Open
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
| @@ -0,0 +1,2 @@ | |||
| {"messages": [ { "role": "system", "content": "You are a helpful assistant that can answer questions about Gmail. You have access to tools to help you find information." }, { "role": "user", "content": "Fetch the first 5 emails in my gmail inbox and get the sender. Output the sender only." } ], "ground_truth": "The response contains 5 email addresses." } | |||
There was a problem hiding this comment.
Bug: Judging Descriptions, Not Content
The Gmail test's ground truth is a meta-description ("The response contains 5 email addresses.") rather than actual expected content. The LLM judge checks if the output literally contains this string, not whether the output actually has 5 email addresses. This differs from the Notion test which uses actual expected content ("Pizzeria Badiali") and will cause the Gmail test to fail even with correct outputs.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Note
Replaces the Gmail-only test with a multi-service Klavis MCP dataset (Gmail, Notion, Outlook), updates the MCP auth env var, and points the pytest to the new dataset.
tests/pytest/datasets/klavis_mcp_test.jsonlwith prompts/ground truths forGmail,Notion, andOutlook Calendar.tests/pytest/datasets/gmail_inbox.jsonl.tests/pytest/test_pytest_klavis_mcp.pyto useklavis_mcp_test.jsonl(adds brief Notion setup note).tests/pytest/mcp_configurations/klavis_strata_mcp.jsonauthorization fromBearer ${KLAVIS_API_KEY}toBearer ${KLAVIS_AUTH_TOKEN}.Written by Cursor Bugbot for commit 78dbd75. This will update automatically on new commits. Configure here.