fix: guard None metadata/doc in tool_check_duplicate and Layer1/Layer2
Chroma 1.5.x can return ``None`` inside the ``metadatas`` / ``documents`` lists of a query/get result for partially-flushed rows. The codebase already has a systemic None-guard pattern (merged #999, #1013, #1019) but three call sites were still unguarded: * ``mcp_server.tool_check_duplicate`` (``mcp_server.py:487-488``) — ``meta = results["metadatas"][0][i]`` followed by ``meta.get(...)`` raises ``AttributeError: 'NoneType' object has no attribute 'get'``. The broad ``except Exception`` wrapper (line 504) swallows it and returns an uninformative ``"Duplicate check failed"``. * ``layers.Layer1.generate`` (``layers.py:126``) — iterates ``zip(docs, metas)`` and calls ``meta.get(key)`` in the importance loop. A single None metadata blows up the entire wake-up render. * ``layers.Layer2.retrieve`` (``layers.py:224``) — same pattern, same crash path for the on-demand render. Apply the same ``meta = meta or {}`` / ``doc = doc or ""`` idiom used by the merged guards in the search path. Three-line additions, no behaviour change on well-formed results. Tests added: * ``test_check_duplicate_handles_none_metadata`` — mocks the collection query to return ``None`` for one metadata and document, asserts the call does not crash and the sentinel-rendered entry has wing/room "?" and empty content. * ``test_layer1_handles_none_metadata`` / ``_handles_none_document`` * ``test_layer2_handles_none_metadata`` Relationship to other open PRs: * **#1019** guarded ``searcher.py`` loops. This PR extends the same guard to the three call sites #1019 did not touch. * **#979** fixed ``tool_check_duplicate`` negative similarity but left the None-metadata path unguarded. * Does not overlap **#1013** (``Layer3.search_raw``) or **#999**.
This commit is contained in:
@@ -655,3 +655,72 @@ def test_memory_stack_status_with_palace(tmp_path):
|
||||
|
||||
assert result["total_drawers"] == 42
|
||||
assert result["L0_identity"]["exists"] is True
|
||||
|
||||
|
||||
# ── Layer1 / Layer2 None-metadata guards ───────────────────────────────
|
||||
#
|
||||
# Chroma 1.5.x can return ``None`` inside the ``metadatas`` / ``documents``
|
||||
# lists for partially-flushed rows. The Layer1.generate() and
|
||||
# Layer2.retrieve() loops previously called ``meta.get(...)`` without
|
||||
# coercing, raising ``AttributeError: 'NoneType' object has no attribute
|
||||
# 'get'`` and blowing up the whole wake-up render. These tests guard that
|
||||
# the loops tolerate the None entries and render the rest of the result.
|
||||
|
||||
|
||||
def test_layer1_handles_none_metadata():
|
||||
"""Layer1.generate tolerates None entries in the metadatas list."""
|
||||
docs = ["important memory", "another memory"]
|
||||
metas = [{"room": "decisions", "source_file": "a.txt"}, None]
|
||||
mock_col = _mock_chromadb_for_layer(docs, metas)
|
||||
|
||||
with (
|
||||
patch("mempalace.layers.MempalaceConfig") as mock_cfg,
|
||||
patch("mempalace.layers._get_collection", return_value=mock_col),
|
||||
):
|
||||
mock_cfg.return_value.palace_path = "/fake"
|
||||
layer = Layer1(palace_path="/fake")
|
||||
# Should not raise AttributeError on the None entry.
|
||||
result = layer.generate()
|
||||
|
||||
assert "ESSENTIAL STORY" in result
|
||||
assert "important memory" in result
|
||||
|
||||
|
||||
def test_layer1_handles_none_document():
|
||||
"""Layer1.generate tolerates None entries in the documents list."""
