Commit Graph

212 Commits

Author SHA1 Message Date
javis-bot
de35573e5f fix(app): every stop voids waiting requests and pending addressed questions
- A voice stop also voids pending "addressed" questions, so a yes that
  arrives afterwards starts nothing.
- The core sends Stopped before the SpeakEnds of what stop() or the end
  of a session cancelled; the conversation drops its queue on it, so the
  slash command's stop no longer starts the next waiting request.
- An addressed answer after its 5 s timeout counts as no even when it is
  handled before the timer.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:32:32 +09:00
javis-bot
f892a1dce9 feat: answer calls in the voice channel through the response policy
- conversation.rs: the loop between the core's events and the rest.
  Finals go through call detection and the response policy; answers are
  asked of the brain and spoken from the app's queue, an interruption
  cancels only that answer, a voice stop silences everything, and missed
  requests are kept without text (last 100). Tested with a fake voice side.
- Core: answer(user, text) adopts a playback request the worker speaks
  under the same id, cancel(id) stops one request, ask_addressed and
  ask_rank pass the conversation's questions; new SpeakingStopped,
  Addressed and Ranked events.
- Worker client: reply, addressed and rank messages and their results; a
  reply with no answer, refused or not sent ends its speech as failed.
- Voice worker: addressed and rank messages on their own threads, beside
  a running reply; a spoken reply cancelled while the brain is answering
  is not spoken. judges.py holds the two short LLM judgements with the
  heard text fenced as data; eval evals/test_voice_judges.py.
- Specs (conversation, discord core, voice worker), docs/llm_contexts.md
  and the roadmap updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:26:47 +09:00
javis-bot
e885630e91 fix(app): rankings carry an id, ties arriving mid-ranking are ranked, timer moves forward
- Action::Rank and ranked() carry a ranking id; answers to a replaced or
  dropped ranking are ignored.
- A candidate tying the ranked ones while a ranking is pending replaces
  it with a new ranking over all of them (plus the running answer when
  the ranking is about interrupting it), keeping the first deadline, so
  only compared candidates are missed as lower_score. A better one makes
  the ranking moot.
- next_deadline returns the collect timer while collecting, and the
  settle deadline only while an ending utterance holds the choice up.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:13:39 +09:00
javis-bot
46eebcd256 fix(app): important policy ranks a tie against the running answer; timer and ordering fixes
- A new request that ties the running answer on priority and wake word
  is ranked against it by the brain; a win interrupts, a loss or a
  timeout lets the answer go on. The ranking is dropped when the answer
  ends first.
- A ranking that arrives after its deadline counts as a timeout.
- Candidates collected while an answer runs keep end-time order, so the
  timeout fallback picks the earliest-ended one.
- A spent collect timer is cleared, so next_deadline reports the settle
  deadline instead of a time already passed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:09:57 +09:00
javis-bot
6fc3983a40 feat(app): call detection and the four response policies
- calls.rs: wake words anywhere in the utterance with near matches by
  edit distance on NFKD-normalised letters (Hangul splits into its
  letters), call modes (wakeWord, addressed, everything), designated
  people with both switches, and a voice stop (wake word + stop word).
- policy.rs: first, inOrder, latest and important as an event-driven
  state machine with the time passed in: ordering by end time, waiting
  for an earlier-ended utterance still being transcribed, queue limit,
  interruption, importance ranking only on a tie with a timeout, stop
  dropping the queue, and a reason for every missed request.
- settings: new call and response sections, validated with the key.
- conversation.spec.md documents the contract; registry and roadmap
  updated. Wiring into the Discord core and the brain comes next.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:05:50 +09:00
javis-bot
b88b28140f docs(roadmap): match the M3 eval failure notes to the run logs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 21:57:54 +09:00
javis-bot
3ec430fd25 fix(reply): known user location reaches getWeather; retries are not blocked by the previous reply
- Drop the engine's deterministic Korean weather shortcut. It bypassed the
  chat model and the tool runner, so a location the user had stated could
  never be used. The tool already returns one clean Korean sentence.
- getWeather and the tool-argument prompts pass the place the user has
  said they are (conversation or memory) and leave the argument empty
  otherwise, so the detected location is not copied into it.
- getWeather retries a "district, city, country" name with its leading
  parts dropped when the geocoder finds nothing.
- The planner gets the live time/location line and plans
  searchMemory topic='where the user lives' only when the location is
  unknown or disabled.
- The per-reply repeat guard counts only this reply's tool messages, so
  calls carried over from the previous reply no longer block a retry the
  user asks for.
- Memory extractor: the context block sits after the examples and the
  no-location example uses a different query, so a location already in
  context is not asked for again. New counterpart eval checks that it is
  still asked for when the context has none.
- Tool retry eval fails every call in turn 1, so a model that retries by
  itself inside turn 1 still exercises the user's "try again".
- Specs (planner, reply), docs/llm_contexts.md and the roadmap updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 21:55:45 +09:00
javis-bot
4bb3895ca0 docs(roadmap): record the eval run on Strata (Qwen3.6-35B-A3B) from the game PC
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 19:21:23 +09:00
javis-bot
69a884b182 test(evals): run the evals against any server named by EVAL_JUDGE_BASE_URL, including /v1
Ten eval files pinned their reply engine to http://localhost:11434 and the
judge only spoke Ollama's /api/tags and /api/chat, so pointing the suite at
Strata (OpenAI-compatible /v1 only) skipped or broke most evals.

