langchain

0 Fork 0

mirror of https://github.com/langchain-ai/langchain.git synced 2026-10-05 09:25:14 +03:00

T

dependabot[bot] 019eae0203 chore(deps): bump anyio from 4.14.2 to 4.15.1 in /libs/text-splitters (#40645 )

Bumps [anyio](https://github.com/agronholm/anyio) from 4.14.2 to 4.15.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/agronholm/anyio/releases">anyio's
releases</a>.</em></p>
<blockquote>
<h2>4.15.1</h2>
<ul>
<li>Implemented a compatibility fix for supporting direct access of
<code>anyio.*</code> submodules from the main package even when those
submodules were not directly imported first (<!-- raw HTML omitted --><a
href="https://redirect.github.com/agronholm/anyio/issues/1311">#1311</a>
&lt;<a
href="https://redirect.github.com/agronholm/anyio/issues/1311%5C%3E">agronholm/anyio#1311</a><!--
raw HTML omitted -->)</li>
</ul>
<h2>4.15.0</h2>
<ul>
<li>
<p>Added support for the newer keyword-only arguments on
<code>anyio.Path</code> methods to match the standard library
<code>pathlib.Path</code>:</p>
<ul>
<li><code>follow_symlinks</code> on <code>exists()</code> (Python
3.12+)</li>
<li><code>follow_symlinks</code> on <code>is_dir()</code> (Python
3.13+)</li>
<li><code>follow_symlinks</code> on <code>is_file()</code> (Python
3.13+)</li>
<li><code>follow_symlinks</code> on <code>owner()</code> (Python
3.13+)</li>
<li><code>follow_symlinks</code> on <code>group()</code> (Python
3.13+)</li>
<li><code>newline</code> on <code>read_text()</code> (Python 3.13+)</li>
</ul>
<p>(<a
href="https://redirect.github.com/agronholm/anyio/pull/1286">#1286</a>,
<a
href="https://redirect.github.com/agronholm/anyio/pull/1293">#1293</a>;
PR by <a
href="https://github.com/jaideeppyne"><code>@jaideeppyne</code></a>)</p>
</li>
<li>
<p>Added <code>amap</code>, <code>gather</code>, and
<code>as_completed</code> utility functions to simplify common patterns
(<a
href="https://redirect.github.com/agronholm/anyio/pull/1173">#1173</a>;
PR by <a
href="https://github.com/Graeme22"><code>@Graeme22</code></a>)</p>
</li>
<li>
<p>Added <code>--anyio-mode</code> command-line option as an alternative
to the <code>anyio_mode</code> ini setting, and fix the pytest plugin's
auto mode detection to recognize the mode when set via either
mechanism(e.g: <code>pytest_asyncio</code>). (<a
href="https://redirect.github.com/agronholm/anyio/pull/1242">#1242</a>;
PR by <a
href="https://github.com/EmmanuelNiyonshuti"><code>@EmmanuelNiyonshuti</code></a>)</p>
</li>
<li>
<p>Added the <code>anyio.Future</code> synchronization primitive which
behaves similar to <code>asyncio.Future</code>, allowing tasks to wait
for a value (or exception) from another task (<a
href="https://redirect.github.com/agronholm/anyio/pull/1146">#1146</a>;
PR by <a
href="https://github.com/Vizonex"><code>@Vizonex</code></a>)</p>
</li>
<li>
<p>Added guidance for managing multiple memory object stream producers
and consumers with cloned streams (<a
href="https://redirect.github.com/agronholm/anyio/issues/330">#330</a>;
PR by <a
href="https://github.com/nightcityblade"><code>@nightcityblade</code></a>)</p>
</li>
<li>
<p>Added <code>StapledObjectStream.send_nowait()</code> that delegates
to the underlying <code>ObjectSendStream</code>, if it implements it (<a
href="https://redirect.github.com/agronholm/anyio/pull/1241">#1241</a>;
PR by <a
href="https://github.com/davidbrochart"><code>@davidbrochart</code></a>)</p>
</li>
<li>
<p>Added the <code>move_on_at()</code> and <code>fail_at()</code>
functions to complement <code>move_on_after()</code> and
<code>fail_after()</code></p>
</li>
<li>
<p>Changed the default name for a task spawned with
