Compare commits

...

5 Commits

Author SHA1 Message Date
Hermes Agent
cd3d547db0 docs(#753): complete KBN-010 threat gate 2026-07-14 12:31:05 -05:00
Hermes Agent
9b55de0f91 docs(#753): start KBN-010 threat gate 2026-07-14 12:17:01 -05:00
49e8a54105 docs(#751): Publish native Kanban/SOT canon (#752)
All checks were successful
ci/woodpecker/push/publish Pipeline was successful
ci/woodpecker/push/ci Pipeline was successful
2026-07-14 17:08:09 +00:00
d077183554 docs(tess): remediate M5 qualification findings (#750)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
2026-07-13 19:59:38 +00:00
405984af5a De-hardcode orchestrator and interaction agent names (#748)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
2026-07-13 18:59:27 +00:00
61 changed files with 5263 additions and 342 deletions

View File

@@ -7,7 +7,7 @@ import {
} from '@mosaicstack/discord-plugin';
import { InteractionController } from '../../agent/interaction.controller.js';
import { RuntimeProviderService } from '../../agent/runtime-provider-registry.service.js';
import { TessDurableSessionService } from '../../agent/tess-durable-session.service.js';
import { DurableSessionService } from '../../agent/durable-session.service.js';
import { ChatGateway } from '../../chat/chat.gateway.js';
import { CommandAuthorizationService } from '../../commands/command-authorization.service.js';
@@ -51,7 +51,7 @@ function authorization(): CommandAuthorizationService {
);
}
describe('Tess Discord/CLI durable-session integration', () => {
describe('interaction Discord/CLI durable-session integration', () => {
afterEach(() => {
for (const key of envKeys) {
const value = priorEnv.get(key);
@@ -80,7 +80,7 @@ describe('Tess Discord/CLI durable-session integration', () => {
},
]);
const durable = new TessDurableSessionService(
const durable = new DurableSessionService(
new InMemoryDurableSessionStore() as never,
{} as never,
);

View File

@@ -11,8 +11,8 @@ import { SessionsController } from './sessions.controller.js';
import { AgentConfigsController } from './agent-configs.controller.js';
import { InteractionController } from './interaction.controller.js';
import { RoutingController } from './routing/routing.controller.js';
import { TessDurableSessionRepository } from './tess-durable-session.repository.js';
import { TessDurableSessionService } from './tess-durable-session.service.js';
import { DurableSessionRepository } from './durable-session.repository.js';
import { DurableSessionService } from './durable-session.service.js';
import { CoordModule } from '../coord/coord.module.js';
import { McpClientModule } from '../mcp-client/mcp-client.module.js';
import { SkillsModule } from '../skills/skills.module.js';
@@ -44,8 +44,8 @@ export function createGatewayRuntimeProviderRegistry(): AgentRuntimeProviderRegi
RoutingService,
RoutingEngineService,
SkillLoaderService,
TessDurableSessionRepository,
TessDurableSessionService,
DurableSessionRepository,
DurableSessionService,
{
provide: AGENT_RUNTIME_PROVIDER_REGISTRY,
useFactory: createGatewayRuntimeProviderRegistry,
@@ -76,7 +76,7 @@ export function createGatewayRuntimeProviderRegistry(): AgentRuntimeProviderRegi
RoutingService,
RoutingEngineService,
SkillLoaderService,
TessDurableSessionService,
DurableSessionService,
RuntimeProviderService,
AGENT_RUNTIME_PROVIDER_REGISTRY,
],

View File

@@ -1,7 +1,7 @@
import type { RuntimeProviderRequestContext } from './runtime-provider-registry.service.js';
/** Server-side request for a replay-safe provider message. */
export interface TessProviderOutboxDto {
export interface ProviderOutboxDto {
sessionId: string;
idempotencyKey: string;
correlationId: string;

