Expand description
Compact, failures-only summaries of test-runner output (Plan competitive-harvest t-005). Reads a runner’s verbose output and keeps only what an agent needs to act: the pass/fail counts and each failure with a little context — typically a ~90% token cut versus the raw log.
Runners: Cargo and pytest are parsed precisely (the two relevant to an ASD codebase); everything else falls back to a generic failure-line scan.
Structs§
- Failure
- One failed test plus a few lines of captured detail.
- Test
Summary - Compact result of a test run.
Functions§
- summarize
- Parse test-runner output into a compact summary, auto-detecting the runner.