**Description:** Right now, we interrupt even if the provided ToolConfig
has all false values. We should ignore ToolConfigs which do not have at
least one value marked as true (just as we would if tool_name: False was
passed into the dict).
# Main Changes
1. Adding decorator utilities for dynamically defining middleware with
single hook functions (see an example below for dynamic system prompt)
2. Adding better conditional edge drawing with jump configuration
attached to middleware. Can be registered w/ the decorator new
decorator!
## Decorator Utilities
```py
from langchain.agents.middleware_agent import create_agent, AgentState, ModelRequest
from langchain.agents.middleware.types import modify_model_request
from langchain_core.messages import HumanMessage
from langgraph.checkpoint.memory import InMemorySaver
@modify_model_request
def modify_system_prompt(request: ModelRequest, state: AgentState) -> ModelRequest:
request.system_prompt = (
"You are a helpful assistant."
f"Please record the number of previous messages in your response: {len(state['messages'])}"
)
return request
agent = create_agent(
model="openai:gpt-4o-mini",
middleware=[modify_system_prompt]
).compile(checkpointer=InMemorySaver())
```
## Visualization and Routing improvements
We now require that middlewares define the valid jumps for each hook.
If using the new decorator syntax, this can be done with:
```py
@before_model(jump_to=["__end__"])
@after_model(jump_to=["tools", "__end__"])
```
If using the subclassing syntax, you can use these two class vars:
```py
class MyMiddlewareAgentMiddleware):
before_model_jump_to = ["__end__"]
after_model_jump_to = ["tools", "__end__"]
```
Open for debate if we want to bundle these in a single jump map / config
for a middleware. Easy to migrate later if we decide to add more hooks.
We will need to **really clearly document** that these must be
explicitly set in order to enable conditional edges.
Notice for the below case, `Middleware2` does actually enable jumps.
<table>
<thead>
<tr>
<th>Before (broken), adding conditional edges unconditionally</th>
<th>After (fixed), adding conditional edges sparingly</th>
</tr>
</thead>
<tbody>
<tr>
<td>
<img width="619" height="508" alt="Screenshot 2025-09-23 at 10 23 23 AM"
src="https://github.com/user-attachments/assets/bba2d098-a839-4335-8e8c-b50dd8090959"
/>
</td>
<td>
<img width="469" height="490" alt="Screenshot 2025-09-23 at 10 23 13 AM"
src="https://github.com/user-attachments/assets/717abf0b-fc73-4d5f-9313-b81247d8fe26"
/>
</td>
</tr>
</tbody>
</table>
<details>
<summary>Snippet for the above</summary>
```py
from typing import Any
from langchain.agents.tool_node import InjectedState
from langgraph.runtime import Runtime
from langchain.agents.middleware.types import AgentMiddleware, AgentState
from langchain.agents.middleware_agent import create_agent
from langchain_core.tools import tool
from typing import Annotated
from langchain_core.messages import HumanMessage
from typing_extensions import NotRequired
@tool
def simple_tool(input: str) -> str:
"""A simple tool."""
return "successful tool call"
class Middleware1(AgentMiddleware):
"""Custom middleware that adds a simple tool."""
tools = [simple_tool]
def before_model(self, state: AgentState, runtime: Runtime) -> None:
return None
def after_model(self, state: AgentState, runtime: Runtime) -> None:
return None
class Middleware2(AgentMiddleware):
before_model_jump_to = ["tools", "__end__"]
def before_model(self, state: AgentState, runtime: Runtime) -> None:
return None
def after_model(self, state: AgentState, runtime: Runtime) -> None:
return None
class Middleware3(AgentMiddleware):
def before_model(self, state: AgentState, runtime: Runtime) -> None:
return None
def after_model(self, state: AgentState, runtime: Runtime) -> None:
return None
builder = create_agent(
model="openai:gpt-4o-mini",
middleware=[Middleware1(), Middleware2(), Middleware3()],
system_prompt="You are a helpful assistant.",
)
agent = builder.compile()
```
</details>
## More Examples
### Guardrails `after_model`
<img width="379" height="335" alt="Screenshot 2025-09-23 at 10 40 09 AM"
src="https://github.com/user-attachments/assets/45bac7dd-398e-45d1-ae58-6ecfa27dfc87"
/>
<details>
<summary>Code</summary>
```py
from langchain.agents.middleware_agent import create_agent, AgentState, ModelRequest
from langchain.agents.middleware.types import after_model
from langchain_core.messages import HumanMessage, AIMessage
from langgraph.checkpoint.memory import InMemorySaver
from typing import cast, Any
@after_model(jump_to=["model", "__end__"])
def after_model_hook(state: AgentState) -> dict[str, Any]:
"""Check the last AI message for safety violations."""
