langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

Multi-agent supervisor #406

New Issue
Closed
opened 2026-02-20 17:39:58 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:39:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @jason571 on GitHub (Jan 18, 2025).

Checked other resources

  • This is a bug, not a usage question. For questions, please use GitHub Discussions.
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

I add agent, run shell 
class Router(TypedDict):
    """Worker to route to next. If no workers needed, route to FINISH."""
    next: Literal["researcher", "coder", "shell", "FINISH"]

    def supervisor_node(self, state: State) -> Command[Literal["researcher", "coder", "shell", "__end__"]]:
        messages = [
                       {"role": "system", "content": self.system_prompt},
                   ] + state["messages"]
        response = self.llm.with_structured_output(Router).invoke(messages)
        goto = response["next"]
        if goto == "FINISH":
            goto = END

        mylogging.vip(response)
        return Command(goto=goto, update={"next": goto})

Question: check  Memory Usage
TASK can't FINISH, it keeps executing the shell, I've checked response = self.llm.invoke(messages)
response is FINISH. 
but self.llm.with_structured_output(Router).invoke(messages) response  is {'next': 'shell'}, this is bug.


Agent: [2025-01-18 14:04:30,491]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:30,498]-VIP-[supervisorProcess.py:97]: shell->supervisor
Starting tool: shell_tool with inputs: {'command': 'free -m'}
[2025-01-18 14:04:31,890]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1075       31085           3         298       30988
Swap:           8192           0        8192


Done tool: shell_tool
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1075 MB
- Free memory: 31085 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30988 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:35,914]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:35,940]-VIP-[supervisorProcess.py:97]: shell->supervisor
Starting tool: shell_tool with inputs: {'command': 'free -m'}
[2025-01-18 14:04:37,599]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1077       31083           3         298       30986
Swap:           8192           0        8192


Done tool: shell_tool
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1077 MB
- Free memory: 31083 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30986 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:40,450]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:40,504]-VIP-[supervisorProcess.py:97]: shell->supervisor
[2025-01-18 14:04:41,771]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1079       31081           3         298       30985
Swap:           8192           0        8192


Starting tool: shell_tool with inputs: {'command': 'free -m'}
Done tool: shell_tool
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1079 MB
- Free memory: 31081 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30985 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:44,322]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:44,500]-VIP-[supervisorProcess.py:97]: shell->supervisor
Starting tool: shell_tool with inputs: {'command': 'free -m'}
[2025-01-18 14:04:45,320]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1079       31081           3         298       30984
Swap:           8192           0        8192


Done tool: shell_tool
[2025-01-18 14:04:45,845]-INFO-[_base_client.py:1087]: Retrying request to /chat/completions in 0.483649 seconds
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1079 MB
- Free memory: 31081 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30984 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:49,860]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:50,079]-VIP-[supervisorProcess.py:97]: shell->supervisor
[2025-01-18 14:04:50,978]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1080       31080           3         298       30983
Swap:           8192           0        8192

Error Message and Stack Trace (if applicable)

[2025-01-18 14:04:35,940]-VIP-[supervisorProcess.py:97]: shell->supervisor
Starting tool: shell_tool with inputs: {'command': 'free -m'}
[2025-01-18 14:04:37,599]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1077       31083           3         298       30986
Swap:           8192           0        8192


Done tool: shell_tool
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1077 MB
- Free memory: 31083 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30986 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:40,450]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:40,504]-VIP-[supervisorProcess.py:97]: shell->supervisor
[2025-01-18 14:04:41,771]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1079       31081           3         298       30985
Swap:           8192           0        8192


Starting tool: shell_tool with inputs: {'command': 'free -m'}
Done tool: shell_tool
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1079 MB
- Free memory: 31081 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30985 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:44,322]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:44,500]-VIP-[supervisorProcess.py:97]: shell->supervisor
Starting tool: shell_tool with inputs: {'command': 'free -m'}
[2025-01-18 14:04:45,320]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1079       31081           3         298       30984
Swap:           8192           0        8192


