chore: import upstream snapshot with attribution
CI / changes (push) Has been cancelled
CI / cd libs/checkpoint (push) Has been cancelled
CI / cd libs/checkpoint-conformance (push) Has been cancelled
CI / cd libs/checkpoint-postgres (push) Has been cancelled
CI / cd libs/checkpoint-sqlite (push) Has been cancelled
CI / cd libs/cli (push) Has been cancelled
CI / cd libs/prebuilt (push) Has been cancelled
CI / cd libs/sdk-py (push) Has been cancelled
CI / cd libs/langgraph (push) Has been cancelled
CI / Check SDK methods matching (push) Has been cancelled
CI / Check CLI schema hasn't changed #3.13 (push) Has been cancelled
CI / CLI integration test (push) Has been cancelled
CI / sdk-py integration test (push) Has been cancelled
CI / CI Success (push) Has been cancelled
baseline / benchmark (push) Has been cancelled
Deploy Redirects to GitHub Pages / deploy (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 12:37:18 +08:00
commit a7d6d88f6f
667 changed files with 232986 additions and 0 deletions
@@ -0,0 +1,190 @@
from typing import Any
import pytest
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
Checkpoint,
CheckpointMetadata,
create_checkpoint,
empty_checkpoint,
)
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
class TestAsyncSqliteSaver:
@pytest.fixture(autouse=True)
def setup(self) -> None:
# objects for test setup
self.config_1: RunnableConfig = {
"configurable": {
"thread_id": "thread-1",
"checkpoint_id": "1",
"checkpoint_ns": "",
}
}
self.config_2: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2",
"checkpoint_ns": "",
}
}
self.config_3: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2-inner",
"checkpoint_ns": "inner",
}
}
self.chkpnt_1: Checkpoint = empty_checkpoint()
self.chkpnt_2: Checkpoint = create_checkpoint(self.chkpnt_1, {}, 1)
self.chkpnt_3: Checkpoint = empty_checkpoint()
self.metadata_1: CheckpointMetadata = {
"source": "input",
"step": 2,
"writes": {},
"score": 1,
}
self.metadata_2: CheckpointMetadata = {
"source": "loop",
"step": 1,
"writes": {"foo": "bar"},
"score": None,
}
self.metadata_3: CheckpointMetadata = {}
async def test_combined_metadata(self) -> None:
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_ns": "",
"__super_private_key": "super_private_value",
},
"metadata": {"run_id": "my_run_id"},
}
await saver.aput(config, self.chkpnt_2, self.metadata_2, {})
checkpoint = await saver.aget_tuple(config)
assert checkpoint is not None and checkpoint.metadata == {
**self.metadata_2,
"run_id": "my_run_id",
}
async def test_asearch(self) -> None:
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
await saver.aput(self.config_1, self.chkpnt_1, self.metadata_1, {})
await saver.aput(self.config_2, self.chkpnt_2, self.metadata_2, {})
await saver.aput(self.config_3, self.chkpnt_3, self.metadata_3, {})
# call method / assertions
query_1 = {"source": "input"} # search by 1 key
query_2 = {
"step": 1,
"writes": {"foo": "bar"},
} # search by multiple keys
query_3: dict[str, Any] = {} # search by no keys, return all checkpoints
query_4 = {"source": "update", "step": 1} # no match
search_results_1 = [c async for c in saver.alist(None, filter=query_1)]
assert len(search_results_1) == 1
assert search_results_1[0].metadata == self.metadata_1
search_results_2 = [c async for c in saver.alist(None, filter=query_2)]
assert len(search_results_2) == 1
assert search_results_2[0].metadata == self.metadata_2
search_results_3 = [c async for c in saver.alist(None, filter=query_3)]
assert len(search_results_3) == 3
search_results_4 = [c async for c in saver.alist(None, filter=query_4)]
assert len(search_results_4) == 0
# search by config (defaults to checkpoints across all namespaces)
search_results_5 = [
c
async for c in saver.alist({"configurable": {"thread_id": "thread-2"}})
]
assert len(search_results_5) == 2
assert {
search_results_5[0].config["configurable"]["checkpoint_ns"],
search_results_5[1].config["configurable"]["checkpoint_ns"],
} == {"", "inner"}
# Test limit param
search_results_6 = [
c
async for c in saver.alist(
{"configurable": {"thread_id": "thread-2"}}, limit=1
)
]
assert len(search_results_6) == 1
assert search_results_6[0].config["configurable"]["thread_id"] == "thread-2"
# Test before param
search_results_7 = [
c async for c in saver.alist(None, before=search_results_5[1].config)
]
assert len(search_results_7) == 1
assert search_results_7[0].config["configurable"]["thread_id"] == "thread-1"
async def test_limit_parameter_sql_injection_prevention(self) -> None:
"""Test that the limit parameter properly uses parameterized queries to prevent SQL injection."""
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
# Setup: Create multiple checkpoints
for i in range(5):
config: RunnableConfig = {
"configurable": {
"thread_id": f"thread-{i}",
"checkpoint_ns": "",
}
}
checkpoint = empty_checkpoint()
metadata: CheckpointMetadata = {"index": i}
await saver.aput(config, checkpoint, metadata, {})
# Test that limit works correctly with valid integer
results = [c async for c in saver.alist(None, limit=2)]
assert len(results) == 2
# Test that limit=0 returns no results
results = [c async for c in saver.alist(None, limit=0)]
assert len(results) == 0
# Test that limit=None returns all results
results = [c async for c in saver.alist(None, limit=None)]
assert len(results) == 5
# Test explicit SQL injection attempt via limit parameter
# Even if type checking is bypassed and a malicious string is passed,
# the parameterized query will treat it as a value, not SQL code
# This would cause an error (can't convert string to int for LIMIT),
# which is the correct secure behavior
malicious_limits = [
"1; DROP TABLE checkpoints; --",
"1 OR 1=1",
"999999 UNION SELECT * FROM checkpoints",
]
for malicious_limit in malicious_limits:
# The parameterized query should safely reject non-integer limits
# or convert them in a way that prevents SQL injection
try:
# Bypass type checking by casting
results = [
c
async for c in saver.alist(None, limit=malicious_limit) # type: ignore
]
# If it doesn't raise an error, it should at least not execute the injection
# SQLite's parameter binding will try to convert the string to an integer
# which will either fail or treat it as 0
except Exception:
# Expected: SQLite should reject invalid limit values
pass
# Verify the checkpoints table still exists and has all data
# (would have been dropped if injection succeeded)
results = [c async for c in saver.alist(None, limit=None)]
assert len(results) == 5
@@ -0,0 +1,718 @@
import asyncio
import os
import tempfile
import uuid
from collections.abc import AsyncIterator, Generator, Iterable
from contextlib import asynccontextmanager
from typing import cast
import pytest
from langgraph.store.base import (
GetOp,
Item,
ListNamespacesOp,
PutOp,
SearchOp,
)
from langgraph.store.sqlite import AsyncSqliteStore
from langgraph.store.sqlite.base import SqliteIndexConfig
from tests.test_store import CharacterEmbeddings
@pytest.fixture(scope="function", params=["memory", "file"])
async def store(request: pytest.FixtureRequest) -> AsyncIterator[AsyncSqliteStore]:
"""Create an AsyncSqliteStore for testing."""
if request.param == "memory":
# In-memory store
async with AsyncSqliteStore.from_conn_string(":memory:") as store:
await store.setup()
yield store
else:
# Temporary file store
temp_file = tempfile.NamedTemporaryFile(delete=False)
temp_file.close()
try:
async with AsyncSqliteStore.from_conn_string(temp_file.name) as store:
await store.setup()
yield store
finally:
os.unlink(temp_file.name)
@pytest.fixture(scope="function")
def fake_embeddings() -> CharacterEmbeddings:
"""Create fake embeddings for testing."""
return CharacterEmbeddings(dims=500)
@asynccontextmanager
async def create_vector_store(
fake_embeddings: CharacterEmbeddings,
conn_string: str = ":memory:",
text_fields: list[str] | None = None,
) -> AsyncIterator[AsyncSqliteStore]:
"""Create an AsyncSqliteStore with vector search capabilities."""
index_config: SqliteIndexConfig = {
"dims": fake_embeddings.dims,
"embed": fake_embeddings,
"text_fields": text_fields,
}
async with AsyncSqliteStore.from_conn_string(
conn_string, index=index_config
) as store:
await store.setup()
yield store
@pytest.fixture(scope="function", params=["memory", "file"])
def conn_string(request: pytest.FixtureRequest) -> Generator[str, None, None]:
if request.param == "memory":
yield ":memory:"
else:
temp_file = tempfile.NamedTemporaryFile(delete=False)
temp_file.close()
try:
yield temp_file.name
finally:
os.unlink(temp_file.name)
async def test_no_running_loop(store: AsyncSqliteStore) -> None:
"""Test that sync methods raise proper errors in the main thread."""
with pytest.raises(asyncio.InvalidStateError):
store.put(("foo", "bar"), "baz", {"val": "baz"})
with pytest.raises(asyncio.InvalidStateError):
store.get(("foo", "bar"), "baz")
with pytest.raises(asyncio.InvalidStateError):
store.delete(("foo", "bar"), "baz")
with pytest.raises(asyncio.InvalidStateError):
store.search(("foo", "bar"))
with pytest.raises(asyncio.InvalidStateError):
store.list_namespaces(prefix=("foo",))
with pytest.raises(asyncio.InvalidStateError):
store.batch([PutOp(namespace=("foo", "bar"), key="baz", value={"val": "baz"})])
async def test_large_batches_async(store: AsyncSqliteStore) -> None:
"""Test processing large batch operations asynchronously."""
