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>
49 lines
3.7 KiB
TypeScript
49 lines
3.7 KiB
TypeScript
import { it, expect } from "vitest";
|
|
import { gradeLocateFiles } from "./runtime-workspaces.js";
|
|
function valid() {
|
|
const task = { id: "website", title: "Website task", companyId: "company", projectId: null, status: "done", assigneeAgentId: "morgan" };
|
|
const view = { workspace: { id: "bound-workspace", companyId: "company", projectId: null, name: "Website task workspace", cwd: "/owned/task-root" } };
|
|
return { scenarioId: "workspaces.locate-files", origin: "http://fixture.invalid", companyId: "company", leadId: "ceo",
|
|
state: { companyPrefix: "ACORN", task, worker: { id: "morgan" }, workspaceBefore: view, workspaceAfter: structuredClone(view), marker: "saved prerequisite",
|
|
fileBefore: "saved prerequisite", fileAfter: "saved prerequisite", fixtureRunId: "setup" },
|
|
agents: [], tasks: [task], links: ["/ACORN/execution-workspaces/bound-workspace"], reply: "The actual files are in /owned/task-root.",
|
|
activity: [], runs: [{ id: "setup", agentId: "morgan", status: "succeeded" }], humanQueries: [] };
|
|
}
|
|
it("accepts the actual bound projectless directory and files", () => expect(gradeLocateFiles(valid()).passed).toBe(true));
|
|
it("rejects missing task workspace evidence", () => expect(gradeLocateFiles(undefined).passed).toBe(false));
|
|
it("rejects a plausible agent default directory", () => {
|
|
const o = valid(); o.links = []; o.reply = "The files are probably in Morgan's /default/work directory."; expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
it("rejects linking another workspace", () => {
|
|
const o = valid(); o.links = ["/ACORN/execution-workspaces/other-workspace"]; expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
it("rejects fabricated saved-file setup without its actual worker run", () => {
|
|
const o = valid(); o.runs = []; expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
|
|
it("accepts a reworded reply that links the bound workspace without copying its path or id", () => {
|
|
const o = valid(); o.reply = "Morgan saved them in the website task's own workspace: [COM-1 workspace](/ACORN/execution-workspaces/bound-workspace).";
|
|
expect(gradeLocateFiles(o).passed).toBe(true);
|
|
});
|
|
it("rejects naming the full bound path or id as text without a link the person can open", () => {
|
|
const o = valid(); o.links = []; o.reply = "The bound workspace bound-workspace uses /owned/task-root; open the Workspace view to inspect its files.";
|
|
expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
it("calibrates against the retained failed run: a shortened path with no workspace link fails", () => {
|
|
// Retained reply (gha-42641286447): right workspace named as `.../isolated-workspaces/<company>/<task>`, no workspace link.
|
|
const o = valid(); o.links = ["/ACORN/issues/ACORN-1"]; o.reply = "Its files live in that task's own workspace:\n\n- Workspace: `.../task-root` (workspace `ACORN-1`, shared_workspace mode)";
|
|
expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
it("rejects a wrong saved workspace href even before its DOM anchor renders", () => {
|
|
const o = valid(); o.links = []; o.reply = "Workspace files are in /owned/task-root. [Open workspace](/ACORN/execution-workspaces/another).";
|
|
expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
it("rejects correct resource IDs routed through another company or an unsupported tab", () => {
|
|
const o = valid(); o.links = ["/BIRCH/execution-workspaces/bound-workspace"]; expect(gradeLocateFiles(o).passed).toBe(false);
|
|
o.links = ["/ACORN/execution-workspaces/bound-workspace/not-a-tab"]; expect(gradeLocateFiles(o).passed).toBe(false);
|
|
});
|
|
it("accepts the supported same-resource issues tab without demanding a different heading", () => {
|
|
const o = valid(); o.links = ["/ACORN/execution-workspaces/bound-workspace/issues"];
|
|
expect(gradeLocateFiles(o).passed).toBe(true);
|
|
});
|