common : Generalized XML-style tool-call parsing with streaming support (GLM 4.5/4.6 + MiniMax M2 + SeedOSS + Kimi-K2 + Qwen3-Coder + Apriel-1.5 + Xiaomi-MiMo) (#16932)

* Add files via upload

* fix unit test

* fix crashes for --reasoning-format=none

* Patch buggy official MiniMax-M2 chat template

* add upstream minja fix: https://github.com/ochafik/minja/pull/7

* Fix <think> token not generated

* add test copied from https://github.com/ggml-org/llama.cpp/pull/16946

* cleanup

* Hopes to fix the compilation error on CI

* Delete chat template patching since it’s fixed by upstream Minja

* Remove undeeded Minimax-M2 template patch

https://github.com/ochafik/minja/pull/7#issuecomment-3480356100

* Add proper handling of optional parameters with test
merged tests from: https://github.com/ggml-org/llama.cpp/pull/16946/commits/23d4bb75c485c12ac89f81c424dc03c87a640e8c

* Fix making all tool parameters optional

* Move xml tool parser to separate file

* cleanup & add tests for GLM4.5

* add streaming tests & enhancement & cleanups

Add streaming test for both GLM 4.5 and minimax-m2.
Cleanup for preserved_tokens.
Cleanup for grammar rule name.
Enhance the parser's stability.

* cleanup & add support for Kimi-K2 Qwen3-Coder Apriel-1.5 Xiaomi-MiMo

* apply suggestions from reviewers

* fix a misuse for data.grammar_lazy

* fix grammar when tool have no argument

* Fix `no triggers set for lazy grammar!` for GLM4.5/4.6. Insert additional stops for Kimi-K2

* update chat.cpp

* fix grammar for GLM 4.5/4.6

* Try fix Jinja template for GLM

* Try fix GLM-4.6.jinja

* Update common/chat-parser-xml-toolcall.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update tests/test-chat.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* improve chat template for GLM, rename Kimi-K2 template to Kimi-K2-Thinking

* Improve Kimi-K2 chat template

* Fix unit test

* Fix "Invalid tool call arguments passed" in a rare case.

In a rare case, the model may emit a raw string that begins with a valid JSON string. This commit adds unit tests to cover that scenario and fixes the regression introduced during the Kimi-K2 adaptation.

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

common/CMakeLists.txt

@@ -50,6 +50,8 @@ add_library(${TARGET} STATIC
     base64.hpp
     chat-parser.cpp
     chat-parser.h
+    chat-parser-xml-toolcall.h
+    chat-parser-xml-toolcall.cpp
     chat.cpp
     chat.h
     common.cpp

