fix(evals): create everyday tasks through current composer

Reuse response-based task identity, preserve the exact prompt and chosen project/assignee, and calibrate the browser setup with paused agents.

Co-Authored-By: Paperclip <noreply@paperclip.ing>

tests/e2e/plan-task-fixture.spec.ts

@@ -1,6 +1,6 @@
 import { randomUUID } from "node:crypto";
 import { expect, test } from "@playwright/test";
-import { createPlanTaskThroughUi } from "../runner-e2e/plan-task-ui.js";
+import { createPlanTaskThroughUi, createTaskFromPromptThroughUi } from "../runner-e2e/plan-task-ui.js";
 
 test("planning fixture creates the exact assignment through the current composer without providers", async ({ page, request }) => {
   const companyResponse = await request.post("/api/companies", { data: { name: `Planning setup ${randomUUID()}` } });
@@ -30,3 +30,39 @@ test("planning fixture creates the exact assignment through the current composer
     expect((await request.delete(`/api/companies/${company.id}`)).ok()).toBe(true);
   }
 });
+
+
+test("everyday fixture preserves prompt, selected project and assignee without providers", async ({ page, request }) => {
+  const companyResponse = await request.post("/api/companies", { data: { name: `Everyday setup ${randomUUID()}` } });
+  expect(companyResponse.ok()).toBe(true);
+  const company = await companyResponse.json();
+  try {
+    let lead: { id: string; name: string } | undefined;
+    for (const name of ["A Different Owner", "Everyday Fixture Lead"]) {
+      const response = await request.post(`/api/companies/${company.id}/agents`, { data: {
+        name, role: "general", adapterType: "process", adapterConfig: { command: "false" },
+        runtimeConfig: { heartbeat: { enabled: false } },
+      } });
+      expect(response.ok()).toBe(true);
+      lead = await response.json();
+      expect((await request.post(`/api/agents/${lead!.id}/pause`)).ok()).toBe(true);
+    }
+    let project: { id: string; name: string } | undefined;
+    for (const name of ["A Different Project", "Everyday Fixture Project"]) {
+      const response = await request.post(`/api/companies/${company.id}/projects`, { data: { name } });
+      expect(response.ok()).toBe(true);
+      project = await response.json();
+    }
+    const prompt = "Delegate the implementation to an engineer, review its delivered files, and finish after the revised result is ready.";
+    const created = await createTaskFromPromptThroughUi({ page, companyId: company.id, issuePrefix: company.issuePrefix,
+      agentName: lead!.name, projectName: project!.name, prompt });
+    const issue = await (await request.get(`/api/issues/${created.id}`)).json();
+    expect(issue).toMatchObject({ id: created.id, companyId: company.id, assigneeAgentId: lead!.id,
+      projectId: project!.id, description: prompt, workMode: "standard" });
+    const runs = await request.get(`/api/companies/${company.id}/heartbeat-runs?limit=100`);
+    expect(runs.ok()).toBe(true);
+    expect(await runs.json()).toEqual([]);
+  } finally {
+    expect((await request.delete(`/api/companies/${company.id}`)).ok()).toBe(true);
+  }
+});

tests/runner-e2e/everyday-flow.ts

@@ -13,7 +13,8 @@ import {
 } from "./everyday-delivery.js";
 import type { LiveFixtureValues } from "./live-fixtures.js";
 import type { MatrixExecution } from "./types.js";
-import { createTaskThroughUi, submitTaskReply } from "./user-actions.js";
+import { submitTaskReply } from "./user-actions.js";
+import { createTaskFromPromptThroughUi } from "./plan-task-ui.js";
 import { waitForTaskChatRendered } from "./continuation-screenshot.js";
 import { hasPersistedSource, isSavedSourceCheckpoint } from "./everyday-interruption.js";
 import { setupAggregatorFixture } from "./aggregator-fixture.js";
@@ -667,25 +668,15 @@ export async function runEverydayFlow(input: Input) {
       if (state.connections.length)
         throw new Error("New-connection story requires an unconnected company");
     }
-    await createTaskThroughUi({
+    const created = await createTaskFromPromptThroughUi({
       page,
+      companyId: fixtures.company.id,
       issuePrefix: prefix,
       agentName: fixtures.agent.name,
-      title: execution.task.buildTitle(nonce),
       prompt: ev.prompt,
-      workMode: "standard",
       projectName: project?.name,
     });
-    parent = await pollUntil({
-      label: "browser-created story task",
-      deadlineAt: Date.now() + 30_000,
-      load: () =>
-        api.get<StoryIssue[]>(`/api/companies/${fixtures.company.id}/issues`),
-      accept: (rows) =>
-        rows.some((i) => i.title === execution.task.buildTitle(nonce)),
-    }).then((rows) =>
-      rows.find((i) => i.title === execution.task.buildTitle(nonce))!,
-    );
+    parent = await api.get<StoryIssue>(`/api/issues/${created.id}`);
     input.observe(parent!, []);
     note("task-submitted", { issueId: parent!.id });
     await openParent();

tests/runner-e2e/plan-task-ui.ts

@@ -3,8 +3,8 @@ import { expect, type Page } from "@playwright/test";
 /** The current composer creates a task from its description and assigns its
  * title later. Capture the actual public create response; never guess its ID
  * from a title or mutate the issue behind the browser. */
-export async function createPlanTaskThroughUi(input: {
-  page: Page; companyId: string; issuePrefix: string; agentName: string; prompt: string;
+export async function createTaskFromPromptThroughUi(input: {
+  page: Page; companyId: string; issuePrefix: string; agentName: string; prompt: string; projectName?: string;
 }): Promise<{ id: string }> {
   const { page } = input;
   await page.goto(`/${encodeURIComponent(input.issuePrefix)}/issues`, { waitUntil: "domcontentloaded" });
@@ -18,6 +18,14 @@ export async function createPlanTaskThroughUi(input: {
   await expect(option).toHaveCount(1);
   await option.click();
   await expect(assignee).toContainText(input.agentName);
+  if (input.projectName) {
+    const project = dialog.getByRole("group", { name: "Task project and worktrees", exact: true }).getByRole("button").first();
+    // Focus opens this selector without toggling an already-open popover closed.
+    await project.focus();
+    await page.getByPlaceholder("Search projects...", { exact: true }).fill(input.projectName);
+    await page.getByRole("button", { name: input.projectName, exact: true }).click();
+    await expect(project).toContainText(input.projectName);
+  }
   const responsePromise = page.waitForResponse(response => response.request().method() === "POST" &&
     new URL(response.url()).pathname === `/api/companies/${input.companyId}/issues`);
   await dialog.getByRole("button", { name: "Create task", exact: true }).click();
@@ -25,5 +33,10 @@ export async function createPlanTaskThroughUi(input: {
   if (!response.ok()) throw new Error(`Browser task creation failed: ${response.status()}`);
   const issue = await response.json();
   if (typeof issue.id !== "string" || issue.companyId !== input.companyId) throw new Error("Browser created an unexpected issue identity");
+  if (issue.description !== input.prompt || issue.workMode !== "standard") {
+    throw new Error("Browser task creation changed the requested prompt or work mode");
+  }
   return { id: issue.id };
 }
+
+export const createPlanTaskThroughUi = createTaskFromPromptThroughUi;