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>
65 lines
3.6 KiB
TypeScript
65 lines
3.6 KiB
TypeScript
import { afterEach, expect, it, vi } from "vitest";
|
|
import type { ChatCatalogContext } from "../chat-catalog-contract.js";
|
|
|
|
const port = vi.hoisted(() => ({ now: 45_000, deadlines: [] as number[] }));
|
|
vi.mock("../codex-subscription-fixture.js", () => ({ codexSubscriptionAgentConfig: (value: unknown) => value }));
|
|
vi.mock("../api.js", () => ({ pollUntil: async (options: {
|
|
deadlineAt: number; load(): Promise<unknown>; accept(value: unknown): boolean; reject?(value: unknown): string | undefined;
|
|
}) => {
|
|
port.deadlines.push(options.deadlineAt);
|
|
while (Date.now() < options.deadlineAt) {
|
|
const value = await options.load();
|
|
const rejected = options.reject?.(value);
|
|
if (rejected) throw Error(rejected);
|
|
if (options.accept(value)) return value;
|
|
port.now += 10_000;
|
|
}
|
|
throw Error("Synthetic observer deadline reached");
|
|
} }));
|
|
import { runtimePrimaryCases } from "./runtime-primary.js";
|
|
afterEach(() => vi.restoreAllMocks());
|
|
|
|
type Options = { deadline?: number | "missing"; terminal?: "succeeded" | "running" | "failed" | "cancelled";
|
|
readyAt?: number; lateLoad?: boolean; noWork?: boolean; extraRun?: boolean };
|
|
function fixture(options: Options = {}) {
|
|
port.now = 45_000; port.deadlines.splice(0);
|
|
vi.spyOn(Date, "now").mockImplementation(() => port.now);
|
|
const deadline = options.deadline === undefined ? 300_000 : options.deadline;
|
|
const readyAt = options.readyAt ?? 215_000;
|
|
const get = vi.fn(async () => { throw Error("Reached human preference step"); });
|
|
const ctx = {
|
|
...(deadline === "missing" ? {} : { observationDeadlineAt: deadline }),
|
|
input: { api: { get }, fixtures: { company: { id: "company" }, agent: { id: "ceo" } } },
|
|
issue: () => ({ id: "source", conversationState: port.now >= readyAt ? "waiting" : "active" }),
|
|
refreshIssue: vi.fn(async () => {}),
|
|
allRuns: vi.fn(async () => {
|
|
if (options.lateLoad) port.now = 300_001;
|
|
if (options.noWork) return [];
|
|
return [{ id: "native", companyId: "company", agentId: "ceo",
|
|
status: port.now >= readyAt ? options.terminal ?? "succeeded" : "running" },
|
|
...(options.extraRun ? [{ id: "unexpected", status: "succeeded" }] : [])];
|
|
}),
|
|
} as unknown as ChatCatalogContext;
|
|
return { ctx, get };
|
|
}
|
|
it("owning act observes a delayed real completion only within the remaining original300s before the first human preference action", async () => {
|
|
const f = fixture();
|
|
await expect(runtimePrimaryCases[0]!.act!(f.ctx, {})).rejects.toThrow("Reached human preference step");
|
|
expect(port.deadlines).toEqual([300_000]);
|
|
expect(port.now).toBeGreaterThan(195_000); // old150s allowance from45s setup boundary
|
|
expect(port.now).toBeLessThan(300_000);
|
|
expect(f.get).toHaveBeenCalledExactlyOnceWith("/api/companies/company/primary-agent/me");
|
|
});
|
|
it.each([{ deadline: "missing" }, { deadline: NaN }, { deadline: Infinity }, { deadline: 44_999 }])("owning act refuses unavailable or expired originalclock before native reads %j", async options => {
|
|
const f = fixture(options as Options);
|
|
await expect(runtimePrimaryCases[0]!.act!(f.ctx, {})).rejects.toThrow();
|
|
expect(f.ctx.allRuns).not.toHaveBeenCalled();
|
|
expect(f.get).not.toHaveBeenCalled();
|
|
});
|
|
it.each([{ terminal: "running" }, { terminal: "failed" }, { terminal: "cancelled" }, { noWork: true }, { extraRun: true }, { lateLoad: true }, { readyAt: 300_001 }])("owning act rejects unfinished, invalid or late work before human state changes %j", async options => {
|
|
const f = fixture(options as Options);
|
|
await expect(runtimePrimaryCases[0]!.act!(f.ctx, {})).rejects.toThrow();
|
|
expect(f.get).not.toHaveBeenCalled();
|
|
expect(port.deadlines).toEqual([300_000]);
|
|
});
|