The feature is not wired to the UI yet but is reachable over IPC:
- planning called the premium proxy directly, sending speech to the cloud
even with the local backend selected and failing in local mode
- LLM-provided app names and key combos were spliced into cmd/PowerShell
strings; they are now validated, and combos map named keys (alt+tab no
longer types Alt+T, a, b)
- presets matched substrings and bare nouns ("commute" toggled mute,
"크롬 캐시 지워줘" opened Chrome); they now match whole words only
- a plan without safe=true is treated as unsafe and unsafe shell commands
are not run; URLs go through openExternalSafe
Switching accounts without a sign-out skipped resetToFree, and if the
subscription lookup then failed the new account kept the old one's Pro badge
and ad decision, persisted across restarts.
The chunk store reads whatever database is open at call time, so a query that
was awaiting the model returned an answer built from the previous account's
documents, and a large file being read was inserted into the new account's
knowledge base and synced there. Each operation now remembers the account
scope it started in and stops if it changed.
The lock desktop swallows keyup, so a hold-to-talk recording never ended,
the first shortcut after unlocking was dropped as auto-repeat, and Win from
Win+L made the next suggestion accept wait out the full 1.5s modifier timeout.
On powerMonitor lock-screen/suspend the chord machine now emits released for
emitted triggers and clears its state, and modifier tracking forgets held keys.
stop() during model loading saw no aux model yet and skipped the unload, and
the failure path (e.g. no microphone) never unloaded it, so the caption model
kept VRAM alongside the dictation model until the next session ended.
- Each document gets an indexing run number; a reindex, synced replacement or
delete makes the older run stop instead of embedding stale chunks, reporting
'indexed' early and leaving a progress bar for a deleted document
- Reindexing a file that is now empty throws like addDocument instead of
replacing the stored chunks with nothing
Each 30-second chunk received the previous chunk's text as initial_prompt,
so once one chunk looped on a word the loop became the next chunk's hint
and the rest of the file was the same word. A looping chunk is now
re-transcribed without the hint, looped text is never carried forward, and
runs of 4+ identical phrases or segments are collapsed to one.
Capture still used the old snapshot code: a file copied in Explorer looked
empty and was cleared, and Excel's own formats were dropped on restore. It
now uses the shared clipboard snapshot policy and leaves the clipboard
alone when it couldn't put everything back.
The hidden set lived in page state while the real delete runs from the app
notification after the page unmounts, so leaving and returning during the
undo window showed the item again and it stayed visible after deletion. The
set now lives in a module store and committed ids stay hidden.
Chains were pinned to the premium service, so they always failed in
anonymous local mode and sent text to the cloud for signed-in users who had
chosen the local backend.
Cancel only aborted an in-flight LLM response, which does not exist yet
during STT, so the cancelled speech was answered a few seconds later. A
turn counter bumped by cancel/stop now discards the late transcript.
Setting a channel makes electron-updater allow downgrades, and the channel
check let prerelease channels accept them, so a stable install on beta would
be asked to 'update' down to an older beta.
SQLite lower() only folds ASCII, so importing 'äpfel' next to an existing
'Äpfel' created a second local entry that later collided with the server's
unique index and silently overwrote one spelling. Import now compares with
the same JS identity key as add/update, including duplicates within the file.
Signing in as a different account (e.g. while the previous one was still
waiting on an offline restore) swapped the database under a live
recording, so its final save and audio upload went into the new account.
The sign-out capture shutdown now also runs whenever the open database
belongs to another user.
Checkpoints stay local until stop, so a pull during recording replaced the
saved transcript with the server's empty one; a crash then recovered the
meeting as an error with nothing in it. Status, transcript, end time and
duration of a locally recording meeting are now kept on pull.
Quitting during the few seconds a stop waits for the last caption skipped
the shutdown save, so the in-memory audio and every sentence since the last
checkpoint were lost. Shutdown now saves unless post-processing already
wrote the final result.
The session ignores trailing whitespace but acceptance compared the raw
prefix, so typing one more space after the fix appeared made accept drop
the correction silently and leave the typo in place.
Tags over 80 characters now show a length notice, and adding a tag that
already exists in another case just closes the input, rather than both
landing on a '#tag · retry' badge that repeats the same rejection.
