184 lines
5.3 KiB
Ruby
Raw Normal View History

DEV: artifact system update (#1096) ### Why This pull request fundamentally restructures how AI bots create and update web artifacts to address critical limitations in the previous approach: 1. **Improved Artifact Context for LLMs**: Previously, artifact creation and update tools included the *entire* artifact source code directly in the tool arguments. This overloaded the Language Model (LLM) with raw code, making it difficult for the LLM to maintain a clear understanding of the artifact's current state when applying changes. The LLM would struggle to differentiate between the base artifact and the requested modifications, leading to confusion and less effective updates. 2. **Reduced Token Usage and History Bloat**: Including the full artifact source code in every tool interaction was extremely token-inefficient. As conversations progressed, this redundant code in the history consumed a significant number of tokens unnecessarily. This not only increased costs but also diluted the context for the LLM with less relevant historical information. 3. **Enabling Updates for Large Artifacts**: The lack of a practical diff or targeted update mechanism made it nearly impossible to efficiently update larger web artifacts. Sending the entire source code for every minor change was both computationally expensive and prone to errors, effectively blocking the use of AI bots for meaningful modifications of complex artifacts. **This pull request addresses these core issues by**: * Introducing methods for the AI bot to explicitly *read* and understand the current state of an artifact. * Implementing efficient update strategies that send *targeted* changes rather than the entire artifact source code. * Providing options to control the level of artifact context included in LLM prompts, optimizing token usage. ### What The main changes implemented in this PR to resolve the above issues are: 1. **`Read Artifact` Tool for Contextual Awareness**: - A new `read_artifact` tool is introduced, enabling AI bots to fetch and process the current content of a web artifact from a given URL (local or external). - This provides the LLM with a clear and up-to-date representation of the artifact's HTML, CSS, and JavaScript, improving its understanding of the base to be modified. - By cloning local artifacts, it allows the bot to work with a fresh copy, further enhancing context and control. 2. **Refactored `Update Artifact` Tool with Efficient Strategies**: - The `update_artifact` tool is redesigned to employ more efficient update strategies, minimizing token usage and improving update precision: - **`diff` strategy**: Utilizes a search-and-replace diff algorithm to apply only the necessary, targeted changes to the artifact's code. This significantly reduces the amount of code sent to the LLM and focuses its attention on the specific modifications. - **`full` strategy**: Provides the option to replace the entire content sections (HTML, CSS, JavaScript) when a complete rewrite is required. - Tool options enhance the control over the update process: - `editor_llm`: Allows selection of a specific LLM for artifact updates, potentially optimizing for code editing tasks. - `update_algorithm`: Enables choosing between `diff` and `full` update strategies based on the nature of the required changes. - `do_not_echo_artifact`: Defaults to true, and by *not* echoing the artifact in prompts, it further reduces token consumption in scenarios where the LLM might not need the full artifact context for every update step (though effectiveness might be slightly reduced in certain update scenarios). 3. **System and General Persona Tool Option Visibility and Customization**: - Tool options, including those for system personas, are made visible and editable in the admin UI. This allows administrators to fine-tune the behavior of all personas and their tools, including setting specific LLMs or update algorithms. This was previously limited or hidden for system personas. 4. **Centralized and Improved Content Security Policy (CSP) Management**: - The CSP for AI artifacts is consolidated and made more maintainable through the `ALLOWED_CDN_SOURCES` constant. This improves code organization and future updates to the allowed CDN list, while maintaining the existing security posture. 5. **Codebase Improvements**: - Refactoring of diff utilities, introduction of strategy classes, enhanced error handling, new locales, and comprehensive testing all contribute to a more robust, efficient, and maintainable artifact management system. By addressing the issues of LLM context confusion, token inefficiency, and the limitations of updating large artifacts, this pull request significantly improves the practicality and effectiveness of AI bots in managing web artifacts within Discourse.
