Files
PaperClipAI/tests/runner-e2e/private-reporter-artifacts.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

56 lines
4.2 KiB
TypeScript

import { inspectPrivateFrameworkMetadata } from "./private-framework-report.js";
import { lstat, readFile, readdir, rm, writeFile } from "node:fs/promises";
import path from "node:path";
import { inspectEmbeddedReport, inspectZip } from "./evidence.js";
import { diagnosticSecrets, type DiagnosticSecretExpansion } from "./private-diagnostics.js";
import { findSecretLeak, redactText, sanitizeJson } from "./redaction.js";
import { cellTraceAsset, readPrivateCellTraceAsset, type PrivateCellEvidenceOwner } from "./manual-private-report-assets.js";
export interface ReporterPrivacyIssue { file: string; disposition: "redacted" | "omitted"; reason: string }
const sources = ["server.log", "playwright.log", "junit.xml", "html-report", "blob-report", "playwright-output", "framework-report.json"];
const text = new Set([".log", ".txt", ".md", ".xml", ".html", ".json", ".js", ".css"]);
/** Only reporter/diagnostic sinks are touched, after independent product oracles
* finish. Product API snapshots and work-product bytes are never pre-sanitized.
* Uninspectable/leaking compressed reports are omitted rather than fabricated. */
export async function sanitizePrivateReporterArtifacts(root: string, values: readonly string[] | DiagnosticSecretExpansion,
privateCell?: { owner: PrivateCellEvidenceOwner }): Promise<ReporterPrivacyIssue[]> {
const secrets = diagnosticSecrets(values).values; const issues: ReporterPrivacyIssue[] = [];
const visit = async (relative: string): Promise<void> => {
const filename = path.join(root, relative); const info = await lstat(filename).catch((error: NodeJS.ErrnoException) => { if (error.code === "ENOENT") return null; throw error; });
if (!info) return;
const safeName = redactText(relative, secrets);
if (info.isDirectory()) { for (const name of await readdir(filename)) await visit(path.join(relative, name)); return; }
if (privateCell && cellTraceAsset(relative, privateCell.owner, "original").reserved) {
// These are immutable Playwright program files. Scan and authenticate
// them with the same guard used by packaging; diagnostic text rewriting
// can change clean JavaScript and invalidate its producer identity.
await readPrivateCellTraceAsset({ owner: privateCell.owner, layout: "original", relative,
file: filename, remaining: info.size, secrets });
return;
}
if (info.isSymbolicLink()) { await rm(filename); issues.push({ file: safeName, disposition: "omitted", reason: "reporter symlink cannot be inspected" }); return; }
if (!info.isFile()) return;
if (safeName !== relative) { await rm(filename); issues.push({ file: safeName, disposition: "omitted", reason: "credential in reporter filename" }); return; }
const extension = path.extname(filename).toLowerCase();
if (extension === ".zip") {
const reason = await inspectZip(filename, secrets);
if (reason) { await rm(filename); issues.push({ file: safeName, disposition: "omitted", reason }); }
} else if (text.has(extension)) {
if (info.size > 128 * 1024 * 1024) { await rm(filename); issues.push({ file: safeName, disposition: "omitted", reason: "reporter text exceeds inspection bound" }); return; }
const raw = await readFile(filename, "utf8");
if (relative === "framework-report.json") { inspectPrivateFrameworkMetadata(relative, raw, secrets); return; }
const opaque = extension === ".html" ? await inspectEmbeddedReport(raw, secrets) : null;
if (opaque) { await rm(filename); issues.push({ file: safeName, disposition: "omitted", reason: opaque }); return; }
const leak = findSecretLeak(raw, secrets);
let safe: string;
if (extension === ".json") {
try { safe = `${JSON.stringify(sanitizeJson(JSON.parse(raw), secrets), null, 2)}\n`; }
catch { await rm(filename); issues.push({ file: safeName, disposition: "omitted", reason: "reporter JSON could not be safely parsed" }); return; }
} else safe = redactText(raw, secrets);
if (safe !== raw) await writeFile(filename, safe, { mode: 0o600 });
if (leak) issues.push({ file: safeName, disposition: "redacted", reason: leak });
}
};
for (const source of sources) await visit(source);
return issues;
}