Readd health scores

Avoids constantly turning off a held LED.

README.md

@@ -1,5 +1,8 @@
 # SuperSensor v2.x
 
+**NOTICE**: The Supersensor v2.x is still under development! Parts and configurations
+may change until the design is finalized.
+
 The SuperSensor is an all-in-one voice, motion, presence, temperature/humidity/air
 quality, and light sensor, built on an ESP32 with ESPHome, and inspired
 heavily by the EverythingSmartHome Everything Presence One sensor and the
@@ -18,8 +21,7 @@ it bare if you like the "PCB on a wall" aesthetic.
 To Use:
 
   * Install the ESPHome configuration `supersensor.yaml` to a compatible ESP32 devkit (below).
-  * Install the ESP32 and sensors into the custom PCB (if desired).
+  * Install the ESP32 and sensors into the custom PCB.
-  * [Optional] 3D Print the custom case.
   * Power up the SuperSensor, connect to the WiFi AP, and connect it to your network.
   * Install the SuperSensor somewhere that makes sense.
   * Add/adopt the SuperSensor to HomeAssistant using the automatic name.
@@ -39,15 +41,15 @@ and [my update post on version 2.0](https://www.boniface.me/the-supersensor-2.0)
 
 ## Major Changes from 1.x
 
-1. Replaced the Bosch BME680 with the Sensirion SHT45 and Sensirion SGP30.
+1. Replaced the Bosch BME680 with the Sensirion SHT45 and Sensirion SGP41.
 
    The BME680 proved to be woefully unreliable in my testing. Temperature was fairly accurate (internal heating and offset notwithstanding),
    but humidity was wildly off of what other thermometers/hydrometers would report. In addition, the AQ functionality of the sensor was a
    source of much frustration and I was never able to get it to work reliably, either with the official BSEC library or with my own attempts
    at self-configuration.
 
-   Thus, this sensor has been replaced with two Sensirion sensors which in my experience so far have been much more reliable and consistent,
+   Thus, this sensor has been replaced with two Sensirion sensors which in my experience so far have been much more reliable and consistent.
-   and the cost difference is negligible.
+   There is a slight cost increase due to these sensors, but not signfigant enough to outweigh the benefit of reliable monitoring they confer.
 
 2. Replaced the SR602 PIR sensor with the AM312 PIR sensor.
 
@@ -61,15 +63,12 @@ and [my update post on version 2.0](https://www.boniface.me/the-supersensor-2.0)
 3. Completely redesigned the custom PCB around the above sensor changes, which is now more compact in a 50x55mm almost-square configuration.
 
 4. Significantly cleaned up the ESPHome configuration, to support the above sensors and remove a lot of cruft that was caused by the BME680.
-   This includes a new set of custom AQ calculations based on the SGP30 and SHT45 sensors that, while not necessarily following the full EPA
-   IAQI spec, should still give a reasonable view of the air quality conditions of an interior room and not deviate wildly and nonsensically
-   like the BME680 did. Details of the calculation are provided below.
 
 ## Parts List
 
 | Qty   | Component          | Cost (2025/05 CAD, ex. shipping) | Links |
 |-------|--------------------|----------------------------------|-------|
-| 1     | GY-SGP30           | $5.73                            | [AliExpress](https://www.aliexpress.com/item/1005008473372972.html)  |
+| 1     | GY-SGP41           | $11.08                           | [AliExpress](https://www.aliexpress.com/item/1005006746827606.html)  |
 | 1     | GY-SHT45           | $5.67                            | [AliExpress](https://www.aliexpress.com/item/1005008175340220.html)* |
 | 1     | SR602              | $0.81                            | [AliExpress](https://www.aliexpress.com/item/1005001572550300.html)  |
 | 1     | TSL2591            | $4.59                            | [AliExpress](https://www.aliexpress.com/item/1005008619462097.html)  |
@@ -78,16 +77,59 @@ and [my update post on version 2.0](https://www.boniface.me/the-supersensor-2.0)
 | 1     | ESP32 HW-395       | $6.67                            | [AliExpress](https://www.aliexpress.com/item/1005006019875837.html)* |
 | 2     | RBG LED            | $0.09 ($9.12/100)                | [Amazon](https://www.amazon.ca/dp/B09Y8M2PKS) |
 | 1     | 470Ω resistor      | $0.08 ($7.99/100)                | [Amazon](https://www.amazon.ca/dp/B08MKQX2XT) |
-| 1     | Female pin header† | $1.59 ($15.99/10)                | [Amazon](https://www.amazon.ca/dp/B08CMNRXJ1) |
+| 2     | Female pin header† | $1.59 ($15.99/10)                | [Amazon](https://www.amazon.ca/dp/B08CMNRXJ1) |
 | 1     | Custom PCB (JLC)   | $0.69 ($6.89/10)                 | [GitHub](https://github.com/joshuaboniface/supersensor) |
-| 1     | 3D Printed case    | $?.??‡                           | [GitHub](https://github.com/joshuaboniface/supersensor) |
+| **TOTAL** |                    | **$40.58**                           |       |
-| **TOTAL** |                    | **$33.64**                           |       |
 
