chat: dedicated DeepSeek v3.2 parser + "official" template (ggml-org#21785)

Author: pwilkin

common/chat.cpp

@@ -1656,6 +1656,173 @@ static common_chat_params common_chat_params_init_gigachat_v3(
     return data;
 }
 
+static common_chat_params common_chat_params_init_deepseek_v3_2(const common_chat_template &    tmpl,
+                                                                 const autoparser::generation_params & inputs) {
+    common_chat_params data;
+
+    data.prompt            = common_chat_template_direct_apply_impl(tmpl, inputs);
+    data.format            = COMMON_CHAT_FORMAT_PEG_NATIVE;
+    data.supports_thinking = true;
+    data.thinking_start_tag = "<think>";
+    data.thinking_end_tag   = "</think>";
+    data.preserved_tokens  = {
+        "｜DSML｜",
+        "<think>",
+        "</think>",
+    };
+
+    auto has_tools           = inputs.tools.is_array() && !inputs.tools.empty();
+    auto has_response_format = !inputs.json_schema.is_null() && inputs.json_schema.is_object();
+    auto extract_reasoning   = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
+    auto include_grammar     = has_response_format || (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE);
+
+    const std::string DSML         = "｜DSML｜";
+    const std::string THINK_START  = "<think>";
+    const std::string THINK_END    = "</think>";
+    const std::string FC_START     = "<" + DSML + "function_calls>";
+    const std::string FC_END       = "</" + DSML + "function_calls>";
+    const std::string INVOKE_START = "<" + DSML + "invoke";
+    const std::string INVOKE_END   = "</" + DSML + "invoke>";
+    const std::string PARAM_START  = "<" + DSML + "parameter";
+    const std::string PARAM_END    = "</" + DSML + "parameter>";
+
+    auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) {
+        auto generation_prompt = p.prefix(inputs.generation_prompt, THINK_START);
+        auto end = p.end();
+
+        auto reasoning = p.eps();
+        if (extract_reasoning && inputs.enable_thinking) {
+            reasoning = p.optional(THINK_START + p.reasoning(p.until(THINK_END)) + THINK_END);
+        } else if (extract_reasoning) {
+            // Thinking disabled but reasoning extraction requested: the generation prompt
+            // contains an empty <think></think> pair that must still be consumed.
+            reasoning = p.optional(p.literal(THINK_START) + p.until(THINK_END) + p.literal(THINK_END));
+        }
+
+        if (has_response_format) {
+            auto response_format = p.rule("response-format",
+                p.literal("```json") + p.space() +
+                p.content(p.schema(p.json(), "response-format-schema", inputs.json_schema)) +
+                p.space() + p.literal("```"));
+            return generation_prompt + reasoning + response_format + end;
+        }
+
+        if (!has_tools || inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_NONE) {
+            return generation_prompt + reasoning + p.content(p.rest()) + end;
+        }
+
+        auto tool_choice = p.choice();
+        foreach_function(inputs.tools, [&](const json & tool) {
+            const auto & function = tool.at("function");
+            std::string  name     = function.at("name");
+            auto params   = function.contains("parameters") ? function.at("parameters") : json::object();
+            const auto & props    = params.contains("properties") ? params.at("properties") : json::object();
+
+            std::set<std::string> required;
+            if (params.contains("required")) {
+                params.at("required").get_to(required);
+            }
+
+            auto schema_info = common_schema_info();
+            schema_info.resolve_refs(params);
+
+            std::vector<common_peg_parser> required_parsers;
+            std::vector<common_peg_parser> optional_parsers;
