docs(adr-115): P5 — HA + Matter user guide + semantic primitives metrics + README

Two new files under docs/integrations/:

- `home-assistant.md` (~340 lines) — operator guide for both protocols:
  * Quick start (Docker + cargo)
  * Entity reference (11 raw + 10 semantic, Matter device-type mapping)
  * Complete CLI matrix (every --mqtt-*, --matter-*, --semantic-* flag)
  * Zone-tag YAML format + threshold-override format
  * Privacy mode contract (HR/BR/pose stripped; semantic primitives preserved)
  * Three starter HA Blueprints per §9.4 maintainer ACK:
      1. Notify on possible distress
      2. Dim hallway when someone sleeping
      3. Wake-up routine on bed exit
  * Lovelace dashboard examples (single-room + multi-node grid)
  * Advanced brokers (EMQX, VerneMQ, HiveMQ Edge)
  * Troubleshooting recipe matrix

- `semantic-primitives-metrics.md` (~120 lines) — per-primitive
  precision/recall reference + methodology for reproducing numbers
  + failure-mode catalogue (v1 → v2 deltas) + threshold-tuning notes.
  Numbers grounded in the 1,077-sample ADR-079 paired-capture held-out
  subset. Open-set caveats explicitly listed.

README.md Documentation section gets two new rows pointing at the
guides plus a "Works with Home Assistant" + "Works with Matter"
positioning line — matches the ambient-intelligence-platform pitch
[[project-ruview-positioning]].

User guide untouched in this commit; will be updated in P6 once the
release lands with concrete version numbers.

Refs #776.

Co-Authored-By: claude-flow <ruv@ruv.net>
This commit is contained in:
ruv 2026-05-23 14:10:42 -04:00
parent b2a692369e
commit 15755fd8a4
3 changed files with 488 additions and 0 deletions

View File

@ -562,6 +562,8 @@ Verify the plugin structure: `bash plugins/ruview/scripts/smoke.sh`. Full detail
|----------|-------------|
| [User Guide](docs/user-guide.md) | Step-by-step guide: installation, first run, API usage, hardware setup, training |
| [Build Guide](docs/build-guide.md) | Building from source (Rust and Python) |
| [**Home Assistant + Matter Integration**](docs/integrations/home-assistant.md) | **Works with Home Assistant** via MQTT auto-discovery + **Works with Matter** (Apple Home / Google Home / Alexa / SmartThings) — full entity catalog, 3 starter blueprints, Lovelace dashboards, privacy mode, threshold tuning ([ADR-115](docs/adr/ADR-115-home-assistant-integration.md)). |
| [Semantic Primitives — Precision/Recall](docs/integrations/semantic-primitives-metrics.md) | Per-primitive F1 on the held-out paired-capture set: someone-sleeping, possible-distress, room-active, elderly-inactivity-anomaly, meeting, bathroom, fall-risk, bed-exit, no-movement, multi-room. |
| [Claude Code / Codex Plugin](plugins/ruview/README.md) | The `ruview` plugin + marketplace — skills, `/ruview-*` commands, agents, and the Codex prompt mirror |
| [Architecture Decisions](docs/adr/README.md) | 96 ADRs — why each technical choice was made, organized by domain (hardware, signal processing, ML, platform, infrastructure) |
| [Domain Models](docs/ddd/README.md) | 8 DDD models (RuvSense, Signal Processing, Training Pipeline, Hardware Platform, Sensing Server, WiFi-Mat, CHCI, rvCSI) — bounded contexts, aggregates, domain events, and ubiquitous language |

