feat(agents): smoke tests + README + docs (Stage 6, final)

Closes the agents feature.

Smoke tests (run via `pnpm test:smoke` against a live mcpd at
$MCPD_URL, default https://mcpctl.ad.itaz.eu):

* tests/smoke/agent.smoke.test.ts — full CRUD round-trip:
  create secret + Llm + agent with sampling defaults; `get agents`
  surfaces it; `get agent foo -o yaml | apply -f` round-trips
  identically; create + list a thread via the HTTP API; agent delete
  leaves Llm + secret intact (Restrict + SetNull as designed). Self-
  skips with a warning when /healthz is unreachable.

* tests/smoke/agent-chat.smoke.test.ts — gated on
  MCPCTL_SMOKE_LLM_URL + MCPCTL_SMOKE_LLM_KEY. Provisions secret +
  Llm + agent against a real upstream, runs `mcpctl chat -m … --no-
  stream` (asserts a reply lands), then runs the streaming default
  (asserts text on stdout + `(thread: …)` on stderr). The fast path
  for verifying the in-cluster qwen3-thinking deployment:

      MCPCTL_SMOKE_LLM_URL=http://litellm.nvidia-nim.svc.cluster.local:4000/v1 \
      MCPCTL_SMOKE_LLM_MODEL=qwen3-thinking \
      MCPCTL_SMOKE_LLM_KEY=$(pulumi config get --stack homelab \
        secrets:litellmMcpctlGatewayToken) \
        pnpm test:smoke

Docs:

* README.md — new "Agents" section under Resources with the
  qwen3-thinking quickstart and links to docs/agents.md and
  docs/chat.md. Adds llm + agent rows to the resources table.

* docs/agents.md (new) — full reference: data model, chat-parameter
  table, HTTP API, RBAC mapping, tool-use loop semantics, yaml
  round-trip shorthand, the kubernetes-deployment wiring recipe,
  and a troubleshooting section (namespace collision, llm-in-use,
  pending-row recovery, Anthropic-tool limitation).

* docs/chat.md (new) — user-facing `mcpctl chat` walkthrough:
  modes, per-call flags, slash-commands, threads, and a
  troubleshooting section.

* CLAUDE.md — adds a "Resource types" cheatsheet with one-line
  pointers to each, including the new `agent` row that links to
  the docs.

All suites still green: mcpd 759/759, mcplocal 715/715, cli 430/430.
Smoke tests typecheck and self-skip when no live mcpd is reachable.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Michal
2026-04-25 17:08:37 +01:00
parent 727e7d628c
commit 8b56f09f25
6 changed files with 767 additions and 0 deletions

