mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-07 07:55:47 +01:00
79 lines
7.8 KiB
TypeScript
79 lines
7.8 KiB
TypeScript
import { expect } from "@playwright/test";
|
|
import { readRegisteredArtifacts } from "../registered-artifact.js";
|
|
import { pollUntil } from "../api.js";
|
|
import { sendChatMessage } from "../chat-flow.js";
|
|
import { openStandingChat } from "./identity-support.js";
|
|
import { checks, sameTask, type Entity } from "./internal-support.js";
|
|
import { savedTaskWorkspace } from "./runtime-workspaces.js";
|
|
import { runtimeDefinition, runtimeObservation, observeRuntime } from "./runtime-support.js";
|
|
type Artifact = Awaited<ReturnType<typeof readRegisteredArtifacts>>[number];
|
|
interface Workspace extends Entity { sourceIssueId?: string | null; rootIssueId?: string | null; cwd?: string; repoUrl?: string | null; branchName?: string | null; closedAt?: string | null }
|
|
export function gradeWorkspaceClosure(value: unknown) {
|
|
const c = checks(); const o = runtimeObservation(value);
|
|
c.add("real-closure-retention-evidence", !!o, "Actual lifecycle, source references and independently downloaded retained file bytes are required."); if (!o) return c.result();
|
|
const before = o.state.closingWorkspace as Workspace | undefined; const after = o.state.closedWorkspace as Workspace | undefined;
|
|
const artifact = o.state.retainedArtifact as Artifact | undefined; const prior = o.state.artifact as Artifact | undefined;
|
|
c.add("permitted-actual-workspace-closed", !!before && !!after && before.id === after.id && after.companyId === o.companyId
|
|
&& after.status === "archived" && !!after.closedAt && o.state.closeReadyBeforeQuery === true
|
|
&& o.activity.some(row => row.action === "execution_workspace.updated" && row.entityId === after.id && row.agentId === o.leadId
|
|
&& (row.details?.changedKeys as string[] | undefined)?.includes("status")),
|
|
"The permitted model operation closes the exact genuinely eligible task workspace and has independent agent attribution.");
|
|
c.add("promised-work-retained-and-readable", !!prior?.contentVerified && !!artifact?.contentVerified && artifact.attachmentId === prior.attachmentId
|
|
&& artifact.workProductId === prior.workProductId && artifact.sha256 === prior.sha256 && artifact.content === o.state.fileBefore
|
|
&& artifact.content.trim() === o.state.marker,
|
|
"The actual promised saved file remains accessible with unchanged downloaded bytes and original artifact provenance after closure.");
|
|
c.add("source-history-and-other-workspaces-preserved", !!before && !!after && ["sourceIssueId", "rootIssueId", "repoUrl", "branchName"].every(key => before[key as keyof Workspace] === after[key as keyof Workspace])
|
|
&& o.tasks.length === 2 && sameTask(o.state.task as Entity, o.tasks.find(row => row.id === (o.state.task as Entity).id))
|
|
&& o.state.otherWorkspacesUnchanged === true && o.state.otherFileRetained === true
|
|
&& o.runs.length === 4 && o.runs.every(run => run.status === "succeeded"),
|
|
"Closure retains the task and source records, does not cancel prior execution or affect a separate workspace.");
|
|
c.add("honest-supported-retrieval", /closed|archiv/i.test(o.reply) && /reopen|retriev|download|artifact|attachment|saved (?:file|work)/i.test(o.reply)
|
|
&& !/deleted (?:all|the).*files|force.?reconcil|merged.*branch|cancelled.*other/i.test(o.reply),
|
|
"The reply reports the actual closed state and supported file retrieval without claiming deletion, forced reconciliation or unrelated cancellation.");
|
|
return c.result();
|
|
}
|
|
export const runtimeWorkspaceClosureCases = [runtimeDefinition("workspaces.close-and-reopen", async ctx => {
|
|
const state = await savedTaskWorkspace(ctx, { artifact: true }); const id = state.workspaceBefore.workspace.id;
|
|
const other = await savedTaskWorkspace(ctx, { workerName: "Riley" });
|
|
await ctx.input.api.patch(`/api/issues/${other.task.id}`, { title: "Unrelated retained notes" });
|
|
const closingWorkspace = await ctx.input.api.get<Workspace>(`/api/execution-workspaces/${id}`);
