Jannik/PaperClipAI
1
0 Fork 0
mirror of https://github.com/paperclipai/paperclip.git synced 2026-10-24 18:19:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

test(e2e): grow journal using small paced stream events

Browse Source 
Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed 2026-09-27 16:11:45 -05:00
1 parent 24e32444d2
commit 0a4693d06d
2 files changed
+6 -6
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/runner-e2e/README.md
+2 -2
View File
@@ -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,
tests/runner-e2e/catalog.ts
+4 -4
View File
@@ -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;