All pull requests

Pull requests

• FEAT: program execution scorer in an isolated sandbox (scorer phase 10b)

  #3218·WatchTree-19 opened Oct 14, 2026Contributor·

  ·

• MAINT: Bump the minor-and-patch group with 14 updates

  dependenciespython:uv
  #3217·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  4

• FIX: Do not count an echo of the encoded prompt as a decode in DecodingScorer

  #3216·Jaafer Rahmani (bIackr0se) opened Oct 14, 2026Contributor·

  ·

• MAINT: Bump types-requests from 2.33.0.20260906 to 2.33.0.20261006

  dependenciespython:uv
  #3215·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  8

• MAINT: Bump openai from 2.54.0 to 3.29.0

  dependenciespython:uv
  #3214·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  1

• MAINT: Bump pyarrow from 25.0.1 to 26.0.0

  dependenciespython:uv
  #3213·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  8

• FIX: Only accept and sign blob media from this server's results container

  #3212·varunj-msft opened Oct 14, 2026Contributor·

  ·

• MAINT: Bump the minor-and-patch group with 3 updates

  dependenciesgithub_actions
  #3211·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  8

• MAINT: Bump https://github.com/astral-sh/ruff-pre-commit from v0.16.10 to 0.17.0

  dependenciespre_commit
  #3210·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  8

• MAINT: Bump the minor-and-patch group in /frontend with 9 updates

  dependenciesjavascript
  #3209·dependabot[bot] opened Oct 14, 2026Bot·

  ·
  8

• MAINT: Parse project TOML with tomllib instead of a regex (P311-15)

  #3208·Shivam Maurya (shivampwm2020) opened Oct 14, 2026·

  ·
  5

• TEST: Make scenario resume checks more reliable

  #3207·Richard Lundeen (richlundeen) opened Oct 14, 2026Contributor·

  ·

• FEAT: Add explicit scenario dataset refresh

  #3206·Richard Lundeen (richlundeen) opened Oct 14, 2026Contributor·

  ·

• TEST: fix flaky tests failing build_and_test

  #3203·hannahwestra25 opened Oct 14, 2026Contributor·

  ·

• FIX: give regex, package-hallucination and aggregator configs their own scorer identity

  #3200·Utkarsh Bahuguna (u7k4rs6) opened Oct 14, 2026Contributor·

  ·
  1

• MAINT: deprecate labels on message and prompt-score queries

  #3199·Utkarsh Bahuguna (u7k4rs6) opened Oct 14, 2026Contributor·

  ·
  1

• MAINT Extract message view model from MessageList

  #3198·Isaac Emmanuel (1cbyc) opened Oct 14, 2026·

  ·
  3

  

• MAINT: Coordinate scenario progress refresh per run

  #3197·Richard Lundeen (richlundeen) opened Oct 14, 2026Contributor·

  ·
  1

• TEST: Make analytics benchmark smoke checks independent of request deadlines

  #3195·Richard Lundeen (richlundeen) opened Oct 13, 2026Contributor·

  ·
  

• [DRAFT] FEAT: Add Microsoft decision model scoring

  #3188·Richard Lundeen (richlundeen) opened Oct 13, 2026Contributor·

  ·
  10

  

• FEAT: Improve conversation branching and technique reuse

  #3187·Richard Lundeen (richlundeen) opened Oct 13, 2026Contributor·

  ·
  3

  

• FIX: key model-less objective targets by content hash in analytics v1

  #3171·Utkarsh Bahuguna (u7k4rs6) opened Oct 13, 2026Contributor·

  ·
  1

• FEAT: Add saved attack results analytics GUI

  #3168·Roman Lutz (romanlutz) opened Oct 13, 2026Contributor·

  ·
  

• feat: Add bounded Scenario result hierarchy projections (#3145)

  #3167·Nimit Jain (Nimit3418) opened Oct 13, 2026Contributor·

  ·
  1

  30

  

• FIX: mask words written with combining marks instead of skipping them

  #3155·Nikhil Gupta (Denimworld12) opened Oct 12, 2026·

  ·
  4