src/mcplocal/src/http/routes/proxy.ts

@@ -71,7 +71,9 @@ export function registerProxyRoutes(app: FastifyInstance, client: McpdClient): v
     // Forward the user's auth token to mcpd so RBAC applies per-user.
     // If no user token is present, mcpd will use its auth hook to reject.
     const authHeader = request.headers['authorization'] as string | undefined;
-    const userToken = authHeader?.startsWith('Bearer ') ? authHeader.slice(7) : undefined;
+    const userToken = authHeader !== undefined && authHeader.startsWith('Bearer ')
+      ? authHeader.slice(7)
+      : undefined;
 
     if (isLongRunning(path)) {
       return proxyStreaming(reply, client, request.method, path, querystring, body, userToken);

src/mcplocal/tests/proxy-long-running.test.ts

@@ -1,3 +1,5 @@
+import http from 'node:http';
+
 import Fastify, { type FastifyInstance } from 'fastify';
 import { describe, it, expect, afterEach } from 'vitest';
 
@@ -144,6 +146,63 @@ describe('proxy — long-running route budget', () => {
     expect(res.body).toContain('[DONE]');
   });
 
+  it('delivers each SSE frame while the upstream is still generating', async () => {
+    // The buffering regression is invisible to the pass-through test above:
+    // `inject()` collects the whole body, so a proxy that buffers via
+    // res.text() still passes it. This test proves *progressive* delivery by
+    // making the upstream withhold its final frame until the client has
+    // observed the first one. A buffering proxy can never satisfy that
+    // ordering — the 3s guard resolves the gate so the run fails cleanly
+    // instead of deadlocking.
+    let openGate: (seen: boolean) => void = () => {};
+    const clientSawFirstFrame = new Promise<boolean>((r) => { openGate = r; });
+    const guard = setTimeout(() => openGate(false), 3_000);
+
+    const base = await startUpstream((a) => {
+      a.post('/api/v1/agents/:name/chat', async (_req, reply) => {
+        reply.raw.writeHead(200, { 'Content-Type': 'text/event-stream' });
+        reply.raw.write('data: {"type":"text","delta":"live"}\n\n');
+        await clientSawFirstFrame;
+        reply.raw.write('data: {"type":"final"}\n\n');
+        reply.raw.write('data: [DONE]\n\n');
+        reply.raw.end();
+        return reply;
+      });
+    });
+    const proxy = await startProxy(base, 50);
+    await proxy.listen({ port: 0, host: '127.0.0.1' });
+    const addr = proxy.server.address();
+    if (addr === null || typeof addr === 'string') throw new Error('no address');
+
+    const body = await new Promise<string>((resolve, reject) => {
+      const req = http.request({
+        hostname: '127.0.0.1',
+        port: addr.port,
+        path: '/api/v1/agents/reviewer/chat',
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+      }, (res) => {
+        let acc = '';
+        res.setEncoding('utf-8');
+        res.on('data', (chunk: string) => {
+          acc += chunk;
+          if (acc.includes('"delta":"live"')) openGate(true);
+        });
+        res.on('end', () => resolve(acc));
+        res.on('error', reject);
+      });
+      req.on('error', reject);
+      req.end(JSON.stringify({ message: 'hi', stream: true }));
+    });
+    clearTimeout(guard);
+
+    // The ordering proof: the first frame reached the client while the
+    // upstream was still holding the stream open.
+    await expect(clientSawFirstFrame).resolves.toBe(true);
+    expect(body).toContain('"type":"final"');
+    expect(body).toContain('[DONE]');
+  });
+
   it('relays a non-200 status from a streaming route', async () => {
     const base = await startUpstream((a) => {
       a.post('/api/v1/agents/:name/chat', async (_req, reply) => {

src/mcplocal/tests/smoke/agent-chat.smoke.test.ts

@@ -18,8 +18,12 @@ import { describe, it, expect, beforeAll, afterAll } from 'vitest';
 import http from 'node:http';
 import https from 'node:https';
 import { spawnSync, execSync } from 'node:child_process';
+import { existsSync, readFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { homedir } from 'node:os';
 
 const MCPD_URL = process.env.MCPD_URL ?? 'https://mcpctl.ad.itaz.eu';
+const MCPLOCAL_URL = process.env.MCPLOCAL_URL ?? 'http://localhost:3200';
 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;
@@ -27,6 +31,10 @@ 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-${SUFFIX}`;
+// Dedicated agent for the streaming-timing test: the shared agent's system
+// prompt pins the reply to a single token, which is too short to distinguish
+// live streaming from an end-of-turn buffer dump.
+const STREAM_AGENT_NAME = `smoke-stream-agent-${SUFFIX}`;
 
 interface CliResult { code: number; stdout: string; stderr: string }
 
@@ -99,6 +107,7 @@ describe('agent chat smoke (live LLM)', () => {
   afterAll(() => {
     if (!liveLlmConfigured || !mcpdUp) return;
     run(`delete agent ${AGENT_NAME}`);
+    run(`delete agent ${STREAM_AGENT_NAME}`);
     run(`delete llm ${LLM_NAME}`);
     run(`delete secret ${SECRET_NAME}`);
   });
@@ -139,6 +148,92 @@ describe('agent chat smoke (live LLM)', () => {
     expect(result.stderr).toMatch(/thread:\s+c[a-z0-9]+/);
   });
 
