Files
paperclip/server/src/__tests__/adapter-routes.test.ts
T
Devin Foley ab8b471685 Add built-in grok_local adapter (#6087)
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies, so
adapter quality directly affects what runtimes the control plane can
supervise.
> - Local CLI adapters are one of the core execution surfaces because
they turn real coding tools into Paperclip-managed employees with
heartbeats, transcripts, and reviewability.
> - Grok Build was installed on the Paperclip host, but Paperclip had no
built-in `grok_local` adapter, so the runtime could not be configured
through the normal server/UI/CLI adapter path.
> - That gap needed to be closed with the same built-in registry,
environment diagnostics, transcript parsing, and skill/instructions
behavior that the other local adapters already rely on.
> - After the initial adapter landed, a real follow-up run showed that
Grok streaming text was being rendered one fragment per line, which made
transcripts harder to read even though the runtime itself was working.
> - This pull request adds the built-in `grok_local` adapter end-to-end
and then fixes the transcript parser so streamed Grok output is
coalesced into readable assistant/thinking blocks.
> - The benefit is that Grok Build becomes a first-class Paperclip
runtime with a usable operator experience instead of a partially wired
runtime with noisy transcript output.

## What Changed

- Added a new built-in `@paperclipai/adapter-grok-local` package with
server, UI, and CLI entrypoints.
- Implemented Grok execution, session handling, environment diagnostics,
config building, skill syncing, and parser coverage inside the new
adapter package.
- Registered `grok_local` across the built-in adapter inventories and
capability/display metadata in server, UI, CLI, and shared constants.
- Added adapter route coverage for the new built-in type.
- Fixed Grok transcript readability by emitting streamed `text` and
`thought` fragments as deltas so the shared transcript builder coalesces
them into readable message blocks.
- Added regression tests for the Grok parser and transcript coalescing
behavior.

## Verification

- `pnpm vitest run
packages/adapters/grok-local/src/ui/parse-stdout.test.ts
ui/src/adapters/transcript.test.ts`
- `pnpm --filter @paperclipai/adapter-grok-local build`
- Manual runtime verification on the Paperclip host during
implementation and follow-up review:
  - confirmed the Grok CLI was installed and authenticated
- confirmed the worktree dev server could be restarted cleanly and
health-checked after the parser follow-up
- No screenshots attached. This change is primarily adapter plumbing
plus transcript formatting behavior; reviewers can verify via the
Grok-backed run surfaces directly.

## Risks

- This adds a new built-in adapter, so any missed registration surface
could create inconsistencies between server, UI, and CLI behavior.
- The adapter depends on Grok Build's current event/output shape; if
upstream Grok streaming JSON changes, transcript parsing or session
extraction may need follow-up updates.
- The transcript readability fix intentionally changes how Grok
fragments are grouped, so any downstream code that implicitly expected
one entry per fragment would behave differently.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex via Paperclip `codex_local` agent runtime.
- GPT-5-class coding model with tool use, shell execution, file editing,
and repo inspection enabled.
- Exact backend model ID/context window were not surfaced to the agent
in this Paperclip session.

## 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
- [ ] 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
2026-05-16 09:51:09 -07:00