View File

@@ -0,0 +1,149 @@
/**
* Live-LLM smoke for agent chat.
*
* Runs only when MCPCTL_SMOKE_LLM_URL + MCPCTL_SMOKE_LLM_KEY are set; the
* idea is to point this at a real OpenAI-compatible endpoint and confirm
* the openai-passthrough adapter delivers the user's message and returns
* an assistant reply. For the project's qwen3-thinking deployment:
*
* MCPCTL_SMOKE_LLM_URL=http://litellm.nvidia-nim.svc.cluster.local:4000/v1 \
* MCPCTL_SMOKE_LLM_MODEL=qwen3-thinking \
* MCPCTL_SMOKE_LLM_KEY=sk-... \
* pnpm test:smoke
*
* If the env vars are missing the test self-skips without failing the
* pipeline (the agent CRUD smoke still runs in agent.smoke.test.ts).
*/
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import http from 'node:http';
import https from 'node:https';
import { execSync } from 'node:child_process';
const MCPD_URL = process.env.MCPD_URL ?? 'https://mcpctl.ad.itaz.eu';
const LLM_URL = process.env.MCPCTL_SMOKE_LLM_URL;
const LLM_MODEL = process.env.MCPCTL_SMOKE_LLM_MODEL ?? 'qwen3-thinking';
const LLM_KEY = process.env.MCPCTL_SMOKE_LLM_KEY;
const SUFFIX = Date.now().toString(36);
const SECRET_NAME = `smoke-chat-sec-${SUFFIX}`;
const LLM_NAME = `smoke-chat-llm-${SUFFIX}`;
const AGENT_NAME = `smoke-chat-agent-${SUFFIX}`;
interface CliResult { code: number; stdout: string; stderr: string }
function run(args: string): CliResult {
try {
const stdout = execSync(`mcpctl --direct ${args}`, {
encoding: 'utf-8',
timeout: 60_000,
stdio: ['ignore', 'pipe', 'pipe'],
});
return { code: 0, stdout: stdout.trim(), stderr: '' };
} catch (err) {
const e = err as { status?: number; stdout?: Buffer | string; stderr?: Buffer | string };
return {
code: e.status ?? 1,
stdout: e.stdout ? (typeof e.stdout === 'string' ? e.stdout : e.stdout.toString('utf-8')) : '',
stderr: e.stderr ? (typeof e.stderr === 'string' ? e.stderr : e.stderr.toString('utf-8')) : '',
};
}
}
function healthz(url: string, timeoutMs = 5000): Promise<boolean> {
return new Promise((resolve) => {
const parsed = new URL(`${url.replace(/\/$/, '')}/healthz`);
const driver = parsed.protocol === 'https:' ? https : http;
const req = driver.get({
hostname: parsed.hostname,
port: parsed.port || (parsed.protocol === 'https:' ? 443 : 80),
path: parsed.pathname,
timeout: timeoutMs,
}, (res) => { resolve((res.statusCode ?? 500) < 500); res.resume(); });
req.on('error', () => resolve(false));
req.on('timeout', () => { req.destroy(); resolve(false); });
});
}
let mcpdUp = false;
const liveLlmConfigured = LLM_URL !== undefined && LLM_KEY !== undefined;
describe('agent chat smoke (live LLM)', () => {
beforeAll(async () => {
if (!liveLlmConfigured) {
// eslint-disable-next-line no-console
console.warn('\n ○ agent-chat smoke: skipped — set MCPCTL_SMOKE_LLM_URL + MCPCTL_SMOKE_LLM_KEY to run against a real LLM.\n');
return;
}
mcpdUp = await healthz(MCPD_URL);
if (!mcpdUp) {
// eslint-disable-next-line no-console
console.warn(`\n ○ agent-chat smoke: skipped — ${MCPD_URL}/healthz unreachable.\n`);
}
}, 20_000);
afterAll(() => {
if (!liveLlmConfigured || !mcpdUp) return;
run(`delete agent ${AGENT_NAME}`);
run(`delete llm ${LLM_NAME}`);
run(`delete secret ${SECRET_NAME}`);
});
it('provisions secret + Llm + agent against the live endpoint', () => {
if (!liveLlmConfigured || !mcpdUp) return;
run(`delete secret ${SECRET_NAME}`);
run(`delete llm ${LLM_NAME}`);
run(`delete agent ${AGENT_NAME}`);
const sec = run(`create secret ${SECRET_NAME} --data API_KEY=${LLM_KEY!}`);
expect(sec.code, sec.stderr).toBe(0);
const llm = run([
`create llm ${LLM_NAME}`,
'--type openai',
`--model ${LLM_MODEL}`,
`--url ${LLM_URL!}`,
`--api-key-ref ${SECRET_NAME}/API_KEY`,
].join(' '));
expect(llm.code, llm.stderr).toBe(0);
const agent = run([
`create agent ${AGENT_NAME}`,
`--llm ${LLM_NAME}`,
`--description "live chat smoke"`,
`--system-prompt "You are a smoke test. Always reply with the single token READY."`,
'--default-temperature 0',
'--default-max-tokens 32',
].join(' '));
expect(agent.code, agent.stderr).toBe(0);
});
it('one-shot `mcpctl chat` sends a message and prints a reply', () => {
if (!liveLlmConfigured || !mcpdUp) return;
const result = run(`chat ${AGENT_NAME} -m "ping" --no-stream`);
expect(result.code, result.stderr).toBe(0);
expect(result.stdout.length).toBeGreaterThan(0);
// We can't bind too tightly to model output but the system prompt nudges
// toward "READY". Either way: we got a reply.
expect(result.stderr).toMatch(/thread:\s+c[a-z0-9]+/);
});
it('streaming `mcpctl chat` emits text deltas', () => {
if (!liveLlmConfigured || !mcpdUp) return;
// Default mode is streaming. Pipe stdout/stderr separately.
let stdout = '';
let stderr = '';
try {
const out = execSync(`mcpctl --direct chat ${AGENT_NAME} -m "say hello" 2> /tmp/agent-smoke-err`, {
encoding: 'utf-8', timeout: 60_000,
});
stdout = out;
} catch (err) {
const e = err as { status?: number; stdout?: Buffer | string };
stdout = e.stdout ? (typeof e.stdout === 'string' ? e.stdout : e.stdout.toString('utf-8')) : '';
}
try {
// eslint-disable-next-line @typescript-eslint/no-require-imports
const fs = require('node:fs') as typeof import('node:fs');
stderr = fs.readFileSync('/tmp/agent-smoke-err', 'utf-8');
fs.unlinkSync('/tmp/agent-smoke-err');
} catch { /* ignore */ }
expect(stdout.length).toBeGreaterThan(0);
expect(stderr).toMatch(/thread:\s+c[a-z0-9]+/);
});
});

