What's new in Goatfied.

Aug 10, 2026

Long output is kept, not thrown away

When a command prints more than fits, the whole thing is now saved and the agent can go back for the part it needs.

A test suite that prints ten thousand lines has never fitted into an agent's working memory, so the middle of it was abridged. That kept the verdict at the end visible, which was the important half, but the part that was cut was simply gone. If the answer happened to be in there — the first failure, the stack trace, the line the compiler actually objected to — the agent's only options were to run the whole thing again or to reason about output it could not see. It usually chose the second.

Now the complete output is written to a file first. The agent still gets the abridged version immediately, so it reads the verdict without an extra step, but it is also told where the full text is and can open it at any point. Nothing is discarded, and a slow command does not have to be run twice to be read once. The saved copies are kept out of your version control and cleaned up behind themselves.

Reading files got the same treatment from the other direction. A minified bundle or a base64 blob is often one line that runs for megabytes, and that single line used to arrive whole — crowding out everything around it, including the lines the agent opened the file for. Over-long lines are now cut with the length they were, so the surrounding code stays readable and the agent knows it is looking at an excerpt.

Build 2.14.9

Aug 9, 2026

An agent has to show its working now

Agents may no longer describe work as finished on the strength of expecting it to have worked. The proving command has to have just run.

The surest way to be told a thing was done when it was not is for an agent to reason its way to the conclusion instead of checking. It writes a test, the write does not land, and the next sentence says the test passes — because that is what would have happened. Nothing in the session ever contradicts it, so the claim stands.

Agents now work to an explicit rule: no statement of success without fresh evidence for it. Before saying tests pass, a build is clean or a bug is fixed — and before committing or calling a task done — the agent has to name the command that would prove it, run that command in full, read the result including how it exited, and then report what it actually saw. Pass counts and exit codes get quoted back to you rather than summarised into a yes.

The rule names the specific ways this used to go wrong, so they are recognisable when an agent is about to repeat one: calling a suite green without running it, inferring a build from a linter, declaring a bug fixed without reproducing the original symptom. Hedging words are treated as the tell they are — if the answer is that it should work, the agent goes and finds out whether it does.

Build 2.14.8

Aug 8, 2026

When a command fails, the agent now knows

Two gaps in how an agent was shown the results of what it ran could leave it reporting success it had no way of seeing. Both are closed.

Almost everything an agent runs says how it went on its last line. Tests end with a count of what passed. Compilers end with a count of errors. When the output ran long we were trimming it from the bottom, which meant the agent was handed the noise and had the answer taken away — and an agent with no answer in front of it tends to report what it expected to happen. Long output is now trimmed from the middle instead, so the end always survives, with a note saying how much was cut.

Separately, a command that failed was not saying so. Whether it succeeded was shown to you in the terminal panel but was never stated in the text the agent reads, so a failure with a lot of output could pass for a clean run. Every command now reports its exit status on the first line, and a failure says so in words.

Together these were the main way a session could end up describing work that had not actually landed. If you have seen an agent claim a test suite passed when it had not, this is the cause and it is fixed.

Build 2.14.7

Aug 8, 2026

A tidier space to work in

The strip above where you type has gone from three stacked bars to one, and the buttons that were sitting there permanently have moved to where they are actually useful.

Above the box where you type there were three separate bars: a row of buttons, a task list, and a summary of what had changed. Each had its own outline and its own gap, and together they took up a surprising amount of room for what they said. The task list and the list of changes are now two halves of a single panel with a line between them, and both sit closer to their text.

The row of buttons is gone. One of them only repeated the count of changed files already shown right below it, so it has been removed outright. Opening a terminal and running a saved task have moved down to the bar along the bottom, next to your branch name — they are always available and have nothing to do with whatever the agent is doing right now, so they no longer sit in the middle of the screen.

Committing has moved the other way, up beside Keep and Undo on the list of changed files. It acts on those changes, so it belongs with them — and it now appears only once there is something to commit, instead of waiting around in a session that has not touched a file.

Build 2.14.6

Aug 9, 2026

Less noise, more of what you were reading

A long command no longer takes over the conversation, and the session list has stopped repeating itself. Both changes hand the screen back to the words that actually tell you what happened.

When an agent runs something in the terminal you already see the command and its output in the terminal panel inside the conversation. We were printing the command a second time just underneath, and a single long one could wrap into a dozen lines that pushed the steps on either side of it off the screen. That line is now kept to one line, with the whole command still there on hover.

The session list had the same problem in miniature. Every session carried a small tag naming the mode it was started in, and its name then began with that same word again. In a narrow sidebar that spent the widest part of the row saying nothing new, and cut off the words that tell one session apart from another. Both are gone, and sessions you already have lose the repeated word too.

Build 2.14.5