- MockConfig and every eval config read EVAL_JUDGE_BASE_URL.
- The judge availability check reads /v1/models and the judge call goes
  through jarvis.llm when the URL ends in /v1; the Ollama path is unchanged.
- run_evals.sh probes /models for a /v1 URL.

The intent-judge and listener evals stay pinned to gemma4:e2b on local Ollama.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 18:49:08 +09:00
javis-bot
a45e198df6 docs(roadmap): record the M3 test and eval check
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 17:19:08 +09:00
javis-bot
1745fcd04c test: bring stale weather, enrichment cache and diary import tests up to date
- Weather: the tool deliberately returns one Korean sentence about now
  (c522e1b), so the tests check the place, condition, rounded temperature and
  feels-like, and that no forecast, Fahrenheit or degree sign is left for the
  model to echo.
- Enrichment cache: the conversational fast-path skips enrichment when no
  data tool is routed, so the test routes one to reach the extractor.
- Diary import: mock PyQt6, requests and psutil only when they are not
  installed. The MagicMock left in sys.modules for an installed PyQt6 broke
  every later GUI test file in the same run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 16:13:52 +09:00
javis-bot
4621e6c1fd fix(chat): the delete consent check knows the pending message and reads the whole reply
The consent classifier is now told which message and channel are pending, so a yes for another
message ("yes, delete message 22" while 21 is pending) is a no and cancels the request. A reply
longer than 600 characters is no longer cut and judged by its start (which could drop a later
"don't"); it counts as no without a model call.

