mirror of
https://github.com/openai/codex.git
synced 2026-11-10 21:00:47 +00:00
Add audio output support to dynamic tools and code mode (#34080)
## What changed - Add `inputAudio` content items to dynamic tool responses, app-server events, thread history, and generated protocol schemas. - Add an `audio()` code-mode helper that accepts inline data URLs, audio URL objects, and MCP audio blocks. - Convert MCP audio blocks into model input when audio is supported, and replace unsupported audio with an explanatory text item. - Reject non-data audio URLs and track audio item counts in dynamic tool analytics. ## Testing - Cover audio serialization, protocol round trips, thread-history conversion, MCP modality filtering, code-mode helper inputs, and invalid URL handling. GitOrigin-RevId: 1ed52a8f9c62d4840fb71c5ec736b4a3566243d6
This commit is contained in:
@@ -42,6 +42,9 @@ impl IntoProtocol<FunctionCallOutputContentItem>
|
||||
.or(Some(DEFAULT_IMAGE_DETAIL)),
|
||||
}
|
||||
}
|
||||
codex_code_mode::FunctionCallOutputContentItem::InputAudio { audio_url } => {
|
||||
FunctionCallOutputContentItem::InputAudio { audio_url }
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user