nanobot/tests/agent/test_dream.py
chengyongru 401d1f57fa fix(dream): allow LLM to retry on tool errors instead of failing immediately
Dream Phase 2 uses fail_on_tool_error=True, which terminates the entire
run on the first tool error (e.g. old_text not found in edit_file).
Normal agent runs default to False so the LLM can self-correct and retry.
Dream should behave the same way.
2026-04-05 22:10:34 +08:00

98 lines
3.3 KiB
Python

"""Tests for the Dream class — two-phase memory consolidation via AgentRunner."""
import pytest
from unittest.mock import AsyncMock, MagicMock
from nanobot.agent.memory import Dream, MemoryStore
from nanobot.agent.runner import AgentRunResult
@pytest.fixture
def store(tmp_path):
s = MemoryStore(tmp_path)
s.write_soul("# Soul\n- Helpful")
s.write_user("# User\n- Developer")
s.write_memory("# Memory\n- Project X active")
return s
@pytest.fixture
def mock_provider():
p = MagicMock()
p.chat_with_retry = AsyncMock()
return p
@pytest.fixture
def mock_runner():
return MagicMock()
@pytest.fixture
def dream(store, mock_provider, mock_runner):
d = Dream(store=store, provider=mock_provider, model="test-model", max_batch_size=5)
d._runner = mock_runner
return d
def _make_run_result(
stop_reason="completed",
final_content=None,
tool_events=None,
usage=None,
):
return AgentRunResult(
final_content=final_content or stop_reason,
stop_reason=stop_reason,
messages=[],
tools_used=[],
usage={},
tool_events=tool_events or [],
)
class TestDreamRun:
async def test_noop_when_no_unprocessed_history(self, dream, mock_provider, mock_runner, store):
"""Dream should not call LLM when there's nothing to process."""
result = await dream.run()
assert result is False
mock_provider.chat_with_retry.assert_not_called()
mock_runner.run.assert_not_called()
async def test_calls_runner_for_unprocessed_entries(self, dream, mock_provider, mock_runner, store):
"""Dream should call AgentRunner when there are unprocessed history entries."""
store.append_history("User prefers dark mode")
mock_provider.chat_with_retry.return_value = MagicMock(content="New fact")
mock_runner.run = AsyncMock(return_value=_make_run_result(
tool_events=[{"name": "edit_file", "status": "ok", "detail": "memory/MEMORY.md"}],
))
result = await dream.run()
assert result is True
mock_runner.run.assert_called_once()
spec = mock_runner.run.call_args[0][0]
assert spec.max_iterations == 10
assert spec.fail_on_tool_error is False
async def test_advances_dream_cursor(self, dream, mock_provider, mock_runner, store):
"""Dream should advance the cursor after processing."""
store.append_history("event 1")
store.append_history("event 2")
mock_provider.chat_with_retry.return_value = MagicMock(content="Nothing new")
mock_runner.run = AsyncMock(return_value=_make_run_result())
await dream.run()
assert store.get_last_dream_cursor() == 2
async def test_compacts_processed_history(self, dream, mock_provider, mock_runner, store):
"""Dream should compact history after processing."""
store.append_history("event 1")
store.append_history("event 2")
store.append_history("event 3")
mock_provider.chat_with_retry.return_value = MagicMock(content="Nothing new")
mock_runner.run = AsyncMock(return_value=_make_run_result())
await dream.run()
# After Dream, cursor is advanced and 3, compact keeps last max_history_entries
entries = store.read_unprocessed_history(since_cursor=0)
assert all(e["cursor"] > 0 for e in entries)