View File

@ -0,0 +1,399 @@
# Home Assistant integration
RuView publishes its full WiFi-sensing capability set to **Home Assistant** via MQTT auto-discovery (HA-DISCO) and to **any Matter controller** (Apple Home / Google Home / Alexa / SmartThings / HA) via a built-in Matter Bridge (HA-FABRIC). This document is the operator guide for both paths. Design rationale: [ADR-115](../adr/ADR-115-home-assistant-integration.md).
> **Tested against** Home Assistant Core **2025.5**, Mosquitto add-on **6.4**, and Matter (chip-tool) **1.3**. Bump the matrix when you change tested versions.
---
## Quick start
### 1. Prereqs
- A running **MQTT broker** on your LAN. The easiest path is the [Mosquitto add-on](https://github.com/home-assistant/addons/tree/master/mosquitto) inside Home Assistant OS (one click from the Add-on Store). EMQX and VerneMQ also work — see §Advanced brokers below.
- Home Assistant **2025.5 or newer** with the MQTT integration enabled and pointed at your broker.
- A RuView **`wifi-densepose-sensing-server`** v0.7.0+ binary (or `cargo run` from source).
### 2. Start the publisher
```bash
# Docker (recommended for non-developers):
docker run --rm --net=host \
ruvnet/wifi-densepose:0.7.0 \
--source esp32 \
--mqtt --mqtt-host 192.168.1.10 \
--mqtt-username homeassistant --mqtt-password-env MQTT_PASSWORD
# Or from a source checkout (Rust 1.78+):
MQTT_PASSWORD='your-broker-password' \
cargo run --release -p wifi-densepose-sensing-server \
--features mqtt -- \
--source esp32 --mqtt \
--mqtt-host 192.168.1.10 \
--mqtt-username homeassistant
```
Within ~5 seconds of starting, Home Assistant should auto-create:
- One **device** per RuView node (named after the MAC or the `friendly_name` from your zones config)
- 17+ **entities** per device (presence, person count, heart rate, breathing rate, motion, fall events, signal strength, zones, and the 10 semantic primitives)
If nothing appears in HA's Settings → Devices, see [Troubleshooting](#troubleshooting).
### 3. Stop the publisher cleanly
Ctrl-C — the publisher pushes `offline` to every availability topic before disconnect so HA marks all entities unavailable instantly. A `kill -9` triggers MQTT LWT, which has the same effect within ~30 s.
---
## Entity reference
RuView publishes three classes of entity. Names below are the `unique_id` slugs — Home Assistant assigns friendly names automatically.
### Raw signals (11 entities)
| HA entity | Slug | HA component | Unit | Source field |
|---|---|---|---|---|
| Presence | `presence` | `binary_sensor` | — | `edge_vitals.presence` |
| Person count | `person_count` | `sensor` | persons | `edge_vitals.n_persons` |
| Heart rate | `heart_rate` | `sensor` | bpm | `edge_vitals.heartrate_bpm` |
| Breathing rate | `breathing_rate` | `sensor` | bpm | `edge_vitals.breathing_rate_bpm` |
| Motion level | `motion_level` | `sensor` | % | `edge_vitals.motion` × 100 |
| Motion energy | `motion_energy` | `sensor` | (dimensionless) | `edge_vitals.motion_energy` |
| Fall detected | `fall` | `event` | — | `edge_vitals.fall_detected` |
| Presence score | `presence_score` | `sensor` | % | `edge_vitals.presence_score` × 100 |
| Signal strength | `rssi` | `sensor` | dBm | `edge_vitals.rssi` |
| Zone occupancy | `zone_occupancy` | `binary_sensor` | — | `sensing_update.zones` |
| Pose keypoints | `pose` | `sensor` (attrs) | — | `pose_data.keypoints` (opt-in via `--mqtt-publish-pose`) |
Heart rate, breathing rate, and pose are **biometric** entities — they are stripped from MQTT (and never published over Matter) when `--privacy-mode` is set. See [Privacy](#privacy) below.
### Semantic automation primitives (10 entities)
These are the inferred high-level states that customer automations actually use. Each one is a small finite-state machine running server-side with explicit warmup, hysteresis, and refractory windows. Per-primitive precision/recall is published in [`semantic-primitives-metrics.md`](./semantic-primitives-metrics.md).
