ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

common: Generalized XML-style tool-call parsing with streaming support (#958)

Browse Source 
* port upstream https://github.com/ggml-org/llama.cpp/pull/16932

* Add fixed chat templates.

* fix grammar when tool have no argument

* Insert additional stops for Kimi-K2

* Fix `no triggers set for lazy grammar!` for GLM4.5/4.6

* update chat.cpp

* fix grammar for GLM 4.5/4.6

* chat: Fix streaming parser for granite models (#15682)

* fix(chat): fix streaming parser for granite models

* tests: add test cases for Granite models chat parser

* common : Fix corrupted memory error on json grammar initialization (#16038)

Initalizing RESERVED_NAME in is_reserved_name() is not thread
safe and leads to corrupted memory when used from multiple threads
as can be seen in the asan trace below. This fixes the initialization
to make it thread-safe.

    #0 0x000100abd018 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) __hash_table:1565
    #1 0x000100ab0320 in SchemaConverter::visit(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) json-schema-to-grammar.cpp:802
    #2 0x000100aafc48 in std::__1::__function::__func<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2, std::__1::allocator<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> (std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319
    #3 0x000100a2c938 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&), std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>, void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319
    #4 0x000100a139f8 in foreach_function(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::function<void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)> const&) chat.cpp:762
    #5 0x000100a2a7f4 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0, std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0>, void (common_grammar_builder const&)>::operator()(common_grammar_builder const&) function.h:319
    #6 0x000100aa98f4 in build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&) json-schema-to-grammar.cpp:982
    #7 0x0001009c9314 in common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool) chat.cpp:1110
    #8 0x0001009b8afc in common_chat_templates_apply_jinja(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:1992
    #9 0x0001009b533c in common_chat_templates_apply(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:2074
    #10 0x000100810120 in llamacpp_apply_chat_template+0x724 (predict_oai-98384e17fb94e863:arm64+0x100090120)
    ...

==45482==Register values:
 x[0] = 0x00006020004147f8   x[1] = 0x00006080000013c8   x[2] = 0x0000000000000000   x[3] = 0x0000604006289738
 x[4] = 0x0000000000000002   x[5] = 0x0000000000000001   x[6] = 0x04034000004b4000   x[7] = 0x0000000000000001
 x[8] = 0xbebebebebebebebe   x[9] = 0x17d7d7d7d7d7d7d7  x[10] = 0x00000c04000828ff  x[11] = 0x0000000000000001
x[12] = 0x000000002018d383  x[13] = 0x0000000000000000  x[14] = 0xfa0000000000fafa  x[15] = 0x000010700001ffff
x[16] = 0x000000019dc012c0  x[17] = 0x00000001021284f8  x[18] = 0x0000000000000000  x[19] = 0x00000001700acdc0
x[20] = 0x0000000000000002  x[21] = 0x000000002018d384  x[22] = 0x16dd16fd2e731151  x[23] = 0x0000007000020000
x[24] = 0x0000000100c69c08  x[25] = 0x0000000100c69c20  x[26] = 0x00006080000013c7  x[27] = 0x0000000100c69c00
x[28] = 0x00000001700acd60     fp = 0x00000001700aceb0     lr = 0x0000000100abce30     sp = 0x00000001700acd60
AddressSanitizer can not provide additional info.
SUMMARY: AddressSanitizer: SEGV __hash_table:1565 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&)
Thread T5 created by T0 here:
    #0 0x0001020b99d4 in pthread_create+0x5c (libclang_rt.asan_osx_dynamic.dylib:arm64e+0x359d4)
    #1 0x000100873910 in std::sys::pal::unix:🧵:Thread:🆕:h77254fdd87a28e05+0x118 (predict_oai-98384e17fb94e863:arm64+0x1000f3910)
    #2 0x0001007c7a1c in test::run_test::haeb3c2bcd5ed6cf6+0x76c (predict_oai-98384e17fb94e863:arm64+0x100047a1c)
    #3 0x0001007aedb0 in test::console::run_tests_console::he9d142d704f3a986+0x149c (predict_oai-98384e17fb94e863:arm64+0x10002edb0)
    #4 0x0001007c5758 in test::test_main::hf86a5e20735245b9+0x118 (predict_oai-98384e17fb94e863:arm64+0x100045758)
    #5 0x0001007c5da0 in test::test_main_static::h61ee9c8fd30abca0+0x54 (predict_oai-98384e17fb94e863:arm64+0x100045da0)
    ...