- UpdateService: an already-downloaded version no longer reopens the consent
dialog every 24h, where choosing skip still installed it on quit
- MemoService: export groups and titles by local date so KST 00-09h memos
stop landing under the previous day
- DictationTemplateService: deleting (or remotely removing) the active
session's template cancels the session instead of blocking new ones
- ChainService: update trims names and rejects blank ones like create does
The installer is unsigned, so latest.yml is now signed with an Ed25519 key and the
app verifies the downloaded installer against it before installing.
npm run release -- patch|minor bumps, gates, tags, builds, signs, publishes,
re-verifies the public feed and pushes; --resume continues after a failure.
The retired GitLab registry publisher is removed.
While suggestions are on, typos are no longer replaced silently. The popup shows
the fix next to the candidate and applies it only when the candidate is accepted.
The per-minute request cap rises from 6 to 20 so suggestions keep appearing after
accepting one and continuing to type.
The PC-wide slowdown was not a leak but model residency: boot warmup loaded
gemma4:e4b (~11.6 GB RAM incl. 5.9 GB pinned host buffer, no mmap on Windows
CUDA) and kept it for 30m, next to the large-v3 sidecar. Measured on the HEAD
build: free RAM 7.9 GB -> 32 MB within 20 s; after this change 10.8 GB with no
Ollama model loaded until typing starts.
- single LOCAL_LLM_KEEP_ALIVE (10m) for every local request; no boot warmup
- unload this app's resident Ollama models (keep_alive 0) on quit
- sidecar POST /unload for the aux slot; captions release it on stop
- partial dictation copies only the tail window, not the whole recording
- cap the voice-conversation listen buffer at 5 minutes
- mic test: generation guard so re-entry cannot orphan lease/timers
- startRealtime: single-flight and removeChannel to stop duplicate bindings
- meeting WAV save writes header and PCM without a concat copy
Docs: AI-01 policy note, GAP-PERF-01 with remaining work.
- desktop: mock @nut-tree-fork/nut-js in the shared Vitest setup; template
tests reached the real TextInsertService and libnut killed the worker on the
display-less Linux runner ("Could not open main display").
- mobile: the knowledge realtime test now unsubscribes, so the deletion
reconcile interval no longer keeps Jest alive forever.
- set-forgejo-secrets.mjs syncs every Forgejo secret from the root .env and
refuses local URLs; SUPABASE_URL had been registered as 127.0.0.1:55321, so
payple-renew never succeeded.
Typo auto-correct (INPUT-19)
- TypoCorrectionService + core typo-correction: 2-set Korean layout
mistypes both ways, always-wrong spellings, near-misses of the user's
frequent words, optional model check re-validated in core; applied by
backspace N + paste and cancelled on new keys or window change.
Prediction quality (INPUT-20/21)
- gemma models are sent raw with the user's unfinished sentence pre-filled
into the model turn, so the model truly continues the text (mid-word
joins and spacing exact). Other models keep the instruction prompt.
- Context: text before the caret (opening lines and a fact list of names,
dates, amounts outside the 400-char window), messages just sent in the
same chat window (memory only, 30 min), personal-graph follow-ups and
IDF-ranked related sentences with Korean stemming.
- Guards: first sentence only, restated-prefix stripping (also fixes the
instruction path), repeat drop, no invented dates/names/numbers
(one retry), plain -다 register, no emoji unless the user uses them,
search-box keywords. Fill loop mixes instruction prompts for variety.
- Opt-in real-model probe: tests/integration/suggestion-quality.ollama.test.ts
Suggestions now actually show up
- Terminal (Claude Code): caret trust from the input line, not the whole
screen (status line below the box blocked every keystroke); Korean
composition counts as typing at the end; a grey placeholder filling the
empty box at once is not user text.
- Chrome: UIA focus flicker while typing no longer resets "edited".
- KakaoTalk/RichEdit: trailing paragraph mark ignored for edit position
and stripped so accepted text keeps its separating space.
- While the overlay is visible the suggestion shortcuts are captured so
Ctrl+Alt+Enter no longer also types a newline; released when hidden.
- nut-js preloaded after boot (first accept waited 4.8 s).
CI run 121 failed at "버전·계약 정본 대조": earlier refactors moved update
gating from UpdateService into update-policy.ts (evaluateUpdateOffer ties
decideUpdate + isWithinRollout), the differential-download switch into
update-adapters.ts, and the Forgejo re-release guard into
lib/immutable-package-guard.mjs (sha256 comparison, abort on conflict).
The checks still looked for the old markers in the old files. They now
verify the same guarantees where the code lives, and the self-test's
negative case targets assertNoImmutableConflicts.