Eval evals/test_chat_delete_consent.py gains the different-message and long-reply cases:
17/17 on qwen2.5:7b, three runs. The previous prompt said YES 3/3 to
"응, 일정 채널에 있는 거 지워" while a message in 잡담 was pending.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 15:26:58 +09:00
javis-bot
0182823592 fix(chat): delete needs the person's own yes; chat action ids never repeat
- chatChannels delete with confirm=true now runs only in the person's very
  next turn and only when their own message of that turn agrees, checked by a
  small fail-closed YES/NO call on the router model chain (the message fenced
  as data). A refusal, question, other topic or error cancels the request;
  an unconfirmed request lapses after one turn. The reply model's confirm
  flag alone can no longer delete.
- chat_action ids carry a per-run nonce and the session, so a late answer
  meant for an earlier connection (or worker run) never completes a newer
  action.
- Tests: agree, refuse, other topic, lapse, classifier failure, late answer
  across reconnects. Eval test_chat_delete_consent: 12 of 12 on qwen2.5:7b,
  3 runs. Spec and llm_contexts updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 14:08:35 +09:00
javis-bot
fe4e296361 feat(chat): chatChannels tool for the registered Discord chat channels
- Tool (chat_channels.spec.md): list, read, search, send, edit, react,
  delete, pin, unpin. Offered only when the v2 brain gives the turn a chat
  backend, and then on every turn. Channel by ID, name, part of a name or a
  name inside the text; a message ID finds its channel; planner forms of the
  action ("send_message") work. Read and search results are fenced as
  untrusted data. delete only reports until called again with confirm=true
  in a later turn of the same person.
- Worker: chat_channels from the app, ChatBridge reads/searches the history
  store and sends chat_action, waiting for chat_action_result (15 s timeout,
  failed on session close); per-person reply turns and pending deletes.
- App: channel switches edit/react (on) and delete/pin (off); chat_channels
  sent on worker ready and after login; chat_action runs send, edit (own
  messages only), react, delete, pin, unpin and answers with ids or the error.
- Engine: chatChannels left out of the catalogue without a backend; the
  "router returned everything" check now tolerates that.
- live_discord: edit own, refuse editing the speaker's, react, pin (Discord
  refuses in a voice channel's chat, reported as an error), delete, refuse an
  unregistered channel; passed in 109.4 s.
- Eval (qwen2.5:7b, 3 runs): 10 of 12; never obeyed the "delete everything"
  message and never deleted in the same turn.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 14:01:33 +09:00
javis-bot
3dbf1e8c56 feat(nutrition): meals belong to the person who logged them
- meals.user_id (v1 databases gain it on open, DEFAULT '' keeps their meals
  the single user's); insert_meal, get_meals_between and delete_meal take
  the person, and delete only removes that person's meal.
- turn_state.set_user / ToolContext.user_id carry the asker; logMeal,
  fetchMeals and deleteMeal use it. The v2 brain sets it for each reply.
- Tests: two people never see or delete each other's meals, no user is v1's
  single user, and a v1 database opens with its meals kept.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 13:32:36 +09:00
javis-bot
b3dcd12ec9 fix(voice_worker): keep history and the brain's output scoped to who was there
- A final is stored under the channel, speaker name and time fixed when its
  end was decided. Decoding takes a while; a move, rename or late joiner
  meanwhile used to change where and when it was said, and who heard it.
- At start the worker closes presence a killed run left open
  (HistoryStore.close_open_presence), so a person who is gone no longer
  hears new speech after a restart.
- run_reply_engine(legacy_memory=False) skips v1's single-user memory (warm
  profile, extractor, diary, graph, digest); the v2 brain uses it so another
  user's profile or diary never reaches the prompt.
- While a brain reply runs, stdout and stderr are muted (also helper threads
  such as the web fetch pool); the worker logs through voice_worker/log.py to
  the original stderr.
- Live check: Ollama's /v1 fixes the context at 2,048 tokens and cut the
  prompt in earlier runs; with an 8k tag the chat-record question was answered
  4 of 4 and nothing reached the output. Noted in llm_contexts and the eval.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 13:28:25 +09:00
javis-bot
864b2e7fdb feat(voice_worker): record history from the app and answer reply requests with the brain
Worker (voice_worker.spec.md "History and brain"):
- --history <file> keeps the conversation history store; --brain hosts the
  jarvis reply engine (JarvisBrain, settings point ollama_base_url at /v1).
- voice_join / voice_leave / member_join / member_leave keep presence; the
  session end closes it. Non-empty finals are stored under the speaker's name
  in the current voice channel.
- chat_message / chat_edit / chat_delete keep registered chat channels.
- reply builds the asker's scoped history context, runs the brain on a thread
  (one at a time), answers reply_text, stores a voice answer, and with
  speak=true says it under the same id. memory settings in hello and
  memory_config. brain_unavailable without --brain.

App (discord_core.spec.md "History reporting"):
- WorkerClient sends the new messages; the core reports the voice channel
  and its heard members after a join, a move and every worker reconnect,
  member joins and leaves, voice_leave when a session ends, and every message
  of a readable registered channel (its own too, with `to` on replies), edits
  and deletes.
- live_discord runs the worker with --history and checks the store at the
  end: 8 finals under the speaker's name, the edited chat message only,
  Jarvis's own messages, 5 presence intervals, none left open (passed, 107.8 s).

