Windows Taim features that are not in the Linux window, for the assistant who is reading this

Read TAIM-TOOLS.txt first. Plain sentences when you answer the person: no markdown, no asterisks, no bullets, no tables, because a screen reader reads symbols aloud.

Since Linux window 0.2.0-alpha.33 the Linux window has what the Windows window has, except the items below. In the Settings menu: the speech dictionary (Control D), the assistant order, push to talk with a key and a mode per assistant (hold, or press once to start and again to stop) and Control Alt T to switch the assistant in front. In the Voices menu: voice settings for each assistant and for all of them together, with the speakers and microphone each one uses (these need the sound engine the installer sets up: python-numpy, python-cffi and portaudio, plus the sounddevice file Taim carries in its lib folder). Taim opens on the assistant you last used, and comes back to her after it restarts itself. Control K puts the whole code report in the assistant's tab and on the checks channel.

What is not there, and why.

1. PRIVATE MODE and its conversation key. Left out on purpose; the person does not want it.

2. HOURLY PROJECT SNAPSHOTS AND THE HEALTH WATCHDOG. On the Windows machine they save Jim's projects to his server and watch his server, domains and drives, so they only make sense there. For this computer, a systemd user timer (systemctl --user, taim-snapshot.timer every hour) calling a small script that does git add, commit and push for each project folder would do the same with no model and no tokens, once the person says where the copies should go. Never push anything with a password or key in it, and report a project that cannot be saved instead of forcing it. Ask first.

3. UPDATING INSTALLED TOOLS (Windows: winget, pip and npm, offered at Control Shift U). Linux uses its own package manager; on Omarchy that is omarchy-update.

4. SPEAKING REPLIES WITH TAIM'S OWN VOICE needs a voice (Piper or similar) set in an assistant's json file ("voice" block). Until then the screen reader (Orca) speaks, and Orca has its own pronunciation dictionary (Orca preferences, Pronunciation tab) that works today. When an assistant does have a voice, Taim's speech dictionary is applied to what it says.

After you add anything, tell the person in plain words what it does and which keys it uses, and write a line in the person's notes about it so the next session knows. If a feature turns out to be useful to everyone, tell Jim by email at jim@fidlerinnovations.com so it can be added to the shipped package for all Linux users.
