wind-agent-cli 1.37.2

package/server/modules/websocket/services/chat-session-writer.service.ts

@@ -0,0 +1,145 @@
+import { WS_OPEN_STATE } from '@/modules/websocket/services/websocket-state.service.js';
+import type {
+  LLMProvider,
+  NormalizedMessage,
+  RealtimeClientConnection,
+} from '@/shared/types.js';
+import { createCompleteMessage, readObjectRecord } from '@/shared/utils.js';
+
+type ChatSessionWriterOptions = {
+  connection: RealtimeClientConnection;
+  userId: string | number | null;
+  provider: LLMProvider;
+  /** Provider-native id when resuming an existing session, otherwise null. */
+  providerSessionId: string | null;
+  /**
+   * Invoked the moment the provider runtime reveals its native session id
+   * (either via `setSessionId` or a `session_created` event). The registry
+   * persists the app-id-to-provider-id mapping from this callback.
+   */
+  onProviderSessionId: (providerSessionId: string) => void;
+  /**
+   * Remaps/sequences/buffers one outbound live event. Implemented by the chat
+   * run registry; the writer never forwards a provider event untouched.
+   * Returns `null` when the event must be dropped (duplicate terminal
+   * `complete` after an abort already completed the run).
+   */
+  decorateOutboundEvent: (message: NormalizedMessage) => NormalizedMessage | null;
+};
+
+/**
+ * Gateway writer handed to provider runtimes instead of a raw websocket writer.
+ *
+ * It exposes the exact same surface as `WebSocketWriter` (`send`,
+ * `setSessionId`, `getSessionId`, `updateWebSocket`, `userId`,
+ * `isWebSocketWriter`) so the provider runtime adapters need zero changes —
+ * but everything that flows through
+ * it is translated from the provider's world into the app's protocol:
+ *
+ * - `session_created` events are swallowed and turned into a provider-id
+ *   mapping; the frontend never learns provider-native ids.
+ * - every other event gets `sessionId` remapped to the app session id and a
+ *   per-run `seq` assigned before being forwarded.
+ * - `setSessionId(...)` calls (used by runtimes to label captured ids) are
+ *   intercepted and recorded as the provider-id mapping as well.
+ */
+export class ChatSessionWriter {
+  ws: RealtimeClientConnection;
+  userId: string | number | null;
+  /**
+   * Some runtimes feature-detect their writer with this flag; keep it so the
+   * gateway writer is a drop-in replacement for `WebSocketWriter`.
+   */
+  isWebSocketWriter = true;
+
+  private readonly options: ChatSessionWriterOptions;
+  /**
+   * The provider-native session id as the runtime knows it. Kept locally
+   * (besides the registry) because runtimes read it back via `getSessionId()`
+   * to label their own outgoing events — those labels are remapped on send
+   * anyway, but the runtime-visible value must stay provider-native.
+   */
+  private providerSessionId: string | null;
+
+  constructor(options: ChatSessionWriterOptions) {
+    this.options = options;
+    this.ws = options.connection;
+    this.userId = options.userId;
+    this.providerSessionId = options.providerSessionId;
+  }
+
+  send(data: unknown): void {
+    const record = readObjectRecord(data);
+    if (!record || typeof record.kind !== 'string') {
+      // Provider runtimes only emit kind-based normalized messages. Anything
+      // else indicates a programming error; drop it rather than leaking an
+      // un-remapped payload to the client.
+      console.error('[ChatSessionWriter] Dropping non-normalized outbound payload', data);
+      return;
+    }
+
+    const message = record as NormalizedMessage;
+
+    if (message.kind === 'session_created') {
+      const announcedId =
+        typeof message.newSessionId === 'string' && message.newSessionId
+          ? message.newSessionId
+          : message.sessionId;
+      if (announcedId) {
+        this.captureProviderSessionId(announcedId);
+      }
+      // Swallowed on purpose: the frontend already has the stable app session
+      // id, so there is no client-side handoff to perform anymore.