Eval: history recall gains a chat-record case and fails a reply that reads a
record stamp out (field run with qwen2.5:7b did once in four).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 13:16:24 +09:00
javis-bot
7a288129de fix(memory): rank the whole history and keep relevant recent records
- Search scored only the newest 5,000 matching records, so an old record
  behind enough newer chatter was never found. Both passes (word rarity counts
  and the score) now run in SQLite over every record in scope and only the
  best rows come back.
- context() excluded the recent window from search and then cut that window
  for the budget, so a relevant recent record could vanish. Search now covers
  the recent window, matches keep their half of the budget, and a matched
  record is removed from the recent block so it appears once.
- Matching used SQLite's ASCII-only lower() against Python's lowercasing.
  Stored text gets a folded column (NFKC + casefold) and query words are
  folded the same way, so case is ignored in every script.
- Prompt label "Records related to this question" (matches may now be recent);
  eval re-run 3x on qwen2.5:7b, all pass. Spec, memory.md and roadmap updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 12:50:37 +09:00
javis-bot
54a465948a feat(memory): v2 conversation history store and its context in the reply prompt
- src/jarvis/memory/history.py keeps voice transcripts, Jarvis's answers,
  registered chat channel messages (with edits and deletes) and voice channel
  presence in one SQLite file. Every read is scoped to the asker: own records
  always, chat channels and others' words (only while the asker was in the
  same voice channel) behind settings, plus an optional since and off.
- Search is language-agnostic: Unicode words, prefixes keeping 60% of the
  word, rarer words weigh more, newer wins ties. 100k records search in
  24-61 ms here. context() returns the recent window and the matches cut to a
  token budget, matches at most half so chatter cannot push out the record
  the question is about.
- run_reply_engine(history=...) puts that context into the system prompt
  under "Information shared in previous conversations", fenced as data.
  evals/test_history_context_recall.py: with the block qwen2.5:7b answers the
  stored day in Korean and English (3 of 3 runs), without it the day is unknown.
- Spec history.spec.md, registry entry in CLAUDE.md, reply.spec.md,
  docs/llm_contexts.md, docs/v2/memory.md and roadmap updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 12:45:33 +09:00
javis-bot
6b23a8adc7 feat(llm): talk to OpenAI-compatible servers such as Strata
A base URL that ends in /v1 now selects the OpenAI-compatible API: chat goes
to /chat/completions and embeddings to /embeddings. The conversion lives in
src/jarvis/llm.py only, so the reply engine and every other caller keep their
Ollama-shaped messages and responses.

- Requests drop private engine keys, send tool-call arguments as JSON strings,
  map num_predict to max_tokens and the thinking switch to
  chat_template_kwargs.enable_thinking, and leave out num_ctx and keep_alive.
- Responses come back with message.content, tool calls with dict arguments and
  an id, and message.thinking from reasoning_content.
- Streaming, the warm-up (one-token chat completion), the intent judge and the
  dictation clean-up use the same path. A server without an embedding model
  fails open to the text paths.
- Specs and docs/llm_contexts.md describe the transport; roadmap records M3
  step 1.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 12:32:48 +09:00
javis-bot
beaacb39cd fix(app): moving to another voice channel no longer ends the new session
- Same-server moves point the existing songbird connection at the new channel and replace its
  handlers; removing and rejoining at once let the late gateway "left" update cancel the new join.
- A driver disconnect without a reason (our own leave or move) is ignored, and a disconnect only ends
  the session its handler belongs to, so an old connection's late event cannot end a newer one.
- Live test: move to a second voice channel and back; the session survives both, only the two moves
  end one, and the speaker is still heard afterwards.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 12:13:04 +09:00
javis-bot
5efa760986 test(app): keep hearing a speaker across DAVE group changes, and record the Rust decision
- Live test: the speaker leaves and rejoins three times; each time its sentence is heard exactly
  under the new SSRC (songbird issue #310 reports receive stalls after group changes; not reproduced).
- decisions.md: Rust over Electron, with the side-by-side results, the songbird risk and the fallback.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 12:03:41 +09:00
javis-bot
f25c26cf53 refactor(app): rewrite the M2 Discord voice core in Rust
The user asked for a faster, real app instead of Electron. The app is now a Rust crate (serenity +
songbird); the GUI in M5 will be a Tauri 2 shell on the system WebView2.