|
||||
docs = ["first doc", None]
|
||||
metas = [
|
||||
{"room": "r", "source_file": "a.txt"},
|
||||
{"room": "r", "source_file": "b.txt"},
|
||||
]
|
||||
mock_col = _mock_chromadb_for_layer(docs, metas)
|
||||
|
||||
with (
|
||||
patch("mempalace.layers.MempalaceConfig") as mock_cfg,
|
||||
patch("mempalace.layers._get_collection", return_value=mock_col),
|
||||
):
|
||||
mock_cfg.return_value.palace_path = "/fake"
|
||||
layer = Layer1(palace_path="/fake")
|
||||
result = layer.generate()
|
||||
|
||||
assert result # Render succeeded despite the None document.
|
||||
|
||||
|
||||
def test_layer2_handles_none_metadata():
|
||||
"""Layer2.retrieve tolerates None entries in the metadatas list."""
|
||||
mock_col = MagicMock()
|
||||
mock_col.get.return_value = {
|
||||
"documents": ["first doc", "second doc"],
|
||||
"metadatas": [{"room": "r", "source_file": "a.txt"}, None],
|
||||
}
|
||||
|
||||
with (
|
||||
patch("mempalace.layers.MempalaceConfig") as mock_cfg,
|
||||
patch("mempalace.layers._get_collection", return_value=mock_col),
|
||||
):
|
||||
mock_cfg.return_value.palace_path = "/fake"
|
||||
layer = Layer2(palace_path="/fake")
|
||||
# Should not raise AttributeError on the None entry.
|
||||
result = layer.retrieve()
|
||||
|
||||
assert "L2 — ON-DEMAND" in result
|
||||
|
||||
@@ -9,6 +9,7 @@ via monkeypatch to avoid touching real data.
|
||||
from datetime import datetime
|
||||
import json
|
||||
import sys
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
@@ -495,6 +496,41 @@ class TestWriteTools:
|
||||
result = tool_delete_drawer("nonexistent_drawer")
|
||||
assert result["success"] is False
|
||||
|
||||
def test_check_duplicate_handles_none_metadata(self, monkeypatch, config, kg):
|
||||
"""tool_check_duplicate must tolerate None entries in the result lists
|
||||
that ChromaDB 1.5.x returns for partially-flushed rows.
|
||||
|
||||
Previously ``meta = results["metadatas"][0][i]`` was unguarded and
|
||||
raised ``AttributeError: 'NoneType' object has no attribute 'get'``
|
||||
the moment the first matching drawer came back with None metadata —
|
||||
surfacing to the MCP client as the uninformative
|
||||
``"Duplicate check failed"`` because the broad ``except Exception``
|
||||
wrapper swallows the real cause.
|
||||
"""
|
||||
_patch_mcp_server(monkeypatch, config, kg)
|
||||
from mempalace import mcp_server
|
||||
|
||||
mock_col = MagicMock()
|
||||
mock_col.query.return_value = {
|
||||
"ids": [["d1", "d2"]],
|
||||
"distances": [[0.05, 0.05]],
|
||||
"metadatas": [[{"wing": "w", "room": "r"}, None]],
|
||||
"documents": [["first doc", None]],
|
||||
}
|
||||
monkeypatch.setattr(mcp_server, "_get_collection", lambda: mock_col)
|
||||
|
||||
result = mcp_server.tool_check_duplicate("any content", threshold=0.5)
|
||||
|
||||
# Both entries land in matches (above threshold), None ones rendered
|
||||
# with sentinel values rather than crashing the whole response.
|
||||
assert result.get("is_duplicate") is True
|
||||
assert len(result["matches"]) == 2
|
||||
# The None-metadata entry falls back to sentinels.
|
||||
none_entry = result["matches"][1]
|
||||
assert none_entry["wing"] == "?"
|
||||
assert none_entry["room"] == "?"
|
||||
assert none_entry["content"] == ""
|
||||
|
||||
def test_check_duplicate(self, monkeypatch, config, palace_path, seeded_collection, kg):
|
||||
_patch_mcp_server(monkeypatch, config, kg)
|
||||
from mempalace.mcp_server import tool_check_duplicate
|
||||
|
||||
Reference in New Issue
Block a user