test(tess): cover streamed private key redaction

.gitignore

@@ -15,3 +15,10 @@ infra/step-ca/dev-password
 
 # Scratch dirs created by the framework git-wrapper shell test harnesses
 .mosaic-test-work/
+
+# Transient config files vite/vitest/esbuild write next to a *.config.ts while
+# loading it, then unlink. They are untracked but were not ignored, so turbo's
+# package traversal hashed them and intermittently failed CI with "Package
+# traversal error: ... .timestamp-*.mjs: No such file or directory" when the
+# file vanished mid-scan. Ignoring them removes the race.
+*.timestamp-*.mjs

.prettierignore

@@ -5,3 +5,5 @@ pnpm-lock.yaml
 **/drizzle
 **/.next
 .claude/
+docs/tess/TASKS.md
+docs/scratchpads/

.woodpecker/ci.yml

@@ -7,7 +7,14 @@ variables:
   - &enable_pnpm 'corepack enable'
 
 when:
-  - event: [push, pull_request, manual]
+  # PR + manual CI run on any branch — the pull_request pipeline is the merge gate.
+  # push CI is restricted to protected branches (main) so a feature-branch push no
+  # longer fires a redundant SECOND pipeline alongside its PR pipeline. This ~halves
+  # CI load on the storage-constrained runner with zero loss of gating (branch
+  # protection requires no push/ci status context; main still gets full push CI).
+  - event: [pull_request, manual]
+  - event: push
+    branch: main
 
 # Turbo remote cache (turbo.mosaicstack.dev) is configured via Woodpecker
 # repository-level environment variables (TURBO_API, TURBO_TEAM, TURBO_TOKEN).

apps/gateway/package.json

@@ -31,6 +31,7 @@
     "@mariozechner/pi-ai": "^0.65.0",
     "@mariozechner/pi-coding-agent": "^0.65.0",
     "@modelcontextprotocol/sdk": "^1.27.1",
+    "@mosaicstack/agent": "workspace:^",
     "@mosaicstack/auth": "workspace:^",
     "@mosaicstack/brain": "workspace:^",
     "@mosaicstack/config": "workspace:^",

apps/gateway/src/admin/admin-health.controller.ts

@@ -20,7 +20,7 @@ export class AdminHealthController {
   async check(): Promise<HealthStatusDto> {
     const [database, cache] = await Promise.all([this.checkDatabase(), this.checkCache()]);
 
-    const sessions = this.agentService.listSessions();
+    const sessions = this.agentService.listAllSessionsForSystem();
     const providers = this.providerService.listProviders();
 
     const allOk = database.status === 'ok' && cache.status === 'ok';

apps/gateway/src/agent/__tests__/agent-service-ownership.test.ts

@@ -0,0 +1,142 @@
+import { ForbiddenException } from '@nestjs/common';
+import { describe, expect, it, vi } from 'vitest';
+import { AgentService, type AgentSession } from '../agent.service.js';
+import type { ActorTenantScope } from '../../auth/session-scope.js';
+
+const CONVERSATION_ID = '22222222-2222-4222-8222-222222222222';
+const OWNER_SCOPE: ActorTenantScope = { userId: 'owner-user', tenantId: 'owner-tenant' };
+const FOREIGN_SCOPE: ActorTenantScope = { userId: 'foreign-user', tenantId: 'foreign-tenant' };
+
+type AgentServiceInternals = {
+  sessions: Map<string, AgentSession>;
+  creating: Map<string, Promise<AgentSession>>;
+};
+
+function makeService(): AgentService {
+  return new AgentService(
+    {} as never,
+    {} as never,
+    {} as never,
+    { available: false } as never,
+    {} as never,
+    {} as never,
+    {} as never,
+    null,
+    null,
+    { collect: vi.fn().mockResolvedValue(undefined) } as never,
+  );
+}
+
+function internals(service: AgentService): AgentServiceInternals {
+  return service as unknown as AgentServiceInternals;
+}
+
+function makeSession(scope: ActorTenantScope = OWNER_SCOPE): AgentSession {
+  return {
+    id: CONVERSATION_ID,
+    provider: 'test-provider',
+    modelId: 'test-model',
+    piSession: {
+      thinkingLevel: 'off',
+      getAvailableThinkingLevels: vi.fn().mockReturnValue(['off', 'low', 'high']),
+      setThinkingLevel: vi.fn(),
+      abort: vi.fn().mockResolvedValue(undefined),
+      prompt: vi.fn().mockResolvedValue(undefined),
+      dispose: vi.fn(),
+      getSessionStats: vi.fn(),
+      getContextUsage: vi.fn(),
+    } as unknown as AgentSession['piSession'],
+    listeners: new Set(),
+    unsubscribe: vi.fn(),
+    createdAt: Date.now(),
+    promptCount: 0,
+    channels: new Set(),
+    skillPromptAdditions: [],
+    sandboxDir: '/tmp/tess-session-ownership-test',
+    allowedTools: null,
+    userId: scope.userId,
+    tenantId: scope.tenantId,
+    metrics: {
+      tokens: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
+      modelSwitches: 0,
+      messageCount: 0,
+      lastActivityAt: new Date('2026-07-12T00:00:00Z').toISOString(),
+    },
+  };
+}
+
+describe('AgentService owner/tenant scope enforcement', () => {
+  it('allows owner-scoped operations and rejects foreign scopes for seeded sessions', async () => {
+    const service = makeService();
+    const session = makeSession();
+    internals(service).sessions.set(CONVERSATION_ID, session);
+
+    expect(service.getSession(CONVERSATION_ID, OWNER_SCOPE)).toBe(session);
+    expect(service.getSession(CONVERSATION_ID, FOREIGN_SCOPE)).toBeUndefined();
+    expect(service.getSessionInfo(CONVERSATION_ID, FOREIGN_SCOPE)).toBeUndefined();
+    expect(service.listSessions(OWNER_SCOPE)).toHaveLength(1);
+    expect(service.listSessions(FOREIGN_SCOPE)).toEqual([]);
+
+    service.addChannel(CONVERSATION_ID, 'websocket:owner', OWNER_SCOPE);
+    expect(session.channels.has('websocket:owner')).toBe(true);
+    expect(() => service.addChannel(CONVERSATION_ID, 'websocket:foreign', FOREIGN_SCOPE)).toThrow(
+      ForbiddenException,
+    );
+    expect(() => service.removeChannel(CONVERSATION_ID, 'websocket:owner', FOREIGN_SCOPE)).toThrow(
+      ForbiddenException,
+    );
+
+    expect(() =>
+      service.updateSessionModel(CONVERSATION_ID, 'foreign-model', FOREIGN_SCOPE),
+    ).toThrow(ForbiddenException);
+    service.updateSessionModel(CONVERSATION_ID, 'owner-model', OWNER_SCOPE);
+    expect(session.modelId).toBe('owner-model');
+
+    expect(() =>
+      service.applyAgentConfig(CONVERSATION_ID, 'agent-foreign', 'Foreign Agent', FOREIGN_SCOPE),
+    ).toThrow(ForbiddenException);
+    service.applyAgentConfig(CONVERSATION_ID, 'agent-owner', 'Owner Agent', OWNER_SCOPE);
+    expect(session.agentConfigId).toBe('agent-owner');
+
+    expect(() => service.onEvent(CONVERSATION_ID, vi.fn(), FOREIGN_SCOPE)).toThrow(
+      ForbiddenException,
+    );
+    const cleanup = service.onEvent(CONVERSATION_ID, vi.fn(), OWNER_SCOPE);
+    cleanup();
+
+    await expect(
+      service.prompt(CONVERSATION_ID, 'foreign prompt', FOREIGN_SCOPE),
+    ).rejects.toBeInstanceOf(ForbiddenException);
+    await service.prompt(CONVERSATION_ID, 'owner prompt', OWNER_SCOPE);
+    expect(session.piSession.prompt).toHaveBeenCalledWith('owner prompt');
+
+    await expect(service.destroySession(CONVERSATION_ID, FOREIGN_SCOPE)).rejects.toBeInstanceOf(
+      ForbiddenException,
+    );
+    expect(internals(service).sessions.has(CONVERSATION_ID)).toBe(true);
+
+    await service.destroySession(CONVERSATION_ID, OWNER_SCOPE);
+    expect(session.piSession.dispose).toHaveBeenCalled();
+    expect(internals(service).sessions.has(CONVERSATION_ID)).toBe(false);
+  });
+
+  it('checks owner/tenant scope before returning an in-flight session creation', async () => {
+    const service = makeService();
+    const session = makeSession();
+    internals(service).creating.set(CONVERSATION_ID, Promise.resolve(session));
+
+    await expect(
+      service.createSession(CONVERSATION_ID, {
+        userId: FOREIGN_SCOPE.userId,
+        tenantId: FOREIGN_SCOPE.tenantId,
+      }),
+    ).rejects.toBeInstanceOf(ForbiddenException);
+
+    await expect(
+      service.createSession(CONVERSATION_ID, {
+        userId: OWNER_SCOPE.userId,
+        tenantId: OWNER_SCOPE.tenantId,
+      }),
+    ).resolves.toBe(session);
+  });
+});

apps/gateway/src/agent/__tests__/runtime-provider-registry.service.test.ts

@@ -0,0 +1,285 @@
+import { describe, expect, it } from 'vitest';
+import type {
+  AgentRuntimeProvider,
+  RuntimeAttachHandle,
+  RuntimeAttachMode,
+  RuntimeCapability,
+  RuntimeCapabilitySet,
+  RuntimeHealth,
+  RuntimeMessage,
+  RuntimeScope,
+  RuntimeSession,
+  RuntimeSessionTree,
+  RuntimeStreamEvent,
+} from '@mosaicstack/types';
+import { AgentRuntimeProviderRegistry } from '@mosaicstack/agent';
+import type { ActorTenantScope } from '../../auth/session-scope.js';
+import {
+  RuntimeProviderService,
+  type RuntimeAuditEvent,
+  type RuntimeAuditSink,
+  type RuntimeApprovalVerifier,
+} from '../runtime-provider-registry.service.js';
+
+const OWNER_SCOPE: ActorTenantScope = { userId: 'owner-1', tenantId: 'tenant-1' };
+const CONTEXT = {
+  actorScope: OWNER_SCOPE,
+  channelId: 'cli',
+  correlationId: 'correlation-1',
+};
+
+class RecordingRuntimeProvider implements AgentRuntimeProvider {
+  readonly id = 'fleet';
+  readonly receivedScopes: RuntimeScope[] = [];
+  readonly sentMessages: RuntimeMessage[] = [];
+  terminateCalls = 0;
+  throwAfterSend = false;
+
+  constructor(private readonly supported: RuntimeCapability[]) {}
+
+  async capabilities(scope: RuntimeScope): Promise<RuntimeCapabilitySet> {
+    this.receivedScopes.push(scope);
+    return { supported: this.supported };
+  }
+
+  async health(scope: RuntimeScope): Promise<RuntimeHealth> {
+    this.receivedScopes.push(scope);
+    return { status: 'healthy', checkedAt: '2026-07-12T00:00:00.000Z' };
+  }
+
+  async listSessions(scope: RuntimeScope): Promise<RuntimeSession[]> {
+    this.receivedScopes.push(scope);
+    return [];
+  }
+
+  async getSessionTree(scope: RuntimeScope): Promise<RuntimeSessionTree[]> {
+    this.receivedScopes.push(scope);
+    return [];
+  }
+
+  async *streamSession(
+    _sessionId: string,
+    _cursor: string | undefined,
+    scope: RuntimeScope,
+  ): AsyncIterable<RuntimeStreamEvent> {
+    this.receivedScopes.push(scope);
+    return;
+  }
+
+  async sendMessage(
+    _sessionId: string,
+    message: RuntimeMessage,
+    scope: RuntimeScope,
+  ): Promise<void> {
+    this.receivedScopes.push(scope);
+    this.sentMessages.push(message);
+    if (this.throwAfterSend) {
+      throw new Error('provider acknowledgement failed');
+    }
+  }
+
+  async attach(
+    sessionId: string,
+    mode: RuntimeAttachMode,
+    scope: RuntimeScope,
+  ): Promise<RuntimeAttachHandle> {
+    this.receivedScopes.push(scope);
+    return {
+      attachmentId: 'attachment-1',
+      sessionId,
+      mode,
+      expiresAt: '2026-07-12T00:00:00.000Z',
+    };
+  }
+
+  async detach(_attachmentId: string, scope: RuntimeScope): Promise<void> {
+    this.receivedScopes.push(scope);
+  }
+
+  async terminate(_sessionId: string, _approvalRef: string, scope: RuntimeScope): Promise<void> {
+    this.receivedScopes.push(scope);
+    this.terminateCalls += 1;
+  }
+}
+
+class RecordingAuditSink implements RuntimeAuditSink {
+  readonly events: RuntimeAuditEvent[] = [];
+
+  async record(event: RuntimeAuditEvent): Promise<void> {
+    this.events.push(event);
+  }
+}
+
+class DenyingApprovalVerifier implements RuntimeApprovalVerifier {
+  async consume(): Promise<boolean> {
+    return false;
+  }
+}
+
+class AcceptingApprovalVerifier implements RuntimeApprovalVerifier {
+  consumedAction: Parameters<RuntimeApprovalVerifier['consume']>[1] | undefined;
+
+  async consume(
+    _approvalRef: string,
+    action: Parameters<RuntimeApprovalVerifier['consume']>[1],
+  ): Promise<boolean> {
+    this.consumedAction = action;
+    return true;
+  }
+}
+
+function makeService(
+  provider: RecordingRuntimeProvider,
+  audit: RuntimeAuditSink = new RecordingAuditSink(),
+  approval: RuntimeApprovalVerifier = new DenyingApprovalVerifier(),
+): RuntimeProviderService {
+  const registry = new AgentRuntimeProviderRegistry();
+  registry.register(provider);
+  return new RuntimeProviderService(registry, audit, approval);
+}
+
+describe('RuntimeProviderService security boundary', (): void => {
+  it('derives and freezes only the authenticated actor scope while preserving correlation metadata', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider(['session.send']);
+    const audit = new RecordingAuditSink();
+    const service = makeService(provider, audit);
+
+    await service.sendMessage(
+      'fleet',
+      'session-1',
+      { content: 'hello', idempotencyKey: 'key-1' },
+      CONTEXT,
+    );
+
+    const providerScope = provider.receivedScopes[0];
+    expect(providerScope).toEqual({
+      actorId: OWNER_SCOPE.userId,
+      tenantId: OWNER_SCOPE.tenantId,
+      channelId: CONTEXT.channelId,
+      correlationId: CONTEXT.correlationId,
+    });
+    expect(Object.isFrozen(providerScope)).toBe(true);
+    expect(audit.events).toContainEqual({
+      providerId: 'fleet',
+      operation: 'session.send',
+      outcome: 'succeeded',
+      actorId: OWNER_SCOPE.userId,
+      tenantId: OWNER_SCOPE.tenantId,
+      channelId: CONTEXT.channelId,
+      correlationId: CONTEXT.correlationId,
+      resourceId: 'session-1',
+    });
+    expect(JSON.stringify(audit.events)).not.toContain('hello');
+    expect(JSON.stringify(audit.events)).not.toContain('key-1');
+  });
+
+  it('fails closed before a provider side effect when a capability is missing', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider([]);
+    const service = makeService(provider);
+
+    await expect(
+      service.sendMessage(
+        'fleet',
+        'session-1',
+        { content: 'hello', idempotencyKey: 'key-1' },
+        CONTEXT,
+      ),
+    ).rejects.toThrow(/capability denied/);
+    expect(provider.sentMessages).toEqual([]);
+  });
+
+  it('requires a consumed exact-action approval before termination', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider(['session.terminate']);
+    const approval = new DenyingApprovalVerifier();
+    const service = makeService(provider, new RecordingAuditSink(), approval);
+
+    await expect(
+      service.terminate('fleet', 'session-1', 'forged-approval', CONTEXT),
+    ).rejects.toThrow(/approval denied/);
+    expect(provider.terminateCalls).toBe(0);
+  });
+
+  it('binds an accepted termination approval to provider, session, immutable scope, and correlation', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider(['session.terminate']);
+    const approval = new AcceptingApprovalVerifier();
+    const service = makeService(provider, new RecordingAuditSink(), approval);
+
+    await service.terminate('fleet', 'session-1', 'approval-1', CONTEXT);
+
+    expect(approval.consumedAction).toEqual({
+      providerId: 'fleet',
+      sessionId: 'session-1',
+      actorId: OWNER_SCOPE.userId,
+      tenantId: OWNER_SCOPE.tenantId,
+      channelId: CONTEXT.channelId,
+      correlationId: CONTEXT.correlationId,
+    });
+    expect(provider.terminateCalls).toBe(1);
+  });
+
+  it('fails closed before invoking a provider when audit persistence rejects the request', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider(['session.send']);
+    const unavailableAudit: RuntimeAuditSink = {
+      async record(): Promise<void> {
+        throw new Error('audit unavailable');
+      },
+    };
+    const service = makeService(provider, unavailableAudit);
+
+    await expect(
+      service.sendMessage(
+        'fleet',
+        'session-1',
+        { content: 'hello', idempotencyKey: 'key-1' },
+        CONTEXT,
+      ),
+    ).rejects.toThrow(/audit unavailable/);
+    expect(provider.sentMessages).toEqual([]);
+  });
+
+  it('records a provider error after invocation as failed rather than denied', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider(['session.send']);
+    provider.throwAfterSend = true;
+    const audit = new RecordingAuditSink();
+    const service = makeService(provider, audit);
+
+    await expect(
+      service.sendMessage(
+        'fleet',
+        'session-1',
+        { content: 'hello', idempotencyKey: 'key-1' },
+        CONTEXT,
+      ),
+    ).rejects.toThrow(/provider acknowledgement failed/);
+    expect(provider.sentMessages).toHaveLength(1);
+    expect(audit.events.map((event: RuntimeAuditEvent): string => event.outcome)).toEqual([
+      'requested',
+      'failed',
+    ]);
+  });
+
+  it('does not misreport a completed provider side effect when completion auditing fails', async (): Promise<void> => {
+    const provider = new RecordingRuntimeProvider(['session.send']);
+    let auditCalls = 0;
+    const audit: RuntimeAuditSink = {
+      async record(): Promise<void> {
+        auditCalls += 1;
+        if (auditCalls === 2) {
+          throw new Error('completion audit unavailable');
+        }
+      },
+    };
+    const service = makeService(provider, audit);
+
+    await expect(
+      service.sendMessage(
+        'fleet',
+        'session-1',
+        { content: 'hello', idempotencyKey: 'key-1' },
+        CONTEXT,
+      ),
+    ).resolves.toBeUndefined();
+    expect(provider.sentMessages).toHaveLength(1);
+    expect(auditCalls).toBe(2);
+  });
+});

apps/gateway/src/agent/__tests__/session-ownership.test.ts

@@ -0,0 +1,262 @@
+import { readFileSync } from 'node:fs';
+import { resolve } from 'node:path';
+import { ForbiddenException, NotFoundException } from '@nestjs/common';
+import { describe, expect, it, vi } from 'vitest';
+
+vi.mock('../agent.service.js', () => ({ AgentService: class AgentService {} }));
+vi.mock('../../commands/command-executor.service.js', () => ({
+  CommandExecutorService: class CommandExecutorService {},
+}));
+vi.mock('../routing/routing-engine.service.js', () => ({
+  RoutingEngineService: class RoutingEngineService {},
+}));
+
+import { SessionsController } from '../sessions.controller.js';
+import { ChatController } from '../../chat/chat.controller.js';
+import { ChatGateway } from '../../chat/chat.gateway.js';
+import type { AgentSession } from '../agent.service.js';
+import type { SessionInfoDto } from '../session.dto.js';
+
+const USER_A = { id: 'user-a', tenantId: 'tenant-a' };
+const USER_B = { id: 'user-b', tenantId: 'tenant-b' };
+const CONVERSATION_ID = '11111111-1111-4111-8111-111111111111';
+
+function makeSessionInfo(overrides?: Partial<SessionInfoDto>): SessionInfoDto {
+  return {
+    id: CONVERSATION_ID,
+    provider: 'test-provider',
+    modelId: 'test-model',
+    createdAt: new Date('2026-07-12T00:00:00Z').toISOString(),
+    promptCount: 0,
+    channels: [],
+    durationMs: 0,
+    metrics: {
+      tokens: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
+      modelSwitches: 0,
+      messageCount: 0,
+      lastActivityAt: new Date('2026-07-12T00:00:00Z').toISOString(),
+    },
+    ...overrides,
+  };
+}
+
+function makeAgentSession(owner = USER_A): AgentSession {
+  return {
+    id: CONVERSATION_ID,
+    provider: 'test-provider',
+    modelId: 'test-model',
+    piSession: {
+      thinkingLevel: 'off',
+      getAvailableThinkingLevels: vi.fn().mockReturnValue(['off', 'low', 'high']),
+      setThinkingLevel: vi.fn(),
+      abort: vi.fn().mockResolvedValue(undefined),
+      prompt: vi.fn().mockResolvedValue(undefined),
+      dispose: vi.fn(),
+      getSessionStats: vi.fn(),
+      getContextUsage: vi.fn(),
+    } as unknown as AgentSession['piSession'],
+    listeners: new Set(),
+    unsubscribe: vi.fn(),
+    createdAt: Date.now(),
+    promptCount: 0,
+    channels: new Set(),
+    skillPromptAdditions: [],
+    sandboxDir: '/tmp',
+    allowedTools: null,
+    userId: owner.id,
+    tenantId: owner.tenantId,
+    metrics: {
+      tokens: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
+      modelSwitches: 0,
+      messageCount: 0,
+      lastActivityAt: new Date('2026-07-12T00:00:00Z').toISOString(),
+    },
+  };
+}
+
+function makeScopedAgentService() {
+  const foreign = makeAgentSession(USER_A);
+  return {
+    listSessions: vi.fn((scope?: { userId: string; tenantId?: string }) =>
+      scope?.userId === USER_B.id ? [] : [makeSessionInfo({ id: foreign.id })],
+    ),
+    getSessionInfo: vi.fn((_id: string, scope?: { userId: string; tenantId?: string }) =>
+      scope?.userId === USER_B.id ? undefined : makeSessionInfo({ id: foreign.id }),
+    ),
+    destroySession: vi.fn(),
+    getSession: vi.fn((_id: string, scope?: { userId: string; tenantId?: string }) =>
+      scope?.userId === USER_B.id ? undefined : foreign,
+    ),
+    createSession: vi.fn().mockRejectedValue(new ForbiddenException('Session scope mismatch')),
+    onEvent: vi.fn(() => vi.fn()),
+    addChannel: vi.fn(),
+    removeChannel: vi.fn(),
+    recordMessage: vi.fn(),
+    prompt: vi.fn().mockResolvedValue(undefined),
+  };
+}
+
+describe('TESS-M1-SEC-002 AgentService ownership boundary', () => {
+  it('requires explicit owner+tenant scope on protected session operations', () => {
+    const source = readFileSync(resolve('src/agent/agent.service.ts'), 'utf8');
+
+    expect(source).toContain('getSession(sessionId: string, scope: ActorTenantScope)');
+    expect(source).toContain('listSessions(scope: ActorTenantScope)');
+    expect(source).toContain('getSessionInfo(sessionId: string, scope: ActorTenantScope)');
+    expect(source).toContain(
+      'addChannel(sessionId: string, channel: string, scope: ActorTenantScope)',
+    );
+    expect(source).toContain(
+      'removeChannel(sessionId: string, channel: string, scope: ActorTenantScope)',
+    );
+    expect(source).toContain(
+      'async prompt(sessionId: string, message: string, scope: ActorTenantScope)',
+    );
+    expect(source).toContain('scope: ActorTenantScope,');
+    expect(source).toContain('async destroySession(sessionId: string, scope: ActorTenantScope)');
+    expect(source).not.toContain('scope?: ActorTenantScope');
+  });
+});
+
+describe('TESS-M1-SEC-002 REST session ownership and tenant binding', () => {
+  it('lists only sessions owned by the authenticated owner+tenant scope', () => {
+    const agentService = makeScopedAgentService();
+    const controller = new SessionsController(agentService as never);
+
+    expect(controller.list(USER_B)).toEqual({ sessions: [], total: 0 });
+    expect(agentService.listSessions).toHaveBeenCalledWith({
+      userId: USER_B.id,
+      tenantId: USER_B.tenantId,
+    });
+  });
+
+  it('does not reveal another owner/tenant session by guessed id', () => {
+    const agentService = makeScopedAgentService();
+    const controller = new SessionsController(agentService as never);
+
+    expect(() => controller.findOne(CONVERSATION_ID, USER_B)).toThrow(NotFoundException);
+    expect(agentService.getSessionInfo).toHaveBeenCalledWith(CONVERSATION_ID, {
+      userId: USER_B.id,
+      tenantId: USER_B.tenantId,
+    });
+  });
+
+  it('does not terminate another owner/tenant session by guessed id', async () => {
+    const agentService = makeScopedAgentService();
+    const controller = new SessionsController(agentService as never);
+
+    await expect(controller.destroy(CONVERSATION_ID, USER_B)).rejects.toBeInstanceOf(
+      NotFoundException,
+    );
+    expect(agentService.destroySession).not.toHaveBeenCalled();
+  });
+});
+
+describe('TESS-M1-SEC-002 REST chat send ownership and tenant binding', () => {
+  it('does not send a prompt into another owner/tenant session by guessed conversationId', async () => {
+    const agentService = makeScopedAgentService();
+    const controller = new ChatController(agentService as never);
+
+    await expect(
+      controller.chat({ conversationId: CONVERSATION_ID, content: 'take over' }, USER_B),
+    ).rejects.toMatchObject({ status: 404 });
+
+    expect(agentService.getSession).toHaveBeenCalledWith(CONVERSATION_ID, {
+      userId: USER_B.id,
+      tenantId: USER_B.tenantId,
+    });
+    expect(agentService.prompt).not.toHaveBeenCalled();
+  });
+});
+
+describe('TESS-M1-SEC-002 WebSocket session ownership and tenant binding', () => {
+  function makeGateway(agentService = makeScopedAgentService()) {
+    const brain = {
+      conversations: {
+        findById: vi.fn().mockResolvedValue(undefined),
+        create: vi.fn().mockResolvedValue(undefined),
+        update: vi.fn().mockResolvedValue(undefined),
+        findMessages: vi.fn().mockResolvedValue([]),
+        addMessage: vi.fn().mockResolvedValue(undefined),
+      },
+    };
+    const commandRegistry = { getManifest: vi.fn().mockReturnValue([]) };
+    const commandExecutor = { execute: vi.fn() };
+    const routingEngine = {
+      resolve: vi.fn().mockResolvedValue({ provider: 'test', model: 'test-model' }),
+    };
+    const gateway = new ChatGateway(
+      agentService as never,
+      {} as never,
+      brain as never,
+      commandRegistry as never,
+      commandExecutor as never,
+      routingEngine as never,
+    );
+    return { gateway, agentService };
+  }
+
+  function makeSocket() {
+    return {
+      id: 'socket-b',
+      connected: true,
+      data: { user: USER_B, session: { id: 'auth-session-b', userId: USER_B.id } },
+      emit: vi.fn(),
+      disconnect: vi.fn(),
+    };
+  }
+
+  it('does not attach or send to another owner/tenant session by guessed conversationId', async () => {
+    const { gateway, agentService } = makeGateway();
+    const socket = makeSocket();
+
+    await gateway.handleMessage(socket as never, {
+      conversationId: CONVERSATION_ID,
+      content: 'attach to foreign session',
+    });
+
+    expect(agentService.getSession).toHaveBeenCalledWith(CONVERSATION_ID, {
+      userId: USER_B.id,
+      tenantId: USER_B.tenantId,
+    });
+    expect(agentService.onEvent).not.toHaveBeenCalled();
+    expect(agentService.addChannel).not.toHaveBeenCalled();
+    expect(agentService.prompt).not.toHaveBeenCalled();
+    expect(socket.emit).toHaveBeenCalledWith(
+      'error',
+      expect.objectContaining({ conversationId: CONVERSATION_ID }),
+    );
+  });
+
+  it('does not mutate thinking level on another owner/tenant session', () => {
+    const { gateway, agentService } = makeGateway();
+    const socket = makeSocket();
+
+    gateway.handleSetThinking(socket as never, { conversationId: CONVERSATION_ID, level: 'high' });
+
+    expect(agentService.getSession).toHaveBeenCalledWith(CONVERSATION_ID, {
+      userId: USER_B.id,
+      tenantId: USER_B.tenantId,
+    });
+    expect(socket.emit).toHaveBeenCalledWith(
+      'error',
+      expect.objectContaining({ conversationId: CONVERSATION_ID }),
+    );
+  });
+
+  it('does not terminate another owner/tenant session over WebSocket abort', async () => {
+    const { gateway, agentService } = makeGateway();
+    const socket = makeSocket();
+
+    await gateway.handleAbort(socket as never, { conversationId: CONVERSATION_ID });
+
+    expect(agentService.getSession).toHaveBeenCalledWith(CONVERSATION_ID, {
+      userId: USER_B.id,
+      tenantId: USER_B.tenantId,
+    });
+    expect(socket.emit).toHaveBeenCalledWith(
+      'error',
+      expect.objectContaining({ conversationId: CONVERSATION_ID }),
+    );
+  });
+});

apps/gateway/src/agent/agent.module.ts

@@ -1,4 +1,5 @@
 import { Global, Module } from '@nestjs/common';
+import { AgentRuntimeProviderRegistry } from '@mosaicstack/agent';
 import { AgentService } from './agent.service.js';
 import { ProviderService } from './provider.service.js';
 import { ProviderCredentialsService } from './provider-credentials.service.js';
@@ -13,6 +14,14 @@ import { CoordModule } from '../coord/coord.module.js';
 import { McpClientModule } from '../mcp-client/mcp-client.module.js';
 import { SkillsModule } from '../skills/skills.module.js';
 import { GCModule } from '../gc/gc.module.js';
+import {
+  AGENT_RUNTIME_PROVIDER_REGISTRY,
+  DenyRuntimeApprovalVerifier,
+  RUNTIME_APPROVAL_VERIFIER,
+  RUNTIME_PROVIDER_AUDIT_SINK,
+  RuntimeProviderAuditService,
+  RuntimeProviderService,
+} from './runtime-provider-registry.service.js';
 
 @Global()
 @Module({
@@ -23,6 +32,21 @@ import { GCModule } from '../gc/gc.module.js';
     RoutingService,
     RoutingEngineService,
     SkillLoaderService,
+    {
+      provide: AGENT_RUNTIME_PROVIDER_REGISTRY,
+      useFactory: (): AgentRuntimeProviderRegistry => new AgentRuntimeProviderRegistry(),
+    },
+    RuntimeProviderAuditService,
+    {
+      provide: RUNTIME_PROVIDER_AUDIT_SINK,
+      useExisting: RuntimeProviderAuditService,
+    },
+    DenyRuntimeApprovalVerifier,
+    {
+      provide: RUNTIME_APPROVAL_VERIFIER,
+      useExisting: DenyRuntimeApprovalVerifier,
+    },
+    RuntimeProviderService,
     AgentService,
   ],
   controllers: [ProvidersController, SessionsController, AgentConfigsController, RoutingController],
@@ -33,6 +57,8 @@ import { GCModule } from '../gc/gc.module.js';
     RoutingService,
     RoutingEngineService,
     SkillLoaderService,
+    RuntimeProviderService,
+    AGENT_RUNTIME_PROVIDER_REGISTRY,
   ],
 })
 export class AgentModule {}

apps/gateway/src/agent/agent.service.ts

@@ -1,4 +1,11 @@
-import { Inject, Injectable, Logger, Optional, type OnModuleDestroy } from '@nestjs/common';
+import {
+  ForbiddenException,
+  Inject,
+  Injectable,
+  Logger,
+  Optional,
+  type OnModuleDestroy,
+} from '@nestjs/common';
 import {
   createAgentSession,
   DefaultResourceLoader,
@@ -28,6 +35,7 @@ import type { SessionInfoDto, SessionMetrics } from './session.dto.js';
 import { SystemOverrideService } from '../preferences/system-override.service.js';
 import { PreferencesService } from '../preferences/preferences.service.js';
 import { SessionGCService } from '../gc/session-gc.service.js';
+import type { ActorTenantScope } from '../auth/session-scope.js';
 
 /** A single message from DB conversation history, used for context injection. */
 export interface ConversationHistoryMessage {
@@ -68,6 +76,8 @@ export interface AgentSessionOptions {
   agentConfigId?: string;
   /** ID of the user who owns this session. Used for preferences and system override lookups. */
   userId?: string;
+  /** Server-derived tenant scope that owns this session. Falls back to userId for solo users. */
+  tenantId?: string;
   /**
    * Prior conversation messages to inject as context when resuming a session.
    * These messages are formatted and prepended to the system prompt so the
@@ -94,6 +104,8 @@ export interface AgentSession {
   allowedTools: string[] | null;
   /** User ID that owns this session, used for preference lookups. */
   userId?: string;
+  /** Server-derived tenant scope that owns this session. Falls back to userId for solo users. */
+  tenantId?: string;
   /** Agent config ID applied to this session, if any (M5-001). */
   agentConfigId?: string;
   /** Human-readable agent name applied to this session, if any (M5-001). */
@@ -174,12 +186,20 @@ export class AgentService implements OnModuleDestroy {
       .filter((t) => t.length > 0);
   }
 
-  async createSession(sessionId: string, options?: AgentSessionOptions): Promise<AgentSession> {
+  async createSession(sessionId: string, options: AgentSessionOptions): Promise<AgentSession> {
+    const scope = this.scopeFromOptions(options);
     const existing = this.sessions.get(sessionId);
-    if (existing) return existing;
+    if (existing) {
+      this.assertSessionScope(existing, scope);
+      return existing;
+    }
 
     const inflight = this.creating.get(sessionId);
-    if (inflight) return inflight;
+    if (inflight) {
+      const session = await inflight;
+      this.assertSessionScope(session, scope);
+      return session;
+    }
 
     const promise = this.doCreateSession(sessionId, options).finally(() => {
       this.creating.delete(sessionId);
@@ -342,6 +362,7 @@ export class AgentService implements OnModuleDestroy {
       sandboxDir,
       allowedTools,
       userId: mergedOptions?.userId,
+      tenantId: this.tenantIdFor(mergedOptions?.userId, mergedOptions?.tenantId),
       agentConfigId: mergedOptions?.agentConfigId,
       agentName: resolvedAgentName,
       metrics: {
@@ -473,38 +494,70 @@ export class AgentService implements OnModuleDestroy {
     return this.providerService.getDefaultModel() ?? null;
   }
 
-  getSession(sessionId: string): AgentSession | undefined {
+  getSession(sessionId: string, scope: ActorTenantScope): AgentSession | undefined {
-    return this.sessions.get(sessionId);
+    const session = this.sessions.get(sessionId);
+    if (!session || !this.sessionMatchesScope(session, scope)) return undefined;
+    return session;
   }
 
-  listSessions(): SessionInfoDto[] {
+  listSessions(scope: ActorTenantScope): SessionInfoDto[] {
     const now = Date.now();
-    return Array.from(this.sessions.values()).map((s) => ({
+    return Array.from(this.sessions.values())
-      id: s.id,
+      .filter((s) => this.sessionMatchesScope(s, scope))
-      provider: s.provider,
+      .map((s) => this.toSessionInfo(s, now));
-      modelId: s.modelId,
-      ...(s.agentName ? { agentName: s.agentName } : {}),
-      createdAt: new Date(s.createdAt).toISOString(),
-      promptCount: s.promptCount,
-      channels: Array.from(s.channels),
-      durationMs: now - s.createdAt,
-      metrics: { ...s.metrics },
-    }));
   }
 
-  getSessionInfo(sessionId: string): SessionInfoDto | undefined {
+  listAllSessionsForSystem(): SessionInfoDto[] {
+    const now = Date.now();
+    return Array.from(this.sessions.values()).map((s) => this.toSessionInfo(s, now));
+  }
+
+  getSessionInfo(sessionId: string, scope: ActorTenantScope): SessionInfoDto | undefined {
     const s = this.sessions.get(sessionId);
-    if (!s) return undefined;
+    if (!s || !this.sessionMatchesScope(s, scope)) return undefined;
+    return this.toSessionInfo(s);
+  }
+
+  private scopeFromOptions(options: AgentSessionOptions): ActorTenantScope {
+    if (!options.userId) {
+      throw new ForbiddenException('Session owner scope is required');
+    }
     return {
-      id: s.id,
+      userId: options.userId,
-      provider: s.provider,
+      tenantId: this.tenantIdFor(options.userId, options.tenantId) ?? options.userId,
-      modelId: s.modelId,
+    };
-      ...(s.agentName ? { agentName: s.agentName } : {}),
+  }
-      createdAt: new Date(s.createdAt).toISOString(),
+
-      promptCount: s.promptCount,
+  private tenantIdFor(
-      channels: Array.from(s.channels),
+    userId: string | undefined,
-      durationMs: Date.now() - s.createdAt,
+    tenantId: string | undefined,
-      metrics: { ...s.metrics },
+  ): string | undefined {
+    return tenantId ?? userId;
+  }
+
+  private sessionMatchesScope(session: AgentSession, scope: ActorTenantScope): boolean {
+    return (
+      session.userId === scope.userId && (session.tenantId ?? session.userId) === scope.tenantId
+    );
+  }
+
+  private assertSessionScope(session: AgentSession, scope: ActorTenantScope): void {
+    if (!this.sessionMatchesScope(session, scope)) {
+      throw new ForbiddenException('Session does not belong to the current owner/tenant scope');
+    }
+  }
+
+  private toSessionInfo(session: AgentSession, now = Date.now()): SessionInfoDto {
+    return {
+      id: session.id,
+      provider: session.provider,
+      modelId: session.modelId,
+      ...(session.agentName ? { agentName: session.agentName } : {}),
+      createdAt: new Date(session.createdAt).toISOString(),
+      promptCount: session.promptCount,
+      channels: Array.from(session.channels),
+      durationMs: now - session.createdAt,
+      metrics: { ...session.metrics },
     };
   }
 
@@ -553,9 +606,10 @@ export class AgentService implements OnModuleDestroy {
    * not reconstructed — the model is used on the next createSession call for
    * the same conversationId when the session is torn down or a new one is created.
    */
-  updateSessionModel(sessionId: string, modelId: string): void {
+  updateSessionModel(sessionId: string, modelId: string, scope: ActorTenantScope): void {
     const session = this.sessions.get(sessionId);
     if (!session) return;
+    this.assertSessionScope(session, scope);
     const prev = session.modelId;
     session.modelId = modelId;
     this.recordModelSwitch(sessionId);
@@ -572,48 +626,51 @@ export class AgentService implements OnModuleDestroy {
     sessionId: string,
     agentConfigId: string,
     agentName: string,
+    scope: ActorTenantScope,
     modelId?: string,
   ): void {
     const session = this.sessions.get(sessionId);
     if (!session) return;
+    this.assertSessionScope(session, scope);
     session.agentConfigId = agentConfigId;
     session.agentName = agentName;
     if (modelId) {
-      this.updateSessionModel(sessionId, modelId);
+      this.updateSessionModel(sessionId, modelId, scope);
     }
     this.logger.log(
       `Session ${sessionId}: agent switched to "${agentName}" (${agentConfigId}) (M5-003)`,
     );
   }
 
-  addChannel(sessionId: string, channel: string): void {
+  addChannel(sessionId: string, channel: string, scope: ActorTenantScope): void {
     const session = this.sessions.get(sessionId);
-    if (session) {
+    if (!session) return;
-      session.channels.add(channel);
+    this.assertSessionScope(session, scope);
-    }
+    session.channels.add(channel);
   }
 
-  removeChannel(sessionId: string, channel: string): void {
+  removeChannel(sessionId: string, channel: string, scope: ActorTenantScope): void {
     const session = this.sessions.get(sessionId);
-    if (session) {
+    if (!session) return;
-      session.channels.delete(channel);
+    this.assertSessionScope(session, scope);
-    }
+    session.channels.delete(channel);
   }
 
-  async prompt(sessionId: string, message: string): Promise<void> {
+  async prompt(sessionId: string, message: string, scope: ActorTenantScope): Promise<void> {
     const session = this.sessions.get(sessionId);
     if (!session) {
       throw new Error(`No agent session found: ${sessionId}`);
     }
+    this.assertSessionScope(session, scope);
     session.promptCount += 1;
 
     // Prepend session-scoped system override if present (renew TTL on each turn)
     let effectiveMessage = message;
     if (this.systemOverride) {
-      const override = await this.systemOverride.get(sessionId);
+      const override = await this.systemOverride.get(sessionId, scope);
       if (override) {
         effectiveMessage = `[System Override]\n${override}\n\n${message}`;
-        await this.systemOverride.renew(sessionId);
+        await this.systemOverride.renew(sessionId, scope);
         this.logger.debug(`Applied system override for session ${sessionId}`);
       }
     }
@@ -629,16 +686,28 @@ export class AgentService implements OnModuleDestroy {
     }
   }
 
-  onEvent(sessionId: string, listener: (event: AgentSessionEvent) => void): () => void {
+  onEvent(
+    sessionId: string,
+    listener: (event: AgentSessionEvent) => void,
+    scope: ActorTenantScope,
+  ): () => void {
     const session = this.sessions.get(sessionId);
     if (!session) {
       throw new Error(`No agent session found: ${sessionId}`);
     }
+    this.assertSessionScope(session, scope);
     session.listeners.add(listener);
     return () => session.listeners.delete(listener);
   }
 
-  async destroySession(sessionId: string): Promise<void> {
+  async destroySession(sessionId: string, scope: ActorTenantScope): Promise<void> {
+    const session = this.sessions.get(sessionId);
+    if (!session) return;
+    this.assertSessionScope(session, scope);
+    await this.destroySessionForSystem(sessionId);
+  }
+
+  private async destroySessionForSystem(sessionId: string): Promise<void> {
     const session = this.sessions.get(sessionId);
     if (!session) return;
     this.logger.log(`Destroying agent session ${sessionId}`);
@@ -667,7 +736,7 @@ export class AgentService implements OnModuleDestroy {
 
   async onModuleDestroy(): Promise<void> {
     this.logger.log('Shutting down all agent sessions');
-    const stops = Array.from(this.sessions.keys()).map((id) => this.destroySession(id));
+    const stops = Array.from(this.sessions.keys()).map((id) => this.destroySessionForSystem(id));
     const results = await Promise.allSettled(stops);
     for (const result of results) {
       if (result.status === 'rejected') {

apps/gateway/src/agent/runtime-provider-registry.service.ts

@@ -0,0 +1,404 @@
+import { ForbiddenException, Inject, Injectable, Logger, NotFoundException } from '@nestjs/common';
+import { AgentRuntimeProviderRegistry } from '@mosaicstack/agent';
+import type {
+  AgentRuntimeProvider,
+  RuntimeAttachHandle,
+  RuntimeAttachMode,
+  RuntimeCapability,
+  RuntimeCapabilitySet,
+  RuntimeHealth,
+  RuntimeMessage,
+  RuntimeScope,
+  RuntimeSession,
+  RuntimeSessionTree,
+  RuntimeStreamEvent,
+} from '@mosaicstack/types';
+import type { ActorTenantScope } from '../auth/session-scope.js';
+
+export const AGENT_RUNTIME_PROVIDER_REGISTRY = Symbol('AGENT_RUNTIME_PROVIDER_REGISTRY');
+export const RUNTIME_PROVIDER_AUDIT_SINK = Symbol('RUNTIME_PROVIDER_AUDIT_SINK');
+export const RUNTIME_APPROVAL_VERIFIER = Symbol('RUNTIME_APPROVAL_VERIFIER');
+
+export type RuntimeProviderOperation =
+  | RuntimeCapability
+  | 'runtime.capabilities'
+  | 'runtime.health';
+export type RuntimeProviderAuditOutcome = 'requested' | 'succeeded' | 'denied' | 'failed';
+
+/** Trusted server-side context only; it intentionally excludes client-provided identity fields. */
+export interface RuntimeProviderRequestContext {
+  actorScope: ActorTenantScope;
+  channelId: string;
+  correlationId: string;
+}
+
+/** Metadata-only audit record. Message bodies, idempotency keys, and approval refs are excluded. */
+export interface RuntimeAuditEvent {
+  providerId: string;
+  operation: RuntimeProviderOperation;
+  outcome: RuntimeProviderAuditOutcome;
+  actorId: string;
+  tenantId: string;
+  channelId: string;
+  correlationId: string;
+  resourceId?: string;
+}
+
+export interface RuntimeAuditSink {
+  record(event: RuntimeAuditEvent): Promise<void>;
+}
+
+/** Exact action shape that a durable approval implementation must consume once. */
+export interface RuntimeTerminationAction {
+  providerId: string;
+  sessionId: string;
+  actorId: string;
+  tenantId: string;
+  channelId: string;
+  correlationId: string;
+}
+
+export interface RuntimeApprovalVerifier {
+  consume(approvalRef: string, action: RuntimeTerminationAction): Promise<boolean>;
+}
+
+class RuntimeApprovalDeniedError extends Error {
+  constructor() {
+    super('Runtime termination approval denied');
+  }
+}
+
+/**
+ * The default denies all runtime termination until a durable, exact-action
+ * approval implementation is configured. This is safer than a permissive stub.
+ */
+@Injectable()
+export class DenyRuntimeApprovalVerifier implements RuntimeApprovalVerifier {
+  async consume(_approvalRef: string, _action: RuntimeTerminationAction): Promise<boolean> {
+    return false;
+  }
+}
+
+/**
+ * Temporary metadata-only audit sink. M1 observability can replace this token
+ * with a durable audit writer without changing provider call sites.
+ */
+@Injectable()
+export class RuntimeProviderAuditService implements RuntimeAuditSink {
+  private readonly logger = new Logger(RuntimeProviderAuditService.name);
+
+  async record(event: RuntimeAuditEvent): Promise<void> {
+    this.logger.log(JSON.stringify(event));
+  }
+}
+
+@Injectable()
+export class RuntimeProviderService {
+  private readonly logger = new Logger(RuntimeProviderService.name);
+
+  constructor(
+    @Inject(AGENT_RUNTIME_PROVIDER_REGISTRY)
+    private readonly registry: AgentRuntimeProviderRegistry,
+    @Inject(RUNTIME_PROVIDER_AUDIT_SINK)
+    private readonly audit: RuntimeAuditSink,
+    @Inject(RUNTIME_APPROVAL_VERIFIER)
+    private readonly approvals: RuntimeApprovalVerifier,
+  ) {}
+
+  async capabilities(
+    providerId: string,
+    context: RuntimeProviderRequestContext,
+  ): Promise<RuntimeCapabilitySet> {
+    return this.execute(
+      providerId,
+      'runtime.capabilities',
+      undefined,
+      undefined,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<RuntimeCapabilitySet> =>
+        provider.capabilities(scope),
+    );
+  }
+
+  async health(providerId: string, context: RuntimeProviderRequestContext): Promise<RuntimeHealth> {
+    return this.execute(
+      providerId,
+      'runtime.health',
+      undefined,
+      undefined,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<RuntimeHealth> =>
+        provider.health(scope),
+    );
+  }
+
+  async listSessions(
+    providerId: string,
+    context: RuntimeProviderRequestContext,
+  ): Promise<RuntimeSession[]> {
+    return this.execute(
+      providerId,
+      'session.list',
+      'session.list',
+      undefined,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<RuntimeSession[]> =>
+        provider.listSessions(scope),
+    );
+  }
+
+  async getSessionTree(
+    providerId: string,
+    context: RuntimeProviderRequestContext,
+  ): Promise<RuntimeSessionTree[]> {
+    return this.execute(
+      providerId,
+      'session.tree',
+      'session.tree',
+      undefined,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<RuntimeSessionTree[]> =>
+        provider.getSessionTree(scope),
+    );
+  }
+
+  streamSession(
+    providerId: string,
+    sessionId: string,
+    cursor: string | undefined,
+    context: RuntimeProviderRequestContext,
+  ): AsyncIterable<RuntimeStreamEvent> {
+    return this.stream(
+      providerId,
+      'session.stream',
+      'session.stream',
+      sessionId,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): AsyncIterable<RuntimeStreamEvent> =>
+        provider.streamSession(sessionId, cursor, scope),
+    );
+  }
+
+  async sendMessage(
+    providerId: string,
+    sessionId: string,
+    message: RuntimeMessage,
+    context: RuntimeProviderRequestContext,
+  ): Promise<void> {
+    await this.execute(
+      providerId,
+      'session.send',
+      'session.send',
+      sessionId,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<void> =>
+        provider.sendMessage(sessionId, message, scope),
+    );
+  }
+
+  async attach(
+    providerId: string,
+    sessionId: string,
+    mode: RuntimeAttachMode,
+    context: RuntimeProviderRequestContext,
+  ): Promise<RuntimeAttachHandle> {
+    return this.execute(
+      providerId,
+      'session.attach',
+      'session.attach',
+      sessionId,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<RuntimeAttachHandle> =>
+        provider.attach(sessionId, mode, scope),
+    );
+  }
+
+  async detach(
+    providerId: string,
+    attachmentId: string,
+    context: RuntimeProviderRequestContext,
+  ): Promise<void> {
+    await this.execute(
+      providerId,
+      'session.attach',
+      'session.attach',
+      attachmentId,
+      context,
+      (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<void> =>
+        provider.detach(attachmentId, scope),
+    );
+  }
+
+  async terminate(
+    providerId: string,
+    sessionId: string,
+    approvalRef: string,
+    context: RuntimeProviderRequestContext,
+  ): Promise<void> {
+    await this.execute(
+      providerId,
+      'session.terminate',
+      'session.terminate',
+      sessionId,
+      context,
+      async (provider: AgentRuntimeProvider, scope: RuntimeScope): Promise<void> => {
+        const approved = await this.approvals.consume(approvalRef, {
+          providerId,
+          sessionId,
+          actorId: scope.actorId,
+          tenantId: scope.tenantId,
+          channelId: scope.channelId,
+          correlationId: scope.correlationId,
+        });
+        if (!approved) {
+          throw new RuntimeApprovalDeniedError();
+        }
+        await provider.terminate(sessionId, approvalRef, scope);
+      },
+    );
+  }
+
+  private async execute<T>(
+    providerId: string,
+    operation: RuntimeProviderOperation,
+    requiredCapability: RuntimeCapability | undefined,
+    resourceId: string | undefined,
+    context: RuntimeProviderRequestContext,
+    invoke: (provider: AgentRuntimeProvider, scope: RuntimeScope) => Promise<T>,
+  ): Promise<T> {
+    const scope = this.deriveScope(context);
+    await this.record(providerId, operation, 'requested', scope, resourceId);
+    let invocationStarted = false;
+    try {
+      const provider = this.provider(providerId);
+      if (requiredCapability) {
+        await this.assertCapability(provider, requiredCapability, scope);
+      }
+      invocationStarted = true;
+      const result = await invoke(provider, scope);
+      await this.recordCompletion(providerId, operation, scope, resourceId);
+      return result;
+    } catch (error: unknown) {
+      if (invocationStarted && !(error instanceof RuntimeApprovalDeniedError)) {
+        await this.recordFailure(providerId, operation, scope, resourceId);
+      } else {
+        await this.record(providerId, operation, 'denied', scope, resourceId);
+      }
+      throw error;
+    }
+  }
+
+  private async *stream(
+    providerId: string,
+    operation: RuntimeProviderOperation,
+    requiredCapability: RuntimeCapability,
+    resourceId: string,
+    context: RuntimeProviderRequestContext,
+    invoke: (
+      provider: AgentRuntimeProvider,
+      scope: RuntimeScope,
+    ) => AsyncIterable<RuntimeStreamEvent>,
+  ): AsyncIterable<RuntimeStreamEvent> {
+    const scope = this.deriveScope(context);
+    await this.record(providerId, operation, 'requested', scope, resourceId);
+    let invocationStarted = false;
+    try {
+      const provider = this.provider(providerId);
+      await this.assertCapability(provider, requiredCapability, scope);
+      invocationStarted = true;
+      for await (const event of invoke(provider, scope)) {
+        yield event;
+      }
+      await this.recordCompletion(providerId, operation, scope, resourceId);
+    } catch (error: unknown) {
+      if (invocationStarted) {
+        await this.recordFailure(providerId, operation, scope, resourceId);
+      } else {
+        await this.record(providerId, operation, 'denied', scope, resourceId);
+      }
+      throw error;
+    }
+  }
+
+  private provider(providerId: string): AgentRuntimeProvider {
+    try {
+      return this.registry.require(providerId);
+    } catch (error: unknown) {
+      const message = error instanceof Error ? error.message : 'Runtime provider is not registered';
+      throw new NotFoundException(message);
+    }
+  }
+
+  private async assertCapability(
+    provider: AgentRuntimeProvider,
+    requiredCapability: RuntimeCapability,
+    scope: RuntimeScope,
+  ): Promise<void> {
+    const capabilities = await provider.capabilities(scope);
+    if (!capabilities.supported.includes(requiredCapability)) {
+      throw new ForbiddenException(`Runtime provider capability denied: ${requiredCapability}`);
+    }
+  }
+
+  private deriveScope(context: RuntimeProviderRequestContext): RuntimeScope {
+    const actorId = context.actorScope.userId.trim();
+    const tenantId = context.actorScope.tenantId.trim();
+    const channelId = context.channelId.trim();
+    const correlationId = context.correlationId.trim();
+    if (!actorId || !tenantId || !channelId || !correlationId) {
+      throw new ForbiddenException(
+        'Authenticated runtime actor scope and correlation are required',
+      );
+    }
+    return Object.freeze({ actorId, tenantId, channelId, correlationId });
+  }
+
+  private async recordFailure(
+    providerId: string,
+    operation: RuntimeProviderOperation,
+    scope: RuntimeScope,
+    resourceId: string | undefined,
+  ): Promise<void> {
+    try {
+      await this.record(providerId, operation, 'failed', scope, resourceId);
+    } catch {
+      this.logger.error(
+        `Runtime provider failure audit failed provider=${providerId} operation=${operation} correlation=${scope.correlationId}`,
+      );
+    }
+  }
+
+  private async recordCompletion(
+    providerId: string,
+    operation: RuntimeProviderOperation,
+    scope: RuntimeScope,
+    resourceId: string | undefined,
+  ): Promise<void> {
+    try {
+      await this.record(providerId, operation, 'succeeded', scope, resourceId);
+    } catch {
+      this.logger.error(
+        `Runtime provider completion audit failed provider=${providerId} operation=${operation} correlation=${scope.correlationId}`,
+      );
+    }
+  }
+
+  private async record(
+    providerId: string,
+    operation: RuntimeProviderOperation,
+    outcome: RuntimeProviderAuditOutcome,
+    scope: RuntimeScope,
+    resourceId: string | undefined,
+  ): Promise<void> {
+    await this.audit.record({
+      providerId,
+      operation,
+      outcome,
+      actorId: scope.actorId,
+      tenantId: scope.tenantId,
+      channelId: scope.channelId,
+      correlationId: scope.correlationId,
+      ...(resourceId ? { resourceId } : {}),
+    });
+  }
+}

apps/gateway/src/agent/sessions.controller.ts

@@ -10,6 +10,8 @@ import {
   UseGuards,
 } from '@nestjs/common';
 import { AuthGuard } from '../auth/auth.guard.js';
+import { CurrentUser } from '../auth/current-user.decorator.js';
+import { scopeFromUser, type AuthenticatedUserLike } from '../auth/session-scope.js';
 import { AgentService } from './agent.service.js';
 
 @Controller('api/sessions')
@@ -18,23 +20,24 @@ export class SessionsController {
   constructor(@Inject(AgentService) private readonly agentService: AgentService) {}
 
   @Get()
-  list() {
+  list(@CurrentUser() user: AuthenticatedUserLike) {
-    const sessions = this.agentService.listSessions();
+    const sessions = this.agentService.listSessions(scopeFromUser(user));
     return { sessions, total: sessions.length };
   }
 
   @Get(':id')
-  findOne(@Param('id') id: string) {
+  findOne(@Param('id') id: string, @CurrentUser() user: AuthenticatedUserLike) {
-    const info = this.agentService.getSessionInfo(id);
+    const info = this.agentService.getSessionInfo(id, scopeFromUser(user));
     if (!info) throw new NotFoundException('Session not found');
     return info;
   }
 
