Files
hksdpc255 1920345c3b common : Generalized XML-style tool-call parsing with streaming support (GLM 4.5/4.6 + MiniMax M2 + SeedOSS + Kimi-K2 + Qwen3-Coder + Apriel-1.5 + Xiaomi-MiMo) (#16932)
* Add files via upload

* fix unit test

* fix crashes for --reasoning-format=none

* Patch buggy official MiniMax-M2 chat template

* add upstream minja fix: https://github.com/ochafik/minja/pull/7

* Fix <think> token not generated

* add test copied from https://github.com/ggml-org/llama.cpp/pull/16946

* cleanup

* Hopes to fix the compilation error on CI

* Delete chat template patching since it’s fixed by upstream Minja

* Remove undeeded Minimax-M2 template patch

https://github.com/ochafik/minja/pull/7#issuecomment-3480356100

* Add proper handling of optional parameters with test
merged tests from: https://github.com/ggml-org/llama.cpp/pull/16946/commits/23d4bb75c485c12ac89f81c424dc03c87a640e8c

* Fix making all tool parameters optional

* Move xml tool parser to separate file

* cleanup & add tests for GLM4.5

* add streaming tests & enhancement & cleanups

Add streaming test for both GLM 4.5 and minimax-m2.
Cleanup for preserved_tokens.
Cleanup for grammar rule name.
Enhance the parser's stability.

* cleanup & add support for Kimi-K2 Qwen3-Coder Apriel-1.5 Xiaomi-MiMo

* apply suggestions from reviewers

* fix a misuse for data.grammar_lazy

* fix grammar when tool have no argument

* Fix `no triggers set for lazy grammar!` for GLM4.5/4.6. Insert additional stops for Kimi-K2

* update chat.cpp

* fix grammar for GLM 4.5/4.6

* Try fix Jinja template for GLM

* Try fix GLM-4.6.jinja

* Update common/chat-parser-xml-toolcall.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update tests/test-chat.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* improve chat template for GLM, rename Kimi-K2 template to Kimi-K2-Thinking

* Improve Kimi-K2 chat template

* Fix unit test

* Fix "Invalid tool call arguments passed" in a rare case.

In a rare case, the model may emit a raw string that begins with a valid JSON string. This commit adds unit tests to cover that scenario and fixes the regression introduced during the Kimi-K2 adaptation.