 `*` Ensure you select the correct device on the page as it shows multiple options.
 
-`†` This is optional and only required if you don't want to directly solder the ESP32 to the board, but I recommend it.
+`†` One of these sets is optional, and is useful if you do not want to solder the individual sensors directly to the board (see below).
 
-`‡` Providing a price is impossible due to the wide range of possible fillament types and brands, but should be negligible.
+### To Solder or Not To Solder
+
+Personally, for my Supersensor 1.x's and the initial batch of Supersensor 2.x's, I directly soldered
+all the non-ESP components to the board. This proved to be a major mistake when I later decided
+to switch from SGP30's to SGP41's after some testing and I had to desolder all of them, ruining
+several PCBs in the process. It was also a hassle to desolder the existing sensors for reuse
+during the 1.x to 2.x conversion.
+
+As a result, I actually strongly encourage anyone building one of these units to leverage sockets
+for all components, to allow for quick swapping if any turn out to be defective or if future changes
+are warranted.
+
+Note that due to the PCB design, you *must* socket at least one set of components - either the ESP32
+or the sensors on the front. Due to the positioning and overlap, it would be impossible to solder
+everything directly to the board, as the ESP covers several of the solder points of the front
+sensors and vice versa.
+
+You can use the provided 40-pin female headers exclusively if you wish, and cut them to length for
+the individual sensors as needed, or you can use individually-sized female headers in the following
+quantities should you wish for a slightly neater finish:
+
+* 3x 3-pin (AM302, INMP441 x2)
+* 2x 4-pin (SGP41, SHT45)
+* 1x 5-pin (LD2410C)
+* 1x 6-pin (TSL2591)
+
+I will leave it up to the reader to source these specific sizes if they desire (I found all except
+a 5-pin on Amazon, and just used a 6-pin with one pin removed).
+
+I still directly solder the RGB LEDs and resistor to the board for simplicity as these very small
+leads are not easily socketed, and these components are so inexpensive as to be effectively
+disposable along with the PCB should that be required.
+
+### Part Swaps
+
+To save a little money, it is possible to swap out the two Sensirion sensors for their less-feature-
+rich peers, with no code changes:
+
+* SGP41 -> SGP40 - removes the NOx functionality
+* SHT45 -> SHT40/41/43 - less accuracy
+
+Personally, I do not find the minimal cost savings to be worth sacrificing the extra potential
+functionality, so I recommend using the provided models, but this is up to the builder to decide.
+
+No other parts can be easily swapped without code or PCB design changes.
 
 ## Configurable Options
 
@@ -109,17 +151,19 @@ SuperSensors in a single room and only want one to respond to voice commands.
 If enabled (the default), when overall presence is detected, the LEDs will
 glow "white" at 15% power to signal presence.
 
-### Temperature Offset (selector, -10 to +5 @ 0.1, -5 default)
+### Temperature Offset (selector, -30 to +10 @ 0.1, -5 default)
 
-Allows calibration of the SHT45 temperature sensor with an offset from -10 to +5
+Allows calibration of the SHT45 temperature sensor with an offset from -30 to +10
 degrees C. Useful if the sensor is misreporting actual ambient tempreatures. Due
 to internal heating of the SHT45 by the ESP32, this defaults to -5; further
-calibration may be needed for your sensors and environment.
+calibration may be needed for your sensors and environment based on an external
+reference.
 
