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 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 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
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.
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.
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.
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.
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.
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.
With a 100 ms trigger left in the installed config, generation started in the
gaps between keystrokes; the next key ended the session silently, and that
session still counted against the 5 s minimum interval, so the moment the
user actually paused nothing came (rate-limited). The log showed a
generate-then-vanish cycle every 5-6 s.
The trigger delay now has a 500 ms floor and settings revision 6 resets a
stored value below it to 600 ms. A session ended because the user kept typing
no longer blocks the next request by the minimum interval (per-minute and
daily caps still apply), and that dismissal is logged.
With the embedding server unavailable every chunk failed, yet the document
was stored as indexed=true with 0 chunks, so the knowledge base listed it as
searchable while queries could never match it. The red use-case test caught
this; it had been written off as an environment failure.
Now a run with zero embedded chunks leaves indexed=false and throws
RAGEmbeddingFailed (surfaced by reindex, logged by addDocument).
Tests that only hold on the Windows developer machine now declare it: the
bundled SoX binary and PowerShell device discovery run on win32 only, and
the sidecar venv test runs only when sidecar/.venv exists. The Linux Forgejo
runner skips them instead of failing.
The speech engine now keeps an auxiliary model next to the dictation model
and transcribes with whichever the request names, reloading it once if the
engine restarted. Settings > STT gains a live-caption model so captions can
run on large-v3-turbo while dictation keeps its own model. The runtime
minimum rises to 1.7.0 because older engines would silently ignore the
model choice.
Suggestion paging moves to Up/Down: the page follows the selection and the
last item waits while more candidates are being generated. The Left/Right
page shortcuts are removed; they did nothing until a page had filled and
clash with Intel's display-rotation hotkeys.