test: add test for VoyageAI model provider

mark test incomplete on insufficient credits

test: add test for Reka model provider

test: add test for Mistral model provider

fix groq test and temperature issue

test: add test for Groq model provider

fixes based on tests, improve tests

test: add ModelGeminiTest for Gemini AI provider

first few tests to ensure model providers work

refactor HTTP Client initialization

translation update

add option to always send full page context

upped version

allow models to have a zero token limit

This allows for configuring completely unknown models. For these models
no token limit is known and we will simply do not apply any. Instead we
trust that the

allow models to have a zero token limit

This allows for configuring completely unknown models. For these models
no token limit is known and we will simply do not apply any. Instead we
trust that the model will be either large enough to handle our input or
at least throw useful error messages.

show more ...

fix model full name

introduce a "Generic" model

This is basically an OpenAI implementation, which then can be reused by
most other providers since they usually implement a somewhat compatible
API. The API URL can be se

introduce a "Generic" model

This is basically an OpenAI implementation, which then can be reused by
most other providers since they usually implement a somewhat compatible
API. The API URL can be set manually so it should be easy to add new
unsupported providers.

show more ...

Version upped

upped version

keep page context enabled until reload

This disables it when you change the page

fix overflow of <pre> tags in answers

rewrite roles for Gemini

Gemini expects the role model instead of assistant. Older models allowed
both, the newer ones not.

upped version

new UI with option to chat about the current page

Version upped

updated model data