View File

@@ -6,8 +6,8 @@ import { eq, sql, interactionCheckpoints, interactionInbox } from '@mosaicstack/
import { DurableSessionCoordinator, type DurableSessionIdentity } from '@mosaicstack/agent';
import { afterAll, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
import { createPgliteDb, runPgliteMigrations, type DbHandle } from '@mosaicstack/db';
import { TessDurableSessionRepository } from './tess-durable-session.repository.js';
import { TessDurableSessionService } from './tess-durable-session.service.js';
import { DurableSessionRepository } from './durable-session.repository.js';
import { DurableSessionService } from './durable-session.service.js';
const IDENTITY: DurableSessionIdentity = {
agentName: 'Nova',
@@ -18,7 +18,7 @@ const IDENTITY: DurableSessionIdentity = {
runtimeSessionId: 'nova',
};
describe('TessDurableSessionRepository', () => {
describe('DurableSessionRepository', () => {
let dataDir: string | undefined;
let handle: DbHandle;
let previousAuthSecret: string | undefined;
@@ -48,9 +48,7 @@ describe('TessDurableSessionRepository', () => {
});
it('survives a full PGlite close/reopen mid-session without duplicate inbox or outbox side effects', async () => {
const beforeRestart = new DurableSessionCoordinator(
new TessDurableSessionRepository(handle.db),
);
const beforeRestart = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
await beforeRestart.create(IDENTITY);
await beforeRestart.receive({
sessionId: IDENTITY.sessionId,
@@ -92,7 +90,7 @@ describe('TessDurableSessionRepository', () => {
await handle.close();
handle = createPgliteDb(dataDir!);
const afterRestart = new DurableSessionCoordinator(new TessDurableSessionRepository(handle.db));
const afterRestart = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
const recovered = await afterRestart.recover(IDENTITY.sessionId);
const resumedHandoff = await afterRestart.resumeHandoff('handoff-before-kill');
const handled: string[] = [];
@@ -120,7 +118,7 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('redacts sensitive durable payloads before persistence', async () => {
const coordinator = new DurableSessionCoordinator(new TessDurableSessionRepository(handle.db));
const coordinator = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
await coordinator.create(IDENTITY);
await coordinator.receive({
sessionId: IDENTITY.sessionId,
@@ -157,7 +155,7 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('fails closed when the configured idempotency secret is unavailable', async () => {
const coordinator = new DurableSessionCoordinator(new TessDurableSessionRepository(handle.db));
const coordinator = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
await coordinator.create(IDENTITY);
const secret = process.env['BETTER_AUTH_SECRET'];
delete process.env['BETTER_AUTH_SECRET'];
@@ -177,7 +175,7 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('uses keyed pre-redaction digests to reject distinct sensitive checkpoint payloads', async () => {
const coordinator = new DurableSessionCoordinator(new TessDurableSessionRepository(handle.db));
const coordinator = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
await coordinator.create(IDENTITY);
const input = {
sessionId: IDENTITY.sessionId,
@@ -227,7 +225,7 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('rejects distinct sensitive inbox and outbox payloads under reused idempotency keys', async () => {
const coordinator = new DurableSessionCoordinator(new TessDurableSessionRepository(handle.db));
const coordinator = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
await coordinator.create(IDENTITY);
const inbox = {
sessionId: IDENTITY.sessionId,
@@ -255,7 +253,7 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('rejects database inbox and outbox idempotency-key conflicts', async () => {
const coordinator = new DurableSessionCoordinator(new TessDurableSessionRepository(handle.db));
const coordinator = new DurableSessionCoordinator(new DurableSessionRepository(handle.db));
await coordinator.create(IDENTITY);
await coordinator.receive({
sessionId: IDENTITY.sessionId,
@@ -293,10 +291,10 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('does not requeue a live outbox claim during a normal scoped dispatch', async () => {
const repository = new TessDurableSessionRepository(handle.db);
const repository = new DurableSessionRepository(handle.db);
const coordinator = new DurableSessionCoordinator(repository);
const runtimeProviders = { sendMessage: vi.fn().mockResolvedValue(undefined) };
const service = new TessDurableSessionService(repository, runtimeProviders as never);
const service = new DurableSessionService(repository, runtimeProviders as never);
const input = {
sessionId: IDENTITY.sessionId,
idempotencyKey: 'live-effect',
@@ -333,10 +331,10 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('rejects an outbox correlation mismatch before claiming the pending effect', async () => {
const repository = new TessDurableSessionRepository(handle.db);
const repository = new DurableSessionRepository(handle.db);
const coordinator = new DurableSessionCoordinator(repository);
const runtimeProviders = { sendMessage: vi.fn().mockResolvedValue(undefined) };
const service = new TessDurableSessionService(repository, runtimeProviders as never);
const service = new DurableSessionService(repository, runtimeProviders as never);
const input = {
sessionId: IDENTITY.sessionId,
idempotencyKey: 'mismatch-effect',
@@ -366,10 +364,10 @@ describe('TessDurableSessionRepository', () => {
}, 30_000);
it('dispatches only the outbox record bound to the supplied correlation and channel', async () => {
const repository = new TessDurableSessionRepository(handle.db);
const repository = new DurableSessionRepository(handle.db);
const coordinator = new DurableSessionCoordinator(repository);
const runtimeProviders = { sendMessage: vi.fn().mockResolvedValue(undefined) };
const service = new TessDurableSessionService(repository, runtimeProviders as never);
const service = new DurableSessionService(repository, runtimeProviders as never);
const first = {
sessionId: IDENTITY.sessionId,
idempotencyKey: 'scoped-effect-one',

