fix(gateway): sanitize raw exceptions in /mcp status + /reload sources (P3 re-review#5 blocker)

Co-Authored-By: Claude Haiku 4.5 <[email protected]>

apps/gateway/src/commands/command-executor-p8012.spec.ts

@@ -1,3 +1,4 @@
+import { Logger } from '@nestjs/common';
 import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { CommandExecutorService } from './command-executor.service.js';
 import type { SlashCommandPayload } from '@mosaicstack/types';
@@ -12,6 +13,7 @@ const mockRegistry = {
       { name: 'agent', aliases: ['a'], scope: 'agent', execution: 'socket', available: true },
       { name: 'prdy', aliases: [], scope: 'agent', execution: 'socket', available: true },
       { name: 'tools', aliases: [], scope: 'agent', execution: 'socket', available: true },
+      { name: 'mcp', aliases: [], scope: 'agent', execution: 'socket', available: true },
     ],
     skills: [],
   })),
@@ -72,7 +74,14 @@ const mockChatGateway = {
   broadcastSessionInfo: vi.fn(),
 };
 
-function buildService(redis: typeof mockRedis | null = mockRedis): CommandExecutorService {
+function buildService(
+  redis: typeof mockRedis | null = mockRedis,
+  mcpClient: {
+    reconnectServer: ReturnType<typeof vi.fn>;
+    getServerStatuses: ReturnType<typeof vi.fn>;
+    getToolDefinitions: ReturnType<typeof vi.fn>;
+  } | null = null,
+): CommandExecutorService {
   return new CommandExecutorService(
     mockRegistry as never,
     mockAgentService as never,
@@ -82,7 +91,7 @@ function buildService(redis: typeof mockRedis | null = mockRedis): CommandExecut
     mockBrain as never,
     null,
     mockChatGateway as never,
-    null,
+    mcpClient as never,
   );
 }
 
@@ -258,4 +267,124 @@ describe('CommandExecutorService — P8-012 commands', () => {
     expect(result.command).toBe('tools');
     expect(result.message).toContain('tools');
   });
+
+  // Top-level catch sanitization (P3-4 re-review finding #1): a rejected
+  // Redis `set` inside /provider login is the only reachable path into the
+  // top-level catch in `execute()`. The raw exception must be logged
+  // server-side but never handed back to the socket client.
+  it('sanitizes the top-level command catch, logging the raw exception but never returning it to the client', async () => {
+    const distinctiveRawFailure = 'ECONNREFUSED distinctive-raw-redis-failure-token-9f31';
+    const rawError = new Error(distinctiveRawFailure);
+    const failingRedis = {
+      set: vi.fn().mockRejectedValue(rawError),
+      get: vi.fn(),
+      del: vi.fn(),
+    };
+    const failingService = buildService(failingRedis as unknown as typeof mockRedis);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'provider',
+      args: 'login anthropic',
+      conversationId,
+    };
+    const result = await failingService.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('provider');
+    expect(result.message).toBe('Command failed due to an internal error.');
+    expect(result.message).not.toContain(distinctiveRawFailure);
+    expect(result.message).not.toContain('ECONNREFUSED');
+
+    // The real exception is still logged server-side, as the raw Error
+    // object itself (not stringified/interpolated into the log message).
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(rawError));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
+
+  // Inner catch sanitization (P3-5 operator ruling): every catch in
+  // command-executor.service.ts that returns a SlashCommandResultPayload
+  // must sanitize the client-facing message the same way the top-level
+  // catch does, while still logging the raw exception server-side.
+  it('/agent new sanitizes agent-creation failures, logging the raw exception but never returning it to the client', async () => {
+    const marker = new Error('distinctive-agent-create-failure-token-A17f');
+    mockBrain.agents.create.mockRejectedValueOnce(marker);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'agent',
+      args: 'new my-new-agent',
+      conversationId,
+    };
+    const result = await service.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('agent');
+    expect(result.message).toBe('Failed to create agent due to an internal error.');
+    expect(result.message).not.toContain('distinctive-agent-create-failure-token-A17f');
+
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
+
+  it('/agent <name> switch sanitizes agent-lookup failures, logging the raw exception but never returning it to the client', async () => {
+    const marker = new Error('distinctive-agent-switch-failure-token-B29c');
+    mockBrain.agents.findByName.mockRejectedValueOnce(marker);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'agent',
+      args: 'some-other-agent',
+      conversationId,
+    };
+    const result = await service.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('agent');
+    expect(result.message).toBe('Failed to switch agent due to an internal error.');
+    expect(result.message).not.toContain('distinctive-agent-switch-failure-token-B29c');
+
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
+
+  it('/mcp reconnect sanitizes MCP client failures, logging the raw exception but never returning it to the client', async () => {
+    const marker = new Error('distinctive-mcp-reconnect-failure-token-C33e');
+    const mockMcpClient = {
+      reconnectServer: vi.fn().mockRejectedValue(marker),
+      getServerStatuses: vi.fn(() => []),
+      getToolDefinitions: vi.fn(() => []),
+    };
+    const mcpService = buildService(mockRedis, mockMcpClient);
+    const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const payload: SlashCommandPayload = {
+      command: 'mcp',
+      args: 'reconnect my-server',
+      conversationId,
+    };
+    const result = await mcpService.execute(payload, userScope);
+
+    expect(result.success).toBe(false);
+    expect(result.command).toBe('mcp');
+    expect(result.message).toBe(
+      'Failed to reconnect MCP server "my-server" due to an internal error.',
+    );
+    expect(result.message).not.toContain('distinctive-mcp-reconnect-failure-token-C33e');
+
+    expect(loggerErrorSpy).toHaveBeenCalled();
+    const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
+    expect(loggedRawError).toBe(true);
+
+    loggerErrorSpy.mockRestore();
+  });
 });

apps/gateway/src/commands/command-executor.service.ts

@@ -159,8 +159,13 @@ export class CommandExecutorService {
           };
       }
     } catch (err) {
-      this.logger.error(`Command /${command} failed: ${err}`);
-      return { command, conversationId, success: false, message: String(err) };
+      this.logger.error(`Command /${command} failed`, err);
+      return {
+        command,
+        conversationId,
+        success: false,
+        message: 'Command failed due to an internal error.',
+      };
     }
   }
 
@@ -336,11 +341,11 @@ export class CommandExecutorService {
           data: { agentId: newAgent.id, agentName: newAgent.name },
         };
       } catch (err) {
-        this.logger.error(`Failed to create agent: ${err}`);
+        this.logger.error(`Failed to create agent "${namePart}" for user ${userId}`, err);
         return {
           command: 'agent',
           success: false,
-          message: `Failed to create agent: ${String(err)}`,
+          message: 'Failed to create agent due to an internal error.',
           conversationId,
         };
       }
@@ -391,11 +396,11 @@ export class CommandExecutorService {
         data: { agentId: agentConfig.id, agentName: agentConfig.name, model: agentConfig.model },
       };
     } catch (err) {
-      this.logger.error(`Failed to switch agent "${agentName}": ${err}`);
+      this.logger.error(`Failed to switch agent "${agentName}"`, err);
       return {
         command: 'agent',
         success: false,
-        message: `Failed to switch agent: ${String(err)}`,
+        message: 'Failed to switch agent due to an internal error.',
         conversationId,
       };
     }
@@ -608,11 +613,12 @@ export class CommandExecutorService {
             message: `MCP server "${serverName}" reconnected successfully.`,
           };
         } catch (err) {
+          this.logger.error(`Failed to reconnect MCP server "${serverName}"`, err);
           return {
             command: 'mcp',
             conversationId,
             success: false,
-            message: `Failed to reconnect MCP server "${serverName}": ${err instanceof Error ? err.message : String(err)}`,
+            message: `Failed to reconnect MCP server "${serverName}" due to an internal error.`,
           };
         }
       }

apps/gateway/src/mcp-client/mcp-client.service.spec.ts

@@ -0,0 +1,44 @@
+import { Logger } from '@nestjs/common';
+import { Client } from '@modelcontextprotocol/sdk/client/index.js';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import { McpClientService } from './mcp-client.service.js';
+
+const MCP_LEAK_MARKER = 'MCP_LEAK_MARKER /srv/secret';
+
+describe('McpClientService — failed connect error sanitization', () => {
+  const originalMcpServers = process.env['MCP_SERVERS'];
+
+  beforeEach(() => {
+    process.env['MCP_SERVERS'] = JSON.stringify([
+      { name: 'leaky-server', url: 'http://localhost:9999/mcp' },
+    ]);
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+    if (originalMcpServers === undefined) {
+      delete process.env['MCP_SERVERS'];
+    } else {
+      process.env['MCP_SERVERS'] = originalMcpServers;
+    }
+  });
+
+  it('stores a generic serverEntry.error while logging the raw exception server-side', async () => {
+    vi.spyOn(Client.prototype, 'connect').mockRejectedValue(new Error(MCP_LEAK_MARKER));
+    const errorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+
+    const service = new McpClientService();
+    await service.onModuleInit();
+
+    const statuses = service.getServerStatuses();
+    expect(statuses).toHaveLength(1);
+    expect(statuses[0]?.connected).toBe(false);
+    expect(statuses[0]?.error).toBe('Connection failed (see server logs).');
+    expect(statuses[0]?.error).not.toContain(MCP_LEAK_MARKER);
+
+    const loggedRawMarker = errorSpy.mock.calls.some((call) =>
+      call.some((arg) => typeof arg === 'string' && arg.includes(MCP_LEAK_MARKER)),
+    );
+    expect(loggedRawMarker).toBe(true);
+  });
+});

apps/gateway/src/mcp-client/mcp-client.service.ts

@@ -189,7 +189,7 @@ export class McpClientService implements OnModuleInit, OnModuleDestroy {
       );
     } catch (err) {
       const message = err instanceof Error ? err.message : String(err);
-      serverEntry.error = message;
+      serverEntry.error = 'Connection failed (see server logs).';
       serverEntry.connected = false;
       this.logger.error(`Failed to connect to MCP server "${config.name}": ${message}`);
     }

apps/gateway/src/reload/reload.service.spec.ts

@@ -1,5 +1,8 @@
+import { Logger } from '@nestjs/common';
 import { describe, expect, it, vi } from 'vitest';
+import type { SlashCommandPayload, SystemReloadPayload } from '@mosaicstack/types';
 import { ReloadService } from './reload.service.js';
+import { CommandExecutorService } from '../commands/command-executor.service.js';
 
 function createMockCommandRegistry() {
   return {
@@ -104,3 +107,79 @@ describe('ReloadService', () => {
     expect(() => service.registerPlugin('my-plugin', {})).not.toThrow();
   });
 });
+
+describe('ReloadService — /reload command sanitizes plugin errors', () => {
+  it('generic per-plugin errors reach the chat surface while raw markers stay server-side only', async () => {
+    const registry = {
+      getManifest: vi.fn().mockReturnValue({
+        version: 1,
+        commands: [
+          { name: 'reload', aliases: [], scope: 'core', execution: 'socket', available: true },
+        ],
+        skills: [],
+      }),
+    };
+    const reloadService = new ReloadService(registry as never);
+
+    const RELOAD_LOAD_LEAK_MARKER = 'RELOAD_LOAD_LEAK_MARKER /srv/load-secret';
+    const RELOAD_UNLOAD_LEAK_MARKER = 'RELOAD_UNLOAD_LEAK_MARKER /srv/unload-secret';
+
+    reloadService.registerPlugin('unload-fails', {
+      pluginName: 'unload-fails',
+      onLoad: vi.fn().mockResolvedValue(undefined),
+      onUnload: vi.fn().mockRejectedValue(new Error(RELOAD_UNLOAD_LEAK_MARKER)),
+    });
+    reloadService.registerPlugin('load-fails', {
+      pluginName: 'load-fails',
+      onLoad: vi.fn().mockRejectedValue(new Error(RELOAD_LOAD_LEAK_MARKER)),
+      onUnload: vi.fn().mockResolvedValue(undefined),
+    });
+
+    const errorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
+    const broadcastReload = vi.fn();
+    const mockChatGateway = { broadcastReload };
+    const mockAgentService = { getSession: vi.fn(), applyAgentConfig: vi.fn() };
+    const mockSystemOverride = { set: vi.fn(), get: vi.fn(), clear: vi.fn() };
+    const mockSessionGC = { sweepOrphans: vi.fn() };
+    const mockBrain = { agents: { findByName: vi.fn(), findById: vi.fn(), create: vi.fn() } };
+
+    const executor = new CommandExecutorService(
+      registry as never,
+      mockAgentService as never,
+      mockSystemOverride as never,
+      mockSessionGC as never,
+      null,
+      mockBrain as never,
+      reloadService,
+      mockChatGateway as never,
+      null,
+    );
+
+    const payload: SlashCommandPayload = { command: 'reload', conversationId: 'conv-1' };
+    const result = await executor.execute(payload, { userId: 'user-1', tenantId: 'user-1' });
+
+    expect(result.success).toBe(true);
+    expect(result.message).toContain('unload-fails: unload failed (internal error)');
+    expect(result.message).toContain('load-fails: load failed (internal error)');
+    expect(result.message).not.toContain(RELOAD_UNLOAD_LEAK_MARKER);
+    expect(result.message).not.toContain(RELOAD_LOAD_LEAK_MARKER);
+
+    expect(broadcastReload).toHaveBeenCalledOnce();
+    const broadcastPayload = broadcastReload.mock.calls[0]?.[0] as SystemReloadPayload;
+    expect(broadcastPayload.message).toContain('unload-fails: unload failed (internal error)');
+    expect(broadcastPayload.message).toContain('load-fails: load failed (internal error)');
+    expect(broadcastPayload.message).not.toContain(RELOAD_UNLOAD_LEAK_MARKER);
+    expect(broadcastPayload.message).not.toContain(RELOAD_LOAD_LEAK_MARKER);
+
+    const loggedUnloadMarker = errorSpy.mock.calls.some((call) =>
+      call.some((arg) => typeof arg === 'string' && arg.includes(RELOAD_UNLOAD_LEAK_MARKER)),
+    );
+    const loggedLoadMarker = errorSpy.mock.calls.some((call) =>
+      call.some((arg) => typeof arg === 'string' && arg.includes(RELOAD_LOAD_LEAK_MARKER)),
+    );
+    expect(loggedUnloadMarker).toBe(true);
+    expect(loggedLoadMarker).toBe(true);
+
+    errorSpy.mockRestore();
+  });
+});

apps/gateway/src/reload/reload.service.ts

@@ -58,7 +58,8 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
           await plugin.onUnload();
           reloaded.push(name);
         } catch (err) {
-          errors.push(`${name}: unload failed — ${err}`);
+          this.logger.error(`Plugin "${name}" failed during onUnload: ${err}`);
+          errors.push(`${name}: unload failed (internal error)`);
         }
       }
     }
@@ -69,7 +70,8 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
         try {
           await plugin.onLoad();
         } catch (err) {
-          errors.push(`${name}: load failed — ${err}`);
+          this.logger.error(`Plugin "${name}" failed during onLoad: ${err}`);
+          errors.push(`${name}: load failed (internal error)`);
         }
       }
     }

apps/gateway/src/workspace/workspace.controller.spec.ts

@@ -0,0 +1,104 @@
+import 'reflect-metadata';
+import {
+  type CanActivate,
+  type ExecutionContext,
+  type INestApplication,
+  ValidationPipe,
+} from '@nestjs/common';
+import { FastifyAdapter, type NestFastifyApplication } from '@nestjs/platform-fastify';
+import { Test } from '@nestjs/testing';
+import request from 'supertest';
+import { afterAll, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
+import { AuthGuard } from '../auth/auth.guard.js';
+import { ProjectBootstrapService } from './project-bootstrap.service.js';
+import { WorkspaceController } from './workspace.controller.js';
+
+const bootstrapMock = vi.fn(() =>
+  Promise.resolve({
+    projectId: 'project-1',
+    workspacePath: '/opt/mosaic/.workspaces/users/user-1/project-1',
+  }),
+);
+
+const authGuard: CanActivate = {
+  canActivate(context: ExecutionContext): boolean {
+    const requestContext = context.switchToHttp().getRequest<{ user?: { id: string } }>();
+    requestContext.user = { id: 'user-1' };
+    return true;
+  },
+};
+
+describe('POST /api/workspaces repoUrl validation', () => {
+  let app: INestApplication;
+
+  beforeAll(async () => {
+    const moduleRef = await Test.createTestingModule({
+      controllers: [WorkspaceController],
+      providers: [
+        {
+          provide: ProjectBootstrapService,
+          useValue: { bootstrap: bootstrapMock },
+        },
+      ],
+    })
+      .overrideGuard(AuthGuard)
+      .useValue(authGuard)
+      .compile();
+
+    app = moduleRef.createNestApplication<NestFastifyApplication>(new FastifyAdapter());
+    app.useGlobalPipes(
+      new ValidationPipe({
+        whitelist: true,
+        forbidNonWhitelisted: true,
+        transform: true,
+      }),
+    );
+    await app.init();
+    await app.getHttpAdapter().getInstance().ready();
+  });
+
+  beforeEach(() => {
+    bootstrapMock.mockClear();
+  });
+
+  afterAll(async () => {
+    await app.close();
+  });
+
+  it.each([
+    ['a leading-dash value', '--upload-pack=sh -c id'],
+    ['an ext remote helper', 'ext::sh -c id'],
+    ['a file URL', 'file:///tmp/repository'],
+    ['an unparseable value', 'not a url'],
+    ['an SSH shorthand', '[email protected]:acme/repository.git'],
+    ['a scheme without //', 'https:example.com/acme/repository.git'],
+    ['a hostless git URL', 'git:///tmp/repository'],
+  ])('returns 400 for %s', async (_description, repoUrl) => {
+    const response = await request(app.getHttpServer())
+      .post('/api/workspaces')
+      .send({ name: 'Example', repoUrl })
+      .set('Content-Type', 'application/json');
+
+    expect(response.status).toBe(400);
+    expect(bootstrapMock).not.toHaveBeenCalled();
+  });
+
+  it.each([
+    ['a plain HTTPS repository URL', 'https://example.com/acme/repository.git'],
+    ['a git protocol repository URL', 'git://example.com/acme/repository.git'],
+  ])('accepts %s', async (_description, repoUrl) => {
+    const response = await request(app.getHttpServer())
+      .post('/api/workspaces')
+      .send({ name: 'Example', repoUrl })
+      .set('Content-Type', 'application/json');
+
+    expect(response.status).toBe(201);
+    expect(bootstrapMock).toHaveBeenCalledWith({
+      name: 'Example',
+      description: undefined,
+      userId: 'user-1',
+      teamId: undefined,
+      repoUrl,
+    });
+  });
+});

apps/gateway/src/workspace/workspace.controller.ts

@@ -1,7 +1,11 @@
 import { Body, Controller, Post, UseGuards } from '@nestjs/common';
 import { AuthGuard } from '../auth/auth.guard.js';
 import { CurrentUser } from '../auth/current-user.decorator.js';
-import { ProjectBootstrapService } from './project-bootstrap.service.js';
+import {
+  ProjectBootstrapService,
+  type BootstrapProjectResult,
+} from './project-bootstrap.service.js';
+import { CreateWorkspaceDto } from './workspace.dto.js';
 