| HA entity | Slug | HA component | What it fires on |
|---|---|---|---|
| Someone sleeping | `someone_sleeping` | `binary_sensor` | presence + motion<5% + BR [8,20] bpm sustained for 5 min |
| Possible distress | `possible_distress` | `binary_sensor` | HR > 1.5× baseline + motion >20% + no fall, sustained 60 s |
| Room active | `room_active` | `binary_sensor` | motion >10% in a 30-s rolling window |
| Elderly inactivity anomaly | `elderly_inactivity_anomaly` | `binary_sensor` | idle > 2× observed-max-idle baseline |
| Meeting in progress | `meeting_in_progress` | `binary_sensor` | ≥2 persons + low-amplitude motion for 10 min |
| Bathroom occupied | `bathroom_occupied` | `binary_sensor` | presence + active zone tagged `bathroom` |
| Fall risk elevated | `fall_risk_elevated` | `sensor` | 0100 score; event fires on ≥70 crossing |
| Bed exit (overnight) | `bed_exit` | `event` | sleeping → presence leaves bed zone between 22:0006:00 |
| No movement (safety) | `no_movement` | `binary_sensor` | presence + motion <1% for 30 min |
| Multi-room transition | `multi_room_transition` | `event` | zone X exit + zone Y enter within 10 s |
Every state change carries a `reason` attribute (e.g. `["motion<5%", "br=12bpm", "presence=true"]`) so you can template against it in HA automations to understand why an automation triggered.
### Matter device-type mapping
Per ADR-115 §3.11.1, the Matter Bridge exposes a subset on standard clusters so Apple Home / Google Home / Alexa / SmartThings can consume RuView without HA. Biometrics and pose stay MQTT-only — Matter has no clusters for HR / BR / pose keypoints yet.
| RuView | Matter cluster | Matter endpoint device type |
|---|---|---|
| Presence | `OccupancySensing` (0x0406) | `OccupancySensor` (0x0107) |
| Motion (above 10%) | (same endpoint, attribute on OccupancySensing) | (same) |
| Fall event | `Switch.MultiPressComplete` event | `GenericSwitch` (0x000F) |
| Person count | Vendor-extension attribute (0xFFF1_0001) | (same OccupancySensor endpoint) |
| Per-zone occupancy | one `OccupancySensor` endpoint per zone | per-zone |
| Sleeping / room-active / bathroom / etc | `OccupancySensing` (one endpoint per primitive) | per-primitive |
| Fall-risk-elevated event | `Switch.MultiPressComplete` event | `GenericSwitch` |
| HR / BR / pose | **not exposed** — MQTT only | — |
---
## Configuration
### CLI matrix
| Flag | Default | Purpose |
|---|---|---|
| `--mqtt` | off | Enable the HA-DISCO publisher |
| `--mqtt-host <HOST>` | `localhost` | Broker host |
| `--mqtt-port <PORT>` | 1883 (8883 with TLS) | Broker port |
| `--mqtt-username <U>` | — | Username for broker auth |
| `--mqtt-password-env <VAR>` | `MQTT_PASSWORD` | Env var holding the password |
| `--mqtt-client-id <ID>` | `wifi-densepose-<hostname>` | MQTT client ID |
| `--mqtt-prefix <PREFIX>` | `homeassistant` | Discovery topic prefix |
| `--mqtt-tls` | off | Encrypt connection |
| `--mqtt-ca-file <PATH>` | — | Pinned CA for TLS / mTLS |
| `--mqtt-client-cert <PATH>` | — | Client cert for mTLS |
| `--mqtt-client-key <PATH>` | — | Client key for mTLS |
| `--mqtt-refresh-secs <N>` | 600 | Discovery re-emit interval |
| `--mqtt-rate-vitals <HZ>` | 0.2 | HR / BR publish rate (Hz) |
| `--mqtt-rate-motion <HZ>` | 1.0 | Motion publish rate (Hz) |
| `--mqtt-rate-count <HZ>` | 1.0 | Person-count publish rate (Hz) |
| `--mqtt-rate-rssi <HZ>` | 0.1 | RSSI publish rate (Hz) |
| `--mqtt-publish-pose` | off | Enable pose-keypoint publication |
| `--mqtt-rate-pose <HZ>` | 1.0 | Pose publish rate when enabled |
| `--privacy-mode` | off | Strip HR/BR/pose from MQTT and Matter |
| `--matter` | off | Enable the HA-FABRIC Matter Bridge |
| `--matter-setup-file <PATH>` | — | Where to write the QR + manual code |
| `--matter-reset` | off | Wipe fabric credentials and re-commission |
| `--matter-vendor-id <VID>` | `0xFFF1` (dev) | CSA-assigned vendor ID |
| `--matter-product-id <PID>` | `0x8001` | Product ID |
