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

TypeError: Object of type Send is not JSON serializable when using PostgresSaver checkpoint #1064

New Issue
Closed
opened 2026-02-20 17:42:56 -05:00 by yindo · 3 comments
yindo commented 2026-02-20 17:42:56 -05:00
Owner
Copy Link
Copy Source

Originally created by @lasendo on GitHub (Nov 18, 2025).

Checked other resources

  • This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
  • 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

import operator
from typing import Annotated, TypedDict, List, Optional
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.postgres import PostgresSaver
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
from langgraph.checkpoint.memory import MemorySaver
from langgraph.constants import Send

class OverallState(TypedDict):
    topics: List[str] = ["fine arts", 'firefighters', 'maths']
    jokes: Annotated[List[str], operator.add]
    all_jokes: str

default_state = OverallState(topics=["fine arts", 'firefighters', 'maths'],
                                   jokes=[], all_jokes="")

class JokeState(TypedDict):
    topic: str

def send_topics(state: OverallState):
    print("Sending joke creation")
    return [Send("create_joke", JokeState(topic=topic)) for topic in state["topics"]]

def create_joke(joke_state: JokeState) -> dict:
    return {"jokes": [f'Joke for topic {joke_state["topic"]}']}

def reduce_jokes(state: OverallState) -> dict:
    print("Merge jokes")
    return {"all_jokes": "\n".join(state['jokes'])} 


def main():
    print("Creating graph with...")
    
    # Create graph
    workflow = StateGraph(OverallState)
    workflow.add_node("create_joke", create_joke)
    workflow.add_node("reduce_jokes", reduce_jokes)
    workflow.add_conditional_edges(START, send_topics, {"create_joke"})
    workflow.add_edge("create_joke", "reduce_jokes")
    workflow.add_edge("reduce_jokes", END)
    

    # Try with Memory checkpointing (this should work)
    print("\nTrying with Memory checkpointing...")
    try:
        checkpointer = MemorySaver()
        app = workflow.compile(checkpointer=checkpointer)
        
        print("Running graph with Memory checkpointing...")
        result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}})
        print(f"Result: {result}")
        
    except Exception as e:
        print(f"Error with Memory checkpointing: {e}")
        raise e


    # Try with Postgres checkpointing (this should fail)
    try:
        with PostgresSaver.from_conn_string(
            "postgresql://test_user:test_password@postgres:9999/test_db") as checkpointer:
            checkpointer.setup()
            app = workflow.compile(checkpointer=checkpointer)
            
            print("\n\nRunning graph with Postgres checkpointing...")
            result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}})
            print(f"Result: {result}")
        
    except Exception as e:
        print(f"Error with Postgres checkpointing: {e}")
        raise e

if __name__ == "__main__":
    main()

Error Message and Stack Trace (if applicable)

