test(mcplocal): end-to-end wire-name coverage on the project endpoint

Drives /projects/:name/mcp over the real Streamable HTTP transport with a
fake websearch upstream: tools/list must serve `websearch_fetch_content`
(every name matching the OpenAI function-name charset), calling that wire
name must reach the upstream as bare `fetch_content`, and a legacy client
echoing the canonical `websearch/fetch_content` must still route.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JaFvfHrQyUKCGv6o3N2Wir

src/cli/src/commands/chat.ts

@@ -70,7 +70,7 @@ export function createChatCommand(deps: ChatCommandDeps): Command {
 }
 
 /** What the chat is bound to: a named Agent or a Project. */
-interface ChatSubject {
+export interface ChatSubject {
   kind: 'agent' | 'project';
   name: string;
   /** URL segment, e.g. `agents/reviewer` or `projects/sre` (name url-encoded). */
@@ -97,14 +97,17 @@ function resolveSubject(agent: string | undefined, opts: ChatOpts): ChatSubject
  * `personality` overlay (the project schema rejects unknown fields) and adds
  * `allowSecrets` when requested.
  */
-function chatBody(subject: ChatSubject, message: string, threadId: string | undefined, overrides: Overrides, stream?: boolean): Record<string, unknown> {
+export function chatBody(subject: ChatSubject, message: string, threadId: string | undefined, overrides: Overrides, stream?: boolean): Record<string, unknown> {
   const o: Record<string, unknown> = { ...overrides };
   if (subject.kind === 'project') {
     delete o.personality;
     if (subject.allowSecrets) o.allowSecrets = true;
   }
   const body: Record<string, unknown> = { message, ...o };
-  if (threadId !== undefined) body.threadId = threadId;
+  // Guard the empty string, not just undefined: a turn that dies before its
+  // `final` frame yields no thread id, and sending `threadId: ""` trips mcpd's
+  // min(1) validation — bricking every later message in the REPL with a 400.
+  if (threadId !== undefined && threadId !== '') body.threadId = threadId;
   if (stream === true) body.stream = true;
   return body;
 }
@@ -205,7 +208,11 @@ async function runOneShot(
   const bar = installStatusBar();
   try {
     const finalThread = await streamOnce(deps, subject, message, threadId, overrides, bar);
-    process.stderr.write(`\n(thread: ${finalThread})\n`);
+    if (finalThread !== undefined) {
+      process.stderr.write(`\n(thread: ${finalThread})\n`);
+    } else {
+      process.stderr.write('\n');
+    }
   } finally {
     bar?.teardown();
   }
@@ -262,7 +269,9 @@ async function runRepl(
           const answered = formatAnswered(res.llm, res.model, res.failedOver);
           if (answered !== '') process.stderr.write(`${styleStats(`(${answered})`)}\n`);
         } else {
-          threadId = await streamOnce(deps, subject, line, threadId, overrides, bar);
+          // A failed turn resolves undefined — keep the previous thread (or
+          // none) instead of overwriting it, so the next message still works.
+          threadId = await streamOnce(deps, subject, line, threadId, overrides, bar) ?? threadId;
           process.stdout.write('\n');
         }
       } catch (err) {
@@ -502,15 +511,21 @@ async function chatRequestNonStream(
   });
 }
 
-/** Stream a single chat call. Returns the resolved threadId. */
-async function streamOnce(
+/**
+ * Stream a single chat call. Returns the resolved threadId, or undefined when
+ * the turn never produced a `final` frame (upstream error, early disconnect).
+ * Returning undefined — instead of the old '' — lets callers keep their
+ * previous thread state rather than poisoning the next request with an empty
+ * id that mcpd's validation rejects.
+ */
+export async function streamOnce(
   deps: ChatCommandDeps,
   subject: ChatSubject,
   message: string,
   threadId: string | undefined,
   overrides: Overrides,
   bar: StatusBar | null = null,
-): Promise<string> {
+): Promise<string | undefined> {
   const url = new URL(`${deps.baseUrl}/api/v1/${subject.path}/chat`);
   const body = JSON.stringify(chatBody(subject, message, threadId, overrides, true));
 
@@ -531,7 +546,7 @@ async function streamOnce(
     }
   }
 
-  return new Promise<string>((resolve, reject) => {
+  return new Promise<string | undefined>((resolve, reject) => {
     const driver = url.protocol === 'https:' ? https : http;
     const req = driver.request({
       hostname: url.hostname,
@@ -552,7 +567,7 @@ async function streamOnce(
         return;
       }
       let buf = '';
-      let resolvedThread = threadId ?? '';
+      let resolvedThread: string | undefined = threadId;
       let answered = '';
       res.setEncoding('utf-8');
       res.on('data', (chunk: string) => {

src/cli/tests/commands/chat-thread-brick.test.ts

@@ -0,0 +1,116 @@
+/**
+ * Regression: a failed first turn must not brick the REPL.
+ *
+ * Observed live: the first message died upstream (anthropic 429) before the
+ * stream's `final` frame, streamOnce resolved '' as the thread id, the REPL
+ * stored it, and every later message sent `threadId: ""` — which mcpd's
+ * `z.string().min(1)` rejects with HTTP 400. The session was permanently
+ * stuck: no turn could succeed again, so no `final` frame could ever repair
+ * the thread id.
+ *
+ * The fix has two independent layers, pinned separately below:
+ *   1. streamOnce resolves `undefined` (not '') when no `final` frame arrived,
+ *      and the REPL keeps its previous thread state on undefined;
+ *   2. chatBody never serializes an empty threadId, even if one leaks in.
+ */
+import http from 'node:http';
+import type { AddressInfo } from 'node:net';
+
+import { describe, it, expect, afterEach } from 'vitest';
+
+import { chatBody, streamOnce } from '../../src/commands/chat.js';
+import type { ChatCommandDeps, ChatSubject } from '../../src/commands/chat.js';
+import type { ApiClient } from '../../src/api-client.js';
+
+const subject: ChatSubject = {
+  kind: 'agent',
+  name: 'reviewer',
+  path: 'agents/reviewer',
+  allowSecrets: false,
+};
+
+// streamOnce only touches baseUrl + token; the ApiClient is for the
+// non-streaming path and never dereferenced here.
+function depsFor(baseUrl: string): ChatCommandDeps {
+  return { client: null as unknown as ApiClient, baseUrl, log: () => {} };
+}
+
+let server: http.Server | null = null;
+
+afterEach(async () => {
+  if (server !== null) {
+    await new Promise<void>((r) => server!.close(() => r()));
+    server = null;
+  }
+});
+
+/** Serve one SSE response body for any POST, return the base URL. */
+async function serveSse(frames: string[]): Promise<string> {
+  server = http.createServer((_req, res) => {
+    res.writeHead(200, { 'Content-Type': 'text/event-stream' });
+    for (const f of frames) res.write(`data: ${f}\n\n`);
+    res.end();
+  });
+  await new Promise<void>((r) => server!.listen(0, '127.0.0.1', r));
+  const { port } = server.address() as AddressInfo;
+  return `http://127.0.0.1:${String(port)}`;
+}
+
+describe('chatBody — threadId serialization', () => {
+  it('omits threadId when undefined', () => {
+    expect(chatBody(subject, 'hi', undefined, {})).not.toHaveProperty('threadId');
+  });
+
+  it('omits threadId when empty — the exact payload that 400s against mcpd', () => {
+    expect(chatBody(subject, 'hi', '', {})).not.toHaveProperty('threadId');
+  });
+
+  it('includes a real threadId', () => {
+    expect(chatBody(subject, 'hi', 'cthread123', {})).toHaveProperty('threadId', 'cthread123');
+  });
+});
+
+describe('streamOnce — thread id after a failed turn', () => {
+  it('resolves undefined when the stream errors before any final frame', async () => {
+    const base = await serveSse([
+      '{"type":"error","message":"anthropic stream: HTTP 429"}',
+      '[DONE]',
+    ]);
+    const resolved = await streamOnce(depsFor(base), subject, 'hi', undefined, {});
+    expect(resolved).toBeUndefined();
+  });
+
+  it('keeps the caller-supplied thread when the turn fails mid-conversation', async () => {
+    const base = await serveSse([
+      '{"type":"error","message":"upstream died"}',
+      '[DONE]',
+    ]);
+    const resolved = await streamOnce(depsFor(base), subject, 'hi', 'cexisting1', {});
+    expect(resolved).toBe('cexisting1');
+  });
+
+  it('resolves the threadId announced by the final frame', async () => {
+    const base = await serveSse([
+      '{"type":"text","delta":"pong"}',
+      '{"type":"final","threadId":"cfresh42"}',
+      '[DONE]',
+    ]);
+    const resolved = await streamOnce(depsFor(base), subject, 'hi', undefined, {});
+    expect(resolved).toBe('cfresh42');
+  });
+
+  it('REPL chain: failed turn 1 leaves turn 2 sendable (the brick)', async () => {
+    const base = await serveSse([
+      '{"type":"error","message":"anthropic stream: HTTP 429"}',
+      '[DONE]',
+    ]);
+    // Mirrors runRepl's assignment: threadId = streamOnce(...) ?? threadId
+    let threadId: string | undefined = undefined;
+    threadId = (await streamOnce(depsFor(base), subject, 'hi', threadId, {})) ?? threadId;
+
+    // Turn 2's body must be valid for mcpd: no threadId key at all.
+    const body = chatBody(subject, 'hi again', threadId, {}, true);
+    expect(body).not.toHaveProperty('threadId');
+    expect(body).toHaveProperty('message', 'hi again');
+  });
+});

