DeskPilot

Author(s)

• Raimund Andree

Tags

Copilot GitHubCopilot ShellPilot Agent AI GUI AgenticOperatingModel Windows Linux macOS

Functions

Start-DeskPilot

PSEditions

Core

Dependencies

This module has no dependencies.

Release Notes

## [0.5.0-preview0020] - 2026-09-02

### Added

- **Questions you can tap through instead of typing at.** When the agent needs
 input it now asks **one question at a time**, with its choices as buttons: tap
 an answer and the next question arrives. A question that takes several answers
 toggles them on and off and finishes with **Done**; a question with no choices
 is still answered by replying. You can also still reply with a number — "2"
 picks the second choice, and "1,3" picks two.

 Before this, buttons appeared **only** when the agent happened to ask exactly
 one question, which almost never happened: DeskPilot tells the agent to bundle
 everything it needs into a single request, so a real set of questions arrived as
 a wall of numbered text you had to read and reply to — six questions in one
 message, on a phone. The two halves of DeskPilot had contradicted each other
 since the feature shipped.

 Every list of choices also ends with **Something else - type it**, for when none
 of them is what you mean. Your words reach the agent exactly as written, and the
 buttons keep working in case you change your mind.

- **Let Telegram groups reach Intercom, not just your own chat.** Adding the bot
 to a group used to be a dead end: every message from it was counted, rejected
 and thrown away, with only a line in the Status box to say why. **Settings ›
 Intercom** now has **Also accept messages from a Telegram group** and a box for
 the group ids — separate several with commas, up to ten — and DeskPilot accepts
 them alongside your own chat. It replies wherever it was asked: something sent
 in a group is acknowledged, questioned and reported in that group, while your
 private chat stays private and keeps the check-in status message.

 **This is off by default and needs two switches, because everyone in those
 groups gets exactly the control you have** — instructions, answers to the agent's
 questions, and work in any project you share with groups, including `git push`.
 Telegram decides who is in a group, so anyone added later inherits it. The
 consequence is stated where you turn it on, and repeated on every `/status`
 check-in. Turning a group back off drops anything it had queued or was being
 asked, rather than delivering it to a chat that is no longer trusted.

 **A group reaches only the projects you choose for it.** Each project now has a
 second tick, **also from a group chat**, next to **allow phone control** — and it
 is off even for projects your own phone already drives. Without it, allow-listing
 a group would have silently widened every project you had opted in when you were
 the only person who could reach them. If any project is already shared when you
 switch group access on, DeskPilot names them and asks you to confirm first.

 **`/undo` and `/delete` never work from a group**, whichever project is open.
 They rewrite files on disk and destroy a conversation for good, and they act on
 your own history rather than on the group's work, so they stay with you.
 `/archive` is still open to everyone, because `/unarchive` undoes it.

 The panel also tells you what Telegram will not: a bot in a group sees nothing
 but `/commands`, replies to itself and @mentions until **Group Privacy** is
 turned off in @BotFather and the bot is re-added — which looks exactly like
 DeskPilot ignoring you.

- **The Intercom log says who, not just what.** Every line in the **Status** box
 now names the chat a message came from and the sender Telegram reported, for
 accepted and rejected messages alike. With more than one chat able to reach
 DeskPilot, a log that records only the action cannot tell you afterwards who
 took it. The name is whatever Telegram says it is; DeskPilot does not verify it.

- **A full-screen file viewer.** The viewer opens at a comfortable reading width,
 but a wide table, a long diff or a large screenshot wants the whole window. The
 new ⛶ button in its header takes the viewer edge to edge — no border, no rounded
 corners, no margin — and back again. The choice is remembered, so once you have
 said you want files full screen, every file opens that way until you say
 otherwise. Escape and ✕ still close it.

- **Open a file with your own program.** A spreadsheet, a Word document, a PDF —
 DeskPilot cannot draw any of them, and until now clicking one in the file panel
 said so and stopped. Trying to open a file it can't show now asks whether to
 hand it to the program your computer already uses for that file type, with a
 **Always open .xlsx files this way** box on the question. Tick it and that type
 opens straight away from then on; leave it and DeskPilot asks again next time.
 Every file also has an **↗** button in the viewer, so a Markdown file or an
 image can be opened in your own editor whenever you want it there. The types
 you chose to keep are listed under **Settings › General**, each with a ✕ that
 makes DeskPilot ask again, plus **Forget all**.