+      return;
+    }
+
+    const outbound = this.options.decorateOutboundEvent(message);
+    if (outbound) {
+      this.forward(outbound);
+    }
+  }
+
+  /**
+   * Emits the synthetic terminal `complete` for runs that ended without one
+   * (runtime crash before completing, or user abort).
+   */
+  sendComplete(opts: { exitCode: number; aborted?: boolean }): void {
+    const message = createCompleteMessage({
+      provider: this.options.provider,
+      sessionId: this.providerSessionId,
+      exitCode: opts.exitCode,
+      aborted: opts.aborted,
+    });
+    const outbound = this.options.decorateOutboundEvent(message);
+    if (outbound) {
+      this.forward(outbound);
+    }
+  }
+
+  updateWebSocket(newConnection: RealtimeClientConnection): void {
+    this.ws = newConnection;
+  }
+
+  setSessionId(sessionId: string): void {
+    this.captureProviderSessionId(sessionId);
+  }
+
+  getSessionId(): string | null {
+    return this.providerSessionId;
+  }
+
+  private captureProviderSessionId(providerSessionId: string): void {
+    if (!providerSessionId || this.providerSessionId === providerSessionId) {
+      return;
+    }
+
+    this.providerSessionId = providerSessionId;
+    this.options.onProviderSessionId(providerSessionId);
+  }
+
+  private forward(message: NormalizedMessage): void {
+    if (this.ws.readyState === WS_OPEN_STATE) {
+      this.ws.send(JSON.stringify(message));
+    }
+  }
+}

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

@@ -0,0 +1,425 @@
+import path from 'node:path';
+
+import type { WebSocket } from 'ws';
+
+import { sessionsDb } from '@/modules/database/index.js';
+import { providerModelsService } from '@/modules/providers/index.js';
+import { chatRunRegistry } from '@/modules/websocket/services/chat-run-registry.service.js';
+import { connectedClients, WS_OPEN_STATE } from '@/modules/websocket/services/websocket-state.service.js';
+import {
+  getGlobalImageAssetsDir,
+  isImageAttachmentDescriptor,
+  normalizeAttachmentDescriptors,
+  type ChatAttachmentDescriptor,
+} from '@/shared/image-attachments.js';
+import type {
+  AnyRecord,
+  AuthenticatedWebSocketRequest,
+  LLMProvider,
+  ProviderPermissionDecision,
+  ProviderRuntimeWriter,
+} from '@/shared/types.js';
+import { parseIncomingJsonObject } from '@/shared/utils.js';
+
+/**
+ * Trust boundary for client-supplied image attachments: chat.send options come
+ * straight from the browser, and the provider runtimes read the referenced
+ * files off disk (Claude base64-encodes them into the prompt). Only images
+ * that live directly inside the global upload store (`~/.cloudcli/assets`,
+ * where POST /api/assets/images puts them) are allowed through — anything
+ * else (absolute paths elsewhere, traversal, subdirectories) is dropped.
+ *
+ * Exported for tests; `assetsRootOverride` exists only for them.
+ */
+export function filterAttachmentsToUploadStore(
+  attachments: unknown,
+  assetsRootOverride?: string,
+): ChatAttachmentDescriptor[] {
+  const assetsRoot = path.resolve(assetsRootOverride ?? getGlobalImageAssetsDir());
+
+  return normalizeAttachmentDescriptors(attachments).filter((descriptor) => {
+    // Relative paths are anchored in the store; absolute ones must already be in it.
