From 005fa017566177e1a66d75eba7908d326c5acd60 Mon Sep 17 00:00:00 2001 From: Fede Kamelhar Date: Mon, 3 Aug 2026 09:45:23 -0400 Subject: [PATCH] docs: document `reasoning_content` output removal as a breaking client change (#50624) Signed-off-by: fede-kamel Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> --- docs/features/reasoning_outputs.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/features/reasoning_outputs.md b/docs/features/reasoning_outputs.md index 9495c4672c..fbd23fcdd5 100644 --- a/docs/features/reasoning_outputs.md +++ b/docs/features/reasoning_outputs.md @@ -6,6 +6,7 @@ Reasoning models return an additional `reasoning` field in their outputs, which !!! warning `reasoning` used to be called `reasoning_content`. To migrate, directly replace `reasoning_content` with `reasoning`. + It is important that you also update your client code. Otherwise, your client code could silently read an empty `reasoning_content`, even when `reasoning` is populated. ## Supported Models @@ -105,7 +106,7 @@ Streaming chat completions are also supported for reasoning models. The `reasoni } ``` -OpenAI Python client library does not officially support `reasoning` attribute for streaming output. But the client supports extra attributes in the response. You can use `hasattr` to check if the `reasoning` attribute is present in the response. For example: +OpenAI Python client library does not officially support `reasoning` attribute for streaming output. But the client supports extra attributes in the response. You can use `getattr` to check if the `reasoning` attribute is present in the response. For example: ??? code