chat : add parsing for solar-open-100b

common/chat.cpp

@@ -2573,20 +2573,165 @@ static common_chat_params common_chat_params_init_granite(const common_chat_temp
 static common_chat_params common_chat_params_init_solar_open(const common_chat_template & tmpl, const struct templates_params & inputs) {
     common_chat_params data;
 
-    // TODO: Reasoning effort
-    json additional_context = {};
+    // Copy `reasoning_content` to `reasoning`
+    auto adjusted_messages = json::array();
+    for (const auto & msg : inputs.messages) {
+        if (msg.contains("reasoning_content") && msg.at("reasoning_content").is_string()) {
+            auto adjusted_message = msg;
+            adjusted_message["reasoning"] = msg.at("reasoning_content");
+            adjusted_message.erase("reasoning_content");
+            adjusted_messages.push_back(adjusted_message);
+        } else {
+            adjusted_messages.push_back(msg);
+        }
+    }
 
-    data.prompt = apply(tmpl, inputs, std::nullopt, std::nullopt, additional_context);
-    data.format = COMMON_CHAT_FORMAT_SOLAR_OPEN;
+    auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
+    auto include_grammar = true;
+
+    auto prompt = apply(tmpl, inputs, /* messages_override= */ adjusted_messages);
+
+    // Check if we need to replace the flush token with end token during inference and without generation prompt.
+    if (inputs.is_inference && !inputs.add_generation_prompt) {
+        static constexpr std::string_view return_token = "<|flush|>";
+        static constexpr std::string_view end_token    = "<|end|>";
+        if (size_t pos = prompt.rfind(return_token); pos != std::string::npos) {
+            prompt.replace(pos, return_token.length(), end_token);
+        }
+    }
 
+    data.prompt = prompt;
+    data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
     data.preserved_tokens = {
         "<|think|>",
         "<|content|>",
         "<|begin|>",
         "<|end|>",
+        "<|tool_calls|>",
+        "<|tool_call:begin|>",
+        "<|tool_call:end|>",
+        "<|tool_call:name|>",
+        "<|tool_call:args|>",
     };
 
