mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:38:22 +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>
63 lines
5.0 KiB
TypeScript
63 lines
5.0 KiB
TypeScript
import { readFileSync } from "node:fs";
|
|
import { expect, it, vi } from "vitest";
|
|
import { checkSetupHealthCredential } from "./chat-setup-credential.js";
|
|
import { CHAT_OPENCODE_MODEL } from "./chat-runtime-profile.js";
|
|
const key = "synthetic-credential-never-retained";
|
|
const input = () => ({ executionId: "chat-setup-health.runner-opencode.local.setup-only", provider: "opencode", model: CHAT_OPENCODE_MODEL,
|
|
credential: key, platform: "linux", secrets: [] as string[], now: Date.parse("2026-10-27T00:00:00Z"), env: {
|
|
GITHUB_ACTIONS: "true", GITHUB_REPOSITORY: "paperclipai/paperclip", GITHUB_REF: "refs/heads/master",
|
|
GITHUB_WORKFLOW_REF: "paperclipai/paperclip/.github/workflows/runner-full-stack-e2e.yml@refs/heads/master" } });
|
|
const valid = { data: { is_free_tier: false, usage: 123.45, limit: 150, limit_remaining: 26.55, expires_at: null,
|
|
label: key, creator_user_id: "private-person-id", workspace_id: "private-workspace-id" } };
|
|
it("registers before exactly one fixed read-only request and retains closed recognition facts", async () => {
|
|
const i = input();
|
|
const fetch = vi.fn(async (url, options) => {
|
|
expect(i.secrets).toContain(key); expect(url).toBe("https://openrouter.ai/api/v1/key");
|
|
expect(options).toMatchObject({ method: "GET", redirect: "error", headers: { Authorization: `Bearer ${key}` } });
|
|
expect(options.signal).toBeInstanceOf(AbortSignal); return Response.json(valid);
|
|
});
|
|
const receipt = await checkSetupHealthCredential({ ...i, fetch });
|
|
expect(fetch).toHaveBeenCalledTimes(1);
|
|
expect(receipt).toEqual({ schema: "paperclip.setup-health-credential/v1", code: "recognized", httpStatus: 200, recognized: true, expired: false, budgetAvailable: true });
|
|
expect(JSON.stringify(receipt)).not.toMatch(/synthetic|private-|123\.45|26\.55|150|label|workspace/);
|
|
});
|
|
it.each([401, 403, 429, 500])("does not parse or retain HTTP%s body and never retries", async status => {
|
|
const fetch = vi.fn(async () => new Response(JSON.stringify({ error: { message: key, account: "private-person-id" } }), { status }));
|
|
const receipt = await checkSetupHealthCredential({ ...input(), fetch });
|
|
expect(receipt.recognized).toBe(false); expect(receipt.httpStatus).toBe(status); expect(fetch).toHaveBeenCalledTimes(1);
|
|
expect(JSON.stringify(receipt)).not.toMatch(/synthetic|private-|message|account/);
|
|
});
|
|
it.each([{}, { data: { label: key } }, { ...valid, data: { ...valid.data, usage: "123" } }])("refuses malformed HTTP200 recognition evidence", async body => {
|
|
const receipt = await checkSetupHealthCredential({ ...input(), fetch: vi.fn(async () => Response.json(body)) });
|
|
expect(receipt).toMatchObject({ code: "invalid-response", recognized: false, httpStatus: 200 });
|
|
});
|
|
it("reports actual expiry and zero/unlimited budget distinctly without amounts", async () => {
|
|
const expired = await checkSetupHealthCredential({ ...input(), fetch: vi.fn(async () => Response.json({ data: { ...valid.data, expires_at: "2026-10-01T00:00:00Z", limit_remaining: 0 } })) });
|
|
expect(expired).toMatchObject({ recognized: true, expired: true, budgetAvailable: false });
|
|
const unlimited = await checkSetupHealthCredential({ ...input(), fetch: vi.fn(async () => Response.json({ data: { ...valid.data, limit: null, limit_remaining: null } })) });
|
|
expect(unlimited).toMatchObject({ recognized: true, budgetAvailable: null });
|
|
});
|
|
it("withholds thrown network/timeout details and bounds response bodies", async () => {
|
|
const fetch = vi.fn(async () => { throw new Error(`Authorization ${key} private-error`); });
|
|
expect(await checkSetupHealthCredential({ ...input(), fetch })).toMatchObject({ code: "request-failed", recognized: false });
|
|
expect(fetch).toHaveBeenCalledTimes(1);
|
|
const oversized = await checkSetupHealthCredential({ ...input(), fetch: vi.fn(async () => new Response("x".repeat(32769))) });
|
|
expect(oversized).toMatchObject({ code: "invalid-response", recognized: false });
|
|
});
|
|
it("never requests outside exact trusted remote health/profile prerequisites", async () => {
|
|
const fetch = vi.fn();
|
|
for (const override of [{ executionId: "chat-features.runner-opencode.local.create-backlog" }, { platform: "darwin" },
|
|
{ provider: "codex" }, { model: "another/model" }, { credential: "" }, { env: {} }]) {
|
|
expect(await checkSetupHealthCredential({ ...input(), ...override, fetch })).toMatchObject({ code: "prerequisite-missing", recognized: false });
|
|
}
|
|
expect(fetch).not.toHaveBeenCalled();
|
|
});
|
|
it("gates ordinary fixture creation on recognition and fingerprints the diagnostic source", () => {
|
|
const source = readFileSync(new URL("./runner.spec.ts", import.meta.url), "utf8");
|
|
const start = source.indexOf('if (execution.task.flow === "setup_health") {');
|
|
const guard = source.indexOf('if (!credential.recognized) throw', start);
|
|
const fixtures = source.indexOf('fixtures = await withSdkCanaryPreFixture(', start);
|
|
expect(start).toBeGreaterThan(0); expect(guard).toBeGreaterThan(start); expect(fixtures).toBeGreaterThan(guard);
|
|
expect(readFileSync(new URL("./chat-setup-health.ts", import.meta.url), "utf8")).toContain('"chat-setup-credential.ts"');
|
|
});
|