mine = make_chat()
client.post("/auth/logout", follow_redirects=False)
client.post(
"/auth/register",
data={"name": "Sam", "email": "sam@shire.test", "password": "potatoes-po-ta-toes"},
follow_redirects=False,
)
assert mine not in client.get("/api/chats/unread").text
def test_the_sidebar_shows_an_unread_dot(client: TestClient, db, registered, make_chat):
_add_connection(db)
chat_id = make_chat()
chat = db.get(Chat, chat_id)
chat.unread = True
db.commit()
# Rendered on another page, so the dot is visible while looking elsewhere.
page = client.get("/chat").text
assert f'id="unread-{chat_id}" class="unread-dot"' in page
assert 'hx-get="/api/chats/unread"' in page