char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Piotr Wilkin (ilintar)Autoparser - complete refactoring of parser architecture (#18675)566059a262026-03-06

{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
    {%- if param_spec.type == "array" -%}
        {%- if param_spec['items'] -%}
            {%- if param_spec['items']['type'] == "string" -%}
                {{- "string[]" }}
            {%- elif param_spec['items']['type'] == "number" -%}
                {{- "number[]" }}
            {%- elif param_spec['items']['type'] == "integer" -%}
                {{- "number[]" }}
            {%- elif param_spec['items']['type'] == "boolean" -%}
                {{- "boolean[]" }}
            {%- else -%}
                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
                    {{- "any[]" }}
                {%- else -%}
                    {{- inner_type + "[]" }}
                {%- endif -%}
            {%- endif -%}
            {%- if param_spec.nullable -%}
                {{- " | null" }}
            {%- endif -%}
        {%- else -%}
            {{- "any[]" }}
            {%- if param_spec.nullable -%}
                {{- " | null" }}
            {%- endif -%}
        {%- endif -%}
    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
        {%- if param_spec.type | length > 1 -%}
            {{- param_spec.type | join(" | ") }}
        {%- else -%}
            {{- param_spec.type[0] }}
        {%- endif -%}
    {%- elif param_spec.oneOf -%}
        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
        {%- set has_object_variants = false -%}
        {%- for variant in param_spec.oneOf -%}
            {%- if variant.type == "object" -%}
                {%- set has_object_variants = true -%}
            {%- endif -%}
        {%- endfor -%}
        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
            {{- "any" }}
        {%- else -%}
            {%- for variant in param_spec.oneOf -%}
                {{- render_typescript_type(variant, required_params) -}}
                {%- if variant.description %}
                    {{- "// " + variant.description }}
                {%- endif -%}
                {%- if variant.default is defined %}
                    {{ "// default: " + variant.default|tojson }}
                {%- endif -%}
                {%- if not loop.last %}
                    {{- " | " }}
                {% endif -%}
            {%- endfor -%}
        {%- endif -%}
    {%- elif param_spec.type == "string" -%}
        {%- if param_spec.enum -%}
            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
        {%- else -%}
            {{- "string" }}
            {%- if param_spec.nullable %}
                {{- " | null" }}
            {%- endif -%}
        {%- endif -%}
    {%- elif param_spec.type == "number" -%}
        {{- "number" }}
    {%- elif param_spec.type == "integer" -%}
        {{- "number" }}
    {%- elif param_spec.type == "boolean" -%}
        {{- "boolean" }}
    {%- elif param_spec.type == "object" -%}
        {%- if param_spec.properties -%}
            {{- "{\n" }}
            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
                {{- prop_name -}}
                {%- if prop_name not in (param_spec.required or []) -%}
                    {{- "?" }}
                {%- endif -%}
                {{- ": " }}
                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
                {%- if not loop.last -%}
                    {{-", " }}
                {%- endif -%}
            {%- endfor -%}
            {{- "}" }}
        {%- else -%}
            {{- "object" }}
        {%- endif -%}
    {%- else -%}
        {{- "any" }}
    {%- endif -%}
{%- endmacro -%}

{%- macro render_tools(tools) -%}
    {%- for tool in tools %}
        {{- "// " + tool.function.description + "\n" }}
        {{- "type "+ tool.function.name + " = " }}
        {%- if tool.function.parameters and tool.function.parameters.properties %}
            {{- "(_: {\n" }}
            {%- for param_name, param_spec in tool.function.parameters.properties.items() %}
                {%- if param_spec.description %}
                    {{- "// " + param_spec.description + "\n" }}
                {%- endif %}
                {{- param_name }}
                {%- if param_name not in (tool.function.parameters.required or []) -%}
                    {{- "?" }}
                {%- endif -%}
                {{- ": " }}
                {{- render_typescript_type(param_spec, tool.function.parameters.required or []) }}
                {%- if param_spec.default is defined -%}
                    {%- if param_spec.enum %}
                        {{- ", // default: " + param_spec.default }}
                    {%- elif param_spec.oneOf %}
                        {{- "// default: " + param_spec.default }}
                    {%- else %}
                        {{- ", // default: " + param_spec.default|tojson }}
                    {%- endif -%}
                {%- endif -%}
                {%- if not loop.last %}
                    {{- ",\n" }}
                {%- else %}
                    {{- "\n" }}
                {%- endif -%}
            {%- endfor %}
            {{- "}) => any;" }}
        {%- else -%}
            {{- "() => any;" }}
        {%- endif -%}
        {%- if not loop.last -%}
            {{- "\n" }}
        {%- endif -%}
    {%- endfor %}
{%- endmacro -%}

