[Bugfix] Fix the issue with interleaved thinking when using streaming (#30033)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Chauncey 2025-12-04 19:11:59 +08:00 committed by GitHub
parent e96a6a6dca
commit 6796ce8bdb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 19 additions and 2 deletions

View File

@ -112,7 +112,7 @@ class TestBaseThinkingReasoningParserMethods:
"""Test the is_reasoning_end method."""
parser = TestThinkingReasoningParser(test_tokenizer)
end_token_id = parser.end_token_id
start_token_id = parser.start_token_id
# Test with end token present
assert parser.is_reasoning_end([1, 2, end_token_id, 4]) is True
@ -122,6 +122,16 @@ class TestBaseThinkingReasoningParserMethods:
# Test with empty list
assert parser.is_reasoning_end([]) is False
# Test with interleaved thinking
assert parser.is_reasoning_end([1, start_token_id, 2, end_token_id]) is True
assert parser.is_reasoning_end([1, start_token_id, 2, 3]) is False
assert (
parser.is_reasoning_end(
[1, start_token_id, 2, end_token_id, 2, 2, start_token_id]
)
is False
)
def test_extract_content_ids(self, test_tokenizer):
"""Test the extract_content_ids method."""
parser = TestThinkingReasoningParser(test_tokenizer)

View File

@ -64,8 +64,15 @@ class BaseThinkingReasoningParser(ReasoningParser):
)
def is_reasoning_end(self, input_ids: list[int]) -> bool:
start_token_id = self.start_token_id
end_token_id = self.end_token_id
return any(input_id == end_token_id for input_id in reversed(input_ids))
for i in range(len(input_ids) - 1, -1, -1):
if input_ids[i] == start_token_id:
return False
if input_ids[i] == end_token_id:
return True
return False
def extract_content_ids(self, input_ids: list[int]) -> list[int]:
"""