View File

@@ -0,0 +1,235 @@
/**
* Smoke tests: Agent resource CRUD + thread management against a live mcpd.
*
* Validates Stages 1-5 end-to-end without requiring a live LLM upstream:
* 1. Create a secret + Llm referencing it.
* 2. Create an Agent pinned to that Llm with defaultParams.
* 3. `mcpctl get agents` shows the row; describe pretty-prints it.
* 4. `mcpctl get agent foo -o yaml | apply -f -` round-trips identically.
* 5. POST /api/v1/agents/:name/threads creates a thread; GET lists it.
* 6. Cleanup leaves the underlying Llm/Secret intact.
*
* Actual chat turns (which require a live LLM) live in agent-chat.smoke.test.ts
* and are gated on MCPCTL_SMOKE_LLM_URL being set.
*/
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import http from 'node:http';
import https from 'node:https';
import { execSync } from 'node:child_process';
import { writeFileSync, unlinkSync, mkdtempSync } from 'node:fs';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
const MCPD_URL = process.env.MCPD_URL ?? 'https://mcpctl.ad.itaz.eu';
const SUFFIX = Date.now().toString(36);
const SECRET_NAME = `smoke-agent-sec-${SUFFIX}`;
const LLM_NAME = `smoke-agent-llm-${SUFFIX}`;
const AGENT_NAME = `smoke-agent-${SUFFIX}`;
interface CliResult { code: number; stdout: string; stderr: string }
function run(args: string): CliResult {
try {
const stdout = execSync(`mcpctl --direct ${args}`, {
encoding: 'utf-8',
timeout: 30_000,
stdio: ['ignore', 'pipe', 'pipe'],
});
return { code: 0, stdout: stdout.trim(), stderr: '' };
} catch (err) {
const e = err as { status?: number; stdout?: Buffer | string; stderr?: Buffer | string };
return {
code: e.status ?? 1,
stdout: e.stdout ? (typeof e.stdout === 'string' ? e.stdout : e.stdout.toString('utf-8')) : '',
stderr: e.stderr ? (typeof e.stderr === 'string' ? e.stderr : e.stderr.toString('utf-8')) : '',
};
}
}
function healthz(url: string, timeoutMs = 5000): Promise<boolean> {
return new Promise((resolve) => {
const parsed = new URL(`${url.replace(/\/$/, '')}/healthz`);
const driver = parsed.protocol === 'https:' ? https : http;
const req = driver.get(
{
hostname: parsed.hostname,
port: parsed.port || (parsed.protocol === 'https:' ? 443 : 80),
path: parsed.pathname,
timeout: timeoutMs,
},
(res) => { resolve((res.statusCode ?? 500) < 500); res.resume(); },
);
req.on('error', () => resolve(false));
req.on('timeout', () => { req.destroy(); resolve(false); });
});
}
let mcpdUp = false;
describe('agent smoke', () => {
beforeAll(async () => {
mcpdUp = await healthz(MCPD_URL);
if (!mcpdUp) {
// eslint-disable-next-line no-console
console.warn(`\n ○ agent smoke: skipped — ${MCPD_URL}/healthz unreachable.\n`);
}
}, 20_000);
afterAll(() => {
if (!mcpdUp) return;
run(`delete agent ${AGENT_NAME}`);
run(`delete llm ${LLM_NAME}`);
run(`delete secret ${SECRET_NAME}`);
});
it('creates a secret to back the Llm api key', () => {
if (!mcpdUp) return;
run(`delete secret ${SECRET_NAME}`);
const result = run(`create secret ${SECRET_NAME} --data API_KEY=sk-fake-smoke`);
expect(result.code, result.stderr).toBe(0);
});
it('creates an Llm pinned to that secret', () => {
if (!mcpdUp) return;
run(`delete llm ${LLM_NAME}`);
const result = run([
`create llm ${LLM_NAME}`,
'--type openai',
'--model gpt-4o-mini',
'--url http://localhost:9999',
`--api-key-ref ${SECRET_NAME}/API_KEY`,
].join(' '));
expect(result.code, result.stderr).toBe(0);
});
it('creates an agent pinned to that Llm with sampling defaults', () => {
if (!mcpdUp) return;
run(`delete agent ${AGENT_NAME}`);
const result = run([
`create agent ${AGENT_NAME}`,
`--llm ${LLM_NAME}`,
`--description "smoke agent for end-to-end CRUD"`,
`--system-prompt "You are a smoke-test agent."`,
'--default-temperature 0.2',
'--default-max-tokens 512',
].join(' '));
expect(result.code, result.stderr || result.stdout).toBe(0);
expect(result.stdout).toMatch(new RegExp(`agent '${AGENT_NAME}'`));
});
it('lists the agent in `get agents`', () => {
if (!mcpdUp) return;
const result = run('get agents -o json');
expect(result.code).toBe(0);
