chore(orchestrator): add MS22 PRD, mark P1a+P1b done

Reviewed-on: #607

apps/api/prisma/migrations/20260301144006_ms22_agent_fleet_schema/migration.sql

@@ -0,0 +1,109 @@
+-- CreateTable
+CREATE TABLE "SystemConfig" (
+    "id" TEXT NOT NULL,
+    "key" TEXT NOT NULL,
+    "value" TEXT NOT NULL,
+    "encrypted" BOOLEAN NOT NULL DEFAULT false,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "SystemConfig_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "BreakglassUser" (
+    "id" TEXT NOT NULL,
+    "username" TEXT NOT NULL,
+    "passwordHash" TEXT NOT NULL,
+    "isActive" BOOLEAN NOT NULL DEFAULT true,
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "BreakglassUser_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "LlmProvider" (
+    "id" TEXT NOT NULL,
+    "userId" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "displayName" TEXT NOT NULL,
+    "type" TEXT NOT NULL,
+    "baseUrl" TEXT,
+    "apiKey" TEXT,
+    "apiType" TEXT NOT NULL DEFAULT 'openai-completions',
+    "models" JSONB NOT NULL DEFAULT '[]',
+    "isActive" BOOLEAN NOT NULL DEFAULT true,
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "LlmProvider_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "UserContainer" (
+    "id" TEXT NOT NULL,
+    "userId" TEXT NOT NULL,
+    "containerId" TEXT,
+    "containerName" TEXT NOT NULL,
+    "gatewayPort" INTEGER,
+    "gatewayToken" TEXT NOT NULL,
+    "status" TEXT NOT NULL DEFAULT 'stopped',
+    "lastActiveAt" TIMESTAMP(3),
+    "idleTimeoutMin" INTEGER NOT NULL DEFAULT 30,
+    "config" JSONB NOT NULL DEFAULT '{}',
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "UserContainer_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "SystemContainer" (
+    "id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "role" TEXT NOT NULL,
+    "containerId" TEXT,
+    "gatewayPort" INTEGER,
+    "gatewayToken" TEXT NOT NULL,
+    "status" TEXT NOT NULL DEFAULT 'stopped',
+    "primaryModel" TEXT NOT NULL,
+    "isActive" BOOLEAN NOT NULL DEFAULT true,
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "SystemContainer_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "UserAgentConfig" (
+    "id" TEXT NOT NULL,
+    "userId" TEXT NOT NULL,
+    "primaryModel" TEXT,
+    "fallbackModels" JSONB NOT NULL DEFAULT '[]',
+    "personality" TEXT,
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "UserAgentConfig_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "SystemConfig_key_key" ON "SystemConfig"("key");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "BreakglassUser_username_key" ON "BreakglassUser"("username");
+
+-- CreateIndex
+CREATE INDEX "LlmProvider_userId_idx" ON "LlmProvider"("userId");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "LlmProvider_userId_name_key" ON "LlmProvider"("userId", "name");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "UserContainer_userId_key" ON "UserContainer"("userId");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "SystemContainer_name_key" ON "SystemContainer"("name");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "UserAgentConfig_userId_key" ON "UserAgentConfig"("userId");

apps/api/prisma/schema.prisma

@@ -1625,3 +1625,81 @@ model ConversationArchive {
   @@index([startedAt])
   @@map("conversation_archives")
 }
+
+// ============================================
+// AGENT FLEET MODULE
+// ============================================
+
+model SystemConfig {
+  id        String   @id @default(cuid())
+  key       String   @unique
+  value     String
+  encrypted Boolean  @default(false)
+  updatedAt DateTime @updatedAt
+}
+
+model BreakglassUser {
+  id           String   @id @default(cuid())
+  username     String   @unique
+  passwordHash String
+  isActive     Boolean  @default(true)
+  createdAt    DateTime @default(now())
+  updatedAt    DateTime @updatedAt
+}
+
+model LlmProvider {
+  id          String   @id @default(cuid())
+  userId      String
+  name        String
+  displayName String
+  type        String
+  baseUrl     String?
+  apiKey      String?
+  apiType     String   @default("openai-completions")
+  models      Json     @default("[]")
+  isActive    Boolean  @default(true)
+  createdAt   DateTime @default(now())
+  updatedAt   DateTime @updatedAt
+
+  @@unique([userId, name])
+  @@index([userId])
+}
+
+model UserContainer {
+  id             String   @id @default(cuid())
+  userId         String   @unique
+  containerId    String?
+  containerName  String
+  gatewayPort    Int?
+  gatewayToken   String
+  status         String   @default("stopped")
+  lastActiveAt   DateTime?
+  idleTimeoutMin Int      @default(30)
+  config         Json     @default("{}")
+  createdAt      DateTime @default(now())
+  updatedAt      DateTime @updatedAt
+}
+
+model SystemContainer {
+  id           String   @id @default(cuid())
+  name         String   @unique
+  role         String
+  containerId  String?
+  gatewayPort  Int?
+  gatewayToken String
+  status       String   @default("stopped")
+  primaryModel String
+  isActive     Boolean  @default(true)
+  createdAt    DateTime @default(now())
+  updatedAt    DateTime @updatedAt
+}
+
+model UserAgentConfig {
+  id             String   @id @default(cuid())
+  userId         String   @unique
+  primaryModel   String?
+  fallbackModels Json     @default("[]")
+  personality    String?
+  createdAt      DateTime @default(now())
+  updatedAt      DateTime @updatedAt
+}

