mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
6a73279c0c
- local delete_collection: validate the collection name before rmtree. An unvalidated name like "../.." escaped files_dir and deleted arbitrary directories (path traversal). - legacy page_index(): restore the node_id/summary/text/description enhancements. IndexConfig now carries booleans (pydantic coerces the legacy 'yes'/'no' strings at the boundary), but page_index_main still compared `opt.if_add_node_id == 'yes'` — always False — so every enhancement was silently skipped for legacy-API callers. Conditions now branch on the booleans, matching pageindex/index/page_index.py. - LegacyCloudAPI._request: bound every request with a timeout (30s, 120s read timeout for streamed responses) so a dead connection can't hang legacy submit/poll/chat callers forever. The legacy contract tests pinned the missing timeout; updated to pin its presence instead. Adds regression tests: path-traversal rejection, 'yes'/'no' -> bool coercion, and timeout assertions. Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
# tests/test_config.py
|
|
import pytest
|
|
from pageindex.config import IndexConfig
|
|
|
|
|
|
def test_defaults():
|
|
config = IndexConfig()
|
|
assert config.model == "gpt-4o-2024-11-20"
|
|
assert config.retrieve_model is None
|
|
assert config.toc_check_page_num == 20
|
|
|
|
|
|
def test_overrides():
|
|
config = IndexConfig(model="gpt-5.4", retrieve_model="claude-sonnet")
|
|
assert config.model == "gpt-5.4"
|
|
assert config.retrieve_model == "claude-sonnet"
|
|
|
|
|
|
def test_unknown_key_raises():
|
|
with pytest.raises(Exception):
|
|
IndexConfig(nonexistent_key="value")
|
|
|
|
|
|
def test_model_copy_with_update():
|
|
config = IndexConfig(toc_check_page_num=30)
|
|
updated = config.model_copy(update={"model": "gpt-5.4"})
|
|
assert updated.model == "gpt-5.4"
|
|
assert updated.toc_check_page_num == 30
|
|
|
|
|
|
def test_legacy_yes_no_strings_coerce_to_bool():
|
|
"""Legacy page_index()/run_pageindex callers pass 'yes'/'no' strings;
|
|
pydantic must coerce them to the booleans the pipeline now branches on."""
|
|
config = IndexConfig(if_add_node_id="yes", if_add_node_summary="no")
|
|
assert config.if_add_node_id is True
|
|
assert config.if_add_node_summary is False
|