View File

@@ -33,7 +33,7 @@ import type {
import { DB } from '../database/database.module.js';
@Injectable()
export class TessDurableSessionRepository implements DurableSessionStore {
export class DurableSessionRepository implements DurableSessionStore {
constructor(@Inject(DB) private readonly db: Db) {}
async create(identity: DurableSessionIdentity): Promise<void> {
@@ -51,7 +51,7 @@ export class TessDurableSessionRepository implements DurableSessionStore {
const existing = await this.session(identity.sessionId);
if (!existing || !sameEnrollmentScope(existing, identity)) {
throw new Error(`Durable Tess session identity conflict: ${identity.sessionId}`);
throw new Error(`Durable session identity conflict: ${identity.sessionId}`);
}
// A recovered/re-enrolled runtime can receive a new provider session ID;
// the conversation handle and owner scope remain immutable.
@@ -135,13 +135,13 @@ export class TessDurableSessionRepository implements DurableSessionStore {
),
)
.limit(1);
if (!existing[0]) throw new Error(`Durable Tess inbox enqueue failed: ${input.idempotencyKey}`);
if (!existing[0]) throw new Error(`Durable inbox enqueue failed: ${input.idempotencyKey}`);
const entry = toInbox(existing[0]);
if (
!sameInbox(entry, record) ||
!matchesContentDigest(existing[0].contentDigest, input.content)
) {
throw new Error(`Durable Tess inbox idempotency conflict: ${input.idempotencyKey}`);
throw new Error(`Durable inbox idempotency conflict: ${input.idempotencyKey}`);
}
return { accepted: false, status: entry.status };
}
@@ -224,14 +224,13 @@ export class TessDurableSessionRepository implements DurableSessionStore {
),
)
.limit(1);
if (!existing[0])
throw new Error(`Durable Tess outbox enqueue failed: ${input.idempotencyKey}`);
if (!existing[0]) throw new Error(`Durable outbox enqueue failed: ${input.idempotencyKey}`);
const entry = toOutbox(existing[0]);
if (
!sameOutbox(entry, record) ||
!matchesContentDigest(existing[0].contentDigest, input.content)
) {
throw new Error(`Durable Tess outbox idempotency conflict: ${input.idempotencyKey}`);
throw new Error(`Durable outbox idempotency conflict: ${input.idempotencyKey}`);
}
return { accepted: false, status: entry.status };
}
@@ -338,7 +337,7 @@ export class TessDurableSessionRepository implements DurableSessionStore {
!sameCheckpoint(toCheckpoint(existing[0]), checkpoint) ||
!matchesCheckpointDigest(existing[0].contentDigest, digest)
) {
throw new Error(`Durable Tess checkpoint identity conflict: ${input.checkpointId}`);
throw new Error(`Durable checkpoint identity conflict: ${input.checkpointId}`);
}
}
@@ -360,7 +359,7 @@ export class TessDurableSessionRepository implements DurableSessionStore {
async handoff(input: DurableHandoffInput): Promise<void> {
const checkpoint = await this.findCheckpoint(input.sessionId, input.checkpointId);
if (!checkpoint) {
throw new Error(`Durable Tess handoff checkpoint is unavailable: ${input.checkpointId}`);
throw new Error(`Durable handoff checkpoint is unavailable: ${input.checkpointId}`);
}
const inserted = await this.db
.insert(interactionHandoffs)
@@ -371,7 +370,7 @@ export class TessDurableSessionRepository implements DurableSessionStore {
const existing = await this.findHandoff(input.handoffId);
if (!existing || !sameHandoff(existing, input)) {
throw new Error(`Durable Tess handoff identity conflict: ${input.handoffId}`);
throw new Error(`Durable handoff identity conflict: ${input.handoffId}`);
}
}

