Skip to content

fix(langchain): removing more v0 content #861

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Oct 14, 2025
Merged

fix(langchain): removing more v0 content #861

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
b0dcd02
initial fixes
sydney-runkle Oct 13, 2025
8837d78
improving more pages
sydney-runkle Oct 13, 2025
b9eebdb
nit
sydney-runkle Oct 13, 2025
113761d
rewrite section
sydney-runkle Oct 13, 2025
95070ec
patterns
sydney-runkle Oct 13, 2025
c1e302a
some improvements
sydney-runkle Oct 13, 2025
7c3cb8a
little
sydney-runkle Oct 13, 2025
ffda58d
output snippet woo
sydney-runkle Oct 13, 2025
5315e5d
mermaids
sydney-runkle Oct 13, 2025
473a07d
update size
sydney-runkle Oct 14, 2025
e063d08
Update src/oss/langchain/middleware.mdx
sydney-runkle Oct 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
237 changes: 26 additions & 211 deletions src/oss/langchain/agents.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,7 +204,7 @@ const agent = createAgent({
:::

<Tip>
For model configuration details, see [Models](/oss/langchain/models).
For model configuration details, see [Models](/oss/langchain/models). For dynamic model selection patterns, see [Dynamic model in middleware](/oss/langchain/middleware#dynamic-model).
</Tip>

### Tools
Expand Down Expand Up @@ -519,7 +519,7 @@ const result = await agent.invoke(
For more details on message types and formatting, see [Messages](/oss/langchain/messages). For comprehensive middleware documentation, see [Middleware](/oss/langchain/middleware).
</Tip>

## Advanced configuration
## Advanced concepts

### Structured output

Expand Down Expand Up @@ -677,215 +677,6 @@ const CustomAgentState = createAgent({
To learn more about memory, see [Memory](/oss/concepts/memory). For information on implementing long-term memory that persists across sessions, see [Long-term memory](/oss/langchain/long-term-memory).
</Tip>

### Before model hook

Pre-model hook is middleware that processes state before the model is called. Use cases include message trimming, summarization, and context injection.

```mermaid
%%{
init: {
"fontFamily": "monospace",
"flowchart": {
"curve": "basis"
},
"themeVariables": {"edgeLabelBackground": "transparent"}
}
}%%
graph TD
S(["\_\_start\_\_"])
PRE(before_model)
MODEL(model)
TOOLS(tools)
END(["\_\_end\_\_"])

S --> PRE
PRE --> MODEL
MODEL -.-> TOOLS
MODEL -.-> END
TOOLS --> PRE

classDef blueHighlight fill:#0a1c25,stroke:#0a455f,color:#bae6fd;
class S blueHighlight;
class END blueHighlight;
```

:::python

Use the `@before_model` decorator to create middleware that runs before the model is called:

```python wrap
from langchain.messages import RemoveMessage
from langgraph.graph.message import REMOVE_ALL_MESSAGES
from langchain.agents import create_agent, AgentState
from langchain.agents.middleware import before_model
from langgraph.runtime import Runtime

@before_model
def trim_messages(state: AgentState, runtime: Runtime) -> dict[str, Any] | None:
"""Keep only the last few messages to fit context window."""
messages = state["messages"]

if len(messages) <= 3:
return None # No changes needed

first_msg = messages[0]
recent_messages = messages[-3:] if len(messages) % 2 == 0 else messages[-4:]
new_messages = [first_msg] + recent_messages

return {
"messages": [
RemoveMessage(id=REMOVE_ALL_MESSAGES),
*new_messages
]
}

agent = create_agent(
model,
tools=tools,
middleware=[trim_messages]
)
```

<Info>
When returning `messages` from `before_model` middleware, you should **overwrite the `messages` key** by including `RemoveMessage(id=REMOVE_ALL_MESSAGES)` first, followed by your new messages.
</Info>