Done tool: shell_tool
[2025-01-18 14:04:45,845]-INFO-[_base_client.py:1087]: Retrying request to /chat/completions in 0.483649 seconds
The memory usage is as follows:
- Total memory: 32064 MB
- Used memory: 1079 MB
- Free memory: 31081 MB
- Shared memory: 3 MB
- Buffer/cache memory: 298 MB
- Available memory: 30984 MB

The swap memory usage is as follows:
- Total swap: 8192 MB
- Used swap: 0 MB
- Free swap: 8192 MB[2025-01-18 14:04:49,860]-VIP-[agentSupervisor.py:41]: {'next': 'shell'}
[2025-01-18 14:04:50,079]-VIP-[supervisorProcess.py:97]: shell->supervisor
[2025-01-18 14:04:50,978]-INFO-[tools.py:24]: executing shell output:               total        used        free      shared  buff/cache   available
Mem:           32064        1080       31080           3         298       30983
Swap:           8192           0        8192

Description

Question: check Memory Usage
TASK can't FINISH, it keeps executing the shell, I've checked response = self.llm.invoke(messages)
response is FINISH.

System Info

I add agent, run shell
class Router(TypedDict):
"""Worker to route to next. If no workers needed, route to FINISH."""
next: Literal["researcher", "coder", "shell", "FINISH"]

def supervisor_node(self, state: State) -> Command[Literal["researcher", "coder", "shell", "__end__"]]:
    messages = [
                   {"role": "system", "content": self.system_prompt},
               ] + state["messages"]
    response = self.llm.with_structured_output(Router).invoke(messages)
    goto = response["next"]
    if goto == "FINISH":
        goto = END

    mylogging.vip(response)
    return Command(goto=goto, update={"next": goto})

Question: check Memory Usage
TASK can't FINISH, it keeps executing the shell, I've checked response = self.llm.invoke(messages)
response is FINISH.
but self.llm.with_structured_output(Router).invoke(messages) response is {'next': 'shell'}, this is bug.

