Updates

docs/ROADMAP.md

@@ -61,12 +61,13 @@ and run tests without importing dlinux.
 - [x] Serialize model loading and share the resulting harness engine.
 - [x] Request `device: "gpu"`, `gpu_layers: 99`, and GPU multimodal projection.
 - [x] Reject a CPU result instead of accepting QVAC's internal fallback.
+- [x] Preflight QVAC GPU visibility before downloading or loading a model.
 - [x] Add owner counting and a single close path.
 - [x] Set `QVAC_CONFIG_PATH`, `JARVIS_QVAC_MODEL`, and GPU policy in the user
   service.
 - [~] Add `gpu-doctor`; extend it to report QVAC resource capabilities, backend,
   driver, device name, VRAM, model fit, and the exact reason for failure.
-- [ ] Add master scheduler lanes: interactive voice, computer-use vision,
+- [x] Add master scheduler lanes: interactive voice, computer-use vision,
   background media, and maintenance.
 - [ ] Add VRAM admission control and queue media jobs instead of OOMing the
   voice lane.
@@ -101,9 +102,9 @@ GPU-owned worker.
 ## Phase 3 — daemon lifecycle and D-Bus
 
 - [~] Define `io.qvac.Jarvis.Session` XML.
-- [ ] Implement `Arm`, `Sleep`, `Shutdown`, `Say`, `Ask`, `Cancel`, `SetMode`,
+- [~] Implement `Arm`, `Sleep`, `Shutdown`, `Say`, `Ask`, `Cancel`, `SetMode`,
   and state queries.
-- [ ] Implement token, transcript, reply, audio-level, chip, job, computer
+- [~] Implement token, transcript, reply, audio-level, chip, job, computer
   step, and error signals.
 - [ ] Keep payloads small; stream PCM and screenshots through a Unix socket or
   tmpfs paths.