Files
langgraph/libs/checkpoint-postgres
5c18bde0f8 feat(langgraph): DeltaChannel: store sentinel in blobs, reconstruct from checkpoint_writes (#7586)
# DeltaChannel: sentinel-based checkpoint blobs + write-replay
reconstruction

## Summary

`DeltaChannel` is a new fold-reducer channel that stores only a
zero-byte sentinel in checkpoint blobs instead of the full accumulated
value. On restore, the runtime replays ancestor writes through the
reducer to reconstruct state. For long-running threads with large
accumulating state (e.g. message histories), this delivers dramatically
smaller checkpoint blobs with configurable read-depth bounds.

```python
from typing import Annotated
from typing_extensions import TypedDict
from langgraph.channels.delta import DeltaChannel
from langgraph.graph.message import _messages_delta_reducer

class State(TypedDict):
    # blob per step: ~60 bytes (sentinel) instead of growing full list
    messages: Annotated[list, DeltaChannel(_messages_delta_reducer)]
    # bound read depth to 10 steps via periodic snapshots
    messages_bounded: Annotated[list, DeltaChannel(_messages_delta_reducer, snapshot_frequency=10)]
```

---

## Storage benchmarks (InMemory, ~400 char/msg)

**Messages blob storage** (`checkpoint_blobs` bytes for the messages
channel):

| turns | add\_messages | delta(inf) | delta(freq=50) | delta(freq=10) |
delta(freq=5) |

|------:|-------------:|-----------:|---------------:|---------------:|--------------:|
| 10 | 91.0 KB | 60 B (1517x) | 60 B (1517x) | 14.4 KB (6x) | 32.6 KB
(3x) |
| 50 | 2.20 MB | 300 B (7347x) | 67.1 KB (33x) | 423 KB (5x) | 864 KB
(3x) |
| 100 | 8.78 MB | 600 B (14636x) | 310 KB (28x) | 1.72 MB (5x) | 3.48 MB
(3x) |
| 250 | 54.80 MB | 1.5 KB (36536x) | 2.09 MB (26x) | 10.87 MB (5x) |
21.84 MB (3x) |
| 500 | 219.19 MB | 3.0 KB (73063x) | 8.56 MB (26x) | 43.67 MB (5x) |
87.50 MB (3x) |

**Total checkpoint storage** (blobs + writes + metadata):

| turns | add\_messages | delta(inf) | delta(freq=50) | delta(freq=10) |
delta(freq=5) |

|------:|-------------:|-----------:|---------------:|---------------:|--------------:|
| 10 | 129.7 KB | 38.7 KB (3.4x) | 38.7 KB (3.4x) | 53.1 KB (2.4x) |
71.2 KB (1.8x) |
| 50 | 2.40 MB | 196 KB (12x) | 263 KB (9x) | 620 KB (3.9x) | 1.06 MB
(2.3x) |
| 100 | 9.18 MB | 394 KB (23x) | 703 KB (13x) | 2.12 MB (4.3x) | 3.87 MB
(2.4x) |
| 250 | 55.79 MB | 987 KB (57x) | 3.07 MB (18x) | 11.86 MB (4.7x) |
22.82 MB (2.4x) |
| 500 | 221.16 MB | 1.98 MB (112x) | 10.53 MB (21x) | 45.64 MB (4.9x) |
89.48 MB (2.5x) |

**Write-phase peak heap**:

| turns | add\_messages | delta(inf) | delta(freq=50) | delta(freq=10) |
delta(freq=5) |

|------:|-------------:|-----------:|---------------:|---------------:|--------------:|
| 10 | 456 KB | 199 KB (2.3x) | 199 KB (2.3x) | 212 KB (2.2x) | 232 KB
(2.0x) |
| 50 | 3.04 MB | 742 KB (4.1x) | 805 KB (3.8x) | 1.21 MB (2.5x) | 1.67
MB (1.8x) |
| 100 | 10.70 MB | 1.41 MB (7.6x) | 1.82 MB (5.9x) | 3.42 MB (3.1x) |
5.25 MB (2.0x) |
| 250 | 60.44 MB | 3.36 MB (18x) | 5.67 MB (11x) | 14.87 MB (4.1x) |
26.31 MB (2.3x) |

**Read-phase avg `get_state` latency** (5 calls, InMemory):

| turns | add\_messages | delta(inf) | delta(freq=50) | delta(freq=10) |
delta(freq=5) |

|------:|-------------:|-----------:|---------------:|---------------:|--------------:|
| 10 | 0.7 ms | 1.1 ms (0.6x) | 1.1 ms (0.6x) | 0.8 ms (0.9x) | 0.6 ms
(1.1x) |
| 50 | 2.7 ms | 5.3 ms (0.5x) | 3.5 ms (0.8x) | 2.7 ms (1.0x) | 2.7 ms
(1.0x) |
| 100 | 5.5 ms | 11.1 ms (0.5x) | 6.0 ms (0.9x) | 5.2 ms (1.1x) | 5.4 ms
(1.0x) |
| 250 | 12.9 ms | 27.2 ms (0.5x) | 13.6 ms (0.9x) | 12.9 ms (1.0x) |
13.0 ms (1.0x) |