last_message_content = cast(AIMessage, state["messages"][-1]).content.lower()
print(last_message_content)
unsafe_keywords = ["pineapple"]
if any(keyword in last_message_content for keyword in unsafe_keywords):
# Jump back to model to regenerate response
return {"jump_to": "model", "messages": [HumanMessage("Please regenerate your response, and don't talk about pineapples. You can talk about apples instead.")]}
return {"jump_to": "__end__"}
# Create agent with guardrails middleware
agent = create_agent(
model="openai:gpt-4o-mini",
middleware=[after_model_hook],
system_prompt="Keep your responses to one sentence please!"
).compile()
# Test with potentially unsafe input
result = agent.invoke(
{"messages": [HumanMessage("Tell me something about pineapples")]},
)
for msg in result["messages"]:
print(msg.pretty_print())
"""
================================ Human Message =================================
Tell me something about pineapples
None
================================== Ai Message ==================================
Pineapples are tropical fruits known for their sweet, tangy flavor and distinctive spiky exterior.
None
================================ Human Message =================================
Please regenerate your response, and don't talk about pineapples. You can talk about apples instead.
None
================================== Ai Message ==================================
Apples are popular fruits that come in various varieties, known for their crisp texture and sweetness, and are often used in cooking and baking.
None
"""
```
</details>
Mostly adding a descriptive frontmatter to workflow files. Also address
some formatting and outdated artifacts
No functional changes outside of
[d5457c3](d5457c39ee),
[90708a0](90708a0d99),
and
[338c82d](338c82d21e)
The file-based and title-based labeler workflows were conflicting,
causing the bot to add and remove identical labels in the same
operation. Hopefully this fixes
- Removes Codespell from deps, docs, and `Makefile`s
- Python version requirements in all `pyproject.toml` files now use the
`~=` (compatible release) specifier
- All dependency groups and main dependencies now use explicit lower and
upper bounds, reducing potential for breaking changes
We want state schema as the input schema to middleware nodes because the
conditional edges after these nodes need access to the full state.
Also, we just generally want all state passed to middleware nodes, so we
should be specifying this explicitly. If we don't, the state annotations
used by users in their node signatures are used (so they might be
missing fields).
# Changes
## Adds support for `DynamicSystemPromptMiddleware`
```py
from langchain.agents.middleware import DynamicSystemPromptMiddleware
from langgraph.runtime import Runtime
from typing_extensions import TypedDict
class Context(TypedDict):
user_name: str
def system_prompt(state: AgentState, runtime: Runtime[Context]) -> str:
user_name = runtime.context.get("user_name", "n/a")
return f"You are a helpful assistant. Always address the user by their name: {user_name}"
middleware = DynamicSystemPromptMiddleware(system_prompt)
```
## Adds support for `runtime` in middleware hooks
```py
class AgentMiddleware(Generic[StateT, ContextT]):
def modify_model_request(
self,
request: ModelRequest,
state: StateT,
runtime: Runtime[ContextT], # Optional runtime parameter
) -> ModelRequest:
# upgrade model if runtime.context.subscription is `top-tier` or whatever
```
## Adds support for omitting state attributes from input / output
schemas
```py
from typing import Annotated, NotRequired
from langchain.agents.middleware.types import PrivateStateAttr, OmitFromInput, OmitFromOutput
class CustomState(AgentState):
# Private field - not in input or output schemas
internal_counter: NotRequired[Annotated[int, PrivateStateAttr]]
# Input-only field - not in output schema
user_input: NotRequired[Annotated[str, OmitFromOutput]]
# Output-only field - not in input schema
computed_result: NotRequired[Annotated[str, OmitFromInput]]
```
## Additionally
* Removes filtering of state before passing into middleware hooks
Typing is not foolproof here, still need to figure out some of the
generics stuff w/ state and context schema extensions for middleware.
TODO:
* More docs for middleware, should hold off on this until other prios
like MCP and deepagents are met
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
## Summary
This PR fixes several bugs and improves the example code in
`BaseChatMessageHistory` docstring that would prevent it from working
correctly.
