As the title says, here's my OpenAI Controller for Reactor:
OpenAI Controller per Reactor. Contribute to dbochicchio/reactor-openai development by creating an account on GitHub.
It supports both OpenAI and Azure OpenAI endpoints. You'll need keys/endpoints, according to each service.
The controller supports multiple models, and each one could be mapped as an entity.
It's quite easy to use, and responses can be stored in variables, for easy access. Or sent to another action (Text To Speech, another endpoint, etc).
9013ae50-fd68-42a2-87c3-97479132e465-image.png
80a88eec-7c89-464a-8196-690b4b72d044-image.png
Have fun with LLM into your scenes!
In Home Assistant I have an integration that if I add entities to it, I will get the following error in MSR as certain entity values I'm using in expressions are null for a moment. This is more or less cosmetic issue and happens very rarely as I rarely modify that integration on the hass side.
Screenshot 2024-11-28 at 22.20.41.png
And the expression is
Screenshot 2024-11-28 at 22.38.19.png
Could I "wrap" hass-entity shown above somewhat differently to prevent this error from happening? Using build 24302.
Hello
I am trying to set up Multi System Reactor to automate routines across multiple smart home devices & platforms (e.g., Home Assistant, SmartThings, and Hubitat). While I have successfully linked the systems; I am facing issues with:
-Delays in triggering actions on secondary devices.
-Inconsistent execution of complex logic conditions.
-Synchronization of states between devices when one system updates.
Is there a recommended way to optimize performance & confirm seamless state sharing across systems?
I have checked https://smarthome.community/category/22/multi-system-reactor-msbi guide for reference but still need advice.
Any tips on debugging or log analysis to pinpoint where the issue arises would also be appreciated.
Thank you !
I've managed to use MSR UI on iOS devices to some degree*, so that although UI elements (e.g. rule sets) are not visible in portrait mode, you've seen them in landscape. Now with recents builds (24302) this does not work anymore, elements (rule sets, entities) are not anymore visible in landscape mode.
Does anyone have similar experiences? Using iOS 18 and Safari/Chrome browser.
( *Drag & drop of rule conditions have never worked on a mobile)
@toggledbits Since I have upgraded ZWaveJSController to 24293 from 24257 I am seeing entries related to registering action set_volume, but action is not defined by the capability 143 every time I restart Reactor.
The Siren seems to be doing what it is supposed to do. The volume levels are fine. Should I worry about it?
Reactor version 24302
ZWaveJSController version 24293
Z-Wave JS UI version 9.27.4
zwave-js version 14.3.4
I have the following ACL defined:
groups: admin: users: - admin applications: true api_acls: # This ACL allows users in the "admin" group to access the API - url: "/api" group: admin allow: true log: true # This ACL allows anyone/thing to access the /api/v1/alive API endpoint - url: "/api/v1/alive" allow: trueAnd I have authenticated to MSR as "admin" user. However, I'm getting "access denied" when trying to access http://*******:8111/api/v1/log
So what I'm missing, is my ACL incorrectly defined?
Using build 24302 on Docker.
Thanks to @toggledbits for adding a custom CSS. I've started doing a darker Reactor style.
Here's the file: https://gist.github.com/dbochicchio/825098ac13b7f8cac22012eae37ff7ce
A couple of things are still too bright and I'll eventually catch-up. Just place it under your /config directory, naming the file as customstyles.css. Hard refresh your browser.
Hi
I have just connected a bunch of EzloPi controllers to MSR to import some ESP based devices etc.
They all seemed to have worked and imported in to MSR apart from I have one missing device. It is a Digital Gas Sensor device.
This is how that device looks in the Ezlo API.
Devices Info:
_id: "10696001" deviceTypeId: "ezlopi" parentDeviceId: "10696000" category: "level_sensor" subcategory: "" gatewayId: "457a5069" batteryPowered: false name: "Gas Sensor Digital" type: "sensor" reachable: true persistent: true serviceNotification: false armed: false roomId: "" security: "no" ready: true status: "idle" parentRoom: true protectConfig: "default"Items Info:
_id: "20696001" deviceId: "10696001" hasGetter: true hasSetter: false name: "smoke_density" show: true valueType: "substance_amount" scale: "parts_per_million" value: 2.7472610473632812 valueFormatted: "2.75" status: "idle"There is also an Analog Gas sensor that one did import in to MSR OK.
