common/parser: add GigaChatV3/3.1 models support (ggml-org#19931)

Co-authored-by: Mishusha <pmv26021975@gmail.com>

Author: Mishusha

common/chat.cpp

@@ -1354,6 +1354,77 @@ static common_chat_params common_chat_params_init_lfm2(const common_chat_templat
     return data;
 }
 
+static common_chat_params common_chat_params_init_gigachat_v3(
+        const common_chat_template & tmpl,
+        const autoparser::templates_params & inputs) {
+
+    common_chat_params data;
+
+    data.prompt            = common_chat_template_direct_apply(tmpl, inputs);
+    data.format            = COMMON_CHAT_FORMAT_PEG_NATIVE;
+    data.supports_thinking = false;
+    data.preserved_tokens  = {
+        "<|message_sep|>\n\n",
+        "<|role_sep|>\n",
+    };
+
+    auto has_tools         = inputs.tools.is_array() && !inputs.tools.empty();
+    auto include_grammar   = has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE;
+    auto tool_call_start_prefix = "<|message_sep|>\n\nfunction call<|role_sep|>\n";
+
+    auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) {
+        if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE) {
+            // Build a choice of all available tools
+            auto tool_choice = p.choice();
+            for (const auto & tool : inputs.tools) {
+                const auto & function = tool.at("function");
+                std::string name = function.at("name");
+                const auto & schema = function.at("parameters");
+
+                auto tool_name = p.json_member("name", "\"" + p.tool_name(p.literal(name)) + "\"");
+                auto tool_args = p.json_member("arguments", p.tool_args(p.schema(p.json(), "tool-" + name + "-schema", schema)));
+
+                auto tool_open = p.tool_open(p.literal("{") << tool_name);
+
+                tool_choice |= p.rule("tool-" + name, tool_open << "," << tool_args << "}");
+            }
+
+            // Define the tool call structure
+            auto min_calls = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED ? 1 : 0;
+            auto max_calls = 1; // parallel toolcalls are not supported
+            auto tool_call = p.rule("tool-call", p.literal(tool_call_start_prefix) + tool_choice);
+            auto tool_calls = p.trigger_rule("tool-call-root", p.repeat(tool_call, /* min = */ min_calls, /* max = */ max_calls));
+
+            return p.content(p.until("<|message_sep|>\n\n")) << tool_calls;
+        }
+
+        // Content only parser
+        include_grammar = false;
+        return p.content(p.rest());
+
+    });
+
+    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_call_start_prefix}
+        };
+    }
+    return data;
+}
+
 namespace workaround {
 
 static void map_developer_role_to_system(json & messages) {
@@ -1525,6 +1596,15 @@ static common_chat_params common_chat_templates_apply_jinja(const struct common_
         return common_chat_params_init_lfm2(tmpl, params);
     }
 
+    // GigaChatV3 format detection
+    if (src.find("<|role_sep|>") != std::string::npos &&
+        src.find("<|message_sep|>") != std::string::npos &&
+        src.find("<|function_call|>") == std::string::npos
+    ) {
+        LOG_DBG("Using specialized template: GigaChatV3\n");
+        return common_chat_params_init_gigachat_v3(tmpl, params);
+    }
+
     try {
         LOG_DBG("Using differential autoparser\n");
         struct autoparser::autoparser autoparser;