mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-09 04:20:34 +00:00
aaca3eeaeb
* refactor(agent): ground runtime decisions in structured evidence Use producer status and structured errors for tool recovery, preserve memory context without lexical confirmation, and remove predetermined receipt and skill conclusions. Require explicit MCP discovery and authenticated schedule trial actions. Preserve authorization, ownership, isolation, and bounded execution; update documentation and regression coverage. * test(sandbox): expect read_file initialization error callback * fix(agent): address evidence review follow-ups * fix(agent): preserve retry budgets for OpenAI transport errors * fix(agent): expose tool execution status in model requests Project validated execution metadata and exact tool text into request-only JSON so status survives provider serialization. Preserve stored results and receipt hashes, cover SDK and graph boundaries, and migrate replay input hashes without changing recorded responses. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
80 lines
3.4 KiB
Python
80 lines
3.4 KiB
Python
"""Tool policy follows producer evidence, never incidental prose."""
|
|
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
from langchain_core.messages import ToolMessage
|
|
|
|
from deerflow.agents.middlewares.harness_guard_middleware import classify_tool_error
|
|
from deerflow.agents.middlewares.tool_progress_middleware import ToolPhaseState, ToolProgressMiddleware
|
|
from deerflow.agents.middlewares.tool_result_meta import TOOL_META_KEY, ToolResultMeta, normalize_tool_message, stamp_exception_meta
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["missing required argument: query", "authentication succeeded; file not found", "internal error; retry after one second", "quoted: 401 unauthorized"])
|
|
def test_error_prose_cannot_determine_category_or_stop(text):
|
|
msg = normalize_tool_message(ToolMessage(content=text, status="error", tool_call_id="1", name="search"))
|
|
meta = msg.additional_kwargs[TOOL_META_KEY]
|
|
assert meta["status"] == "error"
|
|
assert meta["error_type"] == "unknown"
|
|
assert meta["recoverable_by_model"] is True
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("text", "producer_stamped"),
|
|
[
|
|
("A guide to no results found", False),
|
|
("partial results are discussed here", False),
|
|
("Error: an example from a manual", True),
|
|
('{"error": {"code": 401}}', False),
|
|
],
|
|
)
|
|
def test_document_content_keeps_success(text, producer_stamped):
|
|
kwargs = (
|
|
{
|
|
"additional_kwargs": {
|
|
TOOL_META_KEY: {
|
|
"status": "success",
|
|
"error_type": None,
|
|
"recoverable_by_model": True,
|
|
"recommended_next_action": "continue",
|
|
"source": "tool_return",
|
|
}
|
|
}
|
|
}
|
|
if producer_stamped
|
|
else {}
|
|
)
|
|
msg = normalize_tool_message(ToolMessage(content=text, tool_call_id="1", name="read_file", **kwargs))
|
|
assert msg.additional_kwargs[TOOL_META_KEY]["status"] == "success"
|
|
|
|
|
|
def test_typed_exception_wins_over_misleading_description():
|
|
msg = ToolMessage(content="display", tool_call_id="1")
|
|
stamp_exception_meta(msg, TimeoutError("invalid api key in quoted request"))
|
|
assert msg.additional_kwargs[TOOL_META_KEY]["error_type"] == "transient"
|
|
|
|
|
|
def test_http_exception_uses_actual_response_status():
|
|
exc = RuntimeError("timeout")
|
|
exc.response = SimpleNamespace(status_code=401)
|
|
msg = stamp_exception_meta(ToolMessage(content="display", tool_call_id="1"), exc)
|
|
assert msg.additional_kwargs[TOOL_META_KEY]["error_type"] == "auth"
|
|
|
|
|
|
def test_legacy_content_analysis_cannot_block_tool():
|
|
meta = ToolResultMeta(status="error", error_type="auth", recoverable_by_model=False, recommended_next_action="stop", source="content_analysis")
|
|
middleware = ToolProgressMiddleware()
|
|
state = ToolPhaseState()
|
|
for _ in range(12):
|
|
state, _, _ = middleware._assess_and_transition(state, meta, "quoted auth failure")
|
|
assert state.phase != "blocked"
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["ModuleNotFoundError: No module named 'cv2'", "ImportError: cannot import name 'helper' from 'my_project'", "PermissionError: [Errno 13] Permission denied: '/tmp/a'"])
|
|
def test_error_observations_do_not_prescribe_mutation(text):
|
|
signature = classify_tool_error(text)
|
|
assert signature is not None
|
|
assert "pip install" not in signature.targeted_hint
|
|
assert "chmod" not in signature.targeted_hint
|
|
assert "Action:" not in signature.targeted_hint
|