met.no's sleet symbols were mapped to WMO 66/67 (freezing rain), so the
answer said 어는 비. They now map to the WMO 4677 rain-and-snow codes
68/69 and 83/84 (진눈깨비, 진눈깨비 소나기).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
DuckDuckGo now serves only its bot-check page (game PC and host alike), so
every search fell to Wikipedia full-text search, which picked unrelated
pages (박진영 for songs for a rainy day, 대한민국 for a graphics card
ranking). Live 2026-11-18 answers took 9-15 s and were wrong.
- Exa's free MCP endpoint (no key) is the first provider after the
live-broadcast Chrome; it returns page text, so no fetch is needed.
- Gemini runs only when Exa found nothing and a CLI login (oauth) or key
(apikey) is present; without a login the CLI is no longer started
(about 2 s per search).
- Wikipedia is used only when the page title is named in the query;
otherwise the honest nothing-found envelope.
- Letters of a script the user did not use are dropped from the query
(the model searched '사과와 배 중哪个가 더 단가요').
- DuckDuckGo removed; spec, docs and tests follow the new order.
- weather: any forecast failure (not only requests errors) tries met.no.
Real model (qwen3.6-35b-a3b, game PC), real network: graphics card
ranking, apples vs pears, rainy-day genres and black holes all answered
correctly in 3.7-5.2 s.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Live 2026-11-18 the open-meteo forecast timed out three times (geocoding
worked) and every weather question ended in 'service unavailable'. The
forecast now waits 6s instead of 10s and then asks met.no (no key),
mapping its symbol to the WMO code the Korean sentence uses.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Free memory is nvidia-smi's memory.free in the app and the voice worker, so the
driver's reserved share no longer counts as free. A card reading still running
when an answer ends finishes on its own and then logs, so an answer shorter
than one reading is logged too, and the answer still never waits for it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The app logs how much of the card is free once the model answers, and the
voice worker reads the card once a second while an answer or a scheduled task
is written and logs the least free memory seen (no text, llm tab), so a slow
answer can be matched to a full card.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every call that no later request continues (call_llm_direct,
call_llm_streaming, the warm-up and the v1 intent judge) now sends
"strata_checkpoint": false on the OpenAI-compatible path. Strata's
Qwen3.6 engine then gives that call's session away first, so with two or
more requests at once a reply's tool turn keeps its session through the
short calls made between its steps. The reply loop's chat_with_messages
is not marked (its next step continues it); the Ollama API gets no new
field. With one request at once nothing changes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Strata reads every reply prompt from the start in 2,048-token steps. The v2
compact prompt carried v1's full tool guidance and constraints (about 900
Qwen3.6 tokens) on every turn with a data tool, and the reply-language
default (about 120 tokens) twice.
COMPACT_TOOL_GUIDANCE keeps the same rules (act instead of refusing, facts
only from the result, look up named things, auto-derived and self-contained
arguments) in about a quarter of the tokens, without English examples; the
reply-language default says the same in half. v1's prompts are unchanged.
Measured on Strata (Qwen3.6, 20 lines of recent conversation): a weather
turn's prompt 3,436 -> 2,722 tokens, a search turn's second call
4,096 -> 3,383. Evals (compact prompt + intent judge, Qwen3.6): 24/24
before, 30/30 twice after (weather location, follow-up arguments, tool-skip
confabulation, search language, reply language, Possessor fidelity, reply
length, multi-turn context).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
After the one nudge, a second answer without the tool no longer goes out
as it is: the turn takes the planned path (the planner runs then, one
extra call only on this failure) and the skipped-tool guard runs the
planned tool, so a made-up "24 degrees" answer cannot reach the user. A
plan that needs no tool (a question back to the user) still lets the
answer go out.
