Create ActiveAgent ActivePrompt Rails Engine for Context Management and Web App Interaction #2
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Review the reasonable reasons branch and consider the intention of having solid agent manage context through messages and fragments (series of messages).
Using this let’s create and ActiveAgent ActivePrompt Rails engine that can handle versioning agents based on their configs, application, and runtime params including model, api, version, instructions, or other agent options like tools or services (CLI/MCP)
Let’s use this active prompt rails engine as an interface forked off of tonsoffun/writebook, but using tonsoffun/fizzy for the latest lexical compatible text editor lexxy
We will demonstrate an agent that can take a simple one liner instructions and using playwright CLI and MCP to interact with web apps and stop to wait for user interaction when stuck on things like authentication workflows (users will get you logged in) be sure the agent uses fragments to cache their progress to allow users to come back to a browser session where the agent left off.
Superconductor Ticket Implementation