N = 100
M = 10
coros = []
for m in range(M):
for i in range(N):
coros.append(
store.aput(
("test", "foo", "bar", "baz", str(m % 2)),
f"key{i}",
value={"foo": "bar" + str(i)},
)
)
coros.append(
asyncio.create_task(
store.aget(
("test", "foo", "bar", "baz", str(m % 2)),
f"key{i}",
)
)
)
coros.append(
asyncio.create_task(
store.alist_namespaces(
prefix=None,
max_depth=m + 1,
)
)
)
coros.append(
asyncio.create_task(
store.asearch(
("test",),
)
)
)
coros.append(
store.aput(
("test", "foo", "bar", "baz", str(m % 2)),
f"key{i}",
value={"foo": "bar" + str(i)},
)
)
coros.append(
store.adelete(
("test", "foo", "bar", "baz", str(m % 2)),
f"key{i}",
)
)
results = await asyncio.gather(*coros)
assert len(results) == M * N * 6
async def test_abatch_order(store: AsyncSqliteStore) -> None:
"""Test ordering of batch operations in async context."""
# Setup test data
await store.aput(("test", "foo"), "key1", {"data": "value1"})
await store.aput(("test", "bar"), "key2", {"data": "value2"})
ops = [
GetOp(namespace=("test", "foo"), key="key1"),
PutOp(namespace=("test", "bar"), key="key2", value={"data": "value2"}),
SearchOp(
namespace_prefix=("test",), filter={"data": "value1"}, limit=10, offset=0
),
ListNamespacesOp(match_conditions=None, max_depth=None, limit=10, offset=0),
GetOp(namespace=("test",), key="key3"),
]
results = await store.abatch(
cast(Iterable[GetOp | PutOp | SearchOp | ListNamespacesOp], ops)
)
assert len(results) == 5
assert isinstance(results[0], Item)
assert isinstance(results[0].value, dict)
assert results[0].value == {"data": "value1"}
assert results[0].key == "key1"
assert results[1] is None # Put operation returns None
assert isinstance(results[2], list)
# SQLite query implementation might return different results
# Just check that we get a list back and don't check the exact content
assert isinstance(results[3], list)
assert len(results[3]) > 0
assert results[4] is None # Non-existent key returns None
# Test reordered operations
ops_reordered = [
SearchOp(namespace_prefix=("test",), filter=None, limit=5, offset=0),
GetOp(namespace=("test", "bar"), key="key2"),
ListNamespacesOp(match_conditions=None, max_depth=None, limit=5, offset=0),
PutOp(namespace=("test",), key="key3", value={"data": "value3"}),
GetOp(namespace=("test", "foo"), key="key1"),
]
results_reordered = await store.abatch(
cast(Iterable[GetOp | PutOp | SearchOp | ListNamespacesOp], ops_reordered)
)
assert len(results_reordered) == 5
assert isinstance(results_reordered[0], list)
assert len(results_reordered[0]) >= 2 # Should find at least our two test items
assert isinstance(results_reordered[1], Item)
assert results_reordered[1].value == {"data": "value2"}
assert results_reordered[1].key == "key2"
assert isinstance(results_reordered[2], list)
assert len(results_reordered[2]) > 0
assert results_reordered[3] is None # Put operation returns None
assert isinstance(results_reordered[4], Item)
assert results_reordered[4].value == {"data": "value1"}
assert results_reordered[4].key == "key1"
async def test_batch_get_ops(store: AsyncSqliteStore) -> None:
"""Test GET operations in batch context."""
# Setup test data
await store.aput(("test",), "key1", {"data": "value1"})
await store.aput(("test",), "key2", {"data": "value2"})
ops = [
GetOp(namespace=("test",), key="key1"),
GetOp(namespace=("test",), key="key2"),
GetOp(namespace=("test",), key="key3"), # Non-existent key
]
results = await store.abatch(ops)
assert len(results) == 3
assert results[0] is not None
assert results[1] is not None
assert results[2] is None
if results[0] is not None:
assert results[0].key == "key1"
if results[1] is not None:
assert results[1].key == "key2"
async def test_batch_put_ops(store: AsyncSqliteStore) -> None:
"""Test PUT operations in batch context."""
ops = [
PutOp(namespace=("test",), key="key1", value={"data": "value1"}),
PutOp(namespace=("test",), key="key2", value={"data": "value2"}),
PutOp(namespace=("test",), key="key3", value=None), # Delete operation
]
results = await store.abatch(ops)
assert len(results) == 3
assert all(result is None for result in results)
# Verify the puts worked
items = await store.asearch(("test",), limit=10)
assert len(items) == 2 # key3 had None value so wasn't stored
async def test_batch_search_ops(store: AsyncSqliteStore) -> None:
"""Test SEARCH operations in batch context."""
# Setup test data
await store.aput(("test", "foo"), "key1", {"data": "value1"})
await store.aput(("test", "bar"), "key2", {"data": "value2"})
ops = [
SearchOp(
namespace_prefix=("test",), filter={"data": "value1"}, limit=10, offset=0
),
SearchOp(namespace_prefix=("test",), filter=None, limit=5, offset=0),
]
results = await store.abatch(ops)
assert len(results) == 2
# SQLite query implementation might return different results
# Just check that we get lists back and don't check the exact content
assert isinstance(results[0], list)
assert isinstance(results[1], list)
assert len(results[1]) >= 1 # We should at least find some results
async def test_batch_list_namespaces_ops(store: AsyncSqliteStore) -> None:
"""Test LIST NAMESPACES operations in batch context."""
# Setup test data
await store.aput(("test", "namespace1"), "key1", {"data": "value1"})
await store.aput(("test", "namespace2"), "key2", {"data": "value2"})
ops = [ListNamespacesOp(match_conditions=None, max_depth=None, limit=10, offset=0)]
results = await store.abatch(ops)
assert len(results) == 1
if isinstance(results[0], list):
assert len(results[0]) == 2
assert ("test", "namespace1") in results[0]
assert ("test", "namespace2") in results[0]
async def test_vector_store_initialization(
fake_embeddings: CharacterEmbeddings,
) -> None:
"""Test store initialization with embedding config."""
async with create_vector_store(fake_embeddings) as store:
assert store.index_config is not None
assert store.index_config["dims"] == fake_embeddings.dims
if hasattr(store.index_config.get("embed"), "embed_documents"):
assert store.index_config["embed"] == fake_embeddings
async def test_vector_insert_with_auto_embedding(
fake_embeddings: CharacterEmbeddings,
conn_string: str,
) -> None:
"""Test inserting items that get auto-embedded."""
async with create_vector_store(fake_embeddings, conn_string=conn_string) as store:
docs = [
("doc1", {"text": "short text"}),
("doc2", {"text": "longer text document"}),
("doc3", {"text": "longest text document here"}),
("doc4", {"description": "text in description field"}),
("doc5", {"content": "text in content field"}),
("doc6", {"body": "text in body field"}),
]
for key, value in docs:
await store.aput(("test",), key, value)
results = await store.asearch(("test",), query="long text")
assert len(results) > 0
doc_order = [r.key for r in results]
assert "doc2" in doc_order
assert "doc3" in doc_order
async def test_vector_update_with_embedding(
fake_embeddings: CharacterEmbeddings,
conn_string: str,
) -> None:
"""Test that updating items properly updates their embeddings."""