apps/api/src/app.module.ts

@@ -39,6 +39,7 @@ import { JobStepsModule } from "./job-steps/job-steps.module";
 import { CoordinatorIntegrationModule } from "./coordinator-integration/coordinator-integration.module";
 import { FederationModule } from "./federation/federation.module";
 import { CredentialsModule } from "./credentials/credentials.module";
+import { CryptoModule } from "./crypto/crypto.module";
 import { MosaicTelemetryModule } from "./mosaic-telemetry";
 import { SpeechModule } from "./speech/speech.module";
 import { DashboardModule } from "./dashboard/dashboard.module";
@@ -111,6 +112,7 @@ import { RlsContextInterceptor } from "./common/interceptors/rls-context.interce
     CoordinatorIntegrationModule,
     FederationModule,
     CredentialsModule,
+    CryptoModule,
     MosaicTelemetryModule,
     SpeechModule,
     DashboardModule,

apps/api/src/crypto/crypto.module.ts

@@ -0,0 +1,10 @@
+import { Module } from "@nestjs/common";
+import { ConfigModule } from "@nestjs/config";
+import { CryptoService } from "./crypto.service";
+
+@Module({
+  imports: [ConfigModule],
+  providers: [CryptoService],
+  exports: [CryptoService],
+})
+export class CryptoModule {}

apps/api/src/crypto/crypto.service.spec.ts

@@ -0,0 +1,71 @@
+import { describe, it, expect, beforeEach } from "vitest";
+import { ConfigService } from "@nestjs/config";
+import { CryptoService } from "./crypto.service";
+
+function createConfigService(secret?: string): ConfigService {
+  return {
+    get: (key: string) => {
+      if (key === "MOSAIC_SECRET_KEY") {
+        return secret;
+      }
+      return undefined;
+    },
+  } as unknown as ConfigService;
+}
+
+describe("CryptoService", () => {
+  let service: CryptoService;
+
+  beforeEach(() => {
+    service = new CryptoService(createConfigService("this-is-a-test-secret-key-with-32+chars"));
+  });
+
+  it("encrypt -> decrypt roundtrip", () => {
+    const plaintext = "my-secret-api-key";
+
+    const encrypted = service.encrypt(plaintext);
+    const decrypted = service.decrypt(encrypted);
+
+    expect(encrypted.startsWith("enc:")).toBe(true);
+    expect(decrypted).toBe(plaintext);
+  });
+
+  it("decrypt rejects tampered ciphertext", () => {
+    const encrypted = service.encrypt("sensitive-token");
+    const payload = encrypted.slice(4);
+    const bytes = Buffer.from(payload, "base64");
+
+    bytes[bytes.length - 1] = bytes[bytes.length - 1]! ^ 0xff;
+
+    const tampered = `enc:${bytes.toString("base64")}`;
+
+    expect(() => service.decrypt(tampered)).toThrow();
+  });
+
+  it("decrypt rejects non-encrypted string", () => {
+    expect(() => service.decrypt("plain-text-value")).toThrow();
+  });
+
+  it("isEncrypted detects prefix correctly", () => {
+    expect(service.isEncrypted("enc:abc")).toBe(true);
+    expect(service.isEncrypted("ENC:abc")).toBe(false);
+    expect(service.isEncrypted("plain-text")).toBe(false);
+  });
+
+  it("generateToken returns 64-char hex string", () => {
+    const token = service.generateToken();
+
+    expect(token).toMatch(/^[0-9a-f]{64}$/);
+  });
+
+  it("different plaintexts produce different ciphertexts (random IV)", () => {
+    const encryptedA = service.encrypt("value-a");
+    const encryptedB = service.encrypt("value-b");
+
+    expect(encryptedA).not.toBe(encryptedB);
+  });
+
+  it("missing MOSAIC_SECRET_KEY throws on construction", () => {
+    expect(() => new CryptoService(createConfigService(undefined))).toThrow();
+  });
+});

