d10bb2ab6f
`scripts/run_tests.sh tests/<dir>/` is how a change gets its regression
coverage run, so a test filed under the wrong directory is a test nobody
runs when that code changes. Two kinds of drift had accumulated.
Parallel directories for one source package, folded into the mirror:
tests/acp -> tests/acp_adapter (its __init__/conftest move with it)
tests/cli -> tests/hermes_cli (prompt_toolkit fixture merged into
hermes_cli/conftest.py)
tests/run_agent -> tests/agent (backoff fixture becomes
agent/conftest.py)
tests/relay -> tests/gateway/relay
tests/state -> tests/hermes_state
246 loose files at tests/ root, routed by the package they import/patch:
hermes_cli, hermes_state, agent, gateway, tools, plugins, tui_gateway, cron.
Installer and desktop-update script tests go to tests/scripts/{install,
desktop_update}/. 43 tests of root-level modules (batch_runner, utils,
hermes_constants, packaging) stay at the root.
Filenames drop their issue numbers (95 files: test_89315_x.py -> test_x.py);
the number stays in the module docstring where it has context.
Collisions: test_cli_skin_integration.py existed in both tests/ and tests/cli
with different subsets — merged into one (10 tests, all kept);
run_agent/test_pre_compress_memory_context.py -> agent/..._handoff.py;
tests/test_account_usage.py -> agent/test_account_usage_fetch.py;
tests/test_web_server.py -> hermes_cli/test_web_server_ws_ping.py.
Deleted: test_minisweagent_path.py (empty since PR #2804),
test_model_picker_scroll.py (tested a private copy of the logic, imported
nothing), test_process_loop_event_loop_warning.py (asserted asyncio behaviour,
imported nothing from Hermes).
Repo-root path arithmetic (Path(__file__).parents[N], dirname chains) is
bumped for the 202 files that changed depth and verified by evaluating every
such expression against the new location. classify_changes' desktop-updater
lane prefix, tests-os.yml's ignore glob and every in-tree path comment follow
the moves. tests/test_tests_tree_layout.py keeps the tree from drifting back.
99 lines
3.5 KiB
Python
99 lines
3.5 KiB
Python
"""Regression: empty-body HTTP 4xx errors must still surface a real provider message.
|
|
|
|
Reported on Windows (#36109): an LLM API call returned HTTP 400 with an *empty*
|
|
parsed SDK ``body`` ({}), so ``_summarize_api_error`` fell through to the bare
|
|
``str(error)`` path and the user saw only "HTTP 400" with no provider detail.
|
|
The SDK leaves ``body`` empty in this case, but the underlying httpx
|
|
``response`` still carries the real payload in ``.text``. These tests lock the
|
|
contract: when ``body`` is empty, fall back to ``response.text`` (parsing a JSON
|
|
``error.message`` / ``message`` when present) so logs and CLI show the real
|
|
provider error. This is a diagnostic improvement and is platform-agnostic.
|
|
"""
|
|
|
|
from types import SimpleNamespace
|
|
from typing import Any
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from run_agent import AIAgent
|
|
|
|
|
|
def _make_empty_body_error(response_text: str, status_code: int = 400) -> Exception:
|
|
"""Mimic an OpenAI-SDK error whose parsed body is empty but whose httpx
|
|
response still holds the payload text."""
|
|
err = Exception("") # str(error) is empty/uninformative on this path
|
|
err.status_code = status_code
|
|
err.body = {} # empty dict — the #36109 trigger
|
|
err.response = SimpleNamespace(text=response_text)
|
|
return err
|
|
|
|
|
|
def test_empty_body_falls_back_to_response_json_error_message():
|
|
"""A JSON payload with error.message is surfaced (not a bare HTTP 400)."""
|
|
err = _make_empty_body_error(
|
|
'{"error": {"message": "model `foo` does not exist", "type": "invalid_request_error"}}'
|
|
)
|
|
summary = AIAgent._summarize_api_error(err)
|
|
assert "HTTP 400" in summary
|
|
assert "model `foo` does not exist" in summary
|
|
|
|
@pytest.mark.parametrize(
|
|
"technical_message",
|
|
[
|
|
"Temporary failure in name resolution",
|
|
"Name or service not known",
|
|
"nodename nor servname provided, or not known",
|
|
"getaddrinfo failed",
|
|
"No address associated with hostname",
|
|
"Network is unreachable",
|
|
],
|
|
)
|
|
def test_network_resolution_failure_explains_that_the_user_may_be_offline(
|
|
technical_message,
|
|
):
|
|
error = OSError(-3, technical_message)
|
|
|
|
summary = AIAgent._summarize_api_error(error)
|
|
|
|
assert summary == (
|
|
"Hermes can't reach the model provider. You may be offline. "
|
|
"Check your internet connection and try again."
|
|
)
|
|
assert "name resolution" not in summary.lower()
|
|
|
|
|
|
def test_wrapped_dns_resolution_failure_gets_the_same_friendly_message():
|
|
try:
|
|
try:
|
|
raise OSError(-3, "Temporary failure in name resolution")
|
|
except OSError as cause:
|
|
raise RuntimeError("Connection error.") from cause
|
|
except RuntimeError as error:
|
|
summary = AIAgent._summarize_api_error(error)
|
|
|
|
assert "You may be offline" in summary
|
|
assert "Connection error" not in summary
|
|
|
|
|
|
def test_unread_streaming_response_does_not_crash_and_falls_back_to_exception_message():
|
|
"""Unread streaming responses must not replace the real provider error."""
|
|
|
|
class _StreamingError(Exception):
|
|
def __init__(self):
|
|
super().__init__("Gemini HTTP 429: quota exceeded")
|
|
self.status_code = 429
|
|
self.response: Any = None
|
|
|
|
err = _StreamingError()
|
|
|
|
class _UnreadStreamingResponse:
|
|
@property
|
|
def text(self):
|
|
raise httpx.ResponseNotRead()
|
|
|
|
err.response = _UnreadStreamingResponse()
|
|
summary = AIAgent._summarize_api_error(err)
|
|
assert "HTTP 429" in summary
|
|
assert "Gemini HTTP 429: quota exceeded" in summary
|