langchain-ai/langserve
1
0
Fork 0
mirror of https://github.com/langchain-ai/langserve.git synced 2026-07-18 10:54:29 -04:00
Code Issues 136 Packages Projects Releases 10 Wiki Activity

Bug: AgentExecutor configurable does not propagate configuration from agent. #86

New Issue
Open
opened 2026-02-16 00:18:42 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 00:18:42 -05:00
Owner
Copy Link
Copy Source

Originally created by @eyurtsev on GitHub (Jan 5, 2024).

Originally assigned to: @eyurtsev on GitHub.

Users reasonably expect that when an agent is configurable, then the configuration information is properly propagated via the Agent Executor. However, this is not the case at the moment.

Bug is shown here: https://github.com/langchain-ai/langserve/pull/376

Needs to be fixed in langchain.

Original issue here: https://github.com/langchain-ai/langserve/issues/314

Originally created by @eyurtsev on GitHub (Jan 5, 2024). Originally assigned to: @eyurtsev on GitHub. Users reasonably expect that when an agent is configurable, then the configuration information is properly propagated via the Agent Executor. However, this is not the case at the moment. Bug is shown here: https://github.com/langchain-ai/langserve/pull/376 Needs to be fixed in langchain. Original issue here: https://github.com/langchain-ai/langserve/issues/314
yindo added the bugconfirmed labels 2026-02-16 00:18:42 -05:00
yindo commented 2026-02-16 00:18:43 -05:00
Author
Owner
Copy Link
Copy Source

@Sinnaeve commented on GitHub (Jun 6, 2024):

Will this be fixed ? There is no new activity so I'm not sure if an alternative exist for configurable_fields with agent.

Currently using langchain.version='0.2.1',
I basically want to configure the prompt at runtime so I can update the promps uses by the model without re-deploying the app.
Concretely during per_req_config, I get the prompt template from an api (with cache) and use a configurable field to pass it to the agent.
It works with a chain like that:

prompt = ChatPromptTemplate.from_messages(messages).configurable_fields(
        messages=ConfigurableField(
            id="prompt_messages",
            name="prompt messages",
        )
    )
chain= prompt | llm
async def per_req_config_modifier(config):
    messages = get_prompt_from_api(prompt_name="chain")
    config['configurable']['prompt_messages'] = messages
    return config
add_routes(app, chain, path="/chain", disabled_endpoints=["playground"],
           per_req_config_modifier=per_req_config_modifier)

But i doesn't work with an agent

with an agent created with:

prompt = ChatPromptTemplate.from_messages(messages).configurable_fields(
        messages=ConfigurableField(
            id="prompt_messages",
            name="prompt messages",
        )
    )
agent = create_sql_agent(llm2,
                                db=None,
                                toolkit=toolkit,
                                agent_type="openai-tools",
                                extra_tools=[another_tool], # in addition to tools from db
                                max_iterations=15,
                                agent_executor_kwargs={'handle_parsing_errors':True,
                                                        },
                                prompt = prompt,
                                verbose=True)

it doesn't work.

the solution proposed in https://github.com/langchain-ai/langserve/blob/main/examples/configurable_agent_executor/server.py doesn't seems to work either for this.

Is there an alternative way to do this I didn't see ?, or maybe agent aren't relevant now and have equivalent in langgraph that works with config fields ?

I could make it work in a notebook, but the change I needed to make were quite complicated:

There is a first issue that is the prompt.partial called in create_sql_agent break the configurable field.
an example of .partial calls is:

if "dialect" in prompt.input_variables:
            prompt = prompt.partial(dialect=toolkit.dialect)

This first issue is easy to fix I just modify create_sql_agent to do after the part where it does .partial calls

prompt = prompt.configurable_fields(
        messages=ConfigurableField(
            id="prompt_messages",
            name="prompt messages",
        )
    )

But then there is a second issue, which is that AgentExecutor and RunnableMultiActionAgent pass the callbacks field of the config but not the configurable field when making the chain calls.

For example if we do

async for chunk in agent.astream(input={"input":"an arbitrary question"}, config={"configurable":{'prompt_messages':new_messages}})
    print(chunk)
  • agent iterator calls astream
  • AgentExecutor.astream create an AgentExecutorIterator object passing field from the config like callbacks, metadata... but not configurable. Then it iter through AgentExecutorIterator
  • so AgentExecutorIterator.__aiter__ is called which will call self.agent_executor._aiter_next_step again without the configurable field that it doesn't have.
  • then AgentExecutor._aiter_next_step is called which calls self.agent.aplan again without the config even so it pass the callbacks
  • then RunnableMultiActionAgent.aplan is called, which calls self.runnable.astream here runnable.astream can take a config field but only config={"callbacks": callbacks} is given. it would work by giving {"callbacks": callbacks, "configurable":configurable} but we didn't pass the configurable field.