-### Humidity Offset (selector, -10 to +10 @ 0.1)
+### Humidity Offset (selector, -20 to +20 @ 0.1)
 
 Allows calibration of the SHT45 humidity sensor with an offset from -10 to +10
-percent relative humidity. Useful if the sensor is misreporting actual humidity.
+percent relative humidity. Useful if the sensor is misreporting actual humidity
+based on an external reference.
 
 ### PIR Hold Time (selector, 0 to +60 @ 5, 0 default)
 
@@ -227,70 +271,28 @@ is likely not useful.
 
 ## AQ Details
 
-The SuperSensor 2.x provides 2 base air quality sensors (numeric), from which
+The SuperSensor 2.0 features an SGP41 air quality sensor by Sensirion. This is a powerful AQ
-4 human-readable text sensors are derived.
+sensor which powers several commercial devices including the AirGradient One, which gave
+us a lot of our configuration via their sharing of algorithms.
 
-The goal of these sensors is to track general comfort and livability in a
+The sensor provides two base readings: a VOC Index, and a NOx Index. These values are both
-room, not specific contaminants or conditions. Because the SGP30 can only
+floating references centered at 100 (VOC) and 1 (NOx), where that value represents "normal"
-track TVOC and eCO2, we do not track particulates, CO, NOx, or CH2O, all
+air over the previous 24 hours. These sensors are very useful for any sort of quick-change
-of which are required for a full EPA (I)AQI score. This means the best
+automations, e.g. turn on a fan if levels spike due to cooking.
-we can do is approximate (I)AQI roughly, and since a scale of 0-500 based
-on approximations seems pointless, I went with much simpler 1-4/5 scores
-instead. I feel this does a good enough job to be useful for 99% of rooms.
 
-We also cannot really debate whether the BME680 is actually any more accurate
+In addition, we leverage AirGradient's published forumulas to convert the VOC index into
-in this regard, since their algorithms are proprietary and all that is exposed
+actual VOC quantities, in both µg/m³ and ppb. While this may drift due to the sensor's regular
-normally is a single resistance value, so in my opinion this is actually
+internal recalibration, I feel that following what AirGradient does is sufficient enough
-superior to that sensor anyways with two discrete datapoints (versus one),
+for any real-world home usage. Further, we use a very rough conversion of the aforementioned
-even if it does still seem limited when compared to dedicated AQ sensors.
+VOC quantity into an eCO2 reading, using Isobutylene as a reference gas. These sensors are
-And that is to say nothing of the issues with that sensor (constantly climbing
+more useful for display purposes, to show the current levels in a room in a dashboard or
-IAQ values over time, poor calibration, etc.).
+other such place, for human consumption. Note that no such conversions are done for NOx as
+there are no (that I can find) published empirical calculations for this conversion, unlike
+for VOCs via AirGradient.
 
