Skip to content

feat(evals): prepare a separate Sol and Jev advisory pilot #169

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vriesd merged 5 commits into from
Oct 5, 2026
Merged

feat(evals): prepare a separate Sol and Jev advisory pilot #169

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a019d27
test(jev): reproduce current advice receipt import failures
vriesdcrv Oct 5, 2026
40f55a4
fix(jev): retain bounded transport diagnostics in imported advice
vriesdcrv Oct 5, 2026
15e4770
feat(evals): prepare a separate Sol and Jev advisory pilot
vriesdcrv Oct 5, 2026
6540428
test(evals): expose advisory order and rejected telemetry gaps
vriesdcrv Oct 5, 2026
807f5f3
fix(evals): bind advisory execution slots and retain rejected telemetry
vriesdcrv Oct 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions evals/recovery-decisions/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,6 +171,10 @@ reviewed corpus before collection. The paired report compares manager selections
with Jev advice replayed through the production controller. Episode-level
qualification remains separate.

The [advisory decision pilot](run-advisory-pilot.md) instead prepares independent
Sol decisions with advice visible only in treatment. Its offline checks grant no
inference authority or qualification.

## Whole-episode tooling

See [Whole-episode comparisons](episode-outcomes.md) for completion, interruption,
Expand Down
Loading
Loading