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>
58 lines
5.4 KiB
TypeScript
58 lines
5.4 KiB
TypeScript
import { CHAT_OPENCODE_MODEL } from "./chat-runtime-profile.js";
|
|
import { mkdtempSync, mkdirSync, writeFileSync, symlinkSync, rmSync, readFileSync } from "node:fs";
|
|
import { createHash } from "node:crypto";
|
|
import path from "node:path";
|
|
import { tmpdir } from "node:os";
|
|
import { afterEach, expect, it } from "vitest";
|
|
import { runOwnedInstalledPreparation, admitsInstalledChat, installedChatTreeIdentity, refreshInstalledChatPins, validateChatInstallConfiguration, CHAT_INSTALL_PLAN } from "./chat-installed-lane.js";
|
|
import type { MatrixExecution } from "./types.js";
|
|
const roots: string[] = []; const sha = (file: string) => createHash("sha256").update(readFileSync(file)).digest("hex");
|
|
afterEach(() => { for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }); });
|
|
function root() { const folder = mkdtempSync(path.join(tmpdir(), "chat-installed-")); roots.push(folder); return folder; }
|
|
it("admits only exact published pins and the two selected source-local Codex operator cases", () => {
|
|
const pin = { version: "1.2.3", integrity: "sha512-YWJj" };
|
|
expect(validateChatInstallConfiguration({ schemaVersion: 1, disposable: true, source: pin }).source).toEqual(pin);
|
|
for (const source of [{ ...pin, version: "file:/source-pack" }, { ...pin, integrity: "unverified" }])
|
|
expect(() => validateChatInstallConfiguration({ schemaVersion: 1, disposable: true, source })).toThrow();
|
|
const execution = { suite: { id: "chat-features", manualOnly: true }, task: { id: "instance-operations.update-instance", flow: "agent_chat" }, profile: { id: "runner-codex-subscription" }, environment: { id: "local" } } as MatrixExecution;
|
|
expect(admitsInstalledChat(execution)).toBe(true);
|
|
const remote = { ...execution, profile: { ...execution.profile, id: "runner-opencode", provider: "opencode", model: CHAT_OPENCODE_MODEL, adapterType: "paperclip_runner", credential: "OPENROUTER_API_KEY" as const } };
|
|
expect(admitsInstalledChat(remote)).toBe(true);
|
|
expect(admitsInstalledChat({ ...remote, profile: { ...remote.profile, model: "other" } })).toBe(false);
|
|
expect(admitsInstalledChat({ ...execution, task: { ...execution.task, id: "tasks.create-backlog" } })).toBe(false);
|
|
expect(admitsInstalledChat({ ...execution, environment: { ...execution.environment, id: "daytona" } })).toBe(false);
|
|
});
|
|
it("hashes the complete actual dependency tree and rejects external dependency links", () => {
|
|
const folder = root(), prefix = path.join(folder, "prefix"); mkdirSync(prefix); writeFileSync(path.join(prefix, "dependency.js"), "original");
|
|
const first = installedChatTreeIdentity(prefix); writeFileSync(path.join(prefix, "dependency.js"), "tampered");
|
|
expect(installedChatTreeIdentity(prefix).treeSha256).not.toBe(first.treeSha256);
|
|
writeFileSync(path.join(folder, "outside.js"), "outside"); symlinkSync(path.join(folder, "outside.js"), path.join(prefix, "escaping.js"));
|
|
expect(() => installedChatTreeIdentity(prefix)).toThrow("escapes");
|
|
});
|
|
it("compares real source bytes to the retained public-artifact pins before every restart", () => {
|
|
const folder = root(), prefix = path.join(folder, "prefix"), cliRoot = path.join(prefix, "lib/node_modules/paperclipai"), serverRoot = path.join(cliRoot, "node_modules/@paperclipai/server");
|
|
mkdirSync(path.join(cliRoot, "dist"), { recursive: true }); mkdirSync(path.join(serverRoot, "dist"), { recursive: true });
|
|
const cli = path.join(cliRoot, "dist/index.js"), server = path.join(serverRoot, "dist/index.js");
|
|
writeFileSync(cli, "export const cli=true;"); writeFileSync(server, "export const server=true;");
|
|
writeFileSync(path.join(cliRoot, "package.json"), JSON.stringify({ name: "paperclipai", version: "1.2.3" }));
|
|
writeFileSync(path.join(serverRoot, "package.json"), JSON.stringify({ name: "@paperclipai/server", version: "1.2.3" }));
|
|
const planFile = path.join(folder, "plan.json");
|
|
writeFileSync(planFile, JSON.stringify({ schemaVersion: 1, executionId: "selected", temporaryRoot: folder, prefix, cli, serverRoot, sourceVersion: "1.2.3",
|
|
artifacts: [{ package: "paperclipai", version: "1.2.3", entrySha256: sha(cli) }, { package: "@paperclipai/server", version: "1.2.3", entrySha256: sha(server) }] }), { mode: 0o600 });
|
|
const env = { [CHAT_INSTALL_PLAN]: planFile, PAPERCLIP_RUNNER_E2E_TEMP_ROOT: folder };
|
|
expect(refreshInstalledChatPins(env, "selected").version).toBe("1.2.3");
|
|
expect(() => refreshInstalledChatPins(env, "other")).toThrow("another target");
|
|
writeFileSync(server, "export const server='tampered';");
|
|
expect(() => refreshInstalledChatPins(env, "selected")).toThrow("independently downloaded");
|
|
});
|
|
|
|
it("retires the exact timed-out preparation child while retaining only the owned partial prefix for disposition", async () => {
|
|
const folder = root(), partial = path.join(folder, "partial-install.json");
|
|
const source = `const child=require("node:child_process").spawn(process.execPath,["-e","setInterval(()=>{},1000)"],{stdio:"ignore"});require("node:fs").writeFileSync(${JSON.stringify(partial)},JSON.stringify({pid:process.pid,descendantPid:child.pid}));setInterval(()=>{},1000);`;
|
|
await expect(runOwnedInstalledPreparation(process.execPath, ["-e", source], { cwd: folder, env: { PATH: process.env.PATH }, timeout: 500 })).rejects.toThrow("preparation failed");
|
|
const { pid, descendantPid } = JSON.parse(readFileSync(partial, "utf8"));
|
|
expect(() => process.kill(pid, 0)).toThrow();
|
|
expect(() => process.kill(descendantPid, 0)).toThrow();
|
|
rmSync(folder, { recursive: true, force: true });
|
|
});
|