-### Base Numeric Values
+Note however that like all MOx sensors, the SGP41 does not differentiate gasses, and as
-
+such cannot tell the difference between normal, everyday natural VOCs like those in
-#### IAQ Index (1-5)
+breath or from e.g. ripening fruit, and dangerous VOCs from e.g. construction materials.
-
+These should be used only as a general indication of air quality over short periods, rather
-The IAQ index is calculated based on the TVOC and eCO2 values from the SGP30
+than an absolute reference over long periods (much to my own frustration but inevitable
-sensor, to provide 5 levels of air quality. This corresponds approximately
+begruding acceptance).
-to the levels provided by the BME680 (0-50, 50-100, 100-200, 200-300, 300+).
-
-5 is "excellent": the TVOC is <65 ppb and the eCO2 is <600 ppm.
-4 is "good": the TVOC is 65-220 ppb or the eCO2 is 600-800 ppm.
-3 is "moderate": the TVOC is 220-660 ppb or the eCO2 is 800-1200 ppm.
-2 is "poor": the TVOC is 660-2200 ppb or the eCO2 is 1200-2000 ppm.
-1 is "unhealthy": the TVOC is >2200 ppb or the eCO2 is >2000 ppm.
-
-#### Room Health Score (1-4)
-
-The Room Health Score is calculated based on the IAQ, temperature, and humidity,
-and is designed to show how "nice" a room is to be in. Generally a 4 is a nice
-place to be, especially for someone with respiratory issues like myself, and lower
-scores indicate more deviations from the norms or poor IAQ.
-
-4 is "optimal": IAQ is >= 4 ("excellent" or "good"), temperature is between 18C and 24C, and humidity is between 40% and 60%.
-3 is "fair": One of the above is not true, and IAQ is >= 3 ("moderate").
-2 is "poor": Two of the above are not true, and IAQ is >= 2 ("poor").
-1 is "bad": All of the above are not true or IAQ is 1 ("unhealthy") regardless of other values.
-
-Note that IAQ levels hold a major sway over this level, and decreasing IAQ
-scores will push the room score lower regardless of temperature or humidity.
-It is best used together with the individual sensors to determine exactly
-what is wrong with the room.
-
-### Derived Text Sensors
-
-#### VOC Level
-
-This reports the VOC level alone, based on the scale under IAQ Index, in textual form ("Excellent, "Good", etc.).
-
-#### CO2 Level
-
-This reports the eCO2 level alone, based on the scale under IAQ Index, in textual form ("Excellent, Good", etc.).
-
-#### IAQ Classification
-
-This reports the IAQ Index in textual form ("Excellent", "Good", etc.).
-
-#### Room Health
-
-This reports the Room Health Score in textual form ("Optimal", "Fair", "Poor", "Bad").

supersensor.yaml

@@ -103,6 +103,11 @@ globals:
     restore_value: no
     initial_value: "0"
 
+  - id: current_wake_word
+    type: std::string
+    restore_value: yes
+    initial_value: '"mww_computer"'
+
 script:
   - id: light_off
     then:
@@ -253,6 +258,17 @@ script:
           }
 
 interval:
+  # Regular MWW state check every 30s
+  - interval: 30s
+    then:
+      - if:
+          condition:
+            - switch.is_on: enable_voice_support
+            - not:
+                micro_wake_word.is_running
+          then:
+            - micro_wake_word.start:
+
   # Regular occupancy state reporting to HASS every 30s
   - interval: 30s
     then:
@@ -273,7 +289,7 @@ interval:
           }
 
 logger:
-  level: WARN
+  level: DEBUG
   baud_rate: 115200
 
 api:
@@ -330,6 +346,9 @@ time:
       then:
         - logger.log: "Time synchronized with Home Assistant"
 
+debug:
+  update_interval: 15s
+
 uart:
   id: ld2410_uart
   rx_pin: GPIO19
@@ -364,9 +383,11 @@ micro_wake_word:
   id: mww
   microphone:
     microphone: mic
-    gain_factor: 4
+    gain_factor: 8
   stop_after_detection: false
   models:
+    - model: github://genehand/Custom_V2_MicroWakeWords/models/computer/computer.json@update-json
+      id: mww_computer
     - model: github://esphome/micro-wake-word-models/models/v2/hey_jarvis.json
       id: mww_hey_jarvis
     - model: github://esphome/micro-wake-word-models/models/v2/hey_mycroft.json
@@ -392,8 +413,8 @@ voice_assistant:
   micro_wake_word: mww
   use_wake_word: false
   noise_suppression_level: 3
-  auto_gain: 4 dbfs
+  auto_gain: 31 dbfs
-  volume_multiplier: 8
+  volume_multiplier: 4
   on_wake_word_detected:
     - logger.log: "Wake word detected in VA pipeline"
     - light.turn_on:
@@ -515,34 +536,75 @@ sensor:
       return heap_caps_get_free_size(MALLOC_CAP_INTERNAL) / 1024;
     entity_category: diagnostic
 
