Compare commits
3 Commits
e3d98d7390
...
draft/mosa
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2708de55b9 | ||
|
|
6b8c3c5d3a | ||
|
|
d1f69bfd37 |
@@ -5,5 +5,3 @@ pnpm-lock.yaml
|
||||
**/drizzle
|
||||
**/.next
|
||||
.claude/
|
||||
docs/tess/TASKS.md
|
||||
docs/scratchpads/
|
||||
|
||||
@@ -7,14 +7,7 @@ variables:
|
||||
- &enable_pnpm 'corepack enable'
|
||||
|
||||
when:
|
||||
# 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
|
||||
- event: [push, pull_request, manual]
|
||||
|
||||
# Turbo remote cache (turbo.mosaicstack.dev) is configured via Woodpecker
|
||||
# repository-level environment variables (TURBO_API, TURBO_TEAM, TURBO_TOKEN).
|
||||
|
||||
@@ -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.listAllSessionsForSystem();
|
||||
const sessions = this.agentService.listSessions();
|
||||
const providers = this.providerService.listProviders();
|
||||
|
||||
const allOk = database.status === 'ok' && cache.status === 'ok';
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
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);
|
||||
});
|
||||
});
|
||||
@@ -1,262 +0,0 @@
|
||||
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 }),
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -1,11 +1,4 @@
|
||||
import {
|
||||
ForbiddenException,
|
||||
Inject,
|
||||
Injectable,
|
||||
Logger,
|
||||
Optional,
|
||||
type OnModuleDestroy,
|
||||
} from '@nestjs/common';
|
||||
import { Inject, Injectable, Logger, Optional, type OnModuleDestroy } from '@nestjs/common';
|
||||
import {
|
||||
createAgentSession,
|
||||
DefaultResourceLoader,
|
||||
@@ -35,7 +28,6 @@ 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 {
|
||||
@@ -76,8 +68,6 @@ 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
|
||||
@@ -104,8 +94,6 @@ 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). */
|
||||
@@ -186,20 +174,12 @@ export class AgentService implements OnModuleDestroy {
|
||||
.filter((t) => t.length > 0);
|
||||
}
|
||||
|
||||
async createSession(sessionId: string, options: AgentSessionOptions): Promise<AgentSession> {
|
||||
const scope = this.scopeFromOptions(options);
|
||||
async createSession(sessionId: string, options?: AgentSessionOptions): Promise<AgentSession> {
|
||||
const existing = this.sessions.get(sessionId);
|
||||
if (existing) {
|
||||
this.assertSessionScope(existing, scope);
|
||||
return existing;
|
||||
}
|
||||
if (existing) return existing;
|
||||
|
||||
const inflight = this.creating.get(sessionId);
|
||||
if (inflight) {
|
||||
const session = await inflight;
|
||||
this.assertSessionScope(session, scope);
|
||||
return session;
|
||||
}
|
||||
if (inflight) return inflight;
|
||||
|
||||
const promise = this.doCreateSession(sessionId, options).finally(() => {
|
||||
this.creating.delete(sessionId);
|
||||
@@ -362,7 +342,6 @@ export class AgentService implements OnModuleDestroy {
|
||||
sandboxDir,
|
||||
allowedTools,
|
||||
userId: mergedOptions?.userId,
|
||||
tenantId: this.tenantIdFor(mergedOptions?.userId, mergedOptions?.tenantId),
|
||||
agentConfigId: mergedOptions?.agentConfigId,
|
||||
agentName: resolvedAgentName,
|
||||
metrics: {
|
||||
@@ -494,70 +473,38 @@ export class AgentService implements OnModuleDestroy {
|
||||
return this.providerService.getDefaultModel() ?? null;
|
||||
}
|
||||
|
||||
getSession(sessionId: string, scope: ActorTenantScope): AgentSession | undefined {
|
||||
const session = this.sessions.get(sessionId);
|
||||
if (!session || !this.sessionMatchesScope(session, scope)) return undefined;
|
||||
return session;
|
||||
getSession(sessionId: string): AgentSession | undefined {
|
||||
return this.sessions.get(sessionId);
|
||||
}
|
||||
|
||||
listSessions(scope: ActorTenantScope): SessionInfoDto[] {
|
||||
listSessions(): SessionInfoDto[] {
|
||||
const now = Date.now();
|
||||
return Array.from(this.sessions.values())
|
||||
.filter((s) => this.sessionMatchesScope(s, scope))
|
||||
.map((s) => this.toSessionInfo(s, now));
|
||||
return Array.from(this.sessions.values()).map((s) => ({
|
||||
id: s.id,
|
||||
provider: s.provider,
|
||||
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 },
|
||||
}));
|
||||
}
|
||||
|
||||
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 {
|
||||
getSessionInfo(sessionId: string): SessionInfoDto | undefined {
|
||||
const s = this.sessions.get(sessionId);
|
||||
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');
|
||||
}
|
||||
if (!s) return undefined;
|
||||
return {
|
||||
userId: options.userId,
|
||||
tenantId: this.tenantIdFor(options.userId, options.tenantId) ?? options.userId,
|
||||
};
|
||||
}
|
||||
|
||||
private tenantIdFor(
|
||||
userId: string | undefined,
|
||||
tenantId: string | undefined,
|
||||
): 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 },
|
||||
id: s.id,
|
||||
provider: s.provider,
|
||||
modelId: s.modelId,
|
||||
...(s.agentName ? { agentName: s.agentName } : {}),
|
||||
createdAt: new Date(s.createdAt).toISOString(),
|
||||
promptCount: s.promptCount,
|
||||
channels: Array.from(s.channels),
|
||||
durationMs: Date.now() - s.createdAt,
|
||||
metrics: { ...s.metrics },
|
||||
};
|
||||
}
|
||||
|
||||
@@ -606,10 +553,9 @@ 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, scope: ActorTenantScope): void {
|
||||
updateSessionModel(sessionId: string, modelId: string): void {
|
||||
const session = this.sessions.get(sessionId);
|
||||
if (!session) return;
|
||||
this.assertSessionScope(session, scope);
|
||||
const prev = session.modelId;
|
||||
session.modelId = modelId;
|
||||
this.recordModelSwitch(sessionId);
|
||||
@@ -626,51 +572,48 @@ 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, scope);
|
||||
this.updateSessionModel(sessionId, modelId);
|
||||
}
|
||||
this.logger.log(
|
||||
`Session ${sessionId}: agent switched to "${agentName}" (${agentConfigId}) (M5-003)`,
|
||||
);
|
||||
}
|
||||
|
||||
addChannel(sessionId: string, channel: string, scope: ActorTenantScope): void {
|
||||
addChannel(sessionId: string, channel: string): void {
|
||||
const session = this.sessions.get(sessionId);
|
||||
if (!session) return;
|
||||
this.assertSessionScope(session, scope);
|
||||
session.channels.add(channel);
|
||||
if (session) {
|
||||
session.channels.add(channel);
|
||||
}
|
||||
}
|
||||
|
||||
removeChannel(sessionId: string, channel: string, scope: ActorTenantScope): void {
|
||||
removeChannel(sessionId: string, channel: string): void {
|
||||
const session = this.sessions.get(sessionId);
|
||||
if (!session) return;
|
||||
this.assertSessionScope(session, scope);
|
||||
session.channels.delete(channel);
|
||||
if (session) {
|
||||
session.channels.delete(channel);
|
||||
}
|
||||
}
|
||||
|
||||
async prompt(sessionId: string, message: string, scope: ActorTenantScope): Promise<void> {
|
||||
async prompt(sessionId: string, message: string): Promise<void> {
|
||||
const session = this.sessions.get(sessionId);
|
||||
if (!session) {
|
||||
throw new Error(`No agent session found: ${sessionId}`);
|
||||
}
|
||||
this.assertSessionScope(session, scope);
|
||||
session.promptCount += 1;
|
||||
|
||||
// Prepend session-scoped system override if present (renew TTL on each turn)
|
||||
let effectiveMessage = message;
|
||||
if (this.systemOverride) {
|
||||
const override = await this.systemOverride.get(sessionId, scope);
|
||||
const override = await this.systemOverride.get(sessionId);
|
||||
if (override) {
|
||||
effectiveMessage = `[System Override]\n${override}\n\n${message}`;
|
||||
await this.systemOverride.renew(sessionId, scope);
|
||||
await this.systemOverride.renew(sessionId);
|
||||
this.logger.debug(`Applied system override for session ${sessionId}`);
|
||||
}
|
||||
}
|
||||
@@ -686,28 +629,16 @@ export class AgentService implements OnModuleDestroy {
|
||||
}
|
||||
}
|
||||
|
||||
onEvent(
|
||||
sessionId: string,
|
||||
listener: (event: AgentSessionEvent) => void,
|
||||
scope: ActorTenantScope,
|
||||
): () => void {
|
||||
onEvent(sessionId: string, listener: (event: AgentSessionEvent) => void): () => 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, 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> {
|
||||
async destroySession(sessionId: string): Promise<void> {
|
||||
const session = this.sessions.get(sessionId);
|
||||
if (!session) return;
|
||||
this.logger.log(`Destroying agent session ${sessionId}`);
|
||||
@@ -736,7 +667,7 @@ 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.destroySessionForSystem(id));
|
||||
const stops = Array.from(this.sessions.keys()).map((id) => this.destroySession(id));
|
||||
const results = await Promise.allSettled(stops);
|
||||
for (const result of results) {
|
||||
if (result.status === 'rejected') {
|
||||
|
||||
@@ -10,8 +10,6 @@ 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')
|
||||
@@ -20,24 +18,23 @@ export class SessionsController {
|
||||
constructor(@Inject(AgentService) private readonly agentService: AgentService) {}
|
||||
|
||||
@Get()
|
||||
list(@CurrentUser() user: AuthenticatedUserLike) {
|
||||
const sessions = this.agentService.listSessions(scopeFromUser(user));
|
||||
list() {
|
||||
const sessions = this.agentService.listSessions();
|
||||
return { sessions, total: sessions.length };
|
||||
}
|
||||
|
||||
@Get(':id')
|
||||
findOne(@Param('id') id: string, @CurrentUser() user: AuthenticatedUserLike) {
|
||||
const info = this.agentService.getSessionInfo(id, scopeFromUser(user));
|
||||
findOne(@Param('id') id: string) {
|
||||
const info = this.agentService.getSessionInfo(id);
|
||||
if (!info) throw new NotFoundException('Session not found');
|
||||
return info;
|
||||
}
|
||||
|
||||
@Delete(':id')
|
||||
@HttpCode(HttpStatus.NO_CONTENT)
|
||||
async destroy(@Param('id') id: string, @CurrentUser() user: AuthenticatedUserLike) {
|
||||
const scope = scopeFromUser(user);
|
||||
const info = this.agentService.getSessionInfo(id, scope);
|
||||
async destroy(@Param('id') id: string) {
|
||||
const info = this.agentService.getSessionInfo(id);
|
||||
if (!info) throw new NotFoundException('Session not found');
|
||||
await this.agentService.destroySession(id, scope);
|
||||
await this.agentService.destroySession(id);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,24 +0,0 @@
|
||||
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,
|
||||
};
|
||||
}
|
||||
@@ -12,8 +12,7 @@ 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: AuthenticatedUserLike');
|
||||
expect(source).toContain('const scope = scopeFromUser(user);');
|
||||
expect(source).toContain('@CurrentUser() user: { id: string }');
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -3,10 +3,8 @@ import {
|
||||
Post,
|
||||
Body,
|
||||
Logger,
|
||||
ForbiddenException,
|
||||
HttpException,
|
||||
HttpStatus,
|
||||
NotFoundException,
|
||||
Inject,
|
||||
UseGuards,
|
||||
} from '@nestjs/common';
|
||||
@@ -15,7 +13,6 @@ 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';
|
||||
|
||||
@@ -35,23 +32,16 @@ export class ChatController {
|
||||
@Throttle({ default: { limit: 10, ttl: 60_000 } })
|
||||
async chat(
|
||||
@Body() body: ChatRequestDto,
|
||||
@CurrentUser() user: AuthenticatedUserLike,
|
||||
@CurrentUser() user: { id: string },
|
||||
): Promise<ChatResponse> {
|
||||
const conversationId = body.conversationId ?? uuid();
|
||||
const scope = scopeFromUser(user);
|
||||
|
||||
try {
|
||||
let agentSession = this.agentService.getSession(conversationId, scope);
|
||||
let agentSession = this.agentService.getSession(conversationId);
|
||||
if (!agentSession) {
|
||||
agentSession = await this.agentService.createSession(conversationId, {
|
||||
userId: scope.userId,
|
||||
tenantId: scope.tenantId,
|
||||
});
|
||||
agentSession = await this.agentService.createSession(conversationId);
|
||||
}
|
||||
} 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),
|
||||
@@ -70,27 +60,20 @@ export class ChatController {
|
||||
reject(new Error('Agent response timed out'));
|
||||
}, 120_000);
|
||||
|
||||
const cleanup = this.agentService.onEvent(
|
||||
conversationId,
|
||||
(event: AgentSessionEvent) => {
|
||||
if (
|
||||
event.type === 'message_update' &&
|
||||
event.assistantMessageEvent.type === 'text_delta'
|
||||
) {
|
||||
responseText += event.assistantMessageEvent.delta;
|
||||
}
|
||||
if (event.type === 'agent_end') {
|
||||
clearTimeout(timer);
|
||||
cleanup();
|
||||
resolve();
|
||||
}
|
||||
},
|
||||
scope,
|
||||
);
|
||||
const cleanup = this.agentService.onEvent(conversationId, (event: AgentSessionEvent) => {
|
||||
if (event.type === 'message_update' && event.assistantMessageEvent.type === 'text_delta') {
|
||||
responseText += event.assistantMessageEvent.delta;
|
||||
}
|
||||
if (event.type === 'agent_end') {
|
||||
clearTimeout(timer);
|
||||
cleanup();
|
||||
resolve();
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
try {
|
||||
await this.agentService.prompt(conversationId, body.content, scope);
|
||||
await this.agentService.prompt(conversationId, body.content);
|
||||
await done;
|
||||
} catch (err) {
|
||||
if (err instanceof HttpException) throw err;
|
||||
|
||||
@@ -1,74 +0,0 @@
|
||||
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',
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -15,7 +15,6 @@ import type { Auth } from '@mosaicstack/auth';
|
||||
import type { Brain } from '@mosaicstack/brain';
|
||||
import type {
|
||||
SetThinkingPayload,
|
||||
SlashCommandApprovalResultPayload,
|
||||
SlashCommandPayload,
|
||||
SystemReloadPayload,
|
||||
RoutingDecisionInfo,
|
||||
@@ -23,11 +22,6 @@ 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';
|
||||
@@ -46,8 +40,6 @@ 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;
|
||||
}
|
||||
@@ -105,48 +97,25 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
const session = this.clientSessions.get(client.id);
|
||||
if (session) {
|
||||
session.cleanup();
|
||||
this.agentService.removeChannel(
|
||||
session.conversationId,
|
||||
`websocket:${client.id}`,
|
||||
session.scope,
|
||||
);
|
||||
this.agentService.removeChannel(session.conversationId, `websocket:${client.id}`);
|
||||
this.clientSessions.delete(client.id);
|
||||
}
|
||||
}
|
||||
|
||||
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,
|
||||
): Promise<void> {
|
||||
const conversationId = data.conversationId ?? uuid();
|
||||
const scope = this.getClientScope(client);
|
||||
if (!scope) {
|
||||
client.emit('error', { conversationId, error: 'Authenticated user scope is required.' });
|
||||
return;
|
||||
}
|
||||
const userId = scope.userId;
|
||||
const userId = (client.data.user as { id: string } | undefined)?.id;
|
||||
|
||||
this.logger.log(`Message from ${client.id} in conversation ${conversationId}`);
|
||||
|
||||
// Ensure agent session exists for this conversation
|
||||
let sessionRoutingDecision: RoutingDecisionInfo | undefined;
|
||||
try {
|
||||
let agentSession = this.agentService.getSession(conversationId, scope);
|
||||
let agentSession = this.agentService.getSession(conversationId);
|
||||
if (!agentSession) {
|
||||
// When resuming an existing conversation, load prior messages to inject as context (M1-004)
|
||||
const conversationHistory = await this.loadConversationHistory(conversationId, userId);
|
||||
@@ -166,7 +135,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
let resolvedProvider = data.provider;
|
||||
let resolvedModelId = data.modelId;
|
||||
|
||||
const modelOverride = modelOverrides.get(this.modelOverrideKey(conversationId, scope));
|
||||
const modelOverride = modelOverrides.get(conversationId);
|
||||
if (modelOverride) {
|
||||
// /model override bypasses routing engine (M4-007)
|
||||
resolvedModelId = modelOverride;
|
||||
@@ -203,7 +172,6 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
modelId: resolvedModelId,
|
||||
agentConfigId: data.agentId,
|
||||
userId,
|
||||
tenantId: scope.tenantId,
|
||||
conversationHistory: conversationHistory.length > 0 ? conversationHistory : undefined,
|
||||
});
|
||||
|
||||
@@ -264,13 +232,9 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
}
|
||||
|
||||
// Subscribe to agent events and relay to client
|
||||
const cleanup = this.agentService.onEvent(
|
||||
conversationId,
|
||||
(event: AgentSessionEvent) => {
|
||||
this.relayEvent(client, conversationId, event);
|
||||
},
|
||||
scope,
|
||||
);
|
||||
const cleanup = this.agentService.onEvent(conversationId, (event: AgentSessionEvent) => {
|
||||
this.relayEvent(client, conversationId, event);
|
||||
});
|
||||
|
||||
// Preserve routing decision from the existing client session if we didn't get a new one
|
||||
const prevClientSession = this.clientSessions.get(client.id);
|
||||
@@ -282,17 +246,16 @@ 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}`, scope);
|
||||
this.agentService.addChannel(conversationId, `websocket:${client.id}`);
|
||||
|
||||
// Send session info so the client knows the model/provider (M4-008: include routing decision)
|
||||
// Include agentName when a named agent config is active (M5-001)
|
||||
{
|
||||
const agentSession = this.agentService.getSession(conversationId, scope);
|
||||
const agentSession = this.agentService.getSession(conversationId);
|
||||
if (agentSession) {
|
||||
const piSession = agentSession.piSession;
|
||||
client.emit('session:info', {
|
||||
@@ -312,7 +275,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
|
||||
// Dispatch to agent
|
||||
try {
|
||||
await this.agentService.prompt(conversationId, data.content, scope);
|
||||
await this.agentService.prompt(conversationId, data.content);
|
||||
} catch (err) {
|
||||
this.logger.error(
|
||||
`Agent prompt failed for client=${client.id}, conversation=${conversationId}`,
|
||||
@@ -330,16 +293,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
@ConnectedSocket() client: Socket,
|
||||
@MessageBody() data: SetThinkingPayload,
|
||||
): void {
|
||||
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);
|
||||
const session = this.agentService.getSession(data.conversationId);
|
||||
if (!session) {
|
||||
client.emit('error', {
|
||||
conversationId: data.conversationId,
|
||||
@@ -380,13 +334,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
const conversationId = data.conversationId;
|
||||
this.logger.log(`Abort requested by ${client.id} for conversation ${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);
|
||||
const session = this.agentService.getSession(conversationId);
|
||||
if (!session) {
|
||||
client.emit('error', {
|
||||
conversationId,
|
||||
@@ -415,45 +363,11 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
@ConnectedSocket() client: Socket,
|
||||
@MessageBody() payload: SlashCommandPayload,
|
||||
): Promise<void> {
|
||||
const scope = this.getClientScope(client);
|
||||
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);
|
||||
const userId = (client.data.user as { id: string } | undefined)?.id ?? 'unknown';
|
||||
const result = await this.commandExecutor.execute(payload, userId);
|
||||
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');
|
||||
@@ -466,23 +380,18 @@ 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,
|
||||
scope: ActorTenantScope,
|
||||
): void {
|
||||
const key = this.modelOverrideKey(conversationId, scope);
|
||||
setModelOverride(conversationId: string, modelName: string | null): void {
|
||||
if (modelName) {
|
||||
modelOverrides.set(key, modelName);
|
||||
modelOverrides.set(conversationId, modelName);
|
||||
this.logger.log(`Model override set: conversation=${conversationId} model="${modelName}"`);
|
||||
|
||||
// M5-002: Update the live session's modelId so session:info reflects the new model immediately
|
||||
this.agentService.updateSessionModel(conversationId, modelName, scope);
|
||||
this.agentService.updateSessionModel(conversationId, modelName);
|
||||
|
||||
// M5-005: Broadcast session:info to all clients subscribed to this conversation
|
||||
this.broadcastSessionInfo(conversationId, scope);
|
||||
this.broadcastSessionInfo(conversationId);
|
||||
} else {
|
||||
modelOverrides.delete(key);
|
||||
modelOverrides.delete(conversationId);
|
||||
this.logger.log(`Model override cleared: conversation=${conversationId}`);
|
||||
}
|
||||
}
|
||||
@@ -490,8 +399,8 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
/**
|
||||
* Return the active model override for a conversation, or undefined if none.
