AI evals

Workflow runs for AI evals

• DebateOwl polish: sentence case, even rows, touch targets, prerendered owl

  failed:
  AI evals#279:Pull request#243synchronizebyProgramcode
  design/debateowl-polish

  Oct 27, 20263s
  More actions for workflow run 279

• Generate writes cases the way school debaters prepare them

  failed:
  AI evals#278:Pull request#244openedbyProgramcode
  feat/case-structure-v2

  Oct 27, 20263s
  More actions for workflow run 278

• Finish the visible DebateLab to DebateOwl rename

  failed:
  AI evals#277:Pull request#241synchronizebycursor[bot]Bot
  design/debateowl-rename-finish

  Oct 27, 20263s
  More actions for workflow run 277

• DebateOwl polish: sentence case, even rows, touch targets, prerendered owl

  failed:
  AI evals#276:Pull request#243openedbyProgramcode
  design/debateowl-polish

  Oct 27, 20263s
  More actions for workflow run 276

• Finish the visible DebateLab to DebateOwl rename

  failed:
  AI evals#275:Pull request#241openedbyProgramcode
  design/debateowl-rename-finish

  Oct 27, 20263s
  More actions for workflow run 275

• AI evals

  failed:
  AI evals#274:Scheduled
  main

  Oct 27, 20263s
  More actions for workflow run 274

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#273:Pull request#228synchronizebyProgramcode
  design/debateowl-restyle

  Oct 26, 20263s
  More actions for workflow run 273

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#272:Pull request#228synchronizebyProgramcode
  design/debateowl-restyle

  Oct 26, 20264s
  More actions for workflow run 272

• AI evals

  failed:
  AI evals#271:Scheduled
  main

  Oct 26, 20263s
  More actions for workflow run 271

• AI evals

  failed:
  AI evals#270:Scheduled
  main

  Oct 25, 20263s
  More actions for workflow run 270

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#269:Pull request#228synchronizebyProgramcode
  design/debateowl-restyle

  Oct 24, 20263s
  More actions for workflow run 269

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#268:Pull request#228synchronizebyProgramcode
  design/debateowl-restyle

  Oct 24, 20263s
  More actions for workflow run 268

• Fix the security audit findings: promo caps, keepalive anon access, error text, import DNS pinning

  failed:
  AI evals#267:Pull request#230openedbyProgramcode
  fix/security-audit-findings

  Oct 24, 20263s
  More actions for workflow run 267

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#266:Pull request#228synchronizebyProgramcode
  design/debateowl-restyle

  Oct 24, 20262s
  More actions for workflow run 266

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#265:Pull request#228synchronizebyProgramcode
  design/debateowl-restyle

  Oct 24, 20263s
  More actions for workflow run 265

• DebateOwl visual restyle: tokens, fonts, tactile buttons and the owl

  failed:
  AI evals#264:Pull request#228openedbyProgramcode
  design/debateowl-restyle

  Oct 24, 20263s
  More actions for workflow run 264

• AI evals

  failed:
  AI evals#263:Scheduled
  main

  Oct 24, 20263s
  More actions for workflow run 263

• T18: keep AI streams alive, recover dropped results, fix Auto Pro charge, refunds, Sparring judge errors

  failed:
  AI evals#262:Pull request#224synchronizebyProgramcode
  fix/t18-ai-stream-reliability

  Oct 23, 20263s
  More actions for workflow run 262

• T18: keep AI streams alive, recover dropped results, fix Auto Pro charge, refunds, Sparring judge errors

  failed:
  AI evals#261:Pull request#224synchronizebyProgramcode
  fix/t18-ai-stream-reliability

  Oct 23, 20264s
  More actions for workflow run 261

• T18: keep AI streams alive, recover dropped results, fix Auto Pro charge, refunds, Sparring judge errors

  failed:
  AI evals#260:Pull request#224synchronizebyProgramcode
  fix/t18-ai-stream-reliability

  Oct 23, 20264s
  More actions for workflow run 260

• T18: keep AI streams alive, recover dropped results, fix Auto Pro charge, refunds, Sparring judge errors

  failed:
  AI evals#259:Pull request#224openedbyProgramcode
  fix/t18-ai-stream-reliability

  Oct 23, 20264s
  More actions for workflow run 259

• Move default, Auto and test-agent model calls onto the Anthropic BYOK key, with a no-fallback guard

  failed:
  AI evals#258:Pull request#220synchronizebyProgramcode
  chore/ai-costs-haiku-byok

  Oct 23, 20264s
  More actions for workflow run 258

• Move default, Auto and test-agent model calls onto the Anthropic BYOK key, with a no-fallback guard

  failed:
  AI evals#257:Pull request#220synchronizebyProgramcode
  chore/ai-costs-haiku-byok

  Oct 23, 20263s
  More actions for workflow run 257

• Localize tab titles, validation and server errors; add ?lang= links (T12: IN-01, SE-01, IN-14, IN-03, IN-04, IN-11)

  failed:
  AI evals#256:Pull request#222synchronizebyProgramcode
  fix/t12-i18n-errors-titles

  Oct 23, 20263s
  More actions for workflow run 256

• Localize tab titles, validation and server errors; add ?lang= links (T12: IN-01, SE-01, IN-14, IN-03, IN-04, IN-11)

  failed:
  AI evals#255:Pull request#222openedbyProgramcode
  fix/t12-i18n-errors-titles

  Oct 23, 20263s
  More actions for workflow run 255