You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Use case: test impact analysis and flaky test history #29
Add a use case: store which tests cover which code, plus every test result per commit.
The idea
Record coverage edges (test covers function or file) and test outcomes for each CI run. Large CI systems build this in-house. A small team could keep it in one file.
Questions it answers
Which tests must run for this change? (reverse reachability from the changed files)
Is this test flaky, or did it start failing at a real commit?
Which code areas have no covering test at a given release?
Why Minigraf fits
Test selection is a graph traversal from changed code to covering tests, including through call edges.
Telling flaky from broken needs result history across commits.
Suggested content
The idea and the two questions (selection and flakiness)
A fact schema (test, covers, calls, result, commit)
A rule for test selection from a set of changed files
A query that finds tests with mixed results on the same commit
Notes
This is an idea for others to build. There is no official tool.
Activity
adityamukho commentedon Oct 19, 2026
Builds on the git sidecar idea in #34, which provides the commit and entity index this use case attaches facts to.
Generated by Claude Code