+    const resolved = path.resolve(assetsRoot, descriptor.path);
+    const relative = path.relative(assetsRoot, resolved);
+    const isDirectChild =
+      relative.length > 0 &&
+      !relative.startsWith('..') &&
+      !path.isAbsolute(relative) &&
+      !relative.includes(path.sep) &&
+      !relative.includes('/');
+
+    if (!isDirectChild) {
+      console.warn(`[Chat] Dropping attachment outside the upload store: ${descriptor.path}`);
+    }
+    return isDirectChild;
+  });
+}
+
+/** Backward-compatible image filter consumed by existing websocket tests. */
+export function filterImagesToUploadStore(
+  images: unknown,
+  assetsRootOverride?: string,
+): ChatAttachmentDescriptor[] {
+  return filterAttachmentsToUploadStore(images, assetsRootOverride);
+}
+
+/** Application boundary for dispatching provider runs and approvals. */
+type ProviderRuntimeGateway = {
+  hasRuntime(provider: string): boolean;
+  run(
+    provider: LLMProvider,
+    command: string,
+    options: AnyRecord,
+    writer: ProviderRuntimeWriter,
+  ): Promise<unknown>;
+  abort(provider: LLMProvider, sessionId: string): Promise<boolean>;
+  resolveToolApproval(requestId: string, payload: ProviderPermissionDecision): void;
+  getPendingApprovalsForSession(sessionId: string): unknown[];
+};
+
+type ChatWebSocketDependencies = {
+  /** Central dispatcher for every provider SDK/CLI runtime. */
+  runtime: ProviderRuntimeGateway;
+};
+
+/**
+ * Extracts the authenticated request user id in the formats currently produced
+ * by platform and OSS auth code paths.
+ */
+function readRequestUserId(
+  request: AuthenticatedWebSocketRequest | undefined
+): string | number | null {
+  const user = request?.user;
+  if (!user) {
+    return null;
+  }
+
+  if (typeof user.id === 'string' || typeof user.id === 'number') {
+    return user.id;
+  }
+
+  if (typeof user.userId === 'string' || typeof user.userId === 'number') {
+    return user.userId;
+  }
+
+  return null;
+}
+
+function sendJson(ws: WebSocket, payload: unknown): void {
+  if (ws.readyState === WS_OPEN_STATE) {
+    ws.send(JSON.stringify(payload));
+  }
+}
+
+/**
+ * Reports a protocol-level failure to the requesting client.
+ *
+ * Protocol errors deliberately use their own `kind` (instead of the provider
+ * `error` message kind) so the frontend can distinguish "your request was
+ * invalid" from "the model run produced an error" without inspecting text.
+ */
+function sendProtocolError(
+  ws: WebSocket,
+  code: string,
+  error: string,
+  sessionId?: string
+): void {
+  sendJson(ws, {
+    kind: 'protocol_error',
+    code,
+    error,
+    sessionId: sessionId ?? null,
+    timestamp: new Date().toISOString(),
+  });
+}
+
+function readRequiredSessionId(data: AnyRecord): string | null {
+  const sessionId = typeof data.sessionId === 'string' ? data.sessionId.trim() : '';
+  return sessionId.length > 0 ? sessionId : null;
+}
+
+/**
+ * Handles `chat.send`: resolves the session row (provider, project path, and
+ * provider-native id all come from the database — never from the client),
+ * registers the run, and dispatches to the provider runtime.
+ */
+async function handleChatSend(
+  ws: WebSocket,
+  userId: string | number | null,
+  data: AnyRecord,
+  dependencies: ChatWebSocketDependencies
+): Promise<void> {
+  const sessionId = readRequiredSessionId(data);
+  if (!sessionId) {
+    sendProtocolError(ws, 'SESSION_ID_REQUIRED', 'chat.send requires a sessionId.');
+    return;
+  }
+
+  const session = sessionsDb.getSessionById(sessionId);
+  if (!session) {
+    sendProtocolError(
+      ws,
+      'SESSION_NOT_FOUND',
+      `Session "${sessionId}" was not found. Create it via POST /api/providers/sessions first.`,
+      sessionId
+    );
+    return;
+  }
+
+  const provider = session.provider as LLMProvider;
+  if (!dependencies.runtime.hasRuntime(provider)) {
+    sendProtocolError(ws, 'UNSUPPORTED_PROVIDER', `Provider "${provider}" is not available.`, sessionId);
+    return;
+  }
+
+  const run = chatRunRegistry.startRun({
+    appSessionId: sessionId,
+    provider,
+    providerSessionId: session.provider_session_id,
+    connection: ws,
+    userId,
+  });
+
+  if (!run) {
+    sendProtocolError(
+      ws,
+      'RUN_IN_PROGRESS',
+      `Session "${sessionId}" already has a run in progress.`,
+      sessionId
+    );
+    return;
+  }
+
+  const clientOptions = (data.options ?? {}) as AnyRecord;
+  const command = typeof data.content === 'string' ? data.content : '';
+
+  // Record what this turn runs with so reopening the session later restores the
+  // same model and reasoning effort, and so the resume path has a
+  // session-scoped model answer to use.
