mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-06 05:56:19 +01:00
97 lines
7.9 KiB
TypeScript
97 lines
7.9 KiB
TypeScript
import { expect } from "@playwright/test";
|
|
import { pollUntil } from "../api.js";
|
|
import { sendChatMessage } from "../chat-flow.js";
|
|
import { checks, type Entity } from "./internal-support.js";
|
|
import { readAgentResource, openStandingChat } from "./identity-support.js";
|
|
import { runtimeDefinition, runtimeObservation, observeRuntime } from "./runtime-support.js";
|
|
|
|
export function gradeReopenConversation(value: unknown) {
|
|
const c = checks(); const o = runtimeObservation(value);
|
|
c.add("persisted-reopen-evidence", !!o, "The existing conversation, original attributed history and navigation result are independently read."); if (!o) return c.result();
|
|
c.add("same-existing-owned-conversation", typeof o.state.existingIssueId === "string" && o.state.reopenedIssueId === o.state.existingIssueId
|
|
&& o.state.reopenedAgentId === o.leadId && o.state.historyRetained === true,
|
|
"The supported result opens the same person's existing Morgan conversation and retains its real prior turn.");
|
|
c.add("navigation-started-no-work", o.state.beforeNavigationRuns === 2 && o.state.afterNavigationRuns === 2
|
|
&& o.state.beforeNavigationChatIds !== undefined && JSON.stringify(o.state.beforeNavigationChatIds) === JSON.stringify(o.state.afterNavigationChatIds)
|
|
&& o.tasks.length === 0,
|
|
"The initial setup and canonical query are the only two runs; navigation creates neither work nor a duplicate standing chat.");
|
|
c.add("private-chat-list-not-readable-to-agent", o.state.agentChatListStatus === 403,
|
|
"The actual agent bearer cannot enumerate the person's private conversation list.");
|
|
c.add("canonical-query-navigation-guidance", typeof o.state.finalQueryReply === "string" && /Morgan|conversation|chat|here|back/i.test(o.state.finalQueryReply)
|
|
&& o.state.navigationMatchesIntendedAgent === true && o.state.finalNavigationLinksCorrect === true,
|
|
"The canonical query's actual attributed reply identifies the existing chat; the supported human navigation opens Morgan and any provided chat link has the correct scope.");
|
|
return c.result();
|
|
}
|
|
export const runtimeAgentChatCases = [runtimeDefinition("agent-chat.reopen-conversation", async ctx => {
|
|
await ctx.input.api.patch(`/api/agents/${ctx.input.fixtures.agent.id}`, { name: "Morgan" });
|
|
// Genuine history runs before shared pre-canonical funding. Subscription
|
|
// usage is unpriced, so fund both actual scopes before that setup turn.
|
|
for (const scope of [{ scopeType: "company", scopeId: ctx.input.fixtures.company.id },
|
|
{ scopeType: "agent", scopeId: ctx.input.fixtures.agent.id }])
|
|
await ctx.input.api.post(`/api/companies/${ctx.input.fixtures.company.id}/budgets/policies`, {
|
|
...scope, amount: 500, hardStopEnabled: true, isActive: true, unpricedUsagePolicy: "allow" });
|
|
const source = await openStandingChat(ctx);
|
|
const lead = await ctx.input.api.get<Entity>(`/api/agents/${ctx.input.fixtures.agent.id}`);
|
|
const historyMarker = `Retained launch context ${ctx.input.nonce}`;
|
|
await sendChatMessage(ctx.input.page, `Remember this launch reference in our conversation: ${historyMarker}. Acknowledge briefly; no task is needed.`);
|
|
await pollUntil({ label: "Genuine prior Morgan conversation", deadlineAt: Date.now() + 150_000,
|
|
load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns() }; },
|
|
accept: ({ source, runs }) => source?.conversationState === "waiting" && runs.length === 1 && runs.every(run => run.status === "succeeded") });
|
|
const history = await ctx.input.api.get<Entity[]>(`/api/issues/${source.id}/comments?order=asc`);
|
|
const firstRuns = await ctx.allRuns();
|
|
if (!history.some(row => row.authorAgentId === ctx.input.fixtures.agent.id && firstRuns.some(run => run.id === row.createdByRunId)))
|
|
throw new Error("Existing Morgan history requires a genuine attributed native reply");
|
|
const read = await readAgentResource(ctx, `/api/companies/${ctx.input.fixtures.company.id}/chats`);
