test: grow continuation journal through distinct tool invocations

Co-Authored-By: Paperclip <noreply@paperclip.ing>

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 50 KiB
-synthetic brief and 1024 paced KiB-sized chunks of command output through the real provider. Before the first browser follow-up,
+It reuses the three-turn warm workflow with 16 separate ordinary execution-tool calls, each printing a bounded 65 KB
+synthetic sample 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.test.ts

@@ -193,7 +193,7 @@ describe("runner E2E catalog", () => {
     expect(suite.expectedMatrixSize).toBe(1);
     expect(suite.profiles.map((profile) => profile.id)).toEqual(["runner-codex"]);
     expect(daytonaLargeJournalTask.flow).toBe("warm_three_turn");
-    expect(daytonaLargeJournalTask.buildPrompt("nonce")).toContain("range(1024)");
+    expect(daytonaLargeJournalTask.buildPrompt("nonce")).toContain("16 separate execution-tool calls");
     expect(daytonaLargeJournalTask.buildFollowupMessages!("nonce")).toEqual(daytonaWarmContinuityTask.buildFollowupMessages!("nonce"));
     expect(selectRunnerExecutions(parseRunnerSelectors(["--all"]))
       .some((cell) => cell.suite.id === suite.id)).toBe(false);

tests/runner-e2e/catalog.ts

@@ -880,13 +880,10 @@ 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 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)]'`,
+    "First exercise ordinary execution history with 16 separate execution-tool calls. In each call, run the Python command below exactly once. Issue the calls one by one. Do not combine them into a shell loop, script, parallel wrapper, or a single tool call: each command must be a separate ordinary execution-tool invocation. Keep a count from 1 through 16. The output is synthetic fixture data and needs no analysis.",
+    `python3 -c 'print("journal-continuity-" + "x" * 65000)'`,
+    "Wait for all 16 execution-tool calls to exit successfully. Do not redirect, suppress, or pipe their stdout. Then do the workspace task below and submit its completion report.",
     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(640),
-    "END SYNTHETIC REFERENCE SAMPLE",
   ].join("\n"),
 };
 
@@ -1073,13 +1070,13 @@ export const runnerSuites: readonly RunnerSuiteFixture[] = [
     id: "daytona-journal-continuity",
     label: "Daytona Large Journal Continuity",
     manualOnly: true,
-    description: "Continue the same native session after a browser-submitted large brief and real tool output grow its durable journal beyond 2 MiB.",
+    description: "Continue the same native session after a separate ordinary tool invocations and their output grow its durable journal beyond 2 MiB.",
     groups: ["daytona", "warm"],
     profiles: codexContinuityProfiles.filter((profile) => profile.id === "runner-codex"),
     environments: [daytonaWarmEnvironment],
     tasks: [daytonaLargeJournalTask],
     expectedMatrixSize: 1,
-    definitionMetadata: { version: 2, journalMinimumBytes: 2 * 1024 * 1024, briefBytes: 50 * 1024, outputChunks: 1024, scheduling: "explicit-only" },
+    definitionMetadata: { version: 3, journalMinimumBytes: 2 * 1024 * 1024, toolInvocations: 16, outputBytesPerInvocation: 65019, scheduling: "explicit-only" },
   },
 ] as const;