|
||||
*/
|
||||
getModelOverride(conversationId: string, scope: ActorTenantScope): string | undefined {
|
||||
return modelOverrides.get(this.modelOverrideKey(conversationId, scope));
|
||||
getModelOverride(conversationId: string): string | undefined {
|
||||
return modelOverrides.get(conversationId);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -500,10 +409,9 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
*/
|
||||
broadcastSessionInfo(
|
||||
conversationId: string,
|
||||
scope: ActorTenantScope,
|
||||
extra?: { agentName?: string; routingDecision?: RoutingDecisionInfo },
|
||||
): void {
|
||||
const agentSession = this.agentService.getSession(conversationId, scope);
|
||||
const agentSession = this.agentService.getSession(conversationId);
|
||||
if (!agentSession) return;
|
||||
|
||||
const piSession = agentSession.piSession;
|
||||
@@ -520,7 +428,7 @@ 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 && this.scopesEqual(session.scope, scope)) {
|
||||
if (session.conversationId === conversationId) {
|
||||
const socket = this.server.sockets.sockets.get(clientId);
|
||||
if (socket?.connected) {
|
||||
socket.emit('session:info', payload);
|
||||
@@ -642,10 +550,7 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
|
||||
|
||||
case 'agent_end': {
|
||||
// Gather usage stats from the Pi session
|
||||
const activeClientSession = this.clientSessions.get(client.id);
|
||||
const agentSession = activeClientSession
|
||||
? this.agentService.getSession(conversationId, activeClientSession.scope)
|
||||
: undefined;
|
||||
const agentSession = this.agentService.getSession(conversationId);
|
||||
const piSession = agentSession?.piSession;
|
||||
const stats = piSession?.getSessionStats();
|
||||
const contextUsage = piSession?.getContextUsage();
|
||||
|
||||
@@ -1,61 +0,0 @@
|
||||
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);
|
||||
});
|
||||
});
|
||||
@@ -1,138 +0,0 @@
|
||||
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}`;
|
||||
}
|
||||
}
|
||||
@@ -89,7 +89,6 @@ 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(() => {
|
||||
@@ -100,7 +99,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain('Usage: /provider login');
|
||||
expect(result.command).toBe('provider');
|
||||
@@ -113,7 +112,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
|
||||
args: 'login anthropic',
|
||||
conversationId,
|
||||
};
|
||||
const result = await service.execute(payload, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('provider');
|
||||
expect(result.message).toContain('anthropic');
|
||||
@@ -139,7 +138,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('Usage: /provider');
|
||||
});
|
||||
@@ -147,7 +146,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('provider');
|
||||
});
|
||||
@@ -155,7 +154,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain('Usage: /provider logout');
|
||||
});
|
||||
@@ -167,7 +166,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
|
||||
args: 'unknown',
|
||||
conversationId,
|
||||
};
|
||||
const result = await service.execute(payload, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain('Unknown subcommand');
|
||||
});
|
||||
@@ -175,7 +174,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('mission');
|
||||
expect(result.message).toContain('Mission status');
|
||||
@@ -184,7 +183,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('Mission status');
|
||||
});
|
||||
@@ -196,7 +195,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
|
||||
args: 'set my-mission-123',
|
||||
conversationId,
|
||||
};
|
||||
const result = await service.execute(payload, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('my-mission-123');
|
||||
});
|
||||
@@ -204,7 +203,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('agent');
|
||||
expect(result.message).toContain('agent');
|
||||
@@ -213,7 +212,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('Usage: /agent');
|
||||
});
|
||||
@@ -225,7 +224,7 @@ describe('CommandExecutorService — P8-012 commands', () => {
|
||||
args: 'my-agent-id',
|
||||
conversationId,
|
||||
};
|
||||
const result = await service.execute(payload, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('my-agent-id');
|
||||
});
|
||||
@@ -233,7 +232,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('prdy');
|
||||
expect(result.message).toContain('mosaic prdy');
|
||||
@@ -242,7 +241,7 @@ 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, userScope);
|
||||
const result = await service.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('tools');
|
||||
expect(result.message).toContain('tools');
|
||||
|
||||
@@ -1,109 +0,0 @@
|
||||
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();
|
||||
});
|
||||
});
|
||||
@@ -3,7 +3,6 @@ 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';
|
||||
@@ -11,7 +10,6 @@ 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()
|
||||
@@ -34,17 +32,10 @@ export class CommandExecutorService {
|
||||
@Optional()
|
||||
@Inject(McpClientService)
|
||||
private readonly mcpClient: McpClientService | null,
|
||||
@Optional()
|
||||
@Inject(CommandAuthorizationService)
|
||||
private readonly authorization: CommandAuthorizationService | null = null,
|
||||
) {}
|
||||
|
||||
async execute(
|
||||
payload: SlashCommandPayload,
|
||||
scope: ActorTenantScope,
|
||||
): Promise<SlashCommandResultPayload> {
|
||||
async execute(payload: SlashCommandPayload, userId: string): Promise<SlashCommandResultPayload> {
|
||||
const { command, args, conversationId } = payload;
|
||||
const userId = scope.userId;
|
||||
|
||||
const def = this.registry.getManifest().commands.find((c) => c.name === command);
|
||||
if (!def) {
|
||||
@@ -56,24 +47,14 @@ 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, scope);
|
||||
return await this.handleModel(args ?? null, conversationId);
|
||||
case 'thinking':
|
||||
return await this.handleThinking(args ?? null, conversationId);
|
||||
case 'system':
|
||||
return await this.handleSystem(args ?? null, conversationId, scope);
|
||||
return await this.handleSystem(args ?? null, conversationId);
|
||||
case 'new':
|
||||
return {
|
||||
command,
|
||||
@@ -113,7 +94,7 @@ export class CommandExecutorService {
|
||||
};
|
||||
}
|
||||
case 'agent':
|
||||
return await this.handleAgent(args ?? null, conversationId, scope);
|
||||
return await this.handleAgent(args ?? null, conversationId, userId);
|
||||
case 'provider':
|
||||
return await this.handleProvider(args ?? null, userId, conversationId);
|
||||
case 'mission':
|
||||
@@ -162,22 +143,13 @@ 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, scope);
|
||||
const currentOverride = this.chatGateway?.getModelOverride(conversationId);
|
||||
if (currentOverride) {
|
||||
return {
|
||||
command: 'model',
|
||||
@@ -199,7 +171,7 @@ export class CommandExecutorService {
|
||||
|
||||
// /model clear removes the override and re-enables automatic routing
|
||||
if (modelName === 'clear') {
|
||||
this.chatGateway?.setModelOverride(conversationId, null, scope);
|
||||
this.chatGateway?.setModelOverride(conversationId, null);
|
||||
return {
|
||||
command: 'model',
|
||||
conversationId,
|
||||
@@ -209,9 +181,9 @@ export class CommandExecutorService {
|
||||
}
|
||||
|
||||
// Set the sticky per-session override (M4-007)
|
||||
this.chatGateway?.setModelOverride(conversationId, modelName, scope);
|
||||
this.chatGateway?.setModelOverride(conversationId, modelName);
|
||||
|
||||
const session = this.agentService.getSession(conversationId, scope);
|
||||
const session = this.agentService.getSession(conversationId);
|
||||
if (!session) {
|
||||
return {
|
||||
command: 'model',
|
||||
@@ -252,11 +224,10 @@ 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, scope);
|
||||
await this.systemOverride.clear(conversationId);
|
||||
return {
|
||||
command: 'system',
|
||||
conversationId,
|
||||
@@ -265,7 +236,7 @@ export class CommandExecutorService {
|
||||
};
|
||||
}
|
||||
|
||||
await this.systemOverride.set(conversationId, args.trim(), scope);
|
||||
await this.systemOverride.set(conversationId, args.trim());
|
||||
return {
|
||||
command: 'system',
|
||||
conversationId,
|
||||
@@ -277,9 +248,8 @@ export class CommandExecutorService {
|
||||
private async handleAgent(
|
||||
args: string | null,
|
||||
conversationId: string,
|
||||
scope: ActorTenantScope,
|
||||
userId: string,
|
||||
): Promise<SlashCommandResultPayload> {
|
||||
const userId = scope.userId;
|
||||
if (!args) {
|
||||
return {
|
||||
command: 'agent',
|
||||
@@ -368,14 +338,11 @@ 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, scope, {
|
||||
agentName: agentConfig.name,
|
||||
});
|
||||
this.chatGateway?.broadcastSessionInfo(conversationId, { agentName: agentConfig.name });
|
||||
|
||||
this.logger.log(
|
||||
`Agent switched to "${agentConfig.name}" (${agentConfig.id}) for conversation ${conversationId} (M5-003)`,
|
||||
|
||||
@@ -159,7 +159,6 @@ 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(() => {
|
||||
@@ -171,7 +170,7 @@ 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, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain('nonexistent');
|
||||
expect(result.command).toBe('nonexistent');
|
||||
@@ -180,7 +179,7 @@ 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, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(mockSessionGC.sweepOrphans).toHaveBeenCalledWith();
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('GC sweep complete');
|
||||
@@ -191,8 +190,8 @@ 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, userScope);
|
||||
expect(mockSystemOverride.set).toHaveBeenCalledWith(conversationId, override, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(mockSystemOverride.set).toHaveBeenCalledWith(conversationId, override);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('override set');
|
||||
});
|
||||
@@ -200,8 +199,8 @@ 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, userScope);
|
||||
expect(mockSystemOverride.clear).toHaveBeenCalledWith(conversationId, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(mockSystemOverride.clear).toHaveBeenCalledWith(conversationId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('cleared');
|
||||
});
|
||||
@@ -213,7 +212,7 @@ describe('CommandExecutorService — integration', () => {
|
||||
args: 'claude-3-opus',
|
||||
conversationId,
|
||||
};
|
||||
const result = await executor.execute(payload, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('model');
|
||||
expect(result.message).toContain('claude-3-opus');
|
||||
@@ -222,7 +221,7 @@ 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, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('high');
|
||||
});
|
||||
@@ -230,7 +229,7 @@ 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, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.message).toContain('Usage:');
|
||||
});
|
||||
@@ -238,7 +237,7 @@ describe('CommandExecutorService — integration', () => {
|
||||
// /new command returns success
|
||||
it('/new returns success', async () => {
|
||||
const payload: SlashCommandPayload = { command: 'new', conversationId };
|
||||
const result = await executor.execute(payload, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe('new');
|
||||
});
|
||||
@@ -246,7 +245,7 @@ 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, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.message).toContain('ReloadService');
|
||||
});
|
||||
@@ -256,7 +255,7 @@ 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, userScope);
|
||||
const result = await executor.execute(payload, userId);
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.command).toBe(cmd);
|
||||
});
|
||||
|
||||
@@ -3,7 +3,6 @@ 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';
|
||||
@@ -25,7 +24,6 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
|
||||
inject: [COMMANDS_QUEUE_HANDLE],
|
||||
},
|
||||
CommandRegistryService,
|
||||
CommandAuthorizationService,
|
||||
CommandExecutorService,
|
||||
],
|
||||
exports: [CommandRegistryService, CommandExecutorService],
|
||||
|
||||
@@ -3,11 +3,7 @@ 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 {
|
||||
createMcpActorContext,
|
||||
deriveMcpToolScopesForUser,
|
||||
type McpService,
|
||||
} from './mcp.service.js';
|
||||
import type { McpService } from './mcp.service.js';
|
||||
import { AUTH } from '../auth/auth.tokens.js';
|
||||
|
||||
/**
|
||||
@@ -71,25 +67,14 @@ async function handleMcpRequest(
|
||||
return;
|
||||
}
|
||||
|
||||
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 }),
|
||||
});
|
||||
const userId = result.user.id;
|
||||
|
||||
// ─── 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, actor);
|
||||
const transport = mcpService.getSession(sessionId);
|
||||
if (!transport) {
|
||||
logger.warn(`MCP session not found: ${sessionId}`);
|
||||
reply.raw.writeHead(404, { 'Content-Type': 'application/json' });
|
||||
@@ -127,10 +112,8 @@ async function handleMcpRequest(
|
||||
}
|
||||
|
||||
// Create new session and handle this initializing request
|
||||
const { transport } = mcpService.createSession(actor);
|
||||
logger.log(
|
||||
`New MCP session created for actor=${actor.userId} tenant=${actor.tenantId} correlation=${actor.correlationId}`,
|
||||
);
|
||||
const { transport } = mcpService.createSession(userId);
|
||||
logger.log(`New MCP session created for user ${userId}`);
|
||||
|
||||
await transport.handleRequest(req.raw, reply.raw, body);
|
||||
}
|
||||
|
||||
@@ -1,461 +0,0 @@
|
||||
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();
|
||||
});
|
||||
});
|
||||
@@ -10,216 +10,11 @@ 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()
|
||||
@@ -238,18 +33,13 @@ 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(actor: McpActorContext): {
|
||||
sessionId: string;
|
||||
transport: StreamableHTTPServerTransport;
|
||||
} {
|
||||
createSession(userId: string): { sessionId: string; transport: StreamableHTTPServerTransport } {
|
||||
const sessionId = randomUUID();
|
||||
|
||||
const transport = new StreamableHTTPServerTransport({
|
||||
sessionIdGenerator: () => sessionId,
|
||||
onsessioninitialized: (id) => {
|
||||
this.logger.log(
|
||||
`MCP session initialized: ${id} for actor=${actor.userId} tenant=${actor.tenantId} correlation=${actor.correlationId}`,
|
||||
);
|
||||
this.logger.log(`MCP session initialized: ${id} for user ${userId}`);
|
||||
},
|
||||
});
|
||||
|
||||
@@ -258,7 +48,7 @@ export class McpService implements OnModuleDestroy {
|
||||
{ capabilities: { tools: {} } },
|
||||
);
|
||||
|
||||
this.registerTools(server, actor);
|
||||
this.registerTools(server, userId);
|
||||
|
||||
transport.onclose = () => {
|
||||
this.logger.log(`MCP session closed: ${sessionId}`);
|
||||
@@ -271,126 +61,31 @@ export class McpService implements OnModuleDestroy {
|
||||
);
|
||||
});
|
||||
|
||||
this.sessions.set(sessionId, { server, transport, createdAt: new Date(), actor });
|
||||
this.sessions.set(sessionId, { server, transport, createdAt: new Date(), userId });
|
||||
return { sessionId, transport };
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the transport for an existing session only when it belongs to the
|
||||
* currently authenticated MCP actor. Guessed or cross-tenant session IDs grant
|
||||
* no authority.
|
||||
* Returns the transport for an existing session, or null if not found.
|
||||
*/
|
||||
getSession(sessionId: string, actor: McpActorContext): StreamableHTTPServerTransport | null {
|
||||
const entry = this.sessions.get(sessionId);
|
||||
if (!entry) return null;
|
||||
if (!sameActorAuthorization(entry.actor, actor)) {
|
||||
this.logger.warn(
|
||||
`MCP session actor or scope mismatch: session=${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)),
|
||||
);
|
||||
getSession(sessionId: string): StreamableHTTPServerTransport | null {
|
||||
return this.sessions.get(sessionId)?.transport ?? null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Registers all platform tools on the given McpServer instance.