+  if (typeof clientOptions.model === 'string' && clientOptions.model.trim()) {
+    providerModelsService.setSessionModel(provider, sessionId, clientOptions.model);
+  }
+  if (typeof clientOptions.effort === 'string' && clientOptions.effort.trim()) {
+    providerModelsService.setSessionEffort(provider, sessionId, clientOptions.effort);
+  }
+
+  const attachmentCandidates = [
+    ...normalizeAttachmentDescriptors(clientOptions.images),
+    ...normalizeAttachmentDescriptors(clientOptions.files),
+    ...normalizeAttachmentDescriptors(clientOptions.attachments),
+  ];
+  const verifiedAttachments = filterAttachmentsToUploadStore(attachmentCandidates);
+  const uniqueAttachments = verifiedAttachments.filter(
+    (descriptor, index, all) => all.findIndex((candidate) => candidate.path === descriptor.path) === index,
+  );
+
+  // The provider runtimes receive the stable app session id. When their
+  // CLI/SDK needs the provider-native id for resume, they resolve it from the
+  // session row themselves (sessionsService.resolveProviderSessionId).
+  // Brand-new sessions have no provider id yet, so the runtime starts fresh
+  // and announces one, which the gateway writer captures and maps back to the
+  // app session id.
+  const runtimeOptions: AnyRecord = {
+    ...clientOptions,
+    // Attachments are re-validated server-side: only direct children of the
+    // global upload store may reach provider runtimes or their file tools.
+    attachments: uniqueAttachments,
+    images: uniqueAttachments.filter(isImageAttachmentDescriptor),
+    files: uniqueAttachments.filter((descriptor) => !isImageAttachmentDescriptor(descriptor)),
+    sessionId,
+    cwd: clientOptions.cwd ?? session.project_path ?? undefined,
+    projectPath: session.project_path ?? clientOptions.projectPath,
+  };
+
+  try {
+    await dependencies.runtime.run(provider, command, runtimeOptions, run.writer);
+  } catch (error) {
+    const message = error instanceof Error ? error.message : String(error);
+    console.error(`[Chat] Provider runtime "${provider}" failed`, { sessionId, error: message });
+  } finally {
+    // Safety net: a runtime that crashed (or resolved) without emitting its
+    // terminal `complete` would otherwise leave the session stuck in
+    // "processing" forever on every connected client. Scoped to THIS run —
+    // a queued message can start the session's next run before this promise
+    // settles, and the session-keyed completeRun would kill that new run.
+    chatRunRegistry.completeRunIfCurrent(run, { exitCode: 1 });
+  }
+}
+
+/**
+ * Handles `chat.abort`: cancels the run for one app session and emits the
+ * terminal `complete` on its behalf (runtimes skip their own complete for
+ * aborted runs, and the registry drops any duplicate).