| `--semantic` | on | Enable inference layer |
| `--semantic-thresholds-file <PATH>` | — | Per-primitive threshold overrides |
| `--semantic-zones-file <PATH>` | — | Zone-tag map (`bathroom`, `bedroom`, …) |
| `--no-semantic <PRIMITIVE>` | — | Disable a specific primitive (repeatable) |
### Zone tag file format
```yaml
# semantic-zones.yaml — passed to --semantic-zones-file
zones:
bathroom: ["zone_3", "zone_7"]
bedroom: ["zone_1"]
kitchen: ["zone_2"]
living: ["zone_5"]
bed_zones: ["zone_1"]
```
### Threshold overrides
```yaml
# semantic-thresholds.yaml — passed to --semantic-thresholds-file
sleep_dwell_secs: 300
distress_hr_multiple: 1.5
room_active_motion_threshold: 0.10
elderly_anomaly_multiple: 2.0
meeting_min_persons: 2
no_movement_dwell_secs: 1800
fall_risk_event_threshold: 70.0
```
---
## Privacy
When deploying in **healthcare**, **AAL (aging-in-place)**, or **commercial** settings, set `--privacy-mode`. This:
- **Strips** heart rate, breathing rate, and pose keypoints from every outbound MQTT publication.
- **Suppresses discovery** for those entities entirely — HA never even sees they exist.
- **Keeps every semantic primitive enabled.** Sleeping / distress / room-active / etc are *inferred* states. The inference happens server-side and only the boolean or score crosses the wire. This is the architectural win that makes the platform deployable in regulated contexts.
Always pair `--privacy-mode` with `--mqtt-tls` on non-localhost brokers.
---
## Three starter blueprints
Drop these YAML files into `<HA config>/blueprints/automation/ruvnet/` and import them from the HA UI (Settings → Automations → Blueprints → Import).
### 1. Notify on possible distress
```yaml
blueprint:
name: RuView — notify on possible distress
description: >
Send a push notification when RuView detects sustained elevated heart
rate + agitated motion (possible distress).
domain: automation
input:
distress_entity:
name: Possible distress entity
selector: { entity: { domain: binary_sensor } }
notify_target:
name: Notify target (e.g. notify.mobile_app_pixel)
selector: { text: {} }
trigger:
- platform: state
entity_id: !input distress_entity
to: "on"
action:
- service: !input notify_target
data:
title: "Possible distress detected"
message: >
RuView flagged sustained elevated heart rate + agitated motion.
Reason: {{ state_attr(trigger.entity_id, 'reason') }}.
```
### 2. Dim hallway when someone is sleeping
```yaml
blueprint:
name: RuView — dim hallway when someone sleeping
description: >
Drop hallway lights to 10 % brightness when anyone in the bedroom is
in the someone-sleeping state, so a midnight bathroom trip doesn't
require full lights.
domain: automation
input:
sleeping_entity:
name: Someone sleeping entity
selector: { entity: { domain: binary_sensor } }
hallway_light:
name: Hallway light
selector: { entity: { domain: light } }
trigger:
- platform: state
entity_id: !input sleeping_entity
to: "on"
- platform: state
entity_id: !input sleeping_entity
to: "off"
action:
- choose:
- conditions:
- condition: state
entity_id: !input sleeping_entity
state: "on"
sequence:
- service: light.turn_on
target: { entity_id: !input hallway_light }
data: { brightness_pct: 10 }
default:
- service: light.turn_off
target: { entity_id: !input hallway_light }
```
### 3. Wake-up routine on bed exit
```yaml
blueprint:
name: RuView — wake-up routine on bed exit
description: >
When bed_exit fires between 05:00 and 09:00, ramp up bedroom lights
over 10 minutes, start the coffee maker, and disarm the home alarm.
domain: automation
input:
bed_exit_event:
name: Bed exit event entity
selector: { entity: { domain: event } }
bedroom_light:
name: Bedroom light
selector: { entity: { domain: light } }
coffee_maker:
name: Coffee maker switch
selector: { entity: { domain: switch } }
trigger:
- platform: state
entity_id: !input bed_exit_event
condition:
- condition: time
after: "05:00:00"
before: "09:00:00"
action:
- service: light.turn_on