common/chat-parser-xml-toolcall.cpp

@@ -0,0 +1,861 @@
+#include "chat.h"
+#include "chat-parser.h"
+#include "common.h"
+#include "json-partial.h"
+#include "json-schema-to-grammar.h"
+#include "log.h"
+#include "regex-partial.h"
+
+using json = nlohmann::ordered_json;
+
+class xml_toolcall_syntax_exception : public std::runtime_error {
+  public:
+    xml_toolcall_syntax_exception(const std::string & message) : std::runtime_error(message) {}
+};
+
+template<typename T>
+inline void sort_uniq(std::vector<T> &vec) {
+    std::sort(vec.begin(), vec.end());
+    vec.erase(std::unique(vec.begin(), vec.end()), vec.end());
+}
+
+template<typename T>
+inline bool all_space(const T &str) {
+    return std::all_of(str.begin(), str.end(), [](unsigned char ch) { return std::isspace(ch); });
+}
+
+static size_t utf8_truncate_safe(const std::string_view s) {
+    size_t len = s.size();
+    if (len == 0) return 0;
+    size_t i = len;
+    for (size_t back = 0; back < 4 && i > 0; ++back) {
+        --i;
+        unsigned char c = s[i];
+        if ((c & 0x80) == 0) {
+            return len;
+        } else if ((c & 0xC0) == 0xC0) {
+            size_t expected_len = 0;
+            if ((c & 0xE0) == 0xC0) expected_len = 2;
+            else if ((c & 0xF0) == 0xE0) expected_len = 3;
+            else if ((c & 0xF8) == 0xF0) expected_len = 4;
+            else return i;
+            if (len - i >= expected_len) {
+                return len;
+            } else {
+                return i;
+            }
+        }
+    }
+    return len - std::min(len, size_t(3));
+}
+
+inline void utf8_truncate_safe_resize(std::string &s) {
+    s.resize(utf8_truncate_safe(s));
+}
+
+inline std::string_view utf8_truncate_safe_view(const std::string_view s) {
+    return s.substr(0, utf8_truncate_safe(s));
+}
+
+static std::optional<common_chat_msg_parser::find_regex_result> try_find_2_literal_splited_by_spaces(common_chat_msg_parser & builder, const std::string & literal1, const std::string & literal2) {
+    if (literal1.size() == 0) return builder.try_find_literal(literal2);
+    const auto saved_pos = builder.pos();
+    while (auto res = builder.try_find_literal(literal1)) {
+        builder.consume_spaces();
+        const auto match_len = std::min(literal2.size(), builder.input().size() - builder.pos());
+        if (builder.input().compare(builder.pos(), match_len, literal2, 0, match_len) == 0) {
+            if (res->prelude.size() != res->groups[0].begin - saved_pos) {
+                res->prelude = builder.str({saved_pos, res->groups[0].begin});
+            }
+            builder.move_to(builder.pos() + match_len);
+            res->groups[0].end = builder.pos();
+            GGML_ASSERT(res->groups[0].begin != res->groups[0].end);
+            return res;
+        }
+        builder.move_to(res->groups[0].begin + 1);
+    }
+    builder.move_to(saved_pos);
+    return std::nullopt;
+}
+
+/**
+ * make a GBNF that accept any strings except those containing any of the forbidden strings.
+ */
+std::string make_gbnf_excluding(std::vector<std::string> forbids) {
+    constexpr auto charclass_escape = [](unsigned char c) -> std::string {
+        if (c == '\\' || c == ']' || c == '^' || c == '-') {
+            std::string s = "\\";
+            s.push_back((char)c);
+            return s;
+        }
+        if (isprint(c)) {
+            return std::string(1, (char)c);
+        }
+        char buf[16];
+        snprintf(buf, 15, "\\x%02X", c);
+        return std::string(buf);
+    };
+    constexpr auto build_expr = [charclass_escape](auto self, const std::vector<std::string>& forbids, int l, int r, int depth) -> std::string {
+        std::vector<std::pair<unsigned char, std::pair<int,int>>> children;
+        int i = l;
+        while (i < r) {
+            const std::string &s = forbids[i];
+            if ((int)s.size() == depth) {
+                ++i;
+                continue;
+            }
+            unsigned char c = (unsigned char)s[depth];
+            int j = i;
+            while (j < r && (int)forbids[j].size() > depth &&
+                   (unsigned char)forbids[j][depth] == c) {
+                ++j;
+            }
+            children.push_back({c, {i, j}});
+            i = j;
+        }
+        std::vector<std::string> alts;
+        if (!children.empty()) {
+            std::string cls;
+            for (auto &ch : children) cls += charclass_escape(ch.first);
+            alts.push_back(std::string("[^") + cls + "]");
+        }
+        for (auto &ch : children) {
+            std::string childExpr = self(self, forbids, ch.second.first, ch.second.second, depth+1);
+            if (!childExpr.empty()) {
+                std::string quoted_ch = "\"";
+                if (ch.first == '\\') quoted_ch += "\\\\";
+                else if (ch.first == '"') quoted_ch += "\\\"";
+                else if (isprint(ch.first)) quoted_ch.push_back(ch.first);
+                else {
+                    char buf[16];
+                    snprintf(buf, 15, "\\x%02X", ch.first);
+                    quoted_ch += buf;
+                }
+                quoted_ch += "\"";
+                std::string branch = quoted_ch + std::string(" ") + childExpr;
+                alts.push_back(branch);
+            }
+        }
+        if (alts.empty()) return "";
+        std::ostringstream oss;
+        oss << "( ";
+        for (size_t k = 0; k < alts.size(); ++k) {
+            if (k) oss << " | ";
+            oss << alts[k];
+        }
+        oss << " )";
+        return oss.str();
+    };
+    if (forbids.empty()) return "( . )*";
+    sort(forbids.begin(), forbids.end());
+    std::string expr = build_expr(build_expr, forbids, 0, forbids.size(), 0);
+    if (expr.empty()) {
+        std::string cls;
+        for (auto &s : forbids) if (!s.empty()) cls += charclass_escape((unsigned char)s[0]);
+        expr = std::string("( [^") + cls + "] )";
+    }
+    if (forbids.size() == 1)
+        return expr + "*";
+    else
+        return std::string("( ") + expr + " )*";
+}
+
+/**
+ * Build grammar for xml-style tool call
+ * form.scope_start and form.scope_end can be empty.
+ * Requires data.format for model-specific hacks.
+ */
+void build_grammar_xml_tool_call(common_chat_params & data, const json & tools, const struct xml_tool_call_format & form) {
+    GGML_ASSERT(!form.tool_start.empty());
+    GGML_ASSERT(!form.tool_sep.empty());
+    GGML_ASSERT(!form.key_start.empty());
+    GGML_ASSERT(!form.val_end.empty());
+    GGML_ASSERT(!form.tool_end.empty());
+
+    std::string key_val_sep = form.key_val_sep;
+    if (form.key_val_sep2) {
+        key_val_sep += "\n";
+        key_val_sep += *form.key_val_sep2;
+    }
+    GGML_ASSERT(!key_val_sep.empty());
+
+    if (tools.is_array() && !tools.empty()) {
+        data.grammar = build_grammar([&](const common_grammar_builder &builder) {
+            auto string_arg_val = form.last_val_end ?
+                    builder.add_rule("string-arg-val", make_gbnf_excluding({form.val_end, *form.last_val_end})) :
+                    builder.add_rule("string-arg-val", make_gbnf_excluding({form.val_end}));
+
+            std::vector<std::string> tool_rules;
+            for (const auto & tool : tools) {
+                if (!tool.contains("type") || tool.at("type") != "function" || !tool.contains("function")) {
+                    LOG_WRN("Skipping tool without function: %s", tool.dump(2).c_str());
+                    continue;
+                }
+                const auto & function = tool.at("function");
+                if (!function.contains("name") || !function.at("name").is_string()) {
+                    LOG_WRN("Skipping invalid function (invalid name): %s", function.dump(2).c_str());
+                    continue;
+                }
+                if (!function.contains("parameters") || !function.at("parameters").is_object()) {
+                    LOG_WRN("Skipping invalid function (invalid parameters): %s", function.dump(2).c_str());
+                    continue;
+                }
+                std::string name = function.at("name");
+                auto parameters = function.at("parameters");
+                builder.resolve_refs(parameters);
+
+                struct parameter_rule {
+                    std::string symbol_name;
+                    bool is_required;
+                };
+                std::vector<parameter_rule> arg_rules;
+                if (!parameters.contains("properties") || !parameters.at("properties").is_object()) {
+                    LOG_WRN("Skipping invalid function (invalid properties): %s", function.dump(2).c_str());
+                    continue;
+                } else {
+                    std::vector<std::string> requiredParameters;
+                    if (parameters.contains("required")) {
+                        try { parameters.at("required").get_to(requiredParameters); }
+                        catch (const std::runtime_error&) {
+                            LOG_WRN("Invalid function required parameters, ignoring: %s", function.at("required").dump(2).c_str());
+                        }
+                    }
+                    sort_uniq(requiredParameters);
+                    for (const auto & [key, value] : parameters.at("properties").items()) {
+                        std::string quoted_key = key;
+                        bool required = std::binary_search(requiredParameters.begin(), requiredParameters.end(), key);
+                        if (form.key_start.back() == '"' && key_val_sep[0] == '"') {
+                            quoted_key = gbnf_format_literal(key);
+                            quoted_key = quoted_key.substr(1, quoted_key.size() - 2);
+                        }
+                        arg_rules.push_back(parameter_rule {builder.add_rule("func-" + name + "-kv-" + key,
+                            gbnf_format_literal(form.key_start) + " " +
+                            gbnf_format_literal(quoted_key) + " " +
+                            gbnf_format_literal(key_val_sep) + " " +
+                            ((value.contains("type") && value["type"].is_string() && value["type"] == "string" && (!form.raw_argval || *form.raw_argval)) ?
+                                    (form.raw_argval ?
+                                            string_arg_val :
+                                            "( " + string_arg_val + " | " + builder.add_schema(name + "-arg-" + key, value) + " )"
+                                    ) :
+                                    builder.add_schema(name + "-arg-" + key, value)
+                            )
+                        ), required});
+                    }
+                }
+
+                auto next_arg_with_sep = builder.add_rule(name + "-last-arg-end", form.last_val_end ? gbnf_format_literal(*form.last_val_end) : gbnf_format_literal(form.val_end));
+                decltype(next_arg_with_sep) next_arg = "\"\"";
+                for (auto i = arg_rules.size() - 1; /* i >= 0 && */ i < arg_rules.size(); --i) {
+                    std::string include_this_arg = arg_rules[i].symbol_name + " " + next_arg_with_sep;
+                    next_arg = builder.add_rule(name + "-arg-after-" + std::to_string(i), arg_rules[i].is_required ?
+                            include_this_arg : "( " + include_this_arg + " ) | " + next_arg
+                    );
+                    include_this_arg = gbnf_format_literal(form.val_end) + " " + include_this_arg;
+                    next_arg_with_sep = builder.add_rule(name + "-arg-after-" + std::to_string(i) + "-with-sep", arg_rules[i].is_required ?
+                            include_this_arg : "( " + include_this_arg + " ) | " + next_arg_with_sep
+                    );
+                }
+
+                std::string quoted_name = name;
+                if (form.tool_start.back() == '"' && form.tool_sep[0] == '"') {
+                    quoted_name = gbnf_format_literal(name);
+                    quoted_name = quoted_name.substr(1, quoted_name.size() - 2);
+                }
+                quoted_name = gbnf_format_literal(quoted_name);
+                // Kimi-K2 uses functions.{{ tool_call['function']['name'] }}:{{ loop.index }} as function name
+                if (data.format == COMMON_CHAT_FORMAT_KIMI_K2) {
+                    quoted_name = "\"functions.\" " + quoted_name + " \":\" [0-9]+";
+                }
+                tool_rules.push_back(builder.add_rule(name + "-call",
+                        gbnf_format_literal(form.tool_start) + " " +
+                        quoted_name + " " +
+                        gbnf_format_literal(form.tool_sep) + " " +
+                        next_arg
+                ));
+            }
+
+            auto tool_call_once = builder.add_rule("root-tool-call-once", string_join(tool_rules, " | "));
+            auto tool_call_more = builder.add_rule("root-tool-call-more", gbnf_format_literal(form.tool_end) + " " + tool_call_once);
+            auto call_end = builder.add_rule("root-call-end", form.last_tool_end ? gbnf_format_literal(*form.last_tool_end) : gbnf_format_literal(form.tool_end));
+            auto tool_call_multiple_with_end = builder.add_rule("root-tool-call-multiple-with-end", tool_call_once + " " + tool_call_more + "* " + call_end);
+            builder.add_rule("root",
+                (form.scope_start.empty() ? "" : gbnf_format_literal(form.scope_start) + " ") +
+                tool_call_multiple_with_end  + "?" +
+                (form.scope_end.empty() ? "" : " " + gbnf_format_literal(form.scope_end))
+            );
+        });
+
+        // grammar trigger for tool call
+        data.grammar_triggers.push_back({ COMMON_GRAMMAR_TRIGGER_TYPE_WORD, form.scope_start + form.tool_start });
+    }
+}
+
+/**
+ * Parse XML-Style tool call for given xml_tool_call_format. Return false for invalid syntax and get the position untouched.
+ * Throws xml_toolcall_syntax_exception if there is invalid syntax and cannot recover the original status for common_chat_msg_parser.
+ * form.scope_start, form.tool_sep and form.scope_end can be empty.
+ */
+inline bool parse_xml_tool_calls(common_chat_msg_parser & builder, const struct xml_tool_call_format & form) {
+    GGML_ASSERT(!form.tool_start.empty());
+    GGML_ASSERT(!form.key_start.empty());
+    GGML_ASSERT(!form.key_val_sep.empty());
+    GGML_ASSERT(!form.val_end.empty());
+    GGML_ASSERT(!form.tool_end.empty());
+
+    // Helper to choose return false or throw error
+    constexpr auto return_error = [](common_chat_msg_parser & builder, auto &start_pos, const bool &recovery) {
+        LOG_DBG("Failed to parse XML-Style tool call at position: %s\n", gbnf_format_literal(builder.consume_rest().substr(0, 20)).c_str());
+        if (recovery) {
+            builder.move_to(start_pos);
+            return false;
+        } else throw xml_toolcall_syntax_exception("Tool call parsing failed with unrecoverable errors. Try using a grammar to constrain the model’s output.");
+    };
+    // Drop substring from needle to end from a JSON
+    constexpr auto partial_json = [](std::string &json_str, std::string_view needle = "XML_TOOL_CALL_PARTIAL_FLAG") {
+        auto pos = json_str.rfind(needle);
+        if (pos == std::string::npos) {
+            return false;
+        }
+        for (auto i = pos + needle.size(); i < json_str.size(); ++i) {
+            unsigned char ch = static_cast<unsigned char>(json_str[i]);
+            if (ch != '\'' && ch != '"' && ch != '}' && ch != ':' && !std::isspace(ch)) {
+                return false;
+            }
+        }
+        if (pos != 0 && json_str[pos - 1] == '"') {
+            --pos;
+        }
+        json_str.resize(pos);
+        return true;
+    };
+    // Helper to generate a partial argument JSON
+    constexpr auto gen_partial_json = [partial_json](auto set_partial_arg, auto &arguments, auto &builder, auto &function_name) {
+        auto rest = builder.consume_rest();
+        utf8_truncate_safe_resize(rest);
+        set_partial_arg(rest, "XML_TOOL_CALL_PARTIAL_FLAG");
+        auto tool_str = arguments.dump();
+        if (partial_json(tool_str)) {
+            if (builder.add_tool_call(function_name, "", tool_str)) {
+                return;
+            }
+        }
+        LOG_DBG("Failed to parse partial XML-Style tool call, fallback to non-partial: %s\n", tool_str.c_str());
+    };
+    // Helper to find a close (because there may be form.last_val_end or form.last_tool_end)
+    constexpr auto try_find_close = [](
+            common_chat_msg_parser & builder,
+            const std::string & end,
+            const std::optional<std::string> & alt_end,
+            const std::string & end_next,
+            const std::optional<std::string> & alt_end_next
+    ) {
+        auto saved_pos = builder.pos();
+        auto tc = builder.try_find_literal(end);
+        auto val_end_size = end.size();
+        if (alt_end) {
+            auto pos_1 = builder.pos();
+            builder.move_to(saved_pos);
+            auto tc2 = try_find_2_literal_splited_by_spaces(builder, *alt_end, end_next);
+            if (alt_end_next) {
+                builder.move_to(saved_pos);
+                auto tc3 = try_find_2_literal_splited_by_spaces(builder, *alt_end, *alt_end_next);
+                if (tc3 && (!tc2 || tc2->prelude.size() > tc3->prelude.size())) {
+                    tc2 = tc3;
+                }
+            }
+            if (tc2 && (!tc || tc->prelude.size() > tc2->prelude.size())) {
+                tc = tc2;
+                tc->groups[0].end = std::min(builder.input().size(), tc->groups[0].begin + alt_end->size());
+                builder.move_to(tc->groups[0].end);
+                val_end_size = alt_end->size();
+            } else {
+                builder.move_to(pos_1);
+            }
+        }
+        return std::make_pair(val_end_size, tc);
+    };
+    // Helper to find a val_end or last_val_end, returns matched pattern size
+    const auto try_find_val_end = [try_find_close, &builder, &form]() {
+        return try_find_close(builder, form.val_end, form.last_val_end, form.tool_end, form.last_tool_end);
+    };
+    // Helper to find a tool_end or last_tool_end, returns matched pattern size
+    const auto try_find_tool_end = [try_find_close, &builder, &form]() {
+        return try_find_close(builder, form.tool_end, form.last_tool_end, form.scope_end, std::nullopt);
+    };
+
+    bool recovery = true;
+    const auto start_pos = builder.pos();
+    if (!all_space(form.scope_start)) {
+        if (auto tc = builder.try_find_literal(form.scope_start)) {
+            if (all_space(tc->prelude)) {
+                if (form.scope_start.size() != tc->groups[0].end - tc->groups[0].begin)
+                    throw common_chat_msg_partial_exception("Partial literal: " + gbnf_format_literal(form.scope_start));
+            } else {
+                builder.move_to(start_pos);
+                return false;
+            }
+        } else return false;
+    }
+    while (auto tc = builder.try_find_literal(form.tool_start)) {
+        if (!all_space(tc->prelude)) {
+            LOG_DBG("XML-Style tool call: Expected %s, but found %s, trying to match next pattern\n",
+                    gbnf_format_literal(form.tool_start).c_str(),
+                    gbnf_format_literal(tc->prelude).c_str()
+            );
+            builder.move_to(tc->groups[0].begin - tc->prelude.size());
+            break;
+        }
+
+        // Find tool name
+        auto func_name = builder.try_find_literal(all_space(form.tool_sep) ? form.key_start : form.tool_sep);
+        if (!func_name) {
+            auto [sz, tc] = try_find_tool_end();
+            func_name = tc;
+        }
+        if (!func_name) {
+            // Partial tool name not supported
+            throw common_chat_msg_partial_exception("incomplete tool_call");
+        }
+        // If the model generate multiple tool call and the first tool call has no argument
+        if (func_name->prelude.find(form.tool_end) != std::string::npos || (form.last_tool_end ? func_name->prelude.find(*form.last_tool_end) != std::string::npos : false)) {
+            builder.move_to(func_name->groups[0].begin - func_name->prelude.size());
+            auto [sz, tc] = try_find_tool_end();
+            func_name = tc;
+        }
+
+        // Parse tool name
+        builder.move_to(all_space(form.tool_sep) ? func_name->groups[0].begin : func_name->groups[0].end);
+        std::string function_name = string_strip(func_name->prelude);
+        // Kimi-K2 uses functions.{{ tool_call['function']['name'] }}:{{ loop.index }} as function name
+        if (builder.syntax().format == COMMON_CHAT_FORMAT_KIMI_K2) {
+            if (string_starts_with(function_name, "functions.")) {
+                static const std::regex re(":\\d+$");
+                if (std::regex_search(function_name, re)) {
+                    function_name = function_name.substr(10, function_name.rfind(":") - 10);
+                }
+            }
+        }
+
+        // Argument JSON
+        json arguments = json::object();
+
+        // Helper to generate a partial argument JSON
+        const auto gen_partial_args = [&](auto set_partial_arg) {
+            gen_partial_json(set_partial_arg, arguments, builder, function_name);
+        };
+
+        // Parse all arg_key/arg_value pairs
+        while (auto tc = builder.try_find_literal(form.key_start)) {
+            if (!all_space(tc->prelude)) {
+                LOG_DBG("XML-Style tool call: Expected %s, but found %s, trying to match next pattern\n",
+                        gbnf_format_literal(form.key_start).c_str(),
+                        gbnf_format_literal(tc->prelude).c_str()
+                );
+                builder.move_to(tc->groups[0].begin - tc->prelude.size());
+                break;
+            }
+            if (tc->groups[0].end - tc->groups[0].begin != form.key_start.size()) {
+                auto tool_call_arg = arguments.dump();
+                if (tool_call_arg.size() != 0 && tool_call_arg[tool_call_arg.size() - 1] == '}') {
+                    tool_call_arg.resize(tool_call_arg.size() - 1);
+                }
+                builder.add_tool_call(function_name, "", tool_call_arg);
+                throw common_chat_msg_partial_exception("Partial literal: " + gbnf_format_literal(form.key_start));
+            }
+
+            // Parse arg_key
+            auto key_res = builder.try_find_literal(form.key_val_sep);
+            if (!key_res) {
+                gen_partial_args([&](auto &rest, auto &needle) {arguments[rest + needle] = "";});
+                throw common_chat_msg_partial_exception("Expected " + gbnf_format_literal(form.key_val_sep) + " after " + gbnf_format_literal(form.key_start));
+            }
+            if (key_res->groups[0].end - key_res->groups[0].begin != form.key_val_sep.size()) {
+                gen_partial_args([&](auto &, auto &needle) {arguments[key_res->prelude + needle] = "";});
+                throw common_chat_msg_partial_exception("Partial literal: " + gbnf_format_literal(form.key_val_sep));
+            }
+            auto &key = key_res->prelude;
+            recovery = false;
+
+            // Parse arg_value
+            if (form.key_val_sep2) {
+                if (auto tc = builder.try_find_literal(*form.key_val_sep2)) {
+                    if (!all_space(tc->prelude)) {
+                        LOG_DBG("Failed to parse XML-Style tool call: Unexcepted %s between %s and %s\n",
+                                gbnf_format_literal(tc->prelude).c_str(),
+                                gbnf_format_literal(form.key_val_sep).c_str(),
+                                gbnf_format_literal(*form.key_val_sep2).c_str()
+                        );
+                        return return_error(builder, start_pos, false);
+                    }
+                    if (tc->groups[0].end - tc->groups[0].begin != form.key_val_sep2->size()) {
+                        gen_partial_args([&](auto &, auto &needle) {arguments[key] = needle;});
+                        throw common_chat_msg_partial_exception("Partial literal: " + gbnf_format_literal(*form.key_val_sep2));
+                    }
+                } else {
+                    gen_partial_args([&](auto &, auto &needle) {arguments[key] = needle;});
+                    throw common_chat_msg_partial_exception("Expected " + gbnf_format_literal(*form.key_val_sep2) + " after " + gbnf_format_literal(form.key_val_sep));
+                }
+            }
+            auto val_start = builder.pos();
+
+            // Test if arg_val is a partial JSON
+            std::optional<common_json> value_json = std::nullopt;
+            if (!form.raw_argval || !*form.raw_argval) {
+                try { value_json = builder.try_consume_json(); }
+                catch (const std::runtime_error&) { builder.move_to(val_start); }
+                // TODO: Delete this when json_partial adds top-level support for null/true/false
+                if (builder.pos() == val_start) {
+                    const static std::regex number_regex(R"([0-9-][0-9]*(\.\d*)?([eE][+-]?\d*)?)");
+                    builder.consume_spaces();
+                    std::string_view sv = utf8_truncate_safe_view(builder.input());
+                    sv.remove_prefix(builder.pos());
+                    std::string rest = "a";
+                    if (sv.size() < 6) rest = sv;
+                    if (string_starts_with("null", rest) || string_starts_with("true", rest) || string_starts_with("false", rest) || std::regex_match(sv.begin(), sv.end(), number_regex)) {
+                        value_json = {123, {"123", "123"}};
+                        builder.consume_rest();
+                    } else {
+                        builder.move_to(val_start);
+                    }
+                }
+            }
+
+            // If it is a JSON and followed by </arg_value>, parse as json
+            // cannot support streaming because it may be a plain text starting with JSON
+            if (value_json) {
+                auto json_end = builder.pos();
+                builder.consume_spaces();
+                if (builder.pos() == builder.input().size()) {
+                    if (form.raw_argval && !*form.raw_argval && (value_json->json.is_string() || value_json->json.is_object() || value_json->json.is_array())) {
+                        arguments[key] = value_json->json;
+                        auto json_str = arguments.dump();
+                        if (!value_json->healing_marker.json_dump_marker.empty()) {
+                            GGML_ASSERT(std::string::npos != json_str.rfind(value_json->healing_marker.json_dump_marker));
+                            json_str.resize(json_str.rfind(value_json->healing_marker.json_dump_marker));
+                        } else {
+                            GGML_ASSERT(json_str.back() == '}');
+                            json_str.resize(json_str.size() - 1);
+                        }
+                        builder.add_tool_call(function_name, "", json_str);
+                    } else {
+                        gen_partial_args([&](auto &, auto &needle) {arguments[key] = needle;});
+                    }
+                    LOG_DBG("Possible JSON arg_value: %s\n", value_json->json.dump().c_str());
+                    throw common_chat_msg_partial_exception("JSON arg_value detected. Waiting for more tokens for validations.");
+                }
+                builder.move_to(json_end);
+                auto [val_end_size, tc] = try_find_val_end();
+                if (tc && all_space(tc->prelude) && value_json->healing_marker.marker.empty()) {
+                    if (tc->groups[0].end - tc->groups[0].begin != val_end_size) {
+                        gen_partial_args([&](auto &, auto &needle) {arguments[key] = needle;});
+                        LOG_DBG("Possible terminated JSON arg_value: %s\n", value_json->json.dump().c_str());
+                        throw common_chat_msg_partial_exception("Partial literal: " + gbnf_format_literal(form.val_end) + (form.last_val_end ? gbnf_format_literal(*form.last_val_end) : ""));
+                    } else arguments[key] = value_json->json;
+                } else builder.move_to(val_start);
+            }
+
+            // If not, parse as plain text
+            if (val_start == builder.pos()) {
+                if (auto [val_end_size, value_plain] = try_find_val_end(); value_plain) {
+                    auto &value_str = value_plain->prelude;
+                    if (form.trim_raw_argval) value_str = string_strip(value_str);
+                    if (value_plain->groups[0].end - value_plain->groups[0].begin != val_end_size) {
+                        gen_partial_args([&](auto &, auto &needle) {arguments[key] = value_str + needle;});
+                        throw common_chat_msg_partial_exception(
+                                "Expected " + gbnf_format_literal(form.val_end) +
+                                " after " + gbnf_format_literal(form.key_val_sep) +
+                                (form.key_val_sep2 ? " " + gbnf_format_literal(*form.key_val_sep2) : "")
+                        );
+                    }
+                    arguments[key] = value_str;
+                } else {
+                    if (form.trim_raw_argval) {
+                        gen_partial_args([&](auto &rest, auto &needle) {arguments[key] = string_strip(rest) + needle;});
+                    } else {
+                        gen_partial_args([&](auto &rest, auto &needle) {arguments[key] = rest + needle;});
+                    }
+                    throw common_chat_msg_partial_exception(
+                            "Expected " + gbnf_format_literal(form.val_end) +
+                            " after " + gbnf_format_literal(form.key_val_sep) +
+                            (form.key_val_sep2 ? " " + gbnf_format_literal(*form.key_val_sep2) : "")
+                    );
+                }
+            }
+        }
+
+        // Consume closing tag
+        if (auto [tool_end_size, tc] = try_find_tool_end(); tc) {
+            if (!all_space(tc->prelude)) {
+                LOG_DBG("Failed to parse XML-Style tool call: Expected %s, but found %s\n",
+                        gbnf_format_literal(form.tool_end).c_str(),
+                        gbnf_format_literal(tc->prelude).c_str()
+                );
+                return return_error(builder, start_pos, recovery);
+            }
+            if (tc->groups[0].end - tc->groups[0].begin == tool_end_size) {
+                // Add the parsed tool call
+                if (!builder.add_tool_call(function_name, "", arguments.dump())) {
+                    throw common_chat_msg_partial_exception("Failed to add XML-Style tool call");
+                }
+                recovery = false;
+                continue;
+            }
+        }
+
+        auto tool_call_arg = arguments.dump();
+        if (tool_call_arg.size() != 0 && tool_call_arg[tool_call_arg.size() - 1] == '}') {
+            tool_call_arg.resize(tool_call_arg.size() - 1);
+        }
+        builder.add_tool_call(function_name, "", tool_call_arg);
+        throw common_chat_msg_partial_exception("Expected " + gbnf_format_literal(form.tool_end) + " after " + gbnf_format_literal(form.val_end));
+    }
+    if (auto tc = builder.try_find_literal(form.scope_end)) {
+        if (!all_space(tc->prelude)) {
+            LOG_DBG("Failed to parse XML-Style tool call: Expected %s, but found %s\n",
+                    gbnf_format_literal(form.scope_end).c_str(),
+                    gbnf_format_literal(tc->prelude).c_str()
+            );
+            return return_error(builder, start_pos, recovery);
+        }
+    } else {
+        if (all_space(form.scope_end)) return true;
+        builder.consume_spaces();
+        if (builder.pos() == builder.input().size())
+            throw common_chat_msg_partial_exception("incomplete tool calls");
+        LOG_DBG("Failed to parse XML-Style tool call: Expected %s, but found %s\n",
+                gbnf_format_literal(form.scope_end).c_str(),
+                gbnf_format_literal(builder.consume_rest()).c_str()
+        );
+        return return_error(builder, start_pos, recovery);
+    }
+
+    return true;
+}
+
+/**
+ * Parse XML-Style tool call for given xml_tool_call_format. Return false for invalid syntax and get the position untouched.
+ * May cause std::runtime_error if there is invalid syntax because partial valid tool call is already sent out to client.
+ * form.scope_start, form.tool_sep and form.scope_end can be empty.
+ */
+bool common_chat_msg_parser::try_consume_xml_tool_calls(const struct xml_tool_call_format & form) {
+    auto pos = pos_;
+    auto tsize = result_.tool_calls.size();
+    try { return parse_xml_tool_calls(*this, form); }
+    catch (const xml_toolcall_syntax_exception&) {}
+    move_to(pos);
+    result_.tool_calls.resize(tsize);
+    return false;
+}
+
+/**
+ * Parse content uses reasoning and XML-Style tool call
+ * TODO: Note that form.allow_toolcall_in_think is not tested yet. If anyone confirms it works, this comment can be removed.
+ */
+inline void parse_msg_with_xml_tool_calls(common_chat_msg_parser & builder, const struct xml_tool_call_format & form, const std::string & start_think = "<think>", const std::string & end_think = "</think>") {
+    constexpr auto rstrip = [](std::string &s) {
+        s.resize(std::distance(s.begin(), std::find_if(s.rbegin(), s.rend(), [](unsigned char ch) { return !std::isspace(ch); }).base()));
+    };
+    // Erase substring from l to r, along with additional spaces nearby
+    constexpr auto erase_spaces = [](auto &str, size_t l, size_t r) {
+        while (/* l > -1 && */ --l < str.size() && std::isspace(static_cast<unsigned char>(str[l])));
+        ++l;
+        while (++r < str.size() && std::isspace(static_cast<unsigned char>(str[r])));
+        if (l < r) str[l] = '\n';
+        if (l + 1 < r) str[l + 1] = '\n';
+        if (l != 0) l += 2;
+        str.erase(l, r - l);
+        return l;
+    };
+    constexpr auto trim_suffix = [](std::string &content, std::initializer_list<std::string_view> list) {
+        auto best_match = content.size();
+        for (auto pattern: list) {
+            if (pattern.size() == 0) continue;
+            for (auto match_idx = content.size() - std::min(pattern.size(), content.size()); content.size() > match_idx; match_idx++) {
+                auto match_len = content.size() - match_idx;
+                if (content.compare(match_idx, match_len, pattern.data(), match_len) == 0 && best_match > match_idx) {
+                    best_match = match_idx;
+                }
+            }
+        }
+        if (content.size() > best_match) {
+            content.erase(best_match);
+        }
+    };
+    const auto trim_potential_partial_word = [&start_think, &end_think, &form, trim_suffix](std::string &content) {
+        return trim_suffix(content, {
+            start_think, end_think, form.scope_start, form.tool_start, form.tool_sep, form.key_start,
+            form.key_val_sep, form.key_val_sep2 ? form.key_val_sep2->c_str() : "",
+            form.val_end, form.last_val_end ? form.last_val_end->c_str() : "",
+            form.tool_end, form.last_tool_end ? form.last_tool_end->c_str() : "",
+            form.scope_end
+        });
+    };
+
+
+    // Trim leading spaces without affecting keyword matching
+    static const common_regex spaces_regex("\\s*");
+    {
+        auto tc = builder.consume_regex(spaces_regex);
+        auto spaces = builder.str(tc.groups[0]);
+        auto s1 = spaces.size();
+        trim_potential_partial_word(spaces);
+        auto s2 = spaces.size();
+        builder.move_to(builder.pos() - (s1 - s2));
+    }
+
+    // Parse content
+    bool reasoning_unclosed = builder.syntax().thinking_forced_open;
+    std::string unclosed_reasoning_content("");
+    for (;;) {
+        auto tc = try_find_2_literal_splited_by_spaces(builder, form.scope_start, form.tool_start);
+        std::string content;
+        std::string tool_call_start;
+
+        if (tc) {
+            content = std::move(tc->prelude);
+            tool_call_start = builder.str(tc->groups[0]);
+            LOG_DBG("Matched tool start: %s\n", gbnf_format_literal(tool_call_start).c_str());
+        } else {
+            content = builder.consume_rest();
+            utf8_truncate_safe_resize(content);
+        }
+
+        // Handle unclosed think block
+        if (reasoning_unclosed) {
+            if (auto pos = content.find(end_think); pos == std::string::npos && builder.pos() != builder.input().size()) {
+                unclosed_reasoning_content += content;
+                if (form.allow_toolcall_in_think) {
+                    builder.move_to(tc->groups[0].begin);
+                    if (!builder.try_consume_xml_tool_calls(form)) {
+                        unclosed_reasoning_content += tool_call_start;
+                        builder.move_to(tc->groups[0].end);
+                    }
+                } else {
+                    unclosed_reasoning_content += tool_call_start;
+                }
+                continue;
+            } else {
+                reasoning_unclosed = false;
+                std::string reasoning_content;
+                if (pos == std::string::npos) {
+                    reasoning_content = std::move(content);
+                } else {
+                    reasoning_content = content.substr(0, pos);
+                    content.erase(0, pos + end_think.size());
+                }
+                if (builder.pos() == builder.input().size() && all_space(content)) {
+                    rstrip(reasoning_content);
+                    trim_potential_partial_word(reasoning_content);
+                    rstrip(reasoning_content);
+                    if (reasoning_content.empty()) {
+                        rstrip(unclosed_reasoning_content);
+                        trim_potential_partial_word(unclosed_reasoning_content);
+                        rstrip(unclosed_reasoning_content);
+                        if (unclosed_reasoning_content.empty()) continue;
+                    }
+                }
+                if (builder.syntax().reasoning_format == COMMON_REASONING_FORMAT_NONE || builder.syntax().reasoning_in_content) {
+                    builder.add_content(start_think);
+                    builder.add_content(unclosed_reasoning_content);
+                    builder.add_content(reasoning_content);
+                    if (builder.pos() != builder.input().size() || !all_space(content))
+                        builder.add_content(end_think);
+                } else {
+                    builder.add_reasoning_content(unclosed_reasoning_content);
+                    builder.add_reasoning_content(reasoning_content);
+                }
+                unclosed_reasoning_content.clear();
+            }
+        }
+
+        // Handle multiple think block
+        bool toolcall_in_think = false;
+        for (auto think_start = content.find(start_think); think_start != std::string::npos; think_start = content.find(start_think, think_start)) {
+            if (auto think_end = content.find(end_think, think_start + start_think.size()); think_end != std::string::npos) {
+                if (builder.syntax().reasoning_format != COMMON_REASONING_FORMAT_NONE && !builder.syntax().reasoning_in_content) {
+                    auto reasoning_content = content.substr(think_start + start_think.size(), think_end - think_start - start_think.size());
+                    builder.add_reasoning_content(reasoning_content);
+                    think_start = erase_spaces(content, think_start, think_end + end_think.size() - 1);
+                } else {
+                    think_start = think_end + end_think.size() - 1;
+                }
+            } else {
+                // This <tool_call> start is in thinking block, skip this tool call
+                auto pos = think_start + start_think.size();
+                unclosed_reasoning_content = content.substr(pos) + tool_call_start;
+                reasoning_unclosed = true;
+                content.resize(think_start);
+                toolcall_in_think = true;
+            }
+        }
+
+        if (builder.syntax().reasoning_format != COMMON_REASONING_FORMAT_NONE && !builder.syntax().reasoning_in_content) {
+            rstrip(content);
+            // Handle unclosed </think> token from content: delete all </think> token
+            if (auto pos = content.rfind(end_think); pos != std::string::npos) {
+                while (pos != std::string::npos) {
+                    pos = erase_spaces(content, pos, pos + end_think.size() - 1);
+                    pos = content.rfind(end_think, pos);
+                }
+            }
+            // Strip if needed
+            if (content.size() > 0 && std::isspace(static_cast<unsigned char>(content[0]))) {
+                content = string_strip(content);
+            }
+        }
+
+        // remove potential partial suffix
+        if (content.size() > 0 && builder.pos() == builder.input().size() && unclosed_reasoning_content.empty()) {
+            rstrip(content);
+            trim_potential_partial_word(content);
+            rstrip(content);
+        }
+
+        // Add content
+        if (content.size() != 0) {
+            // If there are multiple content blocks
+            if (builder.syntax().reasoning_format != COMMON_REASONING_FORMAT_NONE && !builder.syntax().reasoning_in_content && builder.result().content.size() != 0) {
+                builder.add_content("\n\n");
+            }
+            builder.add_content(content);
+        }
+
+        // This <tool_call> start is in thinking block, skip this tool call
+        if (toolcall_in_think && !form.allow_toolcall_in_think) {
+            continue;
+        }
+
+        // There is no tool call and all content is parsed
+        if (!tc) {
+            GGML_ASSERT(builder.pos() == builder.input().size());
+            GGML_ASSERT(unclosed_reasoning_content.empty());
+            GGML_ASSERT(!reasoning_unclosed);
+            break;
+        }
+
+        builder.move_to(tc->groups[0].begin);
+        if (builder.try_consume_xml_tool_calls(form)) {
+            auto end_of_tool = builder.pos();
+            builder.consume_spaces();
+            if (builder.pos() != builder.input().size()) {
+                builder.move_to(end_of_tool);
+                if (!builder.result().content.empty()) {
+                    builder.add_content("\n\n");
+                }
+            }
+        } else {
+            static const common_regex next_char_regex(".");
+            auto c = builder.str(builder.consume_regex(next_char_regex).groups[0]);
+            rstrip(c);
+            builder.add_content(c);
+        }
+    }
+}
+
+/**
+ * Parse content uses reasoning and XML-Style tool call
+ * TODO: Note that form.allow_toolcall_in_think is not tested yet. If anyone confirms it works, this comment can be removed.
+ */
+void common_chat_msg_parser::consume_reasoning_with_xml_tool_calls(const struct xml_tool_call_format & form, const std::string & start_think, const std::string & end_think) {
+    parse_msg_with_xml_tool_calls(*this, form, start_think, end_think);
+}

