mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-09 19:46:11 +00:00
fix: tool call parsing for LFM2 and LFM2.5 models (#21242)
* fix: tool call parsing for LFM2 and LFM2.5 models' * refactor: add test / break out lfm2 and lfm2.5 parsing logic
This commit is contained in:
parent
744c0c7310
commit
1d6d4cf7a5
3 changed files with 197 additions and 9 deletions
100
common/chat.cpp
100
common/chat.cpp
|
|
@ -1274,11 +1274,12 @@ 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)
|
||||
// LFM2 format: uses <|tool_list_start|>[...]<|tool_list_end|> in system prompt
|
||||
// and <|tool_call_start|>[name(arg="val")]<|tool_call_end|> for tool calls.
|
||||
// - Reasoning: <think>{reasoning}</think> (optional)
|
||||
// - Content: text before a tool call (optional)
|
||||
// - Tool calls: Python-style, e.g. [function_name(arg1="value1", arg2="value2")]
|
||||
// Tool calls can appear multiple times (parallel tool calls supported)
|
||||
static common_chat_params common_chat_params_init_lfm2(const common_chat_template & tmpl,
|
||||
const autoparser::generation_params & inputs) {
|
||||
common_chat_params data;
|
||||
|
|
@ -1319,9 +1320,9 @@ static common_chat_params common_chat_params_init_lfm2(const common_chat_templat
|
|||
if (!has_tools || inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_NONE) {
|
||||
return generation_prompt + reasoning + p.content(p.rest()) + end;
|
||||
}
|
||||
|
||||
auto tool_calls = p.rule("tool-calls",
|
||||
p.trigger_rule("tool-call", p.literal(TOOL_CALL_START) +
|
||||
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)
|
||||
)
|
||||
|
|
@ -1349,6 +1350,80 @@ static common_chat_params common_chat_params_init_lfm2(const common_chat_templat
|
|||
{ COMMON_GRAMMAR_TRIGGER_TYPE_WORD, TOOL_CALL_START }
|
||||
};
|
||||
}
|
||||
return data;
|
||||
}
|
||||
|
||||
// LFM2.5 format: uses plain "List of tools: [...]" in system prompt, no wrapper tokens.
|
||||
// Tool calls are bare [name(arg="val")], though model may optionally emit <|tool_call_start|>.
|
||||
// - Reasoning: <think>{reasoning}</think> (optional)
|
||||
// - Content: text before a tool call (optional)
|
||||
// - Tool calls: Python-style, e.g. [function_name(arg1="value1", arg2="value2")]
|
||||
// Tool calls can appear multiple times (parallel tool calls supported)
|
||||
static common_chat_params common_chat_params_init_lfm2_5(const common_chat_template & tmpl,
|
||||
const autoparser::generation_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_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 THINK_START = "<think>";
|
||||
const std::string THINK_END = "</think>";
|
||||
|
||||
data.thinking_start_tag = THINK_START;
|
||||
data.thinking_end_tag = THINK_END;
|
||||
|
||||
auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) {
|
||||
auto generation_prompt = p.prefix(inputs.generation_prompt, THINK_START);
|
||||
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 generation_prompt + reasoning + p.content(p.rest()) + end;
|
||||
}
|
||||
|
||||
auto tool_calls = p.rule("tool-calls",
|
||||
p.trigger_rule("tool-call",
|
||||
p.python_style_tool_calls(inputs.tools, inputs.parallel_tool_calls)
|
||||
)
|
||||
);
|
||||
|
||||
auto content = p.content(p.until_one_of({"<|tool_call_start|>", "["}));
|
||||
auto maybe_start = p.optional(p.literal("<|tool_call_start|>"));
|
||||
return generation_prompt + reasoning + content + maybe_start + 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);
|
||||
});
|
||||
foreach_function(inputs.tools, [&](const json & tool) {
|
||||
const std::string name = tool.at("function").at("name");
|
||||
data.grammar_triggers.push_back({ COMMON_GRAMMAR_TRIGGER_TYPE_WORD, "[" + name + "(" });
|
||||
});
|
||||
}
|
||||
|
||||
return data;
|
||||
}
|
||||
|
|
@ -1530,14 +1605,21 @@ static std::optional<common_chat_params> try_specialized_template(
|
|||
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
|
||||
// LFM2 format detection: template uses <|tool_list_start|>[...]<|tool_list_end|> around the tool list
|
||||
// and <|tool_call_start|>[...]<|tool_call_end|> around each tool call
|
||||
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);
|
||||
}
|
||||
|
||||
// LFM2.5 format detection: template uses plain "List of tools: [...]" with no special tokens
|
||||
if (src.find("List of tools: [") != std::string::npos &&
|
||||
src.find("<|tool_list_start|>") == std::string::npos) {
|
||||
LOG_DBG("Using specialized template: LFM2.5\n");
|
||||
return common_chat_params_init_lfm2_5(tmpl, params);
|
||||
}
|
||||
|
||||
// GigaChatV3 format detection
|
||||
if (src.find("<|role_sep|>") != std::string::npos &&
|
||||
src.find("<|message_sep|>") != std::string::npos &&
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue