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>
81 lines
5.9 KiB
TypeScript
81 lines
5.9 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
import { mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
|
|
import { tmpdir } from "node:os";
|
|
import path from "node:path";
|
|
import { afterEach, expect, it } from "vitest";
|
|
import { boundaryScenarioMetadata, chatBoundaryFingerprint } from "./chat-boundary-fingerprint.js";
|
|
import { fingerprintChatDependencyClosure } from "./chat-catalog-fingerprint.js";
|
|
import { findChatCatalogCase } from "./chat-catalog-registry.js";
|
|
import type { MatrixExecution } from "./types.js";
|
|
|
|
const roots: string[] = [];
|
|
afterEach(() => { for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }); });
|
|
const scenario = { id: "access.sign-in", capabilities: ["access/sign-in"], context: "An expired human session.",
|
|
query: "Sign me back in.", expected_outcome: "Real authorized return after sign-in.", attempts: [] as unknown[] };
|
|
function fixture() {
|
|
const root = mkdtempSync(path.join(tmpdir(), "boundary-metadata-fingerprint-")); roots.push(root);
|
|
mkdirSync(path.join(root, "tests/runner-e2e"), { recursive: true });
|
|
const manifestPath = "tests/runner-e2e/chat-campaign-manifest.json";
|
|
const write = (file: string, body: string) => writeFileSync(path.join(root, file), body);
|
|
write("selected.ts", 'import "./dependency.js"; export const load = (name: string) => import(name);');
|
|
write("dependency.ts", 'export const behavior = "original";');
|
|
const descriptor = { scenarioId: scenario.id, boundaryTarget: "authenticated-harness" };
|
|
const manifest = { scenarios: [structuredClone(scenario)], ledger: { completed: 0 } };
|
|
const fingerprint = () => {
|
|
write(manifestPath, JSON.stringify(manifest));
|
|
const frozen = boundaryScenarioMetadata(manifest, descriptor.scenarioId);
|
|
return fingerprintChatDependencyClosure({ root, entries: ["selected.ts"], selected: { descriptor, scenario: frozen, journeyKind: "browser-boundary" },
|
|
normalizedMetadata: { [manifestPath]: frozen } });
|
|
};
|
|
return { manifest, descriptor, write, fingerprint, manifestPath };
|
|
}
|
|
it("keeps ledger, attempt, result and usage updates out of the selected boundary metadata", () => {
|
|
const f = fixture(); const before = f.fingerprint();
|
|
f.manifest.ledger.completed++;
|
|
f.manifest.scenarios[0]!.attempts.push({ result: { outcome: "failed", evidencePaths: ["retained/result.json"] }, usage: { tokens: 123, costUsd: null } });
|
|
expect(f.fingerprint().digest).toBe(before.digest);
|
|
f.manifest.scenarios.push({ ...scenario, id: "unselected.scenario", query: "Unrelated request" });
|
|
expect(f.fingerprint().digest).toBe(before.digest);
|
|
expect(before.unknownDynamicImports).toEqual(["selected.ts"]);
|
|
expect(before.sources.map(row => row.file)).toContain(f.manifestPath);
|
|
});
|
|
it.each(["query", "context", "expected_outcome", "capabilities"] as const)("invalidates selected frozen %s changes", field => {
|
|
const f = fixture(); const before = f.fingerprint().digest;
|
|
if (field === "capabilities") f.manifest.scenarios[0]!.capabilities.push("access/changed");
|
|
else f.manifest.scenarios[0]![field] += " Changed canonical requirement.";
|
|
expect(f.fingerprint().digest).not.toBe(before);
|
|
});
|
|
it("fails closed for missing, wrong, duplicate or malformed selected canonical identity", () => {
|
|
expect(() => boundaryScenarioMetadata({}, scenario.id)).toThrow("Missing");
|
|
expect(() => boundaryScenarioMetadata({ scenarios: [scenario] }, "access.not-the-selected-id")).toThrow("Missing");
|
|
expect(() => boundaryScenarioMetadata({ scenarios: [{ ...scenario, id: undefined }] }, scenario.id)).toThrow("Missing");
|
|
expect(() => boundaryScenarioMetadata({ scenarios: [scenario, scenario] }, scenario.id)).toThrow("duplicate");
|
|
expect(() => boundaryScenarioMetadata({ scenarios: [{ ...scenario, query: null }] }, scenario.id)).toThrow("Invalid");
|
|
});
|
|
it("continues to bind executable bytes, unknown-source closure and selected descriptor identity", () => {
|
|
const f = fixture(); const before = f.fingerprint().digest;
|
|
f.write("dependency.ts", 'export const behavior = "changed executable";');
|
|
expect(f.fingerprint().digest).not.toBe(before);
|
|
f.write("unknown-runtime.ts", 'export const unknown = "conservatively included";');
|
|
const withUnknown = f.fingerprint();
|
|
expect(withUnknown.sources.map(row => row.file)).toContain("unknown-runtime.ts");
|
|
f.write("unknown-runtime.ts", 'export const unknown = "changed unknown code";');
|
|
expect(f.fingerprint().digest).not.toBe(withUnknown.digest);
|
|
const beforeDescriptor = f.fingerprint().digest;
|
|
f.descriptor.boundaryTarget = "changed-target";
|
|
expect(f.fingerprint().digest).not.toBe(beforeDescriptor);
|
|
});
|
|
it("wires the actual boundary lane to the selected scenario projection without dropping its closure", () => {
|
|
const descriptor = findChatCatalogCase("access.sign-in")!;
|
|
const execution = { id: "offline-sign-in", suite: { id: "chat-features" }, environment: { id: "local" }, requiredCredentials: [] } as unknown as MatrixExecution;
|
|
const result = chatBoundaryFingerprint(descriptor, execution, {}, { credentialNames: [], referenceNames: [], externalRequirements: [] });
|
|
const manifest = JSON.parse(readFileSync(new URL("./chat-campaign-manifest.json", import.meta.url), "utf8"));
|
|
const frozen = boundaryScenarioMetadata(manifest, descriptor.scenarioId);
|
|
const expected = createHash("sha256").update(JSON.stringify(frozen)).digest("hex");
|
|
expect(result.sources.find(row => row.file === "tests/runner-e2e/chat-campaign-manifest.json")?.sha256).toBe(expected);
|
|
expect(result.sources.map(row => row.file)).toEqual(expect.arrayContaining(["tests/runner-e2e/chat-boundary-fingerprint.ts", "tests/runner-e2e/runner.spec.ts", "tests/runner-e2e/launch.ts"]));
|
|
expect(result.fingerprintKind).toBe("complete-execution-and-oracle-closure");
|
|
expect(result.unknownDynamicImports.length).toBeGreaterThan(0);
|
|
expect(() => chatBoundaryFingerprint(descriptor, { ...execution, environment: { id: "daytona" } } as MatrixExecution, {})).toThrow("explicitly selected local browser boundary");
|
|
});
|