common/chat-parser-xml-toolcall.h

@@ -0,0 +1,45 @@
+#pragma once
+
+#include "chat.h"
+
+#include <nlohmann/json.hpp>
+
+#include <optional>
+#include <string>
+#include <vector>
+
+
+// Sample config:
+// MiniMax-M2 (left): <minimax:tool_call>\n<invoke name="tool-name">\n<parameter name="key">value</parameter>\n...</invoke>\n...</minimax:tool_call>
+// GLM 4.5   (right): <tool_call>function_name\n<arg_key>key</arg_key>\n<arg_value>value</arg_value>\n</tool_call>
+struct xml_tool_call_format {
+    std::string scope_start; // <minimax:tool_call>\n  // \n                      // can be empty
+    std::string tool_start;  // <invoke name=\"        // <tool_call>
+    std::string tool_sep;    // \">\n                  // \n                      // can be empty only for parse_xml_tool_calls
+    std::string key_start;   // <parameter name=\"     // <arg_key>
+    std::string key_val_sep; // \">                    // </arg_key>\n<arg_value>
+    std::string val_end;     // </parameter>\n         // </arg_value>\n
+    std::string tool_end;    // </invoke>\n            // </tool_call>\n
+    std::string scope_end;   // </minimax:tool_call>   //                         // can be empty
+    // Set this if there can be dynamic spaces inside key_val_sep.
+    // e.g. key_val_sep=</arg_key> key_val_sep2=<arg_value> for GLM4.5
+    std::optional<std::string> key_val_sep2 = std::nullopt;
+    // Set true if argval should only be raw string. e.g. Hello "world" hi
+    // Set false if argval should only be json string. e.g. "Hello \"world\" hi"
+    // Defaults to std::nullopt, both will be allowed.
+    std::optional<bool> raw_argval = std::nullopt;
+    std::optional<std::string> last_val_end = std::nullopt;
+    std::optional<std::string> last_tool_end = std::nullopt;
+    bool trim_raw_argval = false;
+    bool allow_toolcall_in_think = false; // TODO: UNTESTED!!!
+};
+
+// make a GBNF that accept any strings except those containing any of the forbidden strings.
+std::string make_gbnf_excluding(std::vector<std::string> forbids);
+
+/**
+ * Build grammar for xml-style tool call
+ * form.scope_start and form.scope_end can be empty.
+ * Requires data.format for model-specific hacks.
+ */
+void build_grammar_xml_tool_call(common_chat_params & data, const nlohmann::ordered_json & tools, const struct xml_tool_call_format & form);

common/chat-parser.h

@@ -1,6 +1,7 @@
 #pragma once
 
 #include "chat.h"
+#include "chat-parser-xml-toolcall.h"
 #include "json-partial.h"
 #include "regex-partial.h"
 
@@ -119,5 +120,14 @@ class common_chat_msg_parser {
         const std::vector<std::vector<std::string>> & content_paths = {}
     );
 
+    /**
+     * Parse XML-Style tool call for given xml_tool_call_format. Return false for invalid syntax and get the position untouched.
+     * form.scope_start, form.tool_sep and form.scope_end can be empty.
+     */
+    bool try_consume_xml_tool_calls(const struct xml_tool_call_format & form);
+
+    // Parse content uses reasoning and XML-Style tool call
+    void consume_reasoning_with_xml_tool_calls(const struct xml_tool_call_format & form, const std::string & start_think = "<think>", const std::string & end_think = "</think>");
+
     void clear_tools();
 };

common/chat.cpp

@@ -643,6 +643,12 @@ const char * common_chat_format_name(common_chat_format format) {
         case COMMON_CHAT_FORMAT_NEMOTRON_V2: return "Nemotron V2";
         case COMMON_CHAT_FORMAT_APERTUS: return "Apertus";
         case COMMON_CHAT_FORMAT_LFM2_WITH_JSON_TOOLS: return "LFM2 with JSON tools";
+        case COMMON_CHAT_FORMAT_MINIMAX_M2: return "MiniMax-M2";
+        case COMMON_CHAT_FORMAT_GLM_4_5: return "GLM 4.5";
+        case COMMON_CHAT_FORMAT_KIMI_K2: return "Kimi K2";
+        case COMMON_CHAT_FORMAT_QWEN3_CODER_XML: return "Qwen3 Coder";
+        case COMMON_CHAT_FORMAT_APRIEL_1_5: return "Apriel 1.5";
+        case COMMON_CHAT_FORMAT_XIAOMI_MIMO: return "Xiaomi MiMo";
         default:
             throw std::runtime_error("Unknown chat format");
     }
@@ -1807,6 +1813,278 @@ static void common_chat_parse_deepseek_v3_1(common_chat_msg_parser & builder) {
     }
 }
 
