mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-24 00:19:19 +00:00
Tool calls support from mainline (#723)
* Tool calls support from mainline * update cmake * revert api for /completions * Fix broken thinking process for gpt-oss * add missing args and fix webui bugs * add missing args and fix webui bugs2 * Fix reasoning format error * add usage * change default post_sampling_probs to true * add back generated_text * Remove server endpoints tests * add log * Chat fixes * Remove logs * webui: revert extra handling of thinking process --------- Co-authored-by: firecoperana <firecoperana> Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
firecoperana
@@ -1,14 +1,18 @@
|
||||
// Chat parser with builder pattern for incremental parsing
|
||||
#pragma once
|
||||
|
||||
#include "chat.h"
|
||||
#include "json-partial.h"
|
||||
#include "json.hpp"
|
||||
#include "regex-partial.h"
|
||||
|
||||
#include <optional>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
using json = nlohmann::ordered_json;
|
||||
class common_chat_msg_partial_exception : public std::runtime_error {
|
||||
public:
|
||||
common_chat_msg_partial_exception(const std::string & message) : std::runtime_error(message) {}
|
||||
};
|
||||
|
||||
class common_chat_msg_parser {
|
||||
std::string input_;
|
||||
@@ -20,14 +24,7 @@ class common_chat_msg_parser {
|
||||
common_chat_msg result_;
|
||||
|
||||
public:
|
||||
struct find_regex_result {
|
||||
std::string prelude;
|
||||
std::vector<common_string_range> groups;
|
||||
};
|
||||
|
||||
common_chat_msg_parser(const std::string & input, bool is_partial, const common_chat_syntax & syntax);
|
||||
|
||||
// Accessors
|
||||
const std::string & input() const { return input_; }
|
||||
size_t pos() const { return pos_; }
|
||||
const std::string & healing_marker() const { return healing_marker_; }
|
||||
@@ -35,14 +32,12 @@ class common_chat_msg_parser {
|
||||
const common_chat_msg & result() const { return result_; }
|
||||
const common_chat_syntax & syntax() const { return syntax_; }
|
||||
|
||||
// Position manipulation
|
||||
void move_to(size_t pos) {
|
||||
if (pos > input_.size()) {
|
||||
throw std::runtime_error("Invalid position!");
|
||||
}
|
||||
pos_ = pos;
|
||||
}
|
||||
|
||||
void move_back(size_t n) {
|
||||
if (pos_ < n) {
|
||||
throw std::runtime_error("Can't move back that far!");
|
||||
@@ -53,84 +48,72 @@ class common_chat_msg_parser {
|
||||
// Get the substring of the input at the given range
|
||||
std::string str(const common_string_range & rng) const;
|
||||
|
||||
// Content manipulation
|
||||
// Appends to the result.content field
|
||||
void add_content(const std::string & content);
|
||||
|
||||
// Appends to the result.reasoning_content field
|
||||
void add_reasoning_content(const std::string & reasoning_content);
|
||||
|
||||
// Tool call manipulation
|
||||
void add_tool_call(const common_chat_tool_call & tool_call);
|
||||
// Adds a tool call to the result. If the tool call is too incomplete (e.g. name empty), it won't add anything.
|
||||
bool add_tool_call(const std::string & name, const std::string & id, const std::string & arguments);
|
||||
bool add_tool_call(const json & tool_call);
|
||||
bool add_tool_calls(const json & arr);
|
||||
void clear_tools();
|
||||
|
||||
// Parsing utilities
|
||||
std::string consume_rest();
|
||||
bool try_consume_literal(const std::string & literal);
|
||||
void consume_literal(const std::string & literal);
|
||||
bool try_parse_reasoning(const std::string & start_think, const std::string & end_think);
|
||||
// Adds a tool call using the "name", "id" and "arguments" fields of the json object
|
||||
bool add_tool_call(const nlohmann::ordered_json & tool_call);
|
||||
|
||||
// Regex-based parsing methods (new)
|
||||
std::optional<find_regex_result> try_find_regex(const common_regex & regex, size_t from = std::string::npos, bool add_prelude_to_content = true);
|
||||
find_regex_result consume_regex(const common_regex & regex);
|
||||
std::optional<find_regex_result> try_consume_regex(const common_regex & regex);
|
||||
// Adds an array of tool calls using their "name", "id" and "arguments" fields.
