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'.
This commit is contained in:
garrytan committed 2026-09-30 15:59:58 +00:00
1 parent a8a32e3216
commit 79092b22ea
8 files changed
+36 -22

No files matched your search

+1 -1
View File
@@ -7,7 +7,7 @@
| Surfaces / scope | {API, CLI, job, worker, webhook; changed and adjacent contracts} |
| Runtime / native tools | {VERSIONS AND REPOSITORY-SUPPORTED COMMANDS} |
| Fixture ownership / destinations | {ISOLATED ROOT, STORES, DOWNSTREAM TARGETS} |
| Duration / stop reason | {MEASURED COMMAND DURATIONS, COMPLETE OR BOUND/BLOCKER} |
| Duration / stop reason | {CAPTURE durationMs TOTALS, COMPLETE OR BOUND/BLOCKER} |
## Contract outcomes