Omniscio

Agent reply formatting and showing images

The formatting an agent can put in a reply — callouts, centred text, sized images, collapsible sections, keyboard key caps — and how an agent shows you any image file on your machine, including what happens when a picture cannot be displayed.

On this page

What it is

A reply from an agent is drawn as formatted text, not raw characters. Beyond ordinary markdown, an agent can use a fixed set of GitHub-style shapes that GitHub users already reach for, and it can put a picture in front of you — including one saved anywhere on your computer.

Where to find it

Turning it off

The whole thing has a switch (Settings → Features, "Agent Markdown Formatting"), on by default. With it off, every message is drawn exactly as it was before this existed — the shapes above appear as the plain characters the agent wrote.

How it behaves

The formatting an agent can use

Written as Drawn as
> [!NOTE] / [!TIP] / [!IMPORTANT] / [!WARNING] / [!CAUTION] A colour-coded block with its type name and an icon
<div align="center">…</div> Centred text
<div align="right">…</div> Right-aligned text
<img src="…" width="400"> The image at that width instead of full size
<details><summary>…</summary>…</details> A section you can open and close
<kbd>Ctrl+K</kbd> A keyboard key cap, drawn the same way the rest of the app draws shortcuts
<mark>…</mark> Highlighted text
<u>…</u> Underlined text
<sub>…</sub> / <sup>…</sup> Small print set below or above the line, never smaller than 12px
<br> / <br/> / </br> A line break, never the literal characters

Table columns also follow the alignment you specify in markdown — | :---: | centres a column and | ---: | right-aligns it.

A header of two or more words wraps onto even lines only when the column's data is narrower than the header — "Avg sessions" above "150.4" becomes two lines, and the column shrinks to fit the wrapped words, so no empty space is left beside them. Over wider data the header stays on one line. A very long header gets more lines rather than stretching the table, and a single word is never broken.

Only those shapes are honoured. Anything else an agent writes as HTML is shown as plain text, exactly as characters — a deliberate limit, so a reply can never inject markup into the app. Unrecognised callout types behave the same way: > [!SOMETHING] stays an ordinary quote rather than being guessed at.

When an agent writes an address in its reply, the app turns it into a link you can click:

  • a web address without https:// — business.facebook.com works as well as the full form
  • a dev-server address — localhost:5199
  • an Omniscio link to a session, note or share
  • a file path on this computer

The emphasis an agent puts around the address does not stop it: bold, italic and struck through addresses all still open. An address written inside a code block or in backticks stays plain text, because there it is a code sample meant to be read, not clicked.

Showing you a picture

An agent shows you an image by handing the app a file path and the conversation to show it in. The app copies the file in and gives the agent back a markdown line; when the agent writes that line into its reply, the picture appears.

  • Any image file on the machine works, from any folder — not just the project it is working in. PNG, JPEG, GIF, WebP, SVG, BMP and TIFF, up to 50 MB.
  • The picture is visible only in the conversation it was shown in.

What happens automatically

Separately from that, an agent that merely mentions an image path in its reply has the file picked up automatically — but only when it sits inside the project the agent is working in and was written during that same turn. That narrow rule exists on purpose: without it, narration like `icon.png` would silently attach whatever unrelated file happened to match. The explicit route above is the way to show anything outside that.

When a picture cannot be shown

You are told why, in place of the image — never left with a blank gap. You may see:

  • that the message pointed at a file on the computer, which a message cannot load
  • that the picture belongs to another conversation
  • that the message gave no address for it

A refusal from the explicit route says what was wrong and what to do about it — not an image format, no readable file at that path, a file over the size limit, or a conversation id that does not exist.

Worth knowing

  • The app's own bracketed markers never appear on screen. Tokens like [[OMNISCIO_FINAL]] are plumbing that tells the app where a message ends; they are removed before the message is drawn. That holds for one an agent invents, too — a made-up token is cleaned up rather than shown. To genuinely display a token like that, put it inside a code block or backticks, and it is left exactly as written.
  • Stray tool-call markup is hidden too. A model sometimes writes part of its own tool-calling machinery into its answer — a lone closing parameter tag, or DeepSeek's bar-fenced DSML tags at the end of a reply. Those tags are removed before the message is drawn, while the words around them stay. A tag an agent quotes on purpose inside backticks or a code block is left as written.
  • Copying a message gives you the agent's original text, not the formatted result — the drawing happens only on screen, so what you paste elsewhere is what the agent wrote.
  • Naming a file is not the same as showing it. A path on its own tells you nothing you can open, which is why agents are taught to use the route above rather than print a path.
  • A file path written in backticks is clickable. Clicking it opens the file: a picture opens in the built-in file preview, a PDF opens in the in-app viewer when that setting is on (the system's own app otherwise), and a script opens for reading while an installer is revealed in its folder rather than run. This holds for any file the app can open, images and PDFs included.

How an agent's prose and its tool activity are laid out in the feed is Agent Message Display. The interactive multiple-choice pills an agent can put inside its prose are Question widget, and a file you attach to your own message is Chat attachments. The neon "Waiting on you" box that frames the part of a session's newest message listing what only you can do is Needs-you section highlight.

Last verified 2026-10-24