|
||||
bool add_tool_calls(const nlohmann::ordered_json & arr);
|
||||
|
||||
// Progressive parsing primitives (for Phase 4)
|
||||
std::optional<find_regex_result> try_find_literal(const std::string & literal);
|
||||
bool consume_spaces();
|
||||
void set_healing_marker(const std::string & marker);
|
||||
|
||||
|
||||
// Main parsing entry point
|
||||
void parse();
|
||||
|
||||
// Finishing
|
||||
void finish();
|
||||
|
||||
// Result extraction
|
||||
common_chat_msg result_and_reset();
|
||||
bool consume_spaces();
|
||||
|
||||
// Advanced JSON parsing (following original llama.cpp patterns)
|
||||
struct consume_json_result {
|
||||
json value;
|
||||
bool is_partial;
|
||||
void consume_literal(const std::string & literal);
|
||||
|
||||
bool try_parse_reasoning(const std::string & start_think, const std::string & end_think);
|
||||
|
||||
std::string consume_rest();
|
||||
|
||||
struct find_regex_result {
|
||||
std::string prelude;
|
||||
std::vector<common_string_range> groups;
|
||||
};
|
||||
|
||||
std::optional<find_regex_result> try_find_regex(const common_regex & regex, size_t from = std::string::npos, bool add_prelude_to_content = true);
|
||||
|
||||
bool try_consume_literal(const std::string & literal);
|
||||
|
||||
std::optional<find_regex_result> try_find_literal(const std::string & literal);
|
||||
|
||||
find_regex_result consume_regex(const common_regex & regex);
|
||||
|
||||
std::optional<find_regex_result> try_consume_regex(const common_regex & regex);
|
||||
|
||||
std::optional<common_json> try_consume_json();
|
||||
common_json consume_json();
|
||||
consume_json_result consume_json_with_dumped_args(
|
||||
const std::vector<std::vector<std::string>>& args_paths = {},
|
||||
const std::vector<std::vector<std::string>>& content_paths = {}
|
||||
);
|
||||
std::optional<consume_json_result> try_consume_json_with_dumped_args(
|
||||
const std::vector<std::vector<std::string>>& args_paths = {},
|
||||
const std::vector<std::vector<std::string>>& content_paths = {}
|
||||
);
|
||||
|
||||
private:
|
||||
// Internal parsing helpers
|
||||
void parse_kimi_k2_format();
|
||||
void parse_deepseek_r1_format();
|
||||
void parse_generic_format();
|
||||
|
||||
|
||||
// JSON parsing utilities (enhanced streaming support)
|
||||
struct json_parse_result {
|
||||
json value;
|
||||
bool success;
|
||||
struct consume_json_result {
|
||||
nlohmann::ordered_json value;
|
||||
bool is_partial;
|
||||
std::string healing_marker;
|
||||
};
|
||||
|
||||
// Partial detection utilities
|
||||
bool detect_partial_function_call(const std::string& content);
|
||||
void handle_partial_detection();
|
||||
/*
|
||||
Consume (possibly partial) json and converts specific subtrees to (possibly truncated) JSON strings.
|
||||
|
||||
// Legacy find_literal for compatibility
|
||||
std::optional<find_regex_result> try_find_literal_legacy(const std::string & literal);
|
||||
By default, object keys can't be truncated, nor can string values (their corresponding key is removed,
|
||||
e.g. `{"foo": "bar", "baz": "b` -> `{"foo": "bar"}`
|
||||
|
||||
But one can allow subpaths to be kept truncated, and possibly json-dumped to truncated json strings
|
||||
- with `content_paths={{"foo"}}` -> `{"foo": "b` -> {"foo": "b"}`
|
||||
- with `args_paths={{"foo"}}` -> `{"foo": {"b` -> `{"foo": "{b"}`
|
||||
*/
|
||||
consume_json_result consume_json_with_dumped_args(
|
||||
const std::vector<std::vector<std::string>> & args_paths = {},
|
||||
const std::vector<std::vector<std::string>> & content_paths = {}
|
||||
);
|
||||
std::optional<consume_json_result> try_consume_json_with_dumped_args(
|
||||
const std::vector<std::vector<std::string>> & args_paths = {},
|
||||
const std::vector<std::vector<std::string>> & content_paths = {}
|
||||
);
|
||||
|
||||
void clear_tools();
|
||||
};
|
||||
|
||||
// Main parsing function (public API)
|
||||
common_chat_msg common_chat_parse(const std::string & input, bool is_partial, const common_chat_syntax & syntax);
|
||||
|
||||
// Content-only parsing for fallback scenarios (static internal function)
|
||||
|
||||
Reference in New Issue
Block a user