mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 07:12:00 +01:00
## 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>
45 lines
5.2 KiB
TypeScript
45 lines
5.2 KiB
TypeScript
import { mkdtempSync, writeFileSync, rmSync, readFileSync } from "node:fs";
|
|
import { randomBytes, createHash } from "node:crypto";
|
|
import { tmpdir } from "node:os";
|
|
import path from "node:path";
|
|
import { afterEach, expect, it } from "vitest";
|
|
import { CHAT_ORACLE_KEY_ENV, privateOracleIdentity, verifyRetainedPrivateOracle } from "./chat-private-oracle.js";
|
|
import { stageChatPrivateInputs, chatPrivateInputNameIdentity, verifyRetainedChatOracleIdentity, scrubChatPrivateEnvironment, CHAT_PRIVATE_INPUTS_ENV } from "./chat-private-inputs.js";
|
|
import type { MatrixExecution } from "./types.js";
|
|
const roots: string[] = []; afterEach(() => { for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }); });
|
|
function fixture() { const root = mkdtempSync(path.join(tmpdir(), "chat-oracle-")); roots.push(root); const key = path.join(root, "campaign-key"); writeFileSync(key, randomBytes(32), { mode: 0o600 }); return { root, key, env: { [CHAT_ORACLE_KEY_ENV]: key } }; }
|
|
const fields = ["recentMarker", "olderMarker", "recentFactJson", "olderFactJson", "apiVersion"];
|
|
const values = { recentMarker: "private-recent", olderMarker: "private-old", recentFactJson: '{"subject":"Acorn","value":"private-fact","aliases":["private-alias"]}', olderFactJson: '{"subject":"Old","value":"old-fact"}', apiVersion: "2025-09-03" };
|
|
it("commits every audited actual semantic expectation while excluding credentials/incidental IDs", () => {
|
|
const f = fixture(); const original = privateOracleIdentity("notion", fields, values, f.env)!;
|
|
for (const field of fields) expect(privateOracleIdentity("notion", fields, { ...values, [field]: `${values[field as keyof typeof values]}-changed` }, f.env)?.commitment).not.toBe(original.commitment);
|
|
expect(privateOracleIdentity("notion", fields, { ...values, workspaceId: "different-disposable-id", tokenEnv: "different-secret-ref" }, f.env)).toEqual(original);
|
|
const publicValue = JSON.stringify(original); for (const value of Object.values(values)) expect(publicValue).not.toContain(value);
|
|
expect(publicValue).not.toContain(createHash("sha256").update(values.recentFactJson).digest("hex"));
|
|
expect(() => verifyRetainedPrivateOracle(original, "notion", fields, values, f.env)).not.toThrow();
|
|
});
|
|
it("commits the actual AgentMail recipient without retaining its address or a low-entropy digest",()=>{
|
|
const f=fixture(),recipient="synthetic-owner@agentmail.to",identity=privateOracleIdentity("agentmail",["recipient","inboxId","apiTokenEnv"],{recipient,inboxId:recipient,apiTokenEnv:"PAPERCLIP_CHAT_EVAL_AGENTMAIL"},f.env)!;
|
|
expect(identity.fields).toEqual(["recipient"]);expect(privateOracleIdentity("agentmail",["recipient"],{recipient:"different@agentmail.to"},f.env)?.commitment).not.toBe(identity.commitment);
|
|
const publicValue=JSON.stringify(identity);expect(publicValue).not.toContain(recipient);expect(publicValue).not.toContain(createHash("sha256").update(recipient).digest("hex"));
|
|
expect(()=>verifyRetainedPrivateOracle(identity,"agentmail",["recipient"],{recipient:"different@agentmail.to"},f.env)).toThrow("mismatch");
|
|
});
|
|
it("refuses lost, replaced or absent campaign keys and changed retained expectations without creating a replacement", () => {
|
|
const f = fixture(); const original = privateOracleIdentity("notion", fields, values, f.env)!;
|
|
expect(() => privateOracleIdentity("notion", fields, values, {})).toThrow("key unavailable");
|
|
expect(() => verifyRetainedPrivateOracle(original, "notion", fields, { ...values, recentMarker: "changed" }, f.env)).toThrow("mismatch");
|
|
writeFileSync(f.key, randomBytes(32)); expect(() => verifyRetainedPrivateOracle(original, "notion", fields, values, f.env)).toThrow("mismatch");
|
|
rmSync(f.key); expect(() => verifyRetainedPrivateOracle(original, "notion", fields, values, f.env)).toThrow();
|
|
});
|
|
it("retains only opaque names/commitments across envelope cleanup and requalifies with actual host expectations/key", () => {
|
|
const f = fixture(); const config = path.join(f.root, "external.json"); const keyBytes = readFileSync(f.key).toString("hex");
|
|
writeFileSync(config, JSON.stringify({ schemaVersion: 1, providers: { notion: { disposable: true, resourceIds: ["disposable"], credentialEnv: ["PAPERCLIP_CHAT_EVAL_NOTION_AUTH"], prerequisites: values } } }), { mode: 0o600 });
|
|
const descriptor = { externalInput: { provider: "notion" as const, fields } }; const execution = { id: "selected" } as MatrixExecution;
|
|
const env = { ...f.env, PAPERCLIP_CHAT_CATALOG_EXTERNAL_CONFIG: config, PAPERCLIP_CHAT_EVAL_NOTION_AUTH: "never-committed-credential" };
|
|
const staged = stageChatPrivateInputs({ execution, descriptor, privateDir: f.root, secrets: [], env }); const retained = chatPrivateInputNameIdentity("selected", { [CHAT_PRIVATE_INPUTS_ENV]: staged.filename, PAPERCLIP_RUNNER_E2E_TEMP_ROOT: f.root });
|
|
rmSync(staged.filename); expect(() => verifyRetainedChatOracleIdentity(retained, descriptor, env)).not.toThrow();
|
|
expect(JSON.stringify(retained)).not.toContain(keyBytes); expect(JSON.stringify(retained)).not.toContain("never-committed-credential");
|
|
const publicEnv = scrubChatPrivateEnvironment({ ...env }, []); expect(publicEnv[CHAT_ORACLE_KEY_ENV]).toBeUndefined();
|
|
rmSync(f.key); expect(() => verifyRetainedChatOracleIdentity(retained, descriptor, env)).toThrow();
|
|
});
|