TypeError: Object of type Send is not JSON serializable
 Traceback (most recent call last):
   File "/app/app.py", line 75, in <module>
     main()
   File "/app/app.py", line 72, in main
     raise e
   File "/app/app.py", line 67, in main
     result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}})
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1927, in invoke
     for chunk in self.stream(
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1596, in stream
     with SyncPregelLoop(
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 874, in __exit__
     return self.stack.__exit__(exc_type, exc_value, traceback)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/contextlib.py", line 601, in __exit__
     raise exc_details[1]
   File "/usr/local/lib/python3.11/contextlib.py", line 586, in __exit__
     if cb(*exc_details):
        ^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 107, in __exit__
     task.result()
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result
     return self.__get_result()
            ^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
     raise self._exception
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 70, in done
     task.result()
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result
     return self.__get_result()
            ^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
     raise self._exception
   File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
     result = self.fn(*self.args, **self.kwargs)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 799, in _checkpointer_put_after_previous
     prev.result()
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 456, in result
     return self.__get_result()
            ^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
     raise self._exception
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 70, in done
     task.result()
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result
     return self.__get_result()
            ^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
     raise self._exception
   File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
     result = self.fn(*self.args, **self.kwargs)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 799, in _checkpointer_put_after_previous
     prev.result()
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 456, in result
     return self.__get_result()
            ^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
     raise self._exception
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 70, in done
     task.result()
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result
     return self.__get_result()
            ^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
     raise self._exception
   File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
     result = self.fn(*self.args, **self.kwargs)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 801, in _checkpointer_put_after_previous
     cast(BaseCheckpointSaver, self.checkpointer).put(
   File "/usr/local/lib/python3.11/site-packages/langgraph/checkpoint/postgres/__init__.py", line 321, in put
     cur.execute(
   File "/usr/local/lib/python3.11/site-packages/psycopg/cursor.py", line 93, in execute
     self._conn.wait(
   File "/usr/local/lib/python3.11/site-packages/psycopg/connection.py", line 453, in wait
     return waiting.wait(gen, self.pgconn.socket, interval=interval)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "psycopg_binary/_psycopg/waiting.pyx", line 219, in psycopg_binary._psycopg.wait_c
   File "/usr/local/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 194, in _execute_gen
     pgq = self._convert_query(query, params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 453, in _convert_query
     pgq.convert(query, params)
   File "/usr/local/lib/python3.11/site-packages/psycopg/_queries.py", line 95, in convert
     self.dump(vars)
   File "/usr/local/lib/python3.11/site-packages/psycopg/_queries.py", line 106, in dump
     self.params = self._tx.dump_sequence(params, self._want_formats)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "psycopg_binary/_psycopg/transform.pyx", line 353, in psycopg_binary._psycopg.Transformer.dump_sequence
   File "psycopg_binary/_psycopg/transform.pyx", line 404, in psycopg_binary._psycopg.Transformer.dump_sequence
   File "/usr/local/lib/python3.11/site-packages/psycopg/types/json.py", line 218, in dump
     if isinstance((data := dumps(obj)), str):
                            ^^^^^^^^^^
   File "/usr/local/lib/python3.11/json/__init__.py", line 231, in dumps
     return _default_encoder.encode(obj)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/json/encoder.py", line 200, in encode
     chunks = self.iterencode(o, _one_shot=True)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/json/encoder.py", line 258, in iterencode
     return _iterencode(o, 0)
            ^^^^^^^^^^^^^^^^^
   File "/usr/local/lib/python3.11/json/encoder.py", line 180, in default
     raise TypeError(f'Object of type {o.__class__.__name__} '
 TypeError: Object of type Send is not JSON serializable

Description

Recently I wanted to persist the checkpoint data of my graph. I imported PostgresSaver (actually AsyncPosgresSaver) and figured out how to call this from the documentation: https://docs.langchain.com/oss/python/langgraph/add-memory#example-using-postgres-checkpointer.

However, I found that my implementation using Send as specified in many Map-Reduce implementations using LangGraph (e.g. https://www.youtube.com/watch?v=JQznvlSatPQ) raises a TypeError due to the Send class not being JSON serializable.

I found some other issues regarding serialization, but none are specific to this scenario.

The code shows that whereas with MemorySaver it works, with the database and PostgresSaver there is a need to serialize data, which turns out to contain the Send.

The output shown at the termina when I perform docker compose up for the app container is:

Creating graph with...
 
