@cloudcli-ai/cloudcli 1.33.0 → 1.33.2

package/server/modules/providers/services/provider-models.service.ts

@@ -17,6 +17,7 @@ import { readProviderSessionActiveModelChange } from '@/shared/utils.js';
 
 export const PROVIDER_MODELS_CACHE_TTL_MS = 3 * 24 * 60 * 60 * 1000;
 const PROVIDER_MODELS_CACHE_VERSION = 1;
+const UNCACHED_PROVIDERS = new Set<LLMProvider>(['claude']);
 
 type ProviderModelsServiceDependencies = {
   resolveProvider?: (provider: LLMProvider) => Pick<IProvider, 'models'>;
@@ -232,10 +233,42 @@ export const createProviderModelsService = (dependencies: ProviderModelsServiceD
     return request;
   };
 
+  const loadDirectModels = (
+    provider: LLMProvider,
+  ): Promise<ProviderModelsResult> => {
+    const request = resolveProvider(provider).models.getSupportedModels()
+      .then((models) => {
+        const currentTime = now();
+        return {
+          models,
+          cache: {
+            updatedAt: new Date(currentTime).toISOString(),
+            expiresAt: new Date(currentTime).toISOString(),
+            source: 'fresh' as const,
+          },
+        };
+      })
+      .finally(() => {
+        pendingRequests.delete(provider);
+      });
+
+    pendingRequests.set(provider, request);
+    return request;
+  };
+
   const getProviderModels = async (
     provider: LLMProvider,
     options: ProviderModelsOptions = {},
   ): Promise<ProviderModelsResult> => {
+    if (UNCACHED_PROVIDERS.has(provider)) {
+      const pendingRequest = pendingRequests.get(provider);
+      if (pendingRequest) {
+        return pendingRequest;
+      }
+
+      return loadDirectModels(provider);
+    }
+
     if (options.bypassCache) {
       const pendingRequest = pendingRequests.get(provider);
       if (pendingRequest) {

package/server/modules/providers/tests/provider-models.service.test.ts

@@ -130,6 +130,37 @@ test('provider models are cached for the three-day ttl', async () => {
   }
 });
 
+test('claude provider models are always loaded directly from the provider', async () => {
+  const tempRoot = await mkdtemp(path.join(os.tmpdir(), 'provider-model-cache-claude-direct-'));
+  let loadCount = 0;
+
+  try {
+    const service = createProviderModelsService({
+      cachePath: path.join(tempRoot, 'models-cache.json'),
+      resolveProvider: (provider) => ({
+        models: {
+          getSupportedModels: async () => {
+            loadCount += 1;
+            return createModels(`${provider}-${loadCount}`);
+          },
+          getCurrentActiveModel: async () => createCurrentActiveModel(`${provider}-active`),
+          changeActiveModel: async (input) => createSessionActiveModelChange(provider, input),
+        },
+      }),
+    });
+
+    const first = await service.getProviderModels('claude');
+    const second = await service.getProviderModels('claude');
+
+    assert.equal(loadCount, 2);
+    assert.equal(first.models.DEFAULT, 'claude-1');
+    assert.equal(second.models.DEFAULT, 'claude-2');
+    assert.equal(second.cache.source, 'fresh');
+  } finally {
+    await rm(tempRoot, { recursive: true, force: true });
+  }
+});
+
 test('provider model cache is persisted across service instances', async () => {
   const tempRoot = await mkdtemp(path.join(os.tmpdir(), 'provider-model-cache-file-'));
   const cachePath = path.join(tempRoot, 'models-cache.json');

package/server/modules/websocket/services/shell-websocket.service.ts

@@ -18,6 +18,7 @@ type ShellIncomingMessage = {
   provider?: string;
   initialCommand?: string;
   isPlainShell?: boolean;
+  forceRestart?: boolean;
 };
 
 type PtySessionEntry = {
@@ -180,6 +181,7 @@ export function handleShellConnection(
         const hasSession = readBoolean(data.hasSession);
         const provider = readString(data.provider, 'claude');
         const initialCommand = readString(data.initialCommand);
+        const forceRestart = readBoolean(data.forceRestart);
         const isPlainShell =
           readBoolean(data.isPlainShell) ||
           (!!initialCommand && !hasSession) ||
@@ -200,7 +202,7 @@ export function handleShellConnection(
             : '';
         ptySessionKey = `${projectPath}_${sessionId ?? 'default'}${commandSuffix}`;
 
-        if (isLoginCommand) {
+        if (isLoginCommand || forceRestart) {
           const oldSession = ptySessionsMap.get(ptySessionKey);
           if (oldSession) {
             if (oldSession.timeoutId) {
@@ -211,7 +213,8 @@ export function handleShellConnection(
           }
         }
 
