mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-17 21:34:48 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - The chat eval catalog checks real chat journeys against saved product state > - Full cohort 12 (OpenCode with `openrouter/deepseek/deepseek-v4.1-flash-1017`) failed three cases where the agent did the correct thing > - In each case the harness, not the product, broke the journey: it left a page too early, could not answer a choice card, or pressed keys faster than the drag library listens > - A harness that breaks the journey cannot measure the product > - This pull request makes the harness act like a person in these three journeys, counts a verified card choice as a human action, and keeps each check able to fail a broken product > - The benefit is that these three cases measure the product again ## Linked Issues or Issue Description **What happened?** In full cohort 12, three cases failed for harness reasons: - `agents.choose-primary`: the CEO answered correctly. The harness clicked the crown and confirmed. Then it waited for "My primary agent" with `.first()`. The sidebar already showed the CEO's crown, so this wait passed at once. The harness then navigated away before the browser sent `PUT /primary-agent/me`. The server log has no PUT. The read-back still showed the CEO. - `tasks.ambiguous-task`: the CEO changed nothing and asked a correct question card. The card linked both tasks and offered "COM-1 (Launch project)", "COM-2 (Experiments project)" and "Both tasks". The harness could only answer with a text box or an "Other" option. It threw "The linked question has no supported explicit clarification input". - `steering.edit-queued-message`: the person's edit saved (PATCH 200). The keyboard reorder (Space, ArrowUp, Space) sent no `PUT /queued-comments/order` in 2 gestures. Cohort 9 had the same failure. **Expected behavior** Each journey completes as a person does it, and the oracle grades the saved result. **Steps to reproduce** 1. Use master `f7ddab8e94`. 2. Run the Runner Full-Stack E2E workflow with `all=false` and the three case ids `chat-features.runner-opencode.local.<case>`. 3. Read each case's `playwright.log` and `server.log`. **Additional context** - Primary agent: the crown fills at once (optimistic update) and the save starts on confirm. The mutation lives in the app-level `PrimaryAgentProvider`, so in-app navigation does not cancel it. In the failed run the confirm and the full-page `goto` happened within the same second, and the PUT never reached the server. Only a full page load in the first milliseconds can lose the save. A person cannot do that in practice, so this is not a product bug. No UI change. - Keyboard reorder: dnd-kit's `KeyboardSensor` starts the drag on Space, adds its keydown listener in a `setTimeout`, and `sortableKeyboardCoordinates` ignores arrows until the rows are measured on a later render. Keys pressed back to back can arrive before this. In the production Storybook story (headless Chromium), back-to-back `locator.press` moved the item in 6 of 8 tries. Keys about 150 ms apart moved it 5 of 5 times, also after an Edit and Save. With the drag-start wait and a paint between keys it moved 16 of 16 times, also at 6x CPU throttle. The keyboard reorder works for people, so this is not a product bug. No UI change. ## What Changed - `runtime-primary.ts`: wait for the browser's own `PUT /primary-agent/me` that names Morgan, require 2xx, and poll the read-back until Morgan is primary before leaving the page. Look for the "My primary agent" crown only in the header that holds Morgan's avatar. Add `isPrimarySaveRequest`. Oracle `runtime-primary.v6`. - `chat-linked-question.ts` / `internal-tasks.ts`: add `chosenTaskOption`. It finds the one option of the bound saved question that names the Launch task's identifier (a setup literal) and no other candidate's. It uses the option id for the rendered DOM id and the payload's submit label. It does not read option wording. The harness selects that option, checks `aria-checked`, submits, and waits for the `respond` POST. The old text and "Other" paths stay for other cards. The checks that nothing changes before the answer and that only COM-1 changes after it are unchanged. - `chat-catalog-contract.ts` / `internal-tasks.ts`: a chosen option saves no comment, so the flow counted only one human action and failed `catalog-original-human-query`. `tasks.ambiguous-task` now joins the cases that may count a bound UI answer. The case declares `expectedHumanQuestionAnswer` only after the harness answered through the choice, and names the chosen question and option. The flow then verifies the answered card independently: answered by this person, exactly the Launch option and no typed text, one audit event, and one continuation run after it. Oracle `internal.ambiguous-task.v8`. - `chat-catalog-contract.ts`: `chatCatalogHumanQuestionPolicies` takes the answering person and mirrors the server's user rule in `evaluateIssueThreadInteractionResolverAudience`. `anyone` and `human_only` admit the person. `not_creator` admits a person who did not create the card. With no resolver (a pending card) `not_creator` stays rejected, so other callers keep their behavior. For the ambiguous-task choice, an unaddressed card is accepted, as the server allows. - `runtime-queue.ts`: `keyboardMoveQueuedMessageUp` waits for the handle's `aria-pressed="true"` after Space. It lets the page paint before ArrowUp and before the closing Space. It records whether each gesture started a drag. Oracle `edit-queued-message.structural.v7`. - No scenario YAML changed, so the TestOps manifest needs no entry. ## Verification - `npx vitest run --config tests/runner-e2e/vitest.config.ts` for `chat-linked-question.test.ts`, `chat-catalog-consistency.test.ts`, `runtime-primary.test.ts`, `runtime-queue.test.ts`, `internal.test.ts`, `external-company-secret.test.ts`, `external-personal-secret.test.ts`, `turn-response-card.test.ts`, `runtime-task-coordination.test.ts`: pass. - Red/green: the two new keyboard tests fail on the old `keyboardMoveQueuedMessageUp` and pass on the new one. The resolver-policy test fails on the old `chatCatalogHumanQuestionPolicies` (`not_creator` answered by a person who is not the creator) and passes on the new one; `not_creator` answered by its creator and a pending card stay rejected. The choice-accounting test fails on the old allow list. - `chosenTaskOption` tests use the cohort 12 card shape, a reworded card, and cards with no single choice (both, duplicate, neither, `COM-10`, a different card). - `npx tsc -p tests/runner-e2e/tsconfig.json --noEmit`: pass. `node --test tests/runner-e2e/chat-full-catalog-testops-manifest.test.mjs`: 10 pass. - Paid narrow run 1 (commit `33399f8370`): https://github.com/paperclipai/paperclip/actions/runs/43446445525. `agents.choose-primary` passed (browser `PUT /primary-agent/me` 200). `steering.edit-queued-message` passed (browser `PUT /queued-comments/order` 200). `tasks.ambiguous-task` selected COM-1 (`respond` 200, only COM-1 became high) but failed `catalog-original-human-query`, because the flow did not count the choice. Later commits fix that. - Paid narrow run 2 (`c90c2aa26a`) was cancelled by run 3 before its case finished. - Paid narrow run 3 (`tasks.ambiguous-task` only, final verifier `fee3bbd453`): https://github.com/paperclipai/paperclip/actions/runs/43452010284 ## Risks - Low risk. Test harness only. - The ambiguous-task harness now answers through a structured choice when one exists. If the agent asks a card with no option that names only the Launch task, the old text and "Other" paths still apply. - `chatCatalogHumanQuestionPolicies` accepts `not_creator` only when a resolver is passed. Callers that check pending cards pass none, so their behavior is unchanged. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, via Claude Code with tool use and code execution. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
252 lines
22 KiB
TypeScript
252 lines
22 KiB
TypeScript
import { chatCatalogNativePhaseDeadline, chatCatalogNativePhaseIsTimely } from "../chat-catalog-contract.js";
|
|
import { expect, type Locator, type Page, type Response } 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 { collectRunEvents } from "../run-observations.js";
|
|
import type { ChatCatalogContext } from "../chat-catalog-contract.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";
|
|
/** Move a queued message up one place with the drag handle's keyboard gesture, as a keyboard user does.
