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

@@ -78,8 +78,8 @@ 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 | not-started | phase-1a | Prisma schema: SystemConfig, BreakglassUser, LlmProvider, UserContainer, SystemContainer, UserAgentConfig + migration | —     | api     | feat/ms22-p1a-schema         | —          | P1b,P1c,P1d,P1e | —               | —       | —         | 20K        | —          |       |
+| 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 | not-started | phase-1b | Encryption service (AES-256-GCM) for API keys and tokens                                                              | —     | api     | feat/ms22-p1b-crypto         | —          | P1c,P1e,P1g     | —               | —       | —         | 15K        | —          |       |
+| 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        | —          |       |