mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-15 10:30:37 +09:00
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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 run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge
251 lines
7.5 KiB
TypeScript
251 lines
7.5 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import { afterAll, afterEach, beforeAll, describe, expect, it } from "vitest";
|
|
import { eq } from "drizzle-orm";
|
|
import { agents, companies, createDb, environmentLeases, environments, heartbeatRuns } from "@paperclipai/db";
|
|
import {
|
|
getEmbeddedPostgresTestSupport,
|
|
startEmbeddedPostgresTestDatabase,
|
|
} from "./helpers/embedded-postgres.js";
|
|
import { environmentService } from "../services/environments.ts";
|
|
|
|
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
|
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
|
|
|
|
if (!embeddedPostgresSupport.supported) {
|
|
console.warn(
|
|
`Skipping embedded Postgres environment service tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
|
);
|
|
}
|
|
|
|
describeEmbeddedPostgres("environmentService leases", () => {
|
|
let stopDb: (() => Promise<void>) | null = null;
|
|
let db!: ReturnType<typeof createDb>;
|
|
let svc!: ReturnType<typeof environmentService>;
|
|
|
|
beforeAll(async () => {
|
|
const started = await startEmbeddedPostgresTestDatabase("environment-service");
|
|
stopDb = started.stop;
|
|
db = createDb(started.connectionString);
|
|
svc = environmentService(db);
|
|
});
|
|
|
|
afterEach(async () => {
|
|
await db.delete(environmentLeases);
|
|
await db.delete(heartbeatRuns);
|
|
await db.delete(agents);
|
|
await db.delete(environments);
|
|
await db.delete(companies);
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await stopDb?.();
|
|
});
|
|
|
|
async function seedEnvironment() {
|
|
const companyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const environmentId = randomUUID();
|
|
const runId = randomUUID();
|
|
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Acme",
|
|
status: "active",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
await db.insert(agents).values({
|
|
id: agentId,
|
|
companyId,
|
|
name: "CodexCoder",
|
|
role: "engineer",
|
|
status: "active",
|
|
adapterType: "codex_local",
|
|
adapterConfig: {},
|
|
runtimeConfig: {},
|
|
permissions: {},
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
await db.insert(environments).values({
|
|
id: environmentId,
|
|
companyId,
|
|
name: "Local",
|
|
driver: "local",
|
|
status: "active",
|
|
config: {},
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
await db.insert(heartbeatRuns).values({
|
|
id: runId,
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "manual",
|
|
status: "running",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
|
|
return { companyId, agentId, environmentId, runId };
|
|
}
|
|
|
|
it("acquires and releases a lease for a run", async () => {
|
|
const { companyId, environmentId, runId } = await seedEnvironment();
|
|
|
|
const lease = await svc.acquireLease({
|
|
companyId,
|
|
environmentId,
|
|
heartbeatRunId: runId,
|
|
metadata: { driver: "local" },
|
|
});
|
|
|
|
expect(lease.status).toBe("active");
|
|
expect(lease.heartbeatRunId).toBe(runId);
|
|
|
|
const released = await svc.releaseLease(lease.id);
|
|
|
|
expect(released?.status).toBe("released");
|
|
expect(released?.releasedAt).not.toBeNull();
|
|
});
|
|
|
|
it("releases all active leases for a run without touching unrelated rows", async () => {
|
|
const { companyId, agentId, environmentId, runId } = await seedEnvironment();
|
|
const otherRunId = randomUUID();
|
|
|
|
await db.insert(heartbeatRuns).values({
|
|
id: otherRunId,
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "manual",
|
|
status: "running",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
|
|
const targetLease = await svc.acquireLease({
