7 views
-/https://github.com/berriai/litellm/issues/28429
GitHub · issue

#28429 [Bug]: test connect Dashscope model failed

  • State: open
  • Author: @maxzhang2017
  • Labels: bug, llm translation, ui-dashboard

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

A bug happened! the body send to Dashscope has an redundant curly braces

<img width="668" height="754" alt="Image" src="https://github.com/user-attachments/assets/cc149672-1fa7-4e16-b66b-cba3f4f8d296" />

### Steps to Reproduce

1. Add a Dashscope Model 2. test connect

### Relevant log output

```shell litellm.BadRequestError: DashscopeException - No static resource api-openai/v1/chat/completions/chat/completions. stack trace: Traceback (most recent call last): File "/app/.venv/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 930, in acompletion headers, response = await self.make_openai_chat_completion_request( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<4 lines>... ) ^ File "/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/logging_utils.py", line 297, in async_wrapper result = await func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/app/.venv/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 461, in make_openai_c…

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (3 events)
#0 of 0 · 31d19h2m36s ago — entered · #import:https:::github.com:berriai:litellm post #1837
The right-side change spans shared token-counting logic, multimodal content handling, provider-specific accounting, and regression coverage, creating broader compatibility risk. The left-side change is more likely a localized endpoint construction or configuration correction with narrower testing scope.
Implementing the left issue requires coordinated billing-model changes across cost calculation, reservation consistency, cached-token handling, and regression coverage; the right issue is comparatively localized request-path correction.
#0 of 0 · 31d18h58m17s ago — current · #import:https:::github.com:berriai:litellm post #1911
The left issue requires coordinated asynchronous lifecycle, timeout, cancellation, cleanup, and MCP protocol behavior changes with concurrency-sensitive testing. The right issue is comparatively localized to provider request translation or endpoint construction, with narrower validation scope.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search