 **A program or a script is never opened this way, and there is no way to allow
 one.** The agent writes into the same folder the file panel lists, so a
 `.exe`, `.bat`, `.ps1`, `.sh`, `.lnk` — or a `budget.xlsx.exe` — is refused
 outright rather than confirmed, and cannot be remembered either; opening it
 would be running it. Those files are still readable in DeskPilot's own viewer.
 Backed by a new `POST /api/fs/open`, confined to the selected Project exactly
 like the file tree, which chooses no program and passes no arguments of its
 own.

- **Image previews instead of "there is no text to compare."** A screenshot the
 agent saved, a logo you dropped into the Project, an icon that changed — the
 Diff viewer and the file viewer now *show the picture* for the formats a
 browser can draw (PNG, JPEG, GIF, WebP, BMP, ICO, AVIF), captioned with what
 happened to the file, on a checkerboard so a transparent image reads on either
 theme. Anything else still says plainly that it has no text to compare. There
 is no before-and-after for a picture: the preview is the file as it stands
 now.

 Backed by a new `GET /api/fs/image`, confined to the selected Project exactly
 like the file tree. It is the file's **own signature bytes** that decide the
 media type it is served under, never its extension, so a file named `.png`
 that is really a web page is refused rather than handed to the browser. SVG is
 deliberately not previewed — it is script-capable markup, and being text it
 is already readable as text. Every response now also carries
 `X-Content-Type-Options: nosniff`.

- **Automatic response retries.** A Turn no longer stops at the first transient
 Engine failure or successful-but-empty response before work has begun. The new
 **Response retries** Setting controls how many extra attempts DeskPilot makes
 after the first (`0–100`, default `2`), with each wait capped at five seconds;
 `0` turns the behavior off, and Stop remains responsive during the wait.
 Retries stop as soon as any answer or Tool Activity has appeared, so DeskPilot
 never repeats a command or write behind the user's back. The Setting also says
 plainly that failed attempts can still consume time and Copilot credits, and
 the final token and cost Usage includes every attempt the Engine recorded
 rather than only the successful one.

- **MCP servers.** DeskPilot can now attach Model Context Protocol servers, so
 the agent gains tools from programs you choose — an issue tracker, a database,
 a document store — beside its own. A new **MCP servers** tab in Settings takes
 either a command DeskPilot runs or the path to an `mcp.json` you already keep
 for another editor (both the VS Code `servers` and the Claude `mcpServers`
 shapes are read). Each server reports what it is actually doing: whether it is
 running, which protocol version it negotiated, and exactly which tools it
 contributes. Nothing is ever discovered on its own — a file that can start a
 program has to be named by you — and a server's tools appear in the Activity
 panel as they are called, marked apart from DeskPilot's own so you can always
 tell whose code just ran.

 Three deliberate limits, because an MCP server is somebody else's program
 running with your privileges. **Secrets are never stored:** a server that needs
 a token names the environment variable, and DeskPilot reads the value from its
 own environment when it starts the server, so a settings backup cannot leak a
 key. **Reach can be narrowed:** *Only offer these tools* attaches a server for
 the two tools you want and keeps the rest away from the agent entirely. And a
 new **MCP servers** permission withholds every attached server's tools for a
 job without stopping the servers — while the panel states plainly that the
 other permissions limit DeskPilot's own tools and do not limit an attached
 server, which can bring file and shell tools of its own.

 Requires ShellPilot 0.4.0-preview0007 or later; on an older engine the panel
 says so and everything else works as before.

- **You can now watch the agent work.** The Activity panel only ever appeared
 once a job had finished, as an unordered list of what it had touched — so while
 the agent was working, the window said nothing beyond a spinner unless *Show
 the model's thinking* was on, and the only files it named live were the ones it
 wrote. Every tool the agent uses now appears in the panel the moment it is used,
 in order: the files it reads and writes, the folders it lists, the commands it
 runs, the **pages it fetches**, the searches it makes. A run of the same kind of
 action folds into one line — *Read 6 files*, *Fetched 2 pages* — which is open
 while the job runs and closed when it ends, leaving the whole panel as a single
 line the reader can open again. The account is kept with the message, so it
 survives a reload, and a job that was stopped or ran out of its step budget now