fix(cli): stop the MCP stdio bridge serialising requests

The bridge's stdin loop awaited every request before reading the next line, so
it handled exactly one at a time. A single slow call therefore stalled every
later request — and because those requests were never even sent, nothing could
time them out. The client saw silence, not an error.

Observed 2026-08-05: two gitea calls through this bridge sat completely mute
until Claude Code aborted them at its own 1800s idle limit, reporting "sent no
response or progress". The upstream was healthy the whole time — a fresh
session answered the same tools in 0.3s, and the gitea MCP server's own log
showed the calls never reached it. They died queued in the bridge.

JSON-RPC ids exist precisely so responses may return out of order, so nothing
here needed a queue. Requests now dispatch concurrently and are tracked in a
set; stdin close awaits them before the session DELETE, otherwise a concurrent
call races the teardown and dies with a 404.

We still serialise until the session id exists: it arrives on the first
response, and firing later requests without it would open a second upstream
session. A client sends `initialize` first and waits for the reply anyway, so
this costs one round trip rather than throughput.

Also makes the per-request timeout configurable via MCPCTL_MCP_TIMEOUT_MS
(default unchanged at 30s) and names it in the timeout error, so a project with
genuinely long tool calls can raise it instead of hitting a hardcoded wall.

Tests pin both halves: a fast request must overtake a slow one (this fails on
the old serial code — verified by reverting), and a failed request must still
produce a JSON-RPC error carrying the original id rather than nothing.

src/cli/src/commands/mcp.ts

@@ -11,6 +11,14 @@ export interface McpBridgeOptions {
   stderr: NodeJS.WritableStream;
 }
 
+/**
+ * Per-request socket-inactivity timeout for the bridge. A stalled upstream must
+ * become a JSON-RPC error, not silence: the client cannot distinguish "still
+ * working" from "wedged", and its own idle limit may be half an hour away.
+ * Raise it for a project with genuinely long tool calls.
+ */
+export const BRIDGE_TIMEOUT_MS = Number(process.env['MCPCTL_MCP_TIMEOUT_MS']) || 30_000;
+
 export function postJsonRpc(
   url: string,
   body: string,
@@ -37,7 +45,7 @@ export function postJsonRpc(
         path: parsed.pathname,
         method: 'POST',
         headers,
-        timeout: 30_000,
+        timeout: BRIDGE_TIMEOUT_MS,
       },
       (res) => {
         const chunks: Buffer[] = [];
@@ -54,7 +62,7 @@ export function postJsonRpc(
     req.on('error', reject);
     req.on('timeout', () => {
       req.destroy();
-      reject(new Error('Request timed out'));
+      reject(new Error(`Request timed out after ${BRIDGE_TIMEOUT_MS}ms (set MCPCTL_MCP_TIMEOUT_MS to change)`));
     });
     req.write(body);
     req.end();
@@ -128,19 +136,15 @@ export async function runMcpBridge(opts: McpBridgeOptions): Promise<void> {
 
   const rl = createInterface({ input: stdin, crlfDelay: Infinity });
 
-  for await (const line of rl) {
+  /**
-    const trimmed = line.trim();
+   * In-flight requests. Dispatch is CONCURRENT after the session is
-    if (!trimmed) continue;
+   * established — see the head-of-line note below — so stdin can keep being
-
+   * read while a slow call is outstanding.
-    // Parse request ID for error responses
+   */
-    let requestId: unknown = null;
+  const inFlight = new Set<Promise<void>>();
-    try {
-      const parsed = JSON.parse(trimmed) as Record<string, unknown>;
-      requestId = parsed.id ?? null;
-    } catch {
-      // Non-JSON or notification — no id to respond to
-    }
 
+  /** POST one JSON-RPC message and write whatever comes back to stdout. */
+  const dispatch = async (trimmed: string, requestId: unknown): Promise<void> => {
     try {
       const result = await postJsonRpc(endpointUrl, trimmed, sessionId, token);
 