View File

@@ -1,23 +1,23 @@
import { ForbiddenException, Inject, Injectable } from '@nestjs/common';
import { DurableSessionCoordinator, type DurableSessionIdentity } from '@mosaicstack/agent';
import type { TessProviderOutboxDto } from './tess-durable-session.dto.js';
import { TessDurableSessionRepository } from './tess-durable-session.repository.js';
import type { ProviderOutboxDto } from './durable-session.dto.js';
import { DurableSessionRepository } from './durable-session.repository.js';
import {
RuntimeProviderService,
type RuntimeProviderRequestContext,
} from './runtime-provider-registry.service.js';
/**
* Scoped gateway boundary for the canonical Tess state machine. It deliberately
* Scoped gateway boundary for the canonical durable session state machine. It deliberately
* uses composition: raw state methods cannot be injected into channel, CLI, or
* MCP adapters without a server-derived actor/tenant/correlation context.
*/
@Injectable()
export class TessDurableSessionService {
export class DurableSessionService {
private readonly coordinator: DurableSessionCoordinator;
constructor(
@Inject(TessDurableSessionRepository) repository: TessDurableSessionRepository,
@Inject(DurableSessionRepository) repository: DurableSessionRepository,
@Inject(RuntimeProviderService) private readonly runtimeProviders: RuntimeProviderService,
) {
this.coordinator = new DurableSessionCoordinator(repository);
@@ -32,12 +32,12 @@ export class TessDurableSessionService {
identity.ownerId !== context.actorScope.userId ||
identity.tenantId !== context.actorScope.tenantId
) {
throw new ForbiddenException('Durable Tess enrollment scope mismatch');
throw new ForbiddenException('Durable session enrollment scope mismatch');
}
await this.coordinator.create(identity);
}
async queueProviderSend(input: TessProviderOutboxDto): Promise<void> {
async queueProviderSend(input: ProviderOutboxDto): Promise<void> {
const snapshot = await this.coordinator.snapshot(input.sessionId);
this.assertScope(snapshot.identity.ownerId, snapshot.identity.tenantId, input);
await this.coordinator.enqueueOutbox({
@@ -50,9 +50,9 @@ export class TessDurableSessionService {
});
}
async dispatchProviderOutbox(sessionId: string, input: TessProviderOutboxDto): Promise<void> {
async dispatchProviderOutbox(sessionId: string, input: ProviderOutboxDto): Promise<void> {
if (sessionId !== input.sessionId) {
throw new ForbiddenException('Durable Tess outbox session mismatch');
throw new ForbiddenException('Durable outbox session mismatch');
}
const snapshot = await this.coordinator.snapshot(sessionId);
this.assertScope(snapshot.identity.ownerId, snapshot.identity.tenantId, input);
@@ -92,7 +92,7 @@ export class TessDurableSessionService {
}
/** Startup/recovery-only path; normal queue/dispatch methods never requeue live work. */
async recoverProviderSession(sessionId: string, input: TessProviderOutboxDto): Promise<void> {
async recoverProviderSession(sessionId: string, input: ProviderOutboxDto): Promise<void> {
const snapshot = await this.coordinator.snapshot(sessionId);
this.assertScope(snapshot.identity.ownerId, snapshot.identity.tenantId, input);
await this.coordinator.recover(sessionId);
@@ -100,24 +100,24 @@ export class TessDurableSessionService {
private assertOutboxScope(
entry: { kind: string; correlationId: string; channelId: string },
input: TessProviderOutboxDto,
input: ProviderOutboxDto,
): void {
if (
entry.kind !== 'provider.send' ||
entry.correlationId !== input.correlationId ||
entry.channelId !== input.context.channelId
) {
throw new ForbiddenException('Durable Tess outbox scope or correlation mismatch');
throw new ForbiddenException('Durable outbox scope or correlation mismatch');
}
}
private assertScope(ownerId: string, tenantId: string, input: TessProviderOutboxDto): void {
private assertScope(ownerId: string, tenantId: string, input: ProviderOutboxDto): void {
if (
input.context.actorScope.userId !== ownerId ||
input.context.actorScope.tenantId !== tenantId ||
input.context.correlationId !== input.correlationId
) {
throw new ForbiddenException('Durable Tess session scope or correlation mismatch');
throw new ForbiddenException('Durable session scope or correlation mismatch');
}
}
}