68d63dab-b871-4f44-912b-cf6e0b9eb4c6-image.png
Devices Info:
_id: "10696000" deviceTypeId: "ezlopi" parentDeviceId: "10696000" category: "security_sensor" subcategory: "gas" gatewayId: "457a5069" batteryPowered: false name: "Gas Sensor Analog" type: "sensor" reachable: true persistent: true serviceNotification: false armed: false roomId: "" security: "no" ready: true status: "idle" parentRoom: true protectConfig: "default"Items Info:
_id: "20696000" deviceId: "10696000" hasGetter: true hasSetter: false name: "gas_alarm" show: true valueType: "token" enum: 0: "no_gas" 1: "combustible_gas_detected" 2: "toxic_gas_detected" 3: "unknown" valueFormatted: "no_gas" value: "no_gas" status: "idle"And this is how this MQ2 Gas Sensor looks like on their dashboard:
Digital
cb77dfa3-4af5-4d06-9635-89207a716a89-image.png
Analog
4fb4da1b-e946-4b89-876c-bcd9f5699b6c-image.png
They have an EzloPi website here you can create your own sensor projects using ESP boards, which is very interesting stuff!
And I just wrote on the Ezlo forum here, how to connect an EzloPi controller to MSR.
THANKS.
Build 21228 has been released. Docker images available from DockerHub as usual, and bare-metal packages here.
Home Assistant up to version 2021.8.6 supported; the online version of the manual will now state the current supported versions; Fix an error in OWMWeatherController that could cause it to stop updating; Unify the approach to entity filtering on all hub interface classes (controllers); this works for device entities only; it may be extended to other entities later; Improve error detail in messages for EzloController during auth phase; Add isRuleSet() and isRuleEnabled() functions to expressions extensions; Implement set action for lock and passage capabilities (makes them more easily scriptable in some cases); Fix a place in the UI where 24-hour time was not being displayed.A couple of things for you @toggledbits, since you mentioned that this release has new features and some tweaks are expected.
Local expressions cannot be deleted. Pushing the X button has no effect for me.
When cloning an entity action, the result is strange (first is cloned one, second is the original action):
a92ea094-9e2c-4aaa-bf47-2d07a6ffdbd0-image.png
When changing the action on the cloned element, the params are added to the original one. See screenshot:
92ac3011-83c8-466b-bd23-47d483ad7a52-image.png
Dark theme has a couple of strange contrasts. One is visible in the previous screenshots (white text on yellow background). Another one is in groups (blue text on blue background):
9b3c4988-53ef-44e6-9672-30e744cacb75-image.png
Overall, I found blue, yellow, red and green (in buttons and forms) to be too bright.
On the bright side:
I love the new script action: thank you! The dark theme is a great start to avoid getting blinded at night I promise I'll try very soon the new features around actions. Thanks!@toggledbits
I just upgraded to version MSR 24293, bare metal running on Fedora. Upon restart, I am getting a error banner:
I followed the new directions about npm
npm i --no-save --no-package-lock --omit dev
Any idea what the issue is?
Seems like switching the UI to the newly added dark mode (thank you for this) does nothing. The UI stays in light mode and only a few buttons turn into dark mode (see screenshot)
Things I have tried:
Hard refresh
Different browser
Different computer
Restarting Reactor
Failed troubleshooting attempts:
No errors in Chrome console
No relevant errors in Reactor log (can still PM the full log file)
Reactor version: latest-24293-ea42a81d
Hardware: Odroid N2+
Linux version: Ubuntu 24.04.1 LTS
3df2806f-9146-485b-9ec1-d056e91cefe5-image.png Dark mode enabled
ff823023-c079-4684-b01f-d6ac6527d31a-image.png Light mode enabled
Good morning,
I have a service MQTT service that needs a restart occasionally. The add-on (Smartbed MQTT) is for the smart bed base for my bed. It has a "safety light" that I can control from HAAS & MSR as a light entity, and also moves the head of the bed to a preset at bedtime, and then lies it back flat in the morning The problem is, from time to time, the light becomes "unavailable" Restarting from the Add-ons tab in HAAS always fixes it, but I should be able to detect when it happens when "light.tempur_pedic_safety_lights" is not true or false, i.e., unavailable.