{{ bos_token }}

{%- set system_token = '<|system_start|>' -%}
{%- set end_system_token = '<|system_end|>' -%}
{%- set developer_token = '<|developer_start|>' -%}
{%- set end_developer_token = '<|developer_end|>' -%}
{%- set user_token = '<|user_start|>' -%}
{%- set end_user_token = '<|user_end|>' -%}
{%- set assistant_token = '<|assistant_start|>' -%}
{%- set end_assistant_token = '<|assistant_end|>' -%}
{%- set inner_token = '<|inner_prefix|>' -%}
{%- set outer_token = '<|inner_suffix|>' -%}
{%- set tool_calls_token = '<|tools_prefix|>' -%}
{%- set end_tool_calls_token = '<|tools_suffix|>' -%}

{%- set ns = namespace(in_assistant=false, in_tool=false, in_inner=false, assistant_format=none) -%}

{%- if messages and messages[0].role == 'system' -%}
    {%- if "content" in messages[0] -%}
        {%- if messages[0].content is string -%}
            {{ system_token + messages[0].content + end_system_token }}
        {%- elif messages[0].content is mapping and "text" in messages[0].content -%}
            {{ system_token + messages[0].content.text + end_system_token }}
        {%- else -%}
            {{- raise_exception("Invalid system message") -}}
        {%- endif -%}
    {%- else -%}
        {{- raise_exception("Invalid system message") -}}
    {%- endif -%}
    {%- set loop_messages = messages[1:] -%}
{%- else -%}
    {{ system_token + 'You are Apertus, a helpful assistant created by the SwissAI initiative.\nKnowledge cutoff: 2024-04\nCurrent date: ' + strftime_now('%Y-%m-%d') + end_system_token }}
    {%- set loop_messages = messages -%}
{%- endif -%}

{{ developer_token + 'Deliberation: ' }}
{%- if enable_thinking is defined and enable_thinking -%}
    {{ 'enabled\n' }}
{%- else -%}
    {{ 'disabled\n' }}
{%- endif -%}
{%- if tools is defined and tools -%}
    {{ 'Tool Capabilities:\n' + render_tools(tools) }}
{%- else -%}
    {{ 'Tool Capabilities: disabled' }}
{%- endif -%}
{{ end_developer_token }}