==45482==ABORTING

* common : fix reasoning before forced tool call via tool_choice = required (#16264)

* common : fix reasoning before forced tool call via tool_choice = required

* common : improve reasoning and commentary handling when tool_choice is required

(cherry picked from commit c746984956d6882c2de73d53ae2bb3bdf889e475)

---------

Co-authored-by: Alde Rojas <hello@alde.dev>

* Try fix Jinja template for GLM

* Improve Kimi-K2 chat template

* 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: shun095 <8069181+shun095@users.noreply.github.com>
Co-authored-by: David Ribeiro Alves <davidralves@gmail.com>
Co-authored-by: crat0z <11581854+crat0z@users.noreply.github.com>
Co-authored-by: Alde Rojas <hello@alde.dev>
This commit is contained in:
hksdpc255
2025-11-19 01:29:58 +11:00
committed by GitHub
parent 0157f78061
commit 2ebd715fa0
18 changed files with 3255 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/CMakeLists.txt
View File

@@ -56,6 +56,8 @@ add_library(${TARGET} STATIC
chat.h
chat-parser.cpp
chat-parser.h
chat-parser-xml-toolcall.h
chat-parser-xml-toolcall.cpp
common.cpp
sampling.h
sampling.cpp

861
common/chat-parser-xml-toolcall.cpp Normal file
View File

@@ -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("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("Skipping invalid function (invalid name): %s", function.dump(2).c_str());
continue;
}
if (!function.contains("parameters") || !function.at("parameters").is_object()) {
LOG("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("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("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("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("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("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("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("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("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("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("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("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("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("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);
}

45
common/chat-parser-xml-toolcall.h Normal file
View File

@@ -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);

10
common/chat-parser.h
View File

@@ -1,6 +1,7 @@
#pragma once
#include "chat.h"
#include "chat-parser-xml-toolcall.h"
#include "json-partial.h"
#include "regex-partial.h"
@@ -114,5 +115,14 @@ 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();
};

