Phase 10b colour push: theme reads as Magnotia, not "subdued generic dark".
Same lightness band as Phase 10a (AA preserved), more chroma across accent,
status tokens, and zone surfaces.
Dark accent: #c98555 -> #d68450 (subtle/hover/glow recomputed).
Light accent: #a06a3e -> #a3683a.
Dark status: success #7ec89a -> #5fc28a, danger #e87171 -> #e85f5f,
warning #e8c86e -> #e8be4a.
Light status: success #2f7549 -> #1f7344, danger #a83838 -> #b32626,
warning #b89a3e -> #a08a1f.
Sensory zones pushed further apart so each zone reads as its own
environment: cave cools toward blue-grey, energy warms toward red-orange,
reset cools toward green. AA on body text verified for every Card surface
in both themes.
Stale accent rgba (201,133,85) replaced with new (214,132,80) across nine
files. --shadow-accent in colors_and_type.css mirrored.
No secondary tint token added: Magnotia's identity is amber-as-the-only-
meaningful-colour. Cheaper to add a second meaningful colour later if a
real need appears than to dilute the discipline now.
Default surfaces, text tokens, and borders untouched per scope.
Per the project's no-dashes feedback rule (see CORBEL-Main memory
feedback_no_dashes.md), em-dashes in user-visible copy are the single
biggest "AI wrote this" surface tell. Forty-two occurrences across ten
files: ten in SettingsPage's group descriptions and option labels
(audio device picker, vocabulary help, prompt placeholders, model
descriptions), four in FirstRunPage's setup steps, three in
DictationPage / FilesPage / Energy chip tooltips, plus the privacy
bullets ("100% offline, no Python required, no cloud, no accounts,
no telemetry"), the rejection toast, MicroSteps thumb labels, and the
shutdown ritual prompts.
Replacement rule: subordinate-clause em-dashes followed by lowercase
become commas; sentence-break em-dashes followed by capitals become
full stops. Code comments left intact.
One non-em-dash regression caught while reviewing: TasksPage's energy
filter "no selection" placeholder showed "—" as a literal label; the
script changed it to a comma which read as a UI bug. Replaced with
"Any" instead.
Record button had active:scale-[0.93] transition-all, which contradicts
the brand motion guideline ("never bounce, slow, calm, deliberate"). The
record button is the most-touched control in the app; a 7% press-shrink
on it sets the wrong tone for everything else.
Removed the scale transform, removed the inline transition-duration
override (the global * rule in app.css already animates the named
properties at --duration-ui). Also updated the inline shadow rgba from
(232,168,124,0.3) to (201,133,85,0.3) so the glow tracks the new
a11y-darkened accent fill instead of the pre-Phase-10a amber.
Replace all instances of the legacy product names "Kon" and "Corbie" with
"Magnotia" across user-facing copy, code identifiers, package names, bundle
ids, file paths, and documentation. Preserves the unrelated "konsole" (KDE
terminal) reference and the parent CORBEL company name.
- Renames 10 Rust crates (kon-* → magnotia-*) and the tauri binary
- Updates package.json, tauri.conf.json (productName + identifier)
- Renames CSS classes (kon-rh-* → magnotia-rh-*) and animations
- Renames brand and roadmap docs
- Regenerates Cargo.lock and package-lock.json
Verified: svelte-check passes; pure-rust crates compile under new names.
Platform-dispatched TTS (spd-say + espeak-ng fallback on Linux, say on
macOS, PowerShell System.Speech on Windows) with a shared SpeakerButton
component. Tap to speak, tap again to stop; only one button speaks at
a time so two surfaces don't talk over each other. Text always travels
via argv (or a PowerShell here-string delivered through -EncodedCommand
on Windows) so user content never enters a shell string.
Mount points: DictationPage transcript footer, transcript viewer header,
per-step in MicroSteps. Settings gains a "Read aloud" accordion with
voice picker (lazy-loaded from the OS synth), rate slider 0.5-2.0x,
and a British-English test utterance.