Evals (qwen3:8b, EVAL_COMPACT_PROMPT=1 EVAL_INTENT_JUDGE=1, 3 runs):
the five tool-skip/weather/screen/follow-up/router files 72/84 (71/84 on
0.1.20, same known failures); Possessor director-then-filmography 0/3,
also 0/3 on 0.1.20 (qwen3:8b stops after one search; webSearch turns are
still planned).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
When the router's only pick is a tool that does its job in one call
(getWeather, logMeal, fetchMeals, screenView) and the chat model calls
tools natively, the planner no longer runs: on Strata it averaged 2.5 s
per tool turn (2026-11-16 16:45-16:58 engine log, 9 calls) before the
answer could start. Search, browsers, schedule, notes, chat channels and
picks of two or more tools still plan. The rule reads the router's pick,
not the words, so it is language-agnostic.
Without a plan the skipped-tool guard has nothing to run, so these turns
get one nudge instead: an answer given before any tool ran is dropped and
the model is asked to call the tool (or ask for a missing detail).
Evals (qwen3:8b, EVAL_COMPACT_PROMPT=1 EVAL_INTENT_JUDGE=1, 3 runs of
tool_skip_confabulation, weather_autoderive_location, screen_view_tool,
followup_supplies_missing_tool_arg, tool_router_implicit): 71/84 before,
72/84 after, same known failures; planner calls 14 -> 3.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- botBrowser `play`: searches YouTube for the words as said, opens the first video (not an ad,
without the playlist) and starts it, in one call (an address given opens that page); `type`
also takes `query`. Live 0.1.19: the model stopped on YouTube's home page or the results, a
retry was refused as a third call, and the answer still said the video played.
- `brain.location` (기본 위치, default 대한민국) goes to the brain as `location_name`: the time line
says it without GeoIP (no database on the game PC), and getWeather without a place uses it.
- Planner and webSearch keep search words in the user's language (never translated into
English), so recommendations fit where the user is.
Evals (qwen3:8b, 3 runs): play ending on a playing video found with the words as said 0/6 -> 5/6;
Korean searches for Korean requests 6/9 -> 8/9.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Playback sends how long the clip playing when a request was stopped had played (tts_played
last_ms); the worker cuts the last sentence of that recording to it.
- botBrowser open takes the search words as plain `query`: the tool puts them, encoded, into the
address's empty search parameter or types them into the site's search box. The description
tells the model to search this way and never put words into an address itself (live: 아이유
hand-encoded into 아이우). Eval (qwen3:8b, 3 runs): right words reach YouTube 1/3 -> 3/3.
- When a page's main video does not play (also after the tool pressed play, or it failed to load),
a note after the page says it is not playing and not to say it plays. Eval: a paused video
reported as playing 1/3 -> 0/3.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Playback tells the worker how much of each request was played (tts_played); the worker keeps a
spoken answer's recording only that far (an answer stopped mid-way no longer keeps its unheard
rest, and is marked stopped); nothing played or never reported: no file.
- Old recording day folders are also removed with the first recording of each new day.
- response.interrupt off, latest: a request whose final comes after a newer one's is replaced
instead of replacing it.
- botBrowser presses play on a page's paused main player also after open, not only after a click.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Alone with Jarvis, whatever the speaker says is answered without asking the judge. With others
present the judge is told how many people are in the channel and how many may call Jarvis: with
one other person most of what the speaker says counts as said to Jarvis (unclear is yes); with
more, or not known, the question is the group one it was before. Live 2026-11-16: alone in the
channel, questions without the wake word got no answer because the judge assumed a group.
Eval (qwen3:8b, pair cases): 3/7 before, 6/7 after; group cases unchanged.
Also: the protocol test fixture's brain takes the trace argument (the test failed since traces).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 로그 screen: "보이는 글 txt로 저장" (logs_save_text), a 대화 view that saves the days'
conversation with every trace in full (history_export), and a 목소리 view with the
voice.record switch and the days' recordings as a zip with an index (voice_export).
- Voice worker: with JARVIS_RECORDINGS_DIR (voice.record, off by default) each final and each
spoken answer is kept as a WAV with an index line; day folders older than 7 days removed.
- response.interrupt (default on): off, latest/important finish the running answer first.