   @Delete(':id')
   @HttpCode(HttpStatus.NO_CONTENT)
-  async destroy(@Param('id') id: string) {
+  async destroy(@Param('id') id: string, @CurrentUser() user: AuthenticatedUserLike) {
-    const info = this.agentService.getSessionInfo(id);
+    const scope = scopeFromUser(user);
+    const info = this.agentService.getSessionInfo(id, scope);
     if (!info) throw new NotFoundException('Session not found');
-    await this.agentService.destroySession(id);
+    await this.agentService.destroySession(id, scope);
   }
 }

apps/gateway/src/auth/session-scope.ts

@@ -0,0 +1,24 @@
+export interface AuthenticatedUserLike {
+  id: string;
+  tenantId?: string | null;
+  teamId?: string | null;
+  organizationId?: string | null;
+  orgId?: string | null;
+}
+
+export interface ActorTenantScope {
+  userId: string;
+  tenantId: string;
+}
+
+/**
+ * Build the immutable server-derived scope used for Tess session operations.
+ * Current Mosaic auth is user-scoped; future org/team claims can populate one
+ * of the tenant fields without allowing clients to choose another tenant.
+ */
+export function scopeFromUser(user: AuthenticatedUserLike): ActorTenantScope {
+  return {
+    userId: user.id,
+    tenantId: user.tenantId ?? user.teamId ?? user.organizationId ?? user.orgId ?? user.id,
+  };
+}

apps/gateway/src/chat/__tests__/chat-security.test.ts

@@ -12,7 +12,8 @@ describe('Chat controller source hardening', () => {
     const source = readFileSync(resolve('src/chat/chat.controller.ts'), 'utf8');
 
     expect(source).toContain('@UseGuards(AuthGuard)');
-    expect(source).toContain('@CurrentUser() user: { id: string }');
+    expect(source).toContain('@CurrentUser() user: AuthenticatedUserLike');
+    expect(source).toContain('const scope = scopeFromUser(user);');
   });
 });
 

apps/gateway/src/chat/chat.controller.ts

@@ -3,8 +3,10 @@ import {
   Post,
   Body,
   Logger,
+  ForbiddenException,
   HttpException,
   HttpStatus,
+  NotFoundException,
   Inject,
   UseGuards,
 } from '@nestjs/common';
@@ -13,6 +15,7 @@ import { Throttle } from '@nestjs/throttler';
 import { AgentService } from '../agent/agent.service.js';
 import { AuthGuard } from '../auth/auth.guard.js';
 import { CurrentUser } from '../auth/current-user.decorator.js';
+import { scopeFromUser, type AuthenticatedUserLike } from '../auth/session-scope.js';
 import { v4 as uuid } from 'uuid';
 import { ChatRequestDto } from './chat.dto.js';
 
@@ -32,16 +35,23 @@ export class ChatController {
   @Throttle({ default: { limit: 10, ttl: 60_000 } })
   async chat(
     @Body() body: ChatRequestDto,
-    @CurrentUser() user: { id: string },
+    @CurrentUser() user: AuthenticatedUserLike,
   ): Promise<ChatResponse> {
     const conversationId = body.conversationId ?? uuid();
+    const scope = scopeFromUser(user);
 
     try {
-      let agentSession = this.agentService.getSession(conversationId);
+      let agentSession = this.agentService.getSession(conversationId, scope);
       if (!agentSession) {
-        agentSession = await this.agentService.createSession(conversationId);
+        agentSession = await this.agentService.createSession(conversationId, {
+          userId: scope.userId,
+          tenantId: scope.tenantId,
+        });
       }
     } catch (err) {
+      if (err instanceof ForbiddenException) {
+        throw new NotFoundException('Session not found');
+      }
       this.logger.error(
         `Session creation failed for conversation=${conversationId}`,
         err instanceof Error ? err.stack : String(err),
@@ -60,20 +70,27 @@ export class ChatController {
         reject(new Error('Agent response timed out'));
       }, 120_000);
 
-      const cleanup = this.agentService.onEvent(conversationId, (event: AgentSessionEvent) => {
+      const cleanup = this.agentService.onEvent(
-        if (event.type === 'message_update' && event.assistantMessageEvent.type === 'text_delta') {
+        conversationId,
-          responseText += event.assistantMessageEvent.delta;
+        (event: AgentSessionEvent) => {
-        }
+          if (
-        if (event.type === 'agent_end') {
+            event.type === 'message_update' &&
-          clearTimeout(timer);
+            event.assistantMessageEvent.type === 'text_delta'
-          cleanup();
+          ) {
-          resolve();
+            responseText += event.assistantMessageEvent.delta;
-        }
+          }
-      });
+          if (event.type === 'agent_end') {
+            clearTimeout(timer);
+            cleanup();
+            resolve();
+          }
+        },
+        scope,
+      );
     });
 
     try {
-      await this.agentService.prompt(conversationId, body.content);
+      await this.agentService.prompt(conversationId, body.content, scope);
       await done;
     } catch (err) {
       if (err instanceof HttpException) throw err;

apps/gateway/src/chat/chat.gateway-auth.ts

@@ -1,3 +1,4 @@
+import { timingSafeEqual } from 'node:crypto';
 import type { IncomingHttpHeaders } from 'node:http';
 import { fromNodeHeaders } from 'better-auth/node';
 
@@ -12,6 +13,19 @@ export interface SessionAuth {
   };
 }
 
+export function validateDiscordServiceToken(
+  candidate: unknown,
+  expected: string | undefined,
+): boolean {
+  if (typeof candidate !== 'string' || !expected) return false;
+  const candidateBuffer = Buffer.from(candidate);
+  const expectedBuffer = Buffer.from(expected);
+  return (
+    candidateBuffer.length === expectedBuffer.length &&
+    timingSafeEqual(candidateBuffer, expectedBuffer)
+  );
+}
+
 export async function validateSocketSession(
   headers: IncomingHttpHeaders,
   auth: SessionAuth,

apps/gateway/src/chat/chat.gateway-command-approval.spec.ts

@@ -0,0 +1,74 @@
+import { describe, expect, it, vi } from 'vitest';
+import type { SlashCommandPayload } from '@mosaicstack/types';
+import { ChatGateway } from './chat.gateway.js';
+
+const payload: SlashCommandPayload = {
+  command: 'gc',
+  conversationId: 'conversation-1',
+  approvalId: 'approval-1',
+};
+
+function buildGateway(commandExecutor: {
+  execute: ReturnType<typeof vi.fn>;
+  createApproval: ReturnType<typeof vi.fn>;
+}): ChatGateway {
+  return new ChatGateway(
+    {} as never,
+    {} as never,
+    {} as never,
+    {} as never,
+    commandExecutor as never,
+    {} as never,
+  );
+}
+
+describe('ChatGateway command approval ingress', () => {
+  it('passes the client approval ID through to command execution while deriving the actor server-side', async (): Promise<void> => {
+    const commandExecutor = {
+      execute: vi.fn().mockResolvedValue({ ...payload, success: true }),
+      createApproval: vi.fn(),
+    };
+    const gateway = buildGateway(commandExecutor);
+    const client = { data: { user: { id: 'admin-1' } }, emit: vi.fn() };
+
+    await gateway.handleCommandExecute(client as never, payload);
+
+    expect(commandExecutor.execute).toHaveBeenCalledWith(payload, {
+      userId: 'admin-1',
+      tenantId: 'admin-1',
+    });
+    expect(client.emit).toHaveBeenCalledWith(
+      'command:result',
+      expect.objectContaining({ success: true }),
+    );
+  });
+
+  it('issues a durable approval only for the authenticated actor', async (): Promise<void> => {
+    const commandExecutor = {
+      execute: vi.fn(),
+      createApproval: vi.fn().mockResolvedValue({
+        approvalId: 'approval-1',
+        expiresAt: '2026-07-12T00:05:00.000Z',
+      }),
+    };
+    const gateway = buildGateway(commandExecutor);
+    const client = { data: { user: { id: 'admin-1' } }, emit: vi.fn() };
+
+    await gateway.handleCommandApproval(client as never, {
+      command: 'gc',
+      conversationId: 'conversation-1',
+    });
+
+    expect(commandExecutor.createApproval).toHaveBeenCalledWith(
+      { command: 'gc', conversationId: 'conversation-1' },
+      { userId: 'admin-1', tenantId: 'admin-1' },
+    );
+    expect(client.emit).toHaveBeenCalledWith('command:approval', {
+      command: 'gc',
+      conversationId: 'conversation-1',
+      success: true,
+      approvalId: 'approval-1',
+      expiresAt: '2026-07-12T00:05:00.000Z',
+    });
+  });
+});

apps/gateway/src/chat/chat.gateway-redaction.spec.ts

@@ -0,0 +1,170 @@
+import { describe, expect, it, vi } from 'vitest';
+import { ChatGateway } from './chat.gateway.js';
+
+const CONVERSATION_ID = 'conversation-1';
+const CANARY = 'sk_canary12345678';
+
+type GatewayInternals = {
+  clientSessions: Map<string, unknown>;
+  relayEvent(client: unknown, conversationId: string, event: unknown): void;
+};
+
+function buildGateway() {
+  const brain = {
+    conversations: {
+      addMessage: vi.fn().mockResolvedValue(undefined),
+    },
+  };
+  const agentService = {
+    getSession: vi.fn().mockReturnValue(undefined),
+  };
+  const gateway = new ChatGateway(
+    agentService as never,
+    {} as never,
+    brain as never,
+    {} as never,
+    {} as never,
+    {} as never,
+  );
+
+  return { gateway: gateway as unknown as GatewayInternals, brain };
+}
+
+describe('ChatGateway redaction boundary', (): void => {
+  it('redacts a secret split across assistant deltas before egress and persistence', (): void => {
+    const { gateway } = buildGateway();
+    const client = {
+      connected: true,
+      id: 'client-1',
+      data: { user: { id: 'user-1' } },
+      emit: vi.fn(),
+    };
+    const session = {
+      conversationId: CONVERSATION_ID,
+      cleanup: vi.fn(),
+      assistantText: '',
+      toolCalls: [],
+      pendingToolCalls: new Map(),
+      scope: { userId: 'user-1', tenantId: 'tenant-1' },
+    };
+    gateway.clientSessions.set(client.id, session);
+
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: 'sk_canary' },
+    });
+
+    expect(JSON.stringify(client.emit.mock.calls)).not.toContain('sk_canary');
+
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: '12345678 ' },
+    });
+
+    expect(client.emit).toHaveBeenCalledWith('agent:text', {
+      conversationId: CONVERSATION_ID,
+      text: '[REDACTED_SECRET] ',
+    });
+    expect(session.assistantText).toBe(`${CANARY} `);
+    expect(JSON.stringify(client.emit.mock.calls)).not.toContain(CANARY);
+  });
+
+  it('retains a split secret label until its value can be redacted', (): void => {
+    const { gateway } = buildGateway();
+    const client = {
+      connected: true,
+      id: 'client-1',
+      data: { user: { id: 'user-1' } },
+      emit: vi.fn(),
+    };
+
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: 'token ' },
+    });
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: '=canaryvalue123 ' },
+    });
+
+    expect(client.emit).toHaveBeenCalledWith('agent:text', {
+      conversationId: CONVERSATION_ID,
+      text: '[REDACTED_SECRET] ',
+    });
+    expect(JSON.stringify(client.emit.mock.calls)).not.toContain('canaryvalue123');
+  });
+
+  it('holds a streamed private key until it can be redacted', (): void => {
+    const { gateway } = buildGateway();
+    const client = {
+      connected: true,
+      id: 'client-1',
+      data: { user: { id: 'user-1' } },
+      emit: vi.fn(),
+    };
+
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: '-----BEGIN PRIVATE KEY-----\ncanary' },
+    });
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: '\n-----END PRIVATE KEY-----' },
+    });
+
+    expect(client.emit).toHaveBeenCalledWith('agent:text', {
+      conversationId: CONVERSATION_ID,
+      text: '[REDACTED_SECRET]',
+    });
+    expect(JSON.stringify(client.emit.mock.calls)).not.toContain('canary');
+  });
+
+  it('drops an oversized unterminated stream fragment rather than retaining it', (): void => {
+    const { gateway } = buildGateway();
+    const client = {
+      connected: true,
+      id: 'client-1',
+      data: { user: { id: 'user-1' } },
+      emit: vi.fn(),
+    };
+
+    gateway.relayEvent(client, CONVERSATION_ID, {
+      type: 'message_update',
+      assistantMessageEvent: { type: 'text_delta', delta: 'x'.repeat(8_193) },
+    });
+
+    expect(client.emit).toHaveBeenCalledWith('agent:text', {
+      conversationId: CONVERSATION_ID,
+      text: '[REDACTED_STREAM_OVERFLOW]',
+    });
+  });
+
+  it('persists only redacted assistant content with classifications', (): void => {
+    const { gateway, brain } = buildGateway();
+    const client = {
+      connected: true,
+      id: 'client-1',
+      data: { user: { id: 'user-1' } },
+      emit: vi.fn(),
+    };
+    gateway.clientSessions.set(client.id, {
+      conversationId: CONVERSATION_ID,
+      cleanup: vi.fn(),
+      assistantText: CANARY,
+      toolCalls: [],
+      pendingToolCalls: new Map(),
+      scope: { userId: 'user-1', tenantId: 'tenant-1' },
+    });
+
+    gateway.relayEvent(client, CONVERSATION_ID, { type: 'agent_end' });
+
+    expect(brain.conversations.addMessage).toHaveBeenCalledWith(
+      expect.objectContaining({
+        content: '[REDACTED_SECRET]',
+        metadata: expect.objectContaining({ classifications: ['secret'] }),
+      }),
+      'user-1',
+    );
+    expect(JSON.stringify(brain.conversations.addMessage.mock.calls)).not.toContain(CANARY);
+  });
+});

apps/gateway/src/chat/chat.gateway.ts

@@ -11,10 +11,17 @@ import {
 } from '@nestjs/websockets';
 import { Server, Socket } from 'socket.io';
 import type { AgentSessionEvent } from '@mariozechner/pi-coding-agent';
+import {
+  verifyDiscordIngressEnvelope,
+  type DiscordIngressEnvelope,
+  type DiscordIngressPayload,
+} from '@mosaicstack/discord-plugin';
 import type { Auth } from '@mosaicstack/auth';
 import type { Brain } from '@mosaicstack/brain';
+import { redactSensitiveContent } from '@mosaicstack/log';
 import type {
   SetThinkingPayload,
+  SlashCommandApprovalResultPayload,
   SlashCommandPayload,
   SystemReloadPayload,
   RoutingDecisionInfo,
@@ -22,13 +29,19 @@ import type {
 } from '@mosaicstack/types';
 import { AgentService, type ConversationHistoryMessage } from '../agent/agent.service.js';
 import { AUTH } from '../auth/auth.tokens.js';
+import {
+  scopeFromUser,
+  type ActorTenantScope,
+  type AuthenticatedUserLike,
+} from '../auth/session-scope.js';
 import { BRAIN } from '../brain/brain.tokens.js';
 import { CommandRegistryService } from '../commands/command-registry.service.js';
 import { CommandExecutorService } from '../commands/command-executor.service.js';
 import { RoutingEngineService } from '../agent/routing/routing-engine.service.js';
 import { v4 as uuid } from 'uuid';
 import { ChatSocketMessageDto } from './chat.dto.js';
-import { validateSocketSession } from './chat.gateway-auth.js';
+import { validateDiscordServiceToken, validateSocketSession } from './chat.gateway-auth.js';
+import { DiscordReplayProtector } from '../plugin/discord-replay-protector.js';
 
 /** Per-client state tracking streaming accumulation for persistence. */
 interface ClientSession {
@@ -40,6 +53,8 @@ interface ClientSession {
   toolCalls: Array<{ toolCallId: string; toolName: string; args: unknown; isError: boolean }>;
   /** Tool calls in-flight (started but not ended yet). */
   pendingToolCalls: Map<string, { toolName: string; args: unknown }>;
+  /** Server-derived owner/tenant scope for this socket's conversation attachment. */
+  scope: ActorTenantScope;
   /** Last routing decision made for this session (M4-008) */
   lastRoutingDecision?: RoutingDecisionInfo;
 }
@@ -49,6 +64,38 @@ interface ClientSession {
  * Keyed by conversationId, value is the model name to use.
  */
 const modelOverrides = new Map<string, string>();
+const MAX_REDACTION_BUFFER_LENGTH = 8_192;
+
+function isDiscordIngressEnvelope(value: unknown): value is DiscordIngressEnvelope {
+  if (typeof value !== 'object' || value === null) return false;
+  const envelope = value as { payload?: unknown; signature?: unknown };
+  if (
+    typeof envelope.signature !== 'string' ||
+    typeof envelope.payload !== 'object' ||
+    envelope.payload === null
+  ) {
+    return false;
+  }
+  const payload = envelope.payload as Record<string, unknown>;
+  return [
+    payload['correlationId'],
+    payload['messageId'],
+    payload['guildId'],
+    payload['channelId'],
+    payload['userId'],
+    payload['conversationId'],
+    payload['content'],
+  ].every((field: unknown): boolean => typeof field === 'string');
+}
+
+function isChatSocketMessage(value: unknown): value is ChatSocketMessageDto {
+  if (typeof value !== 'object' || value === null) return false;
+  const payload = value as { content?: unknown; conversationId?: unknown };
+  return (
+    typeof payload.content === 'string' &&
+    (payload.conversationId === undefined || typeof payload.conversationId === 'string')
+  );
+}
 
 @WebSocketGateway({
   cors: {
@@ -62,6 +109,11 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
 
   private readonly logger = new Logger(ChatGateway.name);
   private readonly clientSessions = new Map<string, ClientSession>();
+  /** Raw stream fragments are kept in memory only until they are safe to redact and emit. */
+  private readonly textEgressBuffers = new Map<string, string>();
+  private readonly thinkingEgressBuffers = new Map<string, string>();
+  private readonly overflowedEgress = new Set<string>();
+  private readonly discordReplayProtector = new DiscordReplayProtector();
 
   constructor(
     @Inject(AgentService) private readonly agentService: AgentService,
@@ -77,6 +129,13 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
   }
 
   async handleConnection(client: Socket): Promise<void> {
+    const serviceToken = client.handshake.auth['discordServiceToken'];
+    if (validateDiscordServiceToken(serviceToken, process.env['DISCORD_SERVICE_TOKEN'])) {
+      client.data.discordService = true;
+      this.logger.log(`Authenticated Discord service connected: ${client.id}`);
+      return;
+    }
+
     const session = await validateSocketSession(client.handshake.headers, this.auth);
     if (!session) {
       this.logger.warn(`Rejected unauthenticated WebSocket client: ${client.id}`);
@@ -87,8 +146,6 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     client.data.user = session.user;
     client.data.session = session.session;
     this.logger.log(`Client connected: ${client.id}`);
-
-    // Broadcast command manifest to the newly connected client
     client.emit('commands:manifest', { manifest: this.commandRegistry.getManifest() });
   }
 
@@ -97,25 +154,84 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     const session = this.clientSessions.get(client.id);
     if (session) {
       session.cleanup();
-      this.agentService.removeChannel(session.conversationId, `websocket:${client.id}`);
+      this.agentService.removeChannel(
+        session.conversationId,
+        `websocket:${client.id}`,
+        session.scope,
+      );
       this.clientSessions.delete(client.id);
     }
+    this.textEgressBuffers.delete(client.id);
+    this.thinkingEgressBuffers.delete(client.id);
+    this.overflowedEgress.delete(this.egressKey(client, 'agent:text'));
+    this.overflowedEgress.delete(this.egressKey(client, 'agent:thinking'));
+  }
+
+  private getClientScope(client: Socket): ActorTenantScope | null {
+    const user = client.data.user as AuthenticatedUserLike | undefined;
+    if (!user?.id) return null;
+    return scopeFromUser(user);
+  }
+
+  private modelOverrideKey(conversationId: string, scope: ActorTenantScope): string {
+    return `${scope.tenantId}:${scope.userId}:${conversationId}`;
+  }
+
+  private scopesEqual(a: ActorTenantScope, b: ActorTenantScope): boolean {
+    return a.userId === b.userId && a.tenantId === b.tenantId;
   }
 
   @SubscribeMessage('message')
   async handleMessage(
     @ConnectedSocket() client: Socket,
-    @MessageBody() data: ChatSocketMessageDto,
+    @MessageBody() rawData: unknown,
   ): Promise<void> {
+    let discordIngress: DiscordIngressPayload | null = null;
+    let data: ChatSocketMessageDto;
+    if (client.data.discordService) {
+      if (!isDiscordIngressEnvelope(rawData)) {
+        this.logger.warn(`Rejected malformed Discord ingress from ${client.id}`);
+        return;
+      }
+      discordIngress = this.resolveDiscordIngress(client, rawData);
+      if (!discordIngress) return;
+      data = { conversationId: discordIngress.conversationId, content: discordIngress.content };
+    } else {
+      if (!isChatSocketMessage(rawData)) {
+        this.logger.warn(`Rejected malformed chat message from ${client.id}`);
+        return;
+      }
+      data = rawData;
+    }
     const conversationId = data.conversationId ?? uuid();
-    const userId = (client.data.user as { id: string } | undefined)?.id;
+    const discordServiceUserId = process.env['DISCORD_SERVICE_USER_ID'];
+    if (discordIngress && !discordServiceUserId) {
+      this.logger.warn(
+        `Rejected Discord ingress without configured service owner from ${client.id}`,
+      );
+      return;
+    }
+    const scope = discordIngress
+      ? {
+          userId: discordServiceUserId!,
+          tenantId: process.env['DISCORD_SERVICE_TENANT_ID'] ?? discordServiceUserId!,
+        }
+      : this.getClientScope(client);
+    if (!scope) {
+      client.emit('error', { conversationId, error: 'Authenticated user scope is required.' });
+      return;
+    }
+    const userId = scope.userId;
+    const correlationId = discordIngress?.correlationId;
 
-    this.logger.log(`Message from ${client.id} in conversation ${conversationId}`);
+    this.logger.log(
+      `Message from ${client.id} in conversation ${conversationId}${correlationId ? ` correlation=${correlationId}` : ''}`,
+    );
 
     // Ensure agent session exists for this conversation
     let sessionRoutingDecision: RoutingDecisionInfo | undefined;
     try {
-      let agentSession = this.agentService.getSession(conversationId);
+      let agentSession = this.agentService.getSession(conversationId, scope);
       if (!agentSession) {
         // When resuming an existing conversation, load prior messages to inject as context (M1-004)
         const conversationHistory = await this.loadConversationHistory(conversationId, userId);
@@ -135,7 +251,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
         let resolvedProvider = data.provider;
         let resolvedModelId = data.modelId;
 
-        const modelOverride = modelOverrides.get(conversationId);
+        const modelOverride = modelOverrides.get(this.modelOverrideKey(conversationId, scope));
         if (modelOverride) {
           // /model override bypasses routing engine (M4-007)
           resolvedModelId = modelOverride;
@@ -172,6 +288,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
           modelId: resolvedModelId,
           agentConfigId: data.agentId,
           userId,
+          tenantId: scope.tenantId,
           conversationHistory: conversationHistory.length > 0 ? conversationHistory : undefined,
         });
 
@@ -210,9 +327,17 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
           {
             conversationId,
             role: 'user',
-            content: data.content,
+            content: redactSensitiveContent(data.content).content,
             metadata: {
               timestamp: new Date().toISOString(),
+              ...(correlationId
+                ? {
+                    correlationId,
+                    discordMessageId: discordIngress?.messageId,
+                    discordUserId: discordIngress?.userId,
+                  }
+                : {}),
+              classifications: redactSensitiveContent(data.content).classifications,
             },
           },
           userId,
@@ -232,9 +357,13 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     }
 
     // Subscribe to agent events and relay to client
-    const cleanup = this.agentService.onEvent(conversationId, (event: AgentSessionEvent) => {
+    const cleanup = this.agentService.onEvent(
-      this.relayEvent(client, conversationId, event);
+      conversationId,
-    });
+      (event: AgentSessionEvent) => {
+        this.relayEvent(client, conversationId, event);
+      },
+      scope,
+    );
 
     // Preserve routing decision from the existing client session if we didn't get a new one
     const prevClientSession = this.clientSessions.get(client.id);
@@ -246,16 +375,17 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
       assistantText: '',
       toolCalls: [],
       pendingToolCalls: new Map(),
+      scope,
       lastRoutingDecision: routingDecisionToStore,
     });
 
     // Track channel connection
-    this.agentService.addChannel(conversationId, `websocket:${client.id}`);
+    this.agentService.addChannel(conversationId, `websocket:${client.id}`, scope);
 
     // Send session info so the client knows the model/provider (M4-008: include routing decision)
     // Include agentName when a named agent config is active (M5-001)
     {
-      const agentSession = this.agentService.getSession(conversationId);
+      const agentSession = this.agentService.getSession(conversationId, scope);
       if (agentSession) {
         const piSession = agentSession.piSession;
         client.emit('session:info', {
@@ -271,11 +401,21 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     }
 
     // Send acknowledgment
-    client.emit('message:ack', { conversationId, messageId: uuid() });
+    client.emit('message:ack', {
+      conversationId,
+      messageId: uuid(),
+      ...(correlationId
+        ? {
+            correlationId,
+            discordMessageId: discordIngress?.messageId,
+            discordUserId: discordIngress?.userId,
+          }
+        : {}),
+    });
 
     // Dispatch to agent
     try {
-      await this.agentService.prompt(conversationId, data.content);
+      await this.agentService.prompt(conversationId, data.content, scope);
     } catch (err) {
       this.logger.error(
         `Agent prompt failed for client=${client.id}, conversation=${conversationId}`,
@@ -293,7 +433,16 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     @ConnectedSocket() client: Socket,
     @MessageBody() data: SetThinkingPayload,
   ): void {
-    const session = this.agentService.getSession(data.conversationId);
+    const scope = this.getClientScope(client);
+    if (!scope) {
+      client.emit('error', {
+        conversationId: data.conversationId,
+        error: 'Authenticated user scope is required.',
+      });
+      return;
+    }
+
+    const session = this.agentService.getSession(data.conversationId, scope);
     if (!session) {
       client.emit('error', {
         conversationId: data.conversationId,
@@ -334,7 +483,13 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     const conversationId = data.conversationId;
     this.logger.log(`Abort requested by ${client.id} for conversation ${conversationId}`);
 
-    const session = this.agentService.getSession(conversationId);
+    const scope = this.getClientScope(client);
+    if (!scope) {
+      client.emit('error', { conversationId, error: 'Authenticated user scope is required.' });
+      return;
+    }
+
+    const session = this.agentService.getSession(conversationId, scope);
     if (!session) {
       client.emit('error', {
         conversationId,
@@ -363,11 +518,45 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     @ConnectedSocket() client: Socket,
     @MessageBody() payload: SlashCommandPayload,
   ): Promise<void> {
-    const userId = (client.data.user as { id: string } | undefined)?.id ?? 'unknown';
+    const scope = this.getClientScope(client);
-    const result = await this.commandExecutor.execute(payload, userId);
+    if (!scope) {
+      client.emit('command:result', {
+        command: payload.command,
+        conversationId: payload.conversationId,
+        success: false,
+        message: 'Authenticated user scope is required.',
+      });
+      return;
+    }
+
+    const result = await this.commandExecutor.execute(payload, scope);
     client.emit('command:result', result);
   }
 
+  @SubscribeMessage('command:approve')
+  async handleCommandApproval(
+    @ConnectedSocket() client: Socket,
+    @MessageBody() payload: SlashCommandPayload,
+  ): Promise<void> {
+    const scope = this.getClientScope(client);
+    const approval = scope ? await this.commandExecutor.createApproval(payload, scope) : null;
+    const result: SlashCommandApprovalResultPayload = approval
+      ? {
+          command: payload.command,
+          conversationId: payload.conversationId,
+          success: true,
+          approvalId: approval.approvalId,
+          expiresAt: approval.expiresAt,
+        }
+      : {
+          command: payload.command,
+          conversationId: payload.conversationId,
+          success: false,
+          message: 'Not authorized to approve this command.',
+        };
+    client.emit('command:approval', result);
+  }
+
   broadcastReload(payload: SystemReloadPayload): void {
     this.server.emit('system:reload', payload);
     this.logger.log('Broadcasted system:reload to all connected clients');
@@ -380,18 +569,23 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
    * M5-005: Emits session:info to clients subscribed to this conversation when a model is set.
    * M5-007: Records a model switch in session metrics.
    */
-  setModelOverride(conversationId: string, modelName: string | null): void {
+  setModelOverride(
+    conversationId: string,
+    modelName: string | null,
+    scope: ActorTenantScope,
+  ): void {
+    const key = this.modelOverrideKey(conversationId, scope);
     if (modelName) {
-      modelOverrides.set(conversationId, modelName);
+      modelOverrides.set(key, modelName);
       this.logger.log(`Model override set: conversation=${conversationId} model="${modelName}"`);
 
       // M5-002: Update the live session's modelId so session:info reflects the new model immediately
-      this.agentService.updateSessionModel(conversationId, modelName);
+      this.agentService.updateSessionModel(conversationId, modelName, scope);
 
       // M5-005: Broadcast session:info to all clients subscribed to this conversation
-      this.broadcastSessionInfo(conversationId);
+      this.broadcastSessionInfo(conversationId, scope);
     } else {
-      modelOverrides.delete(conversationId);
+      modelOverrides.delete(key);
       this.logger.log(`Model override cleared: conversation=${conversationId}`);
     }
   }
@@ -399,8 +593,8 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
   /**
    * Return the active model override for a conversation, or undefined if none.
    */
-  getModelOverride(conversationId: string): string | undefined {
+  getModelOverride(conversationId: string, scope: ActorTenantScope): string | undefined {
-    return modelOverrides.get(conversationId);
+    return modelOverrides.get(this.modelOverrideKey(conversationId, scope));
   }
 
   /**
@@ -409,9 +603,10 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
    */
   broadcastSessionInfo(
     conversationId: string,
+    scope: ActorTenantScope,
     extra?: { agentName?: string; routingDecision?: RoutingDecisionInfo },
   ): void {
-    const agentSession = this.agentService.getSession(conversationId);
+    const agentSession = this.agentService.getSession(conversationId, scope);
     if (!agentSession) return;
 
     const piSession = agentSession.piSession;
@@ -428,7 +623,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
 
     // Emit to all clients currently subscribed to this conversation
     for (const [clientId, session] of this.clientSessions) {
-      if (session.conversationId === conversationId) {
+      if (session.conversationId === conversationId && this.scopesEqual(session.scope, scope)) {
         const socket = this.server.sockets.sockets.get(clientId);
         if (socket?.connected) {
           socket.emit('session:info', payload);
@@ -442,6 +637,39 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
    * Creates it if absent — safe to call concurrently since a duplicate insert
    * would fail on the PK constraint and be caught here.
    */
+  private resolveDiscordIngress(
+    client: Socket,
+    envelope: DiscordIngressEnvelope,
+  ): DiscordIngressPayload | null {
+    const payload = verifyDiscordIngressEnvelope(
+      envelope,
+      process.env['DISCORD_SERVICE_TOKEN'] ?? '',
+      {
+        guildIds: this.readDiscordAllowlist('DISCORD_ALLOWED_GUILD_IDS'),
+        channelIds: this.readDiscordAllowlist('DISCORD_ALLOWED_CHANNEL_IDS'),
+        userIds: this.readDiscordAllowlist('DISCORD_ALLOWED_USER_IDS'),
+      },
+    );
+    if (!payload) {
+      this.logger.warn(`Rejected invalid Discord ingress envelope from ${client.id}`);
+      return null;
+    }
+    if (!this.discordReplayProtector.claim(payload.messageId)) {
+      this.logger.warn(
+        `Rejected replayed Discord message=${payload.messageId} correlation=${payload.correlationId}`,
+      );
+      return null;
+    }
+    return payload;
+  }
+
+  private readDiscordAllowlist(name: string): string[] {
+    return (process.env[name] ?? '')
+      .split(',')
+      .map((id: string): string => id.trim())
+      .filter((id: string): boolean => id.length > 0);
+  }
+
   private async ensureConversation(conversationId: string, userId: string): Promise<void> {
     try {
       const existing = await this.brain.conversations.findById(conversationId, userId);
@@ -527,6 +755,127 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
     }
   }
 
+  private appendAndFlushRedactedEgress(
+    client: Socket,
+    conversationId: string,
+    eventName: 'agent:text' | 'agent:thinking',
+    buffers: Map<string, string>,
+    delta: string,
+  ): void {
+    const key = this.egressKey(client, eventName);
+    if (this.overflowedEgress.has(key)) return;
+
+    const buffered = `${buffers.get(client.id) ?? ''}${delta}`;
+    if (buffered.length > MAX_REDACTION_BUFFER_LENGTH) {
+      buffers.delete(client.id);
+      this.overflowedEgress.add(key);
+      client.emit(eventName, { conversationId, text: '[REDACTED_STREAM_OVERFLOW]' });
+      return;
+    }
+
+    buffers.set(client.id, buffered);
+    this.flushRedactedEgress(client, conversationId, eventName, buffers, false);
+  }
+
+  /**
+   * Holds any suffix that could become a secret, email, or phone number after a
+   * later stream chunk. This avoids relying on downstream redaction after data
+   * has already reached the socket.
+   */
+  private flushRedactedEgress(
+    client: Socket,
+    conversationId: string,
+    eventName: 'agent:text' | 'agent:thinking',
+    buffers: Map<string, string>,
+    final: boolean,
+  ): void {
+    const key = this.egressKey(client, eventName);
+    if (this.overflowedEgress.has(key)) {
+      if (final) this.overflowedEgress.delete(key);
+      return;
+    }
+
+    const buffered = buffers.get(client.id) ?? '';
+    const releaseLength = final ? buffered.length : this.safeRedactionPrefixLength(buffered);
+    const released = buffered.slice(0, releaseLength);
+    const pending = buffered.slice(releaseLength);
+
+    if (pending) {
+      buffers.set(client.id, pending);
+    } else {
+      buffers.delete(client.id);
+    }
+
+    if (released) {
+      client.emit(eventName, {
+        conversationId,
+        text: redactSensitiveContent(released).content,
+      });
+    }
+  }
+
+  private safeRedactionPrefixLength(content: string): number {
+    let retainedFrom = content.length;
+
+    // Retain the current token because it may become a split secret or email.
+    const token = /(?:^|\s)(\S*)$/.exec(content);
+    if (token) {
+      const matched = token[0] ?? '';
+      const trailingToken = token[1] ?? '';
+      retainedFrom = token.index + matched.length - trailingToken.length;
+    }
+
+    // The secret classifier accepts whitespace around ':' and '=', so preserve
+    // a pending label until its value and delimiter are both complete.
+    const pendingSecretLabel =
+      /(?:^|[^A-Za-z0-9_])((?:api[_-]?key|token|password|secret|bearer|authorization)\s*)$/i.exec(
+        content,
+      );
+    if (pendingSecretLabel) {
+      const label = pendingSecretLabel[1] ?? '';
+      retainedFrom = Math.min(
+        retainedFrom,
+        pendingSecretLabel.index + pendingSecretLabel[0].length - label.length,
+      );
+    }
+
+    const secretLabel = /(?:api[_-]?key|token|password|secret|authorization)\s*[:=]\s*$/i.exec(
+      content,
+    );
+    if (secretLabel) {
+      retainedFrom = Math.min(retainedFrom, secretLabel.index);
+    }
+
+    // Phone numbers can contain whitespace and punctuation; preserve the full
+    // trailing numeric candidate until a non-phone character establishes a boundary.
+    const phone = /(?:^|[^A-Za-z0-9_])(\+?\d[\d(). -]*)$/.exec(content);
+    if (phone) {
+      const matched = phone[0] ?? '';
+      const trailingPhoneCandidate = phone[1] ?? '';
+      retainedFrom = Math.min(
+        retainedFrom,
+        phone.index + matched.length - trailingPhoneCandidate.length,
+      );
+    }
+
+    const privateKeyStart = content.lastIndexOf('-----BEGIN');
+    if (privateKeyStart >= 0) {
+      const privateKey = content.slice(privateKeyStart);
+      if (/-----END(?: [A-Z]+)* KEY-----/.test(privateKey)) {
+        // Release the complete block in one pass so the full-block classifier can redact it.
+        retainedFrom = content.length;
+      } else {
+        retainedFrom = Math.min(retainedFrom, privateKeyStart);
+      }
+    }
+
+    return retainedFrom;
+  }
+
+  private egressKey(client: Socket, eventName: 'agent:text' | 'agent:thinking'): string {
+    return `${client.id}:${eventName}`;
+  }
+
   private relayEvent(client: Socket, conversationId: string, event: AgentSessionEvent): void {
     if (!client.connected) {
       this.logger.warn(
@@ -544,13 +893,20 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
           cs.toolCalls = [];
           cs.pendingToolCalls.clear();
         }
+        this.textEgressBuffers.set(client.id, '');
+        this.thinkingEgressBuffers.set(client.id, '');
+        this.overflowedEgress.delete(this.egressKey(client, 'agent:text'));
+        this.overflowedEgress.delete(this.egressKey(client, 'agent:thinking'));
         client.emit('agent:start', { conversationId });
         break;
       }
 
       case 'agent_end': {
         // Gather usage stats from the Pi session
-        const agentSession = this.agentService.getSession(conversationId);
+        const activeClientSession = this.clientSessions.get(client.id);
+        const agentSession = activeClientSession
+          ? this.agentService.getSession(conversationId, activeClientSession.scope)
+          : undefined;
         const piSession = agentSession?.piSession;
         const stats = piSession?.getSessionStats();
         const contextUsage = piSession?.getContextUsage();
@@ -569,6 +925,20 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
             }
           : undefined;
 
+        this.flushRedactedEgress(
+          client,
+          conversationId,
+          'agent:text',
+          this.textEgressBuffers,
+          true,
+        );
+        this.flushRedactedEgress(
+          client,
+          conversationId,
+          'agent:thinking',
+          this.thinkingEgressBuffers,
+          true,
+        );
         client.emit('agent:end', {
           conversationId,
           usage: usagePayload,
@@ -611,8 +981,11 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
               {
                 conversationId,
                 role: 'assistant',
-                content: cs.assistantText,
+                content: redactSensitiveContent(cs.assistantText).content,
-                metadata,
+                metadata: {
+                  ...metadata,
+                  classifications: redactSensitiveContent(cs.assistantText).classifications,
+                },
               },
               userId,
             )
@@ -634,20 +1007,26 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
       case 'message_update': {
         const assistantEvent = event.assistantMessageEvent;
         if (assistantEvent.type === 'text_delta') {
-          // Accumulate assistant text for persistence
+          // Keep raw stream material in memory only; persist and emit only redacted text.
           const cs = this.clientSessions.get(client.id);
           if (cs) {
             cs.assistantText += assistantEvent.delta;
           }
-          client.emit('agent:text', {
+          this.appendAndFlushRedactedEgress(
+            client,
             conversationId,
-            text: assistantEvent.delta,
+            'agent:text',
-          });
+            this.textEgressBuffers,
+            assistantEvent.delta,
+          );
         } else if (assistantEvent.type === 'thinking_delta') {
-          client.emit('agent:thinking', {
+          this.appendAndFlushRedactedEgress(
+            client,
             conversationId,
-            text: assistantEvent.delta,
+            'agent:thinking',
-          });
+            this.thinkingEgressBuffers,
+            assistantEvent.delta,
+          );
         }
         break;
       }

apps/gateway/src/commands/command-authorization.service.spec.ts

@@ -0,0 +1,61 @@
+import { describe, expect, it } from 'vitest';
+import type { CommandDef, SlashCommandPayload } from '@mosaicstack/types';
+import { CommandAuthorizationService } from './command-authorization.service.js';
+
+const adminCommand: CommandDef = {
+  name: 'gc',
+  description: 'GC',
+  aliases: [],
+  scope: 'admin',
+  execution: 'socket',
+  available: true,
+};
+const payload: SlashCommandPayload = { command: 'gc', conversationId: 'conversation-1' };
+
+function createService(role: string): CommandAuthorizationService {
+  const entries = new Map<string, string>();
+  const db = {
+    select: () => ({ from: () => ({ where: () => ({ limit: async () => [{ role }] }) }) }),
+  };
+  const redis = {
+    get: async (key: string) => entries.get(key) ?? null,
+    set: async (key: string, value: string) => {
+      entries.set(key, value);
+    },
+    del: async (key: string) => Number(entries.delete(key)),
+  };
+  return new CommandAuthorizationService(db as never, redis);
+}
+
+describe('CommandAuthorizationService', () => {
+  it('consumes one exact actor-bound approval once', async (): Promise<void> => {
+    const service = createService('admin');
+    const approval = await service.createApproval(adminCommand, payload, 'admin-1');
+    expect(approval).not.toBeNull();
+    expect(
+      (await service.authorize(adminCommand, payload, 'admin-1', approval!.approvalId)).allowed,
+    ).toBe(true);
+    expect(
+      (await service.authorize(adminCommand, payload, 'admin-1', approval!.approvalId)).allowed,
+    ).toBe(false);
+  });
+
+  it('rejects an approval when the structured action is mutated', async (): Promise<void> => {
+    const service = createService('admin');
+    const approval = await service.createApproval(adminCommand, payload, 'admin-1');
+    const mutated = { ...payload, conversationId: 'other-conversation' };
+    expect(approval).not.toBeNull();
+    expect(
+      (await service.authorize(adminCommand, mutated, 'admin-1', approval!.approvalId)).allowed,
+    ).toBe(false);
+  });
+
+  it('denies an admin command to a member before approval is considered', async (): Promise<void> => {
+    const service = createService('member');
+    const approval = await service.createApproval(adminCommand, payload, 'member-1');
+    expect(approval).toBeNull();
+    expect(
+      (await service.authorize(adminCommand, payload, 'member-1', 'forged-approval-id')).allowed,
+    ).toBe(false);
+  });
+});

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

@@ -0,0 +1,138 @@
+import { createHash, randomUUID } from 'node:crypto';
+import { Inject, Injectable } from '@nestjs/common';
+import { eq, users as usersTable, type Db } from '@mosaicstack/db';
+import type { CommandDef, SlashCommandPayload } from '@mosaicstack/types';
+import { DB } from '../database/database.module.js';
+import { COMMANDS_REDIS } from './commands.tokens.js';
+
+export type CommandRole = 'admin' | 'member' | 'viewer';
+
+export interface CommandApproval {
+  approvalId: string;
+  actionDigest: string;
+  actorId: string;
+  command: string;
+  expiresAt: string;
+}
+
+export interface CommandAuthorizationResult {
+  allowed: boolean;
+  reason?: string;
+}
+
+@Injectable()
+export class CommandAuthorizationService {
+  constructor(
+    @Inject(DB) private readonly db: Db,
+    @Inject(COMMANDS_REDIS)
+    private readonly redis: {
+      get(key: string): Promise<string | null>;
+      set(key: string, value: string, ...args: string[]): Promise<unknown>;
+      del(key: string): Promise<number>;
+    },
+  ) {}
+
+  async authorize(
+    command: CommandDef,
+    payload: SlashCommandPayload,
+    actorId: string,
+    approvalId?: string,
+  ): Promise<CommandAuthorizationResult> {
+    const role = await this.resolveRole(actorId);
+    if (!role || !this.hasScope(role, command.scope)) {
+      return { allowed: false, reason: 'not authorized for this command scope' };
+    }
+    if (command.scope !== 'admin') return { allowed: true };
+    if (!approvalId) return { allowed: false, reason: 'durable approval is required' };
+    const actionDigest = this.actionDigest(command.name, payload);
+    const approved = await this.consumeApproval(approvalId, actorId, actionDigest);
+    return approved
+      ? { allowed: true }
+      : {
+          allowed: false,
+          reason: 'approval is invalid, expired, replayed, or does not match this action',
+        };
+  }
+
+  async createApproval(
+    command: CommandDef,
+    payload: SlashCommandPayload,
+    actorId: string,
+  ): Promise<CommandApproval | null> {
+    const role = await this.resolveRole(actorId);
+    if (!role || command.scope !== 'admin' || !this.hasScope(role, command.scope)) return null;
+
+    const approvalId = randomUUID();
+    const expiresAt = new Date(Date.now() + 5 * 60_000).toISOString();
+    const approval: CommandApproval = {
+      approvalId,
+      actionDigest: this.actionDigest(command.name, payload),
+      actorId,
+      command: command.name,
+      expiresAt,
+    };
+    await this.redis.set(this.key(approvalId), JSON.stringify(approval), 'EX', '300');
+    return approval;
+  }
+
+  private async resolveRole(actorId: string): Promise<CommandRole | null> {
+    const [user] = await this.db
+      .select({ role: usersTable.role })
+      .from(usersTable)
+      .where(eq(usersTable.id, actorId))
+      .limit(1);
+    const role = user?.role;
+    return role === 'admin' || role === 'member' || role === 'viewer' ? role : null;
+  }
+
+  private hasScope(role: CommandRole, scope: CommandDef['scope']): boolean {
+    if (role === 'admin') return true;
+    return role === 'member' && (scope === 'core' || scope === 'agent');
+  }
+
+  private async consumeApproval(
+    approvalId: string,
+    actorId: string,
+    actionDigest: string,
+  ): Promise<boolean> {
+    const key = this.key(approvalId);
+    const encoded = await this.redis.get(key);
+    if (!encoded) return false;
+    const parsed: unknown = JSON.parse(encoded);
+    if (
+      !this.isApproval(parsed) ||
+      parsed.actorId !== actorId ||
+      parsed.actionDigest !== actionDigest ||
+      Date.parse(parsed.expiresAt) <= Date.now()
+    )
+      return false;
+    return (await this.redis.del(key)) === 1;
+  }
+
+  private actionDigest(command: string, payload: SlashCommandPayload): string {
+    return createHash('sha256')
+      .update(
+        JSON.stringify({
+          command,
+          args: payload.args?.trim() ?? '',
+          conversationId: payload.conversationId,
+        }),
+      )
+      .digest('hex');
+  }
+
+  private isApproval(value: unknown): value is CommandApproval {
+    return (
+      typeof value === 'object' &&
+      value !== null &&
+      'approvalId' in value &&
+      'actionDigest' in value &&
+      'actorId' in value &&
+      'expiresAt' in value
+    );
+  }
+
+  private key(approvalId: string): string {
+    return `tess:command-approval:${approvalId}`;
+  }
+}

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

@@ -89,6 +89,7 @@ function buildService(): CommandExecutorService {
 describe('CommandExecutorService — P8-012 commands', () => {
   let service: CommandExecutorService;
   const userId = 'user-123';
+  const userScope = { userId, tenantId: userId };
   const conversationId = 'conv-456';
 
   beforeEach(() => {
@@ -99,31 +100,26 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /provider login — missing provider name
   it('/provider login with no provider name returns usage error', async () => {
     const payload: SlashCommandPayload = { command: 'provider', args: 'login', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(false);
     expect(result.message).toContain('Usage: /provider login');
     expect(result.command).toBe('provider');
   });
 
-  // /provider login anthropic — success with URL containing poll token
+  // /provider login anthropic — no bearer token or auth URL reaches chat output
-  it('/provider login <name> returns success with URL and poll token', async () => {
+  it('/provider login <name> keeps its one-time token out of chat output', async () => {
     const payload: SlashCommandPayload = {
       command: 'provider',
       args: 'login anthropic',
       conversationId,
     };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('provider');
     expect(result.message).toContain('anthropic');
-    expect(result.message).toContain('http');
+    expect(result.message).not.toContain('http');
-    // data should contain loginUrl and pollToken
+    expect(result.message).not.toContain('token=');
-    expect(result.data).toBeDefined();
+    expect(result.data).toEqual({ provider: 'anthropic' });
-    const data = result.data as Record<string, unknown>;
-    expect(typeof data['loginUrl']).toBe('string');
-    expect(typeof data['pollToken']).toBe('string');
-    expect(data['loginUrl'] as string).toContain('anthropic');
-    expect(data['loginUrl'] as string).toContain(data['pollToken'] as string);
     // Verify Valkey was called
     expect(mockRedis.set).toHaveBeenCalledOnce();
     const [key, value, , ttl] = mockRedis.set.mock.calls[0] as [string, string, string, number];
@@ -138,7 +134,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /provider with no args — returns usage
   it('/provider with no args returns usage message', async () => {
     const payload: SlashCommandPayload = { command: 'provider', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('Usage: /provider');
   });
@@ -146,7 +142,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /provider list
   it('/provider list returns success', async () => {
     const payload: SlashCommandPayload = { command: 'provider', args: 'list', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('provider');
   });
@@ -154,7 +150,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /provider logout with no name — usage error
   it('/provider logout with no name returns error', async () => {
     const payload: SlashCommandPayload = { command: 'provider', args: 'logout', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(false);
     expect(result.message).toContain('Usage: /provider logout');
   });
@@ -166,7 +162,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
       args: 'unknown',
       conversationId,
     };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(false);
     expect(result.message).toContain('Unknown subcommand');
   });
@@ -174,7 +170,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /mission status
   it('/mission status returns stub message', async () => {
     const payload: SlashCommandPayload = { command: 'mission', args: 'status', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('mission');
     expect(result.message).toContain('Mission status');
@@ -183,7 +179,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /mission with no args
   it('/mission with no args returns status stub', async () => {
     const payload: SlashCommandPayload = { command: 'mission', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('Mission status');
   });
@@ -195,7 +191,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
       args: 'set my-mission-123',
       conversationId,
     };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('my-mission-123');
   });
@@ -203,7 +199,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /agent list
   it('/agent list returns stub message', async () => {
     const payload: SlashCommandPayload = { command: 'agent', args: 'list', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('agent');
     expect(result.message).toContain('agent');
@@ -212,7 +208,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /agent with no args
   it('/agent with no args returns usage', async () => {
     const payload: SlashCommandPayload = { command: 'agent', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('Usage: /agent');
   });
@@ -224,7 +220,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
       args: 'my-agent-id',
       conversationId,
     };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('my-agent-id');
   });
@@ -232,7 +228,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /prdy
   it('/prdy returns PRD wizard message', async () => {
     const payload: SlashCommandPayload = { command: 'prdy', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('prdy');
     expect(result.message).toContain('mosaic prdy');
@@ -241,7 +237,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
   // /tools
   it('/tools returns tools stub message', async () => {
     const payload: SlashCommandPayload = { command: 'tools', conversationId };
-    const result = await service.execute(payload, userId);
+    const result = await service.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('tools');
     expect(result.message).toContain('tools');

apps/gateway/src/commands/command-executor-tess-security.spec.ts

@@ -0,0 +1,109 @@
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+import type { SlashCommandPayload } from '@mosaicstack/types';
+import { CommandAuthorizationService } from './command-authorization.service.js';
+import { CommandExecutorService } from './command-executor.service.js';
+
+const registry = {
+  getManifest: vi.fn(() => ({
+    version: 1,
+    commands: [
+      {
+        name: 'gc',
+        description: 'System-wide garbage collection',
+        aliases: [],
+        scope: 'admin' as const,
+        execution: 'socket' as const,
+        available: true,
+      },
+    ],
+    skills: [],
+  })),
+};
+
+const sessionGc = {
+  sweepOrphans: vi.fn().mockResolvedValue({ orphanedSessions: 1, totalCleaned: [], duration: 1 }),
+};
+
+const scope = (userId: string) => ({ userId, tenantId: 'tenant-1' });
+
+const authorization = {
+  authorize: vi.fn((_command: unknown, _payload: unknown, actorId: string) =>
+    Promise.resolve(
+      actorId === 'member-1'
+        ? { allowed: false, reason: 'durable approval is required' }
+        : { allowed: false, reason: 'not authorized for this command scope' },
+    ),
+  ),
+};
+
+function buildExecutor(authorizationService: unknown = authorization): CommandExecutorService {
+  return new CommandExecutorService(
+    registry as never,
+    { getSession: vi.fn() } as never,
+    { clear: vi.fn(), set: vi.fn() } as never,
+    sessionGc as never,
+    { set: vi.fn() } as never,
+    { agents: {} } as never,
+    null,
+    null,
+    null,
+    authorizationService as never,
+  );
+}
+
+function createDurableAuthorization(): CommandAuthorizationService {
+  const entries = new Map<string, string>();
+  const db = {
+    select: () => ({ from: () => ({ where: () => ({ limit: async () => [{ role: 'admin' }] }) }) }),
+  };
+  const redis = {
+    get: async (key: string) => entries.get(key) ?? null,
+    set: async (key: string, value: string) => {
+      entries.set(key, value);
+    },
+    del: async (key: string) => Number(entries.delete(key)),
+  };
+  return new CommandAuthorizationService(db as never, redis);
+}
+
+describe('TESS-M1-SEC-001 command authorization abuse cases', () => {
+  const payload: SlashCommandPayload = { command: 'gc', conversationId: 'conversation-1' };
+
+  beforeEach((): void => {
+    vi.clearAllMocks();
+  });
+
+  it('denies a forged admin identity and does not execute a system-wide command', async (): Promise<void> => {
+    const result = await buildExecutor().execute(payload, scope('admin-forged-by-client'));
+
+    expect(result.success).toBe(false);
+    expect(result.message).toContain('not authorized');
+    expect(sessionGc.sweepOrphans).not.toHaveBeenCalled();
+  });
+
+  it('denies a privileged command without a server-bound durable approval', async (): Promise<void> => {
+    const result = await buildExecutor().execute(payload, scope('member-1'));
+
+    expect(result.success).toBe(false);
+    expect(result.message).toContain('approval');
+    expect(sessionGc.sweepOrphans).not.toHaveBeenCalled();
+  });
+
+  it('executes an admin command only after a valid durable approval is issued and supplied', async (): Promise<void> => {
+    const executor = buildExecutor(createDurableAuthorization());
+
+    const adminScope = scope('admin-1');
+    const denied = await executor.execute(payload, adminScope);
+    const approval = await executor.createApproval(payload, adminScope);
+    const approved = await executor.execute(
+      { ...payload, approvalId: approval?.approvalId },
+      adminScope,
+    );
+
+    expect(denied.success).toBe(false);
+    expect(denied.message).toContain('approval');
+    expect(approval).not.toBeNull();
+    expect(approved.success).toBe(true);
+    expect(sessionGc.sweepOrphans).toHaveBeenCalledOnce();
+  });
+});

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

@@ -3,6 +3,7 @@ import type { QueueHandle } from '@mosaicstack/queue';
 import type { Brain } from '@mosaicstack/brain';
 import type { SlashCommandPayload, SlashCommandResultPayload } from '@mosaicstack/types';
 import { AgentService } from '../agent/agent.service.js';
+import type { ActorTenantScope } from '../auth/session-scope.js';
 import { ChatGateway } from '../chat/chat.gateway.js';
 import { SessionGCService } from '../gc/session-gc.service.js';
 import { SystemOverrideService } from '../preferences/system-override.service.js';
@@ -10,6 +11,7 @@ import { ReloadService } from '../reload/reload.service.js';
 import { McpClientService } from '../mcp-client/mcp-client.service.js';
 import { BRAIN } from '../brain/brain.tokens.js';
 import { COMMANDS_REDIS } from './commands.tokens.js';
+import { CommandAuthorizationService } from './command-authorization.service.js';
 import { CommandRegistryService } from './command-registry.service.js';
 
 @Injectable()
@@ -32,10 +34,17 @@ export class CommandExecutorService {
     @Optional()
     @Inject(McpClientService)
     private readonly mcpClient: McpClientService | null,
+    @Optional()
+    @Inject(CommandAuthorizationService)
+    private readonly authorization: CommandAuthorizationService | null = null,
   ) {}
 
-  async execute(payload: SlashCommandPayload, userId: string): Promise<SlashCommandResultPayload> {
+  async execute(
+    payload: SlashCommandPayload,
+    scope: ActorTenantScope,
+  ): Promise<SlashCommandResultPayload> {
     const { command, args, conversationId } = payload;
+    const userId = scope.userId;
 
     const def = this.registry.getManifest().commands.find((c) => c.name === command);
     if (!def) {
@@ -47,14 +56,24 @@ export class CommandExecutorService {
       };
     }
 
+    const authorization = await this.authorization?.authorize(
+      def,
+      payload,
+      userId,
+      payload.approvalId,
+    );
+    if (authorization && !authorization.allowed) {
+      return { command, conversationId, success: false, message: authorization.reason };
+    }
+
     try {
       switch (command) {
         case 'model':
-          return await this.handleModel(args ?? null, conversationId);
+          return await this.handleModel(args ?? null, conversationId, scope);
         case 'thinking':
           return await this.handleThinking(args ?? null, conversationId);
         case 'system':
-          return await this.handleSystem(args ?? null, conversationId);
+          return await this.handleSystem(args ?? null, conversationId, scope);
         case 'new':
           return {
             command,
@@ -94,7 +113,7 @@ export class CommandExecutorService {
           };
         }
         case 'agent':
-          return await this.handleAgent(args ?? null, conversationId, userId);
+          return await this.handleAgent(args ?? null, conversationId, scope);
         case 'provider':
           return await this.handleProvider(args ?? null, userId, conversationId);
         case 'mission':
@@ -143,13 +162,22 @@ export class CommandExecutorService {
     }
   }
 