343 lines
13 KiB
TypeScript

import express from "express";
import request from "supertest";
import { afterEach, beforeEach, describe, expect, it } from "vitest";
import { vi } from "vitest";
import type { ServerAdapterModule } from "../adapters/index.js";
const mockAdapterPluginStore = vi.hoisted(() => ({
listAdapterPlugins: vi.fn(),
addAdapterPlugin: vi.fn(),
removeAdapterPlugin: vi.fn(),
getAdapterPluginByType: vi.fn(),
getAdapterPluginsDir: vi.fn(),
getDisabledAdapterTypes: vi.fn(),
setAdapterDisabled: vi.fn(),
}));
const mockPluginLoader = vi.hoisted(() => ({
buildExternalAdapters: vi.fn(),
loadExternalAdapterPackage: vi.fn(),
getUiParserSource: vi.fn(),
getOrExtractUiParserSource: vi.fn(),
reloadExternalAdapter: vi.fn(),
}));
const overridingConfigSchemaAdapter: ServerAdapterModule = {
type: "claude_local",
execute: async () => ({ exitCode: 0, signal: null, timedOut: false }),
testEnvironment: async () => ({
adapterType: "claude_local",
status: "pass",
checks: [],
testedAt: new Date(0).toISOString(),
}),
getConfigSchema: async () => ({
version: 1,
fields: [
{
key: "mode",
type: "text",
label: "Mode",
},
],
}),
};
let registerServerAdapter: typeof import("../adapters/registry.js").registerServerAdapter;
let unregisterServerAdapter: typeof import("../adapters/registry.js").unregisterServerAdapter;
let findServerAdapter: typeof import("../adapters/registry.js").findServerAdapter;
let setOverridePaused: typeof import("../adapters/registry.js").setOverridePaused;
let adapterRoutes: typeof import("../routes/adapters.js").adapterRoutes;
let errorHandler: typeof import("../middleware/index.js").errorHandler;
function registerModuleMocks() {
vi.doMock("node:child_process", async () => vi.importActual("node:child_process"));
vi.doMock("../adapters/plugin-loader.js", () => mockPluginLoader);
vi.doMock("../services/adapter-plugin-store.js", () => mockAdapterPluginStore);
vi.doMock("../routes/adapters.js", async () => vi.importActual("../routes/adapters.js"));
vi.doMock("../routes/authz.js", async () => vi.importActual("../routes/authz.js"));
vi.doMock("../middleware/index.js", async () => vi.importActual("../middleware/index.js"));
}
function createApp(actorOverrides: Partial<Express.Request["actor"]> = {}) {
const app = express();
app.use(express.json());
app.use((req, _res, next) => {
(req as any).actor = {
type: "board",
userId: "local-board",
companyIds: [],
source: "local_implicit",
isInstanceAdmin: false,
...actorOverrides,
};
next();
});
app.use("/api", adapterRoutes());
app.use(errorHandler);
return app;
}
describe("adapter routes", () => {
beforeEach(async () => {
vi.resetModules();
vi.doUnmock("node:child_process");
vi.doUnmock("../adapters/registry.js");
vi.doUnmock("../adapters/plugin-loader.js");
vi.doUnmock("../services/adapter-plugin-store.js");
vi.doUnmock("../routes/adapters.js");
vi.doUnmock("../routes/authz.js");
vi.doUnmock("../middleware/index.js");
registerModuleMocks();
mockAdapterPluginStore.listAdapterPlugins.mockReturnValue([]);
mockAdapterPluginStore.addAdapterPlugin.mockResolvedValue(undefined);
mockAdapterPluginStore.removeAdapterPlugin.mockReturnValue(false);
mockAdapterPluginStore.getAdapterPluginByType.mockReturnValue(undefined);
mockAdapterPluginStore.getAdapterPluginsDir.mockReturnValue("/tmp/paperclip-adapter-routes-test");
mockAdapterPluginStore.getDisabledAdapterTypes.mockReturnValue([]);
mockAdapterPluginStore.setAdapterDisabled.mockReturnValue(false);
mockPluginLoader.buildExternalAdapters.mockResolvedValue([]);
mockPluginLoader.loadExternalAdapterPackage.mockResolvedValue(null);
mockPluginLoader.getUiParserSource.mockResolvedValue(null);
mockPluginLoader.getOrExtractUiParserSource.mockResolvedValue(null);
mockPluginLoader.reloadExternalAdapter.mockResolvedValue(null);
const [registry, routes, middleware] = await Promise.all([
vi.importActual<typeof import("../adapters/registry.js")>("../adapters/registry.js"),
import("../routes/adapters.js"),
import("../middleware/index.js"),
]);
registerServerAdapter = registry.registerServerAdapter;