:::
:::js
```ts wrap
import { createAgent, type AgentState } from "langchain";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";
import { RemoveMessage } from "@langchain/core/messages";

const trimMessages = (state: AgentState) => {
const messages = state.messages;

if (messages.length <= 3) {
return { messages };
}

const firstMsg = messages[0];
const recentMessages = messages.length % 2 === 0
? messages.slice(-3)
: messages.slice(-4);

const newMessages = [firstMsg, ...recentMessages];

return {
messages: [
new RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
...newMessages
]
};
};

const agent = createAgent({
model: "openai:gpt-4o",
tools,
preModelHook: trimMessages,
});
```
:::

### After model hook

After model hook is middleware that processes the model's response before tool execution. Use cases include validation, guardrails, or other post-processing.

```mermaid
%%{
init: {
"fontFamily": "monospace",
"flowchart": {
"curve": "basis"
},
"themeVariables": {"edgeLabelBackground": "transparent"}
}
}%%
graph TD
S(["\_\_start\_\_"])
MODEL(model)
POST(after_model)
TOOLS(tools)
END(["\_\_end\_\_"])

S --> MODEL
MODEL --> POST
POST -.-> END
POST -.-> TOOLS
TOOLS --> MODEL

classDef blueHighlight fill:#0a1c25,stroke:#0a455f,color:#bae6fd;
class S blueHighlight;
class END blueHighlight;
class POST greenHighlight;
```

:::python

Use the `@after_model` decorator to create middleware that runs after the model is called:

```python wrap
from typing import Any
from langchain.messages import AIMessage, RemoveMessage
from langgraph.graph.message import REMOVE_ALL_MESSAGES
from langchain.agents import create_agent, AgentState
from langchain.agents.middleware import after_model
from langgraph.runtime import Runtime

@after_model
def validate_response(state: AgentState, runtime: Runtime) -> dict[str, Any] | None:
"""Check model response for policy violations."""
messages = state["messages"]
last_message = messages[-1]

if "confidential" in last_message.content.lower():
return {
"messages": [
RemoveMessage(id=REMOVE_ALL_MESSAGES),
*messages[:-1],
AIMessage(content="I cannot share confidential information.")
]
}

return None # No changes needed

agent = create_agent(
model,
tools=tools,
middleware=[validate_response]
)
```

:::
:::js
```ts wrap
import { createAgent, type AgentState, AIMessage, RemoveMessage } from "langchain";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";

const validateResponse = (state: AgentState) => {
const messages = state.messages;
const lastMessage = messages.at(-1)?.text;

if (lastMessage?.toLowerCase().includes("confidential")) {
return {
messages: [
new RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
...state.messages.slice(0, -1),
new AIMessage("I cannot share confidential information."),
],
};
}
return {};
};

const agent = createAgent({
model: "openai:gpt-4o",
tools,
postModelHook: validateResponse,
});
```
:::

### Streaming

We've seen how the agent can be called with `.invoke` to get a final response. If the agent executes multiple steps, this may take a while. To show intermediate progress, we can stream back messages as they occur.
Expand Down Expand Up @@ -931,3 +722,27 @@ for await (const chunk of stream) {
<Tip>
For more details on streaming, see [Streaming](/oss/langchain/streaming).
</Tip>

### Middleware
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can add specific code examples here if we want, but I think middleware section makes more sense


[Middleware](/oss/langchain/middleware) provides powerful extensibility for customizing agent behavior at different stages of execution. You can use middleware to:

- Process state before the model is called (e.g., message trimming, context injection)
- Modify or validate the model's response (e.g., guardrails, content filtering)
- Handle tool execution errors with custom logic
- Implement dynamic model selection based on state or context
- Add custom logging, monitoring, or analytics

Middleware integrates seamlessly into the agent's execution graph, allowing you to intercept and modify data flow at key points without changing the core agent logic.

:::python
<Tip>
For comprehensive middleware documentation including decorators like `@before_model`, `@after_model`, and `@wrap_tool_call`, see [Middleware](/oss/langchain/middleware).
</Tip>
:::

:::js
<Tip>
For comprehensive middleware documentation including hooks like `beforeModel`, `afterModel`, and `wrapToolCall`, see [Middleware](/oss/langchain/middleware).
</Tip>
:::
Loading