v1.5.0

Fix

• There was a change in the StackSpot API response that caused the token count to break
  • NOTE: I was contacted and informed that the fields are under review and that after that the documentation will be updated.

develop

This is the release from develop

v1.4.0

This version includes everything that was released in the beta versions below without any changes.

Versions

• 1.4.0-beta.2
• 1.4.0-beta.1

v1.4.0-beta.2

Added

• Created new Tool get_todo_items
• New parameter in agent configuration to indicate if it can control the ha:
  • It basically indicates whether the agent has access or not to the Tools
  • By default this option is false
• New LLM Model parameter:
  • Informational only
  • Appears on the device
  • No effect on the agent

Improvements

• New naming strategy for sub-entries
• Improved device information

v1.4.0-beta.1

⚠️ Attention

Note that this gives the agent access to change states in your HA. Consider that LLMs are not deterministic and may call services and/or change statuses that they shouldn't. Use at your own risk.

---

Added

• Powers to change status and call for services
  • Now your agent can get entities status or call services, this is now possible using the tools.
  • Two tools are being made available, get_entity_state and call_service; The agent can decide when and which one calls.

Changed

• Now the variable exposed_entities is created at the HA start and updated every 5 minutes.

v1.3.0

Added

• New variable exposed_entities for prompts
• KS (knowledge-source)
  • They are used to give agents more context, you can store information on them and the agent will be enriched with them
  • see: https://ai.stackspot.com/docs/knowledge-s

v1.2.2

Fix

• Injects username into prompt, only when context has this information

v1.2.1

Fix

• Token validation correction when expired

v1.2.0

Added

• AI task support: You can now create a new input to generate data with an agent.
  • See: AI Task
  • Note: Requires Home Assistant in version 2025.8.0

v1.1.0

Added

• Now you can define a personalized prompt for the agent.