* 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
* 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
* Bulleting update & version bump
* Bulletin.md updates
* Format bulletin
* Added info about new documentation theme.
---------
Co-authored-by: lc0rp <2609411+lc0rp@users.noreply.github.com>
* Added SUMMARIZATION_TRIGGER_LENGTH
browse_website won't summarize content that's shorter
than SUMMARIZATION_TRIGGER_LENGTH.
It defaults to 250 characters, which is approximately 50 tokens.
* Refactor BrowserOptions
* Use tokens instead of length
to trigger summarization
* Bugfix
* fix: Always return links even if not summarizing
feat: Increase the number of links returned from 5 to 20
---------
Co-authored-by: lc0rp <2609411+lc0rp@users.noreply.github.com>
Co-authored-by: James Collins <collijk@uw.edu>
* Add information on how to improve Auto-GPT with agbenchmark
* Update introduction.md
* Update docs/challenges/introduction.md
Co-authored-by: Reinier van der Leer <reinier.vanderleer@agpt.co>
* Update introduction.md
---------
Co-authored-by: James Collins <collijk@uw.edu>
Co-authored-by: Reinier van der Leer <reinier.vanderleer@agpt.co>
* fix omitted "()" in __str__(self) in core/ability/base.py
* put back async keyword in the base class
* Remove extra () in OpenAISettings class in
autogpt/core/resourece/model_providers/openai.py
---------
Co-authored-by: James Collins <collijk@uw.edu>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
* 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
* Use modern material theme for docs
* Further file path fixes, and doc updates to specify when relative paths are expected
* fix: lint
* Remove unwated changes
* Remove comments
---------
Co-authored-by: lc0rp <2609411+lc0rp@users.noreply.github.com>
Co-authored-by: Reinier van der Leer <reinier.vanderleer@agpt.co>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
