The first cut replaced any Hangul word within one jamo of a learned term.
Measured against the real local corpus (three stored meeting transcripts)
it changed 286 of 3,005 words: 하면 became 라면, 이제 became 이게, 매일 became
메일. Most of what the app learns from typing is ordinary grammar, so
distance alone cannot separate a misheard word from a correct one.
Deterministic correction now covers only dictionary pronunciations and the
Latin identifiers the user types, preserving their casing. Korean terms
still bias recognition through the prompt hint and guide the polish
prompt. Re-measured on the same transcripts: 0 of 3,005 words changed.
Hangul-layout typing artifacts (dkssudgktpdy) are dropped from the hint.
The tree carried uncommitted work from several areas (web push, mobile
screens, admin charts, test-hygiene cleanup, CI and map docs). It is landed
as one commit so the release pipeline can start from a clean tree; the
desktop transcript-correction behaviour shipped in the previous commit and
is unchanged here.
Meeting and caption transcription never used what the app had already
learned: speech recognition ran with a fixed Korean prompt, the refine
prompt had no glossary, refined lines stopped inside the caption service,
and the saved transcript was a raw join of segments. Names and jargon the
user types every day were therefore re-mangled on every recording.
The learned corpus (user dictionary plus personal phrases) now feeds one
glossary that biases recognition, fixes mistyped words deterministically
right after each line is finalized, and is handed to the local model when
it polishes a line. Refined lines also reach the meeting transcript and
screen through a new segment-updated event.
Corrections never touch words the user actually wrote, refuse ties between
equally likely candidates, and keep particles intact.
Acceptance waited for modifiers using only the uiohook-tracked set; a missed keyup
made it time out after 1.5 s and paste while Ctrl/Alt counted as held, so nothing
was inserted. Trust GetAsyncKeyState instead, and suppress new suggestions while an
accept is in flight.
Typed deltas were saved per snapshot (every 0.4-0.8 s), storing mid-word fragments.
Buffer them per field and save one diff on idle, sentence end, send or focus change;
drop short pieces, URLs, trailing jamo and truncated emoji.
The window survives a renderer crash, so the get*Window() getters never
recreated it and the popup stayed blank until the app restarted (and a
crashed suggestion overlay could still swallow clicks). On crashed, oom or
abnormal-exit the ready flag is cleared and the renderer reloads, at most
once per 30s so a renderer that keeps dying is not restarted in a loop.
The login item now passes --autostart (also used when querying it, which
Windows needs to match the registration). On such a launch the main window
is shown inactive instead of focused, flashed and pinned on top for a second,
so typing that already started in another app is not interrupted. Existing
registrations migrate on the next startup sync.
The tip drew its done state on session-completed, before the async insert
ran and even when auto-insert was off or the text was empty. A failed insert
also left the screen-saver-level tip over the result popup's copy button.
session-completed now says whether an insert follows, VoiceModeService emits
text-inserted on success, and the tip hides first when the insert fails.
The popups are non-focusable, so nothing closed them except their own toggle,
Esc or a selection, while they held Enter, arrows, Esc and 0-9 as global
shortcuts. Typing "3" or Enter in another app inserted a history entry or
switched the active command. A click outside the popup (converted from
physical pixels to DIP) or 15s without a navigation key now dismisses it and
releases the keys.
- Settings > Input: the excluded-apps field was reset from every telemetry
snapshot (several per second while typing), so edits vanished before blur
saved them; it now syncs only when the saved list changes
- Templates: a failed save (e.g. deleted on another device) closed the dialog
and dropped the edits; it now stays open and shows why, and a failed
session start is reported too
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.