|
|
const readiness = await ctx.input.api.get<{ state: string }>(`/api/execution-workspaces/${id}/close-readiness`);
|
|
if (!["ready", "ready_with_warnings"].includes(readiness.state)) throw new Error("Completed fixture is not genuinely eligible for supported workspace closure");
|
|
await openStandingChat(ctx);
|
|
await sendChatMessage(ctx.input.page, `For my next instruction, focus on the completed Website task ${state.task.identifier ?? state.task.id} and its exact execution workspace ${id}. Its saved website-fixture.txt must remain retrievable. The separate Unrelated retained notes task and its workspace belong to Riley and must stay untouched. Acknowledge the target only; do not close, reopen or change either workspace yet.`);
|
|
await pollUntil({ label: "Native closure target context retained", deadlineAt: Date.now() + 150_000,
|
|
load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns() }; },
|
|
accept: value => value.source?.conversationState === "waiting" && value.runs.length === 3 && value.runs.every(run => run.status === "succeeded") });
|
|
const otherWorkspace = await ctx.input.api.get<Workspace>(`/api/execution-workspaces/${other.workspaceBefore.workspace.id}`);
|
|
return { ...state, closingWorkspace, closeReadyBeforeQuery: true, otherTask: other.task, otherFileBefore: other.fileBefore, otherWorkspacesBefore: [otherWorkspace] };
|
|
}, gradeWorkspaceClosure, {
|
|
sourceFiles: ["chat-catalog-domains/runtime-workspace-closure.ts", "chat-catalog-domains/runtime-workspaces.ts", "chat-catalog-domains/runtime-support.ts", "chat-scenarios/workspaces.yaml"],
|
|
setupHumanMessageCount: 1, expectedHumanMessageCount: 2, expectedRunCount: 4, attemptTimeoutMs: 900_000,
|
|
async observe(ctx, state) {
|
|
const before = state.closingWorkspace as Workspace;
|
|
state.closedWorkspace = await ctx.input.api.get<Workspace>(`/api/execution-workspaces/${before.id}`);
|
|
[state.retainedArtifact] = await readRegisteredArtifacts(ctx.input.api, (state.task as Entity).id, String(state.fixtureRunId), ["website-fixture.txt"]);
|
|
const inventory = await ctx.input.api.get<Workspace[]>(`/api/companies/${ctx.input.fixtures.company.id}/execution-workspaces`);
|
|
state.otherWorkspacesUnchanged = (state.otherWorkspacesBefore as Workspace[]).every(prior => inventory.some(row => row.id === prior.id
|
|
&& row.status === prior.status && row.cwd === prior.cwd && row.sourceIssueId === prior.sourceIssueId && row.rootIssueId === prior.rootIssueId));
|
|
const other = await ctx.input.api.get<{ content: { data: string } }>(`/api/issues/${(state.otherTask as Entity).id}/file-resources/content?workspace=execution&path=website-fixture.txt`);
|
|
state.otherFileRetained = other.content.data === state.otherFileBefore;
|
|
return observeRuntime(ctx, state);
|
|
},
|
|
async verifyResult(ctx, state) {
|
|
const source = ctx.input.page.url(); const workspace = state.closedWorkspace as Workspace;
|
|
await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/execution-workspaces/${workspace.id}`, { waitUntil: "domcontentloaded" });
|
|
await ctx.input.page.reload({ waitUntil: "domcontentloaded" });
|
|
await expect(ctx.input.page.getByRole("heading", { name: workspace.name!, exact: true }).first()).toBeVisible();
|
|
await expect(ctx.input.page.getByRole("button", { name: "Close workspace", exact: true })).toBeDisabled();
|
|
const artifact = state.retainedArtifact as Artifact;
|
|
const download = ctx.input.page.waitForEvent("download");
|
|
await ctx.input.page.goto(`/api/attachments/${artifact.attachmentId}/content?download=1`).catch(error => {
|
|
if (!/Download is starting|net::ERR_ABORTED/i.test(String(error))) throw error;
|
|
});
|
|
if ((await download).suggestedFilename() !== "website-fixture.txt") throw new Error("Closed workspace retrieval returned a different saved file");
|
|
await ctx.input.evidence("runtime-closed-workspace-retained-file.json", { workspaceId: workspace.id, attachmentId: artifact.attachmentId, sha256: artifact.sha256 });
|
|
await ctx.input.page.goto(source, { waitUntil: "domcontentloaded" });
|
|
},
|
|
})];
|