Review feedback (MINOR): the original <= 0.0 clamp caught negatives
and zero but not non-finite inputs. Rust's saturating float-to-int
cast turns f64::INFINITY into u64::MAX, which would park the capture
buffer origin beyond any reachable sample index and trim the whole
buffer forever if a future end_secs source ever produces infinity
(clock glitch, overflow upstream, corrupted timestamp in a pass).
Adds is_finite() check. NaN, +infinity, -infinity, and zero all
return 0, which downstream trim_buffer_to_commit_point treats as
no-op. Test covers all three non-finite cases.
Review feedback (CRITICAL): when a chunk hit max_chunk_samples during
continuous speech, emit_active_chunk reset state to Idle. The next
1-2 loud frames of post-split continued speech went into onset_buffer
and were silently cleared if silence arrived before the 3-frame onset
threshold — 50-100ms of user audio lost at every max-chunk boundary
in long-continuous-speech scenarios.
Splits emit_active_chunk into two variants:
- emit_active_chunk_and_close: the existing behaviour. Used for
end-of-utterance closes and end-of-session flush. Truncates trailing
silence, resets state to Idle.
- emit_active_chunk_continue: mid-utterance split on max_chunk. Stays
in State::InSpeech, clears active_chunk for continued accumulation,
advances active_chunk_start by the emitted length so the next
chunk's start_sample is contiguous with this one's end. No
silence-trim (by definition still in speech — end-of-utterance
takes priority).
Adds max_chunk_split_preserves_audio_contiguity test: feeds 17 frames
of continuous speech into a chunker with a 4-frame cap, asserts
(a) chunk[i+1].start_sample == chunk[i].start_sample + chunk[i].samples.len()
across every pair, and (b) the final emitted region reaches the end
of the fed speech with no sample loss.
Review feedback (CRITICAL): LocalAgreement::push could panic with an
index OOB when a later pass arrived shorter than committed_count.
Concrete case: commit [a, b], next pass arrives [a] — lcp_len=1,
new_committed=max(1, 2)=2, then latest[2..] panicked because
latest.len()==1.
A Whisper re-transcription of an overlapping window can legitimately
collapse repeated segments, or the user can stop mid-utterance after
some tokens were already committed, both of which produce this
shape. The committed_count invariant still holds (non-shrinkage) —
it is the slicing that was unsafe.
Clamps every latest[..] slice against latest.len() before indexing.
committed_count stays at new_committed even when the pass is shorter:
non-shrinkage is relative to what we have already emitted, not to
the current pass length. newly_committed and tentative both return
empty when the shorter pass has nothing past the committed prefix.
Adds two regression tests:
- shorter_pass_after_commit_does_not_panic (commit 2, push 1)
- empty_pass_after_commit_does_not_panic (commit 1, push empty)
New streaming::buffer_trim module with two pure helpers:
- sample_index_for_seconds(end_secs, sample_rate) -> u64: converts
LocalAgreement::last_committed_end_secs() into an absolute sample
index. Defensive against negative end_secs (treats as 0) so a future
clock-skewed timestamp cannot wrap to a huge u64.
- trim_buffer_to_commit_point(buffer, buffer_start_sample,
commit_sample_index) -> new_buffer_start_sample: drains the prefix
of the capture buffer that falls below the commit point and returns
the new absolute-index origin.
Edge cases covered by tests:
- commit before buffer start → no drain
- commit equal to buffer start → no drain
- commit inside buffer → drain prefix, advance origin
- commit at buffer end → drain all, origin moves forward
- commit past buffer end → drain all, origin parks at commit (rare
edge after a committer reset)
- sample_index_for_seconds rounds nearest, negatives clamp to 0
- integration with LocalAgreement::last_committed_end_secs
trim_bounds_buffer_over_long_session is the acceptance fixture for
the ufal #120/#102 failure mode: 100 cycles of 16_000 captured samples
with a 200-sample tentative tail per cycle, and the buffer stays below
2× the tentative envelope instead of growing to 1.6M samples.
Integration into src-tauri/src/commands/live.rs deferred to the
dogfood session that wires VadChunker and LocalAgreement end-to-end —
the trim is a one-line replacement at the maybe_dispatch_chunk drain
site once the committer is feeding it commit points.
New streaming::commit_policy module implementing ufal's
LocalAgreement-n pattern: tokens emitted by the streaming ASR
pipeline stay tentative until N consecutive passes produce the same
prefix, at which point the agreed prefix commits.
