Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 21 additions & 6 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,20 +8,35 @@ submodule.

## [Unreleased]

## [0.15.1] — 2026-09-24

**See what your agent is doing while it does it.** In 0.15.0 you sent a message and then waited,
with no way to tell whether the agent was writing you an essay or had wandered off. Now you
watch the reply come in, and a small meter tells you how much of the agent's memory the
conversation is using, so you can tidy up before it starts forgetting things. We also fixed a
couple of small things 0.15.0 got wrong.

**Included engine:** [MandoCode CLI v0.15.1](https://github.com/DevMando/MandoCode/releases/tag/v0.15.1).

### Added
- **Watch replies as they're written.** The agent's reply now appears in the transcript as it
streams, instead of all at once when it's finished. If the agent says something before using a
tool ("let me check the docs…"), that text becomes its own card above the tool call, and the
answer gets a second card. The conversation reads in the order it happened, instead of merging
everything into one card at the end.
- **A context meter in every tab.** The strip under the message box now shows how full the agent's
context window is, for example "Context ▰▰▰▱▱▱ 41% of 32k tokens", with a bar that turns
yellow and then red as it fills. It tells you when to `/compact` before the model starts losing the
earlier conversation. The colors are tuned to stay readable in every theme, a full window also
shows ⚠ so the warning never depends on color alone, and screen readers announce it. Cloud models,
which manage their own window, show their token count.
- **A context meter in every tab.** A model can only keep so much of a conversation in mind at
once. That limit is its *context window*. Once a conversation outgrows it, the earliest messages
start slipping away. The strip under the message box now shows how full the window is, for
example "Context ▰▰▰▱▱▱ 41% of 32k tokens", with a bar that turns yellow and then red as it
fills. When it gets high, run `/compact`: it squeezes the conversation into a short recap so the
agent keeps the thread without the bulk. The colors are tuned to stay readable in every theme, a
full window also shows ⚠ so the warning never depends on color alone, and screen readers
announce it. Cloud models manage their own window, so for them the meter shows the token count
instead.

### Fixed
- **Reply speed is back.** The summary after each reply had stopped showing how fast the model
was answering (tokens per second) once streaming became the default. It shows again.
- **The "Add tag" button is fully visible again.** In the Manage tags dialog, the name box was a
fixed width, which pushed the button past the dialog's edge and cut it off. The name box now
shrinks to fit, so the color picker and the whole button always fit on the row.
Expand Down
52 changes: 52 additions & 0 deletions docs/release-notes-0.15.1.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
# v0.15.1 — Watch your agent think

0.15.0 was a big release. It rebuilt the engine that runs your agents, and it left one thing
feeling worse than before: you'd send a message and then stare at a spinner until the whole
answer landed at once. Is it working? Is it stuck? You couldn't tell.

This update fixes that, adds a gauge you'll wish you'd always had, and cleans up a couple of
rough edges.

## Replies show up as they're written

You now see the agent's reply come in while it's writing, the same way you would in a chat app.
The order of the conversation makes more sense too. If the agent says "let me check the docs"
before looking something up, that line gets its own card, then you see the lookup, then the
answer. Before, all of that was squashed into one card at the end.

## A meter that tells you when the agent is running out of room

Every AI model can only keep so much of a conversation in mind at once. Go past that limit and
it quietly starts forgetting the beginning: the file you mentioned an hour ago, the decision you
made together earlier. Until now you had no way of seeing it coming.

Under the message box there's now a small bar, like "Context ▰▰▰▱▱▱ 41% of 32k tokens." It
turns yellow as it fills and red when it's nearly full. When it's getting high, type
`/compact`. The agent sums up the conversation so far and carries on from that summary, with
plenty of room to spare.

The colors stay readable in every theme, a full bar also shows ⚠ so you don't have to rely on
color, and screen readers read it out. Cloud models handle their own memory, so for those the
meter just shows how many tokens you've used.

## Small fixes

- **Reply speed is back.** The line under each reply shows how fast the model answered again.
It went missing in 0.15.0.
- **The "Add tag" button isn't cut off anymore.** In the Manage tags dialog, the button was
sliding off the edge of the window. It fits now.

## Under the hood

This release includes [MandoCode CLI v0.15.1](https://github.com/DevMando/MandoCode/releases/tag/v0.15.1).
Everything is in the [full changelog](https://github.com/DevMando/MandoCode.Desktop/blob/v0.15.1/CHANGELOG.md).

## Install

Download **MandoCode.Desktop-v0.15.1-win-x64.zip** from this release, extract **all** of it
into a folder, and run **MandoCode.Desktop.exe**. Everything you need is in the zip, including
.NET. The only other thing Windows needs is Microsoft Edge WebView2, which most PCs already have.
You'll still need a model provider such as Ollama, and Ollama's cloud models need a
subscription.

Already on 0.15.0? MandoCode Desktop will let you know the update is ready within a day.
2 changes: 1 addition & 1 deletion src/MandoCode.Desktop/MandoCode.Desktop.csproj
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
<WindowsAppSDKSelfContained>true</WindowsAppSDKSelfContained>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
<Version>0.15.0</Version>
<Version>0.15.1</Version>
<Authors>Armando Fernandez (DevMando)</Authors>
<Description>MandoCode Desktop — the MandoCode AI coding agent with a native WinUI 3 interface.</Description>
<!-- Embedded in the exe → taskbar, Alt-Tab, and Explorer icon. The title-bar icon is set at
Expand Down
Loading