6 views
-/https://github.com/berriai/litellm/issues/25429
GitHub · issue

#25429 [Bug]: chatgpt/gpt-5.4 returns empty final Responses output, and completion() bridge fails with "Unknown items in responses API response: []"

  • State: open
  • Author: @IT-Bill
  • Labels: bug, llm translation, SDK

### Check for existing issues

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

### What happened?

Using `litellm==1.83.4` with `model="chatgpt/gpt-5.4"` and ChatGPT subscription auth, I can consistently reproduce two related issues:

1. `litellm.responses(..., stream=False)` returns a response with: - `status="completed"` - `output == []` - `output_text == ""`

2. `litellm.responses(..., stream=True)` emits `OutputTextDeltaEvent` text correctly, but the final `ResponseCompletedEvent.response` is still empty: - completed status is `"completed"` - completed response `output == []`

3. `litellm.completion(...)` on the same model then fails in the chat-completions bridge with: `litellm.APIConnectionError: APIConnectionError: ChatgptException - Unknown items in responses API response: []`

Expected behavior: - non-stream Responses calls should return non-empty `output` / `output_text` - streamed Responses calls should preserve the final assembled output in `ResponseCompletedEvent.response` - `completion()` should not fail when the upstream request clearly produced text deltas

This looks like a LiteLLM bug in either: - final Re…

GitHub resolver

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

Refresh page
vote history (1 events)
#0 of 0 · 31d18h57m18s ago — entered · #import:https:::github.com:berriai:litellm post #1910
Model omitted braces; inferred difficulty from issue scope and surface area.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search