Improve interactive CLI and mission workflow#202
Conversation
- Refactor `src/cognitive/cli.py` to use an `InteractiveShell` class. - Implement split plan-then-execute flow with `Y/n` confirmation. - Add real-time step updates using an `on_step_update` callback. - Add `status`, `plan`, `artifacts`, and `view` commands to the shell. - Implement ANSI color-coding for better readability. - Enhance `MissionExecutorService` with planning and state retrieval methods. - Add unit tests for the new split workflow. - Improve EOF and interrupt handling in the shell. Co-authored-by: hackerxj2010 <198651211+hackerxj2010@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
1 participant
Enhanced the cognitive layer's Python CLI and mission execution service to provide a more interactive and transparent experience, similar to advanced AI coding assistants. Key improvements include a split planning and execution flow with manual confirmation, real-time step progress updates, and new interactive commands for inspecting mission state and artifacts.
PR created automatically by Jules for task 3226020955796232475 started by @hackerxj2010