langchain-ai/deepagents
1
0
Fork 0
mirror of https://github.com/langchain-ai/deepagents.git synced 2026-07-22 17:55:31 -04:00
Code Issues 169 Packages Projects Releases 16 Wiki Activity

Agent name on Middleware #105

New Issue
Closed
opened 2026-02-16 08:19:53 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 08:19:53 -05:00
Owner
Copy Link
Copy Source

Originally created by @oscmejia on GitHub (Nov 4, 2025).

I s it possible to get each agent name of a middleware?
I'm setting name for each agent, and in the middleware using before_model and after_model, but only reciving information like the models name and token information.

any help will be apreciated.

Originally created by @oscmejia on GitHub (Nov 4, 2025). I s it possible to get each agent name of a middleware? I'm setting `name` for each agent, and in the middleware using `before_model` and `after_model`, but only reciving information like the models name and token information. any help will be apreciated.
yindo closed this issue 2026-02-16 08:19:53 -05:00
yindo commented 2026-02-16 08:19:54 -05:00
Author
Owner
Copy Link
Copy Source

@flingjie commented on GitHub (Nov 5, 2025):

What do you mean by “setting a name for each agent”?
If you’re referring to the sub-agent name, for example:

critique_sub_agent = {
    "name": "critique-agent",
    "description": "xxxx",
    "system_prompt": sub_critique_prompt,
}

You can actually see this name in the tool_calls field of the state during the before_model hook.

class LoggingMiddleware(AgentMiddleware):
    def before_model(self, state: AgentState, runtime: Runtime) -> dict[str, Any] | None:
        print(f"About to call model with {state}")
        return None
Image
@flingjie commented on GitHub (Nov 5, 2025): What do you mean by “setting a name for each agent”? If you’re referring to the **sub-agent name**, for example: ```python critique_sub_agent = { "name": "critique-agent", "description": "xxxx", "system_prompt": sub_critique_prompt, } ``` You can actually see this name in the `tool_calls` field of the `state` during the `before_model` hook. ``` class LoggingMiddleware(AgentMiddleware): def before_model(self, state: AgentState, runtime: Runtime) -> dict[str, Any] | None: print(f"About to call model with {state}") return None ``` <img width="1285" height="124" alt="Image" src="https://github.com/user-attachments/assets/489cea96-c360-4e23-9790-7942a0eb0bd2" />
yindo commented 2026-02-16 08:19:54 -05:00
Author
Owner
Copy Link
Copy Source

@oscmejia commented on GitHub (Nov 5, 2025):

thanks @flingjie
What I'm trying to do is create a middleware where wrap_model_call gets the name of the agent (main or nay subagent)

@oscmejia commented on GitHub (Nov 5, 2025): thanks @flingjie What I'm trying to do is create a middleware where `wrap_model_call` gets the name of the agent (main or nay subagent)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
MCP
backends
bug
cli
config
customization
deepagents
documentation
external
feature
fix
good first issue
help wanted
integration
internal
invalid
middleware
model
needs investigation
p0
p1
p2
p3
performance
pull-request
Mirrored from GitHub Pull Request
 question
sdk
subagents
unable to reproduce
windows
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/deepagents#105
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?