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

A JSON serializable problem on PostgresSaver #875

New Issue
Closed
opened 2026-02-20 17:42:12 -05:00 by yindo · 9 comments
yindo commented 2026-02-20 17:42:12 -05:00
Owner
Copy Link
Copy Source

Originally created by @gs-max on GitHub (Jul 31, 2025).

Originally assigned to: @casparb on GitHub.

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

from langchain.chat_models import init_chat_model
from langgraph.graph import StateGraph, MessagesState, START
from langgraph.checkpoint.postgres import PostgresSaver

model = init_chat_model(model="anthropic:claude-3-5-haiku-latest")

DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"
with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
    # checkpointer.setup()

    def call_model(state: MessagesState):
        response = model.invoke(state["messages"])
        return {"messages": response}

    builder = StateGraph(MessagesState)
    builder.add_node(call_model)
    builder.add_edge(START, "call_model")

    graph = builder.compile(checkpointer=checkpointer)

    config = {
        "configurable": {
            "thread_id": "1"
        }
    }

    for chunk in graph.stream(
        {"messages": [{"role": "user", "content": "hi! I'm bob"}]},
        config,
        stream_mode="values"
    ):
        chunk["messages"][-1].pretty_print()

    for chunk in graph.stream(
        {"messages": [{"role": "user", "content": "what's my name?"}]},
        config,
        stream_mode="values"
    ):
        chunk["messages"][-1].pretty_print()

Error Message and Stack Trace (if applicable)

Traceback (most recent call last):
  File "/Users/gaoshuo/Downloads/项目2_基于LangGraph实现智能分诊系统/L1-Project-2/apiTest.py", line 31, in <module>
    for chunk in graph.stream(
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1723, in stream
    with SyncPregelLoop(
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 959, in __exit__
    return self.stack.__exit__(exc_type, exc_value, traceback)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/contextlib.py", line 601, in __exit__
    raise exc_details[1]
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/contextlib.py", line 586, in __exit__
    if cb(*exc_details):
       ^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 120, in __exit__
    task.result()
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 83, in done
    task.result()
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 886, in _checkpointer_put_after_previous
    cast(BaseCheckpointSaver, self.checkpointer).put(
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/checkpoint/postgres/__init__.py", line 323, in put
    cur.execute(
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/cursor.py", line 93, in execute
    self._conn.wait(
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/connection.py", line 414, in wait
    return waiting.wait(gen, self.pgconn.socket, interval=interval)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/waiting.py", line 333, in wait_poll
    s = next(gen)
        ^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 194, in _execute_gen
    pgq = self._convert_query(query, params)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 453, in _convert_query
    pgq.convert(query, params)
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_queries.py", line 95, in convert
    self.dump(vars)
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_queries.py", line 106, in dump
    self.params = self._tx.dump_sequence(params, self._want_formats)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_py_transformer.py", line 193, in dump_sequence
    out[i] = dumper.dump(param)
             ^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/types/json.py", line 149, in dump
    if isinstance((data := dumps(obj)), str):
                           ^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/__init__.py", line 231, in dumps
    return _default_encoder.encode(obj)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/encoder.py", line 200, in encode
    chunks = self.iterencode(o, _one_shot=True)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/encoder.py", line 258, in iterencode
    return _iterencode(o, 0)
           ^^^^^^^^^^^^^^^^^
  File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/encoder.py", line 180, in default
    raise TypeError(f'Object of type {o.__class__.__name__} '
TypeError: Object of type AIMessage is not JSON serializable

Description

I am developing an agent for financial report analysis using LangGraph and have run into a persistent issue.
The problem arises when I try to run my workflow. I expect to see the output from the LLM, but instead, I encounter a TypeError: Object of type AIMessage is not JSON serializable.
After some debugging, I've narrowed down the cause to the PostgresSaver checkpointer. Specifically, the error occurs right after my generate node returns a message from the LLM (an AIMessage). If I use in-memory storage instead of PostgresSaver, the workflow runs without any issues.
What's more puzzling is that this error does not occur after other nodes in the workflow return messages. It only appears when the final node completes its work and the very last message needs to be processed. I can confirm this from the print statements in my terminal, which show that the return values from intermediate nodes are being correctly outputted and seemingly saved.
To validate my findings, I tried running the official LangGraph memory tutorial from the documentation (link: https://langchain-ai.github.io/langgraph/how-tos/memory/add-memory/?h=asyncpostgressaver#__tabbed_1_1). I used the code provided in the first tab for PostgresSaver. To my surprise, I encountered the exact same error， the TypeError is raised immediately after. This behavior is identical to what I'm experiencing in my own project.
This issue has been troubling me for several days, and I'm unsure if it's a bug, a configuration mistake on my part, or something else entirely.
For context, here are some of the key dependencies in my project environment:
pip install langgraph==0.2.74
pip install langchain-openai==0.3.6