Rust tests cover rate mapping, NaN handling, and Windows here-string
terminator safety. No pause/resume, no SSML, no cloud voices — that
stays out of scope per the Layer-1 roadmap.
Independent review surfaced three majors and one nit. All actioned.
MAJOR 1 — profile scoping:
`decompose_and_store` and `extract_tasks_from_transcript_cmd` now
accept an optional `profile_id` (wired from `profilesStore.activeProfileId`
in MicroSteps.svelte and DictationPage.svelte), and thread it into the
feedback-retrieval query so per-profile decomposition styles do not
leak into each other. `record_feedback` gets the same treatment.
MAJOR 2 — prompt-budget regression on long inputs:
New `trim_to_budget` helper + `FEW_SHOT_CHAR_BUDGET = 2000` char cap
in `src-tauri/src/commands/tasks.rs`. Retrieval still pulls up to 5
rows but they are char-counted and truncated against the budget
before being sent to the LLM. Char cost matches the `Input: ...\n
Good output: ...` render path so the budget maps cleanly to ~570
Qwen3 tokens, well inside the 8192-context reserve after the 512-
or 768-token response allocation. Oldest-first drop order (iteration
stops at cost exceeded) preserves the most recent correction which
is the one carrying the user's live preference.
MAJOR 3 — inline edit stale-rollback race:
`saveEdit` in MicroSteps.svelte now stamps a monotonic per-step
`saveToken`. Each edit bumps the token; on failure the rollback
only fires if `saveToken[step.id] === myToken`, so a slow-failing
first save can no longer overwrite a faster successful second save.
NIT — retrieval ordering stability:
`list_feedback_examples` ORDER BY now `created_at DESC, id DESC`.
SQLite timestamp precision is one second; without the secondary
key, bursty feedback within the same second would select
non-deterministically.
Also: malformed `context_json` now warns via eprintln! rather than
disappearing silently — Codex minor.
All green: cargo build + 249 tests + clippy -D warnings + fmt
+ svelte-check (0/0) + npm run build.
Two new Settings → AI knobs that compose cleanly with what already
shipped (aiTier, LLM model, translator prompt framing).
**B.1 #15 — Named cleanup presets.** LlmPromptPreset enum
(Default / Email / Notes / Code) appends a short context hint onto
the CLEANUP_PROMPT just before generation. Presets shape tone and
structure ("email paragraph", "bulleted meeting notes", "preserve
technical terms") without licensing the content-editing the
translator-not-editor framing forbids. cleanup_transcript_text_cmd
now takes `preset: Option<String>` which runs through the new
LlmPromptPreset::parse (normalises aliases like "meeting-notes",
collapses unknown values to Default).
**A.1 #28 — Sequential-GPU guard.** New LocalEngine::unload drops
the backend + model_id so a subsequent load actually reclaims VRAM.
load_llm_model, load_model, and load_parakeet_model Tauri commands
grow an optional `concurrent: bool` argument. When concurrent is
Some(false), loading LLM first unloads whisper+parakeet, and vice
versa — prevents VRAM OOM on tight-VRAM setups. Default is the
previous parallel behaviour so nothing changes for multi-GB cards.
Transcribe-in-progress paths (transcribe_pcm, transcribe_file, live)
pass None, so mid-dictation model loads don't accidentally tear
down the LLM.
Settings UI (AI section):
- Cleanup preset segmented button + descriptive copy for each option.
- GPU concurrency segmented button with explicit trade-off text
("faster transitions vs fits in tight VRAM").
Frontend wiring:
- settings.llmPromptPreset flows from DictationPage's
cleanupTranscriptIfEnabled into the Tauri command.
- settings.aiGpuConcurrency flows from both DictationPage (auto-load
on record) and SettingsPage (manual load/unload buttons) as
`concurrent: "parallel" === true` to the load commands.