+ */
+async function handleChatAbort(
+  ws: WebSocket,
+  data: AnyRecord,
+  dependencies: ChatWebSocketDependencies
+): Promise<void> {
+  const sessionId = readRequiredSessionId(data);
+  if (!sessionId) {
+    sendProtocolError(ws, 'SESSION_ID_REQUIRED', 'chat.abort requires a sessionId.');
+    return;
+  }
+
+  const run = chatRunRegistry.getRun(sessionId);
+  if (!run || run.status !== 'running') {
+    sendProtocolError(ws, 'NO_ACTIVE_RUN', `Session "${sessionId}" has no active run.`, sessionId);
+    return;
+  }
+
+  const success = await dependencies.runtime.abort(run.provider, sessionId);
+
+  chatRunRegistry.completeRun(sessionId, {
+    exitCode: success ? 0 : 1,
+    aborted: true,
+  });
+}
+
+/**
+ * Handles `chat.subscribe`: for each requested session, reports whether a run
+ * is processing, re-attaches the live stream to this socket, replays missed
+ * events (seq > lastSeq), and includes pending permission requests.
+ *
+ * This single message replaces the old `check-session-status`,
+ * `get-pending-permissions`, and Claude-only writer reconnect flows.
+ */
+function handleChatSubscribe(
+  ws: WebSocket,
+  data: AnyRecord,
+  dependencies: ChatWebSocketDependencies
+): void {
+  const targets = Array.isArray(data.sessions) ? data.sessions : [];
+
+  for (const target of targets) {
+    if (!target || typeof target !== 'object') {
+      continue;
+    }
+
+    const sessionId = typeof (target as AnyRecord).sessionId === 'string'
+      ? ((target as AnyRecord).sessionId as string).trim()
+      : '';
+    if (!sessionId) {
+      continue;
+    }
+
+    const lastSeqRaw = (target as AnyRecord).lastSeq;
+    const lastSeq = typeof lastSeqRaw === 'number' && Number.isFinite(lastSeqRaw)
+      ? Math.max(0, Math.floor(lastSeqRaw))
+      : 0;
+
+    const run = chatRunRegistry.getRun(sessionId);
+    const isProcessing = chatRunRegistry.isProcessing(sessionId);
+
+    // Future live events for this run should land on the socket that asked —
+    // this is what makes mid-stream page refreshes work for all providers.
+    if (isProcessing) {
+      chatRunRegistry.attachConnection(sessionId, ws);
+    }
+
+    // Pending approvals are tracked under the app session id inside the
+    // Claude runtime, so they can be looked up directly.
+    const pendingPermissions = dependencies.runtime.getPendingApprovalsForSession(sessionId);
+
+    sendJson(ws, {
+      kind: 'chat_subscribed',
+      sessionId,
+      isProcessing,
+      lastSeq: run?.lastSeq ?? 0,
+      pendingPermissions,
+      timestamp: new Date().toISOString(),
+    });
+
+    // Replay only for RUNNING runs, strictly after the ack. Completed runs
+    // are fully persisted to the provider transcript and served over REST —
+    // replaying them (e.g. after a page reload where the client's lastSeq is
+    // 0) would duplicate messages the history fetch already returned.
+    if (isProcessing) {
+      for (const event of chatRunRegistry.replayEvents(sessionId, lastSeq)) {
+        sendJson(ws, event);
+      }
+    }
+  }
+}
+
+/**
+ * Handles `chat.permission-response`: forwards a tool-approval decision to the
+ * pending approval resolver (Claude is the only provider with interactive
+ * approvals today, but the message is intentionally provider-neutral).
+ */
+function handlePermissionResponse(data: AnyRecord, dependencies: ChatWebSocketDependencies): void {
+  if (typeof data.requestId !== 'string' || data.requestId.length === 0) {
+    return;
+  }
+
+  dependencies.runtime.resolveToolApproval(data.requestId, {
+    allow: Boolean(data.allow),
+    updatedInput: data.updatedInput,
+    message: typeof data.message === 'string' ? data.message : undefined,
+    rememberEntry: data.rememberEntry,
+  });
+}
+
+/**
+ * Handles authenticated chat websocket messages used by the main chat panel.
+ *
+ * Inbound protocol (client to server):
+ * - `chat.send`                { sessionId, content, options? }
+ * - `chat.abort`               { sessionId }
+ * - `chat.subscribe`           { sessions: [{ sessionId, lastSeq? }] }
+ * - `chat.permission-response` { requestId, allow, updatedInput?, message?, rememberEntry? }
+ *
+ * Outbound protocol (server to client): every frame is `kind`-based — either
+ * a provider `NormalizedMessage` (with `seq`) or a gateway event
+ * (`chat_subscribed`, `session_upserted`, `loading_progress`,
+ * `protocol_error`).
