discourse-ai/lib/completions/tool_call.rb

42 lines
965 B
Ruby
Raw Normal View History

# frozen_string_literal: true
module DiscourseAi
module Completions
class ToolCall
attr_reader :id, :name, :parameters
attr_accessor :partial
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
def partial?
!!@partial
end
def initialize(id:, name:, parameters: nil)
@id = id
@name = name
self.parameters = parameters if parameters
@parameters ||= {}
@partial = false
end
def parameters=(parameters)
raise ArgumentError, "parameters must be a hash" unless parameters.is_a?(Hash)
@parameters = parameters.symbolize_keys
end
def ==(other)
id == other.id && name == other.name && parameters == other.parameters
end
def to_s
"#{name} - #{id} (\n#{parameters.map(&:to_s).join("\n")}\n)"
end
def dup
call = ToolCall.new(id: id, name: name, parameters: parameters.deep_dup)
call.partial = partial
call
end
end
end
end