A merge that could not combine anything no longer repeats itself
Nothing was combined, and the scan kept going until someone stopped it: four and a half hours on one scan before this was found. Now a step that cannot combine anything puts every group into one final prompt. A small group goes in whole, and a large one is shortened only as far as the window needs, with a note at the cut. The report says when this happened.
A peer hub no longer takes on work it cannot finish because it re-read a prompt
A hub that takes work from other hubs estimates how long a call will take before accepting it, from how fast it has recently read prompts. When it was sent the same prompt more than once, the model server answered the repeats almost instantly, because it still held the prompt it had just read. Those repeats counted as fast readings and pulled the estimate down, so the hub accepted a much larger call it then could not finish before its deadline.
Each call now records a short fingerprint of its prompt (a digest, not the text), and only the first reading of any prompt counts toward the estimate.
Full technical release notes for 7.4.0 are on the changelog, alongside every other Ghost Architect™ Local release.
Ghost Architect™ Local runs on your own hardware.
If you want an evaluation trial, the download page tells you how to get the tarball, verify it, and start the evaluation trial on your own hardware.
Request Ghost Architect™ LocalEJ Wisner, founder of Ghost Architect™. Local pricing is monthly, per team size, with no per-token bill; the numbers are on the pricing page.