Files
PaperClipAI/tests/runner-e2e/chat-private-oracle.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

36 lines
3.7 KiB
TypeScript

import { createHmac, timingSafeEqual } from "node:crypto";
import { lstatSync, readFileSync } from "node:fs";
export const CHAT_ORACLE_KEY_ENV = "PAPERCLIP_CHAT_ORACLE_COMMITMENT_KEY";
/** Audited with external owner: these actual private values select expected
* Notion answers/provider contract. IDs, origins and credential references are
* provenance, never included. New semantic consumers require an explicit edit. */
export const privateOracleSemanticFields = { notion: ["recentMarker", "olderMarker", "recentFactJson", "olderFactJson", "apiVersion"],agentmail:["recipient"] } as const;
export interface PrivateOracleIdentity { provider: string; fields: string[]; keyIdentity: string; commitment: string }
function readKey(env: NodeJS.ProcessEnv): Buffer {
const filename = env[CHAT_ORACLE_KEY_ENV]; if (!filename) throw new Error("Private oracle campaign commitment key unavailable");
let info; try { info = lstatSync(filename); } catch { throw new Error("Private oracle campaign commitment key unavailable"); }
if (!info.isFile() || info.isSymbolicLink() || (info.mode & 0o777) !== 0o600 || typeof process.getuid === "function" && info.uid !== process.getuid()) throw new Error("Private oracle key must be an existing owned0600 regular file");
let bytes: Buffer; try { bytes = readFileSync(filename); } catch { throw new Error("Private oracle campaign commitment key unavailable"); } if (bytes.length !== 32) throw new Error("Private oracle key must contain exactly32 existing random bytes"); return bytes;
}
export function oracleSemanticFields(provider: string, declaredFields: readonly string[]): string[] {
const audited = privateOracleSemanticFields[provider as keyof typeof privateOracleSemanticFields] as readonly string[] | undefined;
return declaredFields.filter(field => audited?.includes(field)).sort();
}
export function privateOracleIdentity(provider: string, declaredFields: readonly string[], prerequisites: Record<string, string>, env: NodeJS.ProcessEnv): PrivateOracleIdentity | undefined {
const fields = oracleSemanticFields(provider, declaredFields); if (!fields.length) return;
if (fields.some(field => typeof prerequisites[field] !== "string" || !prerequisites[field]?.trim())) throw new Error("Selected private oracle expectations unavailable");
const key = readKey(env); const mac = (value: string) => createHmac("sha256", key).update(value).digest("hex");
return { provider, fields, keyIdentity: mac("paperclip.chat-catalog.oracle-key.v1"),
commitment: mac(JSON.stringify({ schema: "paperclip.chat-catalog.oracle-expectations.v1", provider, fields: fields.map(field => [field, prerequisites[field]]) })) };
}
/** Host reconciliation must re-read the existing campaign key and actual
* private expectations. A lost/replaced key or changed oracle input cannot
* silently authenticate a retained old observation. No key is ever generated. */
export function verifyRetainedPrivateOracle(expected: PrivateOracleIdentity | undefined, provider: string, declaredFields: readonly string[], prerequisites: Record<string, string>, env: NodeJS.ProcessEnv) {
const current = privateOracleIdentity(provider, declaredFields, prerequisites, env);
if (!current && !expected) return;
if (!current || !expected || current.provider !== expected.provider || JSON.stringify(current.fields) !== JSON.stringify(expected.fields)
|| !/^[a-f0-9]{64}$/.test(expected.keyIdentity) || !/^[a-f0-9]{64}$/.test(expected.commitment)
|| !timingSafeEqual(Buffer.from(current.keyIdentity, "hex"), Buffer.from(expected.keyIdentity, "hex")) || !timingSafeEqual(Buffer.from(current.commitment, "hex"), Buffer.from(expected.commitment, "hex"))) throw new Error("Retained private oracle commitment/key mismatch; evidence is ineligible until provenance is resolved");
}