apps/api/src/crypto/crypto.service.ts

@@ -0,0 +1,82 @@
+import { Injectable } from "@nestjs/common";
+import { ConfigService } from "@nestjs/config";
+import { createCipheriv, createDecipheriv, hkdfSync, randomBytes } from "crypto";
+
+const ALGORITHM = "aes-256-gcm";
+const ENCRYPTED_PREFIX = "enc:";
+const IV_LENGTH = 12;
+const AUTH_TAG_LENGTH = 16;
+const DERIVED_KEY_LENGTH = 32;
+const HKDF_SALT = "mosaic.crypto.v1";
+const HKDF_INFO = "mosaic-db-secret-encryption";
+
+@Injectable()
+export class CryptoService {
+  private readonly key: Buffer;
+
+  constructor(private readonly config: ConfigService) {
+    const secret = this.config.get<string>("MOSAIC_SECRET_KEY");
+
+    if (!secret) {
+      throw new Error("MOSAIC_SECRET_KEY environment variable is required");
+    }
+
+    if (secret.length < 32) {
+      throw new Error("MOSAIC_SECRET_KEY must be at least 32 characters");
+    }
+
+    this.key = Buffer.from(
+      hkdfSync(
+        "sha256",
+        Buffer.from(secret, "utf8"),
+        Buffer.from(HKDF_SALT, "utf8"),
+        Buffer.from(HKDF_INFO, "utf8"),
+        DERIVED_KEY_LENGTH
+      )
+    );
+  }
+
+  encrypt(plaintext: string): string {
+    const iv = randomBytes(IV_LENGTH);
+    const cipher = createCipheriv(ALGORITHM, this.key, iv);
+    const ciphertext = Buffer.concat([cipher.update(plaintext, "utf8"), cipher.final()]);
+    const authTag = cipher.getAuthTag();
+    const payload = Buffer.concat([iv, ciphertext, authTag]).toString("base64");
+
+    return `${ENCRYPTED_PREFIX}${payload}`;
+  }
+
+  decrypt(encrypted: string): string {
+    if (!this.isEncrypted(encrypted)) {
+      throw new Error("Value is not encrypted");
+    }
+
+    const payloadBase64 = encrypted.slice(ENCRYPTED_PREFIX.length);
+
+    try {
+      const payload = Buffer.from(payloadBase64, "base64");
+      if (payload.length < IV_LENGTH + AUTH_TAG_LENGTH) {
+        throw new Error("Encrypted payload is too short");
+      }
+
+      const iv = payload.subarray(0, IV_LENGTH);
+      const authTag = payload.subarray(payload.length - AUTH_TAG_LENGTH);
+      const ciphertext = payload.subarray(IV_LENGTH, payload.length - AUTH_TAG_LENGTH);
+
+      const decipher = createDecipheriv(ALGORITHM, this.key, iv);
+      decipher.setAuthTag(authTag);
+
+      return Buffer.concat([decipher.update(ciphertext), decipher.final()]).toString("utf8");
+    } catch {
+      throw new Error("Failed to decrypt value");
+    }
+  }
+
+  isEncrypted(value: string): boolean {
+    return value.startsWith(ENCRYPTED_PREFIX);
+  }
+
+  generateToken(): string {
+    return randomBytes(32).toString("hex");
+  }
+}

