`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.
76 lines
2.9 KiB
Python
76 lines
2.9 KiB
Python
"""Tests for #7100 — transient failures (429/timeout) must not drop the
|
|
user message from the transcript.
|
|
|
|
The #1630 fix introduced a blanket skip of transcript writes on any
|
|
``failed`` agent result. That was correct for context-overflow failures
|
|
(which would otherwise cause a session-growth loop), but it also caused
|
|
transient provider failures (rate limits, read timeouts, connection
|
|
resets) to silently drop the user's message — so the agent had no memory
|
|
of the last turn on the next attempt.
|
|
|
|
The gateway classifier must distinguish:
|
|
|
|
* ``compression_exhausted=True`` OR context-keyword errors OR a generic
|
|
``400`` on a long history → context-overflow → skip transcript
|
|
* everything else that fails → transient → persist the user message
|
|
"""
|
|
|
|
|
|
from gateway.run_turn import is_context_overflow_failure_result
|
|
|
|
|
|
def _classify(agent_result: dict, history_len: int) -> tuple[bool, bool]:
|
|
"""``(agent_failed_early, is_context_overflow_failure)`` as the gateway computes them."""
|
|
return bool(agent_result.get("failed")), is_context_overflow_failure_result(agent_result, history_len)
|
|
|
|
|
|
class TestContextOverflowStillSkipsTranscript:
|
|
"""#1630 behavior must be preserved for real context-overflow cases."""
|
|
|
|
def test_compression_exhausted_is_context_overflow(self):
|
|
agent_result = {
|
|
"failed": True,
|
|
"compression_exhausted": True,
|
|
"error": "Request payload too large: max compression attempts reached.",
|
|
}
|
|
failed, ctx_overflow = _classify(agent_result, history_len=100)
|
|
assert failed
|
|
assert ctx_overflow
|
|
|
|
|
|
class TestTransientFailureKeepsUserMessage:
|
|
"""Transient provider failures must NOT skip the transcript — doing so
|
|
drops the user message and the agent forgets the turn. (#7100)"""
|
|
|
|
def test_rate_limit_429_is_not_context_overflow(self):
|
|
agent_result = {
|
|
"failed": True,
|
|
"error": (
|
|
"API call failed after 3 retries: 429 Too Many Requests "
|
|
"— rate limit exceeded"
|
|
),
|
|
}
|
|
failed, ctx_overflow = _classify(agent_result, history_len=10)
|
|
assert failed
|
|
assert not ctx_overflow
|
|
|
|
def test_read_timeout_is_not_context_overflow(self):
|
|
agent_result = {
|
|
"failed": True,
|
|
"error": "ReadTimeout: HTTPSConnectionPool(host='api.z.ai'): Read timed out.",
|
|
}
|
|
failed, ctx_overflow = _classify(agent_result, history_len=10)
|
|
assert failed
|
|
assert not ctx_overflow
|
|
|
|
|
|
class TestSuccessfulResultUnaffected:
|
|
def test_successful_result_neither_failed_nor_overflow(self):
|
|
agent_result = {
|
|
"final_response": "Hello!",
|
|
"messages": [{"role": "assistant", "content": "Hello!"}],
|
|
}
|
|
failed, ctx_overflow = _classify(agent_result, history_len=10)
|
|
assert not failed
|
|
assert not ctx_overflow
|