|
|
return { existingIssueId: source.id, lead, history, historyMarker, setupRunIds: firstRuns.map(run => run.id), agentChatListStatus: read.status };
|
|
}, gradeReopenConversation, {
|
|
authentication: "human-session", setupHumanMessageCount: 1, expectedHumanMessageCount: 2, expectedRunCount: 2, attemptTimeoutMs: 420_000,
|
|
async act(ctx, state) {
|
|
await pollUntil({ label: "Canonical reopen query settled", deadlineAt: Date.now() + 150_000,
|
|
load: async () => { await ctx.refreshIssue(); return { source: ctx.issue(), runs: await ctx.allRuns() }; },
|
|
accept: ({ source, runs }) => source?.conversationState === "waiting" && runs.length === 2 && runs.every(run => run.status === "succeeded") });
|
|
const source = ctx.issue()!; const runs = await ctx.allRuns();
|
|
const comments = await ctx.input.api.get<Entity[]>(`/api/issues/${source.id}/comments?order=asc`);
|
|
const setupIds = state.setupRunIds as string[];
|
|
const finalReplies = comments.filter(row => row.authorAgentId === ctx.input.fixtures.agent.id
|
|
&& runs.some(run => run.id === row.createdByRunId && !setupIds.includes(run.id)));
|
|
state.finalQueryReply = finalReplies.map(row => row.body ?? "").join("\n");
|
|
const allFinalLinks: string[] = [];
|
|
let href: string | undefined;
|
|
for (const reply of finalReplies) {
|
|
const links = await ctx.input.page.locator(`[id=${JSON.stringify(`comment-${reply.id}`)}] a[href]`).evaluateAll(rows => rows.map(row => row.getAttribute("href")!));
|
|
allFinalLinks.push(...links);
|
|
href ??= links.find(link => {
|
|
const url = new URL(link, ctx.input.api.baseURL);
|
|
return url.origin === ctx.input.api.baseURL && url.pathname.split("/").includes("chats")
|
|
&& [ctx.input.fixtures.agent.id, (state.lead as Entity).urlKey].includes(decodeURIComponent(url.pathname.split("/").at(-1)!));
|
|
});
|
|
|
|
}
|
|
const lead = state.lead as Entity;
|
|
state.finalNavigationLinksCorrect = allFinalLinks.filter(link => new URL(link, ctx.input.api.baseURL).pathname.includes("/chats")).every(link => {
|
|
const url = new URL(link, ctx.input.api.baseURL); const parts = url.pathname.split("/").map(decodeURIComponent);
|
|
return url.origin === ctx.input.api.baseURL && parts[1] === ctx.input.fixtures.company.issuePrefix
|
|
&& (parts.at(-1) === "chats" || [lead.id, lead.urlKey].includes(parts.at(-1)));
|
|
});
|
|
state.beforeNavigationRuns = runs.length;
|
|
const chatList = `/api/companies/${ctx.input.fixtures.company.id}/chats`;
|
|
state.beforeNavigationChatIds = (await ctx.input.api.get<Entity[]>(chatList)).map(row => row.id).sort();
|
|
if (href) await ctx.input.page.locator(`[id^="comment-"] a[href=${JSON.stringify(href)}]`).last().click();
|
|
else await ctx.input.page.goto(`/${ctx.input.fixtures.company.issuePrefix}/chats`, { waitUntil: "domcontentloaded" });
|
|
await expect(ctx.input.page.getByTestId("task-chat-composer-input")).toBeVisible();
|
|
await ctx.input.page.reload({ waitUntil: "domcontentloaded" });
|
|
await expect(ctx.input.page.getByTestId("task-chat-composer-input")).toBeVisible();
|
|
const routeRef = decodeURIComponent(new URL(ctx.input.page.url()).pathname.split("/").at(-1)!);
|
|
state.navigationMatchesIntendedAgent = [lead.id, lead.urlKey].includes(routeRef);
|
|
await ctx.refreshIssue(); state.reopenedIssueId = ctx.issue()?.id;
|
|
const reopened = await ctx.input.api.get<{ conversationAgentId: string }>(`/api/issues/${ctx.issue()!.id}`);
|
|
state.reopenedAgentId = reopened.conversationAgentId;
|
|
const after = await ctx.input.api.get<Entity[]>(`/api/issues/${source.id}/comments?order=asc`);
|
|
state.historyRetained = (state.history as Entity[]).every(prior => after.some(row => row.id === prior.id && row.body === prior.body && row.createdByRunId === prior.createdByRunId));
|
|
state.afterNavigationRuns = (await ctx.allRuns()).length;
|
|
state.afterNavigationChatIds = (await ctx.input.api.get<Entity[]>(chatList)).map(row => row.id).sort();
|
|
},
|
|
observe: observeRuntime,
|
|
async verifyResult(ctx) { await expect(ctx.input.page.getByTestId("task-chat-composer-input")).toBeVisible(); },
|
|
})];
|