+  async createApproval(payload: SlashCommandPayload, scope: ActorTenantScope) {
+    const def = this.registry
+      .getManifest()
+      .commands.find((command) => command.name === payload.command);
+    if (!def || !this.authorization) return null;
+    return this.authorization.createApproval(def, payload, scope.userId);
+  }
+
   private async handleModel(
     args: string | null,
     conversationId: string,
+    scope: ActorTenantScope,
   ): Promise<SlashCommandResultPayload> {
     if (!args || args.trim().length === 0) {
       // Show current override or usage hint
-      const currentOverride = this.chatGateway?.getModelOverride(conversationId);
+      const currentOverride = this.chatGateway?.getModelOverride(conversationId, scope);
       if (currentOverride) {
         return {
           command: 'model',
@@ -171,7 +199,7 @@ export class CommandExecutorService {
 
     // /model clear removes the override and re-enables automatic routing
     if (modelName === 'clear') {
-      this.chatGateway?.setModelOverride(conversationId, null);
+      this.chatGateway?.setModelOverride(conversationId, null, scope);
       return {
         command: 'model',
         conversationId,
@@ -181,9 +209,9 @@ export class CommandExecutorService {
     }
 
     // Set the sticky per-session override (M4-007)
-    this.chatGateway?.setModelOverride(conversationId, modelName);
+    this.chatGateway?.setModelOverride(conversationId, modelName, scope);
 
-    const session = this.agentService.getSession(conversationId);
+    const session = this.agentService.getSession(conversationId, scope);
     if (!session) {
       return {
         command: 'model',
@@ -224,10 +252,11 @@ export class CommandExecutorService {
   private async handleSystem(
     args: string | null,
     conversationId: string,
+    scope: ActorTenantScope,
   ): Promise<SlashCommandResultPayload> {
     if (!args || args.trim().length === 0) {
       // Clear the override when called with no args
-      await this.systemOverride.clear(conversationId);
+      await this.systemOverride.clear(conversationId, scope);
       return {
         command: 'system',
         conversationId,
@@ -236,7 +265,7 @@ export class CommandExecutorService {
       };
     }
 
-    await this.systemOverride.set(conversationId, args.trim());
+    await this.systemOverride.set(conversationId, args.trim(), scope);
     return {
       command: 'system',
       conversationId,
@@ -248,8 +277,9 @@ export class CommandExecutorService {
   private async handleAgent(
     args: string | null,
     conversationId: string,
-    userId: string,
+    scope: ActorTenantScope,
   ): Promise<SlashCommandResultPayload> {
+    const userId = scope.userId;
     if (!args) {
       return {
         command: 'agent',
@@ -338,11 +368,14 @@ export class CommandExecutorService {
         conversationId,
         agentConfig.id,
         agentConfig.name,
+        scope,
         agentConfig.model ?? undefined,
       );
 
       // Broadcast updated session:info so TUI TopBar reflects new agent/model
-      this.chatGateway?.broadcastSessionInfo(conversationId, { agentName: agentConfig.name });
+      this.chatGateway?.broadcastSessionInfo(conversationId, scope, {
+        agentName: agentConfig.name,
+      });
 
       this.logger.log(
         `Agent switched to "${agentConfig.name}" (${agentConfig.id}) for conversation ${conversationId} (M5-003)`,
@@ -403,22 +436,28 @@ export class CommandExecutorService {
           };
         }
         const pollToken = crypto.randomUUID();
-        const key = `mosaic:auth:poll:${pollToken}`;
+        const tokenDigest = await crypto.subtle.digest(
-        // Store pending state in Valkey (TTL 5 minutes)
+          'SHA-256',
+          new TextEncoder().encode(pollToken),
+        );
+        const tokenHash = Array.from(new Uint8Array(tokenDigest), (byte: number): string =>
+          byte.toString(16).padStart(2, '0'),
+        ).join('');
+        const key = `mosaic:auth:poll:${tokenHash}`;
+        // Persist only a short-lived token digest. The raw token is delivered only by
+        // the authenticated dashboard flow, never in chat output or command metadata.
         await this.redis.set(
           key,
           JSON.stringify({ status: 'pending', provider: providerName, userId }),
           'EX',
           300,
         );
-        // In production this would construct an OAuth URL
-        const loginUrl = `${process.env['MOSAIC_BASE_URL'] ?? 'http://localhost:3000'}/auth/provider/${providerName}?token=${pollToken}`;
         return {
           command: 'provider',
           success: true,
-          message: `Open this URL to authenticate with ${providerName}:\n${loginUrl}`,
+          message: `Provider login for ${providerName} is ready. Continue in the authenticated dashboard.`,
           conversationId,
-          data: { loginUrl, pollToken, provider: providerName },
+          data: { provider: providerName },
         };
       }
 

apps/gateway/src/commands/commands.integration.spec.ts

@@ -159,6 +159,7 @@ describe('CommandExecutorService — integration', () => {
   let registry: CommandRegistryService;
   let executor: CommandExecutorService;
   const userId = 'user-integ-001';
+  const userScope = { userId, tenantId: userId };
   const conversationId = 'conv-integ-001';
 
   beforeEach(() => {
@@ -170,7 +171,7 @@ describe('CommandExecutorService — integration', () => {
   // Unknown command returns error
   it('unknown command returns success:false with descriptive message', async () => {
     const payload: SlashCommandPayload = { command: 'nonexistent', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(result.success).toBe(false);
     expect(result.message).toContain('nonexistent');
     expect(result.command).toBe('nonexistent');
@@ -179,7 +180,7 @@ describe('CommandExecutorService — integration', () => {
   // /gc handler calls SessionGCService.sweepOrphans (admin-only, no userId arg)
   it('/gc calls SessionGCService.sweepOrphans without arguments', async () => {
     const payload: SlashCommandPayload = { command: 'gc', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(mockSessionGC.sweepOrphans).toHaveBeenCalledWith();
     expect(result.success).toBe(true);
     expect(result.message).toContain('GC sweep complete');
@@ -190,8 +191,8 @@ describe('CommandExecutorService — integration', () => {
   it('/system with text calls SystemOverrideService.set', async () => {
     const override = 'You are a helpful assistant.';
     const payload: SlashCommandPayload = { command: 'system', args: override, conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
-    expect(mockSystemOverride.set).toHaveBeenCalledWith(conversationId, override);
+    expect(mockSystemOverride.set).toHaveBeenCalledWith(conversationId, override, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('override set');
   });
@@ -199,8 +200,8 @@ describe('CommandExecutorService — integration', () => {
   // /system with no args clears the override
   it('/system with no args calls SystemOverrideService.clear', async () => {
     const payload: SlashCommandPayload = { command: 'system', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
-    expect(mockSystemOverride.clear).toHaveBeenCalledWith(conversationId);
+    expect(mockSystemOverride.clear).toHaveBeenCalledWith(conversationId, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('cleared');
   });
@@ -212,7 +213,7 @@ describe('CommandExecutorService — integration', () => {
       args: 'claude-3-opus',
       conversationId,
     };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('model');
     expect(result.message).toContain('claude-3-opus');
@@ -221,7 +222,7 @@ describe('CommandExecutorService — integration', () => {
   // /thinking with valid level returns success
   it('/thinking with valid level returns success', async () => {
     const payload: SlashCommandPayload = { command: 'thinking', args: 'high', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('high');
   });
@@ -229,7 +230,7 @@ describe('CommandExecutorService — integration', () => {
   // /thinking with invalid level returns usage message
   it('/thinking with invalid level returns usage message', async () => {
     const payload: SlashCommandPayload = { command: 'thinking', args: 'invalid', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.message).toContain('Usage:');
   });
@@ -237,7 +238,7 @@ describe('CommandExecutorService — integration', () => {
   // /new command returns success
   it('/new returns success', async () => {
     const payload: SlashCommandPayload = { command: 'new', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(result.success).toBe(true);
     expect(result.command).toBe('new');
   });
@@ -245,7 +246,7 @@ describe('CommandExecutorService — integration', () => {
   // /reload without reloadService returns failure
   it('/reload without ReloadService returns failure', async () => {
     const payload: SlashCommandPayload = { command: 'reload', conversationId };
-    const result = await executor.execute(payload, userId);
+    const result = await executor.execute(payload, userScope);
     expect(result.success).toBe(false);
     expect(result.message).toContain('ReloadService');
   });
@@ -255,7 +256,7 @@ describe('CommandExecutorService — integration', () => {
   for (const cmd of stubCommands) {
     it(`/${cmd} returns success (stub)`, async () => {
       const payload: SlashCommandPayload = { command: cmd, conversationId };
-      const result = await executor.execute(payload, userId);
+      const result = await executor.execute(payload, userScope);
       expect(result.success).toBe(true);
       expect(result.command).toBe(cmd);
     });

apps/gateway/src/commands/commands.module.ts

@@ -3,6 +3,7 @@ import { createQueue, type QueueHandle } from '@mosaicstack/queue';
 import { ChatModule } from '../chat/chat.module.js';
 import { GCModule } from '../gc/gc.module.js';
 import { ReloadModule } from '../reload/reload.module.js';
+import { CommandAuthorizationService } from './command-authorization.service.js';
 import { CommandExecutorService } from './command-executor.service.js';
 import { CommandRegistryService } from './command-registry.service.js';
 import { COMMANDS_REDIS } from './commands.tokens.js';
@@ -24,6 +25,7 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
       inject: [COMMANDS_QUEUE_HANDLE],
     },
     CommandRegistryService,
+    CommandAuthorizationService,
     CommandExecutorService,
   ],
   exports: [CommandRegistryService, CommandExecutorService],

apps/gateway/src/federation/client/__tests__/query-source.service.spec.ts

@@ -0,0 +1,255 @@
+import 'reflect-metadata';
+import { describe, expect, it, vi } from 'vitest';
+import type { Db } from '@mosaicstack/db';
+import type { FederationListResponse } from '@mosaicstack/types';
+import {
+  FederationClientError,
+  type FederationClientService,
+} from '../federation-client.service.js';
+import { type QuerySourceError, QuerySourceService } from '../query-source.service.js';
+
+interface TestRow {
+  id: string;
+  title: string;
+}
+
+interface PeerRow {
+  id: string;
+  commonName: string;
+  endpointUrl: string | null;
+  clientKeyPem: string | null;
+  state: 'active' | 'pending' | 'suspended' | 'revoked';
+}
+
+const LOCAL_ROWS: TestRow[] = [
+  { id: 'local-1', title: 'Local One' },
+  { id: 'local-2', title: 'Local Two' },
+];
+
+const PEER_A: PeerRow = {
+  id: 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa',
+  commonName: 'peer-a',
+  endpointUrl: 'https://peer-a.example.com',
+  clientKeyPem: 'sealed-key-a',
+  state: 'active',
+};
+
+const PEER_B: PeerRow = {
+  id: 'bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb',
+  commonName: 'peer-b',
+  endpointUrl: 'https://peer-b.example.com',
+  clientKeyPem: 'sealed-key-b',
+  state: 'active',
+};
+
+const PEER_LOCALHOST: PeerRow = {
+  id: 'cccccccc-cccc-cccc-cccc-cccccccccccc',
+  commonName: 'peer-localhost',
+  endpointUrl: 'https://localhost:3001',
+  clientKeyPem: 'sealed-key-c',
+  state: 'active',
+};
+
+function makeDb(activePeers: PeerRow[]): Db {
+  const orderBy = vi.fn().mockResolvedValue(activePeers);
+  const where = vi.fn().mockReturnValue({ orderBy });
+  const from = vi.fn().mockReturnValue({ where });
+  const select = vi.fn().mockReturnValue({ from });
+
+  return {
+    select,
+    insert: vi.fn(),
+    update: vi.fn(),
+    delete: vi.fn(),
+    transaction: vi.fn(),
+  } as unknown as Db;
+}
+
+function makeFederationClient(
+  list: (
+    peerId: string,
+    resource: string,
+    request: Record<string, unknown>,
+  ) => Promise<FederationListResponse<TestRow>>,
+): FederationClientService {
+  return {
+    list: list as unknown as FederationClientService['list'],
+  } as FederationClientService;
+}
+
+function makeLocalResponse(rows: TestRow[] = LOCAL_ROWS): Promise<FederationListResponse<TestRow>> {
+  return Promise.resolve({ items: rows });
+}
+
+describe('QuerySourceService', () => {
+  it('routes source="local" to the local executor and tags rows as local', async () => {
+    const list = vi.fn(async (): Promise<FederationListResponse<TestRow>> => ({ items: [] }));
+    const service = new QuerySourceService(makeDb([PEER_A]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'local',
+      resource: 'tasks',
+      request: { cursor: 'ignored-for-local-test' },
+      local: () => makeLocalResponse(),
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'local-2', title: 'Local Two', _source: 'local' },
+      ],
+    });
+    expect(list).not.toHaveBeenCalled();
+  });
+
+  it('routes source="federated:<host>" to the matching active peer and tags rows with peer commonName', async () => {
+    const list = vi.fn(
+      async (): Promise<FederationListResponse<TestRow>> => ({
+        items: [{ id: 'remote-1', title: 'Remote One' }],
+      }),
+    );
+    const service = new QuerySourceService(makeDb([PEER_A, PEER_B]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'federated:peer-b.example.com',
+      resource: 'tasks',
+      request: { status: 'open' },
+      local: () => makeLocalResponse(),
+    });
+
+    expect(result).toEqual({
+      items: [{ id: 'remote-1', title: 'Remote One', _source: 'peer-b' }],
+    });
+    expect(list).toHaveBeenCalledWith(PEER_B.id, 'tasks', { status: 'open' });
+  });
+
+  it('matches federated hosts by endpoint host including non-default port', async () => {
+    const list = vi.fn(
+      async (): Promise<FederationListResponse<TestRow>> => ({
+        items: [{ id: 'remote-port', title: 'Remote Port' }],
+      }),
+    );
+    const service = new QuerySourceService(makeDb([PEER_LOCALHOST]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'federated:localhost:3001',
+      resource: 'tasks',
+      request: {},
+      local: () => makeLocalResponse(),
+    });
+
+    expect(result).toEqual({
+      items: [{ id: 'remote-port', title: 'Remote Port', _source: 'peer-localhost' }],
+    });
+    expect(list).toHaveBeenCalledWith(PEER_LOCALHOST.id, 'tasks', {});
+  });
+
+  it('fans out source="all" to local plus every active outbound peer in parallel and merges tagged rows', async () => {
+    const callOrder: string[] = [];
+    const list = vi.fn(async (peerId: string): Promise<FederationListResponse<TestRow>> => {
+      callOrder.push(`remote-start:${peerId}`);
+      await Promise.resolve();
+      return {
+        items: [{ id: `remote-${peerId.slice(0, 1)}`, title: `Remote ${peerId.slice(0, 1)}` }],
+      };
+    });
+    const service = new QuerySourceService(makeDb([PEER_A, PEER_B]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'all',
+      resource: 'tasks',
+      request: { limit: 25 },
+      local: async () => {
+        callOrder.push('local-start');
+        await Promise.resolve();
+        return { items: [{ id: 'local-1', title: 'Local One' }] };
+      },
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'remote-a', title: 'Remote a', _source: 'peer-a' },
+        { id: 'remote-b', title: 'Remote b', _source: 'peer-b' },
+      ],
+    });
+    expect(list).toHaveBeenCalledTimes(2);
+    expect(callOrder).toEqual([
+      'local-start',
+      `remote-start:${PEER_A.id}`,
+      `remote-start:${PEER_B.id}`,
+    ]);
+  });
+
+  it('marks source="all" as partial and truncated when any subquery returns a cursor', async () => {
+    const list = vi.fn(
+      async (): Promise<FederationListResponse<TestRow>> => ({
+        items: [{ id: 'remote-a', title: 'Remote A' }],
+        nextCursor: 'remote-next',
+      }),
+    );
+    const service = new QuerySourceService(makeDb([PEER_A]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'all',
+      resource: 'tasks',
+      request: {},
+      local: () => makeLocalResponse([{ id: 'local-1', title: 'Local One' }]),
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'remote-a', title: 'Remote A', _source: 'peer-a' },
+      ],
+      _partial: true,
+      _truncated: true,
+    });
+  });
+
+  it('returns _partial=true for source="all" when one peer fails without dropping successful sources', async () => {
+    const list = vi.fn(async (peerId: string): Promise<FederationListResponse<TestRow>> => {
+      if (peerId === PEER_B.id) {
+        throw new FederationClientError({
+          code: 'NETWORK',
+          message: 'peer unavailable',
+          peerId,
+        });
+      }
+      return { items: [{ id: 'remote-a', title: 'Remote A' }] };
+    });
+    const service = new QuerySourceService(makeDb([PEER_A, PEER_B]), makeFederationClient(list));
+
+    const result = await service.list<TestRow>({
+      source: 'all',
+      resource: 'tasks',
+      request: {},
+      local: () => makeLocalResponse([{ id: 'local-1', title: 'Local One' }]),
+    });
+
+    expect(result).toEqual({
+      items: [
+        { id: 'local-1', title: 'Local One', _source: 'local' },
+        { id: 'remote-a', title: 'Remote A', _source: 'peer-a' },
+      ],
+      _partial: true,
+    });
+  });
+
+  it('throws QuerySourceError when a federated host does not match an active outbound peer', async () => {
+    const list = vi.fn(async (): Promise<FederationListResponse<TestRow>> => ({ items: [] }));
+    const service = new QuerySourceService(makeDb([PEER_A]), makeFederationClient(list));
+
+    await expect(
+      service.list<TestRow>({
+        source: 'federated:missing.example.com',
+        resource: 'tasks',
+        request: {},
+        local: () => makeLocalResponse(),
+      }),
+    ).rejects.toMatchObject({
+      name: 'QuerySourceError',
+      code: 'PEER_NOT_FOUND',
+    } satisfies Partial<QuerySourceError>);
+  });
+});

apps/gateway/src/federation/client/index.ts

@@ -11,3 +11,13 @@ export {
   type FederationClientErrorCode,
   type FederationClientErrorOptions,
 } from './federation-client.service.js';
+export {
+  QuerySourceService,
+  QuerySourceError,
+  type QuerySource,
+  type QuerySourceErrorCode,
+  type QuerySourceErrorOptions,
+  type QuerySourceListOptions,
+  type QuerySourceListResponse,
+  type LocalListExecutor,
+} from './query-source.service.js';

apps/gateway/src/federation/client/query-source.service.ts

@@ -0,0 +1,261 @@
+/**
+ * QuerySourceService — gateway query source router (FED-M3-09).
+ *
+ * Accepts the federation query-layer `source` selector and routes list-style
+ * reads to local storage, one federated peer, or all active outbound peers.
+ *
+ * `source: "all"` is intentionally tolerant of per-peer failures: local data
+ * and successful peer responses are returned, and the envelope is marked
+ * `_partial: true`.  Local failures still reject because there is no safe local
+ * fallback and the gateway's own storage is expected to be authoritative.
+ */
+
+import { Inject, Injectable, Logger } from '@nestjs/common';
+import { and, eq, federationPeers, isNotNull, type Db } from '@mosaicstack/db';
+import {
+  SOURCE_LOCAL,
+  tagWithSource,
+  type FederationListResponse,
+  type SourceTag,
+} from '@mosaicstack/types';
+import { DB } from '../../database/database.module.js';
+import { FederationClientService } from './federation-client.service.js';
+
+export type QuerySource = 'local' | 'all' | `federated:${string}`;
+
+export type QuerySourceErrorCode = 'INVALID_SOURCE' | 'PEER_NOT_FOUND';
+
+export interface QuerySourceErrorOptions {
+  code: QuerySourceErrorCode;
+  message: string;
+  source: string;
+}
+
+export class QuerySourceError extends Error {
+  readonly code: QuerySourceErrorCode;
+  readonly source: string;
+
+  constructor(opts: QuerySourceErrorOptions) {
+    super(opts.message);
+    this.name = 'QuerySourceError';
+    this.code = opts.code;
+    this.source = opts.source;
+  }
+}
+
+export type LocalListExecutor<T extends object> = () => Promise<FederationListResponse<T> | T[]>;
+
+export interface QuerySourceListOptions<T extends object> {
+  source: QuerySource;
+  resource: string;
+  request?: Record<string, unknown>;
+  local: LocalListExecutor<T>;
+}
+
+export type QuerySourceListResponse<T extends object> = FederationListResponse<T & SourceTag>;
+
+interface OutboundPeer {
+  id: string;
+  commonName: string;
+  endpointUrl: string;
+}
+
+interface TaggedList<T extends object> {
+  items: Array<T & SourceTag>;
+  partial: boolean;
+  truncated: boolean;
+  nextCursor?: string;
+}
+
+@Injectable()
+export class QuerySourceService {
+  private readonly logger = new Logger(QuerySourceService.name);
+
+  constructor(
+    @Inject(DB) private readonly db: Db,
+    @Inject(FederationClientService) private readonly federationClient: FederationClientService,
+  ) {}
+
+  async list<T extends object>(
+    options: QuerySourceListOptions<T>,
+  ): Promise<QuerySourceListResponse<T>> {
+    const request = options.request ?? {};
+
+    if (options.source === 'local') {
+      const local = await this.runLocal(options.local);
+      return this.toResponse(this.tagList(local, SOURCE_LOCAL));
+    }
+
+    if (options.source === 'all') {
+      return this.listAll(options.resource, request, options.local);
+    }
+
+    if (options.source.startsWith('federated:')) {
+      const host = options.source.slice('federated:'.length).trim();
+      if (!host) {
+        throw new QuerySourceError({
+          code: 'INVALID_SOURCE',
+          message: 'Federated source must include a host after federated:',
+          source: options.source,
+        });
+      }
+
+      const peer = await this.findPeerByHost(host, options.source);
+      const remote = await this.federationClient.list<T>(peer.id, options.resource, request);
+      return this.toResponse(this.tagList(remote, peer.commonName));
+    }
+
+    throw new QuerySourceError({
+      code: 'INVALID_SOURCE',
+      message: `Unsupported query source: ${options.source}`,
+      source: options.source,
+    });
+  }
+
+  private async listAll<T extends object>(
+    resource: string,
+    request: Record<string, unknown>,
+    local: LocalListExecutor<T>,
+  ): Promise<QuerySourceListResponse<T>> {
+    const peers = await this.listActiveOutboundPeers();
+
+    const localPromise = this.runLocal(local).then((response) =>
+      this.tagList(response, SOURCE_LOCAL),
+    );
+    const remotePromises = peers.map(async (peer: OutboundPeer): Promise<TaggedList<T> | null> => {
+      try {
+        const response = await this.federationClient.list<T>(peer.id, resource, request);
+        return this.tagList(response, peer.commonName);
+      } catch (error: unknown) {
+        this.logger.warn(
+          `Federated query to peer ${peer.commonName} (${peer.id}) failed; returning partial all-source response: ${
+            error instanceof Error ? error.message : String(error)
+          }`,
+        );
+        return null;
+      }
+    });
+
+    const [localResult, ...remoteResults] = await Promise.all([localPromise, ...remotePromises]);
+    const successfulRemoteResults = remoteResults.filter(
+      (result: TaggedList<T> | null): result is TaggedList<T> => result !== null,
+    );
+    const allResults = [localResult, ...successfulRemoteResults];
+    const peerFailure = successfulRemoteResults.length !== peers.length;
+
+    return this.mergeTaggedLists(allResults, peerFailure);
+  }
+
+  private async runLocal<T extends object>(
+    local: LocalListExecutor<T>,
+  ): Promise<FederationListResponse<T>> {
+    const response = await local();
+    if (Array.isArray(response)) {
+      return { items: response };
+    }
+    return response;
+  }
+
+  private tagList<T extends object>(
+    response: FederationListResponse<T>,
+    source: string,
+  ): TaggedList<T> {
+    return {
+      items: tagWithSource(response.items, source),
+      partial: response._partial === true,
+      truncated: response._truncated === true || response.nextCursor !== undefined,
+      nextCursor: response.nextCursor,
+    };
+  }
+
+  private mergeTaggedLists<T extends object>(
+    lists: Array<TaggedList<T>>,
+    peerFailure: boolean,
+  ): QuerySourceListResponse<T> {
+    const items = lists.flatMap((list: TaggedList<T>) => list.items);
+    const partial =
+      peerFailure ||
+      lists.some((list: TaggedList<T>) => list.partial || list.nextCursor !== undefined);
+    const truncated = lists.some((list: TaggedList<T>) => list.truncated);
+
+    const response: QuerySourceListResponse<T> = { items };
+    if (partial) {
+      response._partial = true;
+    }
+    if (truncated) {
+      response._truncated = true;
+    }
+    return response;
+  }
+
+  private toResponse<T extends object>(tagged: TaggedList<T>): QuerySourceListResponse<T> {
+    const response: QuerySourceListResponse<T> = {
+      items: tagged.items,
+    };
+    if (tagged.nextCursor !== undefined) {
+      response.nextCursor = tagged.nextCursor;
+    }
+    if (tagged.partial) {
+      response._partial = true;
+    }
+    if (tagged.truncated) {
+      response._truncated = true;
+    }
+    return response;
+  }
+
+  private async findPeerByHost(sourceHost: string, source: string): Promise<OutboundPeer> {
+    const host = normalizeHost(sourceHost);
+    const peers = await this.listActiveOutboundPeers();
+    const peer = peers.find((candidate: OutboundPeer) => {
+      const commonName = normalizeHost(candidate.commonName);
+      const endpointHosts = endpointHostKeys(candidate.endpointUrl).map((endpointHost: string) =>
+        normalizeHost(endpointHost),
+      );
+      return commonName === host || endpointHosts.includes(host);
+    });
+
+    if (!peer) {
+      throw new QuerySourceError({
+        code: 'PEER_NOT_FOUND',
+        message: `No active outbound federation peer matches source ${source}`,
+        source,
+      });
+    }
+
+    return peer;
+  }
+
+  private async listActiveOutboundPeers(): Promise<OutboundPeer[]> {
+    const rows = await this.db
+      .select({
+        id: federationPeers.id,
+        commonName: federationPeers.commonName,
+        endpointUrl: federationPeers.endpointUrl,
+      })
+      .from(federationPeers)
+      .where(
+        and(
+          eq(federationPeers.state, 'active'),
+          isNotNull(federationPeers.endpointUrl),
+          isNotNull(federationPeers.clientKeyPem),
+        ),
+      )
+      .orderBy(federationPeers.commonName);
+
+    return rows.filter((row): row is OutboundPeer => typeof row.endpointUrl === 'string');
+  }
+}
+
+function normalizeHost(host: string): string {
+  return host.trim().toLowerCase();
+}
+
+function endpointHostKeys(endpointUrl: string): string[] {
+  try {
+    const url = new URL(endpointUrl);
+    return Array.from(new Set([url.host, url.hostname].filter((host: string) => host.length > 0)));
+  } catch {
+    return [];
+  }
+}

apps/gateway/src/federation/federation.module.ts

@@ -4,26 +4,35 @@ import { CaService } from './ca.service.js';
 import { EnrollmentController } from './enrollment.controller.js';
 import { EnrollmentService } from './enrollment.service.js';
 import { FederationController } from './federation.controller.js';
+import { CapabilitiesController } from './server/verbs/capabilities.controller.js';
 import { GrantsService } from './grants.service.js';
-import { FederationClientService } from './client/index.js';
+import { FederationClientService, QuerySourceService } from './client/index.js';
-import { FederationAuthGuard } from './server/index.js';
+import { FederationAuthGuard, FederationScopeService } from './server/index.js';
+import { ListController } from './server/verbs/list.controller.js';
+import { FederationListQueryService } from './server/verbs/list-query.service.js';
 
 @Module({
-  controllers: [EnrollmentController, FederationController],
+  controllers: [EnrollmentController, FederationController, CapabilitiesController, ListController],
   providers: [
     AdminGuard,
     CaService,
     EnrollmentService,
     GrantsService,
     FederationClientService,
+    QuerySourceService,
     FederationAuthGuard,
+    FederationScopeService,
+    FederationListQueryService,
   ],
   exports: [
     CaService,
     EnrollmentService,
     GrantsService,
     FederationClientService,
+    QuerySourceService,
     FederationAuthGuard,
+    FederationScopeService,
+    FederationListQueryService,
   ],
 })
 export class FederationModule {}

apps/gateway/src/federation/server/__tests__/scope.service.spec.ts

@@ -0,0 +1,324 @@
+/**
+ * Unit tests for FederationScopeService (FED-M3-04).
+ *
+ * Coverage:
+ *  - resource allowlist deny
+ *  - excluded resource deny
+ *  - invalid scope deny
+ *  - invalid requested limit deny
+ *  - native RBAC deny as subjectUserId
+ *  - scope/native filter intersection for personal and team rows
+ *  - native RBAC personal deny wins over scope include_personal allow/default
+ *  - max_rows_per_query cap
+ */
+
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+import { FederationScopeService, type FederationNativeRbacEvaluator } from '../scope.service.js';
+import type { FederationContext } from '../federation-context.js';
+
+const GRANT_ID = 'grant-1';
+const PEER_ID = 'peer-1';
+const SUBJECT_USER_ID = 'user-1';
+
+function makeContext(scope: Record<string, unknown>): FederationContext {
+  return {
+    grantId: GRANT_ID,
+    peerId: PEER_ID,
+    subjectUserId: SUBJECT_USER_ID,
+    scope,
+  };
+}
+
+function makeNativeRbac(
+  result: Awaited<ReturnType<FederationNativeRbacEvaluator['evaluateReadAccess']>>,
+): FederationNativeRbacEvaluator {
+  return {
+    evaluateReadAccess: vi.fn().mockResolvedValue(result),
+  };
+}
+
+describe('FederationScopeService', () => {
+  let service: FederationScopeService;
+
+  beforeEach(() => {
+    service = new FederationScopeService();
+  });
+
+  it('allows a granted resource and returns a capped query filter', async () => {
+    const nativeRbac = makeNativeRbac({
+      allowed: true,
+      access: { includePersonal: true, teamIds: ['team-1', 'team-2'] },
+    });
+
+    const result = await service.evaluateAccess({
+      context: makeContext({
+        resources: ['tasks'],
+        filters: { tasks: { include_teams: ['team-1', 'team-3'], include_personal: true } },
+        max_rows_per_query: 50,
+      }),
+      resource: 'tasks',
+      requestedLimit: 500,
+      nativeRbac,
+    });
+
+    expect(result).toEqual({
+      allowed: true,
+      filter: {
+        resource: 'tasks',
+        subjectUserId: SUBJECT_USER_ID,
+        includePersonal: true,
+        teamIds: ['team-1'],
+        limit: 50,
+        maxRowsPerQuery: 50,
+      },
+    });
+    expect(nativeRbac.evaluateReadAccess).toHaveBeenCalledWith({
+      grantId: GRANT_ID,
+      peerId: PEER_ID,
+      subjectUserId: SUBJECT_USER_ID,
+      resource: 'tasks',
+    });
+  });
+
+  it('defaults absent resource filters to native RBAC personal and team visibility', async () => {
+    const result = await service.evaluateAccess({
+      context: makeContext({ resources: ['notes'], max_rows_per_query: 100 }),
+      resource: 'notes',
+      nativeRbac: makeNativeRbac({
+        allowed: true,
+        access: { includePersonal: true, teamIds: ['team-1', 'team-2'] },
+      }),
+    });
+
+    expect(result).toMatchObject({
+      allowed: true,
+      filter: {
+        includePersonal: true,
+        teamIds: ['team-1', 'team-2'],
+        limit: 100,
+      },
+    });
+  });
+
+  it('honors include_personal false even when native RBAC allows personal rows', async () => {
+    const result = await service.evaluateAccess({
+      context: makeContext({
+        resources: ['memory'],
+        filters: { memory: { include_personal: false } },
+        max_rows_per_query: 25,
+      }),
+      resource: 'memory',
+      nativeRbac: makeNativeRbac({
+        allowed: true,
+        access: { includePersonal: true, teamIds: [] },
+      }),
+    });
+
+    expect(result).toMatchObject({
+      allowed: true,
+      filter: {
+        includePersonal: false,
+        teamIds: [],
+      },
+    });
+  });
+
+  it('does not leak personal rows when scope allows personal but native RBAC denies personal', async () => {
+    const result = await service.evaluateAccess({
+      context: makeContext({
+        resources: ['tasks'],
+        filters: { tasks: { include_personal: true } },
+        max_rows_per_query: 25,
+      }),
+      resource: 'tasks',
+      nativeRbac: makeNativeRbac({
+        allowed: true,
+        access: { includePersonal: false, teamIds: ['team-1'] },
+      }),
+    });
+
+    expect(result).toMatchObject({
+      allowed: true,
+      filter: {
+        includePersonal: false,
+        teamIds: ['team-1'],
+      },
+    });
+  });
+
+  it('does not widen native RBAC when scope includes teams the user cannot access', async () => {
+    const result = await service.evaluateAccess({
+      context: makeContext({
+        resources: ['tasks'],
+        filters: { tasks: { include_teams: ['team-2'], include_personal: false } },
+        max_rows_per_query: 25,
+      }),
+      resource: 'tasks',
+      nativeRbac: makeNativeRbac({
+        allowed: true,
+        access: { includePersonal: true, teamIds: ['team-1'] },
+      }),
+    });
+
+    expect(result).toMatchObject({
+      allowed: true,
+      filter: {
+        includePersonal: false,
+        teamIds: [],
+      },
+    });
+  });
+
+  it('denies invalid grant scope before RBAC evaluation', async () => {
+    const nativeRbac = makeNativeRbac({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+
+    const result = await service.evaluateAccess({
+      context: makeContext({ resources: [], max_rows_per_query: 100 }),
+      resource: 'tasks',
+      nativeRbac,
+    });
+
+    expect(result).toMatchObject({
+      allowed: false,
+      deny: {
+        code: 'invalid_scope',
+        stage: 'scope_parse',
+        statusCode: 400,
+        grantId: GRANT_ID,
+        subjectUserId: SUBJECT_USER_ID,
+        resource: 'tasks',
+      },
+    });
+    expect(nativeRbac.evaluateReadAccess).not.toHaveBeenCalled();
+  });
+
+  it('denies unsupported resource names before RBAC evaluation', async () => {
+    const nativeRbac = makeNativeRbac({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+
+    const result = await service.evaluateAccess({
+      context: makeContext({ resources: ['tasks'], max_rows_per_query: 100 }),
+      resource: 'unknown_resource',
+      nativeRbac,
+    });
+
+    expect(result).toMatchObject({
+      allowed: false,
+      deny: {
+        code: 'invalid_resource',
+        stage: 'resource_allowlist',
+        statusCode: 403,
+      },
+    });
+    expect(nativeRbac.evaluateReadAccess).not.toHaveBeenCalled();
+  });
+
+  it('denies resources explicitly present in excluded_resources before allowlist miss', async () => {
+    const nativeRbac = makeNativeRbac({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+
+    const result = await service.evaluateAccess({
+      context: makeContext({
+        resources: ['tasks'],
+        excluded_resources: ['credentials'],
+        max_rows_per_query: 100,
+      }),
+      resource: 'credentials',
+      nativeRbac,
+    });
+
+    expect(result).toMatchObject({
+      allowed: false,
+      deny: {
+        code: 'resource_excluded',
+        stage: 'resource_exclusion',
+        statusCode: 403,
+        resource: 'credentials',
+      },
+    });
+    expect(nativeRbac.evaluateReadAccess).not.toHaveBeenCalled();
+  });
+
+  it('denies supported resources that are not granted by scope', async () => {
+    const nativeRbac = makeNativeRbac({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+
+    const result = await service.evaluateAccess({
+      context: makeContext({ resources: ['tasks'], max_rows_per_query: 100 }),
+      resource: 'notes',
+      nativeRbac,
+    });
+
+    expect(result).toMatchObject({
+      allowed: false,
+      deny: {
+        code: 'resource_not_granted',
+        stage: 'resource_allowlist',
+        statusCode: 403,
+        resource: 'notes',
+      },
+    });
+    expect(nativeRbac.evaluateReadAccess).not.toHaveBeenCalled();
+  });
+
+  it('denies invalid requested row limits before RBAC evaluation', async () => {
+    const nativeRbac = makeNativeRbac({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+
+    const result = await service.evaluateAccess({
+      context: makeContext({ resources: ['tasks'], max_rows_per_query: 100 }),
+      resource: 'tasks',
+      requestedLimit: 0,
+      nativeRbac,
+    });
+
+    expect(result).toMatchObject({
+      allowed: false,
+      deny: {
+        code: 'invalid_limit',
+        stage: 'row_cap',
+        statusCode: 400,
+        details: { requestedLimit: 0 },
+      },
+    });
+    expect(nativeRbac.evaluateReadAccess).not.toHaveBeenCalled();
+  });
+
+  it('denies when native RBAC rejects subjectUserId access to the resource', async () => {
+    const result = await service.evaluateAccess({
+      context: makeContext({ resources: ['tasks'], max_rows_per_query: 100 }),
+      resource: 'tasks',
+      nativeRbac: makeNativeRbac({
+        allowed: false,
+        reason: 'read:tasks denied',
+        details: { permission: 'tasks:read' },
+      }),
+    });
+
+    expect(result).toEqual({
+      allowed: false,
+      deny: {
+        code: 'native_rbac_denied',
+        stage: 'native_rbac',
+        statusCode: 403,
+        message: 'read:tasks denied',
+        grantId: GRANT_ID,
+        peerId: PEER_ID,
+        subjectUserId: SUBJECT_USER_ID,
+        resource: 'tasks',
+        details: { permission: 'tasks:read' },
+      },
+    });
+  });
+});

apps/gateway/src/federation/server/index.ts

@@ -10,4 +10,22 @@
  */
 
 export { FederationAuthGuard } from './federation-auth.guard.js';
+export { FederationScopeService } from './scope.service.js';
 export type { FederationContext } from './federation-context.js';
+export type {
+  FederationNativeRbacAccess,
+  FederationNativeRbacAllowedResult,
+  FederationNativeRbacDeniedResult,
+  FederationNativeRbacEvaluator,
+  FederationNativeRbacRequest,
+  FederationNativeRbacResult,
+  FederationScopeAllowedResult,
+  FederationScopeDeniedResult,
+  FederationScopeDenyCode,
+  FederationScopeDenyDetails,
+  FederationScopeDenyReason,
+  FederationScopeDenyStage,
+  FederationScopeEvaluationInput,
+  FederationScopeEvaluationResult,
+  FederationScopeQueryFilter,
+} from './scope.service.js';

apps/gateway/src/federation/server/scope.service.ts

@@ -0,0 +1,272 @@
+/**
+ * FederationScopeService — M3 server-side scope enforcement pipeline.
+ *
+ * Pure trust-boundary service: it validates the grant scope, asks an injected
+ * native RBAC evaluator what the subject user can read locally, intersects that
+ * answer with the federation scope filters, and returns a query filter for the
+ * verb controllers. The service performs no DB calls directly.
+ */
+
+import { Injectable } from '@nestjs/common';
+import {
+  FEDERATION_RESOURCE_VALUES,
+  type FederationResource,
+  FederationScopeError,
+  parseFederationScope,
+} from '../scope-schema.js';
+import type { FederationContext } from './federation-context.js';
+
+const federationResourceSet: ReadonlySet<string> = new Set<string>(FEDERATION_RESOURCE_VALUES);
+
+export type FederationScopeDenyStage =
+  | 'scope_parse'
+  | 'resource_allowlist'
+  | 'resource_exclusion'
+  | 'native_rbac'
+  | 'row_cap';
+
+export type FederationScopeDenyCode =
+  | 'invalid_scope'
+  | 'invalid_resource'
+  | 'resource_not_granted'
+  | 'resource_excluded'
+  | 'native_rbac_denied'
+  | 'invalid_limit';
+
+export type FederationScopeDenyStatus = 400 | 403;
+
+export interface FederationScopeDenyDetails {
+  readonly [key: string]: string | number | boolean | readonly string[];
+}
+
+export interface FederationScopeDenyReason {
+  readonly code: FederationScopeDenyCode;
+  readonly stage: FederationScopeDenyStage;
+  readonly statusCode: FederationScopeDenyStatus;
+  readonly message: string;
+  readonly grantId: string;
+  readonly peerId: string;
+  readonly subjectUserId: string;
+  readonly resource: string;
+  readonly details?: FederationScopeDenyDetails;
+}
+
+export interface FederationNativeRbacRequest {
+  readonly grantId: string;
+  readonly peerId: string;
+  readonly subjectUserId: string;
+  readonly resource: FederationResource;
+}
+
+export interface FederationNativeRbacAccess {
+  /** Whether this user may read personal rows for this resource. */
+  readonly includePersonal: boolean;
+
+  /** Team IDs this user may read for this resource under native RBAC. */
+  readonly teamIds: readonly string[];
+}
+
+export interface FederationNativeRbacAllowedResult {
+  readonly allowed: true;
+  readonly access: FederationNativeRbacAccess;
+}
+
+export interface FederationNativeRbacDeniedResult {
+  readonly allowed: false;
+  readonly reason?: string;
+  readonly details?: FederationScopeDenyDetails;
+}
+
+export type FederationNativeRbacResult =
+  | FederationNativeRbacAllowedResult
+  | FederationNativeRbacDeniedResult;
+
+export interface FederationNativeRbacEvaluator {
+  evaluateReadAccess(request: FederationNativeRbacRequest): Promise<FederationNativeRbacResult>;
+}
+
+export interface FederationScopeEvaluationInput {
+  readonly context: FederationContext;
+  readonly resource: string;
+  readonly requestedLimit?: number;
+  readonly nativeRbac: FederationNativeRbacEvaluator;
+}
+
+export interface FederationScopeQueryFilter {
+  readonly resource: FederationResource;
+  readonly subjectUserId: string;
+  readonly includePersonal: boolean;
+  readonly teamIds: readonly string[];
+  readonly limit: number;
+  readonly maxRowsPerQuery: number;
+}
+
+export interface FederationScopeAllowedResult {
+  readonly allowed: true;
+  readonly filter: FederationScopeQueryFilter;
+}
+
+export interface FederationScopeDeniedResult {
+  readonly allowed: false;
+  readonly deny: FederationScopeDenyReason;
+}
+
+export type FederationScopeEvaluationResult =
+  | FederationScopeAllowedResult
+  | FederationScopeDeniedResult;
+
+function isFederationResource(resource: string): resource is FederationResource {
+  return federationResourceSet.has(resource);
+}
+
+function uniqueStrings(values: readonly string[]): readonly string[] {
+  return Array.from(new Set<string>(values));
+}
+
+function intersectTeamIds(
+  nativeTeamIds: readonly string[],
+  scopedTeamIds: readonly string[] | undefined,
+): readonly string[] {
+  const uniqueNativeTeamIds = uniqueStrings(nativeTeamIds);
+
+  if (scopedTeamIds === undefined) {
+    return uniqueNativeTeamIds;
+  }
+
+  const nativeSet = new Set<string>(uniqueNativeTeamIds);
+  return uniqueStrings(scopedTeamIds).filter((teamId: string): boolean => nativeSet.has(teamId));
+}
+
+function makeDenyReason(params: {
+  readonly code: FederationScopeDenyCode;
+  readonly stage: FederationScopeDenyStage;
+  readonly statusCode?: FederationScopeDenyStatus;
+  readonly message: string;
+  readonly context: FederationContext;
+  readonly resource: string;
+  readonly details?: FederationScopeDenyDetails;
+}): FederationScopeDeniedResult {
+  return {
+    allowed: false,
+    deny: {
+      code: params.code,
+      stage: params.stage,
+      statusCode: params.statusCode ?? 403,
+      message: params.message,
+      grantId: params.context.grantId,
+      peerId: params.context.peerId,
+      subjectUserId: params.context.subjectUserId,
+      resource: params.resource,
+      ...(params.details !== undefined ? { details: params.details } : {}),
+    },
+  };
+}
+
+@Injectable()
+export class FederationScopeService {
+  async evaluateAccess(
+    input: FederationScopeEvaluationInput,
+  ): Promise<FederationScopeEvaluationResult> {
+    const { context, resource, requestedLimit, nativeRbac } = input;
+
+    let scope: ReturnType<typeof parseFederationScope>;
+    try {
+      scope = parseFederationScope(context.scope);
+    } catch (error: unknown) {
+      const message =
+        error instanceof FederationScopeError
+          ? 'Federation grant scope is invalid'
+          : 'Federation grant scope could not be parsed';
+      const details = error instanceof Error ? { reason: error.message } : undefined;
+      return makeDenyReason({
+        code: 'invalid_scope',
+        stage: 'scope_parse',
+        statusCode: 400,
+        message,
+        context,
+        resource,
+        ...(details !== undefined ? { details } : {}),
+      });
+    }
+
+    if (!isFederationResource(resource)) {
+      return makeDenyReason({
+        code: 'invalid_resource',
+        stage: 'resource_allowlist',
+        message: 'Requested federation resource is not supported',
+        context,
+        resource,
+        details: { supportedResources: FEDERATION_RESOURCE_VALUES },
+      });
+    }
+
+    if (scope.excluded_resources.includes(resource)) {
+      return makeDenyReason({
+        code: 'resource_excluded',
+        stage: 'resource_exclusion',
+        message: 'Requested federation resource is explicitly excluded by grant scope',
+        context,
+        resource,
+      });
+    }
+
+    if (!scope.resources.includes(resource)) {
+      return makeDenyReason({
+        code: 'resource_not_granted',
+        stage: 'resource_allowlist',
+        message: 'Requested federation resource is not granted by scope',
+        context,
+        resource,
+        details: { grantedResources: scope.resources },
+      });
+    }
+
+    if (requestedLimit !== undefined && (!Number.isInteger(requestedLimit) || requestedLimit < 1)) {
+      return makeDenyReason({
+        code: 'invalid_limit',
+        stage: 'row_cap',
+        statusCode: 400,
+        message: 'Requested row limit must be a positive integer',
+        context,
+        resource,
+        details: { requestedLimit },
+      });
+    }
+
+    const nativeResult = await nativeRbac.evaluateReadAccess({
+      grantId: context.grantId,
+      peerId: context.peerId,
+      subjectUserId: context.subjectUserId,
+      resource,
+    });
+
+    if (!nativeResult.allowed) {
+      return makeDenyReason({
+        code: 'native_rbac_denied',
+        stage: 'native_rbac',
+        message: nativeResult.reason ?? 'Subject user is not allowed to read this resource',
+        context,
+        resource,
+        ...(nativeResult.details !== undefined ? { details: nativeResult.details } : {}),
+      });
+    }
+
+    const scopeFilter = scope.filters?.[resource];
+    const includePersonal =
+      Boolean(scopeFilter?.include_personal ?? true) && nativeResult.access.includePersonal;
+    const teamIds = intersectTeamIds(nativeResult.access.teamIds, scopeFilter?.include_teams);
+    const limit = Math.min(requestedLimit ?? scope.max_rows_per_query, scope.max_rows_per_query);
+
+    return {
+      allowed: true,
+      filter: {
+        resource,
+        subjectUserId: context.subjectUserId,
+        includePersonal,
+        teamIds,
+        limit,
+        maxRowsPerQuery: scope.max_rows_per_query,
+      },
+    };
+  }
+}

apps/gateway/src/federation/server/verbs/__tests__/capabilities.controller.spec.ts

@@ -0,0 +1,88 @@
+import 'reflect-metadata';
+import { RequestMethod } from '@nestjs/common';
+import { describe, expect, it } from 'vitest';
+import type { FastifyRequest } from 'fastify';
+import { FederationCapabilitiesResponseSchema, FEDERATION_VERBS } from '@mosaicstack/types';
+import { FederationScopeError } from '../../../scope-schema.js';
+import { FederationAuthGuard } from '../../federation-auth.guard.js';
+import { CapabilitiesController } from '../capabilities.controller.js';
+
+const VALID_SCOPE = {
+  resources: ['tasks', 'notes'],
+  excluded_resources: ['credentials'],
+  max_rows_per_query: 250,
+} as const;
+
+const DEFAULTED_SCOPE = {
+  resources: ['memory'],
+  max_rows_per_query: 10,
+} as const;
+
+function makeRequest(scope: Record<string, unknown>): FastifyRequest {
+  return {
+    federationContext: {
+      grantId: 'grant-1',
+      peerId: 'peer-1',
+      subjectUserId: 'user-1',
+      scope,
+    },
+  } as FastifyRequest;
+}
+
+describe('CapabilitiesController', () => {
+  it('declares GET /api/federation/v1/capabilities', () => {
+    expect(Reflect.getMetadata('path', CapabilitiesController)).toBe(
+      'api/federation/v1/capabilities',
+    );
+    expect(Reflect.getMetadata('path', CapabilitiesController.prototype.getCapabilities)).toBe('/');
+    expect(Reflect.getMetadata('method', CapabilitiesController.prototype.getCapabilities)).toBe(
+      RequestMethod.GET,
+    );
+  });
+
+  it('is protected only by FederationAuthGuard', () => {
+    const guards = Reflect.getMetadata('__guards__', CapabilitiesController) as unknown[];
+
+    expect(guards).toEqual([FederationAuthGuard]);
+  });
+
+  it('returns resources, excluded resources, max rows, and M3 supported verbs from the active grant scope', () => {
+    const controller = new CapabilitiesController();
+
+    const response = controller.getCapabilities(makeRequest(VALID_SCOPE));
+
+    expect(response).toEqual({
+      resources: ['tasks', 'notes'],
+      excluded_resources: ['credentials'],
+      max_rows_per_query: 250,
+      supported_verbs: [...FEDERATION_VERBS],
+    });
+    expect(FederationCapabilitiesResponseSchema.safeParse(response).success).toBe(true);
+  });
+
+  it('applies scope defaults without RBAC or resource filtering', () => {
+    const controller = new CapabilitiesController();
+
+    const response = controller.getCapabilities(makeRequest(DEFAULTED_SCOPE));
+
+    expect(response).toEqual({
+      resources: ['memory'],
+      excluded_resources: [],
+      max_rows_per_query: 10,
+      supported_verbs: ['list', 'get', 'capabilities'],
+    });
+  });
+
+  it('rejects invalid scope state instead of returning an invalid capabilities contract', () => {
+    const controller = new CapabilitiesController();
+
+    expect(() =>
+      controller.getCapabilities(
+        makeRequest({
+          resources: [],
+          max_rows_per_query: 0,
+        }),
+      ),
+    ).toThrow(FederationScopeError);
+  });
+});

