mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 00:26:28 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - The chat-feature evals measure whether agents complete real chat requests through the product > - The chat catalog eval harness and its repairs live on the `chat-eval/master-candidate` branch, not on master > - Today's work made 139 of 242 chat evals pass in verified single-case live runs. Each product fix landed on master as its own pull request > - The eval-side changes (setups, graders, fault seams, evidence capture) still exist only on the candidate > - This pull request lands the harness on master. Master stays the source of truth for product behavior > - The benefit is one tree: evals run against master commits, and product fixes reach the evals as soon as they merge ## Linked Issues or Issue Description Refs #19441, Refs #19599, Refs #20270, Refs #20334, Refs #20342, Refs #20344, Refs #20354, Refs #20360, Refs #20373, Refs #20382, Refs #20409 **What existing behavior does this improve?** The chat catalog eval harness and the product it evaluates live on a long-running branch outside master. Eval fixes do not reach master, so master-based eval runs use old setups and graders. **Subsystem affected** `tests/runner-e2e` chat catalog harness, plus a small set of product changes that exist only on the candidate. **Proposed change** Land the harness on master. Every product fix from this eval work already merged to master as its own pull request. Conflicts keep master's product behavior. ## What Changed - Most of the diff (808 of 851 files) is under `tests/runner-e2e/`: chat-catalog domains, scenarios, descriptors, the TestOps manifest, private evidence tooling, and their tests. - Graders now check saved state, setup literals and rendered or clicked links. Many keyword and regex checks on free-form replies are removed. Each changed grader has a bumped `oracleVersion` and calibration tests (a valid reply, a reworded valid reply, and broken variants that must fail). - The shared link helper `hasLink` no longer treats a list link (for example `/COM/issues?view=mine`) as a link to every task without a URL key. - Setup fixes build real state through supported product routes: routine history, agent grants through the board grant route, budget holds with a real cap, and a storage-layer archive fault for `inbox-search.archive-partial-failure`. - Browser boundary journeys (sign-in, chat-disabled, onboarding) now write the standard pass evidence files. - Retargeted cases, approved by the maintainer: `agent-chat.chat-disabled` (Conference Room gate), `agents.restore-instructions` (no saved instruction history), `access.manage-membership` (member permission edits stay board-only). - The private evidence trusted files (`manual-private-handoff.ts`, `manual-private-retention.ts`, `manual-private-report-assets.ts`) are byte-identical to master. - Product files outside `tests/` (43 files, +1,328 −49) carry candidate-only changes that master does not yet have. Most are tests. The main code changes are in `request-human-input.ts`, `heartbeat-run-summary.ts`, `native-completion-feedback.ts`, `native-run-finalizer.ts`, `openapi.ts`, `secrets.ts` and `IssueChatLongThreadPerf.tsx`. ## Verification - `pnpm vitest run chat-catalog-domains chat-catalog-contract.test.ts chat-catalog-consistency.test.ts unit-launcher.test.mjs --testTimeout=180000` in `tests/runner-e2e`: 269 files pass, 3,550 tests pass. - `node --test chat-full-catalog-testops-manifest.test.mjs`: 10 pass. - `node tests/runner-e2e/source-sdk-public-inputs.mjs <HEAD> --check`: no change. - `tsc` for `server` and `tests/runner-e2e`: clean. - Live single-case verification: 139 of 242 cases passed on paid runs, and a person read the saved evidence for each. These are single-case runs, not one full-cohort run. ## Risks - Large diff. Most of it is test-only, but the 43 non-test files change product code paths. Review those files first. - Some graders