 Trying with Memory checkpointing...
 Running graph with Memory checkpointing...
 Sending joke creation
 Merge jokes
 Result: {'topics': ['fine arts', 'firefighters', 'maths'], 'jokes': ['Joke for topic fine arts', 'Joke for topic firefighters', 'Joke for topic maths'], 'all_jokes': 'Joke for topic fine arts\nJoke for topic firefighters\nJoke for topic maths'}
 
 
 Running graph with Postgres checkpointing...
 Sending joke creation
 Merge jokes
 Error with Postgres checkpointing: Object of type Send is not JSON serializable

System Info

I am using dockercompose:

services:

  postgres:
    image: postgres
    restart: always
    environment:
      - POSTGRES_USER=test_user
      - POSTGRES_PASSWORD=test_password
      - POSTGRES_DB=test_db
      - PGPORT=9999
    ports:
      - 9999:9999
    volumes:
      - postgres_data:/var/lib/postgresql/data

  app:
    build: .
    depends_on:
      - postgres
    environment:
      - POSTGRES_HOST=postgres
      - POSTGRES_PORT=9999
      - POSTGRES_DB=test_db
      - POSTGRES_USER=test_user
      - POSTGRES_PASSWORD=test_password
    volumes:
      - .:/app/

volumes:
  postgres_data:

Where the Dockerfile for app is:

FROM python:3.11-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install -r requirements.txt

COPY . .

CMD ["python", "app.py"]

The requirements:

langchain==0.3.9
langchain-community==0.3.8
langchain-core==0.3.21
langchain-experimental==0.3.3
langgraph==0.2.53
langgraph-checkpoint==2.1.2
langgraph-checkpoint-postgres==3.0.1
langgraph-sdk==0.1.40
psycopg[binary,pool]
psycopg==3.2.12
psycopg-pool==3.2.7
pydantic==2.10.2
Originally created by @lasendo on GitHub (Nov 18, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [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 import operator from typing import Annotated, TypedDict, List, Optional from langgraph.graph import StateGraph, START, END from langgraph.checkpoint.postgres import PostgresSaver from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver from langgraph.checkpoint.memory import MemorySaver from langgraph.constants import Send class OverallState(TypedDict): topics: List[str] = ["fine arts", 'firefighters', 'maths'] jokes: Annotated[List[str], operator.add] all_jokes: str default_state = OverallState(topics=["fine arts", 'firefighters', 'maths'], jokes=[], all_jokes="") class JokeState(TypedDict): topic: str def send_topics(state: OverallState): print("Sending joke creation") return [Send("create_joke", JokeState(topic=topic)) for topic in state["topics"]] def create_joke(joke_state: JokeState) -> dict: return {"jokes": [f'Joke for topic {joke_state["topic"]}']} def reduce_jokes(state: OverallState) -> dict: print("Merge jokes") return {"all_jokes": "\n".join(state['jokes'])} def main(): print("Creating graph with...") # Create graph workflow = StateGraph(OverallState) workflow.add_node("create_joke", create_joke) workflow.add_node("reduce_jokes", reduce_jokes) workflow.add_conditional_edges(START, send_topics, {"create_joke"}) workflow.add_edge("create_joke", "reduce_jokes") workflow.add_edge("reduce_jokes", END) # Try with Memory checkpointing (this should work) print("\nTrying with Memory checkpointing...") try: checkpointer = MemorySaver() app = workflow.compile(checkpointer=checkpointer) print("Running graph with Memory checkpointing...") result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}}) print(f"Result: {result}") except Exception as e: print(f"Error with Memory checkpointing: {e}") raise e # Try with Postgres checkpointing (this should fail) try: with PostgresSaver.from_conn_string( "postgresql://test_user:test_password@postgres:9999/test_db") as checkpointer: checkpointer.setup() app = workflow.compile(checkpointer=checkpointer) print("\n\nRunning graph with Postgres checkpointing...") result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}}) print(f"Result: {result}") except Exception as e: print(f"Error with Postgres checkpointing: {e}") raise e if __name__ == "__main__": main() ``` ### Error Message and Stack Trace (if applicable) ```shell TypeError: Object of type Send is not JSON serializable Traceback (most recent call last): File "/app/app.py", line 75, in <module> main() File "/app/app.py", line 72, in main raise e File "/app/app.py", line 67, in main result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}}) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1927, in invoke for chunk in self.stream( File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1596, in stream with SyncPregelLoop( File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 874, in __exit__ return self.stack.__exit__(exc_type, exc_value, traceback) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/contextlib.py", line 601, in __exit__ raise exc_details[1] File "/usr/local/lib/python3.11/contextlib.py", line 586, in __exit__ if cb(*exc_details): ^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 107, in __exit__ task.result() File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 70, in done task.result() File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 799, in _checkpointer_put_after_previous prev.result() File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 456, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 70, in done task.result() File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 799, in _checkpointer_put_after_previous prev.result() File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 456, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 70, in done task.result() File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 801, in _checkpointer_put_after_previous cast(BaseCheckpointSaver, self.checkpointer).put( File "/usr/local/lib/python3.11/site-packages/langgraph/checkpoint/postgres/__init__.py", line 321, in put cur.execute( File "/usr/local/lib/python3.11/site-packages/psycopg/cursor.py", line 93, in execute self._conn.wait( File "/usr/local/lib/python3.11/site-packages/psycopg/connection.py", line 453, in wait return waiting.wait(gen, self.pgconn.socket, interval=interval) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "psycopg_binary/_psycopg/waiting.pyx", line 219, in psycopg_binary._psycopg.wait_c File "/usr/local/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 194, in _execute_gen pgq = self._convert_query(query, params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 453, in _convert_query pgq.convert(query, params) File "/usr/local/lib/python3.11/site-packages/psycopg/_queries.py", line 95, in convert self.dump(vars) File "/usr/local/lib/python3.11/site-packages/psycopg/_queries.py", line 106, in dump self.params = self._tx.dump_sequence(params, self._want_formats) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "psycopg_binary/_psycopg/transform.pyx", line 353, in psycopg_binary._psycopg.Transformer.dump_sequence File "psycopg_binary/_psycopg/transform.pyx", line 404, in psycopg_binary._psycopg.Transformer.dump_sequence File "/usr/local/lib/python3.11/site-packages/psycopg/types/json.py", line 218, in dump if isinstance((data := dumps(obj)), str): ^^^^^^^^^^ File "/usr/local/lib/python3.11/json/__init__.py", line 231, in dumps return _default_encoder.encode(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/json/encoder.py", line 200, in encode chunks = self.iterencode(o, _one_shot=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/json/encoder.py", line 258, in iterencode return _iterencode(o, 0) ^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/json/encoder.py", line 180, in default raise TypeError(f'Object of type {o.__class__.__name__} ' TypeError: Object of type Send is not JSON serializable ``` ### Description Recently I wanted to persist the checkpoint data of my graph. I imported PostgresSaver (actually AsyncPosgresSaver) and figured out how to call this from the documentation: https://docs.langchain.com/oss/python/langgraph/add-memory#example-using-postgres-checkpointer. However, I found that my implementation using `Send` as specified in many Map-Reduce implementations using LangGraph (e.g. https://www.youtube.com/watch?v=JQznvlSatPQ) raises a `TypeError` due to the `Send` class not being JSON serializable. I found some other issues regarding serialization, but none are specific to this scenario. The code shows that whereas with `MemorySaver` it works, with the database and `PostgresSaver` there is a need to serialize data, which turns out to contain the `Send`. The output shown at the termina when I perform `docker compose up` for the app container is: ```console Creating graph with... Trying with Memory checkpointing... Running graph with Memory checkpointing... Sending joke creation Merge jokes Result: {'topics': ['fine arts', 'firefighters', 'maths'], 'jokes': ['Joke for topic fine arts', 'Joke for topic firefighters', 'Joke for topic maths'], 'all_jokes': 'Joke for topic fine arts\nJoke for topic firefighters\nJoke for topic maths'} Running graph with Postgres checkpointing... Sending joke creation Merge jokes Error with Postgres checkpointing: Object of type Send is not JSON serializable ``` ### System Info I am using dockercompose: ```docker-compose.yml services: postgres: image: postgres restart: always environment: - POSTGRES_USER=test_user - POSTGRES_PASSWORD=test_password - POSTGRES_DB=test_db - PGPORT=9999 ports: - 9999:9999 volumes: - postgres_data:/var/lib/postgresql/data app: build: . depends_on: - postgres environment: - POSTGRES_HOST=postgres - POSTGRES_PORT=9999 - POSTGRES_DB=test_db - POSTGRES_USER=test_user - POSTGRES_PASSWORD=test_password volumes: - .:/app/ volumes: postgres_data: ``` Where the Dockerfile for app is: ```DockerFile FROM python:3.11-slim WORKDIR /app COPY requirements.txt . RUN pip install -r requirements.txt COPY . . CMD ["python", "app.py"] ``` The requirements: ```requirements.txt langchain==0.3.9 langchain-community==0.3.8 langchain-core==0.3.21 langchain-experimental==0.3.3 langgraph==0.2.53 langgraph-checkpoint==2.1.2 langgraph-checkpoint-postgres==3.0.1 langgraph-sdk==0.1.40 psycopg[binary,pool] psycopg==3.2.12 psycopg-pool==3.2.7 pydantic==2.10.2 ```
yindo added the bugpending labels 2026-02-20 17:42:56 -05:00
yindo closed this issue 2026-02-20 17:42:56 -05:00
yindo commented 2026-02-20 17:42:57 -05:00
Author
Owner
Copy Link
Copy Source

