mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:55:46 +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>
66 lines
4.2 KiB
TypeScript
66 lines
4.2 KiB
TypeScript
import type { ChatCatalogContext } from "../chat-catalog-contract.js";
|
|
import { installIdentitySession, type createAuthenticatedPerson } from "./identity-auth.js";
|
|
import { RunnerApi } from "../api.js";
|
|
import { createOwnedChatRunEvidenceObserver } from "../chat-run-evidence-observer.js";
|
|
|
|
type Person = Awaited<ReturnType<typeof createAuthenticatedPerson>>;
|
|
/** One case's real person transition. Session material remains in this closure;
|
|
* all retained receipts contain public user/conversation identities only. */
|
|
export async function installCommentaryReader(ctx: ChatCatalogContext, person: Person, ownerId: string) {
|
|
const { api, page } = ctx.input;
|
|
if (ctx.scenario.id !== "activity.agent-feedback" || ctx.input.ownedRunEvidenceObserver)
|
|
throw new Error("Commentary reader installation requires its exact unbound scenario");
|
|
const original = await api.get<{ user?: { id: string } }>("/api/auth/get-session");
|
|
if (original.user?.id !== ownerId || person.id === ownerId) throw new Error("Commentary needs distinct real owner and reader sessions");
|
|
const cookies = await page.context().cookies(api.baseURL);
|
|
if (!cookies.length) throw new Error("Commentary owner has no genuine browser session to restore");
|
|
const cookie = cookies.map(row => `${row.name}=${row.value}`).join("; ");
|
|
// A separate client freezes only the real owner's existing cookie. Its
|
|
// mutation methods never escape: the approved observer exposes GETs only.
|
|
const evidenceApi = new RunnerApi(page.context().request);
|
|
evidenceApi.setBrowserSession(cookie);
|
|
ctx.input.ownedRunEvidenceObserver = createOwnedChatRunEvidenceObserver(evidenceApi, ctx.input.fixtures.company.id);
|
|
let restored = false;
|
|
const restore = async () => {
|
|
if (restored) return;
|
|
await installIdentitySession(page.context(), api.baseURL, cookie);
|
|
api.setBrowserSession(cookie);
|
|
if ((await api.get<{ user?: { id: string } }>("/api/auth/get-session")).user?.id !== ownerId)
|
|
throw new Error("Commentary owner session restoration did not preserve its real identity");
|
|
restored = true;
|
|
};
|
|
try {
|
|
await person.installSessionOn(page.context());
|
|
person.bindApiSession(api);
|
|
// Reload drops the previous person's cached React state as well as using
|
|
// the newly installed genuine server session for all following UI requests.
|
|
await page.reload({ waitUntil: "domcontentloaded" });
|
|
const apiPerson = await api.get<{ user?: { id: string } }>("/api/auth/get-session");
|
|
// Independently authenticate the actual browser jar, without recording the
|
|
// auth DTO or cookie header in Playwright's API trace.
|
|
const browserCookie = (await page.context().cookies(api.baseURL)).map(row => `${row.name}=${row.value}`).join("; ");
|
|
const response = await fetch(new URL("/api/auth/get-session", api.baseURL), { redirect: "error", signal: AbortSignal.timeout(15_000),
|
|
headers: { Cookie: browserCookie, Origin: api.baseURL } });
|
|
let browserPerson: { user?: { id: string } };
|
|
try {
|
|
if (!response.ok) throw new Error("Commentary browser session could not be independently read");
|
|
browserPerson = await response.json();
|
|
} finally { if (!response.bodyUsed) await response.body?.cancel(); }
|
|
if (apiPerson.user?.id !== person.id || browserPerson.user?.id !== person.id)
|
|
throw new Error("Commentary API and browser do not represent the same real reader");
|
|
const source = await api.post<{ id: string; companyId: string; conversationUserId: string; conversationAgentId: string }>(
|
|
`/api/companies/${ctx.input.fixtures.company.id}/chats/${ctx.input.fixtures.agent.id}`);
|
|
await ctx.refreshIssue();
|
|
if (source.companyId !== ctx.input.fixtures.company.id || source.conversationUserId !== person.id
|
|
|| source.conversationAgentId !== ctx.input.fixtures.agent.id || ctx.issue()?.id !== source.id)
|
|
throw new Error("Canonical commentary conversation is not owned by its actual reader");
|
|
const receipt = { ownerId, readerId: person.id, apiUserId: apiPerson.user.id, browserUserId: browserPerson.user.id,
|
|
sourceIssueId: source.id, sourceConversationUserId: source.conversationUserId };
|
|
await ctx.input.evidence("chat-catalog-commentary-reader-identity.json", receipt);
|
|
return { receipt, restore };
|
|
} catch (error) {
|
|
await restore();
|
|
throw error;
|
|
}
|
|
}
|