* Add OpenAI compatible cost calculation
* Requesty: Prepare for correct price calculation
* Native OpenAI: Update model caching info
According to [OpenAI's
website](https://platform.openai.com/docs/guides/prompt-caching),
gpt-4o, gpt-4o-mini, o1-preview and o1-mini support caching.
For gpt-4o, even though gpt-4o-2024-05-13 and
chatgpt-4o-latest do no support caching, users will see there are no
cached tokens, which will help avoid confusion.
* Native OpenAI: Call getModel once
* Native OpenAI: Extract yield usage into method
* Native OpenAI: Add caching and cost info to task header
* DeepSeek: Add cost info to task header
* Add changeset
* Provide explicit command chaining instructions
* Added shell detection for powershell
The default-shell library being used only returns cmd for windows users. This change will utilize VS Code API calls to determine the user's shell/terminal settings. MacOS & Linux will, for now, continue to use the existing method. Still working on tests.
* Replaced default-shell, added tests
Replaced default-shell with local code that replicates the old behavior on macOS & Linux
Windows shell detection uses VS Code settings to get the user's default terminal profile
Adjusted prompt change
* One small change
* Removed & attributed old package + typo
* Added VSC load for other OSes, refactor, better tests
* Fixed system.ts explicit git lines
* Added back changes for terminal-command-chaining
* One minor, but important change
* Chore: Pretier for consistant formatting
- TODO: This PR needs to be updated by Saoud after he runs `npm install` & `npm format:fix` and commits the results of the prettier changes.
* Revert prettier config
* Run npm install
* Fix prettier config and ignore package lock
* Run format
---------
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