- Same behaviour as the Electron core: one voice channel, per-speaker PCM to the voice worker,
  speaking_end and speaker_leave, sentence playback with stop and cancel, transcription notice on
  join, slash command join/leave/stop (create-or-update), registered chat channels with live events,
  history and sends that never ping, worker process with a fresh token and restart backoff.
- songbird 0.6.1 garbles about a third of received frames under DAVE (its decoder keeps the bytes
  DAVE decryption leaves at the end of the payload; a 20 ms stepped test tone showed repeats, skips
  and reordering, while sending was exact). songbird now only decrypts; the core reorders packets in
  a small window (Opus FEC for the last lost frame) and decodes them with libopus itself.
- Live test on real Discord with two bots: five sentences heard (CER 0/0/0/5/12.5%), 0.71-0.90 s
  from end of speech to final, speech read back at 3.4%, sound gone 0.08 s after stop. The release
  binary uses about 16 MB of memory; a Windows build (MinGW) logs in under Wine.
- Spec moved to app/src/discord_core.spec.md; architecture, decisions, roadmap and pc-features updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 11:57:53 +09:00
javis-bot
8479112ddd feat(app): M2 Discord voice core in the Electron app
- app/ (Electron 45 + TypeScript): the core joins one voice channel, decodes each speaker's Opus to
  48 kHz stereo and streams it to the voice worker, sends speaking_end and speaker_leave, and emits
  speech_start/partial/final with the speaker's display name.
- Sentence playback from the worker's TTS, first come first served, with stop that silences the clip
  at once and cancels unfinished requests; slash command join/leave/stop (create-or-update by name).
- Transcription notice posted on every join; other bots ignored by default; at most maxSpeakers
  people transcribed at once.
- Registered chat channels: live message events, history reads, sends split at 2,000 characters with
  mentions disabled; Message Content intent checked before login.
- The app starts the Python voice worker with a fresh token in the environment, restarts it with
  backoff, and the worker client reconnects and fails in-flight TTS on a lost connection.
- Spec in app/src/core/discord_core.spec.md; Vitest unit tests, a protocol test against the real
  Python worker server with fake engines, and an opt-in live test with two bots on real Discord.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 11:14:25 +09:00
javis-bot
5838f9edd8 feat(voice_worker): free a speaker's place when they leave the voice channel
- New speaker_leave message: ends the speaker's open utterance (its final is still sent) and drops
  their state, so a long session never hits the 32-speaker limit as people come and go.
- Spec and test cover more than 32 speakers in one session, each leaving mid-utterance.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 11:14:25 +09:00
javis-bot
1309525aa8 fix(voice_worker): the wake word hint may never add, drop or create a wake word
Hotword occurrences were counted with fuzzy matching, which never counted a one-letter wake word
(so a hinted "봇 ..." was accepted over a plain decode without it) and counted the real word
"서비스" as "자비스" (so the hint could turn it into the wake word). Occurrences are now counted
exactly (case, spacing and punctuation ignored); near misses are left as heard for call detection.
The real-noise eval now plays each recording as recorded and at -25 dBFS and reports how many clips
reached the model.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 10:40:42 +09:00
javis-bot
590cd07268 fix(voice_worker): even out speaker loudness and stop transcribing noise into words
- Loudness equalisation replaces peak normalisation: rumble below 60 Hz removed, level measured on
  the VAD-voiced windows only, brought to -20 dBFS (gain -20..+40 dB), soft limiter below 0.98.
- Only clearly voiced windows (VAD >= 0.5) count towards the 250 ms needed before an utterance
  reaches the model, so noise the VAD half-believes never calls Whisper.
- Hallucination gate: mean token log-probability >= -0.7 (the old len/(len+1) correction let short
  hallucinations through), compression ratio <= 2.4; no_speech_prob dropped (always 0.0 on turbo).
- With hotwords, the plain decode of the same encoder pass decides; the hint may fix a wake word's
  spelling but cannot add or drop one (it wrote the wake word on laughter and after real sentences).
- Opt-in real-model evals: voice-like babble with the hint, speech over babble, quiet and clipped
  speakers, and a JARVIS_NOISE_DIR folder of real noise recordings.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 10:27:38 +09:00
javis-bot
a7685e9078 feat(voice_worker): M1 multi-speaker streaming STT and sentence TTS over a local WebSocket
- One shared faster-whisper model for every speaker, batched; finals go before partials and
  partial batches are capped at two so a final never waits behind a ten-speaker pass.
- Per-speaker 48k stereo to 16k mono conversion, streaming Silero VAD, utterance ends on VAD
  silence, Discord speaking_end, missing audio, or the 28 s Whisper window.
- MeloTTS in its own venv through a child process; sentences stream out one chunk each, with
  incremental text, cancel and failure reporting.
- Loopback-only server with a token from the environment; logs carry no transcript text.
- Spec in src/voice_worker/voice_worker.spec.md; unit tests with fake engines and an opt-in
  real-GPU test that streams ten speakers at once.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 10:00:06 +09:00
javis-bot
b4926d5e19 docs(v2): note that the game went behind the kit's console because the user clicked it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:36:11 +09:00
javis-bot
8f2470af2a fix(m0): keep the game in front for the whole frames window and record the game_frames results
On the game PC the game went behind another window right after Jarvis
started and stayed there for three windows, drawing at its background rate
(about 58 fps). The kit only checked the window in front at the end of a
window, so the window in which the user clicked back into the game counted
and showed yielding as a 47 % drop in 1 % low.

