PageIndex/tests/test_config.py

42 lines
1.3 KiB
Python
Raw Normal View History

# 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
fix: prompt-injection delimiter escape, legacy config coercion, gather resilience, true cross-thread concurrency bound Addresses items 4-8 from the max-effort review of PR #272 (VectifyAI/PageIndex#272). - agent.py: wrap_with_doc_context() strips '<'/'>' from doc_name/doc_description (untrusted: unsanitized filename / LLM-generated from document content) before inserting them into the <docs>...</docs> block, so embedded content can never form a literal </docs> that closes the delimiter early and escapes the untrusted-data boundary SCOPED_SYSTEM_PROMPT relies on. Deterministic per-field transform, doesn't touch the (cacheable) static system prompt. - ConfigLoader.load() (legacy 0.2.x compat) now routes merged overrides through IndexConfig before returning, so a legacy 'no' string gets pydantic's bool coercion instead of surviving as a truthy non-empty string — page_index_main's bare `if opt.if_add_node_summary:` checks (changed from `== 'yes'` elsewhere in this PR) were silently inverting caller intent and firing unwanted billed LLM calls. - verify_toc, process_large_node_recursively, tree_parser, generate_summaries_for_structure, generate_summaries_for_structure_md: added return_exceptions=True to their asyncio.gather calls (llm_completion/ llm_acompletion raise RuntimeError on retry exhaustion, added earlier in this PR), each with a degrade path matching the pattern already used by sibling hardened gathers in the same files. One transient LLM failure no longer aborts the whole document's indexing. - _llm_semaphore is now a true process-wide ceiling (threading.Semaphore, shared across every thread/event loop) instead of one asyncio.Semaphore per event loop -- concurrently indexing N documents on N threads no longer multiplies the effective cap by N. A max_concurrency_scope() override is layered as a second, nested, per-loop restriction that can only tighten the effective cap within the ceiling, never widen past it. - set_llm_params() mutated a bare process-wide dict with no per-call isolation, unlike max_concurrency which already had ContextVar scoping. Added llm_params_scope() (mirrors max_concurrency_scope) + IndexConfig.llm_params, wired into build_index() the same way max_concurrency already was, so concurrent indexing jobs with different llm kwargs don't leak into each other. Adds regression tests for all five. Full suite: 221 passed, 2 skipped (one pre-existing, unrelated flaky cloud-streaming test intermittently fails on rerun; confirmed independent of this change). Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
2026-07-09 11:15:12 +08:00
def test_llm_params_field_defaults_to_none():
assert IndexConfig().llm_params is None
assert IndexConfig(llm_params={"temperature": 1}).llm_params == {"temperature": 1}