async with create_vector_store(fake_embeddings, conn_string=conn_string) as store:
await store.aput(("test",), "doc1", {"text": "zany zebra Xerxes"})
await store.aput(("test",), "doc2", {"text": "something about dogs"})
await store.aput(("test",), "doc3", {"text": "text about birds"})
results_initial = await store.asearch(("test",), query="Zany Xerxes")
assert len(results_initial) > 0
assert results_initial[0].score is not None
assert results_initial[0].key == "doc1"
initial_score = results_initial[0].score
await store.aput(("test",), "doc1", {"text": "new text about dogs"})
results_after = await store.asearch(("test",), query="Zany Xerxes")
after_score = next((r.score for r in results_after if r.key == "doc1"), 0.0)
assert (
after_score is not None
and initial_score is not None
and after_score < initial_score
)
results_new = await store.asearch(("test",), query="new text about dogs")
for r in results_new:
if r.key == "doc1":
assert (
r.score is not None
and after_score is not None
and r.score > after_score
)
# Don't index this one
await store.aput(
("test",), "doc4", {"text": "new text about dogs"}, index=False
)
results_new = await store.asearch(
("test",), query="new text about dogs", limit=3
)
assert not any(r.key == "doc4" for r in results_new)
async def test_vector_search_with_filters(
fake_embeddings: CharacterEmbeddings,
conn_string: str,
) -> None:
"""Test combining vector search with filters."""
async with create_vector_store(fake_embeddings, conn_string=conn_string) as store:
docs = [
("doc1", {"text": "red apple", "color": "red", "score": 4.5}),
("doc2", {"text": "red car", "color": "red", "score": 3.0}),
("doc3", {"text": "green apple", "color": "green", "score": 4.0}),
("doc4", {"text": "blue car", "color": "blue", "score": 3.5}),
]
for key, value in docs:
await store.aput(("test",), key, value)
# Vector search with filters can be inconsistent in test environments
# Skip asserting exact results as we've already validated the functionality
# in the synchronous tests
_ = await store.asearch(("test",), query="apple", filter={"color": "red"})
# Skip asserting exact results as we've already validated the functionality
# in the synchronous tests
_ = await store.asearch(("test",), query="car", filter={"color": "red"})
# Skip asserting exact results as we've already validated the functionality
# in the synchronous tests
_ = await store.asearch(
("test",), query="bbbbluuu", filter={"score": {"$gt": 3.2}}
)
# Skip asserting exact results as we've already validated the functionality
# in the synchronous tests
_ = await store.asearch(
("test",), query="apple", filter={"score": {"$gte": 4.0}, "color": "green"}
)
async def test_vector_search_pagination(fake_embeddings: CharacterEmbeddings) -> None:
"""Test pagination with vector search."""
async with create_vector_store(fake_embeddings) as store:
for i in range(5):
await store.aput(
("test",), f"doc{i}", {"text": f"test document number {i}"}
)
results_page1 = await store.asearch(("test",), query="test", limit=2)
results_page2 = await store.asearch(("test",), query="test", limit=2, offset=2)
assert len(results_page1) == 2
assert len(results_page2) == 2
assert results_page1[0].key != results_page2[0].key
all_results = await store.asearch(("test",), query="test", limit=10)
assert len(all_results) == 5
async def test_vector_search_edge_cases(fake_embeddings: CharacterEmbeddings) -> None:
"""Test edge cases in vector search."""
async with create_vector_store(fake_embeddings) as store:
await store.aput(("test",), "doc1", {"text": "test document"})
results = await store.asearch(("test",), query="")
assert len(results) == 1
results = await store.asearch(("test",), query=None)
assert len(results) == 1
long_query = "test " * 100
results = await store.asearch(("test",), query=long_query)
assert len(results) == 1
special_query = "test!@#$%^&*()"
results = await store.asearch(("test",), query=special_query)
assert len(results) == 1
async def test_embed_with_path(
fake_embeddings: CharacterEmbeddings,
) -> None:
"""Test vector search with specific text fields in SQLite store."""
async with create_vector_store(
fake_embeddings, text_fields=["key0", "key1", "key3"]
) as store:
# This will have 2 vectors representing it
doc1 = {
# Omit key0 - check it doesn't raise an error
"key1": "xxx",
"key2": "yyy",
"key3": "zzz",
}
# This will have 3 vectors representing it
doc2 = {
"key0": "uuu",
"key1": "vvv",
"key2": "www",
"key3": "xxx",
}
await store.aput(("test",), "doc1", doc1)
await store.aput(("test",), "doc2", doc2)
# doc2.key3 and doc1.key1 both would have the highest score
results = await store.asearch(("test",), query="xxx")
assert len(results) == 2
assert results[0].key != results[1].key
assert results[0].score > 0.9
assert results[1].score > 0.9
# ~Only match doc2
results = await store.asearch(("test",), query="uuu")
assert len(results) == 2
assert results[0].key != results[1].key
assert results[0].key == "doc2"
assert results[0].score > results[1].score
# Un-indexed - will have low results for both. Not zero (because we're projecting)
# but less than the above.
results = await store.asearch(("test",), query="www")
assert len(results) == 2
assert results[0].score < 0.9
assert results[1].score < 0.9
async def test_basic_store_ops(
fake_embeddings: CharacterEmbeddings,
) -> None:
"""Test vector search with specific text fields in SQLite store."""
async with create_vector_store(
fake_embeddings, text_fields=["key0", "key1", "key3"]
) as store:
uid = uuid.uuid4().hex
namespace = (uid, "test", "documents")
item_id = "doc1"
item_value = {"title": "Test Document", "content": "Hello, World!"}
results = await store.asearch((uid,))
assert len(results) == 0
await store.aput(namespace, item_id, item_value)
item = await store.aget(namespace, item_id)
assert item is not None
assert item.namespace == namespace
assert item.key == item_id
assert item.value == item_value
assert item.created_at is not None
assert item.updated_at is not None
updated_value = {
"title": "Updated Test Document",
"content": "Hello, LangGraph!",
}
await asyncio.sleep(1.01)
await store.aput(namespace, item_id, updated_value)
updated_item = await store.aget(namespace, item_id)
assert updated_item is not None
assert updated_item.value == updated_value
assert updated_item.updated_at > item.updated_at
different_namespace = (uid, "test", "other_documents")
item_in_different_namespace = await store.aget(different_namespace, item_id)
assert item_in_different_namespace is None
new_item_id = "doc2"
new_item_value = {"title": "Another Document", "content": "Greetings!"}
await store.aput(namespace, new_item_id, new_item_value)
items = await store.asearch((uid, "test"), limit=10)
assert len(items) == 2
assert any(item.key == item_id for item in items)
assert any(item.key == new_item_id for item in items)
namespaces = await store.alist_namespaces(prefix=(uid, "test"))
assert (uid, "test", "documents") in namespaces
await store.adelete(namespace, item_id)
await store.adelete(namespace, new_item_id)
deleted_item = await store.aget(namespace, item_id)
assert deleted_item is None
deleted_item = await store.aget(namespace, new_item_id)
assert deleted_item is None
empty_search_results = await store.asearch((uid, "test"), limit=10)
assert len(empty_search_results) == 0
async def test_list_namespaces(
fake_embeddings: CharacterEmbeddings,
) -> None:
"""Test list namespaces functionality with various filters."""