Types:
- Token: text + absolute start/end seconds. PartialEq is text-only so
identical words from overlapping Whisper windows compare equal even
when their timestamps drift.
- CommitDecision { newly_committed, tentative }: the partition fed
back to the live-session worker after each pass.
- CommitPolicy enum with LocalAgreement { n }. Default is n=2 (ufal).
- LocalAgreement: stateful committer with push/flush/reset and a
last_committed_end_secs accessor. Brief item #25 uses the latter
to compute the sample-index drain target for aggressive buffer trim.
Invariants exercised by tests:
- first pass is all tentative (need 2 passes to commit under n=2)
- two matching passes commit their common prefix
- divergent second pass commits nothing
- extending agreement commits only the newly-agreed tokens
- tentative tail tracks latest pass only (no stale guesses)
- committed prefix never shrinks, even if later passes contradict
- flush emits any tentative-but-not-committed tail at session end
- flush on empty history is a no-op
- reset clears all commit state
- n=3 requires three matching passes before anything commits
- CommitPolicy::default() is LocalAgreement { n: 2 }
Integration into src-tauri/src/commands/live.rs deferred — the
tentative/committed split needs the B-side 'tentative: bool' field on
LiveResultMessage.segments (workstream-B #24 UI contract) and
validation against real streaming captures before going live.
New crates/transcription/src/streaming/ module with:
- VadChunker trait: Send-bound, object-safe, push/flush/reset/
next_sample_index. Same surface a future Silero backend will
present, so live.rs wiring does not change when Silero drops in.
- VadChunk type: (start_sample: u64, samples: Vec<f32>) for
commit-policy sample-offset bookkeeping in #24.
- RmsVadChunker: fallback backend the plan permits while the
ort 2.0.0-rc.10 vs rc.12 ecosystem conflict blocks silero-vad-rust
/ voice_activity_detector. Tuned to match the existing
evaluate_speech_gate behaviour (enter 0.003, exit 0.0014, 3-frame
onset, 500 ms silence close, 2 s max chunk).
Key behavioural properties, each backed by a test:
- pure silence emits nothing
- samples between exit and enter thresholds never trigger onset
- a single loud frame does not start a chunk (sustained speech only)
- sustained speech followed by silence emits exactly one chunk
- hysteresis: a dip between enter and exit does not split a chunk
- max_chunk_samples caps continuous speech (Whisper never fed > 2 s)
- flush surfaces in-flight speech
- flush on an idle chunker emits nothing
- reset restores a clean state
- emitted chunk start_sample includes the onset buffer (Whisper sees
the speech attack, not post-onset audio)
Open items tracked as follow-ups:
1. Silero backend via direct ort rc.12 bridge (Handy-style). Blocked
on either ecosystem ort alignment or dedicated bridge session.
2. Integration into src-tauri/src/commands/live.rs. Deferred so
threshold tuning can be validated against real microphone
captures rather than synthetic constant-signal fixtures.
The Vec<f32> in-memory accumulator on run_live_session had three
failure modes: (a) a crash during transcription took the recording
with it, (b) RAM grew linearly with session length, (c) OOM killed
the capture thread silently.
New kon_audio::WavWriter wraps hound::WavWriter<BufWriter<File>> with
an append-friendly API and a 500 ms-granularity header flush. On any
abort after a flush the on-disk file is a valid, playable WAV. Unit
test (brief item #19 acceptance) simulates the abort with
std::mem::forget and asserts the pre-flush samples are recoverable.
Live capture now:
- resolves the destination path at start_live_transcription_session
time via a new resolve_recording_path helper extracted from
persist_audio_samples,
- opens a WavWriter before any samples arrive, sample rate taken from
LocalEngine::capabilities() (#13 wiring) with 16 kHz fallback,
- feeds the resampler output through WavWriter::append inside
append_resampled_audio — drops the writer with a user-visible
warning if a write fails mid-session,
- calls flush() at stop (after resampler tail), finalise() on clean
exit, and drops-to-last-flushed state on abort.
LiveSessionSummary.audio_samples → audio_path: the path is already
written by the time stop_live_transcription_session runs; no
post-session write step remains for live capture.
persist_audio_samples is kept for the offline save_audio command.
New crates/transcription/src/transcriber.rs defines a Transcriber
trait (Send supertrait for spawn_blocking travel) with
TranscriberCapabilities (sample_rate, channels, supports_initial_prompt).