src/mcplocal/src/http/index.ts

@@ -2,7 +2,7 @@ export { createHttpServer } from './server.js';
 export type { HttpServerDeps } from './server.js';
 export { loadHttpConfig } from './config.js';
 export type { HttpConfig } from './config.js';
-export { McpdClient, AuthenticationError, ConnectionError } from './mcpd-client.js';
+export { McpdClient, AuthenticationError, ConnectionError, UpstreamTimeoutError } from './mcpd-client.js';
 export { registerProxyRoutes } from './routes/proxy.js';
 export { registerMcpEndpoint } from './mcp-endpoint.js';
 export { registerProjectMcpEndpoint } from './project-mcp-endpoint.js';

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

@@ -13,6 +13,7 @@ import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/
 import type { JSONRPCMessage } from '@modelcontextprotocol/sdk/types.js';
 import type { McpRouter } from '../router.js';
 import type { JsonRpcRequest } from '../types.js';
+import { WireNameCodec, routeWithWireNames } from '../util/wire-names.js';
 
 interface SessionEntry {
   transport: StreamableHTTPServerTransport;
@@ -20,6 +21,9 @@ interface SessionEntry {
 
 export function registerMcpEndpoint(app: FastifyInstance, router: McpRouter): void {
   const sessions = new Map<string, SessionEntry>();
+  // One codec for the shared router: serve OpenAI-safe tool names on the wire,
+  // map tools/call names back to the internal `server/tool` form.
+  const wireCodec = new WireNameCodec();
 
   // POST /mcp — JSON-RPC requests (initialize, tools/call, etc.)
   app.post('/mcp', async (request, reply) => {
@@ -52,7 +56,11 @@ export function registerMcpEndpoint(app: FastifyInstance, router: McpRouter): vo
     transport.onmessage = async (message: JSONRPCMessage) => {
       // The transport sends us JSON-RPC messages; route them through McpRouter
       if ('method' in message && 'id' in message) {
-        const response = await router.route(message as unknown as JsonRpcRequest);
+        const response = await routeWithWireNames(
+          wireCodec,
+          (req) => router.route(req),
+          message as unknown as JsonRpcRequest,
+        );
         await transport.send(response as unknown as JSONRPCMessage);
       }
       // Notifications (no id) are ignored — router doesn't handle inbound notifications

src/mcplocal/src/http/mcpd-client.ts

@@ -20,9 +20,41 @@ export class ConnectionError extends Error {
   }
 }
 
+/**
+ * Thrown when mcpd was reachable but did not finish in time.
+ *
+ * Deliberately NOT a ConnectionError. Folding timeouts into "cannot connect"
+ * is what made this class of failure so expensive to diagnose: mcpd answered
+ * /healthz in 32ms while the proxy insisted the daemon was down. A timeout and
+ * an unreachable daemon need different messages and different status codes.
+ */
+export class UpstreamTimeoutError extends Error {
+  constructor(readonly url: string, readonly timeoutMs: number) {
+    super(`mcpd did not respond within ${String(timeoutMs)}ms: ${url}`);
+    this.name = 'UpstreamTimeoutError';
+  }
+}
+
+/** True when `err` is an AbortSignal.timeout() firing. */
+function isTimeout(err: unknown): boolean {
+  return err instanceof DOMException && err.name === 'TimeoutError';
+}
+
 /** Default timeout for mcpd requests (ms). Prevents indefinite hangs on slow upstream tool calls. */
 export const DEFAULT_TIMEOUT_MS = 30_000;
 
+/**
+ * Budget for routes that are *expected* to run long: agent/project chat and
+ * raw inference. An agent turn is a multi-turn tool-use loop and legitimately
+ * runs for minutes, so the 30s default is not a safety net there — it is a
+ * guaranteed failure. Matches `STREAM_TIMEOUT_MS` in the CLI's chat command
+ * (src/cli/src/commands/chat.ts), which already allowed 10 minutes; mcplocal
+ * sitting in the middle with 30s was the binding constraint.
+ *
+ * Override with `MCPLOCAL_LONG_TIMEOUT_MS`.
+ */
+export const LONG_RUNNING_TIMEOUT_MS = Number(process.env['MCPLOCAL_LONG_TIMEOUT_MS']) || 600_000;
+
 /**
  * Discovery-class operations (tools/list, resources/list, prompts/list) should not share
  * the full tool-call timeout budget — a single dead upstream would stall session init for
@@ -121,9 +153,7 @@ export class McpdClient {
     try {
       res = await fetch(url, init);
     } catch (err: unknown) {
-      if (err instanceof DOMException && err.name === 'TimeoutError') {
-        throw new ConnectionError(this.baseUrl, new Error(`Request timed out after ${this.timeoutMs}ms`));
-      }
+      if (isTimeout(err)) throw new UpstreamTimeoutError(this.baseUrl, this.timeoutMs);
       throw new ConnectionError(this.baseUrl, err);
     }
 
@@ -131,7 +161,18 @@ export class McpdClient {
       throw new AuthenticationError();
     }
 
-    const text = await res.text();
+    // The body read MUST be inside a try. mcpd writes SSE headers immediately
+    // on chat routes, so fetch() resolves long before the turn finishes and the
+    // abort lands here instead — previously escaping as a raw DOMException and
+    // surfacing to the user as an opaque `500 code:23`.
+    let text: string;
+    try {
+      text = await res.text();
+    } catch (err: unknown) {
+      if (isTimeout(err)) throw new UpstreamTimeoutError(this.baseUrl, this.timeoutMs);
+      throw new ConnectionError(this.baseUrl, err);
+    }
+
     let parsed: unknown;
     try {
       parsed = JSON.parse(text);
@@ -142,6 +183,51 @@ export class McpdClient {
     return { status: res.status, body: parsed };
   }
 
+  /**
+   * Forward a request and hand back the raw Response, body unread.
+   *
+   * `forward()` buffers through `res.text()`, which is fine for CRUD but
+   * defeats streaming entirely: an SSE chat arrives at the client as one blob
+   * after the turn ends, so the token-by-token output the CLI draws never
+   * appears. Streaming routes use this instead and pipe the body straight
+   * through.
+   */
+  async forwardStream(
+    method: string,
+    path: string,
+    query: string,
+    body: unknown | undefined,
+    authOverride?: string,
+  ): Promise<Response> {
+    const url = `${this.baseUrl}${path}${query ? `?${query}` : ''}`;
+    const headers: Record<string, string> = {
+      ...this.extraHeaders,
+      'Authorization': `Bearer ${authOverride ?? this.token}`,
+      // Accept both: mcpd picks SSE or JSON based on the request's `stream` flag.
+      'Accept': 'text/event-stream, application/json',
+    };
+
+    const init: RequestInit = {
+      method,
+      headers,
+      signal: AbortSignal.timeout(this.timeoutMs),
+    };
+    if (body !== undefined && body !== null && method !== 'GET' && method !== 'HEAD') {
+      headers['Content-Type'] = 'application/json';
+      init.body = JSON.stringify(body);
+    }
+
+    try {
+      const res = await fetch(url, init);
+      if (res.status === 401) throw new AuthenticationError();
+      return res;
+    } catch (err: unknown) {
+      if (err instanceof AuthenticationError) throw err;
+      if (isTimeout(err)) throw new UpstreamTimeoutError(this.baseUrl, this.timeoutMs);
+      throw new ConnectionError(this.baseUrl, err);
+    }
+  }
+
   private async request<T>(method: string, path: string, body?: unknown): Promise<T> {
     const result = await this.forward(method, path, '', body);
 

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

@@ -27,6 +27,7 @@ import { createFavouriteIndexPlugin } from '../proxymodel/plugins/favourite-inde
 import { composePlugins } from '../proxymodel/plugins/compose.js';
 import type { ProxyModelPlugin } from '../proxymodel/plugin.js';
 import { AuditCollector } from '../audit/collector.js';
+import { WireNameCodec, routeWithWireNames } from '../util/wire-names.js';
 
 interface ProjectCacheEntry {
   router: McpRouter;
@@ -45,6 +46,10 @@ export function registerProjectMcpEndpoint(app: FastifyInstance, mcpdClient: Mcp
   let resolvedUserName: string | null | undefined; // undefined = not yet resolved
   const projectCache = new Map<string, ProjectCacheEntry>();
   const sessions = new Map<string, SessionEntry>();
+  // Wire-name codecs are keyed per project and OUTLIVE the router cache TTL:
+  // a client may call a tool it listed minutes ago through a refreshed router,
+  // and the mapping must still resolve.
+  const wireCodecs = new Map<string, WireNameCodec>();
 
   /** Resolve the mcplocal owner's userName once from /auth/me using mcplocal's own credentials. */
   async function ensureUserName(): Promise<string | null> {
@@ -331,7 +336,18 @@ export function registerProjectMcpEndpoint(app: FastifyInstance, mcpdClient: Mcp
         });
 
         const ctx = transport.sessionId ? { sessionId: transport.sessionId, correlationId } : { correlationId };
-        const response = await router.route(message as unknown as JsonRpcRequest, ctx);
+        // Wire-name translation happens HERE, at the client boundary, so the
+        // router, plugins and audit all keep canonical `server/tool` names.
+        let codec = wireCodecs.get(projectName);
+        if (!codec) {
+          codec = new WireNameCodec();
+          wireCodecs.set(projectName, codec);
+        }
+        const response = await routeWithWireNames(
+          codec,
+          (req) => router.route(req, ctx),
+          message as unknown as JsonRpcRequest,
+        );
 
         // Forward queued notifications BEFORE the response — the response send
         // closes the POST SSE stream, so notifications must go first.

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

@@ -1,10 +1,62 @@
 /**
  * Catch-all proxy route that forwards /api/v1/* requests to mcpd.
  */
-import type { FastifyInstance } from 'fastify';
-import { AuthenticationError, ConnectionError } from '../mcpd-client.js';
+import { Readable } from 'node:stream';
+
+import type { FastifyInstance, FastifyReply } from 'fastify';
+
+import { AuthenticationError, ConnectionError, UpstreamTimeoutError, LONG_RUNNING_TIMEOUT_MS } from '../mcpd-client.js';
 import type { McpdClient } from '../mcpd-client.js';
 
+/**
+ * Routes that are expected to run long and/or stream.
+ *
+ * An agent turn is a multi-turn tool-use loop — minutes, not seconds — so the
+ * 30s default budget guarantees failure rather than guarding against it. These
+ * also stream SSE, which must be piped rather than buffered or the client sees
+ * one blob at the end instead of live output.
+ */
+const LONG_RUNNING = [
+  /^\/api\/v1\/agents\/[^/]+\/chat\b/,
+  /^\/api\/v1\/projects\/[^/]+\/chat\b/,
+  /^\/api\/v1\/llms\/[^/]+\/infer\b/,
+  /^\/api\/v1\/inference-tasks\/[^/]+\/stream\b/,
+];
+
+function isLongRunning(path: string): boolean {
+  return LONG_RUNNING.some((re) => re.test(path));
+}
+
+/** Headers worth preserving from mcpd; everything else is re-derived by Fastify. */
+const PASSTHROUGH_HEADERS = ['content-type', 'cache-control', 'x-accel-buffering'];
+
+function sendUpstreamError(reply: FastifyReply, err: unknown): FastifyReply | undefined {
+  if (err instanceof AuthenticationError) {
+    return reply.code(401).send({
+      error: 'unauthorized',
+      message: 'Authentication with mcpd failed. Run `mcpctl login` to refresh your token.',
+    });
+  }
+  if (err instanceof UpstreamTimeoutError) {
+    // 504, not 503 — mcpd was reachable, it just did not finish. Reporting this
+    // as "cannot reach mcpd" sent a previous debugging session chasing a
+    // network fault while /healthz answered in 32ms.
+    return reply.code(504).send({
+      error: 'upstream_timeout',
+      message:
+        `mcpd did not respond within ${String(err.timeoutMs)}ms. The daemon is reachable — the ` +
+        'request itself ran long. Raise MCPLOCAL_LONG_TIMEOUT_MS if this is a legitimately slow turn.',
+    });
+  }
+  if (err instanceof ConnectionError) {
+    return reply.code(503).send({
+      error: 'service_unavailable',
+      message: 'Cannot reach mcpd daemon. Is it running?',
+    });
+  }
+  return undefined;
+}
+
 export function registerProxyRoutes(app: FastifyInstance, client: McpdClient): void {
   app.all('/api/v1/*', async (request, reply) => {
     const path = (request.url.split('?')[0]) ?? '/';
@@ -19,25 +71,78 @@ 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);
+    }
 
