mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
chat : Seed OSS thinking + tool call support (#15552)
* Reasoning and tool-calling support for Seed OSS * Fix grammar and partial parsing * Whitespace * New chat template * Update common/chat.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update common/chat.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Remove unused 'purge_healing_marker' helper --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
committed by
GitHub
parent
009b709d6e
commit
60e5eee31f
153
common/chat.cpp
153
common/chat.cpp
@@ -622,6 +622,7 @@ 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_SEED_OSS: return "Seed-OSS";
|
||||
default:
|
||||
throw std::runtime_error("Unknown chat format");
|
||||
}
|
||||
@@ -2059,6 +2060,94 @@ static void common_chat_parse_granite(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 common_chat_params common_chat_params_init_without_tools(const common_chat_template & tmpl, const struct templates_params & inputs) {
|
||||
common_chat_params data;
|
||||
data.prompt = apply(tmpl, inputs);
|
||||
@@ -2075,8 +2164,62 @@ static common_chat_params common_chat_params_init_without_tools(const common_cha
|
||||
return data;
|
||||
}
|
||||
|
||||
static common_chat_params common_chat_params_init_seed_oss(
|
||||
const common_chat_template & tmpl,
|
||||
templates_params & params,
|
||||
const common_chat_templates_inputs & inputs)
|
||||
{
|
||||
common_chat_params data;
|
||||
data.prompt = apply(tmpl, params);
|
||||
data.format = COMMON_CHAT_FORMAT_SEED_OSS;
|
||||
if (string_ends_with(data.prompt, "<seed:think>")) {
|
||||
if (!inputs.enable_thinking) {
|
||||
data.prompt += "</seed:think>";
|
||||
} else {
|
||||
data.thinking_forced_open = true;
|
||||
}
|
||||
}
|
||||
|
||||
if (params.tools.is_array() && !params.tools.empty()) {
|
||||
data.grammar_lazy = inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
|
||||
data.grammar = build_grammar([&](const common_grammar_builder & builder) {
|
||||
std::vector<std::string> tool_rules;
|
||||
foreach_function(params.tools, [&](const json & tool) {
|
||||
const auto & function = tool.at("function");
|
||||
std::string name = function.at("name");
|
||||
auto parameters = function.at("parameters");
|
||||
builder.resolve_refs(parameters);
|
||||
|
||||
// Create rule for Seed-OSS function call format
|
||||
std::string param_rules;
|
||||
if (parameters.contains("properties")) {
|
||||
for (const auto & [key, value] : parameters.at("properties").items()) {
|
||||
param_rules += "\"<parameter=" + key + ">\"" + builder.add_schema(name + "-arg-" + key, value) +
|
||||
"\"</parameter>\"";
|
||||
}
|
||||
}
|
||||
|
||||
tool_rules.push_back(builder.add_rule(name + "-call",
|
||||
"\"<seed:tool_call>\" space \"<function=" + name + ">\" space " +
|
||||
param_rules +
|
||||
" \"</function>\" space \"</seed:tool_call>\""));
|
||||
});
|
||||
|
||||
data.grammar_triggers.push_back({ COMMON_GRAMMAR_TRIGGER_TYPE_WORD, "<seed:tool_call>" });
|
||||
|
||||
data.preserved_tokens = {
|
||||
"<seed:think>", "</seed:think>", "<seed:tool_call>", "</seed:tool_call>",
|
||||
"<function=", "</function>", "<parameter=", "</parameter>",
|
||||
};
|
||||
|
||||
builder.add_rule("root", string_join(tool_rules, " | "));
|
||||
});
|
||||
}
|
||||
return data;
|
||||
}
|
||||
|
||||
static common_chat_params common_chat_templates_apply_jinja(
|
||||
const struct common_chat_templates * tmpls,
|
||||
const struct common_chat_templates * tmpls,
|
||||
const struct common_chat_templates_inputs & inputs)
|
||||
{
|
||||
templates_params params;
|
||||
@@ -2145,6 +2288,11 @@ static common_chat_params common_chat_templates_apply_jinja(
|
||||
return common_chat_params_init_gpt_oss(tmpl, params);
|
||||
}
|
||||
|
||||
// Seed-OSS
|
||||
if (src.find("<seed:think>") != std::string::npos) {
|
||||
return common_chat_params_init_seed_oss(tmpl, params, inputs);
|
||||
}
|
||||
|
||||
// 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())) {
|
||||
@@ -2303,6 +2451,9 @@ 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_SEED_OSS:
|
||||
common_chat_parse_seed_oss(builder);
|
||||
break;
|
||||
default:
|
||||
throw std::runtime_error(std::string("Unsupported format: ") + common_chat_format_name(builder.syntax().format));
|
||||
}
|
||||
|
||||
@@ -111,6 +111,7 @@ enum common_chat_format {
|
||||
COMMON_CHAT_FORMAT_COMMAND_R7B,
|
||||
COMMON_CHAT_FORMAT_GRANITE,
|
||||
COMMON_CHAT_FORMAT_GPT_OSS,
|
||||
COMMON_CHAT_FORMAT_SEED_OSS,
|
||||
|
||||
COMMON_CHAT_FORMAT_COUNT, // Not a format, just the # formats
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user