pip install langchain-community==0.3.19
pip install langchain-chroma==0.2.2
pip install pdfminer
pip install pdfminer.six
pip install nltk==3.9.1
pip install psycopg2==2.9.10
pip install concurrent-log-handler==0.9.25

pip install langgraph-checkpoint-postgres
pip install psycopg psycopg-pool
I would sincerely appreciate any help or insights someone could offer to resolve this.
Thank you!

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132
Python Version: 3.11.13 (main, Jun 5 2025, 08:21:08) [Clang 14.0.6 ]

Package Information

langchain_core: 0.3.72
langchain: 0.3.27
langchain_community: 0.3.19
langsmith: 0.3.45
langchain_chroma: 0.2.2
langchain_openai: 0.3.6
langchain_text_splitters: 0.3.9
langgraph_sdk: 0.1.74

Optional packages not installed

langserve

Other Dependencies

aiohttp<4.0.0,>=3.8.3: Installed. No version info available.
async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.
chromadb!=0.5.10,!=0.5.11,!=0.5.12,!=0.5.4,!=0.5.5,!=0.5.7,!=0.5.9,<0.7.0,>=0.4.0: Installed. No version info available.
dataclasses-json<0.7,>=0.5.7: Installed. No version info available.
httpx: 0.28.1
httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.
httpx>=0.25.2: Installed. No version info available.
jsonpatch<2.0,>=1.33: Installed. No version info available.
langchain-anthropic;: Installed. No version info available.
langchain-aws;: Installed. No version info available.
langchain-azure-ai;: Installed. No version info available.
langchain-cohere;: Installed. No version info available.
langchain-community;: Installed. No version info available.
langchain-core!=0.3.0,!=0.3.1,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,<0.4.0,>=0.2.43: Installed. No version info available.
langchain-core<1.0.0,>=0.3.35: Installed. No version info available.
langchain-core<1.0.0,>=0.3.41: Installed. No version info available.
langchain-core<1.0.0,>=0.3.72: Installed. No version info available.
langchain-deepseek;: Installed. No version info available.
langchain-fireworks;: Installed. No version info available.
langchain-google-genai;: Installed. No version info available.
langchain-google-vertexai;: Installed. No version info available.
langchain-groq;: Installed. No version info available.
langchain-huggingface;: Installed. No version info available.
langchain-mistralai;: Installed. No version info available.
langchain-ollama;: Installed. No version info available.
langchain-openai;: Installed. No version info available.
langchain-perplexity;: Installed. No version info available.
langchain-text-splitters<1.0.0,>=0.3.9: Installed. No version info available.
langchain-together;: Installed. No version info available.
langchain-xai;: Installed. No version info available.
langchain<1.0.0,>=0.3.20: Installed. No version info available.
langsmith-pyo3: Installed. No version info available.
langsmith<0.4,>=0.1.125: Installed. No version info available.
langsmith>=0.1.17: Installed. No version info available.
langsmith>=0.3.45: Installed. No version info available.
numpy<2.0.0,>=1.22.4;: Installed. No version info available.
numpy<2.0.0,>=1.26.2;: Installed. No version info available.
numpy<3,>=1.26.2: Installed. No version info available.
openai-agents: Installed. No version info available.
openai<2.0.0,>=1.58.1: Installed. No version info available.
opentelemetry-api: 1.36.0
opentelemetry-exporter-otlp-proto-http: Installed. No version info available.
opentelemetry-sdk: 1.36.0
orjson: 3.11.1
orjson>=3.10.1: Installed. No version info available.
packaging: 25.0
packaging>=23.2: Installed. No version info available.
pydantic: 2.11.7
pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic>=2.7.4: Installed. No version info available.
pytest: Installed. No version info available.
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.4
requests-toolbelt: 1.0.0
requests<3,>=2: Installed. No version info available.
rich: 14.1.0
SQLAlchemy<3,>=1.4: Installed. No version info available.
tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
tiktoken<1,>=0.7: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.
zstandard: 0.23.0