|
||||
*/
|
||||
registerTools(server: McpServer, actor: McpActorContext): void {
|
||||
private registerTools(server: McpServer, _userId: string): void {
|
||||
// ─── Brain: Project tools ────────────────────────────────────────────
|
||||
|
||||
server.registerTool(
|
||||
'brain_list_projects',
|
||||
{
|
||||
description: 'List all projects in the brain.',
|
||||
inputSchema: strictObject({}),
|
||||
inputSchema: z.object({}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'brain_list_projects', params);
|
||||
const projects = filterProjectsForActor(
|
||||
actor,
|
||||
(await this.brain.projects.findAll()) as ProjectLike[],
|
||||
);
|
||||
async () => {
|
||||
const projects = await this.brain.projects.findAll();
|
||||
return {
|
||||
content: [{ type: 'text' as const, text: JSON.stringify(projects, null, 2) }],
|
||||
};
|
||||
@@ -401,21 +96,17 @@ export class McpService implements OnModuleDestroy {
|
||||
'brain_get_project',
|
||||
{
|
||||
description: 'Get a project by ID.',
|
||||
inputSchema: strictObject({
|
||||
inputSchema: z.object({
|
||||
id: z.string().describe('Project ID (UUID)'),
|
||||
}),
|
||||
},
|
||||
async ({ id, ...params }) => {
|
||||
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;
|
||||
async ({ id }) => {
|
||||
const project = await this.brain.projects.findById(id);
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text' as const,
|
||||
text: authorizedProject
|
||||
? JSON.stringify(authorizedProject, null, 2)
|
||||
: `Project not found: ${id}`,
|
||||
text: project ? JSON.stringify(project, null, 2) : `Project not found: ${id}`,
|
||||
},
|
||||
],
|
||||
};
|
||||
@@ -428,23 +119,20 @@ export class McpService implements OnModuleDestroy {
|
||||
'brain_list_tasks',
|
||||
{
|
||||
description: 'List tasks, optionally filtered by project, mission, or status.',
|
||||
inputSchema: strictObject({
|
||||
inputSchema: z.object({
|
||||
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 (params) => {
|
||||
assertMcpToolAuthorized(actor, 'brain_list_tasks', params);
|
||||
const { projectId, missionId, status } = params;
|
||||
async ({ projectId, missionId, status }) => {
|
||||
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();
|
||||
const scopedTasks = await this.filterTasksForActor(actor, tasks as TaskLike[]);
|
||||
return { content: [{ type: 'text' as const, text: JSON.stringify(scopedTasks, null, 2) }] };
|
||||
return { content: [{ type: 'text' as const, text: JSON.stringify(tasks, null, 2) }] };
|
||||
},
|
||||
);
|
||||
|
||||
@@ -452,7 +140,7 @@ export class McpService implements OnModuleDestroy {
|
||||
'brain_create_task',
|
||||
{
|
||||
description: 'Create a new task in the brain.',
|
||||
inputSchema: strictObject({
|
||||
inputSchema: z.object({
|
||||
title: z.string().describe('Task title'),
|
||||
description: z.string().optional().describe('Task description'),
|
||||
projectId: z.string().optional().describe('Project ID'),
|
||||
@@ -461,8 +149,6 @@ 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,
|
||||
@@ -476,7 +162,7 @@ export class McpService implements OnModuleDestroy {
|
||||
'brain_update_task',
|
||||
{
|
||||
description: 'Update an existing task.',
|
||||
inputSchema: strictObject({
|
||||
inputSchema: z.object({
|
||||
id: z.string().describe('Task ID'),
|
||||
title: z.string().optional(),
|
||||
description: z.string().optional(),
|
||||
@@ -485,17 +171,9 @@ 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, {
|
||||
@@ -520,19 +198,14 @@ export class McpService implements OnModuleDestroy {
|
||||
'brain_list_missions',
|
||||
{
|
||||
description: 'List all missions, optionally filtered by project.',
|
||||
inputSchema: strictObject({
|
||||
inputSchema: z.object({
|
||||
projectId: z.string().optional().describe('Filter by project ID'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'brain_list_missions', params);
|
||||
const { projectId } = params;
|
||||
const missions = await this.filterMissionsForActor(
|
||||
actor,
|
||||
(projectId
|
||||
? await this.brain.missions.findByProject(projectId)
|
||||
: await this.brain.missions.findAll()) as MissionLike[],
|
||||
);
|
||||
async ({ projectId }) => {
|
||||
const missions = projectId
|
||||
? await this.brain.missions.findByProject(projectId)
|
||||
: await this.brain.missions.findAll();
|
||||
return { content: [{ type: 'text' as const, text: JSON.stringify(missions, null, 2) }] };
|
||||
},
|
||||
);
|
||||
@@ -540,12 +213,13 @@ export class McpService implements OnModuleDestroy {
|
||||
server.registerTool(
|
||||
'brain_list_conversations',
|
||||
{
|
||||
description: 'List conversations for the authenticated MCP actor.',
|
||||
inputSchema: strictObject({}),
|
||||
description: 'List conversations for a user.',
|
||||
inputSchema: z.object({
|
||||
userId: z.string().describe('User ID'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'brain_list_conversations', params);
|
||||
const conversations = await this.brain.conversations.findAll(actor.userId);
|
||||
async ({ userId }) => {
|
||||
const conversations = await this.brain.conversations.findAll(userId);
|
||||
return {
|
||||
content: [{ type: 'text' as const, text: JSON.stringify(conversations, null, 2) }],
|
||||
};
|
||||
@@ -558,15 +232,14 @@ export class McpService implements OnModuleDestroy {
|
||||
'memory_search',
|
||||
{
|
||||
description:
|
||||
'Search stored insights and knowledge for the authenticated MCP actor using natural language.',
|
||||
inputSchema: strictObject({
|
||||
'Search across stored insights and knowledge using natural language. Returns semantically similar results.',
|
||||
inputSchema: z.object({
|
||||
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 (params) => {
|
||||
assertMcpToolAuthorized(actor, 'memory_search', params);
|
||||
const { query, limit } = params;
|
||||
async ({ userId, query, limit }) => {
|
||||
if (!this.embeddings.available) {
|
||||
return {
|
||||
content: [
|
||||
@@ -578,11 +251,7 @@ export class McpService implements OnModuleDestroy {
|
||||
};
|
||||
}
|
||||
const embedding = await this.embeddings.embed(query);
|
||||
const results = await this.memory.insights.searchByEmbedding(
|
||||
actor.userId,
|
||||
embedding,
|
||||
limit ?? 5,
|
||||
);
|
||||
const results = await this.memory.insights.searchByEmbedding(userId, embedding, limit ?? 5);
|
||||
return { content: [{ type: 'text' as const, text: JSON.stringify(results, null, 2) }] };
|
||||
},
|
||||
);
|
||||
@@ -590,21 +259,20 @@ export class McpService implements OnModuleDestroy {
|
||||
server.registerTool(
|
||||
'memory_get_preferences',
|
||||
{
|
||||
description: 'Retrieve stored preferences for the authenticated MCP actor.',
|
||||
inputSchema: strictObject({
|
||||
description: 'Retrieve stored preferences for a user.',
|
||||
inputSchema: z.object({
|
||||
userId: z.string().describe('User ID'),
|
||||
category: z
|
||||
.string()
|
||||
.optional()
|
||||
.describe('Filter by category: communication, coding, workflow, appearance, general'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'memory_get_preferences', params);
|
||||
const { category } = params;
|
||||
async ({ userId, category }) => {
|
||||
type Cat = 'communication' | 'coding' | 'workflow' | 'appearance' | 'general';
|
||||
const prefs = category
|
||||
? await this.memory.preferences.findByUserAndCategory(actor.userId, category as Cat)
|
||||
: await this.memory.preferences.findByUser(actor.userId);
|
||||
? await this.memory.preferences.findByUserAndCategory(userId, category as Cat)
|
||||
: await this.memory.preferences.findByUser(userId);
|
||||
return { content: [{ type: 'text' as const, text: JSON.stringify(prefs, null, 2) }] };
|
||||
},
|
||||
);
|
||||
@@ -613,8 +281,9 @@ export class McpService implements OnModuleDestroy {
|
||||
'memory_save_preference',
|
||||
{
|
||||
description:
|
||||
'Store a learned preference for the authenticated MCP actor (e.g., "prefers tables over paragraphs").',
|
||||
inputSchema: strictObject({
|
||||
'Store a learned user preference (e.g., "prefers tables over paragraphs", "timezone: America/Chicago").',
|
||||
inputSchema: z.object({
|
||||
userId: z.string().describe('User ID'),
|
||||
key: z.string().describe('Preference key'),
|
||||
value: z.string().describe('Preference value (JSON string)'),
|
||||
category: z
|
||||
@@ -623,9 +292,7 @@ export class McpService implements OnModuleDestroy {
|
||||
.describe('Category: communication, coding, workflow, appearance, general'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'memory_save_preference', params);
|
||||
const { key, value, category } = params;
|
||||
async ({ userId, key, value, category }) => {
|
||||
type Cat = 'communication' | 'coding' | 'workflow' | 'appearance' | 'general';
|
||||
let parsedValue: unknown;
|
||||
try {
|
||||
@@ -634,7 +301,7 @@ export class McpService implements OnModuleDestroy {
|
||||
parsedValue = value;
|
||||
}
|
||||
const pref = await this.memory.preferences.upsert({
|
||||
userId: actor.userId,
|
||||
userId,
|
||||
key,
|
||||
value: parsedValue,
|
||||
category: (category as Cat) ?? 'general',
|
||||
@@ -648,8 +315,9 @@ export class McpService implements OnModuleDestroy {
|
||||
'memory_save_insight',
|
||||
{
|
||||
description:
|
||||
'Store a learned insight, decision, or knowledge for the authenticated MCP actor.',
|
||||
inputSchema: strictObject({
|
||||
'Store a learned insight, decision, or knowledge extracted from the current interaction.',
|
||||
inputSchema: z.object({
|
||||
userId: z.string().describe('User ID'),
|
||||
content: z.string().describe('The insight or knowledge to store'),
|
||||
category: z
|
||||
.string()
|
||||
@@ -657,13 +325,11 @@ export class McpService implements OnModuleDestroy {
|
||||
.describe('Category: decision, learning, preference, fact, pattern, general'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'memory_save_insight', params);
|
||||
const { content, category } = params;
|
||||
async ({ userId, content, category }) => {
|
||||
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: actor.userId,
|
||||
userId,
|
||||
content,
|
||||
embedding,
|
||||
source: 'agent',
|
||||
@@ -680,11 +346,16 @@ export class McpService implements OnModuleDestroy {
|
||||
{
|
||||
description:
|
||||
'Get the current orchestration mission status including milestones, tasks, and active session.',
|
||||
inputSchema: strictObject({}),
|
||||
inputSchema: z.object({
|
||||
projectPath: z
|
||||
.string()
|
||||
.optional()
|
||||
.describe('Project path. Defaults to gateway working directory.'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'coord_mission_status', params);
|
||||
const status = await this.coordService.getMissionStatus(process.cwd());
|
||||
async ({ projectPath }) => {
|
||||
const resolvedPath = projectPath ?? process.cwd();
|
||||
const status = await this.coordService.getMissionStatus(resolvedPath);
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
@@ -700,11 +371,16 @@ export class McpService implements OnModuleDestroy {
|
||||
'coord_list_tasks',
|
||||
{
|
||||
description: 'List all tasks from the orchestration TASKS.md file.',
|
||||
inputSchema: strictObject({}),
|
||||
inputSchema: z.object({
|
||||
projectPath: z
|
||||
.string()
|
||||
.optional()
|
||||
.describe('Project path. Defaults to gateway working directory.'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'coord_list_tasks', params);
|
||||
const tasks = await this.coordService.listTasks(process.cwd());
|
||||
async ({ projectPath }) => {
|
||||
const resolvedPath = projectPath ?? process.cwd();
|
||||
const tasks = await this.coordService.listTasks(resolvedPath);
|
||||
return { content: [{ type: 'text' as const, text: JSON.stringify(tasks, null, 2) }] };
|
||||
},
|
||||
);
|
||||
@@ -713,14 +389,17 @@ export class McpService implements OnModuleDestroy {
|
||||
'coord_task_detail',
|
||||
{
|
||||
description: 'Get detailed status for a specific orchestration task.',
|
||||
inputSchema: strictObject({
|
||||
inputSchema: z.object({
|
||||
taskId: z.string().describe('Task ID (e.g. P2-005)'),
|
||||
projectPath: z
|
||||
.string()
|
||||
.optional()
|
||||
.describe('Project path. Defaults to gateway working directory.'),
|
||||
}),
|
||||
},
|
||||
async (params) => {
|
||||
assertMcpToolAuthorized(actor, 'coord_task_detail', params);
|
||||
const { taskId } = params;
|
||||
const detail = await this.coordService.getTaskStatus(process.cwd(), taskId);
|
||||
async ({ taskId, projectPath }) => {
|
||||
const resolvedPath = projectPath ?? process.cwd();
|
||||
const detail = await this.coordService.getTaskStatus(resolvedPath, taskId);
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
|
||||
@@ -1,13 +1,9 @@
|
||||
import { Injectable, Logger } from '@nestjs/common';
|
||||
import { createQueue, type QueueHandle } from '@mosaicstack/queue';
|
||||
import type { ActorTenantScope } from '../auth/session-scope.js';
|
||||
|
||||
const scopedSessionId = (sessionId: string, scope: ActorTenantScope) =>
|
||||
`${scope.tenantId}:${scope.userId}:${sessionId}`;
|
||||
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 SESSION_SYSTEM_KEY = (sessionId: string) => `mosaic:session:${sessionId}:system`;
|
||||
const SESSION_SYSTEM_FRAGMENTS_KEY = (sessionId: string) =>
|
||||
`mosaic:session:${sessionId}:system:fragments`;
|
||||
const SYSTEM_OVERRIDE_TTL_SECONDS = 604800; // 7 days
|
||||
|
||||
interface OverrideFragment {
|
||||
@@ -24,9 +20,9 @@ export class SystemOverrideService {
|
||||
this.handle = createQueue();
|
||||
}
|
||||
|
||||
async set(sessionId: string, override: string, scope: ActorTenantScope): Promise<void> {
|
||||
async set(sessionId: string, override: string): Promise<void> {
|
||||
// Load existing fragments
|
||||
const existing = await this.handle.redis.get(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope));
|
||||
const existing = await this.handle.redis.get(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId));
|
||||
const fragments: OverrideFragment[] = existing
|
||||
? (JSON.parse(existing) as OverrideFragment[])
|
||||
: [];
|
||||
@@ -41,11 +37,11 @@ export class SystemOverrideService {
|
||||
// Store both: fragments array and condensed result
|
||||
const pipeline = this.handle.redis.pipeline();
|
||||
pipeline.setex(
|
||||
SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope),
|
||||
SESSION_SYSTEM_FRAGMENTS_KEY(sessionId),
|
||||
SYSTEM_OVERRIDE_TTL_SECONDS,
|
||||
JSON.stringify(fragments),
|
||||
);
|
||||
pipeline.setex(SESSION_SYSTEM_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS, condensed);
|
||||
pipeline.setex(SESSION_SYSTEM_KEY(sessionId), SYSTEM_OVERRIDE_TTL_SECONDS, condensed);
|
||||
await pipeline.exec();
|
||||
|
||||
this.logger.debug(
|
||||
@@ -53,21 +49,21 @@ export class SystemOverrideService {
|
||||
);
|
||||
}
|
||||
|
||||
async get(sessionId: string, scope: ActorTenantScope): Promise<string | null> {
|
||||
return this.handle.redis.get(SESSION_SYSTEM_KEY(sessionId, scope));
|
||||
async get(sessionId: string): Promise<string | null> {
|
||||
return this.handle.redis.get(SESSION_SYSTEM_KEY(sessionId));
|
||||
}
|
||||
|
||||
async renew(sessionId: string, scope: ActorTenantScope): Promise<void> {
|
||||
async renew(sessionId: string): Promise<void> {
|
||||
const pipeline = this.handle.redis.pipeline();
|
||||
pipeline.expire(SESSION_SYSTEM_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
|
||||
pipeline.expire(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
|
||||
pipeline.expire(SESSION_SYSTEM_KEY(sessionId), SYSTEM_OVERRIDE_TTL_SECONDS);
|
||||
pipeline.expire(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId), SYSTEM_OVERRIDE_TTL_SECONDS);
|
||||
await pipeline.exec();
|
||||
}
|
||||
|
||||
async clear(sessionId: string, scope: ActorTenantScope): Promise<void> {
|
||||
async clear(sessionId: string): Promise<void> {
|
||||
await this.handle.redis.del(
|
||||
SESSION_SYSTEM_KEY(sessionId, scope),
|
||||
SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope),
|
||||
SESSION_SYSTEM_KEY(sessionId),
|
||||
SESSION_SYSTEM_FRAGMENTS_KEY(sessionId),
|
||||
);
|
||||
this.logger.debug(`Cleared system override for session ${sessionId}`);
|
||||
}
|
||||
|
||||
@@ -67,11 +67,10 @@ The MVP is complete when ALL declared workstreams are complete AND every cross-c
|
||||
|
||||
## Workstreams
|
||||
|
||||
| # | 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 |
|
||||
| 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 |
|
||||
| # | 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 |
|
||||
| W2+ | TBD | (additional workstreams declared as scoped) | — | — | Scope creep is expected and explicitly accommodated |
|
||||
|
||||
### Likely Additional Workstreams (Not Yet Declared)
|
||||
|
||||
|
||||
96
docs/PRD.md
96
docs/PRD.md
@@ -79,102 +79,6 @@ 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
|
||||
|
||||
@@ -14,10 +14,9 @@
|
||||
|
||||
## Workstream Rollup
|
||||
|
||||
| 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 |
|
||||
| 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 |
|
||||
| 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 |
|
||||
|
||||
## Cross-Cutting Tracking
|
||||
|
||||
|
||||
61
docs/fleet/proposals/mosaic-platform-prd/DEBATE-FINDINGS.md
Normal file
61
docs/fleet/proposals/mosaic-platform-prd/DEBATE-FINDINGS.md
Normal file
@@ -0,0 +1,61 @@
|
||||
# Debate Findings & Dispositions — Mosaic Platform PRD
|
||||
|
||||
> **Convener:** mos-claude-1 · **Date:** 2026-07-09 · **Panel:** 9 personas × 2 rounds (8 Claude lenses + independent Codex runtime), 20 agents, ~1.05M tokens
|
||||
> **Artifacts:** `jarvis-brain:docs/scratchpads/mosaic-platform-prd-debate/` (THREAD.md — full transcript · SYNTHESIS.md — Principal-Engineer close-out)
|
||||
> **Mandate (Jason, 2026-07-09):** "debate and make judgment calls." D1–D12 were held fixed; the panel attacked only the implementing structure. Dispositions below are the convener's judgment calls, folded into the sibling docs in this directory. Items marked **OPEN — Jason** need his call at ratification.
|
||||
|
||||
## How to read this
|
||||
|
||||
Every synthesis finding (SYNTHESIS.md §1, items 1–24) is dispositioned here. **Accepted** findings are folded into the PRDs/YAML as inline fixes or "Debate-accepted deltas" rows; this file is the traceability record. Severity labels are the panel's (P0 blocker → P3 note).
|
||||
|
||||
## P0 findings — all accepted, folded inline
|
||||
|
||||
| # | Finding | Disposition |
|
||||
| --- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| 1 | Storage-authority contradiction (X2 "relational + flat-file backends" vs Q "Postgres sole record") | **Accepted.** X2 rewritten: Postgres authoritative for all product entities; flat-file backend is a derived, regenerated, **read-only projection**. |
|
||||
| 2 | Phase-1 Jarvis executes external PA ops before the relay exists (J2 vs NS-11) | **Accepted.** J2 split: **J2a** workspace-internal entities (phase 1) / **J2b** external integrations (phase 2, `depends_on: [P2]`). Phase-1 has no external credential path at all. |
|
||||
| 3 | `phase` vs `depends_on` disagree; dispatcher obedience undefined | **Accepted.** Phases encoded as real DAG edges (`X2 depends_on [J2a, P2]`, J2b gate above); sandbox dispatch-test added to ratification checklist (README Gate Zero §). |
|
||||
| 4 | Four load-bearing upstream artifacts unverified (memory subsystem, Hermes-MCP tool equivalents, push pipeline, wake/event router) | **Accepted.** README gains **Gate Zero** (pre-ratification artifact audit); presumed-MISSING rows get goal cards now: **M1** (memory subsystem), **J6** (event/wake router), **K3** (push pipeline). Parity map's MCP row re-pointed at concrete deliverables. |
|
||||
| 5 | X-R4 migration manifest wrong about its own source tree (phantom `tickets.json`, unlisted dirs, six divergent memory stores, live Vikunja sync unmapped) | **Accepted.** X-R4 rewritten: migrator stage 1 = machine-generated source census (incl. untracked paths + all memory stores), per-path disposition, any `unknown` blocks; re-point list generated from `tools/sync_*.py`; Vikunja disposition line added to X-R6. |
|
||||
|
||||
## P1 findings — all accepted
|
||||
|
||||
| # | Finding | Disposition (folded as deltas) |
|
||||
| --- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| 6 | Events have no provider join key; re-point duplicates the calendar | **Accepted.** Provider-sourced events migrate **from the provider**; flat files supply only brain-native events. DST/recurrence fixture is the AC (X-R6 delta). |
|
||||
| 7 | Approval pipeline has no state machine (double-execute / approve≠execute) | **Accepted.** P deltas: CAS on one durable row, terminal states, consumed-event dedupe table (shared substrate with bridge + wake dedupe), payload persisted at request time, poll/ack outcomes, per-capability retry class, staleness bound, `approved_unexecuted` alarm, re-surface = re-**prepare** with machine diff. |
|
||||
| 8 | "Cannot bypass by construction" false: agent-readable vault creds + host-resident creds outside the relay | **Accepted.** Credentials gateway-only + scoped capability tokens; P1 gains host credential inventory with continuous scheduled scan in the health floor; clean-host AC passes with empty exemption list. |
|
||||
| 9 | Silent auto-deny steady state (fail-closed TTL + single surface + unprovisioned push) | **Accepted.** K gains homeserver ops + monitored push (K3); CLI approval surface ships **with** P2; delivered/seen tracking + TTL/2 escalation; `denied` / `expired_seen` / `expired_unseen` distinct terminal states. |
|
||||
| 10 | Prompt injection → durable memory; wake turns add system-role injection | **Accepted.** J2 write-side trust rule (transitive `source_trust=external`; standing-instruction-shaped content needs user ratification before retrievable); wake turns templated with provenance-tagged data fields. |
|
||||
| 11 | Exactly-one-Jarvis has no fencing incl. the Matrix send path | **Accepted.** New **J-R16** workspace lease `(workspace_id, epoch)` CAS row in product Postgres; epoch on every write; pre-send lease re-check; takeover notice; degraded = mute-with-notice. NS-10 amended: one main agent per **workspace**. |
|
||||
| 12 | Matrix principal resolution undefined (Codex #2, unanswered in R2) | **Accepted.** K/P delta: immutable Matrix user ID + bridge provenance + workspace membership → product principal; unlinked/bridged-unlinked identities read-only, cannot approve/butt-in/trigger external writes. All four Codex fixtures = deny + audit. |
|
||||
| 13 | Policy evaluation time undefined (Codex #7, unanswered in R2) | **Accepted.** Immutable policy snapshot on every prepared action/card; execution revalidates or fails `policy_changed`; delegated effects gated by grant **intersection**. |
|
||||
|
||||
## P2/P3 findings — accepted (see per-PRD delta sections)
|
||||
|
||||
14 Hermes evidence snapshot **before** stop (machine gate) · 15 Q1 crash barriers + `external_refs` unique-index table (one mechanism, three consumers) · 16 rollback honestly scoped (transport-only, point-of-no-return = first native card) + bounded day-30 review with three recorded outcomes · 17 human-attention budget (rate limits, quotas, deferrable flag, away state) · 18 self-referential-loop containment (provenance labels, source-grounded retrieval preference, retrieval eval gate ≥50 queries / ≥90% baseline recall@5 + negative queries, tombstones, priority budget, day-1 trend telemetry) · 19 butt-in exclusive lease + structured control-plane API + break-glass doctrine · 20 default-closed capability gating with `unclassified` third state · 21 per-agent atomic approval-routing cutover table · 22 `needs-decision` card lifecycle (immutable spec + typed amendments; `ratified_by` authorizes dispatch, never merge) · 23 retention class per durable table; dedupe pruning checkpoint-coupled · 24 AC-NS-8 made measurable (distinct quota pools pinned in profile; TTFT p95 ≤ 1.2× baseline, ≥30 interleaved turns).
