Files
LLeMbas/tests/test_sharing.py
T
Jaroslav Beneš 21001f2eb8 Knowledge, notes, memory and skills, and a harness to make them used
Four places a model can reach for, differing in who writes a record and how it
gets in front of the model.

**Knowledge** is uploaded by a person and searched by the model. It goes through
`services/files.py:prepare` — the same pipeline as a chat attachment — so the
same PDF produces the same text whichever way it arrived, and `Document` carries
the same content columns as `Attachment` for the same reason.

**Notes** are written by the model and edited by you. Too long to inject, so
they are searched.

**Memory** is short facts, and every one of them goes into every request. That
single decision is where the rest of its design comes from: records are capped
short, the block has a budget, there is no search tool because the model is
already looking at them, and they are not shareable — a record about a person is
not content to hand round.

**Skills** are saved procedures. Only the name and description are injected; the
body is fetched when the model decides one applies, which is what makes a
hundred skills affordable. A model may write and revise its own — the safety
story is not a gate but a record: every revision is kept, attributed and
revertible. A model that has just read a hostile page can save a skill that
outlives the conversation, and the honest mitigation is that it is visible and
undoable rather than that it was prevented.

**The harness** is why any of it gets used. A model handed a tools array
ignores it and answers from recall, because nothing in the request suggests
otherwise. `services/harness.py` assembles a preamble from what this chat
actually has: when to reach for each tool, the memories, the skill index.

This is an exception to "system prompts are precedence, not concatenation", and
a deliberate one. That rule governs the three *authored* layers and is
untouched — exactly one still wins. The harness is a different axis: it
describes the machinery rather than the behaviour, nobody authored it, and there
is nothing for it to disagree with. It is prepended to whichever authored prompt
won, in one system message, since several endpoints reject a second.

Supporting changes:

- **Sharing**, in one helper. `visible_to()` is the only definition of who can
  see a library item and every listing and tool goes through it. Sharing grants
  *reading*; two people editing one note with no history and no merge is worse
  than copying it. **Administrators do not bypass this** — they bypass
  permissions elsewhere because an admin can grant themselves those anyway, but
  reading somebody's private notes is a different act.
- **FTS5**, created by `db/migrations.py:ensure_fts` with the triggers an
  external-content index needs. Idempotent, like the column sync beside it.
  Terms are ANDed and then ORed: the caller is usually a model writing a whole
  question, and requiring every word loses the match on one absent term.
- **The attach button is a menu** — file, image, a web page, or a document from
  the library. Attaching a document copies it, because history must not change
  when a document is edited later.
- **A URL fetcher with an SSRF guard.** This server can reach the router, the
  other services on the box and LLeMbas itself, and the address can come from a
  model. Private ranges are refused *after resolution* and redirects are followed
  by hand so every hop is checked. An admin can open it deliberately.
- **Model capabilities split** into protocol support and a toggle per built-in
  tool. Rows predating the split have no `tool_*` keys, and absent counts as on
  when `tools` is on — otherwise an upgrade silently takes web search away from
  every model already configured for it.

Also fixes the test fixture, which built the schema with `create_all` and so ran
against a database without the FTS tables production has; it now runs
`sync_schema`, the same path startup takes.

430 tests, ruff clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-21 19:43:57 +02:00

