mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-06 21:05:21 +02:00
DottaandPaperclip
24beb00575
Add shared rich ACP transport, durable questions and permissions, verified provider packaging, and bounded activity and plan presentation. Keep Cursor, Copilot, and Pi pending their separate provider qualification. Persist interaction settlement before publication, fence failed writes until fresh recovery, and preserve owned-process cleanup. Incorporate reviewed mainline integration with extended harness coverage. Co-Authored-By: Paperclip <noreply@paperclip.ing>
50 lines
3.8 KiB
TypeScript
50 lines
3.8 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import { runnerMatrix, runnerSuites, extendedHarnessProfiles, extendedHarnessFileTask } from "./catalog.js";
|
|
import { buildRunnerE2EProcessEnvironment, buildPaperclipServerEnvironment } from "./harness-env.js";
|
|
import { parseRunnerSelectors, selectRunnerExecutions } from "./selectors.js";
|
|
import { findSecretLeak, redactText } from "./redaction.js";
|
|
|
|
const selected = runnerMatrix.filter(cell => cell.suite.id === "extended-harnesses");
|
|
describe("extended ACP harness qualification", () => {
|
|
it("has exactly five real product journeys per provider in both environments, excluded from all", () => {
|
|
expect(selected).toHaveLength(30);
|
|
expect(new Set(selected.map(cell => cell.environment.id))).toEqual(new Set(["local", "daytona"]));
|
|
expect(new Set(selected.map(cell => cell.task.id))).toEqual(new Set([
|
|
"hello-complete", "question-resume-complete", "plan-approve-complete", "structured-question-restart-resume", "file-edit-validate",
|
|
]));
|
|
const all = selectRunnerExecutions(parseRunnerSelectors(["--all"]));
|
|
expect(all.some(cell => cell.suite.id === "extended-harnesses")).toBe(false);
|
|
expect(runnerSuites.find(suite => suite.id === "extended-harnesses")?.manualOnly).toBe(true);
|
|
});
|
|
it("uses exact discovered models, encrypted credential references and pending qualification metadata", () => {
|
|
expect(extendedHarnessProfiles.map(profile => profile.model)).toEqual([
|
|
"gpt-5.6-luna[context=272k,reasoning=medium,fast=false]", "gpt-5.6-luna", "openrouter/deepseek/deepseek-v4-flash-0731",
|
|
]);
|
|
for (const profile of extendedHarnessProfiles) {
|
|
expect(profile.modelQualification.source).toBe("candidate_runner_profile");
|
|
const secretRef = { type: "secret_ref" as const, secretId: "11111111-1111-4111-8111-111111111111", version: "latest" as const };
|
|
const payload = profile.buildAgent({ executionId: "fixture", environmentId: "local", environmentFixtureId: "local", workspacePath: "/tmp/workspace", secretRefs: { [profile.credential]: secretRef } });
|
|
expect(payload.adapterConfig).toMatchObject({ provider: "acpx", model: profile.model, timeoutSec: 120, acpxAgent: profile.qualificationCandidate, env: { [profile.credential]: secretRef } });
|
|
}
|
|
});
|
|
it("replaces ambient admission with the selected exact pairs and strips raw provider credentials from server", () => {
|
|
const cell = selected[0]!;
|
|
const ambient = { PAPERCLIP_RUNNER_ACPX_QUALIFICATION: "ambient", CURSOR_AUTH_TOKEN: "cursor", CURSOR_API_KEY: "cursor-key", COPILOT_GITHUB_TOKEN: "copilot", GH_TOKEN: "github", GITHUB_TOKEN: "github" };
|
|
const env = buildRunnerE2EProcessEnvironment(ambient, [cell]);
|
|
expect(JSON.parse(env.PAPERCLIP_RUNNER_ACPX_QUALIFICATION!)).toEqual([{ agent: "cursor", model: cell.profile.model }]);
|
|
const server = buildPaperclipServerEnvironment(env);
|
|
for (const name of Object.keys(ambient).filter(name => name !== "PAPERCLIP_RUNNER_ACPX_QUALIFICATION")) expect(server[name]).toBeUndefined();
|
|
expect(buildRunnerE2EProcessEnvironment(ambient, []).PAPERCLIP_RUNNER_ACPX_QUALIFICATION).toBeUndefined();
|
|
expect(() => buildRunnerE2EProcessEnvironment({}, [{ ...cell, suite: { ...cell.suite, manualOnly: false } }])).toThrow("explicit");
|
|
});
|
|
it("grades the actual file independently of the model's validation claim", () => {
|
|
const cell = selected.find(cell => cell.task.id === "file-edit-validate")!;
|
|
expect(extendedHarnessFileTask.buildMatchers("nonce", cell)).toContainEqual({ kind: "file_exact", path: "extended-nonce.txt", expected: "verified-nonce\n" });
|
|
});
|
|
it("redacts and detects GitHub credential shapes even without the bound value", () => {
|
|
const token = `github_pat_${"x".repeat(40)}`;
|
|
expect(findSecretLeak(token, [])).toBe("secret-shaped value");
|
|
expect(redactText(token, [])).not.toContain(token);
|
|
});
|
|
});
|