<code>TaskGroup.create_task(func())</code> to match the default task
name for the analogous task spawned with
<code>TaskGroup.start_soon(func)</code> or
<code>TaskGroup.start(func)</code> in more situations. Previously, the
default name of a <code>TaskGroup.create_task</code> task never included
the module name. (The default name for a task spawned with
<code>TaskGroup.start_soon</code> or <code>TaskGroup.start</code>
typically includes the module name.) (<a
href="https://redirect.github.com/agronholm/anyio/pull/1234">#1234</a>;
PR by <a
href="https://github.com/gschaffner"><code>@gschaffner</code></a>)</p>
</li>
<li>
<p>Changed the <code>anyio</code> and <code>anyio.abc</code> modules to
lazily (much like <code>810</code>) import the necessary submodules.
This is done by parsing the AST of the module and building a lookup
table from the <code>if TYPE_CHECKING:</code> block. A fallback mode has
been provided for installations where the source code is unavailable
(e.g. PyInstaller). (<a
href="https://redirect.github.com/agronholm/anyio/pull/1169">#1169</a>)</p>
</li>
<li>
<p>Fixed free-threading compatibility issues arising from the fact that
on Python 3.14 free-threading builds, newly created threads inherit the
current context by default, causing AnyIO to behave erroneously in
relation to <code>start_blocking_portal()</code> and
<code>anyio.to_thread.run_sync()</code> (<a
href="https://redirect.github.com/agronholm/anyio/pull/1224">#1224</a>;
PR by <a
href="https://github.com/EmmanuelNiyonshuti"><code>@EmmanuelNiyonshuti</code></a>)</p>
</li>
<li>
<p>Fixed <code>SpooledTemporaryFile.readinto()</code> and
<code>readinto1()</code> reading twice before rollover, so the
destination buffer was overwritten by the second read and the file
position advanced twice, silently losing data (<a
href="https://redirect.github.com/agronholm/anyio/pull/1215">#1215</a>;
PR by <a
href="https://github.com/c-tonneslan"><code>@c-tonneslan</code></a>)</p>
</li>
<li>
<p>Added a <code>reason</code> parameter to <code>fail_after</code> (and
the new <code>fail_at</code>) allowing for added exception context when
raising <code>TimeoutError</code> (<a
href="https://redirect.github.com/agronholm/anyio/pull/1227">#1227</a>;
PR by <a
href="https://github.com/Graeme22"><code>@Graeme22</code></a>)</p>
</li>
<li>
<p>Fixed the default <code>TaskHandle.name</code> missing part of the
task name for tasks started with <code>TaskGroup.start</code> on Trio
(<a
href="https://redirect.github.com/agronholm/anyio/issues/1231">#1231</a>;
PR by <a
href="https://github.com/gschaffner"><code>@gschaffner</code></a>)</p>
</li>
<li>
<p>Fixed <code>anyio.run</code> leaking, or at least, delaying
collection of loop and root_task due to the root task being cached in a
<code>RunVar</code>. (<a
href="https://redirect.github.com/agronholm/anyio/issues/1203">#1203</a>;
PR by <a
href="https://github.com/tapetersen"><code>@tapetersen</code></a>)</p>
</li>
<li>
<p>Fixed <code>anyio.Path.with_stem()</code> silently producing a wrong
path (e.g. <code>Path(&quot;.txt&quot;)</code>) instead of raising
<code>ValueError</code> when given an empty stem on a path with a
non-empty suffix, unlike <code>pathlib.PurePath.with_stem</code> (<a
href="https://redirect.github.com/agronholm/anyio/pull/1200">#1200</a>;
PR by <a
href="https://github.com/Sanjays2402"><code>@Sanjays2402</code></a>)</p>
</li>
<li>
<p>Fixed <code>UNIXSocketStream.aclose()</code> raising
<code>asyncio.InvalidStateError</code> when a concurrent receive or send
operation had just been cancelled on the asyncio backend (<a
href="https://redirect.github.com/agronholm/anyio/issues/1267">#1267</a>;
PR by <a
