import { chatCatalogNativePhaseDeadline, chatCatalogNativePhaseIsTimely } from "../chat-catalog-contract.js"; import { expect } from "@playwright/test"; import { createHash } from "node:crypto"; import { writeFile } from "node:fs/promises"; import { inflateRawSync } from "node:zlib"; import { pollUntil } from "../api.js"; import { checks, type Entity } from "./internal-support.js"; import { busyRuntimeWorker, releaseRuntimeWorker } from "./runtime-busy-worker.js"; import { runtimeDefinition, runtimeObservation, observeRuntime, type RuntimeAgent } from "./runtime-support.js"; import type { IssueAttachment, IssueQueuedCommentQueue } from "../../../packages/shared/src/types/issue.js"; import type { IssueWorkProduct } from "../../../packages/shared/src/types/work-product.js"; const MAX_DELIVERABLE_BYTES = 262_144; /** Text of each stored or deflated entry in a zip deliverable, read from its central directory; [] when it is not a readable zip. */ export function zipEntryTexts(bytes: Buffer): string[] { try { const eocd = bytes.lastIndexOf(Buffer.from([0x50, 0x4b, 0x05, 0x06])); if (eocd < 0 || eocd + 22 > bytes.length) return []; const texts: string[] = []; let at = bytes.readUInt32LE(eocd + 16); for (let index = 0, count = bytes.readUInt16LE(eocd + 10); index < count && at + 46 <= bytes.length && bytes.readUInt32LE(at) === 0x02014b50; index++) { const method = bytes.readUInt16LE(at + 10), size = bytes.readUInt32LE(at + 20), local = bytes.readUInt32LE(at + 42); const start = local + 30 + bytes.readUInt16LE(local + 26) + bytes.readUInt16LE(local + 28), data = bytes.subarray(start, start + size); if (method === 0) texts.push(data.toString("utf8")); else if (method === 8) texts.push(inflateRawSync(data, { maxOutputLength: 4 * MAX_DELIVERABLE_BYTES }).toString("utf8")); at += 46 + bytes.readUInt16LE(at + 28) + bytes.readUInt16LE(at + 30) + bytes.readUInt16LE(at + 32); } return texts; } catch { return []; } } /** Find a message object with the exact comment id and body, descending into JSON nested as string values. */ function jsonCarriesComment(value: unknown, comment: { id: string; body: string }, depth = 0): boolean { if (depth > 6) return false; if (typeof value === "string") { const text = value.trim(); if (!/^[[{]/.test(text)) return false; try { return jsonCarriesComment(JSON.parse(text), comment, depth + 1); } catch { return false; } } if (Array.isArray(value)) return value.some(item => jsonCarriesComment(item, comment, depth + 1)); if (!value || typeof value !== "object") return false; const row = value as Record; return (row.id === comment.id && row.body === comment.body) || Object.values(row).some(item => jsonCarriesComment(item, comment, depth + 1)); } /** Native continuations embed new comments as JSON (an envelope may nest it again as a string), so a body with quotes or newlines appears escaped. */ export function promptCarriesComment(prompt: string | undefined, comment: { id: string; body: string }) { return typeof prompt === "string" && prompt.includes(comment.id) && (prompt.includes(comment.body) || prompt.includes(JSON.stringify(comment.body).slice(1, -1)) || jsonCarriesComment(prompt, comment)); } /** A task is named by its setup-assigned identifier (which chat links) or by a link to its page. */ export function replyNamesTask(reply: string, task: Entity) { const keys = [task.identifier, task.id].filter((key): key is string => !!key); return keys.some(key => new RegExp(`(? run.status === "succeeded") && o.runs.filter(run => run.agentId === (o.state.worker as Entity).id).length === 2, "The same saved requirement is consumed by one ordinary successor native turn after the real prior owner settles."); c.add("earlier-work-and-contact-result-retained", o.state.initialBriefRevisionRetained === true && (o.state.contactResultRevision === true || o.state.contactResultDeliverable === true) && o.tasks.length === 1 && o.tasks[0]?.id === task.id && o.tasks[0]?.assigneeAgentId === (o.state.worker as Entity).id && o.tasks[0]?.status === "done", "The original worker's saved brief revision remains inspectable and the successor saves an actual contact-section result on the same task, as a document revision or a registered deliverable."); return c.result(); } export const runtimeQueueCases = [runtimeDefinition("steering.queue-follow-up", busyRuntimeWorker, gradeQueuedFollowup, { oracleVersion: "paperclip.chat-catalog.runtime-queue.v3", sourceFiles: ["chat-catalog-domains/runtime-queue.ts", "chat-catalog-domains/runtime-busy-worker.ts", "chat-catalog-domains/runtime-support.ts", "chat-scenarios/steering.yaml"], expectedRunCount: 3, attemptTimeoutMs: 720_000, setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["lead-ready", "real-busy-worker", "worker-task-scope"] }, async verifySetup(ctx, state) { const c = checks(); const lead = await ctx.input.api.get(`/api/agents/${ctx.input.fixtures.agent.id}`); const worker = await ctx.input.api.get(`/api/agents/${(state.worker as Entity).id}`); const run = (await ctx.allRuns()).find(row => row.id === state.workerRunId); c.add("lead-ready", lead.lifecycleState === "ready" && ["active", "idle"].includes(lead.status ?? ""), "The actual controller is admitted normally."); c.add("real-busy-worker", worker.lifecycleState === "ready" && ["active", "running"].includes(worker.status ?? "") && run?.status === "running" && state.workerWasReallyWaiting === true, "Morgan is genuinely busy in a native tool wait, without a fabricated busy state."); c.add("worker-task-scope", run?.agentId === worker.id && run.companyId === ctx.input.fixtures.company.id && [run.contextSnapshot?.issueId, (run as typeof run & { nativeIssueId?: string })?.nativeIssueId].includes((state.task as Entity).id), "The actual active owner belongs to the exact task and company."); return c.result(); }, async act(ctx, state) { const phase = await pollUntil({ label: "Canonical follow-up saved while Morgan remains active", deadlineAt: chatCatalogNativePhaseDeadline(ctx, Date.now() + 150_000), load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns(), queue: await ctx.input.api.get(`/api/issues/${(state.task as Entity).id}/queued-comments`) }; }, accept: value => chatCatalogNativePhaseIsTimely(ctx) && (value.source?.conversationState === "waiting" && value.runs.length === 2 && value.runs.find(run => run.id === state.workerRunId)?.status === "running" && value.runs.some(run => run.agentId === ctx.input.fixtures.agent.id && run.status === "succeeded") && !!savedRequirement(value.queue, ctx.input.fixtures.agent.id)) }); const canonical = phase.runs.find(run => run.agentId === ctx.input.fixtures.agent.id)!; state.canonicalRunId = canonical.id; state.workerStatusAtReply = phase.runs.find(run => run.id === state.workerRunId)!.status; state.queuedAtReply = phase.queue; state.queryReply = (await observeRuntime(ctx, state)).reply; const source = ctx.input.page.url(), task = state.task as Entity; await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/issues/${task.identifier ?? task.id}`, { waitUntil: "domcontentloaded" }); const requirement = savedRequirement(phase.queue, ctx.input.fixtures.agent.id)!; await expect(ctx.input.page.getByTestId(`task-chat-queued-message-${requirement.comment.id}`)).toBeVisible(); await ctx.input.capture("actual-contact-followup-queue", "Contact requirement remains visibly queued behind real active work", "runtime-contact-queue.png"); await ctx.input.page.goto(source, { waitUntil: "domcontentloaded" }); const marker = `Original website brief ${ctx.input.nonce}`; state.briefMarker = marker; await writeFile((state.gate as { gate: string }).gate, `The human brief is now ready: save an initial task document with the exact reference ${marker}, then finish this current turn normally. Keep all prior user requirements queued by Paperclip intact for normal delivery; do not create tasks or external effects.