WEBDIENSTE/langgraph

Fork 0

mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-22 23:52:23 +02:00

Files

T

History

398d6cc59d chore(langgraph): add guide/conformance for delta channel checkpointer (#7736 )

## Summary

Add a user-facing design doc and `get_delta_channel_keepset` helper for
third-party `BaseCheckpointSaver` authors who need to support graphs
using `DeltaChannel`.

**Deliverables:**

1. ~~**`docs/delta-channel-checkpointer-guide.md`** — comprehensive
guide covering~~:
moved to docs repo

2. **`BaseCheckpointSaver.get_delta_channel_keepset` /
`aget_delta_channel_keepset`** — returns the minimum set of ancestor
`checkpoint_id`s that must survive deletion for a given head's
`DeltaChannel` reconstruction to remain intact. Enables safe `prune`
implementations without silently corrupting delta history.

3. **Docstring warnings** on `prune`, `aprune`, `delete_for_runs`,
`adelete_for_runs`, `copy_thread`, `acopy_thread` explaining the
DeltaChannel pitfall (silent data loss if ancestor writes/snapshots are
deleted).

4. **Three new conformance capabilities** in
`libs/checkpoint-conformance`:
- `delta_channel_history` — validates the `aget_delta_channel_history`
walk contract
   - `delta_channel_keepset` — validates the keep-set contract
- `delta_channel_reconstruction` — end-to-end round-trip (aput +
aput_writes + history + reconstruct)

## Test plan

- [x] `make format lint` passes in `libs/checkpoint`,
`libs/checkpoint-conformance`
- [x] All three new conformance capabilities pass against
`InMemorySaver`
- [x] Run conformance against SQLite saver 
- [x] Run conformance against Postgres saver

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-05-07 17:34:46 -07:00

langgraph

feat(checkpoint-sqlite): override get_delta_channel_history with streaming walk (#7702 )

2026-05-05 15:30:57 -04:00

tests

chore(langgraph): add guide/conformance for delta channel checkpointer (#7736 )

2026-05-07 17:34:46 -07:00

LICENSE

docs: add license files for checkpoint-sqlite and checkpoint-postgres (#6392 )

2025-11-07 07:39:06 -05:00

Makefile

chore: add make type target for type checking (#6748 )

2026-02-21 05:13:38 +00:00

pyproject.toml

feat(checkpoint-sqlite): override get_delta_channel_history with streaming walk (#7702 )

2026-05-05 15:30:57 -04:00

README.md

docs: document LANGGRAPH_STRICT_MSGPACK for checkpoint security (#7517 )

2026-04-15 13:05:55 -07:00

uv.lock

feat(checkpoint-sqlite): override get_delta_channel_history with streaming walk (#7702 )

2026-05-05 15:30:57 -04:00

README.md

LangGraph SQLite Checkpoint

Implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite)

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

from langgraph.checkpoint.sqlite import SqliteSaver

write_config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
read_config = {"configurable": {"thread_id": "1"}}

with SqliteSaver.from_conn_string(":memory:") 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
    checkpointer.put(write_config, checkpoint, {}, {})

    # load checkpoint
    checkpointer.get(read_config)

    # list checkpoints
    list(checkpointer.list(read_config))

Async

from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver

async with AsyncSqliteSaver.from_conn_string(":memory:") 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)]