@@ -178,9 +182,48 @@ export async function runMcpBridge(opts: McpBridgeOptions): Promise<void> {
         stdout.write(errorResponse + '\n');
       }
     }
+  };
+
+  for await (const line of rl) {
+    const trimmed = line.trim();
+    if (!trimmed) continue;
+
+    // Parse request ID for error responses
+    let requestId: unknown = null;
+    try {
+      const parsed = JSON.parse(trimmed) as Record<string, unknown>;
+      requestId = parsed.id ?? null;
+    } catch {
+      // Non-JSON or notification — no id to respond to
     }
 
-  // stdin closed — cleanup session
+    // HEAD-OF-LINE BLOCKING: this loop used to `await` every request, so the
+    // bridge handled exactly one at a time. A single slow call stalled EVERY
+    // later request — the client saw silence rather than an error, because the
+    // queued requests were never even sent, so nothing could time them out.
+    // Observed 2026-08-05: two gitea calls sat mute until the client aborted
+    // them at its own 1800s idle limit, while the upstream server was healthy
+    // and answering other sessions in milliseconds. JSON-RPC ids exist exactly
+    // so responses can come back out of order; nothing here needs a queue.
+    //
+    // We still serialise until the session id exists: it comes back on the
+    // first response, and firing later requests without it would open a second
+    // upstream session. In practice a client sends `initialize` first and waits
+    // for its reply anyway, so this costs one round trip, not throughput.
+    if (sessionId === undefined) {
+      await dispatch(trimmed, requestId);
+      continue;
+    }
+
+    const p = dispatch(trimmed, requestId).finally(() => inFlight.delete(p));
+    inFlight.add(p);
+  }
+
+  // stdin closed — let outstanding work finish before tearing the session down,
+  // otherwise a concurrent call races the DELETE and dies with a 404.
+  if (inFlight.size > 0) {
+    await Promise.allSettled([...inFlight]);
+  }
   if (sessionId) {
     await sendDelete(endpointUrl, sessionId, token);
   }