|
|
* Saving an edit disables every handle until that queue change settles, and a gesture pressed on a disabled
|
|
* handle does nothing, so wait for this handle to be enabled first. The gesture must send the queue order
|
|
* request; its status is returned so the caller can tell an accepted move from a refused one. When a gesture
|
|
* sends nothing, `beforeRetry` (for example a reload that refetches the queue) runs and the gesture is pressed
|
|
* again, up to `attempts` gestures in all; every gesture is reported. */
|
|
export async function keyboardMoveQueuedMessageUp(page: Pick<Page, "waitForResponse" | "evaluate">, handle: Pick<Locator, "isEnabled" | "focus" | "press" | "getAttribute">,
|
|
timeoutMs = 15_000, intervalMs = 100, options: { attempts?: number; beforeRetry?: () => Promise<void> } = {}): Promise<{ status: number; waitedForEnabledMs: number; gestures: number; dragStarted: boolean[] }> {
|
|
const dragStarted: boolean[] = [];
|
|
// The drag library starts a keyboard drag on Space but listens for the next keys only after a timer, and moves
|
|
// only once it has measured the rows on a later render. A person's keystrokes are far apart; automated ones are
|
|
// not, so wait for the handle to report the drag (aria-pressed) and let the page paint between keys.
|
|
const settle = () => page.evaluate(() => new Promise<void>(resolve => setTimeout(() => requestAnimationFrame(() => requestAnimationFrame(() => resolve())), 0)));
|
|
const waitForDrag = async () => {
|
|
const started = Date.now();
|
|
while (await handle.getAttribute("aria-pressed") !== "true") {
|
|
if (Date.now() - started >= Math.min(timeoutMs, 3_000)) return false;
|
|
await new Promise(resolve => setTimeout(resolve, Math.min(intervalMs, 50)));
|
|
}
|
|
return true;
|
|
};
|
|
const attempts = Math.max(1, options.attempts ?? 1);
|
|
for (let gesture = 1; ; gesture++) {
|
|
const started = Date.now();
|
|
while (!await handle.isEnabled()) {
|
|
if (Date.now() - started >= timeoutMs) throw new Error("The queued message's reorder handle stayed disabled");
|
|
await new Promise(resolve => setTimeout(resolve, intervalMs));
|
|
}
|
|
const waitedForEnabledMs = Date.now() - started;
|
|
const sent = page.waitForResponse((response: Response) => response.request().method() === "PUT"
|
|
&& new URL(response.url()).pathname.endsWith("/queued-comments/order"), { timeout: timeoutMs });
|
|
sent.catch(() => undefined);
|
|
await handle.focus(); await handle.press("Space");
|
|
const dragging = await waitForDrag(); dragStarted.push(dragging);
|
|
if (dragging) { await settle(); await handle.press("ArrowUp"); await settle(); await handle.press("Space"); }
|
|
const response = dragging ? await sent.catch(() => null) : null;
|
|
if (response) return { status: response.status(), waitedForEnabledMs, gestures: gesture, dragStarted };
|
|
if (gesture >= attempts) throw new Error(`The keyboard reorder gesture sent no queue order request after ${gesture} gesture(s) (drag started: ${dragStarted.join(", ")})`);
|
|
await options.beforeRetry?.();
|
|
}
|
|
}
|
|
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<string, unknown>;
|
|
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 const TASK_HISTORY_READ_EVENT = "task_history.read";
|
|
export function historyReadRevisions(events: ReadonlyArray<{ eventType?: unknown; payload?: unknown }>) {
|
|
const reads: Record<string, string> = {};
|
|
for (const row of events) {
|
|
if (row.eventType !== TASK_HISTORY_READ_EVENT) continue;
|
|
const comments = (row.payload as { comments?: unknown } | null | undefined)?.comments;
|
|
if (!comments || typeof comments !== "object" || Array.isArray(comments)) continue;
|
|
for (const [id, at] of Object.entries(comments as Record<string, unknown>))
|
|
if (typeof at === "string" && Number.isFinite(Date.parse(at)) && !(Date.parse(reads[id] ?? "") >= Date.parse(at))) reads[id] = at;
|
|
}
|
|
return reads;
|
|
}
|
|
export function readCurrentRevision(reads: Record<string, string> | undefined, comment: { id: string; updatedAt?: unknown } | undefined) {