are now less strict on reply wording. A person must read replies for meaning on those cases. - 42 cases need disposable outside accounts (Notion, Slack, GitHub, Daytona and others) and stay blocked. `access.invite-teammate` stays failing until local agent isolation lands, because the runner's durable state keeps a live invite token. - The paid workflow compares the trusted private-evidence files with master. They are unchanged, so this risk is low. ## Model Used Anthropic Claude Opus 5.5 (`claude-opus-5-5`), with tool use and code execution, in Claude Code. Subagents used the same model. ## 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> Co-authored-by: Paperclip <noreply@paperclip.ing>
96 lines
6.9 KiB
TypeScript
96 lines
6.9 KiB
TypeScript
import { expect } from "@playwright/test";
|
||
import { projectPrivacyCases } from "./internal-privacy.js";
|
||
import { repositoryProjectCases } from "./internal-repositories.js";
|
||
import { projectWorkCases } from "./internal-task-creation.js";
|
||
import type { ChatCatalogCase } from "../chat-catalog-contract.js";
|
||
import { project, task, goal, putDocument, entity, observation, checks, hasLink, sameTask, type Entity, type InternalObservation } from "./internal-support.js";
|
||
import { makeDefinition, retryDefinition, fixtureWorker } from "./internal-definition.js";
|
||
|
||
export function grade_projects(value: unknown) {
|
||
const c = checks(); const o = observation(value);
|
||
c.add("complete-independent-observation", !!o, "Missing API, document, audit or rendered-link evidence cannot pass.");
|
||
if (!o) return c.result();
|
||
const before = o.state.task ? entity(o.state, "task") : undefined;
|
||
const current = before && o.tasks.find(row => row.id === before.id);
|
||
const savedProject = o.state.project ? entity(o.state, "project") : undefined;
|
||
const projectNow = savedProject && o.projects.find(row => row.id === savedProject.id);
|
||
const authored = (action: string, id: string) => o.activity.some(row => row.action === action && row.entityId === id && row.agentId === o.leadId);
|
||
const linkedTask = () => !!current && hasLink(o, "issues", current);
|
||
switch (o.scenarioId) {
|
||
case "projects.create-project": {
|
||
const created = o.projects.filter(row => row.name === "Launch");
|
||
c.add("one-company-project", created.length === 1 && created[0]?.companyId === o.companyId, "Exactly one Launch is saved in the active company.");
|
||
c.add("agent-created-project", created.length === 1 && authored("project.created", created[0]!.id), "Creation is attributed to the acting CEO rather than fixture setup.");
|
||
c.add("usable-project-link", created.length === 1 && hasLink(o, "projects", created[0]!), "Chat renders the exact saved project link.");
|
||
c.add("retry-reuses-first-project", initialProjectCreation(observation(o.state.firstCreation)) && Array.isArray(o.state.firstIds) && o.state.firstIds.length === 1 && created[0]?.id === o.state.firstIds[0]
|
||
&& o.humanQueries.filter(query => query === o.state.retryQuery).length === 2, "The exact user retry preserves the first saved project rather than silently creating and replacing it.");
|
||
c.add("no-invented-ready-work", o.tasks.length === 0 && !/\b(?:deployed|website is ready|repository is ready)\b/i.test(o.reply), "Creation does not invent execution, repository readiness or a deployment.");
|
||
break;
|
||
}
|
||
case "projects.archive-project": {
|
||
c.add("archived-not-deleted", !!projectNow && Number.isFinite(Date.parse(projectNow.archivedAt ?? "")), "Launch remains retrievable in the supported archived state.");
|
||
c.add("history-retained", !!before && sameTask(before, current) && o.documents.some(row => row.body === o.state.originalBody)
|
||
&& o.activity.some(row => row.id === o.state.originalActivityId), "The original task, document bytes and creation audit survive archiving.");
|
||