|
||||
|
||||
**All accepted.** None conflicts with D1–D12.
|
||||
|
||||
## Open disagreements — convener judgment calls
|
||||
|
||||
| § | Question | Call |
|
||||
| --- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| 3.1 | Gate architecture: tiered blocking pack (Moonshot+Ops+ML-Cal) vs 4 artifact-existence machine gates + pass/fail-free pre-registered dossier (Contrarian) | **Adopted the agreed floor now** (4 machine gates on irreversible transitions, pre-registration, priced amendments, day-1 emission — folded into X). Superstructure choice is **OPEN — Jason**. Convener recommendation: **Contrarian's dossier + dumb gates** — the tier demonstrably gamed itself within one debate round (13+ claims vs cap 10, slot-riding, zero demotions); simple machine gates don't degrade under pressure. |
|
||||
| 3.2 | Audit schema: additive-only typed schema (Coder-Data) vs six-field mandatory envelope + typed payloads + pinned checked-in queries (Contrarian) | **Adopted: minimal envelope + schema-on-read** (folded into P1 delta). Rationale: preserves "can't add data later" essentials without a god-schema by committee; an additive typed layer can be grown later where query pain proves it. |
|
||||
| 3.3 | Unclassified capability: reject at call time vs version-scoped activation hold vs capability-scoped hold | **Adopted: capability-scoped hold** (Contrarian R2#6a, synthesis editor concurs) — gate the capability, ship the version; security patches are never pinned behind classification. |
|
||||
| 3.4 | Away mode: fail-closed expiry labeled `expired_during_away` vs suppress preparation while away | **Adopted: suppress preparation** of non-deferrable requests while away + audited suppressed-preparations list swept on return. Cleaner than labeling corpses; nothing expires that was never surfaced. |
|
||||
| 3.5 | Memory-exclusion scope for measurement artifacts | **Adopted: normative/parametric split** (Contrarian R2#4) — rules the agent is scored against stay retrievable; thresholds/seeds/drill timings/canary templates are excluded. |
|
||||
| 3.6 | Statistical instruments | **Adopted:** deterministic named crash barriers as the gate; residual randomized soak is **trace-directed**, not wall-clock-uniform. |
|
||||
| 3.7 | K2 scope narrowing by Hermes traffic audit | **Adopted as a Gate Zero action:** run the audit pre-ratification; platforms with live traffic become the must-have subset gating X3. |
|
||||
|
||||
## Process rules adopted (README)
|
||||
|
||||
- **Gate Zero** — pre-ratification upstream-artifact audit (`present @ SHA` or MISSING → goal card).
|
||||
- **Conflict register** — spec contradictions block the requirement, not the mission ("alert, don't auto-resolve" promoted to specs).
|
||||
- **DoD line** on every goal card (runbook, health-floor alerts, AGENTS.md).
|
||||
- **Silent-roster rule** — a panel member's silent round records their open findings as open items, never consensus (Codex's R2 silence on #2/#7 is the instance; both were folded as P1 items 12–13 above, explicitly not consensus-resolved).
|
||||
|
||||
## Addendum — logging & telemetry (Jason, 2026-07-09, post-debate)
|
||||
|
||||
Requirement raised outside the panel, folded in the same pass: Mosaic Stack must support **inbound error reporting/logging** from agents and installs, plus **optional anonymous agentic-efficiency telemetry** — no IP or PII capture, opt-in. The P0 of this capability already exists: **MALS** (Mosaic Agent Log System, FastAPI+Postgres, `~/src/mals`), currently dark because its k3s migration landed without an Ingress (tracked: infrastructure #135). Folded as new **workstream L** (L1 restore MALS · L2 Mosaic-native ingestion · L3 anonymous telemetry) + standing objective **NS-14**. Day-1 trial-metric emission (finding 18) targets MALS until W3 panels exist.
|
||||
@@ -0,0 +1,58 @@
|
||||
# PRD — Backlog Provider Sync Adapters · Workstream Q
|
||||
|
||||
> **Status:** DRAFT for ratification · **Goals:** Q1–Q3 · **Doctrine:** NS-12 (ratified D3)
|
||||
> **Debate pass 2026-07-09:** panel findings folded — see `DEBATE-FINDINGS.md`.
|
||||
|
||||
## Mission
|
||||
|
||||
Users choose where they _see and touch_ work — Gitea, GitHub, a local kanban — while the **Mosaic Backlog on native Postgres stays the sole record and dispatch engine** (upholds ASM-1; NS-3/NS-4/NS-5 guarantees never depend on an external provider). Providers attach as bidirectional sync adapters.
|
||||
|
||||
## Requirements
|
||||
|
||||
### Adapter interface + Gitea (Q1)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Q-R1 | A `BacklogProviderAdapter` interface: map card ⇄ external item (create/update/close/comment/label), with stable external-id linkage stored on the card. |
|
||||
| Q-R2 | Sync is bidirectional and conflict-safe: native record wins on divergence; external edits arrive as proposed mutations (applied if non-conflicting, else surfaced). |
|
||||
| Q-R3 | Claims, TTLs, depends_on DAG, and dispatch state live **only** in the native record; adapters project them (e.g. as labels/comments) but never own them. |
|
||||
| Q-R4 | Gitea adapter first (webhook + API), configured per workspace: repo mapping, label conventions, direction (mirror-out / mirror-in / full). |
|
||||
| Q-R5 | Adapter enable/disable is workspace configuration; zero adapters is a fully supported mode. |
|
||||
|
||||
### GitHub (Q2)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Q-R6 | Same interface, GitHub Issues backend. Existing `packages/cli-tools` platform detection informs but does not implement this (that is dev tooling, not product runtime). |
|
||||
|
||||
### Local kanban (Q3)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Q-R7 | A webUI kanban board over the native backlog (no external provider needed) — the "local kanban" choice. Builds on W3's card views and/or the existing `KanbanBoard` component upgraded from demo-grade to live data. |
|
||||
|
||||
## Debate-accepted deltas (2026-07-09) — normative
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Q-R8 | **External-ref linkage is one shared mechanism:** a unique-indexed `external_refs(entity_id, system, external_id)` table serves adapter linkage (Q-R1), migration idempotency (X-R4 anti-join), and re-point verification (X-R6) — built once, three consumers. Idempotent upsert; a violated unique index is a converge signal, never an overwrite. |
|
||||
| Q-R9 | **Crash-safe external creates:** the adapter writes a `pending-link` row **before** any external create and embeds a deterministic card-id marker in the created item, so a crash between create and link-back is recovered by scan, never by duplicate creation. |
|
||||
| Q-R10 | **Echo-loop guard:** both directions carry revision counters; adapter-authored external edits are tagged (marker/actor) and skipped on read-back. A sync cycle that would re-import its own write is a hard test failure. |
|
||||
| Q-R11 | The sync engine is a **level-triggered reconciler** over desired-vs-observed state (same doctrine as J6), not a webhook-only event chase: webhooks accelerate convergence, the reconciler guarantees it. Missed webhooks are a latency event, not a correctness event. |
|
||||
| Q-R12 | Card spec immutability (J-R20) projects cleanly: the mirrored issue body is the pinned spec revision; amendments append as **ordered provider comments**, never body rewrites, so external watchers see the same amendment history as the native record. |
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. A card created by Jarvis (J3) appears as a Gitea issue within one sync interval; closing the issue in Gitea marks the card for review, not silent closure; dispatch/claims never round-trip through Gitea.
|
||||
2. Killing the adapter mid-mission: dispatch continues unaffected (record is native); on restart, sync converges without duplicates.
|
||||
3. The same mission can be mirrored to Gitea and viewed on the local kanban simultaneously without state divergence.
|
||||
4. **Named crash barriers** at every external-call boundary (`before_external_create`, `after_create_before_link`, `after_link_before_ack`): kill the adapter at each; zero duplicate external items, zero orphaned cards. CI rule: a new external call site without a named barrier + kill test **fails the build**. Residual randomized soak is trace-directed (§3.6 disposition).
|
||||
|
||||
## Non-goals
|
||||
|
||||
- External provider AS the backlog (vetoed — "truly swappable backends" option declined 2026-07-09).
|
||||
- Two-way sync of claims/TTL semantics (external systems can't express them; projection only).
|
||||
|
||||
## Assumptions
|
||||
|
||||
- ASSUMPTION: the delivery fleet's _engineering_ PR/issue flow on the stack repo itself continues to use `cli-tools`/Gitea directly — workstream Q is the product feature for user workspaces, not a replacement for the dev workflow.
|
||||
@@ -0,0 +1,83 @@
|
||||
# PRD — Hermes Decommission & Tenant-1 Migration · Workstream X
|
||||
|
||||
> **Status:** DRAFT for ratification · **Goals:** X1–X3 · **Doctrine:** NS-13, ASM-8 (Hermes untouched until verified parity)
|
||||
> Ratified direction (D2, 2026-07-09): Mosaic absorbs **all four** Hermes functions — messaging bridge, task board, permission relay, multi-platform reach.
|
||||
> **Debate pass 2026-07-09:** panel findings folded — this PRD took the heaviest rewrite (storage authority, migration census, memory-store hygiene, honest rollback scope). See `DEBATE-FINDINGS.md`.
|
||||
|
||||
## Deployment scope (D12/ASM-9)
|
||||
|
||||
The trial runs in the **homelab**. Hermes and the primitive-era stack (`mos-claude.service`, jarvis-brain boards) live in the **USC/web1 environment**, which is untouched during the trial. This workstream therefore lands in two stages: **X-in-homelab** (prove parity where the fleet is native — mainly K/P/Q verification plus tenant-1 migration) and **X-at-USC** (post-trial adoption: apply the parity checklist to web1, migrate Mos-on-web1 to `mosaic-agent@orchestrator`, then decommission Hermes there, with `/src/infrastructure` GitOps updates in the same delivery set).
|
||||
|
||||
**Trial go/no-go (D12/ASM-9 gate):** the homelab→USC promotion is **owner-judgment**, not an automated metric. The stage gate is: _Jason instantiates and operates the split-agent stack in the homelab and is satisfied with its operation._ Only on that explicit sign-off does X-at-USC begin. The capability ACs (AC-NS-8…11) are the evidence Jason weighs; they inform the decision but do not auto-trigger USC deployment.
|
||||
|
||||
## Mission
|
||||
|
||||
Retire Hermes entirely. Mosaic becomes the platform for transport (Matrix connector), task board (native backlog + webUI/adapters), approvals (permission relay), and multi-platform reach (mautrix bridges). In the same arc, Jason's jarvis-brain flat-file data migrates into the product as **tenant #1**, making the product's PA feature set the dogfooded default.
|
||||
|
||||
## Parity map (what replaces what)
|
||||
|
||||
| Hermes function | Mosaic replacement | Workstream |
|
||||
| ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | ---------- |
|
||||
| Messaging bridge (Discord/Telegram/…) | Matrix connector + mautrix bridges | K1, K2 |
|
||||
| Kanban / task board | Native Mosaic Backlog + webUI board + provider adapters | A\*, Q, W3 |
|
||||
| Permission relay (`permissions_*`) | Guard-rails engine + approval queue (Matrix + webUI) | P1–P3 |
|
||||
| Cross-platform user reach | mautrix bridges (agents speak Matrix only) | K2 |
|
||||
| Hermes MCP tools in agent sessions | **Per-tool equivalence table** (Gate Zero artifact): approvals → P2, board ops → Q1/A\*, messaging → K1 — not a generic "gateway API" gesture | P2, Q1, K1 |
|
||||
|
||||
## Requirements
|
||||
|
||||
### Parity checklist + cutover plan (X1)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| X-R1 | A written, testable parity checklist per row above; each item verified in production before its Hermes counterpart is disabled. The checklist is seeded from a **pre-trial usage audit**: per-MCP-tool and per-capability call counts over a trailing window, plus an inventory of Hermes-held provider callbacks/webhooks and secrets. Parity rows with `n < 5` real invocations in the window cannot be "verified by traffic" — they get **scheduled drills in weeks 1–3** of the observation window instead of silent green. |
|
||||
| X-R1a | **Approval-routing cutover is per-agent atomic:** a cutover table states, per agent, the single moment its `permissions_*` path flips from Hermes to the P relay. No agent ever has two live approval paths; no approval window where neither path is live. |
|
||||
| X-R2 | Cutover is staged with rollback at every stage; Hermes runs untouched until AC-NS-11 is verified (ASM-8). **Rollback is honestly scoped (debate #16): it restores _transport_ (Hermes services + MCP registrations) — board/approval state created natively during the trial does NOT back-migrate.** The **point of no return is the first native-only card**; the runbook says so explicitly, and the abort path (below) is written before cutover, not during an incident. |
|
||||
| X-R3 | The Matrix charter's live-cutover rules apply: stated window, announce before/after, rollback ready. |
|
||||
|
||||
### Tenant-1 migration (X2)
|
||||
|
||||
**Framing (ratified 2026-07-09, storage authority clarified by debate P0 #1):** jarvis-brain **is the P0 (prototype) Mosaic Stack** — its flat-file data layer is the zeroth implementation of what the product does properly. Migration is therefore _P0 → proper Mosaic Stack_. **Native Postgres is the sole authoritative store for every product entity** (consistent with workstream Q's "sole record" doctrine and NS-3/NS-4/NS-5). A flat-file backend, where offered, is a **derived, regenerated, read-only projection** — the same relationship generated views have to JSON in the P0 today — never a co-equal write target. Two distinct data classes migrate — they are not the same destination and neither is frozen:
|
||||
|
||||
- **(a) PA data** (projects, tasks, events, tickets, knowledge) → product entities in the Jason workspace (Project/Task/Event/KnowledgeEntry), authoritative in Postgres; flat-file export available as a read-only projection.
|
||||
- **(b) Agent memory & operational knowledge** (runbooks, digests, scratchpads, OpenBrain thoughts) → the **enhanced memory subsystem (goal M1: vector DB + memory service)**. This flow stays **live and writable** throughout — it was never Hermes and must not be frozen by the PA cutover.
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| X-R4 | **Stage 1 of the migrator is a machine-generated source census, not a hand-written file list** (debate P0 #5 — the hand list was already wrong about its own tree). The census walks the live repo (tracked + untracked), inventories every data path — `data/**`, all memory stores (`memory/`, `memories/`, `memory_store*`, `memory.md`, `brain.jsonl`, `jarvis.db`, digests), scratchpads, notes, prior-generation artifacts — and assigns each a disposition: `migrate-as-PA(entity type)` / `migrate-as-memory(M1 class)` / `derived-regenerate` / `retire-with-history`. **Any path dispositioned `unknown` blocks the run.** Stage 2 migrates per-disposition, preserving source ids in metadata; idempotency via anti-join on the shared `external_refs` table (Q-R8); named crash barriers at each phase boundary. A **field-map table** covers the full `brain.py` query surface (status, progress, due, priority, domain, notes, staleness) → product entity fields, so AC 2 is checkable field-by-field. |
|
||||
| X-R5 | Dry-run mode with a diffable report **generated from the census** (counts per disposition, per-entity field mapping, unmapped-field list — must be empty or explicitly waived); Jason ratifies the report before the real run (canonical-data gate — this is the one migration step that is his call). |
|
||||
| X-R6 | External sync jobs (GLPI, Google Calendar, ICS, Gmail, **Vikunja — disposition decided here: re-point or retire, not silently dropped**) each get a **written per-integration transition protocol**: freeze flat-file sync job → verify product integration live → re-point → verify → retire old job. **Provider-sourced events migrate FROM the provider, not from flat files** (flat files supply only brain-native events) — the provider join key is authoritative, so re-pointing cannot duplicate the calendar (debate #6). Calendar fixture (Codex): a DST-crossing recurring event with one moved and one cancelled occurrence, plus an all-day event, round-trips with zero duplicates and correct local times. |
|
||||
| X-R7 | Agent memory/operational knowledge (b) is migrated into the M1 memory subsystem **before** any jarvis-brain retirement; the memory write path stays continuously available (no read-only freeze of an active substrate). The census classifies every memory item: `ratified` / `superseded` / `draft` / `rejected` / `debate-artifact` / `protocol-normative` / `protocol-parametric`. **Parametric measurement artifacts (thresholds, seeds, drill timings, canary templates) are excluded from embedding** (§3.5 disposition — rules the agent is scored against stay retrievable; the knobs do not). Superseded/rejected items get **tombstones**, and supersession triggers re-embedding of affected summaries. **Retirement gate: a retrieval eval — ≥50 representative queries, ≥90% of baseline recall@5, plus negative queries (rejected/superseded content must NOT surface) — passes against M1 before any flat-file store goes read-only.** After cutover: write paths to retired stores are killed and a CI lint fails any reintroduction. Only once **both** (a) and (b) are migrated and verified is the jarvis-brain repo retired read-only (history preserved); generated views and brain.py retire. This closes the P0 prototype. |
|
||||
|
||||
### Decommission (X3)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| X-R8 | **Pre-stop evidence snapshot is a machine gate:** before Hermes stops, a checksummed snapshot of its state (board items, pending approvals, bridge registrations, per-tool usage counts) is captured and stored with the trial artifacts. The drill schedule (X-R1) and the credential-revocation report both **cite the snapshot checksum** — no snapshot, no stop. Then: services stopped, disabled, and removed from infra (GitOps: `/src/infrastructure` updated in the same delivery set); credentials revoked — the revocation report cites a **final scan** showing zero live references; MCP registrations removed from agent runtimes. |
|
||||
| X-R9 | **Bounded day-30 review** between stop and removal, pre-registered before cutover (dossier: what will be measured, panels cited, drill results attached — see W-R15/L1 for where the metrics live, `stack_version`-segmented so mid-window upgrades don't blur rates). The review records exactly one of three outcomes: **promote** (remove Hermes), **extend with named blockers** (each blocker a card with an owner), or **abort** (execute the pre-written abort runbook; transport-only rollback per X-R2). "Insufficient data" is a recordable outcome that forces extend — never a shrug into promote. Any in-window regression flips back per X-R2. |
|
||||
|
||||
## Machine gates on irreversible transitions (debate §3.1 agreed floor)
|
||||
|
||||
Four **artifact-existence gates** — dumb, checkable, ungameable — sit on the irreversible transitions. Each is "the artifact exists and passes its check", not a scored rubric:
|
||||
|
||||
1. **Pre-stop snapshot** exists with valid checksum (X-R8) — gates Hermes stop.