+ */
+export function handleChatConnection(
+  ws: WebSocket,
+  request: AuthenticatedWebSocketRequest,
+  dependencies: ChatWebSocketDependencies
+): void {
+  console.log('[INFO] Chat WebSocket connected');
+  connectedClients.add(ws);
+
+  const userId = readRequestUserId(request);
+
+  ws.on('message', async (rawMessage) => {
+    try {
+      const parsed = parseIncomingJsonObject(rawMessage);
+      if (!parsed) {
+        throw new Error('Invalid websocket payload');
+      }
+
+      const data = parsed as AnyRecord;
+      const messageType = typeof data.type === 'string' ? data.type : '';
+
+      switch (messageType) {
+        case 'chat.send':
+          await handleChatSend(ws, userId, data, dependencies);
+          return;
+        case 'chat.abort':
+          await handleChatAbort(ws, data, dependencies);
+          return;
+        case 'chat.subscribe':
+          handleChatSubscribe(ws, data, dependencies);
+          return;
+        case 'chat.permission-response':
+          handlePermissionResponse(data, dependencies);
+          return;
+        default:
+          sendProtocolError(ws, 'UNKNOWN_MESSAGE_TYPE', `Unknown message type "${messageType}".`);
+          return;
+      }
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error);
+      console.error('[ERROR] Chat WebSocket error:', message);
+      sendProtocolError(ws, 'INTERNAL_ERROR', message);
+    }
+  });
+
+  ws.on('close', () => {
+    console.log('[INFO] Chat client disconnected');
+    connectedClients.delete(ws);
+  });
+}

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

@@ -0,0 +1,65 @@
+import { WebSocket } from 'ws';
+
+/**
+ * Proxies an authenticated client websocket to a plugin websocket endpoint.
+ */
+export function handlePluginWsProxy(
+  clientWs: WebSocket,
+  pathname: string,
+  getPluginPort: (pluginName: string) => number | null
+): void {
+  const pluginName = pathname.replace('/plugin-ws/', '');
+  if (!pluginName || /[^a-zA-Z0-9_-]/.test(pluginName)) {
+    clientWs.close(4400, 'Invalid plugin name');
+    return;
+  }
+
+  const port = getPluginPort(pluginName);
+  if (!port) {
+    clientWs.close(4404, 'Plugin not running');
+    return;
+  }
+
+  const upstream = new WebSocket(`ws://127.0.0.1:${port}/ws`);
+
+  upstream.on('open', () => {
+    console.log(`[Plugins] WS proxy connected to "${pluginName}" on port ${port}`);
+  });
+
+  upstream.on('message', (data, isBinary) => {
+    if (clientWs.readyState === WebSocket.OPEN) {
+      clientWs.send(data, { binary: isBinary });
+    }
+  });
+
+  clientWs.on('message', (data, isBinary) => {
+    if (upstream.readyState === WebSocket.OPEN) {
+      upstream.send(data, { binary: isBinary });
+    }
+  });
+
+  upstream.on('close', () => {
+    if (clientWs.readyState === WebSocket.OPEN) {
+      clientWs.close();
+    }
+  });
+
+  clientWs.on('close', () => {
+    if (upstream.readyState === WebSocket.OPEN) {
+      upstream.close();
+    }
+  });
+
+  upstream.on('error', (error) => {
+    console.error(`[Plugins] WS proxy error for "${pluginName}":`, error.message);
+    if (clientWs.readyState === WebSocket.OPEN) {
+      clientWs.close(4502, 'Upstream error');
+    }
+  });
+
+  clientWs.on('error', () => {
+    if (upstream.readyState === WebSocket.OPEN) {
+      upstream.close();
+    }
+  });
+}