The October release, in all three editions, and the useful part is the context window.
The window is discovered. A local engine knows how much context it was given, and can report it:
ollama /api/chat when the context length is set, a LM Studio request for a loaded model,
llama.cpp's /props. Pengy reads it, caches it, and a window discovered from the live provider
overrides a stale config value. /endpoint shows it.
Usage is now "used of total". The GUI and web UI show the model's context usage against the
window size, in a distinct colour when it is close to the limit, and the token estimate includes the
system prompt and tool schemas, which are the part of the request you cannot see in the message list
and which are a large share of a tool-heavy conversation. context_window and context_usage are
published in the JSON and CLI outputs.
Why this matters: 1.9.1's context-recovery reduction needs to know when to start. Guessing a window size against a model you do not control is how an agent either wastes turns hitting provider errors or throws away context it did not need to.
The Windows half is the biggest Windows work in this history. PowerShell is a first-class tool
(run_powershell), a real bash implementation is added where bash exists, run_bash on Windows
requires an ssh host, elevated=true means UAC (elevation is not faked by prompting for a
password, which on Windows means sending it over the network to get a token). Process kill uses
taskkill /T /F because os.killpg does not exist there, and the Rust edition's kill_on_drop was
a no-op, so timeouts never actually stopped processes.
The C++ edition spent this release fixing crashes: SIGSEGV on the tool-approval path, a crash when a
worker's event callback re-entered Qt, and a Qt signal-slot collision on finished(bool).