+            for (const auto & [param_name, param_schema] : props.items()) {
+                bool is_required = required.find(param_name) != required.end();
+                bool is_string   = schema_info.resolves_to_string(param_schema);
+
+                auto arg = p.tool_arg(
+                    p.tool_arg_open(
+                        p.literal(PARAM_START + " name=\"") +
+                        p.tool_arg_name(p.literal(param_name)) +
+                        p.literal("\" string=\"" + std::string(is_string ? "true" : "false") + "\">")) +
+                    (is_string
+                         ? p.tool_arg_string_value(p.until(PARAM_END))
+                         : p.tool_arg_json_value(p.schema(p.json(),
+                                                          "tool-" + name + "-arg-" + param_name + "-schema",
+                                                          param_schema, false))) +
+                    p.tool_arg_close(p.literal(PARAM_END)));
+
+                auto named_arg = p.rule("tool-" + name + "-arg-" + param_name, arg);
+                if (is_required) {
+                    required_parsers.push_back(named_arg);
+                } else {
+                    optional_parsers.push_back(named_arg);
+                }
+            }
+
+            common_peg_parser args_seq = p.eps();
+            for (size_t i = 0; i < required_parsers.size(); i++) {
+                if (i > 0) {
+                    args_seq = args_seq + p.space();
+                }
+                args_seq = args_seq + required_parsers[i];
+            }
+
+            if (!optional_parsers.empty()) {
+                common_peg_parser any_opt = p.choice();
+                for (const auto & opt : optional_parsers) {
+                    any_opt |= opt;
+                }
+                args_seq = args_seq + p.repeat(p.space() + any_opt, 0, -1);
+            }
+
+            common_peg_parser invoke_body = args_seq;
+            auto func_parser = p.tool(
+                p.tool_open(p.literal(INVOKE_START + " name=\"") +
+                            p.tool_name(p.literal(name)) + p.literal("\">\n")) +
+                invoke_body + p.space() +
+                p.tool_close(p.literal(INVOKE_END)));
+
+            tool_choice |= p.rule("tool-" + name, func_parser);
+        });
+
+        auto require_tools = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+        common_peg_parser tool_calls = p.eps();
+        if (inputs.parallel_tool_calls) {
+            tool_calls = p.trigger_rule("tool-call",
+                p.literal(FC_START) + p.space() + tool_choice +
+                p.zero_or_more(p.space() + tool_choice) + p.space() + p.literal(FC_END));
+        } else {
+            tool_calls = p.trigger_rule("tool-call",
+                p.literal(FC_START) + p.space() + tool_choice + p.space() + p.literal(FC_END));
+        }
+
+        if (!require_tools) {
+            tool_calls = p.optional(tool_calls);
+        }
+
+        auto content_before_tools = p.content(p.until(FC_START));
+        return generation_prompt + reasoning + content_before_tools + tool_calls + end;
+    });
+
+    data.parser = parser.save();
+
+    if (include_grammar) {
+        data.grammar_lazy = !(has_response_format || (has_tools && inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED));
+        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.contains("parameters") ? function.at("parameters") : json::object();
+                builder.resolve_refs(schema);
+            });
+            if (has_response_format) {
+                auto schema = inputs.json_schema;
+                builder.resolve_refs(schema);
+            }
+            parser.build_grammar(builder, data.grammar_lazy);
+        });
+
+        data.grammar_triggers = {
+            { COMMON_GRAMMAR_TRIGGER_TYPE_WORD, FC_START },
+        };
+    }
+
+    return data;
+}
+
 namespace workaround {
 
