aboutsummaryrefslogtreecommitdiffstats
path: root/assistant.py
AgeCommit message (Collapse)AuthorFilesLines
16 hoursFinal review: startup probe, error messages, refusal exit, docsDanilo M.1-4/+24
A startup probe that failed with anything but OSError (llama-server not in router mode, an empty model list) crashed the daemon at boot, against its own comment; it is caught like the per-request failures now. llama-server's reasons reach the client: an HTTP error carries its body and an error chunk mid-stream its message, where the client used to see 'choices'. A daemon that refuses to start, or fails before serving, exits 1 instead of 0. assistant.sh no longer mistakes a --test run for the daemon. AGENTS.md said every section from Hardware to Kokoro was voice-only, which included findings the daemon still applies; it now names the voice ones. It also claimed a stopped reply emits nothing after done, while a late ctx can. The spec lists every error message, the example config no longer shows a non-default temperature as the default, and the updates tool stops telling the model not to read lists aloud. The spec is marked implemented. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
16 hoursMake thinking a config key, on by defaultDanilo M.1-1/+2
Measured live: with reasoning on, a two-line question took 21 s of thinking before its first token, against about 5 s for questions that needed little. thinking = false in config.toml skips it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
16 hoursProtocol: check command arguments, keep readers alive, one daemonDanilo M.1-33/+107
From review of the protocol commit. An exception inside a command, such as an id SQLite cannot bind, killed that client's reader and left a deaf connection still receiving events; commands now run under a try that answers error. Ids must be integers: delete with no id compared None to an unsaved conversation's None and wiped it, and a string id deleted the row through SQLite's affinity while the Python comparison missed, leaving the current conversation pointing at nothing so every later answer failed to save. ask, search and their arguments are type-checked instead of coerced. serve() refuses to start over a socket that answers, since unlinking it orphaned the live daemon's clients, and main() removes the socket only if it served it. The accept loop logs and continues on errors instead of dying silently, and a client line over a megabyte is dropped. The two known ceilings, a stalled client delaying everyone once for 2 s and a stopped reply holding the llama-server slot until its next chunk, are marked. New checks cover each of these and a client connecting mid-reply. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
16 hoursTake questions on the socket and stream replies backDanilo M.1-49/+363
Each client gets a reader thread; commands are ask, stop, new, list, open, search and delete. A reply streams think, token and tool events through say(), which checks the turn counter under the same lock that stop takes, so a stopped reply cannot send a token after its done. A finished turn is saved; a stopped one is not. hello carries the current conversation and any reply in flight, so a reconnecting canvas redraws both. Errors from llama-server become an error event and the daemon stays up; every exit path of main() logs a line, which the voice version's silent death lacked. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
17 hoursHistory: enforce modes on existing paths, index turns, strip NULDanilo M.1-4/+12
From review of the storage commit. makedirs and connect leave an existing directory or file at whatever mode it had, so a history dir made earlier with the default umask stayed 0755; both are now chmodded. A NUL in a search ended the FTS string and raised instead of returning nothing. The index on turns(conv, seq) serves the seq lookup per save, load_conv and the cascade, which otherwise scan every turn. The self-check now also asserts that an OR query matches nothing, which a non-raising but unquoted query would not. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
17 hoursKeep conversations in SQLite with full-text searchDanilo M.1-0/+126
One file under XDG_DATA_HOME, 0700 directory and 0600 file. turns.messages holds what the model is sent for the turn, user/reply/tools what the canvas draws. FTS5 with remove_diacritics finds città from citta. The query is quoted as one phrase so FTS syntax typed by the user is matched as text, and the self-check's integrity-check proves a conversation delete cascades into the index. Co-Authored-By: Claude Haiku 5.5 <noreply@anthropic.com>
17 hoursDrop the voice pipelineDanilo M.1-463/+33
The assistant becomes a text daemon behind the quickshell canvas. STT, TTS, the mic button loop, the presentation gate, the audio levels and the overlay config table go; the socket, the tool runner, the never-swap model rule and the config merge stay. The reply loop goes with the voice and returns with the text protocol. The voice version is tagged voice-v1, so later voice work starts from the tag instead of from dormant code. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-28Let arecord die with the assistantDanilo M.1-1/+1
