7 views
-/https://github.com/berriai/litellm/issues/29675
GitHub · issue

#29675 [Bug]: not all models for github_copilot are listed

  • State: open
  • Author: @theodiem
  • Labels: bug, proxy, llm translation

### Check for existing issues

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

### What happened?

Not all the models/reasoning are listed for github_copilot provider. Here is the list from vscode model selector:

<img width="783" height="425" alt="Image" src="https://github.com/user-attachments/assets/f6787a89-4b58-48c8-9f2a-3c7488654236" /> And, for example, gpt-5 mini, gpt-5.4, gpt-5.4-mini supports reasoning.

Here is what I get from litellm:

<img width="895" height="379" alt="Image" src="https://github.com/user-attachments/assets/7805f7b1-1d0a-439e-8e61-add8d1ef2260" />

I can configure gpt-5.4 with: ``` model_list: - model_name: gpt-5.4 litellm_params: model: github_copilot/gpt-5.4 order: 10 model_info: mode: responses ```

But still i get errors about not suppoting tool calls with reasoning, even if I set base_model to either gpt-5.4 or azure_ai/gpt-5.4

### Steps to Reproduce

1. Try to add model with github_copilot provider

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

Proxy

### What LiteLLM version are you on ?

v1.87.0

### Twitter / LinkedIn details

_No response_

GitHub resolver

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

Refresh page
vote history (2 events)
#0 of 0 · 31d18h7m46s ago — entered · #import:https:::github.com:berriai:litellm post #2725
The left issue is harder because it likely spans provider integration, model metadata, capability detection, and proxy validation across several variants. The right appears more localized to diagnosing and correcting one provider's streaming behavior.
#0 of 0 · 31d17h39m40s ago — current · #import:https:::github.com:berriai:litellm post #3218
34705 is harder because it requires a coordinated security fix across multiple logging implementations, preserving diagnostics while reliably redacting secrets and neutralizing control characters, plus broad regression coverage. 29675 is comparatively narrower provider-specific metadata and capability mapping work.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search