apps/gateway/src/federation/server/verbs/__tests__/list-query.service.spec.ts

@@ -0,0 +1,428 @@
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
+import {
+  createPgliteDb,
+  insights,
+  missionTasks,
+  missions,
+  preferences,
+  projects,
+  runPgliteMigrations,
+  teams,
+  users,
+  type Db,
+  type DbHandle,
+} from '@mosaicstack/db';
+import type { FederationScopeQueryFilter } from '../../scope.service.js';
+import { FederationListQueryService } from '../list-query.service.js';
+
+const TASK_FILTER: FederationScopeQueryFilter = {
+  resource: 'tasks',
+  subjectUserId: 'user-1',
+  includePersonal: true,
+  teamIds: [],
+  limit: 2,
+  maxRowsPerQuery: 2,
+};
+
+const SUBJECT_USER_ID = 'fed-m3-05-subject';
+const OTHER_USER_ID = 'fed-m3-05-other';
+const TEAM_ID = '05000000-0000-4000-8000-000000000001';
+const UNAUTHORIZED_TEAM_ID = '05000000-0000-4000-8000-000000000002';
+const PERSONAL_PROJECT_ID = '05000000-0000-4000-8000-000000000101';
+const TEAM_PROJECT_ID = '05000000-0000-4000-8000-000000000102';
+const UNAUTHORIZED_PROJECT_ID = '05000000-0000-4000-8000-000000000103';
+const PERSONAL_MISSION_ID = '05000000-0000-4000-8000-000000000201';
+const TEAM_MISSION_ID = '05000000-0000-4000-8000-000000000202';
+const UNAUTHORIZED_MISSION_ID = '05000000-0000-4000-8000-000000000203';
+const SUBJECT_TEAM_NOTE_ID = '05000000-0000-4000-8000-000000000301';
+const OTHER_TEAM_NOTE_ID = '05000000-0000-4000-8000-000000000302';
+const SUBJECT_PERSONAL_NOTE_ID = '05000000-0000-4000-8000-000000000303';
+const SUBJECT_UNAUTHORIZED_NOTE_ID = '05000000-0000-4000-8000-000000000304';
+const INSIGHT_ONE_ID = '05000000-0000-4000-8000-000000000401';
+const INSIGHT_TWO_ID = '05000000-0000-4000-8000-000000000402';
+const PREFERENCE_ONE_ID = '05000000-0000-4000-8000-000000000501';
+const PREFERENCE_TWO_ID = '05000000-0000-4000-8000-000000000502';
+
+let dbHandle: DbHandle | undefined;
+
+function makeService() {
+  return new FederationListQueryService({} as Db);
+}
+
+function makeDbService() {
+  if (!dbHandle) {
+    throw new Error('test DB not initialized');
+  }
+  return new FederationListQueryService(dbHandle.db);
+}
+
+async function seedNotesFixture() {
+  if (!dbHandle) {
+    throw new Error('test DB not initialized');
+  }
+
+  await dbHandle.db.insert(users).values([
+    {
+      id: SUBJECT_USER_ID,
+      name: 'Federation Subject',
+      email: `${SUBJECT_USER_ID}@example.test`,
+      emailVerified: false,
+    },
+    {
+      id: OTHER_USER_ID,
+      name: 'Federation Other',
+      email: `${OTHER_USER_ID}@example.test`,
+      emailVerified: false,
+    },
+  ]);
+
+  await dbHandle.db.insert(teams).values([
+    {
+      id: TEAM_ID,
+      name: 'FED-M3-05 Team',
+      slug: 'fed-m3-05-team',
+      ownerId: SUBJECT_USER_ID,
+      managerId: SUBJECT_USER_ID,
+    },
+    {
+      id: UNAUTHORIZED_TEAM_ID,
+      name: 'FED-M3-05 Unauthorized Team',
+      slug: 'fed-m3-05-unauthorized-team',
+      ownerId: OTHER_USER_ID,
+      managerId: OTHER_USER_ID,
+    },
+  ]);
+
+  await dbHandle.db.insert(projects).values([
+    {
+      id: PERSONAL_PROJECT_ID,
+      name: 'FED-M3-05 Personal Project',
+      ownerId: SUBJECT_USER_ID,
+      ownerType: 'user',
+    },
+    {
+      id: TEAM_PROJECT_ID,
+      name: 'FED-M3-05 Team Project',
+      teamId: TEAM_ID,
+      ownerType: 'team',
+    },
+    {
+      id: UNAUTHORIZED_PROJECT_ID,
+      name: 'FED-M3-05 Unauthorized Project',
+      teamId: UNAUTHORIZED_TEAM_ID,
+      ownerType: 'team',
+    },
+  ]);
+
+  await dbHandle.db.insert(missions).values([
+    {
+      id: PERSONAL_MISSION_ID,
+      name: 'FED-M3-05 Personal Mission',
+      projectId: PERSONAL_PROJECT_ID,
+      userId: SUBJECT_USER_ID,
+    },
+    {
+      id: TEAM_MISSION_ID,
+      name: 'FED-M3-05 Team Mission',
+      projectId: TEAM_PROJECT_ID,
+      userId: SUBJECT_USER_ID,
+    },
+    {
+      id: UNAUTHORIZED_MISSION_ID,
+      name: 'FED-M3-05 Unauthorized Mission',
+      projectId: UNAUTHORIZED_PROJECT_ID,
+      userId: SUBJECT_USER_ID,
+    },
+  ]);
+
+  await dbHandle.db.insert(missionTasks).values([
+    {
+      id: SUBJECT_TEAM_NOTE_ID,
+      missionId: TEAM_MISSION_ID,
+      userId: SUBJECT_USER_ID,
+      notes: 'subject note on team mission',
+      createdAt: new Date('2026-06-24T03:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T03:00:00.000Z'),
+    },
+    {
+      id: OTHER_TEAM_NOTE_ID,
+      missionId: TEAM_MISSION_ID,
+      userId: OTHER_USER_ID,
+      notes: 'other user note on team mission',
+      createdAt: new Date('2026-06-24T02:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T02:00:00.000Z'),
+    },
+    {
+      id: SUBJECT_PERSONAL_NOTE_ID,
+      missionId: PERSONAL_MISSION_ID,
+      userId: SUBJECT_USER_ID,
+      notes: 'subject note on personal mission',
+      createdAt: new Date('2026-06-24T01:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T01:00:00.000Z'),
+    },
+    {
+      id: SUBJECT_UNAUTHORIZED_NOTE_ID,
+      missionId: UNAUTHORIZED_MISSION_ID,
+      userId: SUBJECT_USER_ID,
+      notes: 'subject note outside grant-visible missions',
+      createdAt: new Date('2026-06-24T04:00:00.000Z'),
+      updatedAt: new Date('2026-06-24T04:00:00.000Z'),
+    },
+  ]);
+
+  const memoryCreatedAt = new Date('2026-06-24T05:00:00.000Z');
+  await dbHandle.db.insert(insights).values([
+    {
+      id: INSIGHT_ONE_ID,
+      userId: SUBJECT_USER_ID,
+      content: 'first insight',
+      source: 'agent',
+      createdAt: memoryCreatedAt,
+      updatedAt: memoryCreatedAt,
+    },
+    {
+      id: INSIGHT_TWO_ID,
+      userId: SUBJECT_USER_ID,
+      content: 'second insight',
+      source: 'agent',
+      createdAt: memoryCreatedAt,
+      updatedAt: memoryCreatedAt,
+    },
+  ]);
+
+  await dbHandle.db.insert(preferences).values([
+    {
+      id: PREFERENCE_ONE_ID,
+      userId: SUBJECT_USER_ID,
+      key: 'fed-m3-05-pref-1',
+      value: { enabled: true },
+      createdAt: memoryCreatedAt,
+      updatedAt: memoryCreatedAt,
+    },
+    {
+      id: PREFERENCE_TWO_ID,
+      userId: SUBJECT_USER_ID,
+      key: 'fed-m3-05-pref-2',
+      value: { enabled: false },
+      createdAt: memoryCreatedAt,
+      updatedAt: memoryCreatedAt,
+    },
+  ]);
+}
+
+function stubRows(
+  service: FederationListQueryService,
+  ...pages: Array<Array<Record<string, unknown>>>
+) {
+  const mock = vi.fn();
+  for (const page of pages) {
+    mock.mockResolvedValueOnce(page);
+  }
+  (
+    service as unknown as {
+      listAllRows: (
+        _filter: FederationScopeQueryFilter,
+        _rowLimit: number,
+        _cursor: unknown,
+      ) => Promise<Array<Record<string, unknown>>>;
+    }
+  ).listAllRows = mock;
+  return mock;
+}
+
+describe('FederationListQueryService', () => {
+  beforeAll(async () => {
+    dbHandle = createPgliteDb(`memory://fed-m3-05-list-${Date.now()}`);
+    await runPgliteMigrations(dbHandle);
+    await seedNotesFixture();
+  });
+
+  afterAll(async () => {
+    await dbHandle?.close();
+    dbHandle = undefined;
+  });
+
+  it('denies sensitive resources in native RBAC for M3 list reads', async () => {
+    const service = makeService();
+
+    await expect(
+      service.evaluateReadAccess({
+        grantId: 'grant-1',
+        peerId: 'peer-1',
+        subjectUserId: 'user-1',
+        resource: 'credentials',
+      }),
+    ).resolves.toMatchObject({
+      allowed: false,
+      reason: 'credentials federation list access is not implemented in M3',
+    });
+  });
+
+  it('allows personal memory reads without requiring team lookup', async () => {
+    const service = makeService();
+
+    await expect(
+      service.evaluateReadAccess({
+        grantId: 'grant-1',
+        peerId: 'peer-1',
+        subjectUserId: 'user-1',
+        resource: 'memory',
+      }),
+    ).resolves.toEqual({
+      allowed: true,
+      access: { includePersonal: true, teamIds: [] },
+    });
+  });
+
+  it('applies the scope row cap and returns an opaque next cursor when truncated', async () => {
+    const service = makeService();
+    const listAllRows = stubRows(
+      service,
+      [
+        { id: '3', createdAt: new Date('2026-06-24T03:00:00.000Z') },
+        { id: '2', createdAt: new Date('2026-06-24T02:00:00.000Z') },
+        { id: '1', createdAt: new Date('2026-06-24T01:00:00.000Z') },
+      ],
+      [{ id: '1', createdAt: new Date('2026-06-24T01:00:00.000Z') }],
+    );
+
+    const firstPage = await service.list({ filter: TASK_FILTER });
+
+    expect(firstPage).toEqual({
+      items: [
+        { id: '3', createdAt: new Date('2026-06-24T03:00:00.000Z') },
+        { id: '2', createdAt: new Date('2026-06-24T02:00:00.000Z') },
+      ],
+      truncated: true,
+      nextCursor: expect.any(String),
+    });
+
+    expect(listAllRows).toHaveBeenNthCalledWith(1, TASK_FILTER, 3, undefined);
+
+    const secondPage = await service.list({ filter: TASK_FILTER, cursor: firstPage.nextCursor });
+    expect(secondPage).toEqual({
+      items: [{ id: '1', createdAt: new Date('2026-06-24T01:00:00.000Z') }],
+      truncated: false,
+    });
+    expect(listAllRows).toHaveBeenNthCalledWith(
+      2,
+      TASK_FILTER,
+      3,
+      expect.objectContaining({ id: '2' }),
+    );
+  });
+
+  it('rejects invalid cursors instead of falling back to the first page', async () => {
+    const service = makeService();
+    stubRows(service, [{ id: '1' }]);
+
+    await expect(service.list({ filter: TASK_FILTER, cursor: 'not-base64-json' })).rejects.toThrow(
+      'Invalid federation list cursor',
+    );
+  });
+
+  it('throws when a truncated page cannot encode a resumable cursor', async () => {
+    const service = makeService();
+    stubRows(service, [
+      { id: '2', createdAt: 'not-a-date' },
+      { id: '1', createdAt: 'not-a-date' },
+    ]);
+
+    await expect(service.list({ filter: { ...TASK_FILTER, limit: 1 } })).rejects.toThrow(
+      'Federation list cursor cannot be encoded',
+    );
+  });
+
+  it('throws on unsupported resources instead of crashing pagination', async () => {
+    const service = makeService();
+
+    await expect(
+      service.list({
+        filter: {
+          ...TASK_FILTER,
+          resource: 'unknown-resource' as FederationScopeQueryFilter['resource'],
+        },
+      }),
+    ).rejects.toThrow('Unsupported federation list resource');
+  });
+
+  it('does not leak another user mission task notes through team-scoped note reads', async () => {
+    const service = makeDbService();
+
+    const result = await service.list({
+      filter: {
+        resource: 'notes',
+        subjectUserId: SUBJECT_USER_ID,
+        includePersonal: false,
+        teamIds: [TEAM_ID],
+        limit: 10,
+        maxRowsPerQuery: 10,
+      },
+    });
+
+    const ids = result.items.map((item) => item['id']);
+    expect(ids).toEqual([SUBJECT_TEAM_NOTE_ID]);
+    expect(ids).not.toContain(OTHER_TEAM_NOTE_ID);
+  });
+
+  it('does not return subject personal mission task notes when includePersonal is false', async () => {
+    const service = makeDbService();
+
+    const result = await service.list({
+      filter: {
+        resource: 'notes',
+        subjectUserId: SUBJECT_USER_ID,
+        includePersonal: false,
+        teamIds: [TEAM_ID],
+        limit: 10,
+        maxRowsPerQuery: 10,
+      },
+    });
+
+    expect(result.items.map((item) => item['id'])).not.toContain(SUBJECT_PERSONAL_NOTE_ID);
+  });
+
+  it('does not return subject notes from missions outside the grant-visible project set', async () => {
+    const service = makeDbService();
+
+    const result = await service.list({
+      filter: {
+        resource: 'notes',
+        subjectUserId: SUBJECT_USER_ID,
+        includePersonal: true,
+        teamIds: [TEAM_ID],
+        limit: 10,
+        maxRowsPerQuery: 10,
+      },
+    });
+
+    const ids = result.items.map((item) => item['id']);
+    expect(ids).toContain(SUBJECT_PERSONAL_NOTE_ID);
+    expect(ids).toContain(SUBJECT_TEAM_NOTE_ID);
+    expect(ids).not.toContain(SUBJECT_UNAUTHORIZED_NOTE_ID);
+    expect(ids).not.toContain(OTHER_TEAM_NOTE_ID);
+  });
+
+  it('paginates memory deterministically across insights and preferences', async () => {
+    const service = makeDbService();
+    const filter: FederationScopeQueryFilter = {
+      resource: 'memory',
+      subjectUserId: SUBJECT_USER_ID,
+      includePersonal: true,
+      teamIds: [],
+      limit: 2,
+      maxRowsPerQuery: 2,
+    };
+
+    const firstPage = await service.list({ filter });
+    const secondPage = await service.list({ filter, cursor: firstPage.nextCursor });
+    const firstPageIds = firstPage.items.map((item) => item['id']);
+    const secondPageIds = secondPage.items.map((item) => item['id']);
+    const allIds = [...firstPageIds, ...secondPageIds];
+
+    expect(firstPage).toMatchObject({ truncated: true, nextCursor: expect.any(String) });
+    expect(firstPageIds).toEqual([INSIGHT_TWO_ID, INSIGHT_ONE_ID]);
+    expect(secondPageIds).toEqual([PREFERENCE_TWO_ID, PREFERENCE_ONE_ID]);
+    expect(new Set(allIds).size).toBe(allIds.length);
+  });
+});

apps/gateway/src/federation/server/verbs/__tests__/list.controller.spec.ts

@@ -0,0 +1,188 @@
+import 'reflect-metadata';
+import { RequestMethod } from '@nestjs/common';
+import type { FastifyRequest } from 'fastify';
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+import { FederationAuthGuard } from '../../federation-auth.guard.js';
+import type {
+  FederationScopeEvaluationResult,
+  FederationScopeQueryFilter,
+} from '../../scope.service.js';
+import { ListController } from '../list.controller.js';
+import type { FederationListQueryResult } from '../list-query.service.js';
+
+const FEDERATION_CONTEXT = {
+  grantId: 'grant-1',
+  peerId: 'peer-1',
+  subjectUserId: 'user-1',
+  scope: { resources: ['tasks'], max_rows_per_query: 25 },
+};
+
+const TASK_FILTER: FederationScopeQueryFilter = {
+  resource: 'tasks',
+  subjectUserId: 'user-1',
+  includePersonal: true,
+  teamIds: ['team-1'],
+  limit: 10,
+  maxRowsPerQuery: 25,
+};
+
+function makeRequest(): FastifyRequest {
+  return { federationContext: FEDERATION_CONTEXT } as unknown as FastifyRequest;
+}
+
+function allowedScope(
+  filter: FederationScopeQueryFilter = TASK_FILTER,
+): FederationScopeEvaluationResult {
+  return { allowed: true, filter };
+}
+
+function makeController(opts?: {
+  scopeResult?: FederationScopeEvaluationResult;
+  queryResult?: FederationListQueryResult;
+}) {
+  const scope = {
+    evaluateAccess: vi.fn().mockResolvedValue(opts?.scopeResult ?? allowedScope()),
+  };
+  const query = {
+    evaluateReadAccess: vi.fn(),
+    list: vi.fn().mockResolvedValue(
+      opts?.queryResult ?? {
+        items: [
+          {
+            id: 'task-1',
+            title: 'Federated task',
+            createdAt: new Date('2026-06-24T00:00:00.000Z'),
+          },
+        ],
+        truncated: false,
+      },
+    ),
+  };
+
+  return {
+    controller: new ListController(scope as never, query as never),
+    scope,
+    query,
+  };
+}
+
+describe('ListController', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it('declares POST /api/federation/v1/list/:resource protected only by FederationAuthGuard', () => {
+    expect(Reflect.getMetadata('path', ListController)).toBe('api/federation/v1/list');
+    expect(Reflect.getMetadata('path', ListController.prototype.list)).toBe(':resource');
+    expect(Reflect.getMetadata('method', ListController.prototype.list)).toBe(RequestMethod.POST);
+    expect(Reflect.getMetadata('__guards__', ListController)).toEqual([FederationAuthGuard]);
+  });
+
+  it('runs AuthGuard context through ScopeService and returns local-source tagged rows', async () => {
+    const { controller, scope, query } = makeController();
+
+    const response = await controller.list('tasks', makeRequest(), { limit: 10 });
+
+    expect(scope.evaluateAccess).toHaveBeenCalledWith({
+      context: FEDERATION_CONTEXT,
+      resource: 'tasks',
+      requestedLimit: 10,
+      nativeRbac: query,
+    });
+    expect(query.list).toHaveBeenCalledWith({ filter: TASK_FILTER, cursor: undefined });
+    expect(response).toEqual({
+      items: [
+        {
+          id: 'task-1',
+          title: 'Federated task',
+          createdAt: new Date('2026-06-24T00:00:00.000Z'),
+          _source: 'local',
+        },
+      ],
+    });
+  });
+
+  it('preserves pagination metadata when row cap truncates the query layer result', async () => {
+    const { controller } = makeController({
+      queryResult: {
+        items: [{ id: 'task-1' }],
+        nextCursor: 'cursor-2',
+        truncated: true,
+      },
+    });
+
+    const response = await controller.list('tasks', makeRequest(), { cursor: 'cursor-1' });
+
+    expect(response).toEqual({
+      items: [{ id: 'task-1', _source: 'local' }],
+      nextCursor: 'cursor-2',
+      _truncated: true,
+    });
+  });
+
+  it('returns a federation error envelope when auth guard context is missing', async () => {
+    const { controller, scope, query } = makeController();
+
+    await expect(
+      controller.list('tasks', {} as unknown as FastifyRequest, {}),
+    ).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'unauthorized',
+          message: 'Federation context missing',
+        },
+      },
+      status: 401,
+    });
+    expect(scope.evaluateAccess).not.toHaveBeenCalled();
+    expect(query.list).not.toHaveBeenCalled();
+  });
+
+  it('returns a federation error envelope when scope evaluation denies access', async () => {
+    const { controller, query } = makeController({
+      scopeResult: {
+        allowed: false,
+        deny: {
+          code: 'resource_excluded',
+          stage: 'resource_exclusion',
+          statusCode: 403,
+          message: 'Requested federation resource is explicitly excluded by grant scope',
+          grantId: 'grant-1',
+          peerId: 'peer-1',
+          subjectUserId: 'user-1',
+          resource: 'credentials',
+        },
+      },
+    });
+
+    await expect(controller.list('credentials', makeRequest(), {})).rejects.toMatchObject({
+      response: {
+        error: {
+          code: 'scope_violation',
+          message: 'Requested federation resource is explicitly excluded by grant scope',
+        },
+      },
+      status: 403,
+    });
+    expect(query.list).not.toHaveBeenCalled();
+  });
+
+  it('rejects malformed request body fields before querying storage', async () => {
+    const { controller, scope, query } = makeController();
+
+    await expect(controller.list('tasks', makeRequest(), { cursor: 123 })).rejects.toMatchObject({
+      response: { error: { code: 'invalid_request' } },
+      status: 400,
+    });
+    await expect(controller.list('tasks', makeRequest(), { limit: false })).rejects.toMatchObject({
+      response: { error: { code: 'invalid_request' } },
+      status: 400,
+    });
+    await expect(controller.list('tasks', makeRequest(), { limit: 'abc' })).rejects.toMatchObject({
+      response: { error: { code: 'invalid_request' } },
+      status: 400,
+    });
+    expect(scope.evaluateAccess).not.toHaveBeenCalled();
+    expect(query.list).not.toHaveBeenCalled();
+  });
+});

apps/gateway/src/federation/server/verbs/capabilities.controller.ts

@@ -0,0 +1,38 @@
+/**
+ * Federation capabilities verb (FED-M3-07).
+ *
+ * Returns the read-only capability envelope for the active grant attached by
+ * FederationAuthGuard. This endpoint intentionally does not invoke native RBAC
+ * or ScopeService: an active grant is enough to ask what the grant allows.
+ */
+
+import { Controller, Get, Req, UseGuards } from '@nestjs/common';
+import type { FastifyRequest } from 'fastify';
+import {
+  FEDERATION_VERBS,
+  type FederationCapabilitiesResponse,
+  type FederationVerb,
+} from '@mosaicstack/types';
+import { parseFederationScope } from '../../scope-schema.js';
+import { FederationAuthGuard } from '../federation-auth.guard.js';
+import '../federation-context.js';
+
+@Controller('api/federation/v1/capabilities')
+@UseGuards(FederationAuthGuard)
+export class CapabilitiesController {
+  @Get()
+  getCapabilities(@Req() request: FastifyRequest): FederationCapabilitiesResponse {
+    if (!request.federationContext) {
+      throw new Error('Federation context missing after auth guard');
+    }
+
+    const scope = parseFederationScope(request.federationContext.scope);
+
+    return {
+      resources: [...scope.resources],
+      excluded_resources: [...scope.excluded_resources],
+      max_rows_per_query: scope.max_rows_per_query,
+      supported_verbs: [...FEDERATION_VERBS] satisfies FederationVerb[],
+    };
+  }
+}

apps/gateway/src/federation/server/verbs/list-query.service.ts

@@ -0,0 +1,408 @@
+/**
+ * Federation list query layer (FED-M3-05).
+ *
+ * Read-only DB adapter used by ListController after FederationAuthGuard and
+ * FederationScopeService have established the subject user, allowed resource,
+ * native-RBAC intersection, and row cap. Audit writes are intentionally
+ * deferred to M4.
+ */
+
+import { Inject, Injectable } from '@nestjs/common';
+import {
+  and,
+  desc,
+  eq,
+  inArray,
+  insights,
+  isNotNull,
+  lt,
+  missionTasks,
+  missions,
+  or,
+  preferences,
+  projects,
+  tasks,
+  teamMembers,
+  type Db,
+} from '@mosaicstack/db';
+import type {
+  FederationNativeRbacEvaluator,
+  FederationNativeRbacRequest,
+  FederationNativeRbacResult,
+  FederationScopeQueryFilter,
+} from '../scope.service.js';
+import { DB } from '../../../database/database.module.js';
+
+export interface FederationListQueryRequest {
+  readonly filter: FederationScopeQueryFilter;
+  readonly cursor?: string;
+}
+
+export interface FederationListQueryResult<T extends object = Record<string, unknown>> {
+  readonly items: T[];
+  readonly nextCursor?: string;
+  readonly truncated: boolean;
+}
+
+type CursorSource = 'insights' | 'preferences';
+const CURSOR_SOURCE = Symbol('federationCursorSource');
+
+type RowObject = Record<string, unknown> & { readonly [CURSOR_SOURCE]?: CursorSource };
+
+interface KeysetCursor {
+  readonly createdAt: Date;
+  readonly id: string;
+  readonly source?: CursorSource;
+}
+
+function encodeCursor(row: RowObject): string {
+  const createdAt = row['createdAt'];
+  const id = row['id'];
+  if (!(createdAt instanceof Date) || typeof id !== 'string') {
+    throw new Error('Federation list cursor cannot be encoded');
+  }
+
+  const source = row[CURSOR_SOURCE];
+  return Buffer.from(
+    JSON.stringify({ createdAt: createdAt.toISOString(), id, ...(source ? { source } : {}) }),
+    'utf8',
+  ).toString('base64url');
+}
+
+function decodeCursor(cursor: string | undefined): KeysetCursor | undefined {
+  if (cursor === undefined) {
+    return undefined;
+  }
+
+  try {
+    const parsed = JSON.parse(Buffer.from(cursor, 'base64url').toString('utf8')) as unknown;
+    if (typeof parsed !== 'object' || parsed === null) {
+      throw new Error('cursor must be an object');
+    }
+
+    const { createdAt, id, source } = parsed as {
+      createdAt?: unknown;
+      id?: unknown;
+      source?: unknown;
+    };
+    if (typeof createdAt !== 'string' || typeof id !== 'string' || id.length === 0) {
+      throw new Error('cursor is missing createdAt or id');
+    }
+    if (source !== undefined && source !== 'insights' && source !== 'preferences') {
+      throw new Error('cursor source is invalid');
+    }
+
+    const date = new Date(createdAt);
+    if (Number.isNaN(date.getTime())) {
+      throw new Error('cursor createdAt is invalid');
+    }
+
+    return { createdAt: date, id, ...(source ? { source } : {}) };
+  } catch {
+    throw new Error('Invalid federation list cursor');
+  }
+}
+
+function paginate<T extends RowObject>(rows: T[], limit: number): FederationListQueryResult<T> {
+  const page = rows.slice(0, limit);
+  const hasMore = rows.length > limit;
+  const nextCursor = hasMore ? encodeCursor(page[page.length - 1] ?? {}) : undefined;
+
+  return {
+    items: page,
+    truncated: hasMore,
+    ...(nextCursor !== undefined ? { nextCursor } : {}),
+  };
+}
+
+function markCursorSource<T extends RowObject>(row: T, source: CursorSource): T {
+  Object.defineProperty(row, CURSOR_SOURCE, {
+    value: source,
+    enumerable: false,
+    configurable: false,
+  });
+  return row;
+}
+
+function sortRows(rows: RowObject[]): RowObject[] {
+  return [...rows].sort((a, b) => {
+    const aTime = a['createdAt'] instanceof Date ? a['createdAt'].getTime() : 0;
+    const bTime = b['createdAt'] instanceof Date ? b['createdAt'].getTime() : 0;
+    if (aTime !== bTime) {
+      return bTime - aTime;
+    }
+    return String(b['id'] ?? '').localeCompare(String(a['id'] ?? ''));
+  });
+}
+
+@Injectable()
+export class FederationListQueryService implements FederationNativeRbacEvaluator {
+  constructor(@Inject(DB) private readonly db: Db) {}
+
+  async evaluateReadAccess(
+    request: FederationNativeRbacRequest,
+  ): Promise<FederationNativeRbacResult> {
+    if (request.resource === 'credentials' || request.resource === 'api_keys') {
+      return {
+        allowed: false,
+        reason: `${request.resource} federation list access is not implemented in M3`,
+        details: { resource: request.resource },
+      };
+    }
+
+    if (request.resource === 'memory') {
+      return { allowed: true, access: { includePersonal: true, teamIds: [] } };
+    }
+
+    const teamIds = await this.listSubjectTeamIds(request.subjectUserId);
+    return { allowed: true, access: { includePersonal: true, teamIds } };
+  }
+
+  async list<T extends RowObject = RowObject>(
+    request: FederationListQueryRequest,
+  ): Promise<FederationListQueryResult<T>> {
+    const cursor = decodeCursor(request.cursor);
+    const rows = await this.listAllRows(request.filter, request.filter.limit + 1, cursor);
+    return paginate(rows as T[], request.filter.limit);
+  }
+
+  private async listAllRows(
+    filter: FederationScopeQueryFilter,
+    rowLimit: number,
+    cursor: KeysetCursor | undefined,
+  ): Promise<RowObject[]> {
+    switch (filter.resource) {
+      case 'tasks':
+        return this.listTasks(filter, rowLimit, cursor);
+      case 'notes':
+        return this.listNotes(filter, rowLimit, cursor);
+      case 'memory':
+        return this.listMemory(filter, rowLimit, cursor);
+      case 'credentials':
+      case 'api_keys':
+        return [];
+      default:
+        throw new Error(`Unsupported federation list resource: ${String(filter.resource)}`);
+    }
+  }
+
+  private async listSubjectTeamIds(subjectUserId: string): Promise<string[]> {
+    const rows = await this.db
+      .select({ teamId: teamMembers.teamId })
+      .from(teamMembers)
+      .where(eq(teamMembers.userId, subjectUserId));
+
+    return rows.map((row) => row.teamId);
+  }
+
+  private async listAccessibleProjectIds(filter: FederationScopeQueryFilter): Promise<string[]> {
+    const clauses = [];
+    if (filter.includePersonal) {
+      clauses.push(and(eq(projects.ownerType, 'user'), eq(projects.ownerId, filter.subjectUserId)));
+    }
+    if (filter.teamIds.length > 0) {
+      clauses.push(
+        and(eq(projects.ownerType, 'team'), inArray(projects.teamId, [...filter.teamIds])),
+      );
+    }
+
+    if (clauses.length === 0) {
+      return [];
+    }
+
+    const rows = await this.db
+      .select({ id: projects.id })
+      .from(projects)
+      .where(clauses.length === 1 ? clauses[0] : or(...clauses));
+
+    return rows.map((row) => row.id);
+  }
+
+  private async listMissionIds(projectIds: readonly string[]): Promise<string[]> {
+    if (projectIds.length === 0) {
+      return [];
+    }
+
+    const rows = await this.db
+      .select({ id: missions.id })
+      .from(missions)
+      .where(inArray(missions.projectId, [...projectIds]));
+
+    return rows.map((row) => row.id);
+  }
+
+  private async listTasks(
+    filter: FederationScopeQueryFilter,
+    rowLimit: number,
+    cursor: KeysetCursor | undefined,
+  ): Promise<RowObject[]> {
+    const projectIds = await this.listAccessibleProjectIds(filter);
+    const missionIds = await this.listMissionIds(projectIds);
+    const clauses = [];
+
+    if (projectIds.length > 0) {
+      clauses.push(inArray(tasks.projectId, projectIds));
+    }
+    if (missionIds.length > 0) {
+      clauses.push(inArray(tasks.missionId, missionIds));
+    }
+
+    if (clauses.length === 0) {
+      return [];
+    }
+
+    const scopeClause = clauses.length === 1 ? clauses[0] : or(...clauses);
+    const cursorClause = cursor
+      ? or(
+          lt(tasks.createdAt, cursor.createdAt),
+          and(eq(tasks.createdAt, cursor.createdAt), lt(tasks.id, cursor.id)),
+        )
+      : undefined;
+
+    const rows = await this.db
+      .select({
+        id: tasks.id,
+        title: tasks.title,
+        description: tasks.description,
+        status: tasks.status,
+        priority: tasks.priority,
+        projectId: tasks.projectId,
+        missionId: tasks.missionId,
+        assignee: tasks.assignee,
+        tags: tasks.tags,
+        dueDate: tasks.dueDate,
+        metadata: tasks.metadata,
+        createdAt: tasks.createdAt,
+        updatedAt: tasks.updatedAt,
+      })
+      .from(tasks)
+      .where(and(scopeClause, cursorClause))
+      .orderBy(desc(tasks.createdAt), desc(tasks.id))
+      .limit(rowLimit);
+
+    return sortRows(rows as RowObject[]);
+  }
+
+  private async listNotes(
+    filter: FederationScopeQueryFilter,
+    rowLimit: number,
+    cursor: KeysetCursor | undefined,
+  ): Promise<RowObject[]> {
+    const projectIds = await this.listAccessibleProjectIds(filter);
+    const missionIds = await this.listMissionIds(projectIds);
+
+    if (missionIds.length === 0) {
+      return [];
+    }
+
+    // mission_tasks rows are user-scoped even when the mission belongs to a team.
+    // Team visibility can narrow the mission set, but it must never widen the
+    // query to other users' mission task notes.
+    const scopeClause = and(
+      eq(missionTasks.userId, filter.subjectUserId),
+      inArray(missionTasks.missionId, missionIds),
+    );
+    const cursorClause = cursor
+      ? or(
+          lt(missionTasks.createdAt, cursor.createdAt),
+          and(eq(missionTasks.createdAt, cursor.createdAt), lt(missionTasks.id, cursor.id)),
+        )
+      : undefined;
+
+    const rows = await this.db
+      .select({
+        id: missionTasks.id,
+        missionId: missionTasks.missionId,
+        taskId: missionTasks.taskId,
+        status: missionTasks.status,
+        content: missionTasks.notes,
+        createdAt: missionTasks.createdAt,
+        updatedAt: missionTasks.updatedAt,
+      })
+      .from(missionTasks)
+      .where(and(scopeClause, cursorClause, isNotNull(missionTasks.notes)))
+      .orderBy(desc(missionTasks.createdAt), desc(missionTasks.id))
+      .limit(rowLimit);
+
+    return sortRows(rows.filter((row) => row.content !== '') as RowObject[]);
+  }
+
+  private async listMemory(
+    filter: FederationScopeQueryFilter,
+    rowLimit: number,
+    cursor: KeysetCursor | undefined,
+  ): Promise<RowObject[]> {
+    if (!filter.includePersonal) {
+      return [];
+    }
+    if (cursor && cursor.source === undefined) {
+      throw new Error('Invalid federation list cursor');
+    }
+
+    const rows: RowObject[] = [];
+
+    // Memory spans two physical tables. To keep pagination deterministic and
+    // resumable without a SQL UNION, M3 emits a fixed block order: all insights
+    // first, then preferences. The opaque cursor records which table produced
+    // the boundary row, so the next page never re-applies one table's keyset to
+    // the other table (which could duplicate/skip rows at equal timestamps).
+    if (cursor?.source !== 'preferences') {
+      const insightCursorClause = cursor
+        ? or(
+            lt(insights.createdAt, cursor.createdAt),
+            and(eq(insights.createdAt, cursor.createdAt), lt(insights.id, cursor.id)),
+          )
+        : undefined;
+      const insightRows = await this.db
+        .select({
+          id: insights.id,
+          kind: insights.source,
+          content: insights.content,
+          category: insights.category,
+          relevanceScore: insights.relevanceScore,
+          metadata: insights.metadata,
+          createdAt: insights.createdAt,
+          updatedAt: insights.updatedAt,
+        })
+        .from(insights)
+        .where(and(eq(insights.userId, filter.subjectUserId), insightCursorClause))
+        .orderBy(desc(insights.createdAt), desc(insights.id))
+        .limit(rowLimit);
+
+      rows.push(...(insightRows as RowObject[]).map((row) => markCursorSource(row, 'insights')));
+    }
+
+    const remaining = rowLimit - rows.length;
+    if (remaining <= 0) {
+      return rows;
+    }
+
+    const preferenceCursorClause =
+      cursor?.source === 'preferences'
+        ? or(
+            lt(preferences.createdAt, cursor.createdAt),
+            and(eq(preferences.createdAt, cursor.createdAt), lt(preferences.id, cursor.id)),
+          )
+        : undefined;
+    const preferenceRows = await this.db
+      .select({
+        id: preferences.id,
+        kind: preferences.category,
+        key: preferences.key,
+        value: preferences.value,
+        source: preferences.source,
+        mutable: preferences.mutable,
+        createdAt: preferences.createdAt,
+        updatedAt: preferences.updatedAt,
+      })
+      .from(preferences)
+      .where(and(eq(preferences.userId, filter.subjectUserId), preferenceCursorClause))
+      .orderBy(desc(preferences.createdAt), desc(preferences.id))
+      .limit(remaining);
+
+    rows.push(
+      ...(preferenceRows as RowObject[]).map((row) => markCursorSource(row, 'preferences')),
+    );
+    return rows;
+  }
+}

apps/gateway/src/federation/server/verbs/list.controller.ts

@@ -0,0 +1,147 @@
+/**
+ * Federation list verb (FED-M3-05).
+ *
+ * POST /api/federation/v1/list/:resource
+ *
+ * Pipeline: FederationAuthGuard attaches the active grant context, then
+ * FederationScopeService enforces grant scope + native RBAC intersection, then
+ * the read-only query layer returns capped rows tagged with `_source`. Read
+ * audit-log writes are deferred to M4; this controller does not persist request
+ * or response bodies.
+ */
+
+import {
+  Body,
+  Controller,
+  HttpException,
+  Inject,
+  Param,
+  Post,
+  Req,
+  UseGuards,
+} from '@nestjs/common';
+import type { FastifyRequest } from 'fastify';
+import {
+  FederationInvalidRequestError,
+  FederationScopeViolationError,
+  FederationUnauthorizedError,
+  SOURCE_LOCAL,
+  tagWithSource,
+  type FederationListResponse,
+  type SourceTag,
+} from '@mosaicstack/types';
+import { FederationAuthGuard } from '../federation-auth.guard.js';
+import '../federation-context.js';
+import { FederationScopeService } from '../scope.service.js';
+import { FederationListQueryService } from './list-query.service.js';
+
+interface FederationListRequestBody {
+  readonly limit?: unknown;
+  readonly cursor?: unknown;
+}
+
+type FederatedRow = Record<string, unknown> & SourceTag;
+
+function parseLimit(body: FederationListRequestBody | undefined): number | undefined {
+  if (body?.limit === undefined) {
+    return undefined;
+  }
+
+  const parsed =
+    typeof body.limit === 'number'
+      ? body.limit
+      : typeof body.limit === 'string' && body.limit.trim().length > 0
+        ? Number(body.limit)
+        : Number.NaN;
+
+  if (!Number.isSafeInteger(parsed) || parsed < 1) {
+    throw new HttpException(
+      new FederationInvalidRequestError(
+        'Federation list limit must be a positive integer',
+      ).toEnvelope(),
+      400,
+    );
+  }
+
+  return parsed;
+}
+
+function parseCursor(body: FederationListRequestBody | undefined): string | undefined {
+  if (body?.cursor === undefined) {
+    return undefined;
+  }
+  if (typeof body.cursor === 'string') {
+    return body.cursor;
+  }
+  throw new HttpException(
+    new FederationInvalidRequestError('Federation list cursor must be a string').toEnvelope(),
+    400,
+  );
+}
+
+@Controller('api/federation/v1/list')
+@UseGuards(FederationAuthGuard)
+export class ListController {
+  constructor(
+    @Inject(FederationScopeService) private readonly scope: FederationScopeService,
+    @Inject(FederationListQueryService) private readonly query: FederationListQueryService,
+  ) {}
+
+  @Post(':resource')
+  async list(
+    @Param('resource') resource: string,
+    @Req() request: FastifyRequest,
+    @Body() body?: FederationListRequestBody,
+  ): Promise<FederationListResponse<FederatedRow>> {
+    if (!request.federationContext) {
+      throw new HttpException(
+        new FederationUnauthorizedError('Federation context missing').toEnvelope(),
+        401,
+      );
+    }
+
+    const requestedLimit = parseLimit(body);
+    const cursor = parseCursor(body);
+    const scopeResult = await this.scope.evaluateAccess({
+      context: request.federationContext,
+      resource,
+      requestedLimit,
+      nativeRbac: this.query,
+    });
+
+    if (!scopeResult.allowed) {
+      const ErrorClass =
+        scopeResult.deny.statusCode === 400
+          ? FederationInvalidRequestError
+          : FederationScopeViolationError;
+      throw new HttpException(
+        new ErrorClass(scopeResult.deny.message, scopeResult.deny).toEnvelope(),
+        scopeResult.deny.statusCode,
+      );
+    }
+
+    let result: Awaited<ReturnType<FederationListQueryService['list']>>;
+    try {
+      result = await this.query.list({ filter: scopeResult.filter, cursor });
+    } catch (error: unknown) {
+      if (error instanceof Error && error.message === 'Invalid federation list cursor') {
+        throw new HttpException(
+          new FederationInvalidRequestError('Federation list cursor is invalid').toEnvelope(),
+          400,
+        );
+      }
+      throw error;
+    }
+
+    const response: FederationListResponse<FederatedRow> = {
+      items: tagWithSource(result.items, SOURCE_LOCAL),
+    };
+    if (result.nextCursor !== undefined) {
+      response.nextCursor = result.nextCursor;
+    }
+    if (result.truncated) {
+      response._truncated = true;
+    }
+    return response;
+  }
+}

apps/gateway/src/mcp/mcp.controller.ts

@@ -3,7 +3,11 @@ import { Logger } from '@nestjs/common';
 import { fromNodeHeaders } from 'better-auth/node';
 import type { Auth } from '@mosaicstack/auth';
 import type { NestFastifyApplication } from '@nestjs/platform-fastify';
-import type { McpService } from './mcp.service.js';
+import {
+  createMcpActorContext,
+  deriveMcpToolScopesForUser,
+  type McpService,
+} from './mcp.service.js';
 import { AUTH } from '../auth/auth.tokens.js';
 
 /**
@@ -67,14 +71,25 @@ async function handleMcpRequest(
     return;
   }
 
-  const userId = result.user.id;
+  const authUser = result.user as {
+    id: string;
+    role?: string | null;
+    tenantId?: string | null;
+    organizationId?: string | null;
+  };
+  const actor = createMcpActorContext({
+    userId: authUser.id,
+    role: authUser.role,
+    tenantId: authUser.tenantId ?? authUser.organizationId ?? undefined,
+    scopes: deriveMcpToolScopesForUser({ role: authUser.role }),
+  });
 
   // ─── Session routing ─────────────────────────────────────────────────────
   const sessionId = req.raw.headers['mcp-session-id'];
 
   if (typeof sessionId === 'string' && sessionId.length > 0) {
     // Existing session request
-    const transport = mcpService.getSession(sessionId);
+    const transport = mcpService.getSession(sessionId, actor);
     if (!transport) {
       logger.warn(`MCP session not found: ${sessionId}`);
       reply.raw.writeHead(404, { 'Content-Type': 'application/json' });
@@ -112,8 +127,10 @@ async function handleMcpRequest(
   }
 
   // Create new session and handle this initializing request
-  const { transport } = mcpService.createSession(userId);
+  const { transport } = mcpService.createSession(actor);
-  logger.log(`New MCP session created for user ${userId}`);
+  logger.log(
+    `New MCP session created for actor=${actor.userId} tenant=${actor.tenantId} correlation=${actor.correlationId}`,
+  );
 
   await transport.handleRequest(req.raw, reply.raw, body);
 }

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

@@ -0,0 +1,461 @@
+import { describe, expect, it, vi } from 'vitest';
+import type { z } from 'zod';
+import type { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
+import type { Brain } from '@mosaicstack/brain';
+import type { Memory } from '@mosaicstack/memory';
+import type { EmbeddingService } from '../memory/embedding.service.js';
+import type { CoordService } from '../coord/coord.service.js';
+import {
+  assertMcpToolAuthorized,
+  createMcpActorContext,
+  deriveMcpToolScopesForUser,
+  MCP_TOOL_SCOPES,
+  McpService,
+  type McpToolName,
+} from './mcp.service.js';
+
+type ToolResult = { content: Array<{ type: 'text'; text: string }> };
+type ToolHandler = (params: Record<string, unknown>) => Promise<ToolResult>;
+
+interface CapturedTool {
+  inputSchema: z.ZodType;
+  handler: ToolHandler;
+}
+
+function makeCapturingServer(): { server: McpServer; tools: Map<string, CapturedTool> } {
+  const tools = new Map<string, CapturedTool>();
+  const server = {
+    registerTool(name: string, config: { inputSchema: z.ZodType }, handler: ToolHandler): void {
+      tools.set(name, { inputSchema: config.inputSchema, handler });
+    },
+  };
+  return { server: server as unknown as McpServer, tools };
+}
+
+function makeService(opts?: {
+  projects?: Array<Record<string, unknown> & { id: string; ownerId?: string | null }>;
+  missions?: Array<
+    Record<string, unknown> & { id: string; projectId?: string | null; userId?: string | null }
+  >;
+  tasks?: Array<
+    Record<string, unknown> & {
+      id: string;
+      projectId?: string | null;
+      missionId?: string | null;
+      status?: string;
+    }
+  >;
+}) {
+  const projects = opts?.projects ?? [];
+  const missions = opts?.missions ?? [];
+  const tasks = opts?.tasks ?? [];
+  const brain = {
+    projects: {
+      findAll: vi.fn(async () => projects),
+      findById: vi.fn(async (id: string) => projects.find((project) => project.id === id) ?? null),
+    },
+    tasks: {
+      findAll: vi.fn(async () => tasks),
+      findById: vi.fn(async (id: string) => tasks.find((task) => task.id === id) ?? null),
+      findByProject: vi.fn(async (projectId: string) =>
+        tasks.filter((task) => task.projectId === projectId),
+      ),
+      findByMission: vi.fn(async (missionId: string) =>
+        tasks.filter((task) => task.missionId === missionId),
+      ),
+      findByStatus: vi.fn(async (status: string) => tasks.filter((task) => task.status === status)),
+      create: vi.fn(async (task: Record<string, unknown>) => ({ id: 'task-1', ...task })),
+      update: vi.fn(async (id: string, updates: Record<string, unknown>) => ({ id, ...updates })),
+    },
+    missions: {
+      findAll: vi.fn(async () => missions),
+      findById: vi.fn(async (id: string) => missions.find((mission) => mission.id === id) ?? null),
+      findByProject: vi.fn(async (projectId: string) =>
+        missions.filter((mission) => mission.projectId === projectId),
+      ),
+    },
+    conversations: {
+      findAll: vi.fn(async (userId: string) => [{ id: 'conversation-1', userId }]),
+    },
+  } as unknown as Brain;
+
+  const memory = {
+    insights: {
+      searchByEmbedding: vi.fn(async (userId: string) => [{ id: 'insight-1', userId }]),
+      create: vi.fn(async (insight: Record<string, unknown>) => ({ id: 'insight-2', ...insight })),
+    },
+    preferences: {
+      findByUser: vi.fn(async (userId: string) => [{ key: 'theme', userId }]),
+      findByUserAndCategory: vi.fn(async (userId: string, category: string) => [
+        { key: 'theme', userId, category },
+      ]),
+      upsert: vi.fn(async (preference: Record<string, unknown>) => ({
+        id: 'pref-1',
+        ...preference,
+      })),
+    },
+  } as unknown as Memory;
+
+  const embeddings = {
+    available: true,
+    embed: vi.fn(async () => [0.1, 0.2, 0.3]),
+  } as unknown as EmbeddingService;
+
+  const coord = {
+    getMissionStatus: vi.fn(async () => null),
+    listTasks: vi.fn(async () => []),
+    getTaskStatus: vi.fn(async () => null),
+  } as unknown as CoordService;
+
+  return {
+    service: new McpService(brain, memory, embeddings, coord),
+    brain: brain as unknown as {
+      conversations: { findAll: ReturnType<typeof vi.fn> };
+      tasks: {
+        create: ReturnType<typeof vi.fn>;
+        update: ReturnType<typeof vi.fn>;
+      };
+    },
+    memory: memory as unknown as {
+      insights: { searchByEmbedding: ReturnType<typeof vi.fn> };
+    },
+    coord: coord as unknown as {
+      listTasks: ReturnType<typeof vi.fn>;
+    },
+  };
+}
+
+function getTool(tools: Map<string, CapturedTool>, name: McpToolName): CapturedTool {
+  const tool = tools.get(name);
+  if (!tool) throw new Error(`Missing captured tool ${name}`);
+  return tool;
+}
+
+function makeMemberActor(userId = 'authenticated-user') {
+  return createMcpActorContext({
+    userId,
+    role: 'member',
+    scopes: deriveMcpToolScopesForUser({ role: 'member' }),
+  });
+}
+
+function makeAdminActor(userId = 'admin-user', tenantId?: string) {
+  return createMcpActorContext({
+    userId,
+    tenantId,
+    role: 'admin',
+    scopes: deriveMcpToolScopesForUser({ role: 'admin' }),
+  });
+}
+
+function makePlatformAdminActor(userId = 'platform-admin-user') {
+  return createMcpActorContext({
+    userId,
+    role: 'platform-admin',
+    scopes: deriveMcpToolScopesForUser({ role: 'platform-admin' }),
+  });
+}
+
+describe('MCP actor identity and tool scope enforcement', () => {
+  it('derives immutable actor, tenant, channel, correlation, and explicit tool scopes server-side', () => {
+    const actor = createMcpActorContext({
+      userId: ' user-authenticated ',
+      role: 'member',
+      scopes: deriveMcpToolScopesForUser({ role: 'member' }),
+    });
+
+    expect(actor.userId).toBe('user-authenticated');
+    expect(actor.tenantId).toBe('user:user-authenticated');
+    expect(actor.role).toBe('member');
+    expect(actor.channel).toBe('mcp');
+    expect(actor.correlationId).toMatch(/[0-9a-f-]{36}/i);
+    expect(actor.scopes.has(MCP_TOOL_SCOPES.memory_search)).toBe(true);
+    expect(actor.scopes.has(MCP_TOOL_SCOPES.coord_list_tasks)).toBe(false);
+    expect(
+      deriveMcpToolScopesForUser({ role: 'admin' }).has(MCP_TOOL_SCOPES.coord_list_tasks),
+    ).toBe(false);
+    expect(
+      deriveMcpToolScopesForUser({ role: 'platform-admin' }).has(MCP_TOOL_SCOPES.coord_list_tasks),
+    ).toBe(true);
+  });
+
+  it('fails closed when scopes are not supplied by the authenticated context policy', () => {
+    const actor = createMcpActorContext({ userId: 'user-authenticated' });
+
+    expect(actor.scopes.size).toBe(0);
+    expect(() => assertMcpToolAuthorized(actor, 'memory_search', { query: 'notes' })).toThrow(
+      'MCP tool scope denied: memory:insight:read',
+    );
+  });
+
+  it('fails closed when a tool caller supplies actor or tenant identity fields', () => {
+    const actor = createMcpActorContext({ userId: 'user-authenticated' });
+
+    expect(() =>
+      assertMcpToolAuthorized(actor, 'memory_search', {
+        userId: 'victim-user',
+        query: 'private data',
+      }),
+    ).toThrow('MCP caller-controlled identity field is forbidden: userId');
+
+    expect(() =>
+      assertMcpToolAuthorized(actor, 'coord_list_tasks', {
+        tenantId: 'victim-tenant',
+        projectPath: '/tmp/project',
+      }),
+    ).toThrow('MCP caller-controlled identity field is forbidden: tenantId');
+
+    expect(() =>
+      assertMcpToolAuthorized(actor, 'brain_create_task', {
+        title: 'forged org',
+        organizationId: 'victim-org',
+      }),
+    ).toThrow('MCP caller-controlled identity field is forbidden: organizationId');
+
+    expect(() =>
+      assertMcpToolAuthorized(actor, 'brain_update_task', {
+        title: 'forged team',
+        teamId: 'victim-team',
+      }),
+    ).toThrow('MCP caller-controlled identity field is forbidden: teamId');
+  });
+
+  it('fails closed when the server-derived actor lacks the required per-tool scope', () => {
+    const actor = createMcpActorContext({ userId: 'user-authenticated', scopes: [] });
+
+    expect(() => assertMcpToolAuthorized(actor, 'memory_search', { query: 'notes' })).toThrow(
+      'MCP tool scope denied: memory:insight:read',
+    );
+  });
+
+  it('removes caller-controlled userId from memory schemas and never queries victim memory', async () => {
+    const { service, memory } = makeService();
+    const { server, tools } = makeCapturingServer();
+    const actor = makeMemberActor('authenticated-user');
+
+    service.registerTools(server, actor);
+    const tool = getTool(tools, 'memory_search');
+
+    expect(tool.inputSchema.safeParse({ userId: 'victim-user', query: 'anything' }).success).toBe(
+      false,
+    );
+    await expect(tool.handler({ userId: 'victim-user', query: 'anything' })).rejects.toThrow(
+      'MCP caller-controlled identity field is forbidden: userId',
+    );
+    expect(memory.insights.searchByEmbedding).not.toHaveBeenCalled();
+
+    await tool.handler({ query: 'only my notes' });
+    expect(memory.insights.searchByEmbedding).toHaveBeenCalledWith(
+      'authenticated-user',
+      [0.1, 0.2, 0.3],
+      5,
+    );
+  });
+
+  it('binds conversation listing to the authenticated actor instead of a caller-supplied userId', async () => {
+    const { service, brain } = makeService();
+    const { server, tools } = makeCapturingServer();
+    const actor = makeMemberActor('authenticated-user');
+
+    service.registerTools(server, actor);
+    const tool = getTool(tools, 'brain_list_conversations');
+
+    expect(tool.inputSchema.safeParse({ userId: 'victim-user' }).success).toBe(false);
+    await expect(tool.handler({ userId: 'victim-user' })).rejects.toThrow(
+      'MCP caller-controlled identity field is forbidden: userId',
+    );
+    expect(brain.conversations.findAll).not.toHaveBeenCalled();
+
+    await tool.handler({});
+    expect(brain.conversations.findAll).toHaveBeenCalledWith('authenticated-user');
+  });
+
+  it('scopes brain project, mission, and task reads to the authenticated actor', async () => {
+    const { service } = makeService({
+      projects: [
+        { id: 'project-owned', ownerId: 'authenticated-user', name: 'owned' },
+        { id: 'project-victim', ownerId: 'victim-user', name: 'victim' },
+      ],
+      missions: [
+        { id: 'mission-owned', projectId: 'project-owned' },
+        { id: 'mission-victim', userId: 'victim-user', projectId: 'project-victim' },
+      ],
+      tasks: [
+        { id: 'task-owned-project', projectId: 'project-owned', status: 'not-started' },
+        { id: 'task-owned-mission', missionId: 'mission-owned', status: 'not-started' },
+        { id: 'task-victim-project', projectId: 'project-victim', status: 'not-started' },
+        { id: 'task-unowned', status: 'not-started' },
+      ],
+    });
+    const { server, tools } = makeCapturingServer();
+    const actor = makeMemberActor('authenticated-user');
+
+    service.registerTools(server, actor);
+
+    const projects = JSON.parse(
+      (await getTool(tools, 'brain_list_projects').handler({})).content[0]!.text,
+    );
+    expect(projects.map((project: { id: string }) => project.id)).toEqual(['project-owned']);
+
+    const missions = JSON.parse(
+      (await getTool(tools, 'brain_list_missions').handler({})).content[0]!.text,
+    );
+    expect(missions.map((mission: { id: string }) => mission.id)).toEqual(['mission-owned']);
+
+    const tasks = JSON.parse(
+      (await getTool(tools, 'brain_list_tasks').handler({})).content[0]!.text,
+    );
+    expect(tasks.map((task: { id: string }) => task.id)).toEqual([
+      'task-owned-project',
+      'task-owned-mission',
+    ]);
+  });
+
+  it('enforces tenant boundaries for tenant-admin brain project, mission, and task reads', async () => {
+    const { service } = makeService({
+      projects: [
+        {
+          id: 'project-tenant-a',
+          ownerId: 'other-user-a',
+          teamId: 'tenant-a',
+          name: 'same tenant',
+        },
+        {
+          id: 'project-tenant-b',
+          ownerId: 'other-user-b',
+          teamId: 'tenant-b',
+          name: 'other tenant',
+        },
+      ],
+      missions: [
+        { id: 'mission-tenant-a', tenantId: 'tenant-a', projectId: 'project-tenant-a' },
+        { id: 'mission-tenant-b', tenantId: 'tenant-b', projectId: 'project-tenant-b' },
+      ],
+      tasks: [
+        { id: 'task-tenant-a', projectId: 'project-tenant-a', status: 'not-started' },
+        { id: 'task-tenant-b', projectId: 'project-tenant-b', status: 'not-started' },
+      ],
+    });
+    const { server, tools } = makeCapturingServer();
+    const actor = makeAdminActor('tenant-admin-user', 'tenant-a');
+
+    service.registerTools(server, actor);
+
+    const projects = JSON.parse(
+      (await getTool(tools, 'brain_list_projects').handler({})).content[0]!.text,
+    );
+    expect(projects.map((project: { id: string }) => project.id)).toEqual(['project-tenant-a']);
+
+    const missions = JSON.parse(
+      (await getTool(tools, 'brain_list_missions').handler({})).content[0]!.text,
+    );
+    expect(missions.map((mission: { id: string }) => mission.id)).toEqual(['mission-tenant-a']);
+
+    const tasks = JSON.parse(
+      (await getTool(tools, 'brain_list_tasks').handler({})).content[0]!.text,
+    );
+    expect(tasks.map((task: { id: string }) => task.id)).toEqual(['task-tenant-a']);
+  });
+
+  it('denies tenant-admin task writes outside the authenticated tenant', async () => {
+    const { service, brain } = makeService({
+      projects: [
+        { id: 'project-tenant-a', ownerId: 'other-user-a', teamId: 'tenant-a' },
+        { id: 'project-tenant-b', ownerId: 'other-user-b', teamId: 'tenant-b' },
+      ],
+      missions: [
+        { id: 'mission-tenant-a', tenantId: 'tenant-a', projectId: 'project-tenant-a' },
+        { id: 'mission-tenant-b', tenantId: 'tenant-b', projectId: 'project-tenant-b' },
+      ],
+      tasks: [
+        { id: 'task-tenant-a', projectId: 'project-tenant-a', status: 'not-started' },
+        { id: 'task-tenant-b', projectId: 'project-tenant-b', status: 'not-started' },
+      ],
+    });
+    const { server, tools } = makeCapturingServer();
+    const actor = makeAdminActor('tenant-admin-user', 'tenant-a');
+
+    service.registerTools(server, actor);
+
+    await expect(
+      getTool(tools, 'brain_create_task').handler({
+        title: 'unscoped tenant write',
+      }),
+    ).rejects.toThrow('MCP task scope denied');
+    expect(brain.tasks.create).not.toHaveBeenCalled();
+
+    await expect(
+      getTool(tools, 'brain_create_task').handler({
+        title: 'cross-tenant write',
+        projectId: 'project-tenant-b',
+      }),
+    ).rejects.toThrow('MCP task project scope denied');
+    expect(brain.tasks.create).not.toHaveBeenCalled();
+
+    await expect(
+      getTool(tools, 'brain_update_task').handler({
+        id: 'task-tenant-a',
+        projectId: 'project-tenant-b',
+      }),
+    ).rejects.toThrow('MCP task project scope denied');
+    expect(brain.tasks.update).not.toHaveBeenCalled();
+
+    const updateResult = await getTool(tools, 'brain_update_task').handler({
+      id: 'task-tenant-b',
+      title: 'cross-tenant update',
+    });
+    expect(updateResult.content[0]!.text).toBe('Task not found: task-tenant-b');
+    expect(brain.tasks.update).not.toHaveBeenCalled();
+
+    await getTool(tools, 'brain_create_task').handler({
+      title: 'same-tenant write',
+      projectId: 'project-tenant-a',
+    });
+    expect(brain.tasks.create).toHaveBeenCalledWith(
+      expect.objectContaining({ projectId: 'project-tenant-a', title: 'same-tenant write' }),
+    );
+  });
+
+  it('keeps admin-only coordination tools on server-derived paths', async () => {
+    const { service, coord } = makeService();
+    const { server, tools } = makeCapturingServer();
+    const member = makeMemberActor('authenticated-user');
+    const tenantAdmin = makeAdminActor('admin-user');
+    const platformAdmin = makePlatformAdminActor('platform-admin-user');
+
+    service.registerTools(server, member);
+    const memberTool = getTool(tools, 'coord_list_tasks');
+    expect(memberTool.inputSchema.safeParse({ projectPath: '/tmp/victim' }).success).toBe(false);
+    await expect(memberTool.handler({})).rejects.toThrow('MCP tool scope denied: coord:read');
+
+    tools.clear();
+    service.registerTools(server, tenantAdmin);
+    const tenantAdminTool = getTool(tools, 'coord_list_tasks');
+    await expect(tenantAdminTool.handler({})).rejects.toThrow('MCP tool scope denied: coord:read');
+
+    tools.clear();
+    service.registerTools(server, platformAdmin);
+    const platformAdminTool = getTool(tools, 'coord_list_tasks');
+    await platformAdminTool.handler({ projectPath: '/tmp/victim' });
+    expect(coord.listTasks).toHaveBeenCalledWith(process.cwd());
+  });
+
+  it('does not attach a guessed or stale-scope MCP session to another authenticated context', async () => {
+    const { service } = makeService();
+    const owner = makeMemberActor('owner-user');
+    const attacker = makeMemberActor('attacker-user');
+    const admin = makeAdminActor('admin-user');
+    const downgradedAdmin = makeMemberActor('admin-user');
+
+    const { sessionId, transport } = service.createSession(owner);
+    const staleSession = service.createSession(admin);
+
+    expect(service.getSession(sessionId, owner)).toBe(transport);
+    expect(service.getSession(sessionId, attacker)).toBeNull();
+    expect(service.getSession(sessionId, owner)).toBe(transport);
+    expect(service.getSession(staleSession.sessionId, downgradedAdmin)).toBeNull();
+    expect(service.getSession(staleSession.sessionId, admin)).toBe(staleSession.transport);
+
+    await service.onModuleDestroy();
+  });
+});

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

@@ -10,11 +10,216 @@ import { MEMORY } from '../memory/memory.tokens.js';
 import { EmbeddingService } from '../memory/embedding.service.js';
 import { CoordService } from '../coord/coord.service.js';
 
