mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 07:12:00 +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>
76 lines
6.4 KiB
TypeScript
76 lines
6.4 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
import { describe, expect, it, vi } from "vitest";
|
|
import type { ChatCatalogContext } from "./chat-catalog-contract.js";
|
|
import { uploadFactualQueryAttachment, type ChatQueryAttachmentReceipt } from "./chat-query-attachments.js";
|
|
import { buildPaperclipTaskMarkdown } from "../../server/src/services/heartbeat/task-markdown.js";
|
|
vi.mock("@playwright/test", () => ({ expect: () => ({ toBeVisible: async () => {}, toContainText: async () => {}, not: { toContainText: async () => {} } }) }));
|
|
const id = "11111111-1111-4111-8111-111111111111";
|
|
function fixture() {
|
|
const body = "Destination: Synthetic Launch Notes, launch page.\nThe public launch is November 8, 2030.";
|
|
let uploaded: ChatQueryAttachmentReceipt | undefined;
|
|
const state = { patch: {} as Partial<ChatQueryAttachmentReceipt>, changedBytes: false, humanId: "human", deploymentMode: "authenticated", existing: false };
|
|
const inputFile = vi.fn(async (file: { name: string; buffer: Buffer }) => {
|
|
uploaded = { id, companyId: "company", issueId: "source", issueCommentId: null, originalFilename: file.name, contentPath: `/api/attachments/${id}/content`, byteSize: file.buffer.length,
|
|
sha256: createHash("sha256").update(file.buffer).digest("hex"), createdByUserId: "human", createdByAgentId: null, ...state.patch };
|
|
});
|
|
const post = vi.fn(async () => ({})); const evidence = vi.fn(async () => undefined);
|
|
const page = { goto: vi.fn(async () => undefined), getByTestId: () => ({}), locator: () => ({ first: () => ({ setInputFiles: inputFile }) }) };
|
|
const api = { baseURL: "http://fixture.test", post,
|
|
get: vi.fn(async (path: string) => path === "/api/health" ? { deploymentMode: state.deploymentMode } : path === "/api/auth/get-session" ? { user: state.humanId ? { id: state.humanId } : undefined }
|
|
: uploaded ? [uploaded] : state.existing ? [{ originalFilename: "launch-update.md" }] : []),
|
|
getAttachmentContent: vi.fn(async () => Buffer.from(state.changedBytes ? "Different launch data" : body)) };
|
|
const ctx = { scenario: { id: "app-permissions.ask-before-action" }, input: { api, page, evidence, fixtures: { company: { id: "company", issuePrefix: "RUN" }, agent: { id: "ceo" } } },
|
|
refreshIssue: vi.fn(async () => undefined), issue: () => ({ id: "source" }) } as unknown as ChatCatalogContext;
|
|
return { ctx, state, body, inputFile, evidence, post, page };
|
|
}
|
|
describe("genuine factual canonical query input", () => {
|
|
it("uses the production native context's wake attachment descriptor while conversation descriptions remain suppressed", () => {
|
|
const hiddenDescription = "This incidental chat description is not the person's current input.";
|
|
const markdown = buildPaperclipTaskMarkdown({ issue: { id: "source", identifier: "RUN-1", title: "Chat with CEO", conversationAgentId: "ceo", description: hiddenDescription },
|
|
nativeRunner: true, wakeComments: [{ id: "canonical", body: "Original canonical request\n\n[launch-update.md](/api/attachments/" + id + "/content)",
|
|
attachments: [{ id, filename: "launch-update.md", contentType: "text/markdown", byteSize: 100, contentPath: `/api/attachments/${id}/content` }] }] });
|
|
expect(markdown).not.toContain(hiddenDescription);
|
|
expect(markdown).toContain('Attachments on wake comment "canonical"');
|
|
expect(markdown).toContain('"id":"' + id + '"');
|
|
expect(markdown).toContain('"filename":"launch-update.md"');
|
|
expect(markdown).toContain("Original canonical request");
|
|
});
|
|
it("uploads actual draft facts with independently read bytes and human/source identity without sending a comment", async () => {
|
|
const f = fixture(); const receipt = await uploadFactualQueryAttachment(f.ctx, { filename: "launch-update.md", body: f.body });
|
|
expect(receipt).toMatchObject({ id, createdByUserId: "human", issueId: "source", issueCommentId: null });
|
|
expect(f.inputFile.mock.calls[0]![0].buffer.toString("utf8")).toBe(f.body);
|
|
expect(f.post).toHaveBeenCalledExactlyOnceWith("/api/companies/company/chats/ceo");
|
|
expect(f.page.goto).toHaveBeenCalledExactlyOnceWith("http://fixture.test/RUN/chats/ceo", { waitUntil: "domcontentloaded" });
|
|
expect(f.evidence).toHaveBeenCalledWith("chat-catalog-factual-query-input.json", expect.objectContaining({ body: f.body }));
|
|
expect(f.body).not.toMatch(/approval|ask.first|call_api|execute|expected|tool/);
|
|
});
|
|
it.each(["company", "source", "human", "agent", "bytes", "bound-comment"]) ("rejects plausible wrong %s upload provenance", async kind => {
|
|
const f = fixture();
|
|
if (kind === "company") f.state.patch.companyId = "foreign";
|
|
if (kind === "source") f.state.patch.issueId = "different-source";
|
|
if (kind === "human") f.state.patch.createdByUserId = "other-human";
|
|
if (kind === "agent") f.state.patch.createdByAgentId = "agent";
|
|
if (kind === "bytes") f.state.changedBytes = true;
|
|
if (kind === "bound-comment") f.state.patch.issueCommentId = "pre-existing-comment";
|
|
await expect(uploadFactualQueryAttachment(f.ctx, { filename: "launch-update.md", body: f.body })).rejects.toThrow("bytes/source/human");
|
|
expect(f.evidence).not.toHaveBeenCalled();
|
|
});
|
|
it("rejects trusted-local/fake-user input and duplicate pre-existing context", async () => {
|
|
const noPerson = fixture(); noPerson.state.humanId = "";
|
|
await expect(uploadFactualQueryAttachment(noPerson.ctx, { filename: "launch-update.md", body: noPerson.body })).rejects.toThrow("real authenticated human");
|
|
expect(noPerson.inputFile).not.toHaveBeenCalled();
|
|
const implicit = fixture(); implicit.state.deploymentMode = "local_trusted";
|
|
await expect(uploadFactualQueryAttachment(implicit.ctx, { filename: "launch-update.md", body: implicit.body })).rejects.toThrow("real authenticated human");
|
|
expect(implicit.inputFile).not.toHaveBeenCalled();
|
|
const duplicate = fixture(); duplicate.state.existing = true;
|
|
await expect(uploadFactualQueryAttachment(duplicate.ctx, { filename: "launch-update.md", body: duplicate.body })).rejects.toThrow("already exists");
|
|
});
|
|
it("does not authorize arbitrary cases or wrong file identities", async () => {
|
|
const f = fixture();
|
|
await expect(uploadFactualQueryAttachment(f.ctx, { filename: "selected-source.md", body: f.body })).rejects.toThrow("Undeclared");
|
|
f.ctx.scenario.id = "documents-artifacts.find-artifact";
|
|
await expect(uploadFactualQueryAttachment(f.ctx, { filename: "launch-update.md", body: f.body })).rejects.toThrow("Undeclared");
|
|
expect(f.post).not.toHaveBeenCalled();
|
|
});
|
|
});
|