@Balmy-afterGlow commented on GitHub (Dec 5, 2025):

me too

@Balmy-afterGlow commented on GitHub (Dec 5, 2025): me too
yindo commented 2026-02-20 17:42:57 -05:00
Author
Owner
Copy Link
Copy Source

@Balmy-afterGlow commented on GitHub (Dec 6, 2025):

@lasendo You can try to upgrade your langgraph version to 5.0.0 or above. Because the memory storage location of checkpoint[pending_sends] has changed, this should be a compatibility issue.

@Balmy-afterGlow commented on GitHub (Dec 6, 2025): @lasendo You can try to upgrade your langgraph version to 5.0.0 or above. Because the memory storage location of checkpoint[pending_sends] has changed, this should be a compatibility issue.
yindo commented 2026-02-20 17:42:57 -05:00
Author
Owner
Copy Link
Copy Source

@lasendo commented on GitHub (Jan 29, 2026):

Thank you, @Balmy-afterGlow.
I have been delaying this for a while, hoping to get a more detailed feedback on the issue.

I guess you mean v0.5.0, as the latest LangGraph version to date is the v1.0.7.

I did several attempts with the docker compose setup changing the versions of LangGraph, while not specifying any for [
langchain, langchain-community, langchain-core, langchain-experimental, langgraph-checkpoint and langgraph-sdk], i.e.

langchain 
langchain-community 
langchain-core 
langchain-experimental 
langgraph==[version] 
langgraph-checkpoint 
langgraph-checkpoint-postgres==3.0.1 
langgraph-sdk 
psycopg[binary,pool] 
psycopg==3.2.12 
psycopg-pool==3.2.7 
pydantic==2.10.2

I tried for [version] 0.3.1, 0.4.0, 0.5.0, 0.5.1, 0.5.2, 0.5.3, 0.6.0, 1.0.0, 1.0.7.