+  it('streams progressively THROUGH mcplocal — frames arrive during generation, not in one burst', async () => {
+    if (!liveLlmConfigured || !mcpdUp) return;
+    // The regression this pins: mcplocal's /api/v1/* proxy buffered SSE via
+    // res.text(), so the CLI showed nothing until the turn finished and then
+    // dumped the whole answer at once. The --direct tests above bypass
+    // mcplocal entirely and cannot catch that. This one posts to the local
+    // proxy (the path `mcpctl chat` actually takes) and asserts frames are
+    // spread across the generation window: with buffering, everything lands
+    // within a few ms of stream end.
+    if (!(await healthz(MCPLOCAL_URL))) {
+      // eslint-disable-next-line no-console
+      console.warn(`\n  ○ mcplocal streaming smoke: skipped — ${MCPLOCAL_URL}/healthz unreachable.\n`);
+      return;
+    }
+    let token = '';
+    try {
+      const credsPath = join(homedir(), '.mcpctl', 'credentials');
+      if (existsSync(credsPath)) {
+        const creds = JSON.parse(readFileSync(credsPath, 'utf-8')) as { token?: string };
+        if (creds.token !== undefined) token = creds.token;
+      }
+    } catch { /* unauthenticated — the request will 401 and fail loudly */ }
+
+    run(`delete agent ${STREAM_AGENT_NAME}`);
+    const agent = run([
+      `create agent ${STREAM_AGENT_NAME}`,
+      `--llm ${LLM_NAME}`,
+      `--description "mcplocal streaming smoke"`,
+      `--system-prompt "You are a smoke test. Follow the user's instructions exactly."`,
+      '--default-temperature 0',
+      '--default-max-tokens 512',
+    ].join(' '));
+    expect(agent.code, agent.stderr).toBe(0);
+
+    const url = new URL(`${MCPLOCAL_URL.replace(/\/$/, '')}/api/v1/agents/${STREAM_AGENT_NAME}/chat`);
+    const deltaTimes: number[] = [];
+    let endTime = 0;
+    let status = 0;
+    let raw = '';
+
+    await new Promise<void>((resolve, reject) => {
+      const req = http.request({
+        hostname: url.hostname,
+        port: url.port || 80,
+        path: url.pathname,
+        method: 'POST',
+        timeout: 120_000,
+        headers: {
+          'Content-Type': 'application/json',
+          ...(token !== '' ? { Authorization: `Bearer ${token}` } : {}),
+        },
+      }, (res) => {
+        status = res.statusCode ?? 0;
+        res.setEncoding('utf-8');
+        let buf = '';
+        res.on('data', (chunk: string) => {
+          raw += chunk;
+          buf += chunk;
+          let nl: number;
+          while ((nl = buf.indexOf('\n\n')) !== -1) {
+            const frame = buf.slice(0, nl);
+            buf = buf.slice(nl + 2);
+            if (/"type":"(text|thinking)"/.test(frame)) deltaTimes.push(Date.now());
+          }
+        });
+        res.on('end', () => { endTime = Date.now(); resolve(); });
+        res.on('error', reject);
+      });
+      req.on('error', reject);
+      req.on('timeout', () => { req.destroy(); reject(new Error('stream timed out')); });
+      req.end(JSON.stringify({
+        message: 'Count from 1 to 40, one number per line. No other text.',
+        stream: true,
+        max_tokens: 400,
+      }));
+    });
+
+    expect(status, raw.slice(0, 500)).toBe(200);
+    expect(deltaTimes.length).toBeGreaterThanOrEqual(2);
+    // The buffering signature: every frame lands in the same final burst as
+    // stream end. Live streaming puts the first delta well before the end —
+    // a 40-line generation spans seconds; 300ms is a conservative floor.
+    const firstDelta = deltaTimes[0]!;
+    expect(endTime - firstDelta).toBeGreaterThanOrEqual(300);
+  }, 150_000);
+
   it('streaming `mcpctl chat` emits text deltas', () => {
     if (!liveLlmConfigured || !mcpdUp) return;
     // Default mode is streaming. Pipe stdout/stderr separately.