ChatGPT set as preferred and prefer local processing. Custom sentence that works locally still being processed by ChatGPT.

[Doni49]

I have ChatGPT configured as Preferred and the option to "Prefer processing locally" is turned on. But if I make a request that uses a custom sentence, debug shows that it was processed by ChatGPT NOT the local option.

If I set the local option (HA Cloud) as preferred and make the SAME REQUEST, it works fine and in fact it worked fine before I ever tried to add ChatGPT.

Here's the definition of the custom sentence automation.

`description: "Viice Controls"
mode: single
triggers:

• trigger: conversation
  command: What's the Temp
  id: Get Temperatures
  conditions: []
  actions:
• choose:
  • conditions:

    • condition: trigger
      id:

      • Get Temperatures
        sequence:

    • set_conversation_response: >
      It's currently {{
      state_attr('climate.t6_pro_z_wave_programmable_thermostat','current_temperature')
      }} degrees and the thermostat is set to {% if
      states('climate.t6_pro_z_wave_programmable_thermostat') ==
      'heat_cool' %} Heat Cool to keep the temperature between {{
      state_attr('climate.t6_pro_z_wave_programmable_thermostat','target_temp_low')
      }} and {{
      state_attr('climate.t6_pro_z_wave_programmable_thermostat','target_temp_high')
      }} degrees.

      {% elif states('climate.t6_pro_z_wave_programmable_thermostat') ==
      'off' %} off.

      {% elif states('climate.t6_pro_z_wave_programmable_thermostat') ==
      'heat' %} heat to keep the temperature above {{
      state_attr('climate.t6_pro_z_wave_programmable_thermostat','temperature')
      }} degree.

      {% elif states('climate.t6_pro_z_wave_programmable_thermostat') ==
      'cool' %} cool to keep the temperature below {{
      state_attr('climate.t6_pro_z_wave_programmable_thermostat','temperature')
      }} degree.

      {% endif %}
      `

[Doni49]

In both scenarios, HA Cloud is set as the speech-to-text engine. So just to be sur eit wasn’t simply a matter of me saying the phrase slightly different, I recorded myself saying " Hey Jarvis {pause} What’s the Temp".

Then I laid my phone down next to the VPE and played the recording. When I checked the debug, it was handled by ChatGPT. Then I set HA Cloud to be preferred, put my phone in the same spot and played the recording again.

When I check the debug, it WAS processed locally.

[Ramblurr]

I believe this is a documented limitation.

[Doni49]

I was just informed of this over in the HA forums. The one thing I'm having trouble understanding about: if the integration doesn't support sentence triggers, how is it accurately processing the request?

[Doni49]

I also have one more question about that idea.

Since HA Cloud is the Speech-to-text engine, why isn't HA checking to see if the local option CAN process it before even passing it to the OpenAI integration? If the local option can process it, the integration shouldn't even know about it.