-  - platform: sgp30
+  - platform: debug
-    eco2: 
+    free:
-      name: "SGP30 eCO2"
+      name: "Heap Free"
-      id: sgp30_eco2
+    block:
-      accuracy_decimals: 1
+      name: "Heap Max Block"
+    loop_time:
+      name: "Loop Time"
+    cpu_frequency:
+      name: "CPU Frequency"
+
+  - platform: sgp4x
+    voc:
+      name: "SGP41 VOC Index"
+      id: sgp41_voc_index
+      accuracy_decimals: 0
+      icon: mdi:waves-arrow-up
+      filters:
+        - sliding_window_moving_average:          # We take a reading every 15 seconds, but calculate the sliding
+            window_size: 12                       # average over 12 readings i.e. 60 seconds/1 minute to normalize
+            send_every: 3                         # brief spikes while still sending a value every 15 seconds.
+    nox:
+      name: "SGP41 NOx Index"
+      id: sgp41_nox_index
+      accuracy_decimals: 0
+      icon: mdi:waves-arrow-up
       filters:
         - sliding_window_moving_average:
-            window_size: 20
+            window_size: 12
-            send_every: 1
+            send_every: 3
-    tvoc:
-      name: "SGP30 TVOC"
-      id: sgp30_tvoc
-      accuracy_decimals: 1
-      filters:
-        - sliding_window_moving_average:
-            window_size: 20
-            send_every: 1
-    eco2_baseline:
-      name: "SGP30 Baseline eCO2"
-      id: sgp30_baseline_ec02
-    tvoc_baseline:
-      name: "SGP30 Baseline TVOC"
-      id: sgp30_baseline_tvoc
     compensation:
       temperature_source: sht45_temperature
       humidity_source: sht45_humidity
-    store_baseline: yes
+    store_baseline: true
-    update_interval: 15s
+    update_interval: 5s
+
+  - platform: template
+    name: "SGP41 TVOC (µg/m³)"
+    id: sgp41_tvoc_ugm3
+    icon: mdi:molecule
+    lambda: |-
+      float i = id(sgp41_voc_index).state;
+      if (i < 1) return NAN;
+      float tvoc = (log(501.0 - i) - 6.24) * -878.53;
+      return tvoc;
+    unit_of_measurement: "µg/m³"
+    accuracy_decimals: 0
+
+  - platform: template
+    name: "SGP41 TVOC (ppb)"
+    id: sgp41_tvoc_ppb
+    icon: mdi:molecule
+    lambda: |-
+      float tvoc_ugm3 = id(sgp41_tvoc_ugm3).state;
+      float tvoc_ppm = tvoc_ugm3 * 0.436;  // ppb estimated using isobutylene MW (56.1 g/mol)
+      return tvoc_ppm;
+    unit_of_measurement: "ppb"
+    accuracy_decimals: 0
+
+  - platform: template
+    name: "SGP41 eCO2 (appr.)"
+    id: sgp41_eco2_appr
+    icon: mdi:molecule-co2
+    lambda: |-
+      float tvoc_ppb = id(sgp41_tvoc_ppb).state;
+      float eco2_ppm = 400.0 + 1.5 * tvoc_ppb;
+      if (eco2_ppm > 2000) eco2_ppm = 2000;
+      return eco2_ppm;
+    unit_of_measurement: "ppm"
+    accuracy_decimals: 0
 
   - platform: sht4x
     temperature:
@@ -572,9 +634,9 @@ sensor:
     humidity: sht45_humidity
     id: sht45_absolute_humidity
 
-  # Dew Point
   - platform: template
     name: "SHT45 Dew Point"
+    icon: mdi:thermometer-water
     id: sht45_dew_point
     unit_of_measurement: "°C"
     lambda: |-
@@ -586,47 +648,38 @@ sensor:
       return (b * alpha) / (a - alpha);
     update_interval: 15s
 