`, "utf8"); const delivered = await pollUntil({ label: "Normal successor receives actual queued contact requirement", deadlineAt: Date.now() + 240_000, load: async () => ({ task: await ctx.input.api.get(`/api/issues/${task.id}`), runs: await ctx.allRuns(), queue: await ctx.input.api.get(`/api/issues/${task.id}/queued-comments`) }), accept: value => value.task.status === "done" && value.runs.length === 3 && value.runs.every(run => run.status === "succeeded") && value.queue.entries.length === 0, reject: value => value.runs.length > 3 || value.runs.some(run => ["failed", "cancelled", "timed_out"].includes(run.status)) ? "The single declared queued continuation failed or duplicated work" : undefined }); const successors = delivered.runs.filter(run => run.agentId === (state.worker as Entity).id && run.id !== state.workerRunId); const inputs = await Promise.all(successors.map(run => ctx.input.api.get<{ runnerProfileJson?: { nativeExecutionInput?: { task?: { prompt?: string } } } }>(`/api/heartbeat-runs/${run.id}`))); state.consumedCommentId = requirement.comment.id; state.consumingRunCount = successors.length; state.deliveryNativeInputBound = inputs.length === 1 && promptCarriesComment(inputs[0]?.runnerProfileJson?.nativeExecutionInput?.task?.prompt, requirement.comment); state.queueEmptyAfterDelivery = delivered.queue.entries.length === 0; }, async observe(ctx, state) { const o = await observeRuntime(ctx, state); state.initialBriefRevisionRetained = o.revisions.some(revision => revision.createdByRunId === state.workerRunId && (revision.body ?? "").includes(String(state.briefMarker))); const successorIds = o.runs.filter(run => run.agentId === (state.worker as Entity).id && run.id !== state.workerRunId).map(run => run.id); state.contactResultRevision = o.revisions.some(revision => successorIds.includes(revision.createdByRunId ?? "") && /contact/i.test(revision.body ?? "") && revision.createdByAgentId === (state.worker as Entity).id && o.documents.some(doc => doc.id === revision.documentId && doc.latestRevisionId === revision.id)); // A website build may be delivered as a registered file (often a zip) rather than a document; its file name is the model's, so read every successor deliverable's verified bytes. const taskId = (state.task as Entity).id; const [products, attachments] = await Promise.all([ctx.input.api.get(`/api/issues/${taskId}/work-products`), ctx.input.api.get(`/api/issues/${taskId}/attachments`)]); const delivered = attachments.filter(attachment => attachment.issueId === taskId && successorIds.includes(attachment.originatingRunId ?? "") && attachment.byteSize <= MAX_DELIVERABLE_BYTES && products.some(product => product.type === "artifact" && product.createdByRunId === attachment.originatingRunId && product.metadata?.attachmentId === attachment.id)); const texts: string[] = []; for (const attachment of delivered) { const bytes = await ctx.input.api.getAttachmentContent(attachment.id); if (bytes.length !== attachment.byteSize || createHash("sha256").update(bytes).digest("hex") !== attachment.sha256) continue; const entries = zipEntryTexts(bytes); texts.push(...(entries.length > 0 ? entries : [bytes.toString("utf8")])); } state.contactResultDeliverable = texts.some(text => /contact/i.test(text)); return o; }, async verifyResult(ctx, state) { const source = ctx.input.page.url(), task = state.task as Entity; await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/issues/${task.identifier ?? task.id}`, { waitUntil: "domcontentloaded" }); await ctx.input.page.reload({ waitUntil: "domcontentloaded" }); await expect(ctx.input.page.getByRole("heading", { name: task.title!, exact: true }).first()).toBeVisible(); await expect(ctx.input.page.getByTestId("task-chat-queued-messages")).toHaveCount(0); await ctx.input.page.goto(source, { waitUntil: "domcontentloaded" }); }, cleanup: async (_ctx, state) => releaseRuntimeWorker(state), })];