Tests: three new preset cases in crates/ai-formatting/src/llm_client.rs
(parse aliases, suffix non-empty for non-default, default suffix
empty). All 139 existing lib tests still pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Hands-off feedback for recording lifecycle: a short C5 pitch at
record start, a falling G4 at record stop, and a staggered C5–E5–G5
major third when the finalise flow completes. Synthesised at runtime
via the Web Audio API (OscillatorNode + linear-ramped GainNode
envelope) rather than shipping WAV assets — keeps the binary size
flat and lets us tweak timbre without touching bundled files.
Off by default. Settings → Output exposes the toggle with a volume
slider (0–100%, default 15%) and a "Test" button that plays the
completion cue so the user can confirm loudness without recording.
Hooked at three call sites in DictationPage:
- playStartCue after page.recording = true in startRecording
- playStopCue at the top of stopRecording
- playCompleteCue just before `saved = true` at the end of
finaliseTranscription's transcript-present branch
All three no-op when settings.soundCues is false. The Web Audio
context is lazily constructed on first cue (most browsers suspend
it until a user gesture — Tauri's webview inherits that). If the
AudioContext can't be built we silently drop the cue rather than
throwing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The LLM runtime has been quiet since it shipped in Phase 3 — users
had no surface-level signal that cleanup was loaded, warming, or
actively generating. Settings has verbose status text internally,
but a dictation-flow user never opens Settings during a run.
New: a shared $state store drives a small chip in the sidebar that
reflects the true LLM state in ≤500 ms of any transition (brief
item #31 acceptance). Five states:
off → hidden (user has aiTier === "off")
warming → model download or first load in flight; amber pulse
ready → loaded + idle; green dot
generating → cleanup_transcript_text_cmd or
extract_tasks_from_transcript_cmd in flight; accent
pulse with Sparkles icon
error → last operation failed; red dot with AlertTriangle
The store exposes three calls: refreshLlmStatus(aiTier) (polls the
backend), markGenerating(detail) / markGenerationDone(success).
DictationPage wraps its cleanup + extract calls in mark-generating
pairs. SettingsPage's LLM load / unload / delete / download paths
also refresh the global store so Settings-initiated transitions
surface in the sidebar immediately. The chip collapses to a
dot-only compact form when the sidebar is collapsed.
No backend changes — everything wires onto the existing
`get_llm_status` Tauri command.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ported the best bits of OpenWhispr's TranscriptionPreviewOverlay into Kon's
window conventions. Off by default — toggle in Settings → Output → "Floating
preview when Kon is unfocused". Opens only when the main window isn't
focused at the start of a recording, so it never adds noise when the user
can already see the transcript in the main surface.
Phase state machine (src/routes/preview/+page.svelte):
- listening — pulsing dot, no text yet
- live — animated bars + streaming raw Whisper output
- cleanup — accent bars while the LLM cleanup pass runs
- final — checkmark + formatted text + 4s auto-hide
Data plumbing: raw segment text is captured before post_process_segments in
live.rs (new raw_text field on LiveResultMessage) and in transcription.rs
(new raw_text in the transcription-result payload). DictationPage forwards
raw_text to the overlay via Tauri global events — preview-listening on
start, preview-append per chunk, preview-cleanup before the LLM pass,
preview-final with the formatted text, preview-hide when a run produced no
transcript (empty recording / cancel).
Window is always_on_top, skip_taskbar, focused=false so it never steals
focus from whatever the user is dictating into. open_preview_window shows
an existing hidden preview or builds it fresh; close_preview_window hides
without destroying so the next open is instant.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds an opt-in "auto-paste into focused window" toggle. When enabled, the
dictation pipeline sets the clipboard and then sends a Ctrl+V / Cmd+V
keystroke to whatever window currently has focus — the common case after a
global-hotkey dictation, since Kon's own window never stole focus.
