Commit Graph

289 Commits

Author SHA1 Message Date
Erik Peterson
ff4e53d0e6 Streamline / clarify shell command control configuration (#4628)
* Streamline / clarify shell command control configuration

* Fix lint
2023-06-09 11:48:20 -07:00
Erik Peterson
cce50bef50 Fix issues with information retrieval challenge a (#4622)
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-06-09 11:02:52 -07:00
Auto-GPT-Bot
8215039785 Update cassette submodule 2023-06-09 17:46:06 +00:00
Erik Peterson
94280b2d14 Add command for directly executing python code (#4581)
* Add command for directly executing python code

* Fix docstring

* Clarify / update filename references

---------

Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-06-09 10:40:32 -07:00
merwanehamadi
3d06b2e4c0 Decrement information retrieval challenge a (#4637) 2023-06-09 10:02:03 -07:00
merwanehamadi
12ed5a957b Fix debug code challenge (#4632) 2023-06-09 08:40:06 -07:00
merwanehamadi
3b0d49a3e0 Make test write file hard (#4481) 2023-06-09 07:50:57 -07:00
merwanehamadi
bd2e26a20f Inform users that challenges can be flaky (#4616)
* Inform users that challenges can be flaky

* Update challenge_decorator.py
2023-06-09 07:43:56 -07:00
Stefan Ayala
1e851ba3ea Feat set token limits based on model (#4498)
* feat: set max token limits for better user experience

* fix: use OPEN_AI_CHAT_MODELS max limits

* fix: use the old default of 8000

* fix: formatting so isort/black checks pass

* fix: avoid circular dependencies

* fix: use better to avoid circular imports

* feat: introduce soft limits and use them

* fix: circular import issue and missing field

* fix: move import to avoid overriding doc comment

* feat: DRY things up and set token limit for fast llm models too

* tests: make linter tests happy

* test: use the max token limits in config.py test

* fix: remove fast token limit from config

* feat: remove smart token limit from config

* fix: remove unused soft_token_limit var

* fix: remove unneeded tests, settings aren't in config anymore

---------

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
2023-06-07 10:16:53 +02:00
Erik Peterson
fdc6e12945 Improve logic and error messages for file reading and writing with Python code (#4567)
* Fix issues with file reading and writing with Python code

* Change error message, use Workspace.get_path

---------

Co-authored-by: Reinier van der Leer <github@pwuts.nl>
2023-06-07 02:54:02 +02:00
Auto-GPT-Bot
835decc6c1 Update challenge scores 2023-06-06 21:48:57 +00:00
merwanehamadi
53efa8f6bf Update cassette submodule & fix current_score.json generation (#4601)
* Update cassette submodule

* add a new line when building current_score.json
2023-06-06 23:46:41 +02:00
Erik Peterson
055806e124 Fix inverted logic for deny_command (#4563) 2023-06-06 22:56:17 +02:00
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
Auto-GPT-Bot
8a881f70a3 Update cassette submodule 2023-06-06 14:35:43 +00:00
merwanehamadi
ee6b97ef5e Fix Python CI "update cassettes" step (#4591)
* Fix updated cassettes step

* Clarifications

* Use github.ref_name instead of github.ref

* Fix duplicate runs on `master`

---------

Co-authored-by: Reinier van der Leer <github@pwuts.nl>
2023-06-06 16:27:08 +02:00
Auto-GPT-Bot
60ac0c4da1 Update challenge scores 2023-06-05 14:39:45 +00:00
Reinier van der Leer
576f24e3ae Merge branch 'master' into release-0.4.0 2023-06-05 16:08:35 +02:00
Benny van der Lans
74e8a886e6 Add replace_in_file command (#4565)
Resubmission of #3643

---------

Co-authored-by: Reinier van der Leer <github@pwuts.nl>
2023-06-04 19:37:35 +02:00
merwanehamadi
59d31b021d Skip flaky challenges (#4573) 2023-06-04 18:20:13 +02:00
merwanehamadi
af28510aba Fix test_web_selenium (#4554) 2023-06-04 16:38:32 +02:00
Merwane Hamadi
02846fcf91 remove information retrieval challenge b from beaten challenges 2023-06-03 21:24:36 -07:00
Auto-GPT-Bot
378126822f Update submodule reference 2023-06-03 14:51:55 +00:00
Auto-GPT-Bot
55a8e242b0 Update current score 2023-06-03 14:51:53 +00:00
merwanehamadi
79ba85a22e Cache Python Packages in the CI pipeline (#4488) 2023-06-03 15:48:32 +01:00
Auto-GPT-Bot
64973bfe12 Update submodule reference 2023-05-30 23:33:40 +00:00
Auto-GPT-Bot
41df0204f3 Update current score 2023-05-30 23:33:38 +00:00
Douglas Schonholtz
f6ee61d607 create debug challenge (#4286)
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: symphony <john.tian31@gmail.com>
2023-05-30 16:28:32 -07:00
merwanehamadi
87776b2886 Make the information retrieval challenge a harder while still passing (#4468) 2023-05-30 15:56:58 -07:00
Auto-GPT-Bot
387f65c16c Update submodule reference 2023-05-30 19:15:33 +00:00
Auto-GPT-Bot
4c25fabec9 Update current score 2023-05-30 19:15:30 +00:00
merwanehamadi
6806b66509 Information retrieval challenge (#4456)
* test: add information retrieval challenge b

* test: get information retrieval challenge be working.

* chore: clean up comments and imports.

* chore: fix incorrect import

* chore: clean up imports.

* fix: add web_selenium cmd. resolve missing loop cycle

* chore: remove commented code and unused imports.

