PEG parser for LFM2 (#20251)
* PEG parser for LFM2 * Simplify using python_value()
This commit is contained in:
Piotr Wilkin (ilintar)
committed by
GitHub
GitHub
parent
d417bc43dd
commit
97c64fbdbd
@@ -476,6 +476,74 @@ common_peg_parser common_chat_peg_builder::standard_constructed_tools(
|
||||
return force_tool_calls ? section : optional(section);
|
||||
}
|
||||
|
||||
// Python-style tool calls: name(arg1="value1", arg2=123)
|
||||
// Used only by LFM2 for now, so we don't merge it into autoparser
|
||||
common_peg_parser common_chat_peg_builder::python_style_tool_calls(
|
||||
const nlohmann::json & tools,
|
||||
bool parallel_tool_calls) {
|
||||
if (!tools.is_array() || tools.empty()) {
|
||||
return eps();
|
||||
}
|
||||
|
||||
auto tool_choices = choice();
|
||||
|
||||
for (const auto & tool_def : tools) {
|
||||
if (!tool_def.contains("function")) {
|
||||
continue;
|
||||
}
|
||||
const auto & function = tool_def.at("function");
|
||||
std::string name = function.at("name");
|
||||
nlohmann::json params = function.contains("parameters") ? function.at("parameters") : nlohmann::json::object();
|
||||
|
||||
auto args = eps();
|
||||
if (params.contains("properties") && !params["properties"].empty()) {
|
||||
auto arg_choice = choice();
|
||||
for (const auto & el : params["properties"].items()) {
|
||||
const std::string & prop_name = el.key();
|
||||
const auto & prop_def = el.value();
|
||||
bool is_string_type = (prop_def.contains("type") && prop_def["type"] == "string");
|
||||
|
||||
auto arg_name_parser = literal(prop_name);
|
||||
|
||||
common_peg_parser arg_value_parser = eps();
|
||||
auto string_value_parser = choice({
|
||||
literal("\"") + tool_arg_string_value(json_string_content()) + literal("\""),
|
||||
literal("'") + tool_arg_string_value(json_string_content()) + literal("'")
|
||||
});
|
||||
|
||||
if (is_string_type) {
|
||||
arg_value_parser = string_value_parser;
|
||||
} else {
|
||||
arg_value_parser = tool_arg_value(python_value());
|
||||
}
|
||||
|
||||
// Full argument: name="value" or name=value
|
||||
auto arg_rule = tool_arg(
|
||||
tool_arg_open(eps()) +
|
||||
tool_arg_name(arg_name_parser) +
|
||||
literal("=") +
|
||||
arg_value_parser +
|
||||
tool_arg_close(eps())
|
||||
);
|
||||
arg_choice |= arg_rule;
|
||||
}
|
||||
|
||||
args = arg_choice + zero_or_more("," + space() + arg_choice);
|
||||
}
|
||||
|
||||
auto tool_parser = tool(tool_open(tool_name(literal(name)) + literal("(")) +
|
||||
space() + tool_args(args) + space() + tool_close(literal(")"))
|
||||
);
|
||||
|
||||
tool_choices |= rule("tool-" + name, tool_parser);
|
||||
}
|
||||
|
||||
if (parallel_tool_calls) {
|
||||
return "[" + space() + tool_choices + zero_or_more("," + space() + tool_choices) + space() + "]";
|
||||
}
|
||||
return "[" + space() + tool_choices + space() + "]";
|
||||
}
|
||||
|
||||
// Helper: Parse dot notation key into prefix and field name
|
||||
static std::pair<std::string, std::string> parse_key_spec(const std::string & key) {
|
||||
auto dot_pos = key.find('.');
|
||||
|
||||
@@ -112,6 +112,11 @@ class common_chat_peg_builder : public common_peg_parser_builder {
|
||||
bool parallel_tool_calls,
|
||||
bool force_tool_calls);
|
||||
|
||||
// Helper for Python-style function call format: name(arg1="value1", arg2=123)
|
||||
// Used by LFM2 and similar templates
|
||||
common_peg_parser python_style_tool_calls(const nlohmann::json & tools,
|
||||
bool parallel_tool_calls);
|
||||
|
||||
private:
|
||||
// Implementation helpers for standard_json_tools — one per JSON tool call layout mode
|
||||
common_peg_parser build_json_tools_function_is_key(const nlohmann::json & tools,
|
||||
|
||||
@@ -1274,6 +1274,82 @@ static common_chat_params common_chat_params_init_kimi_k2(const common_chat_temp
|
||||
return data;
|
||||
}
|
||||
|
||||
