mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 08:53:19 +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>
77 lines
6.4 KiB
TypeScript
77 lines
6.4 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import { afterAll, beforeAll, describe, expect, it } from "vitest";
|
|
import { agents, companies, createDb, issueInboxArchives, issues } from "../../packages/db/src/index.js";
|
|
import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "../../packages/db/src/test-embedded-postgres.js";
|
|
import { issueService } from "../../server/src/services/issues.js";
|
|
import { armArchiveStorageFault, archiveStorageFaultSql, type ArchiveFaultBinding } from "./chat-archive-storage-fault.js";
|
|
|
|
it("refuses every execution except its own single selected case", async () => {
|
|
const binding = { companyId: randomUUID(), agentId: randomUUID(), personId: "person-0001", taskIds: [randomUUID(), randomUUID(), randomUUID()] };
|
|
await expect(armArchiveStorageFault({ executionId: "chat-features.runner-opencode.local.inbox-search.archive-done", binding, env: { PAPERCLIP_RUNNER_E2E_EXECUTION_IDS: JSON.stringify(["chat-features.runner-opencode.local.inbox-search.archive-done"]) } })).rejects.toThrow("single selected");
|
|
const own = "chat-features.runner-opencode.local.inbox-search.archive-partial-failure";
|
|
await expect(armArchiveStorageFault({ executionId: own, binding, env: { PAPERCLIP_RUNNER_E2E_EXECUTION_IDS: JSON.stringify([own, "other"]) } })).rejects.toThrow("single selected");
|
|
await expect(armArchiveStorageFault({ executionId: own, binding, env: { PAPERCLIP_RUNNER_E2E_EXECUTION_IDS: JSON.stringify([own]) } })).rejects.toThrow("owned runner instance");
|
|
expect(() => archiveStorageFaultSql("abcdefabcdef", { ...binding, personId: "x'; drop table issues; --" })).toThrow("exact owned binding");
|
|
expect(() => archiveStorageFaultSql("abcdefabcdef", { ...binding, taskIds: binding.taskIds.slice(0, 2) })).toThrow("exact owned binding");
|
|
});
|
|
|
|
const support = await getEmbeddedPostgresTestSupport();
|
|
const describeEmbedded = support.supported ? describe : describe.skip;
|
|
describeEmbedded("archive storage fault against the product's own archive write", () => {
|
|
let database: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | undefined;
|
|
let db: ReturnType<typeof createDb>;
|
|
beforeAll(async () => { database = await startEmbeddedPostgresTestDatabase("paperclip-archive-storage-fault-"); db = createDb(database.connectionString); }, 120_000);
|
|
afterAll(async () => { await database?.cleanup(); });
|
|
|
|
async function seed() {
|
|
const companyId = randomUUID(), agentId = randomUUID(), otherAgentId = randomUUID(), personId = `person-${randomUUID()}`;
|
|
await db.insert(companies).values({ id: companyId, name: `Fault ${companyId}`, issuePrefix: `AF${companyId.replaceAll("-", "").slice(0, 6).toUpperCase()}` });
|
|
await db.insert(agents).values([agentId, otherAgentId].map(id => ({ id, companyId, name: `Agent ${id.slice(0, 4)}`, role: "engineer", status: "active", adapterType: "codex_local", adapterConfig: {}, runtimeConfig: {}, permissions: {} })));
|
|
const taskIds: string[] = [randomUUID(), randomUUID(), randomUUID()], unrelated = randomUUID();
|
|
await db.insert(issues).values([...taskIds, unrelated].map((id, index) => ({ id, companyId, title: `Delivered ${index}`, status: "done", priority: "medium" })));
|
|
return { binding: { companyId, agentId, personId, taskIds } satisfies ArchiveFaultBinding, otherAgentId, unrelated };
|
|
}
|
|
async function install(binding: ArchiveFaultBinding) {
|
|
const statements = archiveStorageFaultSql(randomUUID().replaceAll("-", "").slice(0, 12), binding);
|
|
await db.$client.begin(async tx => { for (const statement of statements.install) await tx.unsafe(statement); });
|
|
return {
|
|
statements,
|
|
failures: async () => Promise.all(statements.failures.map(async statement => Number((await db.$client.unsafe(statement))[0]?.hits ?? 0))),
|
|
run: async (list: string[]) => { for (const statement of list) await db.$client.unsafe(statement); },
|
|
};
|
|
}
|
|
const svc = () => issueService(db);
|
|
const asAgent = (agentId: string) => ({ archivedByActorType: "agent" as const, archivedByAgentId: agentId, archivedByRunId: null });
|
|
const outcome = (promise: Promise<unknown>) => promise.then(() => "ok", (error: { code?: string; cause?: { code?: string } }) => error.code ?? error.cause?.code ?? "error");
|
|
|
|
it("fails only the third agent archive in storage, counts it, and clears on release", async () => {
|
|
const { binding, otherAgentId, unrelated } = await seed(); const fault = await install(binding);
|
|
const archive = (issueId: string, userId = binding.personId, agentId = binding.agentId) => outcome(svc().archiveInbox(binding.companyId, issueId, userId, new Date(), asAgent(agentId)));
|
|
expect(await archive(binding.taskIds[0]!)).toBe("ok");
|
|
expect(await archive(binding.taskIds[1]!)).toBe("ok");
|
|
expect(await archive(binding.taskIds[2]!)).toBe("58030");
|
|
expect(await archive(binding.taskIds[2]!)).toBe("58030");
|
|
expect(await fault.failures()).toEqual([0, 0, 2]);
|
|
// Scope: another person, another agent, a human write and an unrelated task are untouched.
|
|
expect(await archive(binding.taskIds[2]!, "someone-else")).toBe("ok");
|
|
expect(await archive(binding.taskIds[2]!, binding.personId, otherAgentId)).toBe("ok");
|
|
expect(await archive(unrelated)).toBe("ok");
|
|
const saved = await db.select().from(issueInboxArchives);
|
|
expect(saved.filter(row => row.userId === binding.personId && binding.taskIds.includes(row.issueId)).map(row => row.archivedByAgentId)).toEqual(expect.arrayContaining([binding.agentId, binding.agentId, otherAgentId]));
|
|
await fault.run(fault.statements.release);
|
|
expect(await archive(binding.taskIds[2]!)).toBe("ok");
|
|
expect(await fault.failures()).toEqual([0, 0, 2]);
|
|
await fault.run(fault.statements.remove);
|
|
expect(Number((await db.$client.unsafe(`select count(*) as n from pg_proc where proname like 'paperclip_e2e_archive_fault_%'`))[0]?.n)).toBe(0);
|
|
});
|
|
|
|
it("still lets exactly two of three parallel archives commit", async () => {
|
|
const { binding } = await seed(); const fault = await install(binding);
|
|
const results = await Promise.all(binding.taskIds.map(issueId => outcome(svc().archiveInbox(binding.companyId, issueId, binding.personId, new Date(), asAgent(binding.agentId)))));
|
|
expect(results.filter(result => result === "ok")).toHaveLength(2);
|
|
expect(results.filter(result => result === "58030")).toHaveLength(1);
|
|
expect((await fault.failures()).reduce((a, b) => a + b, 0)).toBe(1);
|
|
await fault.run(fault.statements.remove);
|
|
});
|
|
});
|