async with create_vector_store(
fake_embeddings, text_fields=["key0", "key1", "key3"]
) as store:
test_pref = str(uuid.uuid4())
test_namespaces = [
(test_pref, "test", "documents", "public", test_pref),
(test_pref, "test", "documents", "private", test_pref),
(test_pref, "test", "images", "public", test_pref),
(test_pref, "test", "images", "private", test_pref),
(test_pref, "prod", "documents", "public", test_pref),
(test_pref, "prod", "documents", "some", "nesting", "public", test_pref),
(test_pref, "prod", "documents", "private", test_pref),
]
# Add test data
for namespace in test_namespaces:
await store.aput(namespace, "dummy", {"content": "dummy"})
# Test prefix filtering
prefix_result = await store.alist_namespaces(prefix=(test_pref, "test"))
assert len(prefix_result) == 4
assert all(ns[1] == "test" for ns in prefix_result)
# Test specific prefix
specific_prefix_result = await store.alist_namespaces(
prefix=(test_pref, "test", "documents")
)
assert len(specific_prefix_result) == 2
assert all(ns[1:3] == ("test", "documents") for ns in specific_prefix_result)
# Test suffix filtering
suffix_result = await store.alist_namespaces(suffix=("public", test_pref))
assert len(suffix_result) == 4
assert all(ns[-2] == "public" for ns in suffix_result)
# Test combined prefix and suffix
prefix_suffix_result = await store.alist_namespaces(
prefix=(test_pref, "test"), suffix=("public", test_pref)
)
assert len(prefix_suffix_result) == 2
assert all(
ns[1] == "test" and ns[-2] == "public" for ns in prefix_suffix_result
)
# Test wildcard in prefix
wildcard_prefix_result = await store.alist_namespaces(
prefix=(test_pref, "*", "documents")
)
assert len(wildcard_prefix_result) == 5
assert all(ns[2] == "documents" for ns in wildcard_prefix_result)
# Test wildcard in suffix
wildcard_suffix_result = await store.alist_namespaces(
suffix=("*", "public", test_pref)
)
assert len(wildcard_suffix_result) == 4
assert all(ns[-2] == "public" for ns in wildcard_suffix_result)
wildcard_single = await store.alist_namespaces(
suffix=("some", "*", "public", test_pref)
)
assert len(wildcard_single) == 1
assert wildcard_single[0] == (
test_pref,
"prod",
"documents",
"some",
"nesting",
"public",
test_pref,
)
# Test max depth
max_depth_result = await store.alist_namespaces(max_depth=3)
assert all(len(ns) <= 3 for ns in max_depth_result)
max_depth_result = await store.alist_namespaces(
max_depth=4, prefix=(test_pref, "*", "documents")
)
assert len(set(res for res in max_depth_result)) == len(max_depth_result) == 5
# Test pagination
limit_result = await store.alist_namespaces(prefix=(test_pref,), limit=3)
assert len(limit_result) == 3
offset_result = await store.alist_namespaces(prefix=(test_pref,), offset=3)
assert len(offset_result) == len(test_namespaces) - 3
empty_prefix_result = await store.alist_namespaces(prefix=(test_pref,))
assert len(empty_prefix_result) == len(test_namespaces)
assert set(empty_prefix_result) == set(test_namespaces)
# Clean up
for namespace in test_namespaces:
await store.adelete(namespace, "dummy")
async def test_search_items(
fake_embeddings: CharacterEmbeddings,
) -> None:
"""Test search_items functionality by calling store methods directly."""
base = "test_search_items"
test_namespaces = [
(base, "documents", "user1"),
(base, "documents", "user2"),
(base, "reports", "department1"),
(base, "reports", "department2"),
]
test_items = [
{"title": "Doc 1", "author": "John Doe", "tags": ["important"]},
{"title": "Doc 2", "author": "Jane Smith", "tags": ["draft"]},
{"title": "Report A", "author": "John Doe", "tags": ["final"]},
{"title": "Report B", "author": "Alice Johnson", "tags": ["draft"]},
]
async with create_vector_store(
fake_embeddings, text_fields=["key0", "key1", "key3"]
) as store:
# Insert test data
for ns, item in zip(test_namespaces, test_items, strict=False):
key = f"item_{ns[-1]}"
await store.aput(ns, key, item)
# 1. Search documents
docs = await store.asearch((base, "documents"))
assert len(docs) == 2
assert all(item.namespace[1] == "documents" for item in docs)
# 2. Search reports
reports = await store.asearch((base, "reports"))
assert len(reports) == 2
assert all(item.namespace[1] == "reports" for item in reports)
# 3. Pagination
first_page = await store.asearch((base,), limit=2, offset=0)
second_page = await store.asearch((base,), limit=2, offset=2)
assert len(first_page) == 2
assert len(second_page) == 2
keys_page1 = {item.key for item in first_page}
keys_page2 = {item.key for item in second_page}
assert keys_page1.isdisjoint(keys_page2)
all_items = await store.asearch((base,))
assert len(all_items) == 4
john_items = await store.asearch((base,), filter={"author": "John Doe"})
assert len(john_items) == 2
assert all(item.value["author"] == "John Doe" for item in john_items)
draft_items = await store.asearch((base,), filter={"tags": ["draft"]})
assert len(draft_items) == 2
assert all("draft" in item.value["tags"] for item in draft_items)
for ns in test_namespaces:
key = f"item_{ns[-1]}"
await store.adelete(ns, key)
@@ -0,0 +1,35 @@
"""Run delta-channel conformance capabilities against AsyncSqliteSaver."""
from __future__ import annotations
import pytest
pytest.importorskip(
"langgraph.checkpoint.conformance",
reason="langgraph-checkpoint-conformance not installed",
)
pytest.importorskip("aiosqlite", reason="aiosqlite not installed")
@pytest.mark.asyncio
async def test_delta_channel_conformance():
from langgraph.checkpoint.conformance import validate
from langgraph.checkpoint.conformance.initializer import checkpointer_test
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
@checkpointer_test(name="AsyncSqliteSaver")
async def sqlite_saver():
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
yield saver
report = await validate(
sqlite_saver,
capabilities={
"delta_channel_history",
},
)
for cap, result in report.results.items():
if result.passed is False:
details = "\n".join(result.failures or [])
pytest.fail(f"Capability {cap} failed:\n{details}")
@@ -0,0 +1,170 @@
"""Sqlite-specific migration smoke tests: BinaryOperatorAggregate -> DeltaChannel.
Mirrors `libs/langgraph/tests/test_delta_channel_migration.py` (which
covers `InMemorySaver` + a third-party fallback to the base default
impl). This file exercises the same migration scenario through the
sqlite-specific `SqliteSaver.get_delta_channel_history` override —
specifically that the streaming ancestor walk finds a pre-migration
plain `channel_values[ch]` entry and surfaces it as the `seed`, with
post-migration writes folding on top through the reducer.
Pre-migration checkpoints under `BinaryOperatorAggregate` carry the
full accumulated value at every settled super-step boundary. The
override has to identify those as "real" seeds (not `_DeltaSnapshot`
sentinels) — the saver layer is intentionally delta-agnostic and just
returns whatever is stored in `channel_values[ch]`.
"""
from __future__ import annotations
import operator
from typing import Annotated, Any
import pytest
from langchain_core.runnables import RunnableConfig
# `langgraph` core isn't a dep of `langgraph-checkpoint-sqlite`. Skip the
# whole module rather than importerror-ing in the standalone CI shape.
pytest.importorskip("langgraph.channels.delta", reason="langgraph core not installed")
pytest.importorskip("langgraph.channels.binop", reason="langgraph core not installed")
pytest.importorskip("langgraph.graph", reason="langgraph core not installed")
from langgraph.channels.binop import BinaryOperatorAggregate # type: ignore[import-untyped] # noqa: E402,I001
from langgraph.channels.delta import DeltaChannel # type: ignore[import-untyped] # noqa: E402
from langgraph.graph import END, START, StateGraph # type: ignore[import-untyped] # noqa: E402
from typing_extensions import TypedDict # noqa: E402
from langgraph.checkpoint.sqlite import SqliteSaver # noqa: E402
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver # noqa: E402
pytestmark = pytest.mark.anyio
def _noop(_state: Any) -> dict:
return {}
def _list_concat(state: list, writes: list) -> list:
result = list(state)
for w in writes:
result.extend(w if isinstance(w, list) else [w])
return result
def _binop_graph(checkpointer: Any) -> Any:
class BinopState(TypedDict):
items: Annotated[list, BinaryOperatorAggregate(list, operator.add)]
return (
StateGraph(BinopState)
.add_node("noop", _noop)
.add_edge(START, "noop")
.add_edge("noop", END)
.compile(checkpointer=checkpointer)
)
def _delta_graph(checkpointer: Any) -> Any:
class DeltaState(TypedDict):
items: Annotated[list, DeltaChannel(_list_concat)]
return (
StateGraph(DeltaState)
.add_node("noop", _noop)
.add_edge(START, "noop")
.add_edge("noop", END)
.compile(checkpointer=checkpointer)
)
def _drive(graph: Any, config: RunnableConfig, tag: str, n: int) -> None:
for i in range(n):
graph.invoke({"items": [f"{tag}{i}"]}, config)
async def _adrive(graph: Any, config: RunnableConfig, tag: str, n: int) -> None:
for i in range(n):
await graph.ainvoke({"items": [f"{tag}{i}"]}, config)
def _settled_boundaries(history: list) -> list[tuple[RunnableConfig, list]]:
"""`(config, items)` for every checkpoint with `next == ('__start__',)`
— the stable inter-invoke boundaries that round-trip predictably.
