mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-15 18:56:05 +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>
120 lines
8.8 KiB
TypeScript
120 lines
8.8 KiB
TypeScript
import { expect } from "@playwright/test";
|
|
import type { ChatCatalogCase, ChatCatalogContext } from "../chat-catalog-contract.js";
|
|
import { observeInternal, type Entity, type InternalObservation } from "./internal-support.js";
|
|
|
|
export interface IdentityObservation extends InternalObservation {
|
|
companies: Entity[]; company: Entity; agents: Entity[]; interactions: Interaction[];
|
|
}
|
|
export interface Interaction extends Entity {
|
|
idempotencyKey?: string | null;
|
|
kind: string; status: string; payload: { prompt?: string; runtimeRequestId?: string; toolAction?: { connectionId?: string; actionRequestId?: string }; questionSet?: { description?: string; submitLabel?: string; questions: Array<{ id: string; prompt: string; answerMode: string; required?: boolean; customAnswer?: { enabled: boolean; label?: string } }> } };
|
|
result?: { outcome?: string; commentId?: string; toolAction?: { status: string; errorCode?: string | null; errorMessage?: string | null }; answers?: Array<{ questionId: string; otherText?: string; optionIds?: string[] }> };
|
|
resolvedByUserId?: string; resolvedByAgentId?: string; sourceRunId?: string;
|
|
}
|
|
export async function openStandingChat(ctx: ChatCatalogContext) {
|
|
await ctx.input.api.post(`/api/companies/${ctx.input.fixtures.company.id}/chats/${ctx.input.fixtures.agent.id}`);
|
|
await ctx.refreshIssue();
|
|
if (!ctx.issue()) throw new Error("Public standing-chat creation did not persist");
|
|
return ctx.issue()!;
|
|
}
|
|
export async function observeIdentity(ctx: ChatCatalogContext, state: Record<string, unknown>): Promise<IdentityObservation> {
|
|
const internal = await observeInternal(ctx, state);
|
|
const root = `/api/companies/${ctx.input.fixtures.company.id}`;
|
|
const [companies, company, agents, interactions] = await Promise.all([
|
|
ctx.input.api.get<Entity[]>("/api/companies"), ctx.input.api.get<Entity>(root),
|
|
ctx.input.api.get<Entity[]>(`${root}/agents`),
|
|
ctx.issue() ? ctx.input.api.get<Interaction[]>(`/api/issues/${ctx.issue()!.id}/interactions`) : Promise.resolve([]),
|
|
]);
|
|
return { ...internal, companies, company, agents, interactions };
|
|
}
|
|
export function identityObservation(value: unknown): IdentityObservation | undefined {
|
|
const o = value as IdentityObservation | undefined;
|
|
return o && typeof o.companyId === "string" && typeof o.leadId === "string" && !!o.state && !!o.company
|
|
&& [o.tasks, o.projects, o.goals, o.activity, o.documents, o.links, o.runs, o.companies, o.agents, o.interactions].every(Array.isArray) ? o : undefined;
|
|
}
|
|
export function identityDefinition(scenarioId: string, setup: ChatCatalogCase["setup"], grade: ChatCatalogCase["grade"], extra: Partial<ChatCatalogCase> = {}): ChatCatalogCase {
|
|
const definition: ChatCatalogCase = { scenarioId, setup, grade, observe: observeIdentity, oracleVersion: "paperclip.chat-catalog.identity.v1",
|
|
sourceFiles: ["chat-catalog-domains/identity-support.ts", "chat-catalog-domains/internal-support.ts", `chat-catalog-domains/identity-${scenarioId.split(".")[0]}.ts`, `chat-scenarios/${scenarioId.split(".")[0]}.yaml`],
|
|
expectedRunCount: 1, turnTimeoutMs: 120_000, attemptTimeoutMs: 300_000,
|
|
async verifyResult(ctx) { await expect(ctx.input.page.getByTestId("task-chat-composer-input")).toBeVisible(); }, ...extra };
|
|
return { ...definition,
|
|
async setup(ctx) {
|
|
try { return await definition.setup(ctx); }
|
|
catch (error) { await cleanupIdentityProbes(ctx); throw error; }
|
|
},
|
|
async cleanup(ctx, state) {
|
|
try { await cleanupIdentityProbes(ctx); }
|
|
finally { await definition.cleanup?.(ctx, state); }
|
|
},
|
|
};
|
|
}
|
|
/** Opt-in callers consume the original flow clock, never a fresh outer budget. */
|
|
export function remainingIdentityObservationBudget(ctx: ChatCatalogContext): number {
|
|
const deadline = ctx.observationDeadlineAt;
|
|
const now = Date.now();
|
|
if (!Number.isFinite(deadline) || deadline! <= now) throw new Error("Original identity observation budget exhausted or missing");
|
|
return deadline! - now;
|
|
}
|
|
export async function waitForReply(ctx: ChatCatalogContext, observationDeadlineAt?: number) {
|
|
const { pollUntil } = await import("../api.js");
|
|
await pollUntil({ label: "initial identity response", deadlineAt: observationDeadlineAt ?? Date.now() + 150_000, intervalMs: 500,
|
|
load: async () => { await ctx.refreshIssue(); return { issue: ctx.issue(), runs: await ctx.allRuns() }; },
|
|