     try {
       const result = await client.forward(request.method, path, querystring, body, userToken);
       return reply.code(result.status).send(result.body);
     } catch (err: unknown) {
-      if (err instanceof AuthenticationError) {
-        return reply.code(401).send({
-          error: 'unauthorized',
-          message: 'Authentication with mcpd failed. Run `mcpctl login` to refresh your token.',
-        });
-      }
-      if (err instanceof ConnectionError) {
-        return reply.code(503).send({
-          error: 'service_unavailable',
-          message: 'Cannot reach mcpd daemon. Is it running?',
-        });
-      }
+      const handled = sendUpstreamError(reply, err);
+      if (handled) return handled;
       throw err;
     }
   });
 }
+
+/**
+ * Pipe a long-running response straight through, headers and all.
+ *
+ * Hijacks the reply so Fastify does not try to serialize a stream, then copies
+ * mcpd's status and content-type before piping. `x-accel-buffering` matters:
+ * mcpd sets it to `no` so intermediaries don't buffer SSE, and dropping it here
+ * would reintroduce the exact stall we are fixing.
+ */
+async function proxyStreaming(
+  reply: FastifyReply,
+  client: McpdClient,
+  method: string,
+  path: string,
+  querystring: string,
+  body: unknown,
+  userToken: string | undefined,
+): Promise<void> {
+  const longClient = client.withTimeout(LONG_RUNNING_TIMEOUT_MS);
+
+  let res: Response;
+  try {
+    res = await longClient.forwardStream(method, path, querystring, body, userToken);
+  } catch (err: unknown) {
+    const handled = sendUpstreamError(reply, err);
+    if (handled) return;
+    throw err;
+  }
+
+  const headers: Record<string, string> = {};
+  for (const name of PASSTHROUGH_HEADERS) {
+    const value = res.headers.get(name);
+    if (value !== null) headers[name] = value;
+  }
+
+  reply.hijack();
+  reply.raw.writeHead(res.status, headers);
+
+  if (res.body === null) {
+    reply.raw.end();
+    return;
+  }
+
+  try {
+    // Node's Readable.fromWeb bridges the fetch ReadableStream onto the socket.
+    await new Promise<void>((resolve, reject) => {
+      const upstream = Readable.fromWeb(res.body as Parameters<typeof Readable.fromWeb>[0]);
+      upstream.on('error', reject);
+      reply.raw.on('close', () => { upstream.destroy(); resolve(); });
+      upstream.pipe(reply.raw).on('finish', resolve).on('error', reject);
+    });
+  } catch {
+    // Headers are already on the wire, so there is no status left to change.
+    // Close the socket; the client surfaces the truncated stream.
+    if (!reply.raw.writableEnded) reply.raw.end();
+  }
+}

src/mcplocal/src/index.ts

@@ -11,7 +11,7 @@ export type { MainResult } from './main.js';
 export { ProviderRegistry } from './providers/index.js';
 export type { LlmProvider, CompletionOptions, CompletionResult, ChatMessage } from './providers/index.js';
 export { OpenAiProvider, AnthropicProvider, OllamaProvider, GeminiCliProvider, DeepSeekProvider } from './providers/index.js';
-export { createHttpServer, loadHttpConfig, McpdClient, AuthenticationError, ConnectionError, registerProxyRoutes } from './http/index.js';
+export { createHttpServer, loadHttpConfig, McpdClient, AuthenticationError, ConnectionError, UpstreamTimeoutError, registerProxyRoutes } from './http/index.js';
 export type { HttpConfig, HttpServerDeps } from './http/index.js';
 export type {
   JsonRpcRequest,

src/mcplocal/src/util/wire-names.ts

@@ -0,0 +1,126 @@
+/**
+ * Wire-safe tool-name codec for client-facing MCP endpoints.
+ *
+ * Internally the proxy namespaces tools as `server/tool`, and presentation
+ * plugins add `favourite/<tool>`, `all/<server>/<tool>` and
+ * `agent-<name>/chat`. A `/` is not a valid character in OpenAI-style
+ * function names (`^[a-zA-Z0-9_.-]{1,64}$`), so hosts that forward MCP tool
+ * names verbatim as LLM function names (LibreChat) depend on the model
+ * faithfully echoing an illegal name. deepseek-v4-flash intermittently drops
+ * the `server/` prefix; the host's registry lookup then fails and it reports
+ * the tool's "MCP server is temporarily unavailable" while nothing is down
+ * (the librechat fetch_content incident, 2026-08-25). Claude Code and the pi
+ * extension dodge this only because they sanitize names client-side.
+ *
+ * The codec translates ONLY at the HTTP boundary:
+ *   - tools/list responses are rewritten to wire-safe names (`/` → `_`),
+ *   - tools/call requests are mapped back to the presented (internal) name
+ *     via an exact-match reverse map.
+ *
+ * Everything inside the proxy — routing maps, plugins, favourites config,
+ * audit events — keeps the canonical names. Inbound names with no map entry
+ * (legacy clients echoing slash names, virtual tools called before any
+ * tools/list) pass through unchanged, so existing clients keep working.
+ *
+ * The maps live per project router (not per session) so a client that
+ * reconnects mid-conversation still resolves names listed on its previous
+ * session, as long as the process is alive. After a restart the first
+ * tools/list (which every MCP client performs on initialize) repopulates them.
+ */
+import type { JsonRpcRequest, JsonRpcResponse } from '../types.js';
+
+/** Replace every character that is invalid in an OpenAI-style function name. */
+export function sanitizeWireName(name: string): string {
+  return name.replace(/[^A-Za-z0-9_.-]/g, '_');
+}
+
+export class WireNameCodec {
+  /** wire name → presented (internal) name */
+  private toPresented = new Map<string, string>();
+  /** presented (internal) name → wire name */
+  private toWire = new Map<string, string>();
+
+  /**
+   * Wire name for a presented tool name. Stable for the codec's lifetime.
+   *
+   * Collisions (two presented names sanitizing to the same string, or a
+   * sanitized name shadowing a tool that already uses that exact name) get a
+   * numeric suffix — first registration wins the plain name. This keeps the
+   * reverse map unambiguous; order within one tools/list pass is stable, so
+   * suffixes are deterministic in practice.
+   */
+  encodeName(presented: string): string {
+    const existing = this.toWire.get(presented);
+    if (existing !== undefined) return existing;
+
+    const base = sanitizeWireName(presented);
+    let wire = base;
+    for (let i = 2; this.toPresented.has(wire) && this.toPresented.get(wire) !== presented; i++) {
+      wire = `${base}_${String(i)}`;
+    }
+    if (wire !== base) {
+      console.warn(`[wire-names] collision: '${presented}' presented as '${wire}' (base '${base}' taken by '${this.toPresented.get(base) ?? '?'}')`);
+    }
+    this.toWire.set(presented, wire);
+    this.toPresented.set(wire, presented);
+    return wire;
+  }
+
+  /** The presented name a wire name maps to, or the input unchanged if unknown. */
+  decodeName(wire: string): string {
+    return this.toPresented.get(wire) ?? wire;
+  }
+
+  /**
+   * Rewrite a tools/list response's tool names to wire-safe names,
+   * registering each mapping. Non-list responses and errors pass through.
+   */
+  encodeToolsList(response: JsonRpcResponse): JsonRpcResponse {
+    if (response.error !== undefined) return response;
+    if (response.result === null || typeof response.result !== 'object') return response;
+    const result = response.result as Record<string, unknown>;
+    const tools: unknown = result['tools'];
+    if (!Array.isArray(tools)) return response;
+
+    let changed = false;
+    const encoded = (tools as unknown[]).map((tool) => {
+      if (tool === null || typeof tool !== 'object' || typeof (tool as { name?: unknown }).name !== 'string') return tool;
+      const presented = (tool as { name: string }).name;
+      const wire = this.encodeName(presented);
+      if (wire === presented) return tool;
+      changed = true;
+      return { ...(tool as Record<string, unknown>), name: wire };
+    });
+
+    if (!changed) return response;
+    return { ...response, result: { ...result, tools: encoded } };
+  }
+
+  /**
+   * Map a tools/call request's wire name back to the presented name.
+   * Requests for unknown names (or without a name) pass through unchanged.
+   */
+  decodeToolCall(request: JsonRpcRequest): JsonRpcRequest {
+    const params = request.params;
+    const name = params?.['name'];
+    if (typeof name !== 'string') return request;
+    const presented = this.toPresented.get(name);
+    if (presented === undefined || presented === name) return request;
+    return { ...request, params: { ...params, name: presented } };
+  }
+}
+
+/**
+ * Route one client request through `route` with wire-name translation:
+ * decode the tool name on the way in (tools/call), encode tool names on the
+ * way out (tools/list). Every other method is untouched.
+ */
+export async function routeWithWireNames(
+  codec: WireNameCodec,
+  route: (request: JsonRpcRequest) => Promise<JsonRpcResponse>,
+  request: JsonRpcRequest,
+): Promise<JsonRpcResponse> {
+  const inbound = request.method === 'tools/call' ? codec.decodeToolCall(request) : request;
+  const response = await route(inbound);
+  return request.method === 'tools/list' ? codec.encodeToolsList(response) : response;
+}