-    // TODO: Tool calling
+    auto parser = build_chat_peg_native_parser([&](common_chat_peg_native_builder & p) {
+        auto lit_think = p.atomic(p.literal("<|think|>"));
+        auto lit_assistant_begin = p.atomic(p.literal("<|begin|>assistant"));
+        auto lit_content = p.atomic(p.literal("<|content|>"));
+        auto lit_end = p.atomic(p.literal("<|end|>"));
+        auto parser_until_end = p.until("<|end|>");
+
+        // reasoning <- "<|think|>" (!"<|end|>" .)*
+        auto parser_reasoning = p.rule("reasoning", lit_think + p.reasoning(parser_until_end));
+
+        // content <- "<|content|>" (!"<|end|>" .)*
+        auto parser_content = p.rule("content", lit_content + p.content(parser_until_end));
+
+        // wrap_choice(items) <- item-choice wrapped*
+        // item-choice        <- items[0] / ... / items[n]
+        // wrapped            <- "<|end|><|begin|>assistant" item-choice
+        auto wrap_choice = [&](const std::vector<common_peg_parser> & items) {
+            auto choice = p.choice(items);
+            return choice + p.zero_or_more(lit_end + lit_assistant_begin + choice);
+        };
+
+        // wrap_seq(items) <- item[0] "<|end|><|begin|>assistant" item[1] ...
+        auto wrap_seq = [&](const std::vector<common_peg_parser> & items) {
+            auto seq = p.sequence();
+            for (auto i = 0u; i < items.size(); i++) {
+                if (i == 0) {
+                    seq += items[i];
+                    continue;
+                }
+                seq += lit_end + lit_assistant_begin + items[i];
+            }
+            return seq;
+        };
+
+        // Response format parser
+        if (inputs.json_schema.is_object() && !inputs.json_schema.empty()) {
+            auto parser_response_format = lit_content + p.content(p.schema(p.json(), "response-format", inputs.json_schema));
+            return p.choice({
+                wrap_seq({parser_reasoning, parser_response_format}),
+                wrap_seq({parser_response_format})
+            });
+        }
+
+        auto lit_tool_call_begin = p.literal("<|tool_call:begin|>");
+        auto lit_tool_call_name = p.literal("<|tool_call:name|>");
+        auto lit_tool_call_args = p.literal("<|tool_call:args|>");
+        auto lit_tool_call_end = p.literal("<|tool_call:end|>");
+
+        // Tool call parser
+        if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE) {
+            auto parser_tool_call = p.choice();
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto & function = tool.at("function");
+                std::string name = function.at("name");
+                const auto & schema = function.at("parameters");
+
+                // tool(name, schema) <- name "<|tool_call:args|>" schema
+                parser_tool_call |= p.rule("tool-" + name,
+                    p.atomic(p.tool_name(p.literal(name)) + lit_tool_call_args)
+                    + p.tool_args(p.schema(p.json(), "tool-" + name + "-schema", schema)));
+            });
+
+            auto min_calls = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED ? 1 : 0;
+            auto max_calls = inputs.parallel_tool_calls ? -1 : 1;
+
+            // tool-calls  <- "<|tool_calls|>" tool-call+
+            // tool-call   <- "<|tool_call:begin|> call-id "<|tool_call:name|>" &([^<]+ "<|tool_call:args|>") tool-choice "<|tool_call:end|>"
+            // call-id     <- [a-zA-Z0-9_-]+
+            // tool-choice <- tool(t[0].name, t[0].schema) / ... / tool(t[n].name, t[n].schema)
+            auto parser_tool_calls = p.trigger_rule("tool-calls",
+                p.atomic(p.literal("<|tool_calls|>"))
+                + p.repeat(
+                    p.tool_open(
+                        lit_tool_call_begin
+                        + p.tool_id(p.chars("[a-zA-Z0-9_-]", 1, -1))
+                        + lit_tool_call_name
+                        + p.peek(p.chars("[^<]", 1, -1) + lit_tool_call_args))
+                    + parser_tool_call
+                    + p.tool_close(lit_tool_call_end),
+                /* min = */ 1,
+                /* max = */ max_calls));
+
+            if (min_calls == 1) {
+                // If required, then try any combination of the reasoning, content, and tool call
+                return p.choice({
+                    wrap_seq({parser_reasoning, parser_content, parser_tool_calls}),
+                    wrap_seq({parser_reasoning, parser_tool_calls}),
+                    wrap_seq({parser_content, parser_tool_calls}),
+                    wrap_seq({parser_tool_calls})
+                });
+            }
+
+            return wrap_choice({parser_reasoning, parser_content, parser_tool_calls});
+        }
+
+        // Content only parser
+        include_grammar = false;
+        return wrap_choice({parser_reasoning, parser_content});
+    });
+
+    data.parser = parser.save();
+
+    if (include_grammar) {
+        data.grammar_lazy = has_tools && inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_AUTO;
+
+        data.grammar = build_grammar([&](const common_grammar_builder & builder) {
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto & function = tool.at("function");
+                auto schema = function.at("parameters");
+                builder.resolve_refs(schema);
+            });
+            parser.build_grammar(builder, data.grammar_lazy);
+        });
+
+        data.grammar_triggers = {
+            {COMMON_GRAMMAR_TRIGGER_TYPE_WORD, "<|tool_calls|>"}
+        };
+    }
 
     return data;
 }
@@ -3043,6 +3188,13 @@ static common_chat_params common_chat_templates_apply_jinja(
         return common_chat_params_init_apriel_1_5(tmpl, params);
     }
 
