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>
61 lines
6.4 KiB
TypeScript
61 lines
6.4 KiB
TypeScript
import { describe, expect, it, vi } from "vitest";
|
|
import { uploadFactualQueryAttachment } from "../chat-query-attachments.js";
|
|
vi.mock("../chat-query-attachments.js", async importOriginal => ({ ...await importOriginal<typeof import("../chat-query-attachments.js")>(), uploadFactualQueryAttachment: vi.fn(async () => ({ id: "customer-brief-upload" })) }));
|
|
import { customerBugFacts, preservesCustomerBugFacts, gradeIntegratorCaseCreation, integratorCaseCreationCases } from "./integrator-case-create.js";
|
|
function valid() {
|
|
const brief = { id: "brief", issueId: "primary", companyId: "company", key: "brief", body: Object.values(customerBugFacts).join("\n") };
|
|
const workflow = { id: "workflow", issueId: "primary", companyId: "company", key: "workflow", body: "Morgan investigates, saves findings, then hands this same primary task to its next owner for review." };
|
|
const revision = (doc: typeof brief) => ({ id: `${doc.id}-revision`, documentId: doc.id, issueId: "primary", key: doc.key, body: doc.body, createdByAgentId: "ceo", createdByRunId: "source-run", createdAt: "2026-10-26T12:00:00Z" });
|
|
return { scenarioId: "cases.create-case", origin: "https://fixture.test", companyId: "company", leadId: "ceo", state: { project: { id: "project" }, task: { id: "source-brief" }, worker: { id: "morgan" } },
|
|
tasks: [{ id: "source-brief", title: "Customer bug brief" }, { id: "primary", companyId: "company", title: "Customer checkout bug", assigneeAgentId: "morgan" }], projects: [], goals: [], comments: [], documents: [], revisions: [], humanQueries: [], activity: [], reply: "Created the case and started Morgan's investigation on its primary task.", links: ["/ACORN/cases/case", "/ACORN/issues/primary"],
|
|
cases: [{ id: "case", companyId: "company", projectId: "project", workIssueId: "primary", fields: structuredClone(customerBugFacts) }],
|
|
handoffs: { case: [{ id: "kickoff", caseId: "case", version: 1, issueId: "primary", toAgentId: "morgan", actorId: "ceo", sourceRunId: "source-run", state: "delivered" }] }, taskDocuments: { primary: [workflow, brief] },
|
|
documentVersions: { "primary:workflow": [revision(workflow)], "primary:brief": [revision(brief)] },
|
|
runs: [{ id: "source-run", agentId: "ceo", status: "succeeded" }, { id: "investigation", agentId: "morgan", status: "running", contextSnapshot: { issueId: "primary" }, startedAt: "2026-10-26T12:01:00Z" }] };
|
|
}
|
|
describe("real case kickoff independent controls", () => {
|
|
it("requires the real primary task, first Morgan dispatch and original saved documents", () => {
|
|
expect(gradeIntegratorCaseCreation(valid()).passed).toBe(true);
|
|
expect(gradeIntegratorCaseCreation(undefined).passed).toBe(false);
|
|
const passive = valid(); passive.cases[0]!.workIssueId = "";
|
|
expect(gradeIntegratorCaseCreation(passive).passed).toBe(false);
|
|
const late = valid(); late.documentVersions["primary:brief"][0]!.createdAt = "2026-10-26T12:02:00Z";
|
|
expect(gradeIntegratorCaseCreation(late).passed).toBe(false);
|
|
const otherOwner = valid(); otherOwner.taskDocuments.primary[1]!.issueId = "source-brief";
|
|
expect(gradeIntegratorCaseCreation(otherOwner).passed).toBe(false);
|
|
const wrongWorker = valid(); wrongWorker.handoffs.case[0]!.toAgentId = "riley";
|
|
expect(gradeIntegratorCaseCreation(wrongWorker).passed).toBe(false);
|
|
const repaired = valid(); repaired.documentVersions["primary:brief"][0]!.body = "Investigate a bug.";
|
|
expect(gradeIntegratorCaseCreation(repaired).passed).toBe(false);
|
|
expect(gradeIntegratorCaseCreation({ ...valid(), links: ["/ACORN/cases/case"] }).passed).toBe(false);
|
|
});
|
|
it("accepts changed wording of factual fields but rejects swapped expected/observed behavior", () => {
|
|
const paraphrase = { customer: "Acorn Test Shop", issue: "Checkout stops responding", browser: "Safari 18 on iPhone 15", steps: ["Add the trial item", "Fill the test address", "Press Pay"], expectedBehavior: "An order confirmation should be shown", observedBehavior: "Without confirmation; customer is not charged" };
|
|
expect(preservesCustomerBugFacts(paraphrase)).toBe(true);
|
|
expect(preservesCustomerBugFacts({ ...paraphrase, expectedBehavior: "No order confirmation appears" })).toBe(false);
|
|
expect(preservesCustomerBugFacts({ ...paraphrase, browser: "Chrome on Android" })).toBe(false);
|
|
expect(preservesCustomerBugFacts({ ...paraphrase, observedBehavior: "Order confirmation appears and customer is charged" })).toBe(false);
|
|
});
|
|
});
|
|
|
|
it("places the genuine customer brief on the canonical conversation's normal document surface", async () => {
|
|
const source = { id: "standing-chat", title: "Chat with CEO" }; let saved: Record<string, unknown> | undefined;
|
|
const created: string[] = []; const patches: Array<{ path: string; body: unknown }> = [];
|
|
const api = {
|
|
get: async (path: string) => path.endsWith("/documents/brief") ? saved : path.startsWith("/api/agents/") ? { id: "morgan", companyId: "company", lifecycleState: "ready" } : { enableCases: false },
|
|
patch: async (path: string, body: unknown) => { patches.push({ path, body }); return {}; },
|
|
post: async (path: string, body: Record<string, unknown>) => { created.push(path); return { ...body, id: path.endsWith("/projects") ? "project" : "morgan" }; },
|
|
putSensitive: async (path: string, body: Record<string, unknown>) => { expect(path).toBe("/api/issues/standing-chat/documents/brief"); saved = { ...body, issueId: source.id }; return saved; },
|
|
};
|
|
const ctx = { input: { nonce: "offline", api, evidence: async () => undefined, fixtures: { company: { id: "company" }, agent: { id: "ceo" }, environment: { id: "environment" }, secretRefs: {} }, execution: { environment: { id: "local" }, profile: { credential: "ANTHROPIC_API_KEY", buildAgent: () => ({}) } } },
|
|
refreshIssue: async () => {}, issue: () => source } as unknown as Parameters<typeof integratorCaseCreationCases[0]["setup"]>[0];
|
|
const state = await integratorCaseCreationCases[0]!.setup(ctx);
|
|
expect((state.task as { id: string }).id).toBe(source.id);
|
|
expect(saved?.body).toContain(customerBugFacts.customer);
|
|
expect(uploadFactualQueryAttachment).toHaveBeenLastCalledWith(ctx, { filename: "customer-bug-brief.md", body: saved?.body });
|
|
expect((state.factualContextAttachment as { id: string }).id).toBe("customer-brief-upload");
|
|
expect(created.some(path => path.endsWith("/issues"))).toBe(false);
|
|
expect(patches).toContainEqual({ path: "/api/issues/standing-chat", body: { projectId: "project" } });
|
|
await integratorCaseCreationCases[0]!.cleanup!(ctx, state);
|
|
});
|