Files
PaperClipAI/tests/runner-e2e/chat-run-evidence-observer.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

65 lines
4.2 KiB
TypeScript

import type { RunnerApi } from "./api.js";
import type { ChatFlowInput, ChatRun } from "./chat-flow.js";
export interface OwnedChatRunEvidenceObserver {
readonly companyId: string;
readonly origin: string;
listRuns(): Promise<ChatRun[]>;
get<T>(path: string): Promise<T>;
getRunObservation<T>(path: string): Promise<T>;
}
const uuid = /^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$/i;
/** The caller freezes a genuine owner's separate authenticated client before
* changing the product actor. The returned interface exposes no mutation API. */
export function createOwnedChatRunEvidenceObserver(api: Pick<RunnerApi, "baseURL" | "get" | "getRunObservation">, companyId: string): OwnedChatRunEvidenceObserver {
if (!uuid.test(companyId)) throw new Error("Run evidence observer requires the owned company identity");
const origin = new URL(api.baseURL).origin;
if (origin !== api.baseURL) throw new Error("Run evidence observer requires an exact API origin");
const known = new Set<string>();
async function read<T>(path: string): Promise<T> {
const url = new URL(path, origin);
if (url.origin !== origin || url.username || url.password || url.hash) throw new Error("Run evidence observer escaped its origin");
const match = /^\/api\/heartbeat-runs\/([^/]+)(?:\/(events|log))?$/.exec(url.pathname);
if (!match || !uuid.test(match[1]!) || !known.has(match[1]!)) throw new Error("Run evidence requires an independently listed owned run");
const kind = match[2];
const keys = [...url.searchParams.keys()];
const allowed = !kind ? !url.search : kind === "events"
? keys.length === 2 && keys.every(key => ["afterSeq", "limit"].includes(key)) && /^\d+$/.test(url.searchParams.get("afterSeq") ?? "") && /^[1-9]\d*$/.test(url.searchParams.get("limit") ?? "")
: keys.length === 1 && url.searchParams.get("limitBytes") === "1048576";
if (!allowed) throw new Error("Run evidence observer rejected an unauthorized path or query");
const value = kind === "log" ? await api.get<T>(url.pathname + url.search) : await api.getRunObservation<T>(url.pathname + url.search);
if (!kind) {
const row = value as ChatRun;
if (row.id !== match[1] || row.companyId !== companyId) throw new Error("Run evidence detail does not match its owned list identity");
}
return value;
}
return Object.freeze({ companyId, origin, get: read, getRunObservation: read,
async listRuns() {
const rows = await api.getRunObservation<ChatRun[]>(`/api/companies/${companyId}/heartbeat-runs?limit=100`);
if (!Array.isArray(rows) || rows.some(row => !uuid.test(row.id) || row.companyId !== companyId) || new Set(rows.map(row => row.id)).size !== rows.length)
throw new Error("Run evidence list contains foreign, invalid or duplicate run identities");
known.clear(); for (const row of rows) known.add(row.id);
return Promise.all(rows.map(row => read<ChatRun>(`/api/heartbeat-runs/${row.id}`)));
},
});
}
/** This exceptional independent observer belongs to precisely one privacy case.
* Ordinary product calls always continue using input.api's actual human actor. */
export function chatRunEvidenceApi(input: Pick<ChatFlowInput, "api" | "execution" | "fixtures" | "ownedRunEvidenceObserver">): Pick<RunnerApi, "get" | "getRunObservation"> {
const observer = input.ownedRunEvidenceObserver;
if (!observer) return input.api;
if (input.execution.suite.id !== "chat-features" || input.execution.task.id !== "activity.agent-feedback"
|| observer.companyId !== input.fixtures.company.id || observer.origin !== input.api.baseURL)
throw new Error("Independent run evidence observer is outside its exact approved scenario/company/origin");
return observer;
}
export async function readChatRuns(input: Pick<ChatFlowInput, "api" | "execution" | "fixtures" | "ownedRunEvidenceObserver">): Promise<ChatRun[]> {
const api = chatRunEvidenceApi(input);
if (input.ownedRunEvidenceObserver) return input.ownedRunEvidenceObserver.listRuns();
const rows = await api.getRunObservation<ChatRun[]>(`/api/companies/${input.fixtures.company.id}/heartbeat-runs?limit=100`);
return Promise.all(rows.map(row => api.getRunObservation<ChatRun>(`/api/heartbeat-runs/${row.id}`)));
}