src/mcplocal/tests/mcp-endpoint-wire-names.test.ts

@@ -0,0 +1,100 @@
+import { describe, it, expect, vi } from 'vitest';
+import Fastify from 'fastify';
+import { registerMcpEndpoint } from '../src/http/mcp-endpoint.js';
+import type { McpRouter } from '../src/router.js';
+import type { JsonRpcRequest, JsonRpcResponse } from '../src/types.js';
+
+/**
+ * End-to-end over the Streamable HTTP transport: the /mcp endpoint must serve
+ * OpenAI-safe tool names on tools/list and map them back to the router's
+ * canonical `server/tool` names on tools/call (the librechat fetch_content
+ * incident, 2026-08-25).
+ */
+
+function parseSse(body: string): JsonRpcResponse {
+  const dataLine = body.split('\n').find((l) => l.startsWith('data: '));
+  if (!dataLine) throw new Error(`no SSE data line in: ${body}`);
+  return JSON.parse(dataLine.slice('data: '.length)) as JsonRpcResponse;
+}
+
+describe('registerMcpEndpoint wire names', () => {
+  it('lists wire-safe names and routes calls back to canonical names', async () => {
+    const routed: JsonRpcRequest[] = [];
+    const fakeRouter = {
+      route: vi.fn(async (req: JsonRpcRequest): Promise<JsonRpcResponse> => {
+        routed.push(req);
+        switch (req.method) {
+          case 'initialize':
+            return {
+              jsonrpc: '2.0',
+              id: req.id,
+              result: {
+                protocolVersion: '2024-11-05',
+                serverInfo: { name: 'test', version: '0' },
+                capabilities: { tools: {} },
+              },
+            };
+          case 'tools/list':
+            return {
+              jsonrpc: '2.0',
+              id: req.id,
+              result: { tools: [{ name: 'websearch/fetch_content', inputSchema: { type: 'object' } }] },
+            };
+          case 'tools/call':
+            return {
+              jsonrpc: '2.0',
+              id: req.id,
+              result: { content: [{ type: 'text', text: 'ok' }] },
+            };
+          default:
+            return { jsonrpc: '2.0', id: req.id, result: {} };
+        }
+      }),
+    } as unknown as McpRouter;
+
+    const app = Fastify();
+    registerMcpEndpoint(app, fakeRouter);
+    await app.ready();
+    try {
+      const headers = {
+        'content-type': 'application/json',
+        accept: 'application/json, text/event-stream',
+      };
+
+      const init = await app.inject({
+        method: 'POST',
+        url: '/mcp',
+        headers,
+        payload: { jsonrpc: '2.0', id: 1, method: 'initialize', params: { protocolVersion: '2024-11-05', capabilities: {}, clientInfo: { name: 't', version: '0' } } },
+      });
+      expect(init.statusCode).toBe(200);
+      const sessionId = init.headers['mcp-session-id'] as string;
+      expect(sessionId).toBeTruthy();
+      const sessionHeaders = { ...headers, 'mcp-session-id': sessionId };
+
+      const list = await app.inject({
+        method: 'POST',
+        url: '/mcp',
+        headers: sessionHeaders,
+        payload: { jsonrpc: '2.0', id: 2, method: 'tools/list' },
+      });
+      const listResponse = parseSse(list.body);
+      const tools = (listResponse.result as { tools: Array<{ name: string }> }).tools;
+      expect(tools.map((t) => t.name)).toEqual(['websearch_fetch_content']);
+
+      const call = await app.inject({
+        method: 'POST',
+        url: '/mcp',
+        headers: sessionHeaders,
+        payload: { jsonrpc: '2.0', id: 3, method: 'tools/call', params: { name: 'websearch_fetch_content', arguments: { url: 'https://x' } } },
+      });
+      const callResponse = parseSse(call.body);
+      expect(callResponse.error).toBeUndefined();
+
+      const routedCall = routed.find((r) => r.method === 'tools/call');
+      expect(routedCall?.params?.['name']).toBe('websearch/fetch_content');
+    } finally {
+      await app.close();
+    }
+  });
+});

src/mcplocal/tests/mcpd-client.test.ts

@@ -1,6 +1,6 @@
 import { describe, it, expect, afterAll, afterEach } from 'vitest';
 import http from 'node:http';
-import { McpdClient, ConnectionError } from '../src/http/mcpd-client.js';
+import { McpdClient, ConnectionError, UpstreamTimeoutError } from '../src/http/mcpd-client.js';
 
 /**
  * Create a local HTTP server for testing McpdClient behavior.
@@ -85,7 +85,7 @@ describe('McpdClient', () => {
 
   // ── Timeout behavior ──
 
-  it('times out on slow responses and throws ConnectionError', async () => {
+  it('times out on slow responses and throws UpstreamTimeoutError', async () => {
     const { server, url } = await createTestServer((_req, _res) => {
       // Never respond — simulates a hanging upstream tool call
     });
@@ -96,7 +96,7 @@ describe('McpdClient', () => {
 
     const start = Date.now();
     await expect(client.post('/api/v1/mcp/proxy', { serverId: 's1' })).rejects.toThrow(
-      /timed out/,
+      /did not respond within/,
     );
     const elapsed = Date.now() - start;
 
@@ -105,7 +105,7 @@ describe('McpdClient', () => {
     expect(elapsed).toBeLessThan(3000);
   });
 
-  it('timeout error is a ConnectionError with descriptive message', async () => {
+  it('timeout is NOT a ConnectionError — a slow daemon is not an absent one', async () => {
     const { server, url } = await createTestServer((_req, _res) => {
       // Never respond
     });
@@ -117,8 +117,12 @@ describe('McpdClient', () => {
       await client.get('/test');
       expect.unreachable('Should have thrown');
     } catch (err) {
-      expect(err).toBeInstanceOf(ConnectionError);
-      expect((err as Error).message).toContain('Request timed out after 200ms');
+      // Reporting a timeout as "cannot connect" is what sent a previous
+      // debugging session chasing a network fault that did not exist.
+      expect(err).toBeInstanceOf(UpstreamTimeoutError);
+      expect(err).not.toBeInstanceOf(ConnectionError);
+      expect((err as UpstreamTimeoutError).timeoutMs).toBe(200);
+      expect((err as Error).message).toContain('did not respond within 200ms');
     }
   });
 
