garrytanandcapy-ai[bot] 9fa5e97c96 fix(ship-budget): measure readers only by the dispatch program's reading pair, price them from packet bytes, stop the parent on a failed child (GSTA-167) ...

Replay 2 on gstack-evals #36 priced the Red Team at 7.43M x 1.875 = 13.94M because
reservation r5 was settled at the next --returned check, so its interval held the
child's own review, QA and packet build. Now:
- settle / check --returned take --dispatched-at <reading before the readers> and
  --readers; without that pair (a later program), or with another command's reading
  in between, the dispatch is UNMEASURED and teaches nothing.
- --next accepts role@bytes; a reader's prior is 3 x (call floor + bytes/4), and the
  learned dispatch factor never prices a reader above the larger of its prior and the
  run's clean per-reader mean.
- reconcile of a refused, incomplete or interrupted child stops the run, so every
  check refuses until a regenerated child reconciles complete or resume runs.

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

2026-10-29 23:28:12 +00:00

..

sections

fix(ship-budget): measure readers only by the dispatch program's reading pair, price them from packet bytes, stop the parent on a failed child (GSTA-167)

2026-10-29 23:28:12 +00:00

SKILL.md

v1.91.316.0 ship: token cap with real meters and fresh-context delegation (GSTA-152 PR A) (#3593)

2026-10-29 10:29:23 +00:00

SKILL.md.tmpl

v1.91.316.0 ship: token cap with real meters and fresh-context delegation (GSTA-152 PR A) (#3593)

2026-10-29 10:29:23 +00:00