mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-10-26 19:01:39 -04:00
85ce1d0172
Small models carry every tool definition on every request, and the
per-kind trios (four searches, three getters, three readers) cost a
quarter of an 8k context while giving the model near-duplicate choices.
Three generic endpoints replace them:
- POST files/search: one search over videos, archives, and docs with an
optional kind; channel (name or id), domain, author, subject each
imply their kind and are ignored for other kinds. When the term also
names channels/domains/authors, they are returned as `matches` so the
model can narrow without a second tool. Channels resolve by name, so
the library map already in the prompt is enough: no list call first.
- GET files/{id}: detail by id whatever the kind; videos now report
has_captions/has_comments and the full description, archives keep
their snapshot history.
- GET files/{id}/content?part=text|comments: captions, page text, or
comments, paged; a wrong part for the kind says what the file is.
Inventories take an optional slug on GET /inventories (one tool lists
and fetches). Listings are slimmed: no derivable captions/text links,
no size/mimetype, duration as H:MM:SS, published as a date. The
library map gains the tag names.
wrolpi_mcp keeps every existing tool name; the wrappers now call the
generic routes, and search_files/get_file/read_content are exposed too.
The old per-kind endpoints remain until the modes switch over.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
62 lines
2.5 KiB
Python
62 lines
2.5 KiB
Python
"""Tests for the library map injected into every chat."""
|
|
import time
|
|
from unittest import mock
|
|
|
|
import pytest
|
|
|
|
from modules.ai import context
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_build_library_context(async_client, test_session, video_factory, archive_factory,
|
|
test_zim, food_inventory_factory, tag_factory):
|
|
"""The map carries today's date, counts, and exact names."""
|
|
from wrolpi.collections.models import Collection
|
|
test_session.add(Collection(name='Talking Sasquach', kind='channel'))
|
|
await tag_factory('Food Preservation')
|
|
video_factory(title='a video')
|
|
archive_factory(domain='example.com', title='a page', contents='contents')
|
|
food_inventory_factory(name='Pantry')
|
|
test_session.commit()
|
|
|
|
text = context.build_library_context()
|
|
assert 'Today is' in text
|
|
assert '1 videos, 1 archived web pages' in text
|
|
assert 'Talking Sasquach' in text
|
|
assert 'example.com' in text
|
|
assert 'WROLPi example ZIM' in text
|
|
assert 'Pantry' in text
|
|
assert 'Tags (1): Food Preservation' in text
|
|
assert 'user spellings may differ' in text
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_library_context_caps_names(async_client, test_session, archive_factory):
|
|
"""A huge library lists at most MAX_NAMES names per category, plus a count of the rest."""
|
|
for i in range(context.MAX_NAMES + 5):
|
|
archive_factory(domain=f'site{i:02}.com', title=f'page {i}', contents='x')
|
|
test_session.commit()
|
|
|
|
text = context.build_library_context()
|
|
assert f'Archived websites ({context.MAX_NAMES + 5}):' in text
|
|
assert 'and 5 more' in text
|
|
listed = [i for i in range(context.MAX_NAMES + 5) if f'site{i:02}.com' in text]
|
|
assert len(listed) == context.MAX_NAMES
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_library_context_cache_and_degradation(async_client, test_session):
|
|
"""The map is cached briefly; a build failure serves the stale copy rather than crashing chat."""
|
|
context._cache.update(text=None, expires=0.0)
|
|
first = context.get_library_context()
|
|
assert first and 'Today is' in first
|
|
|
|
with mock.patch('modules.ai.context.build_library_context', side_effect=RuntimeError('db down')) as build:
|
|
# Cached: the builder is not called.
|
|
assert context.get_library_context() == first
|
|
build.assert_not_called()
|
|
|
|
# Expired + failing builder: the stale copy is served.
|
|
context._cache['expires'] = time.time() - 1
|
|
assert context.get_library_context() == first
|
|
build.assert_called_once()
|