## Summary Replaces the single-roundtrip `UNION ALL` DeltaChannel read with a two-stage query that avoids fetching unused snapshot blobs, then removes the old combined path entirely. ### Problem `_get_channel_writes_history` used a single `UNION ALL` query that fetched **all** checkpoint metadata, writes, and blobs for a `(thread_id, channel)` in one shot. With `snapshot_frequency=N`, this pulled back O(N/freq) full-size snapshot blobs even though only the nearest one is needed to seed reconstruction. At 500 turns with `snapshot_frequency=10`, this meant fetching ~100 complete message-history snapshots per read. ### Solution Two-stage read: - **Stage 1** — lightweight scan of `checkpoints` only (no blob bytes): walks the parent chain from the target checkpoint and stops at the first ancestor with a snapshot, returning `chain_cids` and `seed_version` - **Stage 2** — targeted fetch: only the writes for `chain_cids` and the single seed blob at `seed_version` The two-stage path is now unconditional — the old combined query and `LG_DELTA_TWO_STAGE_QUERY` env-var gate have been removed. ### Sentinel cleanup `DELTA_SENTINEL` is now a pure in-memory signal and is never written to storage: - Postgres `put()` already stripped it from `channel_values` before writing blobs - Memory saver `put()` now stores `"empty"` instead of serializing the sentinel - `EXT_DELTA_SENTINEL` (msgpack ext code 8) removed from `JsonPlusSerializer` - `DELTA_SENTINEL` is kept as an in-memory marker: `DeltaChannel.checkpoint()` returns it so savers know to skip it, and `_ChannelWritesHistory.seed` uses it to mean "no snapshot found, start from empty" ## Performance Benchmarked at `snapshot_frequency=10` on Postgres (`~100 tok/msg`): | turns | old combined query | two-stage | |------:|-------------------:|----------:| | 50 | 6.0ms | 2.8ms (2.1x faster) | | 100 | 10.1ms | 5.6ms (1.8x faster) | | 500 | **216.1ms** | 15.3ms (**14x faster**) | The old query's read time grew super-linearly with turn count because each read fetched O(N/freq) full snapshot blobs. Two-stage keeps read depth bounded by `snapshot_frequency` regardless of thread length. ## Test plan - `make test` in `libs/checkpoint`, `libs/checkpoint-postgres`, `libs/langgraph` - Removed `test_delta_sentinel_serde_round_trip` (sentinel no longer serializable) - Updated `test_memory.py` — delta channel blobs stored as `"empty"`, not serialized sentinel - Updated `test_channels.py` — `channel_values` no longer contains sentinel key for DeltaChannels - Deleted `test_delta_channel_two_stage_benchmark.py` (one-stage vs two-stage comparison; path no longer exists) --------- Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
LangGraph Checkpoint Postgres
Implementation of LangGraph CheckpointSaver that uses Postgres.
Dependencies
By default langgraph-checkpoint-postgres installs psycopg (Psycopg 3) without any extras. However, you can choose a specific installation that best suits your needs here (for example, psycopg[binary]).
Security
Important
Set
LANGGRAPH_STRICT_MSGPACK=trueor pass an explicitallowed_msgpack_moduleslist when creating your checkpointer. This restricts checkpoint deserialization to known-safe types, preventing code execution if the database is compromised. See the langgraph-checkpoint README for details.
Usage
Important
When using Postgres checkpointers for the first time, make sure to call
.setup()method on them to create required tables. See example below.
Important
When manually creating Postgres connections and passing them to
PostgresSaverorAsyncPostgresSaver, make sure to includeautocommit=Trueandrow_factory=dict_row(from psycopg.rows import dict_row). See a full example in this how-to guide.Why these parameters are required:
autocommit=True: Required for the.setup()method to properly commit the checkpoint tables to the database. Without this, table creation may not be persisted.row_factory=dict_row: Required because the PostgresSaver implementation accesses database rows using dictionary-style syntax (e.g.,row["column_name"]). The defaulttuple_rowfactory returns tuples that only support index-based access (e.g.,row[0]), which will causeTypeErrorexceptions when the checkpointer tries to access columns by name.Example of incorrect usage:
# ❌ This will fail with TypeError during checkpointer operations with psycopg.connect(DB_URI) as conn: # Missing autocommit=True and row_factory=dict_row checkpointer = PostgresSaver(conn) checkpointer.setup() # May not persist tables properly # Any operation that reads from database will fail with: # TypeError: tuple indices must be integers or slices, not str
from langgraph.checkpoint.postgres import PostgresSaver
write_config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
read_config = {"configurable": {"thread_id": "1"}}
DB_URI = "postgres://postgres:postgres@localhost:5432/postgres?sslmode=disable"
with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
# call .setup() the first time you're using the checkpointer
checkpointer.setup()
checkpoint = {
"v": 4,
"ts": "2024-07-31T20:14:19.804150+00:00",
"id": "1ef4f797-8335-6428-8001-8a1503f9b875",
"channel_values": {
"my_key": "meow",
"node": "node"
},
"channel_versions": {
"__start__": 2,
"my_key": 3,
"start:node": 3,
"node": 3
},
"versions_seen": {
"__input__": {},
"__start__": {
"__start__": 1
},
"node": {
"start:node": 2
}
},
}
# store checkpoint
checkpointer.put(write_config, checkpoint, {}, {})
# load checkpoint
checkpointer.get(read_config)
# list checkpoints
list(checkpointer.list(read_config))
Async
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
async with AsyncPostgresSaver.from_conn_string(DB_URI) as checkpointer:
checkpoint = {
"v": 4,
"ts": "2024-07-31T20:14:19.804150+00:00",
"id": "1ef4f797-8335-6428-8001-8a1503f9b875",
"channel_values": {
"my_key": "meow",
"node": "node"
},
"channel_versions": {
"__start__": 2,
"my_key": 3,
"start:node": 3,
"node": 3
},
"versions_seen": {
"__input__": {},
"__start__": {
"__start__": 1
},
"node": {
"start:node": 2
}
},
}
# store checkpoint
await checkpointer.aput(write_config, checkpoint, {}, {})
# load checkpoint
await checkpointer.aget(read_config)
# list checkpoints
[c async for c in checkpointer.alist(read_config)]