Backend (src-tauri/src/commands/paste.rs) probes for a platform paste tool
and falls back cleanly:
- Linux Wayland: wtype > ydotool > xdotool
- Linux X11: xdotool > ydotool > wtype
- macOS: osascript System Events keystroke
- Windows: PowerShell WScript.Shell SendKeys
detect_paste_backends is a pure probe used by Settings to describe the
available backend next to the toggle (or nudge the user to install one).
paste_text always copies first, so auto-paste failure degrades to the
existing clipboard-only behaviour and surfaces a warn toast.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
kon-llm now owns a real LlamaBackend + LlamaModel, with three Qwen3 tiers
(1.7B Q4, 4B-Instruct-2507 Q4, 14B Q5) selectable per hardware. Downloads
are resumable with SHA-256 verification and stored under ~/.kon/models/llm.
Engine exposes three high-level surfaces — all greedy/temp-0, GBNF-constrained
where output shape matters:
- cleanup_text (prompt-injection-hardened system prompt; profile terms
appended as "preserve these spellings" suffix)
- decompose_task (3–7 micro-steps, constrained JSON array)
- extract_tasks (optional-array; empty when no explicit commitments)
post_process_segments now takes an Option<&LlmEngine> and, when loaded and
format_mode != Raw, joins segments → cleanup → replaces segments with the
cleaned text (first segment span). Rule-based path still runs first; LLM
errors log and keep rule-based output.
Tauri commands: recommend_llm_tier, check_llm_model, download_llm_model,
load_llm_model, unload_llm_model, delete_llm_model, get_llm_status,
cleanup_transcript_text_cmd, extract_tasks_from_transcript_cmd,
decompose_and_store (LLM-backed subtasks).
Settings: AI tier toggle (off / cleanup / tasks), model picker with
downloaded/loaded status, download progress events via
kon:llm-download-progress.
Dictation: ensureLlmModelLoaded on mount, cleanupTranscriptIfEnabled after
stop when tier != off and format_mode != Raw, LLM task extraction when
tier=tasks (regex fallback on failure).
Interim: both llama-cpp-sys-2 and whisper-rs-sys statically link their own
ggml, so src-tauri/build.rs emits -Wl,--allow-multiple-definition on Linux.
Replace with a system-ggml shared-lib setup as a follow-up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Major quality pass on top of Phase 2. Five substantive changes plus
cross-cutting touches across audio, hotkey, transcription, and Tauri
command layers.
Transcription quality
- Long-audio chunking in commands/transcription.rs: Parakeet and large
file transcription now chunk-and-recompose with overlap trimming, so
the live-path chunking advantage extends to file-based workflows.
- Stateful live speech gate in commands/live.rs on top of the earlier
duplicate-boundary filtering — distinguishes start-of-speech from
mid-speech and holds state across chunks.
Auto-learning corrections
- New crates/ai-formatting/src/correction_learning.rs: extracts user
text corrections from viewer edits and proposes additions to the
active profile's vocabulary.
- src-tauri/src/commands/profiles.rs bridge for frontend-driven
confirmation of learned terms.
- src/routes/viewer/+page.svelte hooks the learning path into the
segment-edit flow so corrections feed profile_terms without a
separate 'train this profile' UX.
Transcript profile provenance
- Migration v8 (crates/storage/src/migrations.rs) adds profile_id to
transcripts, defaulting to DEFAULT_PROFILE_ID so existing rows stay
valid.
- crates/storage/src/database.rs: TranscriptRow + CRUD carry profile_id.
- src-tauri/src/commands/transcripts.rs: add_transcript accepts and
persists profile_id.
- DictationPage.svelte + FilesPage.svelte send activeProfileId on
capture so learned corrections are attributed to the right profile.
Cleanup prompt contract
- crates/ai-formatting/src/llm_client.rs hardened: the CLEANUP_PROMPT
now specifies concrete do/do-not rules, ready for a real model-backed
cleanup pass. The llm_client is still a stub — kon-llm remains unwired
— but the prompt shape is final.