- Bot browser: Chrome lets pages start video and sound; botBrowser reports each page's media
state, waits for a player to start after open/click, and presses play on a video page a click
led to when its player stayed paused (live: a clicked YouTube video stayed paused).
- webSearch reads `query` when `search_query` is missing (live: both searches of an answer failed).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A trace is now kept the moment the request arrives (at the time it was
asked, ms -1), its steps are stored as the engine adds each one, and it
ends with the answer. Traces a killed run left unfinished are closed at
start. The 대화 screen reads a trace still being made as pending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Stretching all of the speed-up from 1.0 kept every sound but sounded
awkward (UTMOS 3.13 at 1.5, against 3.73 for MeloTTS's own 1.5), while
MeloTTS's own speed past 1.25 drops sounds (sentence-final "요" and first
syllables, 4.6% character errors at 1.5). MeloTTS now speaks up to 1.25
and the WSOLA stretch does only the rest, with a 5 ms search: 2.6% and
UTMOS 3.56 at 1.5 through the real child. Version 0.1.6.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
MeloTTS's own speed shortens every sound and slurred fast speech (Whisper
large-v3 on five Korean sentences, three renders each: 5.5% character
errors at 1.5 and 20% at 2.0, against 1.4% at 1.0). The MeloTTS child now
speaks at most at its natural pace and makes faster speech with a WSOLA
time stretch that keeps the pitch (1.9% at 1.5, 2.2% at 2.0, about 15 ms
per 4 s of speech).
A voice.tts.speed saved while the services run goes to the worker at once
(new tts_speed message) and applies from the next sentence; the client
sends it again whenever the worker connects again. Version 0.1.4.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- screenView tool (screen_view.spec.md): whole screen, monitor by number, window by part of its
title or program, or the list of monitors and windows; fast, normal or detailed pictures.
- The app captures with Windows Graphics Capture (app/src/screen.rs, admin.spec.md "Screen
viewing"), decides for the asker (only people registered for PC control), never picks, lists
or shows excluded programs (pcControl.screenExclude, password managers by default), refuses
minimised windows and black pictures, and records screen.view in the activity log.
- Pictures ride on the tool message (ToolExecutionResult.images); llm.py sends them to
OpenAI-compatible servers as image parts after the tool messages. They stay in that reply only:
not in the tool carryover, logs or prompt dumps.
- The LLM reads pictures only when screen viewing is available (--vision gpu normally, cpu in a
game), measured apart for the placement; otherwise screenView is a disabled tool.
- Worker: screen_action / screen_action_result, 4 MiB messages.
- Eval evals/test_screen_view_tool.py; Windows check tests/screen_windows.rs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On the shared screen a tab brought to the front makes Chrome bring its window forward and take the
keyboard focus from the game or program the user is in (seen on the game PC). The botBrowser tool
now opens each person's page in a window of its own, behind and at the place and size of the bot
browser's window (Target.createTarget with newWindow and background), and closes it again if the
connection to it fails. While the browser runs on the virtual monitor, the app looks for new Chrome
windows every 200 ms and settles each like the first (tool window, fitted to the work area, without
activating it), the newest in front of the older ones, so the shared screen shows the page the bot
opened last.