docs/PRD-MS22.md

@@ -0,0 +1,114 @@
+# PRD: MS22 — Fleet Evolution (DB-Centric Agent Architecture)
+
+## Metadata
+
+- Owner: Jason Woltje
+- Date: 2026-03-01
+- Status: in-progress
+- Design Doc: `docs/design/MS22-DB-CENTRIC-ARCHITECTURE.md`
+
+## Problem Statement
+
+Mosaic Stack needs a multi-user agent fleet where each user gets their own isolated OpenClaw instance with their own LLM provider credentials and agent config. The system must be Docker-first with minimal environment variables and all configuration managed through the WebUI.
+
+## Objectives
+
+1. **Minimal bootstrap** — 2 env vars (`DATABASE_URL`, `MOSAIC_SECRET_KEY`) to start the entire stack
+2. **DB-centric config** — All runtime config in Postgres, managed via WebUI
+3. **Per-user isolation** — Each user gets their own OpenClaw container with own API keys, memory, sessions
+4. **Onboarding wizard** — First-boot experience: breakglass admin → OIDC → LLM provider → agent config
+5. **Settings UI** — Runtime management of providers, agents, and auth config
+6. **Mosaic as gatekeeper** — Users never talk to OpenClaw directly; Mosaic proxies all requests
+7. **Zero cross-user access** — Full container, volume, and DB isolation between users
+
+## Security Requirements
+
+- User A cannot access User B's API keys, chat history, or agent memory
+- All API keys stored encrypted (AES-256-GCM) in database
+- Breakglass admin always works as OIDC fallback
+- OIDC config stored in DB (not env vars) — configured via settings UI
+- Container-to-container communication blocked by default
+- Admin cannot decrypt other users' API keys
+
+## Phase 0: Knowledge Layer — COMPLETE
+
+- Findings API (pgvector, CRUD, similarity search)
+- AgentMemory API (key/value store)
+- ConversationArchive API (pgvector, ingest, search)
+- OpenClaw mosaic skill
+- Session log ingestion pipeline
+
+## Phase 1: DB-Centric Agent Fleet
+
+### Phase 1a: DB Schema — COMPLETE
+
+- SystemConfig, BreakglassUser, LlmProvider, UserContainer, SystemContainer, UserAgentConfig tables
+
+### Phase 1b: Encryption Service — COMPLETE
+
+- CryptoService (AES-256-GCM using MOSAIC_SECRET_KEY)
+
+### Phase 1c: Internal Config API
+
+- `GET /api/internal/agent-config/:id` — assembles openclaw.json from DB
+- Auth: bearer token (container's own gateway token)
+- Returns complete openclaw.json with decrypted provider credentials
+
+### Phase 1d: Container Lifecycle Manager
+
+- Docker API integration via `dockerode` npm package
+- Start/stop/health-check/reap user containers
+- Auto-generate gateway tokens, assign ports
+- Docker socket access required (`/var/run/docker.sock`)
+
+### Phase 1e: Onboarding API
+
+- First-boot detection (`SystemConfig.onboarding.completed`)
+- `POST /api/onboarding/breakglass` — create admin user
+- `POST /api/onboarding/oidc` — save OIDC provider config
+- `POST /api/onboarding/provider` — add LLM provider + test connection
+- `POST /api/onboarding/complete` — mark done
+
+### Phase 1f: Onboarding Wizard UI
+
+- Multi-step wizard component
+- Skip-able OIDC step
+- LLM provider connection test
+
+### Phase 1g: Settings API
+
+- CRUD: LLM providers (per-user scoped)
+- CRUD: Agent config (model assignments, personalities)
+- CRUD: OIDC config (admin only)
+- Breakglass password reset (admin only)
+
+### Phase 1h: Settings UI
+
+- Settings/Providers page
+- Settings/Agent Config page
+- Settings/Auth page (OIDC + breakglass)
+
+### Phase 1i: Chat Proxy
+
+- Route WebUI chat to user's OpenClaw container
+- SSE streaming pass-through
+- Ensure container is running before proxying (auto-start)
+
+### Phase 1j: Docker Compose + Entrypoint
+
+- Simplified compose (core services only — user containers are dynamic)
+- Entrypoint: fetch config from API, write openclaw.json, start gateway
+- Health check integration
+
+### Phase 1k: Idle Reaper
+
+- Cron job to stop inactive user containers
+- Configurable idle timeout (default 30min)
+- Preserve state volumes
+
+## Future Phases (out of scope)
+
+- Phase 2: Agent fleet standup (predefined agent roles)
+- Phase 3: WebUI chat + task management integration
+- Phase 4: Multi-LLM provider management UI (advanced)
+- Team workspaces (shared agent contexts) — explicitly out of scope

