E2E Evals

Workflow runs for E2E Evals

• docs(agents): Cursor Cloud dev environment setup notes

  cancelled:
  E2E Evals#68:Pull request#55openedbytime-attack
  cursor/setup-dev-environment-2c04

  Aug 18, 20262d 0h 0m 13s
  More actions for workflow run 68

• feat(qa): record an agent walking a web or iOS app, then open it

  cancelled:
  E2E Evals#67:Pull request#54synchronizebycursor[bot]Bot
  cursor/qa-recording-d3d5

  Aug 18, 20263d 0h 0m 12s
  More actions for workflow run 67

• feat(qa): record an agent walking a web or iOS app, then open it

  cancelled:
  E2E Evals#66:Pull request#54openedbytime-attack
  cursor/qa-recording-d3d5

  Aug 18, 20261d 5h 26m 19s
  More actions for workflow run 66

• feat(plan): full autonomy by default, retire stale model priors

  cancelled:
  E2E Evals#65:Pull request#53openedbytime-attack
  release/gstack2-public-beta

  Aug 10, 20263d 0h 0m 3s
  More actions for workflow run 65

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#64:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 10, 20261d 4h 54m 55s
  More actions for workflow run 64

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#63:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 202618h 29m 47s
  More actions for workflow run 63

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#62:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 202649m 47s
  More actions for workflow run 62

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#61:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20261m 15s
  More actions for workflow run 61

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#60:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20262h 33m 55s
  More actions for workflow run 60

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#59:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20264m 57s
  More actions for workflow run 59

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#58:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20263m 57s
  More actions for workflow run 58

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#57:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20265m 57s
  More actions for workflow run 57

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#56:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20267m 9s
  More actions for workflow run 56

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#55:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20262m 43s
  More actions for workflow run 55

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#54:Pull request#52synchronizebytime-attack
  release/gstack2-public-beta

  Aug 9, 20261m 16s
  More actions for workflow run 54

• release: GStack 2 public beta — v2.0.0.0

  cancelled:
  E2E Evals#53:Pull request#52openedbytime-attack
  release/gstack2-public-beta

  Aug 9, 20261d 0h 4m 40s
  More actions for workflow run 53

• feat: measured web-data provider contract — Firecrawl/Exa/Context.dev/Aside/local, selectable per task

  cancelled:
  E2E Evals#52:Pull request#40synchronizebytime-attack
  time-attack/web-data-providers

  Jul 29, 20262d 0h 0m 3s
  More actions for workflow run 52

• feat: add make-pdf as a 6th skill in skills/ (Markdown → styled PDF)

  cancelled:
  E2E Evals#51:Pull request#51openedbytime-attack
  restore-make-pdf

  Jul 24, 20262d 0h 0m 2s
  More actions for workflow run 51

• Non-Mac hosts: build legs route through a macOS CI runner (v1.64.20.0)

  cancelled:
  E2E Evals#50:Pull request#50openedbytime-attack
  time-attack/windows-ci-lane

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 50

• Pricing folded into the authorization moment (v1.64.19.0)

  cancelled:
  E2E Evals#49:Pull request#49openedbytime-attack
  time-attack/pricing-question

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 49

• Session-minted upload key: nobody types an app-specific password (v1.64.18.0)

  cancelled:
  E2E Evals#48:Pull request#48openedbytime-attack
  time-attack/upload-key-mint

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 48

• Shared judgment clause 13: evidence before claimed limitations (v1.64.17.0)

  cancelled:
  E2E Evals#47:Pull request#47openedbytime-attack
  time-attack/appleship-evidence-clause

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 47

• Classify errors before credentials; no browser in the Apple journey (v1.64.16.0)

  cancelled:
  E2E Evals#46:Pull request#46openedbytime-attack
  time-attack/appleship-cli-only

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 46

• Auth failures: re-sign-in before any password fallback (v1.64.15.0)

  cancelled:
  E2E Evals#45:Pull request#45openedbytime-attack
  time-attack/appleship-resignin

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 45

• Restore ban on browser-driven credential creation (v1.64.14.0)

  cancelled:
  E2E Evals#44:Pull request#44openedbytime-attack
  time-attack/appleship-credential-ban

  Jul 24, 20262d 0h 0m 3s
  More actions for workflow run 44