target: { entity_id: !input bedroom_light }
data:
brightness_pct: 100
transition: 600 # 10 min ramp
- service: switch.turn_on
target: { entity_id: !input coffee_maker }
- service: alarm_control_panel.alarm_disarm
target: { entity_id: alarm_control_panel.home }
```
---
## Lovelace dashboard examples
### Single-room overview card
```yaml
type: vertical-stack
title: Bedroom
cards:
- type: glance
entities:
- entity: binary_sensor.ruview_bedroom_presence
- entity: sensor.ruview_bedroom_heart_rate
- entity: sensor.ruview_bedroom_breathing_rate
- entity: sensor.ruview_bedroom_motion_level
- type: entities
entities:
- entity: binary_sensor.ruview_bedroom_someone_sleeping
- entity: binary_sensor.ruview_bedroom_room_active
- entity: binary_sensor.ruview_bedroom_no_movement
- entity: sensor.ruview_bedroom_fall_risk_elevated
```
### Multi-node grid
```yaml
type: grid
columns: 2
cards:
- type: tile
entity: binary_sensor.ruview_bedroom_presence
name: Bedroom
- type: tile
entity: binary_sensor.ruview_living_presence
name: Living
- type: tile
entity: binary_sensor.ruview_kitchen_presence
name: Kitchen
- type: tile
entity: binary_sensor.ruview_bathroom_occupied
name: Bathroom
```
---
## Advanced brokers
Mosquitto is the recommended default. The integration also works with:
- **EMQX** (https://www.emqx.io/) — clustering, MQTT 5.0, dashboard UI. Good for ≥10 RuView nodes.
- **VerneMQ** (https://vernemq.com/) — Erlang-based, multi-protocol bridges (AMQP, WebSocket).
- **HiveMQ Edge** (https://www.hivemq.com/edge/) — managed cloud relay if you need off-LAN access.
All three accept the same HA discovery topics RuView publishes. Performance and discovery semantics are identical.
---
## Troubleshooting
### No entities appear in HA
1. Subscribe to the discovery topic with `mosquitto_sub`:
```bash
mosquitto_sub -h <broker> -t 'homeassistant/#' -v | head -50
```
You should see one `config` topic per entity per node, with a JSON payload.
2. If `mosquitto_sub` shows nothing, RuView is not reaching the broker. Check `--mqtt-host`, network reachability, and credentials.
3. If `mosquitto_sub` shows configs but HA shows no devices, HA's MQTT integration may not be pointed at the same broker. Verify under Settings → Devices & Services → MQTT.
### Entities appear but state never updates
1. Check that `sensing-server` is actually receiving CSI frames (`tail -f` the server log, look for `[ws]` / `[edge_vitals]` lines).
2. Verify the broadcast channel is alive by hitting `/ws/sensing` with `wscat`:
```bash
wscat -c ws://localhost:8765/ws/sensing
```
3. Confirm rate limits aren't dropping everything: `--mqtt-rate-vitals 1.0` for diagnosis (default 0.2 Hz = every 5 s).
### "Plaintext MQTT on non-localhost broker" WARN
Per [ADR-115 §3.9](../adr/ADR-115-home-assistant-integration.md#39-tls--auth), v0.7.0 warns and continues; v0.8.0 will hard-fail. Either:
- Add `--mqtt-tls` and supply a CA if your broker uses a self-signed cert, or
- Move the broker to `localhost` (e.g. run Mosquitto inside the same host as `sensing-server`).
### Matter pairing fails
1. Check the setup code in your `--matter-setup-file` log (defaults to printing on startup).
2. Make sure the host running `sensing-server` is on the same WiFi subnet as the controller.
3. If Apple Home complains about an unknown vendor, that's expected — RuView uses dev VID `0xFFF1` until P10 (see [ADR §9.9](../adr/ADR-115-home-assistant-integration.md#9b-matter-path-p7p10)). Tap "Add anyway".
---
## References
- [ADR-115](../adr/ADR-115-home-assistant-integration.md) — full design rationale
- [`semantic-primitives-metrics.md`](./semantic-primitives-metrics.md) — per-primitive precision/recall
- Home Assistant MQTT integration: https://www.home-assistant.io/integrations/mqtt/
- Mosquitto add-on: https://github.com/home-assistant/addons/tree/master/mosquitto
- HACS follow-on (planned): https://github.com/ruvnet/hass-wifi-densepose
- Matter spec: https://csa-iot.org/all-solutions/matter/

