Repository navigation

feat(labs): add blind model evaluations and orchestration guidance - #53

Merged

ScriptedAlchemy merged 15 commits into

mainfrom

feat/blind-model-evaluation

Nov 5, 2026

Merged

feat(labs): add blind model evaluations and orchestration guidance#53
ScriptedAlchemy merged 15 commits into
mainfrom
feat/blind-model-evaluation

Commits on Nov 3, 2026
- feat(labs): add blind model evaluations and orchestration guidance
  ScriptedAlchemy
  committed
  66e82f5
- fix(labs): respect judge settings and preserve outcome evidence
  ScriptedAlchemy
  committed
  85730a9
- refactor(labs): simplify model evaluation plumbing
  ScriptedAlchemy
  committed
  c813d10
- chore: merge main into blind model evaluation review
  
  ScriptedAlchemy
  and
  codex
  committed
  14c6bad
- test(mobile): isolate labs imports in settings controls tests
  
  ScriptedAlchemy
  and
  codex
  committed
  06550ee
- fix(labs): redact bare Claude model family names from judge evidence
  
  ScriptedAlchemy
  and
  codex
  committed
  ebef167
- test: isolate inherited T3 shim settings from provider replays
  
  ScriptedAlchemy
  and
  codex
  committed
  af37b9c
- fix(labs): keep identity names out of judge evidence after escaped newlines
  
  ScriptedAlchemy
  and
  claude
  committed
  f9a29ed
- fix(web): unavailable-model warning no longer points at another environment
  
  ScriptedAlchemy
  and
  claude
  committed
  000e626
Commits on Nov 4, 2026
- Merge remote-tracking branch 'origin/main' into feat/blind-model-evaluation
  
  ScriptedAlchemy
  and
  claude
  committed
  1cac2a5
- fix(labs): build model evaluations against the merged main
  
  ScriptedAlchemy
  and
  claude
  committed
  5962abc
- test(labs): include the renumbered evaluation migration in preview reconciliation
  
  ScriptedAlchemy
  and
  claude
  committed
  a09a9c9
- Merge remote-tracking branch 'origin/main' into xreview/pr53
  ScriptedAlchemy
  committed
  a3192a5
- Merge remote-tracking branch 'origin/main' into xreview/pr53
  ScriptedAlchemy
  committed
  ac50a85
Commits on Nov 5, 2026
- Merge remote-tracking branch 'origin/main' into xreview/pr53
  ScriptedAlchemy
  committed
  081bd84

Commits

Commits on Nov 3, 2026

Commits on Nov 4, 2026

Commits on Nov 5, 2026