From 0a4693d06d18fc002f46a6f173c8e1cf74cb6768 Mon Sep 17 00:00:00 2001 From: Dotta Date: Sun, 27 Sep 2026 16:11:45 -0500 Subject: [PATCH] test(e2e): grow journal using small paced stream events Co-Authored-By: Paperclip --- tests/runner-e2e/README.md | 4 ++-- tests/runner-e2e/catalog.ts | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tests/runner-e2e/README.md b/tests/runner-e2e/README.md index 4525a9359f4..c9cf26e2abf 100644 --- a/tests/runner-e2e/README.md +++ b/tests/runner-e2e/README.md @@ -136,8 +136,8 @@ 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 180 KiB -synthetic brief and four MiB of bounded command output through the real provider. Before the first browser follow-up, +It reuses the three-turn warm workflow with a browser-submitted 120 KiB +synthetic brief and 1024 paced KiB-sized chunks of 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 is injected or modified. The usual workspace, sandbox, provider, process, diff --git a/tests/runner-e2e/catalog.ts b/tests/runner-e2e/catalog.ts index fd65481cd31..2fba1b81680 100644 --- a/tests/runner-e2e/catalog.ts +++ b/tests/runner-e2e/catalog.ts @@ -880,12 +880,12 @@ export const daytonaLargeJournalTask: RunnerTaskFixture = { label: "Large journal three-turn workspace continuity", buildTitle: (nonce) => `Runner E2E large journal continuity ${nonce}`, buildPrompt: (nonce) => [ - "First exercise ordinary command-output streaming with this bounded diagnostic. Execute this Python command exactly once, allowing it to print all 64 chunks. Do not redirect, suppress, pipe, or summarize its stdout; the transport must receive the output. The repeated text is synthetic fixture data and needs no analysis. Wait for the command to exit successfully before continuing.", - `python3 -c 'import sys,time; [(sys.stdout.write("journal-continuity-" + "x" * 65500 + "\\n"), sys.stdout.flush(), time.sleep(0.05)) for _ in range(64)]'`, + "First exercise ordinary command-output streaming with this bounded diagnostic. Execute this Python command exactly once, allowing it to print all 1024 chunks. Do not redirect, suppress, pipe, or summarize its stdout; the transport must receive the output. The repeated text is synthetic fixture data and needs no analysis. Wait for the command to exit successfully before continuing.", + `python3 -c 'import sys,time; [(sys.stdout.write("journal-continuity-" + "x" * 1000 + "\\n"), sys.stdout.flush(), time.sleep(0.05)) for _ in range(1024)]'`, 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(2304), + ("synthetic-reference-sample " + "x".repeat(52) + "\n").repeat(1536), "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: 180 * 1024, outputChunks: 64, scheduling: "explicit-only" }, + definitionMetadata: { version: 2, journalMinimumBytes: 2 * 1024 * 1024, briefBytes: 120 * 1024, outputChunks: 1024, scheduling: "explicit-only" }, }, ] as const;