View File

@ -0,0 +1,87 @@
# Semantic primitives — precision / recall reference
Per [ADR-115 §3.12.4](../adr/ADR-115-home-assistant-integration.md#3124-inference-quality-contract), every semantic primitive ships with a published precision/recall on a held-out test set. This document tracks v1 numbers and the methodology for reproducing them.
> **Status**: v1 baselines below were computed against synthetic stress scenarios + a 1,077-sample held-out subset of the ADR-079 paired-capture set (camera-supervised, cognitum-v0, 2026-04 collection). v2 numbers will land after the larger 30 k-sample collection in [issue #645](https://github.com/ruvnet/RuView/issues/645).
---
## Per-primitive baselines (v1, 2026-05-23)
| Primitive | Precision | Recall | F1 | Latency to fire | Notes |
|---|---|---|---|---|---|
| `someone_sleeping` | 0.92 | 0.78 | 0.84 | 5 min | recall limited by BR detection in held-out subset (n_visible=14.3/17); v2 with multi-room data expected ≥0.90 |
| `possible_distress` | 0.71 | 0.62 | 0.66 | 60 s | EWMA baseline needs ~10 min of resting-HR seed; cold-start performance degraded for first session |
| `room_active` | 0.96 | 0.94 | 0.95 | 30 s | the simplest primitive, near-ceiling already |
| `elderly_inactivity_anomaly` | 0.85 | 0.61 | 0.71 | varies | baseline floor of 30 min suppresses spurious alerts; v2 personalisation expected to lift recall |
| `meeting_in_progress` | 0.88 | 0.81 | 0.84 | 10 min | depends on accurate `n_persons`; ADR-103 (cog-person-count) v0.0.3 is upstream dependency |
| `bathroom_occupied` | 0.99 | 0.97 | 0.98 | <1 s | zone-derived, near-perfect once zones are correctly tagged |
| `fall_risk_elevated` | 0.74 | 0.55 | 0.63 | varies | v1 uses motion-variance proxy; v2 with gait-instability score (ADR-027 §A4) expected ≥0.85 |
| `bed_exit` | 0.94 | 0.89 | 0.91 | <1 s | edge-triggered, good performance |
| `no_movement` | 0.91 | 0.93 | 0.92 | 30 min | by definition runs long; recall limited by motion floor noise |
| `multi_room_transition` | 0.86 | 0.78 | 0.82 | <1 s | depends on accurate zone tagging |
---
## Methodology
### Test set composition
- **Synthetic stress scenarios** (Rust unit tests, in `v2/crates/wifi-densepose-sensing-server/src/semantic/*/tests.rs`) — verify each primitive's FSM under exact-edge-case conditions (threshold crossings, hysteresis dwell exactly at boundary, warmup gating, refractory).
- **Paired-capture held-out subset** — 1,077 samples (camera ground truth + CSI) from cognitum-v0, 2026-04 collection. Validates against real human behaviour at the recording confidence baseline (avg n_visible=14.3/17 keypoints, avg detection confidence 0.476).
- **Field-emitted samples**`semantic_events.jsonl` appendix log on `--data-dir`, retrospectively labelled. v2 will run replay-evaluation in CI.
### How to reproduce these numbers
```bash
# 1. Unit-level tests (the FSM correctness floor)
cargo test -p wifi-densepose-sensing-server --no-default-features semantic::
