From d87a91372919e3cc8c42d4b245cac20e3de05140 Mon Sep 17 00:00:00 2001
From: Samy <12219635+touzenesmy@users.noreply.github.com>
Date: Tue, 11 Aug 2026 20:47:11 -0400
Subject: [PATCH] fix(ui): stop stripping the word assistant from rendered text
 (#5974)

* fix: stop stripping the word 'assistant' from rendered text

The QWEN_BARE_MARKER_RE regex in both the Python backend (tool_parsing.py)
and JS frontend (chatRenderer.js) was matching any standalone occurrence of
the word 'assistant' separated by any whitespace, then replacing it with a
space. This caused normal English uses like 'Home assistant' to render as
'Home '.

Fixed by narrowing the word-boundary check from [\t\r\n ] (any whitespace)
to [\r\n] (line boundaries only), so only Qwen-format role-token leaks
(where 'assistant' appears alone on a line) are stripped.

* fix(tests): update bare-marker test expectations for #5971

Move 'x assistant y' from STRIPPED to KEPT (mid-sentence must survive).
Add 'Before\nassistant\nAfter' to STRIPPED (bare-marker on own line).

* fix(ui): strip whitespace-padded assistant role markers

---------

Co-authored-by: samy <samy@users.noreply.github.com>
Co-authored-by: Alexandre Teixeira <alexandremagteixeira@gmail.com>
---
 src/tool_parsing.py                        | 2 +-
 static/js/chatRenderer.js                  | 2 +-
 tests/test_tool_parsing_bare_end_marker.py | 5 ++++-
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/src/tool_parsing.py b/src/tool_parsing.py
index 98dc1b5f6..5b5d283ec 100644
--- a/src/tool_parsing.py
+++ b/src/tool_parsing.py
@@ -193,7 +193,7 @@ _QWEN_ROLE_MARKER_RE = re.compile(r"</?\|(?:assistant|assistan|user|system|tool)
 # one; see #5547. `|end`, `end|`, `|end|` and `/|end|` still strip as before.
 _QWEN_BARE_MARKER_RE = re.compile(
     r"(?:^|[\t\r\n ])(?:/?\|end\||\|end|end\|)(?=[\t\r\n ]|$)|"
-    r"(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)",
+    r"(?:^|[\r\n])[ \t]*assistan(?:t)?[ \t]*(?=[\r\n]|$)",
     re.IGNORECASE,
 )
 
diff --git a/static/js/chatRenderer.js b/static/js/chatRenderer.js
index 1d6e2e4a9..b29909242 100644
--- a/static/js/chatRenderer.js
+++ b/static/js/chatRenderer.js
@@ -481,7 +481,7 @@ const QWEN_ROLE_MARKER_RE = /<\/?\|(?:assistant|assistan|user|system|tool)\|>?|<
 // Keep in sync with _QWEN_BARE_MARKER_RE in src/tool_parsing.py. At least one
 // pipe is required around `end`: with both optional (`\|?end\|?`) this also ate
 // a bare `end` on its own line, breaking Ruby/Lua/shell snippets (#5547).
-const QWEN_BARE_MARKER_RE = /(?:^|[\t\r\n ])(?:\/?\|end\||\|end|end\|)(?=[\t\r\n ]|$)|(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)/gi;
+const QWEN_BARE_MARKER_RE = /(?:^|[\t\r\n ])(?:\/?\|end\||\|end|end\|)(?=[\t\r\n ]|$)|(?:^|[\r\n])[ \t]*assistan(?:t)?[ \t]*(?=[\r\n]|$)/gi;
 // Self-narration about tool results (model echoing stdout/exit_code)
 const TOOL_NARRATION_RE = /(?:The (?:result|output) shows?:?\s*)?-?\s*(?:stdout|stderr|exit_code):\s*.+/gi;
 
diff --git a/tests/test_tool_parsing_bare_end_marker.py b/tests/test_tool_parsing_bare_end_marker.py
index 6167c8dde..703cf616d 100644
--- a/tests/test_tool_parsing_bare_end_marker.py
+++ b/tests/test_tool_parsing_bare_end_marker.py
@@ -34,6 +34,7 @@ KEPT = [
     ("append end", "append end"),
     ("END", "END"),
     ("\nEnd\n", "End"),
+    ("x assistant y", "x assistant y"),          # mid-sentence must survive (#5971)
 ]
 
 # Real markers — at least one pipe, plus the role word — with the exact output
@@ -44,7 +45,9 @@ STRIPPED = [
     ("a /|end| b", "a  b"),
     ("a |end b", "a  b"),
     ("a end| b", "a  b"),
-    ("x assistant y", "x  y"),
+    ("Before\nassistant\nAfter", "Before \nAfter"),   # bare-marker on its own line still stripped
+    ("Before\n  assistant\t \nAfter", "Before \nAfter"),     # whitespace-padded marker still stripped
+    ("Before\n\tassistan  \nAfter", "Before \nAfter"),       # truncated marker variant still stripped
 ]