Cross-cutting polish
- Minor touches in audio (capture/decode/resample), hotkey (lib/linux/stub),
core, transcription (concurrency/model_manager/local_engine/whisper_rs),
and the rest of src-tauri/src/commands/*: error-path tightening, log
clarity, TS-migration follow-ups (@ts-nocheck additions for incremental
typing).
Verified locally: npm run check, cargo test -p kon-ai-formatting,
cargo test -p kon-storage, cargo test -p kon --lib commands::live::tests,
cargo check — all green.
Scope boundary: kon-llm crate is still a stub; task extraction remains
rule-based. Bundled local-LLM runtime is the next clean step and is not
in this commit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Both the status-line hint next to the record button and the empty-state
message now read settings.globalHotkey reactively, so 'Press record or
Super+E' (or whatever the user has bound) stays in sync with the actual
shortcut.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wholesale JS -> TS migration of the frontend — stores, utils, actions,
and all Svelte component scripts adopt type annotations. Compile-time
surfaces (app.d.ts, lib/types/) added for shared DTO types.
Build plumbing:
- package.json: dev:frontend script that runs svelte-kit sync first
- tauri.conf.json: beforeDevCommand points at dev:frontend
- run.sh: dropped the sed-hack that temporarily blanked beforeDevCommand;
now relies on npm run dev:frontend to avoid double-Vite
- jsconfig.json: allowImportingTsExtensions
Preserves all Group 1 behaviour:
- page.svelte.ts keeps loadHistory / loadTasks Tauri-first, no
localStorage; saveTranscriptMeta + mapTranscriptRow + mapTaskRow
intact; update_task_cmd and update_transcript_meta_cmd invocations
carry the correct payload shape.
- Toasts, preferences stores typed without behaviour change.
- Viewer still routes segment edits through saveTranscriptMeta; the
Task 1.5 TODO markers are gone.
taskExtractor.ts is functionally improved during the migration:
- multi-task matches in the same sentence
- list-style shopping-verb expansion (get bread, milk, and cheese)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
THE PROBLEM (Codex review + architecture-review.md §1, §14):
Multiple critical paths discard errors silently — `let _ = insert_transcript(...)`,
`.catch(() => {})`, inline `error = ...` state that not every page surfaces. ND
users in particular need explicit feedback when something fails; silent
failure is worse than no feature.
SHIPPED:
src/lib/stores/toasts.svelte.js (new):
- Minimal in-house toast store (~80 lines, no svelte-french-toast dep)
- Severity → palette: info/success → moss, warn → signal, error → ember
- Auto-dismiss durations per severity (success 3s, info 4s, warn 6s,
error sticky)
- `invokeWithToast(invoke, command, args, errorTitle?)` helper wraps a
Tauri invoke and toasts on failure while still throwing for callers
that need to handle the error themselves
src/lib/components/ToastViewport.svelte (new):
- Reads from the toasts store
- Bottom-right stack, max-width clamp on small screens
- aria-live=polite + role=alert on error toasts (screen-reader friendly)
- Slide-in animation honours `html.reduce-motion` for the existing
preferences toggle
- Severity left-border in brand colours via existing CSS variables
src/routes/+layout.svelte:
- Mounts <ToastViewport /> once at the app root so toasts work from any
page or window
src/lib/pages/DictationPage.svelte:
- First error-toast wiring: failures starting recording now show a
sticky toast in addition to the inline `error` panel
- Replaces a previously easy-to-miss failure-mode
NEXT (Day 4 batch):
- Wire toasts into FilesPage, HistoryPage, SettingsPage, ModelDownloader
(all currently swallow errors)
- Add `add_transcript`, `list_transcripts`, `update_transcript` (closes the
long-standing TODO Codex flagged), `delete_transcript` Tauri commands
wrapping the existing storage layer
- Switch addToHistory to dual-write (localStorage + SQLite) so the
canonical store catches up with the actual transcript flow
- FTS5 transcripts_fts virtual table + search command
- Wrap multi-row writes (decompose_and_store) in DB transactions
Day 1 follow-up to 96980c7. The device-picker UI in Settings now
actually takes effect: settings.microphoneDevice flows from the Svelte
store, through the Tauri invoke, into MicrophoneCapture::start_with_device
on the Rust side.
