mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-01 03:46:41 -04:00
* feat(realtime): EOU-driven semantic_vad turn detection Add a `semantic_vad` turn-detection mode to the realtime API that feeds the transcription model live and decides "the user finished speaking" from the `<EOU>` end-of-utterance token rather than from silence alone. When EOU fires the turn commits immediately (~0.3s); otherwise it falls back to an eagerness-scaled silence threshold (low/med/high = 8/4/2s). Plumbing, bottom to top: - proto: `AudioTranscriptionLive` bidirectional RPC (config-first oneof, mono float PCM @16k, ready-ack / Unimplemented degrade signal) plus `TranscriptResult.eou` for the unary retranscribe gate. - pkg/grpc: client/server/base/embed scaffolding for the bidi stream, modeled on AudioTransformStream; release stream conns on terminal Recv. - parakeet-cpp: live transcription RPC with per-C-call engine locking (one live stream per turn, finalize+free at commit); bump parakeet.cpp to ABI v5 — incremental StreamingMel (no more quadratic per-feed mel recompute that delayed EOU on long turns) and the <EOU>/<EOB> split; strip the literal <EOU>/<EOB> from offline text and set Eou. - core/backend: LiveTranscriptionSession wrapper + pipeline `turn_detection:` config block (type/eagerness/retranscribe). - realtime: semantic_vad integration — live input captions streamed as transcription deltas while the user speaks, EOU-immediate commit with eagerness fallback, optional retranscribe gate (batch re-decode must also end in <EOU> to confirm), clause synthesis off the LLM token callback, and per-turn live-transcription / model_load telemetry. - UI: show the realtime pipeline components as a vertical list. Docs and tests included; opt-in via the pipeline YAML or per-session `session.update`. Non-streaming STT backends degrade to silence-only. Assisted-by: Claude Code:claude-opus-4-8 [Read] [Edit] [Write] [Bash] Assisted-by: Claude Code:claude-fable-5 [Read] [Edit] [Bash] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): explicit formally-verified state machines + parakeet streaming driver The realtime API had several implicit state machines whose state was inferred from scattered booleans, channels, and five separate mutexes, leaving illegal/inconsistent states reachable. Make them explicit and keep the implementation in step with a formal design; rework the parakeet streaming backend along the same lines. Realtime state machines (M1-M5). Each is a sealed sum-type State/Event/Effect with a total, pure Next(state,event)->(state,[]effect) behind a single-writer Coordinator: M1 conncoord connection lifecycle: VAD toggle + once-only teardown (replaces vadServerStarted + a `done` channel closed from two sites). M2 turncoord turn detection: collapses speechStarted and the live-stream "turn open" flag into one state, so discardTurn can no longer desync them and suppress the next onset. M3 respcoord response coordination: serializes the dual-writer start/cancel so at most one response is live; one response.done per response.create. M4 compactcoord conversation compaction: single-flight (replaces the `compacting atomic.Bool` CAS). M5 ttscoord TTS pipeline: open->closing->closed, idempotent wait(), rejects enqueue-after-close (was a silent drop). The Coordinator/Sink/Next plumbing — only the sealed types and Next differed per machine — is extracted once into core/http/endpoints/openai/coordinator as a generic Coordinator[S,E,F]; each machine keeps its public API via type aliases, so no sink, call-site, or test moved. Hierarchy. session_lifecycle.fizz models M1 as the parent region with its children (M2/M3/M4) as one statechart and asserts ChildrenDieWithParent (conn torn => all children terminal, none start after teardown). respcoord and compactcoord gain an absorbing Terminated state + Shutdown event; conncoord's teardown drives the children terminal. This closes a compaction teardown gap: a fire-and-forget compaction could outlive a torn session — compactionSink now takes a session-scoped cancellable context + WaitGroup and joins the in-flight summarize+evict on shutdown. Formal verification. formal-verification/ holds one authoritative FizzBee spec per machine plus the composition spec, each with an always-assertion and a documented one-line edit that makes the checker fail (verified non-vacuous). scripts/realtime-conformance.sh is fail-closed: all Go conformance suites under -race AND a model-check of every .fizz spec; a missing FizzBee is a hard error (only the loud REALTIME_CONFORMANCE_SKIP_FIZZBEE=1 bypasses it, never in CI). FizzBee is pinned by sha256 and installed via