feat: LLM intent router, direct chat execution, and Memory V2 light intervention

Wire chat intent routing with direct_chat on regular sessions, skill-selected
short-circuit to Agent, memory light/heavy intervention tiers, and fix direct
chat UI stuck streaming after completion.

Co-authored-by: Cursor <cursoragent@cursor.com>

agent-run-gateway.mjs

@@ -173,6 +173,13 @@ function withRunMetadata(userMessage, { toolMode = 'chat', taskType = null, forc
   return { ...message, metadata };
 }
 
+function normalizeSessionMessageCount(value) {
+  if (value == null || value === '') return null;
+  const parsed = Number(value);
+  if (!Number.isFinite(parsed) || parsed < 0) return null;
+  return Math.floor(parsed);
+}
+
 function getRunOptionsFromMessage(userMessage) {
   const metadata = userMessage?.metadata;
   const runMetadata = metadata?.[RUN_METADATA_KEY] ?? metadata?.agentRun ?? {};
@@ -187,6 +194,9 @@ function getRunOptionsFromMessage(userMessage) {
     taskType: normalizeTaskType(runMetadata?.taskType ?? metadata?.taskType),
     forceDeepReasoning: runMetadata?.forceDeepReasoning === true || metadata?.forceDeepReasoning === true,
     validation: normalizeToolGatewayValidation(runMetadata?.validation ?? metadata?.toolGatewayValidation),
+    sessionMessageCount: normalizeSessionMessageCount(
+      runMetadata?.sessionMessageCount ?? metadata?.sessionMessageCount,
+    ),
   };
 }
 
@@ -213,6 +223,7 @@ export function createAgentRunGateway({
   tkmindProxy,
   toolGateway = null,
   directChatService = null,
+  chatIntentRouter = null,
   retryDelaysMs = DEFAULT_RUN_RETRY_DELAYS_MS,
   autoDispatch = envFlag(process.env.MEMIND_AGENT_RUN_AUTODISPATCH, true),
   maxConcurrentRuns = positiveInteger(
@@ -387,21 +398,83 @@ export function createAgentRunGateway({
     }
   }
 
+  async function resolveGrantedSkills(userId) {
+    if (!userId) return [];
+    if (userAuth?.getUserSkills) {
+      const skills = await userAuth.getUserSkills(userId).catch(() => null);
+      if (Array.isArray(skills?.grantedSkills)) return skills.grantedSkills;
+    }
+    if (!userAuth?.getUserCapabilities) return [];
+    const caps = await userAuth.getUserCapabilities(userId).catch(() => null);
+    return Array.isArray(caps?.grantedSkills) ? caps.grantedSkills : [];
+  }
+
+  async function resolveRunRouting(row, userMessage, runOptions) {
+    if (!chatIntentRouter?.classify) return null;
+    const enabled = chatIntentRouter.isEnabled
+      ? await Promise.resolve(chatIntentRouter.isEnabled()).catch(() => false)
+      : true;
+    if (!enabled) return null;
+    const grantedSkills = await resolveGrantedSkills(row.user_id);
+    return chatIntentRouter.classify({
+      userId: row.user_id,
+      userMessage,
+      sessionId: row.agent_session_id ?? null,
+      sessionMessageCount: runOptions.sessionMessageCount,
+      toolMode: runOptions.toolMode,
+      forceDeepReasoning: runOptions.forceDeepReasoning,
+      grantedSkills,
+    });
+  }
+
   async function executeRun(row, runId) {
-    const userMessage = safeJsonParse(row.user_message_json, {});
+    let userMessage = safeJsonParse(row.user_message_json, {});
     const runOptions = getRunOptionsFromMessage(userMessage);
     const toolGatewayStatus = toolGateway?.getStatus ? toolGateway.getStatus() : null;
-    if (!runOptions.forceDeepReasoning && directChatService?.canHandle?.({
+    const routing = await resolveRunRouting(row, userMessage, runOptions);
+    if (routing) {
+      await appendEvent(runId, 'intent_routed', routing);
+      if (routing.route === 'agent_orchestration' && chatIntentRouter?.applyAgentOrchestration) {
+        const grantedSkills = await resolveGrantedSkills(row.user_id);
+        userMessage = chatIntentRouter.applyAgentOrchestration(userMessage, routing, { grantedSkills });
+      }
+    }
+    const routingDecision = routing?.route ?? null;
+    const preferDirectChat =
+      routingDecision === 'direct_chat' ||
+      (isDirectChatSessionId(row.agent_session_id ?? null) && !runOptions.forceDeepReasoning);
+    const directChatInput = {
       sessionId: row.agent_session_id ?? null,
       toolMode: runOptions.toolMode,
       userMessage,
-    })) {
+      routingDecision,
+    };
+    const canDirectChat = Boolean(
+      preferDirectChat && directChatService?.canHandle?.(directChatInput),
+    );
+    if (preferDirectChat && !canDirectChat) {
+      const rejection = directChatService?.explainCanHandle?.(directChatInput);
+      await appendEvent(runId, 'direct_chat_skipped', {
+        sessionId: row.agent_session_id ?? null,
+        routingDecision,
+        reason: rejection?.reason ?? 'can_handle_false',
+      });
+    }
+    if (canDirectChat) {
       try {
         const result = await directChatService.run({
           userId: row.user_id,
           sessionId: row.agent_session_id ?? null,
           requestId: row.request_id,
           userMessage,
+          routingDecision,
+          routingMemory: routing?.memory ?? null,
+          onSessionReady: async (activeSessionId) => {
+            await pool.query(
+              `UPDATE h5_agent_runs SET agent_session_id = ?, updated_at = ? WHERE id = ?`,
+              [activeSessionId, nowMs(), runId],
+            );
+          },
         });
         await appendEvent(runId, 'direct_chat_completed', {
           sessionId: result.sessionId,
@@ -495,7 +568,10 @@ export function createAgentRunGateway({
       sessionId,
       row.request_id,
       userMessage,
-      { toolMode: runOptions.toolMode },
+      {
+        toolMode: runOptions.toolMode,
+        forceDeepReasoning: runOptions.forceDeepReasoning,
+      },
     );
     return { sessionId };
   }
@@ -610,6 +686,12 @@ export function createAgentRunGateway({
        ) h ON h.run_id = r.id
        WHERE r.status = 'running' AND h.latest_heartbeat_at IS NULL`,
     );
+    const chatIntentRouterStatus = chatIntentRouter?.getStatus
+      ? await Promise.resolve(chatIntentRouter.getStatus()).catch((err) => ({
+          enabled: false,
+          error: err instanceof Error ? err.message : String(err),
+        }))
+      : null;
     return {
       autoDispatch,
       maxConcurrentRuns,
@@ -635,6 +717,7 @@ export function createAgentRunGateway({
       terminalStatuses: [...TERMINAL_STATUSES],
       toolGateway: toolGateway?.getStatus ? toolGateway.getStatus() : null,
       directChat: directChatService?.getStatus ? directChatService.getStatus() : null,
+      chatIntentRouter: chatIntentRouterStatus,
     };
   }