+
+static common_chat_params common_chat_params_init_minimax_m2(const common_chat_template & tmpl, const struct templates_params & params) {
+    common_chat_params data;
+    data.grammar_lazy = params.tools.is_array() && !params.tools.empty() && params.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+    data.prompt = apply(tmpl, params);
+    data.format = COMMON_CHAT_FORMAT_MINIMAX_M2;
+
+    // Handle thinking tags based on prompt ending
+    if (string_ends_with(data.prompt, "<think>\n")) {
+        if (!params.enable_thinking) {
+            // Close the thinking tag immediately if thinking is disabled
+            data.prompt += "</think>\n\n";
+        } else {
+            // Mark thinking as forced open (template started with <think>)
+            data.thinking_forced_open = true;
+        }
+    }
+
+    // Preserve MiniMax-M2 special tokens
+    data.preserved_tokens = {
+        "<think>",
+        "</think>",
+        "<minimax:tool_call>",
+        "</minimax:tool_call>",
+    };
+
+    // build grammar for tool call
+    static const xml_tool_call_format form {
+        /* form.scope_start = */ "<minimax:tool_call>\n",
+        /* form.tool_start  = */ "<invoke name=\"",
+        /* form.tool_sep    = */ "\">\n",
+        /* form.key_start   = */ "<parameter name=\"",
+        /* form.key_val_sep = */ "\">",
+        /* form.val_end     = */ "</parameter>\n",
+        /* form.tool_end    = */ "</invoke>\n",
+        /* form.scope_end   = */ "</minimax:tool_call>",
+    };
+    build_grammar_xml_tool_call(data, params.tools, form);
+
+    return data;
+}
+
+static void common_chat_parse_minimax_m2(common_chat_msg_parser & builder) {
+    static const xml_tool_call_format form {
+        /* form.scope_start = */ "<minimax:tool_call>",
+        /* form.tool_start  = */ "<invoke name=\"",
+        /* form.tool_sep    = */ "\">",
+        /* form.key_start   = */ "<parameter name=\"",
+        /* form.key_val_sep = */ "\">",
+        /* form.val_end     = */ "</parameter>",
+        /* form.tool_end    = */ "</invoke>",
+        /* form.scope_end   = */ "</minimax:tool_call>",
+    };
+    builder.consume_reasoning_with_xml_tool_calls(form, "<think>", "</think>");
+}
+
+static common_chat_params common_chat_params_init_qwen3_coder_xml(const common_chat_template & tmpl, const struct templates_params & params) {
+    common_chat_params data;
+    data.grammar_lazy = params.tools.is_array() && !params.tools.empty() && params.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+    data.prompt = apply(tmpl, params);
+    data.format = COMMON_CHAT_FORMAT_QWEN3_CODER_XML;
+
+    data.preserved_tokens = {
+        "<tool_call>",
+        "</tool_call>",
+        "<function=",
+        "</function>",
+        "<parameter=",
+        "</parameter>",
+    };
+
+    // build grammar for tool call
+    static const xml_tool_call_format form {
+        /* form.scope_start = */ "<tool_call>\n",
+        /* form.tool_start  = */ "<function=",
+        /* form.tool_sep    = */ ">\n",
+        /* form.key_start   = */ "<parameter=",
+        /* form.key_val_sep = */ ">\n",
+        /* form.val_end     = */ "\n</parameter>\n",
+        /* form.tool_end    = */ "</function>\n",
+        /* form.scope_end   = */ "</tool_call>",
+    };
+    build_grammar_xml_tool_call(data, params.tools, form);
+
+    return data;
+}
+
+static void common_chat_parse_qwen3_coder_xml(common_chat_msg_parser & builder) {
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "<tool_call>";
+        form.tool_start  = "<function=";
+        form.tool_sep    = ">";
+        form.key_start   = "<parameter=";
+        form.key_val_sep = ">";
+        form.val_end     = "</parameter>";
+        form.tool_end    = "</function>";
+        form.scope_end   = "</tool_call>";
+        form.trim_raw_argval = true;
+        return form;
+    })();
+    builder.consume_reasoning_with_xml_tool_calls(form);
+}
+
+static common_chat_params common_chat_params_init_kimi_k2(const common_chat_template & tmpl, const struct templates_params & params) {
+    common_chat_params data;
+    data.grammar_lazy = params.tools.is_array() && !params.tools.empty() && params.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+    data.prompt = apply(tmpl, params);
+    data.format = COMMON_CHAT_FORMAT_KIMI_K2;
+
+    data.preserved_tokens = {
+        "<think>",
+        "</think>",
+        "<|tool_calls_section_begin|>",
+        "<|tool_call_begin|>",
+        "<|tool_call_argument_begin|>",
+        "<|tool_call_end|>",
+        "<|tool_calls_section_end|>",
+        "<|im_end|>",
+        "<|im_system|>",
+        "<|im_middle|>",
+    };
+
+    data.additional_stops.insert(data.additional_stops.end(), {
+        "<|im_end|>",
+        "<|im_middle|>"
+    });
+    // build grammar for tool call
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "<|tool_calls_section_begin|>";
+        form.tool_start  = "<|tool_call_begin|>";
+        form.tool_sep    = "<|tool_call_argument_begin|>{";
+        form.key_start   = "\"";
+        form.key_val_sep = "\": ";
+        form.val_end     = ", ";
+        form.tool_end    = "}<|tool_call_end|>";
+        form.scope_end   = "<|tool_calls_section_end|>";
+        form.raw_argval  = false;
+        form.last_val_end = "";
+        return form;
+    })();
+    build_grammar_xml_tool_call(data, params.tools, form);
+
+    return data;
+}
+
+static void common_chat_parse_kimi_k2(common_chat_msg_parser & builder) {
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "<|tool_calls_section_begin|>";
+        form.tool_start  = "<|tool_call_begin|>";
+        form.tool_sep    = "<|tool_call_argument_begin|>{";
+        form.key_start   = "\"";
+        form.key_val_sep = "\": ";
+        form.val_end     = ", ";
+        form.tool_end    = "}<|tool_call_end|>";
+        form.scope_end   = "<|tool_calls_section_end|>";
+        form.raw_argval  = false;
+        form.last_val_end = "";
+        return form;
+    })();
+    builder.consume_reasoning_with_xml_tool_calls(form, "<think>", "</think>");
+}
+
+static common_chat_params common_chat_params_init_apriel_1_5(const common_chat_template & tmpl, const struct templates_params & params) {
+    common_chat_params data;
+    data.grammar_lazy = params.tools.is_array() && !params.tools.empty() && params.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+    data.prompt = apply(tmpl, params);
+    data.format = COMMON_CHAT_FORMAT_APRIEL_1_5;
+
+    data.preserved_tokens = {
+        "<thinking>",
+        "</thinking>",
+        "<tool_calls>",
+        "</tool_calls>",
+    };
+
+    // build grammar for tool call
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "<tool_calls>[";
+        form.tool_start  = "{\"name\": \"";
+        form.tool_sep    = "\", \"arguments\": {";
+        form.key_start   = "\"";
+        form.key_val_sep = "\": ";
+        form.val_end     = ", ";
+        form.tool_end    = "}, ";
+        form.scope_end   = "]</tool_calls>";
+        form.raw_argval  = false;
+        form.last_val_end = "";
+        form.last_tool_end = "}";
+        return form;
+    })();
+    build_grammar_xml_tool_call(data, params.tools, form);
+
+    return data;
+}
+
+static void common_chat_parse_apriel_1_5(common_chat_msg_parser & builder) {
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "<tool_calls>[";
+        form.tool_start  = "{\"name\": \"";
+        form.tool_sep    = "\", \"arguments\": {";
+        form.key_start   = "\"";
+        form.key_val_sep = "\": ";
+        form.val_end     = ", ";
+        form.tool_end    = "}, ";
+        form.scope_end   = "]</tool_calls>";
+        form.raw_argval  = false;
+        form.last_val_end = "";
+        form.last_tool_end = "}";
+        return form;
+    })();
+    builder.consume_reasoning_with_xml_tool_calls(form, "<thinking>", "</thinking>");
+}
+
+static common_chat_params common_chat_params_init_xiaomi_mimo(const common_chat_template & tmpl, const struct templates_params & params) {
+    common_chat_params data;
+    data.grammar_lazy = params.tools.is_array() && !params.tools.empty() && params.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+    data.prompt = apply(tmpl, params);
+    data.format = COMMON_CHAT_FORMAT_XIAOMI_MIMO;
+
+    data.preserved_tokens = {
+        "<tool_call>",
+        "</tool_call>",
+    };
+
+    // build grammar for tool call
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "\n";
+        form.tool_start  = "<tool_call>\n{\"name\": \"";
+        form.tool_sep    = "\", \"arguments\": {";
+        form.key_start   = "\"";
+        form.key_val_sep = "\": ";
+        form.val_end     = ", ";
+        form.tool_end    = "}\n</tool_call>";
+        form.scope_end   = "";
+        form.raw_argval  = false;
+        form.last_val_end = "";
+        return form;
+    })();
+    build_grammar_xml_tool_call(data, params.tools, form);
+
+    return data;
+}
+
+static void common_chat_parse_xiaomi_mimo(common_chat_msg_parser & builder) {
+    static const xml_tool_call_format form = ([]() {
+        xml_tool_call_format form {};
+        form.scope_start = "";
+        form.tool_start  = "<tool_call>\n{\"name\": \"";
+        form.tool_sep    = "\", \"arguments\": {";
+        form.key_start   = "\"";
+        form.key_val_sep = "\": ";
+        form.val_end     = ", ";
+        form.tool_end    = "}\n</tool_call>";
+        form.scope_end   = "";
+        form.raw_argval  = false;
+        form.last_val_end = "";
+        return form;
+    })();
+    builder.consume_reasoning_with_xml_tool_calls(form);
+}
+
 static common_chat_params common_chat_params_init_gpt_oss(const common_chat_template & tmpl, const struct templates_params & inputs) {
     common_chat_params data;
 
@@ -2041,6 +2319,100 @@ static void common_chat_parse_gpt_oss(common_chat_msg_parser & builder) {
     }
 }
 
+static common_chat_params common_chat_params_init_glm_4_5(const common_chat_template & tmpl, const struct templates_params & inputs) {
+    common_chat_params data;
+    data.grammar_lazy = inputs.tools.is_array() && !inputs.tools.empty() && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+
+    std::string prompt = apply(tmpl, inputs);
+
+    // match the existing trimming behavior
+    if (inputs.add_bos && string_starts_with(prompt, tmpl.bos_token())) {
+        prompt.erase(0, tmpl.bos_token().size());
+    }
+    if (inputs.add_eos && string_ends_with(prompt, tmpl.eos_token())) {
+        prompt.erase(prompt.size() - tmpl.eos_token().size());
+    }
+    if (string_ends_with(prompt, "<think>")) {
+        if (!inputs.enable_thinking) {
+            prompt += "</think>";
+        } else {
+            data.thinking_forced_open = true;
+        }
+    }
+
+    // add GLM preserved tokens
+    data.preserved_tokens = {
+        "<|endoftext|>",
+        "[MASK]",
+        "[gMASK]",
+        "[sMASK]",
+        "<sop>",
+        "<eop>",
+        "<|system|>",
+        "<|user|>",
+        "<|assistant|>",
+        "<|observation|>",
+        "<|begin_of_image|>",
+        "<|end_of_image|>",
+        "<|begin_of_video|>",
+        "<|end_of_video|>",
+        "<|begin_of_audio|>",
+        "<|end_of_audio|>",
+        "<|begin_of_transcription|>",
+        "<|end_of_transcription|>",
+        "<|code_prefix|>",
+        "<|code_middle|>",
+        "<|code_suffix|>",
+        "/nothink",
+        "<think>",
+        "</think>",
+        "<tool_call>",
+        "</tool_call>",
+        "<arg_key>",
+        "</arg_key>",
+        "<arg_value>",
+        "</arg_value>"
+    };
+
+    // extra GLM 4.5 stop word
+    data.additional_stops.insert(data.additional_stops.end(), {
+        "<|user|>",
+        "<|observation|>"
+    });
+
+    // build grammar for tool call
+    static const xml_tool_call_format form {
+        /* form.scope_start = */ "",
+        /* form.tool_start  = */ "\n<tool_call>",
+        /* form.tool_sep    = */ "\n",
+        /* form.key_start   = */ "<arg_key>",
+        /* form.key_val_sep = */ "</arg_key>\n<arg_value>",
+        /* form.val_end     = */ "</arg_value>\n",
+        /* form.tool_end    = */ "</tool_call>\n",
+        /* form.scope_end   = */ "",
+    };
+    build_grammar_xml_tool_call(data, inputs.tools, form);
+
+    data.prompt = prompt;
+    data.format = COMMON_CHAT_FORMAT_GLM_4_5;
+    return data;
+}
+
+static void common_chat_parse_glm_4_5(common_chat_msg_parser & builder) {
+    static const xml_tool_call_format form {
+        /* form.scope_start  = */ "",
+        /* form.tool_start   = */ "<tool_call>",
+        /* form.tool_sep     = */ "",
+        /* form.key_start    = */ "<arg_key>",
+        /* form.key_val_sep  = */ "</arg_key>",
+        /* form.val_end      = */ "</arg_value>",
+        /* form.tool_end     = */ "</tool_call>",
+        /* form.scope_end    = */ "",
+        /* form.key_val_sep2 = */ "<arg_value>",
+    };
+    builder.consume_reasoning_with_xml_tool_calls(form, "<think>", "</think>");
+}
+
 static common_chat_params common_chat_params_init_firefunction_v2(const common_chat_template & tmpl, const struct templates_params & inputs) {
     LOG_DBG("%s\n", __func__);
     common_chat_params data;
@@ -2704,91 +3076,17 @@ static void common_chat_parse_lfm2(common_chat_msg_parser & builder) {
 }
 
 static void common_chat_parse_seed_oss(common_chat_msg_parser & builder) {
-    // Parse thinking tags first - this handles the main reasoning content
-    builder.try_parse_reasoning("<seed:think>", "</seed:think>");
-
-    if (!builder.syntax().parse_tool_calls) {
-        builder.add_content(builder.consume_rest());
-        return;
-    }
-
-    // Parse tool calls - Seed-OSS uses <seed:tool_call> format
-    static const common_regex tool_call_begin_regex("<seed:tool_call>");
-    static const common_regex tool_call_end_regex("</seed:tool_call>");
-    static const common_regex function_regex("<function=([^>]+)>");
-    static const common_regex param_regex("<parameter=([^>]+)>");
-
-    while (auto tool_res = builder.try_find_regex(tool_call_begin_regex)) {
-        builder.consume_spaces();  // Consume whitespace after <seed:tool_call>
-
-        // Look for function call inside tool call, ignore any content before it
-        if (auto func_res = builder.try_find_regex(function_regex, std::string::npos, false)) {
-            auto function_name = builder.str(func_res->groups[1]);
-
-            // Parse Seed-OSS parameters <parameter=name>value</parameter>
-            json args = json::object();
-            // Parse all parameters
-            while (auto param_res = builder.try_find_regex(param_regex, std::string::npos, false)) {
-                // again, ignore noise around parameters
-                auto param_name = builder.str(param_res->groups[1]);
-                builder.move_to(param_res->groups[0].end);
-                builder.consume_spaces();  // Consume whitespace after parameter
-                auto savedPos = builder.pos();
-                if (auto param_parse = builder.try_find_literal("</parameter>")) {
-                    auto param = param_parse->prelude;
-                    builder.move_to(savedPos);
-                    try {
-                        if (auto param_res = builder.try_consume_json()) {
-                            args[param_name] = param_res->json;
-                        } else {
-                            args[param_name] = param;
-                        }
-                    } catch (json::exception &) {
-                        args[param_name] = param;
-                    }
-                } else {
-                    throw common_chat_msg_partial_exception("Incomplete tool parameter");
-                }
-            }
-            // Look for closing function tag
-            auto end_func = builder.try_find_literal("</function>");
-            if (end_func) {
-                builder.move_to(end_func->groups[0].end);
-                builder.consume_spaces();  // Consume whitespace after </function>
-
-                // Add the tool call with parsed arguments, but only if we REALLY got the literal
-                auto eaten_fragment = builder.input().substr(end_func->groups[0].begin, end_func->groups[0].end);
-                auto funlen = std::string("</function>").length();
-                if (eaten_fragment.length() >= funlen && eaten_fragment.substr(0, funlen) == std::string("</function>")) {
-                    if (!builder.add_tool_call(function_name, "", args.dump())) {
-                        throw common_chat_msg_partial_exception("Incomplete tool call");
-                    }
-                } else {
-                    throw common_chat_msg_partial_exception("Incomplete tool call");
-                }
-            } else {
-                throw common_chat_msg_partial_exception("Incomplete tool call");
-            }
-            // Look for closing tool call tag
-            if (auto end_tool = builder.try_find_regex(tool_call_end_regex, std::string::npos, false)) {
-                builder.move_to(end_tool->groups[0].end);
-                builder.consume_spaces();  // Consume trailing whitespace after tool call
-            } else {
-                throw common_chat_msg_partial_exception("Incomplete tool call");
-            }
-        } else {
-            // No function found - don't consume content here, let it be handled at the end
-            break;
-        }
-    }
-
-    // Consume any remaining whitespace after all tool call processing
-    builder.consume_spaces();
-    auto remaining = builder.consume_rest();
-    // If there's any non-whitespace content remaining, add it as content
-    if (!string_strip(remaining).empty()) {
-        builder.add_content(remaining);
-    }
+    static const xml_tool_call_format form {
+        /* form.scope_start = */ "<seed:tool_call>",
+        /* form.tool_start  = */ "<function=",
+        /* form.tool_sep    = */ ">",
+        /* form.key_start   = */ "<parameter=",
+        /* form.key_val_sep = */ ">",
+        /* form.val_end     = */ "</parameter>",
+        /* form.tool_end    = */ "</function>",
+        /* form.scope_end   = */ "</seed:tool_call>",
+    };
+    builder.consume_reasoning_with_xml_tool_calls(form, "<seed:think>", "</seed:think>");
 }
 
 static common_chat_params common_chat_params_init_without_tools(const common_chat_template & tmpl, const struct templates_params & inputs) {
@@ -2927,6 +3225,35 @@ static common_chat_params common_chat_templates_apply_jinja(
         return common_chat_params_init_granite(tmpl, params);
     }
 
