biondizzle
9051c610d2
The streaming path was using is_reasoning_end(previous_token_ids) to check if reasoning had ended. On multi-turn conversations, previous_token_ids includes the entire chat history, including think-end tokens from prior assistant messages. This caused the parser to incorrectly think reasoning was already over before the model generated anything, routing all thinking text to content instead of reasoning. Fix: Replace the token-ID-based check with a text-based state variable (_reasoning_ended) that tracks reasoning end based solely on what the model has generated in the current turn. Reset on each new generation. Also includes the chat template for reference.
96 lines
3.4 KiB
Django/Jinja
96 lines
3.4 KiB
Django/Jinja
{%- macro render_content(msg) -%}
|
|
{%- set c = msg.get('content') -%}
|
|
{%- if c is string -%}
|
|
{{ c }}
|
|
{%- elif c is not none -%}
|
|
{% for content in c -%}
|
|
{% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
|
|
<|media_start|>image<|media_content|><|media_pad|><|media_end|>
|
|
{% else -%}
|
|
{{ content['text'] }}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{%- endif -%}
|
|
{%- endmacro -%}
|
|
|
|
{% macro set_roles(message) -%}
|
|
{%- set role_name = message.get('name') or message['role'] -%}
|
|
{%- if message['role'] == 'user' -%}
|
|
<|im_user|>{{role_name}}<|im_middle|>
|
|
{%- elif message['role'] == 'assistant' -%}
|
|
<|im_assistant|>{{role_name}}<|im_middle|>
|
|
{%- else -%}
|
|
<|im_system|>{{role_name}}<|im_middle|>
|
|
{%- endif -%}
|
|
{%- endmacro -%}
|
|
|
|
|
|
{%- macro render_toolcalls(message) -%}
|
|
<|tool_calls_section_begin|>
|
|
{%- for tool_call in message['tool_calls'] -%}
|
|
{%- set formatted_id = tool_call['id'] -%}
|
|
<|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
|
|
{%- endfor -%}
|
|
<|tool_calls_section_end|>
|
|
{%- endmacro -%}
|
|
|
|
|
|
{# Find last non-tool-call assisitant message #}
|
|
{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
|
|
{%- for idx in range(messages|length-1, -1, -1) -%}
|
|
{%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
|
|
{%- set ns.last_non_tool_call_assistant_msg = idx -%}
|
|
{%- break -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
|
|
{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
|
|
{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
|
|
{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
|
|
|
|
{%- if tools -%}
|
|
<|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
|
|
{%- endif -%}
|
|
|
|
{%- for message in hist_msgs -%}
|
|
{%- if loop.first and messages[0]['role'] != 'system' -%}
|
|
<|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
|
|
{%- endif -%}
|
|
{{set_roles(message)}}
|
|
{%- if message['role'] == 'assistant' -%}
|
|
<think></think>{{render_content(message)}}
|
|
{%- if message.get('tool_calls') -%}
|
|
{{render_toolcalls(message)}}
|
|
{%- endif -%}
|
|
{%- elif message['role'] == 'tool' -%}
|
|
{%- set tool_call_id = message.tool_call_id -%}
|
|
## Return of {{ tool_call_id }}
|
|
{{render_content(message)}}
|
|
{%- elif message['content'] is not none -%}
|
|
{{render_content(message)}}
|
|
{%- endif -%}
|
|
<|im_end|>
|
|
{%- endfor -%}
|
|
|
|
{%- for message in suffix_msgs -%}
|
|
{{set_roles(message)}}
|
|
{%- if message['role'] == 'assistant' -%}
|
|
{%- set rc = message.get('reasoning_content', '') -%}
|
|
<think>{{rc}}</think>{{render_content(message)}}
|
|
{%- if message.get('tool_calls') -%}
|
|
{{render_toolcalls(message)}}
|
|
{%- endif -%}
|
|
{%- elif message['role'] == 'tool' -%}
|
|
{%- set tool_call_id = message.tool_call_id -%}
|
|
## Return of {{ tool_call_id }}
|
|
{{render_content(message)}}
|
|
{%- elif message['content'] is not none -%}
|
|
{{render_content(message)}}
|
|
{%- endif -%}
|
|
<|im_end|>
|
|
{%- endfor -%}
|
|
|
|
|
|
{%- if add_generation_prompt -%}
|
|
<|im_assistant|>assistant<|im_middle|>
|
|
{%- endif -%} |