local-llm-rn 1.0.0

package/cpp/common/chat-parser.h

@@ -0,0 +1,133 @@
+#pragma once
+
+#include "chat.h"
+#include "chat-parser-xml-toolcall.h"
+#include "json-partial.h"
+#include "regex-partial.h"
+
+#include <nlohmann/json_fwd.hpp>
+
+#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_parser_params syntax_; // TODO: rename to params
+    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_parser_params & 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_; }
+    const common_chat_parser_params & syntax() const { return syntax_; }
+
+    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);
+
+    // Adds a tool call using the short form: { "tool_name": { "arg1": val, "arg2": val } }
+    bool add_tool_call_short_form(const nlohmann::ordered_json & tool_call);
+
+    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 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();
+
+    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 = {}
+    );
+
+    /**
+     * Parse XML-Style tool call for given xml_tool_call_format. Return false for invalid syntax and get the position untouched.
+     * form.scope_start, form.tool_sep and form.scope_end can be empty.
+     */
+    bool try_consume_xml_tool_calls(const struct xml_tool_call_format & form);
+
+    // Parse content uses reasoning and XML-Style tool call
+    void consume_reasoning_with_xml_tool_calls(const struct xml_tool_call_format & form, const std::string & start_think = "<think>", const std::string & end_think = "</think>");
+
+    void clear_tools();
+};

package/cpp/common/chat-peg-parser.cpp

@@ -0,0 +1,124 @@
+#include "chat-peg-parser.h"
+
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+
+static std::string_view trim_trailing_space(std::string_view sv, int max = -1) {
+    int count = 0;
+    while (!sv.empty() && std::isspace(static_cast<unsigned char>(sv.back()))) {
+        if (max != -1 && count <= max) {
+            break;
+        }
+        sv.remove_suffix(1);
+        count++;
+    }
+    return sv;
+}
+
+void common_chat_peg_mapper::from_ast(const common_peg_ast_arena & arena, const common_peg_parse_result & result) {
+    arena.visit(result, [this](const common_peg_ast_node & node) {
+        map(node);
+    });
+}
+
+void common_chat_peg_mapper::map(const common_peg_ast_node & node) {
+    bool is_reasoning = node.tag == common_chat_peg_builder::REASONING;
+    bool is_content = node.tag == common_chat_peg_builder::CONTENT;
+
+    if (is_reasoning) {
+        result.reasoning_content = std::string(trim_trailing_space(node.text));
+    }
+
+    if (is_content) {
+        result.content = std::string(trim_trailing_space(node.text));
+    }
+}
+
+void common_chat_peg_native_mapper::map(const common_peg_ast_node & node) {
+    common_chat_peg_mapper::map(node);
+
+    bool is_tool_open = node.tag == common_chat_peg_native_builder::TOOL_OPEN;
+    bool is_tool_name = node.tag == common_chat_peg_native_builder::TOOL_NAME;
+    bool is_tool_id = node.tag == common_chat_peg_native_builder::TOOL_ID;
+    bool is_tool_args = node.tag == common_chat_peg_native_builder::TOOL_ARGS;
+
+    if (is_tool_open) {
+        result.tool_calls.emplace_back();
+        current_tool = &result.tool_calls.back();
+    }
+
+    if (is_tool_id && current_tool) {
+        current_tool->id = std::string(trim_trailing_space(node.text));
+    }
+
+    if (is_tool_name && current_tool) {
+        current_tool->name = std::string(trim_trailing_space(node.text));
+    }
+
+    if (is_tool_args && current_tool) {
+        current_tool->arguments = std::string(trim_trailing_space(node.text));
+    }
+}
+
+void common_chat_peg_constructed_mapper::map(const common_peg_ast_node & node) {
+    common_chat_peg_mapper::map(node);
+
+    bool is_tool_open = node.tag == common_chat_peg_constructed_builder::TOOL_OPEN;
+    bool is_tool_name = node.tag == common_chat_peg_constructed_builder::TOOL_NAME;
+    bool is_tool_close = node.tag == common_chat_peg_constructed_builder::TOOL_CLOSE;
+    bool is_arg_open = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_OPEN;
+    bool is_arg_close = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_CLOSE;
+    bool is_arg_name = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_NAME;
+    bool is_arg_string = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_STRING_VALUE;
+    bool is_arg_json = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_JSON_VALUE;
+
+    if (is_tool_open) {
+        result.tool_calls.emplace_back();
+        current_tool = &result.tool_calls.back();
+        arg_count = 0;
+    }
+
+    if (is_tool_name) {
+        current_tool->name = std::string(node.text);
+        current_tool->arguments = "{";
+    }
+
+    if (is_arg_open) {
+        needs_closing_quote = false;
+    }
+
+    if (is_arg_name && current_tool) {
+        if (arg_count > 0) {
+            current_tool->arguments += ",";
+        }
+        current_tool->arguments += json(trim_trailing_space(node.text)).dump() + ":";
+        ++arg_count;
+    }
+
+    if (is_arg_string && current_tool) {
+        // Serialize to JSON, but exclude the end quote
+        std::string dumped = json(trim_trailing_space(node.text)).dump();
+        current_tool->arguments += dumped.substr(0, dumped.size() - 1);
+        needs_closing_quote = true;
+    }
+
+    if (is_arg_close && current_tool) {
+        if (needs_closing_quote) {
+            current_tool->arguments += "\"";
+            needs_closing_quote = false;
+        }
+    }
+
+    if (is_arg_json && current_tool) {
+        current_tool->arguments += std::string(trim_trailing_space(node.text));
+    }
+
+    if (is_tool_close && current_tool) {
+        if (needs_closing_quote) {
+            current_tool->arguments += "\"";
+            needs_closing_quote = false;
+        }
+        current_tool->arguments += "}";
+    }
+}