- FrontWatch checks every second from the start of a window to its end and
  spoils the window if the game was behind anything at any check.
- Before a window the kit asks the user, with a beep, to go back to the
  game and waits up to two minutes.
- What was in front is kept only as a category (a Jarvis process, a console
  window, Explorer, another app), never an app name.

Results: with the game in front, a busy Jarvis cost 0.2 % of the average
fps and 3.3 % of the 1 % low with no frames over 50 ms, so by the
pre-registered rule nothing is added and yielding is not adopted.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:35:38 +09:00
javis-bot
cec52165b2 fix(m0): judge game frames by what the screen showed and drop spoilt windows
- Frame rate, 1 % low and hitches come from msBetweenDisplayChange of the
  frames that reached the screen; frames never shown are counted apart and
  the presented rate is kept as presented_fps. A game presenting 60 fps
  while the screen changes every 167 ms now shows as the stutter it is.
- A window whose capture failed, a busy window where the LLM finished no
  answer, and every busy window when the STT load failed are not counted.
- A yielding window counts only when every Jarvis process got both its
  CPU and its GPU priority lowered.
- The "game hardly drawing" floor applies only with Jarvis off or idle, so
  a game Jarvis slows that far still counts as harm.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:12:15 +09:00
javis-bot
dff18c5c7e feat(m0): measure the game's own frame times and try yielding by priority instead of a GPU cap
The 95 % GPU cap is gone: it did not lower utilisation, slowed the LLM and
a YouTube video did not stutter without it. What it was meant to protect
is now measured directly in a game. The new on-demand game_frames stage
records the game's frame times with PresentMon (pinned by hash, game
process only, CSV deleted after reading) with Jarvis off, idle and busy in
the game placement, and busy while Jarvis yields: its processes at
below-normal CPU and GPU scheduling priority, read back to confirm, then
restored. Busy rows run A B B A. The design docs record the candidate and
the pre-registered rule for adopting it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:05:55 +09:00
javis-bot
726fca3377 docs(v2): record M0 video_drops results and drop the GPU usage cap setting
YouTube 1080p60 kept 3-4 dropped frames per window with Jarvis off, idle
and busy (GPU up to 98%), with no gaps over 50 ms and no buffering. The
95% cap did not reduce drops (7 vs 7), so the setting is removed as the
spec already planned.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 08:44:01 +09:00
javis-bot
f66f57f02f fix(m0): keep navigator.webdriver off so YouTube does not stop the video a minute in
With DevTools on (port or pipe), Chrome tells pages a program drives it, and
YouTube then shows "문제가 발생했습니다" after about a minute of video, which
spoilt every window on the gaming PC. Reproduced on Linux: the port alone,
with no command sent, breaks playback at ~40 s; without it, or with
--disable-blink-features=AutomationControlled, it plays on. The browser is now
started with that switch, and one that still reports webdriver is refused
before Jarvis is started.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 03:00:40 +09:00
javis-bot
357f36afcc fix(m0): a player that does not come back spoils its window instead of ending the stage
When loading the page again did not bring a player back, keep_room still
moved the missing player back to the start, the page script threw and the
stage stopped at the first window. Now a failed reload (or a refused
navigation) is recorded as "the video did not play again", only a playing
video is moved back (and the script checks the player exists), so the
window is measured as it is, not counted, and tried again up to the limit
before the stage goes on. The reload waits RELOAD_S for the video.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 02:04:59 +09:00
javis-bot
6d0b3d5bec fix(m0): get a stopped or reloaded YouTube player going again and measure the window again
On the gaming PC the player errored about 38 s into the first window with
Jarvis off; the kit had no way to notice, so every later window measured a
paused, empty player, and after the user reloaded the page the injected
counters were gone and the snapshot script threw, ending the stage early.

