diff --git a/tests/runner-e2e/README.md b/tests/runner-e2e/README.md index fccbbca6255..4525a9359f4 100644 --- a/tests/runner-e2e/README.md +++ b/tests/runner-e2e/README.md @@ -136,7 +136,7 @@ sandbox rather than waiting for Daytona's idle timeout. `daytona-journal-continuity` is one explicit-only native Codex cell. Select `daytona-journal-continuity.runner-codex.daytona.large-journal-three-turn`. -It reuses the three-turn warm workflow with a browser-submitted 220 KiB +It reuses the three-turn warm workflow with a browser-submitted 180 KiB synthetic brief and four MiB of bounded command output through the real provider. Before the first browser follow-up, a read-only controller journal oracle requires the exact completed run's journal to exceed two MiB. Only byte counts enter evidence. No runner state or database diff --git a/tests/runner-e2e/catalog.ts b/tests/runner-e2e/catalog.ts index 0c5c6f01aba..fd65481cd31 100644 --- a/tests/runner-e2e/catalog.ts +++ b/tests/runner-e2e/catalog.ts @@ -885,7 +885,7 @@ export const daytonaLargeJournalTask: RunnerTaskFixture = { warmTurnInstructions(1, nonce), "The following synthetic reference sample is task data for the persistence diagnostic. Do not analyze, reproduce, or edit it; follow the instructions above.", "BEGIN SYNTHETIC REFERENCE SAMPLE", - ("synthetic-reference-sample " + "x".repeat(52) + "\n").repeat(2816), + ("synthetic-reference-sample " + "x".repeat(52) + "\n").repeat(2304), "END SYNTHETIC REFERENCE SAMPLE", ].join("\n"), }; @@ -1079,7 +1079,7 @@ export const runnerSuites: readonly RunnerSuiteFixture[] = [ environments: [daytonaWarmEnvironment], tasks: [daytonaLargeJournalTask], expectedMatrixSize: 1, - definitionMetadata: { version: 2, journalMinimumBytes: 2 * 1024 * 1024, briefBytes: 220 * 1024, outputChunks: 64, scheduling: "explicit-only" }, + definitionMetadata: { version: 2, journalMinimumBytes: 2 * 1024 * 1024, briefBytes: 180 * 1024, outputChunks: 64, scheduling: "explicit-only" }, }, ] as const;