// LFM2 format:
|
||||
// - Reasoning: <think>{reasoning}</think> (optional, only if enable_thinking is true)
|
||||
// - Content: text after reasoning (optional)
|
||||
// - Tool calls: <|tool_call_start|>[function_name(arg1="value1", arg2="value2")]<|tool_call_end|>
|
||||
// Tool calls can appear multiple times (parallel tool calls)
|
||||
static common_chat_params common_chat_params_init_lfm2(const common_chat_template & tmpl,
|
||||
const autoparser::templates_params & inputs) {
|
||||
common_chat_params data;
|
||||
|
||||
data.prompt = common_chat_template_direct_apply(tmpl, inputs);
|
||||
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
|
||||
data.supports_thinking = true;
|
||||
data.preserved_tokens = {
|
||||
"<|tool_list_start|>",
|
||||
"<|tool_list_end|>",
|
||||
"<|tool_call_start|>",
|
||||
"<|tool_call_end|>",
|
||||
"<think>",
|
||||
"</think>",
|
||||
};
|
||||
|
||||
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
|
||||
auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
|
||||
auto include_grammar = has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE;
|
||||
|
||||
|
||||
const std::string TOOL_CALL_START = "<|tool_call_start|>";
|
||||
const std::string TOOL_CALL_END = "<|tool_call_end|>";
|
||||
const std::string THINK_START = "<think>";
|
||||
const std::string THINK_END = "</think>";
|
||||
auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) {
|
||||
|
||||
auto end = p.end();
|
||||
|
||||
auto reasoning = p.eps();
|
||||
if (extract_reasoning && inputs.enable_thinking) {
|
||||
reasoning = p.optional(THINK_START + p.reasoning(p.until(THINK_END)) + THINK_END);
|
||||
}
|
||||
|
||||
if (!has_tools || inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_NONE) {
|
||||
return reasoning + p.content(p.rest()) + end;
|
||||
}
|
||||
|
||||
auto tool_calls = p.rule("tool-calls",
|
||||
p.trigger_rule("tool-call", p.literal(TOOL_CALL_START) +
|
||||
p.python_style_tool_calls(inputs.tools, inputs.parallel_tool_calls) +
|
||||
p.literal(TOOL_CALL_END)
|
||||
)
|
||||
);
|
||||
|
||||
auto content = p.content(p.until(TOOL_CALL_START));
|
||||
|
||||
return reasoning + content + tool_calls + end;
|
||||
});
|
||||
|
||||
data.parser = parser.save();
|
||||
|
||||
if (include_grammar) {
|
||||
data.grammar_lazy = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_AUTO;
|
||||
data.grammar = build_grammar([&](const common_grammar_builder & builder) {
|
||||
foreach_function(inputs.tools, [&](const json & tool) {
|
||||
const auto & function = tool.at("function");
|
||||
auto schema = function.at("parameters");
|
||||
builder.resolve_refs(schema);
|
||||
});
|
||||
parser.build_grammar(builder, data.grammar_lazy);
|
||||
});
|
||||
|
||||
data.grammar_triggers = {
|
||||
{ COMMON_GRAMMAR_TRIGGER_TYPE_WORD, TOOL_CALL_START }
|
||||
};
|
||||
}
|
||||
|
||||
return data;
|
||||
}
|
||||
|
||||
namespace workaround {
|
||||
|
||||
// if first message is system and template does not support it, merge it with next message
|
||||
@@ -1422,6 +1498,14 @@ static common_chat_params common_chat_templates_apply_jinja(const struct common_
|
||||
return common_chat_params_init_kimi_k2(tmpl, params);
|
||||
}
|
||||
|
||||
// LFM2 - uses <|tool_list_start|>/<|tool_list_end|> markers and <|tool_call_start|>[name(args)]<|tool_call_end|> format
|
||||
// Detection: template has "<|tool_list_start|>" and "<|tool_list_end|>" markers
|
||||
if (src.find("<|tool_list_start|>") != std::string::npos &&
|
||||
src.find("<|tool_list_end|>") != std::string::npos) {
|
||||
LOG_DBG("Using specialized template: LFM2\n");
|
||||
return common_chat_params_init_lfm2(tmpl, params);
|
||||
}
|
||||
|
||||
try {
|
||||
LOG_DBG("Using differential autoparser\n");
|
||||
struct autoparser::autoparser autoparser;
|
||||
|
||||
Reference in New Issue
Block a user