Checked on the game PC: the bot's window loading a public page comes in front of the first, both
out of the taskbar and Alt+Tab, the focus staying in Discord also with the user idle for hours.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each collection target can announce new items at once or in a daily digest
(off by default) in collect.notifyChannel, as titles and links only, with no
LLM; each post is recorded in the activity log. The brain gets a read-only
collectedNews tool (every target's newest items by default, fenced as
untrusted web content), offered with the app's collection file and the
collection feature, and available to scheduled tasks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A personalNotes tool (add, list, delete the asker's own notes) offered only
with a notes backend. The app keeps the notes in config/notes.json and sends
the asker's with every voice, chat and task reply; the reply engine puts them
in a <person_notes> fence as that person's preferences, which never permit an
action or a tool. The worker's schedule bridge becomes a shared app bridge
for schedule_action and note_action. A 사람별 지침 screen edits and deletes
any note; features.notes turns the tool and the notes off.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each chat channel action the brain's tool asked for and each schedule
delivery is recorded in activity/<day>.jsonl by kind, target, who asked and
outcome, never its text, kept 30 days. The worker's chat_action carries the
asker. A 한 일 screen lists the newest entries.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The brain gets a schedule tool (add, list, delete the asker's own reminders,
timers and tasks) offered only with a schedule backend. The voice worker asks
the app through schedule_action and runs fired tasks as reply via task with
read-only tools, no MCP and a fresh short-term memory. The app keeps the
schedules in config/schedules.json, fires them every 5 s, speaks them when the
person is in Jarvis's voice channel and otherwise posts in the chat channel
they asked in (or schedule.chatChannel for voice). A feature switch and a
예약 screen list and delete everyone's schedules.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- the app's ready message says whether the game stage runs (llm ready game=true); the worker then
holds partial passes while a reply is being written and runs them again, the newest audio per
speaker, when no answer is; finals never wait; without a game nothing changes
- M0 gamemode_tune decision: the game placement answered 1.7 times faster with partials held
(64.9 against 37.5 tok/s with a partial pass every 2 s)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- the normal stage reads other programs' memory afresh (the card after the LLM stopped, less the
STT worker's model) and keeps it; the game stage counts from the latest normal reading, so the
game is not counted against its own reserve
- a restart that fails brings back the stage that ran before and tells the brain ready; the
failed stage is tried again after 60 s, three times at most; when nothing comes back the brain
is told paused so requests fail at once
- the worker client keeps the latest llm state and sends it first on every connection
- switches are numbered: llm switching carries an id, llm_idle names it, and a late idle of an
earlier switch no longer lets a new one through
- a request that waited 180 s for a switch fails without calling the brain
- the dashboard shows the stage that runs also on a fallback placement without experts
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- while the services run, game mode decides the stage (perf.rs): a game means the game stage at
once (or pause with game.pauseInGame); its end brings the normal stage back after
game.revertSeconds (default 30)
- a change tells the voice worker the LLM switches (llm switching, with a notice), waits until
the brain has written the answers in progress (llm_idle, at most 2 minutes), restarts the LLM in
the stage and tells the worker it is ready or paused
- the game stage runs at 16K context, one request at a time, half the engine's CPU threads and
the game placement (reserve game.reserveGb, default 8, else 2 GiB, else 0 GiB, else pause),
measured once at that context; every placement of a run counts other programs' memory as it
was when the services started
- the voice worker gates every LLM use: on switching new work waits (at most 180 s), the first
spoken request that waits hears the notice once under its own id, on ready all go on, on
paused nothing is answered
- dashboard: "성능 단계: 게임 중 · 게임에 X GB" / 일시정지; game mode screen: game VRAM, revert
wait, pause in game
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- each asker has a tab and connection of their own (at most 5, least recently used closes first)
- links, forms and window.open that would open a new tab load in the same tab
- one 15 s deadline covers connecting, the action and the page; events do not extend it
- a broken connection retries only open and read; click, type and back may have run and are not repeated
- <<< and >>> in page content are replaced so it cannot close the fence
- the description says how to search on a site (open, then type with submit=true); eval case 0/3 -> 3/3 on qwen3:8b
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
open, read, click (label or [n]), type (optionally Enter) and back; page content comes back fenced
as untrusted data; only http(s) addresses; no LLM call. Offered only when the app started the bot
browser (JARVIS_BROWSER_CDP) and the browser feature is on; meanwhile fetchWebPage, which has no
address guard, is not offered. Eval evals/test_bot_browser_tool.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- IPv6 counts as public only in 2000::/3 (without 2001::/23, documentation and 6to4), so site
local fec0::/10 and IPv4-compatible addresses are refused; the collector uses the same rule
- every proxy connection is a task of one set: a stop ends the open CONNECT tunnels and waits
until their sockets are gone
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The request line is ASCII: other characters and spaces in the path and query go as UTF-8 %HH,
while existing %HH and separators stay.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The name lookup runs on a daemon thread waited for only until the deadline, and a watchdog
shuts the connection down at the deadline, so a server that sends its status line or headers
byte by byte within the per-read limit is cut off too. A response cut short is a failure.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- the fetcher resolves once, requires every address to be public and connects only to those
(TLS still checks the name), so DNS rebinding cannot reach the local network; redirects too
- 15 s for the whole fetch also against servers that send slowly; no URL in any log line
- a site whose title alone changed is kept again
- target names that differ only in case are refused (one Windows folder)
- the worker always gets the collection file, so results older than the keep days go also
with no targets or the feature off
- the results screen lists every target with results, not only those in the newest 100
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Targets (none by default), interval and keep days on a new 백그라운드 수집 screen with the
results; the worker collects on its own thread through the web search's address check and
writes only to the data folder's collect/ (logs carry target names and counts).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Discovery runs outside the MCP tool cache's lock (one at a time), so a turn reading the cached
tools never waits for a slow server; a new conversation refreshes in the background.