 static void map_developer_role_to_system(json & messages) {
@@ -1927,6 +2094,15 @@ std::optional<common_chat_params> common_chat_try_specialized_template(
         return common_chat_params_init_gigachat_v3(tmpl, params);
     }
 
+    // DeepSeek V3.2 format detection: template defines dsml_token and uses it for tool calls.
+    // The template source contains the token as a variable assignment, not as a literal in markup.
+    if (src.find("dsml_token") != std::string::npos &&
+        src.find("function_calls") != std::string::npos &&
+        src.find("DSML") != std::string::npos) {
+        LOG_DBG("Using specialized template: DeepSeek V3.2\n");
+        return common_chat_params_init_deepseek_v3_2(tmpl, params);
+    }
+
     // Gemma4 format detection
     if (src.find("'<|tool_call>call:'") != std::string::npos) {
         if (src.find("{#- OpenAI Chat Completions:") == std::string::npos) {

models/templates/deepseek-ai-DeepSeek-V3.2.jinja

@@ -0,0 +1,141 @@
+{%- if not add_generation_prompt is defined -%}
+  {%- set add_generation_prompt = false -%}
+{%- endif -%}
+{%- if not thinking is defined -%}
+  {%- if enable_thinking is defined -%}
+    {%- set thinking = enable_thinking -%}
+  {%- else -%}
+    {%- set thinking = false -%}
+  {%- endif -%}
+{%- endif -%}
+{%- set dsml_token = '｜DSML｜' -%}
+{%- set thinking_start_token = '<think>' -%}
+{%- set thinking_end_token = '</think>' -%}
+{%- set tools_header = '## Tools\n\nYou have access to a set of tools you can use to answer the user\'s question.\nYou can invoke functions by writing a "<' + dsml_token + 'function_calls>" block like the following as part of your reply to the user:\n<' + dsml_token + 'function_calls>\n<' + dsml_token + 'invoke name="$FUNCTION_NAME">\n<' + dsml_token + 'parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</' + dsml_token + 'parameter>\n...\n</' + dsml_token + 'invoke>\n<' + dsml_token + 'invoke name="$FUNCTION_NAME2">\n...\n</' + dsml_token + 'invoke>\n</' + dsml_token + 'function_calls>\n\nString and scalar parameters should be specified as is without any escaping or quotes, while lists and objects should use JSON format. The "string" attribute should be set to "true" for string type parameters and "false" for other types (numbers, booleans, arrays, objects).\n\nIf the thinking_mode is enabled, then after function results you should strongly consider outputting a thinking block. Here is an example:\n\n<' + dsml_token + 'function_calls>\n...\n</' + dsml_token + 'function_calls>\n\n<function_results>\n...\n</function_results>\n\n' + thinking_start_token + '...thinking about results' + thinking_end_token + '\n\nHere are the functions available in JSONSchema format:\n<functions>\n' -%}
+{%- set tools_footer = '</functions>\n' -%}
+{%- set ns = namespace(system_prompt='', is_first_sp=true) -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'system' -%}
+    {%- if ns.is_first_sp -%}
+      {%- set ns.system_prompt = ns.system_prompt + (message['content'] or '') -%}
+      {%- set ns.is_first_sp = false -%}
+    {%- else -%}
+      {%- set ns.system_prompt = ns.system_prompt + '\n\n' + (message['content'] or '') -%}
+    {%- endif -%}
+  {%- endif -%}
+{%- endfor -%}
+{%- if tools is defined and tools -%}
+  {%- set ts = namespace(schemas='') -%}
+  {%- for tool in tools -%}
+    {%- if tool['type'] == 'function' -%}
+      {%- set ts.schemas = ts.schemas + (tool['function'] | tojson) + '\n' -%}
+    {%- endif -%}
+  {%- endfor -%}
+  {%- if ns.system_prompt -%}
+    {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tools_header + ts.schemas + tools_footer -%}
+  {%- else -%}
+    {%- set ns.system_prompt = tools_header + ts.schemas + tools_footer -%}
+  {%- endif -%}
+{%- endif -%}
+{{- bos_token -}}
+{{- ns.system_prompt -}}
+{%- set last_user_idx = namespace(value=-1) -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'user' or message['role'] == 'developer' -%}
+    {%- set last_user_idx.value = loop.index0 -%}
+  {%- endif -%}
+{%- endfor -%}
