import { chatCatalogNativePhaseDeadline, chatCatalogNativePhaseIsTimely, chatCatalogNativePhaseRemainingBudget } from "../chat-catalog-contract.js"; import { expect, type Page } from "@playwright/test"; import type { Issue } from "../../../packages/shared/src/types/issue.js"; import type { HeartbeatRun } from "../../../packages/shared/src/types/heartbeat.js"; import { pollUntil } from "../api.js"; import { collectRunEvents } from "../run-observations.js"; import { readRecord, recordParams } from "./api-read-receipts.js"; import { sendChatMessage } from "../chat-flow.js"; import { checks, type Entity } from "./internal-support.js"; import { runtimeDefinition, runtimeWorker, runtimeObservation, observeRuntime } from "./runtime-support.js"; const record = (value: unknown): Record => value && typeof value === "object" && !Array.isArray(value) ? value as Record : {}; /** * Whether a run re-read Website's saved state (its own retained events, never reply text): a successful * call_api read of the task, its documents or the company task list, bound by its saved input digest * (bodies are redacted before saving), or a completed dedicated task tool whose output names the task. */ export function readTaskState(events: readonly Record[], task: { id?: string; identifier?: string | null; companyId?: string | null }) { const params = recordParams("id", task.id, task.identifier); if (task.id && readRecord(events, [ ...["GET /api/issues/{id}", "GET /api/issues/{id}/documents", "GET /api/issues/{id}/work-products"].map(operationId => ({ operationId, pathParams: params })), { operationId: "GET /api/companies/{companyId}/issues", pathParams: [...recordParams("companyId", task.companyId), undefined], paged: true }, ])) return true; return events.some(row => { const envelope = record(record(row.payload).prpEvent), payload = record(envelope.payload), output = typeof payload.output === "string" ? payload.output : ""; return row.eventType === "tool.execution.completed" && envelope.sourceKind === "runner" && payload.status === "completed" && ["paperclip_get_task", "paperclip_search_tasks"].includes(String(payload.name)) && [task.id, task.identifier].some(id => !!id && output.includes(id)); }); } async function chooseStatus(page: Page, status: "Todo" | "Done") { await page.getByRole("button", { name: /^Change status \(current:/ }).first().click(); await page.getByRole("button", { name: new RegExp(`^${status}(?:\\s*${status})?$`) }).filter({ visible: true }).first().click(); } type RunLike = { id: string; agentId?: string | null; status: string; contextSnapshot?: Record | null }; export function isBlockedInteractionRun(run: RunLike, task: { id: string }, design: { id: string }, workerId: string) { const context = run.contextSnapshot ?? {}; return run.agentId === workerId && run.status === "succeeded" && context.dependencyBlockedInteraction === true && context.issueId === task.id && Array.isArray(context.unresolvedBlockerIssueIds) && context.unresolvedBlockerIssueIds.includes(design.id); } export function gradeDesignDependency(value: unknown) { const c = checks(), o = runtimeObservation(value); c.add("actual-dependency-and-native-admission-evidence", !!o, "The saved dependency, real unfinished prerequisite and later eligible native result must be independently read."); if (!o) return c.result(); const s = o.state, task = s.task as Entity, design = s.design as Entity, waiting = s.waitingTask as Issue, finished = o.tasks.find(row => row.id === task.id); c.add("actual-first-class-blocker-saved", waiting?.id === task.id && waiting.companyId === o.companyId && waiting.assigneeAgentId === (s.worker as Entity).id && waiting.blockedBy?.length === 1 && waiting.blockedBy[0]?.id === design.id && s.designUnfinishedAtWait === true && o.activity.some(row => row.action === "issue.blockers_updated" && row.entityId === task.id && row.agentId === o.leadId && (row.details?.addedBlockedByIssueIds as string[] | undefined)?.includes(design.id)), "The CEO actually installs the Design edge on the intended Website task; a comment alone is insufficient."); const interactionIds = Array.isArray(s.preApprovalInteractionRunIds) ? s.preApprovalInteractionRunIds as string[] : []; const interactions = o.runs.filter(row => interactionIds.includes(row.id)), work = o.runs.filter(row => !interactionIds.includes(row.id)); c.add("blocked-ordinary-admission-and-usable-ui", s.blockerVisible === true && s.noWorkerBeforeApproval === true && s.attemptedBeforeApproval === true && [200, 422, 409].includes(Number(s.beforeApprovalStatus)) && s.noWebsiteResultBeforeApproval === true && interactions.length === interactionIds.length && interactions.every(row => isBlockedInteractionRun(row, task, design, (s.worker as Entity).id)), "Ordinary human start is attempted while Design is unfinished, but no Website work is admitted (a server-marked blocked-interaction reply to a comment is allowed) and nothing is saved on Website; the task UI exposes the exact blocker."); c.add("one-eligible-worker-after-real-human-approval", s.humanApprovedDesign === true && s.workerAdmissionAfterApproval === true && finished?.status === "done" && finished.assigneeAgentId === (s.worker as Entity).id && o.tasks.length === 2 && s.actualWebsiteResult === true && work.length === 3 && o.runs.every(row => row.status === "succeeded") && work.filter(row => row.agentId === (s.worker as Entity).id).length === 1, "After actual human Design completion clears the prerequisite, ordinary admission runs Morgan once and produces the genuine saved Website result."); // The saved edge, admission and document prove the outcome; a person reads the replies for meaning. c.add("later-own-phase-reports-actual-result", s.finalReplyAttributed === true && String(s.finalReply ?? "").trim().length > 0 && s.finalReadTaskState === true, "A declared factual human follow-up receives its own native reply, answered from a fresh product read of saved task state rather than a pre-approval response."); return c.result(); } export const runtimeDependencyCases = [runtimeDefinition("task-coordination.block-on-design", async ctx => { const worker = await runtimeWorker(ctx), root = `/api/companies/${ctx.input.fixtures.company.id}`, marker = `Approved website ${ctx.input.nonce}`; for (const scope of [{ scopeType: "company", scopeId: ctx.input.fixtures.company.id }, { scopeType: "agent", scopeId: worker.id }]) await ctx.input.api.post(`${root}/budgets/policies`, { ...scope, amount: 500, hardStopEnabled: true, isActive: true, unpricedUsagePolicy: "allow" }); const design = await ctx.input.api.post(`${root}/issues`, { title: "Design", status: "backlog", description: `A semantic HTML website with accessible labels. Await the actual human approval; reference ${marker}.` }); const task = await ctx.input.api.post(`${root}/issues`, { title: "Website", status: "backlog", assigneeAgentId: worker.id, description: `Implement the approved Design as a small website plan. Once eligible, read the actual Design task and save a task document with the exact reference ${marker}, accessible labels and a clear primary action, then finish normally. Do not deploy, create other tasks or invent approval.` }); return { worker, task, design, marker }; }, gradeDesignDependency, { expectedHumanMessageCount: 2, expectedRunCount: 4, minimumRunCount: 3, attemptTimeoutMs: 720_000, oracleVersion: "paperclip.chat-catalog.runtime.block-on-design.v9", sourceFiles: ["chat-catalog-domains/runtime-dependency.ts", "chat-catalog-domains/api-read-receipts.ts", "chat-catalog-domains/runtime-support.ts", "run-observations.ts", "chat-scenarios/task-coordination.yaml"], async act(ctx, state) { const workerId = (state.worker as Entity | undefined)?.id ?? "", websiteTask = state.task as Entity, gate = state.design as Entity; const settled = await pollUntil({ label: "Saved dependency and canonical reply before human approval", deadlineAt: chatCatalogNativePhaseDeadline(ctx, Date.now() + 150_000), load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns() }; }, accept: v => chatCatalogNativePhaseIsTimely(ctx) && v.source?.conversationState === "waiting" && v.runs.filter(row => row.agentId !== workerId).length === 1 && v.runs.every(row => row.status === "succeeded") && v.runs.filter(row => row.agentId === workerId).every(row => isBlockedInteractionRun(row, websiteTask, gate, workerId)), reject: v => v.runs.filter(row => row.agentId !