+export const MCP_CALLER_IDENTITY_FIELDS = [
+  'actorId',
+  'actor',
+  'authenticatedUserId',
+  'channel',
+  'organizationId',
+  'ownerId',
+  'sessionUserId',
+  'teamId',
+  'tenant',
+  'tenantId',
+  'user',
+  'userId',
+] as const;
+
+type McpCallerIdentityField = (typeof MCP_CALLER_IDENTITY_FIELDS)[number];
+
+export const MCP_TOOL_SCOPES = {
+  brain_list_projects: 'brain:project:read',
+  brain_get_project: 'brain:project:read',
+  brain_list_tasks: 'brain:task:read',
+  brain_create_task: 'brain:task:write',
+  brain_update_task: 'brain:task:write',
+  brain_list_missions: 'brain:mission:read',
+  brain_list_conversations: 'brain:conversation:read',
+  memory_search: 'memory:insight:read',
+  memory_get_preferences: 'memory:preference:read',
+  memory_save_preference: 'memory:preference:write',
+  memory_save_insight: 'memory:insight:write',
+  coord_mission_status: 'coord:read',
+  coord_list_tasks: 'coord:read',
+  coord_task_detail: 'coord:read',
+} as const;
+
+export type McpToolName = keyof typeof MCP_TOOL_SCOPES;
+export type McpToolScope = (typeof MCP_TOOL_SCOPES)[McpToolName];
+
+export interface McpActorContext {
+  userId: string;
+  tenantId: string;
+  role: string;
+  channel: 'mcp';
+  correlationId: string;
+  scopes: ReadonlySet<McpToolScope>;
+}
+
 interface SessionEntry {
   server: McpServer;
   transport: StreamableHTTPServerTransport;
   createdAt: Date;
+  actor: McpActorContext;
+}
+
+const GLOBAL_ADMIN_MCP_SCOPES = new Set<McpToolScope>(Object.values(MCP_TOOL_SCOPES));
+const TENANT_ADMIN_MCP_SCOPES = new Set<McpToolScope>([
+  MCP_TOOL_SCOPES.brain_list_projects,
+  MCP_TOOL_SCOPES.brain_get_project,
+  MCP_TOOL_SCOPES.brain_list_tasks,
+  MCP_TOOL_SCOPES.brain_create_task,
+  MCP_TOOL_SCOPES.brain_update_task,
+  MCP_TOOL_SCOPES.brain_list_missions,
+  MCP_TOOL_SCOPES.brain_list_conversations,
+  MCP_TOOL_SCOPES.memory_search,
+  MCP_TOOL_SCOPES.memory_get_preferences,
+  MCP_TOOL_SCOPES.memory_save_preference,
+  MCP_TOOL_SCOPES.memory_save_insight,
+]);
+const MEMBER_MCP_SCOPES = new Set<McpToolScope>([
+  MCP_TOOL_SCOPES.brain_list_projects,
+  MCP_TOOL_SCOPES.brain_get_project,
+  MCP_TOOL_SCOPES.brain_list_tasks,
+  MCP_TOOL_SCOPES.brain_list_missions,
+  MCP_TOOL_SCOPES.brain_list_conversations,
+  MCP_TOOL_SCOPES.memory_search,
+  MCP_TOOL_SCOPES.memory_get_preferences,
+  MCP_TOOL_SCOPES.memory_save_preference,
+  MCP_TOOL_SCOPES.memory_save_insight,
+]);
+
+export function deriveMcpToolScopesForUser(input: {
+  role?: string | null;
+}): ReadonlySet<McpToolScope> {
+  if (input.role === 'platform-admin' || input.role === 'super-admin') {
+    return new Set(GLOBAL_ADMIN_MCP_SCOPES);
+  }
+  if (input.role === 'admin') {
+    return new Set(TENANT_ADMIN_MCP_SCOPES);
+  }
+  return new Set(MEMBER_MCP_SCOPES);
+}
+
+export function createMcpActorContext(input: {
   userId: string;
+  tenantId?: string;
+  role?: string | null;
+  scopes?: Iterable<McpToolScope>;
+  correlationId?: string;
+}): McpActorContext {
+  const userId = input.userId.trim();
+  if (userId.length === 0) {
+    throw new Error('MCP authenticated user is required');
+  }
+
+  return {
+    userId,
+    tenantId: input.tenantId?.trim() || `user:${userId}`,
+    role: input.role ?? 'member',
+    channel: 'mcp',
+    correlationId: input.correlationId ?? randomUUID(),
+    scopes: new Set(input.scopes ?? []),
+  };
+}
+
+export function assertNoCallerControlledIdentity(params: unknown): void {
+  if (params === null || typeof params !== 'object') return;
+
+  const keys = new Set(Object.keys(params));
+  const forbidden = MCP_CALLER_IDENTITY_FIELDS.find((field: McpCallerIdentityField) =>
+    keys.has(field),
+  );
+  if (forbidden) {
+    throw new Error(`MCP caller-controlled identity field is forbidden: ${forbidden}`);
+  }
+}
+
+export function assertMcpToolAuthorized(
+  actor: McpActorContext,
+  toolName: McpToolName,
+  params: unknown,
+): void {
+  assertNoCallerControlledIdentity(params);
+  const requiredScope = MCP_TOOL_SCOPES[toolName];
+  if (!actor.scopes.has(requiredScope)) {
+    throw new Error(`MCP tool scope denied: ${requiredScope}`);
+  }
+}
+
+function strictObject<T extends z.ZodRawShape>(shape: T): z.ZodObject<T> {
+  return z.object(shape).strict();
+}
+
+type TenantScopedLike = {
+  tenantId?: string | null;
+  organizationId?: string | null;
+  teamId?: string | null;
+};
+type ProjectLike = TenantScopedLike & { id: string; ownerId?: string | null };
+type MissionLike = TenantScopedLike & {
+  id: string;
+  projectId?: string | null;
+  userId?: string | null;
+};
+type TaskLike = TenantScopedLike & {
+  projectId?: string | null;
+  missionId?: string | null;
+  userId?: string | null;
+};
+
+function isGlobalAdminActor(actor: McpActorContext): boolean {
+  return actor.role === 'platform-admin' || actor.role === 'super-admin';
+}
+
+function isTenantAdminActor(actor: McpActorContext): boolean {
+  return actor.role === 'admin';
+}
+
+function matchesTenant(actor: McpActorContext, record: TenantScopedLike): boolean {
+  return (
+    record.tenantId === actor.tenantId ||
+    record.organizationId === actor.tenantId ||
+    record.teamId === actor.tenantId
+  );
+}
+
+function filterProjectsForActor<T extends ProjectLike>(actor: McpActorContext, projects: T[]): T[] {
+  if (isGlobalAdminActor(actor)) return projects;
+  return projects.filter(
+    (project) =>
+      project.ownerId === actor.userId ||
+      (isTenantAdminActor(actor) && matchesTenant(actor, project)),
+  );
+}
+
+function filterMissionsByDirectActorScope<T extends MissionLike>(
+  actor: McpActorContext,
+  missions: T[],
+): T[] {
+  if (isGlobalAdminActor(actor)) return missions;
+  return missions.filter(
+    (mission) =>
+      mission.userId === actor.userId ||
+      (isTenantAdminActor(actor) && matchesTenant(actor, mission)),
+  );
+}
+
+function scopesEqual(left: ReadonlySet<McpToolScope>, right: ReadonlySet<McpToolScope>): boolean {
+  if (left.size !== right.size) return false;
+  for (const scope of left) {
+    if (!right.has(scope)) return false;
+  }
+  return true;
+}
+
+function sameActorAuthorization(stored: McpActorContext, current: McpActorContext): boolean {
+  return (
+    stored.userId === current.userId &&
+    stored.tenantId === current.tenantId &&
+    stored.role === current.role &&
+    scopesEqual(stored.scopes, current.scopes)
+  );
 }
 
 @Injectable()
@@ -33,13 +238,18 @@ export class McpService implements OnModuleDestroy {
    * Creates a new MCP session with its own server + transport pair.
    * Returns the transport for use by the controller.
    */
-  createSession(userId: string): { sessionId: string; transport: StreamableHTTPServerTransport } {
+  createSession(actor: McpActorContext): {
+    sessionId: string;
+    transport: StreamableHTTPServerTransport;
+  } {
     const sessionId = randomUUID();
 
     const transport = new StreamableHTTPServerTransport({
       sessionIdGenerator: () => sessionId,
       onsessioninitialized: (id) => {
-        this.logger.log(`MCP session initialized: ${id} for user ${userId}`);
+        this.logger.log(
+          `MCP session initialized: ${id} for actor=${actor.userId} tenant=${actor.tenantId} correlation=${actor.correlationId}`,
+        );
       },
     });
 
@@ -48,7 +258,7 @@ export class McpService implements OnModuleDestroy {
       { capabilities: { tools: {} } },
     );
 
-    this.registerTools(server, userId);
+    this.registerTools(server, actor);
 
     transport.onclose = () => {
       this.logger.log(`MCP session closed: ${sessionId}`);
@@ -61,31 +271,126 @@ export class McpService implements OnModuleDestroy {
       );
     });
 
-    this.sessions.set(sessionId, { server, transport, createdAt: new Date(), userId });
+    this.sessions.set(sessionId, { server, transport, createdAt: new Date(), actor });
     return { sessionId, transport };
   }
 
   /**
-   * Returns the transport for an existing session, or null if not found.
+   * Returns the transport for an existing session only when it belongs to the
+   * currently authenticated MCP actor. Guessed or cross-tenant session IDs grant
+   * no authority.
    */
-  getSession(sessionId: string): StreamableHTTPServerTransport | null {
+  getSession(sessionId: string, actor: McpActorContext): StreamableHTTPServerTransport | null {
-    return this.sessions.get(sessionId)?.transport ?? null;
+    const entry = this.sessions.get(sessionId);
+    if (!entry) return null;
+    if (!sameActorAuthorization(entry.actor, actor)) {
+      this.logger.warn(
+        `MCP session actor or scope mismatch: session=${sessionId} actor=${actor.userId} tenant=${actor.tenantId} role=${actor.role}`,
+      );
+      return null;
+    }
+    return entry.transport;
+  }
+
+  private async isProjectAuthorized(actor: McpActorContext, projectId: string): Promise<boolean> {
+    if (isGlobalAdminActor(actor)) return true;
+    const project = (await this.brain.projects.findById(projectId)) as ProjectLike | undefined;
+    return project ? filterProjectsForActor(actor, [project]).length === 1 : false;
+  }
+
+  private async filterMissionsForActor<T extends MissionLike>(
+    actor: McpActorContext,
+    missions: T[],
+  ): Promise<T[]> {
+    if (isGlobalAdminActor(actor)) return missions;
+
+    const projects = (await this.brain.projects.findAll()) as ProjectLike[];
+    const projectIds = new Set(
+      filterProjectsForActor(actor, projects).map((project) => project.id),
+    );
+
+    return missions.filter(
+      (mission) =>
+        filterMissionsByDirectActorScope(actor, [mission]).length === 1 ||
+        (typeof mission.projectId === 'string' && projectIds.has(mission.projectId)),
+    );
+  }
+
+  private async isMissionAuthorized(actor: McpActorContext, missionId: string): Promise<boolean> {
+    if (isGlobalAdminActor(actor)) return true;
+    const mission = (await this.brain.missions.findById(missionId)) as MissionLike | undefined;
+    if (!mission) return false;
+    return (await this.filterMissionsForActor(actor, [mission])).length === 1;
+  }
+
+  private async assertTaskReferencesAuthorized(
+    actor: McpActorContext,
+    refs: { projectId?: string | null; missionId?: string | null },
+  ): Promise<void> {
+    if (refs.projectId && !(await this.isProjectAuthorized(actor, refs.projectId))) {
+      throw new Error('MCP task project scope denied');
+    }
+    if (refs.missionId && !(await this.isMissionAuthorized(actor, refs.missionId))) {
+      throw new Error('MCP task mission scope denied');
+    }
+  }
+
+  private async assertTaskCreateScopeAuthorized(
+    actor: McpActorContext,
+    refs: { projectId?: string | null; missionId?: string | null },
+  ): Promise<void> {
+    if (!isGlobalAdminActor(actor) && !refs.projectId && !refs.missionId) {
+      throw new Error('MCP task scope denied');
+    }
+    await this.assertTaskReferencesAuthorized(actor, refs);
+  }
+
+  private async filterTasksForActor<T extends TaskLike>(
+    actor: McpActorContext,
+    tasks: T[],
+  ): Promise<T[]> {
+    if (isGlobalAdminActor(actor)) return tasks;
+
+    const [projects, missions] = await Promise.all([
+      this.brain.projects.findAll(),
+      this.brain.missions.findAll(),
+    ]);
+    const projectIds = new Set(
+      filterProjectsForActor(actor, projects as ProjectLike[]).map((project) => project.id),
+    );
+    const missionIds = new Set(
+      (await this.filterMissionsForActor(actor, missions as MissionLike[])).map(
+        (mission) => mission.id,
+      ),
+    );
+
+    return tasks.filter(
+      (task) =>
+        task.userId === actor.userId ||
+        (isTenantAdminActor(actor) && matchesTenant(actor, task)) ||
+        (typeof task.projectId === 'string' && projectIds.has(task.projectId)) ||
+        (typeof task.missionId === 'string' && missionIds.has(task.missionId)),
+    );
   }
 
   /**
    * Registers all platform tools on the given McpServer instance.
    */
-  private registerTools(server: McpServer, _userId: string): void {
+  registerTools(server: McpServer, actor: McpActorContext): void {
     // ─── Brain: Project tools ────────────────────────────────────────────
 
     server.registerTool(
       'brain_list_projects',
       {
         description: 'List all projects in the brain.',
-        inputSchema: z.object({}),
+        inputSchema: strictObject({}),
       },
-      async () => {
+      async (params) => {
-        const projects = await this.brain.projects.findAll();
+        assertMcpToolAuthorized(actor, 'brain_list_projects', params);
+        const projects = filterProjectsForActor(
+          actor,
+          (await this.brain.projects.findAll()) as ProjectLike[],
+        );
         return {
           content: [{ type: 'text' as const, text: JSON.stringify(projects, null, 2) }],
         };
@@ -96,17 +401,21 @@ export class McpService implements OnModuleDestroy {
       'brain_get_project',
       {
         description: 'Get a project by ID.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
           id: z.string().describe('Project ID (UUID)'),
         }),
       },
-      async ({ id }) => {
+      async ({ id, ...params }) => {
-        const project = await this.brain.projects.findById(id);
+        assertMcpToolAuthorized(actor, 'brain_get_project', params);
+        const project = (await this.brain.projects.findById(id)) as ProjectLike | undefined;
+        const authorizedProject = project ? filterProjectsForActor(actor, [project])[0] : undefined;
         return {
           content: [
             {
               type: 'text' as const,
-              text: project ? JSON.stringify(project, null, 2) : `Project not found: ${id}`,
+              text: authorizedProject
+                ? JSON.stringify(authorizedProject, null, 2)
+                : `Project not found: ${id}`,
             },
           ],
         };
@@ -119,20 +428,23 @@ export class McpService implements OnModuleDestroy {
       'brain_list_tasks',
       {
         description: 'List tasks, optionally filtered by project, mission, or status.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
           projectId: z.string().optional().describe('Filter by project ID'),
           missionId: z.string().optional().describe('Filter by mission ID'),
           status: z.string().optional().describe('Filter by status'),
         }),
       },
-      async ({ projectId, missionId, status }) => {
+      async (params) => {
+        assertMcpToolAuthorized(actor, 'brain_list_tasks', params);
+        const { projectId, missionId, status } = params;
         type TaskStatus = 'not-started' | 'in-progress' | 'blocked' | 'done' | 'cancelled';
         let tasks;
         if (projectId) tasks = await this.brain.tasks.findByProject(projectId);
         else if (missionId) tasks = await this.brain.tasks.findByMission(missionId);
         else if (status) tasks = await this.brain.tasks.findByStatus(status as TaskStatus);
         else tasks = await this.brain.tasks.findAll();
-        return { content: [{ type: 'text' as const, text: JSON.stringify(tasks, null, 2) }] };
+        const scopedTasks = await this.filterTasksForActor(actor, tasks as TaskLike[]);
+        return { content: [{ type: 'text' as const, text: JSON.stringify(scopedTasks, null, 2) }] };
       },
     );
 
@@ -140,7 +452,7 @@ export class McpService implements OnModuleDestroy {
       'brain_create_task',
       {
         description: 'Create a new task in the brain.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
           title: z.string().describe('Task title'),
           description: z.string().optional().describe('Task description'),
           projectId: z.string().optional().describe('Project ID'),
@@ -149,6 +461,8 @@ export class McpService implements OnModuleDestroy {
         }),
       },
       async (params) => {
+        assertMcpToolAuthorized(actor, 'brain_create_task', params);
+        await this.assertTaskCreateScopeAuthorized(actor, params);
         type Priority = 'low' | 'medium' | 'high' | 'critical';
         const task = await this.brain.tasks.create({
           ...params,
@@ -162,7 +476,7 @@ export class McpService implements OnModuleDestroy {
       'brain_update_task',
       {
         description: 'Update an existing task.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
           id: z.string().describe('Task ID'),
           title: z.string().optional(),
           description: z.string().optional(),
@@ -171,9 +485,17 @@ export class McpService implements OnModuleDestroy {
             .optional()
             .describe('not-started, in-progress, blocked, done, cancelled'),
           priority: z.string().optional(),
+          projectId: z.string().optional().describe('Project ID'),
+          missionId: z.string().optional().describe('Mission ID'),
         }),
       },
       async ({ id, ...updates }) => {
+        assertMcpToolAuthorized(actor, 'brain_update_task', updates);
+        const existing = (await this.brain.tasks.findById(id)) as TaskLike | undefined;
+        if (!existing || (await this.filterTasksForActor(actor, [existing])).length === 0) {
+          return { content: [{ type: 'text' as const, text: `Task not found: ${id}` }] };
+        }
+        await this.assertTaskReferencesAuthorized(actor, updates);
         type TaskStatus = 'not-started' | 'in-progress' | 'blocked' | 'done' | 'cancelled';
         type Priority = 'low' | 'medium' | 'high' | 'critical';
         const task = await this.brain.tasks.update(id, {
@@ -198,14 +520,19 @@ export class McpService implements OnModuleDestroy {
       'brain_list_missions',
       {
         description: 'List all missions, optionally filtered by project.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
           projectId: z.string().optional().describe('Filter by project ID'),
         }),
       },
-      async ({ projectId }) => {
+      async (params) => {
-        const missions = projectId
+        assertMcpToolAuthorized(actor, 'brain_list_missions', params);
-          ? await this.brain.missions.findByProject(projectId)
+        const { projectId } = params;
-          : await this.brain.missions.findAll();
+        const missions = await this.filterMissionsForActor(
+          actor,
+          (projectId
+            ? await this.brain.missions.findByProject(projectId)
+            : await this.brain.missions.findAll()) as MissionLike[],
+        );
         return { content: [{ type: 'text' as const, text: JSON.stringify(missions, null, 2) }] };
       },
     );
@@ -213,13 +540,12 @@ export class McpService implements OnModuleDestroy {
     server.registerTool(
       'brain_list_conversations',
       {
-        description: 'List conversations for a user.',
+        description: 'List conversations for the authenticated MCP actor.',
-        inputSchema: z.object({
+        inputSchema: strictObject({}),
-          userId: z.string().describe('User ID'),
-        }),
       },
-      async ({ userId }) => {
+      async (params) => {
-        const conversations = await this.brain.conversations.findAll(userId);
+        assertMcpToolAuthorized(actor, 'brain_list_conversations', params);
+        const conversations = await this.brain.conversations.findAll(actor.userId);
         return {
           content: [{ type: 'text' as const, text: JSON.stringify(conversations, null, 2) }],
         };
@@ -232,14 +558,15 @@ export class McpService implements OnModuleDestroy {
       'memory_search',
       {
         description:
-          'Search across stored insights and knowledge using natural language. Returns semantically similar results.',
+          'Search stored insights and knowledge for the authenticated MCP actor using natural language.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
-          userId: z.string().describe('User ID to search memory for'),
           query: z.string().describe('Natural language search query'),
           limit: z.number().optional().describe('Max results (default 5)'),
         }),
       },
-      async ({ userId, query, limit }) => {
+      async (params) => {
+        assertMcpToolAuthorized(actor, 'memory_search', params);
+        const { query, limit } = params;
         if (!this.embeddings.available) {
           return {
             content: [
@@ -251,7 +578,11 @@ export class McpService implements OnModuleDestroy {
           };
         }
         const embedding = await this.embeddings.embed(query);
-        const results = await this.memory.insights.searchByEmbedding(userId, embedding, limit ?? 5);
+        const results = await this.memory.insights.searchByEmbedding(
+          actor.userId,
+          embedding,
+          limit ?? 5,
+        );
         return { content: [{ type: 'text' as const, text: JSON.stringify(results, null, 2) }] };
       },
     );
@@ -259,20 +590,21 @@ export class McpService implements OnModuleDestroy {
     server.registerTool(
       'memory_get_preferences',
       {
-        description: 'Retrieve stored preferences for a user.',
+        description: 'Retrieve stored preferences for the authenticated MCP actor.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
-          userId: z.string().describe('User ID'),
           category: z
             .string()
             .optional()
             .describe('Filter by category: communication, coding, workflow, appearance, general'),
         }),
       },
-      async ({ userId, category }) => {
+      async (params) => {
+        assertMcpToolAuthorized(actor, 'memory_get_preferences', params);
+        const { category } = params;
         type Cat = 'communication' | 'coding' | 'workflow' | 'appearance' | 'general';
         const prefs = category
-          ? await this.memory.preferences.findByUserAndCategory(userId, category as Cat)
+          ? await this.memory.preferences.findByUserAndCategory(actor.userId, category as Cat)
-          : await this.memory.preferences.findByUser(userId);
+          : await this.memory.preferences.findByUser(actor.userId);
         return { content: [{ type: 'text' as const, text: JSON.stringify(prefs, null, 2) }] };
       },
     );
@@ -281,9 +613,8 @@ export class McpService implements OnModuleDestroy {
       'memory_save_preference',
       {
         description:
-          'Store a learned user preference (e.g., "prefers tables over paragraphs", "timezone: America/Chicago").',
+          'Store a learned preference for the authenticated MCP actor (e.g., "prefers tables over paragraphs").',
-        inputSchema: z.object({
+        inputSchema: strictObject({
-          userId: z.string().describe('User ID'),
           key: z.string().describe('Preference key'),
           value: z.string().describe('Preference value (JSON string)'),
           category: z
@@ -292,7 +623,9 @@ export class McpService implements OnModuleDestroy {
             .describe('Category: communication, coding, workflow, appearance, general'),
         }),
       },
-      async ({ userId, key, value, category }) => {
+      async (params) => {
+        assertMcpToolAuthorized(actor, 'memory_save_preference', params);
+        const { key, value, category } = params;
         type Cat = 'communication' | 'coding' | 'workflow' | 'appearance' | 'general';
         let parsedValue: unknown;
         try {
@@ -301,7 +634,7 @@ export class McpService implements OnModuleDestroy {
           parsedValue = value;
         }
         const pref = await this.memory.preferences.upsert({
-          userId,
+          userId: actor.userId,
           key,
           value: parsedValue,
           category: (category as Cat) ?? 'general',
@@ -315,9 +648,8 @@ export class McpService implements OnModuleDestroy {
       'memory_save_insight',
       {
         description:
-          'Store a learned insight, decision, or knowledge extracted from the current interaction.',
+          'Store a learned insight, decision, or knowledge for the authenticated MCP actor.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
-          userId: z.string().describe('User ID'),
           content: z.string().describe('The insight or knowledge to store'),
           category: z
             .string()
@@ -325,11 +657,13 @@ export class McpService implements OnModuleDestroy {
             .describe('Category: decision, learning, preference, fact, pattern, general'),
         }),
       },
-      async ({ userId, content, category }) => {
+      async (params) => {
+        assertMcpToolAuthorized(actor, 'memory_save_insight', params);
+        const { content, category } = params;
         type Cat = 'decision' | 'learning' | 'preference' | 'fact' | 'pattern' | 'general';
         const embedding = this.embeddings.available ? await this.embeddings.embed(content) : null;
         const insight = await this.memory.insights.create({
-          userId,
+          userId: actor.userId,
           content,
           embedding,
           source: 'agent',
@@ -346,16 +680,11 @@ export class McpService implements OnModuleDestroy {
       {
         description:
           'Get the current orchestration mission status including milestones, tasks, and active session.',
-        inputSchema: z.object({
+        inputSchema: strictObject({}),
-          projectPath: z
-            .string()
-            .optional()
-            .describe('Project path. Defaults to gateway working directory.'),
-        }),
       },
-      async ({ projectPath }) => {
+      async (params) => {
-        const resolvedPath = projectPath ?? process.cwd();
+        assertMcpToolAuthorized(actor, 'coord_mission_status', params);
-        const status = await this.coordService.getMissionStatus(resolvedPath);
+        const status = await this.coordService.getMissionStatus(process.cwd());
         return {
           content: [
             {
@@ -371,16 +700,11 @@ export class McpService implements OnModuleDestroy {
       'coord_list_tasks',
       {
         description: 'List all tasks from the orchestration TASKS.md file.',
-        inputSchema: z.object({
+        inputSchema: strictObject({}),
-          projectPath: z
-            .string()
-            .optional()
-            .describe('Project path. Defaults to gateway working directory.'),
-        }),
       },
-      async ({ projectPath }) => {
+      async (params) => {
-        const resolvedPath = projectPath ?? process.cwd();
+        assertMcpToolAuthorized(actor, 'coord_list_tasks', params);
-        const tasks = await this.coordService.listTasks(resolvedPath);
+        const tasks = await this.coordService.listTasks(process.cwd());
         return { content: [{ type: 'text' as const, text: JSON.stringify(tasks, null, 2) }] };
       },
     );
@@ -389,17 +713,14 @@ export class McpService implements OnModuleDestroy {
       'coord_task_detail',
       {
         description: 'Get detailed status for a specific orchestration task.',
-        inputSchema: z.object({
+        inputSchema: strictObject({
           taskId: z.string().describe('Task ID (e.g. P2-005)'),
-          projectPath: z
-            .string()
-            .optional()
-            .describe('Project path. Defaults to gateway working directory.'),
         }),
       },
-      async ({ taskId, projectPath }) => {
+      async (params) => {
-        const resolvedPath = projectPath ?? process.cwd();
+        assertMcpToolAuthorized(actor, 'coord_task_detail', params);
-        const detail = await this.coordService.getTaskStatus(resolvedPath, taskId);
+        const { taskId } = params;
+        const detail = await this.coordService.getTaskStatus(process.cwd(), taskId);
         return {
           content: [
             {

apps/gateway/src/plugin/discord-ingress.security.spec.ts

@@ -0,0 +1,89 @@
+import { describe, expect, it } from 'vitest';
+import {
+  createDiscordIngressEnvelope,
+  verifyDiscordIngressEnvelope,
+  type DiscordIngressPayload,
+} from '@mosaicstack/discord-plugin';
+import { validateDiscordServiceToken } from '../chat/chat.gateway-auth.js';
+import { DiscordReplayProtector } from './discord-replay-protector.js';
+
+const SERVICE_TOKEN = 'test-service-token';
+
+function createPayload(overrides: Partial<DiscordIngressPayload> = {}): DiscordIngressPayload {
+  return {
+    correlationId: 'correlation-001',
+    messageId: 'discord-message-001',
+    guildId: 'guild-001',
+    channelId: 'channel-001',
+    userId: 'user-001',
+    conversationId: 'discord-channel-001',
+    content: 'hello Tess',
+    ...overrides,
+  };
+}
+
+describe('Discord ingress security', () => {
+  it('accepts only the configured Discord service identity', () => {
+    expect(validateDiscordServiceToken(SERVICE_TOKEN, SERVICE_TOKEN)).toBe(true);
+    expect(validateDiscordServiceToken('wrong-service-token', SERVICE_TOKEN)).toBe(false);
+    expect(validateDiscordServiceToken(undefined, SERVICE_TOKEN)).toBe(false);
+  });
+
+  it('rejects unauthenticated or tampered service envelopes', () => {
+    const envelope = createDiscordIngressEnvelope(createPayload(), SERVICE_TOKEN);
+
+    expect(verifyDiscordIngressEnvelope(envelope, SERVICE_TOKEN)).toEqual(createPayload());
+    expect(verifyDiscordIngressEnvelope(envelope, 'wrong-service-token')).toBeNull();
+    expect(
+      verifyDiscordIngressEnvelope(
+        { ...envelope, payload: { ...envelope.payload, content: 'forged command' } },
+        SERVICE_TOKEN,
+      ),
+    ).toBeNull();
+  });
+
+  it.each([
+    ['guild', { guildId: 'unlisted-guild' }],
+    ['channel', { channelId: 'unlisted-channel' }],
+    ['user', { userId: 'unlisted-user' }],
+  ])(
+    'rejects an unallowlisted Discord %s',
+    (_kind: string, overrides: Partial<DiscordIngressPayload>) => {
+      const envelope = createDiscordIngressEnvelope(createPayload(overrides), SERVICE_TOKEN);
+
+      expect(
+        verifyDiscordIngressEnvelope(envelope, SERVICE_TOKEN, {
+          guildIds: ['guild-001'],
+          channelIds: ['channel-001'],
+          userIds: ['user-001'],
+        }),
+      ).toBeNull();
+    },
+  );
+
+  it('retains Discord message and correlation IDs after authenticated allowlisted validation', () => {
+    const payload = createPayload({
+      correlationId: 'correlation-trace-123',
+      messageId: 'discord-snowflake-987',
+    });
+    const envelope = createDiscordIngressEnvelope(payload, SERVICE_TOKEN);
+
+    expect(
+      verifyDiscordIngressEnvelope(envelope, SERVICE_TOKEN, {
+        guildIds: ['guild-001'],
+        channelIds: ['channel-001'],
+        userIds: ['user-001'],
+      }),
+    ).toEqual(payload);
+  });
+
+  it('rejects a replayed Discord message ID while retaining bounded replay state', () => {
+    const replayProtector = new DiscordReplayProtector(60_000, 2);
+
+    expect(replayProtector.claim('discord-message-001')).toBe(true);
+    expect(replayProtector.claim('discord-message-001')).toBe(false);
+    expect(replayProtector.claim('discord-message-002')).toBe(true);
+    expect(replayProtector.claim('discord-message-003')).toBe(true);
+    expect(replayProtector.size).toBe(2);
+  });
+});

apps/gateway/src/plugin/discord-replay-protector.ts

@@ -0,0 +1,40 @@
+/**
+ * Bounded replay cache for Discord's globally unique native message IDs.
+ * Durable ingress idempotency is added with Tess's canonical inbox/outbox work.
+ */
+export class DiscordReplayProtector {
+  private readonly claimedAt = new Map<string, number>();
+
+  constructor(
+    private readonly ttlMs = 15 * 60 * 1000,
+    private readonly maxEntries = 10_000,
+  ) {}
+
+  get size(): number {
+    return this.claimedAt.size;
+  }
+
+  /** Claims an ID exactly once within its bounded retention window. */
+  claim(messageId: string, now = Date.now()): boolean {
+    this.prune(now);
+    if (this.claimedAt.has(messageId)) return false;
+
+    this.claimedAt.set(messageId, now);
+    this.evictOverflow();
+    return true;
+  }
+
+  private prune(now: number): void {
+    for (const [messageId, claimedAt] of this.claimedAt) {
+      if (now - claimedAt >= this.ttlMs) this.claimedAt.delete(messageId);
+    }
+  }
+
+  private evictOverflow(): void {
+    while (this.claimedAt.size > this.maxEntries) {
+      const oldestMessageId = this.claimedAt.keys().next().value;
+      if (oldestMessageId === undefined) return;
+      this.claimedAt.delete(oldestMessageId);
+    }
+  }
+}

apps/gateway/src/plugin/plugin.module.ts

@@ -50,19 +50,41 @@ class TelegramChannelPluginAdapter implements IChannelPlugin {
 
 const DEFAULT_GATEWAY_URL = 'http://localhost:14242';
 
+function requiredDiscordAllowlist(name: string): string[] {
+  const value = process.env[name]
+    ?.split(',')
+    .map((id: string): string => id.trim())
+    .filter((id: string): boolean => id.length > 0);
+  if (!value || value.length === 0) {
+    throw new Error(`${name} is required when DISCORD_BOT_TOKEN is configured`);
+  }
+  return value;
+}
+
 function createPluginRegistry(): IChannelPlugin[] {
   const plugins: IChannelPlugin[] = [];
   const discordToken = process.env['DISCORD_BOT_TOKEN'];
   const discordGuildId = process.env['DISCORD_GUILD_ID'];
   const discordGatewayUrl = process.env['DISCORD_GATEWAY_URL'] ?? DEFAULT_GATEWAY_URL;
+  const discordServiceToken = process.env['DISCORD_SERVICE_TOKEN'];
+  const discordServiceUserId = process.env['DISCORD_SERVICE_USER_ID'];
 
   if (discordToken) {
+    if (!discordServiceToken || !discordServiceUserId) {
+      throw new Error(
+        'DISCORD_SERVICE_TOKEN and DISCORD_SERVICE_USER_ID are required when DISCORD_BOT_TOKEN is configured',
+      );
+    }
     plugins.push(
       new DiscordChannelPluginAdapter(
         new DiscordPlugin({
           token: discordToken,
           guildId: discordGuildId,
           gatewayUrl: discordGatewayUrl,
+          serviceToken: discordServiceToken,
+          allowedGuildIds: requiredDiscordAllowlist('DISCORD_ALLOWED_GUILD_IDS'),
+          allowedChannelIds: requiredDiscordAllowlist('DISCORD_ALLOWED_CHANNEL_IDS'),
+          allowedUserIds: requiredDiscordAllowlist('DISCORD_ALLOWED_USER_IDS'),
         }),
       ),
     );

apps/gateway/src/preferences/system-override.service.ts

@@ -1,9 +1,13 @@
 import { Injectable, Logger } from '@nestjs/common';
 import { createQueue, type QueueHandle } from '@mosaicstack/queue';
+import type { ActorTenantScope } from '../auth/session-scope.js';
 
-const SESSION_SYSTEM_KEY = (sessionId: string) => `mosaic:session:${sessionId}:system`;
+const scopedSessionId = (sessionId: string, scope: ActorTenantScope) =>
-const SESSION_SYSTEM_FRAGMENTS_KEY = (sessionId: string) =>
+  `${scope.tenantId}:${scope.userId}:${sessionId}`;
-  `mosaic:session:${sessionId}:system:fragments`;
+const SESSION_SYSTEM_KEY = (sessionId: string, scope: ActorTenantScope) =>
+  `mosaic:session:${scopedSessionId(sessionId, scope)}:system`;
+const SESSION_SYSTEM_FRAGMENTS_KEY = (sessionId: string, scope: ActorTenantScope) =>
+  `mosaic:session:${scopedSessionId(sessionId, scope)}:system:fragments`;
 const SYSTEM_OVERRIDE_TTL_SECONDS = 604800; // 7 days
 
 interface OverrideFragment {
@@ -20,9 +24,9 @@ export class SystemOverrideService {
     this.handle = createQueue();
   }
 
-  async set(sessionId: string, override: string): Promise<void> {
+  async set(sessionId: string, override: string, scope: ActorTenantScope): Promise<void> {
     // Load existing fragments
-    const existing = await this.handle.redis.get(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId));
+    const existing = await this.handle.redis.get(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope));
     const fragments: OverrideFragment[] = existing
       ? (JSON.parse(existing) as OverrideFragment[])
       : [];
@@ -37,11 +41,11 @@ export class SystemOverrideService {
     // Store both: fragments array and condensed result
     const pipeline = this.handle.redis.pipeline();
     pipeline.setex(
-      SESSION_SYSTEM_FRAGMENTS_KEY(sessionId),
+      SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope),
       SYSTEM_OVERRIDE_TTL_SECONDS,
       JSON.stringify(fragments),
     );
-    pipeline.setex(SESSION_SYSTEM_KEY(sessionId), SYSTEM_OVERRIDE_TTL_SECONDS, condensed);
+    pipeline.setex(SESSION_SYSTEM_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS, condensed);
     await pipeline.exec();
 
     this.logger.debug(
@@ -49,21 +53,21 @@ export class SystemOverrideService {
     );
   }
 
-  async get(sessionId: string): Promise<string | null> {
+  async get(sessionId: string, scope: ActorTenantScope): Promise<string | null> {
-    return this.handle.redis.get(SESSION_SYSTEM_KEY(sessionId));
+    return this.handle.redis.get(SESSION_SYSTEM_KEY(sessionId, scope));
   }
 
-  async renew(sessionId: string): Promise<void> {
+  async renew(sessionId: string, scope: ActorTenantScope): Promise<void> {
     const pipeline = this.handle.redis.pipeline();
-    pipeline.expire(SESSION_SYSTEM_KEY(sessionId), SYSTEM_OVERRIDE_TTL_SECONDS);
+    pipeline.expire(SESSION_SYSTEM_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
-    pipeline.expire(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId), SYSTEM_OVERRIDE_TTL_SECONDS);
+    pipeline.expire(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
     await pipeline.exec();
   }
 
-  async clear(sessionId: string): Promise<void> {
+  async clear(sessionId: string, scope: ActorTenantScope): Promise<void> {
     await this.handle.redis.del(
-      SESSION_SYSTEM_KEY(sessionId),
+      SESSION_SYSTEM_KEY(sessionId, scope),
-      SESSION_SYSTEM_FRAGMENTS_KEY(sessionId),
+      SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope),
     );
     this.logger.debug(`Cleared system override for session ${sessionId}`);
   }

docs/MISSION-MANIFEST.md

@@ -67,10 +67,11 @@ The MVP is complete when ALL declared workstreams are complete AND every cross-c
 
 ## Workstreams
 
-| #   | ID  | Name                                        | Status            | Manifest                                                                | Notes                                               |
+| #   | ID   | Name                                        | Status            | Manifest                                                                | Notes                                               |
-| --- | --- | ------------------------------------------- | ----------------- | ----------------------------------------------------------------------- | --------------------------------------------------- |
+| --- | ---- | ------------------------------------------- | ----------------- | ----------------------------------------------------------------------- | --------------------------------------------------- |
-| W1  | FED | Federation v1                               | planning-complete | [docs/federation/MISSION-MANIFEST.md](./federation/MISSION-MANIFEST.md) | 7 milestones, ~175K tokens, issues #460–#466 filed  |
+| W1  | FED  | Federation v1                               | planning-complete | [docs/federation/MISSION-MANIFEST.md](./federation/MISSION-MANIFEST.md) | 7 milestones, ~175K tokens, issues #460–#466 filed  |
-| W2+ | TBD | (additional workstreams declared as scoped) | —                 | —                                                                       | Scope creep is expected and explicitly accommodated |
+| W2  | TESS | Tess interaction agent                      | planning-complete | [docs/tess/MISSION-MANIFEST.md](./tess/MISSION-MANIFEST.md)             | 5 milestones; issue #706; M1 issue #707 ready       |
+| W3+ | TBD  | (additional workstreams declared as scoped) | —                 | —                                                                       | Scope creep is expected and explicitly accommodated |
 
 ### Likely Additional Workstreams (Not Yet Declared)
 

docs/PRD.md

@@ -79,6 +79,102 @@ Jarvis (v0.2.0) is a self-hosted AI assistant with a Python FastAPI backend and
 
 ---
 
+## Tess Interaction Agent Workstream (TESS)
+
+### Problem and Objective
+
+Jason needs one durable, operator-facing Mosaic agent outside Hermes that is reachable through a dedicated Discord channel and CLI, can attach to and operate the Mosaic fleet and transitional Hermes agents, and preserves context across restarts and compaction. Mos remains the coding/general fleet orchestrator; Tess is the complementary human interaction, visibility, control, and migration agent.
+
+The objective is to ship **Tess** (from _tessera_, a piece of a mosaic) as a Pi-native, GPT-5.6 Sol agent with high reasoning. Tess must use Mosaic-owned contracts and plugins so Hermes can be replaced incrementally rather than becoming a permanent architectural dependency.
+
+### Scope
+
+#### In Scope
+
+1. `TESS-ARP-001`: A runtime-neutral `AgentRuntimeProvider` contract supporting `listSessions`, `streamSession`, `sendMessage`, `terminate`, `getSessionTree`, `attach`, health, capability discovery, and normalized events/errors.
+2. `TESS-PI-001`: A long-running Pi-native Tess agent profile/service pinned to GPT-5.6 Sol with high reasoning, explicit tool policy, lifecycle hooks, durable checkpoints, and restart recovery.
+3. `TESS-DSC-001`: Dedicated Discord channel binding to Tess through the Mosaic gateway, with allowlists/RBAC, thread/reply policy, streaming, attachments, approvals, and correlation IDs.
+4. `TESS-CLI-001`: `mosaic tess` CLI commands for chat, status, session listing, attach/detach, send/steer/stop, provider health, and recovery.
+5. `TESS-FLT-001`: Fleet plugin capabilities for roster/status/heartbeat inspection, message delivery, session hierarchy, safe attach, and controlled restart/recovery.
+6. `TESS-MOS-001`: Explicit Mos coordination boundary and tools: hand off orchestration requests, observe mission/task state, receive results, and never silently compete for orchestration authority.
+7. `TESS-HRM-001`: Transitional Hermes adapter for profiles/agents, sessions, streaming/messages, Kanban, skills, memory, tools, cron, and health, using capability negotiation and fail-closed unsupported operations.
+8. `TESS-MEM-001`: Unified memory/retrieval plugin with scoped search/recent/capture/stats, startup context injection, provenance, redaction, namespace isolation, and flat-file/project truth precedence.
+9. `TESS-STA-001`: Durable agent state, inbox, handoff, compaction-recovery, and resume reconstruction.
+10. `TESS-PLG-001`: Plugin/tool catalog covering runtime bootstrap, repository/PR workflow, fleet diagnostics, incident-safe read operations, Discord interaction, and extensible MCP/skill discovery.
+11. `TESS-TRN-001`: Replaceable transport providers: tmux/fleet now, Matrix/native Mosaic transport later, with no Discord/CLI business logic coupled to transport details.
+12. `TESS-SEC-001`: RBAC, per-operation authorization, explicit approval for destructive/privileged/customer-visible actions, audit events, secret/PII redaction, tenant isolation, and bounded command execution.
+13. `TESS-SEC-002`: Command execution SHALL enforce declared scope/role server-side; admin/system and destructive operations SHALL require policy-bound durable approval.
+14. `TESS-SEC-003`: Every session list/read/attach/send/terminate operation SHALL enforce server-derived owner and tenant scope; guessed or client-supplied IDs SHALL grant no authority.
+15. `TESS-SEC-004`: MCP tools SHALL derive actor/tenant from authenticated context and SHALL NOT accept caller-controlled identity fields.
+16. `TESS-SEC-005`: Discord plugin ingress SHALL authenticate service identity, enforce guild/channel/user allowlists, propagate correlation/message IDs, and reject replay.
+17. `TESS-SEC-006`: Secret/PII classification and redaction SHALL occur before persistence and before channel egress, including tool metadata and authentication flows.
+18. `TESS-SEC-007`: Approvals SHALL be one-time, expiring, actor/tenant-bound, and cryptographically bound to the exact structured action digest.
+19. `TESS-SEC-008`: Ingress, provider sends, tool side effects, and responses SHALL use durable inbox/outbox/checkpoints and idempotency records for restart-safe replay.
+20. `TESS-SEC-009`: Garbage collection and retention SHALL be session/tenant scoped unless executed as a separately authorized and audited system-wide job.
+21. `TESS-OBS-001`: Structured logs, traces, health/readiness, provider latency/errors, session lifecycle, tool audit, and actionable recovery diagnostics.
+22. `TESS-MIG-001`: Capability inventory and staged Hermes-to-Mosaic migration matrix with coexistence, cutover, rollback, and deprecation gates.
+
+#### Out of Scope
+
+1. Replacing Mos as coding/general fleet orchestrator.
+2. Making Hermes the Mosaic core or coupling Mosaic domain logic to Hermes schemas.
+3. Migrating every historical chat verbatim; only policy-compliant indexed summaries and user-selected sessions are migrated.
+4. Unrestricted shell execution from Discord.
+5. Full web UI parity in the first Tess operational milestone; gateway contracts must remain web-consumable.
+6. Replacing tmux before Matrix/native transport reaches operational parity.
+
+### Stakeholder and User Requirements
+
+- Jason must be able to converse with the same Tess session from Discord and CLI.
+- Jason must be able to see what is running, stale, blocked, or unhealthy without attaching manually to every session.
+- Jason must be able to attach to Tess and authorized fleet sessions through supported CLI controls.
+- Tess must collaborate with Mos and the fleet while preserving a single clear orchestration authority.
+- The system must migrate useful Hermes/OpenClaw capabilities intentionally, with evidence, instead of copying implementations wholesale.
+
+### Non-Functional Requirements
+
+1. **Security:** default-deny provider/tool capabilities, least privilege, no secrets in logs/prompts/commits, Discord user/channel authorization, and auditable approvals.
+2. **Reliability:** durable inbox/checkpoints; idempotent message handling; reconnect with bounded backoff; no message loss or duplicate execution across gateway restart.
+3. **Performance:** first acknowledgement within 2 seconds when connected; streamed agent output begins within 5 seconds excluding model/provider delay; status reads return within 2 seconds under nominal local conditions.
+4. **Observability:** every ingress message and resulting provider/tool operation carries a correlation ID across Discord, gateway, Tess, provider, and audit events.
+5. **Maintainability:** channel, runtime, transport, memory, and external-agent integrations remain adapter-based with contract tests.
+6. **Privacy:** only scoped context enters external runtimes; persisted messages/memories follow retention and redaction policy.
+7. **Portability:** Tess runs through Pi/Mosaic contracts and does not require Hermes to start or serve native Mosaic operations.
+
+### Acceptance Criteria
+
+1. `AC-TESS-01`: A dedicated Discord channel and `mosaic tess chat` connect to one durable Tess session and stream responses bidirectionally.
+2. `AC-TESS-02`: `mosaic tess status|sessions|tree|attach|send|stop` operate against authorized provider capabilities with stable typed outputs and actionable errors.
+3. `AC-TESS-03`: Tess runs GPT-5.6 Sol at high reasoning and its effective runtime/model/tool policy is visible through status without exposing credentials.
+4. `AC-TESS-04`: Tess can inspect and message the Mosaic fleet, hand orchestration work to Mos, and demonstrate that Tess does not independently claim Mos-owned orchestration work.
+5. `AC-TESS-05`: Hermes adapter demonstrates session listing, streaming/message delivery, hierarchy mapping, and at least one approved capability in each of Kanban, skills, memory, tools, and cron—or reports unsupported capabilities fail-closed.
+6. `AC-TESS-06`: Restart/compaction test preserves session identity, pending inbox, last durable checkpoint, and a resumable handoff without duplicate side effects.
+7. `AC-TESS-07`: Unauthorized Discord users/channels, cross-tenant access, unsafe tool calls, forged approvals, and sensitive-output cases are denied and audited.
+8. `AC-TESS-08`: tmux/fleet and Matrix/native transport implementations pass the same provider contract suite; Matrix may remain non-default until readiness gates pass.
+9. `AC-TESS-09`: Baseline quality gates, unit/integration/contract tests, Discord+CLI E2E, restart/recovery tests, independent code review, and security review are green.
+10. `AC-TESS-10`: Migration matrix documents every audited Hermes/OpenClaw capability as native, adapted, deferred, or rejected, with cutover and rollback evidence.
+11. `AC-TESS-11`: User, admin, developer, API/OpenAPI, operations/recovery, and plugin-authoring documentation is current and linked from the sitemap.
+
+### Constraints, Dependencies, Risks, and Assumptions
+
+- Dependency: Mosaic gateway remains the single API surface; Pi is the native runtime; Valkey/PostgreSQL provide canonical durable state where required.
+- Dependency: Discord bot credentials and dedicated channel ID are deployment secrets provisioned outside source control.
+- Risk: Tess could drift into a second orchestrator. Mitigation: explicit role policy, Mos handoff contract, authority checks, and E2E boundary tests.
+- Risk: broad Hermes compatibility can freeze legacy semantics into Mosaic. Mitigation: Mosaic-owned normalized contracts and capability negotiation.
+- Risk: Discord creates a privileged remote-control surface. Mitigation: pairing/allowlists, RBAC, approvals, rate limits, audit, and safe tool classes.
+- Risk: transcript ingestion can violate privacy or overload memory. Mitigation: scoped opt-in import, redacted summaries, provenance, retention, and deduplication.
+- Risk: current root filesystem has limited headroom. Mitigation: isolated worktrees, no duplicated dependency installation unless required, and cleanup only after active-lane verification.
+- `ASSUMPTION:` The public name is **Tess**, because the user requested a name and the tessera/Mosaic relationship is distinctive; config must permit later display-name changes without renaming APIs or storage keys.
+- `ASSUMPTION:` The dedicated Discord channel ID and final guild policy will be supplied/provisioned during deployment, so implementation uses explicit configuration and fail-fast startup validation.
+- `ASSUMPTION:` tmux/fleet is the production transport for the first operational milestone; Matrix/native transport is implemented behind the same contract and promoted only after parity/reliability verification.
+- `ASSUMPTION:` Project/task truth remains in canonical Mosaic/project stores; semantic memory systems are retrieval/mirror layers, not hidden authorities.
+
+### Testing and Delivery Intent
+
+Delivery uses five gated milestones: runtime contracts/security; Pi service/state; Discord/CLI; fleet/Hermes/plugin suite; migration/Matrix/recovery/qualification. Every source-code task requires tests, independent review, a PR to `main`, terminal-green CI, and issue/task closure. Production activation additionally requires a clean-host Pi launch, dedicated Discord channel smoke test, CLI attach test, restart/recovery drill, and rollback procedure.
+
+---
+
 ## Architecture
 
 ### High-Level System Diagram

docs/TASKS.md

@@ -14,9 +14,10 @@
 
 ## Workstream Rollup
 
-| id  | status            | workstream          | progress         | tasks file                                        | notes                                                           |
+| id  | status            | workstream             | progress         | tasks file                                        | notes                                                           |
-| --- | ----------------- | ------------------- | ---------------- | ------------------------------------------------- | --------------------------------------------------------------- |
+| --- | ----------------- | ---------------------- | ---------------- | ------------------------------------------------- | --------------------------------------------------------------- |
-| W1  | planning-complete | Federation v1 (FED) | 0 / 7 milestones | [docs/federation/TASKS.md](./federation/TASKS.md) | M1 task breakdown populated; M2–M7 deferred to mission planning |
+| W1  | planning-complete | Federation v1 (FED)    | 0 / 7 milestones | [docs/federation/TASKS.md](./federation/TASKS.md) | M1 task breakdown populated; M2–M7 deferred to mission planning |
+| W2  | planning-complete | Tess interaction agent | 0 / 5 milestones | [docs/tess/TASKS.md](./tess/TASKS.md)             | Issue #706; independent planning gate PASS; M1 issue #707 ready |
 
 ## Cross-Cutting Tracking
 

docs/architecture/channel-protocol.md

@@ -232,6 +232,10 @@ The following sections document how each supported channel maps its native messa
 
 **Outbound:** Adapter calls Discord REST `POST /channels/{id}/messages`. Markdown content is sent as-is (Discord renders it). For `contentType = "code"` the adapter wraps in triple-backtick fences with the `metadata.language` tag.
 
+### Discord service ingress security
+
+The Discord adapter is an authenticated gateway service, not an anonymous Socket.IO client. It presents `DISCORD_SERVICE_TOKEN` during its `/chat` connection and signs each inbound envelope using HMAC-SHA-256. The envelope contains the Discord native message ID and a generated correlation ID. Gateway verifies the service credential, signature, and configured guild/channel/user allowlists before agent dispatch, then rejects duplicate native message IDs inside its bounded replay window. All three allowlists are default-deny and required when the Discord plugin is enabled. The service credential is injected at runtime and is never logged or included in protocol payloads.
+
 ---
 
 ### Telegram

docs/federation/TASKS.md

@@ -91,22 +91,22 @@ Goal: Two federated gateways exchange real data over mTLS. Inbound requests pass
 >
 > **Tracking issue:** #462.
 
