gstack

0 Fork 0

mirror of https://github.com/garrytan/gstack.git synced 2026-11-05 16:34:00 +01:00

Files

T

History

garrytanandcapy-ai[bot] 1b3aab988a docs: document one-case-shard cost attribution and the train verdict cost line; put the undercounted train costs on record

/document-release (ship-owned audit) added the attribution rule and the ATTEMPT: cost-line form to docs/TESTING_INTERNALS.md, docs/troubleshooting.md#cost-unknown and docs/evals/census-red.md. The CHANGELOG headline now says every train cost the coordinator reported until this fix was the undercounted verdict figure (about $24 per train against about $33 real).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

2026-10-26 15:37:16 +00:00

judge-controls

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033 )

2026-10-06 18:07:50 +00:00

census-red.md

docs: document one-case-shard cost attribution and the train verdict cost line; put the undercounted train costs on record

2026-10-26 15:37:16 +00:00

detector-inventory.md

v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033 )

2026-10-06 18:07:50 +00:00

headroom-diagnosis-2026-10.md

v1.91.108.0 fix(evals): census repair — the late-input and simplification fixtures stop inviting their own failures (#3153 ) (#3200 )