This commit introduces the NewTaskButton widget, designed to allow users to create new tasks. The button follows specific design guidelines, including dimensions, colors, and layout.
Key Features:
Button with a set height and adaptive width.
Icon and text layout within the button.
Styling for background, border, and corner radius.
Associated tests to ensure the button's functionality and appearance.
* Rename PromptConfig to AIDirectives
* Make PromptGenerator primarily responsible for generating prompt instead of AIConfig
* Refactor PromptGenerator
* Add `available` attribute to `Command` class, to determine availability based on `Agent` state
This commit introduces the ChatViewModel, which manages the business logic for chat interactions associated with tasks. The ViewModel communicates with a mock data source, offering functionalities like fetching chats for a specific task and sending chat messages.
In addition to the implementation, comprehensive tests for ChatViewModel have been provided to ensure its behavior is consistent with our design goals and expectations.
Key Features:
Chat management in ChatViewModel.
Tests covering all major functionalities of ChatViewModel.
Mock data source updates to emulate chat data interactions.
This commit introduces the TaskViewModel, which manages the business logic for tasks. The ViewModel interacts with a mock data source, providing functionalities like fetching tasks, selecting a task, creating, and deleting tasks.
Additionally, comprehensive tests for TaskViewModel have been added to ensure its behavior aligns with expectations. The mock data source has also been updated to support the new functionalities.
Key Features:
- Task management in TaskViewModel.
- Tests for each major functionality in TaskViewModel.
- Mock data source to simulate data interactions.
* Add categories to command registry
* Fix tests
* Clean up prompt generation
* Rename Performance Evaluations to Best Practices
* Move specification of response format from system prompt to Agent.construct_base_prompt
* Clean up PromptGenerator class
* Add debug logging to AIConfig autogeneration
* Clarify prompting and add support for multiple thought processes to Agent
* WIP: PlanningAgent
* Disable message history by default on BaseAgent
* Add CommandOutput and ThoughtProcessOutput type aliases
* Fix interrupts in main.py
* Use custom exceptions and clean up exception/error handling
* Remove duplicate agent_history.py
* Update PlanningAgent from upstream
* WIP: Support for dynamic in-prompt context
* WIP: response formats for PlanningAgent three-stage cycle
* Remove browsing overlay & separate browsing from extraction code
* Fix human feedback
* Fix tests
* Include history in Agent prompt generation
* Code improvements in agent.py
* Add ask_user command and revise system prompt