-| id        | status      | description                                                                                                                                                                                                                                                                                            | issue | agent  | branch                               | depends_on       | estimate | notes                                                                                                                                                    |
+| id        | status      | description                                                                                                                                                                                                                                                                                            | issue | agent  | branch                               | depends_on                        | estimate | notes                                                                                                                                                    |
-| --------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- | ------ | ------------------------------------ | ---------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| --------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- | ------ | ------------------------------------ | --------------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FED-M3-01 | not-started | `packages/types/src/federation/` — request/response DTOs for `list`, `get`, `capabilities` verbs. Wire-format zod schemas + inferred TS types. Includes `FederationRequest`, `FederationListResponse<T>`, `FederationGetResponse<T>`, `FederationCapabilitiesResponse`, error envelope, `_source` tag. | #462  | sonnet | feat/federation-m3-types             | —                | 4K       | Reusable from gateway server + client + harness. Pure types — no I/O, no NestJS.                                                                         |
+| FED-M3-01 | done        | `packages/types/src/federation/` — request/response DTOs for `list`, `get`, `capabilities` verbs. Wire-format zod schemas + inferred TS types. Includes `FederationRequest`, `FederationListResponse<T>`, `FederationGetResponse<T>`, `FederationCapabilitiesResponse`, error envelope, `_source` tag. | #462  | sonnet | feat/federation-m3-types             | —                                 | 4K       | Reusable from gateway server + client + harness. Pure types — no I/O, no NestJS.                                                                         |
-| FED-M3-02 | not-started | `tools/federation-harness/` scaffold: `docker-compose.two-gateways.yml` (Server A + Server B + step-CA), `seed.ts` (provisions grants, peers, sample tasks/notes/credentials per scope variant), `harness.ts` helper (boots stack, returns typed clients). README documents harness use.               | #462  | sonnet | feat/federation-m3-harness           | DEPLOY-04 (soft) | 8K       | Falls back to local docker-compose if `mos-test-1/-2` not yet redeployed (DEPLOY chain blocked on IMG-FIX). Permanent test infra used by M3+.            |
+| FED-M3-02 | done        | `tools/federation-harness/` scaffold: `docker-compose.two-gateways.yml` (Server A + Server B + step-CA), `seed.ts` (provisions grants, peers, sample tasks/notes/credentials per scope variant), `harness.ts` helper (boots stack, returns typed clients). README documents harness use.               | #462  | sonnet | feat/federation-m3-harness           | DEPLOY-04 (soft)                  | 8K       | Falls back to local docker-compose if `mos-test-1/-2` not yet redeployed (DEPLOY chain blocked on IMG-FIX). Permanent test infra used by M3+.            |
-| FED-M3-03 | not-started | `apps/gateway/src/federation/server/federation-auth.guard.ts` (NestJS guard). Validates inbound client cert from Fastify TLS context, extracts `grantId` + `subjectUserId` from custom OIDs, loads grant from DB, asserts `status='active'`, attaches `FederationContext` to request.                  | #462  | sonnet | feat/federation-m3-auth-guard        | M3-01            | 8K       | Reuses OID parsing logic mirrored from `ca.service.ts` post-issuance verification. 401 on malformed/missing OIDs; 403 on revoked/expired/missing grant.  |
+| FED-M3-03 | done        | `apps/gateway/src/federation/server/federation-auth.guard.ts` (NestJS guard). Validates inbound client cert from Fastify TLS context, extracts `grantId` + `subjectUserId` from custom OIDs, loads grant from DB, asserts `status='active'`, attaches `FederationContext` to request.                  | #462  | sonnet | feat/federation-m3-auth-guard        | M3-01                             | 8K       | Reuses OID parsing logic mirrored from `ca.service.ts` post-issuance verification. 401 on malformed/missing OIDs; 403 on revoked/expired/missing grant.  |
-| FED-M3-04 | not-started | `apps/gateway/src/federation/server/scope.service.ts`. Pipeline: (1) resource allowlist + excluded check, (2) native RBAC eval as `subjectUserId`, (3) scope filter intersection (`include_teams`, `include_personal`), (4) `max_rows_per_query` cap. Pure service — DB calls injected.                | #462  | sonnet | feat/federation-m3-scope-service     | M3-01            | 10K      | Hardest correctness target in M3. Reuses `parseFederationScope` (M2-03). Returns either `{ allowed: true, filter }` or structured deny reason for audit. |
+| FED-M3-04 | in-progress | `apps/gateway/src/federation/server/scope.service.ts`. Pipeline: (1) resource allowlist + excluded check, (2) native RBAC eval as `subjectUserId`, (3) scope filter intersection (`include_teams`, `include_personal`), (4) `max_rows_per_query` cap. Pure service — DB calls injected.                | #462  | sonnet | feat/federation-m3-scope-service     | M3-01                             | 10K      | Hardest correctness target in M3. Reuses `parseFederationScope` (M2-03). Returns either `{ allowed: true, filter }` or structured deny reason for audit. |
-| FED-M3-05 | not-started | `apps/gateway/src/federation/server/verbs/list.controller.ts`. Wires AuthGuard → ScopeService → tasks/notes/memory query layer; applies row cap; tags rows with `_source`. Resource selector via path param.                                                                                           | #462  | sonnet | feat/federation-m3-verb-list         | M3-03, M3-04     | 6K       | Routes: `POST /api/federation/v1/list/:resource`. No body persistence. Audit write deferred to M4.                                                       |
+| FED-M3-05 | in-progress | `apps/gateway/src/federation/server/verbs/list.controller.ts`. Wires AuthGuard → ScopeService → tasks/notes/memory query layer; applies row cap; tags rows with `_source`. Resource selector via path param.                                                                                           | #462  | sonnet | feat/federation-m3-verb-list         | M3-03, M3-04                      | 6K       | Routes: `POST /api/federation/v1/list/:resource`. No body persistence. Audit write deferred to M4.                                                       |
-| FED-M3-06 | not-started | `apps/gateway/src/federation/server/verbs/get.controller.ts`. Single-resource fetch by id; same pipeline as list. 404 on not-found, 403 on RBAC/scope deny — both audited the same way.                                                                                                                | #462  | sonnet | feat/federation-m3-verb-get          | M3-03, M3-04     | 6K       | `POST /api/federation/v1/get/:resource/:id`. Mirrors list controller patterns.                                                                           |
+| FED-M3-06 | not-started | `apps/gateway/src/federation/server/verbs/get.controller.ts`. Single-resource fetch by id; same pipeline as list. 404 on not-found, 403 on RBAC/scope deny — both audited the same way.                                                                                                                | #462  | sonnet | feat/federation-m3-verb-get          | M3-03, M3-04                      | 6K       | `POST /api/federation/v1/get/:resource/:id`. Mirrors list controller patterns.                                                                           |
-| FED-M3-07 | not-started | `apps/gateway/src/federation/server/verbs/capabilities.controller.ts`. Read-only enumeration: returns `{ resources, excluded_resources, max_rows_per_query, supported_verbs }` derived from grant scope. Always allowed for an active grant — no RBAC eval.                                            | #462  | sonnet | feat/federation-m3-verb-capabilities | M3-03            | 4K       | `GET /api/federation/v1/capabilities`. Smallest verb; useful sanity check that mTLS + auth guard work end-to-end.                                        |
+| FED-M3-07 | done        | `apps/gateway/src/federation/server/verbs/capabilities.controller.ts`. Read-only enumeration: returns `{ resources, excluded_resources, max_rows_per_query, supported_verbs }` derived from grant scope. Always allowed for an active grant — no RBAC eval.                                            | #462  | sonnet | feat/federation-m3-verb-capabilities | M3-03                             | 4K       | `GET /api/federation/v1/capabilities`. Smallest verb; useful sanity check that mTLS + auth guard work end-to-end.                                        |
-| FED-M3-08 | not-started | `apps/gateway/src/federation/client/federation-client.service.ts`. Outbound mTLS dialer: picks `(certPem, sealed clientKey)` from `federation_peers`, unwraps key, builds undici Agent with mTLS, calls peer verb, parses typed response, wraps non-2xx into `FederationClientError`.                  | #462  | sonnet | feat/federation-m3-client            | M3-01            | 8K       | Independent of server stream — can land in parallel with M3-03/04. Cert/key cached per-peer; flushed by future M5/M6 logic.                              |
+| FED-M3-08 | done        | `apps/gateway/src/federation/client/federation-client.service.ts`. Outbound mTLS dialer: picks `(certPem, sealed clientKey)` from `federation_peers`, unwraps key, builds undici Agent with mTLS, calls peer verb, parses typed response, wraps non-2xx into `FederationClientError`.                  | #462  | sonnet | feat/federation-m3-client            | M3-01                             | 8K       | Independent of server stream — can land in parallel with M3-03/04. Cert/key cached per-peer; flushed by future M5/M6 logic.                              |
-| FED-M3-09 | not-started | `apps/gateway/src/federation/client/query-source.service.ts`. Accepts `source: "local" \| "federated:<host>" \| "all"` from gateway query layer; for `"all"` fans out to local + each peer in parallel; merges results; tags every row with `_source`.                                                 | #462  | sonnet | feat/federation-m3-query-source      | M3-08            | 8K       | Per-peer failure surfaces as `_partial: true` in response, not hard failure (sets up M5 offline UX). M5 adds caching + circuit breaker on top.           |
+| FED-M3-09 | done        | `apps/gateway/src/federation/client/query-source.service.ts`. Accepts `source: "local" \| "federated:<host>" \| "all"` from gateway query layer; for `"all"` fans out to local + each peer in parallel; merges results; tags every row with `_source`.                                                 | #462  | sonnet | feat/federation-m3-query-source      | M3-08                             | 8K       | Per-peer failure surfaces as `_partial: true` in response, not hard failure (sets up M5 offline UX). M5 adds caching + circuit breaker on top.           |
-| FED-M3-10 | not-started | Integration tests for MILESTONES.md M3 acceptance #6 (malformed OIDs → 401; valid cert + revoked grant → 403) and #7 (`max_rows_per_query` cap). Real PG, mocked TLS context (Fastify req shim).                                                                                                       | #462  | sonnet | feat/federation-m3-integration       | M3-05, M3-06     | 8K       | Vitest profile gated by `FEDERATED_INTEGRATION=1`. Single-gateway suite; no harness required.                                                            |
+| FED-M3-10 | not-started | Integration tests for MILESTONES.md M3 acceptance #6 (malformed OIDs → 401; valid cert + revoked grant → 403) and #7 (`max_rows_per_query` cap). Real PG, mocked TLS context (Fastify req shim).                                                                                                       | #462  | sonnet | feat/federation-m3-integration       | M3-05, M3-06                      | 8K       | Vitest profile gated by `FEDERATED_INTEGRATION=1`. Single-gateway suite; no harness required.                                                            |
-| FED-M3-11 | not-started | E2E tests for MILESTONES.md M3 acceptance #1, #2, #3, #4, #5, #8, #9, #10 (8 cases). Uses harness from M3-02; two real gateways, real Step-CA, real mTLS. Each test asserts both happy-path response and audit/no-persist invariants.                                                                  | #462  | sonnet | feat/federation-m3-e2e               | M3-02, M3-09     | 12K      | Largest single task. Each acceptance gets its own `it(...)` for clear failure attribution.                                                               |
+| FED-M3-11 | not-started | E2E tests for MILESTONES.md M3 acceptance #1, #2, #3, #4, #5, #8, #9, #10 (8 cases). Uses harness from M3-02; two real gateways, real Step-CA, real mTLS. Each test asserts both happy-path response and audit/no-persist invariants.                                                                  | #462  | sonnet | feat/federation-m3-e2e               | M3-02, M3-04, M3-05, M3-06, M3-09 | 12K      | Largest single task. Each acceptance gets its own `it(...)` for clear failure attribution.                                                               |
-| FED-M3-12 | not-started | Independent security review (sonnet, not author of M3-03/04/05/06/07/08/09): focus on cert-SAN spoofing, OID extraction edge cases, scope-bypass via filter manipulation, RBAC-bypass via subjectUser swap, response leakage when scope deny.                                                          | #462  | sonnet | feat/federation-m3-security-review   | M3-11            | 10K      | Two review rounds budgeted. PRD requires explicit test for every 401/403 path — review verifies coverage.                                                |
+| FED-M3-12 | not-started | Independent security review (sonnet, not author of M3-03/04/05/06/07/08/09): focus on cert-SAN spoofing, OID extraction edge cases, scope-bypass via filter manipulation, RBAC-bypass via subjectUser swap, response leakage when scope deny.                                                          | #462  | sonnet | feat/federation-m3-security-review   | M3-11                             | 10K      | Two review rounds budgeted. PRD requires explicit test for every 401/403 path — review verifies coverage.                                                |
-| FED-M3-13 | not-started | Docs update: `docs/federation/SETUP.md` mTLS handshake section, new `docs/federation/HARNESS.md` for federation-harness usage, OID reference table in SETUP.md, scope enforcement pipeline diagram. Runbook still M7-deferred.                                                                         | #462  | haiku  | feat/federation-m3-docs              | M3-12            | 5K       | One ASCII diagram for the auth-guard → scope → RBAC pipeline; helps future reviewers reason about denial paths.                                          |
+| FED-M3-13 | not-started | Docs update: `docs/federation/SETUP.md` mTLS handshake section, new `docs/federation/HARNESS.md` for federation-harness usage, OID reference table in SETUP.md, scope enforcement pipeline diagram. Runbook still M7-deferred.                                                                         | #462  | haiku  | feat/federation-m3-docs              | M3-12                             | 5K       | One ASCII diagram for the auth-guard → scope → RBAC pipeline; helps future reviewers reason about denial paths.                                          |
-| FED-M3-14 | not-started | PR aggregate close, CI green, merge to main, close #462. Release tag `fed-v0.3.0-m3`. Update mission manifest M3 row → done; M4 row → in-progress when work begins.                                                                                                                                    | #462  | sonnet | chore/federation-m3-close            | M3-13            | 3K       | Same close pattern as M1-12 / M2-13.                                                                                                                     |
+| FED-M3-14 | not-started | PR aggregate close, CI green, merge to main, close #462. Release tag `fed-v0.3.0-m3`. Update mission manifest M3 row → done; M4 row → in-progress when work begins.                                                                                                                                    | #462  | sonnet | chore/federation-m3-close            | M3-13                             | 3K       | Same close pattern as M1-12 / M2-13.                                                                                                                     |
 
 **M3 estimate:** ~100K tokens (vs MILESTONES.md 40K — same per-task breakdown pattern as M1/M2: tests, review, and docs split out from implementation cost). Largest milestone in the federation mission.
 
@@ -118,6 +118,10 @@ Goal: Two federated gateways exchange real data over mTLS. Inbound requests pass
 
 **Test bed fallback:** If `mos-test-1.woltje.com` / `mos-test-2.woltje.com` are still blocked on `FED-M2-DEPLOY-IMG-FIX` when M3-11 is ready to run, the harness's local `docker-compose.two-gateways.yml` is a sufficient stand-in. Production-host validation moves to M7 acceptance suite (PRD AC-12).
 
+**Backlog sync — 2026-06-24 (orchestrator):** Status reconciled against `origin/main` (release 0.0.48). Landed on main: **FED-M3-01** (DTOs, PR #506), **FED-M3-02** (harness scaffold, PR #505), **FED-M3-03** (mTLS auth-guard, PR #509 — CRIT-1/2 + HIGH-1..4 remediated in-PR), **FED-M3-08** (outbound mTLS client, PR #508). With M3-01/03/08 merged, three cards became dependency-clear and were dispatched to the idle coder lane: **FED-M3-04** scope.service → coder0 (`feat/federation-m3-scope-service`); **FED-M3-09** query-source + **FED-M3-07** capabilities verb → coder1 (`feat/federation-m3-query-source` first). Reviewer warmed for the M3 trust-boundary PRs. Remaining blocked-by-DAG: M3-05/06 (await M3-04), M3-10 (await M3-05/06), M3-11 (await M3-09), M3-12→14 (tail). Deploy chain (DEPLOY-IMG-FIX → 03/04) still independent of M3 code — harness local docker-compose fallback covers M3-11.
+
+**Backlog sync #2 — 2026-06-24 (orchestrator):** **FED-M3-09** (query-source) merged via PR #673 and **FED-M3-07** (capabilities) merged via PR #674 — both squash-merged on independent agent review-of-record + green CI (formal Gitea approve unavailable under the shared service account; merge is not gated by the self-approve guard). **FED-M3-05** (list verb) dispatched to coder1 (based on the M3-04 branch, rebase onto main once #672 lands). **FED-M3-04** (scope.service, PR #672) is in review-changes (one include_personal no-leak test outstanding). **DAG fix:** corrected `FED-M3-11` depends_on from `M3-02, M3-09` → `M3-02, M3-04, M3-05, M3-06, M3-09` — the E2E acceptance cases (#1–#5, #8–#10) exercise list/get over mTLS, so the server verbs + scope service are hard prerequisites; the original edge set omitted them and caused a premature M3-11 dispatch. Note: M3 read-path invariant for M3-11 is **no-persist + existing enrollment audit only** — read-verb audit-log writes are deferred to M4 (see M3-05/06 notes), so M3-11 must not assert read-audit-log entries.
+
 ## Milestone 4 — search + audit + rate limit (FED-M4)
 
 _Deferred. Issue #463._

docs/fleet/NORTH_STAR.md

@@ -0,0 +1,79 @@
+# Mosaic Fleet — NORTH STAR
+
+> **Generated file — do not edit by hand.**
+> Projected deterministically from [`NORTH_STAR.yaml`](./NORTH_STAR.yaml) by the pure
+> generator in `packages/mosaic/src/commands/fleet.ts` (`renderNorthStarMarkdown`).
+> Edit the YAML, then regenerate. Self-contained Mosaic — no Hermes dependency.
+
+## Mission
+
+A self-driving Mosaic system that 24/7 unattended converts a machine-readable goal set into merged, CI-green, budget-bounded change — looping plan→backlog→assign→execute→verify→merge→reassess — on Mosaic's OWN native backlog/dispatch engine. Mosaic is general-purpose: the user declares the system type they want (software delivery, personal assistant, research, business/operations, …) and the orchestrator provisions the matching persona roster and structure; the delivery fleet is one profile among many.
+
+## Substrate
+
+The Mosaic Backlog is the backlog of record + dispatch engine, built on Mosaic's native Postgres storage service (@mosaicstack/db drizzle; PGlite-embedded by default, full Postgres by config). NOT Hermes.
+
+## Standing objectives
+
+- **NS-1** — Single machine-readable source (this file) drives planning; prose docs are projections.
+- **NS-2** — Every backlog item is an independently-shippable unit with stable id, priority, depends_on DAG, represented as a Mosaic Backlog card; spend tracked as advisory projection.
+- **NS-3** — The supervisor guarantees movement: no idle agent while ready dependency-satisfied work exists; no empty backlog without a replan request; assignment via Mosaic native dispatch/claim.
+- **NS-4** — Exactly one merge-gate approver; nothing reaches main except via pr-merge.sh after pr-ci-wait.sh success; Gitea branch protection is the backstop.
+- **NS-5** — Every unit bounded by wall-clock TTL on its claim; token caps enforced only where a real meter exists, else advisory.
+- **NS-6** — Context cleared between tasks for ephemeral runners (reset_between_tasks); persona+mission re-injected per task.
+- **NS-7** — Meta-loop (session-review + enhancer) continuously proposes small fleet-improvement PRs.
+- **NS-8** — Single operator-flippable PAUSE kill-switch (fleet/run/PAUSED) honored before every dispatch and every merge.
+- **NS-9** — Mosaic is a general-purpose multi-agent system: the user declares the SYSTEM TYPE to run (e.g. software delivery, personal assistant, research, business/operations) and the orchestrator provisions the matching persona roster and org structure from a cross-domain baseline persona library; the delivery/coding fleet is one profile among many.
+
+## Success criteria
+
+- **AC-NS-1** — The supervisor keeps a two-agent floor (1 orchestrator + >=1 enhancer) healthy across reboot.
+- **AC-NS-2** — A goal added to this YAML is decomposed to cards and either merged or escalated, with no human in the loop.
+- **AC-NS-3** — No PR merges with failure/error/no-status/timeout CI, and none bypass pr-merge.sh.
+- **AC-NS-4** — TTL is enforced on claims; token caps remain advisory until a real meter exists.
+- **AC-NS-5** — Flipping fleet/run/PAUSED halts dispatch and merges within one tick.
+- **AC-NS-6** — A user can declare a system type and the fleet provisions the matching persona roster + topology from the baseline library, with no code change.
+- **AC-NS-7** — A user-customized persona (edited or added via the orchestrator) survives `mosaic update`: baseline reseed never clobbers user overrides.
+
+## Workstreams
+
+| id  | title                                                                                                       |
+| --- | ----------------------------------------------------------------------------------------------------------- |
+| A   | Substrate — Mosaic Backlog on native Postgres storage service                                               |
+| B   | Supervisor — movement guarantee, two-agent floor, dispatch/claim                                            |
+| C   | Planner — goal decomposition into independently-shippable cards                                             |
+| D   | Merge-gate — single approver, pr-merge.sh after CI wait                                                     |
+| E   | Meta-loop — session-review + enhancer improvement PRs                                                       |
+| F   | Safety-rails — TTL claims, advisory spend, PAUSE kill-switch                                                |
+| H   | Personas & system profiles — cross-domain library, system-type provisioning, update-surviving customization |
+
+## Goals (backlog projection)
+
+| id  | title                                                                                                                                             | phase | priority    | depends_on |
+| --- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | ----------- | ---------- |
+| A1  | Machine-readable NORTH_STAR.yaml + Markdown projection                                                                                            | 1     | must-have   | —          |
+| A2  | Mosaic Backlog schema + storage-service card store (drizzle/PGlite)                                                                               | 1     | must-have   | A1         |
+| A3a | Card lifecycle — create/claim/release with stable ids + depends_on DAG                                                                            | 1     | must-have   | A2         |
+| A3b | TTL-bounded claim enforcement (wall-clock) on cards                                                                                               | 1     | must-have   | A3a        |
+| A4  | Advisory spend projection per card (degrades to TTL, no real meter)                                                                               | 1     | should-have | A3a        |
+| B1  | Supervisor tick — readiness scan, two-agent-floor health check                                                                                    | 2     | must-have   | A3a        |
+| B2  | Native dispatch/claim — assign ready dependency-satisfied work                                                                                    | 2     | must-have   | A3b, B1    |
+| B3a | Planner decompose — goal added to YAML → cards                                                                                                    | 2     | must-have   | A2, B1     |
+| B3b | Replan request on empty backlog; escalate on no-decompose                                                                                         | 2     | should-have | B3a        |
+| G1  | PAUSE kill-switch + merge-gate honored before dispatch and merge                                                                                  | 2     | must-have   | B2         |
+| H1  | Cross-domain baseline persona library (exec, marketing, ops, research, assistant + engineering roles)                                             | 1     | must-have   | A1         |
+| H2  | System-type profiles — declarative mapping of system type to persona roster + topology                                                            | 2     | must-have   | H1         |
+| H3  | System-type provisioning — user declares type; orchestrator instantiates the matching roster + structure                                          | 2     | must-have   | H2         |
+| H4  | Update-surviving persona customization — ad-hoc edits/additions persisted in a PRESERVE-protected override layer (baseline merged with overrides) | 2     | must-have   | H1         |
+
+## Assumptions (vetoable)
+
+- **ASM-1** (vetoable) — The Mosaic Backlog on the native Postgres storage service is the backlog of record.
+- **ASM-2** (vetoable) — Claude gate roles have no native busy status, so readiness = pane-idle + heartbeat.
+- **ASM-3** (vetoable) — Two-agent floor = 1 orchestrator + >=1 enhancer.
+- **ASM-4** (vetoable) — Baseline personas ship in framework/fleet/roles/ (reseeded on update); user overrides live in a separate PRESERVE_PATHS-protected layer and win on merge.
+
+## Spend
+
+- **advisory:** true
+- No per-task token meter yet; budgets degrade to TTL. Spend is tracked only as an advisory projection alongside each card.

docs/fleet/NORTH_STAR.yaml

@@ -0,0 +1,215 @@
+# Mosaic Fleet — NORTH_STAR (machine-readable source of truth)
+#
+# This file is the single machine-readable source of truth for fleet planning.
+# Prose docs (including NORTH_STAR.md) are deterministic PROJECTIONS of this file.
+# Regenerate the Markdown projection with the pure generator in
+# packages/mosaic/src/commands/fleet.ts (renderNorthStarMarkdown). Edit the YAML,
+# never the .md.
+#
+# Self-contained Mosaic. NO Hermes runtime dependency. The backlog of record is
+# the Mosaic Backlog on Mosaic's OWN native Postgres storage service.
+
+version: 1
+
+mission: >-
+  A self-driving Mosaic system that 24/7 unattended converts a machine-readable
+  goal set into merged, CI-green, budget-bounded change — looping
+  plan→backlog→assign→execute→verify→merge→reassess — on Mosaic's OWN native
+  backlog/dispatch engine. Mosaic is general-purpose: the user declares the
+  system type they want (software delivery, personal assistant, research,
+  business/operations, …) and the orchestrator provisions the matching persona
+  roster and structure; the delivery fleet is one profile among many.
+
+substrate:
+  note: >-
+    The Mosaic Backlog is the backlog of record + dispatch engine, built on
+    Mosaic's native Postgres storage service (@mosaicstack/db drizzle;
+    PGlite-embedded by default, full Postgres by config). NOT Hermes.
+
+standing_objectives:
+  - id: NS-1
+    text: >-
+      Single machine-readable source (this file) drives planning; prose docs are
+      projections.
+  - id: NS-2
+    text: >-
+      Every backlog item is an independently-shippable unit with stable id,
+      priority, depends_on DAG, represented as a Mosaic Backlog card; spend
+      tracked as advisory projection.
+  - id: NS-3
+    text: >-
+      The supervisor guarantees movement: no idle agent while ready
+      dependency-satisfied work exists; no empty backlog without a replan
+      request; assignment via Mosaic native dispatch/claim.
+  - id: NS-4
+    text: >-
+      Exactly one merge-gate approver; nothing reaches main except via
+      pr-merge.sh after pr-ci-wait.sh success; Gitea branch protection is the
+      backstop.
+  - id: NS-5
+    text: >-
+      Every unit bounded by wall-clock TTL on its claim; token caps enforced
+      only where a real meter exists, else advisory.
+  - id: NS-6
+    text: >-
+      Context cleared between tasks for ephemeral runners
+      (reset_between_tasks); persona+mission re-injected per task.
+  - id: NS-7
+    text: >-
+      Meta-loop (session-review + enhancer) continuously proposes small
+      fleet-improvement PRs.
+  - id: NS-8
+    text: >-
+      Single operator-flippable PAUSE kill-switch (fleet/run/PAUSED) honored
+      before every dispatch and every merge.
+  - id: NS-9
+    text: >-
+      Mosaic is a general-purpose multi-agent system: the user declares the
+      SYSTEM TYPE to run (e.g. software delivery, personal assistant, research,
+      business/operations) and the orchestrator provisions the matching persona
+      roster and org structure from a cross-domain baseline persona library; the
+      delivery/coding fleet is one profile among many.
+
+success_criteria:
+  - id: AC-NS-1
+    text: >-
+      The supervisor keeps a two-agent floor (1 orchestrator + >=1 enhancer)
+      healthy across reboot.
+  - id: AC-NS-2
+    text: >-
+      A goal added to this YAML is decomposed to cards and either merged or
+      escalated, with no human in the loop.
+  - id: AC-NS-3
+    text: >-
+      No PR merges with failure/error/no-status/timeout CI, and none bypass
+      pr-merge.sh.
+  - id: AC-NS-4
+    text: >-
+      TTL is enforced on claims; token caps remain advisory until a real meter
+      exists.
+  - id: AC-NS-5
+    text: >-
+      Flipping fleet/run/PAUSED halts dispatch and merges within one tick.
+  - id: AC-NS-6
+    text: >-
+      A user can declare a system type and the fleet provisions the matching
+      persona roster + topology from the baseline library, with no code change.
+  - id: AC-NS-7
+    text: >-
+      A user-customized persona (edited or added via the orchestrator) survives
+      `mosaic update`: baseline reseed never clobbers user overrides.
+
+workstreams:
+  - id: A
+    title: Substrate — Mosaic Backlog on native Postgres storage service
+  - id: B
+    title: Supervisor — movement guarantee, two-agent floor, dispatch/claim
+  - id: C
+    title: Planner — goal decomposition into independently-shippable cards
+  - id: D
+    title: Merge-gate — single approver, pr-merge.sh after CI wait
+  - id: E
+    title: Meta-loop — session-review + enhancer improvement PRs
+  - id: F
+    title: Safety-rails — TTL claims, advisory spend, PAUSE kill-switch
+  - id: H
+    title: Personas & system profiles — cross-domain library, system-type provisioning, update-surviving customization
+
+goals:
+  - id: A1
+    title: Machine-readable NORTH_STAR.yaml + Markdown projection
+    phase: 1
+    priority: must-have
+    depends_on: []
+  - id: A2
+    title: Mosaic Backlog schema + storage-service card store (drizzle/PGlite)
+    phase: 1
+    priority: must-have
+    depends_on: [A1]
+  - id: A3a
+    title: Card lifecycle — create/claim/release with stable ids + depends_on DAG
+    phase: 1
+    priority: must-have
+    depends_on: [A2]
+  - id: A3b
+    title: TTL-bounded claim enforcement (wall-clock) on cards
+    phase: 1
+    priority: must-have
+    depends_on: [A3a]
+  - id: A4
+    title: Advisory spend projection per card (degrades to TTL, no real meter)
+    phase: 1
+    priority: should-have
+    depends_on: [A3a]
+  - id: B1
+    title: Supervisor tick — readiness scan, two-agent-floor health check
+    phase: 2
+    priority: must-have
+    depends_on: [A3a]
+  - id: B2
+    title: Native dispatch/claim — assign ready dependency-satisfied work
+    phase: 2
+    priority: must-have
+    depends_on: [A3b, B1]
+  - id: B3a
+    title: Planner decompose — goal added to YAML → cards
+    phase: 2
+    priority: must-have
+    depends_on: [A2, B1]
+  - id: B3b
+    title: Replan request on empty backlog; escalate on no-decompose
+    phase: 2
+    priority: should-have
+    depends_on: [B3a]
+  - id: G1
+    title: PAUSE kill-switch + merge-gate honored before dispatch and merge
+    phase: 2
+    priority: must-have
+    depends_on: [B2]
+  - id: H1
+    title: Cross-domain baseline persona library (exec, marketing, ops, research, assistant + engineering roles)
+    phase: 1
+    priority: must-have
+    depends_on: [A1]
+  - id: H2
+    title: System-type profiles — declarative mapping of system type to persona roster + topology
+    phase: 2
+    priority: must-have
+    depends_on: [H1]
+  - id: H3
+    title: System-type provisioning — user declares type; orchestrator instantiates the matching roster + structure
+    phase: 2
+    priority: must-have
+    depends_on: [H2]
+  - id: H4
+    title: Update-surviving persona customization — ad-hoc edits/additions persisted in a PRESERVE-protected override layer (baseline merged with overrides)
+    phase: 2
+    priority: must-have
+    depends_on: [H1]
+
+assumptions:
+  - id: ASM-1
+    vetoable: true
+    text: >-
+      The Mosaic Backlog on the native Postgres storage service is the backlog
+      of record.
+  - id: ASM-2
+    vetoable: true
+    text: >-
+      Claude gate roles have no native busy status, so readiness = pane-idle +
+      heartbeat.
+  - id: ASM-3
+    vetoable: true
+    text: 'Two-agent floor = 1 orchestrator + >=1 enhancer.'
+  - id: ASM-4
+    vetoable: true
+    text: >-
+      Baseline personas ship in framework/fleet/roles/ (reseeded on update);
+      user overrides live in a separate PRESERVE_PATHS-protected layer and win
+      on merge.
+
+spend:
+  advisory: true
+  note: >-
+    No per-task token meter yet; budgets degrade to TTL. Spend is tracked only
+    as an advisory projection alongside each card.

docs/fleet/backlog-conventions.md

@@ -0,0 +1,138 @@
+# Fleet Backlog Conventions
+
+The **backlog** is Mosaic's native backlog-of-record for fleet work. It is built
+end-to-end on Mosaic's own storage layer (`@mosaicstack/db`, drizzle/Postgres)
+and surfaced as `mosaic fleet backlog <sub> --json`.
+
+> **Mosaic-native, no Hermes.** This backlog REPLACES the former Hermes adapter.
+> There is **no** runtime dependency on Hermes, `hermes kanban`, or `~/.hermes`
+> anywhere in this feature. Anything previously delegated to Hermes is recreated
+> here on Mosaic's own Postgres storage layer.
+
+## Storage tier — PGlite by default, Postgres by config
+
+The backlog uses the existing Mosaic storage layer; there is **no** new database
+engine (no sqlite, no raw client).
+
+| Condition                      | Tier                 | Data location                    |
+| ------------------------------ | -------------------- | -------------------------------- |
+| `DATABASE_URL` set             | Full server Postgres | the configured database          |
+| `PGLITE_DATA_DIR` set (no URL) | Embedded PGlite      | that directory                   |
+| neither (default)              | Embedded PGlite      | `~/.config/mosaic/fleet/backlog` |
+
+PGlite is real Postgres semantics in-process — including the row locks the atomic
+claim relies on — so the **same code** runs on a laptop (embedded, single-host
+default) and on a full Postgres deployment. Switching tiers is config-only.
+
+The schema (`backlog` table) is created automatically on first CLI use:
+`runMigrations()` for Postgres, `runPgliteMigrations()` for embedded PGlite.
+
+### Update safety
+
+The embedded PGlite store lives under `~/.config/mosaic/fleet/backlog`, which is
+listed in `PRESERVE_PATHS` in `packages/mosaic/framework/install.sh`. This means
+`mosaic update` (which runs the framework sync with `rsync --delete`) will **not**
+wipe the operator's backlog — same protection as the roster, per-agent env, and
+heartbeat run dir.
+
+## Card schema
+
+A card is one row in the `backlog` table:
+
+| Column              | Type                | Notes                                                         |
+| ------------------- | ------------------- | ------------------------------------------------------------- |
+| `id`                | text (PK)           | Stable, caller-supplied id (e.g. `A4`, `fleet-001`).          |
+| `title`             | text                | Required.                                                     |
+| `body`              | text (nullable)     | Free-form description.                                        |
+| `phase`             | text (nullable)     | Board/phase grouping (see below).                             |
+| `priority`          | int (default 0)     | **Higher = sooner.** Claim picks the max-priority ready card. |
+| `status`            | enum                | `ready` \| `claimed` \| `blocked` \| `done`.                  |
+| `depends_on`        | jsonb `string[]`    | DAG edges — ids of cards this one depends on.                 |
+| `claim_owner`       | text (nullable)     | Owner token of the active claim.                              |
+| `claim_ttl_seconds` | int (nullable)      | TTL of the active claim.                                      |
+| `claimed_at`        | timestamptz (null)  | When the claim was taken. `claimed_at + ttl` = expiry.        |
+| `attempts`          | int (default 0)     | Incremented each time the card is claimed.                    |
+| `idempotency_key`   | text (unique, null) | Dedups `create`; NULLs are distinct in Postgres.              |
+| `acceptance`        | jsonb (nullable)    | Acceptance criteria (array of strings or object).             |
+| `created_at`        | timestamptz         |                                                               |
+| `updated_at`        | timestamptz         |                                                               |
+
+`depends_on` is modeled as a `jsonb` array column rather than a separate edge
+table. Justification: it matches the repo's existing style (e.g. `tasks.tags`,
+`agents.skills`, `routing_rules.conditions` are all jsonb arrays), keeps a card
+self-contained, and the DAG is small (per-card dependency lists), so a join table
+would add ceremony without benefit.
+
+### Board / phase convention
+
+`phase` is a free-form grouping string used as the board column / milestone label
+(e.g. `M1`, `fleet`, `infra`). `list --phase <phase>` filters to one board lane.
+`priority` orders cards **within** the ready pool regardless of phase.
+
+## Status lifecycle
+
+```
+            create
+              │
+              ▼
+   ┌──────► ready ───── claim ─────► claimed ───── complete ─────► done
+   │          │                         │
+   │       block                  reclaim (TTL expiry or --id)
+   │          ▼                         │
+   │       blocked                      └──────────────────────────┘ (back to ready)
+   └──────────┘  (reclaim / re-create can return a card to ready)
+```
+
+- **ready** — eligible to be claimed once every `depends_on` card is `done`.
+- **claimed** — a worker holds it; `claim_owner` + `claimed_at` set.
+- **blocked** — explicitly parked; never auto-claimed.
+- **done** — completed; satisfies dependents.
+
+## Atomic claim (`FOR UPDATE SKIP LOCKED`) + TTL
+
+`claim` is atomic. Inside a single transaction it locks candidate `ready` rows
+with `SELECT ... FOR UPDATE SKIP LOCKED` (via the drizzle `sql` operator), picks
+the highest-priority deps-satisfied card, and flips it to `claimed`. Because a row
+already locked by a concurrent claimer is **skipped**, two claimers can **never**
+both win the same card — the loser falls through to the next candidate or gets
+`null`. (Proven by the concurrency tests in `packages/db/src/backlog.spec.ts`.)
+
+- **Deps gate:** a card is only claimable when every id in `depends_on` is `done`.
+- **TTL:** `claim --ttl <sec>` (default **900s**) records `claim_ttl_seconds`.
+- **reclaim:** releases claims whose `claimed_at + ttl` is in the past (expired)
+  back to `ready`, clearing the claim fields. `reclaim --id <id>` force-releases a
+  specific card regardless of expiry. This is how a crashed worker's card returns
+  to the pool.
+
+## CLI — `mosaic fleet backlog <sub> --json`
+
+All subcommands support `--json`.
+
+| Subcommand                                                                                    | Purpose                                                                                   |
+| --------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| `create --id --title [--body --phase --priority --depends-on --acceptance --idempotency-key]` | Create a card; `idempotency_key` dedups (repeat returns the existing card).               |
+| `list [--status --phase --ready-only]`                                                        | List cards. `--ready-only` = status `ready` AND all deps `done`.                          |
+| `claim --owner [--ttl <sec> --id <id>]`                                                       | Atomically claim the highest-priority ready card (or `--id`). Returns the card or `null`. |
+| `reclaim [--id <id>]`                                                                         | Release expired claims (or a specific card) back to `ready`.                              |
+| `link --from --to`                                                                            | Add a `depends_on` edge (`--from` depends on `--to`).                                     |
+| `stats`                                                                                       | Counts by status, oldest-ready age, expired-claim count.                                  |
+| `block --id`                                                                                  | Set a card to `blocked`.                                                                  |
+| `complete --id`                                                                               | Set a card to `done` (releases any claim).                                                |
+
+### Example
+
+```sh
+# Seed two cards, the second depends on the first.
+mosaic fleet backlog create --id A1 --title "schema" --priority 5
+mosaic fleet backlog create --id A2 --title "service" --depends-on A1 --priority 9
+
+# A2 is gated on A1, so claim returns A1 first.
+mosaic fleet backlog claim --owner worker-1 --ttl 600 --json
+
+# Finish A1; now A2 is ready.
+mosaic fleet backlog complete --id A1
+mosaic fleet backlog list --ready-only --json
+
+# Recover stalled work.
+mosaic fleet backlog reclaim --json
+```

docs/fleet/north-star.md

@@ -353,6 +353,25 @@ re-evaluate if isolation or write-volume demands it.
 - **Docs as projections:** `docs/TASKS.md` and `MISSION-MANIFEST.md` become generated exports of the DB, not hand-maintained.
 - **Sub-decision pending:** dedicated schema in existing PG instance (recommended) vs. dedicated PG instance. Revisit if isolation or write-volume demands it.
 
+## Decisions of record (2026-06-24, with Jason)
+
+- **Per-agent model switch (operator-configurable, NOT a global lock):** model selection is
+  **per-agent**, never a host-global pin. Claude sessions MUST NOT be locked to a single model in
+  `~/.claude/settings.json`; each agent chooses its model independently. The plumbing already exists —
+  roster `model_hint` → `MOSAIC_AGENT_MODEL` → `start-agent-session.sh` appends `--model <hint>` to that
+  agent's harness (claude or pi); settable today via `mosaic fleet add|edit <agent> --model <hint>`.
+  **North-star target:** surface this as a **per-agent model switch in the webUI** (with CLI/TUI parity
+  per MVP-X1) — read the roster, expose a per-agent model dropdown, write `model_hint` back, and restart
+  that one agent to apply. Unset = inherit the harness default. This **composes with** the budget
+  downgrade ladder (opus → sonnet → haiku, then Claude → Codex): the operator sets the per-agent model
+  _intent/ceiling_; budget pacing may downgrade within policy. Tracked as a Fleet `TASKS.md` entry under
+  the Phase-5 webUI surface.
+- **Orchestrator runtime (confirmed live):** the **orchestrator and enhancer run Claude Opus 4.8 in the
+  Claude Code harness**; only workers (coder/reviewer) run pi/gpt-5.5. Consistent with the 2026-06-20
+  "Claude reserved for Claude Code only" decision (the orchestrator runs _in_ Claude Code, not an
+  alternate Claude harness). Pi/gpt-5.5 as the orchestrator is permitted **only if proven** at least as
+  satisfactory; absent that proof, the orchestrator stays on Claude Opus 4.8.
+
 ## Future enhancements (north-star, post-MVP — not on the MVP track)
 
 - **Mosaic Claude Discord Plugin** — a first-party Mosaic Discord connector that properly

docs/guides/admin-guide.md

@@ -293,13 +293,24 @@ Each OIDC provider requires its client ID, client secret, and issuer URL togethe
 
 ### Plugins
 
-| Variable               | Description                                                                |
+| Variable                      | Description                                                                                                                               |
-| ---------------------- | -------------------------------------------------------------------------- |
+| ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
-| `DISCORD_BOT_TOKEN`    | Discord bot token (enables Discord plugin)                                 |
+| `DISCORD_BOT_TOKEN`           | Discord bot token (enables Discord plugin)                                                                                                |
-| `DISCORD_GUILD_ID`     | Discord guild/server ID                                                    |
+| `DISCORD_SERVICE_TOKEN`       | Required high-entropy service credential used to authenticate and sign Discord ingress; inject through the approved secret mechanism only |
-| `DISCORD_GATEWAY_URL`  | Gateway URL for Discord plugin to call (default: `http://localhost:14242`) |
+| `DISCORD_SERVICE_USER_ID`     | Required Mosaic service-principal user ID that owns persisted Discord conversations; the original Discord user ID remains audit metadata  |
-| `TELEGRAM_BOT_TOKEN`   | Telegram bot token (enables Telegram plugin)                               |
+| `DISCORD_GUILD_ID`            | Discord guild/server ID                                                                                                                   |
-| `TELEGRAM_GATEWAY_URL` | Gateway URL for Telegram plugin to call                                    |
+| `DISCORD_GATEWAY_URL`         | Gateway URL for Discord plugin to call (default: `http://localhost:14242`)                                                                |
+| `DISCORD_ALLOWED_GUILD_IDS`   | Required comma-separated Discord guild snowflake allowlist; default-deny                                                                  |
+| `DISCORD_ALLOWED_CHANNEL_IDS` | Required comma-separated Discord channel snowflake allowlist; default-deny                                                                |
+| `DISCORD_ALLOWED_USER_IDS`    | Required comma-separated Discord user snowflake allowlist; default-deny                                                                   |
+| `TELEGRAM_BOT_TOKEN`          | Telegram bot token (enables Telegram plugin)                                                                                              |
+| `TELEGRAM_GATEWAY_URL`        | Gateway URL for Telegram plugin to call                                                                                                   |
+
+### Discord ingress security
+
+When `DISCORD_BOT_TOKEN` is configured, `DISCORD_SERVICE_TOKEN`, `DISCORD_SERVICE_USER_ID`, and all three Discord allowlists are required. Gateway startup fails rather than enabling a broad or unauthenticated remote-control surface. The service user ID identifies a provisioned Mosaic service principal for persistence; the original Discord user ID is retained in ingress audit metadata. The service token is a secret supplied by the approved runtime secret mechanism and is never committed or logged.
+
+Inbound Discord messages must originate from an allowed guild, channel, and user, mention the bot, and carry a signed envelope containing the native Discord message ID and a generated correlation ID. The gateway validates the service identity, envelope signature, and allowlists again before dispatching. Replayed Discord message IDs are rejected during the bounded ingress replay window. Durable inbox/idempotency retention is introduced with Tess durable state.
 
 ### Observability
 

docs/scratchpads/462-fed-m3-04-scope-service.md

@@ -0,0 +1,60 @@
+# Scratchpad — FED-M3-04 Scope Service
+
+## Objective
+
+Implement `apps/gateway/src/federation/server/scope.service.ts` for the M3 inbound federation scope-enforcement pipeline.
+
+## Scope / Constraints
+
+- Task: FED-M3-04, issue #462.
+- Branch: `feat/federation-m3-scope-service` from `origin/main` @ 0.0.48.
+- Pure service: no direct DB access; native RBAC/data access is injected per evaluation call.
+- Reuse `parseFederationScope` from M2-03.
+- Workers do not edit `docs/federation/TASKS.md` per repo AGENTS.md.
+
+## Acceptance Criteria
+
+1. Resource allowlist and `excluded_resources` enforced.
+2. Native RBAC evaluated as `subjectUserId` through an injected evaluator.
+3. Scope filter intersection supports `include_teams` and `include_personal` without widening native RBAC.
+4. `max_rows_per_query` caps requested limits.
+5. Service returns `{ allowed: true, filter }` or a structured deny reason usable by M4 audit.
+6. Unit tests cover every deny path.
+
+## Plan
+
+1. Inspect existing federation scope/schema/auth guard contracts.
+2. Add pure `FederationScopeService` plus typed result/filter/deny interfaces.
+3. Add focused unit tests for happy paths, filter intersection, row cap, and deny paths.
+4. Export/register service for future verb controllers.
+5. Run situational tests, baseline gates, code review, then PR.
+
+## Budget
+
+- Provided model tier: sonnet.
+- Estimate from task row: 10K tokens.
+- Working cap assumption: keep implementation focused to FED-M3-04 surfaces only.
+
+## Progress
+
+- Intake complete; dirty base worktree avoided by creating isolated worktree at `/home/jarvis/src/mosaic-mono-v1-fed-m3-04`.
+- Project PRD and federation task spec reviewed.
+- Added `FederationScopeService` with structured allow/deny result types and injected native RBAC evaluator contract.
+- Added unit coverage for happy path, row cap, filter intersection, and every deny path.
+- Exported/registered the service for upcoming M3 verb controllers.
+
+## Verification Evidence
+
+- `pnpm --filter @mosaicstack/gateway test -- src/federation/server/__tests__/scope.service.spec.ts` — pass (10 tests before review update; 11 tests after adding include_personal no-leak coverage).
+- `pnpm build` — pass (23 successful tasks).
+- `pnpm typecheck` — pass (41 successful tasks; re-run after review update).
+- `pnpm lint` — pass (23 successful tasks; re-run after review update).
+- `pnpm format:check` — pass (re-run after review update).
+- `pnpm test` — pass after starting local `postgres`/`valkey` and running `pnpm --filter @mosaicstack/db db:push` for the DB-backed cross-user isolation suite (41 successful tasks; gateway 477 passed / 11 skipped).
+- Code review: `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings.
+- Security review: `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — risk none, 0 findings.
+
+## Risks / Blockers
+
+- Issue #462 is already closed in provider output; likely milestone tracking mismatch. Will still reference #462 in PR body unless orchestrator redirects.
+- Local full-test setup required `docker compose up -d postgres valkey` + `db:push`; containers were stopped with `docker compose down` after verification.

docs/scratchpads/561-python-is-python3.md

@@ -0,0 +1,33 @@
+# Issue #561 — Bare python on agent hosts
+
+## Objective
+
+Make the durable bootstrap/provisioning guidance ensure agent hosts provide a bare `python` command that resolves to Python 3.
+
+## Scope
+
+- Add Debian/Ubuntu `python-is-python3` to agent-host prerequisites in bootstrap docs.
+- Check for actual OS package provisioning scripts and update only if an existing agent-host package install path exists.
+- Do not touch live host state.
+- Do not update `docs/TASKS.md`; repo guidance says workers read it but never modify it.
+
+## Recon
+
+- Issue #561 confirms repeated `python: command not found` failures from fleet agents that emit `python foo.py`.
+- `guides/BOOTSTRAP.md` and `packages/mosaic/framework/guides/BOOTSTRAP.md` are the source and packaged framework copies of the bootstrap guide.
+- Targeted repo sweep found no agent-host Debian package provisioning script. Existing `apt-get install` hits are CI/test helper paths or unrelated deployment docs.
+
+## Plan
+
+1. Add a host prerequisite section to both bootstrap guide copies.
+2. Include `python-is-python3` in the Debian/Ubuntu package list with an issue comment.
+3. Note the non-Debian equivalent as a `/usr/bin/python -> python3` symlink.
+4. Validate markdown/diff, run shell syntax checks where applicable, run required review, commit, queue guard, and push.
+
+## Validation Log
+
+- `rg` recon: no existing agent-host Debian package provisioning script; only CI/test helper `apt-get install` paths and unrelated deployment docs.
+- `git diff --check`: passed.
+- `bash -n packages/mosaic/framework/install.sh tools/install.sh packages/mosaic/framework/tools/bootstrap/init-project.sh packages/mosaic/framework/tools/_scripts/mosaic-bootstrap-repo`: passed. No touched shell scripts.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted`: approved, 0 findings.
+- `pnpm format:check`: initially blocked because `node_modules` was absent and `prettier` was unavailable; `pnpm install --frozen-lockfile` initially hit an invalid `/root` pnpm store path. Reran install with `--store-dir /home/hermes/agent-work/.pnpm-store`, then `pnpm format:check` passed.

docs/scratchpads/672-fleet-personas-timeout.md

@@ -0,0 +1,25 @@
+# Scratchpad — fleet-personas spec timeout
+
+## Objective
+
+Raise the `@mosaicstack/mosaic` Vitest timeout to 30s at config level so filesystem-backed fleet drift-guard specs (`fleet-personas`, `fleet-profiles`, and siblings) stop false-reding under contended CI.
+
+## Plan
+
+1. Move timeout policy into `packages/mosaic/vitest.config.ts` with `testTimeout: 30_000`.
+2. Remove the narrower `fleet-personas.spec.ts` local override so PR #677 fixes the suite class, not one file.
+3. Run targeted fleet specs plus typecheck/lint/format gates.
+4. Commit, queue guard, push, PR update.
+
+## Evidence
+
+- `pnpm --filter @mosaicstack/mosaic test -- src/commands/fleet-personas.spec.ts` — pass (8 tests; initial narrow fix).
+- `pnpm typecheck` — pass (41 tasks; initial narrow fix).
+- `pnpm lint` — pass (23 tasks; initial narrow fix).
+- `pnpm format:check` — pass after formatting this scratchpad (initial narrow fix).
+- Package-wide timeout follow-up:
+  - `pnpm --filter @mosaicstack/mosaic test -- src/commands/fleet-personas.spec.ts src/commands/fleet-profiles.spec.ts` — pass (24 tests).
+  - `pnpm --filter @mosaicstack/mosaic test` — pass (44 files / 618 tests).
+  - `pnpm typecheck` — pass (41 tasks).
+  - `pnpm lint` — pass (23 tasks).
+  - `pnpm format:check` — pass.

docs/scratchpads/703-wrapper-interactive-auth.md

@@ -0,0 +1,49 @@
+# #703 Git Wrapper Interactive and Auth Resilience
+
+## Objective
+
+Restore the deployed Git wrapper contract: issue-create supports interactive invocation and Gitea mutation behavior tolerates a stale Tea authenticated user by validating current identity and using the existing host-scoped API fallback.
+
+## Scope
+
+- `packages/mosaic/framework/tools/git/issue-create.sh`
+- `packages/mosaic/framework/tools/git/detect-platform.sh`
+- Git wrapper regression harnesses
+- This scratchpad
+
+## Requirements / acceptance evidence
+
+1. `issue-create -i` and `--interactive` prompt for missing issue fields without exposing credentials.
+2. Explicit command-line fields retain precedence and do not trigger prompt input.
+3. Gitea wrapper resolves the current user dynamically from the target host and does not rely on the saved Tea user identity.
+4. A Tea `GetUserByName` failure falls back to authenticated API creation.
+5. Existing body-safety, login-resolution, issue-create, and pr-create paths remain green.
+6. Source framework is re-seeded to deployed `~/.config/mosaic`, then deployed wrappers are verified end to end.
+
+## Plan
+
+1. Add failing shell regression harness for interactive input and stale Tea user fallback.
+2. Implement minimal helper and parser changes.
+3. Run wrapper harnesses, syntax checks, and repository baseline checks.
+4. Re-seed deployed framework and run live wrapper verification.
+5. Commit, queue guard, push, open PR, and stop for independent review.
+
+## Progress
+
+- Issue #703 filed before code; issue comment records #536 root cause and stale-login trigger.
+- Deployed wrapper `issue-create.sh -i` reproduced: `Unknown option: -i` (exit 1).
+- Live Tea mutation did not reproduce `GetUserByName` on this host because the current mosaicstack Tea login is valid. The test harness models the reported stale authenticated-user condition.
+- Implemented `-i` / `--interactive` prompt collection and a dynamic Tea `/user` validation. A stale Tea identity now selects the existing host-scoped Gitea API fallback before mutation for both issue and PR creation.
+- Re-seeded the framework with `MOSAIC_INSTALL_MODE=keep MOSAIC_SYNC_ONLY=1 bash packages/mosaic/framework/install.sh`. Installed and source wrapper SHA-256 values matched.
+- Live deployed verification: interactive issue-create opened then closed #704; installed dynamic identity resolved `jason.woltje`.
+
+## Verification
+
+- PASS: `packages/mosaic/framework/tools/git/test-issue-create-interactive-auth.sh`
+- PASS: `packages/mosaic/framework/tools/git/test-issue-create-body-safety.sh`
+- PASS: `packages/mosaic/framework/tools/git/test-gitea-login-resolution.sh`
+- PASS: `packages/mosaic/framework/tools/git/test-pr-metadata-gitea.sh`
+- PASS: `packages/mosaic/framework/tools/git/test-pr-merge-gitea-empty-uid.sh`
+- PASS: `bash packages/mosaic/framework/tools/git/test-lane-brief-pr-linkage.sh`
+- PASS: `bash -n packages/mosaic/framework/tools/git/*.sh`
+- PASS: Prettier check for this scratchpad

docs/scratchpads/FED-M3-05-list-verb.md

@@ -0,0 +1,52 @@
+# FED-M3-05 — Federation List Verb Scratchpad
+
+## Objective
+
+Implement `POST /api/federation/v1/list/:resource`.
+
+## Scope
+
+- Wire `FederationAuthGuard` → `FederationScopeService` → read-only list query layer.
+- Apply `max_rows_per_query` row cap and return pagination metadata when truncated.
+- Tag returned rows with `_source: "local"`.
+- Keep audit writes deferred to M4.
+- No request/response body persistence.
+
+## Base / branch
+
+- Branch: `feat/federation-m3-verb-list`
+- Base: `main` after M3-04 scope service merged via PR #672 (`c739256a`).
+
+## Implementation notes
+
+- Added `ListController` under `apps/gateway/src/federation/server/verbs/`.
+- Added `FederationListQueryService` as the read-only query layer and native RBAC evaluator.
+- Query resources supported in M3 list path:
+  - `tasks`: project/mission scoped tasks visible through personal/team project access.
+  - `notes`: non-empty `mission_tasks.notes` rows visible through personal/team mission access.
+  - `memory`: user-owned `insights` and `preferences` rows.
+  - `credentials` / `api_keys`: denied by native RBAC in M3 even if present in scope; sensitive-resource implementation is not part of FED-M3-05.
+- Cursor pagination uses an opaque base64url keyset cursor over `(createdAt, id)`; DB reads fetch at most `limit + 1` rows per resource query.
+- Reviewer isolation fix: `mission_tasks.notes` rows are always constrained by `missionTasks.userId = subjectUserId` and accessible mission IDs; team scope narrows missions but never widens to other users' mission task notes.
+- Follow-up review fix: memory listing now uses deterministic table-block pagination (`insights` first, then `preferences`) with cursor source metadata, so one table's cursor is never applied to the other.
+- Follow-up hardening: missing auth-guard context returns a structured federation `unauthorized` envelope; unsupported resources and non-encodable truncated cursors throw instead of silently crashing/truncating.
+
+## Tests
+
+- `pnpm --filter @mosaicstack/gateway test -- list.controller.spec.ts list-query.service.spec.ts` — PASS (16 tests, including PGlite regression coverage for team-scoped notes isolation, unauthorized mission notes exclusion, `includePersonal: false`, deterministic memory pagination, missing context envelope, unsupported resource, and cursor encode failure).
+- `pnpm --filter @mosaicstack/gateway typecheck` — PASS.
+- `pnpm --filter @mosaicstack/gateway lint` — PASS.
+- `pnpm format:check` — PASS.
+- `pnpm typecheck` — PASS (41/41 turbo tasks).
+- `pnpm lint` — PASS (23/23 turbo tasks).
+- `pnpm --filter @mosaicstack/gateway test` — FAIL in pre-existing/live-DB integration suite: `apps/gateway/src/__tests__/cross-user-isolation.test.ts` cleanup cannot connect to local PostgreSQL on `localhost:5433`. New list tests pass; failure is outside FED-M3-05.
+
+## Review evidence
+
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — PASS after follow-up remediation; approve, no findings.
+- `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — PASS after follow-up remediation; risk level none, no findings.
+- Security-review note: read-path audit logging remains intentionally deferred to M4 per orchestrator clarification and FED-M3-05 scope.
+
+## Risks / follow-up
+
+- Read-path audit logging remains intentionally deferred to M4.