- The log hub masks secrets before a line is kept or written, so a key replaced or removed later
stays hidden on the screen, in copies, files and exports, also after a restart.
- The worker takes JARVIS_MCP_ENV out of its environment at start, before MeloTTS runs, and hands
it to the brain.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Settings `features` (weather, webSearch, meals) and `mcpServers` (name, command, args, env names,
enabled), edited on the new 기능 screen. The tools of a feature that is off go into the brain's
`disabled_tools`; only enabled MCP servers go into its `mcps`.
- MCP environment values (API keys) live only in the encrypted secrets (`mcp:<server>:<NAME>`),
shown as stored or not, masked in logs, removed with their server, and reach the worker only in
`JARVIS_MCP_ENV`, which the brain takes out of its environment before giving each server its own.
- `enabled_builtin_tools(cfg)` is the one list the router, toolSearchTool and the executor use, so
a turned-off tool is neither offered nor run, also when the model names it.
- The v2 brain never offers v1's `localFiles` (home folder read/write/delete) and `screenshot`:
anyone in the voice or chat channels could ask for them. Screen viewing comes in M7.
- The brain connects MCP servers on its own thread and logs each outcome without debug logging.
- Stored secrets are masked in the log hub as soon as the data folder is found.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
M5 step 4, second part. The services start the LLM first: the installed
Strata with the M0 kit's model and normal placement (models in
models/llm, parallel 1, or 2 when a chat channel answers every message,
pictures off, --restart), wait until /v1/models lists the model, and stop
it last. The first start downloads the model; the dashboard shows
Strata's last line and percentage, and stop also cancels a start (the
server is cleared). llm.url uses a server the app does not start.
On every start the app writes config/brain.json (Strata's /v1, the
listed model id, memory/jarvis.db) and hands it to the worker as
JARVIS_CONFIG_PATH. Loading a config with its own db_path no longer
creates ~/.local/share/jarvis.
service_start/service_restart run in the background. Settings gain
llm.context and llm.port (model screen) and llm.url (file only).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- redact: a token with sentence dots around it is masked too.
- Worker error messages are always logged (code and id), so the log screen
and the error report show them without debug logging.
- The voice worker logs with stt, llm and tts categories, so its lines land
in those tabs.
- The zip leaves out the oldest lines by the time they were logged, across
every tab's file, not by file name.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every <parameter> value was passed as text, so a delete confirmed with
confirm=true reached chatChannels as "true" and asked again. Values now take
the type the tool's input schema declares (boolean, integer, number, array,
object); a value that does not fit stays text. The roadmap's eval summary now
names the reply-length failure apart from the later passing runs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- compact_prompt: the v2 persona in a tenth of v1's words, answers as short as
possible, the full tool guidance only on turns with a data tool. A greeting's
reply prompt went from about 4,500 to 1,400 tokens on Strata.
- intent_judge: the tool router judges whether the turn needs tools; the
planner runs only when it does. prepare_intent runs the pick ahead on a
partial transcript (worker message prepare), and the reply reuses it.