@@ -146,7 +150,7 @@ describe('McpdClient', () => {
     const derived = client.withHeaders({ 'X-Custom': 'val' });
 
     const start = Date.now();
-    await expect(derived.get('/test')).rejects.toThrow(/timed out/);
+    await expect(derived.get('/test')).rejects.toThrow(/did not respond within/);
     const elapsed = Date.now() - start;
     expect(elapsed).toBeLessThan(2000);
   });

src/mcplocal/tests/project-mcp-endpoint-wire-names.test.ts

@@ -0,0 +1,145 @@
+import { describe, it, expect, vi } from 'vitest';
+import Fastify from 'fastify';
+import { registerProjectMcpEndpoint } from '../src/http/project-mcp-endpoint.js';
+import type { McpRouter } from '../src/router.js';
+import type { JsonRpcRequest, JsonRpcResponse } from '../src/types.js';
+
+/**
+ * End-to-end wire-name test on the endpoint the librechat incident actually
+ * hit: /projects/:name/mcp. A fake `websearch` upstream serves a tool named
+ * `fetch_content`; the client must see `websearch_fetch_content` in
+ * tools/list, and calling that wire name must reach the upstream as plain
+ * `fetch_content` (router canonical `websearch/fetch_content`, prefix
+ * stripped on dispatch).
+ */
+
+const upstreamRequests: JsonRpcRequest[] = [];
+
+vi.mock('../src/discovery.js', () => ({
+  refreshProjectUpstreams: vi.fn(async (router: McpRouter) => {
+    router.addUpstream({
+      name: 'websearch',
+      send: async (req: JsonRpcRequest): Promise<JsonRpcResponse> => {
+        upstreamRequests.push(req);
+        if (req.method === 'tools/list') {
+          return {
+            jsonrpc: '2.0',
+            id: req.id,
+            result: { tools: [{ name: 'fetch_content', description: 'fetch a page', inputSchema: { type: 'object' } }] },
+          };
+        }
+        if (req.method === 'tools/call') {
+          return {
+            jsonrpc: '2.0',
+            id: req.id,
+            result: { content: [{ type: 'text', text: 'page body' }] },
+          };
+        }
+        return { jsonrpc: '2.0', id: req.id, result: {} };
+      },
+      close: async () => {},
+      isAlive: () => true,
+    });
+    return ['websearch'];
+  }),
+  // gated: false → no gate plugin, the full catalog is served at initialize
+  // (the chat-web configuration).
+  fetchProjectLlmConfig: vi.fn(async () => ({ gated: false, llmProvider: 'none' })),
+}));
+
+vi.mock('../src/http/config.js', async () => {
+  const actual = await vi.importActual<typeof import('../src/http/config.js')>('../src/http/config.js');
+  return { ...actual, loadProjectLlmOverride: vi.fn(() => undefined) };
+});
+
+function mockMcpdClient() {
+  const client: Record<string, unknown> = {
+    baseUrl: 'http://test:3100',
+    token: 'test-token',
+    get: vi.fn(async () => []),
+    post: vi.fn(async () => ({})),
+    put: vi.fn(),
+    delete: vi.fn(),
+    forward: vi.fn(async () => ({ status: 200, body: [] })),
+    withHeaders: vi.fn(),
+    withToken: vi.fn(),
+    withTimeout: vi.fn(),
+  };
+  (client.withHeaders as ReturnType<typeof vi.fn>).mockReturnValue(client);
+  (client.withToken as ReturnType<typeof vi.fn>).mockReturnValue(client);
+  (client.withTimeout as ReturnType<typeof vi.fn>).mockReturnValue(client);
+  return client;
+}
+
+function parseSse(body: string): JsonRpcResponse {
+  const dataLine = body.split('\n').find((l) => l.startsWith('data: '));
+  if (!dataLine) throw new Error(`no SSE data line in: ${body}`);
+  return JSON.parse(dataLine.slice('data: '.length)) as JsonRpcResponse;
+}
+
+describe('registerProjectMcpEndpoint wire names', () => {
+  it('serves wire-safe names on the project endpoint and dispatches calls upstream', async () => {
+    upstreamRequests.length = 0;
+    const app = Fastify();
+    registerProjectMcpEndpoint(app, mockMcpdClient() as never);
+    await app.ready();
+    try {
+      const headers = {
+        'content-type': 'application/json',
+        accept: 'application/json, text/event-stream',
+      };
+
+      const init = await app.inject({
+        method: 'POST',
+        url: '/projects/chat-web/mcp',
+        headers,
+        payload: { jsonrpc: '2.0', id: 1, method: 'initialize', params: { protocolVersion: '2024-11-05', capabilities: {}, clientInfo: { name: 't', version: '0' } } },
+      });
+      expect(init.statusCode).toBe(200);
+      const sessionId = init.headers['mcp-session-id'] as string;
+      expect(sessionId).toBeTruthy();
+      const sessionHeaders = { ...headers, 'mcp-session-id': sessionId };
+
+      const list = await app.inject({
+        method: 'POST',
+        url: '/projects/chat-web/mcp',
+        headers: sessionHeaders,
+        payload: { jsonrpc: '2.0', id: 2, method: 'tools/list' },
+      });
+      const listResponse = parseSse(list.body);
+      const tools = (listResponse.result as { tools: Array<{ name: string }> }).tools;
+      const names = tools.map((t) => t.name);
+      expect(names).toContain('websearch_fetch_content');
+      // Every served name must be a valid OpenAI-style function name — the
+      // invariant the librechat incident violated.
+      for (const name of names) {
+        expect(name).toMatch(/^[A-Za-z0-9_.-]+$/);
+      }
+
+      const call = await app.inject({
+        method: 'POST',
+        url: '/projects/chat-web/mcp',
+        headers: sessionHeaders,
+        payload: { jsonrpc: '2.0', id: 3, method: 'tools/call', params: { name: 'websearch_fetch_content', arguments: { url: 'https://x' } } },
+      });
+      const callResponse = parseSse(call.body);
+      expect(callResponse.error).toBeUndefined();
+      expect((callResponse.result as { content: Array<{ text: string }> }).content[0]?.text).toBe('page body');
+
+      // The upstream saw the bare tool name — namespace stripped, not mangled.
+      const upstreamCall = upstreamRequests.find((r) => r.method === 'tools/call');
+      expect(upstreamCall?.params?.['name']).toBe('fetch_content');
+
+      // Legacy clients echoing the canonical slash name keep working.
+      const legacy = await app.inject({
+        method: 'POST',
+        url: '/projects/chat-web/mcp',
+        headers: sessionHeaders,
+        payload: { jsonrpc: '2.0', id: 4, method: 'tools/call', params: { name: 'websearch/fetch_content', arguments: { url: 'https://x' } } },
+      });
+      expect(parseSse(legacy.body).error).toBeUndefined();
+    } finally {
+      await app.close();
+    }
+  });
+});