Also clears the lint gate: a control-character regex in Keycap (range now
starts at U+0020) and unused helpers in two red-team tests.
Wave 3 of the 2026-09-28 design overhaul.
- Esc (no modifiers) cancels an in-progress dictation, recording or
processing: VoiceModeService.requestEscape() queues the dead 'escape'
action. Clicking the capsule cancels only while recording, so a stray
click during processing no longer throws the text away.
- Errors show in the user's language: bootstrap now passes error.code to
the tip (the translated branch never ran), and one core classifier
(voice-error-message) feeds both the tip and the main-window alert.
- Capsule: bars stay flat without input (no fake "alive" wobble before the
mic opens), an indeterminate bar replaces the made-up percentage, the
partial transcript stays visible while processing, an Esc hint, and a
brief "Inserted" state so success is visible.
- All six popups share popups/_shared (Pretendard, one panel radius,
selection, kbd hints, reduced motion). History/command popups get
titles, listbox roles and window sizes from popup-list-geometry (empty
states were clipped); the command popup's "0" key is registered;
result popup explains why it appeared and can be closed; captions keep
a theme-independent dark backing on purpose.
- Popup themes follow the OS when set to system and the document lang
follows the app language.
- Site hero demo mirrors the new capsule (done state, indeterminate bar,
Esc hint; 10 locales).
Wave 2 of the 2026-09-28 design overhaul ("records are the main
character, a quiet instrument"). Decisions: design.md.
- Shell: sidebar with primary Home / Records / Meetings (Ctrl+1..3) and a
secondary "Tools" group; every item is a button with aria-current.
The status bar is removed — its "100% LOCAL PRIVACY · ZERO CLOUD SYNC"
claim contradicted device sync; the sidebar shows only queried state.
- Navigation context (routes, params, back, useRouteRequest) so Home can
open a specific meeting or record.
- Home replaces the dashboard: dictation key, start actions, only real
problems, one-line summary, recent records and meetings, file
transcription, free-tier limits.
- Settings become a full-screen route with vertical tabs (tabs no longer
clip) and a shared row grammar; long-standing bugs fixed: team and
enterprise tiers crashed the license tab (currentTier undefined),
first-run onboarding could not be left, Pro+ saw "upgrade to Pro+".
- Records: date-grouped single list with in-place expansion, search and
tags together, mode/favorite filters, load more past 50, undoable
delete. Meetings: list with search/rename/delete, summary-first detail
(summary | transcript | documents | my notes), notes persisted locally
instead of being lost. Tools pages cleaned up; stale-closure example
chips and a 1550x mouse-distance bug fixed.
- Shared pieces: PageHeader, EmptyStateCard, SearchInput ("/" works),
ConfirmDialog, notify with undo; display-labels maps domain values to
typed i18n keys so missing keys fail to compile.
- Mono font stack falls back to Pretendard for Hangul (Korean labels no
longer render spaced out).
- i18n: new ko/en keys via scripts/i18n-add-keys.mjs (one read-merge-
write so parallel editors cannot clobber locale files).
Some renderer files also carried pre-existing in-flight changes (error
recovery deep links, meeting document hooks); they are included as-is.
Batch of red-team r3 fixes that were in the working tree before the
2026-09-28 design overhaul, committed as one unit with their tests.
- desktop main: STT timeouts and sidecar, voice recording store, sync
(credentials, audio, knowledge reindex, push gates), runtime
provisioner, update policy, AltGr keybindings, voice-command policy,
dictionary file codec/limits, meeting transcript condensing and a
local recording ledger so interrupted-session recovery only closes
meetings this device recorded (a phone's live meeting is left alone).
- mobile: login CSRF via implicit token callbacks rejected, account
deletion/retention, durable queue retention, knowledge realtime
without unfiltered DELETE, meeting re-record failure paths, cloud STT
client, preferences store/resync.
- core: text chunking splits long unbroken transcripts to fit, template
field policy, dictionary limits, meeting markdown inline handling.
- server: payple webhook policy and cancellation order scope, meeting
document generation quota, team RPC null-role guard, unified LLM
quota in-flight accounting, knowledge chunk vector index, meeting
re-record failure paths (migrations 20260929*).
- ci: portable/runtime feed gates, update-policy schema, Forgejo file
delete and alias planning.
Four older tests are updated to the new contracts rather than the old
behavior: token-pair auth callbacks are rejected, knowledge realtime no
longer subscribes to DELETE, long transcript lines are split, and
meeting recovery requires the local recording ledger for empty rows.