href="https://github.com/alloutflo"><code>@alloutflo</code></a>)</p>
</li>
<li>
<p>Fixed the pytest plugin importing the deprecated
<code>_pytest.python.CallSpec2</code> alias, which triggers
<code>PytestRemovedIn10Warning</code> on <code>pytest&gt;=9.2</code> and
crashes pytest at startup when <code>filterwarnings = error</code> is
configured (<a
href="https://redirect.github.com/agronholm/anyio/issues/1271">#1271</a>;
PR by <a
href="https://github.com/matthewfeickert"><code>@matthewfeickert</code></a>)</p>
</li>
<li>
<p>Fixed an asyncio worker thread race that could raise
<code>RuntimeError</code> when the event loop closed between checking
its state and scheduling the worker result (<a
href="https://redirect.github.com/agronholm/anyio/issues/1265">#1265</a>;
PR by <a
href="https://github.com/hansu650"><code>@hansu650</code></a>)</p>
</li>
<li>
<p>Fixed <code>CapacityLimiter</code> on the asyncio backend
over-granting tokens when <code>total_tokens</code> was raised while the
limiter was over-subscribed (<a
href="https://redirect.github.com/agronholm/anyio/pull/1223">#1223</a>;
PR by <a
href="https://github.com/zelinewang"><code>@zelinewang</code></a>)</p>
</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/agronholm/anyio/commit/ffcd1542cd6d127980205f90a0100078849dd703"><code>ffcd154</code></a>
Bumped up the version</li>
<li><a
href="https://github.com/agronholm/anyio/commit/0ecf5ed98d294242509b043ebd1a0843e52d892f"><code>0ecf5ed</code></a>
Added a workaround for third party code accessing unimported submodules
(<a
href="https://redirect.github.com/agronholm/anyio/issues/1309">#1309</a>)</li>
<li><a
href="https://github.com/agronholm/anyio/commit/928366259543412a2deb1e2ba09ea45ffa92ef4f"><code>9283662</code></a>
Bumped up the version</li>
<li><a
href="https://github.com/agronholm/anyio/commit/d137692a90f76e4f71605e32ea5ca94cab3a539d"><code>d137692</code></a>
Improved the instructions for AI agents</li>
<li><a
href="https://github.com/agronholm/anyio/commit/033fc52b8fa8e90c5d0ef24b10b3860e974a6265"><code>033fc52</code></a>
Shield TemporaryDirectory cleanup from cancellation (<a
href="https://redirect.github.com/agronholm/anyio/issues/1304">#1304</a>)</li>
<li><a
href="https://github.com/agronholm/anyio/commit/942e9a6552cc10b5aaa779d84bfc8e2c3d5fcffc"><code>942e9a6</code></a>
[pre-commit.ci] pre-commit autoupdate (<a
href="https://redirect.github.com/agronholm/anyio/issues/1305">#1305</a>)</li>
<li><a
href="https://github.com/agronholm/anyio/commit/b825c3be7cb4ca1a8000b8065d4e147843deb704"><code>b825c3b</code></a>
Fixed pyproject.toml changes not triggering the test suite</li>
<li><a
href="https://github.com/agronholm/anyio/commit/9727dc504681e2986b5bc285de9571fb467539af"><code>9727dc5</code></a>
Fixed start inconsistencies between trio and asyncio (<a
href="https://redirect.github.com/agronholm/anyio/issues/1198">#1198</a>)</li>
<li><a
href="https://github.com/agronholm/anyio/commit/b05fe6d160a640355c201363cab286a7d2581da8"><code>b05fe6d</code></a>
Fixed wrong type in move_on_after (<a
href="https://redirect.github.com/agronholm/anyio/issues/1297">#1297</a>)</li>
<li><a
href="https://github.com/agronholm/anyio/commit/44d0c93cc20079acbf38ba4dbed5ab9df323f153"><code>44d0c93</code></a>
Fixed asyncio task group coroutine cleanup (<a
href="https://redirect.github.com/agronholm/anyio/issues/1275">#1275</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/agronholm/anyio/compare/4.14.2...4.15.1">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=anyio&package-manager=uv&previous-version=4.14.2&new-version=4.15.1)](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/langchain/network/alerts).