 @Controller('api/workspaces')
 @UseGuards(AuthGuard)
@@ -11,20 +15,14 @@ export class WorkspaceController {
   @Post()
   async create(
     @CurrentUser() user: { id: string },
-    @Body()
-    body: {
-      name: string;
-      description?: string;
-      teamId?: string;
-      repoUrl?: string;
-    },
-  ) {
+    @Body() dto: CreateWorkspaceDto,
+  ): Promise<BootstrapProjectResult> {
     return this.bootstrap.bootstrap({
-      name: body.name,
-      description: body.description,
+      name: dto.name,
+      description: dto.description,
       userId: user.id,
-      teamId: body.teamId,
-      repoUrl: body.repoUrl,
+      teamId: dto.teamId,
+      repoUrl: dto.repoUrl,
     });
   }
 }

apps/gateway/src/workspace/workspace.dto.ts

@@ -0,0 +1,33 @@
+import { IsOptional, IsString, IsUrl, Matches, MaxLength } from 'class-validator';
+
+export class CreateWorkspaceDto {
+  @IsString()
+  @MaxLength(255)
+  name!: string;
+
+  @IsOptional()
+  @IsString()
+  @MaxLength(10_000)
+  description?: string;
+
+  @IsOptional()
+  @IsString()
+  teamId?: string;
+
+  @IsOptional()
+  @IsString()
+  @Matches(/^(?:https|git):\/\//i, {
+    message: 'repoUrl must be a valid https:// or git:// URL',
+  })
+  @IsUrl(
+    {
+      protocols: ['https', 'git'],
+      require_host: true,
+      require_protocol: true,
+      require_tld: false,
+      require_valid_protocol: true,
+    },
+    { message: 'repoUrl must be a valid https:// or git:// URL' },
+  )
+  repoUrl?: string;
+}

apps/gateway/src/workspace/workspace.service.spec.ts

@@ -1,11 +1,33 @@
-import { describe, it, expect, beforeEach } from 'vitest';
-import { WorkspaceService } from './workspace.service.js';
+import { BadRequestException } from '@nestjs/common';
+import fs from 'node:fs/promises';
+import os from 'node:os';
 import path from 'node:path';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import { WorkspaceService } from './workspace.service.js';
+
+type ExecFileMock = (
+  command: string,
+  args: readonly string[],
+  options: { cwd: string },
+  callback: (error: Error | null, stdout: string, stderr: string) => void,
+) => void;
+
+const { execFileMock } = vi.hoisted(() => ({
+  execFileMock: vi.fn<ExecFileMock>(),
+}));
+
+vi.mock('node:child_process', () => ({
+  execFile: execFileMock,
+}));
 
 describe('WorkspaceService', () => {
   let service: WorkspaceService;
 
   beforeEach(() => {
+    execFileMock.mockReset();
+    execFileMock.mockImplementation((_command, _args, _options, callback) => {
+      callback(null, '', '');
+    });
     service = new WorkspaceService();
   });
 
@@ -76,4 +98,69 @@ describe('WorkspaceService', () => {
       }
     });
   });
+
+  describe('create', () => {
+    const project = {
+      id: 'project-1',
+      ownerType: 'user',
+      userId: 'user-1',
+      teamId: null,
+    } as const;
+
+    let originalRoot: string | undefined;
+    let temporaryRoot: string;
+
+    beforeEach(async () => {
+      originalRoot = process.env['MOSAIC_ROOT'];
+      temporaryRoot = await fs.mkdtemp(path.join(os.tmpdir(), 'mosaic-workspace-'));
+      process.env['MOSAIC_ROOT'] = temporaryRoot;
+      service = new WorkspaceService();
+    });
+
+    afterEach(async () => {
+      if (originalRoot === undefined) {
+        delete process.env['MOSAIC_ROOT'];
+      } else {
+        process.env['MOSAIC_ROOT'] = originalRoot;
+      }
+      await fs.rm(temporaryRoot, { recursive: true, force: true });
+    });
+
+    it.each([
+      ['a leading-dash URL', '--upload-pack=sh -c id'],
+      ['an ext remote helper', 'ext::sh -c id'],
+      ['a file URL', 'file:///tmp/repository'],
+      ['an unparseable value', 'not a url'],
+      ['an SSH shorthand', '[email protected]:acme/repository.git'],
+      ['a scheme without //', 'https:example.com/acme/repository.git'],
+      ['a hostless git URL', 'git:///tmp/repository'],
+    ])('rejects %s before invoking git', async (_description, repoUrl) => {
+      await expect(service.create(project, repoUrl)).rejects.toBeInstanceOf(BadRequestException);
+      expect(execFileMock).not.toHaveBeenCalled();
+    });
+
+    it.each([
+      ['an HTTPS URL', 'https://example.com/acme/repository.git'],
+      ['a git protocol URL', 'git://example.com/acme/repository.git'],
+    ])('accepts %s and invokes hardened git clone arguments', async (_description, repoUrl) => {
+      const workspacePath = await service.create(project, repoUrl);
+
+      expect(execFileMock).toHaveBeenCalledOnce();
+      expect(execFileMock).toHaveBeenCalledWith(
+        'git',
+        [
+          '-c',
+          'protocol.ext.allow=never',
+          '-c',
+          'protocol.file.allow=never',
+          'clone',
+          '--',
+          repoUrl,
+          '.',
+        ],
+        { cwd: workspacePath },
+        expect.any(Function),
+      );
+    });
+  });
 });

apps/gateway/src/workspace/workspace.service.ts

@@ -1,10 +1,30 @@
-import { Injectable, Logger } from '@nestjs/common';
+import { BadRequestException, Injectable, Logger } from '@nestjs/common';
 import fs from 'node:fs/promises';
 import path from 'node:path';
 import { execFile } from 'node:child_process';
 import { promisify } from 'node:util';
 
 const execFileAsync = promisify(execFile);
+const allowedRepositoryProtocols = new Set(['https:', 'git:']);
+const repositoryUrlPrefixPattern = /^(?:https|git):\/\//i;
+const repositoryUrlError = 'repoUrl must be a valid https:// or git:// URL';
+
+function assertAllowedRepositoryUrl(repoUrl: string): void {
+  if (repoUrl.startsWith('-') || !repositoryUrlPrefixPattern.test(repoUrl)) {
+    throw new BadRequestException(repositoryUrlError);
+  }
+
+  let parsedUrl: URL;
+  try {
+    parsedUrl = new URL(repoUrl);
+  } catch {
+    throw new BadRequestException(repositoryUrlError);
+  }
+
+  if (!allowedRepositoryProtocols.has(parsedUrl.protocol) || parsedUrl.hostname.length === 0) {
+    throw new BadRequestException(repositoryUrlError);
+  }
+}
 
 export interface WorkspaceProject {
   id: string;
@@ -39,14 +59,32 @@ export class WorkspaceService {
    * If repoUrl is provided, clone instead of init.
    */
   async create(project: WorkspaceProject, repoUrl?: string): Promise<string> {
+    if (repoUrl !== undefined) {
+      assertAllowedRepositoryUrl(repoUrl);
+    }
+
     const workspacePath = this.resolvePath(project);
 
     // Create directory
     await fs.mkdir(workspacePath, { recursive: true });
 
-    if (repoUrl) {
-      // Clone existing repo
-      await execFileAsync('git', ['clone', repoUrl, '.'], { cwd: workspacePath });
+    if (repoUrl !== undefined) {
+      // Clone existing repo. Defense in depth keeps dangerous local helpers
+      // disabled and terminates option parsing before positional arguments.
+      await execFileAsync(
+        'git',
+        [
+          '-c',
+          'protocol.ext.allow=never',
+          '-c',
+          'protocol.file.allow=never',
+          'clone',
+          '--',
+          repoUrl,
+          '.',
+        ],
+        { cwd: workspacePath },
+      );
       this.logger.log(`Cloned ${repoUrl} into workspace ${workspacePath}`);
     } else {
       // Init new git repo

apps/web/index.html

@@ -0,0 +1,30 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Mosaic</title>
+    <meta name="description" content="Mosaic Stack Dashboard" />
+    <link rel="preconnect" href="https://fonts.googleapis.com" />
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+    <link
+      rel="stylesheet"
+      href="https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;500;600;700&family=Fira+Code:wght@400;500&display=swap"
+    />
+    <script>
+      // set data-theme before first paint so the stored theme never flashes
+      (function () {
+        try {
+          var theme = window.localStorage.getItem('mosaic-theme') || 'dark';
+          document.documentElement.setAttribute('data-theme', theme === 'light' ? 'light' : 'dark');
+        } catch (error) {
+          document.documentElement.setAttribute('data-theme', 'dark');
+        }
+      })();
+    </script>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.tsx"></script>
+  </body>
+</html>

apps/web/package.json

@@ -4,7 +4,9 @@
   "private": true,
   "scripts": {
     "build": "node ../../scripts/build-web.mjs",
+    "build:vite": "vite build",
     "dev": "next dev",
+    "dev:vite": "vite",
     "lint": "eslint src",
     "typecheck": "tsc --noEmit",
     "test": "vitest run --passWithNoTests",
@@ -13,12 +15,14 @@
   },
   "dependencies": {
     "@mosaicstack/design-tokens": "workspace:^",
+    "@mosaicstack/types": "workspace:^",
     "better-auth": "^1.5.5",
     "clsx": "^2.1.0",
     "next": "^16.0.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-markdown": "^10.1.0",
+    "react-router-dom": "^7.18.2",
     "socket.io-client": "^4.8.0",
     "tailwind-merge": "^3.5.0"
   },
@@ -28,9 +32,11 @@
     "@types/node": "^22.0.0",
     "@types/react": "^19.0.0",
     "@types/react-dom": "^19.0.0",
+    "@vitejs/plugin-react": "^6.0.5",
     "jsdom": "^29.0.0",
     "tailwindcss": "^4.0.0",
     "typescript": "^5.8.0",
-    "vitest": "^2.0.0"
+    "vite": "^8.2.1",
+    "vitest": "^3.2.7"
   }
 }

apps/web/src/app/auth/provider/[provider]/page.tsx

@@ -3,41 +3,56 @@
 import Link from 'next/link';
 import { useEffect, useState } from 'react';
 import { useParams, useSearchParams } from 'next/navigation';
+import { api } from '@/lib/api';
+import { resolveAuthCallbackURL } from '@/lib/auth-redirect';
 import { signIn } from '@/lib/auth-client';
-import { getSsoProvider } from '@/lib/sso-providers';
+import type { SsoProviderDiscovery } from '@/lib/sso';
 
 export default function AuthProviderRedirectPage(): React.ReactElement {
   const params = useParams<{ provider: string }>();
   const searchParams = useSearchParams();
   const providerId = typeof params.provider === 'string' ? params.provider : '';
-  const provider = getSsoProvider(providerId);
-  const callbackURL = searchParams.get('callbackURL') ?? '/chat';
+  const requestedCallbackURL = searchParams.get('callbackURL');
+  const [providerName, setProviderName] = useState<string | null>(null);
   const [error, setError] = useState<string | null>(null);
 
   useEffect(() => {
-    const currentProvider = provider;
-
-    if (!currentProvider) {
-      setError('Unknown SSO provider.');
-      return;
-    }
-
-    if (!currentProvider.enabled) {
-      setError(`${currentProvider.buttonLabel} is not enabled in this deployment.`);
-      return;
-    }
-
-    const activeProvider = currentProvider;
     let cancelled = false;
 
     async function redirectToProvider(): Promise<void> {
-      const result = await signIn.oauth2({
-        providerId: activeProvider.id,
-        callbackURL,
-      });
+      try {
+        const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
+        const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
+        if (cancelled) return;
 
-      if (!cancelled && result?.error) {
-        setError(result.error.message ?? `${activeProvider.buttonLabel} sign in failed.`);
+        const provider = providers.find((candidate) => candidate.id === providerId);
+        if (!provider) {
+          setError('Unknown SSO provider.');
+          return;
+        }
+
+        setProviderName(provider.name);
+        if (!provider.configured) {
+          setError(`${provider.name} is not enabled in this deployment.`);
+          return;
+        }
+        if (provider.loginMode !== 'oidc') {
+          setError(`${provider.name} is not available for OIDC sign in.`);
+          return;
+        }
+
+        const result = await signIn.oauth2({
+          providerId: provider.id,
+          callbackURL,
+        });
+
+        if (!cancelled && result?.error) {
+          setError(result.error.message ?? `${provider.name} sign in failed.`);
+        }
+      } catch (caught: unknown) {
+        if (!cancelled) {
+          setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
+        }
       }
     }
 
@@ -46,19 +61,22 @@ export default function AuthProviderRedirectPage(): React.ReactElement {
     return () => {
       cancelled = true;
     };
-  }, [callbackURL, provider]);
+  }, [providerId, requestedCallbackURL]);
 
   return (
     <div className="mx-auto flex min-h-[50vh] max-w-md flex-col justify-center">
       <h1 className="text-2xl font-semibold text-text-primary">Single sign-on</h1>
       <p className="mt-2 text-sm text-text-secondary">
-        {provider
-          ? `Redirecting you to ${provider.buttonLabel.replace('Continue with ', '')}...`
+        {providerName
+          ? `Redirecting you to ${providerName}...`
           : 'Preparing your sign-in request...'}
       </p>
 
       {error ? (
-        <div className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error">
+        <div
+          role="alert"
+          className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
           <p>{error}</p>
           <Link
             href="/login"

apps/web/src/lib/api.spec.ts

@@ -0,0 +1,57 @@
+import { afterEach, describe, expect, it, vi } from 'vitest';
+import { api } from './api';
+
+describe('api', () => {
+  afterEach(() => {
+    vi.unstubAllGlobals();
+  });
+
+  it('fetches the supplied relative path with credentials and a JSON body', async () => {
+    const fetchMock = vi.fn<typeof fetch>();
+    fetchMock.mockResolvedValue(
+      new Response(JSON.stringify({ ok: true }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchMock);
+
+    await expect(
+      api<{ ok: boolean }>('/api/projects', {
+        method: 'POST',
+        body: { name: 'Mosaic' },
+      }),
+    ).resolves.toEqual({ ok: true });
+
+    expect(fetchMock).toHaveBeenCalledOnce();
+    expect(fetchMock).toHaveBeenCalledWith(
+      '/api/projects',
+      expect.objectContaining({
+        method: 'POST',
+        credentials: 'include',
+        body: JSON.stringify({ name: 'Mosaic' }),
+        headers: expect.objectContaining({
+          Accept: 'application/json',
+          'Content-Type': 'application/json',
+        }),
+      }),
+    );
+  });
+
+  it('throws the gateway JSON error with its statusCode', async () => {
+    const fetchMock = vi.fn<typeof fetch>();
+    fetchMock.mockResolvedValue(
+      new Response(JSON.stringify({ statusCode: 403, message: 'Forbidden' }), {
+        status: 403,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchMock);
+
+    await expect(api('/api/admin/users')).rejects.toMatchObject({
+      name: 'Error',
+      message: 'Forbidden',
+      statusCode: 403,
+    });
+  });
+});

apps/web/src/lib/api.ts

@@ -1,5 +1,3 @@
-const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
-
 export interface ApiRequestInit extends Omit<RequestInit, 'body'> {
   body?: unknown;
 }
@@ -25,7 +23,7 @@ export async function api<T>(path: string, init?: ApiRequestInit): Promise<T> {
     headers['Content-Type'] = 'application/json';
   }
 
-  const res = await fetch(`${GATEWAY_URL}${path}`, {
+  const res = await fetch(path, {
     credentials: 'include',
     ...rest,
     headers,

apps/web/src/lib/auth-client.spec.ts

@@ -0,0 +1,29 @@
+import { afterEach, describe, expect, it, vi } from 'vitest';
+
+describe('auth client origin contract', () => {
+  afterEach(() => {
+    vi.unstubAllGlobals();
+    vi.resetModules();
+  });
+
+  it('uses the same-origin BetterAuth mount at /api/auth', async () => {
+    const fetchMock = vi.fn<typeof fetch>();
+    fetchMock.mockResolvedValue(
+      new Response(JSON.stringify({ session: null, user: null }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchMock);
+
+    const { authClient } = await import('./auth-client');
+    await authClient.getSession();
+
+    expect(fetchMock).toHaveBeenCalledOnce();
+    const firstCall = fetchMock.mock.calls.at(0);
+    expect(firstCall).toBeDefined();
+    const requestURL = new URL(String(firstCall?.[0]), window.location.origin);
+    expect(requestURL.origin).toBe(window.location.origin);
+    expect(requestURL.pathname).toBe('/api/auth/get-session');
+  });
+});

apps/web/src/lib/auth-client.ts

@@ -1,8 +1,9 @@
 import { createAuthClient } from 'better-auth/react';
 import { adminClient, genericOAuthClient } from 'better-auth/client/plugins';
 