Originally created by @jason571 on GitHub (Jan 18, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use GitHub Discussions. - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python I add agent, run shell class Router(TypedDict): """Worker to route to next. If no workers needed, route to FINISH.""" next: Literal["researcher", "coder", "shell", "FINISH"] def supervisor_node(self, state: State) -> Command[Literal["researcher", "coder", "shell", "__end__"]]: messages = [ {"role": "system", "content": self.system_prompt}, ] + state["messages"] response = self.llm.with_structured_output(Router).invoke(messages) goto = response["next"] if goto == "FINISH": goto = END mylogging.vip(response) return Command(goto=goto, update={"next": goto}) Question: check Memory Usage TASK can't FINISH, it keeps executing the shell, I've checked response = self.llm.invoke(messages) response is FINISH. but self.llm.with_structured_output(Router).invoke(messages) response is {'next': 'shell'}, this is bug. Agent: [2025-01-18 14:04:30,491]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:30,498]-VIP-[supervisorProcess.py:97]: shell->supervisor Starting tool: shell_tool with inputs: {'command': 'free -m'} [2025-01-18 14:04:31,890]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1075 31085 3 298 30988 Swap: 8192 0 8192 Done tool: shell_tool The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1075 MB - Free memory: 31085 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30988 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:35,914]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:35,940]-VIP-[supervisorProcess.py:97]: shell->supervisor Starting tool: shell_tool with inputs: {'command': 'free -m'} [2025-01-18 14:04:37,599]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1077 31083 3 298 30986 Swap: 8192 0 8192 Done tool: shell_tool The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1077 MB - Free memory: 31083 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30986 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:40,450]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:40,504]-VIP-[supervisorProcess.py:97]: shell->supervisor [2025-01-18 14:04:41,771]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1079 31081 3 298 30985 Swap: 8192 0 8192 Starting tool: shell_tool with inputs: {'command': 'free -m'} Done tool: shell_tool The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1079 MB - Free memory: 31081 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30985 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:44,322]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:44,500]-VIP-[supervisorProcess.py:97]: shell->supervisor Starting tool: shell_tool with inputs: {'command': 'free -m'} [2025-01-18 14:04:45,320]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1079 31081 3 298 30984 Swap: 8192 0 8192 Done tool: shell_tool [2025-01-18 14:04:45,845]-INFO-[_base_client.py:1087]: Retrying request to /chat/completions in 0.483649 seconds The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1079 MB - Free memory: 31081 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30984 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:49,860]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:50,079]-VIP-[supervisorProcess.py:97]: shell->supervisor [2025-01-18 14:04:50,978]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1080 31080 3 298 30983 Swap: 8192 0 8192 ``` ### Error Message and Stack Trace (if applicable) ```shell [2025-01-18 14:04:35,940]-VIP-[supervisorProcess.py:97]: shell->supervisor Starting tool: shell_tool with inputs: {'command': 'free -m'} [2025-01-18 14:04:37,599]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1077 31083 3 298 30986 Swap: 8192 0 8192 Done tool: shell_tool The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1077 MB - Free memory: 31083 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30986 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:40,450]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:40,504]-VIP-[supervisorProcess.py:97]: shell->supervisor [2025-01-18 14:04:41,771]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1079 31081 3 298 30985 Swap: 8192 0 8192 Starting tool: shell_tool with inputs: {'command': 'free -m'} Done tool: shell_tool The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1079 MB - Free memory: 31081 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30985 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:44,322]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:44,500]-VIP-[supervisorProcess.py:97]: shell->supervisor Starting tool: shell_tool with inputs: {'command': 'free -m'} [2025-01-18 14:04:45,320]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1079 31081 3 298 30984 Swap: 8192 0 8192 Done tool: shell_tool [2025-01-18 14:04:45,845]-INFO-[_base_client.py:1087]: Retrying request to /chat/completions in 0.483649 seconds The memory usage is as follows: - Total memory: 32064 MB - Used memory: 1079 MB - Free memory: 31081 MB - Shared memory: 3 MB - Buffer/cache memory: 298 MB - Available memory: 30984 MB The swap memory usage is as follows: - Total swap: 8192 MB - Used swap: 0 MB - Free swap: 8192 MB[2025-01-18 14:04:49,860]-VIP-[agentSupervisor.py:41]: {'next': 'shell'} [2025-01-18 14:04:50,079]-VIP-[supervisorProcess.py:97]: shell->supervisor [2025-01-18 14:04:50,978]-INFO-[tools.py:24]: executing shell output: total used free shared buff/cache available Mem: 32064 1080 31080 3 298 30983 Swap: 8192 0 8192 ``` ### Description Question: check Memory Usage TASK can't FINISH, it keeps executing the shell, I've checked response = self.llm.invoke(messages) response is FINISH. ### System Info I add agent, run shell class Router(TypedDict): """Worker to route to next. If no workers needed, route to FINISH.""" next: Literal["researcher", "coder", "shell", "FINISH"] def supervisor_node(self, state: State) -> Command[Literal["researcher", "coder", "shell", "__end__"]]: messages = [ {"role": "system", "content": self.system_prompt}, ] + state["messages"] response = self.llm.with_structured_output(Router).invoke(messages) goto = response["next"] if goto == "FINISH": goto = END mylogging.vip(response) return Command(goto=goto, update={"next": goto}) Question: check Memory Usage TASK can't FINISH, it keeps executing the shell, I've checked response = self.llm.invoke(messages) response is FINISH. but self.llm.with_structured_output(Router).invoke(messages) response is {'next': 'shell'}, this is bug.
yindo added the invalid label 2026-02-20 17:39:58 -05:00
yindo closed this issue 2026-02-20 17:39:58 -05:00
yindo commented 2026-02-20 17:39:59 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Jan 20, 2025):

Please provide https://stackoverflow.com/help/minimal-reproducible-example

@vbarda commented on GitHub (Jan 20, 2025): Please provide https://stackoverflow.com/help/minimal-reproducible-example
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label invalid
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/langgraph#406
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?