-  # IAQ Index (1-5, 5=Excellent)
-  - platform: template
-    name: "IAQ Index"
-    id: iaq_index
-    lambda: |-
-      int tvoc = id(sgp30_tvoc).state;
-      int eco2 = id(sgp30_eco2).state;
-      if (tvoc > 2200 || eco2 > 2000) return 1; // Unhealthy
-      if (tvoc > 660 || eco2 > 1200) return 2; // Poor
-      if (tvoc > 220 || eco2 > 800) return 3; // Moderate
-      if (tvoc > 65 || eco2 > 500) return 4; // Good
-      return 5; // Excellent
-    update_interval: 15s
-
-  # Room Health Score (1-4, 4=Optimal)
   - platform: template
     name: "Room Health Score"
-    id: room_health
+    id: room_health_score
+    unit_of_measurement: "%"
+    accuracy_decimals: 0
+    icon: mdi:home-heart
     lambda: |-
+      float voc_index = id(sgp41_voc_index).state;
       float temp = id(sht45_temperature).state;
-      float rh = id(sht45_humidity).state;
+      float humidity = id(sht45_humidity).state;
-      int iaq = id(iaq_index).state;
   
-      bool temp_ok = (temp >= 18 && temp <= 24);
+      // VOC Score (0–100)
-      bool hum_ok = (rh >= 40 && rh <= 60);
+      float voc_score = 0;
-      bool iaq_ok = (iaq >= 4);
+      if (voc_index <= 100) voc_score = 100;
+      else if (voc_index <= 200) voc_score = 80;
+      else if (voc_index <= 300) voc_score = 60;
+      else if (voc_index <= 400) voc_score = 40;
+      else if (voc_index <= 500) voc_score = 50;
+      else voc_score = 0;
   
-      int conditions_met = 0;
+      // Temperature Score (0–100)
-      if (temp_ok) conditions_met++;
+      float temp_score = 100.0 - abs(temp - 23.0) * 10.0;
-      if (hum_ok) conditions_met++;
+      if (temp_score < 0) temp_score = 0;
-      if (iaq_ok) conditions_met++;
   
-      if (iaq_ok && temp_ok && hum_ok) {
+      // Humidity Score (0–100), ideal range 35–55%
-        return 4; // Optimal: All conditions met and IAQ is excellent/good
+      float humidity_score = 100.0 - abs(humidity - 50.0) * 3.0;
-      } else if (iaq >= 3 && conditions_met >= 2) {
+      if (humidity_score < 0) humidity_score = 0;
-        return 3; // Fair: IAQ is moderate and at least 2 conditions met
+  
-      } else if (iaq >= 2 && conditions_met >= 1) {
+      // Weighted average
-        return 2; // Poor: IAQ is poor and at least 1 condition met
+      float overall_score = (voc_score * 0.5 + temp_score * 0.25 + humidity_score * 0.25);
-      } else {
+  
-        return 1; // Bad: All conditions failed or IAQ is unhealthy
+      return round(overall_score);
-      }
     update_interval: 15s
 
   - platform: tsl2591
@@ -679,9 +732,8 @@ binary_sensor:
     name: "SuperSensor Occupancy"
     id: supersensor_occupancy
     device_class: occupancy
-    on_press:
+    on_state:
-      - script.execute: light_off
+      then:
-    on_release:
         - script.execute: light_off
 
   - platform: gpio
@@ -731,6 +783,10 @@ binary_sensor:
       name: "LD2410C Still Target"
 
 text_sensor:
+  - platform: version
+    name: "ESPHome Version"
+    entity_category: diagnostic
+
   - platform: wifi_info
     ip_address:
       name: "WiFi IP Address"
@@ -741,57 +797,44 @@ text_sensor:
     mac_address:
       name: "WiFi MAC Address"
 
+  - platform: debug
+    device:
+      name: "Device Info"
+    reset_reason:
+      name: "Reset Reason"
+
   - platform: ld2410
     version:
       name: "LD2410C Firmware Version"
     mac_address:
       name: "LD2410C MAC Address"
 
