mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
956147d864
- AgentRunner.run: offload to a worker-thread event loop when called from inside a running loop (Jupyter, FastAPI handlers) — mirrors pipeline._run_async; Runner.run_sync raised RuntimeError there. - SQLiteStorage: create connections with check_same_thread=False so close() can actually close connections created by worker threads. Each thread still gets its own connection via threading.local; with the default True those closes raised ProgrammingError (silently swallowed) and leaked every worker connection. - CloudBackend.query: non-streaming chat completions now use a 300s timeout and a single attempt. The default 30s ReadTimeout fired before generation finished and the retry loop re-billed the full server-side retrieval + generation up to three times. _request gains retries/timeout overrides; the exhausted-retry path also no longer sleeps before raising. - MarkdownParser: content before the first heading (abstract/preamble) becomes a node instead of being silently dropped and unretrievable; a file with no headings at all yields a single document node instead of zero nodes (which pushed an empty page list into the pipeline). - LegacyCloudAPI.is_retrieval_ready: API failures (revoked key, network down) now propagate as PageIndexAPIError instead of reading as "not ready", which turned polling loops into infinite loops. Adds regression tests for each fix. Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
81 lines
3.1 KiB
Python
81 lines
3.1 KiB
Python
import pytest
|
|
from pageindex.storage.sqlite import SQLiteStorage
|
|
|
|
@pytest.fixture
|
|
def storage(tmp_path):
|
|
return SQLiteStorage(str(tmp_path / "test.db"))
|
|
|
|
def test_create_and_list_collections(storage):
|
|
storage.create_collection("papers")
|
|
assert "papers" in storage.list_collections()
|
|
|
|
def test_get_or_create_collection_idempotent(storage):
|
|
storage.get_or_create_collection("papers")
|
|
storage.get_or_create_collection("papers")
|
|
assert storage.list_collections().count("papers") == 1
|
|
|
|
def test_delete_collection(storage):
|
|
storage.create_collection("papers")
|
|
storage.delete_collection("papers")
|
|
assert "papers" not in storage.list_collections()
|
|
|
|
def test_save_and_get_document(storage):
|
|
storage.create_collection("papers")
|
|
doc = {
|
|
"doc_name": "test.pdf", "doc_description": "A test",
|
|
"file_path": "/tmp/test.pdf", "doc_type": "pdf",
|
|
"structure": [{"title": "Intro", "node_id": "0001"}],
|
|
}
|
|
storage.save_document("papers", "doc-1", doc)
|
|
result = storage.get_document("papers", "doc-1")
|
|
assert result["doc_name"] == "test.pdf"
|
|
assert result["doc_type"] == "pdf"
|
|
|
|
def test_get_document_structure(storage):
|
|
storage.create_collection("papers")
|
|
structure = [{"title": "Ch1", "node_id": "0001", "nodes": []}]
|
|
storage.save_document("papers", "doc-1", {
|
|
"doc_name": "test.pdf", "doc_type": "pdf",
|
|
"file_path": "/tmp/test.pdf", "structure": structure,
|
|
})
|
|
result = storage.get_document_structure("papers", "doc-1")
|
|
assert result[0]["title"] == "Ch1"
|
|
|
|
def test_list_documents(storage):
|
|
storage.create_collection("papers")
|
|
storage.save_document("papers", "doc-1", {"doc_name": "p1.pdf", "doc_type": "pdf", "file_path": "/tmp/p1.pdf", "structure": []})
|
|
storage.save_document("papers", "doc-2", {"doc_name": "p2.pdf", "doc_type": "pdf", "file_path": "/tmp/p2.pdf", "structure": []})
|
|
docs = storage.list_documents("papers")
|
|
assert len(docs) == 2
|
|
|
|
def test_delete_document(storage):
|
|
storage.create_collection("papers")
|
|
storage.save_document("papers", "doc-1", {"doc_name": "test.pdf", "doc_type": "pdf", "file_path": "/tmp/test.pdf", "structure": []})
|
|
storage.delete_document("papers", "doc-1")
|
|
assert len(storage.list_documents("papers")) == 0
|
|
|
|
def test_delete_collection_cascades_documents(storage):
|
|
storage.create_collection("papers")
|
|
storage.save_document("papers", "doc-1", {"doc_name": "test.pdf", "doc_type": "pdf", "file_path": "/tmp/test.pdf", "structure": []})
|
|
storage.delete_collection("papers")
|
|
assert "papers" not in storage.list_collections()
|
|
|
|
|
|
def test_close_closes_connections_created_in_other_threads(storage):
|
|
"""Regression: with check_same_thread=True, close() from another thread
|
|
raised ProgrammingError (swallowed) and leaked every worker connection."""
|
|
import sqlite3
|
|
import threading
|
|
|
|
conns = {}
|
|
|
|
def worker():
|
|
conns["worker"] = storage._get_conn()
|
|
|
|
t = threading.Thread(target=worker)
|
|
t.start()
|
|
t.join()
|
|
|
|
storage.close() # main thread closes the worker's connection too
|
|
with pytest.raises(sqlite3.ProgrammingError):
|
|
conns["worker"].execute("SELECT 1")
|