"""
return [
(s.config, list(s.values.get("items", [])))
for s in history
if s.next == ("__start__",)
]
def test_migration_preserves_pre_migration_state_sync() -> None:
"""Drive 3 invokes under `BinaryOperatorAggregate`, swap the
annotation to `DeltaChannel` on the same sqlite-backed thread, and
verify every settled pre-migration boundary round-trips exactly.
The override's streaming walk must identify the plain accumulated
list at each pre-migration ancestor as a valid `seed` even though
no `_DeltaSnapshot` was ever written there.
"""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "mig-sync"}}
binop = _binop_graph(saver)
_drive(binop, config, "u", 3)
pre_boundaries = _settled_boundaries(list(binop.get_state_history(config)))
assert len(pre_boundaries) >= 2, "expected multiple settled boundaries"
delta = _delta_graph(saver)
for cfg, items in pre_boundaries:
snap = delta.get_state(cfg)
assert list(snap.values.get("items", [])) == items, (
f"snapshot mismatch at {cfg['configurable']['checkpoint_id']}: "
f"expected {items}, got {snap.values.get('items', [])}"
)
def test_migration_continued_thread_folds_deltas_on_seed_sync() -> None:
"""After migration, driving one more super-step extends the
pre-migration accumulated state via the delta reducer — the seed
plus a single new write.
"""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "mig-continue-sync"}}
binop = _binop_graph(saver)
_drive(binop, config, "u", 3)
pre_history = list(binop.get_state_history(config))
pre_boundaries = _settled_boundaries(pre_history)
# Latest settled boundary — the leaf pre-migration state.
leaf_cfg, leaf_items = pre_boundaries[0]
assert leaf_items, "expected non-empty pre-migration leaf"
delta = _delta_graph(saver)
delta.invoke({"items": ["after-migration"]}, leaf_cfg)
new_state = delta.get_state(config).values["items"]
assert new_state[: len(leaf_items)] == leaf_items
assert "after-migration" in new_state
async def test_migration_preserves_pre_migration_state_async() -> None:
"""Async equivalent of the basic-migration round-trip check on
`AsyncSqliteSaver`."""
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "mig-async"}}
binop = _binop_graph(saver)
await _adrive(binop, config, "u", 3)
pre_history = [s async for s in binop.aget_state_history(config)]
pre_boundaries = _settled_boundaries(pre_history)
assert len(pre_boundaries) >= 2
delta = _delta_graph(saver)
for cfg, items in pre_boundaries:
snap = await delta.aget_state(cfg)
assert list(snap.values.get("items", [])) == items, (
f"async snapshot mismatch at {cfg['configurable']['checkpoint_id']}"
)
@@ -0,0 +1,271 @@
"""Smoke tests for `BaseCheckpointSaver.get_delta_channel_history` on sqlite.
`SqliteSaver` (and `AsyncSqliteSaver`) deliberately don't override the
default implementation in `BaseCheckpointSaver` — these tests pin the
default impl to behave correctly end-to-end against a real persistent
saver and a real `DeltaChannel`-backed graph.
Scenarios covered:
* Empty `channels` argument returns an empty mapping (no I/O).
* On a non-trivial multi-checkpoint thread, per-channel writes come back
oldest→newest.
* When the walk reaches the root without ever finding a stored value,
`seed` is omitted from the entry (consumer treats absence as "start
empty").
* When a `_DeltaSnapshot` blob is present at an ancestor, it is returned
as the `seed`.
* The async saver returns the same shape via `aget_delta_channel_history`.
"""
from __future__ import annotations
import operator
from typing import Annotated, Any
import pytest
from langchain_core.runnables import RunnableConfig
# `langgraph` is not a dep of `langgraph-checkpoint-sqlite`. When tests run
# in the sqlite lib's standalone CI environment without it installed, skip
# the whole module rather than failing at import.
pytest.importorskip("langgraph.channels.delta", reason="langgraph core not installed")
pytest.importorskip("langgraph.graph", reason="langgraph core not installed")
from langgraph.channels.delta import DeltaChannel # type: ignore[import-untyped] # noqa: E402,I001
from langgraph.checkpoint.serde.types import _DeltaSnapshot # noqa: E402
from langgraph.graph import END, START, StateGraph # type: ignore[import-untyped] # noqa: E402
from typing_extensions import TypedDict # noqa: E402
from langgraph.checkpoint.sqlite import SqliteSaver # noqa: E402
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver # noqa: E402
pytestmark = pytest.mark.anyio
# ---------------------------------------------------------------------------
# Graph helpers
# ---------------------------------------------------------------------------
def _noop(_state: Any) -> dict[str, Any]:
return {}
class _DeltaState(TypedDict):
items: Annotated[list, DeltaChannel(operator.add)]
def _delta_graph(checkpointer: Any) -> Any:
return (
StateGraph(_DeltaState)
.add_node("noop", _noop)
.add_edge(START, "noop")
.add_edge("noop", END)
.compile(checkpointer=checkpointer)
)
def _drive(graph: Any, config: RunnableConfig, n: int) -> None:
for i in range(n):
graph.invoke({"items": [f"v{i}"]}, config)
async def _adrive(graph: Any, config: RunnableConfig, n: int) -> None:
for i in range(n):
await graph.ainvoke({"items": [f"v{i}"]}, config)
def _pick_non_root(saver: Any, config: RunnableConfig) -> RunnableConfig:
"""Return a config pointing at a checkpoint that has at least one ancestor.
`get_delta_channel_history` walks the parent chain — calling it on the root
checkpoint produces `writes=[]` and no `seed`, which is uninteresting
for the multi-step assertions below.
"""
history = list(saver.list(config))
assert history, "expected non-empty history"
# `list` yields newest→oldest; the second entry has the first entry
# as its parent, so its parent_config is non-None.
for tup in history:
if tup.parent_config is not None:
return tup.config
raise AssertionError("no checkpoint with a parent in history")
async def _apick_non_root(saver: Any, config: RunnableConfig) -> RunnableConfig:
history = [tup async for tup in saver.alist(config)]
assert history, "expected non-empty history"
for tup in history:
if tup.parent_config is not None:
return tup.config
raise AssertionError("no checkpoint with a parent in history")
# ---------------------------------------------------------------------------
# Sync: SqliteSaver
# ---------------------------------------------------------------------------
def test_empty_channels_returns_empty_mapping_sync() -> None:
"""Empty `channels` short-circuits to `{}` without touching storage."""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "empty"}}
assert saver.get_delta_channel_history(config=config, channels=[]) == {}
def test_writes_history_oldest_to_newest_sync() -> None:
"""Per-channel writes accumulated across the walk come back oldest→newest."""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "history-sync"}}
graph = _delta_graph(saver)
_drive(graph, config, 3)
target_cfg = _pick_non_root(saver, config)
result = saver.get_delta_channel_history(config=target_cfg, channels=["items"])
assert "items" in result
entry = result["items"]
assert isinstance(entry["writes"], list)
# If any writes were collected, their values should be in oldest→newest
# order — i.e. tagged 'v0', 'v1', ... matching invoke order.
write_values: list[Any] = []
for _task_id, channel, value in entry["writes"]:
assert channel == "items"
write_values.extend(value if isinstance(value, list) else [value])
# `_drive` invokes with payloads ['v0'], ['v1'], ['v2']. Whatever
# subset shows up in the chain must be a contiguous prefix in order.
for idx, val in enumerate(write_values):
assert val == f"v{idx}", (
f"writes not in oldest→newest order: {write_values}"
)
def test_seed_present_when_snapshot_in_ancestor_sync() -> None:
"""Inserting a `_DeltaSnapshot` blob at an ancestor → walk returns it as `seed`."""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "seed-sync"}}
graph = _delta_graph(saver)
_drive(graph, config, 2)
# Find the oldest non-root checkpoint, then walk to its parent and
# rewrite that parent's `channel_values["items"]` to a real
# `_DeltaSnapshot`. After this surgery, calling `get_delta_channel_history`
# at the leaf must return the snapshot value as `seed`.
history = list(saver.list(config))
assert len(history) >= 2
leaf_tup = history[0]
# Walk to an ancestor with a parent_config (any non-root will do).
ancestor_tup = next(
(tup for tup in history if tup.parent_config is not None), None
)
assert ancestor_tup is not None
parent_cfg = ancestor_tup.parent_config
assert parent_cfg is not None
parent_tup = saver.get_tuple(parent_cfg)
assert parent_tup is not None
snapshot_value = ["seeded", "items"]
parent_tup.checkpoint["channel_values"]["items"] = _DeltaSnapshot(
snapshot_value
)
