mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:38:22 +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>
63 lines
5.1 KiB
TypeScript
63 lines
5.1 KiB
TypeScript
import { mkdir, mkdtemp, readFile, realpath, rm, stat, symlink, writeFile } from "node:fs/promises";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
import { afterEach, expect, it } from "vitest";
|
|
import { stagePrivateDiagnostics } from "./private-diagnostics.js";
|
|
import { prepareSourceServerDependencies } from "./source-startup.js";
|
|
import { copyRetainedSourceSdk, retainPreparedSourceSdk } from "./source-sdk-evidence.js";
|
|
|
|
const roots: string[] = [], executionId = "chat-features.runner-opencode.local.plugins.install-plugin", sourceRevision = "a".repeat(40);
|
|
afterEach(async () => { await Promise.all(roots.splice(0).map(root => rm(root, { recursive: true, force: true }))); });
|
|
async function fixture(secrets: string[] = []) {
|
|
const root = await realpath(await mkdtemp(path.join(os.tmpdir(), "source-sdk-synthetic-unit-"))); roots.push(root);
|
|
const repositoryRoot = path.join(root, "repo"), temporaryRoot = path.join(root, "attempt"), uploadDir = path.join(root, "uploaded");
|
|
const put = async (file: string, value: string | Buffer) => { await mkdir(path.dirname(path.join(repositoryRoot, file)), { recursive: true }); await writeFile(path.join(repositoryRoot, file), value); };
|
|
await put("scripts/ensure-plugin-build-deps.mjs", await readFile(new URL("../../scripts/ensure-plugin-build-deps.mjs", import.meta.url)));
|
|
await put("pnpm-lock.yaml", "synthetic unit lock\n");
|
|
for (const directory of ["packages/shared", "packages/plugins/sdk"]) {
|
|
await put(`${directory}/src/index.ts`, "export const syntheticFixture = true;\n"); await put(`${directory}/tsconfig.json`, "{}");
|
|
}
|
|
await put("node_modules/typescript/bin/tsc", `const fs=require('node:fs'),path=require('node:path');if(process.env.FAIL_COMPILER==='1')process.exit(7);const dir=path.join(path.dirname(process.argv[3]),'dist');fs.mkdirSync(path.join(dir,'nested'),{recursive:true});fs.writeFileSync(path.join(dir,'index.js'),process.env.SYNTHETIC_OUTPUT_CONTENT||'export const syntheticFixture = true;\\n');fs.writeFileSync(path.join(dir,'nested/child.js'),'export {};\\n');`);
|
|
await mkdir(path.join(temporaryRoot, "selected-private-inputs"), { recursive: true, mode: 0o700 });
|
|
stagePrivateDiagnostics(temporaryRoot, [executionId], secrets);
|
|
const input = { repositoryRoot, temporaryRoot, executionIds: [executionId], sourceRevision, installed: false };
|
|
const prepare = (environment: NodeJS.ProcessEnv = {}) => prepareSourceServerDependencies(repositoryRoot, environment, false, { temporaryRoot, executionIds: [executionId], sourceRevision });
|
|
return { root, repositoryRoot, temporaryRoot, uploadDir, input, prepare };
|
|
}
|
|
|
|
it("initializes owned SDK staging before retention when private capture is outside the temporary root", async () => {
|
|
const f = await fixture();
|
|
const externalCapture = path.join(f.root, "manual-handoff", "capture");
|
|
await mkdir(externalCapture, { recursive: true, mode: 0o700 });
|
|
await f.prepare();
|
|
const staged = path.join(f.temporaryRoot, "artifacts-private");
|
|
expect((await stat(staged)).mode & 0o777).toBe(0o700);
|
|
const receipt = JSON.parse(await readFile(path.join(staged, "source-sdk-build/receipt.json"), "utf8"));
|
|
expect(receipt).toMatchObject({ executionId, sourceRevision });
|
|
expect(receipt.certifiedTargets).toHaveLength(2);
|
|
await expect(copyRetainedSourceSdk(f.temporaryRoot, executionId, sourceRevision, f.uploadDir, [])).resolves.toBeUndefined();
|
|
await expect(stat(path.join(externalCapture, "source-sdk-build"))).rejects.toThrow();
|
|
});
|
|
it("rejects a symlink SDK staging parent without writing retained evidence outside the attempt", async () => {
|
|
const f = await fixture();
|
|
const outside = path.join(f.root, "outside");
|
|
await mkdir(outside, { mode: 0o700 });
|
|
await symlink(outside, path.join(f.temporaryRoot, "artifacts-private"));
|
|
await expect(f.prepare()).rejects.toThrow("Source SDK staging custody invalid");
|
|
await expect(stat(path.join(outside, "source-sdk-build"))).rejects.toThrow();
|
|
});
|
|
it("still rejects changed certified output after staging initialization", async () => {
|
|
const f = await fixture(); await f.prepare();
|
|
await rm(path.join(f.temporaryRoot, "artifacts-private/source-sdk-build"), { recursive: true });
|
|
await writeFile(path.join(f.repositoryRoot, "packages/plugins/sdk/dist/index.js"), "changed compiler bytes");
|
|
await expect(retainPreparedSourceSdk(f.input)).rejects.toThrow("no longer matches");
|
|
await expect(stat(path.join(f.temporaryRoot, "artifacts-private/source-sdk-build"))).rejects.toThrow();
|
|
});
|
|
it.each(["missing redaction registry", "credential contamination", "compiler failure"])("does not retain evidence for %s after staging initialization", async invalid => {
|
|
const f = await fixture(["synthetic-private-upstream-credential-value"]);
|
|
if (invalid === "missing redaction registry") await rm(path.join(f.temporaryRoot, "selected-private-inputs/diagnostic-redaction.json"));
|
|
await expect(f.prepare(invalid === "credential contamination" ? { SYNTHETIC_OUTPUT_CONTENT: "synthetic-private-upstream-credential-value" }
|
|
: invalid === "compiler failure" ? { FAIL_COMPILER: "1" } : {})).rejects.toThrow();
|
|
await expect(stat(path.join(f.temporaryRoot, "artifacts-private/source-sdk-build"))).rejects.toThrow();
|
|
});
|