From 23cb7547659940ebf847ef83a0ccb74903a2cad3 Mon Sep 17 00:00:00 2001 From: garrytan Date: Sun, 4 Oct 2026 05:11:28 +0000 Subject: [PATCH] qa: the checkpoint note is created for browser runs and composed for functional ones Periodic census 37178143007: the qa-only workflow judge scored actionability 3.67 again; one sample read step 2's 'Create exploration-NNN.json' as applying to functional runs before reaching 'Functional: do not write this file'. The sentence now names both surfaces up front; byte-neutral (the browser line drops its restated clause), qa union 1.1098 under its 1.110 cap. One judge run on the repaired text: 3.67/4/4, pass. --- scripts/resolvers/qa.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/resolvers/qa.ts b/scripts/resolvers/qa.ts index 28a6f7685..3821d4273 100644 --- a/scripts/resolvers/qa.ts +++ b/scripts/resolvers/qa.ts @@ -110,7 +110,7 @@ ${reportOnly ? ` **Classify the last result before copying it.** For public or For actual secrets/private payloads, withhold those values and disclose the redaction and replay limits in the report. If no safe exact observation can be retained, stop the affected probe chain; never invent a substitute path, identity or state. -` : ''} **Publish before probing.** Create \`exploration-NNN.json\` in the probe directory, beside its deadline if bounded, with exactly four top-level fields: +` : ''} **Publish before probing.** Create (browser) or compose (functional) \`exploration-NNN.json\` in the probe directory, beside its deadline if bounded, with exactly four top-level fields: observationCommand: last completed probe's full outer command, including guard. observed: its exact decoded child JSON (no wrapper/extra keys), or its full non-JSON text. ${reportOnly ? ` For guarded text, copy the complete span between the guard's started and finished receipt lines. @@ -123,7 +123,7 @@ ${reportOnly ? ` For guarded text, copy the complete span between the guard's Withhold unsafe values, disclose limits and stop that chain. Check fields before publication. No drafts/placeholders or invented safe-path redactions; corrections cannot repair published notes. Functional: do not write this file; the next capture publishes it: \`bun EVIDENCE_TOOL capture PROBE_DIR NNN --deadline DEADLINE_FILE --after PREV --hypothesis 'why' -- CMD\` (PREV: the last complete capture's ID). EVIDENCE_TOOL supplies observed; never transcribe it. - Browser checkpoints use Write: create the four-field file yourself. + Browser checkpoints use Write. Wait for successful checkpoint publication before dispatch. Never backfill or overwrite notes. 3. Run that exact probe; DEADLINE_TOOL enforces the deadline when bounded.