chat : split specialized parsers into common/parsers (#27764)
* chat : split specialized parsers into common/parsers Move the 14 dedicated template parsers out of chat.cpp into one file each under common/parsers, mirroring the src/models split. chat.cpp keeps the template detection in common_chat_try_specialized_template() and drops from 3915 to 1513 lines. common/parsers/parsers.h holds the shared helpers and one declaration per parser. foreach_function/foreach_parameter become inline there since nothing in chat.cpp uses them any more; common_chat_template_direct_apply_impl and common_chat_template_generation_prompt_impl lose static and carry their default arguments in the header. Parser-specific helpers move with their parser: is_lfm2_template, deepseek_v4_sort_tool_results and the gemma4 turn builder. No functional change. Assisted-by: Claude Opus 5 * chat : enumerate parser sources instead of globbing file(GLOB) does not re-run CMake when a source file is added or removed, so an incremental build silently keeps building the old set. List the parsers in common/parsers/sources.cmake and include it from common/CMakeLists.txt. Assisted-by: Claude Opus 5 * split helpers, add newlines
This commit is contained in:
Piotr Wilkin (ilintar)
@@ -0,0 +1,148 @@
|
||||
#include "parsers.h"
|
||||
|
||||
// An assistant turn is rendered as one or more messages, each
|
||||
// "<|start|>assistant to=<recipient><|message|>{content}{END}" where END is
|
||||
// <|eom|> (more messages follow) or <|eot|> (end of turn):
|
||||
// - chain-of-thought: to=self, terminated by <|eom|>
|
||||
// - final answer: to=user, terminated by <|eot|>
|
||||
// The generation prompt is just "<|start|>assistant"; the model emits its own
|
||||
// " to=...<|message|>".
|
||||
common_chat_params common_chat_params_init_muse_glimmer(const common_chat_template & tmpl,
|
||||
const autoparser::generation_params & inputs) {
|
||||
common_chat_params data;
|
||||
|
||||
data.prompt = common_chat_template_direct_apply_impl(tmpl, inputs);
|
||||
data.generation_prompt = "<|start|>assistant";
|
||||
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
|
||||
data.supports_thinking = true;
|
||||
|
||||
data.preserved_tokens = {
|
||||
"<|start|>", "<|message|>", "<|eom|>", "<|eot|>",
|
||||
// ATEM tool-call markup emitted on " to=<tool>" turns.
|
||||
"<atem:function_calls>", "<atem:invoke", "<atem:parameter", "</atem:parameter>",
|
||||
"</atem:invoke>", "</atem:function_calls>",
|
||||
};
|
||||
|
||||
data.message_delimiters = {
|
||||
{ COMMON_CHAT_ROLE_ASSISTANT, "<|start|>assistant" },
|
||||
{ COMMON_CHAT_ROLE_USER, "<|start|>user" },
|
||||
{ COMMON_CHAT_ROLE_SYSTEM, "<|start|>system" },
|
||||
{ COMMON_CHAT_ROLE_TOOL, "<|start|>tool" },
|
||||
};
|
||||
|
||||
if (inputs.has_continuation()) {
|
||||
const auto & msg = inputs.continue_msg;
|
||||
|
||||
data.generation_prompt = "<|start|>assistant to=self<|message|>" + msg.reasoning_content;
|
||||
if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
|
||||
data.generation_prompt += "<|eom|><|start|>assistant to=user<|message|>" + msg.render_content();
|
||||
}
|
||||
|
||||
data.prompt += data.generation_prompt;
|
||||
}
|
||||
|
||||
auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
|
||||
|
||||
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
|
||||
// Constrained grammar whenever tools are offered.
