feat: add SWE-bench Pro benchmark and preflight check system#3

Draft

greynewell wants to merge 14 commits intomainfrom

feat/swe-bench-pro

Commits on Feb 25, 2026

feat: add SWE-bench Pro benchmark and preflight check system

greynewell
and
claude
committed
fix: use shlex.quote for test IDs with special characters

greynewell
and
claude
committed
fix: remove broken unicode normalization from test ID handling

greynewell
and
claude
committed
fix: resolve language alias mismatch in SWE-bench Pro filter

greynewell
and
claude
committed
fix: use language-specific test runners in preflight validation

greynewell
and
claude
committed
fix: correct test command parsing for Go subtests and JS/TS pipe format

greynewell
and
claude
committed
fix: auto-detect JS/TS test runner (jest/mocha/vitest) in containers

greynewell
and
claude
committed

Commits on Mar 15, 2026