232 lines
8.7 KiB
Python

"""Who can see a document, a note or a skill.
The most consequential tests in the library: everything else is a feature not
working, this is somebody reading somebody else's material.
"""
from __future__ import annotations
import pytest
from sqlalchemy import select
from lembas.db.models import (
PRINCIPAL_GROUP,
PRINCIPAL_USER,
Document,
Group,
Note,
Share,
User,
)
from lembas.security.passwords import hash_password
from lembas.services import sharing
from lembas.services.library import documents as documents_service
from lembas.services.library import notes as notes_service
@pytest.fixture
def people(db):
"""Three accounts: an owner, a stranger, and an administrator."""
made = {}
for name, role in (("frodo", "user"), ("gollum", "user"), ("gandalf", "admin")):
user = User(
name=name, email=f"{name}@shire.test", password_hash=hash_password("x"), role=role
)
db.add(user)
made[name] = user
db.commit()
return made
def _note(db, owner, title="Secret"):
return notes_service.create(db, owner=owner, title=title, body="The ring is in the drawer.")
# --- The rule ----------------------------------------------------------------
def test_the_owner_sees_their_own(db, people):
note = _note(db, people["frodo"])
assert sharing.can_read(db, note, people["frodo"])
assert note in db.scalars(notes_service.visible(db, people["frodo"]))
def test_a_stranger_sees_nothing(db, people):
note = _note(db, people["frodo"])
assert not sharing.can_read(db, note, people["gollum"])
assert note not in db.scalars(notes_service.visible(db, people["gollum"]))
def test_an_administrator_gets_no_free_pass(db, people):
"""Admins bypass permissions elsewhere, deliberately -- an admin can grant
themselves those in two clicks. This is different: nobody made this
available to anyone, and administering a box is not being invited."""
note = _note(db, people["frodo"])
assert not sharing.can_read(db, note, people["gandalf"])
assert note not in db.scalars(notes_service.visible(db, people["gandalf"]))
def test_sharing_with_a_person_lets_them_read(db, people):
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[people["gollum"].id], group_ids=[])
assert sharing.can_read(db, note, people["gollum"])
assert note in db.scalars(notes_service.visible(db, people["gollum"]))
def test_sharing_with_a_group_lets_its_members_read(db, people):
group = Group(name="Fellowship")
group.users.append(people["gollum"])
db.add(group)
db.commit()
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[], group_ids=[group.id])
assert sharing.can_read(db, note, people["gollum"])
def test_leaving_a_group_takes_the_access_with_it(db, people):
group = Group(name="Fellowship")
group.users.append(people["gollum"])
db.add(group)
db.commit()
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[], group_ids=[group.id])
group.users.remove(people["gollum"])
db.commit()
db.refresh(people["gollum"])
assert not sharing.can_read(db, note, people["gollum"])
def test_signed_out_sees_nothing(db, people):
_note(db, people["frodo"])
assert list(db.scalars(notes_service.visible(db, None))) == []
# --- Sharing grants reading only ---------------------------------------------
def test_a_share_does_not_grant_writing(db, people):
"""Two people editing one note with no history and no merge is worse than
the inconvenience of copying it."""
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[people["gollum"].id], group_ids=[])
assert sharing.can_read(db, note, people["gollum"])
assert not sharing.can_write(note, people["gollum"])
assert sharing.can_write(note, people["frodo"])
# --- Managing grants ---------------------------------------------------------
def test_set_grants_replaces_rather_than_adds(db, people):
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[people["gollum"].id], group_ids=[])
sharing.set_grants(db, note, user_ids=[people["gandalf"].id], group_ids=[])
assert not sharing.can_read(db, note, people["gollum"])
assert sharing.can_read(db, note, people["gandalf"])
def test_sharing_with_yourself_is_ignored(db, people):
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[people["frodo"].id], group_ids=[])
assert sharing.grants_for(db, note) == []
def test_deleting_a_note_drops_its_shares(db, people):
"""Shares carry no foreign key to their resource -- one column pointing at
three tables cannot have one -- so nothing cascades."""
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[people["gollum"].id], group_ids=[])
notes_service.delete(db, note)
assert db.scalar(select(Share).where(Share.resource_id == note.id)) is None
def test_forgetting_a_principal_drops_their_shares(db, people):
"""A stale row would grant access to whoever next received that id."""
note = _note(db, people["frodo"])
sharing.set_grants(db, note, user_ids=[people["gollum"].id], group_ids=[])
assert sharing.forget_principal(db, PRINCIPAL_USER, people["gollum"].id) == 1
assert sharing.grants_for(db, note) == []
def test_two_kinds_of_resource_do_not_collide(db, people):
"""One shares table across three resource types, so the type must be part
of the match -- otherwise a note and a document sharing an id would share
each other's access."""
note = _note(db, people["frodo"])
document = documents_service.store_upload(
db, owner=people["frodo"], payload=b"hello", filename="a.txt"
)
sharing.set_grants(db, note, user_ids=[people["gollum"].id], group_ids=[])
assert sharing.can_read(db, note, people["gollum"])
assert not sharing.can_read(db, document, people["gollum"])
def test_resource_type_refuses_something_unshareable(db, people):
"""Memory is deliberately not shareable: a record about a person is not
content to hand round."""
from lembas.db.models import Memory
with pytest.raises(ValueError):
sharing.resource_type(Memory)
# --- Through the search path -------------------------------------------------
def test_search_does_not_leak_across_owners(db, people):
"""The index is searched first and the visibility filter applied to what it
returned. Getting that order wrong leaks a hit even without the contents."""
notes_service.create(
db, owner=people["frodo"], title="Mallorn", body="A golden tree of Lothlorien."
)
assert notes_service.search(db, people["frodo"], "golden")
assert notes_service.search(db, people["gollum"], "golden") == []
assert notes_service.search(db, people["gandalf"], "golden") == []
def test_a_shared_document_is_findable_by_the_person_it_was_shared_with(db, people):
document = documents_service.store_upload(
db,
owner=people["frodo"],
payload=b"The mallorn is a golden tree.",
filename="tree.txt",
)
assert documents_service.search(db, people["gollum"], "mallorn") == []
sharing.set_grants(db, document, user_ids=[people["gollum"].id], group_ids=[])
found = documents_service.search(db, people["gollum"], "mallorn")
assert [d.id for d in found] == [document.id]
def test_the_shares_table_records_what_was_asked_for(db, people):
group = Group(name="Fellowship")
db.add(group)
db.commit()
note = _note(db, people["frodo"])
sharing.set_grants(
db, note, user_ids=[people["gollum"].id], group_ids=[group.id]
)
kinds = {(s.principal_type, s.principal_id) for s in sharing.grants_for(db, note)}
assert kinds == {
(PRINCIPAL_USER, people["gollum"].id),
(PRINCIPAL_GROUP, group.id),
}
def test_visibility_is_a_query_filter_not_a_python_loop(db, people):
"""visible_to returns a condition so callers can page and order on the
database side; a Python filter would break pagination silently."""
for index in range(3):
_note(db, people["frodo"], title=f"Note {index}")
_note(db, people["gollum"], title="Theirs")
rows = db.scalars(
notes_service.visible(db, people["frodo"]).order_by(Note.title).limit(2)
)
assert [n.title for n in rows] == ["Note 0", "Note 1"]
def test_documents_and_notes_use_the_same_rule(db, people):
document = documents_service.store_upload(
db, owner=people["frodo"], payload=b"x", filename="a.txt"
)
assert document in db.scalars(documents_service.visible(db, people["frodo"]))
assert document not in db.scalars(documents_service.visible(db, people["gollum"]))
assert list(db.scalars(select(Document).where(sharing.visible_to(Document, None)))) == []