Originally created by @gs-max on GitHub (Jul 31, 2025). Originally assigned to: @casparb on GitHub. ### 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 from langchain.chat_models import init_chat_model from langgraph.graph import StateGraph, MessagesState, START from langgraph.checkpoint.postgres import PostgresSaver model = init_chat_model(model="anthropic:claude-3-5-haiku-latest") DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable" with PostgresSaver.from_conn_string(DB_URI) as checkpointer: # checkpointer.setup() def call_model(state: MessagesState): response = model.invoke(state["messages"]) return {"messages": response} builder = StateGraph(MessagesState) builder.add_node(call_model) builder.add_edge(START, "call_model") graph = builder.compile(checkpointer=checkpointer) config = { "configurable": { "thread_id": "1" } } for chunk in graph.stream( {"messages": [{"role": "user", "content": "hi! I'm bob"}]}, config, stream_mode="values" ): chunk["messages"][-1].pretty_print() for chunk in graph.stream( {"messages": [{"role": "user", "content": "what's my name?"}]}, config, stream_mode="values" ): chunk["messages"][-1].pretty_print() ``` ### Error Message and Stack Trace (if applicable) ```shell Traceback (most recent call last): File "/Users/gaoshuo/Downloads/项目2_基于LangGraph实现智能分诊系统/L1-Project-2/apiTest.py", line 31, in <module> for chunk in graph.stream( File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 1723, in stream with SyncPregelLoop( File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 959, in __exit__ return self.stack.__exit__(exc_type, exc_value, traceback) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/contextlib.py", line 601, in __exit__ raise exc_details[1] File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/contextlib.py", line 586, in __exit__ if cb(*exc_details): ^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 120, in __exit__ task.result() File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/executor.py", line 83, in done task.result() File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/pregel/loop.py", line 886, in _checkpointer_put_after_previous cast(BaseCheckpointSaver, self.checkpointer).put( File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/langgraph/checkpoint/postgres/__init__.py", line 323, in put cur.execute( File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/cursor.py", line 93, in execute self._conn.wait( File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/connection.py", line 414, in wait return waiting.wait(gen, self.pgconn.socket, interval=interval) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/waiting.py", line 333, in wait_poll s = next(gen) ^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 194, in _execute_gen pgq = self._convert_query(query, params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_cursor_base.py", line 453, in _convert_query pgq.convert(query, params) File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_queries.py", line 95, in convert self.dump(vars) File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_queries.py", line 106, in dump self.params = self._tx.dump_sequence(params, self._want_formats) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/_py_transformer.py", line 193, in dump_sequence out[i] = dumper.dump(param) ^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/site-packages/psycopg/types/json.py", line 149, in dump if isinstance((data := dumps(obj)), str): ^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/__init__.py", line 231, in dumps return _default_encoder.encode(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/encoder.py", line 200, in encode chunks = self.iterencode(o, _one_shot=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/encoder.py", line 258, in iterencode return _iterencode(o, 0) ^^^^^^^^^^^^^^^^^ File "/Users/gaoshuo/Downloads/miniconda3/envs/L1-Project-2/lib/python3.11/json/encoder.py", line 180, in default raise TypeError(f'Object of type {o.__class__.__name__} ' TypeError: Object of type AIMessage is not JSON serializable ``` ### Description I am developing an agent for financial report analysis using LangGraph and have run into a persistent issue. The problem arises when I try to run my workflow. I expect to see the output from the LLM, but instead, I encounter a **_TypeError: Object of type AIMessage is not JSON serializable._** After some debugging, I've narrowed down the cause to the PostgresSaver checkpointer. Specifically, the error occurs right after my generate node returns a message from the LLM (an AIMessage). If I use in-memory storage instead of PostgresSaver, the workflow runs without any issues. What's more puzzling is that this error does not occur after other nodes in the workflow return messages. It only appears when the final node completes its work and the very last message needs to be processed. I can confirm this from the print statements in my terminal, which show that the return values from intermediate nodes are being correctly outputted and seemingly saved. **_To validate my findings, I tried running the official LangGraph memory tutorial from the documentation (link: https://langchain-ai.github.io/langgraph/how-tos/memory/add-memory/?h=asyncpostgressaver#__tabbed_1_1). I