View File

@@ -21,8 +21,8 @@ import {
RUNTIME_PROVIDER_AUDIT_SINK,
RuntimeProviderAuditService,
} from './runtime-provider-registry.service.js';
import { TessDurableSessionService } from './tess-durable-session.service.js';
import { TessDurableSessionRepository } from './tess-durable-session.repository.js';
import { DurableSessionService } from './durable-session.service.js';
import { DurableSessionRepository } from './durable-session.repository.js';
import { AgentService } from './agent.service.js';
import { ProviderService } from './provider.service.js';
import { ProviderCredentialsService } from './provider-credentials.service.js';
@@ -88,9 +88,9 @@ describe('Hermes runtime provider reachability', (): void => {
.useValue({ record: vi.fn().mockResolvedValue(undefined) })
.overrideProvider(RUNTIME_APPROVAL_VERIFIER)
.useValue({ consume: vi.fn().mockResolvedValue(false) })
.overrideProvider(TessDurableSessionService)
.overrideProvider(DurableSessionService)
.useValue({})
.overrideProvider(TessDurableSessionRepository)
.overrideProvider(DurableSessionRepository)
.useValue({})
.overrideProvider(AgentService)
.useValue({})
@@ -115,6 +115,38 @@ describe('Hermes runtime provider reachability', (): void => {
await app?.close();
});
it('returns gateway denial responses from the actual guarded interaction routes', async (): Promise<void> => {
if (!app) throw new Error('Nest application did not initialize');
const attachDenied = await app.inject({
method: 'POST',
url: '/api/interaction/Nova/sessions/session-1/attach',
headers: { 'x-correlation-id': 'correlation-1' },
payload: { mode: 'read' },
});
expect(attachDenied.statusCode).toBe(401);
const sendDenied = await app.inject({
method: 'POST',
url: '/api/interaction/Nova/sessions/session-1/send',
headers: { cookie: 'session=trusted', 'x-correlation-id': 'correlation-1' },
payload: {},
});
expect(sendDenied.statusCode).toBe(403);
expect(sendDenied.json()).toMatchObject({
message: 'Content and idempotency key are required',
});
const stopDenied = await app.inject({
method: 'POST',
url: '/api/interaction/Nova/sessions/session-1/stop',
headers: { cookie: 'session=trusted', 'x-correlation-id': 'correlation-1' },
payload: {},
});
expect(stopDenied.statusCode).toBe(403);
expect(stopDenied.json()).toMatchObject({ message: 'Exact-action approval is required' });
});
it('requires authentication and reaches the Hermes provider registered by AgentModule', async (): Promise<void> => {
if (!app) throw new Error('Nest application did not initialize');
const registry = app.get(AGENT_RUNTIME_PROVIDER_REGISTRY);

View File

@@ -17,7 +17,7 @@ import { Observable } from 'rxjs';
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 { TessDurableSessionService } from './tess-durable-session.service.js';
import { DurableSessionService } from './durable-session.service.js';
import { RuntimeApprovalDeniedFilter } from './runtime-approval-denied.filter.js';
import {
RuntimeProviderService,
@@ -34,7 +34,7 @@ import {
export class InteractionController {
constructor(
@Inject(RuntimeProviderService) private readonly runtime: RuntimeProviderService,
@Inject(TessDurableSessionService) private readonly durable: TessDurableSessionService,
@Inject(DurableSessionService) private readonly durable: DurableSessionService,
) {}
@Get('sessions')

View File

@@ -37,7 +37,7 @@ import {
RuntimeProviderService,
type RuntimeAuditSink,
} from '../agent/runtime-provider-registry.service.js';
import { TessDurableSessionService } from '../agent/tess-durable-session.service.js';
import { DurableSessionService } from '../agent/durable-session.service.js';
import { AUTH } from '../auth/auth.tokens.js';
import {
scopeFromUser,
@@ -140,8 +140,8 @@ export class ChatGateway implements OnGatewayInit, OnGatewayConnection, OnGatewa
@Inject(RuntimeProviderService)
private readonly runtimeRegistry: RuntimeProviderService | null = null,
@Optional()
@Inject(TessDurableSessionService)
private readonly durableSessions: TessDurableSessionService | null = null,
@Inject(DurableSessionService)
private readonly durableSessions: DurableSessionService | null = null,
@Optional()
@Inject(RUNTIME_PROVIDER_AUDIT_SINK)
private readonly runtimeAudit: RuntimeAuditSink | null = null,