scripts/install-fizzbee.sh into .tools/ (gitignored). Wired as make test-realtime-conformance, a CI workflow, and a pre-commit path filter. Go conformance tests are Ginkgo/Gomega (per the repo's forbidigo lint): transition tables + fixed-seed property walks + concurrent/-race specs, no rapid dependency. Design map: docs/design/realtime-state-machines.md. Parakeet streaming backend. The same treatment applied to the parakeet-cpp streaming paths: - AudioTranscriptionStream returns codes.Unimplemented for non-streaming models instead of decoding offline and emitting it as one delta + final. A client that asked for streaming learns the model cannot stream rather than receiving a batch result shaped like a stream. New grpcerrors.StreamTranscriptionUnsupported carries that signal; the HTTP /v1/audio/transcriptions stream path surfaces it as an SSE error event. Mirrors AudioTranscriptionLive, which already did this. - utteranceBoundary (boundary.go): a single definition of the end-of-utterance latch, replacing three open-coded finalEou toggles. Modelled as a two-valued type so illegal states are unrepresentable. - Shared decode driver (driver.go): streamFeedResult (one per-feed event) + feedChunk (hides the ABI v4 JSON vs text-only split) + feedSlices + flushTail. The feed loop is written once. - AudioTranscriptionLive becomes a bidi adapter: it streams the per-feed {delta,eou,eob,words} the realtime turn detector consumes and a terminal FinalResult carrying only Text. Segments/duration/eou are offline-only and no longer produced (nor read) on the live path; liveTraceState drops the terminal eou and keeps the per-feed eou_events count. - AudioTranscriptionStream + streamJSON merge into one driver-based function; streamSegmenter is generalized to the unified event with a text-only fallback that preserves the legacy (no-words) library's per-utterance segmentation. Verified: build/vet/gofumpt clean, golangci-lint 0 issues, all coordinator and parakeet packages under -race, the fail-closed conformance gate green, and make test-realtime (12 e2e WS+WebRTC). Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com>
58 lines
2.4 KiB
Plaintext
58 lines
2.4 KiB
Plaintext
---
|
|
# Authoritative formal design for realtime machine M4: conversation compaction.
|
|
#
|
|
# Companion to:
|
|
# - docs/design/realtime-state-machines.md (the map + invariants)
|
|
# - core/http/endpoints/openai/compactcoord (the Go implementation)
|
|
#
|
|
# The Go MBT adapter maps each action below onto compactcoord.Coordinator.Apply
|
|
# and the StateGetter onto compactcoord.Coordinator.State, so this spec is the
|
|
# source of truth the implementation is checked against.
|
|
#
|
|
# The property: at most one background compaction runs per conversation at a time,
|
|
# so two goroutines never summarize+evict the same overflow concurrently (Part 4,
|
|
# invariant #9). The legacy guard is a `compacting atomic.Bool` CAS; here `active`
|
|
# is the number of in-flight compactions, started only from Idle.
|
|
#
|
|
# NOTE: FizzBee is pre-1.0. Validate the exact syntax/CLI against the version
|
|
# pinned in formal-verification/README.md before trusting the gate.
|
|
deadlock_detection: false
|
|
---
|
|
|
|
role Compactor:
|
|
action Init:
|
|
self.active = 0 # compactions in flight -- MUST stay in {0,1}
|
|
self.torn = 0 # session torn down (Terminated) -- absorbing
|
|
|
|
# maybeCompact wants to start a compaction. THE FIX: it starts one only when
|
|
# none is running (single-flight) and not after teardown. To reproduce the
|
|
# legacy race where two goroutines could both compact the same overflow,
|
|
# delete the `self.active == 0` guard (always increment): the checker then
|
|
# reports SingleFlight violated.
|
|
atomic action Trigger:
|
|
if self.active == 0 and self.torn == 0:
|
|
self.active += 1 # StartCompaction
|
|
|
|
# The background compaction goroutine finished (success, error, or timeout).
|
|
atomic action Finished:
|
|
if self.active > 0:
|
|
self.active -= 1
|
|
|
|
# Teardown: the connection (M1) parent cancels + joins the in-flight
|
|
# compaction, then terminates the coordinator so none can start afterwards.
|
|
atomic action Shutdown:
|
|
self.active = 0 # cancelled + joined
|
|
self.torn = 1
|
|
|
|
action Init:
|
|
c = Compactor()
|
|
|
|
# SAFETY: at most one compaction is ever in flight (Part 4, invariant #9).
|
|
always assertion SingleFlight:
|
|
return c.active >= 0 and c.active <= 1
|
|
|
|
# SAFETY: no compaction is in flight once torn (it was cancelled + joined at
|
|
# teardown), so none outlives the session.
|
|
always assertion NoneAfterTeardown:
|
|
return c.torn == 0 or c.active == 0
|