</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

2026-09-18 15:10:34 -04:00

.devcontainer

fix(infra): use langchain_v1 for dev container deps (#34534 )

2025-12-29 18:10:40 -06:00

.github

chore(deps): bump aws-actions/configure-aws-credentials from 6.2.3 to 6.2.4 in the minor-and-patch group (#40564 )

2026-09-17 14:08:20 -04:00

.vscode

chore(infra): remove jupyter recommended extensions (#34430 )

2025-12-19 20:24:58 -06:00

libs

chore(deps): bump anyio from 4.14.2 to 4.15.1 in /libs/text-splitters (#40645 )

2026-09-18 15:10:34 -04:00

openwiki

docs: update OpenWiki (#40318 )

2026-09-09 17:02:42 -04:00

.dockerignore

feat(infra): add .dockerignore for codespaces (#34533 )

2025-12-29 17:58:28 -06:00

.editorconfig

chore: add .editorconfig for consistent coding styles across files (#32261 )

2025-07-27 23:25:30 -04:00

.gitattributes

Update dev container (#6189 )

2023-06-16 15:42:14 -07:00

.gitignore

chore(infra): expand credential coverage in root .gitignore (#39147 )

2026-07-30 11:27:08 -04:00

.markdownlint.json

chore: formatting across codebase (#32466 )

2025-08-08 10:20:10 -04:00

.mcp.json

chore: add reference docs MCP (#35737 )

2026-03-10 23:21:19 -04:00

.pre-commit-config.yaml

chore(infra): wire up per-partner version-consistency pre-commit hooks (#38121 )

2026-06-12 22:08:22 -04:00

AGENTS.md

docs: add openwiki (#40183 )

2026-09-04 11:03:34 +02:00

CITATION.cff

rename repo namespace to langchain-ai (#11259 )

2023-10-01 15:30:58 -04:00

CLAUDE.md

docs: update OpenWiki (#40318 )

2026-09-09 17:02:42 -04:00

LICENSE

Library Licenses (#13300 )

2023-11-28 17:34:27 -08:00

README.md

fix: typo (#39684 )

2026-08-17 15:03:26 -04:00

README.md

The agent engineering platform.

LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the underlying technology evolves.

Tip

Just getting started? Check out Deep Agents — a higher-level package built on LangChain for agents that have built-in capabilities for common usage patterns such as planning, subagents, file system usage, and more.

Quickstart

uv add langchain

from langchain.chat_models import init_chat_model

model = init_chat_model("openai:gpt-5.5")
result = model.invoke("Hello, world!")

If you're looking for more advanced customization or agent orchestration, check out LangGraph, our framework for building controllable agent workflows.

For an equivalent JS/TS library, check out LangChain.js.

Tip

For developing, debugging, and deploying AI agents and LLM applications, see LangSmith.

LangChain ecosystem

While the LangChain framework can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools when building LLM applications.

Deep Agents — Build agents that can plan, use subagents, and leverage file systems for complex tasks
LangGraph — Build agents that can reliably handle complex tasks with our low-level agent orchestration framework
Integrations — Chat & embedding models, tools & toolkits, and more
LangSmith — Agent evals, observability, and debugging for LLM apps
LangSmith Deployment — Deploy and scale agents with a purpose-built platform for long-running, stateful workflows

Why use LangChain?

LangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.

Real-time data augmentation — Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain's vast library of integrations with model providers, tools, vector stores, retrievers, and more
Model interoperability — Swap models in and out as your engineering team experiments to find the best choice for your application's needs. As the industry frontier evolves, adapt quickly — LangChain's abstractions keep you moving without losing momentum
Rapid prototyping — Quickly build and iterate on LLM applications with LangChain's modular, component-based architecture. Test different approaches and workflows without rebuilding from scratch, accelerating your development cycle
Production-ready features — Deploy reliable applications with built-in support for monitoring, evaluation, and debugging through integrations like LangSmith. Scale with confidence using battle-tested patterns and best practices
Vibrant community and ecosystem — Leverage a rich ecosystem of integrations, templates, and community-contributed components. Benefit from continuous improvements and stay up-to-date with the latest AI developments through an active open-source community
Flexible abstraction layers — Work at the level of abstraction that suits your needs — from high-level chains for quick starts to low-level components for fine-grained control. LangChain grows with your application's complexity

Resources

Documentation — conceptual overviews and guides
LangChain ecosystem overview — how LangChain, LangGraph, and Deep Agents fit together
API reference — complete reference for all public classes, functions, and types
Discussions — community forum for technical questions, ideas, and feedback
LangChain Academy — comprehensive, free courses on LangChain libraries and products, made by the LangChain team
Contributing Guide — how to contribute and find good first issues
Code of Conduct — community guidelines and standards