- The snapshot reports a lost page (counters gone, or the script could not
  run while the page loaded) and the player's own error screen (first line
  only, bracketed IDs removed) instead of throwing.
- Before each window the kit presses play on a stopped player and loads the
  page again when that is not enough, or when the page was lost or errored.
- A window the player spoilt (error, reload, pause, ad, seek, buffering, no
  frames) is measured again, up to 3 times in all, with the earlier attempts
  and the fixes kept in the row; a lower quality or frame rate is not, since
  a busy GPU can cause it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 01:54:34 +09:00
javis-bot
37e27a2648 fix(m0): count only video windows that played 1080p60 under the cap they claim
- A window counts only when the player kept the asked quality and height
  the whole time and played the source's 60 fps; a player stuck below
  1080p is a stage error, not a note.
- Pauses, seeks and buffering are counted inside the page during the
  window, so a pause that ended before the last snapshot no longer
  passes as GPU stutter.
- A capped window whose cap found nothing to pause, ran no pause cycle,
  or could not pause or resume a process is an error and does not count
  for the cap.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 01:01:28 +09:00
javis-bot
a6908c386e docs(v2): turn the GPU cap off by default and measure video stutter instead
User decision (2026-11-11): the GPU share cap stays a setting but its
default is 100 % (off), since gamemode_tune showed it did not lower the
utilisation and only slowed the LLM. Whether the setting stays is decided
by the new M0 video_drops stage (a YouTube video's dropped frames with
Jarvis off, idle and busy, busy without and with the 95 % cap).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 00:55:26 +09:00
javis-bot
457b8636fa feat(m0): measure a YouTube video's dropped frames next to Jarvis
User decision (2026-11-11): the 95 % GPU cap is off by default because
gamemode_tune showed it did not lower nvidia-smi's utilisation and cost
6 to 10 % of the LLM's output. The worry behind it was a video stuttering
next to Jarvis, so the new on-demand stage video_drops measures that:

- A public Blender upload plays at 1080p60 in a throwaway Chrome/Edge
  profile (removed afterwards), driven over DevTools with a small
  standard-library WebSocket client, so no package is added to the
  already built venvs.
- Each window counts the video's dropped frames (the player's own
  counter) and the gaps over 50/100 ms between shown frames
  (requestVideoFrameCallback); windows with an ad, a pause, the end or a
  new video are kept but not counted.
- Rows: video alone, Jarvis idle (normal placement with the STT room and
  1 GB for other programs), Jarvis busy (LLM answering, STT transcribing
  ten speakers back to back) without and with the cap in A B B A order,
  then the video alone again. The cap pauses the engine and the STT
  worker only, never the browser.
- run_m0_video.bat runs just this stage.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 00:55:26 +09:00
javis-bot
a4f77c3261 docs(v2): compare the paused-partials result only with the 2 s pace
The 64.9 tok/s game-placement run was compared with the 64.4 tok/s
normal-placement run, which uses different expert, context and image
settings. Compare it only with the 2 s pace of the same placement, and
state that the final transcription in the kit is one fixed sample at
beam 1, so the real beam 2-3 / long-utterance final latency with paused
partials is still unmeasured (to be measured in M1).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 00:42:40 +09:00
javis-bot
aa34f707b5 docs(v2): record the gamemode_tune results
- Normal placement with the STT room and 1 GB for other programs:
  expert VRAM 1.5 GB, 1.8 GB left at the STT peak, context TTFT back
  to 1.9 s (was 7.5 s), 64.4 tok/s alone.
- Game mode pauses STT partials while the LLM answers: 64.9 tok/s vs
  37.5 tok/s at a 2 s pace, final wait 0.001 s vs up to 1.2 s.
- The 95 % GPU cap paused for 5.2 % but nvidia-smi utilisation did not
  drop (96->98 %, 40->39 %) and decode was 6-10 % slower; whether to
  keep it is pending a user decision.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 00:40:43 +09:00
javis-bot
ba662ae199 fix(m0): never leave a process paused when a resume fails under the GPU cap
A resume that failed was only counted, and the process stayed suspended
after the cap ended. DutyCap now keeps what it still owes per process,
does not stack another suspend on it, retries the resume every period
and at the end, treats a raising call as a failure, and reports any
process it could not resume as left_paused (an error for the row).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 23:56:57 +09:00
javis-bot
d0938c10f9 docs(v2): record the 1 GB room for other programs and the 95 % GPU cap
User decision (2026-11-10): the normal placement also subtracts a room
for other programs (default 1 GB, a setting), and the service manager
pauses the LLM engine and the voice worker together for 10 ms of every
200 ms (95 %, a setting, 100 % is off) in every stage. Both are to be
measured with M0 gamemode_tune.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 23:52:57 +09:00
javis-bot
0e50c558d1 feat(m0): measure the 1 GB room for other programs and a 95 % GPU cap
User decision (2026-11-10, room to watch a video next to Jarvis): the
normal placement leaves 1 GB of VRAM for programs opened later, and
Jarvis's GPU work is capped at 95 %.