+// The gateway and BetterAuth client both use /api/auth. Omitting baseURL keeps
+// every browser request on the current origin in development and production.
 export const authClient = createAuthClient({
-  baseURL: process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242',
   plugins: [adminClient(), genericOAuthClient()],
 });
 

apps/web/src/lib/auth-redirect.spec.ts

@@ -0,0 +1,30 @@
+import { describe, expect, it } from 'vitest';
+import { resolveAuthCallbackURL } from './auth-redirect';
+
+const CURRENT_ORIGIN = 'https://mosaic.example';
+
+describe('resolveAuthCallbackURL', () => {
+  it('preserves a canonical same-origin path with search and hash', () => {
+    expect(resolveAuthCallbackURL('/projects?view=active#current', CURRENT_ORIGIN)).toBe(
+      '/projects?view=active#current',
+    );
+  });
+
+  it.each([
+    null,
+    'chat',
+    '//evil.example',
+    '/..//evil.com',
+    '/..//evil.com/x',
+    '/./..//evil.com',
+    '/../..//evil.com',
+    '/foo/..//evil.com',
+    '/\\evil.example',
+    '/\n//evil.example',
+    '/\r//evil.example',
+    '/\t//evil.example',
+    'https://evil.example/phish',
+  ])('falls back to chat for an unsafe callback target %#', (candidate) => {
+    expect(resolveAuthCallbackURL(candidate, CURRENT_ORIGIN)).toBe('/chat');
+  });
+});

apps/web/src/lib/auth-redirect.ts

@@ -0,0 +1,23 @@
+const DEFAULT_AUTH_CALLBACK_URL = '/chat';
+
+/**
+ * Return a canonical same-origin path for post-auth navigation.
+ *
+ * Parsing before comparing origins rejects protocol-relative URLs, backslash
+ * variants, and control characters that the WHATWG parser normalizes away.
+ */
+export function resolveAuthCallbackURL(candidate: string | null, currentOrigin: string): string {
+  if (!candidate?.startsWith('/')) return DEFAULT_AUTH_CALLBACK_URL;
+
+  try {
+    const expectedOrigin = new URL(currentOrigin).origin;
+    const resolved = new URL(candidate, expectedOrigin);
+    if (resolved.origin !== expectedOrigin || resolved.pathname.startsWith('//')) {
+      return DEFAULT_AUTH_CALLBACK_URL;
+    }
+
+    return `${resolved.pathname}${resolved.search}${resolved.hash}`;
+  } catch {
+    return DEFAULT_AUTH_CALLBACK_URL;
+  }
+}

apps/web/src/lib/chat-contract.ts

@@ -0,0 +1,61 @@
+// Centralizes the type-only import of the shared `/chat` Socket.IO contract from
+// the public `@mosaicstack/types` package. `import type` is erased at compile
+// time, so this introduces no runtime dependency — it only reuses the exact
+// payload shapes instead of redeclaring them.
+import type { Socket } from 'socket.io-client';
+import type {
+  AbortPayload,
+  AgentEndPayload,
+  AgentStartPayload,
+  AgentTextPayload,
+  AgentThinkingPayload,
+  ChatMessagePayload,
+  ClientToServerEvents,
+  CommandDef,
+  CommandManifest,
+  CommandManifestPayload,
+  ErrorPayload,
+  MessageAckPayload,
+  RoutingDecisionInfo,
+  ServerToClientEvents,
+  SessionInfoPayload,
+  SessionUsagePayload,
+  SetThinkingPayload,
+  SkillCommandDef,
+  SlashCommandApprovalResultPayload,
+  SlashCommandPayload,
+  SlashCommandResultPayload,
+  SystemReloadPayload,
+  ToolEndPayload,
+  ToolStartPayload,
+} from '@mosaicstack/types';
+
+export type {
+  AbortPayload,
+  AgentEndPayload,
+  AgentStartPayload,
+  AgentTextPayload,
+  AgentThinkingPayload,
+  ChatMessagePayload,
+  ClientToServerEvents,
+  CommandDef,
+  CommandManifest,
+  CommandManifestPayload,
+  ErrorPayload,
+  MessageAckPayload,
+  RoutingDecisionInfo,
+  ServerToClientEvents,
+  SessionInfoPayload,
+  SessionUsagePayload,
+  SetThinkingPayload,
+  SkillCommandDef,
+  SlashCommandApprovalResultPayload,
+  SlashCommandPayload,
+  SlashCommandResultPayload,
+  SystemReloadPayload,
+  ToolEndPayload,
+  ToolStartPayload,
+};
+
+/** The `/chat` namespace socket, narrowed to the exact typed event contract. */
+export type ChatSocket = Socket<ServerToClientEvents, ClientToServerEvents>;

apps/web/src/lib/socket.spec.ts

@@ -0,0 +1,98 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+const { ioMock } = vi.hoisted(() => ({
+  ioMock: vi.fn(),
+}));
+
+vi.mock('socket.io-client', () => ({
+  io: ioMock,
+}));
+
+import { destroySocket, getSocket } from './socket';
+
+interface MockChatSocket {
+  on: ReturnType<typeof vi.fn>;
+  offAny: ReturnType<typeof vi.fn>;
+  disconnect: ReturnType<typeof vi.fn>;
+  /** Test-only helper: fires every handler registered for `event` via
+   * `.on`, mirroring how a real socket.io-client instance invokes its own
+   * listeners (e.g. calling the registered `disconnect` handler(s) on a
+   * real transient disconnect). */
+  trigger(event: string): void;
+}
+
+function createMockSocket(): MockChatSocket {
+  const handlers = new Map<string, Set<() => void>>();
+  const mockSocket: MockChatSocket = {
+    on: vi.fn((event: string, handler: () => void) => {
+      if (!handlers.has(event)) handlers.set(event, new Set());
+      handlers.get(event)?.add(handler);
+      return mockSocket;
+    }),
+    offAny: vi.fn(() => mockSocket),
+    disconnect: vi.fn(() => mockSocket),
+    trigger(event: string): void {
+      for (const handler of handlers.get(event) ?? []) handler();
+    },
+  };
+  return mockSocket;
+}
+
+let currentMock!: MockChatSocket;
+
+describe('chat socket', () => {
+  beforeEach(() => {
+    ioMock.mockReset();
+    // A fresh object per io() call so identity assertions (same singleton vs.
+    // a genuinely new instance) are meaningful.
+    ioMock.mockImplementation(() => {
+      currentMock = createMockSocket();
+      return currentMock;
+    });
+  });
+
+  afterEach(() => {
+    destroySocket();
+  });
+
+  it('creates one same-origin /chat namespace socket', () => {
+    const first = getSocket();
+    const second = getSocket();
+
+    expect(first).toBe(second);
+    expect(ioMock).toHaveBeenCalledOnce();
+    expect(ioMock).toHaveBeenCalledWith('/chat', {
+      withCredentials: true,
+      autoConnect: false,
+      transports: ['websocket', 'polling'],
+    });
+  });
+
+  it('keeps the same singleton instance across a transient disconnect', () => {
+    const first = getSocket();
+
+    // socket.ts must not react to a real socket's `disconnect` event by
+    // nulling the singleton — it registers no such handler at all now.
+    // Actually fire every handler registered via `.on('disconnect', ...)`
+    // (mirroring a real socket.io-client reconnect) instead of merely
+    // calling getSocket() again: this is what makes the test fail if
+    // production reintroduces `socket.on('disconnect', () => { socket =
+    // null; })`, since that handler would run here and null the singleton
+    // before the next getSocket() call.
+    currentMock.trigger('disconnect');
+    const second = getSocket();
+
+    expect(second).toBe(first);
+    expect(ioMock).toHaveBeenCalledOnce();
+  });
+
+  it('only creates a new singleton after an explicit destroySocket()', () => {
+    const first = getSocket();
+
+    destroySocket();
+    const second = getSocket();
+
+    expect(second).not.toBe(first);
+    expect(ioMock).toHaveBeenCalledTimes(2);
+  });
+});

apps/web/src/lib/socket.ts

@@ -1,23 +1,27 @@
-import { io, type Socket } from 'socket.io-client';
+import { io } from 'socket.io-client';
+import type { ChatSocket } from './chat-contract';
 
-const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
+let socket: ChatSocket | null = null;
 
-let socket: Socket | null = null;
-
-export function getSocket(): Socket {
+export function getSocket(): ChatSocket {
   if (!socket) {
-    socket = io(`${GATEWAY_URL}/chat`, {
+    // socket.io-client 4.8.3's `io()` factory declaration always returns the
+    // default unparameterized Socket (it accepts no <ListenEvents, EmitEvents>
+    // generics), so this one cast is the unavoidable boundary between that and the
+    // typed `/chat` contract. Every other call site uses the resulting ChatSocket
+    // with no further assertions.
+    socket = io('/chat', {
       withCredentials: true,
       autoConnect: false,
       transports: ['websocket', 'polling'],
-    });
+    }) as unknown as ChatSocket;
 
-    // Reset singleton reference when socket is fully closed so the next
-    // getSocket() call creates a fresh instance instead of returning a
-    // closed/dead socket.
-    socket.on('disconnect', () => {
-      socket = null;
-    });
+    // A transient `disconnect` (network blip, server restart) must NOT null
+    // the singleton: socket.io-client auto-reconnects this same instance,
+    // and its listeners stay registered across that reconnect. Nulling here
+    // previously orphaned those listeners on the next getSocket() call by
+    // handing back a brand-new, unconnected instance. Only destroySocket()
+    // (an explicit, intentional teardown) may reset the singleton.
   }
   return socket;
 }

apps/web/src/lib/sso-providers.test.ts

@@ -1,48 +0,0 @@
-import { afterEach, describe, expect, it, vi } from 'vitest';
-import { getEnabledSsoProviders, getSsoProvider } from './sso-providers';
-
-describe('sso-providers', () => {
-  afterEach(() => {
-    vi.unstubAllEnvs();
-  });
-
-  it('returns the enabled providers in login button order', () => {
-    vi.stubEnv('NEXT_PUBLIC_WORKOS_ENABLED', 'true');
-    vi.stubEnv('NEXT_PUBLIC_KEYCLOAK_ENABLED', 'true');
-
-    expect(getEnabledSsoProviders()).toEqual([
-      {
-        id: 'workos',
-        buttonLabel: 'Continue with WorkOS',
-        description: 'Enterprise SSO via WorkOS',
-        enabled: true,
-        href: '/auth/provider/workos',
-      },
-      {
-        id: 'keycloak',
-        buttonLabel: 'Continue with Keycloak',
-        description: 'Enterprise SSO via Keycloak',
-        enabled: true,
-        href: '/auth/provider/keycloak',
-      },
-    ]);
-  });
-
-  it('marks disabled providers without exposing them in the enabled list', () => {
-    vi.stubEnv('NEXT_PUBLIC_WORKOS_ENABLED', 'true');
-    vi.stubEnv('NEXT_PUBLIC_KEYCLOAK_ENABLED', 'false');
-
-    expect(getEnabledSsoProviders().map((provider) => provider.id)).toEqual(['workos']);
-    expect(getSsoProvider('keycloak')).toEqual({
-      id: 'keycloak',
-      buttonLabel: 'Continue with Keycloak',
-      description: 'Enterprise SSO via Keycloak',
-      enabled: false,
-      href: '/auth/provider/keycloak',
-    });
-  });
-
-  it('returns null for unknown providers', () => {
-    expect(getSsoProvider('authentik')).toBeNull();
-  });
-});

apps/web/src/lib/sso-providers.ts

@@ -1,53 +0,0 @@
-export type SsoProviderId = 'workos' | 'keycloak';
-
-export interface SsoProvider {
-  id: SsoProviderId;
-  buttonLabel: string;
-  description: string;
-  enabled: boolean;
-  href: string;
-}
-
-const PROVIDER_METADATA: Record<SsoProviderId, Omit<SsoProvider, 'enabled' | 'href'>> = {
-  workos: {
-    id: 'workos',
-    buttonLabel: 'Continue with WorkOS',
-    description: 'Enterprise SSO via WorkOS',
-  },
-  keycloak: {
-    id: 'keycloak',
-    buttonLabel: 'Continue with Keycloak',
-    description: 'Enterprise SSO via Keycloak',
-  },
-};
-
-export function getEnabledSsoProviders(): SsoProvider[] {
-  return (Object.keys(PROVIDER_METADATA) as SsoProviderId[])
-    .map((providerId) => getSsoProvider(providerId))
-    .filter((provider): provider is SsoProvider => provider?.enabled === true);
-}
-
-export function getSsoProvider(providerId: string): SsoProvider | null {
-  if (!isSsoProviderId(providerId)) {
-    return null;
-  }
-
-  return {
-    ...PROVIDER_METADATA[providerId],
-    enabled: isSsoProviderEnabled(providerId),
-    href: `/auth/provider/${providerId}`,
-  };
-}
-
-function isSsoProviderId(value: string): value is SsoProviderId {
-  return value === 'workos' || value === 'keycloak';
-}
-
-function isSsoProviderEnabled(providerId: SsoProviderId): boolean {
-  switch (providerId) {
-    case 'workos':
-      return process.env['NEXT_PUBLIC_WORKOS_ENABLED'] === 'true';
-    case 'keycloak':
-      return process.env['NEXT_PUBLIC_KEYCLOAK_ENABLED'] === 'true';
-  }
-}

apps/web/src/main.tsx

@@ -0,0 +1,19 @@
+import { StrictMode } from 'react';
+import { createRoot } from 'react-dom/client';
+import { RouterProvider } from 'react-router-dom';
+import { ThemeProvider } from '@/providers/theme-provider';
+import { createAppRouter } from '@/routes';
+import '@/app/globals.css';
+
+const container = document.getElementById('root');
+if (!container) {
+  throw new Error('missing #root element');
+}
+
+createRoot(container).render(
+  <StrictMode>
+    <ThemeProvider>
+      <RouterProvider router={createAppRouter()} />
+    </ThemeProvider>
+  </StrictMode>,
+);

apps/web/src/routes.tsx

@@ -0,0 +1,51 @@
+import type { ReactElement } from 'react';
+import { createBrowserRouter, Navigate, Outlet, type RouteObject } from 'react-router-dom';
+import { LoginPage } from '@/spa/pages/login';
+import { RegisterPage } from '@/spa/pages/register';
+import { SsoCallbackPage } from '@/spa/pages/sso-callback';
+import { ChatPage } from '@/spa/pages/chat';
+import { ChatRouteErrorBoundary } from '@/spa/pages/chat-error-boundary';
+import { AuthGuard, GuestGuard } from '@/spa/guards';
+import { Placeholder } from '@/spa/placeholder';
+
+function GuestLayout(): ReactElement {
+  return (
+    <div className="flex min-h-screen items-center justify-center bg-surface-bg px-4 py-8">
+      <div className="w-full max-w-md rounded-xl border border-surface-border bg-surface-card p-8 shadow-lg">
+        <Outlet />
+      </div>
+    </div>
+  );
+}
+
+export const routes: RouteObject[] = [
+  {
+    element: <GuestGuard />,
+    children: [
+      {
+        element: <GuestLayout />,
+        children: [
+          { path: '/login', element: <LoginPage /> },
+          { path: '/register', element: <RegisterPage /> },
+          { path: '/auth/provider/:provider', element: <SsoCallbackPage /> },
+        ],
+      },
+    ],
+  },
+  {
+    element: <AuthGuard />,
+    children: [
+      { path: '/', element: <Navigate to="/chat" replace /> },
+      { path: '/chat', element: <ChatPage />, errorElement: <ChatRouteErrorBoundary /> },
+      { path: '/projects', element: <Placeholder title="Projects" /> },
+      { path: '/projects/:id', element: <Placeholder title="Project" /> },
+      { path: '/tasks', element: <Placeholder title="Tasks" /> },
+      { path: '/settings', element: <Placeholder title="Settings" /> },
+      { path: '/admin', element: <Placeholder title="Admin" /> },
+    ],
+  },
+];
+
+export function createAppRouter(): ReturnType<typeof createBrowserRouter> {
+  return createBrowserRouter(routes);
+}

