Jannik/PaperClipAI
1
0 Fork 0
mirror of https://github.com/paperclipai/paperclip.git synced 2026-10-25 02:26:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: use production instructions in chat hardening journeys

Browse Source 
Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed 2026-09-21 09:08:06 -05:00
1 parent 3d6140ca5d
commit f53f7a1386
2 files changed
+9 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/runner-e2e/catalog.ts
+3 -2
View File
@@ -950,11 +950,12 @@ export const runnerSuites: readonly RunnerSuiteFixture[] = [
id: "agent-chat-hardening", label: "Agent Chat Recovery and Coordination", manualOnly: true,
description: "Native chat startup cancellation, committed sends, hiring, grounded status, and remote continuity.",
groups: ["chat", "native"],
profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id)).map(defaultPermissionProfile),
profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
.map(profile => productionStoryProfile(defaultPermissionProfile(profile))),
environments: [localEnvironment, daytonaWarmEnvironment], tasks: chatHardeningTasks, expectedMatrixSize: 18,
excludedExecutionIds: ["runner-codex", "runner-acpx-claude"].flatMap(profile =>
["stop-startup-new-resume", "hire-delegate-reuse", "blocked-status-review"].map(task => `agent-chat-hardening.${profile}.daytona.${task}`)),
definitionMetadata: { version: 1, permissions: "production-defaults", grading: "durable-state-and-source-evidence", scheduling: "explicit-only" },
definitionMetadata: { version: 1, permissions: "production-defaults", instructions: "production", grading: "durable-state-and-source-evidence", scheduling: "explicit-only" },
},
...(process.env.PAPERCLIP_RUNNER_E2E_CONNECTION_REVIEWS === "1" ? [connectionReviewSuite] : []),
{
tests/runner-e2e/chat-hardening.test.ts
+6
View File
@@ -74,6 +74,12 @@ describe("agent chat hardening oracles", () => {
for (const cell of cells) {
expect(buildRunnerE2EProcessEnvironment({}, [cell]).PAPERCLIP_RUNNER_API_TOOLS_ENABLED).toBe(
["hire-delegate-reuse", "blocked-status-review"].includes(cell.task.id) ? "true" : undefined);
const config = cell.profile.buildAgent({ executionId: "fixture", workspacePath: "/workspace", environmentId: "local",
environmentFixtureId: "local", secretRefs: { [cell.profile.credential]: { type: "secret_ref", secretId: "secret", version: "latest" } } });
expect(config.role).toBe("ceo");
expect(JSON.stringify(config.instructionsBundle)).not.toMatch(/mark the task done|paperclip_finish|POST \/api|PUT \/api/);
expect(config.adapterConfig).not.toHaveProperty("codexPermissionMode");
expect(config.adapterConfig).not.toHaveProperty("acpxPermissionMode");
}
});
});