== workerId).length > 1 || v.runs.some(row => ["failed", "cancelled", "timed_out"].includes(row.status)) || v.runs.some(row => row.agentId === workerId && !isBlockedInteractionRun(row, websiteTask, gate, workerId) && row.status !== "queued" && row.status !== "running") ? "Work was admitted on Website, or a pre-approval run failed or duplicated, before Design approval" : undefined }); state.preApprovalInteractionRunIds = settled.runs.filter(row => row.agentId === workerId).map(row => row.id); state.queryReply = (await observeRuntime(ctx, state)).reply; const source = ctx.input.page.url(), task = state.task as Entity, design = state.design as Entity, websiteRoot = `/api/issues/${task.id}`; state.waitingTask = await ctx.input.api.get(websiteRoot); state.designUnfinishedAtWait = (await ctx.input.api.get(`/api/issues/${design.id}`)).status !== "done"; // The scripted human checks the blocker in the task UI only after it is saved. Without the saved edge the UI // step can only time out on a missing row (gha-43088288923), which reads as a harness defect; stop with the cause. if (!(state.waitingTask as Issue).blockedBy?.some(row => row.id === design.id)) throw new Error("The CEO did not save Design as a blocker on Website before approval; a reply or comment alone does not hold the work"); await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/issues/${task.identifier ?? task.id}`, { waitUntil: "domcontentloaded" }); // A backlog task shows its blockers in the properties panel; the thread's blocker banner appears only once it is Blocked. const blockedBy = ctx.input.page.locator('[data-property-row]:not([inert] *):not([aria-hidden="true"] *)') .filter({ has: ctx.input.page.locator('[data-property-label="Blocked by"]') }).filter({ visible: true }); // Open the panel through the control the page renders ("Show properties"); a fresh panel shows its tab // launcher first, from which a person chooses Properties. const panel = ctx.input.page.getByRole("button", { name: /^(Show properties|Properties|Toggle side panel)$/ }).filter({ visible: true }).first(); const propertiesTab = ctx.input.page.getByRole("option", { name: /^Properties/ }).filter({ visible: true }).first(); await expect.poll(async () => await blockedBy.isVisible() || await propertiesTab.isVisible() || await panel.isVisible()).toBe(true); if (!await blockedBy.isVisible() && !await propertiesTab.isVisible()) await panel.click(); await expect.poll(async () => await blockedBy.isVisible() || await propertiesTab.isVisible()).toBe(true); if (!await blockedBy.isVisible()) await propertiesTab.click(); await expect(blockedBy.getByText(design.identifier ?? "Design").first()).toBeVisible(); state.blockerVisible = true; const websitePaths = [websiteRoot, ...(task.identifier ? [`/api/issues/${task.identifier}`] : [])]; const pending = ctx.input.page.waitForResponse(row => row.request().method() === "PATCH" && websitePaths.includes(new URL(row.url()).pathname)); await chooseStatus(ctx.input.page, "Todo"); state.beforeApprovalStatus = (await pending).status(); state.attemptedBeforeApproval = true; // Reload and independent reads observe the real admission gate, rather // than setting a run's blocked status or pretending the worker executed. await ctx.input.page.reload({ waitUntil: "domcontentloaded" }); state.noWorkerBeforeApproval = (await ctx.allRuns()).every(row => row.agentId !== workerId || (state.preApprovalInteractionRunIds as string[]).includes(row.id)); state.noWebsiteResultBeforeApproval = (await ctx.input.api.get(`${websiteRoot}/documents`)).length === 0 && !["in_progress", "in_review", "done"].includes((await ctx.input.api.get(websiteRoot)).status); await ctx.input.capture("actual-design-dependency-wait", "Website retains its actual Design blocker before human approval", "runtime-design-blocker.png"); await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/issues/${design.identifier ?? design.id}`, { waitUntil: "domcontentloaded" }); await chooseStatus(ctx.input.page, "Done"); const approved = await pollUntil({ label: "Real human Design completion", deadlineAt: Date.now() + 20_000, load: () => ctx.input.api.get(`/api/issues/${design.id}`), accept: row => row.status === "done" }); state.humanApprovedDesign = approved.status === "done"; state.designApprovedAt = Date.now(); const website = await