# Make sure the channel has a version so the optimized blob lookup
# in any future override has something to hit.
parent_tup.checkpoint["channel_versions"].setdefault("items", 1)
saver.put(
parent_tup.parent_config or {"configurable": parent_cfg["configurable"]},
parent_tup.checkpoint,
parent_tup.metadata,
{},
)
result = saver.get_delta_channel_history(
config=leaf_tup.config, channels=["items"]
)
entry = result["items"]
assert "seed" in entry, f"expected seed to be present, got {entry}"
seed = entry["seed"]
assert isinstance(seed, _DeltaSnapshot), (
f"expected _DeltaSnapshot, got {seed!r}"
)
assert seed.value == snapshot_value
def test_seed_omitted_when_walk_reaches_root_sync() -> None:
"""`get_delta_channel_history` on the root checkpoint → no `seed` key, no writes."""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "root-sync"}}
graph = _delta_graph(saver)
_drive(graph, config, 1)
history = list(saver.list(config))
# Root is the oldest checkpoint (no parent_config).
root_tup = history[-1]
assert root_tup.parent_config is None
result = saver.get_delta_channel_history(
config=root_tup.config, channels=["items"]
)
entry = result["items"]
assert "seed" not in entry, f"root-walk should have no seed, got {entry}"
assert entry["writes"] == []
# ---------------------------------------------------------------------------
# Async: AsyncSqliteSaver
# ---------------------------------------------------------------------------
async def test_empty_channels_returns_empty_mapping_async() -> None:
"""Async equivalent of the empty-channels short-circuit."""
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "empty-async"}}
assert await saver.aget_delta_channel_history(config=config, channels=[]) == {}
async def test_writes_history_oldest_to_newest_async() -> None:
"""Async equivalent of the oldest→newest ordering check."""
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "history-async"}}
graph = _delta_graph(saver)
await _adrive(graph, config, 3)
target_cfg = await _apick_non_root(saver, config)
result = await saver.aget_delta_channel_history(
config=target_cfg, channels=["items"]
)
assert "items" in result
entry = result["items"]
assert isinstance(entry["writes"], list)
write_values: list[Any] = []
for _task_id, channel, value in entry["writes"]:
assert channel == "items"
write_values.extend(value if isinstance(value, list) else [value])
for idx, val in enumerate(write_values):
assert val == f"v{idx}", (
f"writes not in oldest→newest order: {write_values}"
)
async def test_seed_omitted_when_walk_reaches_root_async() -> None:
"""Async equivalent of the root-walk seed-absence check."""
async with AsyncSqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {"configurable": {"thread_id": "root-async"}}
graph = _delta_graph(saver)
await _adrive(graph, config, 1)
history = [tup async for tup in saver.alist(config)]
root_tup = history[-1]
assert root_tup.parent_config is None
result = await saver.aget_delta_channel_history(
config=root_tup.config, channels=["items"]
)
entry = result["items"]
assert "seed" not in entry, f"root-walk should have no seed, got {entry}"
assert entry["writes"] == []
+309
View File
@@ -0,0 +1,309 @@
from typing import Any, cast
import pytest
from langchain_core.runnables import RunnableConfig
from langgraph.checkpoint.base import (
Checkpoint,
CheckpointMetadata,
create_checkpoint,
empty_checkpoint,
)
from langgraph.checkpoint.sqlite import SqliteSaver
from langgraph.checkpoint.sqlite.utils import _metadata_predicate, search_where
class TestSqliteSaver:
@pytest.fixture(autouse=True)
def setup(self) -> None:
# objects for test setup
self.config_1: RunnableConfig = {
"configurable": {
"thread_id": "thread-1",
# for backwards compatibility testing
"checkpoint_id": "1",
"checkpoint_ns": "",
}
}
self.config_2: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2",
"checkpoint_ns": "",
}
}
self.config_3: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_id": "2-inner",
"checkpoint_ns": "inner",
}
}
self.chkpnt_1: Checkpoint = empty_checkpoint()
self.chkpnt_2: Checkpoint = create_checkpoint(self.chkpnt_1, {}, 1)
self.chkpnt_3: Checkpoint = empty_checkpoint()
self.metadata_1: CheckpointMetadata = {
"source": "input",
"step": 2,
"writes": {},
"score": 1,
}
self.metadata_2: CheckpointMetadata = {
"source": "loop",
"step": 1,
"writes": {"foo": "bar"},
"score": None,
}
self.metadata_3: CheckpointMetadata = {}
def test_combined_metadata(self) -> None:
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {
"configurable": {
"thread_id": "thread-2",
"checkpoint_ns": "",
"__super_private_key": "super_private_value",
},
"metadata": {"run_id": "my_run_id"},
}
saver.put(config, self.chkpnt_2, self.metadata_2, {})
checkpoint = saver.get_tuple(config)
assert checkpoint is not None and checkpoint.metadata == {
**self.metadata_2,
"run_id": "my_run_id",
}
def test_search(self) -> None:
with SqliteSaver.from_conn_string(":memory:") as saver:
# set up test
# save checkpoints
saver.put(self.config_1, self.chkpnt_1, self.metadata_1, {})
saver.put(self.config_2, self.chkpnt_2, self.metadata_2, {})
saver.put(self.config_3, self.chkpnt_3, self.metadata_3, {})
# call method / assertions
query_1 = {"source": "input"} # search by 1 key
query_2 = {
"step": 1,
"writes": {"foo": "bar"},
} # search by multiple keys
query_3: dict[str, Any] = {} # search by no keys, return all checkpoints
query_4 = {"source": "update", "step": 1} # no match
search_results_1 = list(saver.list(None, filter=query_1))
assert len(search_results_1) == 1
assert search_results_1[0].metadata == self.metadata_1
search_results_2 = list(saver.list(None, filter=query_2))
assert len(search_results_2) == 1
assert search_results_2[0].metadata == self.metadata_2
search_results_3 = list(saver.list(None, filter=query_3))
assert len(search_results_3) == 3
search_results_4 = list(saver.list(None, filter=query_4))
assert len(search_results_4) == 0
# search by config (defaults to checkpoints across all namespaces)
search_results_5 = list(
saver.list({"configurable": {"thread_id": "thread-2"}})
)
assert len(search_results_5) == 2
assert {
search_results_5[0].config["configurable"]["checkpoint_ns"],
search_results_5[1].config["configurable"]["checkpoint_ns"],
} == {"", "inner"}
# search with before param
search_results_6 = list(saver.list(None, before=search_results_5[1].config))
assert len(search_results_6) == 1
assert search_results_6[0].config["configurable"]["thread_id"] == "thread-1"
# search with limit param
search_results_7 = list(
saver.list({"configurable": {"thread_id": "thread-2"}}, limit=1)
)
assert len(search_results_7) == 1
assert search_results_7[0].config["configurable"]["thread_id"] == "thread-2"
def test_search_where(self) -> None:
# call method / assertions
expected_predicate_1 = "WHERE json_extract(CAST(metadata AS TEXT), '$.source') = ? AND json_extract(CAST(metadata AS TEXT), '$.step') = ? AND json_extract(CAST(metadata AS TEXT), '$.writes') = ? AND json_extract(CAST(metadata AS TEXT), '$.score') = ? AND checkpoint_id < ?"
expected_param_values_1 = ["input", 2, "{}", 1, "1"]
assert search_where(
None, cast(dict[str, Any], self.metadata_1), self.config_1
) == (
expected_predicate_1,
expected_param_values_1,
)
def test_metadata_predicate(self) -> None:
# call method / assertions
expected_predicate_1 = [
"json_extract(CAST(metadata AS TEXT), '$.source') = ?",
"json_extract(CAST(metadata AS TEXT), '$.step') = ?",
"json_extract(CAST(metadata AS TEXT), '$.writes') = ?",
"json_extract(CAST(metadata AS TEXT), '$.score') = ?",
]
expected_predicate_2 = [
"json_extract(CAST(metadata AS TEXT), '$.source') = ?",
"json_extract(CAST(metadata AS TEXT), '$.step') = ?",
"json_extract(CAST(metadata AS TEXT), '$.writes') = ?",
"json_extract(CAST(metadata AS TEXT), '$.score') IS ?",
]
expected_predicate_3: list[str] = []
expected_param_values_1 = ["input", 2, "{}", 1]
expected_param_values_2 = ["loop", 1, '{"foo":"bar"}', None]
expected_param_values_3: list[Any] = []
assert _metadata_predicate(cast(dict[str, Any], self.metadata_1)) == (
expected_predicate_1,
expected_param_values_1,
)
assert _metadata_predicate(cast(dict[str, Any], self.metadata_2)) == (
expected_predicate_2,
expected_param_values_2,
)
assert _metadata_predicate(cast(dict[str, Any], self.metadata_3)) == (
expected_predicate_3,
expected_param_values_3,
)
async def test_informative_async_errors(self) -> None:
with SqliteSaver.from_conn_string(":memory:") as saver:
# call method / assertions
with pytest.raises(NotImplementedError, match="AsyncSqliteSaver"):
await saver.aget(self.config_1)
with pytest.raises(NotImplementedError, match="AsyncSqliteSaver"):
await saver.aget_tuple(self.config_1)
with pytest.raises(NotImplementedError, match="AsyncSqliteSaver"):
async for _ in saver.alist(self.config_1):
pass
def test_metadata_predicate_sql_injection_prevention(self) -> None:
"""Test that _metadata_predicate rejects malicious filter keys."""
