mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
748f1a0417
Bug #1 (Critical): get_parent_session_id() doesn't exist on SessionDB. Replaced with get_session(sid)['parent_session_id']. Also fixed lineage walk loop that only ever iterated once due to unconditional break. Bug #2 (Medium): Path traversal via session_id. CheckpointStore._path_for now validates session_id with regex ^[A-Za-z0-9_-]+$ to reject /, \, .. Bug #3 (Critical): 'checkpoint' tool never offered to model. Added 'checkpoint' to the 'todo' toolset tools list in TOOLSETS dict. Bug #4 (Low): flush_checkpoint test didn't call flush_checkpoint. Test now calls AIAgent.flush_checkpoint() directly via mock agent. Bug #5 (Medium): Injection fallback grabbed ANY in_progress checkpoint from unrelated sessions. Removed the broad fallback; caller now walks the parent lineage chain and passes the specific session_id that has a checkpoint file. Added 13 regression tests in test_checkpoint_regression.py covering all five bug fixes.
53 lines
No EOL
1.8 KiB
Python
53 lines
No EOL
1.8 KiB
Python
"""Test that flush_checkpoint writes a checkpoint via checkpoint_tool."""
|
|
import json
|
|
import pytest
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
|
|
def test_flush_checkpoint_method_exists():
|
|
"""AIAgent must have a flush_checkpoint method."""
|
|
from run_agent import AIAgent
|
|
assert hasattr(AIAgent, "flush_checkpoint")
|
|
|
|
|
|
def test_flush_checkpoint_writes_to_store(tmp_path):
|
|
"""flush_checkpoint should write a checkpoint with current session state."""
|
|
from agent.checkpoint_store import CheckpointStore
|
|
|
|
store = CheckpointStore(checkpoints_dir=tmp_path / "checkpoints")
|
|
|
|
mock_todo = MagicMock()
|
|
mock_todo._items = [
|
|
{"content": "Step 1", "status": "completed"},
|
|
{"content": "Step 2", "status": "in_progress"},
|
|
]
|
|
mock_todo.format_for_injection.return_value = "- [x] Step 1\n- [~] Step 2"
|
|
|
|
mock_session_db = MagicMock()
|
|
mock_session_db.get_session_title.return_value = "Test session title"
|
|
|
|
mock_agent = MagicMock()
|
|
mock_agent.session_id = "flush_test_session"
|
|
mock_agent._checkpoint_store = store
|
|
mock_agent._todo_store = mock_todo
|
|
mock_agent._session_db = mock_session_db
|
|
|
|
# Call the real flush_checkpoint method
|
|
from run_agent import AIAgent
|
|
AIAgent.flush_checkpoint(mock_agent)
|
|
|
|
# Verify a checkpoint was written for this session
|
|
saved = store.read("flush_test_session")
|
|
assert saved is not None
|
|
assert saved["task"] == "Test session title"
|
|
assert saved["status"] == "in_progress"
|
|
|
|
|
|
def test_flush_checkpoint_noops_without_store(tmp_path):
|
|
"""flush_checkpoint should silently return if _checkpoint_store is None."""
|
|
mock_agent = MagicMock()
|
|
mock_agent._checkpoint_store = None
|
|
|
|
from run_agent import AIAgent
|
|
# Should not raise
|
|
AIAgent.flush_checkpoint(mock_agent) |