|
||||
2. **Census with zero `unknown` rows** exists (X-R4) — gates the PA migration run.
|
||||
3. **Retrieval eval pass record** exists (X-R7) — gates memory-store retirement.
|
||||
4. **All parity rows green-or-drilled** (X-R1: verified by traffic or by scheduled drill; no silent low-n green) — gates Hermes removal at day-30.
|
||||
|
||||
The gate _superstructure_ beyond this floor (tiered blocking pack vs pre-registered dossier) is **OPEN — Jason** at ratification; convener recommendation in `DEBATE-FINDINGS.md` §3.1.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. AC-NS-11: with Hermes stopped, no fleet or main-agent capability regresses.
|
||||
2. `python tools/brain.py today`'s information content is fully answerable by Jarvis from the product workspace post-X2, verified field-by-field against the X-R4 field-map table.
|
||||
3. Zero references to Hermes MCP tools in any active agent runtime config after X3.
|
||||
4. The X-R6 calendar fixture (DST-crossing recurrence, moved + cancelled occurrence, all-day event) round-trips with zero duplicates.
|
||||
5. The X-R7 retrieval eval passes against M1 before any memory store goes read-only; negative queries return no superseded/rejected content.
|
||||
6. All four machine gates above have their artifacts on record before their respective transitions execute.
|
||||
|
||||
## Sequencing note
|
||||
|
||||
X depends on the longest chains (K1→K2, P2, Q1, J2a→J2b, **M1** — X2 cannot complete class (b) without the memory subsystem existing). Dependencies are real DAG edges in `north-star-additions.yaml` (`X2 depends_on [J2a, P2, M1]`), not prose phases (debate P0 #3). Expected order of value delivery: J1–J4 (Jarvis on existing transport interim) → K1/J5 (Matrix room) → P2, W1–W3, Q1 in parallel → X1 checklist → X2 migration → K2 bridges → X3 decommission.
|
||||
|
||||
- ASSUMPTION (interim transport): until K1 lands, Jarvis may run against the tmux connector (CLI/`agent send`) rather than standing up any Discord channel — keeps D1 (Matrix-first, no #jarvis Discord) intact.
|
||||
@@ -0,0 +1,89 @@
|
||||
# PRD — HMI Main Agent ("Jarvis") · Workstream J
|
||||
|
||||
> **Status:** DRAFT for ratification · **Source of truth once landed:** NORTH_STAR.yaml goals J1–J6
|
||||
> **Depends on upstream:** H2 (system-type profiles), A3a (card lifecycle), B1 (supervisor tick), F4/K1 (Matrix connector)
|
||||
> **Debate pass 2026-07-09:** panel findings folded — see `DEBATE-FINDINGS.md` for dispositions.
|
||||
|
||||
## Mission
|
||||
|
||||
Every Mosaic **workspace** gets exactly one always-on human-machine-interface agent — default alias **Jarvis**, unit `mosaic-agent@main.service` — that owns the human relationship: conversation, idea development, schedule, email, tasks, knowledge. It delegates all engineering/research/ops work to the orchestrator (**Mos**, `mosaic-agent@orchestrator.service`) through the Mosaic Backlog, and reports fleet status to the user without ever interrupting the orchestrator.
|
||||
|
||||
Jarvis is a **Level-0 orchestrator**: it accomplishes its own work through _delegation and subagents_, never by executing coding/infra tasks itself. PA mutations (tasks/events/knowledge) are direct API calls; everything heavier is either a spawned subagent (research, drafting, analysis) or a backlog card handed to Mos (engineering/infra/fleet). This keeps the main agent's context conversational and light.
|
||||
|
||||
This solves the observed failure mode: a busy orchestrator that can't respond, accumulates conversational context rot, and derails over time. Post-split, the orchestrator's context is execution-only.
|
||||
|
||||
Because Jarvis and Mos are **separate agents with separate model capacity** (D11: Jarvis on Opus, Mos on Fable; independent inference quota), orchestrator load cannot degrade conversational latency — the isolation in AC-NS-8 is a capacity guarantee, not merely a separate process.
|
||||
|
||||
## Requirements
|
||||
|
||||
### Persona & runtime (J1)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| J-R1 | Jarvis is provisioned from the personal-assistant persona baseline via system-type profiles (H2/H3); alias, model tier, host, and channel are profile fields, not code. |
|
||||
| J-R2 | Default model tier **Opus** (ratified D11); the orchestrator's tier is independent. Always-_available_ ≠ always-_billed_: Opus is provisioned 24/7 but cost is per-interaction — an idle Jarvis (no user turn in flight) incurs no model spend, so "always-on" carries no standing token bill. |
|
||||
| J-R3 | Jarvis survives reboot under systemd (`mosaic-agent@main`), participates in the fleet heartbeat protocol, and is counted in the supervisor's health floor. |
|
||||
| J-R4 | Persona customization is update-surviving per H4 (override layer wins on merge). |
|
||||
| J-R16 | **Workspace lease (exactly-one fencing):** Jarvis acquires `workspace_lease(workspace_id, epoch)` — a CAS row in product Postgres — before processing any turn. Every PA write, card, and approval carries the epoch; stale-epoch writes are rejected server-side; the connector re-checks the lease immediately before every outbound send. Takeover posts an in-room/in-channel epoch notice. Degraded mode (lease unobtainable) = **mute-with-notice**, never conversational-while-unfenced. Clean shutdown releases the lease. This primitive also excludes homelab/USC split-brain during adoption. |
|
||||
| J-R17 | Per-agent spend metering with a daily budget alarm for `mosaic-agent@main`; a main-agent crash-loop is a distinct, escalated supervisor condition (not a generic restart count). |
|
||||
| J-R18 | **Resume protocol (promoted from open item):** resume context is reconstructed from authoritative queries (board, heartbeats, workspace entities), with narrative summary layered on top; a session-start divergence check flags contradictions between narrative and authoritative state. Jarvis is never re-instantiated from its own lossy summaries alone. |
|
||||
|
||||
### PA toolchain (J2a workspace-internal · J2b external)
|
||||
|
||||
**Split (debate P0 #2):** phase-1 Jarvis operates only on workspace-internal entities — **no external-write credential path exists** until the permission relay (P2) is live. External integrations arrive in phase 2 as J2b, `depends_on: [J2a, P2]`. Test: in a phase-1 deployment, `email:send` is _impossible_ (no credential provisioned), not merely unapproved.
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| J-R5 | (J2a) Jarvis executes personal-assistant mutations **directly** in the user's workspace via the product API: tasks, events/calendar, knowledge entries, ideas. No delegation for PA ops (ratified D4). |
|
||||
| J-R6 | (J2b) External PA integrations (email, external calendars, helpdesk) are workspace-scoped integrations; **raw credentials are held exclusively by the gateway** — Jarvis receives scoped capability tokens, never provider secrets; actions flagged `requires_approval` route through the permission relay (workstream P). |
|
||||
| J-R7 | Until tenant-1 migration (X2) completes, Jarvis may read/write the jarvis-brain flat files as a transitional adapter; the adapter is deleted after the **last verified X-R6 re-point** (not at a nominal "X2 cutover" date). A per-phase, per-entity-type source-of-truth table in the J1 profile states which store is authoritative at every moment. |
|
||||
| J-R19 | **Write-side trust rule:** externally-sourced content (email bodies, bridged messages, webhook payloads) written into workspace entities or memory inherits `source_trust=external` **transitively through summarization**. Standing-instruction-shaped external content requires explicit user ratification before it becomes retrievable. This closes the injection→durable-memory channel. |
|
||||
|
||||
### Delegation contract (J3)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| J-R8 | The Jarvis→Mos handoff is **only** via Mosaic Backlog cards: goal, acceptance criteria, priority, depends_on, advisory budget. Never via chat messages to the orchestrator. |
|
||||
| J-R9 | Jarvis translates conversation outcomes into card sets; ambiguity is resolved with the user _before_ card creation — the orchestrator receives only decision-complete work. |
|
||||
| J-R10 | Card authorship is attributed (author=main-agent, ratified-by=user where applicable) for audit. |
|
||||
| J-R11 | Authority line: Mos holds all execution and merge authority (NS-4). Jarvis relays the user's GO/NO-GO gates as card state, and never acquires fleet mutation, merge, or dispatch rights. `ratified_by=user` authorizes **dispatch only** — it never substitutes for the reviewer-of-record merge gate. |
|
||||
| J-R20 | Card sets are drafted then **published atomically** with client idempotency keys (no partial card sets on crash). Card spec is **immutable after publish**; changes arrive as typed, ordered amendments with a revision counter; reviewer sign-offs pin the spec revision; scope-expanding amendments re-enter ratification. |
|
||||
| J-R21 | **`needs-decision` lifecycle:** a worker hitting genuine ambiguity sets `needs-decision(question, options)` on the card **with a durable checkpoint** (pushed branch + card note) — resume after days is a re-dispatch, not a context continuation. Jarvis relays the question to the user and writes the answer back as an amendment. This is the sanctioned clarification path; J-R8's no-chat rule stands. |
|
||||
| J-R22 | Jarvis-authored cards draw from a **priority budget** (quota per priority class per window) — priority inflation by the card author degrades the field for the whole fleet and is structurally capped, not policed by review. |
|
||||
|
||||
### Passive observability (J4)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| J-R12 | Jarvis answers "what's the fleet doing" from read-only sources: heartbeat files, `mosaic fleet ps` JSON, backlog card states, CI status. Zero messages to the orchestrator for status. |
|
||||
| J-R13 | Jarvis proactively surfaces to the user: blocked cards, failed CI on user-ratified missions, approval requests pending, budget advisories. (PDA-friendly phrasing per SOUL.md.) Delivered via the **J6 event/wake router** — per-agent polling is forbidden. |
|
||||
| J-R23 | **Event/wake router (J6):** one shared, level-triggered reconciler over durable state (heartbeats, card states, approval queue) wakes Jarvis on state _change_ with hysteretic per-condition suppression (wake once, then only on change or declared backoff; suppression survives restarts). Wake turns are **templated** — fixed instruction frame, workspace data only in delimited, provenance-tagged data fields (closes the injection→system-role channel). Idempotent on source event id via the shared consumed-events table. Router is in the health floor; its cost model and latency bound are stated in the J6 card. Reconciles J-R2: an idle Jarvis costs nothing _because waking is event-driven, not poll-driven_. |
|
||||
|
||||
### Channel (J5)
|
||||
|
||||
| ID | Requirement |
|
||||
| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| J-R14 | **Phase 2 (target channel):** Jarvis's conversation lives in a dedicated Matrix room on the self-hosted homeserver via `OrchestratorConnector(matrix)` (K1 = f4 Phase 2). Matrix-first: no Discord channel is created for Jarvis (ratified D1). |
|
||||
| J-R14a | **Phase 1 (interim channel, ratified):** Jarvis runs on the **tmux/CLI connector** — the f4 Phase-1 default connector. The operator launches the `mosaic-agent@main` tmux session and issues `/remote-control` to grant interactive access; this is the day-one conversation surface. No Discord, no Matrix dependency in Phase 1 (keeps D1 intact and unblocks J1–J4 before K1 lands). |
|
||||
| J-R15 | Multi-platform user reach arrives via mautrix bridges (K2); Jarvis's code path is Matrix-only (from Phase 2 onward). |
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. AC-NS-8 **(made measurable)**: distinct credential/quota pools for Jarvis and Mos are pinned in the J1 profile; scripted suite of ≥30 interleaved turns under full orchestrator load; TTFT p95 ≤ 1.2× idle baseline with bootstrap CI; orchestrator receives zero conversational traffic.
|
||||
2. AC-NS-9: a conversationally-agreed mission round-trips (cards → drained → completed → reported by Jarvis) with no chat handoff.
|
||||
3. Kill the orchestrator mid-conversation: Jarvis conversation is unaffected; Jarvis reports the outage from heartbeat state. (Directly exercises the separate-capacity guarantee.)
|
||||
4. `!sys`-equivalent admin verbs work in Jarvis's active channel — the tmux/CLI session in Phase 1, the Matrix room in Phase 2 (status/logs/clear/restart of the main agent).
|
||||
5. **Phase-1 channel:** operator launches the `mosaic-agent@main` tmux session, issues `/remote-control`, and holds a full conversation with Jarvis over CLI with no Matrix/Discord dependency.
|
||||
6. **Fencing:** start a second `mosaic-agent@main` by hand — it fails to acquire the workspace lease, posts a notice, and stays mute; zero duplicate writes or cards reach the workspace (J-R16).
|
||||
7. **Phase-1 credential surface:** audit of a phase-1 install finds no external-provider credential readable by the Jarvis runtime (J2a/J2b split holds by construction).
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Jarvis executing code/infra changes (that is Mos + fleet).
|
||||
- Horizontal sharding of the main agent (rejected in the Matrix charter: split-brain).
|
||||
- Per-workspace fleets (post-MVP per ASM-6).
|
||||
|
||||
## Open items (for Mos's planner)
|
||||
|
||||
- ~~Context hygiene / resume protocol~~ — promoted to J-R18 by the 2026-07-09 debate pass.
|
||||
- Reconcile the old `apps/api` matrix-bot-sdk workspace bridge with the F4 connector design (one Matrix stack, not two). NOTE (verified 2026-07-09): no matrix dependency remains in `apps/api` on `origin/main` — this item is likely already moot; confirm before K1 build.
|
||||
@@ -0,0 +1,98 @@
|
||||
# PRD — Permission Relay · Workstream P
|
||||
|
||||
> **Status:** DRAFT for ratification · **Goals:** P1–P3
|
||||
> **Debate pass 2026-07-09:** panel findings folded — see `DEBATE-FINDINGS.md`. The relay was the panel's densest target; the deltas below are normative.
|
||||
> **Design origin (historical):** `docs/3-architecture/guard-rails-capability-permissions.md` — the "prepare freely, execute with approval" snapshot. **Not present on `origin/main`** (survives only in the stale `/src/mosaic-stack` clone), so its essential model is folded into this PRD below; **this document is the authoritative, self-contained spec for P.**
|
||||
> **Replaces:** Hermes `permissions_list_open` / `permissions_respond` relay (Hermes exit prerequisite, NS-13)
|
||||
|
||||
## Mission
|
||||
|
||||
A human-in-the-loop approval mechanism for agent actions: any capability listed as `requires_approval` is prepared by the agent, queued, and executed only after an explicit human approve — from the Matrix room or the webUI. Today this exists only as a bare `applyGuardRails()` method; Hermes currently fills the gap and must be replaced before decommission.
|
||||
|
||||
## Design model (folded in — the authoritative spec, since the origin snapshot is off-main)
|
||||
|
||||
**Doctrine — "prepare freely, execute with approval":** an agent may plan, draft, and stage any action without friction; only the _committing_ step of a `requires_approval` capability blocks on a human decision.
|
||||
|
||||
**Permission levels (least→most):** `read` → `organize` → `draft` → `execute` → `admin`. A capability grant names a level; `requires_approval` gates the transition into `execute`/`admin` for the capabilities a workspace marks sensitive.
|
||||
|
||||
**Grant shape:** `resource:action` (e.g. `email:send`, `git:push_main`, `dns:update`), scoped per workspace and per agent-persona, stored as configuration (profile field) so a user tightens/loosens without a code change.
|
||||
|
||||
## Requirements
|
||||
|
||||
### Guard-rails engine (P1)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| P-R1 | Capabilities are `resource:action` grants (e.g. `email:send`, `git:push_main`, `dns:update`) with permission levels (read / organize / draft / execute / admin) per the existing design doc. |
|
||||
| P-R2 | Each integration declares its `requires_approval` list; grants are workspace-scoped and per-agent-persona. |
|
||||
| P-R3 | Enforcement sits in the gateway/API dispatch path — an agent cannot bypass it by construction; bypass attempts are audited and denied. |
|
||||
| P-R4 | Policy is configuration (profile field), honoring the configurability pillar: a user can tighten/loosen per capability without code change. |
|
||||
|
||||
### Approval queue + chat approvals (P2)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| P-R5 | A pending approval is a durable queue record: requesting agent, capability, human-readable intent summary, prepared payload reference, TTL. |
|
||||
| P-R6 | Approve/deny from the Matrix room (message action or reply verb); the requesting agent is notified of the outcome and proceeds/aborts. |
|
||||
| P-R7 | Timeout = deny (fail-closed), with **per-capability TTLs** and distinct terminal states: `denied` / `expired_seen` / `expired_unseen` — agents must not reason about an expiry as a human "no". Deny and timeout leave the system unchanged. |
|
||||
| P-R8 | Full audit trail: who approved what, when, from which surface (AC-NS-10). |
|
||||
| P-R9 | The main agent (Jarvis) surfaces pending approvals conversationally (J-R13) but approval authority is the human's — Jarvis never auto-approves. |
|
||||
|
||||
### webUI surface (P3)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ----------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| P-R10 | Pending-approval queue view in `apps/web` with one-click approve/deny, filterable per workspace/agent (depends W3 dashboard shell). |
|
||||
|
||||
## Debate-accepted deltas (2026-07-09) — normative
|
||||
|
||||
### State machine & delivery (extends P-R5–P-R7)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| P-R11 | Approval lifecycle is a **CAS state machine on one durable row**: `pending → approved \| denied \| expired_seen \| expired_unseen`, all terminal. Concurrent surfaces (Matrix, webUI, CLI, TTL reaper) contend via compare-and-swap; exactly one wins. |
|
||||
| P-R12 | The **prepared payload is persisted in the record at request time** — never a reference to requesting-agent process state (the agent may be dead when approval lands). Outcome delivery is **poll/ack**, not push-only; `approved_unexecuted > N min` raises an alarm. |
|
||||
| P-R13 | A **consumed-event dedupe table** (shared substrate with bridged-message and wake-turn dedupe — built once, three consumers) makes approval consumption idempotent under Matrix at-least-once replay. Dedupe retention is **checkpoint-coupled**: events older than the durable sync token are dropped before lookup, so pruning never reopens the replay window. |
|
||||
| P-R14 | Each capability declares `retry: safe \| at-most-once`; a prepare→execute **staleness bound** rejects execution of stale payloads. Re-surfacing an expired item **re-prepares** (new linked record with a rendered machine diff against the original) — never re-queues a stale payload. |
|
||||
| P-R15 | **CLI approval surface** (`mosaic approvals list\|approve\|deny`) ships **with P2** as must-have — the newest infra (Matrix) is never the only approval path. Per-request delivered/seen tracking; TTL/2 escalation via a second path. |
|
||||
|
||||
### Identity & policy (closes Codex #2/#7)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| P-R16 | **Principal resolution:** every inbound approve/deny maps to a product principal via immutable Matrix user ID + bridge provenance + workspace membership. Unlinked identities and bridged puppets without an account link converse read-only and **cannot approve, butt-in, or trigger external writes**. Fixtures: bridged puppet, renamed user, invited non-admin, removed-member-with-lagging-room-membership — all deny + audit with reason. |
|
||||
| P-R17 | **Policy snapshot:** every prepared action and card stores an immutable snapshot (profile id/version, grants evaluated). Execution **revalidates against current policy** or fails with explicit `policy_changed`. Profile changes are audited with schema validation + dry-run impact report. Delegated work (subagent, Jarvis-authored card) executes under the **intersection** of originator and executor grants. |
|
||||
|
||||
### Credential boundary (makes P-R3 true)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| P-R18 | Raw provider credentials are held **exclusively by the gateway**; agents receive scoped capability tokens; the gateway injects secrets server-side. If the agent runtime can read the provider secret, P-R3 is decoration. |
|
||||
| P-R19 | P1 delivers a **fleet-host credential inventory**: every host-resident credential (SSH keys, kubeconfigs, tool tokens) classified `moved-behind-gateway` or `explicitly-exempt(reason, owner, expiry)`. Enforced by a **continuous scheduled scan** of agent-readable paths (alert on unclassified), registered in the health floor. The clean-host install AC passes with an **empty exemption list**. Break-glass is one standing exempt row (owner: operator; audited post-hoc). |
|
||||
|
||||
### Gating defaults & load (closes default-open + human-overdraw)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| P-R20 | **Default-closed inversion:** `execute`/`admin` capabilities on external integrations require approval **unless** workspace-allowlisted. Third state `unclassified`: a capability with no classification **rejects** at the gate. Classification happens at integration-version activation, scoped to the **capability, not the version** — a security patch bundling one new capability ships same-day; only the new capability rejects until classified. Manifest-less capabilities reject + integrity alert. |
|
||||
| P-R21 | Rate limits + `max_pending_per_agent_per_capability`; queue depth and human decision latency are exported metrics with thresholds (rubber-stamping guard). Capabilities carry a `deferrable` flag; a declared **away state** pauses deferrable TTLs, batches pings, and **suppresses preparation** of non-deferrable requests (suppressed list swept, priority-ordered and paginated, on return). |
|
||||
| P-R22 | Approval summaries render **machine-extracted payload facts unconditionally** (recipient, amount, target host — no tunable similarity threshold); agent prose is secondary. **Canary approvals** are gateway-generated, short-circuited at the gateway (never executable), immediately disclosed after decision, timing seeded outside agent-readable stores; the gated criterion is machine-flag correctness — human catch rate is reported with binomial CI, non-blocking. |
|
||||
| P-R23 | Every durable table introduced by P declares a **retention class**, linted in CI; pruning jobs are health-floor registered. Minimal mandatory audit envelope: `ts, workspace, actor, correlation_id, stack_version, schema_version` — payloads are typed free-form with pinned, checked-in queries (debate §3.2 disposition). |
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. AC-NS-10 end-to-end: a `requires_approval` action executes only post-approve; deny/timeout paths verified unchanged + audited.
