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>
49 lines
2.3 KiB
Python
49 lines
2.3 KiB
Python
"""Memory retention must not depend on lexical guesses about user intent."""
|
|
|
|
from copy import deepcopy
|
|
|
|
import pytest
|
|
from langchain_core.messages import AIMessage, HumanMessage
|
|
from test_memory_updater import _make_memory, _make_updater, _memory_config
|
|
|
|
from deerflow.agents.memory.backends.deermem.deer_mem import DeerMem
|
|
from deerflow.agents.memory.backends.deermem.deermem.core.updater import _strip_upload_mentions_from_memory
|
|
|
|
|
|
def test_short_contextual_confirmation_is_preserved(tmp_path):
|
|
messages = [HumanMessage(content="What are my preferences?"), AIMessage(content="Do you always prefer Chinese replies?"), HumanMessage(content="\u662f\u7684"), AIMessage(content="Understood.")]
|
|
memory = DeerMem(backend_config={"storage_path": str(tmp_path)})
|
|
|
|
prepared = memory._prepare_update(messages)
|
|
|
|
assert prepared is not None
|
|
assert prepared[0] == messages
|
|
|
|
|
|
@pytest.mark.parametrize("content", ["User builds file upload systems for a living.", "User prefers uploading documents through the browser."])
|
|
def test_upload_words_cannot_delete_stored_memory(content):
|
|
memory = _make_memory([{"id": "a", "content": content}])
|
|
memory["user"]["workContext"]["summary"] = content
|
|
expected = deepcopy(memory)
|
|
assert _strip_upload_mentions_from_memory(memory) == expected
|
|
|
|
|
|
def test_regex_reinforcement_cannot_confirm_existing_fact():
|
|
updater = _make_updater(config=_memory_config(fact_eviction_policy="hybrid-v1"))
|
|
memory = _make_memory([{"id": "a", "content": "User prefers concise replies", "category": "preference", "confidence": 0.9}])
|
|
result = updater._apply_updates(memory, {"factsToReinforce": [{"id": "a", "scope": "user", "reason": "quoted positive phrase"}]}, signals=frozenset({"reinforcement"}))
|
|
assert result["facts"][0].get("confirmationCount", 0) == 0
|
|
|
|
|
|
def test_extraction_prompt_does_not_prescribe_confirmation_or_confidence():
|
|
updater = _make_updater()
|
|
_, prompt = updater._prepare_update_prompt(
|
|
[HumanMessage(content="The phrase 'yes, exactly' was quoted from a book.")],
|
|
agent_name=None,
|
|
signals=frozenset({"reinforcement"}),
|
|
)
|
|
system = "\n".join(message.content for message in prompt if message.type == "system")
|
|
assert '"factsToReinforce": []' in system
|
|
assert "confidence >= 0.95" not in system
|
|
assert "3-5 concurrent focus themes" not in system
|