### Bugs Fixed
- **Critical bug**: Fixed `json.dump(messages, f)` →
`json.dump(serialized, f)` - was using wrong variable
- **NameError**: Fixed bare variable references to use
`self.storage_path` and `self.session_id`
- **Missing imports**: Added required imports (`json`, `os`, message
converters) to make example runnable
### Improvements
- Added missing type hints following project standards (`messages() ->
list[BaseMessage]`, `clear() -> None`)
- Added robust error handling with `FileNotFoundError` exception
handling
- Added directory creation with `os.makedirs(exist_ok=True)` to prevent
path errors
- Improved performance: `json.load(f)` instead of `json.loads(f.read())`
- Added explicit UTF-8 encoding to all file operations
- Updated stores.py to use modern union syntax (`int | None` vs
`Optional[int]`)
### Test Plan
- [x] Code passes linting (`ruff check`)
- [x] Example code now has all required imports and proper syntax
- [x] Fixed variable references prevent runtime errors
- [x] Follows project's type annotation standards
The example code in the docstring is now fully functional and follows
LangChain's coding standards.
---------
Co-authored-by: sadiqkhzn <sadiqkhzn@users.noreply.github.com>
- **Description:** Updated the dead/unreachable links to Docling from
the additional resources section of the langchain-docling docs
- **Issue:** Fixes langchain-ai/docs/issues/574
- **Dependencies:** None
# Main changes / new features
## Better support for parallel tool calls
1. Support for multiple tool calls requiring human input
2. Support for combination of tool calls requiring human input + those
that are auto-approved
3. Support structured output w/ tool calls requiring human input
4. Support structured output w/ standard tool calls
## Shortcut for allowed actions
Adds a shortcut where tool config can be specified as a `bool`, meaning
"all actions allowed"
```py
HumanInTheLoopMiddleware(tool_configs={"expensive_tool": True})
```
## A few design decisions here
* We only raise one interrupt w/ all `HumanInterrupt`s, currently we
won't be able to execute all tools until all of these are resolved. This
isn't super blocking bc we can't re-invoke the model until all tools
have finished execution. That being said, if you have a long running
auto-approved tool, this could slow things down.
## TODOs
* Ideally, we would rename `accept` -> `approve`
* Ideally, we would rename `respond` -> `reject`
* Docs update (@sydney-runkle to own)
* In another PR I'd like to refactor testing to have one file for each
prebuilt middleware :)
Fast follow to https://github.com/langchain-ai/langchain/pull/32962
which was deemed as too breaking
Adds documentation for the integration langchain-scraperapi, which
contains 3 tools using the ScraperAPI service.
The tools give AI agents the ability to
Scrape the web and return HTML/text/markdown
Perform Google search and return json output
Perform Amazon search and return json output
For reference, here is the official repo for langchain_scraperapi:
https://github.com/scraperapi/langchain-scraperapi
Replaced `input_message` parameter with a directly called tuple, e.g.
`{"messages": [("user", "What is my name?")]}`
Before, the memory function wasn't working with the agent, using the
format of the input_message parameter.
Specifically, on page [Build an
Agent#adding-in-memory](https://python.langchain.com/docs/tutorials/agents/#adding-in-memory)
In the previous code, the query "What's my name?" wasn't working, as the
agent could not recall memory correctly.
<img width="860" height="679" alt="image"
src="https://github.com/user-attachments/assets/dfbca21e-ffe9-4645-a810-3be7a46d81d5"
/>
This PR improves navigation in the summarization how-to section by
adding
cross-links from the single-call guide to the related map-reduce and
refine
guides. This mirrors the docs style guide’s emphasis on clear
cross-references
and should help readers discover the appropriate pattern for longer
texts.
- Source edited: docs/docs/how_to/summarize_stuff.ipynb
- Links added:
- /docs/how_to/summarize_map_reduce/
- /docs/how_to/summarize_refine/
Type: docs-only (no code changes)
Description:
Add a docstring to _load_map_reduce_chain in chains/summarize/ to
explain the purpose of the prompt argument and document function
parameters. This addresses an existing TODO in the codebase.
Issue:
N/A (documentation improvement only)
Dependencies:
None
**Description:**
Add a docstring to `_load_stuff_chain` in `chains/summarize/` to explain
the purpose of the `prompt` argument and document function parameters.
This addresses an existing TODO in the codebase.