src/cli/tests/commands/mcp.test.ts

@@ -483,3 +483,105 @@ describe('createMcpCommand', () => {
     expect(parsed.opts().project).toBe('my-project');
   });
 });
+
+// ---------------------------------------------------------------------------
+// Regression: head-of-line blocking (2026-08-05)
+//
+// The bridge used to `await` every request inside its stdin loop, so it handled
+// exactly one at a time. A single slow call stalled every later request, and
+// because those requests were never even sent, nothing could time them out —
+// the client just saw silence until its own idle limit fired (30 min, in the
+// incident that prompted this). These pin both halves of the fix: later
+// requests must not queue behind a slow one, and a stalled request must produce
+// a JSON-RPC error rather than nothing.
+// ---------------------------------------------------------------------------
+describe('MCP bridge concurrency', () => {
+  let srv: http.Server;
+  let port: number;
+
+  function sse(id: number | string, result: unknown) {
+    return `event: message\ndata: ${JSON.stringify({ jsonrpc: '2.0', id, result })}\n\n`;
+  }
+
+  beforeAll(async () => {
+    srv = http.createServer((req, res) => {
+      let body = '';
+      req.on('data', (c) => (body += c));
+      req.on('end', () => {
+        const msg = JSON.parse(body || '{}') as { id?: number | string; method?: string; params?: any };
+        const headers: Record<string, string> = { 'Content-Type': 'text/event-stream' };
+        if (msg.method === 'initialize') headers['mcp-session-id'] = 'sess-1';
+        // `slow` blocks far longer than `fast`, so a serial bridge would force
+        // fast's response to arrive second.
+        const delay = msg.params?.name === 'slow' ? 400 : 0;
+        setTimeout(() => {
+          res.writeHead(200, headers);
+          res.end(sse(msg.id ?? 0, { ok: msg.params?.name ?? msg.method }));
+        }, delay);
+      });
+    });
+    await new Promise<void>((r) => srv.listen(0, '127.0.0.1', r));
+    port = (srv.address() as any).port;
+  });
+
+  afterAll(async () => {
+    await new Promise<void>((r) => srv.close(() => r()));
+  });
+
+  function bridge(lines: string[], out: string[]) {
+    const stdin = Readable.from(lines.map((l) => l + '\n'));
+    const stdout = new Writable({
+      write(chunk, _enc, cb) {
+        out.push(chunk.toString().trim());
+        cb();
+      },
+    });
+    const stderr = new Writable({ write(_c, _e, cb) { cb(); } });
+    return runMcpBridge({
+      projectName: 'p',
+      mcplocalUrl: `http://127.0.0.1:${port}`,
+      stdin,
+      stdout,
+      stderr,
+    });
+  }
+
+  it('does not let a slow request block a later fast one', async () => {
+    const out: string[] = [];
+    await bridge(
+      [
+        JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'initialize', params: {} }),
+        JSON.stringify({ jsonrpc: '2.0', id: 2, method: 'tools/call', params: { name: 'slow' } }),
+        JSON.stringify({ jsonrpc: '2.0', id: 3, method: 'tools/call', params: { name: 'fast' } }),
+      ],
+      out,
+    );
+    const ids = out.map((l) => (JSON.parse(l) as { id: number }).id);
+    expect(ids).toContain(2);
+    expect(ids).toContain(3);
+    // The whole point: fast (id 3) overtakes slow (id 2). Serially it could not.
+    expect(ids.indexOf(3)).toBeLessThan(ids.indexOf(2));
+  });
+
+  it('answers with a JSON-RPC error instead of silence when a request fails', async () => {
+    const out: string[] = [];
+    const stdin = Readable.from([
+      JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'initialize', params: {} }) + '\n',
+    ]);
+    const stdout = new Writable({
+      write(chunk, _enc, cb) { out.push(chunk.toString().trim()); cb(); },
+    });
+    const stderr = new Writable({ write(_c, _e, cb) { cb(); } });
+    // Port with nothing on it: the POST fails fast, and the bridge must still
+    // emit a response carrying the original id.
+    await runMcpBridge({
+      projectName: 'p',
+      mcplocalUrl: 'http://127.0.0.1:1',
+      stdin, stdout, stderr,
+    });
+    expect(out.length).toBeGreaterThan(0);
+    const msg = JSON.parse(out[0]!) as { id: number; error?: { code: number } };
+    expect(msg.id).toBe(1);
+    expect(msg.error?.code).toBe(-32603);
+  });
+});

src/mcplocal/src/gate/llm-selector.ts

@@ -95,7 +95,11 @@ export class LlmPromptSelector {
   ): Promise<LlmSelectionResult> {
     const { getSystemPromptFn, signal, serverInfer } = opts;
 
-    const DEFAULT_SYSTEM_PROMPT = `You are a context selection assistant. Given a developer's task keywords and a list of available project prompts, select which prompts are relevant to their work. Return a JSON object with "selectedNames" (array of prompt names) and "reasoning" (brief explanation). Priority 10 prompts must always be included.`;
+    // Keep the answer as SHORT as possible: latency is proportional to output
+    // length (a no-think model runs ~10-18 tok/s). Even an "<=8 words" reasoning
+    // got ignored (models write a full sentence → ~7s). Drop the reasoning field
+    // entirely — the gate only needs the names → just {selectedNames} → ~1-2s.
+    const DEFAULT_SYSTEM_PROMPT = `You are a context selection assistant. Given a developer's task keywords and available project prompts, select the relevant ones. Return ONLY this JSON and nothing else: {"selectedNames":[...]}. No reasoning, no prose, no explanation. Priority 10 prompts must always be included.`;
     const systemPrompt = getSystemPromptFn
       ? await getSystemPromptFn('llm-gate-context-selector', DEFAULT_SYSTEM_PROMPT)
       : DEFAULT_SYSTEM_PROMPT;
@@ -105,7 +109,7 @@ export class LlmPromptSelector {
 Available prompts:
 ${promptIndex.map((p) => `- ${p.name} (priority: ${p.priority}): ${p.summary ?? 'No summary'}${p.chapters?.length ? `\n  Chapters: ${p.chapters.join(', ')}` : ''}`).join('\n')}
 