|
|
companyId,
|
|
environmentId,
|
|
heartbeatRunId: runId,
|
|
});
|
|
const otherLease = await svc.acquireLease({
|
|
companyId,
|
|
environmentId,
|
|
heartbeatRunId: otherRunId,
|
|
});
|
|
|
|
const released = await svc.releaseLeasesForRun(runId);
|
|
|
|
expect(released.map((lease) => lease.id)).toEqual([targetLease.id]);
|
|
|
|
const stillActive = await svc.listLeases(environmentId, { status: "active" });
|
|
expect(stillActive.map((lease) => lease.id)).toEqual([otherLease.id]);
|
|
});
|
|
|
|
it("creates and then reuses the default local environment for a company", async () => {
|
|
const companyId = randomUUID();
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Acme",
|
|
status: "active",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
|
|
const created = await svc.ensureLocalEnvironment(companyId);
|
|
const reused = await svc.ensureLocalEnvironment(companyId);
|
|
|
|
expect(created.driver).toBe("local");
|
|
expect(reused.id).toBe(created.id);
|
|
|
|
const rows = await db.select().from(environments).where(eq(environments.companyId, companyId));
|
|
expect(rows).toHaveLength(1);
|
|
expect(rows[0]?.name).toBe("Local");
|
|
});
|
|
|
|
it("leaves an existing default local environment untouched", async () => {
|
|
const companyId = randomUUID();
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Acme",
|
|
status: "active",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
const archivedAt = new Date("2025-01-01T00:00:00.000Z");
|
|
const [existing] = await db
|
|
.insert(environments)
|
|
.values({
|
|
companyId,
|
|
name: "Archived Local",
|
|
description: "Operator-managed local environment",
|
|
driver: "local",
|
|
status: "archived",
|
|
config: { shell: "zsh" },
|
|
metadata: { owner: "operator" },
|
|
createdAt: archivedAt,
|
|
updatedAt: archivedAt,
|
|
})
|
|
.returning();
|
|
|
|
const ensured = await svc.ensureLocalEnvironment(companyId);
|
|
|
|
expect(ensured.id).toBe(existing?.id);
|
|
expect(ensured.name).toBe("Archived Local");
|
|
expect(ensured.status).toBe("archived");
|
|
expect(ensured.metadata).toEqual({ owner: "operator" });
|
|
|
|
const rows = await db.select().from(environments).where(eq(environments.companyId, companyId));
|
|
expect(rows).toHaveLength(1);
|
|
expect(rows[0]?.updatedAt.toISOString()).toBe(archivedAt.toISOString());
|
|
});
|
|
|
|
it("deduplicates concurrent default local environment creation", async () => {
|
|
const companyId = randomUUID();
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Acme",
|
|
status: "active",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
|
|
const results = await Promise.all(
|
|
Array.from({ length: 8 }, () => svc.ensureLocalEnvironment(companyId)),
|
|
);
|
|
|
|
expect(new Set(results.map((environment) => environment.id)).size).toBe(1);
|
|
|
|
const rows = await db.select().from(environments).where(eq(environments.companyId, companyId));
|
|
expect(rows).toHaveLength(1);
|
|
expect(rows[0]?.driver).toBe("local");
|
|
expect(rows[0]?.status).toBe("active");
|
|
});
|
|
|
|
it("allows multiple SSH environments for the same company", async () => {
|
|
const companyId = randomUUID();
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Acme",
|
|
status: "active",
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
});
|
|
|
|
const first = await svc.create(companyId, {
|
|
name: "Production SSH",
|
|
driver: "ssh",
|
|
config: { host: "prod.example.com", username: "deploy" },
|
|
});
|
|
const second = await svc.create(companyId, {
|
|
name: "Staging SSH",
|
|
driver: "ssh",
|
|
config: { host: "staging.example.com", username: "deploy" },
|
|
});
|
|
|
|
expect(first.id).not.toBe(second.id);
|
|
|
|
const rows = await db.select().from(environments).where(eq(environments.companyId, companyId));
|
|
expect(rows.filter((row) => row.driver === "ssh")).toHaveLength(2);
|
|
});
|
|
});
|