used the code provided in the first tab for PostgresSaver. To my surprise, I encountered the exact same error， the TypeError is raised immediately after. This behavior is identical to what I'm experiencing in my own project. This issue has been troubling me for several days, and I'm unsure if it's a bug, a configuration mistake on my part, or something else entirely._** For context, here are some of the key dependencies in my project environment: pip install langgraph==0.2.74 pip install langchain-openai==0.3.6 pip install langchain-community==0.3.19 pip install langchain-chroma==0.2.2 pip install pdfminer pip install pdfminer.six pip install nltk==3.9.1 pip install psycopg2==2.9.10 pip install concurrent-log-handler==0.9.25 pip install langgraph-checkpoint-postgres pip install psycopg psycopg-pool I would sincerely appreciate any help or insights someone could offer to resolve this. Thank you! ### System Info System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132 > Python Version: 3.11.13 (main, Jun 5 2025, 08:21:08) [Clang 14.0.6 ] Package Information ------------------- > langchain_core: 0.3.72 > langchain: 0.3.27 > langchain_community: 0.3.19 > langsmith: 0.3.45 > langchain_chroma: 0.2.2 > langchain_openai: 0.3.6 > langchain_text_splitters: 0.3.9 > langgraph_sdk: 0.1.74 Optional packages not installed ------------------------------- > langserve Other Dependencies ------------------ > aiohttp<4.0.0,>=3.8.3: Installed. No version info available. > async-timeout<5.0.0,>=4.0.0;: Installed. No version info available. > chromadb!=0.5.10,!=0.5.11,!=0.5.12,!=0.5.4,!=0.5.5,!=0.5.7,!=0.5.9,<0.7.0,>=0.4.0: Installed. No version info available. > dataclasses-json<0.7,>=0.5.7: Installed. No version info available. > httpx: 0.28.1 > httpx-sse<1.0.0,>=0.4.0: Installed. No version info available. > httpx>=0.25.2: Installed. No version info available. > jsonpatch<2.0,>=1.33: Installed. No version info available. > langchain-anthropic;: Installed. No version info available. > langchain-aws;: Installed. No version info available. > langchain-azure-ai;: Installed. No version info available. > langchain-cohere;: Installed. No version info available. > langchain-community;: Installed. No version info available. > langchain-core!=0.3.0,!=0.3.1,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,<0.4.0,>=0.2.43: Installed. No version info available. > langchain-core<1.0.0,>=0.3.35: Installed. No version info available. > langchain-core<1.0.0,>=0.3.41: Installed. No version info available. > langchain-core<1.0.0,>=0.3.72: Installed. No version info available. > langchain-deepseek;: Installed. No version info available. > langchain-fireworks;: Installed. No version info available. > langchain-google-genai;: Installed. No version info available. > langchain-google-vertexai;: Installed. No version info available. > langchain-groq;: Installed. No version info available. > langchain-huggingface;: Installed. No version info available. > langchain-mistralai;: Installed. No version info available. > langchain-ollama;: Installed. No version info available. > langchain-openai;: Installed. No version info available. > langchain-perplexity;: Installed. No version info available. > langchain-text-splitters<1.0.0,>=0.3.9: Installed. No version info available. > langchain-together;: Installed. No version info available. > langchain-xai;: Installed. No version info available. > langchain<1.0.0,>=0.3.20: Installed. No version info available. > langsmith-pyo3: Installed. No version info available. > langsmith<0.4,>=0.1.125: Installed. No version info available. > langsmith>=0.1.17: Installed. No version info available. > langsmith>=0.3.45: Installed. No version info available. > numpy<2.0.0,>=1.22.4;: Installed. No version info available. > numpy<2.0.0,>=1.26.2;: Installed. No version info available. > numpy<3,>=1.26.2: Installed. No version info available. > openai-agents: Installed. No version info available. > openai<2.0.0,>=1.58.1: Installed. No version info available. > opentelemetry-api: 1.36.0 > opentelemetry-exporter-otlp-proto-http: Installed. No version info available. > opentelemetry-sdk: 1.36.0 > orjson: 3.11.1 > orjson>=3.10.1: Installed. No version info available. > packaging: 25.0 > packaging>=23.2: Installed. No version info available. > pydantic: 2.11.7 > pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available. > pydantic<3.0.0,>=2.7.4: Installed. No version info available. > pydantic>=2.7.4: Installed. No version info available. > pytest: Installed. No version info available. > PyYAML>=5.3: Installed. No version info available. > requests: 2.32.4 > requests-toolbelt: 1.0.0 > requests<3,>=2: Installed. No version info available. > rich: 14.1.0 > SQLAlchemy<3,>=1.4: Installed. No version info available. > tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available. > tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available. > tiktoken<1,>=0.7: Installed. No version info available. > typing-extensions>=4.7: Installed. No version info available. > zstandard: 0.23.0
yindo added the bugpending labels 2026-02-20 17:42:12 -05:00
yindo closed this issue 2026-02-20 17:42:12 -05:00
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@meng0302 commented on GitHub (Aug 1, 2025):