apps/web/src/spa/chat/commands-panel.spec.tsx

@@ -0,0 +1,280 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+import { CommandsPanel } from './commands-panel';
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+let root: Root | null;
+let container: HTMLElement | null;
+
+async function render(node: Parameters<Root['render']>[0]): Promise<void> {
+  container = document.createElement('div');
+  document.body.append(container);
+  root = createRoot(container);
+  await act(async () => {
+    root?.render(node);
+  });
+}
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+  root = null;
+  container = null;
+});
+
+describe('CommandsPanel', () => {
+  it('shows the frozen local pendingApproval args in the confirmation area, regardless of misleading server message text', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{
+          conversationId: 'c1',
+          command: 'deploy', // matches pendingApproval — this is a legitimately approved request
+          success: true,
+          approvalId: 'ap1',
+          expiresAt: '2026-01-01T00:00:00.000Z',
+          // Free-text server message claims a different, less alarming target
+          // than what will actually be sent — the UI must not rely on this.
+          message: 'This will only affect the staging environment.',
+        }}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    // The exact frozen combined action is visible...
+    expect(container?.textContent).toContain('/deploy');
+    expect(container?.textContent).toContain('prod');
+    // ...and the misleading server free-text is never shown next to it.
+    expect(container?.textContent).not.toContain('staging environment');
+  });
+
+  it('does not throw when a manifest commands entry is null', async () => {
+    const manifest = {
+      commands: [
+        null,
+        {
+          name: 'model',
+          aliases: [],
+          description: 'Change the active model',
+          scope: 'core',
+          execution: 'socket',
+          available: true,
+        },
+      ],
+      skills: [null],
+      version: 1,
+    } as unknown as Parameters<typeof CommandsPanel>[0]['manifest'];
+
+    await expect(
+      render(
+        <CommandsPanel
+          manifest={manifest}
+          results={[]}
+          approval={null}
+          pendingApproval={null}
+          hasConversation={false}
+          onExecute={vi.fn()}
+          onApprove={vi.fn()}
+          onRunApproved={vi.fn()}
+        />,
+      ),
+    ).resolves.not.toThrow();
+
+    expect(container?.textContent).toContain('model');
+  });
+
+  it('shows an explicit no-args fallback when the frozen pendingApproval has no args', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{
+          conversationId: 'c1',
+          command: 'deploy',
+          success: true,
+          approvalId: 'ap1',
+          expiresAt: '2026-01-01T00:00:00.000Z',
+        }}
+        pendingApproval={{ command: 'deploy' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent?.toLowerCase()).toContain('no args');
+  });
+
+  it('renders skills from a skills-only manifest', async () => {
+    await render(
+      <CommandsPanel
+        manifest={{
+          commands: [],
+          skills: [{ name: 'brave-search', description: 'Search the web', available: true }],
+          version: 1,
+        }}
+        results={[]}
+        approval={null}
+        pendingApproval={null}
+        hasConversation={false}
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('brave-search');
+    expect(container?.textContent).toContain('Search the web');
+  });
+
+  it('does not show the Run affordance when approval.success/approvalId are objects, even though command matches pendingApproval', async () => {
+    const approval = {
+      conversationId: 'c1',
+      command: 'deploy',
+      success: { truthy: 'object' },
+      approvalId: { also: 'object' },
+    } as unknown as Parameters<typeof CommandsPanel>[0]['approval'];
+
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={approval}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(
+      [...(container?.querySelectorAll('button') ?? [])].some((button) =>
+        button.textContent?.includes('Run approved command'),
+      ),
+    ).toBe(false);
+  });
+
+  it('shows the guarded server-provided denial reason for a denied approval', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{
+          conversationId: 'c1',
+          command: 'deploy',
+          success: false,
+          message: 'Not authorized',
+        }}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('Not authorized');
+  });
+
+  it('falls back to a stable "Denied." copy when a denial has no usable message', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[]}
+        approval={{ conversationId: 'c1', command: 'deploy', success: false }}
+        pendingApproval={{ command: 'deploy', args: 'prod' }}
+        hasConversation
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('Denied.');
+  });
+
+  it('shows the guarded contract-provided reason for a failed command result, falling back to a stable copy only when absent', async () => {
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[
+          { conversationId: 'c1', command: 'model', success: false, message: 'Unknown model' },
+          { conversationId: 'c1', command: 'deploy', success: false },
+        ]}
+        approval={null}
+        pendingApproval={null}
+        hasConversation={false}
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    expect(container?.textContent).toContain('Unknown model');
+    expect(container?.textContent).toContain('Command failed.');
+  });
+
+  it('bounds an oversized command result message at the render site as defense-in-depth', async () => {
+    const hostileMessage = 'y'.repeat(50_000);
+    await render(
+      <CommandsPanel
+        manifest={null}
+        results={[
+          { conversationId: 'c1', command: 'model', success: false, message: hostileMessage },
+        ]}
+        approval={null}
+        pendingApproval={null}
+        hasConversation={false}
+        onExecute={vi.fn()}
+        onApprove={vi.fn()}
+        onRunApproved={vi.fn()}
+      />,
+    );
+
+    const text = container?.textContent ?? '';
+    expect(text.length).toBeLessThan(hostileMessage.length);
+  });
+
+  it('does not throw when the manifest fields are malformed (non-array commands/skills)', async () => {
+    const manifest = {
+      commands: 'not-an-array',
+      skills: null,
+      version: 1,
+    } as unknown as Parameters<typeof CommandsPanel>[0]['manifest'];
+
+    await expect(
+      render(
+        <CommandsPanel
+          manifest={manifest}
+          results={[]}
+          approval={null}
+          pendingApproval={null}
+          hasConversation={false}
+          onExecute={vi.fn()}
+          onApprove={vi.fn()}
+          onRunApproved={vi.fn()}
+        />,
+      ),
+    ).resolves.not.toThrow();
+  });
+});

apps/web/src/spa/chat/commands-panel.tsx

@@ -0,0 +1,164 @@
+import { useState, type ReactElement } from 'react';
+import type { PendingApproval } from './use-chat-connection';
+import { MAX_COMMAND_MESSAGE_CHARS } from './limits';
+import { asNonEmptyString, asString } from './runtime-guards';
+import type {
+  CommandManifest,
+  SlashCommandApprovalResultPayload,
+  SlashCommandResultPayload,
+} from '@/lib/chat-contract';
+
+/** Stable fallback copy shown for a failed command only when the server's
+ * own guarded, non-empty `message` (e.g. "Unknown model") is absent or
+ * malformed — the structured contract reason itself is otherwise shown
+ * directly, never a raw thrown exception, stack trace, or object value. */
+const COMMAND_FAILURE_COPY = 'Command failed.';
+
+/** Render-site defense-in-depth: `use-chat-connection.ts` already bounds a
+ * stored command:result message at ingestion, but this component must never
+ * assume every caller went through that path — bounding again here means a
+ * hostile/oversized message can never force an unbounded render. */
+function boundMessage(value: string): string {
+  return value.length > MAX_COMMAND_MESSAGE_CHARS
+    ? value.slice(0, MAX_COMMAND_MESSAGE_CHARS)
+    : value;
+}
+
+interface CommandsPanelProps {
+  manifest: CommandManifest | null;
+  results: SlashCommandResultPayload[];
+  approval: SlashCommandApprovalResultPayload | null;
+  pendingApproval: PendingApproval | null;
+  hasConversation: boolean;
+  onExecute: (input: { command: string; args?: string }) => void;
+  onApprove: (input: { command: string; args?: string }) => void;
+  onRunApproved: () => void;
+}
+
+export function CommandsPanel({
+  manifest,
+  results,
+  approval,
+  pendingApproval,
+  hasConversation,
+  onExecute,
+  onApprove,
+  onRunApproved,
+}: CommandsPanelProps): ReactElement {
+  const [command, setCommand] = useState('');
+  const [args, setArgs] = useState('');
+
+  // Defense-in-depth: the reducer already normalizes success/approvalId
+  // before storing `approval`, but a matching command string alone must
+  // never be trusted here either — require the literal boolean `true` and a
+  // non-empty string approvalId, not merely truthy values.
+  const canRunApproved =
+    approval?.success === true &&
+    typeof approval.approvalId === 'string' &&
+    approval.approvalId.length > 0 &&
+    !!pendingApproval &&
+    pendingApproval.command === approval.command;
+
+  // A manifest arrives from the server as untyped JSON at runtime — guard
+  // both collections before mapping so a malformed manifest cannot throw.
+  const commands = Array.isArray(manifest?.commands) ? manifest.commands : [];
+  const skills = Array.isArray(manifest?.skills) ? manifest.skills : [];
+
+  return (
+    <section aria-label="Commands" className="flex flex-col gap-2 border-b px-4 py-3 text-xs">
+      {commands.length > 0 ? (
+        <ul aria-label="Available commands" className="flex flex-col gap-1">
+          {commands.map((cmd, index) => (
+            <li key={asString(cmd?.name) || `cmd-${index}`}>
+              <strong>/{asString(cmd?.name)}</strong> — {asString(cmd?.description)}
+            </li>
+          ))}
+        </ul>
+      ) : null}
+
+      {skills.length > 0 ? (
+        <ul aria-label="Available skills" className="flex flex-col gap-1">
+          {skills.map((skill, index) => (
+            <li key={asString(skill?.name) || `skill-${index}`}>
+              <strong>/skill:{asString(skill?.name)}</strong> — {asString(skill?.description)}
+            </li>
+          ))}
+        </ul>
+      ) : null}
+
+      <div className="flex flex-wrap items-center gap-2">
+        <input
+          aria-label="Command name"
+          value={command}
+          onChange={(event) => setCommand(event.target.value)}
+          placeholder="command"
+        />
+        <input
+          aria-label="Command arguments"
+          value={args}
+          onChange={(event) => setArgs(event.target.value)}
+          placeholder="args (optional)"
+        />
+        <button
+          type="button"
+          disabled={!hasConversation || !command.trim()}
+          onClick={() => onExecute({ command: command.trim(), args: args.trim() || undefined })}
+        >
+          Run command
+        </button>
+        <button
+          type="button"
+          disabled={!hasConversation || !command.trim()}
+          onClick={() => onApprove({ command: command.trim(), args: args.trim() || undefined })}
+        >
+          Request approval
+        </button>
+      </div>
+
+      {approval ? (
+        <div role={approval.success ? 'status' : 'alert'} className="flex items-center gap-2">
+          {/* A successful approval shows stable client copy only — never
+              the server-controlled approval.message or echoed
+              approval.command as the primary confirmation. The frozen local
+              pendingApproval below (not this line) is the sole authoritative
+              statement of what will run. A denial, by contrast, is not an
+              execution authority and safely surfaces the guarded structured
+              reason the server gave (e.g. "Not authorized"), falling back to
+              a stable copy only when absent/malformed. */}
+          <span>
+            {approval.success ? 'Approved.' : asNonEmptyString(approval.message, 'Denied.')}
+          </span>
+          {canRunApproved && pendingApproval ? (
+            <>
+              {/* Authoritative frozen local command+args — what the click below
+                  will actually emit. The server's `approval` above is display-only
+                  and must never be trusted to represent the executed payload. */}
+              <span>
+                Will run: /{pendingApproval.command}{' '}
+                {pendingApproval.args ? pendingApproval.args : '(no args)'}
+              </span>
+              <button type="button" onClick={onRunApproved}>
+                Run approved command
+              </button>
+            </>
+          ) : null}
+        </div>
+      ) : null}
+
+      {results.length > 0 ? (
+        <ul aria-label="Command results" className="flex flex-col gap-1">
+          {results.map((result, index) => (
+            <li key={`${result.command}-${index}`} role={result.success ? 'status' : 'alert'}>
+              /{asString(result.command)}: {result.success ? 'success' : 'failed'}
+              {result.success
+                ? typeof result.message === 'string' && result.message
+                  ? ` — ${boundMessage(result.message)}`
+                  : ''
+                : ` — ${boundMessage(asNonEmptyString(result.message, COMMAND_FAILURE_COPY))}`}
+            </li>
+          ))}
+        </ul>
+      ) : null}
+    </section>
+  );
+}

apps/web/src/spa/chat/composer.tsx

@@ -0,0 +1,98 @@
+import { useState, type KeyboardEvent, type ReactElement } from 'react';
+
+interface ComposerProps {
+  onSend: (input: { content: string; provider?: string; modelId?: string }) => void;
+  onStop: () => void;
+  streaming: boolean;
+  /** True from local send time through server turn startup/ack and
+   * throughout streaming — a superset of `streaming` that also covers the
+   * pre-ack window where a second send could otherwise slip through. */
+  sending: boolean;
+  hasConversation: boolean;
+}
+
+export function Composer({
+  onSend,
+  onStop,
+  streaming,
+  sending,
+  hasConversation,
+}: ComposerProps): ReactElement {
+  const [content, setContent] = useState('');
+  const [provider, setProvider] = useState('');
+  const [modelId, setModelId] = useState('');
+  const busy = streaming || sending;
+
+  function submit(): void {
+    if (busy) return;
+    const trimmed = content.trim();
+    if (!trimmed) return;
+    onSend({
+      content: trimmed,
+      provider: provider.trim() || undefined,
+      modelId: modelId.trim() || undefined,
+    });
+    setContent('');
+  }
+
+  function handleKeyDown(event: KeyboardEvent<HTMLTextAreaElement>): void {
+    if (event.key === 'Enter' && !event.shiftKey) {
+      event.preventDefault();
+      submit();
+    }
+  }
+
+  return (
+    <form
+      onSubmit={(event) => {
+        event.preventDefault();
+        submit();
+      }}
+      className="flex flex-col gap-2 border-t p-4"
+    >
+      <div className="flex flex-wrap gap-2">
+        <input
+          aria-label="Provider"
+          value={provider}
+          onChange={(event) => setProvider(event.target.value)}
+          placeholder="Provider (optional)"
+          className="rounded border px-2 py-1 text-xs"
+        />
+        <input
+          aria-label="Model"
+          value={modelId}
+          onChange={(event) => setModelId(event.target.value)}
+          placeholder="Model (optional)"
+          className="rounded border px-2 py-1 text-xs"
+        />
+      </div>
+      <div className="flex items-end gap-2">
+        <textarea
+          aria-label="Message"
+          value={content}
+          onChange={(event) => setContent(event.target.value)}
+          onKeyDown={handleKeyDown}
+          rows={2}
+          placeholder="Message… (Enter to send, Shift+Enter for a new line)"
+          className="flex-1 resize-none rounded border px-3 py-2 text-sm"
+        />
+        <button
+          type="submit"
+          disabled={!content.trim() || busy}
+          className="rounded px-3 py-2 text-sm font-medium"
+        >
+          Send
+        </button>
+        <button
+          type="button"
+          aria-label="Stop"
+          disabled={!hasConversation || !streaming}
+          onClick={onStop}
+          className="rounded px-3 py-2 text-sm font-medium"
+        >
+          Stop
+        </button>
+      </div>
+    </form>
+  );
+}

apps/web/src/spa/chat/limits.ts

@@ -0,0 +1,22 @@
+/**
+ * Bounds on server-fed chat state. A hostile or malfunctioning gateway can
+ * flood any of these collections; caps keep memory/render cost flat instead
+ * of growing unboundedly for the lifetime of the connection.
+ */
+
+/** Max characters retained for the in-flight streamed text/thinking buffers. */
+export const MAX_STREAM_CHARS = 20_000;
+/** Max transcript turns retained (oldest dropped first). */
+export const MAX_MESSAGES = 500;
+/** Max tool-call entries (including anomaly entries) retained per turn history. */
+export const MAX_TOOLS = 200;
+/** Max slash-command results retained. */
+export const MAX_COMMAND_RESULTS = 200;
+/** Max commands/skills accepted from a single manifest push. */
+export const MAX_MANIFEST_ITEMS = 500;
+/** Max executed approval IDs remembered for single-flight dedup. */
+export const MAX_EXECUTED_APPROVAL_IDS = 200;
+/** Max characters retained for a single command:result message — a hostile
+ * or malfunctioning gateway must not be able to push an unbounded curated
+ * success/failure reason into state (or, defensively, onto the page). */
+export const MAX_COMMAND_MESSAGE_CHARS = 1_000;

apps/web/src/spa/chat/message-transcript.tsx

@@ -0,0 +1,39 @@
+import type { ReactElement } from 'react';
+import type { ChatTranscriptMessage } from './use-chat-connection';
+
+interface MessageTranscriptProps {
+  messages: ChatTranscriptMessage[];
+  streaming: boolean;
+  text: string;
+}
+
+export function MessageTranscript({
+  messages,
+  streaming,
+  text,
+}: MessageTranscriptProps): ReactElement {
+  return (
+    <div
+      role="log"
+      aria-live="polite"
+      aria-label="Conversation"
+      className="flex flex-1 flex-col gap-3 overflow-y-auto p-4"
+    >
+      {messages.map((message) => (
+        <div key={message.id} data-role={message.role} className="whitespace-pre-wrap text-sm">
+          <span className="font-medium">{message.role === 'user' ? 'You' : 'Assistant'}: </span>
+          <span>{message.text}</span>
+          {message.thinking ? (
+            <div className="pt-1 text-xs italic opacity-70">{message.thinking}</div>
+          ) : null}
+        </div>
+      ))}
+      {streaming ? (
+        <div data-role="assistant-streaming" className="whitespace-pre-wrap text-sm">
+          <span className="font-medium">Assistant: </span>
+          <span>{text || 'Thinking…'}</span>
+        </div>
+      ) : null}
+    </div>
+  );
+}

apps/web/src/spa/chat/runtime-guards.ts

@@ -0,0 +1,49 @@
+/**
+ * Socket.IO payloads are only statically typed at the call site — a
+ * misbehaving or compromised gateway can send anything at runtime. These
+ * guards protect the dereference sites that would otherwise throw (`.map` on
+ * a non-array, `.toFixed` on a non-number) or render an object as a React
+ * child.
+ */
+
+export function asString(value: unknown, fallback = ''): string {
+  return typeof value === 'string' ? value : fallback;
+}
+
+/** Like `asString`, but an empty string also falls back — used for guarded
+ * contract-provided reason strings (e.g. a denial or failure message) where
+ * an empty string is not a meaningful value to display in place of the
+ * stable fallback copy. */
+export function asNonEmptyString(value: unknown, fallback: string): string {
+  return typeof value === 'string' && value.length > 0 ? value : fallback;
+}
+
+export function asFiniteNumber(value: unknown, fallback = 0): number {
+  return typeof value === 'number' && Number.isFinite(value) ? value : fallback;
+}
+
+/** Like `asFiniteNumber`, but returns `null` on failure instead of a numeric
+ * fallback — callers that must not fabricate a plausible-looking value (e.g.
+ * `0 tokens` / `$0.0000` for genuinely unknown usage) use this to render an
+ * honest "unavailable" label instead. */
+export function asFiniteNumberOrNull(value: unknown): number | null {
+  return typeof value === 'number' && Number.isFinite(value) ? value : null;
+}
+
+export function asStringArray(value: unknown): string[] {
+  return Array.isArray(value) && value.every((item) => typeof item === 'string') ? value : [];
+}
+
+export function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === 'object' && value !== null;
+}
+
+/** The single point of truth for what counts as a valid conversation ID
+ * anywhere a scoped server event may adopt one into state — a non-empty
+ * string, nothing else. Every site that establishes or compares
+ * `state.conversationId` against a raw socket payload must route through
+ * this guard so a malformed first frame (null/object/number/empty string)
+ * can never be adopted verbatim. */
+export function asConversationId(value: unknown): string | null {
+  return typeof value === 'string' && value.length > 0 ? value : null;
+}