|
||||
2. Approval round-trip from a phone Matrix client (Element) in under 3 taps — **and** the same round-trip via `mosaic approvals` CLI with the homeserver stopped.
|
||||
3. With Hermes stopped, permission flow fully served by Mosaic (feeds AC-NS-11).
|
||||
4. Crash-consistency: kill the gateway at each named barrier (`before_persist`, `after_approve_before_execute`, `after_execute_before_ack`); zero double-executions, zero lost approvals across the suite.
|
||||
5. All four principal-resolution fixtures (P-R16) deny + audit; policy-change race (P-R17) fails `policy_changed`, never executes under stale grants.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Automated quality gates (coordinator/CI approvals) — different system, already exists.
|
||||
- Fine-grained LLM output moderation — out of scope; this governs _actions_.
|
||||
|
||||
## Assumptions
|
||||
|
||||
- ASSUMPTION: the durable queue rides the native Postgres storage service (same substrate as the backlog), not a new datastore.
|
||||
- ASSUMPTION: routine delivery operations already hard-gated as no-confirmation (push/merge per Mosaic contract) are NOT routed through the relay — the relay is for `requires_approval` capabilities only, so it does not reintroduce routine confirmation prompts.
|
||||
@@ -0,0 +1,64 @@
|
||||
# PRD — webUI Fleet Control · Workstream W (realizes F6)
|
||||
|
||||
> **Status:** DRAFT for ratification · **Goals:** W1–W3 · **Upstream anchor:** `PRD-fleet-suite.md` Phase F6 ("webUI hooks — stable JSON contract + terminate/attach(butt-in) surface")
|
||||
> Confirmed gap: zero xterm/pty/tmux code in `apps/web` on either the old snapshot or `origin/main`.
|
||||
> **Debate pass 2026-07-09:** panel findings folded — see `DEBATE-FINDINGS.md`.
|
||||
|
||||
## Mission
|
||||
|
||||
The user can pop in on **any** agentic tmux session from the web, and get a full top-down view of the system — fleet roster, health, work in flight, spend — without touching a terminal. This is the product surface for "user has ability to pop in on any agent session; full top-down view available."
|
||||
|
||||
## Requirements
|
||||
|
||||
### Attach service (W1)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| W-R1 | A gateway service exposes per-agent session streams over WebSocket: **watch** (read-only pane view, cannot type) and **butt-in** (interactive takeover), mirroring the existing CLI verbs `mosaic agent watch/attach`. |
|
||||
| W-R2 | Authz is workspace-scoped through the product auth stack (BetterAuth/Authentik); watch and butt-in are separate grants; butt-in may be `requires_approval` per workspace policy (workstream P). |
|
||||
| W-R3 | Every attach (watch or butt-in) is audited: who, which agent, when, duration. |
|
||||
| W-R4 | Butt-in visibly flags the session to the agent runtime and other viewers (no silent takeover). |
|
||||
| W-R5 | Contract is stable JSON + streaming frames per F6's "stable JSON contract" requirement, so TUI/CLI and webUI share it. |
|
||||
|
||||
### Web terminal (W2)
|
||||
|
||||
| ID | Requirement |
|
||||
| ---- | ----------------------------------------------------------------------------------------------------------- |
|
||||
| W-R6 | xterm.js view in `apps/web` wired to W1: session list → click → live pane; toggle watch↔butt-in per grants. |
|
||||
| W-R7 | Reconnect-safe (network blips resume the stream), mobile-usable read-only view. |
|
||||
|
||||
### Top-down dashboard (W3)
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| W-R8 | Fleet dashboard: roster with per-agent state (systemd + tmux + heartbeat join, as `fleet ps` provides), current card/task, last activity, drift/boot-enable warnings. |
|
||||
| W-R9 | Work-in-flight view: backlog cards by state with depends_on DAG rendering; advisory spend per card (NS-2/NS-5). |
|
||||
| W-R10 | Operator controls: PAUSE kill-switch (NS-8), per-agent terminate (killswitch service), queue pause/resume — each gated + audited; destructive controls confirm. |
|
||||
| W-R11 | Existing widget framework (`AgentStatusWidget`, `OrchestratorEventsWidget`, SSE proxy routes) is the starting point, upgraded to the fleet contract rather than rebuilt. |
|
||||
|
||||
## Debate-accepted deltas (2026-07-09) — normative
|
||||
|
||||
| ID | Requirement |
|
||||
| ----- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| W-R12 | **Butt-in is an exclusive lease** with explicit, visible takeover: at most one interactive holder per session at any instant; a second client must take the lease and both parties see the transfer. Input frames are sequenced and deduped so a reconnect never double-sends; a heartbeat/idle timeout closes both the lease and its audit span — audit spans always terminate (extends W-R1/W-R3/W-R4). |
|
||||
| W-R13 | **Structured control plane:** PAUSE, terminate, restart, approve/deny, and queue operations are typed API verbs with RBAC and audit — never bytes typed into a tmux pane. Raw terminal input via butt-in is **rescue-only** and a separately-grantable permission from the control verbs. |
|
||||
| W-R14 | **Break-glass doctrine (documented, not prevented):** SSH + `tmux attach` on the fleet host bypasses W1 and P **by design**; it is inventoried under P-R19, audited post-hoc from host logs, and never treated as a product path. PAUSE additionally has an **on-host file/CLI actuator** so a dead gateway can never lock the operator out of the control that fixes the gateway. |
|
||||
| W-R15 | W3 ships the **trial metric panels** as workspace-scoped product views over product storage: canary machine-flag correctness, approval decision latency, card priority distribution, wake→ack rate, agent-authored memory retrieval fraction, human interaction load, fixed-input probe stability. The X-R9 trial evidence pack cites these panels; until W3 exists, day-1 emission targets MALS (L1). Workspace isolation fixture: workspace-2 admin sees zero workspace-1 rows. |
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. From a browser (desktop + phone), the user watches a live coder-agent pane read-only, then butt-ins with the right grant, types a message, detaches; agent session continues; audit log shows both.
|
||||
2. Dashboard reflects an agent crash within one heartbeat interval; PAUSE flip halts dispatch within one tick (AC-NS-5) from the UI.
|
||||
3. A user without butt-in grant can watch but cannot type (enforced server-side).
|
||||
4. Two clients contend for butt-in: exactly one holds the lease at any instant, the takeover is visible to both, and after a forced reconnect the input stream shows zero duplicated or interleaved frames (W-R12).
|
||||
5. With the gateway stopped, the operator PAUSEs the fleet via the on-host actuator; the bypass appears in the post-hoc audit (W-R14).
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Replacing tmux as the session substrate (tmux remains the transport; web is a view).
|
||||
- Cross-host federation of the dashboard (rides the existing federation workstream later, per upstream note "Phase 5 rides federation").
|
||||
|
||||
## Assumptions
|
||||
|
||||
- ASSUMPTION: pty bridging terminates at the gateway on the fleet host (web1), not in `apps/web`; Next.js only speaks WebSocket to the gateway.
|
||||
- ASSUMPTION: the jarvis-brain dashboard's node-pty/xterm work (`dashboard/server/terminal.ts`) serves as reference implementation only; code is not ported wholesale into the multi-tenant product without the authz layer above.
|
||||
62
docs/fleet/proposals/mosaic-platform-prd/README.md
Normal file
62
docs/fleet/proposals/mosaic-platform-prd/README.md
Normal file
@@ -0,0 +1,62 @@
|
||||
# Mosaic Platform PRD — Jarvis HMI + Hermes Decommission (DRAFT for ratification)
|
||||
|
||||
**Date:** 2026-07-09 · **Author:** proto-Jarvis session with Jason · **Status:** Decisions D1–D12 **ratified** (fixed inputs); implementing PRD structure **DRAFT** — refined 2026-07-09 post-review, then stress-tested by a 9-persona × 2-round debate panel the same day; all 24 panel findings dispositioned and folded (see `DEBATE-FINDINGS.md`; one item **OPEN — Jason**: gate superstructure, §3.1)
|
||||
**Target home:** `mosaicstack/stack` → `docs/fleet/` (NORTH_STAR.yaml additions + per-phase PRDs)
|
||||
|
||||
> **For the homelab orchestrator:** D1–D12 below are settled constraints, not open questions — do not reopen them. What is under review is only the _implementation_ (workstreams, goals, sequencing) that realizes them.
|
||||
> **Execution:** hand to the **homelab orchestrator** as orchestrated missions once ratified (D12). Land in `docs/fleet/` from `origin/main` — the `/src/mosaic-stack` clone on web1 is 5 months stale and must not be the base. The USC/web1 environment is out of scope for the trial; its cutover (workstream X applied to web1's Hermes + mos-claude) is a post-trial phase.
|
||||
|
||||
## Ratified decisions (Jason, 2026-07-09)
|
||||
|
||||
| # | Decision |
|
||||
| --- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| D1 | Jarvis conversation channel is **Matrix-first** — no #jarvis Discord channel is ever created. |
|
||||
| D2 | Mosaic absorbs **all four** Hermes functions before decommission: messaging bridge, Kanban/task board, permission relay, multi-platform reach. |
|
||||
| D3 | Task handoff: **native Mosaic Backlog is the record; Gitea/GitHub/local-kanban attach as bidirectional sync adapters** (upholds ASM-1). |
|
||||
| D4 | Jarvis executes **PA ops directly** (email, calendar, tasks, knowledge, tickets, research); all code/infra/fleet work is delegated to Mos via the backlog. |
|
||||
| D5 | Mosaic Stack is a **product from day one** — multi-user, Authentik tenancy, per-workspace isolation. |
|
||||
| D6 | Multi-platform reach via **Matrix + mautrix bridges** (telegram/signal/whatsapp/slack/discord); agents only ever speak Matrix. |
|
||||
| D7 | webUI builds on the existing `mosaicstack/stack` monorepo (`apps/web`), realizing the already-scoped F6 phase. |
|
||||
| D8 | **PRD first, then Mos runs it** as orchestrated missions. |
|
||||
| D9 | jarvis-brain flat-file data **migrates into the product as tenant #1** (workspace = Jason); brain.py/flat files retire after cutover. |
|
||||
| D10 | PRD form: **extend NORTH_STAR.yaml + per-phase docs in docs/fleet/** (NS-1 compliant). |
|
||||
| D11 | Jarvis runs **Opus**; Fable stays exclusive to Mos per the standing cost directive. Model tier is a persona/profile field. |
|
||||
| D12 | **Trial in the homelab** (the proper mosaic-fleet deployment, built by the homelab agents from `origin/main`), NOT at USC. The USC/web1 environment runs the primitive-era implementation (`mos-claude.service`, Hermes, jarvis-brain boards) and adopts only after the homelab trial validates. Jason relays this PRD to the homelab agent for implementation. |
|
||||
|
||||
## Artifacts in this draft
|
||||
|
||||
| File | Content |
|
||||
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `north-star-additions.yaml` | Proposed NORTH_STAR.yaml merge: NS-10…NS-14, workstreams J/K/W/P/Q/X + **M** (memory subsystem) + **L** (logging/telemetry), goal cards with DAG |
|
||||
| `PRD-jarvis-main-agent.md` | Workstream J — the HMI main agent |
|
||||
| `PRD-permission-relay.md` | Workstream P — human-in-the-loop approvals |
|
||||
| `PRD-webui-fleet-control.md` | Workstream W — tmux pop-in + top-down view (realizes F6) |
|
||||
| `PRD-backlog-providers.md` | Workstream Q — provider sync adapters |
|
||||
| `PRD-hermes-decommission.md` | Workstream X — parity checklist, tenant-1 migration, cutover |
|
||||
| `DEBATE-FINDINGS.md` | 2026-07-09 debate pass — all 24 findings dispositioned, open-disagreement judgment calls, process rules |
|
||||
|
||||
Workstreams **M** (M1 enhanced memory subsystem) and **L** (L1 restore MALS · L2 Mosaic-native log ingestion · L3 anonymous agentic telemetry, NS-14) carry no standalone PRD doc: M1's scope is defined by its consumers (X-R7 retrieval eval, J memory rules) and L's by the MALS lineage (`~/src/mals`, infrastructure #135); both live as goal cards in the YAML.
|
||||
|
||||
Workstream K (Matrix connector + mautrix bridges) intentionally has no new PRD doc: it extends the existing `docs/fleet/f4-matrix-connector.md`; its deltas are captured as K-goals in the YAML additions and referenced from the J/P/X PRDs.
|
||||
|
||||
## Relationship to existing upstream work
|
||||
|
||||
- Fleet CLI, persona library, system-type profiles (H1–H4), supervisor/dispatch (B), native backlog (A): **already exist or in flight upstream — not re-specified here.**
|
||||
- `f4-matrix-connector.md`: K1 = its Phase 2 implementation (verified present on `origin/main`; Phase 1 already ships the **tmux-default connector** that serves the P1 CLI channel per J-R14a). K2 (mautrix bridges) is additive infra.
|
||||
- F6 (webUI hooks) in `PRD-fleet-suite.md`: realized by workstream W (verified present on `origin/main`).
|
||||
- `docs/3-architecture/guard-rails-capability-permissions.md`: original design snapshot for workstream P — **not present on `origin/main`** (lives only in the stale `/src/mosaic-stack` clone). Its essential model is therefore folded into `PRD-permission-relay.md`, which is now the **self-contained authoritative spec** for P; the old path is cited as historical origin only.
|
||||
|
||||
## Gate Zero — pre-ratification checklist (debate P0 #3/#4, §3.7)
|
||||
|
||||
Ratification does not proceed on presumption. Before D-level sign-off, run and record:
|
||||
|
||||
1. **Upstream-artifact audit.** Every artifact this PRD load-bears on is verified `present @ <SHA>` on `origin/main` or marked **MISSING → goal card**. Presumed-missing rows already carded by this draft: **M1** (enhanced memory subsystem — nothing on main provides vector DB + memory service today), **J6** (event/wake router), **K3** (Matrix push pipeline + homeserver ops). If an audit finds one of these actually exists, retire the card and pin the SHA; if it finds _another_ gap, card it — no silent presumption in either direction.
|
||||
2. **Hermes traffic audit** (§3.7): per-platform bridge traffic + per-MCP-tool call counts over a trailing window. Platforms with live traffic become the must-have K2 subset gating X3; zero-traffic platforms become post-trial nice-to-haves. Feeds the X-R1 parity checklist and its low-n drill list.
|
||||
3. **Sandbox dispatch-test** of the DAG: load `north-star-additions.yaml` into a sandbox backlog and verify the dispatcher's actual claim order respects every `depends_on` edge (phases are documentation; edges are law).
|
||||
|
||||
## Process rules adopted from the debate pass (normative for this PRD's execution)
|
||||
|
||||
- **Conflict register:** a discovered contradiction between spec documents **blocks the affected requirement** (not the whole mission) until a register entry records the resolution. "Alert, don't auto-resolve" is promoted from data conflicts to spec conflicts. A CI lint greps for register references in amended docs.
|
||||
- **DoD line on every goal card:** each card states its definition-of-done additions — runbook updated, health-floor alert registered, AGENTS.md touched — so operational debt can't silently accrue card-by-card.
|
||||
- **Silent-roster rule:** in any panel/review round, a member's silence records their open findings as **open items, never consensus** (instance: Codex's unanswered principal-resolution and policy-evaluation-time findings were folded as P-R16/P-R17, explicitly not consensus-resolved).
|
||||
- **Immutable spec + typed amendments** (J-R20) applies to these PRD docs themselves post-ratification: changes arrive as amendments with a revision counter, and sign-offs pin the revision.
|
||||
@@ -0,0 +1,279 @@
|
||||
# Proposed additions to docs/fleet/NORTH_STAR.yaml — DRAFT (Jason ratification pending, 2026-07-09)
|
||||
#
|
||||
# Merge these entries into the existing NORTH_STAR.yaml sections, then regenerate
|
||||
# NORTH_STAR.md via renderNorthStarMarkdown (packages/mosaic/src/commands/fleet.ts).
|
||||
# Ids chosen to avoid collision with existing workstreams A–H and goals.
|
||||
|
||||
standing_objectives:
|
||||
- id: NS-10
|
||||
text: >-
|
||||
Every Mosaic workspace runs exactly one always-on HMI main agent (default
|
||||
alias "Jarvis", unit mosaic-agent@main) that owns all human conversation
|
||||
and user-level personal-assistant work (ideas, schedule, email, tasks,
|
||||
knowledge) and delegates engineering/research/ops missions to the
|
||||
orchestrator as Mosaic Backlog cards. It is a Level-0 orchestrator:
|
||||
it accomplishes work through delegation and subagents, never by executing
|
||||
coding/infra tasks itself, and it runs on model capacity separate from the
|
||||
orchestrator so its conversational latency is isolated from fleet load. The
|
||||
main agent never executes fleet work itself and never interrupts the
|
||||
orchestrator for status. Exactly-one-per-workspace is enforced by a
|
||||
workspace lease (J-R16), not by convention.
