Add support for Laguna XS.2 & M.1 (#25165)

This commit is contained in:
Joe Rowell
2026-07-22 09:54:08 +08:00
committed by GitHub
parent 66e4bf7e59
commit 1f66c3ce1c
22 changed files with 1091 additions and 1 deletions
+9 -1
View File
@@ -47,6 +47,8 @@ common_chat_params peg_generator::generate_parser(const common_chat_template &
data.generation_prompt = common_chat_template_generation_prompt(tmpl, inputs);
data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
data.preserved_tokens = autoparser.preserved_tokens;
data.additional_stops.insert(data.additional_stops.end(),
autoparser.additional_stops.begin(), autoparser.additional_stops.end());
std::string parser_generation_prompt = data.generation_prompt;
@@ -286,7 +288,13 @@ common_peg_parser analyze_tools::build_func_parser(common_chat_peg_builder & p,
// we only emit tool_close when we can actually see the closing marker. This prevents
// premature closing during partial parsing when we've seen e.g. "</" which could be
// either "</tool_call>" (end) or "<arg_key>" prefix that failed to match.
func_parser = func_parser + p.tool_close(p.peek(p.literal(format.per_call_end)));
// Laguna (v4): the model may emit whitespace between the last </arg_value> and
// </tool_call> even though the template renders them tight. Tolerate optional
// leading space in the close lookahead so the tool call still closes.
auto close_peek = arguments.tolerate_intertag_whitespace
? p.peek(p.space() + p.literal(format.per_call_end))
: p.peek(p.literal(format.per_call_end));
func_parser = func_parser + p.tool_close(close_peek);
} else {
func_parser = func_parser + p.tool_close(p.space()); // force this to process tool closing callbacks in mapper
}
+2
View File
@@ -206,6 +206,7 @@ struct tool_arguments_analysis {
std::string value_prefix; // e.g., "", "<arg_value>", ""
std::string value_suffix; // e.g., "</param>", "</arg_value>", ""
std::string separator; // e.g., "", "\n", ","
bool tolerate_intertag_whitespace = false; // Laguna: accept optional whitespace between arg tags
};
struct tool_id_analysis {
@@ -388,6 +389,7 @@ struct autoparser {
// Preserved tokens for tokenizer (union of all non-empty markers)
std::vector<std::string> preserved_tokens;
std::vector<std::string> additional_stops; // literal stop strings (e.g. Laguna </assistant>) caught however tokenized
autoparser() = default;
+20
View File
@@ -173,6 +173,26 @@ static std::vector<std::function<void(const common_chat_template & tmpl, autopar
LOG_DBG(ANSI_ORANGE "[Patch: JSON name/parameters tool instruction]\n" ANSI_RESET);
}
},
// Laguna (poolside) - the v4 chat template renders reasoning and tool-arg
// delimiters with formatting whitespace ("<think>\n", "</arg_value>\n") that
// the model does not emit, so the inferred delimiters carry a spurious
// newline and never match the model output. Trim to the bare tag. (v8
// renders without the whitespace, so this is a no-op there.)
[](const common_chat_template & tmpl, autoparser & analysis) -> void {
if (tmpl.src.find("laguna_glm_thinking") != std::string::npos) {
analysis.reasoning.start = trim_whitespace(analysis.reasoning.start);
analysis.reasoning.end = trim_whitespace(analysis.reasoning.end);
analysis.tools.arguments.value_prefix = trim_whitespace(analysis.tools.arguments.value_prefix);
analysis.tools.arguments.value_suffix = trim_whitespace(analysis.tools.arguments.value_suffix);
analysis.tools.arguments.separator = trim_whitespace(analysis.tools.arguments.separator);
analysis.tools.arguments.tolerate_intertag_whitespace = true;
// The CONTROL/eot </assistant> token only halts generation when emitted as the
// single token; after tool calls the model can spell it out as text tokens.
// A literal stop string catches it either way.
analysis.additional_stops.push_back("</assistant>");
LOG_DBG(ANSI_ORANGE "[Patch: Laguna]\n" ANSI_RESET);
}
},
});