509
common/chat.cpp
View File

@@ -638,6 +638,12 @@ const char * common_chat_format_name(common_chat_format format) {
case COMMON_CHAT_FORMAT_COMMAND_R7B: return "Command R7B";
case COMMON_CHAT_FORMAT_GRANITE: return "Granite";
case COMMON_CHAT_FORMAT_GPT_OSS: return "GPT-OSS";
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");
}
@@ -1483,6 +1489,278 @@ 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;
auto prompt = apply(tmpl, inputs);
@@ -1560,17 +1838,36 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
);
});
auto recipient_in_role = builder.add_rule("recipient_in_role",
"\"<|start|>assistant\"? \" to=functions.\" ( " +
string_join(tool_rules_recipient_in_role, " | ") + " )"
);
auto recipient_in_channel = builder.add_rule("recipient_in_channel",
channel + " \" to=functions.\" ( " +
string_join(tool_rules_recipient_in_channel, " | ") + " )"
);
builder.add_rule("root", recipient_in_role + " | " + recipient_in_channel);
if (data.grammar_lazy) {
auto recipient_in_role = builder.add_rule("recipient_in_role",
"\"<|start|>assistant\"? \" to=functions.\" ( " +
string_join(tool_rules_recipient_in_role, " | ") + " )"
);
builder.add_rule("root", recipient_in_role + " | " + recipient_in_channel);
} else {
auto not_end = builder.add_rule("not-end",
"[^<] | \"<\" [^|] | \"<|\" [^e] | \"<|e\" [^n] | \"<|en\" [^d] | \"<|end\" [^|] | \"<|end|\" [^>]");
auto analysis = builder.add_rule("analysis",
"\"<|channel|>analysis<|message|>\" ( " + not_end + " )* \"<|end|>\"");
auto commentary = builder.add_rule("commentary",
"\"<|channel|>commentary<|message|>\" ( " + not_end + " )* \"<|end|>\"");
auto recipient_in_role = builder.add_rule("recipient_in_role",
"\" to=functions.\" ( " + string_join(tool_rules_recipient_in_role, " | ") + " )"
);
builder.add_rule("root",
"( " + analysis + " \"<|start|>assistant\" )? " +
"( " + commentary + " \"<|start|>assistant\" )? " +
"( " + recipient_in_role + " | " + recipient_in_channel + " )"
);
}
// Trigger on tool calls that appear in the commentary channel
data.grammar_triggers.push_back({
@@ -1682,6 +1979,100 @@ 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("%s\n", __func__);
common_chat_params data;
@@ -2174,15 +2565,28 @@ static common_chat_params common_chat_params_init_granite(const common_chat_temp
static void common_chat_parse_granite(common_chat_msg_parser & builder) {
// Parse thinking tags
static const common_regex start_think_regex(regex_escape("<think>"));
static const common_regex end_think_regex(regex_escape("</think>"));
// Granite models output partial tokens such as "<" and "<think".
// By leveraging try_consume_regex()/try_find_regex() throwing
// common_chat_msg_partial_exception for these partial tokens,
// processing is interrupted and the tokens are not passed to add_content().
if (auto res = builder.try_consume_regex(start_think_regex)) {
// Restore position for try_parse_reasoning()
builder.move_to(res->groups[0].begin);
builder.try_find_regex(end_think_regex, std::string::npos, false);
// Restore position for try_parse_reasoning()
builder.move_to(res->groups[0].begin);
}
builder.try_parse_reasoning("<think>", "</think>");
// Parse response tags using regex
static const common_regex response_regex("<response>([\\s\\S]*?)</response>");
if (auto res = builder.try_find_regex(response_regex)) {
// Extract the content between the tags (capture group 1)
auto content = builder.str(res->groups[1]);
builder.add_content(content);
builder.move_to(res->groups[0].end);
// Parse response tags
static const common_regex start_response_regex(regex_escape("<response>"));
static const common_regex end_response_regex(regex_escape("</response>"));
// Granite models output partial tokens such as "<" and "<response".
// Same hack as reasoning parsing.
if (builder.try_consume_regex(start_response_regex)) {
builder.try_find_regex(end_response_regex);
}
if (!builder.syntax().parse_tool_calls) {
@@ -2196,13 +2600,10 @@ static void common_chat_parse_granite(common_chat_msg_parser & builder) {
builder.move_to(res->groups[0].end);
// Expect JSON array of tool calls
auto tool_calls_data = builder.consume_json();
if (tool_calls_data.json.is_array()) {
if (!builder.add_tool_calls(tool_calls_data.json)) {
builder.add_content("<|tool_call|>" + tool_calls_data.json.dump());
if (auto tool_call = builder.try_consume_json_with_dumped_args({{{"arguments"}}})) {
if (!builder.add_tool_calls(tool_call->value) || tool_call->is_partial) {
throw common_chat_msg_partial_exception("incomplete tool call");
}
} else {
builder.add_content("<|tool_call|>" + tool_calls_data.json.dump());
}
} else {
builder.add_content(builder.consume_rest());
@@ -2291,6 +2692,35 @@ 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);
@@ -2301,6 +2731,29 @@ static common_chat_params common_chat_templates_apply_jinja(
return common_chat_params_init_gpt_oss(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())) {
@@ -2463,6 +2916,24 @@ static void common_chat_parse(common_chat_msg_parser & builder) {
case COMMON_CHAT_FORMAT_GPT_OSS:
common_chat_parse_gpt_oss(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));
}

6
common/chat.h
View File

@@ -112,6 +112,12 @@ enum common_chat_format {
COMMON_CHAT_FORMAT_COMMAND_R7B,
COMMON_CHAT_FORMAT_GRANITE,
COMMON_CHAT_FORMAT_GPT_OSS,
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
};

21
common/json-partial.cpp
View File

@@ -243,8 +243,25 @@ 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);

15
common/json-schema-to-grammar.cpp
View File

@@ -299,12 +299,13 @@ std::unordered_map<std::string, BuiltinRule> STRING_FORMAT_RULES = {
};
static bool is_reserved_name(const std::string & name) {
static std::unordered_set<std::string> RESERVED_NAMES;
if (RESERVED_NAMES.empty()) {
RESERVED_NAMES.insert("root");
for (const auto &p : PRIMITIVE_RULES) RESERVED_NAMES.insert(p.first);
for (const auto &p : STRING_FORMAT_RULES) RESERVED_NAMES.insert(p.first);
}
static const std::unordered_set<std::string> RESERVED_NAMES = [] {
std::unordered_set<std::string> s;
s.insert("root");
for (const auto & p : PRIMITIVE_RULES) s.insert(p.first);
for (const auto & p : STRING_FORMAT_RULES) s.insert(p.first);
return s;
}();
return RESERVED_NAMES.find(name) != RESERVED_NAMES.end();
}
@@ -387,6 +388,8 @@ 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);

2
common/json-schema-to-grammar.h
View File

@@ -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 = {});