mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:55:46 +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>
34 lines
4.1 KiB
TypeScript
34 lines
4.1 KiB
TypeScript
import { afterEach, expect, it, vi } from "vitest";
|
|
import type { APIRequestContext } from "@playwright/test";
|
|
import { RunnerApi, RunnerApiHttpError } from "./api.js";
|
|
afterEach(() => { vi.unstubAllGlobals(); vi.unstubAllEnvs(); });
|
|
function fixture() { vi.stubEnv("PAPERCLIP_RUNNER_E2E_PORT", "3100"); const instrumented = { get: vi.fn(), post: vi.fn(), patch: vi.fn(), delete: vi.fn(), put: vi.fn() }; const api = new RunnerApi(instrumented as unknown as APIRequestContext); api.setBrowserSession("synthetic-session-cookie-928364"); return { api, instrumented }; }
|
|
it("keeps cookie requests outside Test while preserving actual query/body/JSON and attachment bytes", async () => {
|
|
const { api, instrumented } = fixture(); const calls: Array<{ url: string; options: RequestInit }> = [];
|
|
vi.stubGlobal("fetch", vi.fn(async (url: URL, options: RequestInit) => { calls.push({ url: url.href, options }); return url.pathname.endsWith("/content") ? new Response(Buffer.from([0, 1, 255])) : Response.json({ actualProductValue: "unredacted-product-oracle-canary" }); }));
|
|
await expect(api.get("/api/issues?limit=2", { timeout: 1234 })).resolves.toEqual({ actualProductValue: "unredacted-product-oracle-canary" });
|
|
await api.post("/api/issues", { title: "synthetic" }); await api.patch("/api/issues/one", { status: "backlog" }); await api.delete("/api/issues/one");
|
|
await expect(api.getAttachmentContent("11111111-1111-4111-8111-111111111111")).resolves.toEqual(Buffer.from([0, 1, 255]));
|
|
expect(calls[0]?.url).toBe("http://127.0.0.1:3100/api/issues?limit=2"); expect(calls.map(call => call.options.method)).toEqual(["GET", "POST", "PATCH", "DELETE", "GET"]);
|
|
expect(calls[1]?.options.body).toBe(JSON.stringify({ title: "synthetic" }));
|
|
for (const call of calls) { expect(call.options.redirect).toBe("error"); expect(call.options.headers).toMatchObject({ Cookie: "synthetic-session-cookie-928364", Origin: "http://127.0.0.1:3100" }); }
|
|
for (const method of Object.values(instrumented)) expect(method).not.toHaveBeenCalled();
|
|
});
|
|
it("rejects cross-origin/path escapes before transport and withholds status/error response bodies", async () => {
|
|
const { api } = fixture(); const transport = vi.fn(async () => new Response("private-response-canary-123456", { status: 403 })); vi.stubGlobal("fetch", transport);
|
|
await expect(api.get("https://foreign.invalid/api/issues")).rejects.toThrow("fixture API"); await expect(api.post("/api/../private", {})).rejects.toThrow("fixture API"); expect(transport).not.toHaveBeenCalled();
|
|
const failure = await api.get("/api/private?private=value").catch(error => error); expect(failure).toBeInstanceOf(RunnerApiHttpError); if (!(failure instanceof RunnerApiHttpError)) throw new Error("Expected typed HTTP status"); expect(failure.status).toBe(403);
|
|
expect(failure.message).toBe("GET /api/private returned 403; body withheld"); expect(failure.message).not.toContain("private-response-canary");
|
|
await expect(api.delete("/api/missing", { allowNotFound: true })).rejects.toThrow("403");
|
|
transport.mockImplementation(async () => new Response(null, { status: 404 })); await expect(api.delete("/api/missing", { allowNotFound: true })).resolves.toBeUndefined();
|
|
transport.mockImplementation(async () => { throw new Error("synthetic-session-cookie-928364 private network error"); });
|
|
await expect(api.get("/api/issues")).rejects.toThrow("details withheld");
|
|
});
|
|
it("uses sensitive PATCH outside Test with same session boundary and no raw parse or error diagnostics", async () => {
|
|
const { api, instrumented } = fixture(); const transport = vi.fn(async (_url: URL, _options: RequestInit) => Response.json({ saved: true })); vi.stubGlobal("fetch", transport);
|
|
await expect(api.patchSensitive("/api/agents/one", { privateReference: "synthetic-value" })).resolves.toEqual({ saved: true });
|
|
expect(transport.mock.calls[0]?.[1]).toMatchObject({ method: "PATCH", redirect: "error", body: JSON.stringify({ privateReference: "synthetic-value" }) }); expect(instrumented.patch).not.toHaveBeenCalled();
|
|
transport.mockImplementation(async () => new Response("not-json-private-value"));
|
|
await expect(api.patchSensitive("/api/agents/one", {})).rejects.toThrow("response body withheld");
|
|
});
|