+    // Solar Open
+    if (src.find("<|tool_response:begin|>") != std::string::npos &&
+        src.find("<|tool_response:name|>") != std::string::npos &&
+        src.find("<|tool_response:result|>") != std::string::npos) {
+        return common_chat_params_init_solar_open(tmpl, params);
+    }
+
     // Use generic handler when mixing tools + JSON schema.
     // TODO: support that mix in handlers below.
     if ((params.tools.is_array() && params.json_schema.is_object())) {

models/templates/upstage-Solar-Open-100B.jinja

@@ -0,0 +1,156 @@
+{#- ======== Template Parameters ========  #}
+{%- set add_generation_prompt = add_generation_prompt if add_generation_prompt is defined else true %}
+{%- set default_system_prompt = default_system_prompt if default_system_prompt is defined else true %}
+{%- set reasoning_effort = reasoning_effort if reasoning_effort is defined else "high" %}
+{%- set think_render_option = think_render_option if think_render_option is defined else "lastthink" %}
+
+{#- ======== System Block State ========  #}
+{%- set sys_ns = namespace(is_first_block=true) -%}
+
+{#- ======== Find last user message index ========  #}
+{%- set last_user_idx = namespace(value=-1) -%}
+{%- for message in messages -%}
+    {%- if message.role == 'user' -%}
+        {%- set last_user_idx.value = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- ======== System messages renderers ========  #}
+{%- macro render_system_message(user_system_messages) %}
+    {%- if default_system_prompt %}
+        {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+        {%- set sys_ns.is_first_block = false %}
+        {{- "## Provider System Prompt\n\nYou are Solar Open 100B, a large language model trained by Upstage AI, a Korean startup. Your knowledge cutoff is 2025-07. The current date is " + strftime_now("%Y-%m-%d") + "." }}
+    {%- endif -%}
+    {%- if user_system_messages %}
+        {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+        {%- set sys_ns.is_first_block = false %}
+        {{- "## System Prompt" }}
+        {%- for system_message in user_system_messages %}
+            {{- "\n\n" }}
+            {{- system_message }}
+        {%- endfor %}
+    {%- endif -%}
+{%- endmacro %}
+
+{%- macro render_tool_instruction(tools) %}
+    {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+    {%- set sys_ns.is_first_block = false %}
+    {{- "## Tools\n\n### Tool Call Instruction" }}
+    {{- "\nYou may invoke one or more tools to assist with the user's query. Available tools are provided in JSON Schema format: <|tools:begin|><|tool:begin|><tools-json-object><|tool:end|>...<|tools:end|>\n" }}
+    {{- "\n### Available Tools\n" }}
+    {{- "<|tools:begin|>" }}
+    {%- for tool in tools %}
+        {{- "<|tool:begin|>" }}
+        {{- tool.function | tojson }}
+        {{- "<|tool:end|>" }}
+    {%- endfor %}
+    {{- "<|tools:end|>\n" }}
+    {{- "\n### Tool Call Format\n" }}
+    {{- "For each tool call, return a JSON object with the following structure, enclosed within <|tool_call:begin|> and <|tool_call:end|> tags: \n<|tool_call:begin|><tool-call-id><|tool_call:name|><tool-name><|tool_call:args|><args-json-object><|tool_call:end|>\n" }}
+    {{- "- The <tool-call-id> must be a randomly generated string consisting of 10 lowercase letters (a-z) and/or digits (0-9) (e.g., a1b2c3d4e5)\n" }}
+    {{- "\n### Tool Response Format\n" }}
+    {{- "Each tool is responded by `tool` with the following structure:\n<|tool_response:id|><tool-call-id><|tool_response:name|><tool-name><|tool_response:result|><results><|tool_response:end|>\n" }}
+    {{- "- Ensure the <tool-call-id> matches the corresponding tool call" -}}
+{%- endmacro %}
+
+{%- macro render_json_response_format_instruction(response_format) %}
+    {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+    {%- set sys_ns.is_first_block = false %}
+    {{- "## Output Format Constraint" }}
