Files
PaperClipAI/tests/runner-e2e/chat-catalog-domains/internal-document-context.test.ts
T
f4337bb5fb test(evals): land the chat catalog eval harness on master (#19614)
## 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>
2026-11-10 08:02:11 -06:00

74 lines
5.5 KiB
TypeScript

import { describe, expect, it, vi } from "vitest";
import type { ChatCatalogContext } from "../chat-catalog-contract.js";
import type { IssueAttachment } from "../../../packages/shared/src/types/issue.js";
import { selectDocumentSource } from "./internal-document-context.js";
import { uploadFactualQueryAttachment } from "../chat-query-attachments.js";
vi.mock("../chat-query-attachments.js", () => ({ uploadFactualQueryAttachment: vi.fn(async () => ({ id: "factual-upload" })) }));
function fixture() {
const target = { id: "target", companyId: "company", projectId: "project", identifier: "RUN-1", title: "Website task" };
const source = { id: "chat", companyId: "company", projectId: null as string | null, description: null as string | null };
const document = { id: "doc", issueId: "target", key: "plan", title: "Implementation plan", latestRevisionId: "revision", body: "Original pricing bytes" };
const annotation = { id: "comment", documentId: "doc", originalRevisionId: "revision", status: "open" };
const attachment = { id: "file", issueId: "target", sha256: "original-hash", originalFilename: "website-v1.html", contentPath: "/api/attachments/file/content" } as IssueAttachment;
const api = {
get: vi.fn(async (path: string) => {
if (path === "/api/issues/target") return structuredClone(target);
if (path === "/api/issues/chat") return structuredClone(source);
if (path.endsWith("/annotations?status=all&includeComments=true")) return [structuredClone(annotation)];
if (path.endsWith("/documents/plan")) return structuredClone(document);
if (path.endsWith("/attachments")) return [structuredClone(attachment)];
throw new Error(`Unexpected read ${path}`);
}),
post: vi.fn(async () => ({})),
patch: vi.fn(async (_path: string, value: object) => Object.assign(source, value)),
};
const evidence = vi.fn(async () => undefined);
const ctx = { input: { api, fixtures: { company: { id: "company", issuePrefix: "RUN" }, agent: { id: "ceo" } }, evidence },
refreshIssue: vi.fn(async () => undefined), issue: () => source } as unknown as ChatCatalogContext;
return { ctx, target, source, document, annotation, attachment, api, evidence };
}
describe("factual visible document source selection", () => {
it("persists the selected task/document/comment on the real chat without copying an answer or editing the target", async () => {
const f = fixture(); const original = structuredClone({ document: f.document, annotation: f.annotation });
const receipt = await selectDocumentSource(f.ctx, { task: f.target, document: f.document, annotationId: f.annotation.id });
expect(f.source.description).toBe("Selected source: [Website task](/RUN/issues/RUN-1).\n\nSelected document: [Implementation plan](/RUN/issues/RUN-1#document-plan).\n\nSelected review comment: comment on this document.");
expect(receipt.targetIssueId).toBe("target");
expect(uploadFactualQueryAttachment).toHaveBeenLastCalledWith(f.ctx, { filename: "selected-source.md", body: f.source.description });
expect(receipt.factualContextAttachment.id).toBe("factual-upload");
expect({ document: f.document, annotation: f.annotation }).toEqual(original);
expect(f.api.patch).toHaveBeenCalledExactlyOnceWith("/api/issues/chat", { projectId: "project", description: f.source.description });
expect(f.api.post).toHaveBeenCalledExactlyOnceWith("/api/companies/company/chats/ceo");
expect(f.evidence).toHaveBeenCalledOnce();
});
it("selects an existing revision without supplying which historical contents to restore", async () => {
const f = fixture(); await selectDocumentSource(f.ctx, { task: f.target, document: f.document });
expect(f.source.description).toContain("#document-plan");
expect(f.source.description).not.toMatch(/pricing|revision|restore|previous|Original/);
});
it("selects the actual original delivery and preserves its original bytes", async () => {
const f = fixture(); await selectDocumentSource(f.ctx, { task: f.target, attachment: f.attachment });
expect(f.source.description).toContain("[website-v1.html](/api/attachments/file/content)");
expect(f.source.description).not.toMatch(/headline|shorten|new version/);
expect(f.api.patch.mock.calls.every(([path]) => path === "/api/issues/chat")).toBe(true);
});
it("names the generated workspace source without pre-registering the requested delivery", async () => {
const f = fixture(); await selectDocumentSource(f.ctx, { task: f.target, workspaceFilename: "website.html" });
expect(f.source.description).toContain("Selected workspace file: website.html");
expect(f.source.description).not.toMatch(/attachments|download|upload|register/);
expect(f.api.post).toHaveBeenCalledOnce();
});
it.each(["company", "project", "revision", "annotation", "attachment", "persist"]) ("rejects plausible wrong %s evidence before the canonical turn", async kind => {
const f = fixture(); const input = { task: structuredClone(f.target), document: { ...f.document }, annotationId: "comment", attachment: { ...f.attachment } };
if (kind === "company") f.target.companyId = "foreign";
if (kind === "project") f.target.projectId = "other-project";
if (kind === "revision") f.document.latestRevisionId = "other-revision";
if (kind === "annotation") f.annotation.documentId = "other-doc";
if (kind === "attachment") f.attachment.sha256 = "different-bytes";
if (kind === "persist") f.api.patch.mockImplementation(async () => f.source);
await expect(selectDocumentSource(f.ctx, input)).rejects.toThrow();
expect(f.evidence).not.toHaveBeenCalled();
});
});