Skip to content

Preserve literal think markers in thinking-off histories #967

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bradhilton merged 2 commits into from
Sep 25, 2026
+650 −0
Merged

Preserve literal think markers in thinking-off histories #967

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0c74955
fix: Preserve literal think markers in thinking-off histories
bradhilton Sep 25, 2026
e65e4b1
test: Cover the preceding boundary of literal thinking-off content
bradhilton Sep 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 53 additions & 0 deletions src/art/trajectories/_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4464,6 +4464,58 @@ def _source_covers_complete_sampled_message(
) == normalize_chat_message(projected[0])


def _preserve_literal_thinking_off_content(
history: ChatCompletionsHistory,
messages: list[dict[str, Any]],
template: object,
kwargs: Mapping[str, object],
) -> None:
# This Qwen3.5 template treats any </think> in unstructured content as a
# reasoning separator, even with thinking disabled. Restrict the render-copy
# adaptation to its exact preserved template; other templates may interpret
# an empty reasoning_content field differently.
if (
not isinstance(template, str)
or sha256(template.encode()).hexdigest()
!= "098047d425a6673b1fe1a82a197a481616e53a283beaa8cb76cbb74d38ca6644"
or kwargs.get("enable_thinking") is not False
or kwargs.get("preserve_thinking") is not True
):
return
for message, source in zip(messages, history.message_sources, strict=True):
if (
source is None
or not isinstance(source.exchange, ChatCompletionsExchange)
or source.choice_index is None
or message.get("role") != "assistant"
or not isinstance(content := message.get("content"), str)
or "</think>" not in content
):
continue
request_kwargs = source.exchange.request.get("chat_template_kwargs")
if (
not isinstance(request_kwargs, Mapping)
or request_kwargs.get("enable_thinking") is not False
):
continue
choice = _chat_choice(source)
# Visible-only histories may omit structured reasoning present in the
# source response. Preserve both that source and normalized aliases.
if any(
value is not None and not (isinstance(value, str) and value == "")
for value in (
message.get("reasoning"),
message.get("reasoning_content"),
_field(choice.message, "reasoning"),
_field(choice.message, "reasoning_content"),
)
):
continue
prompt, output, _ = _chat_choice_tokens(choice, source.exchange.response)
if prompt is not None and output is not None:
message["reasoning_content"] = ""


def _tokenize_chat_view(
history: ChatCompletionsHistory,
*,
Expand Down Expand Up @@ -4510,6 +4562,7 @@ def _tokenize_chat_view(
**default_chat_template_kwargs_for_template(template),
**explicit_kwargs,
}
_preserve_literal_thinking_off_content(history, messages, template, kwargs)
ends_with_assistant = bool(messages) and messages[-1].get("role") == "assistant"
segmented = False

Expand Down
154 changes: 154 additions & 0 deletions tests/fixtures/qwen35_preserved_thinking.jinja
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,154 @@
{%- set preserve_thinking = preserve_thinking | default(true) -%}{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if content %}
{{- '\n\n' + content }}
{%- endif %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
{{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
{%- set content = (render_content(message.content, true) if preserve_thinking and message.role == 'assistant' else render_content(message.content, true)|trim) %}
{%- if message.role == "system" %}
{%- if not loop.first %}
{{- raise_exception('System message must be at the beginning.') }}
{%- endif %}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if not preserve_thinking or message.reasoning_content is not string %}{%- set reasoning_content = reasoning_content|trim %}{%- endif %}
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + ('</think>\n\n' if preserve_thinking and message.reasoning_content is string and reasoning_content else '\n</think>\n\n') + content }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is defined %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- else %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}
Loading
Loading