The release after 1.10.0 in the Python line, and the desktop half is about how you steer a reasoning model.
The GUI's Tool Confirm button becomes an Effort selector, saved per chat. Reasoning effort is the
setting that decides how much thinking a model does before it answers, and the right value depends on
the task: high for the thing you are debugging, low for the thing you are summarising. Putting it on
the tab, saved with the chat, is what makes that usable. The global setting follows Settings;
Provider default omits the hint entirely; Minimal is no longer offered, because it produced answers
that were worse than the time it saved.
Throughput is measured honestly. Tokens per second used to be computed from generation time alone, which flattered everything: it ignored latency, prefill and reasoning, and it included retries. The new number is output tokens divided by the final successful request's wall time, including latency, prefill and reasoning, excluding tools and retry waits. A number you can compare between endpoints has to include the parts that differ between endpoints.
Proxy continuation envelopes survive tool calls. Some providers hand back opaque state that must come back on the next request for a reasoning conversation to continue. It was being dropped, and the model lost its own train of thought. Preserving it across tool calls and saved-chat resumes, and dropping it when you switch models (it is bound to the model that made it), is the whole fix.
1.11.2 and 1.11.3 (5 October) changed no files. They exist so the Rust, C++ and Python trees carry
the same number as the release that landed the same day. The real 5 October work is in the Rust and
C++ editions: a web UI that hung the process on a second browser tab, crashed the worker on its
second session, and leaked a socket per tab; a C++ worker that could not drive a tool chain at all
because the event callback re-entered Qt's deleteLater and SIGSEGV'd.