Thread runs sometimes throws HttpException, Graph 'xxx' not found

[Jackoder]

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

import requests
import time
import logging

# Configure logging
logging.basicConfig(
    filename='thread_process.log',
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)

console = logging.StreamHandler()
console.setLevel(logging.INFO)
formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
console.setFormatter(formatter)
logging.getLogger('').addHandler(console)

def log_request_response(response):
    logging.info(f"Request URL: {response.request.url}")
    logging.info(f"Request Method: {response.request.method}")
    logging.info(f"Request Headers: {response.request.headers}")
    if response.request.body:
        logging.info(f"Request Body: {response.request.body}")
    logging.info(f"Response Status Code: {response.status_code}")
    logging.info(f"Response Headers: {response.headers}")
    logging.info(f"Response Body: {response.text}")

import uuid

def create_thread():
    # thread_id = str(uuid.uuid4())  # Generate a UUID for thread_id
    url = "http://127.0.0.1:8123/threads"
    payload = {
    }
    response = requests.post(url, json=payload)
    log_request_response(response)
    response.raise_for_status()
    thread_id = response.json()["thread_id"]
    logging.info(f"Thread created with ID: {thread_id}")
    return thread_id

def run_thread(thread_id):
    url = f"http://127.0.0.1:8123/threads/{thread_id}/runs/wait"
    payload = {
        "assistant_id": "0676914a-25a7-595a-a130-6f9e1ad87f7d",
        "input": {
            "knowledge": "Camera",
            "node": "Rule"
        },
        "after_seconds": 1
    }
    response = requests.post(url, json=payload)
    log_request_response(response)
    response.raise_for_status()
    run_id = response.json()["run_id"]
    logging.info(f"Thread run initiated with Run ID: {run_id}")
    return run_id

def get_thread_status(thread_id):
    url = f"http://127.0.0.1:8123/threads/{thread_id}/runs"
    response = requests.get(url)
    log_request_response(response)
    response.raise_for_status()
    status = response.json()[0]["status"]
    logging.info(f"Current status: {status}")
    return status

def get_thread_result(thread_id):
    url = f"http://127.0.0.1:8123/threads/{thread_id}"
    response = requests.get(url)
    log_request_response(response)
    response.raise_for_status()
    result = response.json()
    logging.info(f"Thread result: {result}")
    return result

def execute_test():
    try:
        thread_id = create_thread()
        retry_count = 0
        run_id = run_thread(thread_id)
        status = get_thread_status(thread_id)
        while status != "success":
            if status == "error":
                retry_count += 1
                if retry_count > 3:
                    logging.error("Thread run failed after 3 retries.")
                    return False
                logging.warning(f"Thread run encountered an error. Retrying {retry_count}/3...")
                run_id = run_thread(thread_id)  # Retry running the thread
            # time.sleep(2)
            status = get_thread_status(thread_id)
        result = get_thread_result(thread_id)
        return True
    except Exception as e:
        logging.error(f"Exception occurred: {e}")
        return False

def main():
    success_count = 0
    total_runs = 10
    for i in range(total_runs):
        logging.info(f"Starting test run {i+1}/{total_runs}")
        if execute_test():
            success_count += 1
        logging.info(f"Test run {i+1}/{total_runs} completed")

    success_rate = (success_count / total_runs) * 100
    logging.info(f"Success rate: {success_rate}%")

if __name__ == "__main__":
    main()

Error Message and Stack Trace (if applicable)