**Issue:**
N/A (documentation improvement only)
**Dependencies:**
None
Bumps [CodSpeedHQ/action](https://github.com/codspeedhq/action) from 3
to 4.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/codspeedhq/action/releases">CodSpeedHQ/action's
releases</a>.</em></p>
<blockquote>
<h2>v4.0.0</h2>
<h2>💥 BREAKING</h2>
<p>It's now required to explicitly set the runner mode to
<code>instrumentation</code> or <code>walltime</code> using either:</p>
<ul>
<li>the <code>mode</code> argument</li>
<li>or the <code>CODSPEED_RUNNER_MODE</code> environment variable</li>
</ul>
<blockquote>
<p>[!TIP]
Before, this variable was automatically set to
<code>instrumentation</code> on every runner except for <a
href="https://codspeed.io/docs/instruments/walltime">CodSpeed macro
runners</a> where it was set to <code>walltime</code> by default.</p>
</blockquote>
<p>Find more details in <a
href="https://codspeed.io/docs/instruments">the instruments
documentation</a>.</p>
<h2>Details</h2>
<h3><!-- raw HTML omitted -->🚀 Features</h3>
<ul>
<li>Make perf profiling enabled by default by <a
href="https://github.com/GuillaumeLagrange"><code>@GuillaumeLagrange</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/110">#110</a></li>
<li>Make the runner mode argument required by <a
href="https://github.com/GuillaumeLagrange"><code>@GuillaumeLagrange</code></a></li>
<li>Use introspected node in walltime mode by <a
href="https://github.com/GuillaumeLagrange"><code>@GuillaumeLagrange</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/108">#108</a></li>
<li>Add instrumented go shell script by <a
href="https://github.com/not-matthias"><code>@not-matthias</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/102">#102</a></li>
</ul>
<h3><!-- raw HTML omitted -->🐛 Bug Fixes</h3>
<ul>
<li>Compute proper load bias by <a
href="https://github.com/not-matthias"><code>@not-matthias</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/107">#107</a></li>
<li>Increase timeout for first perf ping by <a
href="https://github.com/GuillaumeLagrange"><code>@GuillaumeLagrange</code></a></li>
<li>Prevent running with valgrind by <a
href="https://github.com/not-matthias"><code>@not-matthias</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/106">#106</a></li>
</ul>
<h3><!-- raw HTML omitted -->🏗️ Refactor</h3>
<ul>
<li>Change go-runner binary name by <a
href="https://github.com/not-matthias"><code>@not-matthias</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/111">#111</a></li>
</ul>
<p><strong>Full Runner Changelog</strong>: <a
href="https://github.com/CodSpeedHQ/runner/blob/main/CHANGELOG.md">https://github.com/CodSpeedHQ/runner/blob/main/CHANGELOG.md</a></p>
<h2>v3.8.1</h2>
<h2>What's Changed</h2>
<h3><!-- raw HTML omitted -->🐛 Bug Fixes</h3>
<ul>
<li>Don't show error when libpython is not found by <a
href="https://github.com/not-matthias"><code>@not-matthias</code></a></li>
</ul>
<h3><!-- raw HTML omitted -->🏗️ Refactor</h3>
<ul>
<li>Improve conditional compilation in
<code>get_pipe_open_options</code> by <a
href="https://github.com/art049"><code>@art049</code></a> in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/100">#100</a></li>
</ul>
<h3><!-- raw HTML omitted -->⚙️ Internals</h3>
<ul>
<li>Change log level to warn for venv_compat error by <a
href="https://github.com/not-matthias"><code>@not-matthias</code></a>
in <a
href="https://redirect.github.com/CodSpeedHQ/runner/pull/104">#104</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/CodSpeedHQ/action/compare/v3.8.0...v3.8.1">https://github.com/CodSpeedHQ/action/compare/v3.8.0...v3.8.1</a>
<strong>Full Runner Changelog</strong>: <a
href="https://github.com/CodSpeedHQ/runner/blob/main/CHANGELOG.md">https://github.com/CodSpeedHQ/runner/blob/main/CHANGELOG.md</a></p>
<h2>v3.8.0</h2>
<h2>What's Changed</h2>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="653fdc30e6"><code>653fdc3</code></a>
Release v4.0.1 🚀</li>
<li><a
href="4da7be1bda"><code>4da7be1</code></a>
chore: bump runner version to 4.0.1</li>
<li><a
href="172d6c5630"><code>172d6c5</code></a>
chore: make the comment about input validation more discrete</li>
<li><a
href="d15e1ce813"><code>d15e1ce</code></a>
chore: improve the release script</li>
<li><a
href="6eeb021fd0"><code>6eeb021</code></a>
Release v4.0.0 🚀</li>
<li><a
href="74312dabbe"><code>74312da</code></a>
chore: improve the release script</li>
<li><a
href="8a17a350a8"><code>8a17a35</code></a>
ci: add modes to the matrix</li>
<li><a
href="8e3f02a649"><code>8e3f02a</code></a>
feat: make the mode argument required</li>
<li><a
href="97c7a6f5fc"><code>97c7a6f</code></a>
chore: bump runner version to 4.0.0</li>
<li><a
href="8a4cadd026"><code>8a4cadd</code></a>
chore: point the changelog to the runner</li>
<li>See full diff in <a
href="https://github.com/codspeedhq/action/compare/v3...v4">compare
view</a></li>
</ul>
</details>
<br />
[](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 merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@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)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
## Description
This PR adds documentation for the new ZeusDB vector store integration
with LangChain.