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

@@ -0,0 +1,255 @@
+import http from 'node:http';
+
+import Fastify, { type FastifyInstance } from 'fastify';
+import { describe, it, expect, afterEach } from 'vitest';
+
+import {
+  McpdClient,
+  UpstreamTimeoutError,
+  ConnectionError,
+  LONG_RUNNING_TIMEOUT_MS,
+  DEFAULT_TIMEOUT_MS,
+} from '../src/http/mcpd-client.js';
+import { registerProxyRoutes } from '../src/http/routes/proxy.js';
+
+/**
+ * Regression cover for the 30s proxy timeout that made `mcpctl chat` fail with
+ * a misleading "Cannot reach mcpd daemon" 503 while mcpd was answering
+ * /healthz in 32ms.
+ *
+ * Three separate defects are pinned here:
+ *   1. chat routes inherited the 30s CRUD budget, so any turn longer than 30s
+ *      failed — and an agent turn is a tool-use loop that routinely exceeds it;
+ *   2. a timeout was reported as a connection failure, sending diagnosis after
+ *      a network fault that did not exist;
+ *   3. SSE was buffered through res.text(), so streaming never reached the
+ *      client even when the turn finished in time.
+ */
+let app: FastifyInstance | null = null;
+let upstream: FastifyInstance | null = null;
+
+afterEach(async () => {
+  if (app) { await app.close(); app = null; }
+  if (upstream) { await upstream.close(); upstream = null; }
+});
+
+/** A stand-in mcpd. Returns its base URL. */
+async function startUpstream(register: (a: FastifyInstance) => void): Promise<string> {
+  upstream = Fastify();
+  register(upstream);
+  await upstream.listen({ port: 0, host: '127.0.0.1' });
+  const addr = upstream.server.address();
+  if (addr === null || typeof addr === 'string') throw new Error('no address');
+  return `http://127.0.0.1:${String(addr.port)}`;
+}
+
+async function startProxy(baseUrl: string, timeoutMs?: number): Promise<FastifyInstance> {
+  app = Fastify();
+  registerProxyRoutes(app, new McpdClient(baseUrl, 'test-token', {}, timeoutMs));
+  await app.ready();
+  return app;
+}
+
+describe('proxy — long-running route budget', () => {
+  it('gives chat routes the long budget, not the 30s CRUD default', () => {
+    // The constants themselves are the contract: a 30s cap on an agent turn is
+    // a guaranteed failure, not a safety net.
+    expect(DEFAULT_TIMEOUT_MS).toBe(30_000);
+    expect(LONG_RUNNING_TIMEOUT_MS).toBeGreaterThanOrEqual(600_000);
+  });
+
+  it('does not abort an agent chat that outlives the CRUD budget', async () => {
+    const base = await startUpstream((a) => {
+      a.post('/api/v1/agents/:name/chat', async () => {
+        // Longer than the (deliberately tiny) CRUD budget below. Before the
+        // fix this inherited that budget and 503'd.
+        await new Promise((r) => setTimeout(r, 250));
+        return { answer: 'pong' };
+      });
+    });
+    // CRUD budget of 50ms — a chat route must NOT inherit it.
+    const proxy = await startProxy(base, 50);
+
+    const res = await proxy.inject({
+      method: 'POST',
+      url: '/api/v1/agents/reviewer/chat',
+      payload: { message: 'hi' },
+    });
+
+    expect(res.statusCode).toBe(200);
+    expect(res.json()).toEqual({ answer: 'pong' });
+  });
+
+  it('still applies the short budget to ordinary CRUD routes', async () => {
+    const base = await startUpstream((a) => {
+      a.get('/api/v1/servers', async () => {
+        await new Promise((r) => setTimeout(r, 300));
+        return [];
+      });
+    });
+    const proxy = await startProxy(base, 50);
+
+    const res = await proxy.inject({ method: 'GET', url: '/api/v1/servers' });
+    // Times out — and is now reported honestly as a timeout, not a connection fault.
+    expect(res.statusCode).toBe(504);
+    expect(res.json().error).toBe('upstream_timeout');
+  });
+
+  it('reports a timeout as 504, never as "cannot reach mcpd"', async () => {
+    const base = await startUpstream((a) => {
+      a.get('/api/v1/servers', async () => {
+        await new Promise((r) => setTimeout(r, 300));
+        return [];
+      });
+    });
+    const proxy = await startProxy(base, 50);
+
+    const res = await proxy.inject({ method: 'GET', url: '/api/v1/servers' });
+    const body = res.json();
+    expect(body.message).toMatch(/did not respond within/);
+    expect(body.message).not.toMatch(/Cannot reach mcpd/);
+    expect(body.message).toMatch(/reachable/);
+  });
+
+  it('streams SSE through instead of buffering it', async () => {
+    const base = await startUpstream((a) => {
+      a.post('/api/v1/agents/:name/chat', async (_req, reply) => {
+        reply.raw.writeHead(200, {
+          'Content-Type': 'text/event-stream',
+          'Cache-Control': 'no-cache',
+          'X-Accel-Buffering': 'no',
+        });
+        reply.raw.write('data: {"type":"text","delta":"po"}\n\n');
+        reply.raw.write('data: {"type":"text","delta":"ng"}\n\n');
+        reply.raw.write('data: [DONE]\n\n');
+        reply.raw.end();
+        return reply;
+      });
+    });
+    const proxy = await startProxy(base, 50);
+
+    const res = await proxy.inject({
+      method: 'POST',
+      url: '/api/v1/agents/reviewer/chat',
+      payload: { message: 'hi', stream: true },
+    });
+
+    expect(res.statusCode).toBe(200);
+    // Content-type must survive — a client that gets application/json will not
+    // parse the event stream.
+    expect(res.headers['content-type']).toMatch(/text\/event-stream/);
+    // x-accel-buffering=no must survive too, or intermediaries re-buffer the
+    // stream and reintroduce the stall.
+    expect(res.headers['x-accel-buffering']).toBe('no');
+    expect(res.body).toContain('"delta":"po"');
+    expect(res.body).toContain('"delta":"ng"');
+    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) => {
+        return reply.code(404).send({ error: 'Agent not found' });
+      });
+    });
+    const proxy = await startProxy(base, 50);
+
+    const res = await proxy.inject({
+      method: 'POST',
+      url: '/api/v1/agents/ghost/chat',
+      payload: { message: 'hi' },
+    });
+    expect(res.statusCode).toBe(404);
+    expect(res.body).toContain('Agent not found');
+  });
+
+  it('still reports a genuinely unreachable daemon as 503', async () => {
+    // Port 1 is reserved and refuses instantly.
+    const proxy = await startProxy('http://127.0.0.1:1', 500);
+    const res = await proxy.inject({ method: 'GET', url: '/api/v1/servers' });
+
+    expect(res.statusCode).toBe(503);
+    expect(res.json().error).toBe('service_unavailable');
+  });
+
+  it('propagates 401 from a streaming route so login guidance still fires', async () => {
+    const base = await startUpstream((a) => {
+      a.post('/api/v1/agents/:name/chat', async (_req, reply) => reply.code(401).send({}));
+    });
+    const proxy = await startProxy(base, 50);
+
+    const res = await proxy.inject({
+      method: 'POST',
+      url: '/api/v1/agents/reviewer/chat',
+      payload: { message: 'hi' },
+    });
+    expect(res.statusCode).toBe(401);
+    expect(res.json().message).toMatch(/mcpctl login/);
+  });
+});
+
+describe('error taxonomy', () => {
+  it('keeps timeout and unreachable as distinct types', () => {
+    const timeout = new UpstreamTimeoutError('http://mcpd', 30_000);
+    expect(timeout).not.toBeInstanceOf(ConnectionError);
+    expect(timeout.timeoutMs).toBe(30_000);
+    expect(timeout.message).toMatch(/did not respond within 30000ms/);
+  });
+});

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.