2025-01-21 12:33:33,813 - INFO - Request URL: http://127.0.0.1:8123/threads
2025-01-21 12:33:33,813 - INFO - Request Method: POST
2025-01-21 12:33:33,813 - INFO - Request Headers: {'User-Agent': 'python-requests/2.32.3', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive', 'Content-Length': '2', 'Content-Type': 'application/json'}
2025-01-21 12:33:33,813 - INFO - Request Body: b'{}'
2025-01-21 12:33:33,813 - INFO - Response Status Code: 200
2025-01-21 12:33:33,813 - INFO - Response Headers: {'date': 'Tue, 21 Jan 2025 04:33:33 GMT', 'server': 'uvicorn', 'content-length': '220', 'content-type': 'application/json'}
2025-01-21 12:33:33,813 - INFO - Response Body: {"thread_id":"2a6608cc-ec49-41f6-8926-a249dda7ff97","created_at":"2025-01-21T12:33:34.919186+08:00","updated_at":"2025-01-21T12:33:34.919186+08:00","metadata":{},"status":"idle","config":{},"values":null,"interrupts":{}}
2025-01-21 12:33:33,813 - INFO - Thread created with ID: 2a6608cc-ec49-41f6-8926-a249dda7ff97
2025-01-21 12:33:35,551 - INFO - Request URL: http://127.0.0.1:8123/threads/2a6608cc-ec49-41f6-8926-a249dda7ff97/runs/wait
2025-01-21 12:33:35,551 - INFO - Request Method: POST
2025-01-21 12:33:35,552 - INFO - Request Headers: {'User-Agent': 'python-requests/2.32.3', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive', 'Content-Length': '126', 'Content-Type': 'application/json'}
2025-01-21 12:33:35,552 - INFO - Request Body: b'{"assistant_id": "0676914a-25a7-595a-a130-6f9e1ad87f7d", "input": {"knowledge": "Camera", "node": "Rule"}, "after_seconds": 1}'
2025-01-21 12:33:35,552 - INFO - Response Status Code: 200
2025-01-21 12:33:35,552 - INFO - Response Headers: {'date': 'Tue, 21 Jan 2025 04:33:33 GMT', 'server': 'uvicorn', 'location': '/threads/2a6608cc-ec49-41f6-8926-a249dda7ff97/runs/1efd7b0d-fa56-665c-a80c-a655ff544eea/join', 'content-type': 'application/json', 'transfer-encoding': 'chunked'}
2025-01-21 12:33:35,553 - INFO - Response Body: {"__error__":{"error":"HTTPException","message":"404: Graph 'rule' not found"}}
2025-01-21 12:33:35,553 - ERROR - Exception occurred: 'run_id'

Description

After I finished deploying using Docker, the Runs API sometimes throws a Graph 'rule' not found error, with an error rate of about 20%. Is there a problem somewhere, and how should it be resolved?

https://langchain-ai.github.io/langgraph/how-tos/deploy-self-hosted/#using-docker

System Info

System Information

OS: Linux
OS Version: #1 SMP Tue Nov 5 00:21:55 UTC 2024
Python Version: 3.11.11 (main, Dec 4 2024, 08:55:08) [GCC 9.4.0]

Package Information

langchain_core: 0.3.30
langchain: 0.3.12
langchain_community: 0.3.10
langsmith: 0.1.147
langchain_anthropic: 0.3.0
langchain_fireworks: 0.2.5
langchain_openai: 0.3.0
langchain_text_splitters: 0.3.3
langchainhub: 0.1.21
langgraph_api: 0.0.15
langgraph_cli: 0.1.65
langgraph_license: Installed. No version info available.
langgraph_sdk: 0.1.48
langgraph_storage: Installed. No version info available.
langserve: 0.3.0

Other Dependencies

aiohttp: 3.11.10
anthropic: 0.40.0
async-timeout: Installed. No version info available.
click: 8.1.7
cryptography: 43.0.3
dataclasses-json: 0.6.7
defusedxml: 0.7.1
fastapi: 0.115.6
fireworks-ai: 0.15.10
httpx: 0.28.1
httpx-sse: 0.4.0
jsonpatch: 1.33
jsonschema-rs: 0.25.1
langgraph: 0.2.63
langgraph-checkpoint: 2.0.10
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
openai: 1.59.7
orjson: 3.10.12
packaging: 24.2
pydantic: 2.10.3
pydantic-settings: 2.6.1
pyjwt: 2.10.1
python-dotenv: 1.0.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
sse-starlette: 2.1.3
starlette: 0.41.3
structlog: 24.4.0
tenacity: 8.5.0
tiktoken: 0.8.0
types-requests: 2.32.0.20241016
typing-extensions: 4.12.2
uvicorn: 0.32.1
watchfiles: 1.0.0