|
||||
- id: NS-11
|
||||
text: >-
|
||||
Irreversible or externally-visible agent actions pass a human-in-the-loop
|
||||
permission relay (approve/deny from chat or webUI) governed by
|
||||
per-capability guard rails; prepare freely, execute with approval.
|
||||
- id: NS-12
|
||||
text: >-
|
||||
The Mosaic Backlog remains the sole backlog of record; external providers
|
||||
(Gitea, GitHub, local kanban, …) attach as bidirectional sync adapters,
|
||||
never as the record.
|
||||
- id: NS-13
|
||||
text: >-
|
||||
Hermes is fully decommissioned once Mosaic reaches verified parity on
|
||||
transport (Matrix connector), task board (native backlog + webUI),
|
||||
permission relay, and multi-platform reach (mautrix bridges).
|
||||
- id: NS-14
|
||||
text: >-
|
||||
Mosaic Stack accepts inbound structured error/log reporting from every
|
||||
agent and install (MALS-lineage logging service); agentic-efficiency
|
||||
telemetry is optional, opt-in, and anonymous by construction — no IP or
|
||||
PII is captured or derivable from the ingestion path.
|
||||
|
||||
success_criteria:
|
||||
- id: AC-NS-8
|
||||
text: >-
|
||||
A user converses with the main agent in its channel while the
|
||||
orchestrator is under full load; because the main agent runs on separate
|
||||
model capacity (distinct credential/quota pools pinned in the J1
|
||||
profile), its response latency is unaffected and the orchestrator
|
||||
receives zero conversational traffic. Measured, not vibes: scripted
|
||||
suite, >=30 interleaved turns, TTFT p95 <= 1.2x idle baseline with
|
||||
bootstrap CI.
|
||||
- id: AC-NS-9
|
||||
text: >-
|
||||
A mission agreed in the main-agent conversation appears as a backlog card
|
||||
set with acceptance criteria, is drained by the orchestrator without
|
||||
chat-level handoff, and its completion is reported back to the user by the
|
||||
main agent from board/heartbeat state alone.
|
||||
- id: AC-NS-10
|
||||
text: >-
|
||||
An action listed as requires_approval executes only after an explicit
|
||||
human approve from Matrix or webUI; deny and timeout paths leave the
|
||||
system unchanged and audited.
|
||||
- id: AC-NS-11
|
||||
text: >-
|
||||
With Hermes stopped, no fleet or main-agent capability regresses
|
||||
(transport, board, approvals, multi-platform reach all served by Mosaic).
|
||||
|
||||
workstreams:
|
||||
- id: J
|
||||
title: HMI main agent ("Jarvis") — persona, PA toolchain, delegation contract
|
||||
- id: K
|
||||
title: Connectors & multi-platform reach — F4 Matrix implementation + mautrix bridges
|
||||
- id: W
|
||||
title: webUI fleet control — tmux pop-in, top-down view (realizes F6)
|
||||
- id: P
|
||||
title: Permission relay — capability guard rails + human approval queue
|
||||
- id: Q
|
||||
title: Backlog provider sync adapters — Gitea/GitHub/local kanban
|
||||
- id: X
|
||||
title: Hermes decommission & tenant-1 migration
|
||||
- id: M
|
||||
title: Enhanced memory subsystem — vector DB + memory service + provenance/tombstones (Gate Zero MISSING artifact)
|
||||
- id: L
|
||||
title: Logging & telemetry — MALS-lineage inbound error reporting + optional anonymous efficiency telemetry
|
||||
|
||||
goals:
|
||||
# J — HMI main agent
|
||||
- id: J1
|
||||
title: Main-agent persona + profile — instantiate personal-assistant system type as mosaic-agent@main (alias Jarvis), model tier a profile field (Opus default)
|
||||
phase: 1
|
||||
priority: must-have
|
||||
depends_on: [H2]
|
||||
# J2 split (debate P0 #2): phase-1 Jarvis must not hold an external-write
|
||||
# credential path before the permission relay (P2) exists — NS-11 by DAG.
|
||||
- id: J2a
|
||||
title: PA toolchain (workspace-internal) — tasks, events, knowledge, ideas executed directly against the product API in the user's workspace; no external credentials provisioned
|
||||
phase: 1
|
||||
priority: must-have
|
||||
depends_on: [J1]
|
||||
- id: J2b
|
||||
title: PA toolchain (external integrations) — email, external calendars, helpdesk via workspace-scoped integrations; credentials gateway-held; requires_approval routes through the relay
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [J2a, P2]
|
||||
- id: J3
|
||||
title: Delegation contract — main agent authors mission cards (goal, acceptance criteria, budget advisory) onto the backlog; orchestrator drains; no chat-level handoff
|
||||
phase: 1
|
||||
priority: must-have
|
||||
depends_on: [J1, A3a]
|
||||
- id: J4
|
||||
title: Passive fleet observability — main agent answers status from heartbeats, fleet ps JSON, and board state; zero orchestrator interrupts
|
||||
phase: 1
|
||||
priority: must-have
|
||||
depends_on: [J1, B1]
|
||||
- id: J5
|
||||
title: Main-agent Matrix room via OrchestratorConnector(matrix)
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [J1, K1]
|
||||
- id: J6
|
||||
title: Shared event/wake router — level-triggered reconciler over durable state (heartbeats, cards, approvals) with hysteretic per-condition suppression; templated provenance-tagged wake turns; per-agent polling forbidden (Gate Zero MISSING artifact; J-R13 depends on it)
|
||||
phase: 1
|
||||
priority: must-have
|
||||
depends_on: [J1]
|
||||
|
||||
# K — connectors & reach (extends f4-matrix-connector.md)
|
||||
- id: K1
|
||||
title: Matrix connector implementation — CS-API client factory per f4 Phase 2, self-hosted homeserver
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: []
|
||||
# K2 scope (debate §3.7): a pre-ratification Hermes traffic audit narrows the
|
||||
# must-have bridge subset to platforms with live traffic; only that subset
|
||||
# gates X3 — remaining bridges are genuinely optional post-X3.
|
||||
- id: K2
|
||||
title: mautrix bridge deployment (telegram/signal/whatsapp/slack/discord) as GitOps-managed infra; agents speak only Matrix; must-have subset = platforms carrying live Hermes traffic per Gate Zero audit
|
||||
phase: 3
|
||||
priority: should-have
|
||||
depends_on: [K1]
|
||||
- id: K3
|
||||
title: Push pipeline (Sygnal or equivalent) + homeserver ops — monitored delivery checks, health-floor registration, rehearsed backup/restore (Gate Zero MISSING artifact; P2 phone-approval AC depends on it)
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [K1]
|
||||
|
||||
# W — webUI fleet control (realizes F6)
|
||||
- id: W1
|
||||
title: Gateway pty/tmux attach service — read-only watch and interactive butt-in verbs, workspace-scoped authz, audit log
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: []
|
||||
- id: W2
|
||||
title: xterm.js session view in apps/web wired to W1 (watch + butt-in)
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [W1]
|
||||
- id: W3
|
||||
title: Top-down fleet dashboard — roster, heartbeats, cards in flight, advisory spend, PAUSE control
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [B1]
|
||||
|
||||
# P — permission relay
|
||||
- id: P1
|
||||
title: Capability guard-rails engine — resource:action grants, permission levels, requires_approval list per integration
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: []
|
||||
- id: P2
|
||||
title: Approval queue + approve/deny from the Matrix room (timeout = deny; full audit)
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [P1, K1]
|
||||
- id: P3
|
||||
title: Approval surface in webUI (pending queue, one-click approve/deny)
|
||||
phase: 3
|
||||
priority: should-have
|
||||
depends_on: [P1, W3]
|
||||
|
||||
# Q — backlog provider sync adapters
|
||||
- id: Q1
|
||||
title: Provider adapter interface + Gitea adapter (bidirectional card↔issue sync; native backlog stays record)
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [A2]
|
||||
- id: Q2
|
||||
title: GitHub adapter
|
||||
phase: 3
|
||||
priority: should-have
|
||||
depends_on: [Q1]
|
||||
- id: Q3
|
||||
title: Local kanban surface — webUI board view over the native backlog (no external provider required)
|
||||
phase: 2
|
||||
priority: should-have
|
||||
depends_on: [A2, W3]
|
||||
|
||||
# X — Hermes decommission & tenant-1 migration
|
||||
- id: X1
|
||||
title: Hermes parity checklist + cutover plan (transport, board, approvals, reach) with rollback
|
||||
phase: 3
|
||||
priority: must-have
|
||||
depends_on: [K1, P2, Q1]
|
||||
# jarvis-brain is the P0 (prototype) Mosaic Stack; migration targets the proper
|
||||
# stack storage layer. Storage authority (debate P0 #1): Postgres is
|
||||
# authoritative for ALL product entities; the flat-file backend is a derived,
|
||||
# regenerated, READ-ONLY projection — never a second writable store.
|
||||
- id: X2
|
||||
title: 'Tenant-1 migration — P0 (jarvis-brain) into the proper Mosaic Stack: (a) PA data (projects/tasks/events/knowledge) into the Jason workspace, (b) agent memory/runbooks into the enhanced memory subsystem M1 (kept live, not frozen); jarvis-brain retires read-only only after both are verified'
|
||||
phase: 3
|
||||
priority: must-have
|
||||
depends_on: [J2a, P2, M1]
|
||||
- id: X3
|
||||
title: Hermes decommission — stop and remove Hermes services after AC-NS-11 verified; pre-stop evidence snapshot (logs/config/callback inventory + checksum) is a machine gate
|
||||
phase: 4
|
||||
priority: must-have
|
||||
depends_on: [X1, X2, K2]
|
||||
|
||||
# M — enhanced memory subsystem (Gate Zero: cited by X2(b) but not built by
|
||||
# any prior workstream — this card closes that gap)
|
||||
- id: M1
|
||||
title: Enhanced memory subsystem — vector DB + memory service with mandatory provenance (human/agent/external), source-grounded retrieval preference, tombstones + re-embedding on source update, normative/parametric corpus split
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: []
|
||||
|
||||
# L — logging & telemetry (Jason 2026-07-09; NS-14). MALS (~/src/mals) is the
|
||||
# P0 of this capability; restoring it is infra work tracked as
|
||||
# infrastructure#135 (k3s migration landed without an Ingress).
|
||||
- id: L1
|
||||
title: MALS restored & exposed — k3s Ingress for mals.mosaicstack.dev, health verified, authenticated write smoke-tested (infrastructure#135); trial day-1 metric emission targets MALS until W3 panels exist
|
||||
phase: 1
|
||||
priority: must-have
|
||||
depends_on: []
|
||||
- id: L2
|
||||
title: Mosaic-native log ingestion — gateway/API endpoint for structured inbound error reporting from agents and installs (MALS-compatible schema; levels, categories, trace ids), workspace-scoped keys
|
||||
phase: 2
|
||||
priority: must-have
|
||||
depends_on: [L1]
|
||||
- id: L3
|
||||
title: Anonymous agentic-efficiency telemetry — opt-in, aggregate-only, no IP/PII captured or derivable at ingestion (NS-14); feeds W3 trend panels
|
||||
phase: 3
|
||||
priority: should-have
|
||||
depends_on: [L2, W3]
|
||||
|
||||
assumptions:
|
||||
- id: ASM-5
|
||||
vetoable: true
|
||||
text: >-
|
||||
The main agent initially runs on the homelab fleet host alongside the
|
||||
orchestrator under mosaic-agent@main.service; host placement is a config
|
||||
field, not a code assumption. Host co-location does NOT imply shared
|
||||
inference: Jarvis (Opus) and Mos (Fable) hold separate model capacity/quota
|
||||
so orchestrator load cannot degrade conversational latency (AC-NS-8).
|
||||
- id: ASM-6
|
||||
vetoable: true
|
||||
text: >-
|
||||
Product multi-tenancy at MVP means self-hosted installs with multiple
|
||||
workspaces per install (Authentik OIDC); per-tenant isolated FLEETS
|
||||
(agents per workspace) are post-MVP.
|
||||
- id: ASM-7
|
||||
vetoable: true
|
||||
text: >-
|
||||
mautrix bridges are deployed as infrastructure (GitOps), not as Mosaic
|
||||
application code; Mosaic's only conversational protocol is Matrix.
|
||||
- id: ASM-8
|
||||
vetoable: true
|
||||
text: >-
|
||||
During migration (before X3), Hermes remains running untouched; no
|
||||
Hermes-dependent capability is removed until its Mosaic replacement is
|
||||
verified in production.
|
||||
- id: ASM-9
|
||||
vetoable: true
|
||||
text: >-
|
||||
The trial environment is the homelab fleet deployment (D12). Environments
|
||||
running the primitive-era implementation (USC/web1: mos-claude.service,
|
||||
Hermes, jarvis-brain boards) are untouched during the trial; workstream X
|
||||
executes there as a post-trial adoption phase, environment by
|
||||
environment.
|
||||
@@ -1,49 +0,0 @@
|
||||
# #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
|
||||
@@ -1,58 +0,0 @@
|
||||
# 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.
|
||||
@@ -1,27 +0,0 @@
|
||||
# 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.
|
||||
@@ -1,71 +0,0 @@
|
||||
# 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.
|
||||
|
||||
## 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.
|
||||
@@ -1,34 +0,0 @@
|
||||
# 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.
|
||||
@@ -1,46 +0,0 @@
|
||||
# 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. |
|
||||
@@ -1,34 +0,0 @@
|
||||
# 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 |
|
||||
@@ -1,46 +0,0 @@
|
||||
# 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.
|
||||
@@ -1,30 +0,0 @@
|
||||
# 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.
|
||||
@@ -15,23 +15,13 @@
|
||||
#
|
||||
# After loading, service-specific env vars are exported.
|
||||
# Run `load_credentials --help` for details.
|
||||
#
|
||||
# Resolution order (first match wins):
|
||||
# 1. $MOSAIC_CREDENTIALS_FILE (explicit override — never second-guessed)
|
||||
# 2. $HOME/.config/mosaic/credentials.json
|
||||
# 3. /etc/mosaic/credentials.json (host-level fallback)
|
||||
# The /etc fallback exists for HOME-redirected profile environments, where
|
||||
# $HOME points at a per-profile directory that has no credentials file.
|
||||
# Operators symlink /etc/mosaic/credentials.json to the host's canonical
|
||||
# file once, instead of exporting MOSAIC_CREDENTIALS_FILE per invocation.
|
||||
|
||||
if [[ -z "${MOSAIC_CREDENTIALS_FILE:-}" ]]; then
|
||||
for _cand in "$HOME/.config/mosaic/credentials.json" "/etc/mosaic/credentials.json"; do
|
||||
for _cand in "$HOME/.config/mosaic/credentials.json"; do
|
||||
if [[ -f "$_cand" ]]; then MOSAIC_CREDENTIALS_FILE="$_cand"; break; fi
|
||||
done
|
||||
: "${MOSAIC_CREDENTIALS_FILE:=$HOME/.config/mosaic/credentials.json}"
|
||||
fi
|
||||
export MOSAIC_CREDENTIALS_FILE
|
||||
|
||||
_mosaic_require_jq() {
|
||||
if ! command -v jq &>/dev/null; then
|
||||
|
||||
@@ -86,16 +86,7 @@ gitea_url_matches_host() {
|
||||
|
||||
get_gitea_service_for_host() {
|
||||
local host="$1"
|
||||
local cred_file="${MOSAIC_CREDENTIALS_FILE:-}"
|
||||
if [[ -z "$cred_file" ]]; then
|
||||
# Same resolution chain as _lib/credentials.sh: profile HOME, then
|
||||
# host-level /etc only if it exists; neither existing keeps the
|
||||
# $HOME default (matches the lib's final := fallback).
|
||||
cred_file="$HOME/.config/mosaic/credentials.json"
|
||||
if [[ ! -f "$cred_file" && -f /etc/mosaic/credentials.json ]]; then
|
||||
cred_file="/etc/mosaic/credentials.json"
|
||||
fi
|
||||
fi
|
||||
local cred_file="${MOSAIC_CREDENTIALS_FILE:-$HOME/.config/mosaic/credentials.json}"
|
||||
|
||||
case "$host" in
|
||||
git.mosaicstack.dev)
|
||||
@@ -240,33 +231,6 @@ get_gitea_login_for_host() {
|
||||
return 1
|
||||
}
|
||||
|
||||
# Validate the current authenticated Gitea user for a resolved Tea login.
|
||||
# Tea stores a user name with each login which can become stale after user rename,
|
||||
# token rotation, or server migration. Querying /user derives the identity from the
|
||||
# active credential instead of trusting that saved name. Callers fall back to the
|
||||
# host-scoped API path when this validation fails.
|
||||
get_gitea_authenticated_user() {
|
||||
local login_name="$1" response
|
||||
|
||||
command -v tea >/dev/null 2>&1 || return 1
|
||||
response=$(tea api --login "$login_name" /user 2>/dev/null) || return 1
|
||||
TEA_AUTHENTICATED_USER_JSON="$response" python3 - <<'PY'
|
||||
import json
|
||||
import os
|
||||
|
||||
try:
|
||||
user = json.loads(os.environ["TEA_AUTHENTICATED_USER_JSON"])
|
||||
except (KeyError, json.JSONDecodeError):
|
||||
raise SystemExit(1)
|
||||
|
||||
login = user.get("login") if isinstance(user, dict) else None
|
||||
if isinstance(login, str) and login:
|
||||
print(login)
|
||||
raise SystemExit(0)
|
||||
raise SystemExit(1)
|
||||
PY
|
||||
}
|
||||
|
||||
get_default_tea_login() {
|
||||
local logins_json
|
||||
|
||||
|
||||
@@ -33,7 +33,7 @@ Examples:
|
||||
$(basename "$0") -i 42 -l "in-progress" -m "0.2.0"
|
||||
$(basename "$0") -i 42 -a @me
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -60,7 +60,7 @@ while [[ $# -gt 0 ]]; do
|
||||
shift
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
|
||||
@@ -12,7 +12,6 @@ TITLE=""
|
||||
BODY=""
|
||||
LABELS=""
|
||||
MILESTONE=""
|
||||
INTERACTIVE=false
|
||||
|
||||
# get_remote_host and get_gitea_token are provided by detect-platform.sh
|
||||
|
||||
@@ -67,15 +66,13 @@ Options:
|
||||
-b, --body BODY Issue body/description
|
||||
-l, --labels LABELS Comma-separated labels (e.g., "bug,feature")
|
||||
-m, --milestone NAME Milestone name to assign
|
||||
-i, --interactive Prompt for missing issue fields
|
||||
-h, --help Show this help message
|
||||
|
||||
Examples:
|
||||
$(basename "$0") -t "Fix login bug" -l "bug,priority-high"
|
||||
$(basename "$0") -t "Add dark mode" -b "Implement theme switching" -m "0.2.0"
|
||||
$(basename "$0") -i
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -97,12 +94,8 @@ while [[ $# -gt 0 ]]; do
|
||||
MILESTONE="$2"
|
||||
shift 2
|
||||
;;
|
||||
-i|--interactive)
|
||||
INTERACTIVE=true
|
||||
shift
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
@@ -111,13 +104,6 @@ while [[ $# -gt 0 ]]; do
|
||||
esac
|
||||
done
|
||||
|
||||
if [[ "$INTERACTIVE" == true ]]; then
|
||||
[[ -n "$TITLE" ]] || read -r -p "Issue title: " TITLE
|
||||
[[ -n "$BODY" ]] || read -r -p "Issue body (optional): " BODY || true
|
||||
[[ -n "$LABELS" ]] || read -r -p "Labels, comma-separated (optional): " LABELS || true
|
||||
[[ -n "$MILESTONE" ]] || read -r -p "Milestone (optional): " MILESTONE || true
|
||||
fi
|
||||
|
||||
if [[ -z "$TITLE" ]]; then
|
||||
echo "Error: Title is required (-t)" >&2
|
||||
usage
|
||||
@@ -141,11 +127,6 @@ case "$PLATFORM" in
|
||||
gitea_issue_create_api
|
||||
exit $?
