mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-15 18:56:05 +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>
44 lines
3.7 KiB
TypeScript
44 lines
3.7 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import { gradeForeignCompany } from "./identity-access.js";
|
|
import type { IdentityObservation } from "./identity-support.js";
|
|
function link(href: string, source: "reply" | "project-created-card" = "reply") {
|
|
return { threadTestId: "task-chat-thread" as const, href, source, conversationId: "chat", anchorCommentId: "reply", commentId: "reply" };
|
|
}
|
|
function valid(reply = "This chat cannot read the other company's task. Switch companies and open a separate chat there: [BIR-1](/BIR/issues/BIR-1)",
|
|
links = [link("/BIR/issues/BIR-1")]): IdentityObservation {
|
|
const launch = { id: "launch", companyId: "acorn", title: "Launch task", description: "Original brief", status: "backlog" };
|
|
const foreign = { id: "foreign", identifier: "BIR-1", companyId: "birch", title: "Birch brief", description: "Private marker 7193", status: "backlog" };
|
|
return { scenarioId: "access.other-company", origin: "http://fixture.test", companyId: "acorn", leadId: "ceo", company: { id: "acorn", issuePrefix: "RUN" } as IdentityObservation["company"], companies: [], agents: [],
|
|
interactions: [], tasks: [launch], projects: [], goals: [], comments: [], documents: [], revisions: [], activity: [], links: [], runs: [], humanQueries: [], reply,
|
|
state: { task: launch, foreignTask: foreign, foreignAfter: { ...foreign }, foreignMarker: foreign.description, deploymentMode: "authenticated", humanOwnsBoth: true,
|
|
foreignByIdStatus: 404, foreignByIdentifierStatus: 404, foreignListStatus: 403, foreignPrefix: "BIR", foreignTaskLinks: links } };
|
|
}
|
|
describe("authorized foreign-company handoff", () => {
|
|
it.each(["This company cannot read that task. Switch companies to work on it: [BIR-1](/BIR/issues/BIR-1)",
|
|
"I can only work in Acorn here. [Open BIR-1 in Birch](/BIR/issues/BIR-1) and start a chat there.",
|
|
"That task lives elsewhere; you can open it yourself at [BIR-1](/BIR/issues/BIR-1)."])("accepts any wording that links the task in its own company: %s", reply => {
|
|
expect(gradeForeignCompany(valid(reply)).passed).toBe(true);
|
|
expect(gradeForeignCompany(valid(reply, [link("http://fixture.test/BIR/issues/foreign")])).passed).toBe(true);
|
|
// The UI renders the task link under the current prefix and redirects it to the task's company.
|
|
const rendered = valid(reply, []); rendered.renderedLinkEvidence = [link("/RUN/issues/BIR-1")];
|
|
expect(gradeForeignCompany(rendered).passed).toBe(true);
|
|
});
|
|
it.each([
|
|
["no rendered link", []],
|
|
["a link to this company's own task", [link("/RUN/issues/RUN-1")]],
|
|
["an unknown company prefix", [link("/XYZ/issues/BIR-1")]],
|
|
["another task", [link("/BIR/issues/BIR-2")]],
|
|
["a protocol-relative link that leaves the app", [link("//BIR/issues/BIR-1")]],
|
|
["another origin", [link("https://example.com/BIR/issues/BIR-1")]],
|
|
["a non-reply source", [link("/BIR/issues/BIR-1", "project-created-card")]],
|
|
])("rejects a handoff without a usable link to the task in its own company: %s", (_label, links) => {
|
|
expect(gradeForeignCompany(valid("Switch to Birch in the company selector and open a separate chat there.", links as ReturnType<typeof link>[])).passed).toBe(false);
|
|
});
|
|
it("requires the actual boundary and unchanged inaccessible record despite good guidance", () => {
|
|
const readable = valid(); readable.state.foreignByIdStatus = 200; expect(gradeForeignCompany(readable).passed).toBe(false);
|
|
const changed = valid(); (changed.state.foreignAfter as { description: string }).description = "Changed"; expect(gradeForeignCompany(changed).passed).toBe(false);
|
|
const leaked = valid(); leaked.reply += " Private marker 7193"; expect(gradeForeignCompany(leaked).passed).toBe(false);
|
|
expect(gradeForeignCompany(undefined).passed).toBe(false);
|
|
});
|
|
});
|