package/cpp/common/chat-peg-parser.h

@@ -0,0 +1,105 @@
+#pragma once
+
+#include "chat.h"
+#include "peg-parser.h"
+
+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); }
+};
+
+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 void from_ast(const common_peg_ast_arena & arena, const common_peg_parse_result & result);
+    virtual void map(const common_peg_ast_node & node);
+};
+
+class common_chat_peg_native_builder : public common_chat_peg_builder {
+  public:
+    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";
+
+    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); }
+};
+
+class common_chat_peg_native_mapper : public common_chat_peg_mapper {
+    common_chat_tool_call * current_tool;
+
+  public:
+    common_chat_peg_native_mapper(common_chat_msg & msg) : common_chat_peg_mapper(msg) {}
+
+    void map(const common_peg_ast_node & node) override;
+};
+
+inline common_peg_arena build_chat_peg_native_parser(const std::function<common_peg_parser(common_chat_peg_native_builder & builder)> & fn) {
+    common_chat_peg_native_builder builder;
+    builder.set_root(fn(builder));
+    return builder.build();
+}
+
+class common_chat_peg_constructed_builder : public common_chat_peg_builder {
+  public:
+    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_NAME = "tool-name";
+    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_STRING_VALUE = "tool-arg-string-value";
+    static constexpr const char * TOOL_ARG_JSON_VALUE = "tool-arg-json-value";
+
+    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_name(const common_peg_parser & p) { return atomic(tag(TOOL_NAME, 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_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 tag(TOOL_ARG_JSON_VALUE, p); }
+};
+
+class common_chat_peg_constructed_mapper : public common_chat_peg_mapper {
+    common_chat_tool_call * current_tool;
+    int arg_count = 0;
+    bool needs_closing_quote = false;
+
+  public:
+    common_chat_peg_constructed_mapper(common_chat_msg & msg) : common_chat_peg_mapper(msg) {}
+
+    void map(const common_peg_ast_node & node) override;
+};
+
+inline common_peg_arena build_chat_peg_constructed_parser(const std::function<common_peg_parser(common_chat_peg_constructed_builder & builder)> & fn) {
+    common_chat_peg_constructed_builder builder;
+    builder.set_root(fn(builder));
+    return builder.build();
+}