mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-05 03:51:54 +01:00
Evaluate actual chat brief delegation and worker attachment access
This commit is contained in:
1 parent
0d22c3cc1d
commit
1be8e44467
3 files changed
+126
No files matched your search
@@ -0,0 +1,96 @@
|
||||
import { createHash } from "node:crypto";
|
||||
import { expect } from "@playwright/test";
|
||||
import type { ChatCatalogCase, ChatCatalogContext } from "../chat-catalog-contract.js";
|
||||
import type { ChatQueryAttachmentReceipt } from "../chat-query-attachments.js";
|
||||
import { pollUntil } from "../api.js";
|
||||
import { openStandingChat } from "./identity-support.js";
|
||||
import { fixtureWorker, makeDefinition } from "./internal-definition.js";
|
||||
import { checks, entity, hasLink, observation, observeInternal, type Entity, type InternalObservation } from "./internal-support.js";
|
||||
|
||||
interface BriefObservation extends InternalObservation {
|
||||
sourceId?: string; originalBytesHash: string; sourceAttachments: ChatQueryAttachmentReceipt[];
|
||||
workAttachments: ChatQueryAttachmentReceipt[]; workDocuments: Entity[];
|
||||
workerTaskStatus?: number; workerDownloadStatus?: number; workerDownloadedHash?: string; durablePath?: string;
|
||||
}
|
||||
const hash = (bytes: Uint8Array) => createHash("sha256").update(bytes).digest("hex");
|
||||
export function gradeAttachmentBrief(value: unknown) {
|
||||
const c = checks(); const o = observation(value) as BriefObservation | undefined;
|
||||
c.add("independent-upload-and-worker-evidence", !!o && Array.isArray(o.sourceAttachments) && Array.isArray(o.workAttachments) && Array.isArray(o.workDocuments),
|
||||
"The original UI upload, actual work context and independently authenticated worker download are required.");
|
||||
if (!o || !Array.isArray(o.sourceAttachments) || !Array.isArray(o.workAttachments) || !Array.isArray(o.workDocuments)) return c.result();
|
||||
const receipt = o.state.briefAttachment as ChatQueryAttachmentReceipt | undefined;
|
||||
const worker = entity(o.state, "worker"); const work = o.tasks.filter(row => row.id !== o.sourceId); const saved = work[0];
|
||||
c.add("actual-human-upload-retained", !!receipt && receipt.companyId === o.companyId && o.sourceAttachments.some(row => row.id === receipt.id && row.issueId === o.sourceId && row.companyId === o.companyId
|
||||
&& row.createdByUserId === receipt.createdByUserId && row.createdByAgentId == null && row.issueCommentId && row.sha256 === o.state.briefHash)
|
||||
&& o.originalBytesHash === o.state.briefHash, "The original signed-in person's uploaded brief and its exact bytes remain attached to the actual source human comment.");
|
||||
c.add("one-contextual-ordinary-work-task", work.length === 1 && !!saved && saved.companyId === o.companyId && saved.assigneeAgentId === worker.id
|
||||
&& /\b(?:website|landing.page|web page)\b/i.test(`${saved.title} ${saved.description ?? ""}`)
|
||||
&& o.activity.some(row => row.action === "issue.created" && row.entityId === saved.id && row.agentId === o.leadId)
|
||||
&& hasLink(o, "issues", saved), "One actual CEO-created website task is delegated to the intended Morgan and linked in chat.");
|
||||
const context = `${saved?.description ?? ""}\n${o.workDocuments.map(row => row.body ?? "").join("\n")}`;
|
||||
const copied = o.workAttachments.some(row => row.issueId === saved?.id && row.companyId === o.companyId && row.sha256 === o.state.briefHash
|
||||
&& o.durablePath === row.contentPath);
|
