AI evals

Workflow runs for AI evals

• AI evals

  failed:
  AI evals#254:Scheduled
  main

  Oct 23, 20264s
  More actions for workflow run 254

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

  failed:
  AI evals#253:Pull request#220openedbyProgramcode
  chore/ai-costs-haiku-byok

  Oct 23, 20263s
  More actions for workflow run 253

• Show usage, limits and plans consistently (T6: QB-03, QB-06, QB-16, VS-06, QB-09, VS-08, IN-07, QB-11, QB-12, ST-03)

  failed:
  AI evals#252:Pull request#217synchronizebyProgramcode
  fix/t6-usage-pricing

  Oct 23, 20264s
  More actions for workflow run 252

• Show usage, limits and plans consistently (T6: QB-03, QB-06, QB-16, VS-06, QB-09, VS-08, IN-07, QB-11, QB-12, ST-03)

  failed:
  AI evals#251:Pull request#217synchronizebyProgramcode
  fix/t6-usage-pricing

  Oct 23, 20263s
  More actions for workflow run 251

• Show usage, limits and plans consistently (T6: QB-03, QB-06, QB-16, VS-06, QB-09, VS-08, IN-07, QB-11, QB-12, ST-03)

  failed:
  AI evals#250:Pull request#217synchronizebyProgramcode
  fix/t6-usage-pricing

  Oct 23, 20263s
  More actions for workflow run 250

• Show usage, limits and plans consistently (T6: QB-03, QB-06, QB-16, VS-06, QB-09, VS-08, IN-07, QB-11, QB-12, ST-03)

  failed:
  AI evals#249:Pull request#217openedbyProgramcode
  fix/t6-usage-pricing

  Oct 23, 20261m 41s
  More actions for workflow run 249

• Start a debate on the first Generate instead of asking (MD-10, Adam to decide)

  failed:
  AI evals#248:Pull request#212openedbyProgramcode
  fix/t8-md10-generate-autostart

  Oct 23, 20263s
  More actions for workflow run 248

• Polish the prep modes (T8: MD-04, MD-06–12, MD-14, VS-04, AX-05, AX-06)

  failed:
  AI evals#247:Pull request#211synchronizebyProgramcode
  fix/t8-modes-polish

  Oct 23, 20263s
  More actions for workflow run 247

• Polish the prep modes (T8: MD-04, MD-06–12, MD-14, VS-04, AX-05, AX-06)

  failed:
  AI evals#246:Pull request#211synchronizebyProgramcode
  fix/t8-modes-polish

  Oct 23, 20263s
  More actions for workflow run 246

• Polish the prep modes (T8: MD-04, MD-06–12, MD-14, VS-04, AX-05, AX-06)

  failed:
  AI evals#245:Pull request#211openedbyProgramcode
  fix/t8-modes-polish

  Oct 23, 20263s
  More actions for workflow run 245

• Make billing states agree between Settings and the AI functions (T4: QB-02, QB-13, QB-14, QB-15, QB-08, QB-17, SC-03)

  failed:
  AI evals#244:Pull request#207synchronizebyProgramcode
  fix/t4-billing-states

  Oct 23, 20264s
  More actions for workflow run 244

• Make billing states agree between Settings and the AI functions (T4: QB-02, QB-13, QB-14, QB-15, QB-08, QB-17, SC-03)

  failed:
  AI evals#243:Pull request#207synchronizebyProgramcode
  fix/t4-billing-states

  Oct 23, 20263s
  More actions for workflow run 243

• Drain live AI streams until the body closes

  failed:
  AI evals#242:Pull request#204synchronizebyProgramcode
  cursor/live-stream-drain-a248

  Oct 23, 20263s
  More actions for workflow run 242

• Make billing states agree between Settings and the AI functions (T4: QB-02, QB-13, QB-14, QB-15, QB-08, QB-17, SC-03)

  failed:
  AI evals#241:Pull request#207openedbyProgramcode
  fix/t4-billing-states

  Oct 23, 20264s
  More actions for workflow run 241

• Drain live AI streams until the body closes

  failed:
  AI evals#240:Pull request#204synchronizebyProgramcode
  cursor/live-stream-drain-a248

  Oct 23, 20263s
  More actions for workflow run 240

• Drain live AI streams until the body closes

  failed:
  AI evals#239:Pull request#204synchronizebyProgramcode
  cursor/live-stream-drain-a248

  Oct 22, 20263s
  More actions for workflow run 239

• Fix Library and History QA issues (T7: LB-01, LB-03–07, HI-01, MD-05, VS-07)

  failed:
  AI evals#238:Pull request#203synchronizebyProgramcode
  fix/t7-library-history

  Oct 22, 20263s
  More actions for workflow run 238

• Charge Crossfire and Sparring per round, refund runs that produce nothing (batch T5)

  failed:
  AI evals#237:Pull request#201synchronizebyProgramcode
  fix/t5-session-quota-refunds

  Oct 22, 20263s
  More actions for workflow run 237

• Fix import-source stripping whole Wikipedia pages (#195 regression)

  failed:
  AI evals#236:Pull request#197synchronizebyProgramcode
  fix/import-source-wikipedia-chrome

  Oct 22, 20263s
  More actions for workflow run 236

• Drain live AI streams until the body closes

  failed:
  AI evals#235:Pull request#204openedbyProgramcode
  cursor/live-stream-drain-a248

  Oct 22, 20264s
  More actions for workflow run 235

• Fix Library and History QA issues (T7: LB-01, LB-03–07, HI-01, MD-05, VS-07)

  failed:
  AI evals#234:Pull request#203openedbyProgramcode
  fix/t7-library-history

  Oct 22, 20263s
  More actions for workflow run 234

• Charge Crossfire and Sparring per round, refund runs that produce nothing (batch T5)

  failed:
  AI evals#233:Pull request#201openedbyProgramcode
  fix/t5-session-quota-refunds

  Oct 22, 20263s
  More actions for workflow run 233

• Fix import-source stripping whole Wikipedia pages (#195 regression)

  failed:
  AI evals#232:Pull request#197openedbyProgramcode
  fix/import-source-wikipedia-chrome

  Oct 22, 20263s
  More actions for workflow run 232

• Fix the 22 Oct QA backend nits (batch C2)

  failed:
  AI evals#231:Pull request#195synchronizebyProgramcode
  cursor/backend-nits-c2-fbc6

  Oct 22, 20263s
  More actions for workflow run 231

• Fix the 22 Oct QA backend nits (batch C2)

  failed:
  AI evals#230:Pull request#195openedbyProgramcode
  cursor/backend-nits-c2-fbc6

  Oct 22, 20263s
  More actions for workflow run 230