TranscriberCapabilities.sample_rate is load-bearing for the upcoming
progressive WAV writer (#19).
Concrete impls:
- SpeechModelAdapter wraps Box<dyn transcribe_rs::SpeechModel + Send>
for Parakeet (and any future transcribe-rs-backed engine).
- WhisperRsBackend moves its transcribe_sync body into the impl,
widening the signature from &self to &mut self so per-call
WhisperState can be created cleanly through the trait object.
LocalEngine now holds Box<dyn Transcriber + Send>; dispatch in
transcribe_sync collapses from a match to a direct call. Adds
LocalEngine::capabilities() for the WAV-writer.
Cargo feature flag "whisper" (default on) makes whisper-rs, num_cpus,
and the whole whisper_rs_backend module optional. cargo check
--no-default-features -p kon-transcription now builds without pulling
whisper-rs-sys — the escape hatch brief item #6 / #13 called for on
Windows / non-AVX2 / cloud-only builds. load_whisper is cfg-gated
behind the same feature.
src-tauri/src/commands/models.rs load_model_from_disk returns
Box<dyn Transcriber + Send> instead of SpeechBackend; caller chain
(ensure_model_loaded, prewarm_default_model) is unchanged.
transcriber_trait_is_object_safe test lands alongside the trait as a
compile-time witness against future Self-returning / generic-method
additions.
Review feedback: the previous test would pass even if the Range-header
logic in download_file were deleted entirely, because File::create
truncates the stale .part regardless of which branch set
actually_resuming to false.
Tightens spawn_no_range_server to return HTTP 400 when the request
carries no Range header, and only return 200 + full body when Range is
present. A regression that stops sending Range now surfaces as a
download failure (empty body from 400, bytes != body assertion)
instead of silently passing through the truncation path.
The downloader already handles servers that return 200 to a Range
request by falling through to a truncating File::create on the .part
path, discarding stale partial bytes. That branch had no dedicated
fixture test — the SHA mismatch and Range-honouring resume cases were
covered but the mirror / proxy that strips Range support was not.
Adds spawn_no_range_server (always 200, full body regardless of Range
header) and download_file_restarts_when_server_ignores_range. Writes 12
bytes of stale content to .part, kicks off a download, asserts the
final file matches the fresh body exactly (not stale-bytes-prefixed)
and the .part file is cleaned up.
Brings the transcription downloader to test-coverage parity with
crates/llm/src/model_manager.rs per brief item #8 ("test coverage
parity" acceptance).
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>
ufal/whisper_streaming #161 documents the classic Whisper streaming
failure: on ambiguous audio the model falls into a prompt loop,
cascading a single token for 10+ words ("I I I I I I I I I I I…").
The chunk-boundary duplicate detector in live.rs doesn't catch
this — the repeat is within a single chunk, and the text is
technically novel so FTS is happy to keep it.
Fold the detection into is_hallucination as a third pass (after
HALLUCINATION_MARKERS substring-match and HALLUCINATION_TRAIL_PHRASES
exact-match). has_consecutive_repetition walks the token stream
(whitespace-split, lowercased) and returns true when any run of
≥REPETITION_RUN_THRESHOLD (4) identical tokens is found.
Threshold chosen deliberately: three consecutive matches appear in
normal speech ("no no no, that's wrong"), four almost never does.
Tests pin both sides — "I I I I I" detected, "no no no" allowed,
alternating patterns ("I am I am I am I am") allowed regardless of
length.
Phrase-level repetition ("thank you thank you thank you thank you")
is a documented companion failure mode but needs a sliding n-gram
matcher — deferred with a code comment flagging it.
No caller changes: post_process_segments already drops
is_hallucination hits when anti_hallucination is enabled.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Whisper was trained on subtitle corpora, so silence and room tone
trigger caption-style artefacts that the previous three-marker
blocklist ("[blank_audio]", "[music]", "[silence]") didn't catch:
"Thanks for watching!", "Please subscribe.", "ご視聴ありがとうござ
いました", "♪♪♪", etc. Documented in WhisperLive #185 / #246 and
ufal/whisper_streaming #121 as the top streaming-transcript-quality
issue after chunk-boundary repeats.
HALLUCINATION_MARKERS widens from 3 to 16 entries: all common
bracketed non-speech tags (applause / laughter / inaudible /
background noise / sounds), parens variants, and musical notation
(♪ / ♫). Still contains-match so the marker triggers even when
Whisper wraps it in other noise.
