Files
PaperClipAI/tests/runner-e2e/paperclip-document.test.ts
DottaandPaperclip abd0b628ca Clarify legacy issue document delivery in the operational skill
Preserve the tiny hire manual and original assigned-skill case. Add a focused public document/revision/link oracle and explicit presence/absence provenance for a matched skill-only comparison.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-02 15:24:01 -05:00

53 lines
3.6 KiB
TypeScript

import { describe, expect, it } from "vitest";
import { contextIntegrityScenario, PAPERCLIP_DOCUMENT_CASE } from "./context-integrity-cases.js";
import { gradeContextIntegrity, type ContextIntegrityCheckpoint } from "./context-integrity-scoring.js";
function recording() {
const scenario = contextIntegrityScenario(PAPERCLIP_DOCUMENT_CASE, "probe");
const initial: ContextIntegrityCheckpoint = {
phase: "initial", issue: { id: "issue", identifier: "DOC-1", issuePrefix: "DOC", appOrigin: "https://paperclip.example", status: "in_progress" },
documents: [], comments: [], runs: [{ id: "run", status: "running" }],
assignedSkill: { key: scenario.skillKey, runtimeName: scenario.skillKey, versionId: "version", markdown: `Write ${scenario.marker}` },
skillRequestText: `${scenario.prompt}\nUse /${scenario.skillKey}`,
};
const final: ContextIntegrityCheckpoint = {
...initial, phase: "final", issue: { ...initial.issue, status: "done" },
documents: [{ key: "report", body: `Requested ${scenario.marker}`, latestRevisionId: "revision", latestRevisionNumber: 1 }],
comments: [{ authorAgentId: "agent", body: "Saved [report](/DOC/issues/DOC-1#document-report)." }],
runs: [{ id: "run", status: "succeeded" }],
};
return { scenario, initial, final };
}
describe("explicit Paperclip document delivery", () => {
it("checks the actual saved content, revision and exact document link", () => {
const { scenario, initial, final } = recording();
expect(gradeContextIntegrity({ ...scenario, checkpoints: [initial, final] }).every(row => row.passed)).toBe(true);
expect(scenario.prompt).toContain("Paperclip document");
expect(scenario.prompt).not.toContain(scenario.marker);
});
it.each(["https://paperclip.example/DOC/issues/DOC-1#document-report", "<https://paperclip.example/DOC/issues/DOC-1#document-report>"])("accepts the same-app document link %s", target => {
const { scenario, initial, final } = recording();
final.comments[0]!.body = `Saved [report](${target}).`;
expect(gradeContextIntegrity({ ...scenario, checkpoints: [initial, final] }).every(row => row.passed)).toBe(true);
});
it.each(["local-only", "missing-revision", "wrong-content", "local-link", "wrong-document-link", "other-app-link", "user-link-only"])(
"rejects plausible %s delivery", variant => {
const { scenario, initial, final } = recording();
if (variant === "local-only") { final.documents = []; final.comments[0]!.body = "Saved report.md in the workspace."; }
if (variant === "missing-revision") final.documents[0]!.latestRevisionId = null;
if (variant === "wrong-content") final.documents[0]!.body = "A different report";
if (variant === "local-link") final.comments[0]!.body = "Saved [report](./report.md).";
if (variant === "wrong-document-link") final.comments[0]!.body = "Saved [report](/DOC/issues/DOC-1#document-other).";
if (variant === "other-app-link") final.comments[0]!.body = "Saved [report](https://other.example/DOC/issues/DOC-1#document-report).";
if (variant === "user-link-only") { delete final.comments[0]!.authorAgentId; final.comments[0]!.authorUserId = "user"; }
expect(gradeContextIntegrity({ ...scenario, checkpoints: [initial, final] }).some(row => !row.passed)).toBe(true);
},
);
it("preserves the original ambiguous request and assigned output procedure", () => {
expect(contextIntegrityScenario("assigned-skill-explicit-invocation", "probe").prompt).toBe(
"Use the assigned Context integrity output skill for this task, then follow its instructions and finish the task. Do not create child tasks or unrelated deliverables.",
);
});
});