I am not aware why but now the error is different even with v0.2.53 in my docker reproducible setup. The error is:

app-1 |   File "/app/app.py", line 72, in main      
app-1 |     raise e  
app-1 |   File "/app/app.py", line 67, in main      
app-1 |     result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}})        
app-1 |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^        
app-1 |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 2804, in invoke        
app-1 |     for chunk in self.stream(        
app-1 |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 2440, in stream        
app-1 |     while loop.tick(input_keys=self.input_channels):        
app-1 |           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^        
app-1 |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 461, in tick        
app-1 |     updated_channels = self._first(input_keys=input_keys)        
app-1 |                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^        
app-1 |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 712, in _first        
app-1 |     discard_tasks = prepare_next_tasks(        
app-1 |                     ^^^^^^^^^^^^^^^^^^^        
app-1 |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/algo.py", line 431, in prepare_next_tasks        
app-1 |     for idx, _ in enumerate(checkpoint["pending_sends"]):        
app-1 |                             ~~~~~~~~~~^^^^^^^^^^^^^^^^^        
app-1 | KeyError: 'pending_sends'  exited with code 1

which is related to what @Balmy-afterGlow pointed out.

The versions 0.5.0, 0.5.1 and 0.5.2 also crashed, but with a different error:

app-1       | Traceback (most recent call last):
app-1       |   File "/app/app.py", line 3, in <module>
app-1       |     from langgraph.graph import StateGraph, START, END
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/graph/__init__.py", line 2, in <module>
app-1       |     from langgraph.graph.message import MessageGraph, MessagesState, add_messages
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/graph/message.py", line 28, in <module>
app-1       |     from langgraph.graph.state import StateGraph
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/graph/state.py", line 59, in <module>
app-1       |     from langgraph.graph.branch import Branch
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/graph/branch.py", line 31, in <module>
app-1       |     from langgraph.pregel.write import PASSTHROUGH, ChannelWrite, ChannelWriteEntry
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 71, in <module>
app-1       |     from langgraph.pregel.algo import (
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/algo.py", line 73, in <module>
app-1       |     from langgraph.pregel.read import INPUT_CACHE_KEY_TYPE, PregelNode
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/read.py", line 14, in <module>
app-1       |     from langgraph.pregel.protocol import PregelProtocol
app-1       |   File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/protocol.py", line 16, in <module>
app-1       |     class PregelProtocol(Runnable[InputT, Any], Generic[StateT, InputT, OutputT], ABC):
app-1       |   File "<frozen abc>", line 106, in __new__
app-1       | TypeError: Cannot create a consistent method resolution
app-1       | order (MRO) for bases ABC, Generic
app-1 exited with code 1

From v0.5.4 on it succeds. Finally I get the same behavior regardless of the checkpointer:

app-1       | Creating graph with...
app-1       | 
app-1       | Trying with Memory checkpointing...
app-1       | Running graph with Memory checkpointing...
app-1       | Sending joke creation
app-1       | Merge jokes
app-1       | Result: {'topics': ['fine arts', 'firefighters', 'maths'], 'jokes': ['Joke for topic fine arts', 'Joke for topic firefighters', 'Joke for topic maths'], 'all_jokes': 'Joke for topic fine arts\nJoke for topic firefighters\nJoke for topic maths'}
app-1       | 
app-1       | 
app-1       | Running graph with Postgres checkpointing...
app-1       | Sending joke creation
app-1       | Merge jokes
app-1       | Result: {'topics': ['fine arts', 'firefighters', 'maths'], 'jokes': ['Joke for topic fine arts', 'Joke for topic firefighters', 'Joke for topic maths'], 'all_jokes': 'Joke for topic fine arts\nJoke for topic firefighters\nJoke for topic maths'}
@lasendo commented on GitHub (Jan 29, 2026): Thank you, @Balmy-afterGlow. I have been delaying this for a while, hoping to get a more detailed feedback on the issue. I guess you mean v0.5.0, as the latest LangGraph version to date is the v1.0.7. I did several attempts with the docker compose setup changing the versions of LangGraph, while not specifying any for [ langchain, langchain-community, langchain-core, langchain-experimental, langgraph-checkpoint and langgraph-sdk], i.e. ```requirements.txt langchain langchain-community langchain-core langchain-experimental langgraph==[version] langgraph-checkpoint langgraph-checkpoint-postgres==3.0.1 langgraph-sdk psycopg[binary,pool] psycopg==3.2.12 psycopg-pool==3.2.7 pydantic==2.10.2 ``` I tried for [version] 0.3.1, 0.4.0, 0.5.0, 0.5.1, 0.5.2, 0.5.3, 0.6.0, 1.0.0, 1.0.7. I am not aware why but now the error is different even with v0.2.53 in my docker reproducible setup. The error is: ```shell app-1 | File "/app/app.py", line 72, in main app-1 | raise e app-1 | File "/app/app.py", line 67, in main app-1 | result = app.invoke(default_state, config={'configurable': {'thread_id': "1"}}) app-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 2804, in invoke app-1 | for chunk in self.stream( app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 2440, in stream app-1 | while loop.tick(input_keys=self.input_channels): app-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 461, in tick app-1 | updated_channels = self._first(input_keys=input_keys) app-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 712, in _first app-1 | discard_tasks = prepare_next_tasks( app-1 | ^^^^^^^^^^^^^^^^^^^ app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/algo.py", line 431, in prepare_next_tasks app-1 | for idx, _ in enumerate(checkpoint["pending_sends"]): app-1 | ~~~~~~~~~~^^^^^^^^^^^^^^^^^ app-1 | KeyError: 'pending_sends' exited with code 1 ``` which is related to what @Balmy-afterGlow pointed out. The versions 0.5.0, 0.5.1 and 0.5.2 also crashed, but with a different error: ```shell app-1 | Traceback (most recent call last): app-1 | File "/app/app.py", line 3, in <module> app-1 | from langgraph.graph import StateGraph, START, END app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/graph/__init__.py", line 2, in <module> app-1 | from langgraph.graph.message import MessageGraph, MessagesState, add_messages app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/graph/message.py", line 28, in <module> app-1 | from langgraph.graph.state import StateGraph app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/graph/state.py", line 59, in <module> app-1 | from langgraph.graph.branch import Branch app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/graph/branch.py", line 31, in <module> app-1 | from langgraph.pregel.write import PASSTHROUGH, ChannelWrite, ChannelWriteEntry app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 71, in <module> app-1 | from langgraph.pregel.algo import ( app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/algo.py", line 73, in <module> app-1 | from langgraph.pregel.read import INPUT_CACHE_KEY_TYPE, PregelNode app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/read.py", line 14, in <module> app-1 | from langgraph.pregel.protocol import PregelProtocol app-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/protocol.py", line 16, in <module> app-1 | class PregelProtocol(Runnable[InputT, Any], Generic[StateT, InputT, OutputT], ABC): app-1 | File "<frozen abc>", line 106, in __new__ app-1 | TypeError: Cannot create a consistent method resolution app-1 | order (MRO) for bases ABC, Generic app-1 exited with code 1 ``` From v0.5.4 on it succeds. Finally I get the same behavior regardless of the checkpointer: ```shell app-1 | Creating graph with... app-1 | app-1 | Trying with Memory checkpointing... app-1 | Running graph with Memory checkpointing... app-1 | Sending joke creation app-1 | Merge jokes app-1 | Result: {'topics': ['fine arts', 'firefighters', 'maths'], 'jokes': ['Joke for topic fine arts', 'Joke for topic firefighters', 'Joke for topic maths'], 'all_jokes': 'Joke for topic fine arts\nJoke for topic firefighters\nJoke for topic maths'} app-1 | app-1 | app-1 | Running graph with Postgres checkpointing... app-1 | Sending joke creation app-1 | Merge jokes app-1 | Result: {'topics': ['fine arts', 'firefighters', 'maths'], 'jokes': ['Joke for topic fine arts', 'Joke for topic firefighters', 'Joke for topic maths'], 'all_jokes': 'Joke for topic fine arts\nJoke for topic firefighters\nJoke for topic maths'} ```
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 bug pending
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#1064
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?