-Select the relevant prompts. Return JSON: { "selectedNames": [...], "reasoning": "..." }`;
+Select the relevant prompts. Return ONLY: {"selectedNames":[...]}`;
 
     const messages: ChatMessage[] = [
       { role: 'system', content: systemPrompt },

src/mcplocal/src/http/project-mcp-endpoint.ts

@@ -147,10 +147,14 @@ export function registerProjectMcpEndpoint(app: FastifyInstance, mcpdClient: Mcp
       providerRegistry: effectiveRegistry,
     };
     if (resolvedModel) pluginConfig.modelOverride = resolvedModel;
-    // Route gate prompt-selection through this project's server Llm (mcpd
+    // Route gate prompt-selection through a server Llm (mcpd inference proxy)
-    // inference proxy) so cloud/server keys stay at the k8s level; the local
+    // so cloud/server keys stay at the k8s level; the local personal-token
-    // personal-token provider is the fallback. See credential-tiering.
+    // provider is the fallback. See credential-tiering. A dedicated fast
-    if (mcpdConfig.llmProvider) pluginConfig.llmProvider = mcpdConfig.llmProvider;
+    // (no-think) selection Llm can be pinned globally via
+    // MCPCTL_GATE_SELECTION_LLM — it overrides the project's chat llmProvider so
+    // selection stays fast while chat keeps its (thinking) model.
+    const gateSelectionLlm = process.env['MCPCTL_GATE_SELECTION_LLM'] || mcpdConfig.llmProvider;
+    if (gateSelectionLlm) pluginConfig.llmProvider = gateSelectionLlm;
     const basePlugin = createDefaultPlugin(pluginConfig);
     // Optional favourite-index presentation: curated favourite/<tool> + full
     // all/<server>/<tool> + a "prefer favourite/" instruction. Composed AFTER

src/mcplocal/src/proxymodel/plugins/gate.ts

@@ -21,6 +21,26 @@ import { withTimeout, TimeoutError } from '../../util/with-timeout.js';
  * begin_session — on timeout we fall back to deterministic tag matching. */
 const GATE_LLM_TIMEOUT_MS = Number(process.env['MCPCTL_GATE_LLM_TIMEOUT_MS'] ?? '8000');
 
+/**
+ * Extra request fields for the gate's server-Llm selection call. Prompt
+ * selection is mechanical classification that gains nothing from chain-of-
+ * thought, so we ask reasoning models to skip thinking (they otherwise burn the
+ * whole budget reasoning and blow the gate timeout). Sent verbatim by mcpd's
+ * passthrough adapter → litellm/vLLM. Harmless for models that ignore them, and
+ * if a backend rejects them the selector falls back to the local provider.
+ *   - `chat_template_kwargs.enable_thinking:false` — Qwen3 hard-off.
+ *   - `reasoning_effort:'low'` — OpenAI o-series / newer vLLM.
+ * Override with a JSON object in MCPCTL_GATE_SELECT_EXTRA_BODY, or '' to disable.
+ */
+const GATE_SELECT_EXTRA_BODY: Record<string, unknown> = (() => {
+  const raw = process.env['MCPCTL_GATE_SELECT_EXTRA_BODY'];
+  if (raw === '') return {};
+  if (raw !== undefined) {
+    try { return JSON.parse(raw) as Record<string, unknown>; } catch { /* use default */ }
+  }
+  return { chat_template_kwargs: { enable_thinking: false }, reasoning_effort: 'low' };
+})();
+
 export interface GatePluginConfig {
   gated?: boolean;
   providerRegistry?: ProviderRegistry | null;
@@ -308,6 +328,7 @@ async function handleBeginSession(
               temperature: o.temperature,
               max_tokens: o.maxTokens,
               stream: false,
+              ...GATE_SELECT_EXTRA_BODY, // ask reasoning models for a fast, no-think answer
             });
             return pickCompletionText(resp);
           }