aboutsummaryrefslogtreecommitdiffstats
path: root/desktop/modules/ai
AgeCommit message (Collapse)AuthorFilesLines
44 hoursai: drop local chatDanilo M.4-30/+9
local-chat (llamachat) is archived and uninstalled, superseded by desktop-assistant, so its row could only ever read stopped and its buttons called a command that no longer exists. Also folds the control comment that described llamachat's restart dance down to one line. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
44 hoursDrop breaktimer and the archived AI appsDanilo M.5-61/+16
breaktimer is parked and imggen and fanfictioner are archived and uninstalled, so the shell was reading files nothing writes and offering buttons that call commands that no longer exist. Status: remove the bt* properties, the file watchers behind them, the verb runner and the presentation-mode pause/resume. The status page loses BreakRow and the tile falls back to "All clear". AI: remove the imggen and fanfictioner rows from ai-state.sh, their labels and controls, and the pid-based fanfictioner stop. The sd-cli engine row stays, since the wallpaper upscaler uses sd-cli too. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
4 daysai: unload llama's model from the engine rowDanilo M.3-3/+15
The llama.cpp row offers Unload while a model is loaded. It posts to the router's /models/unload, which frees the VRAM and leaves llama-server up, so its web UI stays available; the engines themselves are still never stopped from here. The answer is not read: the next poll shows the row without a model, or with it if the unload failed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
9 daysai: Restart for the desktop assistant and local chatDanilo M.4-12/+42
A Restart button sits before Stop on a running app that has a restart control. The assistant uses assistant.sh restart. llamachat has none, and its --quit answers before the app has exited, so a --daemon sent straight after finds an instance still running and does nothing: the restart quits, waits for --ping to fail (5s at most), then starts it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16chore(assistant): retire the voice overlayDanilo M.1-2/+1
desktop-assistant is a text daemon now (its voice version is the tag voice-v1), and the canvas in desktop/assistant/ is its front end. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05docs(ai): module README, drawer module listDanilo M.1-0/+51
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05feat(ai): drawer page for the local AI stackDanilo M.4-0/+334
Engines are read-only, since stopping llama-server or sd-server takes its web UI down too. Apps start and stop through their own controls, detached so a start outlives a quickshell reload. Fanfictioner has no start (a run needs a story) and stops by pid, children first, so its sd-cli runs go with it and nothing else does. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05fix(ai): count a running sd-cli as the sd engineDanilo M.2-7/+32
fanfictioner runs sd-cli one-shot, not through sd-server, so the sd row read down while a CLI run held VRAM and generated. A running sd-cli now reads up and busy, its model marked (sd-cli), and outranks the web UI. The model is the first --diffusion-model/-m: sd-cli's prompt follows and is free text that may contain "-m". Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05feat(ai): state sweep for the AI stackDanilo M.2-0/+242
Six TSV lines per sweep: llama and sd engines, four apps. llama's slot probe passes autoload=false, since a plain /slots?model= loads the model into VRAM. sd-server has no progress endpoint, so busy is its log having been written in the last 5s. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>