Chris CoutinhoandClaude Opus 4.8
8f7a8432f5
Round-2 review on PR #893:
- Add test_generate_retries_on_connection_error (generate() shares the transient
retry; guards the decorator against accidental removal).
- Add test_process_document_records_drop_on_exhausted_retries: drives
process_document to retry-exhaustion and asserts record_ingest_dropped is
called once with the classified reason (processor-level coverage, not just the
_drop_reason unit).
- Note in _drop_reason that a multi-failure group is labelled by its first leaf
(best-effort, no "mixed" bucket).
SonarCloud: the quality gate was failing on new_security_hotspots_reviewed
(S5332 "use https") from http:// URLs in the test _req() helpers — switched to
https:// (mirrors commit 98c9d58e).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
112 lines
3.3 KiB
Python
112 lines
3.3 KiB
Python
"""Unit tests for the embed-drop classifier (card 309).
|
|
|
|
``processor._drop_reason`` maps a terminal indexing failure to a metric label
|
|
so the transient backend-pod-rollover causes (connection / timeout) are
|
|
alertable on ``astrolabe_vector_ingest_dropped_total`` distinctly from
|
|
persistent faults.
|
|
"""
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from nextcloud_mcp_server.vector import processor
|
|
|
|
|
|
def _req() -> httpx.Request:
|
|
return httpx.Request("POST", "https://gw/v1/embeddings")
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_httpx_connect_and_timeout_classified():
|
|
assert processor._drop_reason(httpx.ConnectError("refused")) == "connection"
|
|
assert processor._drop_reason(httpx.ReadTimeout("slow")) == "timeout"
|
|
assert processor._drop_reason(httpx.ConnectTimeout("slow")) == "timeout"
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_openai_errors_classified():
|
|
from openai import (
|
|
APIConnectionError,
|
|
APITimeoutError,
|
|
InternalServerError,
|
|
RateLimitError,
|
|
)
|
|
|
|
req = _req()
|
|
assert processor._drop_reason(APIConnectionError(request=req)) == "connection"
|
|
assert processor._drop_reason(APITimeoutError(request=req)) == "timeout"
|
|
assert (
|
|
processor._drop_reason(
|
|
RateLimitError("rl", response=httpx.Response(429, request=req), body=None)
|
|
)
|
|
== "rate_limit"
|
|
)
|
|
assert (
|
|
processor._drop_reason(
|
|
InternalServerError(
|
|
"boom", response=httpx.Response(503, request=req), body=None
|
|
)
|
|
)
|
|
== "server"
|
|
)
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_exception_group_unwraps_to_leaf():
|
|
group = BaseExceptionGroup(
|
|
"unhandled errors in a TaskGroup", [httpx.ConnectError("refused")]
|
|
)
|
|
assert processor._drop_reason(group) == "connection"
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_nested_exception_group_descends_to_leaf():
|
|
"""A doubly-wrapped group must still classify by its leaf, not 'other'."""
|
|
nested = BaseExceptionGroup(
|
|
"outer", [BaseExceptionGroup("inner", [httpx.ReadTimeout("slow")])]
|
|
)
|
|
assert processor._drop_reason(nested) == "timeout"
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_qdrant_namespace_classified():
|
|
from qdrant_client.http.exceptions import UnexpectedResponse
|
|
|
|
exc = UnexpectedResponse(500, "err", b"", headers=None)
|
|
assert processor._drop_reason(exc) == "qdrant"
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_unknown_error_falls_back_to_other():
|
|
assert processor._drop_reason(ValueError("nope")) == "other"
|
|
|
|
|
|
@pytest.mark.unit
|
|
async def test_process_document_records_drop_on_exhausted_retries(mocker):
|
|
"""Exhausting retries in process_document increments the drop counter with
|
|
the classified reason (and re-raises so the outer handler counts the error)."""
|
|
from nextcloud_mcp_server.vector.scanner import DocumentTask
|
|
|
|
doc_task = DocumentTask(
|
|
user_id="alice",
|
|
doc_id="42",
|
|
doc_type="note",
|
|
operation="index",
|
|
modified_at=0,
|
|
)
|
|
|
|
mocker.patch.object(
|
|
processor,
|
|
"get_qdrant_client",
|
|
mocker.AsyncMock(return_value=mocker.MagicMock()),
|
|
)
|
|
mocker.patch.object(
|
|
processor, "_index_document", side_effect=httpx.ConnectError("refused")
|
|
)
|
|
rec = mocker.patch.object(processor, "record_ingest_dropped")
|
|
|
|
with pytest.raises(httpx.ConnectError):
|
|
await processor.process_document(doc_task, mocker.MagicMock(), max_retries=1)
|
|
|
|
rec.assert_called_once_with("connection")
|