webui: fix mobile UI displaying subconversations

Fix mobile UI incorrectly showing subconversations (messages with parent_conversation_id)
that should be hidden like in the regular UI to maintain consistent behavior across
all interfaces.

Problem Analysis:
The mobile UI was displaying all messages including subconversations, while the regular
desktop UI correctly filters out messages with hide_output=true. This created an
inconsistent user experience where subconversations (used for internal agent processing)
were visible in the mobile interface but hidden in the desktop interface.

Subconversations are marked with hide_output=true based on conversation.Hidden when
the message's conversation has a parent conversation. These are internal processing
messages that shouldn't be shown to users in either interface.

Implementation Changes:

1. Mobile Chat Filtering Enhancement:
   - Modified shouldShowMessage() method in mobile-chat.ts
   - Added hide_output check at start of filtering logic
   - Returns false immediately for any message with hide_output=true
   - Mirrors the filtering logic used in sketch-timeline.ts (.filter((msg) => !msg.hide_output))

2. Consistent Filtering Logic:
   - Mobile UI now matches regular UI filtering behavior
   - Preserves existing content and type filtering for visible messages
   - Maintains all other message display logic unchanged
   - Uses same pattern as desktop: early return false for hidden messages

Technical Details:
- hide_output field is set based on conversation.Hidden in AgentMessage.SetConvo()
- Subconversations have parent_conversation_id and are marked as hidden
- Regular UI filters with messages.filter((msg) => !msg.hide_output)
- Mobile UI now filters with if (message.hide_output) { return false; }
- No changes needed to aggregateAgentMessages as filtering happens at display level

Benefits:
- Consistent user experience across desktop and mobile interfaces
- Proper hiding of internal agent processing messages
- Clean mobile chat interface without subconversation clutter
- Maintains all existing mobile UI functionality for visible messages

Testing:
- TypeScript compilation passes without errors
- Filtering logic matches pattern used successfully in desktop UI
- Mobile chat component is only message rendering location in mobile UI
- Change isolated to display filtering without affecting message aggregation

This fix ensures mobile users see the same clean conversation view as desktop
users, with internal agent subconversations properly hidden from the interface.

Co-Authored-By: sketch <hello@sketch.dev>
Change-ID: s40a49bd924bde7e2k
1 file changed
tree: 3676987151352442281db156efe22f89249a47ab
  1. .github/
  2. .vscode/
  3. bin/
  4. browser/
  5. claudetool/
  6. cmd/
  7. dockerimg/
  8. experiment/
  9. git_tools/
  10. httprr/
  11. llm/
  12. loop/
  13. skabandclient/
  14. skribe/
  15. termui/
  16. test/
  17. webui/
  18. .clabot
  19. .dockerignore
  20. .gitignore
  21. CONTRIBUTING.md
  22. dear_llm.md
  23. go.mod
  24. go.sum
  25. LICENSE
  26. README.md
README.md

Sketch

Go Reference Discord GitHub Workflow Status License

Sketch is an agentic coding tool. It draws the 🦉

🚀 Overview

Sketch runs in your terminal, has a web UI, understands your code, and helps you get work done. To keep your environment pristine, sketch starts a docker container and outputs its work onto a branch in your host git repository.

Sketch helps with most programming environments, but Sketch has extra goodies for Go.

📋 Quick Start

go install sketch.dev/cmd/sketch@latest
sketch

🔧 Requirements

Currently, Sketch runs on macOS and Linux. It uses Docker for containers.

PlatformInstallation
macOSbrew install colima (or Docker Desktop/Orbstack)
Linuxapt install docker.io (or equivalent for your distro)
WSL2Install Docker Desktop for Windows (docker entirely inside WSL2 is tricky)

The sketch.dev service is used to provide access to an LLM service and give you a way to access the web UI from anywhere.

🤝 Community & Feedback

📖 User Guide

Getting Started

Start Sketch by running sketch in a Git repository. It will open your browser to the Sketch chat interface, but you can also use the CLI interface. Use -open=false if you want to use just the CLI interface.

Ask Sketch about your codebase or ask it to implement a feature. It may take a little while for Sketch to do its work, so hit the bell (🔔) icon to enable browser notifications. We won't spam you or anything; it will notify you when the Sketch agent's turn is done, and there's something to look at.

How Sketch Works

When you start Sketch, it:

  1. Creates a Dockerfile
  2. Builds it
  3. Copies your repository into it
  4. Starts a Docker container with the "inside" Sketch running

This design lets you run multiple sketches in parallel since they each have their own sandbox. It also lets Sketch work without worry: it can trash its own container, but it can't trash your machine.

Sketch's agentic loop uses tool calls (mostly shell commands, but also a handful of other important tools) to allow the LLM to interact with your codebase.

Getting Your Git Changes Out

Sketch is trained to make Git commits. When those happen, they are automatically pushed to the git repository where you started sketch with branch names sketch/*.

Finding Sketch branches:

git branch -a --sort=creatordate | grep sketch/ | tail

The UI keeps track of the latest branch it pushed and displays it prominently. You can use standard Git workflows to pull those branches into your workspace:

git cherry-pick $(git merge-base origin/main sketch/foo)

or merge the branch

git merge sketch/foo

or reset to the branch

git reset --hard sketch/foo

Ie use the same workflows you would if you were pulling in a friend's Pull Request.

Advanced: You can ask Sketch to git fetch sketch-host and rebase onto another commit. This will also fetch where you started Sketch, and we do a bit of "git fetch refspec configuration" to make origin/main work as a git reference.

Don't be afraid of asking Sketch to help you rebase, merge/squash commits, rewrite commit messages, and so forth; it's good at it!

Reviewing Diffs

The diff view shows you changes since Sketch started. Leaving comments on lines adds them to the chat box, and, when you hit Send (at the bottom of the page), Sketch goes to work addressing your comments.

Connecting to Sketch's Container

You can interact directly with the container in three ways:

  1. Web UI Terminal: Use the "Terminal" tab in the UI
  2. SSH: Look at the startup logs or click the information icon to see a command like ssh sketch-ilik-eske-tcha-lott. We have automatically configured your SSH configuration to make these special hostnames work.
  3. Visual Studio Code: Look for a command line or magic link behind the information icon, or when Sketch starts up. This starts a new VSCode session "remoted into" the container. You can edit the code, use the terminal, review diffs, and so forth.

Using SSH (and/or VSCode) allows you to forward ports from the container to your machine. For example, if you want to start your development webserver, you can do something like this:

# Forward container port 8888 to local port 8000
ssh -L8000:localhost:8888 sketch-ilik-epor-tfor-ward go run ./cmd/server

This makes http://localhost:8000/ on your machine point to localhost:8888 inside the container.

Using Browser Tools

You can ask Sketch to browse a web page and take screenshots. There are tools both for taking screenshots and "reading images", the latter of which sends the image to the LLM. This functionality is handy if you're working on a web page and want to see what the in-progress change looks like.

❓ FAQ

"No space left on device"

Docker images, containers, and so forth tend to pile up. Ask Docker to prune unused images and containers:

docker system prune -a

🛠️ Development

Go Reference

See CONTRIBUTING.md for development guidelines.

📄 Open Source

Sketch is open source. It is right here in this repository! Have a look around and mod away.

If you want to run Sketch entirely without the sketch.dev service, you can set the flag -skaband-addr="" and then provide an ANTHROPIC_API_KEY environment variable. (More LLM services coming soon!)