discourse-ai/lib/completions/tool_call_progress_tracker.rb

50 lines
1.2 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
module DiscourseAi
module Completions
class ToolCallProgressTracker
attr_reader :current_key, :current_value, :tool_call
def initialize(tool_call)
@tool_call = tool_call
@current_key = nil
@current_value = nil
@parser = DiscourseAi::Completions::JsonStreamingParser.new
@parser.key do |k|
@current_key = k
@current_value = nil
end
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
@parser.value do |v|
if @current_key
tool_call.notify_progress(@current_key, v)
@current_key = nil
end
end
end
def <<(json)
# llm could send broken json
# in that case just deal with it later
# don't stream
return if @broken
begin
@parser << json
rescue DiscourseAi::Completions::ParserError
@broken = true
return
end
if @parser.state == :start_string && @current_key
# this is is worth notifying
tool_call.notify_progress(@current_key, @parser.buf)
end
@current_key = nil if @parser.state == :end_value
end
end
end
end