feat: Add interactive terminal (PTY) support w/ tests to cua-auto, computer-server, computer, and the cua CLI

.github/workflows/ci-check-docs-links.yml

@@ -61,10 +61,13 @@ jobs:
             --verbose
             --no-progress
             --accept 100..=399
-            --exclude '^file://'
+            --scheme https
+            --scheme http
             --exclude 'localhost'
             --exclude '127\.0\.0\.1'
             --exclude 'example\.com'
+            --exclude 'cua\.ai'
+            --exclude 'platform\.openai\.com'
             './docs/content/**/*.mdx'
           token: ${{ secrets.GITHUB_TOKEN }}
           fail: true

.github/workflows/ci-test-python.yml

@@ -22,6 +22,7 @@ jobs:
           - computer-server
           - mcp-server
           - som
+          - cua-auto
 
     steps:
       - name: Checkout code

README.md

@@ -166,7 +166,7 @@ lume run macos-sequoia-vanilla:latest
 
 | Package                                                               | Description                                                |
 | --------------------------------------------------------------------- | ---------------------------------------------------------- |
-| [cuabot](https://cua.ai/docs/cuabot/cuabot)                           | Multi-agent computer-use sandbox CLI                       |
+| [cuabot](https://docs.trycua.com/cuabot/guide/getting-started/introduction) | Multi-agent computer-use sandbox CLI                  |
 | [cua-agent](https://cua.ai/docs/cua/reference/agent-sdk)              | AI agent framework for computer-use tasks                  |
 | [cua-computer](https://cua.ai/docs/cua/reference/computer-sdk)        | SDK for controlling desktop environments                   |
 | [cua-computer-server](https://cua.ai/docs/cua/reference/computer-sdk) | Driver for UI interactions and code execution in sandboxes |

blog/clawcon-multiplayer.md

@@ -4,7 +4,7 @@ _Published on February 6, 2026 by Francesco Bonacci and Dillon DuPont_
 
 ClawCon brought over 700 attendees to Frontier Tower, with a waitlist that had people lining up down Market Street, and another 20k tuned into the livestream. It was the first community event for OpenClaw, and we had the 2nd demo session.
 
-We're early OpenClaw contributors and sponsors (we documented [how to deploy OpenClaw to macOS sandboxes with Lume](https://docs.trycua.com/lume/guides/openclaw)), and we genuinely believe computer-use works best as a tool inside more general agentic systems like OpenClaw rather than as standalone screen-takeover agents.
+We're early OpenClaw contributors and sponsors (we documented [how to deploy OpenClaw to macOS sandboxes with Lume](https://docs.trycua.com/lume/examples/openclaw)), and we genuinely believe computer-use works best as a tool inside more general agentic systems like OpenClaw rather than as standalone screen-takeover agents.
 
 So we deferred our Hacker News launch to ship something big live on stage.
 

docs/content/docs/cua/guide/advanced/interactive-shell.mdx

@@ -0,0 +1,77 @@
+---
+title: Interactive Shell
+description: Open a live PTY session inside a sandbox or local machine from the CLI or Python SDK
+---
+
+The `cua do shell` command and `computer.pty` API give you an interactive terminal (PTY) session inside any sandbox or local machine — similar to SSH, but without any network setup.
+
+## CLI
+
+```bash
+# Switch to a target first
+cua do switch docker my-container
+# or
+cua do switch host
+
+# Open an interactive shell (bash / PowerShell on host)
+cua do shell
+
+# Run a specific program interactively
+cua do shell python3
+cua do shell vim /etc/hosts
+
+# Override terminal dimensions
+cua do shell --cols 220 --rows 50
+```
+
+The shell is fully interactive — arrow keys, tab completion, and `Ctrl+C` all work. When stdin is piped (non-TTY), the command runs non-interactively and its output is printed normally.
+
+## Python SDK
+
+```python
+from computer import Computer
+
+async with Computer(provider_type="docker", name="my-container") as c:
+    handle = await c.pty.create(
+        command="bash",
+        cols=80,
+        rows=24,
+        on_data=lambda chunk: print(chunk.decode(errors="replace"), end="", flush=True),
+    )
+
+    await handle.send_stdin(b"echo hello\n")
+    await handle.send_stdin(b"exit\n")
+    code = await handle.wait()
+    print(f"exited {code}")
+```
+
+### PtyHandle methods
+
+| Method | Description |
+|---|---|
+| `send_stdin(data: bytes)` | Write bytes to the terminal's stdin |
+| `resize(cols, rows)` | Resize the terminal window |
+| `kill()` | Kill the session process |
+| `disconnect()` | Close the WebSocket without killing the process |
+| `wait()` | Block until the session exits; returns the exit code |
+
+### Reconnecting
+
+```python
+# Disconnect and reconnect later (process keeps running)
+await handle.disconnect()
+
+handle2 = await c.pty.connect(
+    handle.pid,
+    on_data=lambda chunk: print(chunk.decode(errors="replace"), end=""),
+)
+```
+
+## How it works
+
+The PTY stack has four layers:
+
+1. **`cua-auto`** — spawns a real PTY process (`pty` on Unix, `pywinpty` on Windows)
+2. **`computer-server`** — exposes `/pty` REST endpoints and a WebSocket for I/O
+3. **`computer`** — Python client (`PtyInterface`) connecting over HTTP + WebSocket
+4. **`cua do shell`** — sets your terminal to raw mode and proxies I/O through the WebSocket

docs/content/docs/cua/guide/advanced/meta.json

@@ -7,6 +7,7 @@
     "custom-tools",
     "sandboxed-python",
     "local-computer-server",
+    "interactive-shell",
     "human-in-the-loop",
     "vnc-recorder",
     "demonstration-guided-skills",