test: grow journal beyond continuity guard with bounded tool calls

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

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 16 separate ordinary execution-tool calls, each printing a bounded 65 KB
+It reuses the three-turn warm workflow with 80 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

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("16 separate execution-tool calls");
+    expect(daytonaLargeJournalTask.buildPrompt("nonce")).toContain("80 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

@@ -880,9 +880,9 @@ export const daytonaLargeJournalTask: RunnerTaskFixture = {
   label: "Large journal three-turn workspace continuity",
   buildTitle: (nonce) => `Runner E2E large journal continuity ${nonce}`,
   buildPrompt: (nonce) => [
-    "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.",
+    "First exercise ordinary execution history with 80 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 80. 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.",
+    "Wait for all 80 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),
   ].join("\n"),
 };
@@ -1076,7 +1076,7 @@ export const runnerSuites: readonly RunnerSuiteFixture[] = [
     environments: [daytonaWarmEnvironment],
     tasks: [daytonaLargeJournalTask],
     expectedMatrixSize: 1,
-    definitionMetadata: { version: 3, journalMinimumBytes: 2 * 1024 * 1024, toolInvocations: 16, outputBytesPerInvocation: 65019, scheduling: "explicit-only" },
+    definitionMetadata: { version: 3, journalMinimumBytes: 2 * 1024 * 1024, toolInvocations: 80, outputBytesPerInvocation: 65019, scheduling: "explicit-only" },
   },
 ] as const;