* fix (4261): use 2 cycles instead of 3

* chore: fix mypy formatting

* chore: try 2 for mypy formatting

* chore: resolve flake8 issues

* chore: add docs

* chore: resolve linting flake8

* chore: correct formatting to black

* Update challenge_b.md

* refactored challenge

---------

Co-authored-by: PortlandKyGuy <kyleaaron1@gmail.com>
2023-05-30 12:10:49 -07:00
Erik Peterson
b56352e218 Fix #4461: Don't record error requests in challenges (#4469)
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-05-30 07:31:45 -07:00
Auto-GPT-Bot
d3a1770dc0 Update submodule reference 2023-05-30 13:03:41 +00:00
merwanehamadi
22429c6e98 add vcr to dalle (#4474) 2023-05-30 06:00:37 -07:00
Auto-GPT-Bot
56650b60f4 Update current score 2023-05-30 02:33:34 +00:00
merwanehamadi
ba8046753e Update current score when PR merged (#4464) 2023-05-29 19:30:41 -07:00
Luke K (pr-0f3t)
1446ffddb0 Fix #942: Respect --gpt4only, --gpt3only cli args (#3144)
Co-authored-by: Luke K <KayLuke@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
2023-05-29 20:10:51 +03:00
Auto-GPT-Bot
b5d78a48a7 Update submodule reference 2023-05-29 15:29:31 +00:00
merwanehamadi
1127d9c5f5 Master doesn't beat memory challenge b level 1 in a consistent manner (#4460) 2023-05-29 18:25:45 +03:00
merwanehamadi
31cd836530 "Beat Challenges" Mode (#4447)
Co-authored-by: Richard Beales <rich@richbeales.net>
2023-05-29 08:47:06 +01:00
merwanehamadi
ee9f10a8d8 remove unused imports automatically (#4449)
* remove unused imports automatically

* add linters to pr template

* remove useless try statement
2023-05-28 05:50:50 -07:00
Auto-GPT-Bot
78774526f4 Update submodule reference 2023-05-28 01:30:02 +00:00
merwanehamadi
44f6d946f5 fix information retrieval challenge (#4448) 2023-05-27 18:26:30 -07:00
Ryan Johns
03036c1bd6 Added three more tests to check for edge cases in URL validation (#4441)
Co-authored-by: Ryan Johns <rkjohns@verisk.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
2023-05-27 18:58:38 +03:00
k-boikov
064e95b46b Allow spinning to be disabled (#4329) 2023-05-27 00:01:34 +03:00
merwanehamadi
e7c0d3330c Create cassette submodule (#4420)
* gfeat: specify directory of cassettes and automatically load them depending on module

fix: formatting for linter

test: commit newly generated cassettes to their respective folder

tests: update latest fixtures with master

fix: update .gitattributes with updated path to cassettes

fix: use cassettes from master instead of generating them myself

fix: update path in .gitattributes

fix: make sure to match default functionality by using test name for cassette directory

fix: actually add git submodule

ci: checkout git submodules in CI

ci: update git submodules separately to ensure it gets called

feat: add a hooks directory so we can update git submodules on post-checkout

feat: make sure we push the tests/cassettes submodule on merge into master

ci: remove unused code now that we are using git submodules to keep cassettes in sync

fix: simplify how we load the submodule and fix updating cassettes on merge to master

chore: remove echo of checkout hook, it's unneeded

ci: remove unneccesary step

* cassettes submodule

* cassettes submodule

* cassettes submodule

* cassettes submodule

* cassettes submodule

---------

Co-authored-by: Stefan Ayala <stefanayala3266@gmail.com>
2023-05-26 12:33:49 -07:00
Nicholas Tindle
acfd966aa4 Pass Configs to Commands and remove CFG = Config() in the commands/ folder (#4328)
* feat: pass config to call_ai_functions in coimmands

* feat: config for read_audio_from_file

* feat: file operations cfg

NOTE: we replaced the CFG in the command enable with TRUE b/c not sure how to handle this yet

* feat: git command conversion

* feat: google search

* feat: image generation

* feat: extract cfg from browser commands

* feat: remove cfg from execute code commands

* fix: file operation related tests

* fix: linting

* fix: tests for read_audio

* fix: test error

* feat: update cassettes

* fix: linting

* fix: test typechecking

* fix: google_search errors if unexpected kw arg is passed

* fix: pass config param to google search test

* fix: agent commands were broken + cassettes

* fix: agent test

* feat: cassettes

* feat: enable/disable logic for commands

* fix: some commands threw errors

* feat: fix tests

* Add new cassettes

* Add new cassettes

* ci: trigger ci

* Update autogpt/commands/execute_code.py

Co-authored-by: Reinier van der Leer <github@pwuts.nl>

* fix prompt

* fix prompt + rebase

* add config remove useless imports

* put back CFG just for download file

* lint

* The signature should be mandatory in the decorator

* black isort

* fix: remove the CFG

* fix: non typed arg

* lint: type some args

* lint: add types for libraries

* Add new cassettes

* fix: windows compatibility

* fix: add config access to decorator

* fix: remove twitter mention

* DDGS search works at 3.0.2 version

* ci: linting

---------

Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: kinance <kinance@gmail.com>
2023-05-26 08:39:25 -07:00
k-boikov
f07fcdf0a7 Pull auto-gpt-plugin-template from GitHub instead of PyPI (#4402)
* switch from pypi to github for auto-gpt-plugin-template

* adapt tests to new plugin interface
2023-05-26 14:48:36 +02:00
k-boikov
ddf59273e6 Remove obsolete full_message_history kwarg from tests (#4411) 2023-05-25 22:00:52 +03:00