* Limit intent / llm API device_class slots to only necessary services and limited set of values
* Fix ruff errors
* Run ruff format
* Fix typing and improve output schema
* Fix schema and improve flattening
* Revert conftest
* Revert recorder
* Fix ruff format errors
* Update using latest version of voluptuous
* Remigrate device_registry created_at/modified_at
Nightly current does not boot up because the device registry
will have KeyError: created_at if the previous nightly was
installed.
* reduce
* split migration per discord comments
* Indicate database migration in /api/core/state response
* Change API response according to review comment
* Adjust API response
* Update test
* Add test
* init
* Update homeassistant/helpers/update_coordinator.py
Co-authored-by: Joost Lekkerkerker <joostlek@outlook.com>
* fix typo, ruff
* consistency with rest, test
* pylint suppression
* ruff
* ruff
* switch to one test
* add last exc
* add tests for auth & Entry Errors
* move exceptions to correct test
* Update update_coordinator.py
Co-authored-by: G Johansson <goran.johansson@shiftit.se>
* test setup call
* simplify
---------
Co-authored-by: Joost Lekkerkerker <joostlek@outlook.com>
Co-authored-by: G Johansson <goran.johansson@shiftit.se>
* Update voluptuous to 0.15.1
* Fix typing issues
* Add type ignores for json result type
* Update voluptuous to 0.15.2
---------
Co-authored-by: J. Nick Koston <nick@koston.org>
* Add script llm tool
* Add tests
* More tests
* more test
* more test
* Add area and floor resolving
* coverage
* coverage
* fix ColorTempSelector
* fix mypy
* fix mypy
* add script reload test
* Cache script tool parameters
* Make custom_serializer a part of api
---------
Co-authored-by: Michael Hansen <mike@rhasspy.org>
* Add expandable support for data entry form flows
* Update config_validation.py
* optional options
* Adjust
* Correct translations of data within sections
* Update homeassistant/components/kitchen_sink/config_flow.py
Co-authored-by: Robert Resch <robert@resch.dev>
* Add missing import
* Update tests/components/kitchen_sink/test_config_flow.py
Co-authored-by: Robert Resch <robert@resch.dev>
* Format code
* Match frontend when serializing
* Move section class to data_entry_flow
* Correct serializing
* Fix import in kitchen_sink
* Move and update test
---------
Co-authored-by: Bram Kragten <mail@bramkragten.nl>
Co-authored-by: Robert Resch <robert@resch.dev>
* Include speech_slots in IntentResponse.as_dict
* Populate speech_slots only if available
* fix typo
* Add test
* test all fields
* Fix another test
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
* Check exposure in climate intent
* Check exposure in todo list
* Check exposure for weather
* Check exposure in humidity intents
* Add extra checks to weather tests
* Add more checks to todo intent test
* Move climate intents to async_match_targets
* Update test_intent.py
* Update test_intent.py
* Remove patch
* Always do thread safety check when writing state
Refactor the 3 most common places where the thread safety check
for the event loop to be inline to make the check fast enough
that we can keep it long term. While code review catches most
of the thread safety issues in core, some of them still make
it through, and new ones keep getting added. Its not possible
to catch them all with manual code review, so its worth the
tiny overhead to check each time.
Previously the check was limited to custom components
because they were the most common source of thread
safety issues.
* Always do thread safety check when writing state
Refactor the 3 most common places where the thread safety check
for the event loop to be inline to make the check fast enough
that we can keep it long term. While code review catches most
of the thread safety issues in core, some of them still make
it through, and new ones keep getting added. Its not possible
to catch them all with manual code review, so its worth the
tiny overhead to check each time.
Previously the check was limited to custom components
because they were the most common source of thread
safety issues.
* async_fire is more common than expected with ccs
* fix mock
* fix hass mocking
* Automatically fill in slots from LLM context
* Add tests
* Apply suggestions from code review
Co-authored-by: Allen Porter <allen@thebends.org>
---------
Co-authored-by: Allen Porter <allen@thebends.org>
* Ignore deprecated open and close cover intents for LLMs
* Fix LLMs asking which area when there is only one device
* remove unrelated changed
* remove unrelated changes
* Add configuration option positive to DurationSelector
* Rename to allow_negative in conjunction with a deprecation notice
Co-authored-by: Erik Montnemery <erik@montnemery.com>
---------
Co-authored-by: Erik Montnemery <erik@montnemery.com>
* LLM Assist API to ignore timer intents if device doesn't support it
* Refactor to use API instances
* Extract ToolContext class
* Limit exposed intents based on exposed entities
These functions have been stripped down to always return
the same path so there was no longer a need to have a
function for this. This is left-over cleanup from
previous refactoring.