-  # VOC Level
   - platform: template
-    name: "VOC Level"
+    name: "Chemical Pollution"
+    id: sgp41_chemical_pollution
+    icon: mdi:molecule
     lambda: |-
-      int tvoc = id(sgp30_tvoc).state;
+      float voc_index = id(sgp41_voc_index).state;
-      if (tvoc < 65) return {"Excellent"};
+      if (voc_index < 1 || voc_index > 500) return {"Unknown"};
-      if (tvoc < 220) return {"Good"};
+      if (voc_index <= 100) return {"Excellent"};
-      if (tvoc < 660) return {"Moderate"};
+      else if (voc_index <= 200) return {"Good"};
-      if (tvoc < 2200) return {"Poor"};
+      else if (voc_index <= 300) return {"Moderate"};
-      return {"Unhealthy"};
+      else if (voc_index <= 400) return {"Unhealthy"};
+      else return {"Hazardous"};
     update_interval: 15s
 
-  # CO2 Level
-  - platform: template
-    name: "CO2 Level"
-    lambda: |-
-      int eco2 = id(sgp30_eco2).state;
-      if (eco2 < 500) return {"Excellent"};
-      if (eco2 < 800) return {"Good"};
-      if (eco2 < 1200) return {"Moderate"};
-      if (eco2 < 2000) return {"Poor"};
-      return {"Unhealthy"};
-    update_interval: 15s
-
-  # IAQ Classification
-  - platform: template
-    name: "IAQ Classification"
-    lambda: |-
-      int iaq = id(iaq_index).state;
-      if (iaq == 5) return {"Excellent"};
-      if (iaq == 4) return {"Good"};
-      if (iaq == 3) return {"Moderate"};
-      if (iaq == 2) return {"Poor"};
-      return {"Unhealthy"};
-    update_interval: 15s
-
-  # Room Health
   - platform: template
     name: "Room Health"
+    id: room_health_text
+    icon: mdi:home-heart
     lambda: |-
-      int score = id(room_health).state;
+      float score = id(room_health_score).state;
-      if (score == 4) return {"Optimal"};
+      if (score < 0) return {"Unknown"};
-      if (score == 3) return {"Fair"};
+      else if (score >= 90.0) return {"Great"};
-      if (score == 2) return {"Poor"};
+      else if (score >= 80.0) return {"Good"};
-      return {"Bad"};
+      else if (score >= 60.0) return {"Fair"};
+      else if (score >= 40.0) return {"Poor"};
+      else return {"Bad"};
     update_interval: 15s
 
 button:
@@ -1098,34 +1141,100 @@ select:
       name: "LD2410C Distance Resolution"
 