src/mcplocal/tests/wire-names.test.ts

@@ -0,0 +1,168 @@
+import { describe, it, expect, vi } from 'vitest';
+import { sanitizeWireName, WireNameCodec, routeWithWireNames } from '../src/util/wire-names.js';
+import type { JsonRpcRequest, JsonRpcResponse } from '../src/types.js';
+
+describe('sanitizeWireName', () => {
+  it('replaces slashes with underscores', () => {
+    expect(sanitizeWireName('websearch/fetch_content')).toBe('websearch_fetch_content');
+    expect(sanitizeWireName('all/websearch/fetch_content')).toBe('all_websearch_fetch_content');
+  });
+
+  it('keeps names that are already OpenAI-safe', () => {
+    expect(sanitizeWireName('begin_session')).toBe('begin_session');
+    expect(sanitizeWireName('my-grafana.tool')).toBe('my-grafana.tool');
+  });
+
+  it('replaces every character outside [A-Za-z0-9_.-]', () => {
+    expect(sanitizeWireName('a b:c/d')).toBe('a_b_c_d');
+  });
+});
+
+describe('WireNameCodec', () => {
+  it('round-trips a namespaced tool name', () => {
+    const codec = new WireNameCodec();
+    const wire = codec.encodeName('websearch/fetch_content');
+    expect(wire).toBe('websearch_fetch_content');
+    expect(codec.decodeName(wire)).toBe('websearch/fetch_content');
+  });
+
+  it('is stable across repeated encodes', () => {
+    const codec = new WireNameCodec();
+    expect(codec.encodeName('searxng/web_url_read')).toBe('searxng_web_url_read');
+    expect(codec.encodeName('searxng/web_url_read')).toBe('searxng_web_url_read');
+  });
+
+  it('passes unknown inbound names through unchanged', () => {
+    const codec = new WireNameCodec();
+    // Legacy client echoing the slash form, or a virtual tool never listed.
+    expect(codec.decodeName('websearch/fetch_content')).toBe('websearch/fetch_content');
+    expect(codec.decodeName('begin_session')).toBe('begin_session');
+  });
+
+  it('suffixes on collision, first registration wins the plain name', () => {
+    const warn = vi.spyOn(console, 'warn').mockImplementation(() => {});
+    try {
+      const codec = new WireNameCodec();
+      expect(codec.encodeName('foo_bar/baz')).toBe('foo_bar_baz');
+      expect(codec.encodeName('foo/bar_baz')).toBe('foo_bar_baz_2');
+      // Both decode back to their own presented names.
+      expect(codec.decodeName('foo_bar_baz')).toBe('foo_bar/baz');
+      expect(codec.decodeName('foo_bar_baz_2')).toBe('foo/bar_baz');
+      // And stay stable.
+      expect(codec.encodeName('foo/bar_baz')).toBe('foo_bar_baz_2');
+      expect(warn).toHaveBeenCalledOnce();
+    } finally {
+      warn.mockRestore();
+    }
+  });
+
+  it('encodes tools/list responses and leaves other fields intact', () => {
+    const codec = new WireNameCodec();
+    const response: JsonRpcResponse = {
+      jsonrpc: '2.0',
+      id: 1,
+      result: {
+        tools: [
+          { name: 'websearch/fetch_content', description: 'fetch', inputSchema: { type: 'object' } },
+          { name: 'begin_session', description: 'gate' },
+        ],
+      },
+    };
+    const encoded = codec.encodeToolsList(response);
+    const tools = (encoded.result as { tools: Array<{ name: string; description?: string }> }).tools;
+    expect(tools.map((t) => t.name)).toEqual(['websearch_fetch_content', 'begin_session']);
+    expect(tools[0]?.description).toBe('fetch');
+    // Original response object is not mutated.
+    const originalTools = (response.result as { tools: Array<{ name: string }> }).tools;
+    expect(originalTools[0]?.name).toBe('websearch/fetch_content');
+  });
+
+  it('returns error and non-list responses unchanged', () => {
+    const codec = new WireNameCodec();
+    const err: JsonRpcResponse = { jsonrpc: '2.0', id: 1, error: { code: -32603, message: 'boom' } };
+    expect(codec.encodeToolsList(err)).toBe(err);
+    const other: JsonRpcResponse = { jsonrpc: '2.0', id: 1, result: { content: [] } };
+    expect(codec.encodeToolsList(other)).toBe(other);
+  });
+
+  it('decodes tools/call requests for known wire names only', () => {
+    const codec = new WireNameCodec();
+    codec.encodeName('websearch/fetch_content');
+
+    const known: JsonRpcRequest = {
+      jsonrpc: '2.0',
+      id: 2,
+      method: 'tools/call',
+      params: { name: 'websearch_fetch_content', arguments: { url: 'https://x' } },
+    };
+    const decoded = codec.decodeToolCall(known);
+    expect(decoded.params?.['name']).toBe('websearch/fetch_content');
+    expect(decoded.params?.['arguments']).toEqual({ url: 'https://x' });
+    // Original request object is not mutated.
+    expect(known.params?.['name']).toBe('websearch_fetch_content');
+
+    const unknown: JsonRpcRequest = {
+      jsonrpc: '2.0',
+      id: 3,
+      method: 'tools/call',
+      params: { name: 'not_listed', arguments: {} },
+    };
+    expect(codec.decodeToolCall(unknown)).toBe(unknown);
+  });
+});
+
+describe('routeWithWireNames', () => {
+  const listResponse: JsonRpcResponse = {
+    jsonrpc: '2.0',
+    id: 1,
+    result: { tools: [{ name: 'websearch/fetch_content' }, { name: 'searxng/web_url_read' }] },
+  };
+
+  it('serves wire-safe names on tools/list and maps tools/call back', async () => {
+    const codec = new WireNameCodec();
+    const seen: JsonRpcRequest[] = [];
+    const route = async (req: JsonRpcRequest): Promise<JsonRpcResponse> => {
+      seen.push(req);
+      if (req.method === 'tools/list') return listResponse;
+      return { jsonrpc: '2.0', id: req.id, result: { content: [{ type: 'text', text: 'ok' }] } };
+    };
+
+    const listed = await routeWithWireNames(codec, route, { jsonrpc: '2.0', id: 1, method: 'tools/list' });
+    const names = (listed.result as { tools: Array<{ name: string }> }).tools.map((t) => t.name);
+    expect(names).toEqual(['websearch_fetch_content', 'searxng_web_url_read']);
+
+    // The exact scenario from the librechat incident: the model echoes the
+    // wire name; the router must receive the canonical name.
+    await routeWithWireNames(codec, route, {
+      jsonrpc: '2.0',
+      id: 2,
+      method: 'tools/call',
+      params: { name: 'websearch_fetch_content', arguments: { url: 'https://x' } },
+    });
+    expect(seen[1]?.params?.['name']).toBe('websearch/fetch_content');
+  });
+
+  it('keeps legacy slash-name calls working', async () => {
+    const codec = new WireNameCodec();
+    const seen: JsonRpcRequest[] = [];
+    const route = async (req: JsonRpcRequest): Promise<JsonRpcResponse> => {
+      seen.push(req);
+      return { jsonrpc: '2.0', id: req.id, result: {} };
+    };
+    await routeWithWireNames(codec, route, {
+      jsonrpc: '2.0',
+      id: 1,
+      method: 'tools/call',
+      params: { name: 'websearch/fetch_content', arguments: {} },
+    });
+    expect(seen[0]?.params?.['name']).toBe('websearch/fetch_content');
+  });
+
+  it('does not touch other methods', async () => {
+    const codec = new WireNameCodec();
+    const init: JsonRpcRequest = { jsonrpc: '2.0', id: 1, method: 'initialize', params: {} };
+    const response: JsonRpcResponse = { jsonrpc: '2.0', id: 1, result: { protocolVersion: '2024-11-05' } };
+    const out = await routeWithWireNames(codec, async () => response, init);
+    expect(out).toBe(response);
+  });
+});