docs/TASKS.md

@@ -71,3 +71,21 @@ Remaining estimate: ~143K tokens (Codex budget).
 | MS22-SKILL-001  | done   | p0-knowledge | OpenClaw mosaic skill (agents read/write findings/memory)    | TASKS:P0 | stack | feat/ms22-openclaw-skill       | MS22-API-001,MS22-API-002                                 | MS22-VER-P0   | —            | —          | —            | 15K      | —    | Skill in ~/.agents/skills/mosaic/             |
 | MS22-INGEST-001 | done   | p0-knowledge | Session log ingestion pipeline (OpenClaw logs → ConvArchive) | TASKS:P0 | stack | feat/ms22-ingest               | MS22-API-004                                              | MS22-VER-P0   | —            | —          | —            | 20K      | —    | Script to batch-ingest existing logs          |
 | MS22-VER-P0     | done   | p0-knowledge | Phase 0 verification: all modules deployed + smoke tested    | TASKS:P0 | stack | —                              | MS22-TEST-001,MS22-SKILL-001,MS22-INGEST-001,MS22-API-003 | —             | —            | —          | —            | 5K       | —    |                                               |
+
+## MS22 Phase 1: DB-Centric Agent Fleet (reworked)
+
+Design doc: `docs/design/MS22-DB-CENTRIC-ARCHITECTURE.md`
+
+| Task ID  | Status      | Phase    | Description                                                                                                           | Issue | Scope   | Branch                       | Depends On | Blocks          | Assigned Worker | Started | Completed | Est Tokens | Act Tokens | Notes |
+| -------- | ----------- | -------- | --------------------------------------------------------------------------------------------------------------------- | ----- | ------- | ---------------------------- | ---------- | --------------- | --------------- | ------- | --------- | ---------- | ---------- | ----- |
+| MS22-P1a | done        | phase-1a | Prisma schema: SystemConfig, BreakglassUser, LlmProvider, UserContainer, SystemContainer, UserAgentConfig + migration | —     | api     | feat/ms22-p1a-schema         | —          | P1b,P1c,P1d,P1e | —               | —       | —         | 20K        | —          |       |
+| MS22-P1b | done        | phase-1b | Encryption service (AES-256-GCM) for API keys and tokens                                                              | —     | api     | feat/ms22-p1b-crypto         | —          | P1c,P1e,P1g     | —               | —       | —         | 15K        | —          |       |
+| MS22-P1c | not-started | phase-1c | Internal config endpoint: assemble openclaw.json from DB                                                              | —     | api     | feat/ms22-p1c-config-api     | P1a,P1b    | P1i,P1j         | —               | —       | —         | 20K        | —          |       |
+| MS22-P1d | not-started | phase-1d | ContainerLifecycleService: Docker API (dockerode) start/stop/health/reap                                              | —     | api     | feat/ms22-p1d-container-mgr  | P1a        | P1i,P1k         | —               | —       | —         | 25K        | —          |       |
+| MS22-P1e | not-started | phase-1e | Onboarding API: breakglass, OIDC, provider, agents, complete                                                          | —     | api     | feat/ms22-p1e-onboarding-api | P1a,P1b    | P1f             | —               | —       | —         | 20K        | —          |       |
+| MS22-P1f | not-started | phase-1f | Onboarding wizard WebUI (multi-step form)                                                                             | —     | web     | feat/ms22-p1f-onboarding-ui  | P1e        | —               | —               | —       | —         | 25K        | —          |       |
+| MS22-P1g | not-started | phase-1g | Settings API: CRUD providers, agent config, OIDC, breakglass                                                          | —     | api     | feat/ms22-p1g-settings-api   | P1a,P1b    | P1h             | —               | —       | —         | 20K        | —          |       |
+| MS22-P1h | not-started | phase-1h | Settings UI: Providers, Agent Config, Auth pages                                                                      | —     | web     | feat/ms22-p1h-settings-ui    | P1g        | —               | —               | —       | —         | 25K        | —          |       |
+| MS22-P1i | not-started | phase-1i | Chat proxy: route WebUI chat to user's OpenClaw container (SSE)                                                       | —     | api+web | feat/ms22-p1i-chat-proxy     | P1c,P1d    | —               | —               | —       | —         | 20K        | —          |       |
+| MS22-P1j | not-started | phase-1j | Docker entrypoint + health checks + core compose                                                                      | —     | docker  | feat/ms22-p1j-docker         | P1c        | —               | —               | —       | —         | 10K        | —          |       |
+| MS22-P1k | not-started | phase-1k | Idle reaper cron: stop inactive user containers                                                                       | —     | api     | feat/ms22-p1k-idle-reaper    | P1d        | —               | —               | —       | —         | 10K        | —          |       |