What I don't know how to do is how to restart that service. Does anybody have experience in restarting add-ons from MSR?
Running:
Reactor (Multi-hub) latest-24212-3ce15e25 ZWaveJSController [0.1.24232]HAAS:
RPi5-64 (8GB) Core 2024.7.3 Supervisor 2024.08.0 Operating System 13.0 Frontend 20240710.0Hi!
Is it possible to generate two additional log files, the first being the replica of what is displayed on screen by the Rule History widgets and the other with Recently Changed Entities?
And could I configure the generation of one file per day, and delete the older ones? For example, store the last 5 days?
And being more ambitious, does Windget have an icon to open these TXT files in the navigated?
Well, we're approaching Christmas, so here's my request to Santa Claus @toggledbits 🙂
Hi @toggledbits
I'm working on a controller to generate llm response from a prompt in reactor. I have http response coming thru an http request action at the moment, capturing the response inside a local variable. So, it's practically sync.
I want to create a controller, so I don't have to rely on a proxy (and have a simpler architecture), and duplicate absurd http actions, but AFAIK in the current implementation, actions are async only. But if I have multiple requests going on, I cannot be sure what it's really inside an attribute. I also thought that something like a correlation id when sending the request could be used to identity multiple responses, but I wanted to double check with you before starting with something too complicated. I also noticed that some actions in home assistant (ie forecast) are sync and I'm wondering if you have any plan or hint to address this situation. Thanks.
Thanks.
@togglebits I am curious as to why the tilt_sensor.state (primary) = NULL. I believe it should show true or false. I have to use binary_sensor.state instead in my rules.
Again, not sure if this is related to Reactor/ZwaveJSController implementation or the actual Z-Wave JS UI docker version. I have copied, below, the attributes of the tilt sensor in hopes it can help.
Thanks in advance.
Reactor version 23302
ZWaveJSController version 23254
Z-Wave JS UI version 9.3.0.724519f
zwave-js version 12.2.3
Feature Request - Wait for an event/trigger within Reaction [Solved with Work Around]
-
I think this feature request could be accomplished with the use of two or more rules, but it would be great if there was a way to wait for an event or trigger to occur before continuing on in the reactions.
For example, I have a rule that will turn on some exterior lights if you arrive home after the porch lights have been turned off. Right now this rule randomly will turn off between 5-10 minutes after the person has entered the geofence. On some occasions this 5-10 minutes isn't long enough, say if you are unloading the car or something. I would like to kick off the reaction, but pause it part way through and wait for the door to close and lock, then continue it on. Hubitat Rule Machine has a "Wait for event" option, but I really want to keep all my logic within MSR.
-
@3rdStng said in Feature Request - Wait for an event/trigger within Reaction:
I would like to kick off the reaction, but pause it part way through and wait for the door to close and lock, then continue it on.
A Repeat...While group will execute and prevent the remainder of the Reaction from running until it breaks (conditions are no longer met).
The delay prevents it from becoming a huge CPU consumer.
Yes, this is a bit of a kludge, and a dedicated action could be more useful. I'll look into it, but in the meanwhile, this workaround should play nicely.
-
Hmm.... Thanks for this, I think I can make it work, but it may take two Repeat While actions. It doesn't appear that I can wait for a change. It's only waiting for a True or False and not a change from Opened to Closed.
I believe in my rule I would need a "Repeat While the door is false" (open) to wait for someone to actually open the door. Then a "Repeat While the door is true" (closed) to wait for them to close the door and then continuing on the actions to turn off the lights.
-
Well, really if it's just as simple as turning on the lights when the door opens, and then waiting for a close to turn them off, the rule trigger conditions should handle detecting the door opening, and the first action in the Set reaction would be to turn the lights on. Then you can wait for the door to close, and turn the lights off.
But then, if the rule triggers are only detecting if the door is open, why not have the Set reaction turn the lights on, and the Reset reaction turn the lights off? No "wait for" needed at all, because the logic is handling it.
As you disclose details, it's beginning to look like you've imagined a solution based on some other product, and you're trying to get Reactor to work its way, instead of doing it "the Reactor way."