   - platform: template
-    name: "Wake word sensitivity"
+    name: "Wake Word Selector"
-    optimistic: true
+    id: wake_word_selector
-    initial_option: Moderately sensitive
-    restore_value: true
-    entity_category: config
     options:
-      - Slightly sensitive
+      - "Computer"
-      - Moderately sensitive
+      - "Hey Jarvis"
+      - "Hey Mycroft"
+      - "Okay Nabu"
+      - "Alexa"
+    initial_option: "Computer"
+    optimistic: true
+    restore_value: true
+    set_action:
+      # Disable models that aren't selected
+      - if:
+          condition:
+            lambda: 'return x != "Computer";'
+          then:
+            - micro_wake_word.disable_model: mww_computer
+      - if:
+          condition:
+            lambda: 'return x != "Hey Jarvis";'
+          then:
+            - micro_wake_word.disable_model: mww_hey_jarvis
+      - if:
+          condition:
+            lambda: 'return x != "Hey Mycroft";'
+          then:
+            - micro_wake_word.disable_model: mww_hey_mycroft
+      - if:
+          condition:
+            lambda: 'return x != "Okay Nabu";'
+          then:
+            - micro_wake_word.disable_model: mww_okay_nabu
+      - if:
+          condition:
+            lambda: 'return x != "Alexa";'
+          then:
+            - micro_wake_word.disable_model: mww_alexa
+      # Enable model we selected
+      - if:
+          condition:
+            lambda: 'return x == "Computer";'
+          then:
+            - micro_wake_word.enable_model: mww_computer
+      - if:
+          condition:
+            lambda: 'return x == "Hey Jarvis";'
+          then:
+            - micro_wake_word.enable_model: mww_hey_jarvis
+      - if:
+          condition:
+            lambda: 'return x == "Hey Mycroft";'
+          then:
+            - micro_wake_word.enable_model: mww_hey_mycroft
+      - if:
+          condition:
+            lambda: 'return x == "Okay Nabu";'
+          then:
+            - micro_wake_word.enable_model: mww_okay_nabu
+      - if:
+          condition:
+            lambda: 'return x == "Alexa";'
+          then:
+            - micro_wake_word.enable_model: mww_alexa
+
+  - platform: template
+    name: "Wake Word Sensitivity"
+    optimistic: true
+    initial_option: Default
+    restore_value: true
+    options:
+      - Default
+      - More sensitive
       - Very sensitive
-    on_value:
+    set_action:
       # Sets specific wake word probabilities computed for each particular model
       # Note probability cutoffs are set as a quantized uint8 value, each comment has the corresponding floating point cutoff
-      # False Accepts per Hour values are tested against all units and channels from the Dinner Party Corpus.
+      - lambda: |-
-      # These cutoffs apply only to the specific models included in the firmware: okay_nabu@20241226.3, hey_jarvis@v2, hey_mycroft@v2
+          if (x == "Default") {
-      lambda: |-
+            id(mww_computer).set_probability_cutoff(168);     // 0.66 (default)
-        if (x == "Slightly sensitive") {
+            id(mww_hey_jarvis).set_probability_cutoff(247);   // 0.97 (default)
-          id(mww_hey_jarvis).set_probability_cutoff(247);   // 0.97 -> 0.563 FAPH on DipCo (Manifest's default)
+            id(mww_hey_mycroft).set_probability_cutoff(242);  // 0.95 (default)
-          id(mww_hey_mycroft).set_probability_cutoff(253);  // 0.99 -> 0.567 FAPH on DipCo
+            id(mww_okay_nabu).set_probability_cutoff(217);    // 0.85 (default)
-          id(mww_okay_nabu).set_probability_cutoff(217);    // 0.85 -> 0.000 FAPH on DipCo (Manifest's default)
+            id(mww_alexa).set_probability_cutoff(217);        // 0.85 (default)
-          id(mww_alexa).set_probability_cutoff(217);        // 0.85 -> 0.000 FAPH on DipCo (Manifest's default)
+          } else if (x == "More sensitive") {
-        } else if (x == "Moderately sensitive") {
+            id(mww_computer).set_probability_cutoff(153);     // 0.60
-          id(mww_hey_jarvis).set_probability_cutoff(235);   // 0.92 -> 0.939 FAPH on DipCo
+            id(mww_hey_jarvis).set_probability_cutoff(235);   // 0.92
-          id(mww_hey_mycroft).set_probability_cutoff(242);  // 0.95 -> 1.502 FAPH on DipCo (Manifest's default)
+            id(mww_hey_mycroft).set_probability_cutoff(237);  // 0.93
-          id(mww_okay_nabu).set_probability_cutoff(176);    // 0.69 -> 0.376 FAPH on DipCo
+            id(mww_okay_nabu).set_probability_cutoff(176);    // 0.69
-          id(mww_alexa).set_probability_cutoff(176);        // 0.69 -> 0.376 FAPH on DipCo
+            id(mww_alexa).set_probability_cutoff(176);        // 0.69
           } else if (x == "Very sensitive") {
-          id(mww_hey_jarvis).set_probability_cutoff(212);   // 0.83 -> 1.502 FAPH on DipCo
+            id(mww_computer).set_probability_cutoff(138);     // 0.54
-          id(mww_hey_mycroft).set_probability_cutoff(237);  // 0.93 -> 1.878 FAPH on DipCo
+            id(mww_hey_jarvis).set_probability_cutoff(212);   // 0.83
-          id(mww_okay_nabu).set_probability_cutoff(143);    // 0.56 -> 0.751 FAPH on DipCo
+            id(mww_hey_mycroft).set_probability_cutoff(230);  // 0.90
-          id(mww_alexa).set_probability_cutoff(143);        // 0.56 -> 0.751 FAPH on DipCo
+            id(mww_okay_nabu).set_probability_cutoff(143);    // 0.56
+            id(mww_alexa).set_probability_cutoff(143);        // 0.56
           }