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

Streamlit calls not working in callback #23

New Issue
Closed
opened 2026-02-20 17:22:50 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:22:50 -05:00
Owner
Copy Link
Copy Source

Originally created by @i-merge on GitHub (Feb 17, 2024).

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the LangChain documentation with the integrated search.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangChain rather than my code.

Example Code

# Define callback with a streamlit call
@st.cache_data(experimental_allow_widgets=True, persist=True) 
def custom_callback():
   response = st.text_input("Do you want to continue?")
   return response == "y"

def run(...):
   # Calling the callback in run works
   custom_callback()
   handler = HumanApprovalCallbackHandler(custom_callback)
   # Passing it to callbacks will result in an NoSessionContext() error
   response = app.stream(inputs, config={"callbacks": [handler]})

Error Message and Stack Trace (if applicable)

File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 3887, in invoke
return self.bound.invoke(
^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 3353, in invoke
return self._call_with_config(
^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 1246, in _call_with_config
context.run(
File "lib/python3.11/site-packages/langchain_core/runnables/config.py", line 326, in call_func_with_variable_args
return func(input, **kwargs) # type: ignore[call-arg]
^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 3229, in _invoke
output = call_func_with_variable_args(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/runnables/config.py", line 326, in call_func_with_variable_args
return func(input, **kwargs) # type: ignore[call-arg]
^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langgraph/prebuilt/tool_executor.py", line 60, in _execute
output = tool.invoke(tool_invocation.tool_input, config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/tools.py", line 210, in invoke
return self.run(
^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/tools.py", line 331, in run
run_manager = callback_manager.on_tool_start(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_core/callbacks/manager.py", line 1308, in on_tool_start
handle_event(
File "lib/python3.11/site-packages/langchain_core/callbacks/manager.py", line 262, in handle_event
raise e
File "lib/python3.11/site-packages/langchain_core/callbacks/manager.py", line 234, in handle_event
event = getattr(handler, event_name)(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/langchain_community/callbacks/human.py", line 57, in on_tool_start
if self._should_check(serialized) and not self._approve(input_str):
^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/streamlit/runtime/caching/cache_utils.py", line 212, in wrapper
return cached_func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/streamlit/runtime/caching/cache_utils.py", line 240, in call
with spinner(message, cache=True):
File "versions/3.11.7/lib/python3.11/contextlib.py", line 137, in enter
return next(self.gen)
^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/streamlit/elements/spinner.py", line 56, in spinner
message = st.empty()
^^^^^^^^^^
File "lib/python3.11/site-packages/streamlit/elements/empty.py", line 70, in empty
return self.dg._enqueue("empty", empty_proto)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "lib/python3.11/site-packages/streamlit/delta_generator.py", line 530, in _enqueue
_enqueue_message(msg)
File "lib/python3.11/site-packages/streamlit/delta_generator.py", line 869, in _enqueue_message
raise NoSessionContext()
streamlit.errors.NoSessionContext

Description

Adding a callback to stream or invoke with a streamlit call inside will result in NoSessionContext error

System Info

langchain : 0.1.0
langgraph: 0.0.20
streamlit: 1.31.0

Originally created by @i-merge on GitHub (Feb 17, 2024). ### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the LangChain documentation with the integrated search. - [X] I used the GitHub search to find a similar question and didn't find it. - [X] I am sure that this is a bug in LangChain rather than my code. ### Example Code ```python # Define callback with a streamlit call @st.cache_data(experimental_allow_widgets=True, persist=True) def custom_callback(): response = st.text_input("Do you want to continue?") return response == "y" def run(...): # Calling the callback in run works custom_callback() handler = HumanApprovalCallbackHandler(custom_callback) # Passing it to callbacks will result in an NoSessionContext() error response = app.stream(inputs, config={"callbacks": [handler]}) ``` ### Error Message and Stack Trace (if applicable) File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 3887, in invoke return self.bound.invoke( ^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 3353, in invoke return self._call_with_config( ^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 1246, in _call_with_config context.run( File "lib/python3.11/site-packages/langchain_core/runnables/config.py", line 326, in call_func_with_variable_args return func(input, **kwargs) # type: ignore[call-arg] ^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/runnables/base.py", line 3229, in _invoke output = call_func_with_variable_args( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/runnables/config.py", line 326, in call_func_with_variable_args return func(input, **kwargs) # type: ignore[call-arg] ^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langgraph/prebuilt/tool_executor.py", line 60, in _execute output = tool.invoke(tool_invocation.tool_input, config=config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/tools.py", line 210, in invoke return self.run( ^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/tools.py", line 331, in run run_manager = callback_manager.on_tool_start( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_core/callbacks/manager.py", line 1308, in on_tool_start handle_event( File "lib/python3.11/site-packages/langchain_core/callbacks/manager.py", line 262, in handle_event raise e File "lib/python3.11/site-packages/langchain_core/callbacks/manager.py", line 234, in handle_event event = getattr(handler, event_name)(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/langchain_community/callbacks/human.py", line 57, in on_tool_start if self._should_check(serialized) and not self._approve(input_str): ^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/streamlit/runtime/caching/cache_utils.py", line 212, in wrapper return cached_func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/streamlit/runtime/caching/cache_utils.py", line 240, in __call__ with spinner(message, cache=True): File "versions/3.11.7/lib/python3.11/contextlib.py", line 137, in __enter__ return next(self.gen) ^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/streamlit/elements/spinner.py", line 56, in spinner message = st.empty() ^^^^^^^^^^ File "lib/python3.11/site-packages/streamlit/elements/empty.py", line 70, in empty return self.dg._enqueue("empty", empty_proto) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "lib/python3.11/site-packages/streamlit/delta_generator.py", line 530, in _enqueue _enqueue_message(msg) File "lib/python3.11/site-packages/streamlit/delta_generator.py", line 869, in _enqueue_message raise NoSessionContext() streamlit.errors.NoSessionContext ### Description Adding a callback to stream or invoke with a streamlit call inside will result in NoSessionContext error ### System Info langchain : 0.1.0 langgraph: 0.0.20 streamlit: 1.31.0
yindo closed this issue 2026-02-20 17:22:50 -05:00
yindo commented 2026-02-20 17:22:51 -05:00
Author
Owner
Copy Link
Copy Source

@hinthornw commented on GitHub (Apr 14, 2025):

Gonna close as stale

@hinthornw commented on GitHub (Apr 14, 2025): Gonna close as stale
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
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#23
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?