docs/design/MS22-DB-CENTRIC-ARCHITECTURE.md

@@ -0,0 +1,413 @@
+# MS22 Phase 1: DB-Centric Multi-User Agent Architecture
+
+## Design Principles
+
+1. **2 env vars to bootstrap** — `DATABASE_URL` + `MOSAIC_SECRET_KEY`
+2. **DB-centric config** — All runtime config in Postgres, managed via WebUI
+3. **Mosaic is the gatekeeper** — Users authenticate to Mosaic, never to OpenClaw directly
+4. **Per-user agent isolation** — Each user gets their own OpenClaw container(s) with their own credentials
+5. **Onboarding-first** — Breakglass user + wizard on first boot
+6. **Generic product** — No hardcoded names, models, providers, or endpoints
+
+## Architecture Overview
+
+```
+┌─────────────────────────────────────────────────────┐
+│                    MOSAIC WEBUI                      │
+│  (Auth: breakglass local + OIDC via settings)       │
+└──────────────────────┬──────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────┐
+│                    MOSAIC API                        │
+│                                                     │
+│  ┌──────────────┐  ┌────────────────┐  ┌─────────┐ │
+│  │ Onboarding   │  │ Container      │  │ Config  │ │
+│  │ Wizard       │  │ Lifecycle Mgr  │  │ Store   │ │
+│  └──────────────┘  └───────┬────────┘  └─────────┘ │
+│                            │                        │
+└────────────────────────────┼────────────────────────┘
+                             │ Docker API
+          ┌──────────────────┼──────────────────┐
+          │                  │                  │
+          ▼                  ▼                  ▼
+   ┌─────────────┐   ┌─────────────┐   ┌─────────────┐
+   │  OpenClaw   │   │  OpenClaw   │   │  OpenClaw   │
+   │  User A     │   │  User B     │   │  System     │
+   │             │   │             │   │  (admin)    │
+   │ Claude Max  │   │ Z.ai key   │   │ Shared key  │
+   │ own memory  │   │ own memory  │   │ monitoring  │
+   └─────────────┘   └─────────────┘   └─────────────┘
+    Scale to zero      Scale to zero     Always on
+    after idle         after idle
+```
+
+## Container Lifecycle
+
+### User containers (on-demand)
+
+1. User logs in → Mosaic checks `UserContainer` table
+2. No running container → Mosaic calls Docker API to create one
+3. Injects user's encrypted API keys via config endpoint
+4. Routes chat requests to user's container
+5. Idle timeout (configurable, default 30min) → scale to zero
+6. State volume persists (sessions, memory, auth tokens)
+7. Next request → container restarts, picks up state from volume
+
+### System containers (always-on, optional)
+
+- Admin-provisioned for system tasks (monitoring, scheduled jobs)
+- Use admin-configured shared API keys
+- Not tied to any user
+
+## Auth Layers
+
+| Flow                            | Method                                                                 |
+| ------------------------------- | ---------------------------------------------------------------------- |
+| User → Mosaic WebUI             | Breakglass (local) or OIDC (configured in settings)                    |
+| Mosaic API → OpenClaw container | Bearer token (auto-generated per container, stored encrypted in DB)    |
+| OpenClaw → LLM providers        | User's own API keys (delivered via config endpoint, decrypted from DB) |
+| Admin → System settings         | RBAC (admin role required)                                             |
+| Internal config endpoint        | Bearer token (container authenticates to fetch its config)             |
+
+## Database Schema
+
+### System Tables
+
+```prisma
+model SystemConfig {
+  id        String   @id @default(cuid())
+  key       String   @unique  // "oidc.issuerUrl", "oidc.clientId", "onboarding.completed"
+  value     String             // plaintext or encrypted (prefix: "enc:")
+  encrypted Boolean  @default(false)
+  updatedAt DateTime @updatedAt
+}
+
+model BreakglassUser {
+  id           String   @id @default(cuid())
+  username     String   @unique
+  passwordHash String   // bcrypt
+  isActive     Boolean  @default(true)
+  createdAt    DateTime @default(now())
+  updatedAt    DateTime @updatedAt
+}
+```
+
+### Provider Tables (per-user)
+
+```prisma
+model LlmProvider {
+  id          String   @id @default(cuid())
+  userId      String             // owner — each user manages their own providers
+  name        String             // "my-zai", "work-openai", "local-ollama"
+  displayName String             // "Z.ai", "OpenAI (Work)", "Local Ollama"
+  type        String             // "zai" | "openai" | "anthropic" | "ollama" | "custom"
+  baseUrl     String?            // null for built-in, URL for custom/ollama
+  apiKey      String?            // encrypted
+  apiType     String   @default("openai-completions")
+  models      Json     @default("[]")  // [{id, name, contextWindow, maxTokens}]
+  isActive    Boolean  @default(true)
+  createdAt   DateTime @default(now())
+  updatedAt   DateTime @updatedAt
+
+  @@unique([userId, name])
+}
+```
+
+### Container Tables
+
+```prisma
+model UserContainer {
+  id              String    @id @default(cuid())
+  userId          String    @unique
+  containerId     String?   // Docker container ID (null = not running)
+  containerName   String    // "mosaic-user-{userId}"
+  gatewayPort     Int?      // assigned port (null = not running)
+  gatewayToken    String    // encrypted — auto-generated
+  status          String    @default("stopped")  // "running" | "stopped" | "starting" | "error"
+  lastActiveAt    DateTime?
+  idleTimeoutMin  Int       @default(30)
+  config          Json      @default("{}")  // cached openclaw.json for this user
+  createdAt       DateTime  @default(now())
+  updatedAt       DateTime  @updatedAt
+}
+
+model SystemContainer {
