chore: sync latest main for wrapper requalification

This commit is contained in:
JerrettDavis
2026-11-05 13:09:29 -06:00
4 changed files with 204 additions and 12 deletions
+17 -11
View File
@@ -494,11 +494,19 @@ class HNSWVectorIndex:
self._metadata[memory.id] = IndexedMemoryMetadata.from_memory(memory)
self._embeddings[memory.id] = embedding.copy()
# Handle updates (hnswlib doesn't support true updates, so we track separately)
# Updates: add_items with an existing label replaces its vector. A batch
# can name the same id more than once; keep only the last entry so the
# graph, the cached embedding and the metadata end on the same vector
# (hnswlib may apply rows for one label out of order across threads).
update_memories = list({m.id: (m, emb) for m, emb in update_memories}.values())
if update_memories:
self._index.add_items(
np.vstack([emb for _, emb in update_memories]).astype(np.float32),
np.array([self._memory_to_hnsw[m.id] for m, _ in update_memories]),
)
for memory, embedding in update_memories:
self._metadata[memory.id] = IndexedMemoryMetadata.from_memory(memory)
self._embeddings[memory.id] = embedding.copy()
# Note: HNSW embedding stays unchanged unless we remove and re-add
if self._auto_save and self._save_path:
self.save_index(self._save_path)
@@ -748,9 +756,7 @@ class HNSWVectorIndex:
async def update_embedding(self, memory_id: str, embedding: np.ndarray) -> bool:
"""Update the embedding for an indexed memory.
Note: hnswlib doesn't support in-place updates. This stores the new
embedding but the HNSW graph uses the original. For full update,
remove and re-index the memory.
The new vector replaces the old one in the HNSW graph, so search uses it.
Args:
memory_id: The unique identifier of the memory.
@@ -777,15 +783,15 @@ class HNSWVectorIndex:
async def _update_embedding_internal(self, memory_id: str, embedding: np.ndarray) -> bool:
"""Internal embedding update without lock (caller must hold lock).
hnswlib doesn't support true in-place updates, so we:
1. Store the new embedding in our local cache
2. The HNSW index continues to use the old embedding for search
For a true update, the caller should remove and re-index.
hnswlib's ``add_items`` with an existing label replaces that element's
vector in place (``addPoint`` -> ``updatePoint``), so the label and the
id mappings stay as they are and search sees the new vector.
"""
if memory_id not in self._memory_to_hnsw:
hnsw_id = self._memory_to_hnsw.get(memory_id)
if hnsw_id is None:
return False
self._index.add_items(embedding.reshape(1, -1), np.array([hnsw_id]))
self._embeddings[memory_id] = embedding.copy()
return True
+3 -1
View File
@@ -387,7 +387,9 @@ class LocalBackend:
for rel in all_relationships:
source_name = rel.get("source", "").lower()
target_name = rel.get("target", "").lower()
rel_type = rel.get("type", "related_to")
# The memory_save tool schema names the key `relation`
# (tools.py); direct callers and older docs use `type`.
rel_type = rel.get("type") or rel.get("relation") or "related_to"
source_id = entity_id_map.get(source_name)
target_id = entity_id_map.get(target_name)
@@ -0,0 +1,107 @@
"""Re-indexing a memory on the HNSW backend must move it to its new vector.
`HierarchicalMemory.update`, `refresh` and `detach` re-index a memory under the
same id after its content (and so its embedding) changed. The HNSW adapter only
cached the new embedding; the graph kept the old vector, so search still found
the memory by its OLD content and not by the new one.
See https://github.com/headroomlabs-ai/headroom/issues/4362 (item 5).
"""
from __future__ import annotations
import numpy as np
import pytest
from headroom.memory.models import Memory
from headroom.memory.ports import VectorFilter
try:
from headroom.memory.adapters.hnsw import _check_hnswlib_available
HNSW_AVAILABLE = _check_hnswlib_available()
except ImportError:
HNSW_AVAILABLE = False
pytestmark = [
pytest.mark.skipif(not HNSW_AVAILABLE, reason="hnswlib not installed"),
pytest.mark.asyncio,
]
DIM = 8
OLD = np.eye(DIM, dtype=np.float32)[0]
NEW = np.eye(DIM, dtype=np.float32)[1]
def _index():
from headroom.memory.adapters.hnsw import HNSWVectorIndex
return HNSWVectorIndex(dimension=DIM, max_elements=16)
async def _top(index, vector: np.ndarray) -> tuple[str, float]:
results = await index.search(VectorFilter(query_vector=vector, top_k=1))
return results[0].memory.id, results[0].similarity
async def _seed(index) -> Memory:
memory = Memory(id="m1", content="old", user_id="u", embedding=OLD.copy())
await index.index(memory)
