Skip to main content

Terminal Access

You can open an interactive terminal connected directly to the task's container. This lets you run commands, explore the filesystem, resume agents, and debug issues in real-time.

Web-Based Terminal​

Click the Terminal button in the task toolbar to open a terminal in a new browser tab. You're immediately connected to the running container and can execute commands.

The web-based terminal supports:

  • Full shell capabilities (bash)
  • Running commands and tools installed in the container
  • Interactive prompts and text input
  • Colors and text formatting
  • Standard input/output redirection

This is the quickest way to access the container—no local setup required.

Attaching from Your Own Terminal​

If you prefer using your local terminal application, click the dropdown arrow next to the Terminal button and select Copy Attach Command. This copies a coder CLI command to your clipboard.

Paste and run this command in your local terminal to attach directly to the container. This gives you:

  • Your preferred terminal emulator and configuration
  • Better keyboard shortcut support
  • Integration with local tools and shell customizations
  • Easier copy/paste workflows

The attach command connects to the same container as the web terminal—both access the identical environment.

Note: Terminal access is only available while the container is running. If the container stops, restart it to use the terminal again.

Working in the Container​

The container environment has a specific structure:

  • /workspace - The main working directory where repositories are cloned. This is where you'll spend most of your time. All repository code, configurations, and edits live here.
  • /task-output - Output directory containing task metadata, logs, and state information. This is managed by the system.

When you open a terminal, it starts in the /workspace directory by default. All code changes you make here (whether through file editing or terminal commands) are reflected in the Changed Files section after syncing.

Environment Setup​

The container includes:

  • Pre-installed AI agent runtimes (Claude Code, Codex, Gemini, Bob Shell, Grok Build, etc.)
  • Git configured for the workspace
  • Development tools (Node.js, Python, etc.)
  • SSH and other utilities for advanced workflows

Common Operations​

Run a Shell Command​

# Any bash command works as normal
ls -la
grep -r "search-term" .
npm install
python script.py

Resume an AI Agent​

The terminal dropdown menu provides quick shortcuts to resume agents:

# Resume Claude Code from the last session
claude resume

# Resume Codex from the last session
codex resume

# Start a new Claude Code session
claude exec

These commands automatically set up the necessary environment and load previous session state if available.

Apply a Patch Locally​

If you want to apply the current task's patch to a local repository on your machine, use the CLI (not in the terminal):

# From your local machine
coder apply <task-id> <filename>

This is useful if you prefer to review and integrate changes in your local development environment.

Explore the Workspace​

# See what repositories are available
ls /workspace

# View repository status
cd /workspace/<repo-name>
git status

# See recent commits
git log --oneline -10

Interact with the Agent​

When an agent is running, you can:

  • Inspect what it's doing with logs
  • Check intermediate results in /task-output
  • Modify files and re-run commands to guide the agent

All changes made in the terminal contribute to the final diff and appear in the Changed Files section.