From e392c27f7e6981313198c078dd6b3ef01aeb4b1f Mon Sep 17 00:00:00 2001
From: 04cb <0x04cb@gmail.com>
Date: Sat, 11 Apr 2026 00:47:23 +0800
Subject: [PATCH] fix(utils): anchor unclosed think-tag regex to string start
 (#3004)

---
 nanobot/utils/helpers.py        |  4 ++--
 tests/utils/test_strip_think.py | 29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/nanobot/utils/helpers.py b/nanobot/utils/helpers.py
index 3b4f9f25a..1bfd9f18b 100644
--- a/nanobot/utils/helpers.py
+++ b/nanobot/utils/helpers.py
@@ -17,10 +17,10 @@ from loguru import logger
 def strip_think(text: str) -> str:
     """Remove thinking blocks and any unclosed trailing tag."""
     text = re.sub(r"<think>[\s\S]*?</think>", "", text)
-    text = re.sub(r"<think>[\s\S]*$", "", text)
+    text = re.sub(r"^\s*<think>[\s\S]*$", "", text)
     # Gemma 4 and similar models use <thought>...</thought> blocks
     text = re.sub(r"<thought>[\s\S]*?</thought>", "", text)
-    text = re.sub(r"<thought>[\s\S]*$", "", text)
+    text = re.sub(r"^\s*<thought>[\s\S]*$", "", text)
     return text.strip()
 
 
diff --git a/tests/utils/test_strip_think.py b/tests/utils/test_strip_think.py
index 6710dfc93..5828c6d1f 100644
--- a/tests/utils/test_strip_think.py
+++ b/tests/utils/test_strip_think.py
@@ -34,3 +34,32 @@ class TestStripThinkTag:
 
     def test_empty_string(self):
         assert strip_think("") == ""
+
+
+class TestStripThinkFalsePositive:
+    """Ensure mid-content <think>/<thought> tags are NOT stripped (#3004)."""
+
+    def test_backtick_think_tag_preserved(self):
+        text = "*Think Stripping:* A new utility to strip `<think>` tags from output."
+        assert strip_think(text) == text
+
+    def test_prose_think_tag_preserved(self):
+        text = "The model emits <think> at the start of its response."
+        assert strip_think(text) == text
+
+    def test_code_block_think_tag_preserved(self):
+        text = "Example:\n```\ntext = re.sub(r\"<think>[\\s\\S]*\", \"\", text)\n```\nDone."
+        assert strip_think(text) == text
+
+    def test_backtick_thought_tag_preserved(self):
+        text = "Gemma 4 uses `<thought>` blocks for reasoning."
+        assert strip_think(text) == text
+
+    def test_prefix_unclosed_think_still_stripped(self):
+        assert strip_think("<think>reasoning without closing") == ""
+
+    def test_prefix_unclosed_think_with_whitespace(self):
+        assert strip_think("  <think>reasoning...") == ""
+
+    def test_prefix_unclosed_thought_still_stripped(self):
+        assert strip_think("<thought>reasoning without closing") == ""