+  id              String   @id @default(cuid())
+  name            String   @unique  // "mosaic-system-ops", "mosaic-system-monitor"
+  role            String   // "operations" | "monitor" | "scheduler"
+  containerId     String?
+  gatewayPort     Int?
+  gatewayToken    String   // encrypted
+  status          String   @default("stopped")
+  providerId      String?  // references admin-level LlmProvider
+  primaryModel    String   // "zai/glm-5", etc.
+  isActive        Boolean  @default(true)
+  createdAt       DateTime @default(now())
+  updatedAt       DateTime @updatedAt
+}
+```
+
+### User Agent Preferences
+
+```prisma
+model UserAgentConfig {
+  id             String  @id @default(cuid())
+  userId         String  @unique
+  primaryModel   String?           // user's preferred model
+  fallbackModels Json    @default("[]")
+  personality    String?           // custom SOUL.md content
+  providerId     String?           // default provider for this user
+  createdAt      DateTime @default(now())
+  updatedAt      DateTime @updatedAt
+}
+```
+
+## Internal Config Endpoint
+
+`GET /api/internal/agent-config/:containerType/:id`
+
+- Auth: Bearer token (container's own gateway token)
+- Returns: Complete `openclaw.json` generated from DB
+- For user containers: includes user's providers, model prefs, personality
+- For system containers: includes admin provider config
+
+Response assembles openclaw.json dynamically:
+
+```json
+{
+  "gateway": { "mode": "local", "port": 18789, "bind": "lan", "auth": { "mode": "token" } ... },
+  "agents": { "defaults": { "model": { "primary": "<from UserAgentConfig>" } } },
+  "models": { "providers": { "<from LlmProvider rows>": { ... } } }
+}
+```
+
+## Container Lifecycle Manager
+
+NestJS service that manages Docker containers:
+
+```typescript
+class ContainerLifecycleService {
+  // Create and start a user's OpenClaw container
+  async ensureRunning(userId: string): Promise<{ url: string; token: string }>;
+
+  // Stop idle containers (called by cron/scheduler)
+  async reapIdle(): Promise<number>;
+
+  // Stop a specific user's container
+  async stop(userId: string): Promise<void>;
+
+  // Health check all running containers
+  async healthCheckAll(): Promise<HealthStatus[]>;
+
+  // Restart container with updated config
+  async restart(userId: string): Promise<void>;
+}
+```
+
+Uses Docker Engine API (`/var/run/docker.sock` or TCP) via `dockerode` npm package.
+
+## Onboarding Wizard
+
+### First-Boot Detection
+
+- API checks: `SystemConfig.get("onboarding.completed")` → null = first boot
+- WebUI redirects to `/onboarding` if not completed
+
+### Steps
+
+**Step 1: Create Breakglass Admin**
+
+- Username + password → bcrypt → `BreakglassUser` table
+- This user always works, even if OIDC is misconfigured
+
+**Step 2: Configure Authentication (optional)**
+
+- OIDC: provider URL, client ID, client secret → encrypted in `SystemConfig`
+- Skip = breakglass-only auth (can add OIDC later in settings)
+
+**Step 3: Add Your First LLM Provider**
+
+- Pick type → enter API key/endpoint → test connection → save to `LlmProvider`
+- This becomes the admin's default provider
+
+**Step 4: System Agents (optional)**
+
+- Configure always-on system agents for monitoring/ops
+- Or skip — users can just use their own personal agents
+
+**Step 5: Complete**
+
+- Sets `SystemConfig("onboarding.completed") = true`
+- Redirects to dashboard
+
+### Post-Onboarding: User Self-Service
+
+- Each user adds their own LLM providers in profile settings
+- Each user configures their preferred model, personality
+- First chat request triggers container creation
+
+## Docker Compose (final)
+
+```yaml
+services:
+  mosaic-api:
+    image: mosaic/api:latest
+    environment:
+      DATABASE_URL: ${DATABASE_URL}
+      MOSAIC_SECRET_KEY: ${MOSAIC_SECRET_KEY}
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock # Docker API access
+    networks:
+      - internal
+
+  mosaic-web:
+    image: mosaic/web:latest
+    environment:
+      NEXT_PUBLIC_API_URL: http://mosaic-api:4000
+    networks:
+      - internal
+
+  postgres:
+    image: postgres:17
+    environment:
+      POSTGRES_DB: mosaic
+      POSTGRES_USER: mosaic
+      POSTGRES_PASSWORD: ${DATABASE_PASSWORD}
+    volumes:
+      - postgres-data:/var/lib/postgresql/data
+    networks:
+      - internal
+
+  # System agent (optional, admin-provisioned)
+  # mosaic-system:
+  #   image: alpine/openclaw:latest
+  #   ... (managed by ContainerLifecycleService)
+
+  # User containers are NOT in this file —
+  # they are dynamically created by ContainerLifecycleService
+  # via the Docker API at runtime.
+
+networks:
+  internal:
+    driver: overlay
+
+volumes:
+  postgres-data:
+```
+
+Note: User OpenClaw containers are **not** defined in docker-compose. They are
+created dynamically by the `ContainerLifecycleService` when users start chatting.
+
+## Entrypoint (for dynamically created containers)
+
+```sh
+#!/bin/sh
+set -e
+: "${MOSAIC_API_URL:?required}"
+: "${AGENT_TOKEN:?required}"
+: "${AGENT_ID:?required}"
+
+# Fetch config from Mosaic API
+curl -sf "${MOSAIC_API_URL}/api/internal/agent-config/${AGENT_ID}" \
+  -H "Authorization: Bearer ${AGENT_TOKEN}" \
+  -o /tmp/openclaw.json
+
+export OPENCLAW_CONFIG_PATH=/tmp/openclaw.json
+exec openclaw gateway run --bind lan --auth token
+```
+
+Container env vars (injected by ContainerLifecycleService):
+
+- `MOSAIC_API_URL` — internal API URL
+- `AGENT_TOKEN` — this container's bearer token (from DB)
+- `AGENT_ID` — container ID for config lookup
+
+## Config Update Strategy
+
+When a user changes settings (model, provider, personality):
+
+1. Mosaic API updates DB
+2. API calls `ContainerLifecycleService.restart(userId)`
+3. Container restarts, fetches fresh config from API