It was the only child started without PR_SET_PDEATHSIG. The assistant died with no log line and left arecord recording into the unlinked raw file for ~76 minutes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-28Keep tool calls in history, with placeholder resultsDanilo M.1-5/+13
History kept only what was said, so after a few factual answers the model saw no tool behind them and invented the next one: asked for pending updates it made up counts without calling the tool (1/10 on a replayed session). Keeping each turn's tool calls brings it back to 10/10. Their results are replaced by a placeholder, which scores the same and keeps the context close to what it was; a follow-up on an old result calls the tool again. The window is now the last 10 whole turns. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Use beam search in whisper, tell the model about misheard wordsDanilo M.1-0/+4
Whisper wrote "Che ori sono?" twice in one day and the model once answered with the weather. On 10 recorded short questions beam search (beam_size=5) gets 9 right against 8 for greedy, for 0.06 s more; an initial prompt also got 9 but lost one question entirely, so it is not used. The default system prompt now says the user's words come from speech recognition and should be read by how they sound: on "Che ori sono?" stray tool calls went from 1 in 10 to none, other tools unaffected. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Stamp the time on each question, ask for digits, add a temperature keyDanilo M.1-2/+11
With the clock only in the system prompt, "what time is it?" asked again an hour later copied the old answer from history. The current question now carries the date and time too; history stays unstamped, because stamping every message made the model drop tool arguments (the finance account filter went from 6/6 to 0/6). Gemma garbles numbers it spells out in Italian ("trent settler"), 3 in 10 time answers. The default system prompt asks for digits, which Kokoro reads correctly: 20/20 clean. temperature in config.toml is sent with every request; unset keeps the llama-server preset's, which other clients share. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Emit state, context and audio levels from the voice loopDanilo M.1-6/+71
speaking comes from the reply thread, not the speaker: the tool announcement would otherwise replace the tool state while the tool is still running. arecord gets a 33 ms period, because it writes its file in periods and the default left the user's waves at 8 levels a second; the context size is read at startup so the first hello carries it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Broadcast assistant events on a Unix socket for the overlayDanilo M.1-2/+107
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Notify when a press is ignored in presentation or gaming modeDanilo M.1-6/+25
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Compute audio levels for the overlayDanilo M.1-0/+38
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Log the prompt token count of every LLM roundDanilo M.1-1/+7
Asks llama-server for usage in the stream, so the log shows how full the model's context is; history, tool definitions and tool results all count. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Read controller batteries, stop the model guessing system factsDanilo M.1-1/+4
- Game controllers report battery through their kernel driver, not BlueZ: bluetooth.sh falls back to the power supply named after the device address. - Asked for a VM's IP after a listing without one, the model made one up without calling a tool. The default system prompt now says facts about the user's computer, devices, accounts, mail, calendar or money come only from a tool, or it says it does not know. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Pause during games too, not only in presentation modeDanilo M.1-5/+20
The status registry's effective presentation is the OR of the manual flag and status.gaming, which the shell's game detector writes; statusctl presentation get reads only the manual half and printed 0 with a game running. presenting() now reads both files. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Let a button press cut the current reply (barge-in)Danilo M.1-34/+65
Every press bumps a turn counter and kills the running aplay; queued audio from an older turn is dropped, and reply() now runs on its own thread and returns once its turn is stale, so the button loop is never blocked. A cut-off exchange is left out of history so user and assistant messages still alternate. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-26Fix mail counts and finance ranges found testing liveDanilo M.1-1/+1
- 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>
2026-09-26Fix issues found testing the tools liveDanilo M.1-1/+9
- 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>
2026-09-26Let 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>
2026-09-26Use the system kokoro-onnx package, drop the venvDanilo M.1-7/+3
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>
2026-09-25Add push-to-talk voice assistant loopDanilo M.1-0/+281
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>