-        const existingSession = isLoginCommand ? null : ptySessionsMap.get(ptySessionKey);
+        const existingSession =
+          isLoginCommand || forceRestart ? null : ptySessionsMap.get(ptySessionKey);
         if (existingSession) {
           shellProcess = existingSession.pty;
           if (existingSession.timeoutId) {
@@ -368,6 +371,10 @@ export function handleShellConnection(
           }
 
           const session = ptySessionsMap.get(ptySessionKey);
+          if (session && session.pty !== shellProcess) {
+            return;
+          }
+
           if (session && session.ws && session.ws.readyState === WebSocket.OPEN) {
             session.ws.send(
               JSON.stringify({
@@ -451,6 +458,10 @@ export function handleShellConnection(
 
     session.ws = null;
     session.timeoutId = setTimeout(() => {
+      if (ptySessionsMap.get(ptySessionKey as string) !== session) {
+        return;
+      }
+
       session.pty.kill();
       ptySessionsMap.delete(ptySessionKey as string);
     }, PTY_SESSION_TIMEOUT);

package/server/modules/websocket/services/websocket-auth.service.ts

@@ -20,7 +20,13 @@ export function verifyWebSocketClient(
   dependencies: WebSocketAuthDependencies
 ): boolean {
   const request = info.req as AuthenticatedWebSocketRequest;
-  console.log('WebSocket connection attempt to:', request.url);
+  const upgradeUrl = new URL(request.url ?? '/', 'http://localhost');
+  const loggedUrl = new URL(upgradeUrl);
+  if (loggedUrl.searchParams.has('token')) {
+    loggedUrl.searchParams.set('token', 'REDACTED');
+  }
+
+  console.log('WebSocket connection attempt to:', `${loggedUrl.pathname}${loggedUrl.search}`);
 
   // Platform mode: use the first DB user and skip token checks.
   if (dependencies.isPlatform) {
@@ -36,7 +42,6 @@ export function verifyWebSocketClient(
   }
 
   // OSS mode: read JWT from query string first, then Authorization header.
-  const upgradeUrl = new URL(request.url ?? '/', 'http://localhost');
   const token =
     upgradeUrl.searchParams.get('token') ??
     request.headers.authorization?.split(' ')[1] ??

package/server/modules/websocket/services/websocket-server.service.ts

@@ -31,6 +31,24 @@ export function createWebSocketServer(
   });
 
   wss.on('connection', (ws, request) => {
+    // Keep WebSocket alive across reverse-proxy idle timeouts (Cloudflare ~100s,
+    // AWS ALB 60s, nginx 60s, etc.). Without app-level pings these connections
+    // are silently torn down even when the UI is active, causing repeated
+    // reconnect cycles. ws library heartbeat is opt-in.
+    const HEARTBEAT_INTERVAL_MS = 30_000;
+    const heartbeat = setInterval(() => {
+      if (ws.readyState === ws.OPEN) {
+        try {
+          ws.ping();
+        } catch {
+          // socket may have been closed concurrently — interval will be cleared below
+        }
+      }
+    }, HEARTBEAT_INTERVAL_MS);
+    const stopHeartbeat = () => clearInterval(heartbeat);
+    ws.on('close', stopHeartbeat);
+    ws.on('error', stopHeartbeat);
+
     const incomingRequest = request as AuthenticatedWebSocketRequest;
     const url = incomingRequest.url ?? '/';
     const pathname = new URL(url, 'http://localhost').pathname;

package/server/routes/agent.js

@@ -592,12 +592,14 @@ class ResponseCollector {
       }
     }
 
+    const inputTokens = totalInput + totalCacheRead + totalCacheCreation;
+
     return {
-      inputTokens: totalInput,
+      inputTokens,
       outputTokens: totalOutput,
       cacheReadTokens: totalCacheRead,
       cacheCreationTokens: totalCacheCreation,
-      totalTokens: totalInput + totalOutput + totalCacheRead + totalCacheCreation
+      totalTokens: inputTokens + totalOutput
     };
   }
 }

package/server/routes/commands.js

@@ -268,16 +268,35 @@ Custom commands can be created in:
           tokenUsage.contextWindow ??
           0,
       ) || 0;
-    const inputTokensRaw =
+    const normalizedInputValue =
+      tokenUsage.inputTokens ??
+      tokenUsage.input ??
+      tokenUsage.cumulativeInputTokens ??
+      tokenUsage.breakdown?.input ??
+      tokenUsage.promptTokens;
+    const directInputTokens =
       Number(
-        tokenUsage.inputTokens ??
-          tokenUsage.input ??
+        normalizedInputValue ??
           tokenUsage.input_tokens ??
-          tokenUsage.cumulativeInputTokens ??
-          tokenUsage.breakdown?.input ??
-          tokenUsage.promptTokens ??
+          0
+      ) || 0;
+    const cacheReadTokens =
+      Number(
+        tokenUsage.cacheReadTokens ??
+          tokenUsage.cache_read_input_tokens ??
+          tokenUsage.cacheReadInputTokens ??
+          0,
+      ) || 0;
+    const cacheCreationTokens =
+      Number(
+        tokenUsage.cacheCreationTokens ??
+          tokenUsage.cache_creation_input_tokens ??
+          tokenUsage.cacheCreationInputTokens ??
           0,
       ) || 0;
+    const inputTokens = normalizedInputValue == null
+      ? directInputTokens + cacheReadTokens + cacheCreationTokens
+      : directInputTokens;
     const outputTokens =
       Number(
         tokenUsage.outputTokens ??
@@ -288,8 +307,9 @@ Custom commands can be created in:
           tokenUsage.completionTokens ??
           0,
       ) || 0;
-    const hasTokenBreakdown = inputTokensRaw > 0 || outputTokens > 0;
-    const used = reportedUsed || inputTokensRaw + outputTokens;
+    const computedUsed = inputTokens + outputTokens;
+    const hasTokenBreakdown = computedUsed > 0;
+    const used = Math.max(reportedUsed, computedUsed);
 
     return {
       type: "builtin",
@@ -302,7 +322,7 @@ Custom commands can be created in:
         ...(hasTokenBreakdown
           ? {
               tokenBreakdown: {
-                input: inputTokensRaw,
+                input: inputTokens,
                 output: outputTokens,
               },
             }