{%- for message in loop_messages -%}
    {%- if message.role == 'user' -%}
        {%- set ns.in_inner = false -%}
        {%- if ns.in_tool -%}
            {{ ']' }}
            {%- set ns.in_tool = false -%}
        {%- endif -%}
        {%- if ns.in_assistant -%}
            {{ end_assistant_token }}
            {%- set ns.in_assistant = false -%}
        {%- endif -%}
        {%- if "content" in message -%}
            {{ user_token }}
            {%- if message.content is string -%}
                {{ message.content }}
            {%- elif message.content is mapping and "parts" in message.content -%}
                {%- set parts = message.content.parts -%}
                {%- for part in parts -%}
                    {%- if part.type == "text" -%}
                        {{ part.text }}
                    {%- else -%}
                        {{- raise_exception("Invalid user part: " + part.type) -}}
                    {%- endif -%}
                {%- endfor -%}
            {%- else -%}
                {{- raise_exception("Invalid user message: " + message.role) -}}
            {%- endif -%}
            {{ end_user_token }}
        {%- endif -%}
    {%- elif message.role == 'assistant' -%}
        {%- if not ns.in_assistant -%}
            {{ assistant_token }}
            {%- set ns.in_assistant = true -%}
        {%- endif -%}
        {%- if "content" in message and message.content is not none -%}
            {%- if message.content is string and (ns.assistant_format is none or ns.assistant_format == "string") -%}
                {%- if ns.in_tool -%}
                    {{ ']' }}
                    {%- set ns.in_tool = false -%}
                {%- endif -%}
                {%- set ns.assistant_format = "string" -%}
                {{ message.content }}
            {%- elif message.content is mapping and "blocks" in message.content and (ns.assistant_format is none or ns.assistant_format == "mapping") -%}
                {%- set ns.assistant_format = "mapping" -%}
                {%- set blocks = message.content.blocks -%}
                {%- for block in blocks -%}
                    {%- if block.type == 'thoughts' -%}
                        {%- if ns.in_tool -%}
                            {{ ']' }}
                            {%- set ns.in_tool = false -%}
                        {%- endif -%}
                        {%- if not ns.in_inner -%}
                            {%- set ns.in_inner = true -%}
                            {{ inner_token }}
                        {%- endif -%}
                        {{ block.text }}
                    {%- elif block.type == 'tool_calls' -%}
                        {%- if ns.in_tool -%}
                            {{ ']' }}
                            {%- set ns.in_tool = false -%}
                        {%- endif -%}
                        {%- if ns.in_inner and not loop.first and block.calls|length == 1 and block.calls[0].name == 'display_answers' -%}
                            {%- set ns.in_inner = false -%}
                            {{ outer_token }}
                        {%- endif -%}
                        {{ tool_calls_token + '[' }}
                        {%- for tool_call in block.calls -%}
                            {{- '{"' + tool_call.name + '": ' + tool_call.arguments + '}' }}
                            {%- if not loop.last -%}
                                {{- ", " }}
                            {%- endif -%}
                        {%- endfor -%}
                        {{ ']' + end_tool_calls_token }}
                    {%- elif block.type == 'tool_outputs' -%}
                        {%- if ns.in_tool -%}
                            {{- raise_exception("Cannot have both tool outputs as separate messages and tool outputs as blocks") -}}
                        {%- endif -%}
                        {{ '[' }}
                        {%- for tool_output in block.outputs -%}
                            {{- tool_output.output }}
                            {%- if not loop.last -%}
                                {{- ", " }}
                            {%- endif -%}
                        {%- endfor -%}
                        {{- ']' }}
                    {%- elif block.type == 'response' -%}
                        {%- if ns.in_tool -%}
                            {{ ']' }}
                            {%- set ns.in_tool = false -%}
                        {%- endif -%}
                        {%- if (not loop.first and ns.in_inner) or (ns.in_assistant and ns.in_inner) -%}
                            {%- set ns.in_inner = false -%}
                            {{ outer_token }}
                        {%- endif -%}
                        {{ block.text }}
                    {%- else -%}
                        {{- raise_exception("Invalid assistant block type: " + block.type) -}}
                    {%- endif -%}
                {%- endfor -%}
            {%- else -%}
                {{- raise_exception("Invalid assistant content '" + message.content + "', expected " + ns.assistant_format) -}}
            {%- endif -%}
        {%- elif "tool_calls" not in message -%}
            {{- raise_exception("Invalid assistant message " + message) -}}
        {%- endif -%}
        {%- if "tool_calls" in message and message.tool_calls -%}
            {{ tool_calls_token + '[' }}
            {%- for tool_call in message.tool_calls -%}
                {%- if tool_call.type == 'function' -%}
                    {%- set function = tool_call.function -%}
                    {{- '{"' + function.name + '": ' + function.arguments|tojson + '}' }}
                    {%- if not loop.last -%}
                        {{- ", " }}
                    {%- endif -%}
                {%- else -%}
                    {{- raise_exception("Invalid tool call type: " + tool_call.type) -}}
                {%- endif -%}
            {%- endfor -%}
            {{ ']' + end_tool_calls_token }}
        {%- endif -%}
    {%- elif message.role == 'tool' -%}
        {%- if not ns.in_assistant -%}
            {{- raise_exception("Tool message outside of assistant") -}}
        {%- endif -%}
        {%- if not ns.in_tool -%}
            {{ '[' }}
            {%- set ns.in_tool = true -%}
        {%- else -%}
            {{ ", "}}
        {%- endif -%}
        {{ message.content }}
    {%- else -%}
        {{- raise_exception("Invalid message role") -}}
    {%- endif -%}
{%- endfor -%}
{%- if ns.in_tool -%}
    {{ ']' }}
{%- endif -%}
{%- if add_generation_prompt -%}
    {{ assistant_token }}
{%- endif -%}