accept: ({ issue, runs }) => (observationDeadlineAt === undefined || Date.now() < observationDeadlineAt) && issue?.conversationState === "waiting" && runs.length === 1 && runs.every(run => run.status === "succeeded"),
|
|
reject: ({ runs }) => runs.some(run => ["failed", "cancelled", "timed_out"].includes(run.status)) ? "Initial response failed" : undefined });
|
|
}
|
|
export async function identityWorker(ctx: ChatCatalogContext, name = "Morgan") {
|
|
const { api, execution, fixtures, workspacePath, nonce } = ctx.input;
|
|
const base = execution.profile.buildAgent({ environmentId: fixtures.environment.id, environmentFixtureId: execution.environment.id,
|
|
workspacePath, secretRefs: fixtures.secretRefs, executionId: nonce });
|
|
const payload = { ...base, name, role: "engineer", title: "Website engineer", reportsTo: fixtures.agent.id,
|
|
runtimeConfig: { ...(base.runtimeConfig as Record<string, unknown>), heartbeat: { enabled: false, maxConcurrentRuns: 1 } } };
|
|
const { codexSubscriptionAgentConfig } = await import("../codex-subscription-fixture.js");
|
|
return api.post<Entity>(`/api/companies/${fixtures.company.id}/agents`, execution.profile.credential === "CODEX_AUTH_JSON"
|
|
? codexSubscriptionAgentConfig(payload, process.env, fixtures.company.id) : payload);
|
|
}
|
|
/** Real agent bearer, public route and HTTP status. Never pass bearer into
|
|
* Playwright requests, case state, screenshots, model context or evidence. */
|
|
const identityProbeKeys = new WeakMap<ChatCatalogContext, Promise<{ id: string; token: string }>>();
|
|
async function identityProbeKey(ctx: ChatCatalogContext) {
|
|
if (!ctx.input.privateSecrets) throw new Error("Identity probes require attempt-private credential redaction");
|
|
let pending = identityProbeKeys.get(ctx);
|
|
if (!pending) {
|
|
pending = ctx.input.api.postSensitive<{ id: string; token: string }>(`/api/agents/${ctx.input.fixtures.agent.id}/keys`, { name: `access-check-${ctx.input.nonce}` })
|
|
.then(key => { ctx.input.privateSecrets!.push(key.token); return key; });
|
|
identityProbeKeys.set(ctx, pending);
|
|
}
|
|
return pending;
|
|
}
|
|
export async function cleanupIdentityProbes(ctx: ChatCatalogContext) {
|
|
const pending = identityProbeKeys.get(ctx); if (!pending) return;
|
|
const key = await pending;
|
|
await ctx.input.api.delete(`/api/agents/${ctx.input.fixtures.agent.id}/keys/${key.id}`, { allowNotFound: true });
|
|
identityProbeKeys.delete(ctx);
|
|
}
|
|
export async function probeAgentPermission(ctx: ChatCatalogContext, path: string, method: string, body?: unknown) {
|
|
return (await probeAgentPermissionResponse(ctx, path, method, body)).status;
|
|
}
|
|
/** Same probe, also returning the server's error text so a fixture can tell which gate denied it. */
|
|
export async function probeAgentPermissionResponse(ctx: ChatCatalogContext, path: string, method: string, body?: unknown, extraHeaders: Record<string, string> = {}): Promise<{ status: number; error?: string }> {
|
|
const target = new URL(path, ctx.input.api.baseURL);
|
|
if (target.origin !== ctx.input.api.baseURL || !target.pathname.startsWith("/api/")) throw new Error("Agent permission probe escaped fixture API");
|
|
const key = await identityProbeKey(ctx);
|
|
const response = await fetch(target, { method, redirect: "error", signal: AbortSignal.timeout(15_000),
|
|
headers: { ...extraHeaders, Authorization: `Bearer ${key.token}`, "content-type": "application/json" }, ...(body === undefined ? {} : { body: JSON.stringify(body) }) });
|
|
if (response.ok) { await response.body?.cancel(); return { status: response.status }; }
|
|
const error = await response.json().then(value => (value as { error?: unknown }).error, () => undefined);
|
|
return { status: response.status, ...(typeof error === "string" ? { error } : {}) };
|
|
}
|
|
export async function readAgentResource(ctx: ChatCatalogContext, path: string): Promise<{ status: number; data?: unknown }> {
|
|
const target = new URL(path, ctx.input.api.baseURL);
|
|
if (target.origin !== ctx.input.api.baseURL || !target.pathname.startsWith("/api/")) throw new Error("Agent read escaped fixture API");
|
|
const key = await identityProbeKey(ctx);
|
|
const response = await fetch(target, { redirect: "error", signal: AbortSignal.timeout(15_000), headers: { Authorization: `Bearer ${key.token}` } });
|
|
if (!response.ok) { await response.body?.cancel(); return { status: response.status }; }
|
|
return { status: response.status, data: await response.json() };
|
|
}
|
|
export async function followRenderedLink(ctx: ChatCatalogContext, href: string) {
|
|
const link = ctx.input.page.locator(`[id^="comment-"] a[href=${JSON.stringify(href)}]`).first();
|
|
await expect(link).toBeVisible(); await link.click();
|
|
}
|