## Motivation
ZeusDB is a high-performance vector database (Python/Rust backend)
designed for AI applications that need fast similarity search and
real-time vector ops. This integration brings ZeusDB's capabilities to
the LangChain ecosystem, giving developers another production-oriented
option for vector storage and retrieval.
**Key Features:**
- **User-Friendly Python API**: Intuitive interface that integrates
seamlessly with Python ML workflows
- **High Performance**: Powered by a robust Rust backend for
lightning-fast vector operations
- **Enterprise Logging**: Comprehensive logging capabilities for
monitoring and debugging production systems
- **Advanced Features**: Includes product quantization and persistence
capabilities
- **AI-Optimized**: Purpose-built for modern AI applications and RAG
pipelines
## Changes
- Added provider documentation:
`docs/docs/integrations/providers/zeusdb.mdx` (installation, setup).
- Added vector store documentation:
`docs/docs/integrations/vectorstores/zeusdb.ipynb` (quickstart for
creating/querying a ZeusDBVectorStore).
- Registered langchain-zeusdb in `libs/packages.yml` for discovery.
## Target users
- AI/ML engineers building RAG pipelines
- Data scientists working with large document collections
- Developers needing high-throughput vector search
- Teams requiring near real-time vector operations
## Testing
- Followed LangChain's "How to add standard tests to an integration"
guidance.
- Code passes format, lint, and test checks locally.
- Tested with LangChain Core 0.3.74
- Works with Python 3.10 to 3.13
## Package Information
**PyPI:** https://pypi.org/project/langchain-zeusdb
**Github:** https://github.com/ZeusDB/langchain-zeusdb
## Summary
- Add comprehensive type hints to the MyInMemoryStore example code in
BaseStore docstring
- Improve documentation quality and educational value for developers
- Align with LangChain's coding standards requiring type hints on all
Python code
## Changes Made
- Added return type annotations to all methods (__init__, mget, mset,
mdelete, yield_keys)
- Added parameter type annotations using proper generic types (Sequence,
Iterator)
- Added instance variable type annotation for the store attribute
- Used modern Python union syntax (str | None) for optional types
## Test Plan
- Verified Python syntax validity with ast.parse()
- No functional changes to actual code, only documentation improvements
- Example code now follows best practices and coding standards
This change improves the educational value of the example code and
ensures consistency with LangChain's requirement that "All Python code
MUST include type hints and return types" as specified in the
development guidelines.
---------
Co-authored-by: sadiqkhzn <sadiqkhzn@users.noreply.github.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
**Description:**
Introduces documentation notebooks for AI/ML API integration covering
the following use cases:
- Chat models (`ChatAimlapi`)
- Text completion models (`AimlapiLLM`)
- Provider usage examples
- Text embedding models (`AimlapiEmbeddings`)
Additionally, adds the `langchain-aimlapi` package entry to
`libs/packages.yml` for package management.
This PR aims to provide a comprehensive starting point for developers
integrating AI/ML API models with LangChain via the new
`langchain-aimlapi` package.
**Issue:** N/A
**Dependencies:** None
**Twitter handle:** @aimlapi
---
### **To-Do Before Submitting PR:**
* [x] Run `make format`
* [x] Run `make lint`
* [x] Confirm all documentation notebooks are in
`docs/docs/integrations/`
* [x] Double-check `libs/packages.yml` has the correct repo path
* [x] Confirm no `pyproject.toml` modifications were made unnecessarily
Co-authored-by: Mason Daugherty <mason@langchain.dev>
**Description:**
This PR updates the free searches per month from **100** to **250** and
renames SerpAPI to [SerpApi](https://serpapi.com/) to prevent confusion.
Add import API keys and enhance usage instructions in the Jupyter
notebook
**Issue:** N/A
**Dependencies:** N/A
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. **We will not consider
a PR unless these three are passing in CI.** See [contribution
guidelines](https://python.langchain.com/docs/contributing/) for more.