Touched paths (back-to-front):
- src-tauri/src/commands/audio.rs:start_native_capture — new optional
`device_name: Option<String>` parameter; routes to start_with_device
when set, falls back to auto-select start() when None or empty.
- src-tauri/src/commands/live.rs:StartLiveTranscriptionConfig — new
optional `microphone_device: Option<String>` field with same
semantics (rename_all = "camelCase" maps it to microphoneDevice on
the wire).
- src-tauri/src/commands/live.rs:run_live_session — picks
start_with_device when an explicit name is provided.
- src/lib/pages/DictationPage.svelte — passes
microphoneDevice: settings.microphoneDevice || null in the invoke.
Behaviour:
- "Auto" in the picker (empty string) -> backend auto-selects, skipping
monitor sources and validating by RMS energy.
- Specific device -> backend opens that device by exact name; if it has
been disconnected the user gets a clear error pointing them back at
Settings.
cargo check -p kon-audio passes clean. Tauri-crate cargo check requires
cmake (pre-existing infra dependency for whisper-rs-sys); install via
`sudo dnf install cmake clang-devel`.
- Replaced tall header (pt-6 pb-4 with 28px timer + label stack) with 56px control strip
- Control strip: 40px record button + waveform placeholder + 20px timer + status badge + task toggle
- Waveform placeholder shows animated bars during recording, hint text at idle
- Actions moved to dedicated toolbar row (justify-end) below control strip
- Status footer (word count, format mode, profile) moved inside transcript Card
- Insert-at-cursor indicator relocated to status footer
- Page container remains flex-col h-full; transcript area fills all remaining space
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Rename custom event from ramble:toggle-recording to kon:toggle-recording
- Change download filename prefix from ramble- to kon-
- Fix export extension mapping: csv and html formats now produce correct file extensions instead of falling through to .txt
- Add console.warn when PCM buffer exceeds 5-minute cap and gets truncated
- Replace magic numbers with shared constants (MAX_PCM_SAMPLES, MIN_CHUNK_SAMPLES, CHUNK_INTERVAL_MS, FEEDBACK_TIMEOUT_MS)
- Use shared pad() utility from time.js instead of inline reimplementation
- Remove unused saveTasks import
- Simplify redundant 3-branch append logic to 2 branches with clarifying comment
- Use $derived.by to avoid double transcript.trim() in wordCount
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Float window fixes:
- Root layout now detects /float and /viewer URLs and hides Sidebar,
Titlebar, TaskSidebar for secondary windows. Belt-and-braces fix
since +layout@.svelte should handle this but may not in SPA mode.
- Float window title: "Ramble - To-do" → "Kon - To-do"
Transcription doubling guard:
- Added chunk_id deduplication set in DictationPage — if a chunk_id
has already been processed, skip the duplicate result
- Set cleared on each new recording session
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Security fixes from code audit:
- CSP re-enabled in tauri.conf.json with strict directives
(was null — critical vulnerability)
- XSS fix in viewer highlightText(): HTML entities escaped before
inserting <mark> tags via {@html}
- Removed 3 unwrap() calls in rule_based.rs British English conversion
— replaced with safe let-else guards
- Removed unwrap() on main window lookup in lib.rs setup — now uses
if-let for graceful handling
- Wrapped JSON.parse in DictationPage transcription-result listener
with try/catch
Rebrand cleanup:
- Renamed all localStorage keys from ramble_* to kon_* across
7 files (stores, viewer, float, history)
12 tests passing, clippy clean.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New copy_to_clipboard Tauri command using arboard 3.6
- Replaced all 5 navigator.clipboard.writeText() calls across
DictationPage, HistoryPage, FilesPage, and viewer with invoke()
- Native clipboard access independent of WebView permissions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