+    // GLM 4.5: detect by <arg_key> and <arg_value> tags (check before Hermes since both use <tool_call>)
+    if (src.find("[gMASK]<sop>") != std::string::npos &&
+        src.find("<arg_key>") != std::string::npos &&
+        src.find("<arg_value>") != std::string::npos &&
+        params.json_schema.is_null()) {
+        return common_chat_params_init_glm_4_5(tmpl, params);
+    }
+
+    // Qwen3-Coder XML format detection (must come before Hermes 2 Pro)
+    // Detect via explicit XML markers unique to Qwen3-Coder to avoid false positives in other templates.
+    // Require presence of <tool_call>, <function=...>, and <parameter=...> blocks.
+    if (src.find("<tool_call>") != std::string::npos &&
+        src.find("<function>") != std::string::npos &&
+        src.find("<function=") != std::string::npos &&
+        src.find("<parameters>") != std::string::npos &&
+        src.find("<parameter=") != std::string::npos) {
+        return common_chat_params_init_qwen3_coder_xml(tmpl, params);
+    }
+
+    // Xiaomi MiMo format detection (must come before Hermes 2 Pro)
+    if (src.find("<tools>") != std::string::npos &&
+        src.find("# Tools") != std::string::npos &&
+        src.find("</tools>") != std::string::npos &&
+        src.find("<tool_calls>") != std::string::npos &&
+        src.find("</tool_calls>") != std::string::npos &&
+        src.find("<tool_response>") != std::string::npos) {
+        return common_chat_params_init_xiaomi_mimo(tmpl, params);
+    }
+
     // Hermes 2/3 Pro, Qwen 2.5 Instruct (w/ tools)
     if (src.find("<tool_call>") != std::string::npos && params.json_schema.is_null()) {
         return common_chat_params_init_hermes_2_pro(tmpl, params);
@@ -2958,6 +3285,29 @@ static common_chat_params common_chat_templates_apply_jinja(
         return common_chat_params_init_lfm2(tmpl, params);
     }
 
+    // MiniMax-M2 format detection
+    if (src.find("]~!b[") != std::string::npos && src.find("]~b]") != std::string::npos) {
+        return common_chat_params_init_minimax_m2(tmpl, params);
+    }
+
+    // Kimi K2 format detection
+    if (src.find("<|im_system|>tool_declare<|im_middle|>") != std::string::npos &&
+        src.find("<|tool_calls_section_begin|>") != std::string::npos &&
+        src.find("## Return of") != std::string::npos) {
+        return common_chat_params_init_kimi_k2(tmpl, params);
+    }
+
+    // Apriel 1.5 format detection
+    if (src.find("<thinking>") != std::string::npos &&
+        src.find("</thinking>") != std::string::npos &&
+        src.find("<available_tools>") != std::string::npos &&
+        src.find("<|assistant|>") != std::string::npos &&
+        src.find("<|tool_result|>") != std::string::npos &&
+        src.find("<tool_calls>[") != std::string::npos &&
+        src.find("]</tool_calls>") != std::string::npos) {
+        return common_chat_params_init_apriel_1_5(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())) {
@@ -3139,6 +3489,24 @@ static void common_chat_parse(common_chat_msg_parser & builder) {
         case COMMON_CHAT_FORMAT_LFM2_WITH_JSON_TOOLS:
             common_chat_parse_lfm2(builder);
             break;
+        case COMMON_CHAT_FORMAT_MINIMAX_M2:
+            common_chat_parse_minimax_m2(builder);
+            break;
+        case COMMON_CHAT_FORMAT_GLM_4_5:
+            common_chat_parse_glm_4_5(builder);
+            break;
+        case COMMON_CHAT_FORMAT_KIMI_K2:
+            common_chat_parse_kimi_k2(builder);
+            break;
+        case COMMON_CHAT_FORMAT_QWEN3_CODER_XML:
+            common_chat_parse_qwen3_coder_xml(builder);
+            break;
+        case COMMON_CHAT_FORMAT_APRIEL_1_5:
+            common_chat_parse_apriel_1_5(builder);
+            break;
+        case COMMON_CHAT_FORMAT_XIAOMI_MIMO:
+            common_chat_parse_xiaomi_mimo(builder);
+            break;
         default:
             throw std::runtime_error(std::string("Unsupported format: ") + common_chat_format_name(builder.syntax().format));
     }

common/chat.h

@@ -117,6 +117,12 @@ enum common_chat_format {
     COMMON_CHAT_FORMAT_NEMOTRON_V2,
     COMMON_CHAT_FORMAT_APERTUS,
     COMMON_CHAT_FORMAT_LFM2_WITH_JSON_TOOLS,
+    COMMON_CHAT_FORMAT_GLM_4_5,
+    COMMON_CHAT_FORMAT_MINIMAX_M2,
+    COMMON_CHAT_FORMAT_KIMI_K2,
+    COMMON_CHAT_FORMAT_QWEN3_CODER_XML,
+    COMMON_CHAT_FORMAT_APRIEL_1_5,
+    COMMON_CHAT_FORMAT_XIAOMI_MIMO,
 
     COMMON_CHAT_FORMAT_COUNT, // Not a format, just the # formats
 };

common/json-partial.cpp

@@ -297,8 +297,25 @@ bool common_json_parse(
             it = temptative_end;
             return true;
         }
-        // TODO: handle unclosed top-level primitive if the stack was empty but we got an error (e.g. "tru", "\"", etc...)
-        // fprintf(stderr, "Closing: TODO\n");
+        // handle unclosed top-level primitive
+        if (err_loc.position != 0 && !healing_marker.empty() && err_loc.stack.empty()) {
+            std::string str(it, temptative_end);
+            const auto & magic_seed = out.healing_marker.marker = healing_marker;
+            if (can_parse(str + "\"")) {
+                // Was inside an string
+                str += (out.healing_marker.json_dump_marker = magic_seed) + "\"";
+            } else if (str[str.length() - 1] == '\\' && can_parse(str + "\\\"")) {
+                // Was inside an string after an escape
+                str += (out.healing_marker.json_dump_marker = "\\" + magic_seed) + "\"";
+            } else {
+                // TODO: handle more unclosed top-level primitive if the stack was empty but we got an error (e.g. "tru", "\"", etc...)
+                // fprintf(stderr, "Closing: TODO\n");
+                return false;
+            }
+            out.json = json::parse(str);
+            it = temptative_end;
+            return true;
+        }
         return false;
     }
     out.json = json::parse(it, end);

common/json-schema-to-grammar.cpp

@@ -303,6 +303,8 @@ static std::string format_literal(const std::string & literal) {
     return "\"" + escaped + "\"";
 }
 
+std::string gbnf_format_literal(const std::string & literal) { return format_literal(literal); }
+
 class SchemaConverter {
 private:
     friend std::string build_grammar(const std::function<void(const common_grammar_builder &)> & cb, const common_grammar_options & options);

common/json-schema-to-grammar.h

@@ -18,4 +18,6 @@ struct common_grammar_options {
     bool dotall = false;
 };
 
+std::string gbnf_format_literal(const std::string & literal);
+
 std::string build_grammar(const std::function<void(const common_grammar_builder &)> & cb, const common_grammar_options & options = {});

models/templates/GLM-4.6.jinja

@@ -0,0 +1,106 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{{ visible_text(m.content) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments or {} %}
+{% if _args is not mapping %}
+    {{ raise_exception("Invalid tool call arguments passed: " + _args | string) }}
+{% endif %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

models/templates/Kimi-K2-Instruct.jinja

@@ -0,0 +1,64 @@
+{% macro render_content(msg) -%}
+    {%- set c = msg.get('content') -%}
+    {%- if c is string -%}
+      {{ c }}
+    {%- elif c is not none -%}
+      {% for content in c -%}
+        {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
+          <|media_start|>image<|media_content|><|media_pad|><|media_end|>
+        {% else -%}
+          {{ content['text'] }}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+{%- endmacro %}
+
+{%- set tool_response_queue = namespace(ids=[]) -%}
+{%- set tool_call_counter = namespace(value=1) -%}
+
+{%- if tools -%}
+  <|im_system|>tool_declare<|im_middle|>{{ tools | tojson }}<|im_end|>
+{%- endif -%}
+{% for message in messages %}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
+  {% endif %}
+
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {%- endif -%}
+
+  {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}
+    {{render_content(message)}}<|tool_calls_section_begin|>
+    {%- for tool_call in message['tool_calls'] -%}
+      {%- if tool_call['id'] is defined -%}
+        {%- set formatted_id = tool_call['id'] -%}
+      {%- else -%}
+        {%- set formatted_id = 'functions.' + tool_call['function']['name'] + ':' + (tool_call_counter.value | string) -%}
+        {%- set tool_call_counter.value = tool_call_counter.value + 1 -%}
+      {%- endif -%}
+      {%- set _ = tool_response_queue.ids.append(formatted_id) -%}
+      <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+    {%- endfor -%}
+    <|tool_calls_section_end|>
+  {%- elif message['role'] == 'tool' -%}
+    {%- if tool_response_queue.ids -%}
+      {%- set tool_call_id = tool_response_queue.ids.pop(0) -%}
+    {%- else -%}
+      {%- set tool_call_id = 'functions.' + message.get('name', 'unknown') + ':' + (tool_call_counter.value | string) -%}
+    {%- endif -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+{%- endif -%}

models/templates/Kimi-K2-Thinking.jinja

@@ -0,0 +1,112 @@
+{%- macro render_content(msg) -%}
+    {%- set c = msg.get('content') -%}
+    {%- if c is string -%}
+      {{ c }}
+    {%- elif c is not none -%}
+      {% for content in c -%}
+        {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
+          <|media_start|>image<|media_content|><|media_pad|><|media_end|>
+        {% else -%}
+          {{ content['text'] }}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+{%- endmacro -%}
+
+{% macro set_roles(message) -%}
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {%- endif -%}
+{%- endmacro -%}
+
+{%- set tool_response_queue = namespace(ids=[]) -%}
+{%- set tool_call_counter = namespace(value=1) -%}
+
+{%- macro render_toolcalls(message) -%}
+  <|tool_calls_section_begin|>
+  {%- for tool_call in message['tool_calls'] -%}
+    {%- if tool_call['id'] is defined -%}
+      {%- set formatted_id = tool_call['id'] -%}
+    {%- else -%}
+      {%- set formatted_id = 'functions.' + tool_call['function']['name'] + ':' + (tool_call_counter.value | string) -%}
+      {%- set tool_call_counter.value = tool_call_counter.value + 1 -%}
+    {%- endif -%}
+    {%- set _ = tool_response_queue.ids.append(formatted_id) -%}
+    <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+  {%- endfor -%}
+  <|tool_calls_section_end|>
+{%- endmacro -%}
+
+
+{# Find last non-tool-call assisitant message #}
+{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
+{%- for idx in range(messages|length-1, -1, -1) -%}
+    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
+        {%- set ns.last_non_tool_call_assistant_msg = idx -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
+{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
+{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
+
+{%- if tools -%}
+  <|im_system|>tool_declare<|im_middle|>{{ tools | tojson }}<|im_end|>
+{%- endif -%}
+
+{%- if messages|length == 0 or messages[0]['role'] != 'system' -%}
+  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
+{%- endif -%}
+
+{%- for message in hist_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    <think></think>{{render_content(message)}}
+    {%- if message.get('tool_calls') -%}
+      {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- if tool_response_queue.ids -%}
+      {%- set tool_call_id = tool_response_queue.ids.pop(0) -%}
+    {%- else -%}
+      {%- set tool_call_id = 'functions.' + message.get('name', 'unknown') + ':' + (tool_call_counter.value | string) -%}
+    {%- endif -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+{%- for message in suffix_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    {%- set rc = message.get('reasoning_content', '') -%}
+    <think>{{rc}}</think>{{render_content(message)}}
+    {%- if message.get('tool_calls') -%}
+     {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- if tool_response_queue.ids -%}
+      {%- set tool_call_id = tool_response_queue.ids.pop(0) -%}
+    {%- else -%}
+      {%- set tool_call_id = 'functions.' + message.get('name', 'unknown') + ':' + (tool_call_counter.value | string) -%}
+    {%- endif -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+{%- endif -%}

models/templates/MiMo-VL.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are MiMo, an AI assistant developed by Xiaomi.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are MiMo, an AI assistant developed by Xiaomi.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

models/templates/MiniMax-M2.jinja

@@ -0,0 +1,159 @@
+{# ----------‑‑‑ special token variables ‑‑‑---------- #}
+{%- set toolcall_begin_token   = '<minimax:tool_call>'         -%}
+{%- set toolcall_end_token     = '</minimax:tool_call>'        -%}
+{#- Tool Rendering Functions ============================================== -#}
+{%- macro render_tool_namespace(namespace_name, tool_list) -%}
+{%- for tool in tool_list -%}
+<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
+{% endfor -%}
+{%- endmacro -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{ content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{#- System Message Construction ============================================ -#}
+{%- macro build_system_message(system_message) -%}
+    {%- if system_message and system_message.content -%}
+        {{- visible_text(system_message.content) }}
+    {%- else -%}
+        {%- if model_identity is not defined -%}
+            {%- set model_identity = "You are a helpful assistant." -%}
+        {%- endif -%}
+        {{- model_identity }}
+    {%- endif -%}
+    
+    {#- Handle current_date -#}
+    {%- if system_message and system_message.current_date -%}
+        {{- '\n' ~ 'Current date: ' + system_message.current_date }}
+    {%- endif -%}
+    {#- Handle current_location -#}
+    {%- if system_message and system_message.current_location -%}
+        {{- '\n' ~ 'Current location: ' + system_message.current_location }}
+    {%- endif -%}
+{%- endmacro -%}
+{#- Main Template Logic ================================================= -#}
+{#- Extract system message (only first message if it's system) -#}
+{%- set system_message = none -%}
+{%- set conversation_messages = messages -%}
+{%- if messages and messages[0].role == "system" -%}
+    {%- set system_message = messages[0] -%}
+    {%- set conversation_messages = messages[1:] -%}
+{%- endif -%}
+{#- Get the last user message turn, for interleved thinking -#}
+{%- set ns = namespace(last_user_index=-1) %}
+{% for m in conversation_messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{#- Render system message -#}
+{{- ']~!b[' ~ ']~b]system' ~ '\n' }}
+{{- build_system_message(system_message) }}
+{#- Render tools if available -#}
+{%- if tools -%}
+    {{- '\n\n' ~ '# Tools' ~ '\n' ~ 'You may call one or more tools to assist with the user query.\nHere are the tools available in JSONSchema format:' ~ '\n' }}
+    {{- '\n' ~ '<tools>' ~ '\n' }}
+    {{- render_tool_namespace("functions", tools) }}
+    {{- '</tools>' ~ '\n\n' }}
+{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\n' }}
+{{- '\n' ~ toolcall_begin_token }}
+<invoke name="tool-name-1">
+<parameter name="param-key-1">param-value-1</parameter>
+<parameter name="param-key-2">param-value-2</parameter>
+...
+</invoke>
+{{- '\n' ~ toolcall_end_token }}
+{%- endif -%}
+{{- '[e~[\n' }}
+
+{#- Render messages -#}
+{%- set last_tool_call = namespace(name=none) -%}
+{%- for message in conversation_messages -%}
+    {%- if message.role == 'assistant' -%}
+        {#- Only render reasoning_content if no user message follows -#}
+        {{- ']~b]ai' ~ '\n' }}
+
+        {%- set reasoning_content = '' %}
+        {%- set content = visible_text(message.content) %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].strip('\n').split('<think>')[-1].strip('\n') %}
+                {%- set content = content.split('</think>')[-1].strip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if reasoning_content and loop.index0 > ns.last_user_index -%}
+            {{- '<think>' ~ '\n' ~ reasoning_content ~ '\n' ~ '</think>' ~ '\n\n' }}
+        {%- endif -%}
+        {%- if content -%}
+            {{- content }}
+        {%- endif -%}
+        {%- if message.tool_calls -%}
+            {{- '\n' ~ toolcall_begin_token ~ '\n' }}
+
+            {%- for tool_call in message.tool_calls -%}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<invoke name="' + tool_call.name + '">' }}
+                {% set _args = tool_call.arguments %}
+                {%- for k, v in _args.items() %}
+                {{- '<parameter name="' + k + '">' }}
+                {{- v | tojson(ensure_ascii=False) if v is not string else v }}
+                {{- '</parameter>' }}
+                {% endfor %}
+                {{- '</invoke>' ~ '\n' }}
+            {%- endfor -%}
+            
+            {{- toolcall_end_token}}
+            {%- set last_tool_call.name = message.tool_calls[-1].function.name -%}
+        {%- else -%}
+            {%- set last_tool_call.name = none -%}
+        {%- endif -%}
+        {{- '[e~[' ~ '\n' }}
+        
+    {%- elif message.role == 'tool' -%}
+    {%- if last_tool_call.name is none -%}
+        {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+    {%- endif -%}
+    {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}
+        {{- ']~b]tool' }}
+    {%- endif -%}
+    {%- if message.content is string -%}
+        {{- '\n<response>' }}
+        {{- message.content }}
+        {{- '</response>' }}
+    {%- else -%}
+        {%- for tr in message.content -%}
+            {{- '\n<response>' }}
+            {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
+            {{- '\n</response>' }}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}
+        {{- '[e~[\n' -}}
+    {%- endif -%}
+        
+    {%- elif message.role == 'user' -%}
+        {{- ']~b]user' ~ '\n' }}
+        {{- visible_text(message.content) }}
+        {{- '[e~[' ~ '\n' }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt -#}
+{%- if add_generation_prompt -%}
+{{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
+{%- endif -%}

