common : add gemma 4 specialized parser (ggml-org#21418)

* common : add gemma4 dedicated parser

* cont : add '<|tool_response>' as eog

* cont : emit JSON from Gemma4 tool call AST

* cont : more fixes

* cont : refactor convert function

* cont : refine rules and mapping

* cont : add more tests

* cont : clean up

* cont : remove autoparser gemma4 implementation

* cont : more cleanup

* cont : rename gemma4.jinja to match the others

* cont : add custom template to support interleaved thinking

* cont : preserve reasoning in model turns

* cont : fix initializer error

* cont : fix unused vars

* cont : fix accidental static

* cont : fix specialized_template signature

* fix extra semicolon

* remove debug line and extra space [no ci]

Author: aldehir

common/chat-auto-parser-generator.cpp

@@ -7,109 +7,11 @@
 #include "log.h"
 #include "nlohmann/json.hpp"
 
-#include <algorithm>
 #include <stdexcept>
 #include <string>
 
 using json = nlohmann::ordered_json;
 
-namespace {
-
-// Gemma4-specific PEG builder extending the standard chat builder.
-// Adds value type parsers that use <|\"|> as string delimiters
-// instead of JSON's double quotes, and disables json-to-schema
-// conversion for these types.
-class common_peg_gemma4_builder {
-    common_chat_peg_builder & p_;
-    static constexpr const char * QUOTE = "<|\"|>";
-
-public:
-    explicit common_peg_gemma4_builder(common_chat_peg_builder & p) : p_(p) {}
-
-    common_peg_parser gemma4_string() {
-        return p_.rule("gemma4-string", [&]() {
-            return p_.literal(QUOTE) + p_.until(QUOTE) + p_.literal(QUOTE);
-        });
-    }
-
-    common_peg_parser gemma4_number() {
-        return p_.rule("gemma4-number", [&]() {
-            auto digit1_9 = p_.chars("[1-9]", 1, 1);
-            auto digits   = p_.chars("[0-9]");
-            auto int_part = p_.choice({p_.literal("0"), p_.sequence({digit1_9, p_.chars("[0-9]", 0, -1)})});
-            auto frac     = p_.sequence({p_.literal("."), digits});
-            auto exp      = p_.sequence({p_.choice({p_.literal("e"), p_.literal("E")}),
-                                         p_.optional(p_.chars("[+-]", 1, 1)), digits});
-            auto not_number_continuation = p_.negate(p_.chars("[0-9.eE+-]", 1, 1));
-            return p_.sequence({p_.optional(p_.literal("-")), int_part, p_.optional(frac),
-                                p_.optional(exp), not_number_continuation});
-        });
-    }
-
-    common_peg_parser gemma4_bool() {
-        return p_.rule("gemma4-bool", [&]() {
-            return p_.choice({p_.literal("true"), p_.literal("false")});
-        });
-    }
-
-    common_peg_parser gemma4_null() {
-        return p_.rule("gemma4-null", [&]() {
-            return p_.literal("null");
-        });
-    }
-
-    common_peg_parser gemma4_dict() {
-        return p_.rule("gemma4-dict", [&]() {
-            auto ws = p_.space();
-            auto key = p_.until(":");
-            auto member = p_.sequence({key, p_.literal(":"), ws, gemma4_value()});
-            auto members = p_.sequence({member, p_.zero_or_more(p_.sequence({p_.literal(","), ws, member}))});
-            return p_.sequence({
-                p_.literal("{"), ws,
-                p_.choice({p_.literal("}"), p_.sequence({members, ws, p_.literal("}")})})
-            });
-        });
-    }
-
-    common_peg_parser gemma4_array() {
-        return p_.rule("gemma4-array", [&]() {
-            auto ws = p_.space();
-            auto elements = p_.sequence({gemma4_value(), p_.zero_or_more(p_.sequence({p_.literal(","), ws, gemma4_value()}))});
-            return p_.sequence({
-                p_.literal("["), ws,
-                p_.choice({p_.literal("]"), p_.sequence({elements, ws, p_.literal("]")})})
-            });
-        });
-    }
-
-    common_peg_parser gemma4_value() {
-        return p_.rule("gemma4-value", [&]() {
-            return p_.choice({gemma4_string(), gemma4_dict(), gemma4_array(),
-                              gemma4_number(), gemma4_bool(), gemma4_null()});
-        });
-    }
-
-    // Select the appropriate value parser based on JSON schema type.
-    // Does NOT use schema() - the gemma4 types are pure PEG without
-    // JSON schema metadata, so GBNF is generated directly from the
-    // PEG structure.
-    common_peg_parser gemma4_value_for_type(const json & schema) {
-        if (!schema.contains("type") || !schema.at("type").is_string()) {
-            return gemma4_value();
-        }
-        std::string type = schema.at("type").get<std::string>();
-        if (type == "string")  { return gemma4_string(); }
-        if (type == "number")  { return gemma4_number(); }
-        if (type == "integer") { return gemma4_number(); }
-        if (type == "boolean") { return gemma4_bool(); }
-        if (type == "object")  { return gemma4_dict(); }
-        if (type == "array")   { return gemma4_array(); }
-        return gemma4_value();
-    }
-};
-
-}  // anonymous namespace
-
 // Helper to iterate over tools/functions
 static void foreach_function(const json & tools, const std::function<void(const json &)> & fn) {
     for (const auto & tool : tools) {
@@ -141,9 +43,7 @@ common_chat_params peg_generator::generate_parser(const common_chat_template &
     // Create the result structure
     common_chat_params data;
     data.prompt           = common_chat_template_direct_apply(tmpl, inputs);
-    data.format           = (autoparser.tools.format.mode == tool_format::TAG_WITH_GEMMA4_DICT)
-                            ? COMMON_CHAT_FORMAT_PEG_GEMMA4
-                            : COMMON_CHAT_FORMAT_PEG_NATIVE;
+    data.format           = COMMON_CHAT_FORMAT_PEG_NATIVE;
     data.preserved_tokens = autoparser.preserved_tokens;
 
