2026-04-06 22:51:04 +08:00
|
|
|
# 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
|
2026-07-07 10:05:38 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
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}
|