models/templates/Qwen3-Coder.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

models/templates/unsloth-Apriel-1.5.jinja

@@ -0,0 +1,126 @@
+{# Unsloth template fixes #}
+{%- set available_tools_string = '' -%}
+{%- set thought_instructions = '' -%}
+{%- set add_tool_id = true -%}
+{%- set tool_output_format = "default" -%}
+{%- if tools is not none and tools|length > 0 -%}
+    {%- set available_tools_string -%}
+You are provided with function signatures within <available_tools></available_tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about the arguments. You should infer the argument values from previous user responses and the system message. Here are the available tools:
+<available_tools>
+{% for tool in tools %}
+{{ tool|string }}
+{% endfor %}
+</available_tools>
+{%- endset -%}
+{%- endif -%}
+{%- if tool_output_format is none or tool_output_format == "default" -%}
+{%- set tool_output_instructions -%}
+Return all function calls as a list of json objects within <tool_call></tool_call> XML tags. Each json object should contain a function name and arguments as follows:
+<tool_calls>[{"name": <function-name-1>, "arguments": <args-dict-1>}, {"name": <function-name-2>, "arguments": <args-dict-2>},...]</tool_calls>
+{%- endset -%}
+{%- elif tool_output_format == "yaml" -%}
+{%- set tool_output_instructions -%}
+Return all function calls as a list of yaml objects within <tool_call></tool_call> XML tags. Each yaml object should contain a function name and arguments as follows:
+<tool_calls>
+- name: <function-name-1>
+  arguments: <args-dict-1>
+- name: <function-name-2>
+  arguments: <args-dict-2>
+...
+</tool_calls>
+{%- endset -%}
+{%- endif -%}
+{%- if add_thoughts -%}
+{%- set thought_instructions -%}
+Prior to generating the function calls, you should generate the reasoning for why you're calling the function. Please generate these reasoning thoughts between <thinking> and </thinking> XML tags.
+{%- endset -%}
+{%- endif -%}
+{{- bos_token -}}
+{%- set reasoning_prompt='You are a thoughtful and systematic AI assistant built by ServiceNow Language Models (SLAM) lab. Before providing an answer, analyze the problem carefully and present your reasoning step by step. After explaining your thought process, provide the final solution in the following format: [BEGIN FINAL RESPONSE] ... [END FINAL RESPONSE].' -%}
+{%- if messages[0]['role'] != 'system' and tools is not none and tools|length > 0 -%}
+    {{- '<|system|>\n' + reasoning_prompt + available_tools_string + "\n" + tool_output_instructions + '\n<|end|>\n' -}}
+{%- endif -%}
+{%- if messages|selectattr('role', 'equalto', 'system')|list|length == 0 -%}
+{{- '<|system|>\n' + reasoning_prompt + '\n<|end|>\n' -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{- '<|user|>\n' }}
+        {%- if message['content'] is not string %}
+            {%- for chunk in message['content'] %}
+                {%- if chunk['type'] == 'text' %}
+                    {{- chunk['text'] }}
+                {%- elif chunk['type'] == 'image' or chunk['type'] == 'image_url'%}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Unrecognized content type!') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- else %}
+            {{- message['content'] }}
+        {%- endif %}
+        {{- '\n<|end|>\n' }}
+    {%- elif message['role'] == 'content' -%}
+        {%- if message['content'] is not string %}
+            {{- '<|content|>\n' + message['content'][0]['text'] + '\n<|end|>\n' -}}
+        {%- else %}
+            {{- '<|content|>\n' + message['content'] + '\n<|end|>\n' -}}
+        {%- endif -%}
+    {%- elif message['role'] == 'system' -%}
+        {%- if message['content'] is not none and message['content']|length > 0 %}
+            {%- if message['content'] is string %}
+                {%- set system_message = message['content'] %}
+            {%- else %}
+                {%- set system_message = message['content'][0]['text'] %}
+            {%- endif %}
+        {%- else %}
+            {%- set system_message = '' %}
+        {%- endif %}
+        {%- if tools is not none and tools|length > 0 -%}
+            {{- '<|system|>\n' + reasoning_prompt + system_message + '\n' + available_tools_string + '\n<|end|>\n' -}}
+        {%- else -%}
+            {{- '<|system|>\n' + reasoning_prompt + system_message + '\n<|end|>\n' -}}
+        {%- endif -%}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- if loop.last -%}
+            {%- set add_tool_id = false -%}
+        {%- endif -%}
+        {{- '<|assistant|>\n' -}}
+        {%- if message['content'] is not none and message['content']|length > 0 -%}
+            {%- if message['content'] is not string and message['content'][0]['text'] is not none %}
+                {{- message['content'][0]['text'] }}
+            {%- else %}
+                {{- message['content'] -}}
+            {%- endif -%}
+        {%- elif message['chosen'] is not none and message['chosen']|length > 0 -%}
+            {{- message['chosen'][0] -}}
+        {%- endif -%}
+        {%- if add_thoughts and 'thought' in message and message['thought'] is not none -%}
+            {{- '<thinking>' + message['thought'] + '</thinking>' -}}
+        {%- endif -%}
+        {%- if message['tool_calls'] is not none and message['tool_calls']|length > 0 -%}
+            {{- '\n<tool_calls>[' -}}
+            {%- for tool_call in message["tool_calls"] -%}
+                {{- '{"name": "' + tool_call['function']['name'] + '", "arguments": ' + tool_call['function']['arguments']|string -}}
+                {%- if add_tool_id == true -%}
+                    {{- ', "id": "' + tool_call['id'] + '"' -}}
+                {%- endif -%}
+                {{- '}' -}}
+                {%- if not loop.last -%}{{- ', ' -}}{%- endif -%}
+            {%- endfor -%}
+            {{- ']</tool_calls>' -}}
+        {%- endif -%}
+        {{- '\n<|end|>\n' + eos_token -}}
+    {%- elif message['role'] == 'tool' -%}
+        {%- if message['content'] is string %}
+            {%- set tool_message = message['content'] %}
+        {%- else %}
+            {%- set tool_message = message['content'][0]['text'] %}
+        {%- endif -%}
+        {{- '<|tool_result|>\n' + tool_message|string + '\n<|end|>\n' -}}
+    {%- endif -%}
+    {%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}
+        {{- '<|assistant|>\n' -}}
+    {%- endif -%}
+{%- endfor -%}
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}

tests/test-chat.cpp

@@ -75,6 +75,8 @@ static common_chat_msg normalize(const common_chat_msg & msg) {
     }
     return normalized;
 }
+
+
 template <>
 bool equals(const common_chat_msg & expected, const common_chat_msg & actual) {
     return normalize(expected) == normalize(actual);
@@ -148,17 +150,29 @@ static std::string renormalize_json(const std::string & json_str) {
         return json_str;
     }
 }
-static void assert_msg_equals(const common_chat_msg & expected, const common_chat_msg & actual) {
+static void assert_msg_equals(const common_chat_msg & expected, const common_chat_msg & actual, bool ignore_whitespace_differences = false) {
     assert_equals(expected.role, actual.role);
-    assert_equals(expected.content, actual.content);
+    if (ignore_whitespace_differences) {
+        assert_equals(string_strip(expected.content), string_strip(actual.content));
+    } else {
+        assert_equals(expected.content, actual.content);
+    }
     assert_equals(expected.content_parts.size(), actual.content_parts.size());
     for (size_t i = 0; i < expected.content_parts.size(); i++) {
         const auto & expected_part = expected.content_parts[i];
         const auto & actual_part   = actual.content_parts[i];
         assert_equals(expected_part.type, actual_part.type);
-        assert_equals(expected_part.text, actual_part.text);
+        if (ignore_whitespace_differences) {
+            assert_equals(string_strip(expected_part.text), string_strip(actual_part.text));
+        } else {
+            assert_equals(expected_part.text, actual_part.text);
+        }
+    }
+    if (ignore_whitespace_differences) {
+        assert_equals(string_strip(expected.reasoning_content), string_strip(actual.reasoning_content));
+    } else {
+        assert_equals(expected.reasoning_content, actual.reasoning_content);
     }
-    assert_equals(expected.reasoning_content, actual.reasoning_content);
     assert_equals(expected.tool_calls.size(), actual.tool_calls.size());
     for (size_t i = 0; i < expected.tool_calls.size(); i++) {
         const auto & expected_tool_call = expected.tool_calls[i];
@@ -183,6 +197,24 @@ common_chat_tool special_function_tool {
         "required": ["arg1"]
     })",
 };
+common_chat_tool special_function_tool_with_optional_param {
+    /* .name = */ "special_function_with_opt",
+    /* .description = */ "I'm special but have optional stuff",
+    /* .parameters = */ R"({
+        "type": "object",
+        "properties": {
+            "arg1": {
+                "type": "integer",
+                "description": "The arg."
+            },
+            "arg2": {
+                "type": "integer",
+                "description": "The optional arg."
+            }
+        },
+        "required": ["arg1"]
+    })",
+};
 common_chat_tool python_tool {
     /* .name = */ "python",
     /* .description = */ "an ipython interpreter",
@@ -211,7 +243,7 @@ common_chat_tool code_interpreter_tool {
         "required": ["code"]
     })",
 };
-std::vector<common_chat_tool> tools           { special_function_tool, python_tool };
+std::vector<common_chat_tool> tools           { special_function_tool, special_function_tool_with_optional_param, python_tool };
 std::vector<common_chat_tool> llama_3_1_tools { special_function_tool, code_interpreter_tool };
 
 struct delta_data {
@@ -219,6 +251,17 @@ struct delta_data {
     common_chat_params params;
 };
 
+static common_chat_msg simple_assist_msg(const std::string & content, const std::string & reasoning_content = "", const std::string & tool_name = "", const std::string & arguments = "", const std::string & id = "") {
+    common_chat_msg msg;
+    msg.role = "assistant";
+    msg.content = content;
+    msg.reasoning_content = reasoning_content;
+    if (!tool_name.empty()) {
+        msg.tool_calls.push_back({ tool_name, arguments, id });
+    }
+    return msg;
+}
+
 static delta_data init_delta(const struct common_chat_templates * tmpls, const std::vector<std::string> & end_tokens,
                              const common_chat_msg & user_message,
                              const common_chat_msg & delta_message,
@@ -280,7 +323,9 @@ static void test_templates(const struct common_chat_templates * tmpls, const std
                           const std::string & expected_delta = "",
                           bool expect_grammar_triggered = true,
                           bool test_grammar_if_triggered = true,
-                          common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_NONE) {
+                          common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_NONE,
+                          bool ignore_whitespace_differences = false
+                        ) {
     common_chat_msg user_message;
     user_message.role = "user";
     user_message.content = "Hello, world!";
@@ -288,7 +333,11 @@ static void test_templates(const struct common_chat_templates * tmpls, const std
     for (const auto & tool_choice : std::vector<common_chat_tool_choice> {COMMON_CHAT_TOOL_CHOICE_AUTO, COMMON_CHAT_TOOL_CHOICE_REQUIRED}) {
         auto data = init_delta(tmpls, end_tokens, user_message, test_message, tools, tool_choice);
         if (!expected_delta.empty()) {
-            assert_equals(expected_delta, data.delta);
+            if (ignore_whitespace_differences) {
+                assert_equals(string_strip(expected_delta), string_strip(data.delta));
+            } else {
+                assert_equals(expected_delta, data.delta);
+            }
         }
 
         if (expect_grammar_triggered) {
@@ -296,7 +345,7 @@ static void test_templates(const struct common_chat_templates * tmpls, const std
             syntax.format = data.params.format;
             syntax.reasoning_format = reasoning_format;
             const auto msg = common_chat_parse(data.delta, /* is_partial= */ false, syntax);
-            assert_msg_equals(test_message, msg);
+            assert_msg_equals(test_message, msg, ignore_whitespace_differences);
         }
 
         if (!test_message.tool_calls.empty()) {
@@ -373,6 +422,44 @@ static void test_templates(const struct common_chat_templates * tmpls, const std
     }
 }
 
