* 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
* 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>
* 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>
* Fix and clean up path processing in logs module
* Fix path processing throughout the project
* Fix plugins test
* Fix borky pytest vs mkdir(exist_ok=True)
* Update docs and gitignore for new workspace location
* Fix borky pytest vol.2
* ok james
* Move rename module `agent` -> `agents`
* WIP: abstract agent structure into base class and port Agent
* Move command arg path sanitization to decorator
* Add fallback token limit in llm.utils.create_chat_completion
* Rebase `MessageHistory` class on `ChatSequence` class
* Fix linting
* Consolidate logging modules
* Wham Bam Boom
* Fix tests & linting complaints
* Update Agent class docstring
* Fix Agent import in autogpt.llm.providers.openai
* Fix agent kwarg in test_execute_code.py
* Fix benchmarks.py
* Clean up lingering Agent(ai_name=...) initializations
* Fix agent kwarg
* Make sanitize_path_arg decorator more robust
* Fix linting
* Fix command enabling lambda's
* Use relative paths in file ops logger
* Fix test_execute_python_file_not_found
* Fix Config model validation breaking on .plugins
* Define validator for Config.plugins
* Fix Config model issues
* Fix agent iteration budget in testing
* Fix declaration of context_while_think
* Fix Agent.parse_and_process_response signature
* Fix Agent cycle_budget usages
* Fix budget checking in BaseAgent.__next__
* Fix cycle budget initialization
* Fix function calling in BaseAgent.think()
* Include functions in token length calculation
* Fix Config errors
* Add debug thing to patched_api_requestor to investigate HTTP 400 errors
* If this works I'm gonna be sad
* Fix BaseAgent cycle budget logic and document attributes
* Document attributes on `Agent`
* Fix import issues between Agent and MessageHistory
* Improve typing
* Extract application code from the agent (#4982)
* Extract application code from the agent
* Wrap interaction loop in a function and call in benchmarks
* Forgot the important function call
* Add docstrings and inline comments to run loop
* Update typing and docstrings in agent
* Docstring formatting
* Separate prompt construction from on_before_think
* Use `self.default_cycle_instruction` in `Agent.think()`
* Fix formatting
* hot fix the SIGINT handler (#4997)
The signal handler in the autogpt/main.py doesn't work properly because
of the clean_input(...) func. This commit remedies this issue. The issue
is mentioned in
3966cdfd69 (r1264278776)
* Update the sigint handler to be smart enough to actually work (#4999)
* Update the sigint handler to be smart enough to actually work
* Update autogpt/main.py
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Can still use context manager
* Merge in upstream
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Fix CI
* Fix initial prompt construction
* off by one error
* allow exit/EXIT to shut down app
* Remove dead code
---------
Co-authored-by: collijk <collijk@uw.edu>
Co-authored-by: Cyrus <39694513+cyrus-hawk@users.noreply.github.com>
* fix for #4975
* Add TODO based on code comment.
* Use builtin `Path.as_posix()`
* Remove TODO
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* add feature custom text embedding in plugin
* black code format
* _get_embedding_with_plugin()
* Fix docstring & type hint
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Changed Colorama.Fore.ORANGE to YELLOW in config.py, As Colorama does not support an ORANGE color. This fixes a fatal error in run.sh when trying to set the API key through the input() method.
Co-authored-by: James Collins <collijk@uw.edu>
* Add links to github issues in the README and clarify run instructions
* Rename agent subpackage to agents
* Revert all unwanted changes
* Use relative import in `agents/__init__.py`
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Add links to github issues in the README and clarify run instructions
* Move things only used by the agent out of app.py and into the agent module
* Fix busted dynamic import
* Match requests in cassette by hash
* Strip requests more extensively for VCR
* Sort JSON keys on cassette save
* Strip max_tokens from cassettes
* Improve logging in retry decorator
* Raise when quota exceeded
* Clean up @retry_api
* Fix @retry_api
* Remove dead tests/vcr/openai_filter.py
* Add debug logging to execute_python_file
* Make Docker CI pass
* Move path argument sanitization for commands to a decorator
* Fix tests
* Add `@functools.wraps` to `@sanitize_path_arg` decorator
Co-authored-by: James Collins <collijk@uw.edu>
---------
Co-authored-by: James Collins <collijk@uw.edu>
* Consolidate all logging stuff into one module
* Merge import statement for `logs` and `logs.log_cycle`
---------
Co-authored-by: James Collins <collijk@uw.edu>