unregisterServerAdapter = registry.unregisterServerAdapter;
findServerAdapter = registry.findServerAdapter;
setOverridePaused = registry.setOverridePaused;
adapterRoutes = routes.adapterRoutes;
errorHandler = middleware.errorHandler;
setOverridePaused("claude_local", false);
unregisterServerAdapter("claude_local");
registerServerAdapter(overridingConfigSchemaAdapter);
});
afterEach(() => {
setOverridePaused("claude_local", false);
unregisterServerAdapter("claude_local");
});
it("GET /api/adapters includes capabilities object for each adapter", async () => {
const app = createApp();
const res = await request(app).get("/api/adapters");
expect(res.status).toBe(200);
const adapters = Array.isArray(res.body) ? res.body : JSON.parse(res.text);
expect(Array.isArray(adapters)).toBe(true);
expect(adapters.length).toBeGreaterThan(0);
// Every adapter should have a capabilities object
for (const adapter of adapters) {
expect(adapter.capabilities).toBeDefined();
expect(typeof adapter.capabilities.supportsInstructionsBundle).toBe("boolean");
expect(typeof adapter.capabilities.supportsSkills).toBe("boolean");
expect(typeof adapter.capabilities.supportsLocalAgentJwt).toBe("boolean");
expect(typeof adapter.capabilities.requiresMaterializedRuntimeSkills).toBe("boolean");
}
});
it("GET /api/adapters returns correct capabilities for built-in adapters", async () => {
const app = createApp();
const res = await request(app).get("/api/adapters");
expect(res.status).toBe(200);
// codex_local has instructions bundle + skills + jwt, no materialized skills
// (claude_local is overridden by beforeEach, so check codex_local instead)
const codexLocal = res.body.find((a: any) => a.type === "codex_local");
expect(codexLocal).toBeDefined();
expect(codexLocal.capabilities).toMatchObject({
supportsInstructionsBundle: true,
supportsSkills: true,
supportsLocalAgentJwt: true,
requiresMaterializedRuntimeSkills: false,
});
// process adapter should have no local capabilities
const processAdapter = res.body.find((a: any) => a.type === "process");
expect(processAdapter).toBeDefined();
expect(processAdapter.capabilities).toMatchObject({
supportsInstructionsBundle: false,
supportsSkills: false,
supportsLocalAgentJwt: false,
requiresMaterializedRuntimeSkills: false,
});
// cursor adapter should require materialized runtime skills
const cursorAdapter = res.body.find((a: any) => a.type === "cursor");
expect(cursorAdapter).toBeDefined();
expect(cursorAdapter.capabilities.requiresMaterializedRuntimeSkills).toBe(true);
expect(cursorAdapter.capabilities.supportsInstructionsBundle).toBe(true);
const grokAdapter = res.body.find((a: any) => a.type === "grok_local");
expect(grokAdapter).toBeDefined();
expect(grokAdapter.capabilities).toMatchObject({
supportsInstructionsBundle: true,
supportsSkills: true,
supportsLocalAgentJwt: true,
requiresMaterializedRuntimeSkills: true,
});
// hermes_local currently supports skills + local JWT, but not the managed
// instructions bundle flow because the bundled adapter does not consume
// instructionsFilePath at runtime.
const hermesAdapter = res.body.find((a: any) => a.type === "hermes_local");
expect(hermesAdapter).toBeDefined();
expect(hermesAdapter.capabilities).toMatchObject({
supportsInstructionsBundle: false,
supportsSkills: true,
supportsLocalAgentJwt: true,
requiresMaterializedRuntimeSkills: false,
});
});
it("GET /api/adapters derives supportsSkills from listSkills/syncSkills presence", async () => {
const app = createApp();
const res = await request(app).get("/api/adapters");
expect(res.status).toBe(200);
// http adapter has no listSkills/syncSkills
const httpAdapter = res.body.find((a: any) => a.type === "http");
expect(httpAdapter).toBeDefined();
expect(httpAdapter.capabilities.supportsSkills).toBe(false);
// codex_local has listSkills/syncSkills
const codexLocal = res.body.find((a: any) => a.type === "codex_local");
expect(codexLocal).toBeDefined();
expect(codexLocal.capabilities.supportsSkills).toBe(true);