+/**
+ * Test if streaming=true is consistant with streaming=false for given partial parser
+ * Also test if there is any problem with partial message
+ */
+template <typename T>
+static void test_parser_with_streaming(const common_chat_msg & expected, const std::string & raw_message, T parse_msg) {
+    auto merged = simple_assist_msg("");
+    auto last_msg = parse_msg("");
+    for (size_t i = 1; i <= raw_message.size(); ++i) {
+        auto curr_msg = parse_msg(raw_message.substr(0, i));
+        if (curr_msg == simple_assist_msg("")) continue;
+        LOG_INF("Streaming msg: %s\n", common_chat_msgs_to_json_oaicompat<json>({curr_msg}).dump().c_str());
+        for (auto diff: common_chat_msg_diff::compute_diffs(last_msg, curr_msg)) {
+            LOG_INF("Streaming diff: %s\n", common_chat_msg_diff_to_json_oaicompat<json>(diff).dump().c_str());
+            if (!diff.reasoning_content_delta.empty()) {
+                merged.reasoning_content += diff.reasoning_content_delta;
+            }
+            if (!diff.content_delta.empty()) {
+                merged.content += diff.content_delta;
+            }
+            if (diff.tool_call_index != std::string::npos) {
+                if (!diff.tool_call_delta.name.empty()) {
+                    merged.tool_calls.push_back({diff.tool_call_delta.name, "", ""});
+                }
+                if (!diff.tool_call_delta.arguments.empty()) {
+                    GGML_ASSERT(!merged.tool_calls.empty());
+                    merged.tool_calls.back().arguments += diff.tool_call_delta.arguments;
+                }
+            }
+            LOG_INF("Streaming merged: %s\n", common_chat_msgs_to_json_oaicompat<json>({merged}).dump().c_str());
+        }
+        assert_msg_equals(curr_msg, merged, true);
+        last_msg = curr_msg;
+    }
+    assert_msg_equals(expected, parse_msg(raw_message), true);
+    assert_msg_equals(expected, merged, true);
+}
+
 const common_chat_msg message_user {
     "user",
     "Hey there!",
@@ -395,16 +482,7 @@ const common_chat_msg message_user_parts {
     /* .tool_name = */ "",
     /* .tool_call_id = */ "",
 };
-static common_chat_msg simple_assist_msg(const std::string & content, const std::string & reasoning_content = "", const std::string & tool_name = "", const std::string & arguments = "", const std::string & id = "") {
-    common_chat_msg msg;
-    msg.role = "assistant";
-    msg.content = content;
-    msg.reasoning_content = reasoning_content;
-    if (!tool_name.empty()) {
-        msg.tool_calls.push_back({ tool_name, arguments, id });
-    }
-    return msg;
-}
+
 const common_chat_msg message_assist                              = simple_assist_msg("Hello, world!\nWhat's up?");
 const common_chat_msg message_assist_empty                        = simple_assist_msg("");
 const common_chat_msg message_assist_thoughts_unparsed_deepseek   = simple_assist_msg("<think>I'm\nthinking</think>Hello, world!\nWhat's up?");
@@ -417,6 +495,8 @@ const common_chat_msg message_assist_thoughts                    = simple_assist
 const common_chat_msg message_assist_thoughts_unopened_unparsed  = simple_assist_msg("I'm\nthinking</think>Hello, world!\nWhat's up?");
 const common_chat_msg message_assist_thoughts_no_content         = simple_assist_msg("", "I'm\nthinking");
 const common_chat_msg message_assist_call                        = simple_assist_msg("", "", "special_function", "{\"arg1\": 1}");
+const common_chat_msg message_assist_call_noopt                  = simple_assist_msg("", "", "special_function_with_opt", "{\"arg1\": 1}");
+const common_chat_msg message_assist_call_withopt                = simple_assist_msg("", "", "special_function_with_opt", "{\"arg1\": 1, \"arg2\": 2}");
 const common_chat_msg message_assist_call_content                = simple_assist_msg("Hello, world!\nWhat's up?", "", "special_function", "{\"arg1\":1}");
 const common_chat_msg message_assist_call_empty_args             = simple_assist_msg("", "", "special_function");
 const common_chat_msg message_assist_call_cutoff_args            = simple_assist_msg("", "", "special_function", "{\"arg");
@@ -1834,7 +1914,7 @@ static void test_template_output_parsers() {
 
         // Test partial parsing for incomplete tool call - don't actually add the call until parsing parameters is done
         assert_msg_equals(
-            simple_assist_msg("", ""),
+            simple_assist_msg("", "", "calculate_sum", "{\"numbers\":"),
             common_chat_parse(
                 "<seed:tool_call>\n"
                 "<function=calculate_sum>\n"
@@ -2288,6 +2368,940 @@ Hey there!<|im_end|>
         // above verify edge cases and format variations for the tool call output format.
     }
 