|
||||
}
|
||||
if ! get_gitea_authenticated_user "$GITEA_LOGIN_NAME" >/dev/null; then
|
||||
echo "Warning: Tea authenticated-user validation failed (possible stale user/login); trying Gitea API fallback..." >&2
|
||||
gitea_issue_create_api
|
||||
exit $?
|
||||
fi
|
||||
REPO_ARGS=(--repo "$REPO_SLUG" --login "$GITEA_LOGIN_NAME")
|
||||
CMD=(tea issue create "${REPO_ARGS[@]}" --title "$TITLE")
|
||||
[[ -n "$BODY" ]] && CMD+=(--description "$BODY")
|
||||
|
||||
@@ -36,7 +36,7 @@ Examples:
|
||||
$(basename "$0") -m "0.2.0" # Issues in milestone 0.2.0
|
||||
$(basename "$0") --repo ddk/ai-bma # List issues from anywhere
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -67,7 +67,7 @@ while [[ $# -gt 0 ]]; do
|
||||
shift 2
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
|
||||
@@ -37,7 +37,7 @@ Examples:
|
||||
$(basename "$0") -t "0.0.1" -d "Pre-MVP Foundation Sprint"
|
||||
$(basename "$0") -t "0.1.0" -d "MVP Release" --due "2025-03-01"
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -60,7 +60,7 @@ while [[ $# -gt 0 ]]; do
|
||||
shift
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
|
||||
@@ -86,7 +86,7 @@ Examples:
|
||||
$(basename "$0") -i 42 -b "Implements the feature described in #42"
|
||||
$(basename "$0") -t "WIP: New feature" --draft
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -125,7 +125,7 @@ while [[ $# -gt 0 ]]; do
|
||||
shift
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
@@ -183,11 +183,6 @@ case "$PLATFORM" in
|
||||
gitea_pr_create_api
|
||||
exit $?
|
||||
}
|
||||
if ! get_gitea_authenticated_user "$GITEA_LOGIN_NAME" >/dev/null; then
|
||||
echo "Warning: Tea authenticated-user validation failed (possible stale user/login); trying Gitea API fallback..." >&2
|
||||
gitea_pr_create_api
|
||||
exit $?
|
||||
fi
|
||||
REPO_ARGS=(--repo "$REPO_SLUG" --login "$GITEA_LOGIN_NAME")
|
||||
CMD=(tea pr create "${REPO_ARGS[@]}" --title "$TITLE")
|
||||
[[ -n "$BODY" ]] && CMD+=(--description "$BODY")
|
||||
|
||||
@@ -34,7 +34,7 @@ Examples:
|
||||
$(basename "$0") -s merged -a username # Merged PRs by user
|
||||
$(basename "$0") --repo ddk/ai-bma # List PRs from anywhere
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -61,7 +61,7 @@ while [[ $# -gt 0 ]]; do
|
||||
shift 2
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
|
||||
@@ -35,7 +35,7 @@ Examples:
|
||||
$(basename "$0") -n 42 -d # Squash merge and delete branch
|
||||
$(basename "$0") -n 42 --skip-queue-guard # Skip queue guard wait
|
||||
EOF
|
||||
exit "${1:-1}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Parse arguments
|
||||
@@ -63,7 +63,7 @@ while [[ $# -gt 0 ]]; do
|
||||
shift
|
||||
;;
|
||||
-h|--help)
|
||||
usage 0
|
||||
usage
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1" >&2
|
||||
|
||||
@@ -45,11 +45,6 @@ JSON
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ "${1:-}" == "api" ]]; then
|
||||
printf '%s\n' '{"login":"ci-bot"}'
|
||||
exit 0
|
||||
fi
|
||||
|
||||
printf 'tea %s\n' "$*" >> "$MOSAIC_TEST_LOG"
|
||||
if [[ "${MOSAIC_TEA_FAIL_PR_CREATE:-}" == "1" && "$*" == pr\ create* ]]; then
|
||||
echo 'GetUserByName: simulated stale login failure' >&2
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression harness for #701: -h/--help must exit 0, bad args must still exit nonzero.
|
||||
#
|
||||
# Covers the 7 wrappers whose usage() previously hard-coded `exit 1`, so every
|
||||
# --help invocation exited nonzero and logged a phantom isError across fleet lanes.
|
||||
# Asserts, per wrapper:
|
||||
# 1. `--help` exits 0 and prints usage.
|
||||
# 2. `-h` exits 0 and prints usage.
|
||||
# 3. A genuine unknown flag still exits nonzero (usage() default path untouched).
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
WRAPPERS=(
|
||||
issue-assign.sh
|
||||
issue-create.sh
|
||||
issue-list.sh
|
||||
milestone-create.sh
|
||||
pr-create.sh
|
||||
pr-list.sh
|
||||
pr-merge.sh
|
||||
)
|
||||
|
||||
fail=0
|
||||
|
||||
for wrapper in "${WRAPPERS[@]}"; do
|
||||
path="$SCRIPT_DIR/$wrapper"
|
||||
|
||||
if ! output=$(bash "$path" --help 2>&1); then
|
||||
echo "FAIL: $wrapper --help exited nonzero" >&2
|
||||
fail=1
|
||||
elif [[ "$output" != Usage:* ]]; then
|
||||
echo "FAIL: $wrapper --help did not print usage" >&2
|
||||
fail=1
|
||||
fi
|
||||
|
||||
if ! bash "$path" -h >/dev/null 2>&1; then
|
||||
echo "FAIL: $wrapper -h exited nonzero" >&2
|
||||
fail=1
|
||||
fi
|
||||
|
||||
if bash "$path" --this-is-not-a-real-flag >/dev/null 2>&1; then
|
||||
echo "FAIL: $wrapper accepted an unknown flag (should have exited nonzero)" >&2
|
||||
fail=1
|
||||
fi
|
||||
done
|
||||
|
||||
if [[ "$fail" -eq 0 ]]; then
|
||||
echo "help-exit-code regression passed (7/7 wrappers)"
|
||||
fi
|
||||
|
||||
exit "$fail"
|
||||
@@ -55,11 +55,6 @@ JSON
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ "${1:-}" == "api" ]]; then
|
||||
printf '%s\n' '{"login":"ci-bot"}'
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ "${1:-}" == "issue" && "${2:-}" == "create" ]]; then
|
||||
desc=""
|
||||
while [[ $# -gt 0 ]]; do
|
||||
|
||||
@@ -1,88 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression harness for #703: interactive issue creation and stale Tea-user fallback.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/issue-create-interactive-auth}"
|
||||
REPO_DIR="$WORK_DIR/repo"
|
||||
BIN_DIR="$WORK_DIR/bin"
|
||||
LOG_FILE="$WORK_DIR/calls.log"
|
||||
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
|
||||
|
||||
rm -rf "$WORK_DIR"
|
||||
mkdir -p "$REPO_DIR" "$BIN_DIR"
|
||||
git -C "$REPO_DIR" init -q
|
||||
git -C "$REPO_DIR" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
|
||||
|
||||
cat > "$CREDENTIALS_FILE" <<'JSON'
|
||||
{"gitea":{"mosaicstack":{"url":"https://git.mosaicstack.dev","token":"test-token"}}}
|
||||
JSON
|
||||
|
||||
cat > "$BIN_DIR/tea" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
if [[ "$*" == "login list --output json" ]]; then
|
||||
printf '%s\n' '[{"name":"mosaicstack","url":"https://git.mosaicstack.dev"}]'
|
||||
exit 0
|
||||
fi
|
||||
if [[ "${1:-}" == "api" ]]; then
|
||||
if [[ "${MOSAIC_TEA_STALE_USER:-0}" == "1" ]]; then
|
||||
echo 'GetUserByName: stale configured user' >&2
|
||||
exit 1
|
||||
fi
|
||||
printf '%s\n' '{"login":"current-user"}'
|
||||
exit 0
|
||||
fi
|
||||
printf 'tea %s\n' "$*" >> "$MOSAIC_TEST_LOG"
|
||||
exit 0
|
||||
SH
|
||||
|
||||
cat > "$BIN_DIR/curl" <<'SH'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
printf 'curl %s\n' "$*" >> "$MOSAIC_TEST_LOG"
|
||||
printf '%s\n' '{"number":703}'
|
||||
SH
|
||||
chmod +x "$BIN_DIR/tea" "$BIN_DIR/curl"
|
||||
|
||||
run_wrapper() {
|
||||
(
|
||||
cd "$REPO_DIR"
|
||||
PATH="$BIN_DIR:$PATH" \
|
||||
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
|
||||
MOSAIC_TEST_LOG="$LOG_FILE" \
|
||||
"$@"
|
||||
)
|
||||
}
|
||||
|
||||
: > "$LOG_FILE"
|
||||
printf 'Interactive title\nInteractive body\nlabel-a,label-b\nM1\n' | run_wrapper "$SCRIPT_DIR/issue-create.sh" -i >/dev/null
|
||||
|
||||
grep -q -- 'tea issue create --repo mosaicstack/stack --login mosaicstack --title Interactive title --description Interactive body --labels label-a,label-b --milestone M1' "$LOG_FILE"
|
||||
|
||||
# Explicit values take precedence in interactive mode: no title input is
|
||||
# supplied, but the wrapper still creates the issue with the explicit title.
|
||||
: > "$LOG_FILE"
|
||||
printf '\n\n\n' | run_wrapper "$SCRIPT_DIR/issue-create.sh" -i -t 'Explicit title' >/dev/null
|
||||
grep -q -- 'tea issue create --repo mosaicstack/stack --login mosaicstack --title Explicit title' "$LOG_FILE"
|
||||
|
||||
: > "$LOG_FILE"
|
||||
run_wrapper env MOSAIC_TEA_STALE_USER=1 "$SCRIPT_DIR/issue-create.sh" -t 'Fallback title' -b 'Fallback body' >/dev/null 2>"$WORK_DIR/issue-stderr"
|
||||
grep -q -- 'curl .*https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack/issues' "$LOG_FILE"
|
||||
grep -q -- 'Tea authenticated-user validation failed' "$WORK_DIR/issue-stderr"
|
||||
if grep -q -- 'tea issue create' "$LOG_FILE"; then
|
||||
echo 'FAIL: issue-create invoked Tea mutation after stale-user validation failed' >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
: > "$LOG_FILE"
|
||||
run_wrapper env MOSAIC_TEA_STALE_USER=1 "$SCRIPT_DIR/pr-create.sh" -t 'PR fallback' -H feature/wrapfix >/dev/null 2>"$WORK_DIR/pr-stderr"
|
||||
grep -q -- 'curl .*https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack/pulls' "$LOG_FILE"
|
||||
grep -q -- 'Tea authenticated-user validation failed' "$WORK_DIR/pr-stderr"
|
||||
if grep -q -- 'tea pr create' "$LOG_FILE"; then
|
||||
echo 'FAIL: pr-create invoked Tea mutation after stale-user validation failed' >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo 'issue-create interactive/auth regression harness passed'
|
||||
@@ -1,44 +0,0 @@
|
||||
import { describe, expect, it } from 'vitest';
|
||||
import type {
|
||||
AgentRuntimeProvider,
|
||||
RuntimeAttachHandle,
|
||||
RuntimeCapability,
|
||||
RuntimeError,
|
||||
RuntimeSession,
|
||||
RuntimeStreamEvent,
|
||||
} from './agent-runtime-provider.js';
|
||||
|
||||
describe('AgentRuntimeProvider contract', (): void => {
|
||||
it('exposes stable, normalized runtime-only contracts', (): void => {
|
||||
const capability: RuntimeCapability = 'session.attach';
|
||||
const session: RuntimeSession = {
|
||||
id: 'session-1',
|
||||
providerId: 'fleet',
|
||||
runtimeId: 'tmux',
|
||||
state: 'active',
|
||||
createdAt: '2026-07-12T00:00:00.000Z',
|
||||
updatedAt: '2026-07-12T00:00:00.000Z',
|
||||
};
|
||||
const event: RuntimeStreamEvent = {
|
||||
type: 'message.delta',
|
||||
sessionId: session.id,
|
||||
cursor: '2',
|
||||
occurredAt: session.updatedAt,
|
||||
content: 'hello',
|
||||
};
|
||||
const error: RuntimeError = {
|
||||
code: 'capability_unsupported',
|
||||
message: 'Denied',
|
||||
retryable: false,
|
||||
};
|
||||
const attach: RuntimeAttachHandle = {
|
||||
attachmentId: 'attach-1',
|
||||
sessionId: session.id,
|
||||
mode: 'read',
|
||||
expiresAt: session.updatedAt,
|
||||
};
|
||||
const provider: Pick<AgentRuntimeProvider, 'capabilities' | 'getSessionTree' | 'attach'> =
|
||||
{} as Pick<AgentRuntimeProvider, 'capabilities' | 'getSessionTree' | 'attach'>;
|
||||
expect([capability, session.id, event.type, error.code, attach.mode, provider]).toHaveLength(6);
|
||||
});
|
||||
});
|
||||
@@ -1,110 +0,0 @@
|
||||
export type RuntimeCapability =
|
||||
| 'session.list'
|
||||
| 'session.tree'
|
||||
| 'session.stream'
|
||||
| 'session.send'
|
||||
| 'session.attach'
|
||||
| 'session.terminate';
|
||||
export type RuntimeSessionState = 'starting' | 'active' | 'idle' | 'stopped' | 'failed';
|
||||
export type RuntimeAttachMode = 'read' | 'control';
|
||||
|
||||
/** Server-derived immutable authority context. Client identity fields are intentionally absent. */
|
||||
export interface RuntimeScope {
|
||||
readonly actorId: string;
|
||||
readonly tenantId: string;
|
||||
readonly channelId: string;
|
||||
readonly correlationId: string;
|
||||
}
|
||||
export interface RuntimeSession {
|
||||
id: string;
|
||||
providerId: string;
|
||||
runtimeId: string;
|
||||
parentSessionId?: string;
|
||||
state: RuntimeSessionState;
|
||||
createdAt: string;
|
||||
updatedAt: string;
|
||||
}
|
||||
export interface RuntimeSessionTree {
|
||||
session: RuntimeSession;
|
||||
children: RuntimeSessionTree[];
|
||||
}
|
||||
export interface RuntimeCapabilitySet {
|
||||
supported: RuntimeCapability[];
|
||||
}
|
||||
export interface RuntimeHealth {
|
||||
status: 'healthy' | 'degraded' | 'down';
|
||||
checkedAt: string;
|
||||
detail?: string;
|
||||
}
|
||||
export interface RuntimeMessage {
|
||||
content: string;
|
||||
idempotencyKey: string;
|
||||
}
|
||||
export interface RuntimeAttachHandle {
|
||||
attachmentId: string;
|
||||
sessionId: string;
|
||||
mode: RuntimeAttachMode;
|
||||
expiresAt: string;
|
||||
}
|
||||
export interface RuntimeError {
|
||||
code:
|
||||
| 'capability_unsupported'
|
||||
| 'not_found'
|
||||
| 'forbidden'
|
||||
| 'conflict'
|
||||
| 'unavailable'
|
||||
| 'invalid_request';
|
||||
message: string;
|
||||
retryable: boolean;
|
||||
}
|
||||
export type RuntimeStreamEvent =
|
||||
| {
|
||||
type: 'session.state';
|
||||
sessionId: string;
|
||||
cursor: string;
|
||||
occurredAt: string;
|
||||
state: RuntimeSessionState;
|
||||
}
|
||||
| {
|
||||
type: 'message.delta';
|
||||
sessionId: string;
|
||||
cursor: string;
|
||||
occurredAt: string;
|
||||
content: string;
|
||||
}
|
||||
| {
|
||||
type: 'message.complete';
|
||||
sessionId: string;
|
||||
cursor: string;
|
||||
occurredAt: string;
|
||||
messageId: string;
|
||||
}
|
||||
| {
|
||||
type: 'runtime.error';
|
||||
sessionId: string;
|
||||
cursor: string;
|
||||
occurredAt: string;
|
||||
error: RuntimeError;
|
||||
};
|
||||
|
||||
/** Runtime-neutral boundary; implementations fail closed for unsupported operations. */
|
||||
export interface AgentRuntimeProvider {
|
||||
readonly id: string;
|
||||
capabilities(scope: RuntimeScope): Promise<RuntimeCapabilitySet>;
|
||||
health(scope: RuntimeScope): Promise<RuntimeHealth>;
|
||||
listSessions(scope: RuntimeScope): Promise<RuntimeSession[]>;
|
||||
getSessionTree(scope: RuntimeScope): Promise<RuntimeSessionTree[]>;
|
||||
streamSession(
|
||||
sessionId: string,
|
||||
cursor: string | undefined,
|
||||
scope: RuntimeScope,
|
||||
): AsyncIterable<RuntimeStreamEvent>;
|
||||
sendMessage(sessionId: string, message: RuntimeMessage, scope: RuntimeScope): Promise<void>;
|
||||
attach(
|
||||
sessionId: string,
|
||||
mode: RuntimeAttachMode,
|
||||
scope: RuntimeScope,
|
||||
): Promise<RuntimeAttachHandle>;
|
||||
detach(attachmentId: string, scope: RuntimeScope): Promise<void>;
|
||||
terminate(sessionId: string, approvalRef: string, scope: RuntimeScope): Promise<void>;
|
||||
}
|
||||
@@ -2,5 +2,3 @@
|
||||
export interface AgentSessionHandle {
|
||||
readonly id: string;
|
||||
}
|
||||
|
||||
export * from './agent-runtime-provider.js';
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
import type {
|
||||
CommandManifestPayload,
|
||||
SlashCommandApprovalResultPayload,
|
||||
SlashCommandPayload,
|
||||
SlashCommandResultPayload,
|
||||
SystemReloadPayload,
|
||||
@@ -117,7 +116,6 @@ export interface ServerToClientEvents {
|
||||
'session:info': (payload: SessionInfoPayload) => void;
|
||||
'commands:manifest': (payload: CommandManifestPayload) => void;
|
||||
'command:result': (payload: SlashCommandResultPayload) => void;
|
||||
'command:approval': (payload: SlashCommandApprovalResultPayload) => void;
|
||||
'system:reload': (payload: SystemReloadPayload) => void;
|
||||
error: (payload: ErrorPayload) => void;
|
||||
}
|
||||
@@ -127,6 +125,5 @@ export interface ClientToServerEvents {
|
||||
message: (data: ChatMessagePayload) => void;
|
||||
'set:thinking': (data: SetThinkingPayload) => void;
|
||||
'command:execute': (data: SlashCommandPayload) => void;
|
||||
'command:approve': (data: SlashCommandPayload) => void;
|
||||
abort: (data: AbortPayload) => void;
|
||||
}
|
||||
|
||||
@@ -63,18 +63,6 @@ export interface SlashCommandPayload {
|
||||
conversationId: string;
|
||||
command: string;
|
||||
args?: string;
|
||||
/** One-time server-issued approval for a privileged command execution. */
|
||||
approvalId?: string;
|
||||
}
|
||||
|
||||
/** Server response to a request to approve a privileged slash command. */
|
||||
export interface SlashCommandApprovalResultPayload {
|
||||
conversationId: string;
|
||||
command: string;
|
||||
success: boolean;
|
||||
approvalId?: string;
|
||||
expiresAt?: string;
|
||||
message?: string;
|
||||
}
|
||||
|
||||
/** Server response to a slash command */
|
||||
|
||||
Reference in New Issue
Block a user