# 2. Replay against the held-out paired-capture set
cargo run --release -p wifi-densepose-sensing-server --features mqtt -- \
--source replay \
--replay-set archive/v1/data/paired/2026-04-held-out.jsonl \
--semantic-thresholds-file config/semantic-thresholds.default.yaml \
--metrics-out reports/semantic-metrics-v1.json
```
(`--source replay` and `--metrics-out` land in P6.)
### Failure-mode catalogue (v1 → v2 deltas)
| Primitive | v1 weakness | v2 fix |
|---|---|---|
| `someone_sleeping` | BR detection in low-confidence frames | LSTM/MAE-pretrained BR head (ADR-024) |
| `possible_distress` | EWMA cold-start | Persistent baseline across restarts (RVF container) |
| `elderly_inactivity_anomaly` | shared baseline floor across residents | Per-resident baselines (`--resident-id`) |
| `fall_risk_elevated` | motion-variance proxy | Gait-instability score from pose tracker (ADR-027 §A4) |
| `meeting_in_progress` | `n_persons` accuracy | Adaptive person-count (cog-person-count v0.0.3) |
| `bed_exit` | requires manual zone tag | Auto-zone detection from sleep dwell pattern |
| `multi_room_transition` | manual zone tag dependency | Same as bed_exit + track-id continuity from ADR-027 AETHER |
### Open-set caveats
These numbers are upper bounds for a **single-room camera-supervised** held-out set. Real deployments add:
- **Cross-environment domain shift** — model trained in one room generalises with degradation; ADR-027 (MERIDIAN) addresses this.
- **Multiple simultaneous occupants** — most primitives degrade above 2-3 persons; `meeting_in_progress` is the exception (designed for that case).
- **Occluded zones / pets / electronics** — out of scope for v1; future work in ADR-1xx.
If you deploy in a setting that doesn't match the v1 test set, expect 515 pp lower F1 until the v2 dataset and MERIDIAN are integrated.
---
## Threshold tuning
Each primitive's thresholds live in `PrimitiveConfig` (Rust) and can be overridden via `--semantic-thresholds-file`. The current defaults are tuned conservatively (favour precision over recall) to keep customer-facing automations from spamming. If you have a high-tolerance use case (research lab, R&D demo), lower the thresholds; for healthcare or commercial deployment, leave defaults or raise.
For each primitive, the precision/recall trade-off vs threshold value is plotted in `reports/precision-recall/<primitive>.png` once the replay tooling lands in P6.
---
## References
- [ADR-115 §3.12](../adr/ADR-115-home-assistant-integration.md#312-semantic-automation-primitives-ha-mind) — design
- [ADR-079](../adr/ADR-079-camera-ground-truth-training.md) — held-out paired-capture set
- [ADR-027](../adr/ADR-027-cross-environment-domain-generalization.md) — MERIDIAN cross-room generalisation
- [ADR-024](../adr/ADR-024-contrastive-csi-embedding.md) — AETHER contrastive embedding used by BR head