tests: start adding e2e tests #55
Open
Conversation
This file contains 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
sd2k
commented
Mar 26, 2025
sd2k
commented
Apr 4, 2025
12 tasks
| @pytest.mark.parametrize("model", models) | ||
| async def test_loki_logs_tool(model: str, mcp_client: ClientSession): | ||
| tools = await mcp_client.list_tools() | ||
| prompt = "Can you list the last 10 log lines from all containers using any available Loki datasource? Give me the raw log lines. Please use only the necessary tools to get this information." |
There was a problem hiding this comment.
This test is failing for me at least half the time. Generally from trying to put in some non-container label matcher, anything from {job=~".+"} to {job="varlog"}. I wonder if we could at least tweak the prompt or the tool description to get the test to work more consistently.
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Outdated suggestions cannot be applied.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.
This PR adds end-to-end tests for Loki integration and adds test documentation.
This is iteration one as we want to add a basic structure on e2e testing for now. We need to iterate further on them.
Note: prompts needs to be specific when using llm-as-a-judge. I've noticed some flakiness on the llm responses so some times tests are failing, especially the
test_loki_logs_tool.When we are confident that tests are consistently passing then we can make it part of the ruleset.