Files
PaperClipAI/tests/runner-e2e/chat-catalog-domains/runtime-multiple-handoffs.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

50 lines
5.7 KiB
TypeScript

import { expect, it } from "vitest";
import { gradeMultipleHandoffs, promptCarriesComment } from "./runtime-multiple-handoffs.js";
function valid() {
const logo = { id: "logo", identifier: "RUN-1", title: "Logo", companyId: "company", status: "done", assigneeAgentId: "riley" };
const artifact = { contentVerified: true, attachmentId: "logo-file", sha256: "same", content: "<svg><text>Acorn real-marker</text></svg>" };
return { scenarioId: "agent-chat.multiple-handoffs", companyId: "company", leadId: "ceo", agents: [], links: [], activity: [], humanQueries: [], reply: "",
tasks: [logo, { id: "8ba8b5a2-066a-4bb2-b591-e396942ecdf5", assigneeAgentId: "morgan", status: "done" }],
runs: [{ id: "logo-run", agentId: "riley", status: "succeeded" }, { id: "prior", agentId: "morgan", status: "succeeded" },
{ id: "setup", agentId: "ceo", status: "succeeded" }, { id: "canonical", agentId: "ceo", status: "succeeded" }, { id: "consumer", agentId: "morgan", status: "succeeded" }],
state: { task: { id: "8ba8b5a2-066a-4bb2-b591-e396942ecdf5", identifier: "RUN-2" }, worker: { id: "morgan" }, logoWorker: { id: "riley" }, workerRunId: "prior", canonicalRunId: "canonical",
queueAtReply: { issueId: "8ba8b5a2-066a-4bb2-b591-e396942ecdf5", targetRunId: "prior", state: "queued", entries: [{ comment: { id: "headline", authorAgentId: "ceo", createdByRunId: "canonical", body: "Change the headline to Launch sooner." } }] },
sourceHistoryBound: true, workerRunningAtReply: true, nativeDeliveryBound: true, queueEmptyAfterDelivery: true, logoBefore: logo, logoAfter: structuredClone(logo),
logoArtifactBefore: artifact, logoArtifactAfter: { ...artifact }, logoMarker: "real-marker", logoRevisionsUnchanged: true,
queryReply: "I saved the headline feedback on [RUN-2](/RUN/issues/RUN-2) while Morgan is busy. The logo [RUN-1](/RUN/issues/RUN-1) remains unchanged.",
finalHeadlineRevision: true, originalWebsiteRevisionRetained: true } };
}
it("accepts one Website delivery with real completed Logo preservation", () => expect(gradeMultipleHandoffs(valid()).passed).toBe(true));
it("accepts reworded replies that name the affected task by identifier or link", () => {
for (const reply of ["RUN-2's new headline requirement will wait for Morgan's next turn; I left Riley's completed logo alone.",
"Morgan will pick up \"Launch sooner\" when the current turn ends: [Website task](/RUN/issues/RUN-2#comment-headline).",
"Queued for Morgan on RUN-2. Nothing changed on RUN-1."]) {
const o = valid(); o.state.queryReply = reply; expect(gradeMultipleHandoffs(o).passed).toBe(true);
}
});
it("rejects a reply that does not name the affected Website task", () => {
for (const reply of ["I saved the headline change for the website.", "Saved on RUN-20 for Morgan.", "The logo RUN-1 is unchanged."]) {
const o = valid(); o.state.queryReply = reply; expect(gradeMultipleHandoffs(o).passed).toBe(false);
}
});
it("rejects missing independent two-task evidence", () => expect(gradeMultipleHandoffs(undefined).passed).toBe(false));
it("rejects routing headline feedback to Logo instead", () => { const o = valid(); o.state.queueAtReply.issueId = "logo"; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects duplicate saved headline requirements", () => { const o = valid(); o.state.queueAtReply.entries.push({ ...o.state.queueAtReply.entries[0]! }); expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects feedback attributed to the earlier source setup turn", () => { const o = valid(); o.state.queueAtReply.entries[0]!.comment.createdByRunId = "setup"; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects a consuming run without the exact saved comment", () => { const o = valid(); o.state.nativeDeliveryBound = false; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects changing the actual delivered Logo bytes", () => { const o = valid(); o.state.logoArtifactAfter.content = "<svg>new</svg>"; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects retaining a Logo filename but replacing its artifact", () => { const o = valid(); o.state.logoArtifactAfter.attachmentId = "replacement"; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects erasing an earlier Logo revision", () => { const o = valid(); o.state.logoRevisionsUnchanged = false; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects a reply written after the active worker stopped holding the saved instruction", () => { const o = valid(); o.state.workerRunningAtReply = false; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects redirection to a different worker", () => { const o = valid(); o.tasks[1]!.assigneeAgentId = "riley"; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("rejects losing the original Website work", () => { const o = valid(); o.state.originalWebsiteRevisionRetained = false; expect(gradeMultipleHandoffs(o).passed).toBe(false); });
it("finds a delivered comment in a native continuation that embeds it as JSON", () => {
const comment = { id: "b9e3ab32-934e-4d07-a5cf-e06fc28d574a", body: 'The headline must be **"Launch sooner"** — nothing else.\nKeep the logo.' };
const prompt = `## Paperclip Wake Payload\n${JSON.stringify({ messages: [{ id: comment.id, authorType: "agent", body: comment.body }] })}`;
expect(promptCarriesComment(prompt, comment)).toBe(true);
expect(promptCarriesComment(`plain ${comment.id}\n${comment.body}`, comment)).toBe(true);
expect(promptCarriesComment(prompt.replace(comment.id, "other"), comment)).toBe(false);
expect(promptCarriesComment(prompt.replace("Launch sooner", "Launch later"), comment)).toBe(false);
expect(promptCarriesComment(undefined, comment)).toBe(false);
});