+    {{- "\n\nYour final response should follow the JSON schema: \n[Start of schema]" }}
+    {{- response_format }}
+    {{- "\n[End of schema]\nPlease ensure your answers adhere to this format and do not contain any unnecessary text." }}
+{%- endmacro %}
+
+{%- macro get_tool_name(messages, tool_call_id) %}
+    {%- for msg in messages -%}
+        {%- if msg.role == 'assistant' and msg.tool_calls -%}
+            {%- for tool_call in msg.tool_calls -%}
+                {%- if tool_call.id == tool_call_id -%}
+                    {{- tool_call.function.name }}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro %}
+
+{%- macro render_tool_arguments(tool_arguments) %}
+    {%- if tool_arguments is mapping -%}
+        {{- tool_arguments | tojson }}
+    {%- else -%}
+        {{- tool_arguments }}
+    {%- endif -%}
+{%- endmacro %}
+
+{#- ======== Render system message ========  #}
+{%- set ns = namespace(system_messages=[]) -%}
+{%- for message in messages -%}
+    {%- if message.role == 'system' -%}
+        {%- set ns.system_messages = ns.system_messages + [message.content] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if ns.system_messages or default_system_prompt or tools or response_format -%}
+    {{- "<|begin|>system<|content|>" }}
+        {{- render_system_message(ns.system_messages) }}
+        {%- if tools -%}
+            {{- render_tool_instruction(tools) }}
+        {%- endif %}
+        {%- if response_format -%}
+            {{- render_json_response_format_instruction(response_format) }}
+        {%- endif %}
+    {{- "<|end|>" }}
+{%- endif -%}
+
+{#- ======== Render main messages ========  #}
+{%- for message in messages -%}
+    {%- if message.role == 'user' -%}
+         {{- "<|begin|>user<|content|>" + message.content + "<|end|>" }}
+    {%- elif message.role == 'tool' -%}
+        {%- set prev_is_tool = loop.index0 > 0 and messages[loop.index0 - 1].role == 'tool' -%}
+        {%- set next_is_tool = loop.index0 < (messages | length - 1) and messages[loop.index0 + 1].role == 'tool' -%}
+        {%- if not prev_is_tool -%}
+            {{- "<|begin|>tool<|tool_response|>" }}
+        {%- endif -%}
+        {{- "<|tool_response:begin|>" + message.tool_call_id + "<|tool_response:name|>" }}
+        {{- get_tool_name(messages, message.tool_call_id) }}
+        {{- "<|tool_response:result|>" }}
+        {{- message.content }}
+        {{- "<|tool_response:end|>" }}
+        {%- if not next_is_tool -%}
+            {{- "<|end|>" }}
+        {%- endif -%}
+    {%- elif message.role == 'assistant' -%}
+        {#- ======== Assistant Thinking ========  #}
+        {%- if think_render_option == "all" -%}
+            {%- if message.reasoning -%}
+                {{- "<|begin|>assistant<|think|>" + message.reasoning + "<|end|>" }}
+            {%- endif -%}
+        {%- elif think_render_option == "lastthink" -%}
+            {%- if message.reasoning and loop.index0 > last_user_idx.value -%}
+                {{- "<|begin|>assistant<|think|>" + message.reasoning + "<|end|>" }}
+            {%- endif -%}
+        {%- endif -%}
+
+        {#- ======== Assistant Messages ========  #}
+        {%- if message.tool_calls -%}
+            {{- "<|begin|>assistant<|tool_calls|>" }}
+            {%- for tool_call in message.tool_calls -%}
+                {{- "<|tool_call:begin|>" + tool_call.id +"<|tool_call:name|>" + tool_call.function.name + "<|tool_call:args|>" }}
+                {{- render_tool_arguments(tool_call.function.arguments) }}
+                {{- "<|tool_call:end|>" }}
+            {%- endfor -%}
+            {{- "<|calls|>" }}
+        {%- else -%}
+            {{- "<|begin|>assistant<|content|>" + message.content + "<|end|>" }}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if reasoning_effort in ["low", "minimal"] -%}
+        {{- "<|begin|>assistant<|think|><|end|>" }}
+    {%- endif -%}
+    {{- "<|begin|>assistant" }}
+{%- endif -%}