// acpx_local exposes runtime-aware skill snapshots for Claude/Codex/custom ACP agents
const acpxLocal = res.body.find((a: any) => a.type === "acpx_local");
expect(acpxLocal).toBeDefined();
expect(acpxLocal.capabilities.supportsSkills).toBe(true);
});
it("uses the active adapter when resolving config schema for a paused builtin override", async () => {
const app = createApp();
const active = await request(app).get("/api/adapters/claude_local/config-schema");
expect(active.status, JSON.stringify(active.body)).toBe(200);
expect(active.body).toMatchObject({
fields: [{ key: "mode" }],
});
const paused = await request(app)
.patch("/api/adapters/claude_local/override")
.send({ paused: true });
expect(paused.status, JSON.stringify(paused.body)).toBe(200);
const builtin = await request(app).get("/api/adapters/claude_local/config-schema");
expect([200, 404], JSON.stringify(builtin.body)).toContain(builtin.status);
expect(builtin.body).not.toMatchObject({
fields: [{ key: "mode" }],
});
});
it("serves the built-in acpx_local config schema", async () => {
const app = createApp();
const res = await request(app).get("/api/adapters/acpx_local/config-schema");
expect(res.status, JSON.stringify(res.body)).toBe(200);
expect(res.body.fields).toEqual(
expect.arrayContaining([
expect.objectContaining({
key: "agent",
default: "claude",
options: expect.arrayContaining([
expect.objectContaining({ value: "claude" }),
expect.objectContaining({ value: "codex" }),
expect.objectContaining({ value: "custom" }),
]),
}),
expect.objectContaining({
key: "fastMode",
default: false,
meta: { visibleWhen: { key: "agent", values: ["codex"] } },
}),
expect.objectContaining({
key: "warmHandleIdleMs",
default: 0,
}),
]),
);
const keys = res.body.fields.map((field: { key: string }) => field.key);
expect(keys).not.toContain("mode");
expect(keys).not.toContain("permissionMode");
expect(keys).not.toContain("instructionsFilePath");
expect(keys).not.toContain("promptTemplate");
expect(keys).not.toContain("bootstrapPromptTemplate");
});
it("GET /api/adapters includes ACPX model availability", async () => {
const app = createApp();
const res = await request(app).get("/api/adapters");
expect(res.status, JSON.stringify(res.body)).toBe(200);
const acpxLocal = res.body.find((a: any) => a.type === "acpx_local");
expect(acpxLocal).toBeDefined();
expect(acpxLocal.modelsCount).toBeGreaterThan(0);
});
it("rejects signed-in users without org access", async () => {
const app = createApp({
userId: "outsider-1",
source: "session",
companyIds: [],
memberships: [],
isInstanceAdmin: false,
});
const res = await request(app).get("/api/adapters/claude_local/config-schema");
expect(res.status, JSON.stringify(res.body)).toBe(403);
});
it("POST /api/adapters/install preserves module-provided sessionManagement (hot-install parity with init-time IIFE)", async () => {
const HOT_INSTALL_TYPE = "hot_install_session_test";
const declaredSessionManagement = {
supportsSessionResume: true,
nativeContextManagement: "confirmed" as const,
defaultSessionCompaction: {
enabled: true,
maxSessionRuns: 10,
maxRawInputTokens: 100_000,
maxSessionAgeHours: 24,
},
};
const externalModule: ServerAdapterModule = {
type: HOT_INSTALL_TYPE,
execute: async () => ({ exitCode: 0, signal: null, timedOut: false }),
testEnvironment: async () => ({
adapterType: HOT_INSTALL_TYPE,
status: "pass",
checks: [],
testedAt: new Date(0).toISOString(),
}),
sessionManagement: declaredSessionManagement,
};
mockPluginLoader.loadExternalAdapterPackage.mockResolvedValue(externalModule);
const app = createApp({ isInstanceAdmin: true });
const res = await request(app)
.post("/api/adapters/install")
.send({ packageName: "/tmp/fake-hot-install-adapter", isLocalPath: true });
expect(res.status, JSON.stringify(res.body)).toBe(201);
expect(res.body.type).toBe(HOT_INSTALL_TYPE);
const registered = findServerAdapter(HOT_INSTALL_TYPE);
expect(registered).not.toBeNull();
expect(registered?.sessionManagement).toEqual(declaredSessionManagement);
unregisterServerAdapter(HOT_INSTALL_TYPE);
});
});