|
|
if (!comment) return false;
|
|
const read = Date.parse(String(reads?.[comment.id] ?? "")), current = Date.parse(String(comment.updatedAt ?? ""));
|
|
return Number.isFinite(read) && Number.isFinite(current) && read >= current;
|
|
}
|
|
export function resultCitedCommentIds(events: ReadonlyArray<{ eventType?: unknown; payload?: unknown }>) {
|
|
const cited = new Set<string>();
|
|
for (const row of events) {
|
|
if (row.eventType !== "run.result.accepted") continue;
|
|
const result = (row.payload as { prpEvent?: { payload?: { result?: { evidence?: unknown; completionClaim?: { criteria?: unknown } } } } } | null | undefined)?.prpEvent?.payload?.result;
|
|
const refs = [...(Array.isArray(result?.evidence) ? result.evidence.map(entry => (entry as { ref?: unknown } | null)?.ref) : []),
|
|
...(Array.isArray(result?.completionClaim?.criteria) ? result.completionClaim.criteria.flatMap(entry => (entry as { evidenceRefs?: unknown } | null)?.evidenceRefs ?? []) : [])];
|
|
for (const ref of refs) {
|
|
const match = typeof ref === "string" ? /^comment:([0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})/.exec(ref) : null;
|
|
if (match) cited.add(match[1]!);
|
|
}
|
|
}
|
|
return [...cited];
|
|
}
|
|
export async function runHistoryReads(ctx: ChatCatalogContext, runId: string) {
|
|
return (await runCommentReceipts(ctx, runId)).reads;
|
|
}
|
|
export async function runCommentReceipts(ctx: ChatCatalogContext, runId: string) {
|
|
const events = await collectRunEvents<{ seq?: number; eventType?: unknown; payload?: unknown }>((afterSeq, limit) => ctx.input.api.get(`/api/heartbeat-runs/${runId}/events?afterSeq=${afterSeq}&limit=${limit}`));
|
|
return { reads: historyReadRevisions(events), cited: resultCitedCommentIds(events) };
|
|
}
|
|
export function handledInTurn(receipts: { reads?: Record<string, string>; cited?: string[] } | undefined, comment: { id: string; updatedAt?: unknown } | undefined) {
|
|
return !!comment && readCurrentRevision(receipts?.reads, comment) && !!receipts?.cited?.includes(comment.id);
|
|
}
|
|
export function wakeMarksEarlierRead(context: { paperclipWake?: { comments?: Array<{ id?: string; readByEarlierTurn?: boolean }> } } | undefined, commentId: string) {
|
|
return context?.paperclipWake?.comments?.some(row => row.id === commentId && row.readByEarlierTurn === true) === true;
|
|
}
|
|
export function settledQueue<T>(accept: (value: T) => boolean, quietMs: number) {
|
|
let since: number | undefined;
|
|
return (value: T) => { if (!accept(value)) { since = undefined; return false; } since ??= Date.now(); return Date.now() - since >= quietMs; };
|
|
}
|
|
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(`(?<![A-Za-z0-9-])${key.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")}(?![0-9])`).test(reply));
|
|
}
|
|
/** The saved requirement is the one queued comment the controller's canonical turn wrote; its wording is the model's. */
|
|
function savedRequirement(queue: IssueQueuedCommentQueue | undefined, leadId: string) {
|
|
return queue?.entries.length === 1 && queue.entries[0]!.comment.authorAgentId === leadId ? queue.entries[0] : undefined;
|
|
}
|
|
export function queuedFollowUpBrief(marker: string) {
|
|
return [
|
|
`The human brief is now ready. Website brief, reference ${marker}:`,
|
|
"- Product: Acorn Notes, a shared notebook app for small research teams. It launches in beta next month.",
|
|
"- Page: one static website.html page with a light background and a readable sans-serif font.",
|
|
"- Hero: the headline \"Research notes your whole team can find\", the line \"Shared notebooks, full-text search across experiments, and one-click citation export\", and a \"Request early access\" button.",
|
|
"- Features: three short items: shared notebooks, search across every experiment, citation export to BibTeX.",
|
|
"- Pricing: \"Free for teams of up to ten during the beta.\"",
|
|
"- Company details: hello@acornnotes.example, +1 555 0142, 12 Elm Street, Portland, OR 97201.",