# Test various SQL injection payloads
malicious_keys = [
"x') OR '1'='1", # Boolean-based injection
"x') OR 1=1 --", # Comment-based injection
"x') UNION SELECT 1,2,3,4,5,6,7 --", # UNION-based injection
"access') = 'public' OR '1'='1' OR json_extract(value, '$.", # Complex injection
"'; DROP TABLE checkpoints; --", # Destructive injection
]
for malicious_key in malicious_keys:
with pytest.raises(ValueError, match="Invalid filter key"):
_metadata_predicate({malicious_key: "dummy"})
def test_checkpoint_search_sql_injection_prevention(self) -> None:
"""Test that SQL injection via malicious filter keys is prevented in checkpoint search."""
with SqliteSaver.from_conn_string(":memory:") as saver:
# Setup: Create checkpoints with different metadata
config_public: RunnableConfig = {
"configurable": {
"thread_id": "thread-public",
"checkpoint_ns": "",
}
}
config_private: RunnableConfig = {
"configurable": {
"thread_id": "thread-private",
"checkpoint_ns": "",
}
}
checkpoint_public = empty_checkpoint()
checkpoint_private = empty_checkpoint()
metadata_public: CheckpointMetadata = {
"access": "public",
"data": "public information",
}
metadata_private: CheckpointMetadata = {
"access": "private",
"data": "secret information",
"password": "secret123",
}
saver.put(config_public, checkpoint_public, metadata_public, {})
saver.put(config_private, checkpoint_private, metadata_private, {})
# Normal query - should return only public checkpoint
normal_results = list(saver.list(None, filter={"access": "public"}))
assert len(normal_results) == 1
assert normal_results[0].metadata["access"] == "public"
# SQL injection attempt should raise ValueError
malicious_key = (
"access') = 'public' OR '1'='1' OR json_extract(metadata, '$."
)
with pytest.raises(ValueError, match="Invalid filter key"):
list(saver.list(None, filter={malicious_key: "dummy"}))
def test_limit_parameter_sql_injection_prevention(self) -> None:
"""Test that the limit parameter properly uses parameterized queries to prevent SQL injection."""
with SqliteSaver.from_conn_string(":memory:") as saver:
# Setup: Create multiple checkpoints
for i in range(5):
config: RunnableConfig = {
"configurable": {
"thread_id": f"thread-{i}",
"checkpoint_ns": "",
}
}
checkpoint = empty_checkpoint()
metadata: CheckpointMetadata = {"index": i}
saver.put(config, checkpoint, metadata, {})
# Test that limit works correctly with valid integer
results = list(saver.list(None, limit=2))
assert len(results) == 2
# Test that limit=0 returns no results
results = list(saver.list(None, limit=0))
assert len(results) == 0
# Test that limit=None returns all results
results = list(saver.list(None, limit=None))
assert len(results) == 5
def test_metadata_filter_keys_with_hyphens_and_digits(self) -> None:
"""Metadata keys with hyphens and digit-start should be filterable.
This exposes incorrect JSON path handling (unquoted segments) by asserting
that such filters successfully match saved checkpoints.
"""
with SqliteSaver.from_conn_string(":memory:") as saver:
config: RunnableConfig = {
"configurable": {
"thread_id": "thread-hyphen-digit",
"checkpoint_ns": "",
}
}
checkpoint = empty_checkpoint()
metadata: CheckpointMetadata = {
"access-level": "public",
"user": {"access-level": "nested", "123abc": "ok2"},
"123abc": "ok",
}
saver.put(config, checkpoint, metadata, {})
# Top-level hyphenated key
results = list(saver.list(None, filter={"access-level": "public"}))
assert len(results) == 1
# Nested hyphenated key via dotted path
results = list(saver.list(None, filter={"user.access-level": "nested"}))
assert len(results) == 1
# Top-level digit-starting key
results = list(saver.list(None, filter={"123abc": "ok"}))
assert len(results) == 1
# Nested digit-starting key via dotted path
results = list(saver.list(None, filter={"user.123abc": "ok2"}))
assert len(results) == 1
File diff suppressed because it is too large Load Diff
+429
View File
@@ -0,0 +1,429 @@
"""Test SQLite store Time-To-Live (TTL) functionality."""
import asyncio
import os
import tempfile
import time
from collections.abc import Generator
import pytest
from langgraph.store.base import TTLConfig
from langgraph.store.sqlite import SqliteStore
from langgraph.store.sqlite.aio import AsyncSqliteStore
@pytest.fixture
def temp_db_file() -> Generator[str, None, None]:
"""Create a temporary database file for testing."""
fd, path = tempfile.mkstemp()
os.close(fd)
yield path
os.unlink(path)
def test_ttl_basic(temp_db_file: str) -> None:
"""Test basic TTL functionality with synchronous API."""
ttl_seconds = 1
ttl_minutes = ttl_seconds / 60
with SqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes}
) as store:
store.setup()
store.put(("test",), "item1", {"value": "test"})
item = store.get(("test",), "item1")
assert item is not None
assert item.value["value"] == "test"
time.sleep(ttl_seconds + 1.0)
store.sweep_ttl()
item = store.get(("test",), "item1")
assert item is None
@pytest.mark.flaky(retries=3)
def test_ttl_refresh(temp_db_file: str) -> None:
"""Test TTL refresh on read."""
ttl_seconds = 1
ttl_minutes = ttl_seconds / 60
with SqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes, "refresh_on_read": True}
) as store:
store.setup()
# Store an item with TTL
store.put(("test",), "item1", {"value": "test"})
# Sleep almost to expiration
time.sleep(ttl_seconds - 0.5)
swept = store.sweep_ttl()
assert swept == 0
# Get the item and refresh TTL
item = store.get(("test",), "item1", refresh_ttl=True)
assert item is not None
time.sleep(ttl_seconds - 0.5)
swept = store.sweep_ttl()
assert swept == 0
# Get the item, should still be there
item = store.get(("test",), "item1")
assert item is not None
assert item.value["value"] == "test"
# Sleep again but don't refresh this time
time.sleep(ttl_seconds + 0.75)
swept = store.sweep_ttl()
assert swept == 1
# Item should be gone now
item = store.get(("test",), "item1")
assert item is None
def test_ttl_sweeper(temp_db_file: str) -> None:
"""Test TTL sweeper thread."""
ttl_seconds = 2
ttl_minutes = ttl_seconds / 60
ttl_config: TTLConfig = {
"default_ttl": ttl_minutes,
"sweep_interval_minutes": ttl_minutes / 2,
}
with SqliteStore.from_conn_string(
temp_db_file,
ttl=ttl_config,
) as store:
store.setup()
# Start the TTL sweeper
store.start_ttl_sweeper()
# Store an item with TTL
store.put(("test",), "item1", {"value": "test"})
# Item should be there initially
item = store.get(("test",), "item1")
assert item is not None
# Wait for TTL to expire and the sweeper to run
time.sleep(ttl_seconds + (ttl_seconds / 2) + 0.5)
# Item should be gone now (swept automatically)
item = store.get(("test",), "item1")
assert item is None
# Stop the sweeper
store.stop_ttl_sweeper()
@pytest.mark.flaky(retries=3)
def test_ttl_custom_value(temp_db_file: str) -> None:
"""Test TTL with custom value per item."""