* Add types to event tracker data
* fixes
* do not test event internals in other tests
* fixes
* Update homeassistant/helpers/event.py
* cleanup
* cleanup
* Migrate issue registry to use singleton helper
The other registries were already migrated, but since this
one had a read only flag, it required a slightly different
solution since it uses the same hass.data key
* refactor
* Use defaultdict for registry indices
defaultdict is faster and does not have to create an empty
dict that gets throw away when the key is already present
* Use defaultdict for registry indices
defaultdict is faster and does not have to create an empty
dict that gets throw away when the key is already present
* Detect incorrect exception in forwarded platforms
If an integration raises ConfigEntryError/ConfigEntryAuthFailed/ConfigEntryAuthFailed
in a forwarded platform it would affect the state of the config entry and cause it to
process unloads and setup retries in while the other platforms continued to setup
* Detect incorrect exception in forwarded platforms
If an integration raises ConfigEntryError/ConfigEntryAuthFailed/ConfigEntryAuthFailed
in a forwarded platform it would affect the state of the config entry and cause it to
process unloads and setup retries in while the other platforms continued to setup
* Update homeassistant/config_entries.py
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
* adjust
* fix
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
* initial commit
* Undo prompt chenges
* Move format_tool out of the class
* Only catch HomeAssistantError and vol.Invalid
* Add config flow option
* Fix type
* Add translation
* Allow changing API access from options flow
* Allow model picking
* Remove allowing HASS Access in main flow
* Move model to the top in options flow
* Make prompt conditional based on API access
* convert only once to dict
* Reduce debug logging
* Update title
* re-order models
* Address comments
* Move things
* Update labels
* Add tool call tests
* coverage
* Use LLM APIs
* Fixes
* Address comments
* Reinstate the title to not break entity name
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
* Add llm helper
* break out Tool.specification as class members
* Format state output
* Fix intent tests
* Removed auto initialization of intents - let conversation platforms do that
* Handle DynamicServiceIntentHandler.extra_slots
* Add optional description to IntentTool init
* Add device_id and conversation_id parameters
* intent tests
* Add LLM tools tests
* coverage
* add agent_id parameter
* Apply suggestions from code review
* Apply suggestions from code review
* Apply suggestions from code review
* Apply suggestions from code review
* Apply suggestions from code review
* Fix tests
* Fix intent schema
* Allow a Python function to be registered as am LLM tool
* Add IntentHandler.effective_slot_schema
* Ensure IntentHandler.slot_schema to be vol.Schema
* Raise meaningful error on tool not found
* Move this change to a separate PR
* Update todo integration intent
* Remove Tool constructor
* Move IntentTool to intent helper
* Convert custom serializer into class method
* Remove tool_input from FunctionTool auto arguments to avoid recursion
* Remove conversion into Open API format
* Apply suggestions from code review
* Fix tests
* Use HassKey for helpers (see #117012)
* Add support for functions with typed lists, dicts, and sets as type hints
* Remove FunctionTool
* Added API to get registered intents
* Move IntentTool to the llm library
* Return only handlers in intents.async.get
* Removed llm tool registration from intent library
* Removed tool registration
* Add bind_hass back for now
* removed area and floor resolving
* fix test
* Apply suggestions from code review
* Improve coverage
* Fix intent_type type
* Temporary disable HassClimateGetTemperature intent
* Remove bind_hass
* Fix usage of slot schema
* Fix test
* Revert some test changes
* Don't mutate tool_input
---------
Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
* First pass at timers
* Move to separate file
* Refactor to using events
* Add pause/unpause/status
* Add ordinal
* Add test for timed Assist command
* Fix name matching
* Fix IntentHandleError
* Fix again
* Refactor to callbacks
* is_paused -> is_active
* Rename "set timer" to "start timer"
* Move tasks to timer manager
* More fixes
* Remove assist command
* Remove cancel by ordinal
* More tests
* Remove async on callbacks
* Export async_register_timer_handler
* Allow templates for enabling automation triggers
* Test exception for non-limited template
* Use `cv.template` instead of `cv.template_complex`
* skip trigger with invalid enable template
instead of returning and thus not evaluating other triggers
* Import and cache supported feature enum flags only when needed
* Add comment aboud being loaded from executor.
---------
Co-authored-by: J. Nick Koston <nick@koston.org>
Use a dictcomp to reconstruct DeviceInfo
a dictcomp is faster than many sets on the dict by at least
25%
We call this for nearly every device in the registry at
startup
* Small speed up to setting up integration and config entries
When profiling tests, I noticed many calls to get_running_loop. In the places
where we are already in a coro, pass the existing loop so it does not have to
be looked up. I did not do this for places were we are not in a coro since there
is risk that an integration could be doing a non-thread-safe call and its better
that the code raises when trying to fetch the running loop vs the performance
improvement for these cases.
* fix merge
* missed some