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2025-11-18 18:54:15 +01:00

160 lines
6.3 KiB
Django/Jinja

{# ----------‑‑‑ special token variables ‑‑‑---------- #}
{%- set toolcall_begin_token = '<minimax:tool_call>' -%}
{%- set toolcall_end_token = '</minimax:tool_call>' -%}
{#- Tool Rendering Functions ============================================== -#}
{%- macro render_tool_namespace(namespace_name, tool_list) -%}
{%- for tool in tool_list -%}
<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
{% endfor -%}
{%- endmacro -%}
{%- macro visible_text(content) -%}
{%- if content is string -%}
{{ content }}
{%- elif content is iterable and content is not mapping -%}
{%- for item in content -%}
{%- if item is mapping and item.type == 'text' -%}
{{- item.text }}
{%- elif item is string -%}
{{- item }}
{%- endif -%}
{%- endfor -%}
{%- else -%}
{{- content }}
{%- endif -%}
{%- endmacro -%}
{#- System Message Construction ============================================ -#}
{%- macro build_system_message(system_message) -%}
{%- if system_message and system_message.content -%}
{{- visible_text(system_message.content) }}
{%- else -%}
{%- if model_identity is not defined -%}
{%- set model_identity = "You are a helpful assistant." -%}
{%- endif -%}
{{- model_identity }}
{%- endif -%}
{#- Handle current_date -#}
{%- if system_message and system_message.current_date -%}
{{- '\n' ~ 'Current date: ' + system_message.current_date }}
{%- endif -%}
{#- Handle current_location -#}
{%- if system_message and system_message.current_location -%}
{{- '\n' ~ 'Current location: ' + system_message.current_location }}
{%- endif -%}
{%- endmacro -%}
{#- Main Template Logic ================================================= -#}
{#- Extract system message (only first message if it's system) -#}
{%- set system_message = none -%}
{%- set conversation_messages = messages -%}
{%- if messages and messages[0].role == "system" -%}
{%- set system_message = messages[0] -%}
{%- set conversation_messages = messages[1:] -%}
{%- endif -%}
{#- Get the last user message turn, for interleved thinking -#}
{%- set ns = namespace(last_user_index=-1) %}
{% for m in conversation_messages %}
{%- if m.role == 'user' %}
{% set ns.last_user_index = loop.index0 -%}
{%- endif %}
{%- endfor %}
{#- Render system message -#}
{{- ']~!b[' ~ ']~b]system' ~ '\n' }}
{{- build_system_message(system_message) }}
{#- Render tools if available -#}
{%- if tools -%}
{{- '\n\n' ~ '# Tools' ~ '\n' ~ 'You may call one or more tools to assist with the user query.\nHere are the tools available in JSONSchema format:' ~ '\n' }}
{{- '\n' ~ '<tools>' ~ '\n' }}
{{- render_tool_namespace("functions", tools) }}
{{- '</tools>' ~ '\n\n' }}
{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\n' }}
{{- '\n' ~ toolcall_begin_token }}
<invoke name="tool-name-1">
<parameter name="param-key-1">param-value-1</parameter>
<parameter name="param-key-2">param-value-2</parameter>
...
</invoke>
{{- '\n' ~ toolcall_end_token }}
{%- endif -%}
{{- '[e~[\n' }}
{#- Render messages -#}
{%- set last_tool_call = namespace(name=none) -%}
{%- for message in conversation_messages -%}
{%- if message.role == 'assistant' -%}
{#- Only render reasoning_content if no user message follows -#}
{{- ']~b]ai' ~ '\n' }}
{%- set reasoning_content = '' %}
{%- set content = visible_text(message.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].strip('\n').split('<think>')[-1].strip('\n') %}
{%- set content = content.split('</think>')[-1].strip('\n') %}
{%- endif %}
{%- endif %}
{%- if reasoning_content and loop.index0 > ns.last_user_index -%}
{{- '<think>' ~ '\n' ~ reasoning_content ~ '\n' ~ '</think>' ~ '\n\n' }}
{%- endif -%}
{%- if content -%}
{{- content }}
{%- endif -%}
{%- if message.tool_calls -%}
{{- '\n' ~ toolcall_begin_token ~ '\n' }}
{%- for tool_call in message.tool_calls -%}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<invoke name="' + tool_call.name + '">' }}
{% set _args = tool_call.arguments %}
{%- for k, v in _args.items() %}
{{- '<parameter name="' + k + '">' }}
{{- v | tojson(ensure_ascii=False) if v is not string else v }}
{{- '</parameter>' }}
{% endfor %}
{{- '</invoke>' ~ '\n' }}
{%- endfor -%}
{{- toolcall_end_token}}
{%- set last_tool_call.name = message.tool_calls[-1].function.name -%}
{%- else -%}
{%- set last_tool_call.name = none -%}
{%- endif -%}
{{- '[e~[' ~ '\n' }}
{%- elif message.role == 'tool' -%}
{%- if last_tool_call.name is none -%}
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
{%- endif -%}
{%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}
{{- ']~b]tool' }}
{%- endif -%}
{%- if message.content is string -%}
{{- '\n<response>' }}
{{- message.content }}
{{- '</response>' }}
{%- else -%}
{%- for tr in message.content -%}
{{- '\n<response>' }}
{{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
{{- '\n</response>' }}
{%- endfor -%}
{%- endif -%}
{%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}
{{- '[e~[\n' -}}
{%- endif -%}
{%- elif message.role == 'user' -%}
{{- ']~b]user' ~ '\n' }}
{{- visible_text(message.content) }}
{{- '[e~[' ~ '\n' }}
{%- endif -%}
{%- endfor -%}
{#- Generation prompt -#}
{%- if add_generation_prompt -%}
{{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
{%- endif -%}