c.add("attributed-project-update", !!projectNow && authored("project.updated", projectNow.id), "The saved lifecycle change belongs to the acting agent.");
|
||
c.add("historical-api-reachability", !!projectNow && o.state.historicalProjectReadId === projectNow.id && o.state.historicalTaskReadId === before?.id, "The actual archived project and retained task remain independently readable through their public resource APIs.");
|
||
c.add("truthful-archive-report", /\barchived\b/i.test(o.reply) && !assertsDestructiveArchiveChange(o.reply), "The response reports saved archiving without falsely claiming resource deletion or task cancellation.");
|
||
break;
|
||
}
|
||
default: c.add("implemented-scenario", false, "No independent oracle is implemented for this scenario.");
|
||
}
|
||
return c.result();
|
||
}
|
||
|
||
const define = (id: string, setup: ChatCatalogCase["setup"]) => makeDefinition(id, setup, grade_projects);
|
||
export const projectsCases: readonly ChatCatalogCase[] = [
|
||
...projectPrivacyCases,
|
||
...repositoryProjectCases,
|
||
...projectWorkCases,
|
||
retryDefinition("projects.create-project", grade_projects, initialProjectCreation),
|
||
archivedProject(),
|
||
|
||
];
|
||
|
||
function initialProjectCreation(o: InternalObservation | undefined): boolean {
|
||
if (!o) return false;
|
||
const projects = o.projects.filter(row => row.name === "Launch"); const p = projects[0];
|
||
return projects.length === 1 && !!p && p.companyId === o.companyId && o.tasks.length === 0 && hasLink(o, "projects", p)
|
||
&& o.activity.some(row => row.action === "project.created" && row.entityId === p.id && row.agentId === o.leadId)
|
||
&& !/\b(?:deployed|website is ready|repository is ready)\b/i.test(o.reply);
|
||
}
|
||
|
||
function assertsDestructiveArchiveChange(reply: string) {
|
||
for (const match of reply.matchAll(/\b(?:delet(?:e|ed|ing)|cancel(?:led|ed|ling|ing))\b/gi)) {
|
||
const before = reply.slice(Math.max(0, match.index! - 75), match.index);
|
||
if (!/(?:\b(?:not|never|nothing|without|no resources?|no tasks?)|n['’]t|rather than)\s+(?:(?:was|were|is|are|been|be|being|have|has|had)\s+)*$/i.test(before)) return true;
|
||
}
|
||
return false;
|
||
}
|
||
function archivedProject(): ChatCatalogCase {
|
||
const base = define("projects.archive-project", async ctx => {
|
||
const p = await project(ctx, "Launch", { status: "completed" });
|
||
const t = await task(ctx, "Website task", p.id, { status: "done" });
|
||
const body = `# Delivered website\nHistorical receipt ${ctx.input.nonce}.`;
|
||
await putDocument(ctx, t.id, body);
|
||
const activity = await ctx.input.api.get<Entity[]>(`/api/issues/${t.id}/activity`);
|
||
return { project: p, task: t, originalBody: body, originalActivityId: activity.find(row => row.action === "issue.created")?.id };
|
||
});
|
||
return { ...base,
|
||
async observe(ctx, state) {
|
||
const [p, t] = await Promise.all([ctx.input.api.get<Entity>(`/api/projects/${entity(state, "project").id}`), ctx.input.api.get<Entity>(`/api/issues/${entity(state, "task").id}`)]);
|
||
state.historicalProjectReadId = p.id; state.historicalTaskReadId = t.id;
|
||
return base.observe!(ctx, state);
|
||
},
|
||
async verifyResult(ctx, state) {
|
||
const source = ctx.input.page.url();
|
||
for (const [kind, row] of [["projects", entity(state, "project")], ["issues", entity(state, "task")]] as const) {
|
||
await ctx.input.page.goto(new URL(`/${ctx.input.fixtures.company.issuePrefix}/${kind}/${row.id}`, ctx.input.api.baseURL).href, { waitUntil: "domcontentloaded" });
|
||
await expect(ctx.input.page.getByRole("heading", { name: row.name ?? row.title!, exact: true }).first()).toBeVisible();
|
||
await ctx.input.evidence(`chat-catalog-archived-history-${kind}.json`, { id: row.id, actualUrl: ctx.input.page.url(), actualHeading: row.name ?? row.title });
|
||
}
|
||
await ctx.input.page.goto(source, { waitUntil: "domcontentloaded" });
|
||
await expect(ctx.input.page.getByTestId("task-chat-composer-input")).toBeVisible();
|
||
},
|
||
};
|
||
}
|