Files
langgraph/libs/checkpoint-postgres
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
dcfcd1dbb4 chore(deps): bump langchain-core from 1.3.2 to 1.3.3 in /libs/checkpoint-postgres (#7754)
Bumps [langchain-core](https://github.com/langchain-ai/langchain) from
1.3.2 to 1.3.3.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/langchain-ai/langchain/releases">langchain-core's
releases</a>.</em></p>
<blockquote>
<h2>langchain-core==1.3.3</h2>
<p>Changes since langchain-core==1.3.2</p>
<p>release(core): 1.3.3 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37198">#37198</a>)
fix(core): set deprecation <code>since</code> to 1.3.3 to match release
(<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37200">#37200</a>)
fix(core, langchain): harden <code>load()</code> against untrusted
manifests (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37197">#37197</a>)
chore: bump notebook from 7.5.0 to 7.5.6 in /libs/core (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37109">#37109</a>)
chore: bump types-pyyaml from 6.0.12.20250915 to 6.0.12.20260408 in
/libs/core (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37129">#37129</a>)
fix(core): preserve structured <code>inputs</code> on tool runs in
tracers (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37108">#37108</a>)
release(perplexity): 1.2.0 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37091">#37091</a>)
chore(docs): update x handle references (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37081">#37081</a>)
fix(core): make <code>removal</code> optional in
<code>warn_deprecated</code> (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37056">#37056</a>)
fix(core): validate batch_size in _batch and _abatch to prevent infinite
loop (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36663">#36663</a>)
chore(core): mark stream_v2/astream_v2 as beta (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36992">#36992</a>)</p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/langchain-ai/langchain/commit/5039dfec1f8e78459540a7f1b52fb0d6d82e3f07"><code>5039dfe</code></a>
release(core): 1.3.3 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37198">#37198</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/55a7707837742c2f7a9b7e4a5dd428bf615f3b82"><code>55a7707</code></a>
fix(core): set deprecation <code>since</code> to 1.3.3 to match release
(<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37200">#37200</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/c979c6187b6d82f4bef35b10b84b39fa44806b22"><code>c979c61</code></a>
fix(core, langchain): harden <code>load()</code> against untrusted
manifests (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37197">#37197</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/d7031101da78e3f6b6c5956b48a5170c1a33292b"><code>d703110</code></a>
docs: update README.md (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37190">#37190</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/4d50a2a68b38e9acc53027ea7e7cc89e2d80b4c7"><code>4d50a2a</code></a>
ci(infra): run pre-release checks before TestPyPI publish (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37194">#37194</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/9bd730e1991baac4ea80aa07d93110dc1b52ee25"><code>9bd730e</code></a>
fix(fireworks): require <code>api_key</code> in
<code>FireworksEmbeddings</code> (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37193">#37193</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/f475f4191fc3a8d3cf14063b44d524594c080c04"><code>f475f41</code></a>
release(mistralai): 1.1.4 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37191">#37191</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/7dbff48aff508b01dc231ea0cbd4e4e09da92c97"><code>7dbff48</code></a>
fix(mistralai): strip non-wire keys from <code>ToolMessage</code> (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37188">#37188</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/913816c440ea79295370e1af6484e17b86e5d03c"><code>913816c</code></a>
release(fireworks): 1.3.1 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/37189">#37189</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchain/commit/4498d3dc84a85688fa4d15476403a900bc7f9114"><code>4498d3d</code></a>
fix(fireworks): strip non-wire keys from <code>ToolMessage</code> text
content blocks (#...</li>
<li>Additional commits viewable in <a
href="https://github.com/langchain-ai/langchain/compare/langchain-core==1.3.2...langchain-core==1.3.3">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=langchain-core&package-manager=uv&previous-version=1.3.2&new-version=1.3.3)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langgraph/network/alerts).

</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-05-11 14:17:55 -07:00
..

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)]