ctx.input.api.get(websiteRoot); if (website.status === "backlog") { await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/issues/${task.identifier ?? task.id}`, { waitUntil: "domcontentloaded" }); await chooseStatus(ctx.input.page, "Todo"); } const interactionCount = (state.preApprovalInteractionRunIds as string[]).length; const result = await pollUntil({ label: "One ordinary Website admission after Design approval", deadlineAt: chatCatalogNativePhaseDeadline(ctx, Date.now() + 240_000), load: async () => ({ runs: await ctx.allRuns(), task: await ctx.input.api.get(websiteRoot) }), accept: v => chatCatalogNativePhaseIsTimely(ctx) && v.runs.length === 2 + interactionCount && v.runs.every(row => row.status === "succeeded") && v.task.status === "done", reject: v => v.runs.length > 2 + interactionCount || v.runs.some(row => ["failed", "cancelled", "timed_out"].includes(row.status)) ? "Eligible Website admission failed or duplicated native work" : undefined }); const worker = result.runs.find(row => row.agentId === workerId && !(state.preApprovalInteractionRunIds as string[]).includes(row.id))!; const designActivity = await ctx.input.api.get(`/api/issues/${design.id}/activity`); const approval = designActivity.find(row => row.action === "issue.updated" && row.actorType === "user" && row.details?.status === "done"); const workerDetail = await ctx.input.api.get(`/api/heartbeat-runs/${worker.id}`); state.workerAdmissionAfterApproval = !!approval && Date.parse(String(workerDetail.createdAt)) >= Date.parse(approval.createdAt ?? ""); state.websiteRunId = worker.id; await ctx.input.page.goto(source, { waitUntil: "domcontentloaded" }); const followup = `I approved Design ${design.identifier ?? design.id}. What is the actual result of Website ${task.identifier ?? task.id} now?`; await sendChatMessage(ctx.input.page, followup, chatCatalogNativePhaseRemainingBudget(ctx)); const final = await pollUntil({ label: "Own native reply reporting actual post-approval Website outcome", deadlineAt: chatCatalogNativePhaseDeadline(ctx, Date.now() + 150_000), load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns() }; }, accept: v => chatCatalogNativePhaseIsTimely(ctx) && v.source?.conversationState === "waiting" && v.runs.length === 3 + interactionCount && v.runs.every(row => row.status === "succeeded") }); const run = final.runs.find(row => !result.runs.some(prior => prior.id === row.id))!, comments = await ctx.input.api.get(`/api/issues/${ctx.issue()!.id}/comments?order=asc`); const human = comments.filter(row => !row.authorAgentId && row.body === followup), replies = comments.filter(row => row.authorAgentId === ctx.input.fixtures.agent.id && row.createdByRunId === run.id); const detail = await ctx.input.api.get<{ runnerProfileJson?: { nativeExecutionInput?: { task?: { prompt?: string } } } }>(`/api/heartbeat-runs/${run.id}`); state.finalReplyAttributed = human.length === 1 && replies.length > 0 && detail.runnerProfileJson?.nativeExecutionInput?.task?.prompt?.includes(human[0]!.id) === true; state.finalReply = replies.map(row => row.body).join("\n"); state.finalReadTaskState = readTaskState(await collectRunEvents>(afterSeq => ctx.input.api.get(`/api/heartbeat-runs/${run.id}/events?afterSeq=${afterSeq}&limit=1000`)), task); }, async observe(ctx, state) { const o = await observeRuntime(ctx, state); state.actualWebsiteResult = o.revisions.some(row => row.createdByRunId === state.websiteRunId && row.createdByAgentId === (state.worker as Entity).id && (row.body ?? "").includes(String(state.marker)) && o.documents.some(doc => doc.id === row.documentId && doc.latestRevisionId === row.id)); return o; }, async verifyResult(ctx, state) { const source = ctx.input.page.url(), task = state.task as Entity; await ctx.input.page.goto(`/${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: "Website", exact: true }).first()).toBeVisible(); await expect(ctx.input.page.getByRole("button", { name: "Change status (current: Done)", exact: true }).first()).toBeVisible(); await ctx.input.capture("actual-approved-website-result", "The same Website task completed after its real Design prerequisite", "runtime-approved-website.png"); await ctx.input.page.goto(source, { waitUntil: "domcontentloaded" }); }, })];