docs/scratchpads/FED-M3-07-capabilities.md

@@ -0,0 +1,65 @@
+# FED-M3-07 — Capabilities Verb Scratchpad
+
+## Objective
+
+Implement `GET /api/federation/v1/capabilities` in `apps/gateway/src/federation/server/verbs/capabilities.controller.ts`.
+
+## Scope
+
+- Add read-only capabilities controller under federation server verbs.
+- Use `FederationAuthGuard` only; active grant is sufficient and no native RBAC/scope-service eval runs.
+- Response shape: `{ resources, excluded_resources, max_rows_per_query, supported_verbs }` derived from grant scope.
+- Register controller in `FederationModule`.
+- Unit-test happy path, defaults, no-context guard seam, and invalid scope handling.
+
+## Constraints / assumptions
+
+- Issue: #462.
+- Branch: `feat/federation-m3-verb-capabilities` from `origin/main` (`3eeed04e`).
+- Depends on M3-03 auth guard; guard attaches `request.federationContext.scope` after active-grant validation.
+- ASSUMPTION: `supported_verbs` is the M3 verb set from `@mosaicstack/types` (`list`, `get`, `capabilities`).
+- ASSUMPTION: `filters`/`rate_limit` are intentionally omitted for FED-M3-07 because the card’s response shape lists only the four required fields.
+- Budget: no explicit hard cap from orchestrator; working cap ~4K-8K tokens for card implementation + tests + PR cycle.
+
+## Plan
+
+1. Write controller unit tests first.
+2. Implement controller and module registration.
+3. Run scoped tests + typecheck/lint/format.
+4. Run Codex code/security review and remediate.
+5. Commit, queue guard, push, PR via wrapper.
+
+## Progress
+
+- 2026-06-24: Intake complete; fresh worktree created from origin/main.
+- 2026-06-24: Added `CapabilitiesController`, registered it in `FederationModule`, and added 5 unit tests.
+- 2026-06-24: Code/security reviews passed with no findings.
+
+## Tests run
+
+- `pnpm --filter @mosaicstack/gateway test -- capabilities.controller.spec.ts` — PASS (5 tests).
+- `pnpm --filter @mosaicstack/gateway typecheck` — PASS.
+- `pnpm --filter @mosaicstack/gateway lint` — PASS.
+- `pnpm format:check` — PASS.
+- `pnpm typecheck` — PASS (41/41 turbo tasks).
+- `pnpm lint` — PASS (23/23 turbo tasks).
+- `pnpm test` — FAIL in pre-existing/live-DB integration suite: `apps/gateway/src/__tests__/cross-user-isolation.test.ts` cleanup hit PostgreSQL connection/schema state for the `messages` table. Changed capabilities tests passed; failure is outside FED-M3-07 surface. No `fleet-personas.spec` flake encountered.
+
+## Review evidence
+
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — PASS/approve, no findings.
+- `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — PASS, risk level none, no findings.
+
+## Risks / blockers
+
+- Full repo `pnpm test` may hit known `fleet-personas.spec` flake per orchestrator; ignore that specific flake if encountered.
+- Previous card saw local DB schema issue in `cross-user-isolation.test.ts`; scoped capabilities tests should be authoritative for this surface.
+
+## Acceptance evidence mapping
+
+| Acceptance criterion                                                       | Evidence                                                                                                                   |
+| -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
+| GET `/api/federation/v1/capabilities` exists                               | Route metadata test in `capabilities.controller.spec.ts`; scoped test PASS                                                 |
+| Uses active-grant auth guard and no RBAC eval                              | Guard metadata test confirms only `FederationAuthGuard`; controller has no service injections/RBAC calls; scoped test PASS |
+| Response enumerates resources/excluded/max rows/supported verbs from scope | Happy-path/default scope tests + response schema parse; scoped test PASS                                                   |
+| Read-only/no persistence side effects                                      | Controller only parses request `federationContext.scope` and returns a DTO; no DB/service dependency; code review PASS     |

docs/scratchpads/FED-M3-09-query-source.md

@@ -0,0 +1,67 @@
+# FED-M3-09 — Query Source Service Scratchpad
+
+## Objective
+
+Implement `apps/gateway/src/federation/client/query-source.service.ts` for `source: "local" | "federated:<host>" | "all"` routing.
+
+## Scope
+
+- Add QuerySourceService in gateway federation client layer.
+- Unit-test local-only, single federated peer, all-source fan-out/merge, and per-peer partial failures.
+- Keep `docs/federation/TASKS.md` read-only per project agent guidance.
+
+## Constraints / assumptions
+
+- Issue: #462.
+- Branch: `feat/federation-m3-query-source` from `origin/main` (`e0e7be70`).
+- ASSUMPTION: `federated:<host>` should match active outbound peers by `commonName` first and by `endpointUrl` host/hostname as compatibility fallback; source tags use `peer.commonName` per `@mosaicstack/types` source-tag docs.
+- ASSUMPTION: QuerySourceService provides list/fan-out behavior; get/source routing can be layered later because card acceptance says merge rows.
+- ASSUMPTION: `source: "all"` cannot safely return a single continuation cursor for multiple sub-sources; any subquery cursor marks the merged response `_partial: true` + `_truncated: true` while omitting `nextCursor`.
+- Budget: no explicit hard cap from orchestrator; working cap ~8K-12K tokens for card 1 implementation + tests + PR cycle.
+- OpenBrain unavailable: credential loader failed with missing `/home/jarvis/.config/mosaic/credentials.json`; not blocking code delivery.
+
+## Plan
+
+1. Review federation client/types/db patterns.
+2. Write unit tests for source behavior.
+3. Implement QuerySourceService and export/register it in FederationModule.
+4. Run scoped tests, typecheck, lint, format.
+5. Run codex uncommitted review and remediate.
+6. Commit, queue guard, push, PR via wrapper.
+
+## Progress
+
+- 2026-06-24: Intake complete; using isolated worktree to avoid dirty orchestrator files in original checkout.
+- 2026-06-24: Added QuerySourceService, module export, barrel export, and 7 unit tests.
+- 2026-06-24: First Codex review found pagination and port-host matching issues; both remediated with tests.
+
+## Tests run
+
+- `pnpm --filter @mosaicstack/gateway test -- query-source.service.spec.ts` — PASS (7 tests).
+- `pnpm --filter @mosaicstack/gateway typecheck` — PASS.
+- `pnpm --filter @mosaicstack/gateway lint` — PASS.
+- `pnpm format:check` — PASS.
+- `pnpm typecheck` — PASS (41/41 turbo tasks).
+- `pnpm lint` — PASS (23/23 turbo tasks).
+- `pnpm test` — FAIL in pre-existing/live-DB integration suite: `apps/gateway/src/__tests__/cross-user-isolation.test.ts` cleanup hit `relation "messages" does not exist` against local PostgreSQL. Changed QuerySource unit tests passed; failure is outside FED-M3-09 surface and appears tied to local DB schema state.
+
+## Review evidence
+
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — first pass request-changes, 2 should-fix findings (all-source cursor handling; endpoint port host matching).
+- Remediation: `_partial` + `_truncated` when any all-source subquery has `nextCursor`; endpoint match accepts URL `host` and `hostname`; added tests for both.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — PASS/approve, no findings.
+- `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — PASS, risk level none, no findings.
+
+## Risks / blockers
+
+- Federation query layer is not yet wired; service API needs to be stable and easy to compose.
+- Must avoid hard-failing `source: all` on remote peer failures.
+
+## Acceptance evidence mapping
+
+| Acceptance criterion                                                            | Evidence                                                                          |
+| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- |
+| local source returns local rows tagged `_source: local`                         | `query-source.service.spec.ts` local test; scoped test PASS                       |
+| `federated:<host>` queries selected peer and tags rows with peer source         | `query-source.service.spec.ts` commonName/endpoint-host tests; scoped test PASS   |
+| `all` fans out local + active outbound peers in parallel and merges tagged rows | `query-source.service.spec.ts` all-source call-order/merge test; scoped test PASS |
+| per-peer failure on `all` returns `_partial: true`, not throw                   | `query-source.service.spec.ts` peer failure test; scoped test PASS                |

docs/scratchpads/h1-heartbeat-readiness.md

@@ -0,0 +1,66 @@
+# H1 — heartbeat readiness detection
+
+## Objective
+
+Add runtime-agnostic readiness classification to `mosaic fleet ps` so an agent can be reported as working/idle/stuck/stale/dead/unknown instead of treating pane liveness as progress.
+
+## Scope
+
+- `packages/mosaic/src/commands/fleet.ts`
+  - exported readiness state/types/default thresholds/helpers/classifier
+  - `AgentPsRow.readiness` additive JSON field
+  - table HB column and IDLE/STUCK flags
+- `packages/mosaic/src/commands/fleet.spec.ts`
+  - pure classifier branch/boundary coverage
+  - threshold helper coverage
+  - legitimate render/JSON assertion updates for new HB text
+
+## Acceptance Criteria
+
+- Branches covered: dead, unknown, stale, busy working, null-idle working, stuck boundary, idle boundary, working below idle.
+- Threshold env helpers default to 300s/900s and honor positive integer env values.
+- `fleet ps` rows populate `readiness` for roster and unmanaged socket sessions.
+- Table HB text becomes `<age>s/<readiness>` when heartbeat age exists; remains `unknown` when absent.
+- Flags include `IDLE`/`STUCK` for matching readiness.
+- Local gates green: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, fleet vitest.
+- Pre-push queue guard passes; PR opened off `origin/main`; no merge by worker.
+
+## Constraints / Assumptions
+
+- Source branch: `origin/main` @ `e3adc6a`.
+- No scope creep beyond readiness detection.
+- `docs/TASKS.md` and `docs/fleet/TASKS.md` are orchestrator-owned; worker will not modify them.
+- PRD alignment source: `docs/fleet/PRD.md` Phase 2 observability; this is a refinement of heartbeat observability, preserving existing unknown/stale behavior.
+
+## Plan
+
+1. Install dependencies with requested PNPM environment.
+2. Add readiness types/helpers/classifier near heartbeat constants.
+3. Add `readiness` to `AgentPsRow` and populate both row paths.
+4. Update table render and flags.
+5. Add unit tests and update affected ps render/JSON assertions.
+6. Run build precheck + required gates.
+7. Run automated independent review, remediate findings.
+8. Queue guard, push, open PR.
+
+## Progress
+
+- 2026-06-24: Branch created from `origin/main` @ `e3adc6a`.
+- 2026-06-24: Implemented readiness thresholds/classifier, JSON row field, HB column label, and IDLE/STUCK flags.
+- 2026-06-24: Added classifier branch/boundary tests, threshold helper tests, JSON shape assertions, and readiness table rendering assertions.
+
+## Verification Evidence
+
+- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
+- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
+- `pnpm typecheck` — pass, 41/41 tasks successful.
+- `pnpm lint` — pass, 23/23 tasks successful.
+- `pnpm format:check` — pass, all matched files use Prettier style.
+- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 171 tests.
+- `pnpm --filter @mosaicstack/mosaic test` — pass, 39 files / 547 tests; `fleet.spec.ts` 171 tests.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
+
+## Risks / Blockers
+
+- No current blocker.
+- Review tool could not inspect repo files directly due sandbox wrapper limitation, but it reviewed the supplied diff and approved with no findings.

docs/scratchpads/h1b-pane-idle-signal.md

@@ -0,0 +1,53 @@
+# H1b — tmux pane idle signal wiring
+
+## Objective
+
+Feed `classifyReadiness()` a real idle signal on tmux 3.4 by deriving `idleSeconds` from the first available tmux timestamp source: pane activity, then window activity, then session activity.
+
+## Scope
+
+- `packages/mosaic/src/commands/fleet.ts`
+  - Extend `buildTmuxListPanesCommand()` format to include `#{window_activity}` and `#{session_activity}` after the existing fields.
+  - Update `parseTmuxListPanes()` to choose the first non-empty finite positive timestamp and clamp future idle values to 0.
+- `packages/mosaic/src/commands/fleet.spec.ts`
+  - Cover pane/window/session activity parsing behavior, empty-field index alignment, null idle, future clamping, math correctness, and exact tmux format.
+
+## Out of Scope
+
+- No changes to `classifyReadiness()`, thresholds, `AgentPsRow`, or `fleet ps` rendering.
+- No merge by worker; orchestrator routes review/merge.
+- Workers do not modify `docs/TASKS.md`.
+
+## PRD Alignment
+
+Aligned with `docs/fleet/PRD.md` FR-1 and acceptance criteria for truthful `mosaic fleet ps` pane/pid/idle observability.
+
+## Plan
+
+1. Sync branch from latest `origin/main` and install dependencies with required pnpm env.
+2. Add/confirm reproducer tests for tmux 3.4 empty `pane_activity` and new fallback behavior.
+3. Implement the focused parser/format change only.
+4. Run required build, baseline gates, fleet vitest, and independent review.
+5. Run pre-push queue guard, push branch, and open PR to `main` with Mosaic wrapper.
+
+## Progress
+
+- 2026-06-24: Branch `fix/fleet-pane-idle-activity` created from `origin/main` @ `ec8dd7c` after fetching.
+- 2026-06-24: Session-start generated local `.mosaic/orchestrator/*` changes on the previous release branch; stashed as `coder1 session-start state before H1b` to keep this branch clean.
+- 2026-06-24: Added TDD coverage for the tmux 3.4 production case (`pane_activity` empty, `window_activity` populated), exact new list-panes format, null/future/multiple-source behavior.
+- 2026-06-24: Implemented parser fallback without changing readiness classifier thresholds or render shape.
+
+## Verification Evidence
+
+- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
+- Reproducer before implementation: `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — failed as expected (old format, no fallback, negative future idle).
+- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
+- `pnpm typecheck` — pass, 41/41 tasks successful.
+- `pnpm lint` — pass, 23/23 tasks successful.
+- `pnpm format:check` — pass, all matched files use Prettier style.
+- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 176 tests.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
+
+## Risks / Blockers
+
+- No current blocker.

docs/scratchpads/h2-readiness-available.md

@@ -0,0 +1,70 @@
+# H2 — readiness semantics: available, not stuck
+
+## Objective
+
+Correct fleet readiness semantics so a healthy long-idle agent is reported as `available` (good/assignable) instead of `stuck` (fault). Reserve `stuck` in the type/JSON value space for future positive block evidence.
+
+## Scope
+
+- `packages/mosaic/src/commands/fleet.ts`
+  - replace `idle` readiness state with `available`
+  - keep `stuck` in the union but stop emitting it from idle-only heuristics
+  - remove stuck threshold helper/env handling
+  - remove IDLE/STUCK alarm flags from table rendering
+- `packages/mosaic/src/commands/fleet.spec.ts`
+  - update classifier branch/boundary tests
+  - assert very long idle maps to `available`, not `stuck`
+  - update table/JSON assertions for available with no alarm flags
+  - remove stuck threshold helper tests
+
+## Acceptance Criteria
+
+- `classifyReadiness()` remains pure/total/never-throw and maps:
+  - dead/stale/unknown unchanged
+  - busy/null/undefined/non-finite idle to `working`
+  - idle >= activity threshold to `available`
+  - idle < activity threshold to `working`
+- No idle-derived path emits `stuck`.
+- `MOSAIC_HEARTBEAT_IDLE_THRESHOLD` remains backward compatible as the working→available activity threshold.
+- `MOSAIC_HEARTBEAT_STUCK_THRESHOLD` and helper/default are removed.
+- `fleet ps` keeps the idle-seconds column header `IDLE`, renders `available` in HB label, and does not add IDLE/STUCK warning flags.
+- Local gates green: build precheck, typecheck, lint, format:check, fleet vitest.
+- PR opened against `main`; no merge by worker.
+
+## Constraints / Assumptions
+
+- Source branch: `origin/main` @ `1020cfa`.
+- `docs/TASKS.md` is orchestrator-owned; worker will not modify it.
+- Documentation impact is captured in this scratchpad and PR description; no user/admin guide behavior beyond CLI readiness label semantics.
+
+## Plan
+
+1. Install dependencies with requested PNPM environment.
+2. Inspect current H1/H1b readiness implementation and tests.
+3. Update classifier types/helpers/rendering.
+4. Update focused tests.
+5. Run build precheck + required gates.
+6. Run automated code review, remediate any findings.
+7. Queue guard, push, open PR.
+
+## Progress
+
+- 2026-06-24: Branch created from `origin/main` @ `1020cfa`.
+- 2026-06-24: Replaced idle-derived `idle`/`stuck` outputs with `available`; retained `stuck` in type union for future positive block evidence.
+- 2026-06-24: Removed stuck threshold env/helper plumbing and IDLE/STUCK alarm flags.
+- 2026-06-24: Updated classifier and table-render tests for available semantics.
+
+## Verification Evidence
+
+- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
+- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
+- `pnpm typecheck` — pass, 41/41 tasks successful.
+- `pnpm lint` — pass, 23/23 tasks successful.
+- `pnpm format:check` — pass, all matched files use Prettier style.
+- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 177 tests.
+- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
+
+## Risks / Blockers
+
+- No current blocker.
+- Review tool could not inspect repo files directly due sandbox wrapper limitation, but it reviewed the supplied diff and approved with no findings.

docs/scratchpads/tess-20260712.md

@@ -0,0 +1,58 @@
+# Scratchpad — Tess Interaction Agent
+
+## 2026-07-12 — Mission intake
+
+**Objective:** Build a Pi-native GPT-5.6 Sol high-reasoning Mosaic interaction agent, named Tess, as Jason's primary Discord/CLI access point for Mosaic fleet and transitional Hermes capabilities. Tess complements Mos and must not become a competing orchestrator.
+
+**Issue:** #706
+
+**Budget:** No explicit cap provided. Original working estimate was 290K implementation/review tokens. That estimate is superseded after six security prerequisite tasks were added; revised arithmetic total is pending because the calculation tool was blocked by runtime consent. Run at most two workers; prefer one implementation lane plus one independent review/discovery lane. Re-estimate after planning approval and each milestone.
+
+**Evidence gathered:**
+- Mosaic already provides Pi lifecycle hooks, fleet/tmux sessions, Matrix connector/controller pieces, typed chat events, Discord/Telegram channel plugins, and command/plugin registries.
+- Current `IProviderAdapter` is an LLM model/completion abstraction, not an external agent/session provider.
+- Required new seam is `AgentRuntimeProvider`: sessions, stream, message, terminate, hierarchy, attach, health, capabilities.
+- Recurring cross-runtime needs: unified memory/retrieval, Discord routing/approvals, agent state/inbox/compaction recovery, runtime bootstrap, fleet/incident controls, and GitOps workflow.
+- Project truth must remain in canonical project/Mosaic stores; semantic memory is retrieval/mirror.
+
+**Decisions:**
+1. Name: Tess (tessera). Stable machine key `tess`; display name configurable.
+2. Mos owns orchestration; Tess delegates Mos-owned work through an explicit coordination contract.
+3. Gateway owns ingress/auth/routing; Discord and CLI remain thin clients.
+4. tmux/fleet ships first behind an adapter; Matrix/native Mosaic is the forward transport.
+5. Hermes integration is transitional and capability-negotiated; unsupported operations fail closed.
+6. No unrestricted Discord shell. Privileged/destructive/customer-visible actions require authorization and approval.
+
+**Plan:**
+1. Land requirements/architecture/task graph.
+2. Deliver runtime contracts and security model.
+3. Deliver durable Pi service/state.
+4. Deliver Discord and CLI.
+5. Deliver fleet/Mos/Hermes/memory/tool plugins.
+6. Deliver Matrix/native transport, migration matrix, recovery, docs, and qualification.
+
+**Progress:** Issue #706 created. PRD/manifest/tasks initialized on clean branch `feat/tess-interaction-agent` from `origin/main`.
+
+**Risks:** 14 GB root filesystem headroom; active fleet lanes; broad migration scope; Discord privilege boundary; possible duplicate orchestration authority.
+
+## 2026-07-12 — Independent planning and threat review
+
+**Verdict received:** BLOCK TESS-PLAN-001. Coding remains stopped.
+
+**Blocking findings:** formal threat model absent; verification matrix absent; migration inventory implied but absent; non-existent task paths; AC-TESS-03 lacked a crisp test. Security review also identified command scope bypass, cross-tenant session attachment, MCP actor impersonation, unsafe Discord service ingress, pre-persistence/egress secret leakage, non-durable replay, and globally scoped GC.
+
+**Remediation applied:**
+- Added `docs/tess/ARCHITECTURE.md`.
+- Added `docs/tess/THREAT-MODEL.md` with TM-01..12.
+- Added `docs/tess/VERIFICATION-MATRIX.md` mapping AC-TESS-01..11.
+- Added `docs/tess/MIGRATION-INVENTORY.md`.
+- Added hard requirements TESS-SEC-002..009.
+- Added six prerequisite security tasks before provider/ingress implementation.
+- Corrected task paths to existing package surfaces.
+- Added explicit GPT-5.6 Sol/high/tool-policy status verification for AC-TESS-03.
+
+**Re-review 1:** BLOCK only on composite `repo` values that looked like nonexistent paths. Remediated by declaring comma-separated roots and validating every root.
+
+**Final focused review:** PASS. Deterministic audit validated all task repository roots with zero missing paths; no planning placeholders remained; security prerequisites still gate Tess exposure; observability traceability is explicit.
+
+**Current gate:** planning PR must merge to `main` with terminal-green CI before any source-code worker starts.

docs/scratchpads/tess-m1-002-provider-registry.md

@@ -0,0 +1,38 @@
+# TESS-M1-002 — Provider Registry
+
+- **Issue:** #707
+- **Branch:** `feat/tess-provider-registry`
+- **Objective:** Build the runtime provider registry/service boundary that derives immutable actor/tenant/channel/correlation scope server-side, fail-closes unsupported and destructive runtime operations, binds termination approval to the exact structured action, and emits correlation-safe audit events.
+
+## Plan
+
+1. Add a provider-agnostic registry in `@mosaicstack/agent` over the merged `AgentRuntimeProvider` contract.
+2. Write abuse-case tests before implementation for duplicate/unknown providers, immutable server-derived scope, capability denial, approval mismatch/absence, and audit failure.
+3. Implement the Gateway service that converts only authenticated `ActorTenantScope` plus trusted ingress metadata into a frozen `RuntimeScope`, gates capabilities and terminate approval, and records metadata-only audits.
+4. Register the service in `AgentModule`, then run focused, baseline, cold-cache, and independent-review gates.
+
+## Security Invariants
+
+- Caller-supplied actor/tenant identity never reaches runtime providers.
+- Provider capability absence and approval/audit failure deny before side effects.
+- Termination approval is verified against provider, session, actor, tenant, channel, and correlation context.
+- Audit events retain correlation and authority metadata but never message content or approval material.
+
+## Progress
+
+- 2026-07-12: Created fresh worktree from `origin/main` at `119f64e6`; source and Tess planning/security documentation reviewed.
+- 2026-07-12: Security TDD added registry and gateway abuse tests before implementation.
+- 2026-07-12: Implemented `AgentRuntimeProviderRegistry` and gateway `RuntimeProviderService`; registered both in `AgentModule` and documented the internal boundary.
+- 2026-07-12: Independent review found two audit correctness issues. Remediated completion-audit failure handling and provider execution failures: pre-invocation denials are audited as `denied`; post-invocation errors as `failed`; completion audit failure does not misreport a completed effect as retryable.
+- 2026-07-12: Final independent security review: no findings. Final code review had one false positive: `@mosaicstack/types` is already declared in `packages/agent/package.json`.
+
+## Tests
+
+- TDD red: `pnpm --filter @mosaicstack/gateway test -- runtime-provider-registry.service.test.ts` failed before both audit remediations, as expected.
+- Focused: package registry 2 tests and gateway security boundary 7 tests pass.
+- Cold-cache: removed this worktree's `node_modules`, then `pnpm install --offline --frozen-lockfile --store-dir /home/jarvis/.local/share/pnpm/store` passed.
+- Cold-cache baseline: `TURBO_FORCE=true pnpm typecheck` — 42/42 tasks passed; `TURBO_FORCE=true pnpm lint` — 23/23 tasks passed; `TURBO_FORCE=true pnpm format:check` passed; `TURBO_FORCE=true pnpm test` — 42/42 tasks passed (gateway 548 tests passed, 11 intentionally skipped).
+
+## Risks / Blockers
+
+- The canonical durable approval implementation is currently command-specific. This card introduces a fail-closed runtime approval verifier boundary so a runtime provider cannot terminate until its exact-action verifier is wired; later provider implementations cannot bypass it.

docs/scratchpads/tess-m1-sec-001.md

@@ -0,0 +1,27 @@
+# TESS-M1-SEC-001 — Command authorization and exact-action approval
+
+- Issue/milestone: #707 / M1
+- Branch: `fix/tess-command-authz`
+- Requirement: `TESS-SEC-002`, with approval binding controls from `TESS-SEC-007`
+- Scope: `apps/gateway` only, plus required in-repo security/developer documentation.
+
+## Plan
+
+1. Locate the gateway command executor, command metadata, authorization context, and existing test conventions.
+2. Write abuse/authz tests before production changes. Expected red cases: non-admin blocked from admin/system command; forged caller scope cannot authorize; privileged/destructive action requires durable exact-action approval; expired/replayed/mutated approvals deny.
+3. Implement server-derived role/scope enforcement and durable approval validation/consumption with audit results.
+4. Run focused security tests, then repository baseline gates: typecheck, lint, format-check, test.
+5. Run independent security/code review, commit, queue-guard, push, and open the PR to `main` through the stated Gitea API fallback. Stop after PR creation.
+
+## Assumptions
+
+- The existing gateway persistence interface is the available durable approval boundary. If no persistence abstraction exists, a minimal injectable repository interface will be introduced rather than an in-memory approval implementation, because TESS-SEC-002/007 require durable enforcement.
+- “Exact action” is a canonical digest over structured command identity and normalized arguments; role/scope checks always use authenticated server context, not client-declared claims.
+
+## TDD evidence
+
+- Pending: abuse/authz test written and observed red before implementation.
+
+## Verification evidence
+
+- Pending.

docs/scratchpads/tess-m1-sec-004-discord-ingress.md

@@ -0,0 +1,35 @@
+# Scratchpad — TESS-M1-SEC-004 Discord ingress
+
+- **Task / issue:** TESS-M1-SEC-004 / #707
+- **Branch:** `fix/tess-discord-ingress` from `origin/main` at `59e49cfd`
+- **Objective:** Authenticate the Discord plugin service at gateway ingress; enforce explicit guild/channel/user allowlists; attach Discord message and generated correlation IDs; reject replayed native message IDs.
+- **Scope:** `plugins/discord`, `apps/gateway`, and existing Discord admin/developer protocol docs.
+- **Budget:** Task estimate 28K; no explicit hard cap supplied.
+- **Assumptions:** The Discord plugin and gateway share an injected high-entropy `DISCORD_SERVICE_TOKEN`; a configured Discord plugin fails closed without it. Allowlist configuration is comma-separated Discord snowflakes. Discord native message ID is the replay key, with bounded in-memory retention pending the M2 durable inbox/idempotency work.
+
+## Plan
+
+1. Add failing tests covering ingress service authentication/signing, unlisted guild/channel/user rejection, correlation propagation, and replay rejection.
+2. Implement the signed Discord ingress envelope and allowlist validation in the plugin.
+3. Authenticate and validate the envelope at the gateway boundary, then enforce bounded replay protection before agent dispatch.
+4. Document the service-token and allowlist operations; run focused and baseline gates; obtain independent review.
+
+## Progress
+
+- 2026-07-12: Intake complete; PRD TESS-SEC-005, architecture, and threat model reviewed.
+- Added service-token Socket.IO authentication, HMAC-signed Discord envelopes, default-deny guild/channel/user allowlists, correlated message metadata, bounded replay rejection, and fail-fast configuration checks.
+- Code and security reviews completed. Code review findings on service persistence ownership, package-boundary tests, disconnected ingress observability, and chat payload validation were remediated; final independent code review approved.
+
+## Risks / blockers
+
+- Existing `main` has known unrelated Prettier debt; only changed files will be held format-clean. Durable replay persistence is intentionally out of scope for this M1 prerequisite and belongs to TESS-M2 durable inbox/idempotency work.
+
+## Verification evidence
+
+- Focused ingress suite: `pnpm --filter @mosaicstack/gateway test -- discord-ingress.security.spec.ts` — 7 passed.
+- Gateway suite: `pnpm --filter @mosaicstack/gateway test` — 513 passed, 11 skipped.
+- Plugin suite: `pnpm --filter @mosaicstack/discord-plugin test` — no tests, passed by configured `--passWithNoTests`.
+- `pnpm typecheck` — passed.
+- `pnpm lint` — passed.
+- `pnpm format:check` — fails only on the known pre-existing Tess documentation debt listed in the task dispatch; changed files pass targeted Prettier verification.
+- Codex security review — no findings; final Codex code review — approved.

docs/tess/ARCHITECTURE.md

@@ -0,0 +1,77 @@
+# Tess Architecture
+
+## Purpose
+
+Tess is the Mosaic operator interaction plane. Mos remains the coding/general fleet orchestration authority. Tess receives authorized operator intent, presents fleet/session state, delegates Mos-owned work to Mos, and exposes native Mosaic plus transitional external-agent capabilities through normalized providers.
+
+## Component Boundaries
+
+```text
+Discord plugin ─┐
+                ├─ authenticated ingress envelope ─> Mosaic Gateway
+mosaic tess CLI ┘                                  │
+                                                   ├─ policy/approval/audit
+                                                   ├─ Tess durable session service (Pi GPT-5.6 Sol high)
+                                                   ├─ AgentRuntimeProvider registry
+                                                   │   ├─ native Pi provider
+                                                   │   ├─ fleet/tmux provider
+                                                   │   ├─ Hermes adapter
+                                                   │   └─ Matrix/native transport provider
+                                                   ├─ memory/state/inbox plugins
+                                                   └─ Mos coordination adapter ─> Mos / fleet queue
+```
+
+## Core Contract
+
+`AgentRuntimeProvider` is separate from the existing model-completion `IProviderAdapter`. It normalizes external and native agent runtimes without leaking provider-specific schemas.
+
+Required operations:
+
+- `capabilities()` and `health()`
+- `listSessions(scope)`
+- `getSessionTree(scope)`
+- `streamSession(sessionRef, cursor, scope)`
+- `sendMessage(sessionRef, message, idempotencyKey, scope)`
+- `attach(sessionRef, mode, scope)` / `detach()`
+- `terminate(sessionRef, approvalRef, scope)`
+
+Every call receives an immutable, server-derived actor/tenant/channel scope and correlation ID. Caller-supplied actor IDs are forbidden. Unsupported capabilities fail closed with typed errors.
+
+### M1 Registry Boundary
+
+`@mosaicstack/agent` owns the explicit `AgentRuntimeProviderRegistry`; duplicate provider IDs are rejected rather than replaced. Gateway owns `RuntimeProviderService`, which creates a frozen `RuntimeScope` from authenticated `ActorTenantScope` and trusted ingress channel/correlation metadata before every provider call. The service checks the declared provider capability before invoking a side effect and records metadata-only audit events (`providerId`, operation, outcome, actor/tenant/channel, correlation, and resource ID). It never records message bodies, idempotency keys, or approval references.
+
+Termination is fail-closed: a runtime approval verifier must consume a one-time, exact action binding for the provider, session, actor, tenant, channel, and correlation ID before `terminate` reaches a provider. Until the durable verifier is wired, the default verifier denies termination. This internal service introduces no HTTP endpoint; later Discord, CLI, MCP, and provider adapters consume the same gateway boundary.
+
+## Authority Model
+
+| Intent                                                                      | Owner                   | Tess behavior                                                          |
+| --------------------------------------------------------------------------- | ----------------------- | ---------------------------------------------------------------------- |
+| Conversation, status, retrieval, safe diagnostics                           | Tess                    | Execute within policy                                                  |
+| Code/project decomposition, worker assignment, reviews, merge orchestration | Mos                     | Create a correlated handoff and observe result                         |
+| Destructive, privileged, external/customer-visible action                   | Human approval + policy | Propose, wait for durable one-time approval, then execute idempotently |
+| Provider-specific unsupported action                                        | None                    | Fail closed; never emulate silently                                    |
+
+## Session and State Model
+
+A Tess session has stable `sessionId`, `tenantId`, `ownerId`, provider/runtime identity, ingress bindings, cursor, checkpoint, inbox/outbox, and idempotency records. Discord and CLI bind to the same authorized session. Ownership is verified server-side on every list/read/attach/send/terminate operation.
+
+Valkey may hold ephemeral coordination state; PostgreSQL is canonical for durable session bindings, approvals, audit, checkpoints, inbox/outbox, and idempotency. Pi session files are replay sources, not cross-agent truth.
+
+## Transport Strategy
+
+- **Initial:** fleet/tmux provider, including exact target, socket, identity, heartbeat, and safe attach semantics.
+- **Forward:** Matrix/native Mosaic provider using authenticated identity, idempotent transaction IDs, replay cursors, and the same contract suite.
+- Discord/CLI never call tmux or Matrix directly.
+
+## Plugin Families
+
+1. Channel: Discord now; other channels later.
+2. Runtime: Pi, fleet/tmux, Hermes, Matrix/native.
+3. Operator tools: fleet health, Mos handoff, GitOps wrappers, incident-safe diagnostics.
+4. Memory/state: search/recent/capture, durable inbox, checkpoint, handoff, compaction recovery.
+5. Migration: capability inventory, adapters, cutover, rollback, telemetry.
+
+## Deployment
+
+Tess runs as a rostered, systemd-supervised Pi agent using GPT-5.6 Sol and high reasoning. Secrets are supplied through approved runtime secret mechanisms. Startup fails when required model, gateway identity, Discord binding, or durable-state dependencies are missing. Health reports effective model/reasoning/tool policy without credential material.

docs/tess/MIGRATION-INVENTORY.md

@@ -0,0 +1,34 @@
+# Tess Capability Migration Inventory
+
+Status values: `native` · `adapt` · `defer` · `reject`. This is the initial inventory; M5 requires implementation and evidence fields to be completed before cutover.
+
+| Capability                               | Current source                           | Target                                     | Initial status | Cutover/rollback intent                                                 |
+| ---------------------------------------- | ---------------------------------------- | ------------------------------------------ | -------------- | ----------------------------------------------------------------------- |
+| Interactive agent chat/session streaming | Hermes/Pi/OpenClaw                       | Mosaic Tess session service                | native         | Dual-run per channel; revert binding to legacy gateway                  |
+| Discord dedicated-channel routing        | Hermes/Claude/OpenClaw plugins           | Mosaic Discord plugin + gateway            | native         | Per-channel binding switch; legacy bot disabled only after soak         |
+| CLI/TUI session interaction and attach   | Hermes/Pi/tmux                           | `mosaic tess` + AgentRuntimeProvider       | native         | Keep direct tmux attach as break-glass rollback                         |
+| Session list/tree/send/terminate         | Hermes/fleet                             | AgentRuntimeProvider                       | native         | Capability-negotiated adapter remains during migration                  |
+| Mos/fleet orchestration handoff          | tmux messaging/Mosaic fleet              | Mosaic coord/fleet provider                | native         | tmux handoff remains initial transport                                  |
+| Kanban/projects/tasks                    | Hermes Kanban                            | Mosaic queue/coord/project providers       | adapt          | Read projection first; mutating cutover after parity/audit              |
+| Skills catalog/load/manage               | Hermes skills/Pi skills                  | Mosaic skill registry/provider             | adapt          | Import metadata/provenance; preserve source skill until validated       |
+| Tools and MCP                            | Hermes/OpenClaw/MCP                      | Mosaic tool registry/MCP                   | adapt          | Default deny; migrate allowlisted tools one capability at a time        |
+| Cron/scheduled work                      | Hermes cron                              | Mosaic scheduler/queue                     | adapt          | Shadow schedules; prevent duplicate execution; rollback owner field     |
+| Memory search/recent/capture             | jarvis-brain/OpenViking/OpenBrain/Hermes | Mosaic memory provider                     | adapt          | Flat/project stores remain truth; semantic systems are mirrors          |
+| User/profile preferences                 | Hermes memory/user profile               | Mosaic user/memory domain                  | adapt          | Provenance + explicit conflict rules; exportable rollback snapshot      |
+| Agent state/inbox/handoff                | OpenClaw extensions/session files        | Mosaic durable state service               | native         | Read legacy handoff during coexistence; write Mosaic only after cutover |
+| Runtime contract/bootstrap               | Mosaic framework/Hermes/OpenClaw         | Mosaic compose/runtime provider            | native         | Legacy launchers remain until clean-host parity passes                  |
+| Repository/PR workflow                   | Mosaic wrappers/Hermes tools             | Mosaic operator plugin                     | native         | Wrapper-only; no raw-provider fallback                                  |
+| Incident-safe diagnostics                | Hermes skills/tools                      | Mosaic scoped operator plugin              | adapt          | Read-only first; privileged recovery requires approval                  |
+| Broad unrestricted shell from Discord    | Hermes/OpenClaw configurations           | None                                       | reject         | No cutover; replace with allowlisted typed operations                   |
+| Raw full transcript bulk migration       | Hermes/Claude/OpenClaw histories         | Indexed summaries/selective import         | reject         | Keep source archives subject to retention; no automatic copy            |
+| Voice/video interaction                  | Hermes optional tools                    | Future Mosaic channel plugins              | defer          | Not required for Tess operational release                               |
+| Matrix transport                         | Mosaic connector                         | AgentRuntimeProvider Matrix implementation | native         | Non-default until contract/reliability parity; tmux rollback            |
+
+## Cutover Gates
+
+1. Capability contract and security tests pass.
+2. Data mapping/provenance and retention are documented.
+3. Shadow or dual-run shows no unauthorized access, loss, or duplicate effects.
+4. Operator runbook and rollback are exercised.
+5. Channel/provider binding changes are reversible without schema rollback.
+6. Legacy capability is disabled only after a defined soak period and evidence review.

docs/tess/MISSION-MANIFEST.md

@@ -0,0 +1,46 @@
+# Mission Manifest — Tess Interaction Agent
+
+## Mission
+
+- **ID:** tess-20260712
+- **Issue:** #706
+- **Branch:** `feat/tess-interaction-agent`
+- **Phase:** Execution
+- **Current Milestone:** TESS-M1 — Runtime contracts and security foundation
+- **Progress:** 0 / 5 delivery milestones complete
+- **Status:** active
+- **Owner:** Mosaic orchestrator; Mos is coordinating fleet authority
+- **Source PRD:** `docs/PRD.md` — `TESS-*` requirements
+- **Scratchpad:** `docs/scratchpads/tess-20260712.md`
+
+## Mission Statement
+
+Ship Tess as Jason's durable Pi-native GPT-5.6 Sol high-reasoning interaction agent for Discord and CLI, with safe visibility/control of Mosaic fleet and transitional Hermes capabilities, while Mos remains the coding/general orchestration authority.
+
+## Invariants
+
+1. Mosaic is the enterprise AI hub; Hermes is a reference migration adapter.
+2. Gateway is the single API surface.
+3. Mos owns coding/general fleet orchestration; Tess owns human interaction, visibility, mediation, and migration access.
+4. Runtime, transport, channel, memory, and external-agent integrations are replaceable adapters.
+5. No source task completes before merged PR, terminal-green CI, independent review, and linked task/issue closure.
+
+## Milestones
+
+| ID      | Issue | Name                                                                | Status      | Exit gate                                                                                                         |
+| ------- | ----- | ------------------------------------------------------------------- | ----------- | ----------------------------------------------------------------------------------------------------------------- |
+| TESS-M1 | #707  | Runtime contracts and security foundation                           | ready       | AgentRuntimeProvider, normalized events/capabilities/errors, RBAC/audit contracts and contract tests merged       |
+| TESS-M2 | #708  | Durable Pi Tess service and state                                   | not-started | GPT-5.6 Sol high service starts, resumes, checkpoints, and passes restart/compaction tests                        |
+| TESS-M3 | #709  | Discord and CLI interaction surfaces                                | not-started | One durable session works through dedicated Discord binding and `mosaic tess`, including attach and approvals     |
+| TESS-M4 | #710  | Fleet, Mos, Hermes, memory, state, and tool plugins                 | not-started | Fleet/Mos boundary and transitional capability matrix demonstrated end-to-end                                     |
+| TESS-M5 | #711  | Matrix/native migration, recovery, documentation, and qualification | not-started | Transport parity, migration/rollback matrix, security review, docs, greenfield and deployment validation complete |
+
+## Success Criteria
+
+All `AC-TESS-*` criteria in `docs/PRD.md` are mapped to reproducible evidence. The final operational test must prove Discord + CLI session continuity, fleet/Mos coordination, authorized Hermes transition capabilities, denial/audit paths, restart recovery, and rollback.
+
+## Session History
+
+| Session | Date       | Runtime              | Outcome                                                                                                                                     |
+| ------- | ---------- | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
+| S1      | 2026-07-12 | Hermes / GPT-5.6 Sol | User commission captured; Mosaic/OpenViking/session/code archaeology completed; issue #706 created; PRD and task control plane initialized. |

docs/tess/TASKS.md

@@ -0,0 +1,34 @@
+# Tasks — Tess Interaction Agent
+
+> Mission: `tess-20260712` · Issue: #706 · PRD requirements: `TESS-*`
+> Orchestrator is sole writer. Workers must not modify this file.
+> `repo` contains one or more comma-separated repository-relative roots; every listed root must exist before dispatch.
+
+| id | status | description | issue | agent | repo | branch | depends_on | estimate | notes |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| TESS-PLAN-001 | done | Finalize PRD, architecture, authority boundary, threat model, migration inventory, and verification matrix | #706 | sonnet | docs, packages/types, apps/gateway | feat/tess-interaction-agent | — | 22K | Independent gate PASS after two remediation rounds; completion effective when planning PR merges |
+| TESS-M1-SEC-001 | not-started | Enforce command scopes/roles and durable exact-action approval for privileged/destructive commands | #707 | codex | apps/gateway | fix/tess-command-authz | TESS-PLAN-001 | 25K | TESS-SEC-002; security TDD |
+| TESS-M1-SEC-002 | not-started | Enforce owner/tenant binding on session list/read/attach/send/terminate across REST and WS | #707 | codex | apps/gateway | fix/tess-session-ownership | TESS-PLAN-001 | 30K | TESS-SEC-003; security TDD |
+| TESS-M1-SEC-003 | not-started | Bind MCP actor/tenant to authenticated context and add per-tool scopes | #707 | codex | apps/gateway | fix/tess-mcp-identity | TESS-PLAN-001 | 22K | TESS-SEC-004; security TDD |
+| TESS-M1-SEC-004 | not-started | Add authenticated Discord service ingress, allowlists, correlation and replay protection | #707 | codex | plugins/discord, apps/gateway | fix/tess-discord-ingress | TESS-PLAN-001 | 28K | TESS-SEC-005; security TDD |
+| TESS-M1-SEC-005 | not-started | Redact/classify secret and PII before persistence/egress; harden provider login flow | #707 | codex | apps/gateway, packages/log | fix/tess-redaction | TESS-PLAN-001 | 28K | TESS-SEC-006; seeded canary tests |
+| TESS-M1-SEC-006 | not-started | Scope session GC/retention or separate authorized global retention job | #707 | codex | apps/gateway, packages/log | fix/tess-session-gc-scope | TESS-PLAN-001 | 18K | TESS-SEC-009; isolation TDD |
+| TESS-M1-001 | not-started | Define AgentRuntimeProvider, capabilities, session tree, normalized stream events/errors, attach semantics | #707 | codex | packages/types, packages/agent | feat/tess-runtime-contract | TESS-PLAN-001 | 25K | TESS-ARP-001, TESS-TRN-001; contract TDD |
+| TESS-M1-002 | not-started | Implement provider registry/service with immutable actor scope, approval, audit and correlation boundaries | #707 | codex | apps/gateway, packages/agent | feat/tess-provider-registry | TESS-M1-001,TESS-M1-SEC-001,TESS-M1-SEC-002,TESS-M1-SEC-003 | 30K | TESS-SEC-001..004,007; security TDD |
+| TESS-M1-003 | not-started | Implement tmux/fleet runtime provider and safe attach/message/terminate capability policy | #707 | codex | packages/mosaic, packages/agent | feat/tess-fleet-provider | TESS-M1-002 | 30K | TESS-FLT-001; exact target/identity tests |
+| TESS-M1-OBS-001 | not-started | Implement correlation propagation, structured runtime/provider/tool audit, health/readiness and safe effective-policy status | #707 | codex | apps/gateway, packages/agent, packages/log | feat/tess-observability | TESS-M1-002 | 24K | TESS-OBS-001; no credential material |
+| TESS-M1-V | not-started | Independent architecture/security review and complete contract/abuse-suite verification | #707 | sonnet | apps/gateway, packages/agent, packages/log, plugins/discord | review/tess-m1 | TESS-M1-SEC-001,TESS-M1-SEC-002,TESS-M1-SEC-003,TESS-M1-SEC-004,TESS-M1-SEC-005,TESS-M1-SEC-006,TESS-M1-003,TESS-M1-OBS-001 | 20K | Gate M2 |
+| TESS-M2-001 | not-started | Add Tess roster/profile/service pinned to GPT-5.6 Sol high with fail-fast config and observable effective policy | #708 | codex | packages/mosaic/framework | feat/tess-pi-service | TESS-M1-V | 22K | TESS-PI-001; explicit AC-TESS-03 test |
+| TESS-M2-002 | not-started | Implement durable session identity, inbox/outbox, approval, checkpoint, handoff, compaction and restart recovery | #708 | codex | apps/gateway, packages/agent, packages/db | feat/tess-durable-state | TESS-M2-001 | 38K | TESS-STA-001, TESS-SEC-007..008; recovery TDD |
+| TESS-M2-V | not-started | Clean-host Pi launch plus model/policy status and restart/compaction/duplicate-side-effect verification | #708 | sonnet | apps/gateway/src/__tests__/integration, packages/mosaic/src | review/tess-m2 | TESS-M2-002 | 18K | Gate M3; AC-TESS-03/06 |
+| TESS-M3-001 | not-started | Bind dedicated Tess Discord channel with streaming, threads, attachments, pairing/RBAC and approvals | #709 | codex | plugins/discord, apps/gateway | feat/tess-discord | TESS-M2-V,TESS-M1-SEC-004 | 35K | TESS-DSC-001 |
+| TESS-M3-002 | not-started | Implement `mosaic tess` chat/status/sessions/tree/attach/send/stop/health/recover CLI | #709 | codex | packages/mosaic | feat/tess-cli | TESS-M2-V | 30K | TESS-CLI-001 |
+| TESS-M3-V | not-started | Discord+CLI same-session E2E, denial/approval tests, and operator-flow review | #709 | sonnet | apps/gateway/src/__tests__/integration, plugins/discord, packages/mosaic/src | review/tess-m3 | TESS-M3-001,TESS-M3-002 | 20K | Gate M4 |
+| TESS-M4-001 | not-started | Implement Mos coordination handoff/observe/result contract with authority-boundary tests | #710 | codex | packages/coord, apps/gateway | feat/tess-mos-coordination | TESS-M3-V | 25K | TESS-MOS-001 |
+| TESS-M4-002 | not-started | Implement transitional Hermes runtime/capability adapter | #710 | codex | packages/agent, apps/gateway | feat/tess-hermes-adapter | TESS-M3-V | 40K | TESS-HRM-001; no legacy schema in core contracts |
+| TESS-M4-003 | not-started | Implement memory/retrieval, state/inbox, runtime bootstrap, fleet diagnostics and GitOps plugin foundations | #710 | codex | packages/memory, packages/agent, packages/mosaic | feat/tess-operator-plugins | TESS-M3-V | 40K | TESS-MEM-001, TESS-PLG-001 |
+| TESS-M4-V | not-started | Cross-provider capability, privacy, authority and failure-path qualification | #710 | sonnet | apps/gateway/src/__tests__/integration, packages/agent | review/tess-m4 | TESS-M4-001,TESS-M4-002,TESS-M4-003 | 22K | Gate M5 |
+| TESS-M5-001 | not-started | Implement Matrix/native runtime provider behind common contracts and parity suite | #711 | codex | packages/mosaic, packages/agent | feat/tess-matrix-provider | TESS-M4-V | 30K | TESS-TRN-001 |
+| TESS-M5-002 | not-started | Complete migration inventory, cutover, rollback, retention and deprecation evidence | #711 | sonnet | docs/tess | feat/tess-migration-docs | TESS-M4-V | 18K | TESS-MIG-001 |
+| TESS-M5-003 | not-started | Complete OpenAPI, user/admin/developer/plugin/operations docs and checklist | #711 | codex | docs | feat/tess-docs | TESS-M5-001,TESS-M5-002 | 22K | Documentation hard gate |
+| TESS-M5-V | not-started | Full baseline, contract, integration, Discord/CLI E2E, security review, recovery drill and rollback qualification | #711 | sonnet | apps/gateway, packages/agent, plugins/discord, packages/mosaic | review/tess-final | TESS-M5-003 | 35K | Maps AC-TESS-01..11 to evidence |

docs/tess/THREAT-MODEL.md

@@ -0,0 +1,46 @@
+# Tess Threat Model
+
+## Assets and Trust Boundaries
+
+Assets: operator identity, tenant/project data, agent sessions, fleet control, approvals, credentials, memories, tool outputs, audit evidence, and provider transports.
+
+Trust boundaries: Discord→plugin, CLI→gateway, plugin→gateway service identity, gateway→Pi/provider, Tess→Mos/fleet, Tess→Hermes, MCP→gateway, persistence, and tmux/Matrix transports.
+
+## Threat Matrix
+
+| ID    | Severity | Threat                                                                   | Required control                                                                                                                     | Required verification                                                     |
+| ----- | -------- | ------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------- |
+| TM-01 | critical | Client invokes admin/system command without role                         | Server-side scope/role enforcement in executor; durable approval for privileged/destructive commands                                 | Authenticated non-admin and forged-scope tests deny and audit             |
+| TM-02 | critical | Cross-user/tenant list, attach, send, or terminate by guessed session ID | Owner/tenant binding on every session operation; admin override is explicit and audited                                              | Cross-tenant matrix for REST, WS, CLI, Discord and provider methods       |
+| TM-03 | high     | MCP caller supplies another `userId`                                     | Remove actor IDs from schemas; derive actor/tenant from authenticated context; per-tool scopes                                       | Forged actor/tool calls deny; no victim data returned                     |
+| TM-04 | high     | Discord ingress impersonates user/channel or bypasses gateway auth       | Service-to-service identity, guild/channel/user allowlists, signed/correlated envelope, replay protection                            | Invalid service identity, unlisted IDs, replayed message IDs all deny     |
+| TM-05 | high     | Secrets/PII leak in chat, auth links, tool args, logs, memory, or DB     | Redact before persistence/egress; DM/out-of-band auth flow; short-lived hashed token state; output classification                    | Seeded secret/PII canary absent from durable stores/logs/public channel   |
+| TM-06 | high     | Prompt/tool injection escalates from content to privileged action        | Treat messages/files/tool output as untrusted data; structured proposals only; allowlisted tools; approval binds exact action digest | Injection corpus cannot invoke unapproved tools or alter authority        |
+| TM-07 | high     | Approval forged, replayed, or applied to modified action                 | One-time approval with actor, tenant, action digest, expiry, correlation and consumption record                                      | Forged/replayed/expired/mutated approvals deny and audit                  |
+| TM-08 | medium   | Restart causes message loss or duplicate side effects                    | Durable inbox/outbox/checkpoint; idempotency keys; transactional state transitions; bounded replay                                   | Kill/restart at each state transition; exactly-once effect or safe dedupe |
+| TM-09 | medium   | Session GC/retention crosses tenant/session scope                        | Session/user-scoped GC or separately authorized global retention job                                                                 | GC one session; unrelated logs/memory remain unchanged                    |
+| TM-10 | high     | tmux/Matrix transport target or identity spoofing                        | Exact target/socket binding, peer identity verification, Matrix whoami, authenticated transport metadata                             | Wrong socket/peer/room/identity refuses delivery/attach                   |
+| TM-11 | medium   | Hermes adapter exposes unsupported or broader legacy powers              | Capability negotiation, default deny, normalized scopes, adapter sandbox/timeouts                                                    | Unsupported and over-scoped operations fail closed                        |
+| TM-12 | medium   | Tess competes with Mos or bypasses orchestration gates                   | Authority policy and correlated Mos handoff; no Tess worker-claim capability by default                                              | Coding/decomposition intent produces handoff, not direct claim            |
+
+## Security Invariants
+
+1. Authentication is not authorization; every command/tool/provider operation is authorized server-side.
+2. Actor, tenant, roles, and channel bindings come only from authenticated gateway context.
+3. No client-provided session ID grants ownership or attachment.
+4. No privileged action executes without a matching, unexpired, one-time approval when policy requires it.
+5. Redaction occurs before persistence and before channel egress.
+6. Every externally caused operation is replay-safe and correlated.
+7. Provider capability absence is a denial, not an invitation to shell around it.
+
+## Existing Findings That Block Tess
+
+- Command executor lacks server-side enforcement for declared scopes.
+- Session list/reuse/destroy surfaces are not owner-filtered consistently.
+- MCP schemas accept caller-supplied user identity.
+- Discord plugin lacks a complete authenticated service ingress and user/channel allowlists.
+- Chat/tool persistence lacks mandatory redaction.
+- Sessions/pending Discord output are in-memory and not restart-safe.
+- Session GC currently performs globally scoped promotion.
+
+These are tracked as M1 security prerequisites and must pass independent security review before Tess ingress is enabled.

docs/tess/VERIFICATION-MATRIX.md

@@ -0,0 +1,30 @@
+# Tess Verification Matrix
+
+| Acceptance criterion | Requirements                             | Planned evidence                                                                                                                | Gate             |
+| -------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | ---------------- |
+| AC-TESS-01           | TESS-PI-001, TESS-DSC-001, TESS-CLI-001  | Discord/CLI same-session integration and streaming E2E                                                                          | M3-V             |
+| AC-TESS-02           | TESS-ARP-001, TESS-CLI-001, TESS-FLT-001 | CLI contract tests for status/sessions/tree/attach/send/stop, typed denial/error snapshots                                      | M3-V             |
+| AC-TESS-03           | TESS-PI-001, TESS-OBS-001                | Clean service launch; status asserts GPT-5.6 Sol, high reasoning and effective tool policy with secret canaries absent          | M2-V, M3-V       |
+| AC-TESS-04           | TESS-MOS-001, TESS-FLT-001               | Authority E2E: coding request creates Mos handoff; safe status runs in Tess; no competing worker claim                          | M4-V             |
+| AC-TESS-05           | TESS-HRM-001                             | Hermes capability contract suite: sessions/stream/send/tree plus Kanban/skills/memory/tools/cron supported-or-denied matrix     | M4-V             |
+| AC-TESS-06           | TESS-STA-001, TESS-SEC-008               | Kill/restart/compaction fault injection across inbox/outbox/checkpoint transitions; duplicate side-effect detector              | M2-V, M5-V       |
+| AC-TESS-07           | TESS-SEC-001..009                        | Threat-model abuse suite: authz, tenant isolation, forged identity/approval, injection, redaction, transport identity, GC scope | M1-V, M3-V, M5-V |
+| AC-TESS-08           | TESS-TRN-001                             | Common provider contract suite against tmux/fleet and Matrix/native; identity and replay tests                                  | M5-V             |
+| AC-TESS-09           | all                                      | `pnpm typecheck`, lint, format, unit/integration/contract/E2E; independent code and security reviews; CI URLs                   | Every milestone  |
+| AC-TESS-10           | TESS-MIG-001                             | Completed capability inventory with native/adapted/deferred/rejected state, owner, cutover/rollback evidence                    | M5-V             |
+| AC-TESS-11           | TESS-PLG-001, TESS-OBS-001               | OpenAPI and user/admin/developer/plugin/ops docs, sitemap links, documentation checklist                                        | M5-V             |
+
+## Security Abuse Suite Minimum
+
+- Role/scope matrix for every command and provider capability.
+- Cross-tenant and cross-user session ID matrix across REST, WS, Discord, CLI, MCP, and providers.
+- Discord service identity, guild/channel/user allowlist, replay, attachment, and mention/DM policy cases.
+- Prompt/tool injection corpus and structured-proposal enforcement.
+- Approval action-digest mutation, replay, expiry, tenant, and actor mismatch cases.
+- Secret/PII canaries through message, attachment, tool args/output, logs, memory, audit, and error paths.
+- Restart fault injection before/after enqueue, provider send, side effect, response persistence, and acknowledgement.
+- Wrong tmux socket/target and Matrix identity/room/replay cases.
+
+## Evidence Rules
+
+Evidence must include command/test name, terminal result, CI run URL, PR/merge reference, environment, and artifact/log location. A worker self-report is not evidence until independently verified.

eslint.config.mjs

@@ -28,7 +28,9 @@ export default tseslint.config(
             'apps/web/e2e/helpers/*.ts',
             'apps/web/playwright.config.ts',
             'apps/gateway/vitest.config.ts',
+            'packages/db/vitest.config.ts',
             'packages/storage/vitest.config.ts',
+            'packages/mosaic/vitest.config.ts',
             'packages/mosaic/__tests__/*.ts',
             'tools/federation-harness/*.ts',
           ],

guides/BOOTSTRAP.md

@@ -15,6 +15,22 @@ This guide covers how to bootstrap a project so AI agents (Claude, Codex, etc.)
 7. Branching/merging is consistent: `branch -> main` via PR with squash-only merges
 8. Steered-autonomy execution is enabled so agents can run end-to-end with escalation-only human intervention
 
