Files
openchamber/packages/docs/content/docs/agent-control-tool.mdx
T
Bohdan Triapitsyn a5aa32446d feat(browser): replace the preview proxy with a real browser panel and an agent web tool (#2883)
The preview panel worked by proxying a dev server through OpenChamber's own
origin and rewriting the HTML that came back. Anything the rewriter did not
anticipate broke, and pages that refuse to be embedded never loaded at all.
This deletes the proxy (-1604 lines and its tests) and merges the preview and
browser panels into one surface backed by a real Chromium view.

What the panel is now

- A `<webview>` in its own session partition: logins and cookies persist, hot
  reload works because nothing is rewritten, DevTools are one click away.
- Annotation: pick one element, drag a region, or draw freehand, write a note,
  and it reaches chat with a screenshot of the visible page with the marks on it.
- Toolbar: hard reload, page zoom, device sizes, a light/dark switch that
  applies to the page rather than the app, and cookie/cache clearing scoped to
  the panel alone.
- Several pages at once, each tab showing the page's own favicon, and an address
  bar that suggests pages already visited in this project.
- Dev servers are listed from what is actually listening on the machine, checked
  against what a project announced, so a server is offered no matter how it was
  started. One that is still starting is waited for instead of failing.

Remote dev servers

The desktop app binds a local port and pipes raw bytes to the OpenChamber host
over the existing authenticated connection, so the page keeps its own origin at
the root of its own host. The reachable set is exactly what discovery reports
and is re-checked per connection, so an authenticated client cannot dial
arbitrary local services on the host. Links and redirects to another loopback
port stay on the machine that served the page. A tunnel that cannot be opened is
reported; it is never replaced by the plain loopback URL, which would answer
from the user's own machine under a remote address.

Agent control

Browser actions are a separate `openchamber_web` tool: open, snapshot, click,
type, scroll, inspect computed styles, resize between mobile/tablet/desktop, and
capture a screenshot into `.openchamber/screenshots/` in the project. The
existing `openchamber` tool keeps sessions, worktrees and scheduled tasks. Each
has its own setting in the new Settings -> General -> OpenChamber Tools section,
and the plugin is not injected at all when both are off.

Capability belongs to the connected client, not to configuration: a client
declares on its event stream that it can drive a page, which only a Chromium
host does. Exactly one client performs each request — it claims the request
before acting, and the first claim wins — because deciding by whose result
arrives first would be too late for a click that already happened. No client
listening is answered immediately with an explanation rather than a timeout.

Runtime boundaries

Web tabs get a plain iframe that can display a page but not inspect one. The
VS Code extension no longer offers the surface at all, since nothing that makes
the panel worth having works there. Mobile is unaffected.

Native boundary

Camera, microphone, location and device-picker requests from panel pages are
denied — Electron grants them by default when no handler is set, and the panel
loads whatever address the user types. Page capture, appearance emulation and
storage clearing verify that their target belongs to the panel's own session
instead of trusting a web-contents id from the renderer.

Persisted state

Stored `preview` tabs migrate to `browser` (v13 -> v14). Context panel tab
limits are now per surface, so filling one surface no longer evicts another's
tabs. Address history is stored per project and per runtime.

Documentation

`preview.mdx` and `desktop-browser.mdx` rewritten across all locales, the agent
tool settings path corrected, new `DOCUMENTATION.md` for the browser-control
broker and the dev tunnel, and the `ui-api-decoupling` skill updated where it
still described the deleted proxy.
2026-08-13 22:44:13 +03:00

41 lines
2.5 KiB
Plaintext

---
title: Agent Control Tool
description: Let an agent manage OpenChamber sessions, worktrees, and scheduled tasks from chat.
---
# Agent Control Tool
Use the `openchamber` agent tool to manage work in the app directly from chat. It is enabled by default when OpenChamber runs its own local OpenCode server; there is no separate tool to install or shell command to run.
## What you can ask
Ask the agent in plain language. For example:
- "Create a new OpenChamber session in this project, use the `openai/gpt-5.6-sol` model, and send it this prompt: review the authentication flow."
- "Create a new OpenChamber session for this task in a separate worktree, and ask it to add tests for the login flow."
- "Use OpenChamber to list my 10 most recent sessions and include their current status."
- "Create an OpenChamber scheduled task named Weekday review that sends this prompt at 09:00 every weekday: review changes since the last run."
- "Run the OpenChamber scheduled task named Weekday review now."
- "Check the OpenChamber session named Authentication review and show me its latest assistant response."
The tool can list projects and model preferences, create and follow up on sessions, fork a session, create isolated worktree sessions, and manage scheduled tasks. Sessions started this way appear in OpenChamber like any other session, so you can open them and continue the work yourself.
## Keep in mind
- New session prompts return immediately by default. Follow the session in OpenChamber, or ask the agent to check it later.
- A separate worktree is only created when you ask for one. Uncommitted changes from your current worktree are not copied into it.
- The tool cannot delete sessions or worktrees, register project paths, run arbitrary shell commands, or call arbitrary URLs.
## Turn the tool on or off
Open **Settings → General → OpenChamber Tools** and change **Agent control tool**. The setting applies once the managed OpenCode server restarts, which OpenChamber offers as **Apply & Restart**.
The tool is not available when OpenChamber connects to an external OpenCode server through `OPENCODE_HOST` or skip-start, or inside the VS Code extension. Desktop and web installations that use OpenChamber's managed OpenCode server support it automatically.
## Related
- [Scheduled Tasks](/scheduled-tasks/)
- [Worktree Sessions](/worktrees/)
- [Session Goals](/session-goals/)
- [Browser Panel](/desktop-browser/) — the OpenChamber Web tool, for looking at and driving a page