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>
32 lines
3.8 KiB
TypeScript
32 lines
3.8 KiB
TypeScript
import { afterEach, expect, it, vi } from "vitest";
|
|
import type { ChatCatalogContext } from "./chat-catalog-contract.js";
|
|
import { chatCatalogNativePhaseDeadline, chatCatalogNativePhaseIsTimely, chatCatalogOriginalPhaseDeadline } from "./chat-catalog-contract.js";
|
|
import { waitForReply } from "./chat-catalog-domains/identity-support.js";
|
|
const ids = ["companies.export-company", "projects.project-defaults", "questions-and-approvals.ambiguous-yes", "questions-and-approvals.review-plan", "questions-and-approvals.necessary-question", "task-coordination.block-on-design", "gateways-profiles.rotate-token", "gateways-profiles.create-gateway", "workspaces.preview-service", "assistant-connections.consent-read-only", "navigation-preferences.quick-search", "navigation-preferences.edit-profile", "navigation-preferences.broken-link", "projects.share-project"];
|
|
const context = (id: string, deadline: number | undefined = 630000) => ({ scenario: { id }, input: { execution: { id: `chat-features.runner-opencode.local.${id}` } }, observationDeadlineAt: deadline,
|
|
refreshIssue: async () => {}, issue: () => ({ conversationState: "waiting" }), allRuns: async () => [{ status: Date.now() >= 200000 ? "succeeded" : "running" }] }) as unknown as ChatCatalogContext;
|
|
afterEach(() => vi.useRealTimers());
|
|
it.each(ids)("%s reuses the original setup-inclusive deadline and never grants a fresh phase", id => {
|
|
vi.useFakeTimers(); vi.setSystemTime(200000); const c = context(id);
|
|
expect(chatCatalogNativePhaseDeadline(c, 380000)).toBe(630000); expect(chatCatalogOriginalPhaseDeadline(c)).toBe(630000);
|
|
vi.setSystemTime(629999); expect(chatCatalogNativePhaseDeadline(c, 900000)).toBe(630000);
|
|
vi.setSystemTime(630000); expect(chatCatalogNativePhaseIsTimely(c)).toBe(false); expect(() => chatCatalogOriginalPhaseDeadline(c)).toThrow(/exhausted/);
|
|
});
|
|
it.each(["companies.export-company", "navigation-preferences.quick-search", "questions-and-approvals.ambiguous-yes"])("%s actual identity waiter can finish after the incidental150s cap", async id => {
|
|
vi.useFakeTimers(); vi.setSystemTime(0); const c = context(id, 270000); let completed = false;
|
|
const pending = waitForReply(c, chatCatalogOriginalPhaseDeadline(c)).then(() => { completed = true; });
|
|
await vi.advanceTimersByTimeAsync(151000); expect(completed).toBe(false);
|
|
await vi.advanceTimersByTimeAsync(50000); await pending; expect(completed).toBe(true); expect(c.observationDeadlineAt).toBe(270000);
|
|
});
|
|
it("missing, infinite, expired clocks and delayed late successes fail closed", async () => {
|
|
vi.useFakeTimers(); vi.setSystemTime(1000);
|
|
for (const deadline of [undefined, NaN, Infinity, 1000, 999]) { const c = context(ids[0]!, deadline); Object.assign(c, { observationDeadlineAt: deadline }); expect(() => chatCatalogOriginalPhaseDeadline(c)).toThrow(/exhausted/); }
|
|
const c = context(ids[0]!, 1100); c.refreshIssue = async () => { vi.setSystemTime(1101); }; c.allRuns = async () => [{ status: "succeeded" }] as never;
|
|
const pending = waitForReply(c, chatCatalogOriginalPhaseDeadline(c)).then(() => "accepted", () => "expired"); await vi.advanceTimersByTimeAsync(1000); expect(await pending).toBe("expired");
|
|
});
|
|
it("unselected cases and other provider/environment lanes retain authored phase caps", () => {
|
|
vi.useFakeTimers(); vi.setSystemTime(1000);
|
|
for (const id of ["goals.create-goal-tree", "skills.author-skill", "questions-and-approvals.reject-and-revise", "questions-and-approvals.multi-part-question"]) { const c = context(id, 0); expect(chatCatalogOriginalPhaseDeadline(c)).toBeUndefined(); expect(chatCatalogNativePhaseDeadline(c, 151000)).toBe(151000); }
|
|
for (const id of ids) for (const lane of ["runner-codex.local", "runner-opencode.daytona"]) { const c = context(id, 0); Object.assign(c.input.execution, { id: `chat-features.${lane}.${id}` }); expect(chatCatalogOriginalPhaseDeadline(c)).toBeUndefined(); }
|
|
});
|