||||
const originalReference = !!receipt && context.includes(receipt.contentPath) && o.durablePath === receipt.contentPath;
|
||||
c.add("durable-brief-in-work-context", copied || originalReference,
|
||||
"The delegated task owns an exact-byte copy or a durable actual attachment reference; an unavailable filename or source-chat-only attachment fails.");
|
||||
c.add("morgan-can-read-the-real-brief", o.workerTaskStatus === 200 && o.workerDownloadStatus === 200 && o.workerDownloadedHash === o.state.briefHash,
|
||||
"An independent real Morgan bearer reads the work task and downloads the actual referenced brief bytes from its authorized context.");
|
||||
const runs = saved ? o.runs.filter(row => row.contextSnapshot?.issueId === saved.id || row.contextSnapshot?.taskId === saved.id) : [];
|
||||
c.add("separate-real-worker-admission", runs.length === 1 && runs[0]?.agentId === worker.id && ["queued", "running", "succeeded"].includes(runs[0]?.status ?? ""),
|
||||
"Morgan's real admitted run belongs to the new work task, separate from the source conversation.");
|
||||
return c.result();
|
||||
}
|
||||
async function workerReads(ctx: ChatCatalogContext, workerId: string, taskId: string, path: string | undefined) {
|
||||
if (!ctx.input.privateSecrets) throw new Error("Worker brief probe requires private secret redaction");
|
||||
const key = await ctx.input.api.postSensitive<{ id: string; token: string }>(`/api/agents/${workerId}/keys`, { name: "delegated-brief-read-control" });
|
||||
ctx.input.privateSecrets.push(key.token);
|
||||
const get = (value: string) => {
|
||||
const url = new URL(value, ctx.input.api.baseURL);
|
||||
if (url.origin !== ctx.input.api.baseURL || !/^\/api\/(?:issues|attachments)\//.test(url.pathname)) throw new Error("Worker brief read escaped isolated resources");
|
||||
return fetch(url, { redirect: "error", signal: AbortSignal.timeout(15_000), headers: { Authorization: `Bearer ${key.token}` } });
|
||||
};
|
||||
try {
|
||||
const taskRead = await get(`/api/issues/${taskId}`); const workerTaskStatus = taskRead.status; await taskRead.body?.cancel();
|
||||
if (!path) return { workerTaskStatus };
|
||||
const response = await get(path); const workerDownloadStatus = response.status;
|
||||
if (!response.ok) { await response.body?.cancel(); return { workerTaskStatus, workerDownloadStatus }; }
|
||||
const bytes = new Uint8Array(await response.arrayBuffer());
|
||||
if (bytes.byteLength > 65_536) throw new Error("Delegated brief unexpectedly exceeds its fixture size bound");
|
||||
return { workerTaskStatus, workerDownloadStatus, workerDownloadedHash: hash(bytes) };
|
||||
} finally { await ctx.input.api.delete(`/api/agents/${workerId}/keys/${key.id}`); }
|
||||
}
|
||||
const base = makeDefinition("tasks.attachment-brief", async ctx => {
|
||||
const worker = await fixtureWorker(ctx); const source = await openStandingChat(ctx);
|
||||
const briefBody = `# Acorn Field Notes\nBuild a simple accessible website for small research teams.\nUse headline: Research without the busywork.\nOffer early signup with invitation code ORCHID-${ctx.input.nonce}.\n`;
|
||||
const filename = "website-brief.md";
|
||||
await ctx.input.page.locator('input[type="file"]').first().setInputFiles({ name: filename, mimeType: "text/markdown", buffer: Buffer.from(briefBody) });
|
||||
const uploaded = await pollUntil({ label: "Actual human chat brief upload", deadlineAt: Date.now() + 30_000,
|
||||
load: () => ctx.input.api.get<ChatQueryAttachmentReceipt[]>(`/api/issues/${source.id}/attachments`),