|
||||
auto include_grammar = has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE;
|
||||
|
||||
auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) {
|
||||
auto start = p.rule("start", p.literal("<|start|>assistant"));
|
||||
|
||||
if (!extract_reasoning && !include_grammar) {
|
||||
return start + p.content(p.rest());
|
||||
}
|
||||
|
||||
if (extract_reasoning) {
|
||||
p.rule("analysis", p.literal(" to=self<|message|>") + p.reasoning(p.until("<|eom|>")) + p.literal("<|eom|>"));
|
||||
} else {
|
||||
p.rule("analysis", p.literal(" to=self<|message|>") + p.content(p.until("<|eom|>")) + p.literal("<|eom|>"));
|
||||
}
|
||||
auto analysis = p.ref("analysis");
|
||||
|
||||
auto recipient = p.optional(p.literal(" to=user"));
|
||||
auto final_msg = p.rule("final", recipient + p.literal("<|message|>") +
|
||||
p.content(p.until_one_of({ "<|eot|>", "<|eom|>" })));
|
||||
|
||||
if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE) {
|
||||
auto string_value = p.ac(
|
||||
p.tool_arg_string_value(p.until("</atem:parameter>")) + p.tool_arg_close(p.literal("</atem:parameter>")),
|
||||
"</atem:parameter>");
|
||||
|
||||
auto tool_choice = p.choice();
|
||||
foreach_function(inputs.tools, [&](const json & tool) {
|
||||
const auto & function = tool.at("function");
|
||||
const std::string name = function.at("name");
|
||||
auto params = function.contains("parameters") ? function.at("parameters") : json::object();
|
||||
|
||||
auto args = p.eps();
|
||||
if (params.contains("properties") && params.at("properties").is_object() && !params.at("properties").empty()) {
|
||||
auto schema_info = common_schema_info();
|
||||
schema_info.resolve_refs(params);
|
||||
|
||||
auto arg_choice = p.choice();
|
||||
for (const auto & [prop_name, prop_schema] : params.at("properties").items()) {
|
||||
auto value_parser = p.eps();
|
||||
if (schema_info.resolves_to_string(prop_schema)) {
|
||||
value_parser = string_value;
|
||||
} else {
|
||||
value_parser = p.tool_arg_json_value(
|
||||
p.schema(p.json(), "tool-" + name + "-arg-" + prop_name + "-schema", prop_schema, false))
|
||||
+ p.tool_arg_close(p.literal("</atem:parameter>"));
|
||||
}
|
||||
|
||||
auto arg_rule = p.tool_arg(
|
||||
p.tool_arg_open(p.literal("<atem:parameter name=\"") + p.tool_arg_name(p.literal(prop_name)) + p.literal("\">")) +
|
||||
value_parser);
|
||||
|
||||
arg_choice |= arg_rule;
|
||||
}
|
||||
args = p.zero_or_more(arg_choice + p.space());
|
||||
}
|
||||
|
||||
auto tool_parser = p.tool(
|
||||
p.tool_open(p.literal(" to=") + p.until("<|message|>") +
|
||||
p.literal("<|message|><atem:function_calls>") + p.space() +
|
||||
p.literal("<atem:invoke name=\"") + p.tool_name(p.literal(name)) + p.literal("\">") + p.space())
|
||||
<< p.tool_args(args)
|
||||
<< p.tool_close(p.literal("</atem:invoke>") + p.space() + p.literal("</atem:function_calls>")));
|
||||
|
||||
tool_choice |= p.rule("tool-" + name, tool_parser);
|
||||
});
|
||||
|
||||
auto tool_calls = inputs.parallel_tool_calls
|
||||
? p.trigger_rule("tool-call", tool_choice + p.zero_or_more(p.literal("<|eom|>") + start + tool_choice))
|
||||
: p.trigger_rule("tool-call", tool_choice);
|
||||
|
||||
|
||||
if (inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED) {
|
||||
return p.zero_or_more(start + analysis) + start + tool_calls;
|
||||
}
|
||||
auto trailing_calls = p.optional(p.literal("<|eom|>") + start + tool_calls);
|
||||
return p.zero_or_more(start + analysis) + start + (tool_calls | (final_msg + trailing_calls));
|
||||
}
|
||||
|
||||
return p.zero_or_more(start + analysis) + start + final_msg;
|
||||
});
|
||||
|
||||
data.parser = parser.save();
|
||||
|
||||
if (include_grammar) {
|
||||
data.grammar_lazy = inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
|
||||
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.contains("parameters") ? function.at("parameters") : json::object();
|
||||
builder.resolve_refs(schema);
|
||||
});
|
||||
parser.build_grammar(builder, data.grammar_lazy);
|
||||
});
|
||||
data.grammar_triggers = {
|
||||
{ COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN,
|
||||
"<\\|start\\|>assistant( to=(?!self<\\|message\\|>)(?!user<\\|message\\|>)[^<]*?<\\|message\\|>)" },
|
||||
};
|
||||
}
|
||||
|
||||
return data;
|
||||
}
|
||||
Reference in New Issue
Block a user