So this second issue of configurable field not passed is more problematic to me. I can patched all those function to pass configurable field with minimal code but it seems complicated to maintain as they will probably change in te future again.
And I have to patch many functions. For the agent.astream endpoint here I have to patch:

  • AgentExecutor.astream
  • AgentExecutorIterator.__aiter__
  • AgentExecutor._aiter_next_step
  • RunnableMultiActionAgent.aplan

but then for non async version I need to change:

  • AgentExecutor.stream
  • AgentExecutorIterator.__iter__
  • AgentExecutor._iter_next_step
  • RunnableMultiActionAgent.plan

and for invoke I have to additionally change:

  • AgentExecutor.invoke
  • AgentExecutor._calls
    (+ async versions for ainvoke)
@Sinnaeve commented on GitHub (Jun 6, 2024): Will this be fixed ? There is no new activity so I'm not sure if an alternative exist for configurable_fields with agent. Currently using langchain.__version__='0.2.1', I basically want to configure the prompt at runtime so I can update the promps uses by the model without re-deploying the app. Concretely during per_req_config, I get the prompt template from an api (with cache) and use a configurable field to pass it to the agent. It works with a chain like that: ```` prompt = ChatPromptTemplate.from_messages(messages).configurable_fields( messages=ConfigurableField( id="prompt_messages", name="prompt messages", ) ) chain= prompt | llm async def per_req_config_modifier(config): messages = get_prompt_from_api(prompt_name="chain") config['configurable']['prompt_messages'] = messages return config add_routes(app, chain, path="/chain", disabled_endpoints=["playground"], per_req_config_modifier=per_req_config_modifier) ```` But i doesn't work with an agent with an agent created with: ```` prompt = ChatPromptTemplate.from_messages(messages).configurable_fields( messages=ConfigurableField( id="prompt_messages", name="prompt messages", ) ) agent = create_sql_agent(llm2, db=None, toolkit=toolkit, agent_type="openai-tools", extra_tools=[another_tool], # in addition to tools from db max_iterations=15, agent_executor_kwargs={'handle_parsing_errors':True, }, prompt = prompt, verbose=True) ```` it doesn't work. the solution proposed in https://github.com/langchain-ai/langserve/blob/main/examples/configurable_agent_executor/server.py doesn't seems to work either for this. **Is there an alternative way to do this I didn't see ?, or maybe agent aren't relevant now and have equivalent in langgraph that works with config fields ?** ______ I could make it work in a notebook, but the change I needed to make were quite complicated: There is a first issue that is the prompt.partial called in create_sql_agent break the configurable field. an example of .partial calls is: ```` if "dialect" in prompt.input_variables: prompt = prompt.partial(dialect=toolkit.dialect) ```` This first issue is easy to fix I just modify create_sql_agent to do after the part where it does .partial calls ```` prompt = prompt.configurable_fields( messages=ConfigurableField( id="prompt_messages", name="prompt messages", ) ) ```` But then there is a second issue, which is that AgentExecutor and RunnableMultiActionAgent pass the callbacks field of the config but not the configurable field when making the chain calls. For example if we do ```` async for chunk in agent.astream(input={"input":"an arbitrary question"}, config={"configurable":{'prompt_messages':new_messages}}) print(chunk) ```` - agent iterator calls ``astream`` - AgentExecutor.astream create an ``AgentExecutorIterator`` object passing field from the config like callbacks, metadata... but not configurable. Then it iter through ``AgentExecutorIterator`` - so ``AgentExecutorIterator.__aiter__`` is called which will call ``self.agent_executor._aiter_next_step`` again without the configurable field that it doesn't have. - then ``AgentExecutor._aiter_next_step`` is called which calls ``self.agent.aplan`` again without the config even so it pass the callbacks - then ``RunnableMultiActionAgent.aplan`` is called, which calls ``self.runnable.astream`` here ``runnable.astream`` can take a config field but only ``config={"callbacks": callbacks}`` is given. it would work by giving ``{"callbacks": callbacks, "configurable":configurable}`` but we didn't pass the configurable field. So this second issue of configurable field not passed is more problematic to me. I can patched all those function to pass configurable field with minimal code but it seems complicated to maintain as they will probably change in te future again. And I have to patch many functions. For the agent.astream endpoint here I have to patch: - ``AgentExecutor.astream`` - ``AgentExecutorIterator.__aiter__`` - ``AgentExecutor._aiter_next_step`` - ``RunnableMultiActionAgent.aplan`` but then for non async version I need to change: - ``AgentExecutor.stream`` - ``AgentExecutorIterator.__iter__`` - ``AgentExecutor._iter_next_step`` - ``RunnableMultiActionAgent.plan`` and for invoke I have to additionally change: - ``AgentExecutor.invoke`` - ``AgentExecutor._calls`` (+ async versions for ainvoke)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
duplicate
enhancement
help wanted
in-progress
investigate
not langserve
playground
pull-request
Mirrored from GitHub Pull Request
 question
stale
streaming
unable-to-reproduce
wontfix
No Label bug confirmed
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/langserve#86
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?