**Postgres `get_tuple` read latency** (~100 tok/msg per step):

| steps | full-list | delta(inf) | delta(freq=50) | delta(freq=10) |
delta(freq=5) |

|------:|----------:|-----------:|---------------:|---------------:|--------------:|
| 10 | 0.29 ms | 0.21 ms (1.4x) | 0.19 ms (1.6x) | 0.19 ms (1.5x) | 0.19
ms (1.6x) |
| 50 | 0.19 ms | 0.15 ms (1.3x) | 0.19 ms (1.0x) | 0.22 ms (0.8x) | 0.29
ms (0.7x) |
| 100 | 0.27 ms | 0.17 ms (1.6x) | 0.22 ms (1.2x) | 0.23 ms (1.2x) |
0.21 ms (1.3x) |
| 500 | 0.60 ms | 0.30 ms (2.0x) | 0.66 ms (0.9x) | 0.56 ms (1.1x) |
0.69 ms (0.9x) |

**Takeaway:** `snapshot_frequency=10` matches full-list read latency
while still saving 5x on blob storage and ~4x on total storage.

---

## How it works

### Checkpoint blobs

`checkpoint()` always returns `DELTA_SENTINEL` (a zero-byte msgpack ext
marker) instead of the accumulated value. On restore, the saver's
`_get_channel_writes_history` walks the ancestor chain collecting
`checkpoint_writes` entries and replays them through the reducer:

```python
# blob stored per step: ~1 byte (sentinel)
# vs. full list growing O(N) every step with BinaryOperatorAggregate
```

### Reducer interface

`DeltaChannel` takes a **batch reducer** `(state, list[writes]) ->
state` — all writes for a step arrive in one call, enabling single-pass
implementations:

```python
#  Don't use add_messages directly — it's a binary operator, not a batch reducer
messages: Annotated[list, DeltaChannel(add_messages)]  # wrong

#  Use _messages_delta_reducer — single pass, dedup by ID, RemoveMessage support
messages: Annotated[list, DeltaChannel(_messages_delta_reducer)]

#  Or write your own batch reducer for custom types
def my_dict_reducer(state: dict, writes: list[dict]) -> dict:
    result = dict(state)
    for w in writes:
        result.update(w)
    return result

files: Annotated[dict, DeltaChannel(my_dict_reducer)]
```

### Snapshot frequency

`snapshot_frequency=N` writes a full `_DeltaSnapshot` blob every N
pregel steps, bounding replay depth regardless of thread length.
Snapshots are eager — written even if the channel had no update that
step, so the depth bound always holds:

```python
# Replay walks at most 10 ancestors before hitting a snapshot
messages: Annotated[list, DeltaChannel(_messages_delta_reducer, snapshot_frequency=10)]
```

### Migration from `BinaryOperatorAggregate`

Pre-existing threads written under `BinaryOperatorAggregate` work
transparently after swapping the annotation — the saver detects a
plain-value ancestor blob and uses it as the reconstruction seed:

```python
# Before: BinaryOperatorAggregate stores full list every step
items: Annotated[list, add_messages]

# After: DeltaChannel — existing checkpoints still readable, new steps use sentinel
items: Annotated[list, DeltaChannel(_messages_delta_reducer)]
```

### Async write-ordering safety

In `durability="async"` mode (default), `put_writes` calls are
fire-and-forget. `AsyncPregelLoop` tracks in-flight `aput_writes`
futures for DeltaChannel channels in `_delta_write_futs` and drains them
via `await asyncio.gather()` in `_checkpointer_put_after_previous`
before `aput()` — ensuring `checkpoint_writes` are durable before the
sentinel blob is committed.

---

## What's in scope

- **`libs/langgraph/langgraph/channels/delta.py`** — `DeltaChannel`
implementation
- **`libs/langgraph/langgraph/graph/message.py`** —
`_messages_delta_reducer` (experimental)
- **`libs/checkpoint/`** — `_get_channel_writes_history` ancestor-walk
API on `BaseCheckpointSaver`, `InMemorySaver` optimized override
- **`libs/checkpoint-postgres/`** — `PostgresSaver` /
`AsyncPostgresSaver` single-roundtrip UNION ALL override
- **`libs/langgraph/langgraph/pregel/`** — `channels_from_checkpoint` /
`create_checkpoint` wiring, async write-ordering safety

---

## Follow-ups

- **Batch reconstruction**: each DeltaChannel field issues its own
`_get_channel_writes_history` call; a single walk collecting all
sentinel channels would reduce roundtrips proportionally to the number
of DeltaChannel fields.
- **Sync write ordering**: `BackgroundExecutor.__exit__` guarantees
completion before `invoke()` returns, but within a run there's no
explicit ordering between `put_writes` and `put`. Two-phase commit for
sync would close this gap.
- **`ShallowPostgresSaver` compatibility**: shallow savers keep only the
latest checkpoint and have no parent chain to walk; DeltaChannel is
currently incompatible and should raise or warn at compile time.
- Updating the writes table w/ delta epoch ids for more efficient reads
- follow up w/ LSD checkpointer implementations to support delta
channel! and update prune

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Will Fu-Hinthorn <will@langchain.dev>
2026-04-29 17:26:17 -04:00
..
2026-04-27 10:27:56 -04:00

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=true or pass an explicit allowed_msgpack_modules list 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 PostgresSaver or AsyncPostgresSaver, make sure to include autocommit=True and row_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 default tuple_row factory returns tuples that only support index-based access (e.g., row[0]), which will cause TypeError exceptions 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)]