apps/web/src/spa/chat/session-panel.tsx

@@ -0,0 +1,68 @@
+import type { ReactElement } from 'react';
+import type { SessionInfoPayload } from '@/lib/chat-contract';
+import { MAX_MANIFEST_ITEMS } from './limits';
+import { asString, asStringArray } from './runtime-guards';
+
+interface SessionPanelProps {
+  sessionInfo: SessionInfoPayload | null;
+  onSetThinking: (level: string) => void;
+}
+
+const THINKING_LEVEL_UNAVAILABLE = '';
+
+export function SessionPanel({
+  sessionInfo,
+  onSetThinking,
+}: SessionPanelProps): ReactElement | null {
+  if (!sessionInfo) return null;
+
+  // The reducer already caps this before storing it, but the render site
+  // defends independently — a hostile payload must never be able to force
+  // this <select> to lay out an unbounded number of options.
+  const availableThinkingLevels = asStringArray(sessionInfo.availableThinkingLevels).slice(
+    0,
+    MAX_MANIFEST_ITEMS,
+  );
+  const hasThinkingLevels = availableThinkingLevels.length > 0;
+
+  return (
+    <section
+      aria-label="Session info"
+      className="flex flex-wrap items-center gap-3 border-b px-4 py-2 text-xs"
+    >
+      <span>{asString(sessionInfo.provider, 'unknown')}</span>
+      <span>{asString(sessionInfo.modelId, 'unknown')}</span>
+      <label className="flex items-center gap-2">
+        <span>Thinking level</span>
+        <select
+          aria-label="Thinking level"
+          value={
+            hasThinkingLevels ? asString(sessionInfo.thinkingLevel) : THINKING_LEVEL_UNAVAILABLE
+          }
+          onChange={(event) => {
+            // The placeholder option is not a real, settable level — a
+            // malformed availableThinkingLevels list must never let the
+            // client emit set:thinking for it.
+            if (!hasThinkingLevels) return;
+            onSetThinking(event.target.value);
+          }}
+        >
+          {hasThinkingLevels ? (
+            availableThinkingLevels.map((level) => (
+              <option key={level} value={level}>
+                {level}
+              </option>
+            ))
+          ) : (
+            <option value={THINKING_LEVEL_UNAVAILABLE}>Thinking level unavailable</option>
+          )}
+        </select>
+      </label>
+      {sessionInfo.routingDecision ? (
+        <span title={asString(sessionInfo.routingDecision.ruleName)}>
+          {asString(sessionInfo.routingDecision.reason)}
+        </span>
+      ) : null}
+    </section>
+  );
+}

apps/web/src/spa/chat/test-support/fake-chat-socket.ts

@@ -0,0 +1,125 @@
+import { vi } from 'vitest';
+import type { ClientToServerEvents, ServerToClientEvents } from '@/lib/chat-contract';
+
+type ServerEvent = keyof ServerToClientEvents;
+type ClientEvent = keyof ClientToServerEvents;
+type ServerHandler<K extends ServerEvent> = ServerToClientEvents[K];
+type ClientPayload<K extends ClientEvent> = Parameters<ClientToServerEvents[K]>[0];
+
+export interface EmittedEvent<K extends ClientEvent = ClientEvent> {
+  event: K;
+  payload: ClientPayload<K>;
+}
+
+/** The subset of a Socket.IO `ChatSocket` that `useChatConnection` drives. */
+export interface FakeChatSocket {
+  connected: boolean;
+  connect(): FakeChatSocket;
+  on<K extends ServerEvent>(event: K, handler: ServerHandler<K>): FakeChatSocket;
+  off<K extends ServerEvent>(event: K, handler: ServerHandler<K>): FakeChatSocket;
+  emit<K extends ClientEvent>(event: K, payload: ClientPayload<K>): FakeChatSocket;
+}
+
+/**
+ * A typed in-memory stand-in for `getSocket()`. Unlike a bare
+ * `(event: string, payload: unknown) => void` mock, every public method here is
+ * checked against the real `/chat` contract — a typo'd event name or a payload
+ * missing a required field fails to compile instead of silently no-op'ing at
+ * runtime.
+ */
+/** Socket.IO's built-in connection-state events. Not part of the app-level
+ * ServerToClientEvents contract, but real sockets always support them and
+ * `useChatConnection` registers a `disconnect` handler on the real socket. */
+type LifecycleEvent = 'connect' | 'disconnect';
+
+export function createFakeChatSocket(): {
+  socket: FakeChatSocket;
+  listeners: Map<ServerEvent, Set<(payload: never) => void>>;
+  emitted: EmittedEvent[];
+  serverEmit<K extends ServerEvent>(
+    event: K,
+    payload: Parameters<ServerToClientEvents[K]>[0],
+  ): void;
+  /** Escape hatch for malformed-payload tests: bypasses the compile-time
+   * payload contract to simulate a genuinely untrusted runtime value from the
+   * server, e.g. a `session:info` with a non-array `availableThinkingLevels`. */
+  serverEmitRaw(event: ServerEvent, payload: unknown): void;
+  /** Simulates a transient Socket.IO `disconnect` — fires any handler(s)
+   * registered via `socket.on('disconnect', ...)` without clearing any
+   * listeners, mirroring how a real reconnecting socket behaves. */
+  simulateDisconnect(): void;
+  /** Simulates socket.io-client's automatic reconnect of the *same*
+   * instance after a transient disconnect: marks the socket connected again
+   * and fires any handler(s) registered via `socket.on('connect', ...)`,
+   * without clearing or replacing any listeners. */
+  simulateReconnect(): void;
+} {
+  const listeners = new Map<ServerEvent, Set<(payload: never) => void>>();
+  const emitted: EmittedEvent[] = [];
+
+  // Internal storage is intentionally keyed loosely (the per-event handler shape
+  // varies by K, which a single Map can't express); the generic signatures on the
+  // exported `socket`/`serverEmit` above and below are what keep test call sites
+  // type-checked against ServerToClientEvents/ClientToServerEvents.
+  const socket = {
+    connected: false,
+    connect: vi.fn(function connect(this: void) {
+      socket.connected = true;
+      return socket;
+    }),
+    on: vi.fn(function on(this: void, event: ServerEvent, handler: (payload: never) => void) {
+      if (!listeners.has(event)) listeners.set(event, new Set());
+      listeners.get(event)?.add(handler);
+      return socket;
+    }),
+    off: vi.fn(function off(this: void, event: ServerEvent, handler: (payload: never) => void) {
+      listeners.get(event)?.delete(handler);
+      return socket;
+    }),
+    emit: vi.fn(function emit(this: void, event: ClientEvent, payload: unknown) {
+      emitted.push({ event, payload } as EmittedEvent);
+      return socket;
+    }),
+  } as unknown as FakeChatSocket;
+
+  function serverEmit<K extends ServerEvent>(
+    event: K,
+    payload: Parameters<ServerToClientEvents[K]>[0],
+  ): void {
+    for (const handler of listeners.get(event) ?? []) {
+      (handler as (payload: Parameters<ServerToClientEvents[K]>[0]) => void)(payload);
+    }
+  }
+
+  function serverEmitRaw(event: ServerEvent, payload: unknown): void {
+    for (const handler of listeners.get(event) ?? []) {
+      (handler as (payload: unknown) => void)(payload);
+    }
+  }
+
+  function simulateDisconnect(): void {
+    socket.connected = false;
+    const lifecycleKey = 'disconnect' satisfies LifecycleEvent as unknown as ServerEvent;
+    for (const handler of listeners.get(lifecycleKey) ?? []) {
+      (handler as () => void)();
+    }
+  }
+
+  function simulateReconnect(): void {
+    socket.connected = true;
+    const lifecycleKey = 'connect' satisfies LifecycleEvent as unknown as ServerEvent;
+    for (const handler of listeners.get(lifecycleKey) ?? []) {
+      (handler as () => void)();
+    }
+  }
+
+  return {
+    socket,
+    listeners,
+    emitted,
+    serverEmit,
+    serverEmitRaw,
+    simulateDisconnect,
+    simulateReconnect,
+  };
+}

apps/web/src/spa/chat/tool-call-list.spec.tsx

@@ -0,0 +1,63 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+import { ToolCallList } from './tool-call-list';
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+let root: Root | null;
+let container: HTMLElement | null;
+
+async function render(node: Parameters<Root['render']>[0]): Promise<void> {
+  container = document.createElement('div');
+  document.body.append(container);
+  root = createRoot(container);
+  await act(async () => {
+    root?.render(node);
+  });
+}
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+  root = null;
+  container = null;
+});
+
+describe('ToolCallList', () => {
+  it('renders two entries independently, without a duplicate-key warning, when a valid toolCallId is shared', async () => {
+    const consoleError = vi.spyOn(console, 'error').mockImplementation(() => {});
+
+    await render(
+      <ToolCallList
+        tools={[
+          { toolCallId: 'dup', toolName: 'search', status: 'success' },
+          { toolCallId: 'dup', toolName: 'search', status: 'running' },
+        ]}
+      />,
+    );
+
+    const items = [...(container?.querySelectorAll('li') ?? [])];
+    expect(items).toHaveLength(2);
+    expect(items[0]?.textContent).toContain('success');
+    expect(items[1]?.textContent).toContain('running');
+
+    const duplicateKeyWarning = consoleError.mock.calls.some((args) =>
+      args.some((arg) => typeof arg === 'string' && arg.includes('same key')),
+    );
+    expect(duplicateKeyWarning).toBe(false);
+
+    consoleError.mockRestore();
+  });
+});

apps/web/src/spa/chat/tool-call-list.tsx

@@ -0,0 +1,24 @@
+import type { ReactElement } from 'react';
+import type { ToolCallState } from './use-chat-connection';
+
+export function ToolCallList({ tools }: { tools: ToolCallState[] }): ReactElement | null {
+  if (tools.length === 0) return null;
+
+  return (
+    <ul aria-label="Tool calls" className="flex flex-col gap-1 px-4 pb-2 text-xs">
+      {tools.map((tool, index) => (
+        <li
+          // A valid server-controlled toolCallId can legitimately repeat
+          // (e.g. two tool:start events sharing one id) — keying on it alone
+          // would give React two identical keys. Pairing it with its
+          // (stable, append-only) render index keeps every key unique.
+          key={`${tool.toolCallId}-${index}`}
+          role={tool.status === 'error' || tool.status === 'anomaly' ? 'alert' : 'status'}
+        >
+          {tool.toolName} —{' '}
+          {tool.status === 'anomaly' ? 'unexpected end (unknown tool call)' : tool.status}
+        </li>
+      ))}
+    </ul>
+  );
+}

apps/web/src/spa/guards.spec.tsx

@@ -0,0 +1,135 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { createMemoryRouter, RouterProvider, type RouteObject } from 'react-router-dom';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+
+const { useSessionMock } = vi.hoisted(() => ({
+  useSessionMock: vi.fn(),
+}));
+
+vi.mock('@/lib/auth-client', () => ({
+  useSession: useSessionMock,
+}));
+
+import { AuthGuard, GuestGuard } from './guards';
+
+interface RenderedRouter {
+  container: HTMLDivElement;
+  router: ReturnType<typeof createMemoryRouter>;
+}
+
+const mountedRoots: Root[] = [];
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+async function renderRouter(
+  routeObjects: RouteObject[],
+  initialEntry: string,
+): Promise<RenderedRouter> {
+  const container = document.createElement('div');
+  document.body.append(container);
+  const router = createMemoryRouter(routeObjects, { initialEntries: [initialEntry] });
+  const root = createRoot(container);
+  mountedRoots.push(root);
+
+  await act(async () => {
+    root.render(<RouterProvider router={router} />);
+  });
+
+  return { container, router };
+}
+
+afterEach(async () => {
+  for (const root of mountedRoots.splice(0)) {
+    await act(async () => {
+      root.unmount();
+    });
+  }
+  document.body.replaceChildren();
+  useSessionMock.mockReset();
+});
+
+const guestRoutes: RouteObject[] = [
+  {
+    path: '/login',
+    element: <GuestGuard />,
+    children: [{ index: true, element: <p>Guest page</p> }],
+  },
+  { path: '/chat', element: <p>Chat page</p> },
+];
+
+const authenticatedRoutes: RouteObject[] = [
+  {
+    path: '/chat',
+    element: <AuthGuard />,
+    children: [{ index: true, element: <p>Private page</p> }],
+  },
+  { path: '/login', element: <p>Login page</p> },
+];
+
+describe('GuestGuard', () => {
+  it('renders the guest outlet while session lookup is pending', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: true });
+
+    const view = await renderRouter(guestRoutes, '/login');
+
+    expect(view.container.textContent).toContain('Guest page');
+    expect(view.router.state.location.pathname).toBe('/login');
+  });
+
+  it('renders the guest outlet when no session exists', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: false });
+
+    const view = await renderRouter(guestRoutes, '/login');
+
+    expect(view.container.textContent).toContain('Guest page');
+    expect(view.router.state.location.pathname).toBe('/login');
+  });
+
+  it('redirects an authenticated session to chat', async () => {
+    useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
+
+    const view = await renderRouter(guestRoutes, '/login');
+
+    expect(view.container.textContent).toContain('Chat page');
+    expect(view.router.state.location.pathname).toBe('/chat');
+  });
+});
+
+describe('AuthGuard', () => {
+  it('renders the existing loading treatment while session lookup is pending', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: true });
+
+    const view = await renderRouter(authenticatedRoutes, '/chat');
+
+    expect(view.container.textContent).toContain('Loading...');
+    expect(view.router.state.location.pathname).toBe('/chat');
+  });
+
+  it('redirects an unauthenticated visitor to login', async () => {
+    useSessionMock.mockReturnValue({ data: null, isPending: false });
+
+    const view = await renderRouter(authenticatedRoutes, '/chat');
+
+    expect(view.container.textContent).toContain('Login page');
+    expect(view.router.state.location.pathname).toBe('/login');
+  });
+
+  it('renders the authenticated outlet when a session exists', async () => {
+    useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
+
+    const view = await renderRouter(authenticatedRoutes, '/chat');
+
+    expect(view.container.textContent).toContain('Private page');
+    expect(view.router.state.location.pathname).toBe('/chat');
+  });
+});

apps/web/src/spa/guards.tsx

@@ -0,0 +1,23 @@
+import type { ReactElement } from 'react';
+import { Navigate, Outlet } from 'react-router-dom';
+import { useSession } from '@/lib/auth-client';
+
+export function GuestGuard(): ReactElement {
+  const { data: session } = useSession();
+
+  return session ? <Navigate to="/chat" replace /> : <Outlet />;
+}
+
+export function AuthGuard(): ReactElement {
+  const { data: session, isPending } = useSession();
+
+  if (isPending) {
+    return (
+      <div className="flex min-h-screen items-center justify-center">
+        <div className="text-sm text-text-muted">Loading...</div>
+      </div>
+    );
+  }
+
+  return session ? <Outlet /> : <Navigate to="/login" replace />;
+}

apps/web/src/spa/pages/chat-error-boundary.spec.tsx

@@ -0,0 +1,87 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { createMemoryRouter, RouterProvider, type RouteObject } from 'react-router-dom';
+import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
+
+const { useSessionMock } = vi.hoisted(() => ({
+  useSessionMock: vi.fn(),
+}));
+
+vi.mock('@/lib/auth-client', () => ({
+  useSession: useSessionMock,
+}));
+
+import { routes } from '@/routes';
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+function Boom(): never {
+  throw new Error('render blew up');
+}
+
+/** Recursively clones the real exported route table, replacing only the
+ * `/chat` route's `element` with `<Boom />` — every other route (including
+ * the real `AuthGuard` nesting and the real `/chat` `errorElement`) is left
+ * exactly as exported. This is what makes the test fail if a future change
+ * removes the real route's `errorElement`, unlike a hand-built independent
+ * route tree that could drift from production undetected. */
+function replaceChatElementWithBoom(nodes: RouteObject[]): RouteObject[] {
+  return nodes.map((node) => {
+    const cloned: RouteObject = { ...node };
+    if (cloned.path === '/chat') {
+      cloned.element = <Boom />;
+    }
+    if (cloned.children) {
+      cloned.children = replaceChatElementWithBoom(cloned.children);
+    }
+    return cloned;
+  });
+}
+
+let root: Root | null;
+let container: HTMLElement;
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+  root = null;
+  useSessionMock.mockReset();
+});
+
+describe('ChatRouteErrorBoundary', () => {
+  it('renders a recoverable, non-blank fallback when the /chat route element throws during render', async () => {
+    useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
+
+    const routeObjects = replaceChatElementWithBoom(routes);
+    const router = createMemoryRouter(routeObjects, { initialEntries: ['/chat'] });
+
+    container = document.createElement('div');
+    document.body.append(container);
+    root = createRoot(container);
+
+    const consoleErrorSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
+    try {
+      await act(async () => {
+        root?.render(<RouterProvider router={router} />);
+      });
+
+      expect(consoleErrorSpy).toHaveBeenCalled();
+    } finally {
+      consoleErrorSpy.mockRestore();
+    }
+
+    expect(container.textContent).not.toBe('');
+    expect(container.querySelector('[role="alert"]')).toBeTruthy();
+  });
+});

apps/web/src/spa/pages/chat-error-boundary.tsx

@@ -0,0 +1,22 @@
+import type { ReactElement } from 'react';
+import { useRouteError } from 'react-router-dom';
+
+/**
+ * `/chat` renders live, server-driven state (streamed text, tool calls,
+ * manifests) that can carry malformed payloads no compile-time contract can
+ * fully rule out at every dereference site. This is the last line of
+ * defense: if something still throws during render, show a recoverable
+ * alert instead of leaving the user on a blank/white screen.
+ */
+export function ChatRouteErrorBoundary(): ReactElement {
+  useRouteError();
+
+  return (
+    <div role="alert" className="flex min-h-screen flex-col items-center justify-center gap-3 p-8">
+      <p className="text-sm font-medium">Something went wrong loading chat.</p>
+      <a href="/chat" className="text-sm underline">
+        Reload chat
+      </a>
+    </div>
+  );
+}