|
||||
accept: rows => rows.filter(row => row.originalFilename === filename).length === 1 });
|
||||
const receipt = uploaded.find(row => row.originalFilename === filename)!;
|
||||
await expect(ctx.input.page.getByTestId("task-chat-composer-attachments")).toContainText(filename);
|
||||
await expect(ctx.input.page.getByTestId("task-chat-composer-attachments")).not.toContainText("Uploading");
|
||||
return { worker, sourceId: source.id, briefAttachment: receipt, briefHash: hash(Buffer.from(briefBody)) };
|
||||
}, gradeAttachmentBrief);
|
||||
export const taskAttachmentCases: readonly ChatCatalogCase[] = [{ ...base, authentication: "human-session",
|
||||
queryAttachments: [{ stateKey: "briefAttachment", filename: "website-brief.md" }], expectedRunCount: 3, minimumRunCount: 2,
|
||||
runPolicy: { kind: "source-settled-with-active-work", maximumActiveWorkerRuns: 1 },
|
||||
sourceFiles: [...base.sourceFiles, "chat-catalog-domains/internal-task-attachment.ts", "chat-catalog-domains/identity-support.ts", "chat-query-attachments.ts"],
|
||||
async observe(ctx, state): Promise<BriefObservation> {
|
||||
const o = await observeInternal(ctx, state); const source = ctx.issue();
|
||||
const sourceAttachments = source ? await ctx.input.api.get<ChatQueryAttachmentReceipt[]>(`/api/issues/${source.id}/attachments`) : [];
|
||||
const receipt = state.briefAttachment as ChatQueryAttachmentReceipt;
|
||||
const originalBytesHash = hash(await ctx.input.api.getAttachmentContent(receipt.id));
|
||||
const saved = o.tasks.filter(row => row.id !== source?.id)[0]; const workAttachments: ChatQueryAttachmentReceipt[] = []; const workDocuments: Entity[] = [];
|
||||
if (saved) {
|
||||
workAttachments.push(...await ctx.input.api.get<ChatQueryAttachmentReceipt[]>(`/api/issues/${saved.id}/attachments`));
|
||||
for (const summary of await ctx.input.api.get<Entity[]>(`/api/issues/${saved.id}/documents`))
|
||||
workDocuments.push(await ctx.input.api.get<Entity>(`/api/issues/${saved.id}/documents/${encodeURIComponent(summary.key!)}`));
|
||||
}
|
||||
const context = `${saved?.description ?? ""}\n${workDocuments.map(row => row.body ?? "").join("\n")}`;
|
||||
const durablePath = workAttachments.find(row => row.sha256 === state.briefHash)?.contentPath
|
||||
?? (context.includes(receipt.contentPath) ? receipt.contentPath : undefined);
|
||||
const reads = saved ? await workerReads(ctx, entity(state, "worker").id, saved.id, durablePath) : {};
|
||||
return { ...o, sourceId: source?.id, sourceAttachments, originalBytesHash, workAttachments, workDocuments, durablePath, ...reads };
|
||||
},
|
||||
}];
|
||||
@@ -1,6 +1,7 @@
|
||||
import { delegatedTaskCases } from "./internal-task-creation.js";
|
||||
import { taskPrivacyCases } from "./internal-privacy.js";
|
||||
import { taskInventoryCases } from "./internal-task-inventory.js";
|
||||
import { taskAttachmentCases } from "./internal-task-attachment.js";
|
||||
import type { ChatCatalogCase } from "../chat-catalog-contract.js";
|
||||
import { project, task, goal, putDocument, entity, observation, checks, hasLink, sameTask, type Entity } from "./internal-support.js";
|
||||
import { makeDefinition, retryDefinition, fixtureWorker } from "./internal-definition.js";
|
||||
@@ -60,6 +61,7 @@ export const tasksCases: readonly ChatCatalogCase[] = [
|
||||
...delegatedTaskCases,
|
||||
...taskPrivacyCases,
|
||||
...taskInventoryCases,
|
||||
...taskAttachmentCases,
|
||||
ambiguousTask(),
|
||||
