* Correct and clean up JSON handling
* Use ast for message history too
* Lint
* Add comments explaining why we use literal_eval
* Add descriptions to llm_response_format schema
* Parse responses in code blocks
* Be more careful when parsing in code blocks
* Lint
* False believes challenge based on sally anne test.
* Update test_memory_challenge_d.py
* Update challenge_d.md
Some text appearing in bold
* Update test_memory_challenge_d.py
* Update test_memory_challenge_d.py
* Update test_memory_challenge_d.py
* Update test_memory_challenge_d.py
black test_memory_challenge_d.py
* Update test_memory_challenge_d.py
replaced the dynamic time depending of the level to a fix time
* Update test_memory_challenge_d.py
isort command for the libraries
* Refactored memory challenge a
---------
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
* 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