apps/web/src/spa/pages/chat.spec.tsx

@@ -0,0 +1,636 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
+import { createFakeChatSocket } from '@/spa/chat/test-support/fake-chat-socket';
+import { MAX_MANIFEST_ITEMS } from '@/spa/chat/limits';
+
+const { getSocketMock, destroySocketMock } = vi.hoisted(() => ({
+  getSocketMock: vi.fn(),
+  destroySocketMock: vi.fn(),
+}));
+
+vi.mock('@/lib/socket', () => ({
+  getSocket: getSocketMock,
+  destroySocket: destroySocketMock,
+}));
+
+import { ChatPage } from './chat';
+
+function setValue(el: HTMLInputElement | HTMLTextAreaElement, value: string): void {
+  const proto =
+    el instanceof HTMLTextAreaElement ? HTMLTextAreaElement.prototype : HTMLInputElement.prototype;
+  const setter = Object.getOwnPropertyDescriptor(proto, 'value')?.set;
+  setter?.call(el, value);
+  el.dispatchEvent(new Event('input', { bubbles: true }));
+}
+
+function selectValue(el: HTMLSelectElement, value: string): void {
+  const setter = Object.getOwnPropertyDescriptor(HTMLSelectElement.prototype, 'value')?.set;
+  setter?.call(el, value);
+  el.dispatchEvent(new Event('change', { bubbles: true }));
+}
+
+function findButton(container: HTMLElement, text: string): HTMLButtonElement {
+  const button = [...container.querySelectorAll('button')].find((candidate) =>
+    candidate.textContent?.includes(text),
+  );
+  if (!button) throw new Error(`Button with text "${text}" not found`);
+  return button;
+}
+
+let fake: ReturnType<typeof createFakeChatSocket>;
+let root: Root | null;
+let container: HTMLElement;
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+beforeEach(async () => {
+  fake = createFakeChatSocket();
+  getSocketMock.mockReset().mockReturnValue(fake.socket);
+  destroySocketMock.mockReset();
+  container = document.createElement('div');
+  document.body.append(container);
+  root = createRoot(container);
+  await act(async () => {
+    root?.render(<ChatPage />);
+  });
+});
+
+afterEach(async () => {
+  await act(async () => {
+    root?.unmount();
+  });
+  document.body.replaceChildren();
+});
+
+describe('ChatPage', () => {
+  it('streams agent:text and agent:thinking, shows tool status, and finalizes on agent:end with usage', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+    });
+    await act(async () => {
+      fake.serverEmit('agent:thinking', { conversationId: 'c1', text: 'pondering…' });
+      fake.serverEmit('agent:text', { conversationId: 'c1', text: 'Hel' });
+      fake.serverEmit('agent:text', { conversationId: 'c1', text: 'lo!' });
+      fake.serverEmit('agent:tool:start', {
+        conversationId: 'c1',
+        toolCallId: 't1',
+        toolName: 'web_search',
+      });
+    });
+
+    expect(container.textContent).toContain('pondering…');
+    expect(container.textContent).toContain('Hello!');
+    expect(container.textContent).toContain('web_search');
+    expect(container.textContent).toMatch(/running/i);
+
+    await act(async () => {
+      fake.serverEmit('agent:tool:end', {
+        conversationId: 'c1',
+        toolCallId: 't1',
+        toolName: 'web_search',
+        isError: false,
+      });
+      fake.serverEmit('agent:end', {
+        conversationId: 'c1',
+        usage: {
+          provider: 'anthropic',
+          modelId: 'claude',
+          thinkingLevel: 'medium',
+          tokens: { input: 12, output: 34, cacheRead: 0, cacheWrite: 0, total: 46 },
+          cost: 0.02,
+          context: { percent: 3, window: 200000 },
+        },
+      });
+    });
+
+    expect(container.textContent).toMatch(/success/i);
+    expect(container.textContent).toContain('Hello!');
+    expect(container.textContent).toMatch(/46/);
+  });
+
+  it('renders the commands manifest and session info, and lets the user pick a thinking level', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('commands:manifest', {
+        manifest: {
+          commands: [
+            {
+              name: 'model',
+              aliases: ['m'],
+              description: 'Change the active model',
+              scope: 'core',
+              execution: 'socket',
+              available: true,
+            },
+          ],
+          skills: [],
+          version: 1,
+        },
+      });
+      fake.serverEmit('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'medium',
+        availableThinkingLevels: ['low', 'medium', 'high'],
+        routingDecision: {
+          model: 'claude',
+          provider: 'anthropic',
+          ruleName: 'default',
+          reason: 'default routing',
+        },
+      });
+    });
+
+    expect(container.textContent).toContain('model');
+    expect(container.textContent).toContain('Change the active model');
+    expect(container.textContent).toContain('anthropic');
+    expect(container.textContent).toContain('default routing');
+
+    const select = container.querySelector(
+      'select[aria-label="Thinking level"]',
+    ) as HTMLSelectElement;
+    expect(select).toBeTruthy();
+    expect([...select.options].map((o) => o.value)).toEqual(['low', 'medium', 'high']);
+
+    await act(async () => {
+      selectValue(select, 'high');
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'set:thinking',
+      payload: { conversationId: 'c1', level: 'high' },
+    });
+  });
+
+  it('executes and approves commands with exact payloads and surfaces the approval affordance', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    const commandInput = container.querySelector(
+      'input[aria-label="Command name"]',
+    ) as HTMLInputElement;
+    const argsInput = container.querySelector(
+      'input[aria-label="Command arguments"]',
+    ) as HTMLInputElement;
+
+    await act(async () => {
+      setValue(commandInput, 'model');
+      setValue(argsInput, 'gpt-5');
+    });
+    await act(async () => {
+      findButton(container, 'Run command').click();
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'command:execute',
+      payload: { conversationId: 'c1', command: 'model', args: 'gpt-5' },
+    });
+
+    await act(async () => {
+      setValue(commandInput, 'deploy');
+      setValue(argsInput, 'prod');
+    });
+    await act(async () => {
+      findButton(container, 'Request approval').click();
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'command:approve',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod' },
+    });
+
+    await act(async () => {
+      fake.serverEmit('command:approval', {
+        conversationId: 'c1',
+        command: 'deploy',
+        success: true,
+        approvalId: 'ap1',
+        expiresAt: '2026-01-01T00:00:00.000Z',
+      });
+    });
+
+    expect(container.textContent).toMatch(/approved/i);
+
+    await act(async () => {
+      findButton(container, 'Run approved command').click();
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'command:execute',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod', approvalId: 'ap1' },
+    });
+  });
+
+  it('shows visible alert surfaces for a server error and the structured contract reason for a failed command result', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('error', { conversationId: 'c1', error: 'The model is unavailable' });
+      fake.serverEmit('command:result', {
+        conversationId: 'c1',
+        command: 'model',
+        success: false,
+        message: 'Unknown model',
+      });
+    });
+
+    const alerts = [...container.querySelectorAll('[role="alert"]')];
+    const alertText = alerts.map((node) => node.textContent).join(' ');
+    expect(alertText).toContain('The model is unavailable');
+    // The structured, contract-provided denial reason is visibly rendered.
+    expect(alertText).toContain('Unknown model');
+  });
+
+  it('falls back to a stable "Command failed." copy when a failed command result has no usable message', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmitRaw('command:result', {
+        conversationId: 'c1',
+        command: 'model',
+        success: false,
+        message: { bad: 'object' },
+      });
+    });
+
+    const alerts = [...container.querySelectorAll('[role="alert"]')];
+    const alertText = alerts.map((node) => node.textContent).join(' ');
+    expect(alertText).toContain('Command failed.');
+  });
+
+  it('caps availableThinkingLevels before storing and rendering a hostile session payload', async () => {
+    const hostileLevels = Array.from({ length: MAX_MANIFEST_ITEMS + 50 }, (_, i) => `level-${i}`);
+
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'level-0',
+        availableThinkingLevels: hostileLevels,
+      });
+    });
+
+    const select = container.querySelector(
+      'select[aria-label="Thinking level"]',
+    ) as HTMLSelectElement;
+    expect(select).toBeTruthy();
+    expect(select.options.length).toBeLessThanOrEqual(MAX_MANIFEST_ITEMS);
+  });
+
+  it('renders a safe fallback when session:info arrives with a malformed (non-array) availableThinkingLevels, without throwing', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmitRaw('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'medium',
+        availableThinkingLevels: null,
+      });
+    });
+
+    expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
+    const select = container.querySelector(
+      'select[aria-label="Thinking level"]',
+    ) as HTMLSelectElement;
+    expect(select).toBeTruthy();
+    // A malformed level list still shows a visible, safe placeholder option
+    // rather than a silently empty select.
+    expect([...select.options]).toHaveLength(1);
+    expect(select.options[0]?.textContent).toMatch(/unavailable/i);
+
+    await act(async () => {
+      selectValue(select, '');
+    });
+    expect(fake.emitted.filter((e) => e.event === 'set:thinking')).toHaveLength(0);
+  });
+
+  it('renders honest unavailable labels — not fabricated zeros — when agent:end usage has malformed/missing numeric fields', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+      fake.serverEmitRaw('agent:end', {
+        conversationId: 'c1',
+        usage: {
+          provider: { nested: 'object' },
+          modelId: undefined,
+          thinkingLevel: 'medium',
+          tokens: { total: 'not-a-number' },
+          cost: undefined,
+          context: { percent: null, window: 200000 },
+        },
+      });
+    });
+
+    const usage = container.querySelector('[aria-label="Usage"]');
+    expect(usage).toBeTruthy();
+    expect(usage?.textContent).toContain('tokens unavailable');
+    expect(usage?.textContent).toContain('cost unavailable');
+    expect(usage?.textContent).not.toContain('0 tokens');
+    expect(usage?.textContent).not.toContain('$0.0000');
+    expect(usage?.textContent).toContain('unknown/unknown');
+  });
+
+  it('renders a safe fallback for message:ack when messageId is a malformed non-string value, without throwing', async () => {
+    await expect(
+      act(async () => {
+        fake.serverEmitRaw('message:ack', { conversationId: 'c1', messageId: { bad: 'object' } });
+      }),
+    ).resolves.not.toThrow();
+
+    const status = [...container.querySelectorAll('[role="status"]')].find((node) =>
+      node.textContent?.includes('Message accepted'),
+    );
+    expect(status).toBeTruthy();
+    // A malformed messageId gets a stable, visible fallback — never blank,
+    // never the raw object.
+    expect(status?.textContent).toContain('unknown');
+  });
+
+  it('renders safely and does not throw when system:reload.message is a malformed non-string value', async () => {
+    await expect(
+      act(async () => {
+        fake.serverEmitRaw('system:reload', {
+          commands: [],
+          skills: [],
+          providers: [],
+          message: { bad: 'object' },
+        });
+      }),
+    ).resolves.not.toThrow();
+
+    const status = container.querySelector('[role="status"]');
+    expect(status).toBeTruthy();
+    // A malformed reload message renders a stable, visible fallback rather
+    // than a silently empty status line.
+    expect(status?.textContent).toContain('Commands reloaded.');
+  });
+
+  it('renders safely and does not throw when a scoped error carries a malformed non-string error value', async () => {
+    await expect(
+      act(async () => {
+        fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+        fake.serverEmitRaw('error', { conversationId: 'c1', error: ['not', 'a', 'string'] });
+      }),
+    ).resolves.not.toThrow();
+
+    expect(container.querySelector('[role="alert"]')).toBeTruthy();
+  });
+
+  it('sends a message with optional provider/model fields and emits abort from the Stop control', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+    const providerInput = container.querySelector(
+      'input[aria-label="Provider"]',
+    ) as HTMLInputElement;
+    const modelInput = container.querySelector('input[aria-label="Model"]') as HTMLInputElement;
+
+    const stopButtonBefore = container.querySelector(
+      'button[aria-label="Stop"]',
+    ) as HTMLButtonElement;
+    expect(stopButtonBefore.disabled).toBe(true);
+
+    await act(async () => {
+      setValue(textarea, 'hello there');
+      setValue(providerInput, 'anthropic');
+      setValue(modelInput, 'claude');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+
+    expect(fake.emitted).toContainEqual({
+      event: 'message',
+      payload: {
+        conversationId: undefined,
+        content: 'hello there',
+        provider: 'anthropic',
+        modelId: 'claude',
+      },
+    });
+    expect(container.textContent).toContain('hello there');
+
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+    });
+
+    const stopButtonDuring = container.querySelector(
+      'button[aria-label="Stop"]',
+    ) as HTMLButtonElement;
+    expect(stopButtonDuring.disabled).toBe(false);
+
+    await act(async () => {
+      stopButtonDuring.click();
+    });
+
+    expect(fake.emitted).toContainEqual({ event: 'abort', payload: { conversationId: 'c1' } });
+  });
+
+  it('renders the session panel from a pre-ack session:info and keeps it visible after the later ack', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+
+    await act(async () => {
+      setValue(textarea, 'hello');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+    await act(async () => {
+      fake.serverEmit('session:info', {
+        conversationId: 'c1',
+        provider: 'anthropic',
+        modelId: 'claude',
+        thinkingLevel: 'medium',
+        availableThinkingLevels: ['low', 'medium', 'high'],
+      });
+    });
+
+    expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
+    expect(container.textContent).toContain('anthropic');
+
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
+    expect(container.textContent).toContain('anthropic');
+  });
+
+  it('surfaces a pre-ack error as an alert without leaving the Stop control stuck active', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+
+    await act(async () => {
+      setValue(textarea, 'hello');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+    await act(async () => {
+      fake.serverEmit('error', {
+        conversationId: 'c1',
+        error: 'Failed to start agent session. Please try again.',
+      });
+    });
+
+    const alerts = [...container.querySelectorAll('[role="alert"]')];
+    expect(alerts.some((node) => node.textContent?.includes('Failed to start agent session'))).toBe(
+      true,
+    );
+
+    const stopButton = container.querySelector('button[aria-label="Stop"]') as HTMLButtonElement;
+    expect(stopButton.disabled).toBe(true);
+  });
+
+  it('shows an accessible status once the message is acknowledged', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    const statuses = [...container.querySelectorAll('[role="status"]')];
+    expect(statuses.some((node) => node.textContent?.includes('m1'))).toBe(true);
+  });
+
+  it('renders finalized thinking text in the transcript after agent:end, not only while streaming', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+      fake.serverEmit('agent:thinking', { conversationId: 'c1', text: 'reasoning about it' });
+      fake.serverEmit('agent:text', { conversationId: 'c1', text: 'Done.' });
+    });
+
+    expect(container.textContent).toContain('reasoning about it');
+
+    await act(async () => {
+      fake.serverEmit('agent:end', { conversationId: 'c1' });
+    });
+
+    expect(container.textContent).toContain('reasoning about it');
+    expect(container.textContent).toContain('Done.');
+  });
+
+  it('ignores a concurrent approval request and only executes the approved command once', async () => {
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+    });
+
+    const commandInput = container.querySelector(
+      'input[aria-label="Command name"]',
+    ) as HTMLInputElement;
+    const argsInput = container.querySelector(
+      'input[aria-label="Command arguments"]',
+    ) as HTMLInputElement;
+
+    await act(async () => {
+      setValue(commandInput, 'deploy');
+      setValue(argsInput, 'prod');
+    });
+    await act(async () => {
+      findButton(container, 'Request approval').click();
+    });
+    await act(async () => {
+      setValue(argsInput, 'staging');
+    });
+    await act(async () => {
+      findButton(container, 'Request approval').click();
+    });
+
+    expect(fake.emitted.filter((e) => e.event === 'command:approve')).toHaveLength(1);
+    expect(fake.emitted).toContainEqual({
+      event: 'command:approve',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod' },
+    });
+
+    await act(async () => {
+      fake.serverEmit('command:approval', {
+        conversationId: 'c1',
+        command: 'deploy',
+        success: true,
+        approvalId: 'ap1',
+        expiresAt: '2026-01-01T00:00:00.000Z',
+      });
+    });
+
+    await act(async () => {
+      findButton(container, 'Run approved command').click();
+      findButton(container, 'Run approved command').click();
+    });
+
+    expect(fake.emitted.filter((e) => e.event === 'command:execute')).toHaveLength(1);
+    expect(fake.emitted).toContainEqual({
+      event: 'command:execute',
+      payload: { conversationId: 'c1', command: 'deploy', args: 'prod', approvalId: 'ap1' },
+    });
+  });
+
+  it('disables sending a second message while a turn is streaming', async () => {
+    const textarea = container.querySelector(
+      'textarea[aria-label="Message"]',
+    ) as HTMLTextAreaElement;
+
+    await act(async () => {
+      setValue(textarea, 'first');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+    await act(async () => {
+      fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
+      fake.serverEmit('agent:start', { conversationId: 'c1' });
+    });
+
+    const sendButton = findButton(container, 'Send');
+    expect(sendButton.disabled).toBe(true);
+
+    await act(async () => {
+      setValue(textarea, 'second');
+    });
+    await act(async () => {
+      textarea.dispatchEvent(
+        new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
+      );
+    });
+
+    expect(fake.emitted.filter((e) => e.event === 'message')).toHaveLength(1);
+  });
+
+  it('removes socket handlers and tears down the socket on unmount, with no network calls', async () => {
+    expect(fake.listeners.size).toBeGreaterThan(0);
+
+    await act(async () => {
+      root?.unmount();
+    });
+    root = null;
+
+    for (const [, handlers] of fake.listeners) {
+      expect(handlers.size).toBe(0);
+    }
+    expect(destroySocketMock).toHaveBeenCalledOnce();
+  });
+});

