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.
161 lines
4.6 KiB
Python
161 lines
4.6 KiB
Python
"""Tests for AIAgent._sanitize_tool_call_arguments."""
|
|
|
|
import copy
|
|
import logging
|
|
|
|
from run_agent import AIAgent
|
|
|
|
|
|
_MISSING = object()
|
|
|
|
|
|
def _tool_call(call_id="call_1", name="read_file", arguments='{"path":"/tmp/foo"}'):
|
|
function = {"name": name}
|
|
if arguments is not _MISSING:
|
|
function["arguments"] = arguments
|
|
return {
|
|
"id": call_id,
|
|
"type": "function",
|
|
"function": function,
|
|
}
|
|
|
|
|
|
def _assistant_message(*tool_calls):
|
|
return {
|
|
"role": "assistant",
|
|
"content": "tooling",
|
|
"tool_calls": list(tool_calls),
|
|
}
|
|
|
|
|
|
def _tool_message(call_id="call_1", content="ok"):
|
|
return {
|
|
"role": "tool",
|
|
"tool_call_id": call_id,
|
|
"content": content,
|
|
}
|
|
|
|
|
|
def test_valid_arguments_unchanged():
|
|
messages = [
|
|
{"role": "user", "content": "hello"},
|
|
_assistant_message(_tool_call(arguments='{"path":"/tmp/foo"}')),
|
|
_tool_message(content="done"),
|
|
]
|
|
original = copy.deepcopy(messages)
|
|
|
|
repaired = AIAgent._sanitize_tool_call_arguments(messages)
|
|
|
|
assert repaired == 0
|
|
assert messages == original
|
|
|
|
|
|
def test_truncated_arguments_replaced_with_empty_object(caplog):
|
|
messages = [
|
|
_assistant_message(_tool_call(arguments='{"path": "/tmp/foo')),
|
|
]
|
|
|
|
with caplog.at_level(logging.WARNING, logger="run_agent"):
|
|
repaired = AIAgent._sanitize_tool_call_arguments(
|
|
messages,
|
|
logger=logging.getLogger("run_agent"),
|
|
session_id="session-123",
|
|
)
|
|
|
|
assert repaired == 1
|
|
assert messages[0]["tool_calls"][0]["function"]["arguments"] == "{}"
|
|
assert any(
|
|
"session=session-123" in record.message
|
|
and "tool_call_id=call_1" in record.message
|
|
for record in caplog.records
|
|
)
|
|
|
|
|
|
def test_marker_appended_to_existing_tool_message():
|
|
marker = AIAgent._TOOL_CALL_ARGUMENTS_CORRUPTION_MARKER
|
|
messages = [
|
|
_assistant_message(_tool_call(arguments='{"path": "/tmp/foo')),
|
|
_tool_message(content="existing tool output"),
|
|
]
|
|
|
|
repaired = AIAgent._sanitize_tool_call_arguments(messages)
|
|
|
|
assert repaired == 1
|
|
assert messages[1]["content"] == f"{marker}\nexisting tool output"
|
|
|
|
|
|
|
|
|
|
def _disabled_test_marker_message_inserted_when_missing():
|
|
marker = AIAgent._TOOL_CALL_ARGUMENTS_CORRUPTION_MARKER
|
|
messages = [
|
|
_assistant_message(_tool_call(arguments='{"path": "/tmp/foo')),
|
|
{"role": "user", "content": "next turn"},
|
|
]
|
|
|
|
repaired = AIAgent._sanitize_tool_call_arguments(messages)
|
|
|
|
assert repaired == 1
|
|
assert messages[1] == {
|
|
"role": "tool",
|
|
"name": "read_file",
|
|
"tool_call_id": "call_1",
|
|
"content": marker,
|
|
}
|
|
assert messages[2] == {"role": "user", "content": "next turn"}
|
|
|
|
|
|
def test_multiple_corrupted_tool_calls_in_one_message():
|
|
marker = AIAgent._TOOL_CALL_ARGUMENTS_CORRUPTION_MARKER
|
|
messages = [
|
|
_assistant_message(
|
|
_tool_call(call_id="call_1", arguments='{"path": "/tmp/foo'),
|
|
_tool_call(call_id="call_2", arguments='{"path":"/tmp/bar"}'),
|
|
_tool_call(call_id="call_3", arguments='{"mode":"tail"'),
|
|
),
|
|
]
|
|
|
|
repaired = AIAgent._sanitize_tool_call_arguments(messages)
|
|
|
|
assert repaired == 2
|
|
assert messages[0]["tool_calls"][0]["function"]["arguments"] == "{}"
|
|
assert messages[0]["tool_calls"][1]["function"]["arguments"] == '{"path":"/tmp/bar"}'
|
|
assert messages[0]["tool_calls"][2]["function"]["arguments"] == "{}"
|
|
assert messages[1]["tool_call_id"] == "call_1"
|
|
assert messages[1]["content"] == marker
|
|
assert messages[2]["tool_call_id"] == "call_3"
|
|
assert messages[2]["content"] == marker
|
|
|
|
|
|
def test_empty_string_arguments_treated_as_empty_object(caplog):
|
|
messages = [
|
|
_assistant_message(_tool_call(arguments="")),
|
|
]
|
|
|
|
with caplog.at_level(logging.WARNING, logger="run_agent"):
|
|
repaired = AIAgent._sanitize_tool_call_arguments(
|
|
messages,
|
|
logger=logging.getLogger("run_agent"),
|
|
session_id="session-123",
|
|
)
|
|
|
|
assert repaired == 0
|
|
assert messages[0]["tool_calls"][0]["function"]["arguments"] == "{}"
|
|
assert caplog.records == []
|
|
|
|
|
|
def test_non_assistant_messages_ignored():
|
|
messages = [
|
|
{"role": "user", "content": "hello", "tool_calls": [_tool_call(arguments='{"bad":')]},
|
|
{"role": "tool", "tool_call_id": "call_1", "content": "ok"},
|
|
{"role": "system", "content": "sys", "tool_calls": [_tool_call(arguments='{"bad":')]},
|
|
None,
|
|
"not a dict",
|
|
]
|
|
original = copy.deepcopy(messages)
|
|
|
|
repaired = AIAgent._sanitize_tool_call_arguments(messages)
|
|
|
|
assert repaired == 0
|
|
assert messages == original
|