feat(config): lower MCP timeouts and raise JSON body limit

Reduce the default external-MCP silence timeout from 5 min to 1 min and the
overall call timeout from 15 min to 2 min. Update related tests and comments.
Increase Fastify's JSON body limit to 25 MiB (configurable via
HTTP_JSON_BODY_LIMIT) to accommodate large AI‑chat payloads.

BREAKING CHANGE: shorter MCP timeouts may abort long‑running tool calls that
previously succeeded with the older defaults.

apps/server/src/core/ai-chat/external-mcp/mcp-call-timeout.spec.ts

@@ -181,25 +181,25 @@ describe('mcp timeout env helpers', () => {
     else process.env.AI_MCP_CALL_TIMEOUT_MS = ORIG_CALL;
   });
 
-  it('mcpStreamTimeoutMs defaults to 5 min and honors a positive override', () => {
+  it('mcpStreamTimeoutMs defaults to 1 min and honors a positive override', () => {
     delete process.env.AI_MCP_STREAM_TIMEOUT_MS;
-    expect(mcpStreamTimeoutMs()).toBe(300_000);
-    process.env.AI_MCP_STREAM_TIMEOUT_MS = '60000';
     expect(mcpStreamTimeoutMs()).toBe(60_000);
+    process.env.AI_MCP_STREAM_TIMEOUT_MS = '90000';
+    expect(mcpStreamTimeoutMs()).toBe(90_000);
     for (const bad of ['0', '-1', 'x', '']) {
       process.env.AI_MCP_STREAM_TIMEOUT_MS = bad;
-      expect(mcpStreamTimeoutMs()).toBe(300_000);
+      expect(mcpStreamTimeoutMs()).toBe(60_000);
     }
   });
 
-  it('mcpCallTimeoutMs defaults to 15 min and honors a positive override', () => {
+  it('mcpCallTimeoutMs defaults to 2 min and honors a positive override', () => {
     delete process.env.AI_MCP_CALL_TIMEOUT_MS;
-    expect(mcpCallTimeoutMs()).toBe(900_000);
-    process.env.AI_MCP_CALL_TIMEOUT_MS = '120000';
     expect(mcpCallTimeoutMs()).toBe(120_000);
+    process.env.AI_MCP_CALL_TIMEOUT_MS = '180000';
+    expect(mcpCallTimeoutMs()).toBe(180_000);
     for (const bad of ['0', '-1', 'x', '']) {
       process.env.AI_MCP_CALL_TIMEOUT_MS = bad;
-      expect(mcpCallTimeoutMs()).toBe(900_000);
+      expect(mcpCallTimeoutMs()).toBe(120_000);
     }
   });
 });

apps/server/src/core/ai-chat/external-mcp/mcp-clients.service.ts

@@ -523,12 +523,12 @@ export function validateResolvedAddresses(addrs: readonly LookupAddress[]): {
  */
 function buildPinnedDispatcher(): Agent {
   // External-MCP traffic uses a DEDICATED, shorter silence timeout
-  // (`AI_MCP_STREAM_TIMEOUT_MS`, default 5 min) — deliberately tighter than the
+  // (`AI_MCP_STREAM_TIMEOUT_MS`, default 1 min) — deliberately tighter than the
   // chat provider's 15-min `streamTimeoutMs()` — so a byte-silent/hung MCP
-  // upstream is broken in ~5 min instead of 15. We keep the keep-alive options
+  // upstream is broken in ~1 min instead of 15. We keep the keep-alive options
   // from `streamingDispatcherOptions()` but OVERRIDE headers/body timeouts.
   // Accepted trade-off: a legitimately long but byte-silent single tool call,
-  // and an SSE transport idling >5 min BETWEEN tool calls, are also cut here; the
+  // and an SSE transport idling >1 min BETWEEN tool calls, are also cut here; the
   // per-call total cap (wrapToolsWithCallTimeout, `AI_MCP_CALL_TIMEOUT_MS`) is the
   // complementary guard for chatty-but-stuck calls that keep the socket warm yet
   // never return.

