From c0aa06f300e5a38afcea6de79330f76b0d01c934 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Sat, 28 Mar 2026 13:41:23 -0700
Subject: [PATCH] fix(test): update streaming test to match PR #3566 behavior
 change (#3574)

PR #3566 intentionally routes suppressed content to stream_delta_callback
when tool calls are present, so reasoning tag extraction can fire during
streaming. The test was still asserting the old behavior where content
after tool calls was fully suppressed from the callback.

Updated the assertion to match: content IS delivered to the callback
(for tag extraction), with display-level suppression handled by the
CLI's _stream_delta.
---
 tests/test_streaming.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tests/test_streaming.py b/tests/test_streaming.py
index f50510f0a..107a8a4d4 100644
--- a/tests/test_streaming.py
+++ b/tests/test_streaming.py
@@ -362,9 +362,11 @@ class TestStreamingCallbacks:
 
         # Text before tool call IS fired (we don't know yet it will have tools)
         assert "thinking..." in deltas
-        # Text after tool call is NOT fired
-        assert " more text" not in deltas
-        # But content is still accumulated in the response
+        # Text after tool call IS still routed to stream_delta_callback so that
+        # reasoning tag extraction can fire (PR #3566).  Display-level suppression
+        # of non-reasoning text happens in the CLI's _stream_delta, not here.
+        assert " more text" in deltas
+        # Content is still accumulated in the response
         assert response.choices[0].message.content == "thinking... more text"