+{%- set state = namespace(pending_asst_marker=false, pending_tool_marker=false) -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'user' -%}
+    {{- '<｜User｜>' + (message['content'] or '') -}}
+    {%- set state.pending_asst_marker = true -%}
+    {%- set state.pending_tool_marker = false -%}
+  {%- elif message['role'] == 'assistant' -%}
+    {%- set is_after_last_user = loop.index0 > last_user_idx.value -%}
+    {%- if state.pending_asst_marker -%}
+      {{- '<｜Assistant｜>' -}}
+      {%- if is_after_last_user and thinking -%}
+        {{- thinking_start_token -}}
+        {%- if message['reasoning_content'] is defined and message['reasoning_content'] -%}
+          {{- message['reasoning_content'] -}}
+        {%- endif -%}
+        {{- thinking_end_token -}}
+      {%- else -%}
+        {{- thinking_end_token -}}
+      {%- endif -%}
+    {%- elif state.pending_tool_marker -%}
+      {%- if is_after_last_user and thinking -%}
+        {{- '\n\n' + thinking_start_token -}}
+        {%- if message['reasoning_content'] is defined and message['reasoning_content'] -%}
+          {{- message['reasoning_content'] -}}
+        {%- endif -%}
+        {{- thinking_end_token -}}
+      {%- else -%}
+        {{- '\n\n' + thinking_end_token -}}
+      {%- endif -%}
+    {%- endif -%}
+    {%- set state.pending_asst_marker = false -%}
+    {%- set state.pending_tool_marker = false -%}
+    {%- if message['content'] is defined and message['content'] -%}
+      {{- message['content'] -}}
+    {%- endif -%}
+    {%- if message['tool_calls'] -%}
+      {{- '\n\n<' + dsml_token + 'function_calls>\n' -}}
+      {%- for tool in message['tool_calls'] -%}
+        {%- set func = tool['function'] -%}
+        {{- '<' + dsml_token + 'invoke name="' + func['name'] + '">\n' -}}
+        {%- set args = func['arguments'] -%}
+        {%- if args is string -%}
+          {%- set args = args | from_json -%}
+        {%- endif -%}
+        {%- for key, val in args.items() -%}
+          {%- if val is string -%}
+            {{- '<' + dsml_token + 'parameter name="' + key + '" string="true">' + val + '</' + dsml_token + 'parameter>\n' -}}
+          {%- else -%}
+            {{- '<' + dsml_token + 'parameter name="' + key + '" string="false">' + (val | tojson) + '</' + dsml_token + 'parameter>\n' -}}
+          {%- endif -%}
+        {%- endfor -%}
+        {{- '</' + dsml_token + 'invoke>\n' -}}
+      {%- endfor -%}
+      {{- '</' + dsml_token + 'function_calls>' -}}
+    {%- endif -%}
+    {{- '<｜end▁of▁sentence｜>' -}}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set outer_index = loop.index0 -%}
+    {%- set assistant_idx = namespace(value=-1) -%}
+    {%- for prev_msg in messages -%}
+      {%- if prev_msg['role'] == 'assistant' and prev_msg['tool_calls'] and loop.index0 < outer_index -%}
+        {%- set assistant_idx.value = loop.index0 -%}
+      {%- endif -%}
+    {%- endfor -%}
+    {%- set call_order = outer_index - assistant_idx.value -%}
+    {%- set assistant_msg = messages[assistant_idx.value] -%}
+    {%- set tool_call_count = assistant_msg['tool_calls'] | length -%}
+    {%- if call_order == 1 -%}
+      {{- '\n\n<function_results>' -}}
+    {%- endif -%}
+    {{- '\n<result>' + (message['content'] or '') + '</result>' -}}
+    {%- if call_order == tool_call_count -%}
+      {{- '\n</function_results>' -}}
+      {%- set state.pending_asst_marker = false -%}
+      {%- set state.pending_tool_marker = true -%}
+    {%- endif -%}
+  {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+  {%- if state.pending_asst_marker -%}
+    {{- '<｜Assistant｜>' -}}
+    {%- if thinking -%}
+      {{- thinking_start_token -}}
+    {%- else -%}
+      {{- thinking_start_token + thinking_end_token -}}
+    {%- endif -%}
+  {%- elif state.pending_tool_marker -%}
+    {%- if thinking -%}
+      {{- '\n\n' + thinking_start_token -}}
+    {%- else -%}
+      {{- '\n\n' + thinking_start_token + thinking_end_token -}}
+    {%- endif -%}
+  {%- endif -%}
+{%- endif -%}