apps/server/src/integrations/ai/ai-streaming-fetch.ts

@@ -123,19 +123,19 @@ export function streamKeepAliveMs(): number {
   return positiveEnv('AI_STREAM_KEEPALIVE_MS', DEFAULT_STREAM_KEEPALIVE_MS);
 }
 
-/** Default SILENCE timeout for EXTERNAL-MCP transport (5 min). */
-const DEFAULT_MCP_STREAM_TIMEOUT_MS = 300_000;
+/** Default SILENCE timeout for EXTERNAL-MCP transport (1 min). */
+const DEFAULT_MCP_STREAM_TIMEOUT_MS = 60_000;
 
-/** Default total wall-clock cap for ONE external MCP tool call (15 min). */
-const DEFAULT_MCP_CALL_TIMEOUT_MS = 900_000;
+/** Default total wall-clock cap for ONE external MCP tool call (2 min). */
+const DEFAULT_MCP_CALL_TIMEOUT_MS = 120_000;
 
 /**
  * SILENCE timeout (ms) for EXTERNAL-MCP transport ONLY. Override with
  * `AI_MCP_STREAM_TIMEOUT_MS`; a missing/invalid/non-positive value falls back to
- * {@link DEFAULT_MCP_STREAM_TIMEOUT_MS} (5 min).
+ * {@link DEFAULT_MCP_STREAM_TIMEOUT_MS} (1 min).
  *
  * Deliberately tighter than the chat provider's {@link streamTimeoutMs} (15 min)
- * so a byte-silent/hung MCP upstream is broken in ~5 min instead of 15. This is
+ * so a byte-silent/hung MCP upstream is broken in ~1 min instead of 15. This is
  * the undici `headersTimeout`/`bodyTimeout` for the external-MCP dispatcher only
  * — it must NOT change the chat provider, which legitimately needs 15 min between
  * reasoning chunks (#175).
@@ -153,7 +153,7 @@ export function mcpStreamTimeoutMs(): number {
 /**
  * Total wall-clock cap (ms) for ONE external MCP tool call — APP-LEVEL, not
  * transport. Override with `AI_MCP_CALL_TIMEOUT_MS`; a missing/invalid/
- * non-positive value falls back to {@link DEFAULT_MCP_CALL_TIMEOUT_MS} (15 min).
+ * non-positive value falls back to {@link DEFAULT_MCP_CALL_TIMEOUT_MS} (2 min).
  *
  * Catches a tool that keeps the connection warm (SSE heartbeats / trickle) but
  * never returns a result — which the transport silence timeout

apps/server/src/main.ts

@@ -21,10 +21,24 @@ import { recordHttpResponse } from './integrations/metrics/http-metrics.hook';
 import { startMetricsServer } from './integrations/metrics/metrics.server';
 
 async function bootstrap() {
+  // Fastify JSON body cap. Fastify defaults to 1 MiB, which a long AI-chat
+  // research turn exceeds: the client resends the FULL message history (every
+  // tool call + search result) on each turn, so a deep conversation's POST to
+  // /api/ai-chat/stream can be several MB and would otherwise be rejected with
+  // FST_ERR_CTP_BODY_TOO_LARGE (413). Raise the cap; override with
+  // HTTP_JSON_BODY_LIMIT (bytes). A missing/invalid/non-positive value keeps the
+  // 25 MiB default. Multipart uploads are unaffected (their own @fastify/multipart
+  // limits apply); this only bounds JSON/urlencoded request bodies.
+  const bodyLimitEnv = Number(process.env.HTTP_JSON_BODY_LIMIT);
+  const bodyLimit =
+    Number.isFinite(bodyLimitEnv) && bodyLimitEnv > 0
+      ? bodyLimitEnv
+      : 25 * 1024 * 1024;
   const app = await NestFactory.create<NestFastifyApplication>(
     AppModule,
     new FastifyAdapter({
       trustProxy: resolveTrustProxy(process.env.TRUST_PROXY),
+      bodyLimit,
       routerOptions: {
         maxParamLength: 1000,
         ignoreTrailingSlash: true,