134 lines
7.3 KiB
C++
134 lines
7.3 KiB
C++
#pragma once
|
|
|
|
#include "chat.h"
|
|
#include "peg-parser.h"
|
|
|
|
#include <map>
|
|
#include <optional>
|
|
#include <vector>
|
|
|
|
class common_chat_peg_builder : public common_peg_parser_builder {
|
|
public:
|
|
static constexpr const char * REASONING_BLOCK = "reasoning-block";
|
|
static constexpr const char * REASONING = "reasoning";
|
|
static constexpr const char * CONTENT = "content";
|
|
|
|
common_peg_parser reasoning_block(const common_peg_parser & p) { return tag(REASONING_BLOCK, p); }
|
|
|
|
common_peg_parser reasoning(const common_peg_parser & p) { return tag(REASONING, p); }
|
|
|
|
common_peg_parser content(const common_peg_parser & p) { return tag(CONTENT, p); }
|
|
|
|
common_peg_parser tag_with_safe_content(const std::string & tag_name,
|
|
const std::string & marker,
|
|
const common_peg_parser & p);
|
|
};
|
|
|
|
inline common_peg_arena build_chat_peg_parser(
|
|
const std::function<common_peg_parser(common_chat_peg_builder & builder)> & fn) {
|
|
common_chat_peg_builder builder;
|
|
builder.set_root(fn(builder));
|
|
return builder.build();
|
|
}
|
|
|
|
class common_chat_peg_mapper {
|
|
public:
|
|
common_chat_msg & result;
|
|
|
|
common_chat_peg_mapper(common_chat_msg & msg) : result(msg) {}
|
|
|
|
virtual ~common_chat_peg_mapper() = default;
|
|
|
|
virtual void from_ast(const common_peg_ast_arena & arena, const common_peg_parse_result & result);
|
|
virtual void map(const common_peg_ast_node & node);
|
|
};
|
|
|
|
struct content_structure;
|
|
struct tool_call_structure;
|
|
|
|
class common_chat_peg_unified_builder : public common_chat_peg_builder {
|
|
public:
|
|
// Tag constants
|
|
static constexpr const char * TOOL = "tool";
|
|
static constexpr const char * TOOL_OPEN = "tool-open";
|
|
static constexpr const char * TOOL_CLOSE = "tool-close";
|
|
static constexpr const char * TOOL_ID = "tool-id";
|
|
static constexpr const char * TOOL_NAME = "tool-name";
|
|
static constexpr const char * TOOL_ARGS = "tool-args";
|
|
static constexpr const char * TOOL_ARG = "tool-arg";
|
|
static constexpr const char * TOOL_ARG_OPEN = "tool-arg-open";
|
|
static constexpr const char * TOOL_ARG_CLOSE = "tool-arg-close";
|
|
static constexpr const char * TOOL_ARG_NAME = "tool-arg-name";
|
|
static constexpr const char * TOOL_ARG_VALUE = "tool-arg-value";
|
|
static constexpr const char * TOOL_ARG_STRING_VALUE = "tool-arg-string-value"; // For schema-declared string types
|
|
|
|
// Low-level tag methods
|
|
common_peg_parser tool(const common_peg_parser & p) { return tag(TOOL, p); }
|
|
common_peg_parser tool_open(const common_peg_parser & p) { return atomic(tag(TOOL_OPEN, p)); }
|
|
common_peg_parser tool_close(const common_peg_parser & p) { return atomic(tag(TOOL_CLOSE, p)); }
|
|
common_peg_parser tool_id(const common_peg_parser & p) { return atomic(tag(TOOL_ID, p)); }
|
|
common_peg_parser tool_name(const common_peg_parser & p) { return atomic(tag(TOOL_NAME, p)); }
|
|
common_peg_parser tool_args(const common_peg_parser & p) { return tag(TOOL_ARGS, p); }
|
|
common_peg_parser tool_arg(const common_peg_parser & p) { return tag(TOOL_ARG, p); }
|
|
common_peg_parser tool_arg_open(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_OPEN, p)); }
|
|
common_peg_parser tool_arg_close(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_CLOSE, p)); }
|
|
common_peg_parser tool_arg_name(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_NAME, p)); }
|
|
common_peg_parser tool_arg_value(const common_peg_parser & p) { return tag(TOOL_ARG_VALUE, p); }
|
|
|
|
// Use for schema-declared string types - won't be treated as potential JSON container
|
|
common_peg_parser tool_arg_string_value(const common_peg_parser & p) { return tag(TOOL_ARG_STRING_VALUE, p); }
|
|
common_peg_parser tool_arg_json_value(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_VALUE, p)); }
|
|
|
|
// Legacy-compatible helper for building standard JSON tool calls
|
|
// Used by tests and manual parsers
|
|
// name_key/args_key: JSON key names for function name and arguments
|
|
// Empty or "name"/"arguments" will accept both common variations
|
|
// Supports dot notation for nested objects (e.g., "function.name")
|
|
// array_wrapped: if true, tool calls are wrapped in JSON array [...]
|
|
// function_is_key: if true, function name is the JSON key (e.g., {"func_name": {...}})
|
|
// call_id_key: JSON key for string call ID (e.g., "id")
|
|
// gen_call_id_key: JSON key for generated integer call ID (e.g., "tool_call_id")
|
|
// parameters_order: order in which JSON fields should be parsed
|
|
common_peg_parser standard_json_tools(const std::string & section_start,
|
|
const std::string & section_end,
|
|
const nlohmann::json & tools,
|
|
bool parallel_tool_calls,
|
|
bool force_tool_calls,
|
|
const std::string & name_key = "",
|
|
const std::string & args_key = "",
|
|
bool array_wrapped = false,
|
|
bool function_is_key = false,
|
|
const std::string & call_id_key = "",
|
|
const std::string & gen_call_id_key = "",
|
|
const std::vector<std::string> & parameters_order = {});
|
|
|
|
// Legacy-compatible helper for building XML/tagged style tool calls
|
|
// Used by tests and manual parsers
|
|
common_peg_parser standard_constructed_tools(const std::map<std::string, std::string> & markers,
|
|
const nlohmann::json & tools,
|
|
bool parallel_tool_calls,
|
|
bool force_tool_calls);
|
|
};
|
|
|
|
inline common_peg_arena build_chat_peg_unified_parser(
|
|
const std::function<common_peg_parser(common_chat_peg_unified_builder & builder)> & fn) {
|
|
common_chat_peg_unified_builder builder;
|
|
builder.set_root(fn(builder));
|
|
return builder.build();
|
|
}
|
|
|
|
class common_chat_peg_unified_mapper : public common_chat_peg_mapper {
|
|
std::optional<common_chat_tool_call> pending_tool_call; // Tool call waiting for name
|
|
common_chat_tool_call * current_tool = nullptr;
|
|
int arg_count = 0;
|
|
bool needs_closing_quote = false;
|
|
std::string args_buffer; // Buffer to delay arguments until tool name is known
|
|
bool buffer_needs_closing_quote = false; // Track quote state for buffered args
|
|
|
|
public:
|
|
common_chat_peg_unified_mapper(common_chat_msg & msg) : common_chat_peg_mapper(msg) {}
|
|
|
|
void from_ast(const common_peg_ast_arena & arena, const common_peg_parse_result & parse_result_arg) override;
|
|
void map(const common_peg_ast_node & node) override;
|
|
};
|