com.openai.unity 7.7.9 (RageAgainstThePixel#228)

- Fixed Chat sample in 2021.3 LTS

com.openai.unity 7.7.8 (RageAgainstThePixel#226)

- Updated OpenAISettingsInfo.ctr to allow for domain http protocol override (i.e. http://localhost:8080 or http://0.0.0.0:8080)
- Updated OpenAISettingsInfo.BaseRequest public for easier access when implementing custom proxies.
- Updated OpenAISettingsInfo.IsAzureDeployment public for easier access when implementing custom proxies.
- Updated com.utilities.rest -> 2.5.6

com.openai.unity 7.7.7 (RageAgainstThePixel#217)

- Updated static models list
  - Added gpt-4-turbo
  - Marked some models as deprecated since they are no longer available
- Added temperature to CreateRunRequest and CreateThreadAndRunRequest
- Fixed temperature to string conversion to be invariant culture for
audio requests
- Fixed type checking built in function tool calls

com.openai.unity 7.7.6 (RageAgainstThePixel#210)

- Added support for streaming text to speech
  - Added AudioEndpoit.CreateSpeechStreamAsync(SpeechRequest, Action<AudioClip>, CancellationToken)
- Added support for Audio Transcription and Translation verbose json output
  - Added support for timestamp granularities for segments and words
  - Marked CreateTranscriptionAsync obsolete
  - Added CreateTranscriptionTextAsync
  - Added CreateTranscriptionJsonAsync
  - Marked CreateTranspationAsync obsolete
  - Added CreateTranslationTextAsync
  - Added CreateTranslationJsonAsync
- Updated SpeechResponseFormat to include wav and pcm

com.openai.unity 7.7.5 (RageAgainstThePixel#205)

- Allow FunctionPropertyAttribute to be assignable to fields
- Updated Function schema generation
  - Fall back to complex types, and use $ref for discovered types
  - Fixed schema generation to properly assign unsigned integer types

com.openai.unity 7.7.4 (RageAgainstThePixel#203)

- Fixed Threads.RunResponse.WaitForStatusChangeAsync timeout

com.openai.unity 7.7.3 (RageAgainstThePixel#200)

- Updated ChatRequest toolChoice to only send type and name of function, reducing token usage

com.openai.unity 7.7.2 (RageAgainstThePixel#198)

- Added FunctionParameterAttribute to help better inform the feature how to format the Function json

com.openai.unity 7.7.1 (RageAgainstThePixel#196)

- More Function utilities and invoking methods
  - Added FunctionPropertyAttribute to help better inform the feature how to format the Function json
  - Added FromFunc<,> overloads for convenance
  - Fixed invoke args sometimes being casting to wrong type
  - Added additional protections for static and instanced function calls
  - Added additional tool utilities:
    - Tool.ClearRegisteredTools
    - Tool.IsToolRegistered(Tool) - Tool.TryRegisterTool(Tool)
- Updated Sample Chat Behaviour with updated tool implementations
- com.utilities.rest -> 2.5.3

com.openai.unity 7.7.0 (RageAgainstThePixel#194)

- Added `Tool` call and `Function` call Utilities and helper methods
- Added `FunctionAttribute` to decorate methods to be identified and used in function calling
- `Chat.Message.ToolCalls` can be directly invoked using `Function.Invoke()` or `Function.InvokeAsync(CancellationToken)`
- Assistant tool call outputs can be easily generated using `assistnat.GetToolOutputAsync(run.RequiredAction.SubmitToolOutputs.ToolCalls)`
  - Check updated docs for more details and examples
- Fixed `ChatRequest` seed parameter not being set correctly when using tools