HALLUCINATION_TRAIL_PHRASES (renamed from AUTO_THANKS_PHRASES) jumps
from 4 to ~30 entries: YouTube sign-offs, subtitle-credit leakage,
and the two most common non-English variants (Japanese "thanks for
watching" + MBC Korean news sign-off). Stays exact-match so
legitimate dialogue containing "thanks" or "subscribe" mid-sentence
never gets dropped — a new regression test pins that invariant.
The <15-char length gate on trail phrases is removed; some of the
new entries (e.g. "please subscribe to our channel.") are longer.
Exact-match against a known list is safety enough.
No caller changes: post_process_segments already drops segments for
which is_hallucination returns true when anti_hallucination is on.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The previous prompt led with "You are a transcript cleanup assistant"
and listed cleanup rules. That framing quietly licenses the LLM to
treat cleanup as content editing — rephrasing for clarity, summarising
long sentences, "improving" phrasing. That's precisely the failure
mode OpenWhispr / Scriberr / Whispering users complain about ("the
LLM changed my meaning").
New framing lifts Whispering's published baseline: "translator from
spoken to written form — not an editor trying to improve the content."
Adds an explicit rule: do NOT improve, summarise, expand, or rephrase;
faithful written-form translation only, never content editing.
Both load-bearing concerns are now regression-tested — the existing
prompt-injection hardening assertions stay, and a new test pins the
translator framing + explicit no-editing rule against drift during
future refactors.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ports the kon-llm model_manager resume pattern the rest of the way
into kon-transcription::model_manager:
- download() now validates an existing complete file against its
sha256 before skipping; a hash mismatch removes the file and
re-fetches, instead of serving a corrupt file to whisper.cpp.
- download_file() now distinguishes 206 Partial Content, 200 OK
(resume silently ignored by server), and other statuses, rather
than treating any non-206 as 'just use it as a fresh start'.
200-on-Range is handled by discarding the partial and starting
over cleanly.
- New tests: download_file_resumes_from_partial_and_verifies_sha
(TcpListener fixture, same shape as kon-llm's), and
download_file_fails_on_sha_mismatch_and_cleans_part_file.
- sha256_of_file helper + unit test for the existing-file guard.
Dev-deps: tempfile + tokio(net/io-util/macros). Total workspace
lib-test count: 116 → 123.
Co-authored-by: jars <jakejars@users.noreply.github.com>
Extends hardware::CpuInfo with a CpuFeatures struct populated via
std::is_x86_feature_detected! on x86_64 and an architectural
assumption for aarch64 (NEON). Adds has_ggml_baseline() so callers
can cheaply ask 'will whisper.cpp / llama.cpp ship a fast path on
this CPU?' without knowing the arch-specific rule.
The point of #7 is giving the runtime a way to surface a clear
"non-AVX2 fallback" warning before the user hits a wall of silent
slowness. The banner itself ships in the next commit as part of
get_runtime_capabilities (item #1). Tests cover the baseline helper
on both x86 and non-x86 targets.
Co-authored-by: jars <jakejars@users.noreply.github.com>
Adds a build.rs guard that parses Cargo.lock and panics on Windows
if the tokenizers crate ever appears in the workspace dependency
tree, mirroring the MSVC C-runtime conflict that broke Whispering
v7.11.0 when they linked whisper-rs-sys + tokenizers in the same
binary.
On non-Windows hosts the guard downgrades to a cargo:warning so
cross-compilation or CI from Linux surfaces the issue before a
Windows build attempt actually panics.
No tokenizers crate is in the tree today; the guard is preemptive.
If we ever legitimately need HF tokenizers on Windows, the escape
hatch is an out-of-process sidecar (separate CRT).
Co-authored-by: jars <jakejars@users.noreply.github.com>
sqlx 0.8's default feature set pulls in `any`, `macros`, `migrate`, and
`json`. Grepping the workspace confirms none of these are used — the
code calls sqlx::query() / query_scalar() at runtime, implements its own
migration sequencing in crates/storage/src/migrations.rs, is sqlite-only
(no `any` needed), and never derives FromRow / applies sqlx proc-macros.
Dropping them keeps only what's needed: runtime-tokio + sqlite.