- Without stream_browser the screen-share tools are not offered.
- The time context carries the 12-hour form (10:37 was read as pm).
- A <tool_call> block written as the reply is parsed as a call, not spoken.
Evals (Qwen3.6 on Strata, EVAL_COMPACT_PROMPT=1 EVAL_INTENT_JUDGE=1):
221 passed, 4 failed (known failures); new evals/test_voice_reply_length.py
(v2 answers 234 chars against v1's 416) and test_reply_language_default.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The brain passes default_language (worker --reply-language, default Korean) to
the reply engine; unlike the output_language lock it gives way when the user
explicitly asks for a language. Tools get the ko code (--tool-language).
Eval evals/test_reply_language_default.py (Qwen3.6 on Strata): 6/6, English
questions answered in Korean, an explicit English request in English, and the
control without the default answers English in English.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
v1's tts_engine default (English-only Piper) made the reply engine force
English, so Korean questions got English answers. The v2 brain speaks
through the worker's MeloTTS and chat answers are not spoken, so it runs
with tts_engine=melo; an output_language lock still wins.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A person's reply stopped counting as "unanswered" as soon as the worker sent
reply_text, so a delete question that could not be spoken (no TTS, a failed
or stopped speech) or that the app could not post still let the next
"응, 지워" confirm the delete.
- Worker: an answer reaches the person on a tts_done neither failed nor
cancelled (spoken answers), on the app's reply_delivered ok (chat
answers), or at reply_text (unspoken voice answers). tts_unavailable, a
failed or cancelled tts_done, reply_delivered ok=false, no report within
30 s and the session ending all mean it never did: a turn number is
skipped, so the delete asked in it lapses. A reply sent before the
previous answer reached them is still not their next turn.
- App: a chat answer reports reply_delivered with whether Discord took the
post; a late, failed or empty answer reports it was not posted.
- Tests: no TTS, a failed speech, a chat post the app reports failed, and
no report at all do not delete; a spoken and a posted question do.
Conversation and worker client tests for the report.
- Specs: voice_worker.spec.md (reply_delivered, when an answer reaches the
person), discord_core.spec.md, conversation.spec.md.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A delete is confirmed only in the person's very next turn, but turn numbers
were given when a reply started. A "응, 지워" sent while the delete question
was still being written waited for the person's lock and then counted as the
next turn, so the delete went through.
- The worker counts each person's unanswered replies. A reply that arrived
before their previous answer was given skips a turn number, so a delete
asked in that answer lapses.
- After an answer the person never got (failed, or stopped before it was
spoken) a turn number is skipped as well: it asked them nothing.
- Tests with the real chatChannels tool and an agreeing consent check: a yes
sent before the answer does not delete, a yes after a failed answer does
not delete, a yes after the answer deletes.
- Specs: voice_worker.spec.md (turn numbering), chat_channels.spec.md (the
next turn is a message sent after the question was received).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The voice and chat lanes let a person's voice reply start while their chat
reply was still running. The chat delete consent counts "the very next
message" by turn number, so a message that started before the delete was
asked could pass as the confirmation, and the person's dialogue memory
was updated out of order.
- A reply takes its asker's lock, then its lane's: one person's replies
stay one at a time in the order asked, different people's voice and
chat answers still overlap, and a reply waiting for its asker holds no
lane. Test: a person's voice question starts only after their chat
answer.
- Specs and roadmap: the lanes are per person; the roadmap no longer says
voice answers wait behind chat answers.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The voice worker writes voice and chat replies in separate lanes (one
of each at a time), so a chat answer being written never holds up a
voice answer. Tests: a voice reply finishes while a chat reply is still
running; replies of one kind stay one at a time.
- A chat answer arriving 5 minutes or more after it was asked is not
posted, checked when it arrives.
- Specs: the lanes, and that Strata needs --parallel 2 for both lanes'
LLM calls to run at once until the app starts Strata itself (M5).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 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>
- 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>
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>
- 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>