Modifying body in langfuse_filter_pipeline Causes 400 Bad Request Errors in Open-WebUI #137

New Issue

2026-02-15T19:16:13-05:00

yindo commented

2026-02-15 19:16:13 -05:00

Originally created by @mcdorians on GitHub (Oct 6, 2024).

Issue Summary

When using the langfuse_filter_pipeline in Open-WebUI, modifying the part where the body dictionary gets extended with chat_id within the inlet or outlet methods causes a 400 Bad Request error from the downstream API (https://<openai_api_url>/chat/completions). As a result, non-streamed completions like tool requests fail and are ignored because the completions fails..

Steps to Reproduce

Install and activate the langfuse_filter_pipeline.py in Open-WebUI.
Use a tool that triggers a non-streamed completion (e.g., a tool request).
Observe that a 400 Bad Request error occurs in the Open-WebUI logs.
The tool does not function as expected due to this error.

Code Causing the Issue

The following code in langfuse_filter_pipeline.py appears to cause the error:

if "chat_id" not in body:
    unique_id = f"SYSTEM MESSAGE {uuid.uuid4()}"
    body["chat_id"] = unique_id
    print(f"chat_id was missing, set to: {unique_id}")

Even adding any arbitrary key to body every time, such as:

body["my_stupid_test"] = "bla" # in this case every completion request will lead to 400

leads to the same 400 Bad Request error.

Observed Behavior

When chat_id is not set (which is common with non-streamed completions like tool requests), modifying the body in the filter results in a 400 Bad Request error from the downstream API.
The tools are ignored because the requests fail.
Skipping the modification of body avoids the error but may not be ideal for logging purposes.

Expected Behavior

Modifying the body within the filter should not cause a 400 Bad Request error.
Non-streamed completions and tool requests should function correctly even when body is modified for logging or tracking purposes.

Question

Is modifying the body in the filter pipeline not allowed?
Is this behavior expected, or is it a bug in the pipelines framework?
How can we log necessary information using the filter without causing downstream API errors?

Logs

ERROR [open_webui.main] Error: 400: External: 400, message='Bad Request', url='https://<url>/chat/completions'

Additional Information

The issue consistently occurs whenever the body is modified in the filter.
Skipping the modification (e.g., by returning early if chat_id is not present) prevents the error but also skips necessary logging.

if not body.get("chat_id"):
      print("Skipping inlet processing because no chat_id.")
      return body

Request

Please investigate this issue. It seems that modifying the body in the langfuse_filter_pipeline causes downstream API requests to fail with a 400 Bad Request error.

Originally created by @mcdorians on GitHub (Oct 6, 2024). **Issue Summary** When using the `langfuse_filter_pipeline` in Open-WebUI, modifying the part where the `body` dictionary gets extended with `chat_id` within the `inlet` or `outlet` methods causes a `400 Bad Request` error from the downstream API (`https://<openai_api_url>/chat/completions`). As a result, non-streamed completions like tool requests fail and are ignored because the completions fails.. **Steps to Reproduce** 1. Install and activate the `langfuse_filter_pipeline.py` in Open-WebUI. 2. Use a tool that triggers a non-streamed completion (e.g., a tool request). 3. Observe that a `400 Bad Request` error occurs in the Open-WebUI logs. 4. The tool does not function as expected due to this error. **Code Causing the Issue** The following code in `langfuse_filter_pipeline.py` appears to cause the error: ```python if "chat_id" not in body: unique_id = f"SYSTEM MESSAGE {uuid.uuid4()}" body["chat_id"] = unique_id print(f"chat_id was missing, set to: {unique_id}") ``` Even adding any arbitrary key to `body` every time, such as: ```python body["my_stupid_test"] = "bla" # in this case every completion request will lead to 400 ``` leads to the same `400 Bad Request` error. **Observed Behavior** - When `chat_id` is not set (which is common with non-streamed completions like tool requests), modifying the `body` in the filter results in a `400 Bad Request` error from the downstream API. - The tools are ignored because the requests fail. - Skipping the modification of `body` avoids the error but may not be ideal for logging purposes. **Expected Behavior** - Modifying the `body` within the filter should not cause a `400 Bad Request` error. - Non-streamed completions and tool requests should function correctly even when `body` is modified for logging or tracking purposes. **Question** - Is modifying the `body` in the filter pipeline not allowed? - Is this behavior expected, or is it a bug in the pipelines framework? - How can we log necessary information using the filter without causing downstream API errors? **Logs** ``` ERROR [open_webui.main] Error: 400: External: 400, message='Bad Request', url='https://<url>/chat/completions' ``` **Additional Information** - The issue consistently occurs whenever the `body` is modified in the filter. - Skipping the modification (e.g., by returning early if `chat_id` is not present) prevents the error but also skips necessary logging. ```python if not body.get("chat_id"): print("Skipping inlet processing because no chat_id.") return body ``` **Request** Please investigate this issue. It seems that modifying the `body` in the `langfuse_filter_pipeline` causes downstream API requests to fail with a `400 Bad Request` error.

yindo commented

2026-02-15 19:16:14 -05:00

@cspengler-plexxis commented on GitHub (Oct 16, 2024):

This happens in a custom pipeline I've written as well. It would be super useful to be able to add keys to the body dict within the filter (in my case, I want to append context retrieved by the RAG process in the inlet, and then access that context in the outlet so I can log it in a database along with all the other details of the user-assistant exchange).

@cspengler-plexxis commented on GitHub (Oct 16, 2024): This happens in a custom pipeline I've written as well. It would be super useful to be able to add keys to the body dict within the filter (in my case, I want to append context retrieved by the RAG process in the inlet, and then access that context in the outlet so I can log it in a database along with all the other details of the user-assistant exchange).

yindo referenced this issue

2026-02-15 20:15:06 -05:00

[PR #137] [MERGED] enh: Add Valves support to MLX Pipeline #322

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: open-webui/pipelines#137