+4. OpenClaw gateway starts with new config
+5. State volume preserves sessions/memory across restarts
+
+## Task Breakdown
+
+| Task     | Phase          | Scope                                                                                                                 | Dependencies |
+| -------- | -------------- | --------------------------------------------------------------------------------------------------------------------- | ------------ |
+| MS22-P1a | Schema         | Prisma models: SystemConfig, BreakglassUser, LlmProvider, UserContainer, SystemContainer, UserAgentConfig. Migration. | —            |
+| MS22-P1b | Crypto         | Encryption service for API keys/tokens (AES-256-GCM using MOSAIC_SECRET_KEY)                                          | P1a          |
+| MS22-P1c | Config API     | Internal config endpoint: assembles openclaw.json from DB                                                             | P1a, P1b     |
+| MS22-P1d | Container Mgr  | ContainerLifecycleService: Docker API integration (dockerode), start/stop/health/reap                                 | P1a          |
+| MS22-P1e | Onboarding API | Onboarding endpoints: breakglass, OIDC, provider, complete                                                            | P1a, P1b     |
+| MS22-P1f | Onboarding UI  | Multi-step wizard in WebUI                                                                                            | P1e          |
+| MS22-P1g | Settings API   | CRUD: providers, agent config, OIDC, breakglass                                                                       | P1a, P1b     |
+| MS22-P1h | Settings UI    | Settings pages: Providers, Agent Config, Auth                                                                         | P1g          |
+| MS22-P1i | Chat Proxy     | Route WebUI chat → user's OpenClaw container (SSE)                                                                    | P1c, P1d     |
+| MS22-P1j | Docker         | Entrypoint script, health checks, compose for core services                                                           | P1c          |
+| MS22-P1k | Idle Reaper    | Cron service to stop idle user containers                                                                             | P1d          |
+
+## Open Questions (Resolved)
+
+1. ~~Config updates → restart?~~ **Yes.** Mosaic restarts the container, fresh config on boot.
+2. ~~CLI alternative for breakglass?~~ **Yes.** Both WebUI wizard and CLI (`mosaic admin create-breakglass`).
+3. ~~Config cache TTL?~~ **Yes.** Config fetched once at startup, changes trigger restart.
+
+## Security Isolation Model
+
+### Core Principle: ZERO cross-user access
+
+Every user is fully sandboxed. No exceptions.
+
+### Container Isolation
+
+- Each user gets their **own** OpenClaw container (separate process, PID namespace)
+- Each container has its **own** Docker volume (sessions, memory, workspace)
+- Containers run on an **internal-only** Docker network — no external exposure
+- Users NEVER talk to OpenClaw directly — Mosaic proxies all requests
+- Container gateway tokens are unique per-user and single-purpose
+
+### Data Isolation (enforced at API + DB level)
+
+| Data             | Isolation                 | Enforcement                                                                       |
+| ---------------- | ------------------------- | --------------------------------------------------------------------------------- |
+| LLM API keys     | Per-user, encrypted       | `LlmProvider.userId` — all queries scoped by authenticated user                   |
+| Chat history     | Per-user container volume | Separate Docker volume per user, not shared                                       |
+| Agent memory     | Per-user container volume | Separate Docker volume per user                                                   |
+| Agent config     | Per-user                  | `UserAgentConfig.userId` — scoped queries                                         |
+| Container access | Per-user                  | `UserContainer.userId` — Mosaic validates user owns the container before proxying |
+
+### API Enforcement
+
+- **All user-facing endpoints** include `WHERE userId = authenticatedUser.id`
+- **No admin endpoint** exposes another user's API keys (even to admins)
+- **Chat proxy** validates: authenticated user → owns target container → forwards request
+- **Config endpoint** validates: container token matches the container requesting config
+- **Provider CRUD** is fully user-scoped — User A cannot list, read, or modify User B's providers
+
+### What admins CAN see
+
+- Container status (running/stopped) — not contents
+- User list and roles
+- System-level config (OIDC, system agents)
+- Aggregate usage metrics (not individual conversations)
+
+### What admins CANNOT see
+
+- Other users' API keys (encrypted, no decrypt endpoint)
+- Other users' chat history (in container volumes, not in Mosaic DB)
+- Other users' agent memory/workspace contents
+
+### Future: Team Workspaces (NOT in scope)
+
+Team/shared workspaces are a potential future feature where users opt-in to
+shared agent contexts. This requires explicit consent, shared-key management,
+and a different isolation model. **Not designed here. Not built now.**
+
+### Attack Surface Notes
+
+- Docker socket access (`/var/run/docker.sock`) is required by Mosaic API for container management. This is a privileged operation — the Mosaic API container must be trusted.
+- `MOSAIC_SECRET_KEY` is the root of trust for encryption. Rotation requires re-encrypting all secrets in DB.
+- Container-to-container communication is blocked by default (no shared network between user containers unless explicitly configured).