Return and request both use dict type, for example ：{"messages": {"role": "ai", "content": response}} | {"messages": {"role": "ai", "content": request}}

@meng0302 commented on GitHub (Aug 1, 2025): Return and request both use dict type, for example ：{"messages": {"role": "ai", "content": response}} | {"messages": {"role": "ai", "content": request}}
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@amajai commented on GitHub (Aug 1, 2025):

I am also experiencing the same bug.

@amajai commented on GitHub (Aug 1, 2025): I am also experiencing the same bug.
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@Khaled-Abdelhamid commented on GitHub (Aug 12, 2025):

I think this is related some how
https://github.com/langchain-ai/langgraph/issues/5511

@Khaled-Abdelhamid commented on GitHub (Aug 12, 2025): I think this is related some how https://github.com/langchain-ai/langgraph/issues/5511
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@mck782 commented on GitHub (Aug 18, 2025):

I was seeing this in 2.0.23, when rolled back to 2.0.21, the issue is gone

@mck782 commented on GitHub (Aug 18, 2025): I was seeing this in 2.0.23, when rolled back to 2.0.21, the issue is gone
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@soapun commented on GitHub (Aug 20, 2025):

@mck782

Cause of the problem is metadata: ContextMetadata containing key "writes" with current node updates.

In 2.0.21 metadata was serialized with BasePostgresSaver._dump_metadata -> JsonPlusSerializer.dumps
which works fine with pydantic.BaseModel

In 2.0.23 metadata is serialized with psycopg.types.json.Jsonb
which raises TypeError: Object of type AIMessage is not JSON serializable

@soapun commented on GitHub (Aug 20, 2025): @mck782 Cause of the problem is `metadata: ContextMetadata` containing key `"writes"` with current node updates. In 2.0.21 metadata was [serialized ](https://github.com/langchain-ai/langgraph/blob/checkpointpostgres%3D%3D2.0.21/libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py#L247)with `BasePostgresSaver._dump_metadata` -> `JsonPlusSerializer.dumps` which works fine with `pydantic.BaseModel` In 2.0.23 metadata is [serialized](https://github.com/langchain-ai/langgraph/blob/checkpointpostgres%3D%3D2.0.23/libs/checkpoint-postgres/langgraph/checkpoint/postgres/__init__.py#L331) with `psycopg.types.json.Jsonb` which raises `TypeError: Object of type AIMessage is not JSON serializable`
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@aitor0307 commented on GitHub (Sep 9, 2025):

@soapun

Thanks for your answer, it fixed my many-hour fighting with every aspect of my code until I found your comment.

@aitor0307 commented on GitHub (Sep 9, 2025): @soapun Thanks for your answer, it fixed my many-hour fighting with every aspect of my code until I found your comment.
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@basinary commented on GitHub (Sep 27, 2025):

@soapun

Thanks for your answer, it fixed my many-hour fighting with every aspect of my code until I found your comment.

I am encountering the same issue. How can i select the specific version of metadata in conda, win10 enviroment? I have not found metadata in conda list, but just importlib_metadata 8.7.0. Can you give me some suggestions ?

@basinary commented on GitHub (Sep 27, 2025): > [@soapun](https://github.com/soapun) > > Thanks for your answer, it fixed my many-hour fighting with every aspect of my code until I found your comment. I am encountering the same issue. How can i select the specific version of metadata in conda, win10 enviroment? I have not found metadata in conda list, but just importlib_metadata 8.7.0. Can you give me some suggestions ?
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@basinary commented on GitHub (Oct 4, 2025):

Thank you very much!

@basinary commented on GitHub (Oct 4, 2025): Thank you very much!
yindo commented 2026-02-20 17:42:12 -05:00
Author
Owner
Copy Link
Copy Source

@casparb commented on GitHub (Oct 6, 2025):

Fixed by https://github.com/langchain-ai/langgraph/pull/6236. Release coming soon

@casparb commented on GitHub (Oct 6, 2025): Fixed by https://github.com/langchain-ai/langgraph/pull/6236. Release coming soon
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#875
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?