* Add config option for controlling Ollama think parameter
Allows enabling or disable thinking for supported models. Neither option
will dislay thinking content in the chat. Future support for displaying
think content will require frontend changes for formatting.
* Add thinking strings
* Update ollama to use the ChatLog/ChatSession APIs
* Add documentation about history trimming.
* Revert changes to chat_log.py
* Explicitly check for SystemContent when converting system messages
* Remove half of a comment
* Ensure config_flow abort reasons have translations
* Ignore fake_integration in application_credentials
* Mark gardena_bluetooth as needs fixing
* Mark google as needs fixing
* Mark google_assistant_sdk as needs fixing
* Mark homewizard as needs fixing
* Mark homeworks as needs fixing
* Mark honeywell as needs fixing
* Mark jewish_calendar as needs fixing
* Mark lg_netcast as needs fixing
* Mark lifx as needs fixing
* Mark lyric as needs fixing
* Mark madvr as needs fixing
* Mark matter as needs fixing
* Mark melcloud as needs fixing
* Mark motioneye as needs fixing
* Mark ollama as needs fixing
* Mark philips_js as needs fixing
* Mark spotify as needs fixing
* Mark srp_energy as needs fixing
* Mark subaru as needs fixing
* Mark tplink as needs fixing
* Mark yolink as needs fixing
* Mark youtube as needs fixing
* Fix incorrect comment
* Improve quality of ollama function calling by repairing function call arguments
* Fix formatting of the tests
* Run ruff format on ollama conversation
* Add test for non-string arguments
* Add LLM tools support for Ollama
* fix tests
* coverage
* Separate call for tool parameters
* Fix example
* hint on parameters schema if LLM forgot to request it
* Switch to native tool call functionality
* Fix tests
* Fix tools list
* update strings and default model
* Ignore mypy error until fixed upstream
* Ignore mypy error until fixed upstream
* Add missing prompt part
* Update default model
* Default agent as entity
* Migrate constant to point at new value
* Fix tests
* Fix more tests
* Move assist pipeline back to cloud after dependenceis
* Re-organize conversation integration
* Clean up 2 more imports
* Re-export models
* Fix imports
* Uno mas
* Rename agents to models
* Fix cast test that i broke?
* Just blocking till I'm done
* Wrong place