     auto parser = autoparser.build_parser(inputs);
@@ -539,121 +439,4 @@ common_peg_parser analyze_tools::build_tool_parser_tag_tagged(parser_build_conte
            p.end();
 }
 
-common_peg_parser analyze_tools::build_tool_parser_tag_gemma4_dict(parser_build_context & ctx) const {
-    auto &       p           = ctx.p;
-    const auto & inputs      = ctx.inputs;
-    bool         force_tools = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED;
-
-    common_peg_gemma4_builder g4(p);
-    static const std::string QUOTE = "<|\"|>";
-
-    common_peg_parser tool_choice = p.choice();
-
-    foreach_function(inputs.tools, [&](const json & tool) {
-        const auto & func   = tool.at("function");
-        std::string  name   = func.at("name");
-        const auto & params = func.at("parameters");
-
-        if (!params.contains("properties") || !params.at("properties").is_object()) {
-            auto func_parser = p.atomic(
-                p.tool_open(p.literal(function.name_prefix) + p.tool_name(p.literal(name)) + p.literal("{")) +
-                p.tool_args(p.eps()) +
-                p.tool_close(p.literal("}")));
-            tool_choice |= p.rule("tool-" + name, func_parser);
-            return;
-        }
-
-        const auto &          properties = params.at("properties");
-        std::set<std::string> required;
-        if (params.contains("required") && params.at("required").is_array()) {
-            params.at("required").get_to(required);
-        }
-
-        // Build per-argument parsers, sorted alphabetically (matching template's dictsort)
-        struct arg_entry {
-            std::string       param_name;
-            common_peg_parser parser;
-        };
-        std::vector<arg_entry> arg_entries;
-
-        for (const auto & [param_name, param_schema] : properties.items()) {
-            std::string type    = "object";
-            auto        type_v  = param_schema.contains("type") ? param_schema.at("type") : json::object();
-            if (type_v.is_string()) type_v.get_to(type);
-
-            common_peg_parser value_parser = p.eps();
-            if (type == "string") {
-                // String values are delimited by <|"|>...<|"|>
-                value_parser =
-                    p.literal(QUOTE) +
-                    p.tool_arg_string_value(p.schema(p.until(QUOTE),
-                        "tool-" + name + "-arg-" + param_name + "-schema", param_schema, true)) +
-                    p.literal(QUOTE);
-            } else if (type == "number" || type == "integer") {
-                value_parser = p.tool_arg_value(g4.gemma4_number());
-            } else if (type == "boolean") {
-                value_parser = p.tool_arg_value(g4.gemma4_bool());
-            } else if (type == "null") {
-                value_parser = p.tool_arg_value(g4.gemma4_null());
-            } else if (type == "object") {
-                value_parser = p.tool_arg_value(g4.gemma4_dict());
-            } else if (type == "array") {
-                value_parser = p.tool_arg_value(g4.gemma4_array());
-            } else {
-                value_parser = p.tool_arg_value(g4.gemma4_value());
-            }
-
-            auto arg = p.tool_arg(
-                p.tool_arg_open(p.tool_arg_name(p.literal(param_name)) + p.literal(":")) +
-                value_parser +
-                p.tool_arg_close(p.eps()));
-
-            arg_entries.push_back({param_name, p.rule("tool-" + name + "-arg-" + param_name, arg)});
-        }
-
-        // Sort alphabetically to match Jinja's dictsort
-        std::sort(arg_entries.begin(), arg_entries.end(), [](const auto & a, const auto & b) {
-            return a.param_name < b.param_name;
-        });
-
-        // Build arg sequence: any arg, then zero-or-more comma-separated additional args
-        common_peg_parser args_seq = p.eps();
-        if (!arg_entries.empty()) {
-            common_peg_parser any_arg = p.choice();
-            for (auto & entry : arg_entries) {
-                any_arg |= entry.parser;
-            }
-            args_seq = p.optional(
-                any_arg + p.repeat(p.literal(",") + any_arg, 0, (int) arg_entries.size() - 1));
-        }
-
-        // Full parser: call:name{args}
-        auto func_parser = p.atomic(
-            p.tool_open(p.literal(function.name_prefix) + p.tool_name(p.literal(name)) + p.literal("{")) +
-            p.tool_args(args_seq) +
-            p.tool_close(p.literal("}")));
-
-        tool_choice |= p.rule("tool-" + name, func_parser);
-    });
-
-    // Wrap each call in <|tool_call>...</tool_call|>
-    auto wrapped_call = p.literal(format.per_call_start) + tool_choice + p.literal(format.per_call_end);
-
-    common_peg_parser tool_calls = p.eps();
-    if (inputs.parallel_tool_calls) {
-        tool_calls = p.trigger_rule("tool-call", wrapped_call + p.zero_or_more(p.space() + wrapped_call));
-    } else {
-        tool_calls = p.trigger_rule("tool-call", wrapped_call);
-    }
-
-    if (!force_tools) {
-        tool_calls = p.optional(tool_calls);
-    }
-
-    auto content_before_tools = p.until_one_of({ format.per_call_start, ctx.reasoning->start });
-    return ctx.reasoning_parser +
-           (force_tools ? p.eps() : p.optional(p.content(content_before_tools) + p.optional(ctx.reasoning_parser))) +
-           tool_calls + p.end();
-}
-
 }  // namespace autoparser