with SqliteStore.from_conn_string(temp_db_file) as store:
store.setup()
# Store items with different TTLs
store.put(("test",), "item1", {"value": "short"}, ttl=1 / 60) # 1 second
store.put(("test",), "item2", {"value": "long"}, ttl=3 / 60) # 3 seconds
# Item with short TTL
time.sleep(2) # Wait for short TTL
store.sweep_ttl()
# Short TTL item should be gone, long TTL item should remain
item1 = store.get(("test",), "item1")
item2 = store.get(("test",), "item2")
assert item1 is None
assert item2 is not None
# Wait for the second item's TTL
time.sleep(4)
store.sweep_ttl()
# Now both should be gone
item2 = store.get(("test",), "item2")
assert item2 is None
@pytest.mark.flaky(retries=3)
def test_ttl_override_default(temp_db_file: str) -> None:
"""Test overriding default TTL at the item level."""
with SqliteStore.from_conn_string(
temp_db_file,
ttl={"default_ttl": 5 / 60}, # 5 seconds default
) as store:
store.setup()
# Store an item with shorter than default TTL
store.put(("test",), "item1", {"value": "override"}, ttl=1 / 60) # 1 second
# Store an item with default TTL
store.put(("test",), "item2", {"value": "default"}) # Uses default 5 seconds
# Store an item with no TTL
store.put(("test",), "item3", {"value": "permanent"}, ttl=None)
# Wait for the override TTL to expire
time.sleep(2)
store.sweep_ttl()
# Check results
item1 = store.get(("test",), "item1")
item2 = store.get(("test",), "item2")
item3 = store.get(("test",), "item3")
assert item1 is None # Should be expired
assert item2 is not None # Default TTL, should still be there
assert item3 is not None # No TTL, should still be there
# Wait for default TTL to expire
time.sleep(4)
store.sweep_ttl()
# Check results again
item2 = store.get(("test",), "item2")
item3 = store.get(("test",), "item3")
assert item2 is None # Default TTL item should be gone
assert item3 is not None # No TTL item should still be there
@pytest.mark.flaky(retries=3)
def test_search_with_ttl(temp_db_file: str) -> None:
"""Test TTL with search operations."""
ttl_seconds = 1
ttl_minutes = ttl_seconds / 60
with SqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes}
) as store:
store.setup()
# Store items
store.put(("test",), "item1", {"value": "apple"})
store.put(("test",), "item2", {"value": "banana"})
# Search before expiration
results = store.search(("test",), filter={"value": "apple"})
assert len(results) == 1
assert results[0].key == "item1"
# Wait for TTL to expire
time.sleep(ttl_seconds + 1)
store.sweep_ttl()
# Search after expiration
results = store.search(("test",), filter={"value": "apple"})
assert len(results) == 0
@pytest.mark.asyncio
async def test_async_ttl_basic(temp_db_file: str) -> None:
"""Test basic TTL functionality with asynchronous API."""
ttl_seconds = 1
ttl_minutes = ttl_seconds / 60
async with AsyncSqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes}
) as store:
await store.setup()
# Store an item with TTL
await store.aput(("test",), "item1", {"value": "test"})
# Get the item before expiration
item = await store.aget(("test",), "item1")
assert item is not None
assert item.value["value"] == "test"
# Wait for TTL to expire
await asyncio.sleep(ttl_seconds + 1.0)
# Manual sweep needed without the sweeper thread
await store.sweep_ttl()
# Item should be gone now
item = await store.aget(("test",), "item1")
assert item is None
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3)
async def test_async_ttl_refresh(temp_db_file: str) -> None:
"""Test TTL refresh on read with async API."""
ttl_seconds = 1
ttl_minutes = ttl_seconds / 60
async with AsyncSqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes, "refresh_on_read": True}
) as store:
await store.setup()
# Store an item with TTL
await store.aput(("test",), "item1", {"value": "test"})
# Sleep almost to expiration
await asyncio.sleep(ttl_seconds - 0.5)
# Get the item and refresh TTL
item = await store.aget(("test",), "item1", refresh_ttl=True)
assert item is not None
# Sleep again - without refresh, would have expired by now
await asyncio.sleep(ttl_seconds - 0.5)
# Get the item, should still be there
item = await store.aget(("test",), "item1")
assert item is not None
assert item.value["value"] == "test"
# Sleep again but don't refresh this time
await asyncio.sleep(ttl_seconds + 1.0)
# Manual sweep
await store.sweep_ttl()
# Item should be gone now
item = await store.aget(("test",), "item1")
assert item is None
@pytest.mark.asyncio
async def test_async_ttl_sweeper(temp_db_file: str) -> None:
"""Test TTL sweeper thread with async API."""
ttl_seconds = 2
ttl_minutes = ttl_seconds / 60
ttl_config: TTLConfig = {
"default_ttl": ttl_minutes,
"sweep_interval_minutes": ttl_minutes / 2,
}
async with AsyncSqliteStore.from_conn_string(
temp_db_file,
ttl=ttl_config,
) as store:
await store.setup()
# Start the TTL sweeper
await store.start_ttl_sweeper()
# Store an item with TTL
await store.aput(("test",), "item1", {"value": "test"})
# Item should be there initially
item = await store.aget(("test",), "item1")
assert item is not None
# Wait for TTL to expire and the sweeper to run
await asyncio.sleep(ttl_seconds + (ttl_seconds / 2) + 0.5)
# Item should be gone now (swept automatically)
item = await store.aget(("test",), "item1")
assert item is None
# Stop the sweeper
await store.stop_ttl_sweeper()
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3)
async def test_async_search_with_ttl(temp_db_file: str) -> None:
"""Test TTL with search operations using async API."""
ttl_seconds = 1
ttl_minutes = ttl_seconds / 60
async with AsyncSqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes}
) as store:
await store.setup()
# Store items
await store.aput(("test",), "item1", {"value": "apple"})
await store.aput(("test",), "item2", {"value": "banana"})
# Search before expiration
results = await store.asearch(("test",), filter={"value": "apple"})
assert len(results) == 1
assert results[0].key == "item1"
# Wait for TTL to expire
await asyncio.sleep(ttl_seconds + 1)
await store.sweep_ttl()
# Search after expiration
results = await store.asearch(("test",), filter={"value": "apple"})
assert len(results) == 0
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3)
async def test_async_asearch_refresh_ttl(temp_db_file: str) -> None:
"""Test TTL refresh on asearch with async API."""
ttl_seconds = 4.0 # Increased TTL for less sensitivity to timing
ttl_minutes = ttl_seconds / 60.0
async with AsyncSqliteStore.from_conn_string(
temp_db_file, ttl={"default_ttl": ttl_minutes, "refresh_on_read": True}
) as store:
await store.setup()
namespace = ("docs", "user1")
# t=0: items put, expire at t=4.0s
await store.aput(namespace, "item1", {"text": "content1", "id": 1})
await store.aput(namespace, "item2", {"text": "content2", "id": 2})
# t=3.0s: (after sleep ttl_seconds * 0.75 = 3s)
await asyncio.sleep(ttl_seconds * 0.75)
# Perform asearch with refresh_ttl=True for item1.
# item1's TTL should be refreshed. New expiry: t=3.0s + 4.0s = t=7.0s.
# item2's TTL is not affected. Expires at t=4.0s.
searched_items = await store.asearch(
namespace, filter={"id": 1}, refresh_ttl=True
)
assert len(searched_items) == 1
assert searched_items[0].key == "item1"
# t=5.0s: (after sleep ttl_seconds * 0.5 = 2s more. Total elapsed: 3s + 2s = 5s)
await asyncio.sleep(ttl_seconds * 0.5)
# At this point:
# - item1 (refreshed by asearch) should expire at t=7.0s. Should be ALIVE.
# - item2 (original TTL) should have expired at t=4.0s. Should be GONE after sweep.
await store.sweep_ttl()
# Check item1 (should exist due to asearch refresh)
item1_check1 = await store.aget(namespace, "item1", refresh_ttl=False)
assert item1_check1 is not None, (
"Item1 should exist after asearch refresh and first sweep"
)
assert item1_check1.value["text"] == "content1"
# Check item2 (should be gone)
item2_check1 = await store.aget(namespace, "item2", refresh_ttl=False)
assert item2_check1 is None, (
"Item2 should be gone after its original TTL expired"
)
# t=7.5s: (after sleep ttl_seconds * 0.625 = 2.5s more. Total elapsed: 5s + 2.5s = 7.5s)
await asyncio.sleep(ttl_seconds * 0.625)
# At this point:
# - item1 (refreshed by asearch, expired at t=7.0s) should be GONE after sweep.
await store.sweep_ttl()
# Check item1 again (should be gone now)
item1_final_check = await store.aget(namespace, "item1", refresh_ttl=False)
assert item1_final_check is None, (
"Item1 should be gone after its refreshed TTL expired"
)