Files
llama.cpp/common/chat-parser.h
Olivier Chafik f5cd27b71d server: streaming of tool calls and thoughts when --jinja is on (#12379)
* add common_json w/ support for truncated json healing

* add common_chat_msg_diff

* partial common_chat_parse

* refactor parser w/ optionals

* server: wire chat diffs in stream mode

* fix trigger of thinking models (must happen after thoughts are closed)

* fix functionary v3.2 raw python!

* rename: common_chat_syntax (now contains format)

* rm common_regex.at_start

* don't return empty <think></think>

* accommodate yet another deepseek r1 distill fantasy syntax (`<|tool▁calls|>`)

* fix QwQ 32B tool call parsing after thoughts (hermes2)

* better logs for grammar triggers

* consume spaces after parse_json_tool_calls

* fix required tool calls w/ thinking models that have pre-opened thinking tags

* fix thinking model's initial trigger + test qwq's template

* run most test_tool_call tests in stream + non-stream modes

* make functionary v3.2 parsing more strict (differentiate first match from others)

* send final diff from server, to close off raw python arguments

* support partial content streaming in Generic mode

* tool-call: allow content prelude before hermes2 tool calls (for Qwen2.5)

* Update function-calling.md

* Update tool_bench.py

* chat-parser: remove input from exception (llm output may contain PII)

---------

Co-authored-by: ochafik <ochafik@google.com>
Co-authored-by: Olivier Chafik <ochafik@users.noreply.github.com>
2025-05-25 01:48:08 +01:00

117 lines
4.0 KiB
C++

#pragma once
#include "chat.h"
#include "json-partial.h"
#include "json.hpp"
#include "regex-partial.h"
#include <optional>
#include <string>
#include <vector>
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_;
bool is_partial_;
common_chat_syntax syntax_;
std::string healing_marker_;
size_t pos_ = 0;
common_chat_msg result_;
public:
common_chat_msg_parser(const std::string & input, bool is_partial, const common_chat_syntax & syntax);
const std::string & input() const { return input_; }
size_t pos() const { return pos_; }
const std::string & healing_marker() const { return healing_marker_; }
const bool & is_partial() const { return is_partial_; }
const common_chat_msg & result() const { return result_; }
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!");
}
pos_ -= n;
}
// Get the substring of the input at the given range
std::string str(const common_string_range & rng) const;
// 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);
// 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);
// 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);
// Adds an array of tool calls using their "name", "id" and "arguments" fields.
bool add_tool_calls(const nlohmann::ordered_json & arr);
void finish();
bool consume_spaces();
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 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();
struct consume_json_result {
nlohmann::ordered_json value;
bool is_partial;
};
/*
Consume (possibly partial) json and converts specific subtrees to (possibly truncated) JSON strings.
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 = {}
);
};