aboutsummaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorFilesLines
2026-09-26Fix mail counts and finance ranges found testing liveDanilo M.5-18/+68
- mail printed threads and the model called them emails; it now reports messages and threads. - finance spending takes a since date (default the first of the month) instead of a day count, and an optional asset account. The per-account listing needs an end date or the API rejects it; an unknown account name gets the user's accounts back. - Tool errors are capped at 2000 characters like normal output. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Add calc, mail, playing and finance example toolsDanilo M.8-4/+153
All read-only: each command is fixed in its tool file, so the model fills parameters but can never reach mailctl tag or firefly tx add. qalc reads "17.5% of 240" as a modulo, so the calc hint shows percent as a factor. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Document the config folder, the tools and the live testDanilo M.2-3/+77
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Fix issues found testing the tools liveDanilo M.3-7/+16
- The model has no clock and invented a 2025 start date for the calendar; the system prompt now carries the current date and time. - It also derived a wrong weekday from a date; agenda.py prints the weekday itself. - An announcement ran straight into the answer; a 0.6 s pause follows it. - The calendar days hint asks for 30 or more when looking for the next event. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Add weather tool on OpenWeatherMap, reusing the conky cache for homeDanilo M.2-0/+81
A bare city name is ambiguous for the API (plain "Rome" and "Roma" both resolve to Rome, US), so the parameter asks the model for City,CC and the output names the country. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Add calendar tool reading the vdirsyncer folder directlyDanilo M.2-0/+170
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Add example config and the now and search toolsDanilo M.4-0/+73
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Let the model call tools, with a spoken note while slow ones runDanilo M.1-17/+79
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Load tools from the config folder and run them without a shellDanilo M.1-0/+89
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Read settings from config.toml over built-in defaultsDanilo M.1-18/+70
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Add implementation plan for tools and the config folderDanilo M.1-0/+1016
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Add design spec for tools and the config folderDanilo M.1-0/+242
Phase 1 of 2: read-only tools (time, calendar, weather, search) defined as shell-command TOML files in a config folder, plus config.toml for the settings that are constants today. Modifying tools get their own spec after phase 1 is tested live. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Use the system kokoro-onnx package, drop the venvDanilo M.4-31/+10
kokoro-onnx is now packaged (python3-kokoro-onnx, without espeakng-loader) and finds the system espeak-ng with its default config, so the explicit EspeakConfig and the .venv setup go away. Tested live: two Italian questions answered and spoken correctly. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26AGENTS.md: record removal of unused piper and whisper modelsDanilo M.1-5/+7
Piper voices and ggml-base/small are gone from /data/voice-models; the installed piper-tts and python3-pathvalidate packages remain. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25Add push-to-talk voice assistant loopDanilo M.6-0/+1086
The microphone's mute button is the push-to-talk: the ALSA Mic Capture Switch starts and stops a recording. whisper-server (large-v3-turbo, Vulkan on the Arc) transcribes it, the model already resident in llama-server answers, and Kokoro speaks the reply sentence by sentence. Only Italian and English are spoken, so detection is restricted to those two; the voice follows the language of the reply, not of the question. Presses are ignored while presentation mode is on, so calls keep the mic. AGENTS.md records the backend, model and voice comparisons behind these choices. Licensed GPLv2 only. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>