Commit Graph

8 Commits

Author SHA1 Message Date
Reinier van der Leer
db95d4cb84 Agent loop v2: Planning & Task Management (part 1: refactoring) (#4799)
* 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>
2023-07-20 17:34:49 +02:00
Reinier van der Leer
e8b6676b22 Restructure logs.py into a module; include log_cycle (#4921)
* Consolidate all logging stuff into one module

* Merge import statement for `logs` and `logs.log_cycle`

---------

Co-authored-by: James Collins <collijk@uw.edu>
2023-07-09 20:14:25 +02:00
merwanehamadi
cfdb24efac Link all challenges to benchmark python hook (#4786) 2023-06-24 06:20:58 -07:00
merwanehamadi
222101b30e Create run_task python hook to interface with benchmarks (#4778)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-06-23 21:15:20 -07:00
merwanehamadi
d5afbbee26 Add challenge name and level to pytest logs (#4661) 2023-06-12 08:03:14 -07:00
Erik Peterson
fd04db12fa Use prompt_toolkit to enable keyboard navigation in CLI (#4649)
* Use prompt_toolkit to enable keyboard navigation in CLI

* Also update other tests

---------

Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-06-11 14:19:42 -07:00
merwanehamadi
12ed5a957b Fix debug code challenge (#4632) 2023-06-09 08:40:06 -07:00
Reinier van der Leer
dafbd11686 Rearrange tests & fix CI (#4596)
* Rearrange tests into unit/integration/challenge categories

* Fix linting + `tests.challenges` imports

* Fix obscured duplicate test in test_url_validation.py

* Move VCR conftest to tests.vcr

* Specify tests to run & their order (unit -> integration -> challenges) in CI

* Fail Docker CI when tests fail

* Fix import & linting errors in tests

* Fix `get_text_summary`

* Fix linting errors

* Clean up pytest args in CI

* Remove bogus tests from GoCodeo
2023-06-06 10:48:49 -07:00