Why it matters disproportionately on Windows: the `macros` feature pulls
sqlx-macros → sqlx-macros-core → proc-macro2 / syn / quote / async-trait
/ url / heck / dotenvy / sha2 / filetime. Each proc-macro crate on
Windows MSVC compiles to a .dll with a full linker invocation (slower
ABI than Linux/macOS proc-macro .so). Net: tens of seconds shaved off
every cold-cache CI run, compounding with the cache-path fix in the next
commit.
kon-mcp was already lean (default-features = false); matching that shape
across the workspace now.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
QC smoke sweep flagged two clippy -D warnings lints in code this branch
introduced:
- crates/core/src/process_watch.rs — collapsible_if on the meeting-pattern
match loop, merged the two conditions with &&.
- crates/mcp/src/lib.rs — let-else on the id unwrap that short-circuits a
notification, switched to ? since handle_message already returns Option.
All other clippy lints under -D warnings (audio/capture, hotkey/linux,
storage/file_storage, diagnostics, the duplicate-detection helpers in
live.rs) predate this branch and are out of scope.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
search_transcripts already backs onto the transcripts_fts virtual table
(migration v4, trigger-maintained) via MATCH + ORDER BY rank. Adding a
test to lock the behaviour: token matching is case-insensitive, rank-
ordered, and non-matching tokens return nothing. This is Phase G of the
post-OpenWhispr audit — semantic embeddings stay deferred until the FTS
experience actually hits a wall.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Default off. When on, the layout polls detect_meeting_processes every 15s
with the user's app-name patterns. On a fresh match (edge-triggered — no
re-toast until the app goes away and comes back) we fire a reminder toast
that tells the user which meeting app appeared and their global hotkey. We
never start recording on this signal; the ideology rule says the user
decides. The signal is a single channel: process list match only — no mic
activity heuristic, no calendar.
Backend adds kon_core::process_watch::{list_running_process_names,
match_meeting_patterns} over sysinfo, exposed to the frontend as the
detect_meeting_processes Tauri command.
Settings ships two new fields — meetingAutoCapture (bool) and
meetingAutoCaptureApps (string[]) — with a comma-separated input in the
Output section. Default app list is ["zoom", "teams"], user-editable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
New workspace binary crates/mcp exposes Kon's SQLite store to external
agents (Claude desktop, Cline, any MCP client) without running the Tauri
app. Newline-delimited JSON-RPC 2.0 on stdio, MCP protocol 2024-11-05.
Tools shipped (all read-only):
- list_transcripts — recent transcript summaries, limit 1..200 default 20
- get_transcript — full text + metadata by id
- search_transcripts — FTS5-backed query, limit 1..100 default 20
- list_tasks — all tasks (open + done)
No writes. The Tauri app remains the only writer; kon-mcp just opens the
same SQLite file (via kon_storage::init) and reads. Logs land on stderr to
keep stdout clean for the JSON-RPC stream. Smoke-tested end-to-end with
initialize + tools/list over a pipe.
Wire into an MCP client with:
{ "mcpServers": { "kon": { "command": "/path/to/kon-mcp" } } }
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Parakeet-TDT scores 85 on any GPU-equipped English-capable system (Instant
speed + Great accuracy + GPU boost + headroom) vs ~75 for the best distilled
Whisper. A new test in recommendation.rs locks this in so future scoring
tweaks don't silently regress it.
FirstRunPage previously stored settings.modelSize by title-casing a lowercased
alias — which worked for Tiny/Base/Small/Medium but produced
"Whisper-distil-small-en" for the new distil ids. Swap to an id→label map
and pass the raw model id through to download_model/load_model; the backend
already accepts full ids via the whisper_model_id fallback.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two new registry entries (crates/core/src/model_registry.rs):
- whisper-distil-small-en — 336 MB, ~6× faster than whisper-small-en
- whisper-distil-large-v3 — 1.55 GB, near large-v3 accuracy at medium size
Both are whisper.cpp-compatible GGML binaries hosted on HF by the
distil-whisper org; no runtime change, just wider model choice. English-only
by design (matches upstream Distil-Whisper).
The Settings model picker widens to six options — Tiny, Base, Small,
Distil-S, Medium, Distil-L — ordered roughly by accuracy. Download/load
commands now take the resolved model id (whisper-distil-*) instead of the
lowercased label, so the frontend owns the label↔id mapping.
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>
ai-formatting:
- rule_based.rs: collapse_repetitions() merges adjacent duplicate
tokens like 'I I can' -> 'I can' and 'think think that' -> 'think
that'. Normalises case and punctuation before comparison.