|
|
`Save this brief as an initial task document that includes 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.`,
|
|
].join("\n");
|
|
}
|
|
export function gradeQueuedFollowup(value: unknown) {
|
|
const c = checks(); const o = runtimeObservation(value);
|
|
c.add("real-queue-and-delivery-evidence", !!o, "The actual task queue, saved requirement, real initial worker and later consuming native input are required."); if (!o) return c.result();
|
|
const task = o.state.task as Entity; const queued = o.state.queuedAtReply as IssueQueuedCommentQueue | undefined;
|
|
const requirement = savedRequirement(queued, o.leadId);
|
|
c.add("correct-task-ordered-waiting-requirement-once", !!queued && queued.issueId === task.id && ["queued", "deferred"].includes(queued.state ?? "")
|
|
&& queued.entries.length === 1 && requirement?.position === 0 && o.state.workerStatusAtReply === "running"
|
|
&& requirement.comment.createdByRunId === o.state.canonicalRunId,
|
|
"Exactly one contact-section instruction is durably queued in order on the genuine running Website task and attributed to the source controller turn.");
|
|
// Whether the reply describes the requirement as pending is free-form; it is read from the evidence, not matched by wording.
|
|
c.add("canonical-reply-identifies-affected-task", replyNamesTask(String(o.state.queryReply), task),
|
|
"The canonical reply, written while the requirement still waits behind Morgan's active turn, names the Website task it was saved on.");
|
|
c.add("normal-continuation-consumes-exact-input-once", !!requirement && o.state.consumedCommentId === requirement.comment.id
|
|
&& o.state.deliveryNativeInputBound === true && o.state.consumingRunCount === 1 && o.state.queueEmptyAfterDelivery === true
|
|
&& o.runs.length === 3 && o.runs.every(run => 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.v4",
|
|
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<RuntimeAgent>(`/api/agents/${ctx.input.fixtures.agent.id}`);
|
|
const worker = await ctx.input.api.get<RuntimeAgent>(`/api/agents/${(state.worker as Entity).id}`); const run = (await ctx.allRuns()).find(row => row.id === state.workerRunId);
|
|
c.add("lead-ready", lead.lifecycleState === "ready" && ["active", "idle"].includes(lead.status ?? ""), "The actual controller is admitted normally.");
|
|
c.add("real-busy-worker", worker.lifecycleState === "ready" && ["active", "running"].includes(worker.status ?? "") && run?.status === "running" && state.workerWasReallyWaiting === true,
|
|
"Morgan is genuinely busy in a native tool wait, without a fabricated busy state.");
|
|
c.add("worker-task-scope", run?.agentId === worker.id && run.companyId === ctx.input.fixtures.company.id
|
|
&& [run.contextSnapshot?.issueId, (run as typeof run & { nativeIssueId?: string })?.nativeIssueId].includes((state.task as Entity).id), "The actual active owner belongs to the exact task and company.");
|
|
return c.result();
|
|
},
|
|
async act(ctx, state) {
|
|
const phase = await pollUntil({ label: "Canonical follow-up saved while Morgan remains active", deadlineAt: chatCatalogNativePhaseDeadline(ctx, Date.now() + 150_000),
|
|
load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns(), queue: await ctx.input.api.get<IssueQueuedCommentQueue>(`/api/issues/${(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 ${ctx.input.nonce}`; state.briefMarker = marker;
|
|
await writeFile((state.gate as { gate: string }).gate, queuedFollowUpBrief(marker), "utf8");
|
|
const delivered = await pollUntil({ label: "Normal successor receives actual queued contact requirement", deadlineAt: Date.now() + 240_000,
|
|
load: async () => ({ task: await ctx.input.api.get<Entity>(`/api/issues/${task.id}`), runs: await ctx.allRuns(), queue: await ctx.input.api.get<IssueQueuedCommentQueue>(`/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<IssueWorkProduct[]>(`/api/issues/${taskId}/work-products`), ctx.input.api.get<IssueAttachment[]>(`/api/issues/${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),
|
|
})];
|