apps/web/src/spa/pages/chat.tsx

@@ -0,0 +1,92 @@
+import type { ReactElement } from 'react';
+import { CommandsPanel } from '@/spa/chat/commands-panel';
+import { Composer } from '@/spa/chat/composer';
+import { MessageTranscript } from '@/spa/chat/message-transcript';
+import { asFiniteNumberOrNull, asString } from '@/spa/chat/runtime-guards';
+import { SessionPanel } from '@/spa/chat/session-panel';
+import { ToolCallList } from '@/spa/chat/tool-call-list';
+import { useChatConnection } from '@/spa/chat/use-chat-connection';
+
+/** Renders a real value normally, but an honest "unavailable" label instead
+ * of a fabricated `0` for a missing/malformed count — a real `0 tokens` and
+ * an unknown token count must never look the same. */
+function formatTokens(value: unknown): string {
+  const tokens = asFiniteNumberOrNull(value);
+  return tokens === null ? 'tokens unavailable' : `${tokens} tokens`;
+}
+
+/** Same honesty guarantee as `formatTokens`, for cost. */
+function formatCost(value: unknown): string {
+  const cost = asFiniteNumberOrNull(value);
+  return cost === null ? 'cost unavailable' : `$${cost.toFixed(4)}`;
+}
+
+export function ChatPage(): ReactElement {
+  const { state, actions } = useChatConnection();
+  const hasConversation = state.conversationId !== null;
+
+  return (
+    <div className="flex h-[calc(100vh-3.5rem)] min-h-0 flex-col overflow-hidden md:h-screen">
+      <header className="border-b px-4 py-3">
+        <h1 className="text-lg font-semibold">Chat</h1>
+      </header>
+
+      {state.systemReload ? (
+        <div role="status" className="border-b px-4 py-2 text-sm">
+          {asString(state.systemReload.message)}
+        </div>
+      ) : null}
+
+      {state.error ? (
+        <div role="alert" className="border-b px-4 py-2 text-sm">
+          {asString(state.error)}
+        </div>
+      ) : null}
+
+      {state.ack ? (
+        <div role="status" className="border-b px-4 py-1 text-xs opacity-70">
+          Message accepted · conversation {asString(state.ack.conversationId, 'unknown')} · id{' '}
+          {asString(state.ack.messageId, 'unknown')}
+        </div>
+      ) : null}
+
+      <SessionPanel sessionInfo={state.sessionInfo} onSetThinking={actions.setThinking} />
+
+      <MessageTranscript messages={state.messages} streaming={state.streaming} text={state.text} />
+
+      {state.thinking ? (
+        <section aria-label="Thinking" className="px-4 pb-2 text-xs italic opacity-80">
+          {state.thinking}
+        </section>
+      ) : null}
+
+      <ToolCallList tools={state.tools} />
+
+      {state.usage ? (
+        <div aria-label="Usage" className="px-4 pb-2 text-xs opacity-80">
+          {formatTokens(state.usage.tokens?.total)} · {formatCost(state.usage.cost)} ·{' '}
+          {asString(state.usage.provider, 'unknown')}/{asString(state.usage.modelId, 'unknown')}
+        </div>
+      ) : null}
+
+      <CommandsPanel
+        manifest={state.manifest}
+        results={state.commandResults}
+        approval={state.approval}
+        pendingApproval={state.pendingApproval}
+        hasConversation={hasConversation}
+        onExecute={actions.executeCommand}
+        onApprove={actions.approveCommand}
+        onRunApproved={actions.runApprovedCommand}
+      />
+
+      <Composer
+        onSend={actions.sendMessage}
+        onStop={actions.abort}
+        streaming={state.streaming}
+        sending={state.sending}
+        hasConversation={hasConversation}
+      />
+    </div>
+  );
+}

apps/web/src/spa/pages/login.tsx

@@ -0,0 +1,152 @@
+import { useEffect, useState, type FormEvent, type ReactElement } from 'react';
+import { Link, useNavigate } from 'react-router-dom';
+import { SsoProviderButtons } from '@/components/auth/sso-provider-buttons';
+import { api } from '@/lib/api';
+import { authClient, signIn } from '@/lib/auth-client';
+import type { SsoProviderDiscovery } from '@/lib/sso';
+
+export function LoginPage(): ReactElement {
+  const navigate = useNavigate();
+  const [error, setError] = useState<string | null>(null);
+  const [loading, setLoading] = useState(false);
+  const [ssoProviders, setSsoProviders] = useState<SsoProviderDiscovery[]>([]);
+  const [ssoLoadingProviderId, setSsoLoadingProviderId] = useState<
+    SsoProviderDiscovery['id'] | null
+  >(null);
+
+  useEffect(() => {
+    let active = true;
+
+    void api<SsoProviderDiscovery[]>('/api/sso/providers').then(
+      (providers) => {
+        if (active) setSsoProviders(providers.filter((provider) => provider.configured));
+      },
+      () => {
+        if (active) setSsoProviders([]);
+      },
+    );
+
+    return () => {
+      active = false;
+    };
+  }, []);
+
+  async function handleSubmit(event: FormEvent<HTMLFormElement>): Promise<void> {
+    event.preventDefault();
+    setError(null);
+    setLoading(true);
+
+    const form = new FormData(event.currentTarget);
+    const email = String(form.get('email') ?? '');
+    const password = String(form.get('password') ?? '');
+
+    try {
+      const result = await signIn.email({ email, password });
+
+      if (result.error) {
+        setError(result.error.message ?? 'Sign in failed');
+        return;
+      }
+
+      navigate('/chat', { replace: true });
+    } catch (caught: unknown) {
+      setError(caught instanceof Error ? caught.message : 'Sign in failed');
+    } finally {
+      setLoading(false);
+    }
+  }
+
+  async function handleSsoSignIn(providerId: SsoProviderDiscovery['id']): Promise<void> {
+    setError(null);
+    setSsoLoadingProviderId(providerId);
+
+    try {
+      const result = await authClient.signIn.oauth2({
+        providerId,
+        callbackURL: '/chat',
+        newUserCallbackURL: '/chat',
+      });
+
+      if (result.error) {
+        setError(result.error.message ?? `Sign in with ${providerId} failed`);
+        setSsoLoadingProviderId(null);
+      }
+    } catch (caught: unknown) {
+      setError(caught instanceof Error ? caught.message : `Sign in with ${providerId} failed`);
+      setSsoLoadingProviderId(null);
+    }
+  }
+
+  return (
+    <div>
+      <h1 className="text-2xl font-semibold">Sign in</h1>
+      <p className="mt-1 text-sm text-text-secondary">Sign in to your Mosaic account</p>
+
+      {error ? (
+        <div
+          role="alert"
+          className="mt-4 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
+          {error}
+        </div>
+      ) : null}
+
+      <form className="mt-6 space-y-4" onSubmit={handleSubmit}>
+        <div>
+          <label htmlFor="email" className="block text-sm font-medium text-text-secondary">
+            Email
+          </label>
+          <input
+            id="email"
+            name="email"
+            type="email"
+            autoComplete="email"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="[email protected]"
+          />
+        </div>
+
+        <div>
+          <label htmlFor="password" className="block text-sm font-medium text-text-secondary">
+            Password
+          </label>
+          <input
+            id="password"
+            name="password"
+            type="password"
+            autoComplete="current-password"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="••••••••"
+          />
+        </div>
+
+        <button
+          type="submit"
+          disabled={loading}
+          className="w-full rounded-lg bg-blue-600 px-4 py-2.5 text-sm font-medium text-white transition-colors hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 focus:ring-offset-surface-card disabled:opacity-50"
+        >
+          {loading ? 'Signing in...' : 'Sign in'}
+        </button>
+      </form>
+
+      <SsoProviderButtons
+        providers={ssoProviders}
+        loadingProviderId={ssoLoadingProviderId}
+        onOidcSignIn={(providerId) => {
+          void handleSsoSignIn(providerId);
+        }}
+      />
+
+      <p className="mt-4 text-center text-sm text-text-muted">
+        Don&apos;t have an account?{' '}
+        <Link to="/register" className="text-blue-400 hover:text-blue-300">
+          Sign up
+        </Link>
+      </p>
+    </div>
+  );
+}

apps/web/src/spa/pages/register.tsx

@@ -0,0 +1,116 @@
+import { useState, type FormEvent, type ReactElement } from 'react';
+import { Link, useNavigate } from 'react-router-dom';
+import { signUp } from '@/lib/auth-client';
+
+export function RegisterPage(): ReactElement {
+  const navigate = useNavigate();
+  const [error, setError] = useState<string | null>(null);
+  const [loading, setLoading] = useState(false);
+
+  async function handleSubmit(event: FormEvent<HTMLFormElement>): Promise<void> {
+    event.preventDefault();
+    setError(null);
+    setLoading(true);
+
+    const form = new FormData(event.currentTarget);
+    const name = String(form.get('name') ?? '');
+    const email = String(form.get('email') ?? '');
+    const password = String(form.get('password') ?? '');
+
+    try {
+      const result = await signUp.email({ name, email, password });
+
+      if (result.error) {
+        setError(result.error.message ?? 'Registration failed');
+        return;
+      }
+
+      navigate('/chat', { replace: true });
+    } catch (caught: unknown) {
+      setError(caught instanceof Error ? caught.message : 'Registration failed');
+    } finally {
+      setLoading(false);
+    }
+  }
+
+  return (
+    <div>
+      <h1 className="text-2xl font-semibold">Create account</h1>
+      <p className="mt-1 text-sm text-text-secondary">Get started with Mosaic</p>
+
+      {error ? (
+        <div
+          role="alert"
+          className="mt-4 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
+          {error}
+        </div>
+      ) : null}
+
+      <form className="mt-6 space-y-4" onSubmit={handleSubmit}>
+        <div>
+          <label htmlFor="name" className="block text-sm font-medium text-text-secondary">
+            Name
+          </label>
+          <input
+            id="name"
+            name="name"
+            type="text"
+            autoComplete="name"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="Your name"
+          />
+        </div>
+
+        <div>
+          <label htmlFor="email" className="block text-sm font-medium text-text-secondary">
+            Email
+          </label>
+          <input
+            id="email"
+            name="email"
+            type="email"
+            autoComplete="email"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="[email protected]"
+          />
+        </div>
+
+        <div>
+          <label htmlFor="password" className="block text-sm font-medium text-text-secondary">
+            Password
+          </label>
+          <input
+            id="password"
+            name="password"
+            type="password"
+            autoComplete="new-password"
+            required
+            disabled={loading}
+            className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
+            placeholder="••••••••"
+          />
+        </div>
+
+        <button
+          type="submit"
+          disabled={loading}
+          className="w-full rounded-lg bg-blue-600 px-4 py-2.5 text-sm font-medium text-white transition-colors hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 focus:ring-offset-surface-card disabled:opacity-50"
+        >
+          {loading ? 'Creating account...' : 'Create account'}
+        </button>
+      </form>
+
+      <p className="mt-4 text-center text-sm text-text-muted">
+        Already have an account?{' '}
+        <Link to="/login" className="text-blue-400 hover:text-blue-300">
+          Sign in
+        </Link>
+      </p>
+    </div>
+  );
+}

apps/web/src/spa/pages/sso-callback.spec.tsx

@@ -0,0 +1,90 @@
+import { act } from 'react';
+import { createRoot, type Root } from 'react-dom/client';
+import { createMemoryRouter, RouterProvider } from 'react-router-dom';
+import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
+
+const { apiMock, oauth2Mock } = vi.hoisted(() => ({
+  apiMock: vi.fn(),
+  oauth2Mock: vi.fn(),
+}));
+
+vi.mock('@/lib/api', () => ({
+  api: apiMock,
+}));
+
+vi.mock('@/lib/auth-client', () => ({
+  signIn: { oauth2: oauth2Mock },
+}));
+
+import { SsoCallbackPage } from './sso-callback';
+
+const mountedRoots: Root[] = [];
+
+beforeAll(() => {
+  Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
+    configurable: true,
+    value: true,
+  });
+});
+
+beforeEach(() => {
+  apiMock.mockResolvedValue([
+    {
+      id: 'authentik',
+      name: 'Authentik',
+      protocols: ['oidc'],
+      configured: true,
+      loginMode: 'oidc',
+      callbackPath: '/api/auth/oauth2/callback/authentik',
+      teamSync: { enabled: false, claim: null },
+      samlFallback: { configured: false, loginUrl: null },
+      warnings: [],
+    },
+  ]);
+  oauth2Mock.mockResolvedValue({ data: null, error: null });
+});
+
+afterEach(async () => {
+  for (const root of mountedRoots.splice(0)) {
+    await act(async () => {
+      root.unmount();
+    });
+  }
+  document.body.replaceChildren();
+  apiMock.mockReset();
+  oauth2Mock.mockReset();
+});
+
+afterAll(() => {
+  Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
+});
+
+describe('SsoCallbackPage', () => {
+  it('rejects a control-character callback that normalizes to an external origin', async () => {
+    const router = createMemoryRouter(
+      [
+        {
+          path: '/auth/provider/:provider',
+          element: <SsoCallbackPage />,
+        },
+      ],
+      {
+        initialEntries: ['/auth/provider/authentik?callbackURL=%2F%0A%2F%2Fevil.example'],
+      },
+    );
+    const container = document.createElement('div');
+    document.body.append(container);
+    const root = createRoot(container);
+    mountedRoots.push(root);
+
+    await act(async () => {
+      root.render(<RouterProvider router={router} />);
+      await new Promise((resolve) => setTimeout(resolve, 0));
+    });
+
+    expect(oauth2Mock).toHaveBeenCalledWith({
+      providerId: 'authentik',
+      callbackURL: '/chat',
+    });
+  });
+});

apps/web/src/spa/pages/sso-callback.tsx

@@ -0,0 +1,91 @@
+import { useEffect, useState, type ReactElement } from 'react';
+import { Link, useParams, useSearchParams } from 'react-router-dom';
+import { api } from '@/lib/api';
+import { resolveAuthCallbackURL } from '@/lib/auth-redirect';
+import { signIn } from '@/lib/auth-client';
+import type { SsoProviderDiscovery } from '@/lib/sso';
+
+export function SsoCallbackPage(): ReactElement {
+  const { provider: providerId = '' } = useParams<'provider'>();
+  const [searchParams] = useSearchParams();
+  const requestedCallbackURL = searchParams.get('callbackURL');
+  const [providerName, setProviderName] = useState<string | null>(null);
+  const [error, setError] = useState<string | null>(null);
+
+  useEffect(() => {
+    let cancelled = false;
+
+    async function redirectToProvider(): Promise<void> {
+      try {
+        const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
+        const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
+        if (cancelled) return;
+
+        const provider = providers.find((candidate) => candidate.id === providerId);
+        if (!provider) {
+          setError('Unknown SSO provider.');
+          return;
+        }
+
+        setProviderName(provider.name);
+        if (!provider.configured) {
+          setError(`${provider.name} is not enabled in this deployment.`);
+          return;
+        }
+        if (provider.loginMode !== 'oidc') {
+          setError(`${provider.name} is not available for OIDC sign in.`);
+          return;
+        }
+
+        const result = await signIn.oauth2({
+          providerId: provider.id,
+          callbackURL,
+        });
+
+        if (!cancelled && result?.error) {
+          setError(result.error.message ?? `${provider.name} sign in failed.`);
+        }
+      } catch (caught: unknown) {
+        if (!cancelled) {
+          setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
+        }
+      }
+    }
+
+    void redirectToProvider();
+
+    return () => {
+      cancelled = true;
+    };
+  }, [providerId, requestedCallbackURL]);
+
+  return (
+    <div className="mx-auto flex min-h-[50vh] max-w-md flex-col justify-center">
+      <h1 className="text-2xl font-semibold text-text-primary">Single sign-on</h1>
+      <p className="mt-2 text-sm text-text-secondary">
+        {providerName
+          ? `Redirecting you to ${providerName}...`
+          : 'Preparing your sign-in request...'}
+      </p>
+
+      {error ? (
+        <div
+          role="alert"
+          className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
+        >
+          <p>{error}</p>
+          <Link
+            to="/login"
+            className="mt-3 inline-block font-medium text-blue-400 hover:text-blue-300"
+          >
+            Return to login
+          </Link>
+        </div>
+      ) : (
+        <div className="mt-6 rounded-lg border border-surface-border bg-surface-elevated px-4 py-3 text-sm text-text-secondary">
+          If the redirect does not start automatically, return to the login page and try again.
+        </div>
+      )}
+    </div>
+  );
+}

apps/web/src/spa/placeholder.tsx

@@ -0,0 +1,9 @@
+import type { ReactElement } from 'react';
+
+export function Placeholder({ title }: { title: string }): ReactElement {
+  return (
+    <main className="flex min-h-screen items-center justify-center">
+      <h1 className="text-xl font-medium">{title}</h1>
+    </main>
+  );
+}

apps/web/src/spa/routes.spec.tsx

@@ -0,0 +1,70 @@
+import { isValidElement } from 'react';
+import { describe, expect, it } from 'vitest';
+import type { RouteObject } from 'react-router-dom';
+import { routes } from '@/routes';
+import { Placeholder } from '@/spa/placeholder';
+import { ChatPage } from '@/spa/pages/chat';
+
+function collectPaths(routeObjects: RouteObject[]): string[] {
+  return routeObjects.flatMap((route) => [
+    ...(route.path ? [route.path] : []),
+    ...(route.children ? collectPaths(route.children) : []),
+  ]);
+}
+
+function findRoute(routeObjects: RouteObject[], path: string): RouteObject | undefined {
+  for (const route of routeObjects) {
+    if (route.path === path) return route;
+    const nested = route.children ? findRoute(route.children, path) : undefined;
+    if (nested) return nested;
+  }
+  return undefined;
+}
+
+describe('SPA route table', () => {
+  it('covers every v1 parity route from the Phase P RFC', () => {
+    expect(collectPaths(routes).sort()).toEqual(
+      [
+        '/',
+        '/admin',
+        '/auth/provider/:provider',
+        '/chat',
+        '/login',
+        '/projects',
+        '/projects/:id',
+        '/register',
+        '/settings',
+        '/tasks',
+      ].sort(),
+    );
+  });
+
+  it('separates guest and authenticated route groups', () => {
+    const guestPaths = collectPaths(routes.at(0)?.children ?? []);
+    const authPaths = collectPaths(routes.at(1)?.children ?? []);
+    expect(guestPaths).toContain('/login');
+    expect(guestPaths).not.toContain('/chat');
+    expect(authPaths).toContain('/chat');
+  });
+
+  it.each(['/login', '/register', '/auth/provider/:provider'])(
+    'renders a real guest page instead of the P1 placeholder at %s',
+    (path) => {
+      const element = findRoute(routes, path)?.element;
+      expect(isValidElement(element)).toBe(true);
+      if (!isValidElement(element)) throw new Error(`Missing route element for ${path}`);
+      expect(element.type).not.toBe(Placeholder);
+    },
+  );
+
+  it('renders the real chat page instead of the P1 placeholder at /chat, inside the authenticated group', () => {
+    const authPaths = collectPaths(routes.at(1)?.children ?? []);
+    expect(authPaths).toContain('/chat');
+
+    const element = findRoute(routes, '/chat')?.element;
+    expect(isValidElement(element)).toBe(true);
+    if (!isValidElement(element)) throw new Error('Missing route element for /chat');
+    expect(element.type).not.toBe(Placeholder);
+    expect(element.type).toBe(ChatPage);
+  });
+});

apps/web/src/test/setup.spec.ts

@@ -0,0 +1,14 @@
+import { describe, expect, it } from 'vitest';
+
+describe('Vitest abort-controller realm', () => {
+  it('provides a global signal accepted by Node native Request', () => {
+    const controller = new AbortController();
+    const request = new Request('https://mosaic.invalid/navigation', {
+      signal: controller.signal,
+    });
+
+    expect(request.signal).toBeInstanceOf(AbortSignal);
+    controller.abort();
+    expect(request.signal.aborted).toBe(true);
+  });
+});