common/chat-auto-parser.h

@@ -352,6 +352,13 @@ struct analyze_tools : analyze_base {
     common_peg_parser build_tool_parser_json_native(parser_build_context & ctx) const;
     common_peg_parser build_tool_parser_tag_json(parser_build_context & ctx) const;
     common_peg_parser build_tool_parser_tag_tagged(parser_build_context & ctx) const;
+
+    // Shared helper: builds func_parser from open+call_id+args, handling atomic wrapping and close.
+    // atomic_peek: if present, used as the peek expression in the third atomicity branch.
+    common_peg_parser build_func_parser(common_chat_peg_builder & p, const std::string & name,
+                                        const common_peg_parser & call_id_section, bool have_call_id,
+                                        const common_peg_parser & args,
+                                        std::optional<common_peg_parser> atomic_peek) const;
 };
 
 // ============================================================================

common/chat-diff-analyzer.cpp

@@ -92,34 +92,6 @@ static std::vector<std::function<void(const common_chat_template & tmpl, autopar
               LOG_DBG(ANSI_ORANGE "[Patch: Functionary 3.1]\n" ANSI_RESET);
           }
       },
-      // Gemma4 - custom dict format: <|tool_call>call:name{key:<|"|>val<|"|>}<tool_call|>
-      [](const common_chat_template & tmpl, autoparser & analysis) -> void {
-          if (tmpl.src.find("'<|tool_call>call:'") != std::string::npos) {
-              analysis.tools.format.mode           = tool_format::TAG_WITH_GEMMA4_DICT;
-              analysis.tools.format.per_call_start = "<|tool_call>";
-              analysis.tools.format.per_call_end   = "<tool_call|>";
-              analysis.tools.format.section_start  = "";
-              analysis.tools.format.section_end    = "";
-              analysis.tools.function.name_prefix  = "call:";
-              analysis.tools.function.name_suffix  = "";
-              analysis.tools.arguments.start       = "{";
-              analysis.tools.arguments.end         = "}";
-              analysis.tools.arguments.name_prefix = "";
-              analysis.tools.arguments.name_suffix = ":";
-              analysis.tools.arguments.separator   = ",";
-              analysis.reasoning.mode              = reasoning_mode::TAG_BASED;
-              analysis.reasoning.start             = "<|channel>thought";
-              analysis.reasoning.end               = "<channel|>";
-              analysis.preserved_tokens.clear();
-              analysis.preserved_tokens.push_back("<|tool_call>");
-              analysis.preserved_tokens.push_back("<tool_call|>");
-              analysis.preserved_tokens.push_back("<|tool_response>");
-              analysis.preserved_tokens.push_back("<tool_response|>");
-              analysis.preserved_tokens.push_back("<|\"|>");
-              analysis.preserved_tokens.push_back("<|turn>");
-              LOG_DBG(ANSI_ORANGE "[Patch: Gemma4]\n" ANSI_RESET);
-          }
-      },
       // DeepSeek-R1-Distill-Qwen
       [](const common_chat_template & tmpl, autoparser & analysis) -> void {
           if (tmpl.src.find(