chore: more accuracy test tweaks #675
Merged
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
There was a problem hiding this comment.
Pull Request Overview
This PR refines accuracy test expectations to reduce false negatives by making assertions more flexible. The changes ensure that valid tool calls with optional or varying parameters are not incorrectly flagged as inaccurate.
Key changes:
- Updated test expectations to accept optional parameters like
limit,responseBytesLimit,sampleSize, andoperations - Added optional
list-databasesandlist-collectionscalls that models may make before main operations - Refined prompt wording to better elicit expected behavior (e.g., "exported COMPLETE list")
Reviewed Changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| tests/accuracy/find.test.ts | Added optional list calls helper and applied to all test cases; refined prompt wording |
| tests/accuracy/collectionSchema.test.ts | Added optional list-collections calls and flexible parameter matchers |
| tests/accuracy/export.test.ts | Made filter argument accept empty object or undefined |
| tests/accuracy/explain.test.ts | Added flexible matcher for responseBytesLimit parameter |
| tests/accuracy/logs.test.ts | Added flexible matcher for limit parameter |
| tests/accuracy/getPerformanceAdvisor.test.ts | Added flexible matcher for operations parameter array |
| tests/integration/tools/mongodb/read/find.test.ts | Changed string concatenation to template literal for consistency |
| tests/integration/tools/mongodb/read/aggregate.test.ts | Changed string concatenation to template literal for consistency |
| tests/integration/tools/mongodb/metadata/collectionSchema.test.ts | Whitespace-only change (no functional impact) |
| src/tools/mongodb/read/find.ts | Changed multi-line string to template literal for consistency |
| src/tools/mongodb/read/aggregate.ts | Changed multi-line string to template literal for consistency |
| src/tools/mongodb/metadata/collectionSchema.ts | Whitespace-only change (no functional impact) |
blva
approved these changes
Oct 23, 2025
|
Those changes don't fix all the false negatives, but I did run them locally and improved the accuracy of some tests. The annoying part is that those are quite unpredictable so we need multiple runs to identify the flakes. |
📊 Accuracy Test Results📈 Summary
📎 Download Full HTML Report - Look for the Report generated on: 10/23/2025, 12:44:24 PM |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Proposed changes
This tweaks a few more accuracy tests so that the expectations are more loosely defined and don't flag valid tool calls as inaccurate.