mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-18 21:21:05 +02:00
fix: resolve five P1 defects from the SDK review
- 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
This commit is contained in:
parent
6a73279c0c
commit
956147d864
10 changed files with 171 additions and 16 deletions
|
|
@ -202,3 +202,20 @@ def test_query_stream_connect_failure_raises_instead_of_hanging(monkeypatch):
|
|||
|
||||
with pytest.raises(CloudAPIError, match="request failed"):
|
||||
asyncio.run(_run())
|
||||
|
||||
|
||||
def test_query_uses_long_timeout_and_single_attempt(monkeypatch):
|
||||
"""Non-streaming chat completion is non-idempotent and slow: it must get
|
||||
a long timeout and must NOT be retried (each retry re-bills the query)."""
|
||||
backend = CloudBackend(api_key="pi-test")
|
||||
calls = []
|
||||
|
||||
def fake_request(method, url, headers=None, **kwargs):
|
||||
calls.append(kwargs)
|
||||
raise cloud_mod.requests.ConnectionError("boom")
|
||||
|
||||
monkeypatch.setattr(cloud_mod.requests, "request", fake_request)
|
||||
with pytest.raises(CloudAPIError):
|
||||
backend.query("col", "q", doc_ids=["d1"])
|
||||
assert len(calls) == 1
|
||||
assert calls[0]["timeout"] == 300
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue