mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-03 01:46:55 +02:00
test: attribute quoted prior-record field lists, state the judge reason bound in its schema, move split-overflow to marathon
Census 36629958451 reds: - outside-plan-disabled-no-fallback: the model quoted the pre-existing record as a parenthesized field list with its exact timestamp; attribution now requires that exact timestamp and the record's own field values. - plan-devex-peer-comparison-classification: the judge correctly returned missing but wrote a 1069-character reason, voiding the judgment; structured outputs cannot enforce maxLength, so the bound is stated on the field. - plan-ceo-split-overflow ran 504-1188 s as one PTY flow and set the periodic lane's wall clock; it now runs weekly in the marathon lane.
This commit is contained in:
1 parent
f63e1fb7cb
commit
bf4667146c
6 files changed
+52
-8
No files matched your search
@@ -1,5 +1,5 @@
|
||||
/**
|
||||
* /plan-ceo-review split-overflow regression (periodic, paid, real-PTY).
|
||||
* /plan-ceo-review split-overflow regression (marathon, paid, real-PTY).
|
||||
*
|
||||
* Catches the original failure mode the user complained about: when the
|
||||
* agent has 5+ options for ONE conceptual decision, it must split into N
|
||||
@@ -50,7 +50,7 @@ import { ceoSplitDecisionFingerprints, isCeoSplitCandidateCall, isCeoSplitCollec
|
||||
import { CEO_SCOPE_CANDIDATES } from './helpers/plan-review-cases';
|
||||
import { evaluatePlanReviewDecisions } from './helpers/plan-review-decisions';
|
||||
|
||||
const describeE2E = describeE2ETier('periodic');
|
||||
const describeE2E = describeE2ETier('marathon');
|
||||
|
||||
const N = 5;
|
||||
const FLOOR = N - 1; // 4 — must fire at least one AUQ per non-dropped option
|
||||
@@ -60,7 +60,7 @@ const FLOOR = N - 1; // 4 — must fire at least one AUQ per non-dropped option
|
||||
* EVALS_JOBS>1, sibling worktrees) never share one /tmp artifact. */
|
||||
const FIXTURE_PLAN_PATH = '/tmp/gstack-test-plan-ceo-split-overflow.md';
|
||||
|
||||
describeE2E('/plan-ceo-review split-overflow regression (periodic)', () => {
|
||||
describeE2E('/plan-ceo-review split-overflow regression (marathon)', () => {
|
||||
test(
|
||||
`5-option scope decision emits >= ${FLOOR} review-phase AskUserQuestions (no dropping)`,
|
||||
async () => {
|
||||
|
||||
Reference in new issue
Block a user