-
@toggledbits said in Feature Request - Wait for an event/trigger within Reaction:
As you disclose details, it's beginning to look like you've imagined a solution based on some other product, and you're trying to get Reactor to work its way, instead of doing it "the Reactor way."
That is very possible. I'm still mentally mapping this out too. And I 100% know that an image of my rule set would really help clear things up. I'm not in a position to get a screenshot at the moment. I'll try to put my thoughts in to text. (scary)
Rule set as of today:
Triggers:
After midnight AND
Before sunrise AND
Any Presence Sensor in the group changes from Not Present to PresentActions:
Turn on the porch light
Turn on the driveway lights
Wait for a random period of time between 10-15 minutes
Turn off the porch light
Turn off the driveway lightsWhat I am after is within the Actions only. The Triggers are still the same.
Actions:
Turn on the porch light
Turn on the driveway lights
Wait until the HE Hub variable "lastDoorLockEvent" reports "Manually locked"
Wait for a random period of time between 10-15 minutes
Turn off the porch light
Turn off the driveway lightsThe waiting until the hub variable is what's potentially causing the issue. When I go to bed, and assuming the door was open, I'll close it and lock it. So the hub variable now reports "Manually locked". If someone arrives after midnight and before sunrise, the variable will still report "Manually locked" since the lock status hasn't changed yet. So theoretically MSR won't wait since it already sees the variable as what it is looking for.
And as I type this out, I suppose I could insert a set variable into the actions. I honestly haven't looked yet, but can MSR set a variable that is local to the hub only? Not within MSR.
Actions:
Turn on the porch light
Turn on the driveway lights
Set HE Hub variable "lastDoorLockEvent" to "waiting entry"
Repeat Until the HE Hub variable "lastDoorLockEvent" reports "Manually locked"
Wait for a random period of time between 10-15 minutes
Turn off the porch light
Turn off the driveway lightsThe entire concept stems from Hubitat's Rule Machine's "Wait for event" that you can define in a rule. I have a couple of these at my remote HE, where I can't run MSR easily.
-
OK. This makes it much more clear. Your solution is workable. There are a few ways to attack it, but what you've posted should work. You picked up on the state of the hub variable, which is important. You hub variable should appear as an entity with the
string_sensor
capability, and it should have an extended action (x_hubitat_Variable.setVariable
) to let you change the value. -
@toggledbits said in Feature Request - Wait for an event/trigger within Reaction:
hub variable should appear as an entity with the string_sensor capability, and it should have an extended action (x_hubitat_Variable.setVariable) to let you change the value.
Worked perfectly!
Thank you for the feedback and allowing me to type out my thoughts to refine this rule.
-
@toggledbits One case I can think of where this is useful is as follows. Note I try to avoid making multiple rules to achieve this since it make managing them much harder.
I have some triggers (not relevant in this example) for my front doorbell when a person, vehicle, animal or package is detected. Each of these have their own respective rule. In the actions I have TTS action that says "{object name} detected at the front door". I also have another action after that send a notification to my phone with a snapshot and description of the doorbell activity.
The problem I run into, is that on occasion the snapshot takes a few extra seconds to come through. Now in my case I want the TTS to say what's at the door right away regardless of the snapshot since its irrelevant and then wait till the snapshot updates to send the push notification.
To combat the delay I added a condition in my triggers that wait for the snapshot time to update before sending the TTS and notification. Using this workaround it introduces a delay in the TTS action as well. Ideally having a "wait for" action for when the snapshot updates to then send the notification will fix the problem without needing to create another rule.
-
Refined my actions to include a timeout, just in case someone comes home, but they leave without entering the door.
Actions:
Set variable 'lastLockEvent' to "pending entry"
Turn on porch light
Turn on driveway lights
Repeat While:
-- Triggers:
-- [lastLockEvent] contains "manually locked"
-- [OR]
-- [lastLockEvent] contains "pending entry" (condition sustained for 20 minutes)
-- Actions:
-- Delay 10 seconds
Delay random between 1 to 5 minutes
Turn off porch light
Turn off driveway lights -
@toggledbits just an idea related to this "repeat...while" group that it could benefit from similar functionality as is available for pulse to prevent it from looping indefinitely. There are sometimes devices not updating their status properly and in those cases it would be nice to ensure exit within reasonable time.
This functionality can be done in a following way, for example, but would be more straightforward if it was already built-in
-