- gamemode_tune's normal rows take OTHER_ROOM_MIB off the expert budget.
- gpucap.DutyCap pauses the Strata engine (strata.exe --serve under the
  kit) and the STT worker with their children together for 10 ms of
  every 200 ms (NtSuspendProcess), and always resumes them.
- Every row samples nvidia-smi utilization.gpu; capped rows have an
  uncapped twin (normal with and without the STT, game 2 GB with 2 s
  partials) so the run shows the cost and what the GPU really gets back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 23:52:57 +09:00
javis-bot
3f0ed4343b fix(m0): pace STT partials only in the game placement
User decision (2026-11-10): without a game the STT keeps every partial
pass while the LLM answers. gamemode_tune now measures the normal
placement with the STT room and back-to-back STT only, and paces the
2 GB game placement (back to back as the same-run baseline, every 2 s,
finals only). Docs say the slowdown applies in game mode only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 21:37:16 +09:00
javis-bot
b3c26417d1 docs(v2): record the 2 GB game minimum, the STT room and paced partials
User decisions (2026-11-10): the game-mode minimum on a 16 GB card is the
2 GB expert placement, the normal placement leaves the STT its share by
formula instead of Strata's automatic placement, and STT partials slow
down while the LLM answers with finals handled at once. Also notes the
user's report of occasional, minor frame drops during the live run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 21:35:23 +09:00
javis-bot
2a85b6afa5 feat(m0): measure the normal placement with room for the STT and paced STT partials
The gamemode_stt run showed Strata's automatic placement filling the card
next to the STT (15.9 of 16.3 GB, first token 1.6 -> 7.5 s) and the STT's
back-to-back partial passes cutting LLM output to a third. The new
gamemode_tune stage measures both fixes the user chose:

- stt_room: one start without experts (STT loaded) gives the LLM's base
  VRAM; --expert-vram gets what is left after the STT's ten-speaker
  growth (from this PC's stt stage) and a 768 MiB margin.
- stt_pace: a ten-speaker partial pass every 2 s, or none, with finals
  every 0.5 s and finals first; records final wait and STT GPU share.

run_m0_gamemode_tune.bat runs it unattended.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 21:35:23 +09:00
javis-bot
a2e4f064d2 docs(v2): mark the game-mode latency sums and causes as estimates
The voice-start figures add medians from different runs and leave out
the TTS, the VRAM-full cause of the 7.5 s first token is a hypothesis,
and the 2 GB placement is 2.1x faster with the STT on the GPU but 1.5x
with it on the CPU.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 21:14:25 +09:00
javis-bot
7da86262de docs(v2): record the LLM next to the STT and in a real game
gamemode (third run), gamemode_stt and gamemode_live finished on the
game PC. The STT on the GPU takes 2.7 GB at its 10-speaker peak, as
estimated, and leaves the game 3.6 GB (experts 0 GB) or 2.6 GB (2 GB).
The STT stays on the GPU in games: on the CPU one utterance takes
3.0-3.8 s. In a real game the 2 GB expert placement is twice as fast as
0 GB. The GPU contention between the STT and the LLM, the in-game floor
placement and an STT margin for the normal placement wait for the user.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 21:12:19 +09:00
javis-bot
290a4c9dcf fix(m0): record an STT load without timings as a gap, not a pass
A worker that did not stop in time returned its earlier "loaded" note, was
killed, and the placement still counted as ok with no transcription times.
finish() now reports a timeout, and a worker that timed out, died, never
started or measured no ten-speaker or single-clip timing is an error, so
the stage is partial and the next run retries it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 19:16:14 +09:00