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>
49 lines
5.3 KiB
TypeScript
49 lines
5.3 KiB
TypeScript
import { expect, it, vi } from "vitest";
|
|
vi.mock("@playwright/test", () => ({ expect: (target: { isDisabled?: () => boolean; isVisible?: () => boolean }) => ({
|
|
toBeDisabled: async () => { if (!target.isDisabled?.()) throw new Error("Expected actual disabled Next"); },
|
|
toBeVisible: async () => { if (!target.isVisible?.()) throw new Error("Expected current first question visible"); },
|
|
}) }));
|
|
import { questionIdentityCases } from "./chat-catalog-domains/identity-questions-and-approvals.js";
|
|
import type { ChatCatalogContext } from "./chat-catalog-contract.js";
|
|
function fixture(options: { advancesMissing?: boolean; missingValidation?: boolean; createsWork?: boolean; resumesWork?: boolean; wrongPrompt?: boolean; changedPayload?: boolean; prematurelyResolved?: boolean } = {}) {
|
|
let page = 0, answered = false, reads = 0, submitted = false, attemptedMissing = false;
|
|
const clicks: string[] = [], answers: Record<string, string> = {};
|
|
const original = { id: "question", companyId: "company", issueId: "source", kind: "ask_user_questions", status: "pending", payload: { questionSet: { questions: [
|
|
{ id: "audience", prompt: "Who is the audience?", required: true }, { id: "tone", prompt: "What tone should we use?", required: true }, { id: "headline", prompt: "What is your custom headline?", required: true },
|
|
] } } };
|
|
const form: any = { isVisible: () => true, getByText: (prompt: string) => ({ isVisible: () => prompt === "This question is required."
|
|
? attemptedMissing && !options.missingValidation : !options.wrongPrompt && prompt === original.payload.questionSet.questions[page]?.prompt }),
|
|
getByRole: (_role: string, { name }: { name: string | RegExp }) => ({
|
|
isDisabled: () => false,
|
|
isChecked: () => answers.audience === "Researchers",
|
|
click: async () => { const label = String(name); clicks.push(label);
|
|
if (label === "Next") { if (!answered) { attemptedMissing = true; if (options.advancesMissing) page++; return; } page++; answered = !!answers[original.payload.questionSet.questions[page]?.id ?? ""]; }
|
|
else if (label === "Previous question") { page--; answered = !!answers[original.payload.questionSet.questions[page]!.id]; }
|
|
else if (label === "Researchers" || label === "Clear") { answers[original.payload.questionSet.questions[page]!.id] = label; answered = true; }
|
|
else { if (page !== 2 || !answers.headline) throw new Error("Cannot submit incomplete questions"); submitted = true; }
|
|
},
|
|
}),
|
|
getByTestId: () => ({ isVisible: async () => page === 2, locator: () => ({ first: () => ({ fill: async (value: string) => { answers.headline = value; } }) }) }),
|
|
};
|
|
const query = "Help me choose the details for the launch page before you build it.";
|
|
const ctx = { observationDeadlineAt: Date.now() + 300_000, scenario: { query }, issue: () => ({ id: "source", conversationState: "waiting" }), refreshIssue: async () => {}, allRuns: async () => [{ id: "native", companyId: "company", agentId: "ceo", contextSnapshot: { issueId: "source", commentId: "human" }, status: "succeeded" }, ...(options.resumesWork && attemptedMissing ? [{ id: "forbidden-continuation", status: "running" }] : [])],
|
|
input: { fixtures: { company: { id: "company" }, agent: { id: "ceo" } }, page: { locator: () => ({ click: async () => {} }), getByTestId: () => form }, api: { get: async (url: string) => {
|
|
if (url.endsWith("comments?order=asc")) return [{ id: "human", issueId: "source", authorUserId: "person", body: query }];
|
|
if (url.endsWith("interactions")) { reads++; return [{ ...original, status: options.prematurelyResolved ? "resolved" : "pending", payload: options.changedPayload && reads >= 2 ? { replaced: true } : original.payload }]; }
|
|
return options.createsWork && attemptedMissing && url.includes("/issues?") ? [{ id: "forbidden-work" }] : [];
|
|
} } },
|
|
} as unknown as ChatCatalogContext;
|
|
return { ctx, state: { sourceId: "source", original, answer: "Acorn unchanged human answer" } as Record<string, unknown>, clicks, answers, submitted: () => submitted };
|
|
}
|
|
it("actual multipart act clicks enabled Next to observe required blocking, retains earlier choice and submits the exact supplied answer", async () => {
|
|
const f = fixture(), c = questionIdentityCases.find(row => row.scenarioId === "questions-and-approvals.multi-part-question")!;
|
|
await c.act!(f.ctx, f.state);
|
|
expect(f.state.validationObserved).toBe(true); expect(f.state.retainedAudience).toBe(true); expect(f.state.unsubmittedPending).toBe(true);
|
|
expect(f.clicks).toEqual(["Next", "Researchers", "Next", "Previous question", "Next", "Clear", "Next", "/^(Submit|Send) answers$/"]);
|
|
expect(f.answers).toEqual({ audience: "Researchers", tone: "Clear", headline: "Acorn unchanged human answer" }); expect(f.submitted()).toBe(true);
|
|
});
|
|
it.each([{ advancesMissing: true }, { missingValidation: true }, { createsWork: true }, { resumesWork: true }, { wrongPrompt: true }, { changedPayload: true }, { prematurelyResolved: true }])("rejects invalid current required-question proof %j before any answer", async options => {
|
|
const f = fixture(options), c = questionIdentityCases.find(row => row.scenarioId === "questions-and-approvals.multi-part-question")!;
|
|
await expect(c.act!(f.ctx, f.state)).rejects.toThrow(); expect(f.clicks.every(click => click === "Next")).toBe(true); expect(f.answers).toEqual({}); expect(f.submitted()).toBe(false);
|
|
});
|