# A second memory so a stale vector cannot win by being the only entry.
await index.index(
Memory(id="m2", content="other", user_id="u", embedding=np.ones(DIM, np.float32))
)
return memory
async def test_index_on_existing_id_replaces_the_vector() -> None:
index = _index()
memory = await _seed(index)
memory.embedding = NEW.copy()
await index.index(memory)
assert index.size == 2
found, similarity = await _top(index, NEW)
assert found == "m1"
assert similarity == pytest.approx(1.0, abs=1e-5)
async def test_update_embedding_replaces_the_vector() -> None:
index = _index()
await _seed(index)
assert await index.update_embedding("m1", NEW.copy()) is True
found, similarity = await _top(index, NEW)
assert found == "m1"
assert similarity == pytest.approx(1.0, abs=1e-5)
async def test_index_batch_on_existing_id_replaces_the_vector() -> None:
index = _index()
memory = await _seed(index)
memory.embedding = NEW.copy()
assert await index.index_batch([memory]) == 1
assert index.size == 2
found, similarity = await _top(index, NEW)
assert found == "m1"
assert similarity == pytest.approx(1.0, abs=1e-5)
async def test_index_batch_repeated_id_ends_on_the_last_vector() -> None:
index = _index()
await _seed(index)
first = Memory(
id="m1", content="first", user_id="u", embedding=np.eye(DIM, dtype=np.float32)[2]
)
last = Memory(id="m1", content="last", user_id="u", embedding=NEW.copy())
await index.index_batch([first, last])
assert index.size == 2
found, similarity = await _top(index, NEW)
assert found == "m1"
assert similarity == pytest.approx(1.0, abs=1e-5)
assert np.array_equal(index._embeddings["m1"], NEW)
@@ -0,0 +1,77 @@
"""The local backend reads the relationship key the memory_save schema advertises.
`memory_save`'s plain `relationships[]` schema (headroom/memory/tools.py) names the
relationship key `relation`. LocalBackend.save_memory read only `type`, so every
relationship saved through the tool was stored as the default `related_to`.
See https://github.com/headroomlabs-ai/headroom/issues/4362 (item 7).
"""
from __future__ import annotations
from types import SimpleNamespace
from unittest.mock import AsyncMock
import pytest
from headroom.memory.backends.local import LocalBackend
from headroom.memory.models import Memory
from headroom.memory.tools import MEMORY_TOOLS
def _backend() -> tuple[LocalBackend, AsyncMock]:
backend = LocalBackend()
backend._initialized = True
async def fake_add(**kwargs: object) -> Memory:
return Memory(
id="m1",
content=str(kwargs["content"]),
user_id=str(kwargs["user_id"]),
entity_refs=list(kwargs["entity_refs"]), # type: ignore[arg-type]
)
async def fake_add_entity(entity: object) -> object:
return entity
add_relationship = AsyncMock()
backend._hierarchical_memory = SimpleNamespace(add=AsyncMock(side_effect=fake_add))
backend._graph = SimpleNamespace(
get_entity_by_name=AsyncMock(side_effect=lambda user_id, name: None),
add_entity=AsyncMock(side_effect=fake_add_entity),
add_relationship=add_relationship,
)
return backend, add_relationship
def test_schema_names_the_key_relation() -> None:
"""Pins the premise: the advertised schema uses `relation`, not `type`."""
save = next(t for t in MEMORY_TOOLS if t["function"]["name"] == "memory_save")
item = save["function"]["parameters"]["properties"]["relationships"]["items"]
assert "relation" in item["required"]
assert "type" not in item["properties"]
@pytest.mark.asyncio
@pytest.mark.parametrize(
("rel", "expected"),
[
({"source": "Alice", "relation": "works_with", "target": "Bob"}, "works_with"),
({"source": "Alice", "type": "manages", "target": "Bob"}, "manages"),
({"source": "Alice", "target": "Bob"}, "related_to"),
],
)
async def test_relationship_type_is_read_from_relation_or_type(
rel: dict[str, str], expected: str
) -> None:
backend, add_relationship = _backend()
await backend.save_memory(
content="Alice works with Bob",
user_id="alice",
entities=["Alice", "Bob"],
relationships=[rel],
)
add_relationship.assert_awaited_once()
stored = add_relationship.await_args.args[0]
assert stored.relation_type == expected