garrytan 79092b22ea fix(evals): cut path variance at its measured sources ...

- gstack-qa-evidence capture prints startedAt/completedAt/durationMs and, for
  --deadline captures, remainingMs; the functional report takes durations from
  them. The section clock notice asks for one clock read up front instead of one
  after every checkpoint (QA runs spent 7-14% of tool calls on date -u).
- ship plan-completion: skip the audit dispatch when discovery already found no
  plan (the dispatch-vs-skip conflict produced an optional 60-100 s subagent).
- materialize/checkpoint validation errors state the expected schema, so a
  rejected annotations file is fixable in one call instead of blocking the phase.
- session-runner counts turns from the transcript when a run times out, so
  timeouts stop reporting 'turn 0'.

2026-09-30 15:59:58 +00:00

..

references

v1.81.0.0 feat: Aside is the browser gstack drives first; every browsing skill, the PDF/diagram renderer, and web research; the bundled browser stays the automatic fallback (#2810)

2026-09-06 08:54:25 -07:00

sections

fix(qa): define evidence.json where it is built, point the preparation gate at the next section, name measured command durations in the report template

2026-09-30 13:59:06 +00:00

templates

fix(evals): cut path variance at its measured sources

2026-09-30 15:59:58 +00:00

SKILL.md

fix(qa): number the qa value-bar questions from 1 and say reproduced bugs already answer the first two

2026-09-30 13:31:29 +00:00

SKILL.md.tmpl

v1.91.9.0 feat: test value bar in plan-eng-review, review, qa and ship, plus /test-audit (#2998)

2026-09-29 14:35:00 -07:00