Files
langgraph/libs/checkpoint-sqlite
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
8b893e9776 chore(deps): bump langchain-core from 1.2.28 to 1.3.3 in /libs/checkpoint-sqlite (#7751)
Bumps [langchain-core](https://github.com/langchain-ai/langchain) from
1.2.28 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>
<h2>langchain-core==1.3.2</h2>
<p>Changes since langchain-core==1.3.1</p>
<p>release(core): 1.3.2 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36990">#36990</a>)
feat(core): add content-block-centric streaming (v2) (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36834">#36834</a>)</p>
<h2>langchain-core==1.3.1</h2>
<p>Changes since langchain-core==1.3.0</p>
<p>release(core): 1.3.1 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36972">#36972</a>)
feat(core): allow _format_output to pass through list of ToolOutputMixin
instances (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36963">#36963</a>)
chore: bump nbconvert from 7.17.0 to 7.17.1 in /libs/core (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36923">#36923</a>)
feat(core): Update inheritance behavior for tracer metadata for special
keys (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36900">#36900</a>)
chore: bump langsmith from 0.7.13 to 0.7.31 in /libs/core (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36813">#36813</a>)</p>
<h2>langchain-core==1.3.0</h2>
<p>Changes since langchain-core==1.2.31</p>
<p>release(core): release 1.3.0 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36851">#36851</a>)
release(core): 1.3.0a3 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36829">#36829</a>)
chore(core): keep checkpoint_ns behavior in streaming metadata for
backwards compat (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36828">#36828</a>)
feat(core): Add chat model and LLM invocation params to traceable
metadata (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36771">#36771</a>)
fix(core): restore cloud metadata IPs and link-local range in SSRF
policy (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36816">#36816</a>)
chore(deps): bump pytest to <code>9.0.3</code> (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36801">#36801</a>)
chore(core): harden private SSRF utilities (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36768">#36768</a>)
fix(openai): handle content blocks without type key in responses api
conversion (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36725">#36725</a>)
chore: bump pytest from 9.0.2 to 9.0.3 in /libs/core (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36719">#36719</a>)
release(core): 1.3.0.a2 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36698">#36698</a>)
fix(core): Use reference counting for storing inherited run trees to
support garbage collection (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36660">#36660</a>)
docs(core): nit (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36685">#36685</a>)
release(core): 1.3.0a1 (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36656">#36656</a>)
chore(core): reduce streaming metadata / perf (<a
href="https://redirect.github.com/langchain-ai/langchain/issues/36588">#36588</a>)</p>
<h2>langchain-core==1.3.0a3</h2>
<p>Initial release</p>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</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==1.2.28...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=1.2.28&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 14:17:25 -07:00
..

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)]