CI

Workflow runs for CI

• Auto-format Python with ruff — all CI checks should pass now

  completed successfully:
  CI#16:Commit184dc43pushedbyrajfirke
  main

  Jul 18, 202637s
  More actions for workflow run 16

• Fix ruff import ordering in test_analysis.py

  failed:
  CI#15:Commit00ad0e4pushedbyrajfirke
  main

  Jul 18, 202645s
  More actions for workflow run 15

• Fix ruff: remove unused math import from test_analysis.py

  failed:
  CI#14:Commita58637dpushedbyrajfirke
  main

  Jul 18, 202638s
  More actions for workflow run 14

• Fix CI: remove unused tempfile import, replace require() with top-lev…

  failed:
  CI#13:Commita304406pushedbyrajfirke
  main

  Jul 18, 202638s
  More actions for workflow run 13

• Add bench init, fix 15 bugs from multi-pass audit (Phases 10+11)

  failed:
  CI#12:Commitaaafcfbpushedbyrajfirke
  main

  Jul 18, 202632s
  More actions for workflow run 12

• Add docs/ mirror of leaderboard for GitHub Pages

  failed:
  CI#11:Commit19981a4pushedbyrajfirke
  main

  Jul 17, 202641s
  More actions for workflow run 11

• Add leaderboard static site with sortable table and filters

  failed:
  CI#10:Commitb1d8d30pushedbyrajfirke
  main

  Jul 17, 202642s
  More actions for workflow run 10

• Implement Python analysis tools: compare, statistics, visualize, lead…

  failed:
  CI#9:Commit4e3f4eepushedbyrajfirke
  main

  Jul 17, 202633s
  More actions for workflow run 9

• Add 20 feature/refactoring/multi-step tasks — 30 total benchmark suite

  failed:
  CI#8:Commitd3d9f05pushedbyrajfirke
  main

  Jul 17, 202637s
  More actions for workflow run 8

• Add 3 baseline loop adapters: minimal, reflexion, plan-first

  failed:
  CI#7:Commita055972pushedbyrajfirke
  main

  Jul 17, 202627s
  More actions for workflow run 7

• Add metrics engine: 11 calculators, composite scoring, bootstrap CI

  failed:
  CI#6:Commit11c9b73pushedbyrajfirke
  main

  Jul 17, 202633s
  More actions for workflow run 6

• Wire up harness core: CLI, loader, evaluator, LTF collector, runner p…

  failed:
  CI#5:Commit5ca9522pushedbyrajfirke
  main

  Jul 17, 202630s
  More actions for workflow run 5

• Add Docker sandbox for isolated task execution

  failed:
  CI#4:Commitd7a6e9cpushedbyrajfirke
  main

  Jul 17, 202633s
  More actions for workflow run 4

• Add 10 bug-fix benchmark tasks with synthetic repos and hidden tests

  failed:
  CI#3:Commit124d546pushedbyrajfirke
  main

  Jul 17, 202643s
  More actions for workflow run 3

• Add spec + schemas: BENCHMARK.md, metrics.md, JSON Schemas, Ajv valid…

  failed:
  CI#2:Commit72c9d41pushedbyrajfirke
  main

  Jul 17, 202638s
  More actions for workflow run 2

• Initial scaffold: loop-bench v0.1.0

  failed:
  CI#1:Commitbc37cc4pushedbyrajfirke
  main

  Jul 17, 202630s
  More actions for workflow run 1