+## Agent Host Prerequisites
+
+Agent hosts must provide the Python runtime shape that runtime agents and
+Mosaic automation assume is present.
+
+For Debian/Ubuntu hosts:
+
+```bash
+sudo apt-get update
+# #561: bare python invocations from agents must resolve.
+sudo apt-get install -y python3 python-is-python3
+```
+
+For non-Debian hosts, install the equivalent Python 3 runtime and ensure
+`/usr/bin/python` resolves to `python3` (for example, via a managed symlink).
+
 ## Quick Start
 
 ```bash

packages/agent/src/index.ts

@@ -1 +1,3 @@
 export const VERSION = '0.0.0';
+
+export * from './runtime-provider-registry.js';

packages/agent/src/runtime-provider-registry.test.ts

@@ -0,0 +1,95 @@
+import { describe, expect, it } from 'vitest';
+import type {
+  AgentRuntimeProvider,
+  RuntimeAttachHandle,
+  RuntimeAttachMode,
+  RuntimeCapabilitySet,
+  RuntimeHealth,
+  RuntimeMessage,
+  RuntimeScope,
+  RuntimeSession,
+  RuntimeSessionTree,
+  RuntimeStreamEvent,
+} from '@mosaicstack/types';
+import { AgentRuntimeProviderRegistry } from './runtime-provider-registry.js';
+
+class TestRuntimeProvider implements AgentRuntimeProvider {
+  readonly id = 'test-runtime';
+
+  async capabilities(_scope: RuntimeScope): Promise<RuntimeCapabilitySet> {
+    return { supported: ['session.list'] };
+  }
+
+  async health(_scope: RuntimeScope): Promise<RuntimeHealth> {
+    return { status: 'healthy', checkedAt: '2026-07-12T00:00:00.000Z' };
+  }
+
+  async listSessions(_scope: RuntimeScope): Promise<RuntimeSession[]> {
+    return [];
+  }
+
+  async getSessionTree(_scope: RuntimeScope): Promise<RuntimeSessionTree[]> {
+    return [];
+  }
+
+  async *streamSession(
+    _sessionId: string,
+    _cursor: string | undefined,
+    _scope: RuntimeScope,
+  ): AsyncIterable<RuntimeStreamEvent> {
+    return;
+  }
+
+  async sendMessage(
+    _sessionId: string,
+    _message: RuntimeMessage,
+    _scope: RuntimeScope,
+  ): Promise<void> {}
+
+  async attach(
+    _sessionId: string,
+    _mode: RuntimeAttachMode,
+    _scope: RuntimeScope,
+  ): Promise<RuntimeAttachHandle> {
+    return {
+      attachmentId: 'attachment-1',
+      sessionId: 'session-1',
+      mode: 'read',
+      expiresAt: '2026-07-12T00:00:00.000Z',
+    };
+  }
+
+  async detach(_attachmentId: string, _scope: RuntimeScope): Promise<void> {}
+
+  async terminate(_sessionId: string, _approvalRef: string, _scope: RuntimeScope): Promise<void> {}
+}
+
+describe('AgentRuntimeProviderRegistry', (): void => {
+  it('resolves only registered runtime providers', (): void => {
+    const registry = new AgentRuntimeProviderRegistry();
+    const provider = new TestRuntimeProvider();
+
+    registry.register(provider);
+
+    expect(registry.get(provider.id)).toBe(provider);
+    expect(registry.get('unknown-runtime')).toBeUndefined();
+    expect(registry.list()).toEqual([provider]);
+  });
+
+  it('rejects duplicate and blank provider identities rather than silently replacing a runtime', (): void => {
+    const registry = new AgentRuntimeProviderRegistry();
+    const provider = new TestRuntimeProvider();
+
+    registry.register(provider);
+
+    expect((): void => {
+      registry.register(provider);
+    }).toThrow(/already registered/);
+    expect((): void => {
+      registry.require('');
+    }).toThrow(/provider ID is required/);
+    expect((): void => {
+      registry.require('unknown-runtime');
+    }).toThrow(/not registered/);
+  });
+});

packages/agent/src/runtime-provider-registry.ts

@@ -0,0 +1,40 @@
+import type { AgentRuntimeProvider } from '@mosaicstack/types';
+
+/**
+ * Registry for runtime providers. Registration is explicit and replacement is
+ * forbidden so a provider identity cannot be silently hijacked at runtime.
+ */
+export class AgentRuntimeProviderRegistry {
+  private readonly providers = new Map<string, AgentRuntimeProvider>();
+
+  register(provider: AgentRuntimeProvider): void {
+    const providerId = provider.id.trim();
+    if (providerId.length === 0) {
+      throw new Error('Runtime provider ID is required');
+    }
+    if (this.providers.has(providerId)) {
+      throw new Error(`Runtime provider is already registered: ${providerId}`);
+    }
+    this.providers.set(providerId, provider);
+  }
+
+  get(providerId: string): AgentRuntimeProvider | undefined {
+    return this.providers.get(providerId);
+  }
+
+  require(providerId: string): AgentRuntimeProvider {
+    const normalizedProviderId = providerId.trim();
+    if (normalizedProviderId.length === 0) {
+      throw new Error('Runtime provider ID is required');
+    }
+    const provider = this.providers.get(normalizedProviderId);
+    if (!provider) {
+      throw new Error(`Runtime provider is not registered: ${normalizedProviderId}`);
+    }
+    return provider;
+  }
+
+  list(): AgentRuntimeProvider[] {
+    return Array.from(this.providers.values());
+  }
+}

packages/db/drizzle/0011_bitter_gateway.sql

@@ -0,0 +1,22 @@
+CREATE TYPE "public"."backlog_status" AS ENUM('ready', 'claimed', 'blocked', 'done');--> statement-breakpoint
+CREATE TABLE "backlog" (
+	"id" text PRIMARY KEY NOT NULL,
+	"title" text NOT NULL,
+	"body" text,
+	"phase" text,
+	"priority" integer DEFAULT 0 NOT NULL,
+	"status" "backlog_status" DEFAULT 'ready' NOT NULL,
+	"depends_on" jsonb DEFAULT '[]'::jsonb NOT NULL,
+	"claim_owner" text,
+	"claim_ttl_seconds" integer,
+	"claimed_at" timestamp with time zone,
+	"attempts" integer DEFAULT 0 NOT NULL,
+	"idempotency_key" text,
+	"acceptance" jsonb,
+	"created_at" timestamp with time zone DEFAULT now() NOT NULL,
+	"updated_at" timestamp with time zone DEFAULT now() NOT NULL
+);
+--> statement-breakpoint
+CREATE INDEX "backlog_status_priority_idx" ON "backlog" USING btree ("status","priority");--> statement-breakpoint
+CREATE INDEX "backlog_status_claimed_at_idx" ON "backlog" USING btree ("status","claimed_at");--> statement-breakpoint
+CREATE UNIQUE INDEX "backlog_idempotency_key_idx" ON "backlog" USING btree ("idempotency_key");

packages/db/drizzle/meta/_journal.json

@@ -78,6 +78,13 @@
       "when": 1745366400000,
       "tag": "0010_federation_enrollment_tokens",
       "breakpoints": true
+    },
+    {
+      "idx": 11,
+      "version": "7",
+      "when": 1782310438919,
+      "tag": "0011_bitter_gateway",
+      "breakpoints": true
     }
   ]
-}
+}

packages/db/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mosaicstack/db",
-  "version": "0.0.3",
+  "version": "0.0.4",
   "repository": {
     "type": "git",
     "url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

packages/db/src/backlog.spec.ts

@@ -0,0 +1,263 @@
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+import { sql } from 'drizzle-orm';
+import { createPgliteDb } from './client-pglite.js';
+import { runPgliteMigrations } from './migrate.js';
+import type { DbHandle } from './client.js';
+import { BacklogService } from './backlog.js';
+import { backlog } from './schema.js';
+
+// Helper: backdate a claim's claimed_at by 1 hour so it is past any short TTL.
+function sqlBackdate(id: string) {
+  return sql`UPDATE ${backlog} SET claimed_at = now() - interval '1 hour' WHERE ${backlog.id} = ${id}`;
+}
+
+/**
+ * Real Postgres semantics, no external server: embedded in-memory PGlite.
+ * The migration path creates the `backlog` table (and every other table) so the
+ * service runs against the actual generated schema, including the row locks the
+ * atomic-claim path depends on.
+ */
+async function freshService(): Promise<{ handle: DbHandle; svc: BacklogService }> {
+  const handle = createPgliteDb('memory://');
+  await runPgliteMigrations(handle);
+  return { handle, svc: new BacklogService(handle.db) };
+}
+
+describe('BacklogService', () => {
+  let handle: DbHandle;
+  let svc: BacklogService;
+
+  beforeEach(async () => {
+    ({ handle, svc } = await freshService());
+  });
+
+  afterEach(async () => {
+    await handle.close();
+  });
+
+  it('create then list returns the card', async () => {
+    await svc.create({ id: 'c1', title: 'First card', phase: 'M1', priority: 5 });
+    const all = await svc.list();
+    expect(all).toHaveLength(1);
+    expect(all[0]).toMatchObject({ id: 'c1', title: 'First card', phase: 'M1', status: 'ready' });
+  });
+
+  it('idempotency_key dedups create', async () => {
+    const a = await svc.create({ id: 'c1', title: 'one', idempotencyKey: 'k-1' });
+    const b = await svc.create({ id: 'c2', title: 'two', idempotencyKey: 'k-1' });
+    expect(b.id).toBe(a.id);
+    const all = await svc.list();
+    expect(all).toHaveLength(1);
+  });
+
+  it('list filters by status and phase', async () => {
+    await svc.create({ id: 'c1', title: 'a', phase: 'M1' });
+    await svc.create({ id: 'c2', title: 'b', phase: 'M2' });
+    await svc.block('c2');
+    expect(await svc.list({ phase: 'M1' })).toHaveLength(1);
+    expect(await svc.list({ status: 'blocked' })).toHaveLength(1);
+    expect((await svc.list({ status: 'blocked' }))[0]!.id).toBe('c2');
+  });
+
+  describe('atomic claim', () => {
+    it('two concurrent claimers on one card => exactly one wins', async () => {
+      await svc.create({ id: 'only', title: 'the one', priority: 10 });
+
+      // Two independent claimers race for the single ready card on the same db.
+      // The atomic claim path (`FOR UPDATE SKIP LOCKED` inside a transaction)
+      // guarantees the loser's locked row is skipped, so it can never also flip
+      // the card to claimed — it gets the next candidate (none) and returns null.
+      const svcA = new BacklogService(handle.db);
+      const svcB = new BacklogService(handle.db);
+
+      const [a, b] = await Promise.all([
+        svcA.claim({ owner: 'worker-A' }),
+        svcB.claim({ owner: 'worker-B' }),
+      ]);
+
+      const winners = [a, b].filter((c) => c !== null);
+      expect(winners).toHaveLength(1);
+      expect(winners[0]!.id).toBe('only');
+      expect(winners[0]!.status).toBe('claimed');
+      expect(['worker-A', 'worker-B']).toContain(winners[0]!.claimOwner);
+
+      const card = await svc.get('only');
+      expect(card!.status).toBe('claimed');
+      expect(card!.attempts).toBe(1);
+    });
+
+    it('many concurrent claimers on N cards => no card is double-claimed', async () => {
+      // 5 ready cards, 8 concurrent claimers. Exactly 5 win, all distinct.
+      for (let i = 0; i < 5; i++) {
+        await svc.create({ id: `card-${i}`, title: `card ${i}`, priority: i });
+      }
+      const claimers = Array.from({ length: 8 }, (_, i) =>
+        new BacklogService(handle.db).claim({ owner: `w-${i}` }),
+      );
+      const results = await Promise.all(claimers);
+      const won = results.filter((c): c is NonNullable<typeof c> => c !== null);
+      const wonIds = won.map((c) => c.id);
+      expect(won).toHaveLength(5);
+      expect(new Set(wonIds).size).toBe(5); // all distinct — no double-claim
+    });
+
+    it('N concurrent claimers on N ready cards => every claimer wins a distinct card (no starvation)', async () => {
+      // This is the direct benefit of locking exactly ONE ready row per claim
+      // (`FOR UPDATE SKIP LOCKED LIMIT 1`): with as many ready cards as
+      // claimers, NONE should starve. The old "lock the whole ready set"
+      // behaviour let one claimer lock every row, forcing the rest to null even
+      // though cards were free.
+      const N = 6;
+      for (let i = 0; i < N; i++) {
+        await svc.create({ id: `n-${i}`, title: `card ${i}`, priority: i });
+      }
+      const results = await Promise.all(
+        Array.from({ length: N }, (_, i) =>
+          new BacklogService(handle.db).claim({ owner: `w-${i}` }),
+        ),
+      );
+      const won = results.filter((c): c is NonNullable<typeof c> => c !== null);
+      // No claimer starved: all N won.
+      expect(won).toHaveLength(N);
+      // Each won a distinct card.
+      expect(new Set(won.map((c) => c.id)).size).toBe(N);
+      // Every ready card was consumed.
+      expect(await svc.list({ status: 'ready' })).toHaveLength(0);
+    });
+
+    it('sequential claims drain ready cards in priority order and never null while ready remain', async () => {
+      // PGlite-stable fallback assertion of the same property without relying on
+      // true parallelism or wall-clock timing: each claim returns the next
+      // highest-priority distinct card and never spuriously returns null while
+      // ready cards remain.
+      const N = 4;
+      for (let i = 0; i < N; i++) {
+        await svc.create({ id: `s-${i}`, title: `card ${i}`, priority: i });
+      }
+      const order: string[] = [];
+      for (let i = 0; i < N; i++) {
+        const claimed = await svc.claim({ owner: `w-${i}` });
+        expect(claimed).not.toBeNull();
+        order.push(claimed!.id);
+      }
+      // Highest priority first, all distinct.
+      expect(order).toEqual(['s-3', 's-2', 's-1', 's-0']);
+      expect(new Set(order).size).toBe(N);
+      // Now nothing ready remains => null.
+      expect(await svc.claim({ owner: 'late' })).toBeNull();
+    });
+
+    it('claim picks the highest-priority ready card', async () => {
+      await svc.create({ id: 'low', title: 'low', priority: 1 });
+      await svc.create({ id: 'high', title: 'high', priority: 9 });
+      const claimed = await svc.claim({ owner: 'w' });
+      expect(claimed!.id).toBe('high');
+    });
+
+    it('claim of a specific --id', async () => {
+      await svc.create({ id: 'a', title: 'a', priority: 9 });
+      await svc.create({ id: 'b', title: 'b', priority: 1 });
+      const claimed = await svc.claim({ owner: 'w', id: 'b' });
+      expect(claimed!.id).toBe('b');
+    });
+
+    it('claim returns null when nothing is ready', async () => {
+      const claimed = await svc.claim({ owner: 'w' });
+      expect(claimed).toBeNull();
+    });
+  });
+
+  describe('deps DAG gate', () => {
+    it('card with an unfinished dep is not claimable and not ready', async () => {
+      await svc.create({ id: 'dep', title: 'dependency' });
+      await svc.create({ id: 'main', title: 'depends on dep', dependsOn: ['dep'] });
+
+      // `main` should NOT be claimable while `dep` is not done — `dep` wins.
+      const first = await svc.claim({ owner: 'w' });
+      expect(first!.id).toBe('dep');
+
+      // With dep claimed (not done), main still cannot be claimed.
+      const second = await svc.claim({ owner: 'w' });
+      expect(second).toBeNull();
+
+      // ready-only list excludes main while its dep is unfinished.
+      const ready = await svc.list({ readyOnly: true });
+      expect(ready.map((c) => c.id)).not.toContain('main');
+
+      // Once dep is done, main becomes ready and claimable.
+      await svc.complete('dep');
+      const readyAfter = await svc.list({ readyOnly: true });
+      expect(readyAfter.map((c) => c.id)).toContain('main');
+      const third = await svc.claim({ owner: 'w' });
+      expect(third!.id).toBe('main');
+    });
+
+    it('link adds a depends_on edge', async () => {
+      await svc.create({ id: 'a', title: 'a' });
+      await svc.create({ id: 'b', title: 'b' });
+      const linked = await svc.link('a', 'b');
+      expect(linked.dependsOn).toEqual(['b']);
+      // a is now gated on b
+      const claimed = await svc.claim({ owner: 'w' });
+      expect(claimed!.id).toBe('b');
+    });
+  });
+
+  describe('reclaim TTL', () => {
+    it('reclaim returns expired claims to ready', async () => {
+      await svc.create({ id: 'c1', title: 'c1' });
+      const claimed = await svc.claim({ owner: 'w', ttlSeconds: 60 });
+      expect(claimed!.status).toBe('claimed');
+
+      // Backdate the claim so it is well past its TTL.
+      await handle.db.execute(sqlBackdate('c1'));
+
+      const result = await svc.reclaim();
+      expect(result.reclaimed).toEqual(['c1']);
+      const card = await svc.get('c1');
+      expect(card!.status).toBe('ready');
+      expect(card!.claimOwner).toBeNull();
+      expect(card!.claimedAt).toBeNull();
+    });
+
+    it('reclaim does not touch a fresh (unexpired) claim', async () => {
+      await svc.create({ id: 'c1', title: 'c1' });
+      await svc.claim({ owner: 'w', ttlSeconds: 3600 });
+      const result = await svc.reclaim();
+      expect(result.reclaimed).toEqual([]);
+      expect((await svc.get('c1'))!.status).toBe('claimed');
+    });
+
+    it('reclaim --id releases a specific claim regardless of expiry', async () => {
+      await svc.create({ id: 'c1', title: 'c1' });
+      await svc.claim({ owner: 'w', ttlSeconds: 3600 });
+      const result = await svc.reclaim({ id: 'c1' });
+      expect(result.reclaimed).toEqual(['c1']);
+      expect((await svc.get('c1'))!.status).toBe('ready');
+    });
+  });
+
+  describe('stats', () => {
+    it('computes counts, oldest-ready age, and expired-claim count', async () => {
+      await svc.create({ id: 'r1', title: 'r1' });
+      await svc.create({ id: 'r2', title: 'r2' });
+      await svc.create({ id: 'b1', title: 'b1' });
+      await svc.block('b1');
+      await svc.create({ id: 'd1', title: 'd1' });
+      await svc.complete('d1');
+      await svc.create({ id: 'cl1', title: 'cl1' });
+      await svc.claim({ owner: 'w', id: 'cl1', ttlSeconds: 60 });
+      await handle.db.execute(sqlBackdate('cl1'));
+
+      const stats = await svc.stats();
+      expect(stats.counts.ready).toBe(2);
+      expect(stats.counts.blocked).toBe(1);
+      expect(stats.counts.done).toBe(1);
+      expect(stats.counts.claimed).toBe(1);
+      expect(stats.total).toBe(5);
+      expect(stats.expiredClaimCount).toBe(1);
+      expect(stats.oldestReadyAgeSeconds).not.toBeNull();
+      expect(stats.oldestReadyAgeSeconds!).toBeGreaterThanOrEqual(0);
+    });
+  });
+});

packages/db/src/backlog.ts

@@ -0,0 +1,457 @@
+/**
+ * Mosaic-native backlog-of-record service (card A4).
+ *
+ * This is the backlog Mosaic owns end-to-end on its OWN Postgres storage layer.
+ * It REPLACES the former Hermes adapter — there is NO runtime dependency on
+ * Hermes here or anywhere downstream.
+ *
+ * The service takes a `Db` handle, so it works identically against:
+ *   - `createDb()`        — server Postgres (DATABASE_URL / config), and
+ *   - `createPgliteDb()`  — embedded Postgres (file or in-memory).
+ * Same code, same semantics — PGlite gives real Postgres behaviour (including
+ * row locks), so the atomic-claim path is exercised by the in-memory tests.
+ *
+ * Atomic claim: `claim()` selects the highest-priority, deps-satisfied, ready
+ * card with `SELECT ... FOR UPDATE SKIP LOCKED` and flips it to `claimed` inside
+ * one transaction. Two concurrent claimers can therefore NEVER both win the same
+ * card — the loser's locked row is skipped and it picks the next candidate (or
+ * gets null).
+ */
+
+import { and, asc, desc, eq, sql } from 'drizzle-orm';
+import type { Db } from './client.js';
+import { backlog } from './schema.js';
+
+export type BacklogStatus = 'ready' | 'claimed' | 'blocked' | 'done';
+
+export interface BacklogCard {
+  id: string;
+  title: string;
+  body: string | null;
+  phase: string | null;
+  priority: number;
+  status: BacklogStatus;
+  dependsOn: string[];
+  claimOwner: string | null;
+  claimTtlSeconds: number | null;
+  claimedAt: Date | null;
+  attempts: number;
+  idempotencyKey: string | null;
+  acceptance: unknown;
+  createdAt: Date;
+  updatedAt: Date;
+}
+
+export interface CreateCardInput {
+  id: string;
+  title: string;
+  body?: string | null;
+  phase?: string | null;
+  priority?: number;
+  dependsOn?: string[];
+  acceptance?: unknown;
+  idempotencyKey?: string | null;
+  status?: BacklogStatus;
+}
+
+export interface ListFilter {
+  status?: BacklogStatus;
+  phase?: string;
+  /** When true, return only cards that are `ready` AND have all deps `done`. */
+  readyOnly?: boolean;
+}
+
+export interface ClaimOptions {
+  owner: string;
+  /** Claim time-to-live in seconds (default 900). */
+  ttlSeconds?: number;
+  /** Claim a specific card by id instead of the highest-priority ready one. */
+  id?: string;
+}
+
+export interface ReclaimResult {
+  reclaimed: string[];
+}
+
+export interface BacklogStats {
+  counts: Record<BacklogStatus, number>;
+  total: number;
+  oldestReadyAgeSeconds: number | null;
+  expiredClaimCount: number;
+}
+
+export const DEFAULT_CLAIM_TTL_SECONDS = 900;
+
+type Row = typeof backlog.$inferSelect;
+
+/**
+ * Row shape as returned by the raw `SELECT * ... FOR UPDATE SKIP LOCKED` path.
+ * That path bypasses drizzle's column-name mapping, so JSON columns arrive as
+ * the snake_case `depends_on` (and may be a JSON string under some drivers).
+ */
+interface RawRow extends Row {
+  depends_on?: unknown;
+}
+
+function toCard(row: Row): BacklogCard {
+  return {
+    id: row.id,
+    title: row.title,
+    body: row.body,
+    phase: row.phase,
+    priority: row.priority,
+    status: row.status,
+    dependsOn: row.dependsOn ?? [],
+    claimOwner: row.claimOwner,
+    claimTtlSeconds: row.claimTtlSeconds,
+    claimedAt: row.claimedAt,
+    attempts: row.attempts,
+    idempotencyKey: row.idempotencyKey,
+    acceptance: row.acceptance,
+    createdAt: row.createdAt,
+    updatedAt: row.updatedAt,
+  };
+}
+
+/**
+ * The backlog repository/service. Construct with any `Db` handle.
+ */
+export class BacklogService {
+  constructor(private readonly db: Db) {}
+
+  /**
+   * Create a card. If `idempotencyKey` is provided and a card already exists
+   * with that key, the existing card is returned unchanged (no duplicate).
+   */
+  async create(input: CreateCardInput): Promise<BacklogCard> {
+    if (input.idempotencyKey) {
+      const existing = await this.db
+        .select()
+        .from(backlog)
+        .where(eq(backlog.idempotencyKey, input.idempotencyKey))
+        .limit(1);
+      if (existing[0]) return toCard(existing[0]);
+    }
+
+    const inserted = await this.db
+      .insert(backlog)
+      .values({
+        id: input.id,
+        title: input.title,
+        body: input.body ?? null,
+        phase: input.phase ?? null,
+        priority: input.priority ?? 0,
+        status: input.status ?? 'ready',
+        dependsOn: input.dependsOn ?? [],
+        acceptance: input.acceptance ?? null,
+        idempotencyKey: input.idempotencyKey ?? null,
+      })
+      .returning();
+
+    return toCard(inserted[0]!);
+  }
+
+  /** Fetch a single card by id, or null. */
+  async get(id: string): Promise<BacklogCard | null> {
+    const rows = await this.db.select().from(backlog).where(eq(backlog.id, id)).limit(1);
+    return rows[0] ? toCard(rows[0]) : null;
+  }
+
+  /**
+   * List cards with optional filters. `readyOnly` enforces the DAG gate:
+   * a card is "ready" only when its own status is `ready` AND every card in
+   * `depends_on` exists and is `done`.
+   */
+  async list(filter: ListFilter = {}): Promise<BacklogCard[]> {
+    const conditions = [];
+    if (filter.status) conditions.push(eq(backlog.status, filter.status));
+    if (filter.phase) conditions.push(eq(backlog.phase, filter.phase));
+
+    const rows = await this.db
+      .select()
+      .from(backlog)
+      .where(conditions.length ? and(...conditions) : undefined)
+      .orderBy(desc(backlog.priority), asc(backlog.createdAt));
+
+    const cards = rows.map(toCard);
+    if (!filter.readyOnly) return cards;
+
+    const doneIds = await this.doneIdSet();
+    return cards.filter(
+      (c) => c.status === 'ready' && c.dependsOn.every((dep) => doneIds.has(dep)),
+    );
+  }
+
+  private async doneIdSet(): Promise<Set<string>> {
+    const done = await this.db
+      .select({ id: backlog.id })
+      .from(backlog)
+      .where(eq(backlog.status, 'done'));
+    return new Set(done.map((d) => d.id));
+  }
+
+  /**
+   * Atomically claim a card.
+   *
+   * Strategy: inside ONE transaction we lock the candidate row with
+   * `FOR UPDATE SKIP LOCKED LIMIT 1`. A concurrent claimer that already holds
+   * the lock on a row has that row skipped for us, so two claimers can never
+   * both win the same card — and, crucially, each claimer locks exactly ONE
+   * row, so concurrent claimers fan out across distinct ready cards instead of
+   * one claimer locking the whole ready set and starving the rest.
+   *
+   * Candidate selection (when no explicit `id`):
+   *   - status = 'ready'
+   *   - all deps satisfied (every id in depends_on is currently 'done')
+   *   - ordered by priority DESC, created_at ASC
+   *
+   * Returns the claimed card, or null if nothing is claimable.
+   */
+  async claim(opts: ClaimOptions): Promise<BacklogCard | null> {
+    const ttl = opts.ttlSeconds ?? DEFAULT_CLAIM_TTL_SECONDS;
+
+    return this.db.transaction(async (tx) => {
+      // Specific-id path: lock that one ready row (if free) and apply the
+      // deps-satisfied gate in JS, exactly as before.
+      if (opts.id) {
+        const doneRows = await tx
+          .select({ id: backlog.id })
+          .from(backlog)
+          .where(eq(backlog.status, 'done'));
+        const doneIds = new Set(doneRows.map((r) => r.id));
+
+        const result = await tx.execute(
+          sql`SELECT * FROM ${backlog}
+              WHERE ${backlog.id} = ${opts.id} AND ${backlog.status} = 'ready'
+              FOR UPDATE SKIP LOCKED`,
+        );
+        const candidate = rowsOf(result).find((row) =>
+          normalizeDeps(row.depends_on).every((dep) => doneIds.has(dep)),
+        );
+        if (!candidate) return null;
+
+        const updated = await tx
+          .update(backlog)
+          .set({
+            status: 'claimed',
+            claimOwner: opts.owner,
+            claimTtlSeconds: ttl,
+            claimedAt: new Date(),
+            attempts: sql`${backlog.attempts} + 1`,
+            updatedAt: new Date(),
+          })
+          .where(eq(backlog.id, candidate.id))
+          .returning();
+
+        return toCard(updated[0]!);
+      }
+
+      // No-id path: claim the single highest-priority, deps-satisfied ready
+      // card. We lock exactly ONE row in the inner SELECT (`FOR UPDATE SKIP
+      // LOCKED LIMIT 1`) so concurrent claimers grab distinct cards rather than
+      // one claimer locking every ready row and forcing the others to null.
+      //
+      // The deps-satisfied gate is pushed into SQL so `LIMIT 1` lands on the
+      // next genuinely-eligible card: a card is eligible iff none of its
+      // depends_on ids is absent from the set of 'done' card ids.
+      const updated = await tx.execute(
+        sql`UPDATE ${backlog}
+            SET status = 'claimed',
+                claim_owner = ${opts.owner},
+                claim_ttl_seconds = ${ttl},
+                claimed_at = now(),
+                attempts = ${backlog.attempts} + 1,
+                updated_at = now()
+            WHERE ${backlog.id} = (
+              SELECT b.id FROM ${backlog} AS b
+              WHERE b.status = 'ready'
+                AND NOT EXISTS (
+                  SELECT 1
+                  FROM jsonb_array_elements_text(b.depends_on) AS dep
+                  WHERE dep NOT IN (
+                    SELECT d.id FROM ${backlog} AS d WHERE d.status = 'done'
+                  )
+                )
+              ORDER BY b.priority DESC, b.created_at ASC
+              FOR UPDATE SKIP LOCKED
+              LIMIT 1
+            )
+            RETURNING *`,
+      );
+
+      const row = rowsOf(updated)[0];
+      return row ? toCard(rawToRow(row)) : null;
+    });
+  }
+
+  /**
+   * Release expired claims (claimed_at + ttl < now) back to `ready`, OR release
+   * a specific card by id regardless of expiry. Cleared claim fields.
+   * Returns the ids that were released.
+   */
+  async reclaim(opts: { id?: string } = {}): Promise<ReclaimResult> {
+    if (opts.id) {
+      const released = await this.db
+        .update(backlog)
+        .set({
+          status: 'ready',
+          claimOwner: null,
+          claimTtlSeconds: null,
+          claimedAt: null,
+          updatedAt: new Date(),
+        })
+        .where(and(eq(backlog.id, opts.id), eq(backlog.status, 'claimed')))
+        .returning({ id: backlog.id });
+      return { reclaimed: released.map((r) => r.id) };
+    }
+
+    // Expired = status claimed AND claimed_at + (ttl seconds) < now().
+    const released = await this.db
+      .update(backlog)
+      .set({
+        status: 'ready',
+        claimOwner: null,
+        claimTtlSeconds: null,
+        claimedAt: null,
+        updatedAt: new Date(),
+      })
+      .where(
+        and(
+          eq(backlog.status, 'claimed'),
+          sql`${backlog.claimedAt} + make_interval(secs => ${backlog.claimTtlSeconds}) < now()`,
+        ),
+      )
+      .returning({ id: backlog.id });
+    return { reclaimed: released.map((r) => r.id) };
+  }
+
+  /** Add a `depends_on` edge (from → depends on → to). Idempotent. */
+  async link(from: string, to: string): Promise<BacklogCard> {
+    const card = await this.get(from);
+    if (!card) throw new Error(`backlog card not found: ${from}`);
+    const target = await this.get(to);
+    if (!target) throw new Error(`backlog dependency not found: ${to}`);
+    if (from === to) throw new Error('a card cannot depend on itself');
+
+    if (card.dependsOn.includes(to)) return card;
+    const nextDeps = [...card.dependsOn, to];
+    const updated = await this.db
+      .update(backlog)
+      .set({ dependsOn: nextDeps, updatedAt: new Date() })
+      .where(eq(backlog.id, from))
+      .returning();
+    return toCard(updated[0]!);
+  }
+
+  /** Mark a card blocked. */
+  async block(id: string): Promise<BacklogCard | null> {
+    return this.setStatus(id, 'blocked');
+  }
+
+  /** Mark a card done (releasing any claim). */
+  async complete(id: string): Promise<BacklogCard | null> {
+    const updated = await this.db
+      .update(backlog)
+      .set({
+        status: 'done',
+        claimOwner: null,
+        claimTtlSeconds: null,
+        claimedAt: null,
+        updatedAt: new Date(),
+      })
+      .where(eq(backlog.id, id))
+      .returning();
+    return updated[0] ? toCard(updated[0]) : null;
+  }
+
+  private async setStatus(id: string, status: BacklogStatus): Promise<BacklogCard | null> {
+    const updated = await this.db
+      .update(backlog)
+      .set({ status, updatedAt: new Date() })
+      .where(eq(backlog.id, id))
+      .returning();
+    return updated[0] ? toCard(updated[0]) : null;
+  }
+
+  /** Counts by status, oldest-ready age (seconds), and expired-claim count. */
+  async stats(): Promise<BacklogStats> {
+    const all = await this.db.select().from(backlog);
+    const counts: Record<BacklogStatus, number> = {
+      ready: 0,
+      claimed: 0,
+      blocked: 0,
+      done: 0,
+    };
+    let oldestReady: Date | null = null;
+    let expiredClaimCount = 0;
+    const now = Date.now();
+
+    for (const row of all) {
+      counts[row.status] += 1;
+      if (row.status === 'ready') {
+        if (oldestReady === null || row.createdAt < oldestReady) oldestReady = row.createdAt;
+      }
+      if (row.status === 'claimed' && row.claimedAt && row.claimTtlSeconds != null) {
+        const expiry = row.claimedAt.getTime() + row.claimTtlSeconds * 1000;
+        if (expiry < now) expiredClaimCount += 1;
+      }
+    }
+
+    return {
+      counts,
+      total: all.length,
+      oldestReadyAgeSeconds:
+        oldestReady === null ? null : Math.max(0, Math.floor((now - oldestReady.getTime()) / 1000)),
+      expiredClaimCount,
+    };
+  }
+}
+
+/** Extract rows from a drizzle `.execute()` result across drivers (pg / pglite). */
+function rowsOf(result: unknown): RawRow[] {
+  if (Array.isArray(result)) return result as RawRow[];
+  const maybe = result as { rows?: unknown };
+  if (maybe && Array.isArray(maybe.rows)) return maybe.rows as RawRow[];
+  return [];
+}
+
+/**
+ * Map a raw `RETURNING *` row (snake_case columns, possibly string-encoded
+ * timestamps/JSON depending on the driver) onto the drizzle `Row` shape that
+ * `toCard` consumes. Mirrors the column ↔ property mapping in `schema.ts`.
+ */
+function rawToRow(raw: RawRow): Row {
+  const r = raw as unknown as Record<string, unknown>;
+  const toDate = (v: unknown): Date => (v instanceof Date ? v : new Date(v as string));
+  return {
+    id: r.id as string,
+    title: r.title as string,
+    body: (r.body ?? null) as string | null,
+    phase: (r.phase ?? null) as string | null,
+    priority: Number(r.priority),
+    status: r.status as BacklogStatus,
+    dependsOn: normalizeDeps(r.depends_on),
+    claimOwner: (r.claim_owner ?? null) as string | null,
+    claimTtlSeconds: r.claim_ttl_seconds == null ? null : Number(r.claim_ttl_seconds),
+    claimedAt: r.claimed_at == null ? null : toDate(r.claimed_at),
+    attempts: Number(r.attempts),
+    idempotencyKey: (r.idempotency_key ?? null) as string | null,
+    acceptance: r.acceptance ?? null,
+    createdAt: toDate(r.created_at),
+    updatedAt: toDate(r.updated_at),
+  };
+}
+
+/** A raw SQL row returns snake_case `depends_on`; normalize to string[]. */
+function normalizeDeps(value: unknown): string[] {
+  if (Array.isArray(value)) return value as string[];
+  if (typeof value === 'string') {
+    try {
+      const parsed = JSON.parse(value);
+      return Array.isArray(parsed) ? (parsed as string[]) : [];
+    } catch {
+      return [];
+    }
+  }
+  return [];
+}

packages/db/src/index.ts

@@ -3,6 +3,17 @@ export { createPgliteDb } from './client-pglite.js';
 export { runMigrations, runPgliteMigrations } from './migrate.js';
 export * from './schema.js';
 export * from './federation.js';
+export {
+  BacklogService,
+  DEFAULT_CLAIM_TTL_SECONDS,
+  type BacklogCard,
+  type BacklogStatus,
+  type BacklogStats,
+  type ClaimOptions,
+  type CreateCardInput,
+  type ListFilter,
+  type ReclaimResult,
+} from './backlog.js';
 export {
   eq,
   and,

packages/db/src/schema.ts

@@ -587,6 +587,62 @@ export const summarizationJobs = pgTable(
   (t) => [index('summarization_jobs_status_idx').on(t.status)],
 );
 
+// ─── Fleet Backlog ────────────────────────────────────────────────────────────
+// Mosaic-native backlog-of-record (card A4). This REPLACES the former Hermes
+// adapter — there is NO runtime dependency on Hermes. Cards form a dependency
+// DAG (`depends_on`), are claimed atomically by fleet workers via
+// `SELECT ... FOR UPDATE SKIP LOCKED`, and auto-expire via a TTL so a crashed
+// claimer's card returns to the pool.
+
+/**
+ * Lifecycle status of a backlog card.
+ * - ready:   eligible to be claimed (once its deps are all `done`).
+ * - claimed: a worker holds it (claim_owner + claimed_at set); may expire via TTL.
+ * - blocked: explicitly parked; never auto-claimed.
+ * - done:    completed; satisfies dependents.
+ */
+export const backlogStatusEnum = pgEnum('backlog_status', ['ready', 'claimed', 'blocked', 'done']);
+
+export const backlog = pgTable(
+  'backlog',
+  {
+    /** Stable, caller-supplied card id (e.g. "A4", "fleet-001"). PK. */
+    id: text('id').primaryKey(),
+    title: text('title').notNull(),
+    body: text('body'),
+    /** Board/phase grouping (e.g. "M1", "fleet"). Free-form. */
+    phase: text('phase'),
+    /** Higher number = higher priority; claim picks the max-priority ready card. */
+    priority: integer('priority').notNull().default(0),
+    status: backlogStatusEnum('status').notNull().default('ready'),
+    /** DAG edges: ids of cards this one depends on. "ready" requires all done. */
+    dependsOn: jsonb('depends_on').notNull().$type<string[]>().default([]),
+    /** Owner token of the current claim (worker/agent id). NULL when unclaimed. */
+    claimOwner: text('claim_owner'),
+    /** TTL of the active claim in seconds. NULL when unclaimed. */
+    claimTtlSeconds: integer('claim_ttl_seconds'),
+    /** When the active claim was taken. NULL when unclaimed. claimed_at + ttl = expiry. */
+    claimedAt: timestamp('claimed_at', { withTimezone: true }),
+    /** Count of times this card has been claimed (incremented on each claim). */
+    attempts: integer('attempts').notNull().default(0),
+    /** Optional dedup key for `create`; a repeat key returns the existing card. */
+    idempotencyKey: text('idempotency_key'),
+    /** Acceptance criteria — free-form JSON (array of strings or object). */
+    acceptance: jsonb('acceptance'),
+    createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
+    updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
+  },
+  (t) => [
+    // Hot path: claim scans ready cards ordered by priority then age.
+    index('backlog_status_priority_idx').on(t.status, t.priority),
+    // reclaim sweeps claimed cards by claimed_at to find expired ones.
+    index('backlog_status_claimed_at_idx').on(t.status, t.claimedAt),
+    // Idempotent create dedups on this key (NULLs are distinct in Postgres, so
+    // many unkeyed cards coexist; a repeated non-null key collides).
+    uniqueIndex('backlog_idempotency_key_idx').on(t.idempotencyKey),
+  ],
+);
+
 // ─── Federation ──────────────────────────────────────────────────────────────
 // Enums declared before tables that reference them.
 // All federation definitions live in this file (avoids CJS/ESM cross-import

packages/db/vitest.config.ts

@@ -4,5 +4,22 @@ export default defineConfig({
   test: {
     globals: true,
     environment: 'node',
+    // The migration suite spins up a real PGlite (WASM Postgres) instance per
+    // test and applies the full drizzle migration set. Each case legitimately
+    // takes ~5s locally and considerably longer on CI, where turbo runs many
+    // packages' test suites concurrently. The 5s vitest default then expires
+    // mid-migration and the run fails as a phantom "Test timed out in 5000ms"
+    // (often surfacing the underlying WASM `memory access out of bounds` when
+    // the heap is starved). Give migrations real headroom.
+    testTimeout: 120_000,
+    hookTimeout: 120_000,
+    // Each PGlite instance carries a multi-hundred-MB WASM heap. Running test
+    // files in parallel forks multiplies that peak and is what tips the CI
+    // runner into the WASM OOM. A single fork keeps only one instance resident
+    // at a time — slightly slower, but deterministic.
+    pool: 'forks',
+    poolOptions: {
+      forks: { singleFork: true },
+    },
   },
 });

packages/log/src/index.ts

@@ -10,3 +10,8 @@ export {
   type LogQuery,
 } from './agent-logs.js';
 export { registerLogCommand } from './cli.js';
+export {
+  redactSensitiveContent,
+  type RedactionResult,
+  type SensitiveClassification,
+} from './redaction.js';

packages/log/src/redaction.spec.ts

@@ -0,0 +1,25 @@
+import { describe, expect, it } from 'vitest';
+import { redactSensitiveContent } from './redaction.js';
+
+describe('redactSensitiveContent', (): void => {
+  it('redacts seeded secret and PII canaries before persistence or egress', (): void => {
+    const result = redactSensitiveContent(
+      'email canary@example.test token=sk_CANARY12345678 phone +1 555 555 1212',
+    );
+    expect(result.content).not.toContain('canary@example.test');
+    expect(result.content).not.toContain('sk_CANARY12345678');
+    expect(result.content).not.toContain('+1 555 555 1212');
+    expect(result.classifications).toEqual(['secret', 'pii']);
+  });
+
+  it('redacts common provider credential formats', (): void => {
+    const result = redactSensitiveContent(
+      'Authorization: Bearer canary.bearer.token jwt eyJcanary.eyJpayload.eyJsignature aws AKIACANARY1234567890',
+    );
+
+    expect(result.content).not.toContain('canary.bearer.token');
+    expect(result.content).not.toContain('eyJcanary.eyJpayload.eyJsignature');
+    expect(result.content).not.toContain('AKIACANARY1234567890');
+    expect(result.classifications).toEqual(['secret']);
+  });
+});

packages/log/src/redaction.ts

@@ -0,0 +1,40 @@
+export type SensitiveClassification = 'secret' | 'pii';
+
+export interface RedactionResult {
+  content: string;
+  classifications: SensitiveClassification[];
+}
+
+const SECRET_PATTERNS: RegExp[] = [
+  /\b(?:sk|ghp|gitea)_[A-Za-z0-9_-]{8,}\b/g,
+  /\b(?:api[_-]?key|token|password|secret)\s*[:=]\s*[^\s,;]+/gi,
+  /\b(?:authorization\s*:\s*)?bearer\s+[A-Za-z0-9._~+/-]+=*/gi,
+  /\beyJ[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+\b/g,
+  /\b(?:AKIA|ASIA)[A-Z0-9]{16}\b/g,
+  /-----BEGIN(?: [A-Z]+)* KEY-----[\s\S]*?-----END(?: [A-Z]+)* KEY-----/g,
+  /https?:\/\/[^\s?#]+[^\s]*[?&](?:token|key|secret|signature|sig)=[^\s&#]+/gi,
+];
+const PII_PATTERNS: RegExp[] = [
+  /\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b/gi,
+  /\b\+?\d[\d(). -]{7,}\d\b/g,
+];
+
+export function redactSensitiveContent(content: string): RedactionResult {
+  let redacted = content;
+  const classifications: SensitiveClassification[] = [];
+  for (const pattern of SECRET_PATTERNS) {
+    if (pattern.test(redacted)) {
+      classifications.push('secret');
+      redacted = redacted.replace(pattern, '[REDACTED_SECRET]');
+    }
+    pattern.lastIndex = 0;
+  }
+  for (const pattern of PII_PATTERNS) {
+    if (pattern.test(redacted)) {
+      classifications.push('pii');
+      redacted = redacted.replace(pattern, '[REDACTED_PII]');
+    }
+    pattern.lastIndex = 0;
+  }
+  return { content: redacted, classifications: [...new Set(classifications)] };
+}

packages/mosaic/framework/fleet/profiles/business.yaml

@@ -0,0 +1,30 @@
+id: business
+title: Business (Company-in-a-Box)
+description: >-
+  A full company org: the CEO sets direction, the COO and CFO run execution and
+  finance, and the functional leads (product, marketing, sales, operations,
+  customer success) plus a small engineering slice deliver the work. reports_to
+  encodes the org chart.
+lead: ceo
+floor:
+  - ceo
+roster:
+  - class: ceo
+  - class: coo
+    reports_to: ceo
+  - class: cfo
+    reports_to: ceo
+  - class: product-manager
+    reports_to: coo
+  - class: marketing-lead
+    reports_to: coo
+  - class: sales-lead
+    reports_to: coo
+  - class: operations-manager
+    reports_to: coo
+  - class: customer-success-manager
+    reports_to: coo
+  - class: code
+    reports_to: product-manager
+  - class: review
+    reports_to: product-manager

packages/mosaic/framework/fleet/profiles/marketing.yaml

@@ -0,0 +1,25 @@
+id: marketing
+title: Marketing
+description: >-
+  A marketing org that owns strategy, content, channels, and growth. The
+  marketing-lead sets strategy and budget and runs a roster of content, copy,
+  SEO, social, brand, growth, and UX specialists.
+lead: marketing-lead
+floor:
+  - marketing-lead
+roster:
+  - class: marketing-lead
+  - class: content-strategist
+    reports_to: marketing-lead
+  - class: copywriter
+    reports_to: content-strategist
+  - class: seo-specialist
+    reports_to: marketing-lead
+  - class: social-media-manager
+    reports_to: content-strategist
+  - class: brand-strategist
+    reports_to: marketing-lead
+  - class: growth-marketer
+    reports_to: marketing-lead
+  - class: ux-designer
+    reports_to: marketing-lead

packages/mosaic/framework/fleet/profiles/personal-assistant.yaml

@@ -0,0 +1,19 @@
+id: personal-assistant
+title: Personal Assistant
+description: >-
+  A personal-logistics fleet for one principal: handles errands, reminders,
+  calendar, inbox triage, and ad-hoc lookups. The personal-assistant leads and
+  delegates scheduling, inbox triage, and research to specialist seats.
+lead: personal-assistant
+floor:
+  - personal-assistant
+roster:
+  - class: personal-assistant
+  - class: executive-assistant
+    reports_to: personal-assistant
+  - class: scheduler
+    reports_to: executive-assistant
+  - class: inbox-manager
+    reports_to: personal-assistant
+  - class: researcher
+    reports_to: personal-assistant

packages/mosaic/framework/fleet/profiles/research.yaml

@@ -0,0 +1,24 @@
+id: research
+title: Research
+description: >-
+  A research fleet that decomposes a question, gathers and analyzes evidence, and
+  synthesizes cited findings. The lead-researcher owns the agenda and assigns
+  individual questions to researchers and the analytics seats.
+lead: lead-researcher
+floor:
+  - lead-researcher
+roster:
+  - class: lead-researcher
+  - class: researcher
+    reports_to: lead-researcher
+    multiplicity: 2
+  - class: data-analyst
+    reports_to: lead-researcher
+  - class: data-scientist
+    reports_to: lead-researcher
+  - class: market-analyst
+    reports_to: lead-researcher
+  - class: documentation
+    reports_to: lead-researcher
+  - class: review
+    reports_to: lead-researcher

packages/mosaic/framework/fleet/profiles/software-delivery.yaml

@@ -0,0 +1,75 @@
+# Mosaic system-type profile — SCHEMA REFERENCE
+# ---------------------------------------------------------------------------
+# A profile is a DECLARATIVE mapping from a "system type" to a persona roster
+# plus its org topology. Profiles are DATA: drop a new <id>.yaml here and the
+# loader/CLI pick it up with no code change (North Star NS-9 / AC-NS-6).
+#
+# Every persona referenced below (lead, floor[], roster[].class, roster[].reports_to)
+# MUST resolve to a real persona in the library. The loader validates this against
+# the role contracts in ../roles/*.md (see LIBRARY.md for the grouped index).
+#
+# Schema (this file documents every key; other profiles omit the comments):
+#
+#   id:           kebab-case system-type id — MUST equal the filename stem.
+#   title:        human-readable name.
+#   description:  one paragraph — what this system does.
+#   lead:         persona class that coordinates the roster (the orchestrating seat).
+#   floor:        persistent minimum roster that must stay staffed (list of classes).
+#   roster:       the full default roster. Each entry:
+#                   - class:        persona class (MUST resolve to a role file).
+#                     reports_to:   optional — the class this seat reports to
+#                                   (encodes org topology). Omit for the lead.
+#                                   MUST resolve to a class present in this roster.
+#                     multiplicity: optional int (default 1) — e.g. 2 coders.
+#   notes:        optional free text.
+# ---------------------------------------------------------------------------
+id: software-delivery
+title: Software Delivery
+description: >-
+  The engineering fleet that turns ratified objectives into shipped, reviewed,
+  merged code. The lead (orchestrator) runs the supervisor loop and dispatches
+  ready work; it hands goal-decomposition to the planner, which plans phased FRs
+  into a depends_on DAG, decomposition splits them into one-PR-each cards, coders
+  execute to green CI, and review / security-review / site-tester / merge-gate
+  guard the merge. This mirrors today's coding fleet.
+# NOTE: the lead seat is the dedicated "orchestrator" — the always-on coordinator
+# that runs the supervisor tick, dispatches ready work, and routes PRs to the
+# merge-gate while holding only lean coordination state. The planner is now a
+# distinct seat (heavy goal-decomposition context) that reports to the
+# orchestrator. The two-agent floor is orchestrator + enhancer.
+lead: orchestrator
+floor:
+  - orchestrator
+  - enhancer
+roster:
+  - class: orchestrator
+  - class: board
+    reports_to: orchestrator
+  - class: planner
+    reports_to: orchestrator
+  - class: decomposition
+    reports_to: planner
+  - class: code
+    reports_to: decomposition
+    multiplicity: 2
+  - class: review
+    reports_to: orchestrator
+  - class: security-review
+    reports_to: review
+  - class: site-tester
+    reports_to: review
+  - class: documentation
+    reports_to: orchestrator
+  - class: merge-gate
+    reports_to: orchestrator
+  - class: rebase
+    reports_to: merge-gate
+  - class: operator
+    reports_to: orchestrator
+  - class: session-review
+    reports_to: orchestrator
+  - class: enhancer
+    reports_to: orchestrator
+notes: >-
+  Two-agent floor (orchestrator + enhancer) is always staffed; every other seat is
+  added on demand.

packages/mosaic/framework/fleet/roles/LIBRARY.md

@@ -0,0 +1,119 @@
+# Persona Library — fleet role index
+
+This is the discoverable index of the fleet's **persona role library**. Mosaic is
+a general-purpose multi-agent system: the operator declares a _system type_
+(software delivery, personal assistant, research, business/operations, marketing,
+…) and the orchestrator provisions a matching roster by drawing personas from this
+library.
+
+Each row points at a `*.md` role contract in this directory. The two-agent floor
+(**orchestrator** + **enhancer**) is always present; every other persona is added
+on demand. Engineering personas have no explicit `domain:` marker (they are the
+implicit `engineering` domain); cross-domain personas carry a `domain:` key in
+their intro so tooling can group them.
+
+> This file is an index only — no code imports it. To add a persona, drop a new
+> `*.md` next to the others (mirroring the existing structure) and add a row here.
+
+## engineering
+
+| Persona         | Purpose                                                                        |
+| --------------- | ------------------------------------------------------------------------------ |
+| orchestrator    | Always-on coordinator — runs the supervisor loop, dispatches ready work        |
+| board           | Multi-lens deliberation panel; owns the mission's direction, not its execution |
+| planner         | Turns ratified objectives into a phased FR plan wired into a `depends_on` DAG  |
+| decomposition   | Splits FRs into one-PR-each cards wired with `depends_on` edges                |
+| code            | Primary executor — one card, one branch, one PR to green CI                    |
+| review          | Correctness reviewer — judges an open PR on correctness, scope, and coverage   |
+| security-review | Second line of review — secrets, auth, and forbidden-path safety               |
+| site-tester     | Runtime verifier — runs the change and checks behavior vs. acceptance criteria |
+| documentation   | Prose maintainer — keeps human-facing docs and projections in sync             |
+| merge-gate      | Sole approver and auto-merger — the single chokepoint every PR passes through  |
+| rebase          | Freshness keeper — restores stale / unmergeable PR branches or escalates       |
+| operator        | Escalation and control surface — owns exceptions and the fleet pause switch    |
+| session-review  | Post-task retrospective — turns finished work into improvement signals         |
+| enhancer        | Continuous-improvement loop — upgrades the fleet's tools, skills, and harness  |
+
+## executive
+
+| Persona        | Purpose                                                                        |
+| -------------- | ------------------------------------------------------------------------------ |
+| ceo            | Direction-setter and final arbiter — owns the mission's _why_ and _whether_    |
+| coo            | Runs execution and operations — turns strategy into a running machine          |
+| cfo            | Owns financial truth — budgets, runway, and unit economics                     |
+| cto            | Owns technical strategy and architecture direction at the executive level      |
+| chief-of-staff | Force-multiplier for the exec seat — drives priorities, unblocks, runs cadence |
+
+## product
+
+| Persona         | Purpose                                                                     |
+| --------------- | --------------------------------------------------------------------------- |
+| product-manager | Owns the roadmap and problem definition — decides _what_ to build and _why_ |
+| ux-designer     | Owns interaction and flow design — the usability of the experience          |
+| user-researcher | Owns generative and evaluative research — turns user evidence into insight  |
+
+## marketing
+
+| Persona              | Purpose                                                                  |
+| -------------------- | ------------------------------------------------------------------------ |
+| marketing-lead       | Owns marketing strategy, channel mix, and budget; runs the roster        |
+| content-strategist   | Owns the content plan, editorial calendar, and content-to-funnel mapping |
+| copywriter           | Writes the actual copy — ads, landing pages, and emails                  |
+| seo-specialist       | Owns organic search — keyword strategy, on-page/technical SEO, SERPs     |
+| social-media-manager | Owns social presence, posting cadence, and community engagement          |
+| brand-strategist     | Owns brand positioning, voice, and identity guardrails                   |
+| growth-marketer      | Owns funnel experiments — acquisition, activation, and retention loops   |
+
+## sales
+
+| Persona               | Purpose                                                     |
+| --------------------- | ----------------------------------------------------------- |
+| sales-lead            | Owns sales strategy, pipeline targets, and the sales roster |
+| account-executive     | Owns deals from qualified opportunity through to close      |
+| sales-development-rep | Owns top-of-funnel qualification and booking meetings       |
+
+## operations
+
+| Persona            | Purpose                                                                  |
+| ------------------ | ------------------------------------------------------------------------ |
+| operations-manager | Owns running processes, throughput, and operational SLAs day-to-day      |
+| project-manager    | Owns scope, schedule, and delivery of a defined project                  |
+| business-analyst   | Owns requirements gathering, process mapping, and turning needs to specs |
+| hr-generalist      | Owns people operations — onboarding, policy, and employee relations      |
+| recruiter          | Owns sourcing, screening, and filling open roles                         |
+| legal-counsel      | Owns contracts, compliance, and legal-risk review                        |
+| finance-analyst    | Owns financial modeling, reporting, and decision-support analysis        |
+
+## research
+
+| Persona         | Purpose                                                                    |
+| --------------- | -------------------------------------------------------------------------- |
+| lead-researcher | Owns the research agenda — decomposes questions and synthesizes findings   |
+| researcher      | Executes a single research question — gathers, extracts, drafts findings   |
+| data-analyst    | Owns descriptive analysis, dashboards, and "what happened" from data       |
+| data-scientist  | Owns modeling, statistical inference, and predictive/experimental analysis |
+| market-analyst  | Owns market sizing, competitive landscape, and trend analysis              |
+
+## assistant
+
+| Persona             | Purpose                                                             |
+| ------------------- | ------------------------------------------------------------------- |
+| personal-assistant  | Owns the principal's personal logistics, reminders, and errands     |
+| executive-assistant | Owns an executive's calendar, travel, meeting prep, and gatekeeping |
+| scheduler           | Owns conflict-free meeting booking across multiple parties          |
+| inbox-manager       | Owns triage, drafting, and routing of incoming messages             |
+
+## customer
+
+| Persona                  | Purpose                                                          |
+| ------------------------ | ---------------------------------------------------------------- |
+| customer-success-manager | Owns post-sale adoption, retention, and renewal for accounts     |
+| support-agent            | Owns resolving individual customer issues and tickets to closure |
+
+## creative
+
+| Persona          | Purpose                                                           |
+| ---------------- | ----------------------------------------------------------------- |
+| graphic-designer | Owns visual assets — layouts and graphics executed to brand spec  |
+| video-producer   | Owns video from concept through shoot/assembly to delivery        |
+| editor           | Refines and polishes existing content for clarity and consistency |

packages/mosaic/framework/fleet/roles/account-executive.md

@@ -0,0 +1,39 @@
+# Account Executive — fleet role definition
+
+The **account-executive** is the deal-level **closer and quota carrier**
+(`class: account-executive`, `domain: sales`). It owns each opportunity from the
+moment it is qualified to the moment it is won or lost, running the deal cycle
+the **sales-lead** designed the field for.
+
+It is a **persistent** role (`persistent_persona: true`) but task-oriented in
+practice: the seat stays staffed against a quota, while its day-to-day work is
+the set of live deals it is driving at any moment.
+
+## Mandate
+
+1. **Own deals to close** — take each qualified opportunity through discovery,
+   proposal, negotiation, and signature, and own the outcome.
+2. **Carry and hit the quota** — manage a personal number, prioritize the deals
+   most likely to land in-period, and report honest commit/best-case calls.
+3. **Run a clean pipeline** — keep stages, next steps, and close dates accurate
+   so the rollup the **sales-lead** forecasts on is trustworthy.
+4. **Champion the customer internally** — surface real requirements and risks so
+   the deal that closes is one the system can actually deliver.
+
+## Boundaries
+
+- **Does NOT set strategy or quota** — territory, targets, and motion are the
+  **sales-lead**'s call; the AE executes within them.
+- **Does NOT prospect cold top-of-funnel** — meeting generation and first-touch
+  qualification are the **sales-development-rep**'s job; the AE picks up
+  qualified handoffs.
+- **Does NOT redline contracts unilaterally** — non-standard terms and risk go
+  to **legal-counsel** before commitment.
+
+## Persona
+
+A disciplined closer who lives in next-steps and mutual close plans. Its value
+is momentum without happy-ears: it qualifies hard, names blockers early, and
+never lets a stalled deal sit silently in the pipeline.
+
+> Doctrine: cross-domain persona library (sales); see `LIBRARY.md`.