+    {
+        auto tmpls = read_templates("models/templates/MiniMax-M2.jinja");
+        std::vector<std::string> end_tokens{ "[e~[" };
+
+        assert_equals(COMMON_CHAT_FORMAT_MINIMAX_M2, common_chat_templates_apply(tmpls.get(), inputs_no_tools).format);
+        assert_equals(COMMON_CHAT_FORMAT_MINIMAX_M2, common_chat_templates_apply(tmpls.get(), inputs_tools).format);
+
+        // Test parsing regular content
+        assert_msg_equals(message_assist,
+            common_chat_parse(
+                "Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_MINIMAX_M2}));
+
+        // Test parsing content with thinking
+        assert_msg_equals(message_assist_thoughts,
+            common_chat_parse(
+                "<think>I'm\nthinking</think>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {
+                    /* .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /* .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                }));
+
+        // Test parsing tool calls
+        assert_msg_equals(message_assist_call,
+            common_chat_parse(
+                "<minimax:tool_call><invoke name=\"special_function\"><parameter name=\"arg1\">1</parameter></invoke></minimax:tool_call>",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_MINIMAX_M2}));
+
+        // Test parsing tool calls with thinking
+        assert_msg_equals(message_assist_call_thoughts,
+            common_chat_parse(
+                "<think>I'm\nthinking</think><minimax:tool_call><invoke name=\"special_function\"><parameter name=\"arg1\">1</parameter></invoke></minimax:tool_call>",
+                /* is_partial= */ false,
+                {
+                    /*  .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+                }));
+
+        // Test tool calls with extra content
+        assert_msg_equals(message_assist_call_content,
+            common_chat_parse(
+                "<minimax:tool_call><invoke name=\"special_function\"><parameter name=\"arg1\">1</parameter></invoke></minimax:tool_call>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_MINIMAX_M2}
+            ));
+
+        // Test tool calls with extra content AND thinking
+        assert_msg_equals(message_assist_call_thoughts_content,
+            common_chat_parse(
+                "<think>I'm\nthinking</think><minimax:tool_call><invoke name=\"special_function\"><parameter name=\"arg1\">1</parameter></invoke></minimax:tool_call>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {
+                    /*  .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+                }));
+
+        // Test streaming
+        test_parser_with_streaming(message_assist_call_thoughts_content,
+            "<think>I'm\nthinking\n</think>Hello, world!\nWhat's up?\n<minimax:tool_call><invoke name=\"special_function\"><parameter name=\"arg1\">1</parameter></invoke></minimax:tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(message_assist_call_thoughts_unparsed,
+            "<think>I'm\nthinking</think>\n\n<minimax:tool_call><invoke name=\"special_function\"><parameter name=\"arg1\">1</parameter></invoke></minimax:tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_NONE
+            }); });
+        test_parser_with_streaming(message_assist_call_thoughts_content,
+            "<think>I'm\nthinking\n</think>\n\nHello, world!\nWhat's up?\n\n<minimax:tool_call>\n<invoke name=\"special_function\">\n<parameter name=\"arg1\">1</parameter>\n</invoke>\n</minimax:tool_call>\n",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(message_assist_call_withopt,
+            "<minimax:tool_call>\n<invoke name=\"special_function_with_opt\">\n<parameter name=\"arg1\">1</parameter>\n<parameter name=\"arg2\">2</parameter>\n</invoke>\n</minimax:tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_MINIMAX_M2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_NONE
+            }); });
+
+        // Test template generation for regular content
+        test_templates(tmpls.get(), end_tokens, message_assist, tools,
+                      "Hello, world!\nWhat's up?",
+                      /* expect_grammar_triggered= */ false);
+
+        // Test template generation for tool calls
+        test_templates(tmpls.get(), end_tokens, message_assist_call, tools,
+                      "<minimax:tool_call>\n<invoke name=\"special_function\">\n<parameter name=\"arg1\">1</parameter>\n</invoke>\n</minimax:tool_call>",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ true,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_NONE,
+                      /* ignore_whitespace_differences= */ true
+        );
+
+        // Test template generation for tools with optional parameters
+        test_templates(tmpls.get(), end_tokens, message_assist_call_noopt, tools,
+                      "<minimax:tool_call>\n<invoke name=\"special_function_with_opt\">\n<parameter name=\"arg1\">1</parameter>\n</invoke>\n</minimax:tool_call>",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ true,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_NONE,
+                      /* ignore_whitespace_differences= */ true
+        );
+        test_templates(tmpls.get(), end_tokens, message_assist_call_withopt, tools,
+                      "<minimax:tool_call>\n<invoke name=\"special_function_with_opt\">\n<parameter name=\"arg1\">1</parameter>\n<parameter name=\"arg2\">2</parameter>\n</invoke>\n</minimax:tool_call>",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ true,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_NONE,
+                      /* ignore_whitespace_differences= */ true
+        );
+    }
+
+    {
+        auto tmpls = read_templates("models/templates/GLM-4.6.jinja");
+        std::vector<std::string>   end_tokens{ "<|assistant|>", "<|observation|>" };
+
+        assert_equals(COMMON_CHAT_FORMAT_GLM_4_5, common_chat_templates_apply(tmpls.get(), inputs_no_tools).format);
+        assert_equals(COMMON_CHAT_FORMAT_GLM_4_5, common_chat_templates_apply(tmpls.get(), inputs_tools).format);
+
+        // Test parsing regular content
+        assert_msg_equals(message_assist,
+            common_chat_parse(
+                "Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_GLM_4_5}));
+
+        // Test parsing content with thinking
+        assert_msg_equals(message_assist_thoughts,
+            common_chat_parse(
+                "\n<think>I'm\nthinking</think>\nHello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {
+                    /* .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /* .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                }), true);
+
+        // Test parsing tool calls
+        assert_msg_equals(message_assist_call,
+            common_chat_parse(
+                "\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_GLM_4_5}), true);
+
+        // Test parsing tool calls with thinking
+        assert_msg_equals(message_assist_call_thoughts,
+            common_chat_parse(
+                "\n<think>I'm\nthinking</think>\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+                /* is_partial= */ false,
+                {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+                }), true);
+
+        // Test tool calls with extra content
+        assert_msg_equals(message_assist_call_content,
+            common_chat_parse(
+                "\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_GLM_4_5}
+            ), true);
+
+        // Test tool calls with extra content AND thinking
+        assert_msg_equals(message_assist_call_thoughts_content,
+            common_chat_parse(
+                "\n<think>I'm\nthinking</think>Hello, world!\nWhat's up?\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+                /* is_partial= */ false,
+                {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+                }), true);
+
+        // Test streaming
+        test_parser_with_streaming(message_assist_call_thoughts_content,
+            "\n<think>I'm\nthinking</think>Hello, world!\nWhat's up?\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(message_assist_call_thoughts_unparsed,
+            "\n<think>I'm\nthinking</think>\n\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_NONE
+            }); });
+        test_parser_with_streaming(message_assist_call_withopt,
+            "\n<think></think>\n<tool_call>special_function_with_opt\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n<arg_key>arg2</arg_key>\n<arg_value>2</arg_value>\n</tool_call>\n",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+            test_parser_with_streaming(
+                simple_assist_msg("", "", "complex_function", "{\"name\":\"John Doe\",\"age\":30,\"active\":true,\"score\":95.5}"),
+                "<tool_call>complex_function\n"
+                "<arg_key>name</arg_key>\n"
+                "<arg_value>John Doe</arg_value>\n"
+                "<arg_key>age</arg_key>\n"
+                "<arg_value>30</arg_value>\n"
+                "<arg_key>active</arg_key>\n"
+                "<arg_value>true</arg_value>\n"
+                "<arg_key>score</arg_key>\n"
+                "<arg_value>95.5</arg_value>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_GLM_4_5}); });
+        test_parser_with_streaming(
+                simple_assist_msg("", "", "web_search", "{\"query\":\"\\\"From Zero\\\" Linkin Park album tracklist complete songs\",\"limit\":3,\"type\":\"text\"}"),
+                "<tool_call>web_search\n"
+                "<arg_key>query</arg_key>\n"
+                "<arg_value>\"From Zero\" Linkin Park album tracklist complete songs</arg_value>\n"
+                "<arg_key>limit</arg_key>\n"
+                "<arg_value>3</arg_value>\n"
+                "<arg_key>type</arg_key>\n"
+                "<arg_value>text</arg_value>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_GLM_4_5}); });
+
+        // Test interleaved thinking
+        test_parser_with_streaming(simple_assist_msg("Hello, world!\n\nWhat's up?", "I'm\nthinkingThinking2", "special_function", "{\"arg1\": 1}"),
+            "\n<think>I'm\nthinking</think>Hello, world!\n<think>Thinking2</think>What's up?\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(simple_assist_msg("\n<think>I'm\nthinking</think>Hello, world!\n<think>Thinking2</think>What's up?", "", "special_function", "{\"arg1\": 1}"),
+            "\n<think>I'm\nthinking</think>Hello, world!\n<think>Thinking2</think>What's up?\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_GLM_4_5,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_NONE
+            }); });
+
+        // Test template generation for regular content
+        test_templates(tmpls.get(), end_tokens, message_assist, tools,
+                      "\n<think></think>\nHello, world!\nWhat's up?",
+                      /* expect_grammar_triggered= */ false);
+
+        // Test template generation for tool calls
+        test_templates(tmpls.get(), end_tokens, message_assist_call, tools,
+                      "\n<think></think>\n<tool_call>special_function\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>\n",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ false,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                      /* ignore_whitespace_differences= */ true
+        );
+
+        // Test template generation for tools with optional parameters
+        test_templates(tmpls.get(), end_tokens, message_assist_call_noopt, tools,
+                      "\n<think></think>\n<tool_call>special_function_with_opt\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n</tool_call>\n",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ false,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                      /* ignore_whitespace_differences= */ true
+        );
+        test_templates(tmpls.get(), end_tokens, message_assist_call_withopt, tools,
+                      "\n<think></think>\n<tool_call>special_function_with_opt\n<arg_key>arg1</arg_key>\n<arg_value>1</arg_value>\n<arg_key>arg2</arg_key>\n<arg_value>2</arg_value>\n</tool_call>\n",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ false,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                      /* ignore_whitespace_differences= */ true
+        );
+    }
+
+    {
+        auto tmpls = read_templates("models/templates/Kimi-K2-Thinking.jinja");
+        std::vector<std::string> end_tokens{ "<|im_end|>" };
+
+        assert_equals(COMMON_CHAT_FORMAT_KIMI_K2, common_chat_templates_apply(tmpls.get(), inputs_no_tools).format);
+        assert_equals(COMMON_CHAT_FORMAT_KIMI_K2, common_chat_templates_apply(tmpls.get(), inputs_tools).format);
+
+        // Test parsing regular content
+        assert_msg_equals(message_assist,
+            common_chat_parse(
+                "Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_KIMI_K2}));
+
+        // Test parsing content with thinking
+        assert_msg_equals(message_assist_thoughts,
+            common_chat_parse(
+                "<think>I'm\nthinking</think>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {
+                    /* .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /* .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                }));
+
+        // Test parsing tool calls
+        assert_msg_equals(message_assist_call,
+            common_chat_parse(
+                "<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_KIMI_K2}));
+
+        // Test parsing tool calls with thinking
+        assert_msg_equals(message_assist_call_thoughts,
+            common_chat_parse(
+                "<think>I'm\nthinking</think><|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>",
+                /* is_partial= */ false,
+                {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+                }));
+
+        // Test tool calls with extra content
+        assert_msg_equals(message_assist_call_content,
+            common_chat_parse(
+                "<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_KIMI_K2}
+            ));
+
+        // Test tool calls with extra content AND thinking
+        assert_msg_equals(message_assist_call_thoughts_content,
+            common_chat_parse(
+                "<think>I'm\nthinking</think><|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>Hello, world!\nWhat's up?",
+                /* is_partial= */ false,
+                {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+                }));
+
+        // Test streaming
+        test_parser_with_streaming(message_assist_call_thoughts_content,
+            "<think>I'm\nthinking\n</think>Hello, world!\nWhat's up?\n<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(message_assist_call_thoughts_unparsed,
+            "<think>I'm\nthinking</think>\n\n<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_NONE
+            }); });
+        test_parser_with_streaming(message_assist_call_thoughts_content,
+            "<think>I'm\nthinking\n</think>\n\nHello, world!\nWhat's up?\n\n<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>\n",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(message_assist_call_withopt,
+            "<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function_with_opt:1<|tool_call_argument_begin|>{\"arg1\": 1, \"arg2\": 2}<|tool_call_end|><|tool_calls_section_end|>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_NONE
+            }); });
+        test_parser_with_streaming(simple_assist_msg("Hello, world!\nWhat's up?", "I'm\nthinking", "special_function", "{\"arg1\": \"123456\"}"),
+            "<think>I'm\nthinking</think>Hello, world!\nWhat's up?\n<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": \"123456\"}<|tool_call_end|><|tool_calls_section_end|>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(simple_assist_msg("Hello, world!\nWhat's up?", "I'm\nthinking", "special_function", "{\"arg1\": [1, 2, \"345\", 6]}"),
+            "<think>I'm\nthinking</think>Hello, world!\nWhat's up?\n<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": [1, 2, \"345\", 6]}<|tool_call_end|><|tool_calls_section_end|>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+        test_parser_with_streaming(simple_assist_msg("Hello, world!\nWhat's up?", "I'm\nthinking", "special_function", "{\"arg1\": {\"12\": 34, \"5\": [67, 8], \"9\": \"10\"}}"),
+            "<think>I'm\nthinking</think>Hello, world!\nWhat's up?\n<|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": {\"12\": 34, \"5\": [67, 8], \"9\": \"10\"}}<|tool_call_end|><|tool_calls_section_end|>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {
+                    /*  .format = */ COMMON_CHAT_FORMAT_KIMI_K2,
+                    /*  .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK
+            }); });
+
+        // Test template generation for regular content
+        test_templates(tmpls.get(), end_tokens, message_assist, tools,
+                      "<think></think>Hello, world!\nWhat's up?",
+                      /* expect_grammar_triggered= */ false);
+
+        // Test template generation for tool calls
+        test_templates(tmpls.get(), end_tokens, message_assist_call, tools,
+                      "<think></think><|tool_calls_section_begin|><|tool_call_begin|>functions.special_function:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ true,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                      /* ignore_whitespace_differences= */ true
+        );
+
+        // Test template generation for tools with optional parameters
+        test_templates(tmpls.get(), end_tokens, message_assist_call_noopt, tools,
+                      "<think></think><|tool_calls_section_begin|><|tool_call_begin|>functions.special_function_with_opt:1<|tool_call_argument_begin|>{\"arg1\": 1}<|tool_call_end|><|tool_calls_section_end|>",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ true,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                      /* ignore_whitespace_differences= */ true
+        );
+        test_templates(tmpls.get(), end_tokens, message_assist_call_withopt, tools,
+                      "<think></think><|tool_calls_section_begin|><|tool_call_begin|>functions.special_function_with_opt:1<|tool_call_argument_begin|>{\"arg1\": 1, \"arg2\": 2}<|tool_call_end|><|tool_calls_section_end|>",
+                      /* expect_grammar_triggered= */ true,
+                      /* test_grammar_if_triggered= */ true,
+                      /* common_reasoning_format= */ COMMON_REASONING_FORMAT_DEEPSEEK,
+                      /* ignore_whitespace_differences= */ true
+        );
+    }
+
+    // Test Qwen3-Coder XML format
+    {
+        // Basic XML tool call parsing
+        assert_msg_equals(
+            message_assist_call,
+            common_chat_parse(
+                "<tool_call>\n"
+                "  <function=special_function>\n"
+                "    <parameter=arg1>\n"
+                "      1\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+                /* is_partial= */ false,
+                {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}));
+
+        // Multiple parameters with different types
+        common_chat_msg expected_multi_param;
+        expected_multi_param.role = "assistant";
+        expected_multi_param.tool_calls = {
+            { "complex_function", "{\"name\":\"John Doe\",\"age\":30,\"active\":true,\"score\":95.5}", "" }
+        };
+
+        test_parser_with_streaming(expected_multi_param,
+                "<tool_call>\n"
+                "  <function=complex_function>\n"
+                "    <parameter=name>\n"
+                "      John Doe\n"
+                "    </parameter>\n"
+                "    <parameter=age>\n"
+                "      30\n"
+                "    </parameter>\n"
+                "    <parameter=active>\n"
+                "      true\n"
+                "    </parameter>\n"
+                "    <parameter=score>\n"
+                "      95.5\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Special characters and Unicode
+        common_chat_msg expected_special_chars;
+        expected_special_chars.role = "assistant";
+        expected_special_chars.tool_calls = {
+            { "unicode_function", "{\"message\":\"Hello 世界! 🌍 Special chars: @#$%^&*()\"}", "" }
+        };
+
+        test_parser_with_streaming(expected_special_chars,
+                "<tool_call>\n"
+                "  <function=unicode_function>\n"
+                "    <parameter=message>\n"
+                "      Hello 世界! 🌍 Special chars: @#$%^&*()\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Multiline content with newlines and indentation
+        common_chat_msg expected_multiline;
+        expected_multiline.role = "assistant";
+        expected_multiline.tool_calls = {
+            { "code_function", "{\"code\":\"def hello():\\n    print(\\\"Hello, World!\\\")\\n    return True\"}", "" }
+        };
+
+        test_parser_with_streaming(expected_multiline,
+                "<tool_call>\n"
+                "  <function=code_function>\n"
+                "    <parameter=code>\n"
+                "def hello():\n"
+                "    print(\"Hello, World!\")\n"
+                "    return True\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // JSON object as parameter value
+        common_chat_msg expected_json_param;
+        expected_json_param.role = "assistant";
+        expected_json_param.tool_calls = {
+            { "json_function", "{\"config\":{\"host\":\"localhost\",\"port\":8080,\"ssl\":false}}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_json_param,
+                "<tool_call>\n"
+                "  <function=json_function>\n"
+                "    <parameter=config>\n"
+                "      {\"host\": \"localhost\", \"port\": 8080, \"ssl\": false}\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Array as parameter value
+        common_chat_msg expected_array_param;
+        expected_array_param.role = "assistant";
+        expected_array_param.tool_calls = {
+            { "array_function", "{\"items\":[\"apple\",\"banana\",\"cherry\"]}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_array_param,
+                "<tool_call>\n"
+                "  <function=array_function>\n"
+                "    <parameter=items>\n"
+                "      [\"apple\", \"banana\", \"cherry\"]\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Empty parameter
+        common_chat_msg expected_empty_param;
+        expected_empty_param.role = "assistant";
+        expected_empty_param.tool_calls = {
+            { "empty_function", "{\"empty_param\":\"\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_empty_param,
+                "<tool_call>\n"
+                "  <function=empty_function>\n"
+                "    <parameter=empty_param>\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Boolean values (true/false)
+        common_chat_msg expected_boolean;
+        expected_boolean.role = "assistant";
+        expected_boolean.tool_calls = {
+            { "boolean_function", "{\"enabled\":true,\"debug\":false}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_boolean,
+                "<tool_call>\n"
+                "  <function=boolean_function>\n"
+                "    <parameter=enabled>\n"
+                "      true\n"
+                "    </parameter>\n"
+                "    <parameter=debug>\n"
+                "      false\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Null value
+        common_chat_msg expected_null;
+        expected_null.role = "assistant";
+        expected_null.tool_calls = {
+            { "null_function", "{\"optional_param\":null}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_null,
+                "<tool_call>\n"
+                "  <function=null_function>\n"
+                "    <parameter=optional_param>\n"
+                "      null\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Negative numbers and scientific notation
+        common_chat_msg expected_numbers;
+        expected_numbers.role = "assistant";
+        expected_numbers.tool_calls = {
+            { "math_function", "{\"negative\":-42,\"decimal\":-3.14,\"scientific\":1.23e-4}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_numbers,
+                "<tool_call>\n"
+                "  <function=math_function>\n"
+                "    <parameter=negative>\n"
+                "      -42\n"
+                "    </parameter>\n"
+                "    <parameter=decimal>\n"
+                "      -3.14\n"
+                "    </parameter>\n"
+                "    <parameter=scientific>\n"
+                "      1.23e-4\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // XML-like content in parameters (should be escaped)
+        common_chat_msg expected_xml_content;
+        expected_xml_content.role = "assistant";
+        expected_xml_content.tool_calls = {
+            { "xml_function", "{\"xml_content\":\"<root><item>value</item></root>\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_xml_content,
+                "<tool_call>\n"
+                "  <function=xml_function>\n"
+                "    <parameter=xml_content>\n"
+                "      <root><item>value</item></root>\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Quotes and escape characters
+        common_chat_msg expected_quotes;
+        expected_quotes.role = "assistant";
+        expected_quotes.tool_calls = {
+            { "quote_function", "{\"message\":\"She said \\\"Hello!\\\" and left.\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_quotes,
+                "<tool_call>\n"
+                "  <function=quote_function>\n"
+                "    <parameter=message>\n"
+                "      She said \"Hello!\" and left.\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Long parameter value (simplified)
+        std::string long_text = "This is a long text parameter that should test the parser's ability to handle larger amounts of text data.";
+
+        common_chat_msg expected_long_text;
+        expected_long_text.role = "assistant";
+        expected_long_text.tool_calls = {
+            { "long_function", "{\"long_text\":\"" + long_text + "\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_long_text,
+                "<tool_call>\n"
+                "  <function=long_function>\n"
+                "    <parameter=long_text>\n"
+                "      " + long_text + "\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Mixed content with text before and after tool call
+        common_chat_msg expected_mixed_content;
+        expected_mixed_content.role = "assistant";
+        expected_mixed_content.content = "I'll help you search for products. ";
+        expected_mixed_content.tool_calls = {
+            { "search_function", "{\"query\":\"laptops\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_mixed_content,
+                "I'll help you search for products. <tool_call>\n"
+                "  <function=search_function>\n"
+                "    <parameter=query>\n"
+                "      laptops\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Compact format (no extra whitespace)
+        common_chat_msg expected_compact;
+        expected_compact.role = "assistant";
+        expected_compact.tool_calls = {
+            { "compact_function", "{\"param\":\"value\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_compact,
+                "<tool_call><function=compact_function><parameter=param>value</parameter></function></tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Function name with underscores and numbers
+        common_chat_msg expected_complex_name;
+        expected_complex_name.role = "assistant";
+        expected_complex_name.tool_calls = {
+            { "get_user_data_v2", "{\"user_id\":12345}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_complex_name,
+                "<tool_call>\n"
+                "  <function=get_user_data_v2>\n"
+                "    <parameter=user_id>\n"
+                "      12345\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Parameter names with underscores and numbers
+        common_chat_msg expected_complex_params;
+        expected_complex_params.role = "assistant";
+        expected_complex_params.tool_calls = {
+            { "test_function", "{\"param_1\":\"value1\",\"param_2_name\":\"value2\",\"param3\":123}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_complex_params,
+                "<tool_call>\n"
+                "  <function=test_function>\n"
+                "    <parameter=param_1>\n"
+                "      value1\n"
+                "    </parameter>\n"
+                "    <parameter=param_2_name>\n"
+                "      value2\n"
+                "    </parameter>\n"
+                "    <parameter=param3>\n"
+                "      123\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Very deeply nested XML content in parameter
+        common_chat_msg expected_deep_xml;
+        expected_deep_xml.role = "assistant";
+        expected_deep_xml.tool_calls = {
+            { "xml_parser", "{\"xml\":\"<root><level1><level2><level3>deep content</level3></level2></level1></root>\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_deep_xml,
+                "<tool_call>\n"
+                "  <function=xml_parser>\n"
+                "    <parameter=xml>\n"
+                "      <root><level1><level2><level3>deep content</level3></level2></level1></root>\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Parameter with only whitespace
+        common_chat_msg expected_whitespace_param;
+        expected_whitespace_param.role = "assistant";
+        expected_whitespace_param.tool_calls = {
+            { "whitespace_function", "{\"spaces\":\"\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_whitespace_param,
+                "<tool_call>\n"
+                "  <function=whitespace_function>\n"
+                "    <parameter=spaces>\n"
+                "      \n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Parameter with tabs and mixed whitespace
+        common_chat_msg expected_mixed_whitespace;
+        expected_mixed_whitespace.role = "assistant";
+        expected_mixed_whitespace.tool_calls = {
+            { "tab_function", "{\"content\":\"line1\\n\\tindented line\\n    spaces\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_mixed_whitespace,
+                "<tool_call>\n"
+                "  <function=tab_function>\n"
+                "    <parameter=content>\n"
+                "line1\n"
+                "\tindented line\n"
+                "    spaces\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Control characters and special Unicode
+        common_chat_msg expected_control_chars;
+        expected_control_chars.role = "assistant";
+        expected_control_chars.tool_calls = {
+            { "control_function", "{\"text\":\"Line1\\nLine2\\tTabbed\\rCarriage return\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_control_chars,
+                "<tool_call>\n"
+                "  <function=control_function>\n"
+                "    <parameter=text>\n"
+                "Line1\nLine2\tTabbed\rCarriage return\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Emoji and extended Unicode characters
+        common_chat_msg expected_emoji;
+        expected_emoji.role = "assistant";
+        expected_emoji.tool_calls = {
+            { "emoji_function", "{\"message\":\"Hello! 👋 🌟 🚀 Testing emojis: 😀😃😄😁 and symbols: ∑∏∆∇\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_emoji,
+                "<tool_call>\n"
+                "  <function=emoji_function>\n"
+                "    <parameter=message>\n"
+                "      Hello! 👋 🌟 🚀 Testing emojis: 😀😃😄😁 and symbols: ∑∏∆∇\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Mathematical expressions and formulas
+        common_chat_msg expected_math;
+        expected_math.role = "assistant";
+        expected_math.tool_calls = {
+            { "math_function", "{\"formula\":\"E = mc² and ∫f(x)dx = F(x) + C\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_math,
+                "<tool_call>\n"
+                "  <function=math_function>\n"
+                "    <parameter=formula>\n"
+                "      E = mc² and ∫f(x)dx = F(x) + C\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // SQL injection-like content (should be safely escaped)
+        common_chat_msg expected_sql;
+        expected_sql.role = "assistant";
+        expected_sql.tool_calls = {
+            { "sql_function", "{\"query\":\"SELECT * FROM users WHERE id = 1; DROP TABLE users; --\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_sql,
+                "<tool_call>\n"
+                "  <function=sql_function>\n"
+                "    <parameter=query>\n"
+                "      SELECT * FROM users WHERE id = 1; DROP TABLE users; --\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // HTML/XML injection content
+        common_chat_msg expected_html;
+        expected_html.role = "assistant";
+        expected_html.tool_calls = {
+            { "html_function", "{\"content\":\"<script>alert('xss')</script><img src=x onerror=alert(1)>\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_html,
+                "<tool_call>\n"
+                "  <function=html_function>\n"
+                "    <parameter=content>\n"
+                "      <script>alert('xss')</script><img src=x onerror=alert(1)>\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Binary-like content (base64)
+        common_chat_msg expected_binary;
+        expected_binary.role = "assistant";
+        expected_binary.tool_calls = {
+            { "binary_function", "{\"data\":\"SGVsbG8gV29ybGQhIFRoaXMgaXMgYmFzZTY0IGVuY29kZWQgdGV4dC4=\"}", "" }
+        };
+
+        test_parser_with_streaming(
+            expected_binary,
+                "<tool_call>\n"
+                "  <function=binary_function>\n"
+                "    <parameter=data>\n"
+                "      SGVsbG8gV29ybGQhIFRoaXMgaXMgYmFzZTY0IGVuY29kZWQgdGV4dC4=\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+
+        // Very large numbers (should be parsed as scientific notation)
+        common_chat_msg expected_large_numbers;
+        expected_large_numbers.role = "assistant";
+        expected_large_numbers.tool_calls = {
+            { "number_function", "{\"big_int\":1e+60}", "" }  // Large number becomes scientific notation
+        };
+
+        test_parser_with_streaming(
+            expected_large_numbers,
+                "<tool_call>\n"
+                "  <function=number_function>\n"
+                "    <parameter=big_int>\n"
+                "      999999999999999999999999999999999999999999999999999999999999\n"
+                "    </parameter>\n"
+                "  </function>\n"
+                "</tool_call>",
+            [&](const std::string &msg) { return common_chat_parse(msg, /* is_partial= */ true, {COMMON_CHAT_FORMAT_QWEN3_CODER_XML}); });
+    }
+
+    {
+        // Qwen3-Coder template
+        auto tmpls = read_templates("models/templates/Qwen3-Coder.jinja");
+        common_chat_templates_inputs inputs;
+        inputs.messages = { message_user };
+
+        common_chat_tool qwen_union_tool {
+            /* .name = */ "qwen_union",
+            /* .description = */ "Test tool for union/anyOf handling",
+            /* .parameters = */ R"({
+                "type": "object",
+                "properties": {
+                    "priority": { "type": ["number", "null"] },
+                    "maybe_text": { "anyOf": [ { "type": "string" } ] },
+                    "config": { "anyOf": [ { "type": "object" }, { "type": "null" } ] }
+                },
+                "required": []
+            })",
+        };
+        inputs.tools = { qwen_union_tool };
+
+        auto params = common_chat_templates_apply(tmpls.get(), inputs);
+        assert_equals(COMMON_CHAT_FORMAT_QWEN3_CODER_XML, params.format);
+        assert_equals(false, params.grammar.empty());
+
+        // Grammar should compile successfully
+        auto grammar = build_grammar(params.grammar);
+        GGML_ASSERT(grammar && "Failed to build Qwen3-Coder grammar with union types");
+    }
+
 }
 
 static void test_msg_diffs_compute() {