define("tasks.edit-properties", async ctx => {
|
||||
const p = await project(ctx); const worker = await fixtureWorker(ctx);
|
||||
|
||||
@@ -15,6 +15,17 @@ function event(action: string, entityId: string, details?: Record<string, unknow
|
||||
function valid(scenario: string): InternalObservation {
|
||||
const o = base(scenario);
|
||||
switch (scenario) {
|
||||
case "tasks.attachment-brief": {
|
||||
const briefHash = "a".repeat(64); const receipt = { id: "original", companyId: "company", issueId: "chat", issueCommentId: "human-comment",
|
||||
createdByUserId: "person", createdByAgentId: null, sha256: briefHash, contentPath: "/api/attachments/original/content" };
|
||||
o.state = { worker: { id: "morgan" }, briefAttachment: receipt, briefHash };
|
||||
o.tasks[0] = { ...o.tasks[0]!, title: "Build website from attached brief", assigneeAgentId: "morgan" };
|
||||
o.activity = [event("issue.created", "task")];
|
||||
o.runs.push({ id: "worker", companyId: "company", agentId: "morgan", status: "running", contextSnapshot: { issueId: "task" } });
|
||||
Object.assign(o, { sourceId: "chat", sourceAttachments: [receipt], originalBytesHash: briefHash,
|
||||
workAttachments: [{ ...receipt, id: "copy", issueId: "task", contentPath: "/api/attachments/copy/content" }], workDocuments: [],
|
||||
durablePath: "/api/attachments/copy/content", workerTaskStatus: 200, workerDownloadStatus: 200, workerDownloadedHash: briefHash }); break;
|
||||
}
|
||||
case "projects.add-repository":
|
||||
case "projects.replace-repository": {
|
||||
const adding = scenario === "projects.add-repository";
|
||||
@@ -164,6 +175,7 @@ function valid(scenario: string): InternalObservation {
|
||||
return o;
|
||||
}
|
||||
const corrupt: Record<string, (o: InternalObservation) => void> = {
|
||||
"tasks.attachment-brief": o => { Object.assign(o, { workerDownloadStatus: 403 }); },
|
||||
"projects.add-repository": o => { Object.assign(o, { repositoryProject: { ...o.projects[0], workspaces: [{ id: "wrong", repoUrl: "https://github.com/acorn/unapproved" }] } }); },
|
||||
"projects.replace-repository": o => { (o.state.beforeOwnerReplacement as { agentStatus: number }).agentStatus = 200; },
|
||||
"tasks.organize-open-work": o => { o.reply = o.reply.replace("## Unassigned", "## Morgan"); },
|
||||
@@ -444,3 +456,19 @@ describe("repository fixture prerequisites and readback", () => {
|
||||
expect(gradeInternal(o).passed).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("delegated attachment context calibration", () => {
|
||||
it("rejects a source-only brief even when the original human download works", () => {
|
||||
const o = valid("tasks.attachment-brief"); Object.assign(o, { workAttachments: [], durablePath: undefined });
|
||||
expect(gradeInternal(o).passed).toBe(false);
|
||||
});
|
||||
it("accepts a real durable original attachment reference that Morgan can independently retrieve", () => {
|
||||
const o = valid("tasks.attachment-brief"); o.tasks[0]!.description = "Use [the attached brief](/api/attachments/original/content).";
|
||||
Object.assign(o, { workAttachments: [], durablePath: "/api/attachments/original/content" });
|
||||
expect(gradeInternal(o).passed).toBe(true);
|
||||
});
|
||||
it("rejects stale bytes under an available copied filename", () => {
|
||||
const o = valid("tasks.attachment-brief"); Object.assign(o, { workerDownloadedHash: "b".repeat(64) });
|
||||
expect(gradeInternal(o).passed).toBe(false);
|
||||
});
|
||||
});
|
||||
Reference in new issue
Block a user