Qwen 3.8-27b context usage is about 10x of 3.6-27b
Using a "medium" level of reasoning effort (higher levels are excessive), I noticed that context usage in the new version of Qwen 3.8-27b is about 10 times higher than in Qwen 3.6-27b. Has anyone else encountered the same problem? Do you have any suggestions for reducing usage?
try with reasoning-budget = 2048
These are the Thinking Level supported by pi-agent
- off : No reasoning
- minimal : Very brief reasoning (~1k tokens)
- low : Light reasoning (~2k tokens)
- medium : Moderate reasoning (~8k tokens)
- high : Deep reasoning (~16k tokens)
- xhigh : Extra-high reasoning (~32k tokens)
- max : Maximum reasoning
so you are suggesting to set reasoning effort to "low", no good news 😟
Even with the reasoning "medium" it produces hilariously wrong answers to some logical questions. With reasoning "max" it replies right after spending tens of thousands of tokens.
My first impression was influenced by the fact that I hadn't forced any reasoning effort. Without this, Qwen 3.8 never finishes reasoning and consumes an excessive number of tokens, only to obtain an answer that would have been possible with much, much less tokens (the default behavior of Qwen 3.6). Forcing the reasoning level to "medium" in pi-agent improved the situation, and now, with the same prompt, Qwen 3.8 consumes "only" 25% more tokens than Qwen 3.6.
Below are the test screenshots.
Qwen 3.8
Qwen 3.6
Same issue here... Basically 80% of the context is now thinking and the rest is for the output... Which is not a lot left for actually coding ...
{%- 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 %}
{%- set sysns = namespace(count=0, text='') %}
{%- for message in messages %}
{%- if sysns.count == loop.index0 and (message.role == 'system' or message.role == 'developer') %}
{%- set sys_content = render_content(message.content, false, true)|trim %}
{%- if sys_content %}
{%- set sysns.text = sysns.text + ('\n' if sysns.text else '') + sys_content %}
{%- endif %}
{%- set sysns.count = sysns.count + 1 %}
{%- endif %}
{%- endfor %}
{%- set num_sys = sysns.count %}
{%- set merged_system = sysns.text %}
{%- set reasoning_instructions = '' %}
{%- if enable_thinking is undefined or enable_thinking is true %}
{%- set resolved_reasoning_effort = reasoning_effort|default('medium') %}
{%- if resolved_reasoning_effort not in ('xhigh', 'high', 'medium', 'low') %}
{{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are medium (default), low, high, and xhigh.') }}
{%- endif %}
{%- if resolved_reasoning_effort == 'xhigh' %}
{%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think exceptionally deeply through the task, exhaustively validate all edge cases and assumptions, explore alternative paths, and prioritize absolute precision, consistency, and clarity.' %}
{%- elif resolved_reasoning_effort == 'high' %}
{%- set reasoning_instructions = 'Reasoning effort is set to high. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
{%- elif resolved_reasoning_effort == 'medium' %}
{%- set reasoning_instructions = '' %}
{%- elif resolved_reasoning_effort == 'low' %}
{%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
{%- endif %}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{%- if reasoning_instructions %}
{{- reasoning_instructions + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou have access to the following functions:\n\n" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...> block must be nested within 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' }}
{%- if merged_system %}
{{- '\n\n' + merged_system }}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if merged_system %}
{{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + merged_system + '<|im_end|>\n' }}
{%- elif reasoning_instructions %}
{{- '<|im_start|>system\n' + reasoning_instructions + '<|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('') and content.endswith('')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if loop.index0 >= num_sys %}
{%- set content = render_content(message.content, true)|trim %}
{%- if message.role == "system" or message.role == "developer" %}
{{- raise_exception('System message must be at the beginning.') }}
{%- 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 %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
{{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\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 tool_call.name is not defined or tool_call.name is none %}
{{- raise_exception('Tool call is missing a function name.') }}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is mapping %}
{%- 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\n' }}
{%- endfor %}
{%- elif tool_call.arguments is string %}
{%- if tool_call.arguments|trim %}
{{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" were passed as a JSON string. Parse them into an object before calling apply_chat_template.') }}
{%- endif %}
{%- elif tool_call.arguments is defined and tool_call.arguments is not none %}
{{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" must be an object/mapping or a JSON string.') }}
{%- endif %}
{{- '\n' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n\n' }}
{{- content }}
{{- '\n' }}
{%- 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 %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '\n\n\n\n' }}
{%- else %}
{{- '\n' }}
{%- endif %}
{%- endif %}
I had the model go through and make some changes to the template said it to medium default now and fix some issue where the default behavior was to switch high to extra high idk seems to work so far
Same issue. Even trying to benchmarking it is being a pain because it always runs out of steps, or tokens, or ... something.
Same