Add tests for multi-LLM agents and direct OpenAI/Anthropic providers #12
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Ololoshechkin
approved these changes
May 8, 2025
Ololoshechkin
force-pushed
the
zarechneva/direct-executor-tests
branch
from
e689c0c to
3dd1a7b
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I added the code of part of the tests that I performed manually to verify direct OpenAI / Anthropic providers work. I didn't add all of them to avoid code duplication: in most scenarios, I just tweaked executors, added printing out the execution results, or modified prompts/strategies.
Also, all new tests are marked as @disabled right now, because apparently the API tokens are not passed to the code. I'd also argue the necessity of running all of them without mocks in the future.
Anyways, right now it's a kind of saving the artifacts of performed checks. The test code was written by me (but, sure, partially copied from the files in the same module); the tools and parsers were created using Junie (but I did my best to review them).
Original PR: https://github.com/JetBrains/code-engine/pull/512