const rows = JSON.parse(result.stdout) as Array<{ name: string; llm: { name: string }; defaultParams: { temperature?: number } }>;
const row = rows.find((r) => r.name === AGENT_NAME);
expect(row, `agent ${AGENT_NAME} must be present`).toBeDefined();
expect(row!.llm.name).toBe(LLM_NAME);
expect(row!.defaultParams.temperature).toBe(0.2);
});
it('round-trips yaml output through apply -f without diff', () => {
if (!mcpdUp) return;
const yaml = run(`get agent ${AGENT_NAME} -o yaml`);
expect(yaml.code).toBe(0);
expect(yaml.stdout).toMatch(/kind:\s+agent/i);
expect(yaml.stdout).toContain(`name: ${AGENT_NAME}`);
const dir = mkdtempSync(join(tmpdir(), 'mcpctl-agent-smoke-'));
const path = join(dir, 'agent.yaml');
const amended = yaml.stdout.replace(
'smoke agent for end-to-end CRUD',
'smoke agent (amended)',
);
writeFileSync(path, amended);
try {
const applied = run(`apply -f ${path}`);
expect(applied.code, applied.stderr || applied.stdout).toBe(0);
const second = run(`get agent ${AGENT_NAME} -o json`);
const parsed = JSON.parse(second.stdout) as { description: string };
expect(parsed.description).toBe('smoke agent (amended)');
} finally {
unlinkSync(path);
}
});
it('creates a chat thread and the agent lists it', async () => {
if (!mcpdUp) return;
const create = await httpRequest('POST', `${MCPD_URL}/api/v1/agents/${AGENT_NAME}/threads`, {
title: 'smoke thread',
});
expect(create.status).toBe(201);
const created = JSON.parse(create.body) as { id: string };
expect(created.id).toMatch(/^c[a-z0-9]+/);
const list = await httpRequest('GET', `${MCPD_URL}/api/v1/agents/${AGENT_NAME}/threads`, undefined);
expect(list.status).toBe(200);
const threads = JSON.parse(list.body) as Array<{ id: string; title: string }>;
expect(threads.some((t) => t.id === created.id && t.title === 'smoke thread')).toBe(true);
const messages = await httpRequest('GET', `${MCPD_URL}/api/v1/threads/${created.id}/messages`, undefined);
expect(messages.status).toBe(200);
expect(JSON.parse(messages.body)).toEqual([]);
});
it('deletes the agent and leaves the underlying Llm + secret intact', () => {
if (!mcpdUp) return;
const del = run(`delete agent ${AGENT_NAME}`);
expect(del.code, del.stderr).toBe(0);
const llm = run(`describe llm ${LLM_NAME}`);
expect(llm.code).toBe(0);
});
});
interface HttpResponse { status: number; body: string }
/**
* Async HTTP helper. Authenticates using the same token the CLI carries via
* `mcpctl --direct` (read from ~/.mcpctl/credentials.json).
*/
function httpRequest(method: string, urlStr: string, body: unknown): Promise<HttpResponse> {
return new Promise((resolve, reject) => {
const tokenRaw = readToken();
const parsed = new URL(urlStr);
const driver = parsed.protocol === 'https:' ? https : http;
const headers: Record<string, string> = {
Accept: 'application/json',
...(body !== undefined ? { 'Content-Type': 'application/json' } : {}),
...(tokenRaw !== null ? { Authorization: `Bearer ${tokenRaw}` } : {}),
};
const req = driver.request({
hostname: parsed.hostname,
port: parsed.port || (parsed.protocol === 'https:' ? 443 : 80),
path: parsed.pathname + parsed.search,
method,
headers,
timeout: 15_000,
}, (res) => {
const chunks: Buffer[] = [];
res.on('data', (c: Buffer) => chunks.push(c));
res.on('end', () => {
resolve({ status: res.statusCode ?? 0, body: Buffer.concat(chunks).toString('utf-8') });
});
});
req.on('error', reject);
req.on('timeout', () => { req.destroy(); reject(new Error(`httpRequest timeout: ${method} ${urlStr}`)); });
if (body !== undefined) req.write(JSON.stringify(body));
req.end();
});
}
function readToken(): string | null {
try {
const home = process.env.HOME ?? '';
const path = `${home}/.mcpctl/credentials.json`;
// eslint-disable-next-line @typescript-eslint/no-require-imports
const fs = require('node:fs') as typeof import('node:fs');
if (!fs.existsSync(path)) return null;
const raw = fs.readFileSync(path, 'utf-8');
const parsed = JSON.parse(raw) as { token?: string };
return parsed.token ?? null;
} catch {
return null;
}
}