apps/web/src/test/setup.ts

@@ -0,0 +1,23 @@
+import { transferableAbortController } from 'node:util';
+
+// jsdom installs realm-local abort constructors while Node's undici Request
+// remains native. React Router passes a global AbortSignal to Request, so both
+// constructors must come from Node's native realm during tests.
+const nativeController = transferableAbortController();
+const nativeAbortController = nativeController.constructor;
+const nativeAbortSignal = nativeController.signal.constructor;
+
+for (const target of [globalThis, window]) {
+  Object.defineProperties(target, {
+    AbortController: {
+      configurable: true,
+      writable: true,
+      value: nativeAbortController,
+    },
+    AbortSignal: {
+      configurable: true,
+      writable: true,
+      value: nativeAbortSignal,
+    },
+  });
+}

apps/web/vite.config.ts

@@ -0,0 +1,24 @@
+import { fileURLToPath } from 'node:url';
+import react from '@vitejs/plugin-react';
+import { defineConfig } from 'vite';
+
+// The proxy exists only in dev; in production the SPA is same-origin with the gateway
+// (served by it under Candidate A, or behind one FQDN under Candidate B) and every
+// request uses a relative path, so no origin may ever be configured here or in src/.
+const gatewayTarget = 'http://localhost:14242';
+
+export default defineConfig({
+  plugins: [react()],
+  resolve: {
+    alias: {
+      '@': fileURLToPath(new URL('./src', import.meta.url)),
+    },
+  },
+  server: {
+    port: 3100,
+    proxy: {
+      '/api': gatewayTarget,
+      '/socket.io': { target: gatewayTarget, ws: true },
+    },
+  },
+});

apps/web/vitest.config.ts

@@ -1,9 +1,21 @@
+import { fileURLToPath } from 'node:url';
 import { defineConfig } from 'vitest/config';
 
 export default defineConfig({
+  resolve: {
+    alias: {
+      '@': fileURLToPath(new URL('./src', import.meta.url)),
+    },
+  },
+  // tsconfig uses "jsx": "preserve" for Next; tests need esbuild to compile it
+  esbuild: {
+    jsx: 'automatic',
+  },
   test: {
     globals: true,
     environment: 'jsdom',
+    setupFiles: ['./src/test/setup.ts'],
+    isolate: true,
     exclude: ['e2e/**', 'node_modules/**'],
   },
 });

docker/gateway.Dockerfile

@@ -10,6 +10,8 @@ COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
 COPY apps/gateway/package.json ./apps/gateway/
 COPY packages/ ./packages/
 COPY plugins/ ./plugins/
+# the root prepare script runs scripts/install-hooks.mjs on install
+COPY scripts/ ./scripts/
 RUN pnpm install --frozen-lockfile
 COPY . .
 # Build gateway and all of its workspace dependencies via turbo dependency graph
@@ -21,11 +23,22 @@ RUN pnpm --filter @mosaicstack/gateway --prod deploy --legacy /deploy
 FROM base AS runner
 WORKDIR /app
 ENV NODE_ENV=production
+# WorkspaceService shells out to git at runtime and roots workspaces at
+# $MOSAIC_ROOT/.workspaces (apps/gateway/src/workspace/workspace.service.ts);
+# mount a volume over /opt/mosaic to persist workspaces across container restarts.
+# Intentionally unpinned: Alpine's signed repository is the trust anchor; pinning
+# git was declined so routine base-image security updates remain maintainable.
+RUN apk add --no-cache git \
+  && mkdir -p /opt/mosaic/.workspaces \
+  && chown -R node:node /opt/mosaic /app
+ENV MOSAIC_ROOT=/opt/mosaic
 # Use the pnpm deploy output — resolves all deps into a flat, self-contained node_modules
-COPY --from=builder /deploy/node_modules ./node_modules
-COPY --from=builder /deploy/package.json ./package.json
+COPY --chown=node:node --from=builder /deploy/node_modules ./node_modules
+COPY --chown=node:node --from=builder /deploy/package.json ./package.json
 # dist is declared in package.json "files" so pnpm deploy copies it into /deploy;
 # copy from builder explicitly as belt-and-suspenders
-COPY --from=builder /app/apps/gateway/dist ./dist
-EXPOSE 4000
+COPY --chown=node:node --from=builder /app/apps/gateway/dist ./dist
+# gateway defaults to port 14242 (apps/gateway/src/main.ts)
+EXPOSE 14242
+USER node
 CMD ["node", "dist/main.js"]

docker/web.Dockerfile

@@ -8,9 +8,11 @@ WORKDIR /app
 COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
 COPY apps/web/package.json ./apps/web/
 COPY packages/ ./packages/
+# the root prepare script runs scripts/install-hooks.mjs on install
+COPY scripts/ ./scripts/
 RUN pnpm install --frozen-lockfile
 COPY . .
-RUN pnpm --filter @mosaic/web build
+RUN pnpm --filter @mosaicstack/web build
 
 FROM base AS runner
 WORKDIR /app

docs/scratchpads/webui-p2-data-auth.md

@@ -0,0 +1,172 @@
+# WebUI Phase P — P2 Data + Auth Scratchpad
+
+**Task ID:** WEBUI-P2
+**Tracking ref:** stacked on PR #1143 (`feat/webui-p1-vite-skeleton`); no separate issue specified in the author brief
+**Branch:** `feat/webui-p2-data-auth`
+**Started:** 2026-08-09
+**Role:** P2 author worker (must not modify `docs/TASKS.md`)
+
+## Original tasking
+
+> Read `/home/jwoltje/briefs/P2-brief.md` and execute it fully in `/home/jwoltje/src/stack-p1` on branch `feat/webui-p2-data-auth`. Run every listed verification gate, commit locally only, and do not push.
+
+Container path mapping:
+
+- Brief: `/home/jwoltje/distrobox-homes/mosaic-dev/briefs/P2-brief.md`
+- Repo: `/home/jwoltje/distrobox-homes/mosaic-dev/src/stack-p1`
+
+## Objective
+
+Make the P1 Vite SPA authenticate against the Mosaic Gateway by same-origin relative paths, replace guest-route placeholders with real login/register/SSO callback pages, and enforce guest/authenticated route guards without modifying the parallel Next app tree except for unavoidable shared-library import fixes.
+
+## Scope and invariants
+
+- All SPA HTTP and Socket.IO access remains origin-relative (`/api/...`, `/api/auth/...`, `/chat`).
+- No `NEXT_PUBLIC_*`, `VITE_*` origin setting, or hard-coded `http://localhost:14242` under `apps/web/src/`.
+- Verify the Gateway BetterAuth mount path from source before choosing auth-client configuration.
+- Delete the legacy static SSO-provider discovery module and test; runtime `/api/sso/providers` is canonical.
+- Preserve the Next build while adding React Router guest pages and session guards.
+- Never push; stage named files only; do not touch the modified `.mosaic/orchestrator/session.lock`.
+
+## Plan
+
+1. Inspect P1 SPA structure, shared libraries, legacy Next auth pages/components, Gateway auth mount, and current test setup.
+2. Add/adjust tests first for relative API behavior, auth-client origin configuration, relative Socket.IO singleton behavior, and all guard session states; run focused tests and capture expected RED failures.
+3. Implement shared-library relative networking and remove the legacy SSO-provider module/imports.
+4. Port login, register, and provider callback pages to React Router and wire routes.
+5. Implement session-aware guest/auth guards and satisfy focused tests.
+6. Run focused tests, all brief verification gates, invariant searches, and an independent code/security review; remediate and re-run affected gates.
+7. Update this scratchpad with evidence, stage named files only, and commit locally.
+
+## Testing strategy
+
+- TDD is required because this increment changes authentication/session behavior.
+- Primary situational evidence: jsdom router guard state tests plus guest-page/auth-flow contract tests already present or added as needed.
+- Baseline gates: web tests, Vite build, Next build, typecheck, lint, and root format check exactly as listed in the brief.
+- Browser automation is not required by the brief for P2; if used, it will be headless only.
+
+## Budget
+
+No explicit user token cap was provided. Working soft cap: **30K tokens**, derived from a multi-file auth/frontend increment with tests, dual builds, review, and remediation. Keep implementation within the brief; no unrelated refactors or dependencies.
+
+## Progress / evidence
+
+- [x] Loaded mission protocol, active MVP manifest/scratchpad, top-level tasks, PRD, relevant frontend/auth/testing/type/review guides, and matching skills.
+- [x] Resolved host paths to the Distrobox-mapped repo and brief.
+- [x] Confirmed branch `feat/webui-p2-data-auth`, stacked at P1 commit `068d0f9b`.
+- [x] Source and Gateway mount inspection complete.
+- [x] RED tests observed.
+- [x] Implementation complete.
+- [x] Independent review complete and findings remediated.
+- [x] Verification gates complete.
+- [x] Local implementation commit created: `46d68e1f`.
+
+### Source decisions
+
+- Gateway source mounts BetterAuth at `/api/auth/` in `apps/gateway/src/auth/auth.controller.ts`; `packages/auth/src/auth.ts` configures `basePath: '/api/auth'`.
+- BetterAuth 1.5.5 defaults its browser client to `/api/auth` when `baseURL` is omitted. `src/lib/auth-client.ts` therefore omits `baseURL`, preserving same-origin behavior without encoding any gateway origin.
+- The only `src/app/` edit is the transitional Next provider redirect page. Deleting `src/lib/sso-providers.ts` required that mechanical consumer migration; it now uses the same runtime `/api/sso/providers` discovery and callback sanitizer as the SPA.
+- GuestGuard pending behavior intentionally follows the approved brief: if no session object exists (including pending), render `<Outlet />`; only a present session redirects to `/chat`. AuthGuard alone renders the specified pending treatment.
+
+### TDD evidence
+
+- Initial focused run: 9 expected failures, proving absolute API/auth/socket origins, P1 guest placeholders, and missing guard redirects/loading behavior.
+- After implementation: focused contract suite 15/15 passed.
+- Security remediation RED: `%2F%0A%2F%2Fevil.example` reached `signIn.oauth2` as an external-normalizing callback target before the fix.
+- Security remediation GREEN: shared `resolveAuthCallbackURL` unit suite 9/9 plus SPA callback regression 1/1 passed; both SPA and Next consumers use the shared helper.
+
+### Independent review
+
+- Primary Codex wrappers could not run because `jq` is absent; direct Codex fallback then failed authentication with HTTP 401. No review result was claimed from those attempts.
+- Independent Claude Sonnet code review found no implementation-scope blocker, one pending-state UX suggestion, and one pre-existing `api.ts` type-assertion suggestion. The pending-state suggestion was rejected because it contradicts the brief's explicit GuestGuard contract; the API cleanup is outside P2's preserve-contract scope.
+- Independent Claude Sonnet security review found a high-severity control-character open redirect in the callback prefix check shared by the newly ported SPA logic and transitional Next consumer.
+- Remediation centralized WHATWG URL parsing plus exact current-origin comparison in `src/lib/auth-redirect.ts`, returns only path/search/hash, and added the RED-first regression above.
+- Fresh code re-review: `approve`, 0 blockers, 0 should-fix findings.
+- Fresh security re-review: `low`, 0 critical/high/medium/low findings.
+
+### Documentation checklist disposition
+
+- `docs/PRD.md` exists and P2 aligns to FR-8 / AC-7 authentication requirements.
+- No Gateway endpoint, DTO, permission, or API schema changed; existing `/api/auth/*` and `/api/sso/providers` contracts are consumed unchanged, so OpenAPI/API-index updates are not applicable.
+- Route paths were already present in the P1 route table; P2 replaces placeholders without changing site-map navigation, so `docs/SITEMAP.md` is unchanged.
+- User/admin auth behavior is parity with the still-live Next implementation, not a new workflow. Implementation decisions, failure behavior, testing, and migration compatibility are documented here; no publishing action is in scope.
+- Documentation remains in-repo; no generated publishing output was created.
+
+### Final verification evidence
+
+Run fresh after remediation from the locations required by the brief:
+
+- `apps/web: pnpm test` — PASS: `Test Files 9 passed (9)`; `Tests 27 passed (27)`.
+- `apps/web: pnpm build:vite` — PASS: `✓ 113 modules transformed`; `✓ built in 565ms`.
+- `apps/web: pnpm build` — PASS: `✓ Compiled successfully in 4.6s`; 10/10 static pages generated; dynamic provider/project routes retained.
+- `apps/web: pnpm typecheck` — PASS: `tsc --noEmit` exited 0.
+- `apps/web: pnpm lint` — PASS: `eslint src` exited 0.
+- Root `pnpm format:check` — PASS: `All matched files use Prettier code style!`.
+- Invariant scan — PASS: no `NEXT_PUBLIC_*`, `VITE_*`, `GATEWAY_URL`, `http://localhost:14242`, or `sso-providers` references under `apps/web/src`.
+- `git diff --check` — PASS.
+- All six required gates above were repeated successfully after implementation commit `46d68e1f`, proving the exact committed source tree.
+
+## Risks / blockers
+
+- `.mosaic/orchestrator/session.lock` is modified by the active harness and must remain unstaged.
+- P2 changes shared `src/lib/` modules consumed by both Vite and Next, so the Next build is a required compatibility gate.
+
+## Remediation 1 — independent Node 26 verification failure
+
+**Correction received:** 2026-08-09
+
+The orchestrator rejected the P2 verification claim after an independent run under Node 26.4.0 produced 2 failed redirect tests and 2 unhandled errors. React Router passed jsdom's realm-local `AbortSignal` to Node 26's native undici `Request`, which rejects non-native signals. Production guard behavior is correct and must not change.
+
+### Remediation constraints
+
+- Preserve both redirect assertions and all `guards.tsx` behavior; no skips, weakening, or test deletion.
+- Add the smallest Vitest environment repair so global `AbortController` / `AbortSignal` are constructors accepted by native undici `Request`.
+- Run all six required gates, commit named files locally without pushing, leave `.mosaic/orchestrator/session.lock` untouched, then run `apps/web: pnpm test` as the final worktree action.
+- Completion requires zero failed tests, zero test errors, and zero unhandled rejections.
+
+### Remediation plan
+
+1. Reproduce under Node 26.4.0 if an ephemeral matching runtime is available.
+2. Add a Vitest `setupFiles` module deriving Node-native abort constructors from `node:util` and register it in `apps/web/vitest.config.ts`.
+3. Add a direct regression assertion that a global controller's signal is accepted by native `Request`, while retaining the existing redirect behavior tests unchanged.
+4. Run focused Node 22 and Node 26 tests, independent review, all required gates, and local commit(s).
+5. After every edit/commit/status check is complete, run `pnpm test` from `apps/web` as the last command.
+
+### Remediation implementation and evidence
+
+- Reproduced under ephemeral Node `v26.4.0`: `Test Files 1 failed (1)`, `Tests 2 failed | 4 passed (6)`, `Errors 2 errors`, with the exact undici `AbortSignal` realm rejection from the remediation brief.
+- Added `apps/web/src/test/setup.ts`, registered through `vitest.config.ts#setupFiles`. It derives Node-native abort constructors from the built-in `node:util.transferableAbortController()` and aligns both `globalThis` and jsdom `window`; it does not replace `Request`, `Response`, or `fetch`.
+- Explicitly pinned Vitest `isolate: true` so the test-only global constructors cannot leak between test-file environments.
+- Added `src/test/setup.spec.ts`, which proves a global controller signal is accepted by Node's native `Request` and that abort propagation remains functional.
+- Existing `guards.spec.tsx` and production `guards.tsx` remain unchanged.
+- Focused Node 26.4.0 remediation run: `Test Files 2 passed (2)` and `Tests 7 passed (7)`, with zero errors/unhandled rejections.
+- Preliminary full Node 26.4.0 run: `Test Files 9 passed (9)` and `Tests 27 passed (27)`, with zero errors/unhandled rejections before the direct setup regression was added.
+- No dependency was added; `node:util` is a Node built-in.
+
+### Remediation independent review
+
+- First code review: approve, 0 blockers, 0 should-fix; suggested a direct Request regression and version-neutral comment.
+- First security/integrity review: low risk; suggested pinning test isolation explicitly.
+- All suggestions were applied.
+- Fresh code re-review: approve, 0 blockers, 0 should-fix, no findings.
+- Fresh security/integrity re-review: low risk, 0 findings.
+
+### Remediation pre-commit gate evidence
+
+- Node 26.4.0 `pnpm test`: `Test Files 10 passed (10)`; `Tests 28 passed (28)`; zero errors and zero unhandled rejections.
+- `pnpm typecheck`: `tsc --noEmit` exited 0.
+- `pnpm build:vite`: `✓ 113 modules transformed`; `✓ built in 960ms`.
+- `pnpm build` (Next): `✓ Compiled successfully in 4.8s`; static pages generated 10/10.
+- `pnpm lint`: `eslint src` exited 0.
+- Root `pnpm format:check`: `All matched files use Prettier code style!`.
+- Final post-commit non-test gates and final-action Node 26 `pnpm test` remain required before reporting completion.
+
+### Remediation committed verification
+
+- Implementation commit: `e16c08aa` (`test(web): align jsdom abort signals with Node`).
+- Post-commit `pnpm typecheck`: `tsc --noEmit` exited 0.
+- Post-commit `pnpm build:vite`: `✓ 113 modules transformed`; `✓ built in 323ms`.
+- Post-commit `pnpm build` (Next): `✓ Compiled successfully in 4.6s`; static pages generated 10/10.
+- Post-commit `pnpm lint`: `eslint src` exited 0.
+- Post-commit root `pnpm format:check`: `All matched files use Prettier code style!`.
+- Final Node 26 `pnpm test` will be the last worktree action and its verbatim output will be reported to the orchestrator.

scripts/install-hooks.mjs

@@ -75,6 +75,16 @@ export async function installHooks({
 } = {}) {
   if (disabled) return;
 
+  try {
+    await execFileAsync('git', ['--version']);
+  } catch (error) {
+    if (error.code === 'ENOENT') {
+      console.warn('git not found; skipping hook installation');
+      return;
+    }
+    throw error;
+  }
+
   const huskyDir = path.join(root, '.husky');
   const active = path.join(huskyDir, '_');
   const nonce = `${Date.now()}-${process.pid}`;