omnius 1.0.631 → 1.0.634

package/README.md

@@ -484,6 +484,8 @@ The MCP equivalent uses a transport such as
 | `GET` | `/v1/memory/entities` | List extracted memory entities |
 | `POST` | `/v1/memory/jobs/run` | Run a named memory-maintenance job |
 | `POST` | `/v1/memory/feedback` | Record relevance or quality feedback for a memory item |
+| `POST` | `/v1/memory/speaker-identities/enroll` | Admin-only, explicit-consent speaker exemplar enrollment in one exact vector space |
+| `POST` | `/v1/memory/speaker-identities/match` | Admin-only provisional speaker candidate matching without durable assignment |
 | `GET` | `/v1/sessions` | List task sessions |
 | `GET` | `/v1/sessions/{id}` | Get session history |
 | `GET` | `/v1/context` | Current context snapshot |
@@ -538,9 +540,17 @@ the store, `OMNIUS_DISABLE_CONTEXT_WINDOW_DUMPS=1` to disable it, and
 | `GET` | `/v1/audio/classify/health` | Jetson CUDA/TensorRT YAMNet readiness |
 | `POST` | `/v1/audio/classify/setup` | Provision and warm the pinned JetPack TensorRT YAMNet runtime |
 | `POST` | `/v1/audio/classify` | Direct-tool compatible CUDA audio classification |
-| `GET` | `/v1/ocr/readiness` | Advanced OCR package/engine/backend readiness (non-mutating) |
-| `POST` | `/v1/ocr/setup` | Create and verify the isolated advanced OCR runtime |
-| `POST` | `/v1/ocr/advanced` | Agent-equivalent advanced OCR direct-tool alias |
+| `GET` | `/v1/audio/embed/health` | Role-typed embedding readiness (`?kind=acoustic|speaker|semantic`) |
+| `POST` | `/v1/audio/embed/setup` | Provision/warm one role-typed embedding runtime (admin; `?kind=...`) |
+| `POST` | `/v1/audio/embed` | Managed role-typed audio embedding (`?kind=...`) |
+| `GET` | `/v1/audio/diarization/live/readiness` | Non-mutating live/session-local diarization readiness (currently unavailable) |
+| `POST` | `/v1/audio/diarization/live/setup` | Verify/register local Sortformer snapshot (admin; not inference-ready) |
+| `POST` | `/v1/audio/diarization/live` | Reserved managed live speaker-turn contract (currently typed 503) |
+| `POST` | `/v1/audio/diarization/live/cancel` | Cancel managed live diarization when a worker is available |
+| `GET` | `/v1/audio/diarization/reconcile/readiness` | Non-mutating offline/dream reconciliation readiness (currently unavailable) |
+| `POST` | `/v1/audio/diarization/reconcile/setup` | Verify/register local pyannote snapshot (admin; not inference-ready) |
+| `POST` | `/v1/audio/diarization/reconcile` | Reserved managed reconciliation contract (currently typed 503) |
+| `POST` | `/v1/audio/diarization/reconcile/cancel` | Cancel managed reconciliation when a worker is available |
 | `POST` | `/v1/voice/transcribe` | Transcribe audio |
 | `POST` | `/v1/voice/asr` | Legacy transcription alias |
 | `POST` | `/v1/audio/transcriptions` | OpenAI-compatible transcription alias |
@@ -556,7 +566,9 @@ the store, `OMNIUS_DISABLE_CONTEXT_WINDOW_DUMPS=1` to disable it, and
 | `GET` | `/v1/voicechat/ws` | WebSocket upgrade for full-duplex voicechat |
 | `POST` | `/v1/vision/describe` | Vision describe placeholder |
 | `POST` | `/v1/vision/embed` | Create a vision embedding from media |
-| `POST` | `/v1/audio/embed` | Create an audio embedding from audio input |
+| `GET` | `/v1/ocr/readiness` | Non-mutating advanced-OCR dependency and backend readiness |
+| `POST` | `/v1/ocr/setup` | Create and verify the isolated OCR venv (admin scope) |
+| `POST` | `/v1/ocr/advanced` | Agent-equivalent managed advanced OCR (alias of `/v1/tools/ocr_image_advanced/call`) |
 
 `POST /v1/voice/tts` and `/v1/audio/speech` automatically warm the daemon.
 An explicit model must render exactly or the request fails; Omnius does not