2025-02-04 16:27:27 +11:00
# frozen_string_literal: true
module DiscourseAi
module AiBot
module ArtifactUpdateStrategies
class Diff < Base
private
def build_prompt
DiscourseAi::Completions::Prompt.new(
system_prompt,
messages: [{ type: :user, content: user_prompt }],
post_id: post.id,
topic_id: post.topic_id,
)
end
def parse_changes(response)
sections = { html: nil, css: nil, javascript: nil }
current_section = nil
lines = []
response.each_line do |line|
case line
when /^\[(HTML|CSS|JavaScript)\]$/
sections[current_section] = lines.join if current_section && !lines.empty?
current_section = line.match(/^\[(.+)\]$/)[1].downcase.to_sym
lines = []
when %r{^\[/(?:HTML|CSS|JavaScript)\]$}
sections[current_section] = lines.join if current_section && !lines.empty?
current_section = nil
else
lines << line if current_section
end
end
sections.each do |section, content|
sections[section] = extract_search_replace_blocks(content)
end
sections
end
def apply_changes(changes)
source = artifact_version || artifact
updated_content = { js: source.js, html: source.html, css: source.css }
%i[html css javascript].each do |section|
blocks = changes[section]
next unless blocks
content = source.public_send(section == :javascript ? :js : section)
blocks.each do |block|
begin
content =
DiscourseAi::Utils::DiffUtils::SimpleDiff.apply(
content,
block[:search],
block[:replace],
)
rescue DiscourseAi::Utils::DiffUtils::SimpleDiff::NoMatchError
# TODO, we may need to inform caller here, LLM made a mistake which it
# should correct
end
end
updated_content[section == :javascript ? :js : section] = content
end
artifact.create_new_version(
html: updated_content[:html],
css: updated_content[:css],
js: updated_content[:js],
change_description: instructions,
)
end
private
def extract_search_replace_blocks(content)
return nil if content.blank?
blocks = []
remaining = content
pattern = /<<+\s*SEARCH\s*\n(.*?)\n=+\s*\n(.*?)\n>>+\s*REPLACE/m
while remaining =~ pattern
blocks << { search: $1.strip, replace: $2.strip }
remaining = $'
end
blocks.empty? ? nil : blocks
end
def system_prompt
<<~PROMPT
You are a web development expert generating precise search/replace changes for updating HTML, CSS, and JavaScript code.
Important rules:
1. Use EXACTLY this format for changes:
<<<<<<< SEARCH
(exact code to find)
=======
(replacement code)
>>>>>>> REPLACE
2. DO NOT modify the markers or add spaces around them
3. DO NOT add explanations or comments within sections
4. ONLY include [HTML], [CSS], and [JavaScript] sections if they have changes
5. Ensure search text matches EXACTLY - partial matches will fail
6. Keep changes minimal and focused
7. HTML should not include <html>, <head>, or <body> tags, it is injected into a template
JavaScript libraries must be sourced from the following CDNs, otherwise CSP will reject it:
#{AiArtifact::ALLOWED_CDN_SOURCES.join("\n")}
Reply Format:
[HTML]
(changes or empty if no changes)
[/HTML]
[CSS]
(changes or empty if no changes)
[/CSS]
[JavaScript]
(changes or empty if no changes)
[/JavaScript]
Example - Multiple changes in one file:
[JavaScript]
<<<<<<< SEARCH
console.log('old1');
=======
console.log('new1');
>>>>>>> REPLACE
<<<<<<< SEARCH
console.log('old2');
=======
console.log('new2');
>>>>>>> REPLACE
[/JavaScript]
Example - CSS with multiple blocks:
[CSS]
<<<<<<< SEARCH
.button { color: blue; }
=======
.button { color: red; }
>>>>>>> REPLACE
<<<<<<< SEARCH
.text { font-size: 12px; }
=======
.text { font-size: 16px; }
>>>>>>> REPLACE
[/CSS]
PROMPT
end
def user_prompt
source = artifact_version || artifact
<<~CONTENT
Artifact code:
[HTML]
#{source.html}
[/HTML]
[CSS]
#{source.css}
[/CSS]
[JavaScript]
#{source.js}
[/JavaScript]
Instructions:
#{instructions}
CONTENT
end
end
end
end
end