- pipeline.rs: post_process now calls collapse_repetitions when
format_mode is Clean or Smart. Added unit coverage.
audio:
- capture.rs: replace the seven deprecated cpal DeviceTrait::name()
call sites with a device_display_name() helper that uses the
non-deprecated description() path. Keeps identical behaviour,
silences compile warnings, ready for cpal upgrade.
Addresses the 'Christ. Christ.' live-transcription boundary duplicate
Jake saw during Group 1 dogfooding. Does not fix all cross-chunk
overlap cases (see live.rs OVERLAP_SAMPLES for the root cause) but
catches the common stutter pattern at post-processing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
transcribe-rs 0.3.10's ParakeetModel::transcribe_raw ignores its
options argument and calls self.infer(samples, &TimestampGranularity::default())
where default is TimestampGranularity::Token — per-subword segments.
That surfaces in Kon as output like 'T Est Ing One , Two , Three . W Ow ,
This Is T Ri Ble .' because DictationPage joins segment texts with ' '.
Introduce a thin ParakeetWordGranularity wrapper that implements
SpeechModel and overrides transcribe_raw to call the concrete
ParakeetModel::transcribe_with() with ParakeetParams { timestamp_granularity:
Some(Word) }. Pre-existing bug unrelated to Phase 2 work — surfaced during
Group 1 dogfooding because Parakeet was being tested for the first time.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Second dogfood sprint. Headline fix: Linux now uses native KWin/Mutter
decorations instead of fragile frameless `startResizeDragging`, which
collapsed diagonal corner resize to a single axis and made drag feel
laggy. macOS / Windows keep custom chrome via `useCustomChrome` gate.
Other changes:
- Cross-window preferences sync via `kon:preferences-changed` Tauri
event — theme and font changes propagate live to float/viewer.
- Hotkey recorder rewritten to use capture-phase document listener
gated by $effect; button focus was unreliable in webkit2gtk.
- History page redesigned for cognitive-load hygiene: title-first
compact row, inline title input, Edit popout opening /viewer in
edit mode, clipboard export as .md with YAML frontmatter, manual
tag chips + + Add tag input, header tag filter (cap 7), global
Starred filter, `tag:xyz` search syntax.
- `deriveAutoTags` kept as empty hook for post-Task-7 LLM topic tags;
research found all previous auto-tag chips redundant with row UI.
- Viewer window adds edit mode with debounced-save textarea; native
title renamed to "Kon - Transcription Editor".
- Window minimums updated per GNOME HIG + WCAG reflow research:
main 960x600, float 360x480, editor 560x520.
- Microphone picker filters raw ALSA strings (hw:, plughw:, front:,
sysdefault:, null) and dedupes by CARD=X. New `description` field
on DeviceInfo reads /proc/asound/cards so Blue Yeti shows as "Blue
Microphones" instead of the short "Microphones" card name.
- GPU reporting fixed: get_runtime_capabilities now returns
accelerators=[cpu,vulkan] and whisper.supports_gpu=true, matching
the transcribe-rs whisper-vulkan feature linked unconditionally.
- ResizeHandles kept for macOS/Windows frameless: 12px edges, 20px
corners via CSS vars, pointerdown + setPointerCapture, corners
above edges in z-order, rendered as sibling (not child) of the
animated layout root so `position: fixed` is viewport-relative.
- Dueling drag-region handlers removed — `data-tauri-drag-region` and
manual `startDragging()` were stacked on the same elements; kept
the manual handler which has the button/input early-return logic.
See HANDOVER.md for the full session log and deferred items.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
crates/storage/src/migrations.rs:
Replace naive sql.split(';') with split_statements() that tracks
BEGIN...END depth, so migrations containing trigger definitions
execute correctly instead of being split mid-block.
crates/transcription/src/lib.rs:
Re-export transcribe_rs::SpeechModel so callers in src-tauri can
reference it without adding transcribe-rs as a direct dependency.
src-tauri/src/commands/models.rs:
Use Box<dyn SpeechModel + Send> as the load_model_from_disk return
type, matching the trait object that transcription crates produce.
src-tauri/src/commands/transcripts.rs:
Remove the stale .map(|v| v as i32) casts on sample_rate and
audio_channels. InsertTranscriptParams now stores these as i64
(ebf449b), matching the i64 fields on CreateTranscriptRequest;
casting to i32 first would silently truncate large sample rates.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
