mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 00:26:28 +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>
28 lines
5.1 KiB
TypeScript
28 lines
5.1 KiB
TypeScript
import { mkdtemp, writeFile, chmod, rm } from "node:fs/promises";
|
|
import { execFile } from "node:child_process";
|
|
import { promisify } from "node:util";
|
|
import { tmpdir } from "node:os";
|
|
import path from "node:path";
|
|
import { fileURLToPath } from "node:url";
|
|
import type { ChatCatalogContext } from "../chat-catalog-contract.js";
|
|
import { signInPublicFixturePerson } from "../public-mcp-flow.js";
|
|
import { readValidatedPublicOriginReceipt, PUBLIC_ORIGIN_RECEIPT_ENV } from "../chat-public-origin.js";
|
|
import { selectedRuntimeInputs } from "./runtime-private.js";
|
|
import { grokOperatorInputMatches, grokOperatorReceiptMatches, type GrokOperatorInput, type GrokOperatorReceipt } from "./runtime-grok-operator-contract.js";
|
|
export async function runPrivateGrokOperator(input: GrokOperatorInput, secrets: string[]) {
|
|
for (const c of input.publicSession.cookies) secrets.push(c.value); for (const o of input.publicSession.origins) for (const item of o.localStorage) secrets.push(item.value); if (input.webhookKey) secrets.push(input.webhookKey); if (input.webhookUrl) secrets.push(input.webhookUrl);
|
|
if (!grokOperatorInputMatches(input)) throw new Error("Setup blocker: selected authorized Grok operator/private public-session scope is unavailable");
|
|
const directory = await mkdtemp(path.join(tmpdir(), "paperclip-grok-operator-")); await chmod(directory, 0o700);
|
|
try { const filename = path.join(directory, "request.json"); await writeFile(filename, JSON.stringify(input), { mode: 0o600, flag: "wx" }); const loader = fileURLToPath(new URL("../../../server/node_modules/tsx/dist/loader.mjs", import.meta.url)), worker = fileURLToPath(new URL("./runtime-grok-operator-worker.ts", import.meta.url));
|
|
let output: string; try { output = (await promisify(execFile)(process.execPath, ["--import", loader, worker, filename], { timeout: input.operation === "availability" ? 45000 : 420000, maxBuffer: 32768, env: { PATH: process.env.PATH ?? "", HOME: directory, TMPDIR: directory, NODE_ENV: "test", DO_NOT_TRACK: "1" } })).stdout; } catch { throw new Error(input.operation === "availability" ? "Setup blocker: explicitly selected Grok operator did not confirm availability within its bounded private UI; diagnostics withheld" : "Actual Grok human handoff failed; private pairing, OAuth and browser diagnostics withheld"); }
|
|
if (secrets.some(secret => secret && [secret, encodeURIComponent(secret), Buffer.from(secret).toString("base64")].some(v => output.includes(v)))) throw new Error("Grok private child exceeded its closed secret-free receipt"); let receipt: GrokOperatorReceipt; try { receipt = JSON.parse(output); } catch { throw new Error("Grok operator returned no closed receipt"); } if (!grokOperatorReceiptMatches(receipt, { operation: input.operation, executionId: input.executionId, attemptId: input.attemptId, companyId: input.companyId, personId: input.personId, operatorRef: input.operatorRef, botAuthorizationRef: input.botAuthorizationRef })) throw new Error("Grok operator closed receipt identity mismatch"); return receipt;
|
|
} finally { await rm(directory, { recursive: true, force: true }); }
|
|
}
|
|
export async function privateGrokOperator(ctx: ChatCatalogContext, operation: GrokOperatorInput["operation"], existingAgentId?: string) {
|
|
const selected = selectedRuntimeInputs(ctx, "agents.existing-grok-bot"), p = selected.values, secrets = ctx.input.privateSecrets;
|
|
if (!secrets || p.operatorMode !== "interactive-private-ui" || !p.operatorRef || !p.botAuthorizationRef || !selected.resourceIds.includes(p.botAuthorizationRef)) throw new Error("Setup blocker: explicitly selected available human operator and authorized existing Grok Bot reference are required; no desktop driver or ambient session is inferred");
|
|
await signInPublicFixturePerson(ctx.input.api, ctx.input.page.context()); const receiptPath = process.env[PUBLIC_ORIGIN_RECEIPT_ENV], attemptId = process.env.PAPERCLIP_E2E_ACCOUNTING_ATTEMPT_ID; if (!receiptPath || !attemptId) throw new Error("Selected Grok operator requires its actual validated public origin");
|
|
const origin = await readValidatedPublicOriginReceipt({ receiptPath, attemptId, executionId: ctx.input.execution.id, backendOrigin: ctx.input.api.baseURL }), person = await ctx.input.api.get<{ user: { id: string; name: string } }>("/api/auth/get-session"), storage = await ctx.input.page.context().storageState(), hostname = new URL(origin.publicOrigin).hostname;
|
|
return runPrivateGrokOperator({ operation, receiptPath, attemptId, executionId: ctx.input.execution.id, backendOrigin: ctx.input.api.baseURL, publicOrigin: origin.publicOrigin, companyId: ctx.input.fixtures.company.id, companyName: ctx.input.fixtures.company.name, prefix: ctx.input.fixtures.company.issuePrefix!, personId: person.user.id, personName: person.user.name, leadId: ctx.input.fixtures.agent.id, botName: p.botId, operatorRef: p.operatorRef, botAuthorizationRef: p.botAuthorizationRef, operatorMode: "interactive-private-ui", publicSession: { cookies: storage.cookies.filter(c => c.domain.replace(/^\./, "") === hostname), origins: storage.origins.filter(o => o.origin === origin.publicOrigin) }, ...(operation === "setup" ? { existingAgentId, webhookUrl: p.endpoint, webhookKey: selected.reference(p.credentialEnvName) } : {}) }, secrets);
|
|
}
|