View File

@@ -1,31 +1,32 @@
import { Module } from '@nestjs/common';
import { InMemoryMosCoordinationPort } from '@mosaicstack/coord';
import { InMemoryInteractionCoordinationPort } from '@mosaicstack/coord';
import { CoordService } from './coord.service.js';
import { CoordController } from './coord.controller.js';
import { MosCoordinationController } from './mos-coordination.controller.js';
import { InteractionCoordinationController } from './interaction-coordination.controller.js';
import {
MOS_COORDINATION_CONFIG,
MOS_COORDINATION_PORT,
MosCoordinationService,
} from './mos-coordination.service.js';
COORDINATION_CONFIG,
COORDINATION_PORT,
InteractionCoordinationService,
} from './interaction-coordination.service.js';
@Module({
providers: [
CoordService,
{
provide: MOS_COORDINATION_PORT,
useFactory: (): InMemoryMosCoordinationPort => new InMemoryMosCoordinationPort(),
provide: COORDINATION_PORT,
useFactory: (): InMemoryInteractionCoordinationPort =>
new InMemoryInteractionCoordinationPort(),
},
{
provide: MOS_COORDINATION_CONFIG,
provide: COORDINATION_CONFIG,
useFactory: () => ({
interactionAgentId: process.env['MOSAIC_AGENT_NAME'],
orchestrationAgentId: process.env['MOSAIC_ORCHESTRATOR_AGENT_NAME'],
}),
},
MosCoordinationService,
InteractionCoordinationService,
],
controllers: [CoordController, MosCoordinationController],
exports: [CoordService, MosCoordinationService],
controllers: [CoordController, InteractionCoordinationController],
exports: [CoordService, InteractionCoordinationService],
})
export class CoordModule {}

View File

@@ -1,16 +1,27 @@
const PATH_METADATA = 'path';
import { describe, expect, it, vi } from 'vitest';
import { MosCoordinationController } from './mos-coordination.controller.js';
import { InteractionCoordinationController } from './interaction-coordination.controller.js';
const user = { id: 'operator-1', tenantId: 'tenant-a' };
describe('MosCoordinationController', () => {
describe('InteractionCoordinationController', () => {
it('exposes the neutral canonical route and Mos compatibility alias over identical handlers', () => {
expect(Reflect.getMetadata(PATH_METADATA, InteractionCoordinationController)).toEqual([
'api/coord/interaction',
'api/coord/mos',
]);
expect(InteractionCoordinationController.prototype.handoff).toBeTypeOf('function');
expect(InteractionCoordinationController.prototype.observe).toBeTypeOf('function');
expect(InteractionCoordinationController.prototype.result).toBeTypeOf('function');
});
it('derives actor and tenant from the authenticated user rather than handoff input', async () => {
const coordination = {
handoff: vi.fn(async () => ({ handoffId: 'handoff-1' })),
observe: vi.fn(),
result: vi.fn(),
};
const controller = new MosCoordinationController(coordination as never);
const controller = new InteractionCoordinationController(coordination as never);
await controller.handoff({ idempotencyKey: 'request-1', summary: 'Implement' }, user, 'corr-1');
@@ -26,7 +37,7 @@ describe('MosCoordinationController', () => {
it('requires a correlation header before invoking the coordination service', async () => {
const coordination = { handoff: vi.fn(), observe: vi.fn(), result: vi.fn() };
const controller = new MosCoordinationController(coordination as never);
const controller = new InteractionCoordinationController(coordination as never);
await expect(
controller.handoff({ idempotencyKey: 'request-1', summary: 'Implement' }, user, undefined),

View File

@@ -14,27 +14,29 @@ import { CurrentUser } from '../auth/current-user.decorator.js';
import { scopeFromUser, type AuthenticatedUserLike } from '../auth/session-scope.js';
import type { RuntimeProviderRequestContext } from '../agent/runtime-provider-registry.service.js';
import type {
MosCoordinationObservationDto,
MosCoordinationResponseDto,
MosCoordinationResultDto,
CreateMosHandoffDto,
} from './mos-coordination.dto.js';
import { MosCoordinationService } from './mos-coordination.service.js';
InteractionCoordinationObservationDto,
InteractionCoordinationResponseDto,
InteractionCoordinationResultDto,
CreateHandoffDto,
} from './interaction-coordination.dto.js';
import { InteractionCoordinationService } from './interaction-coordination.service.js';
/** Authenticated interaction-plane boundary for the handoff/observe/result-only Mos contract. */
@Controller('api/coord/mos')
/** Authenticated interaction-plane boundary for the handoff/observe/result-only interaction coordination contract. */
/** `api/coord/interaction` is canonical; the Mos path remains a compatibility alias. */
@Controller(['api/coord/interaction', 'api/coord/mos'])
@UseGuards(AuthGuard)
export class MosCoordinationController {
export class InteractionCoordinationController {
constructor(
@Inject(MosCoordinationService) private readonly coordination: MosCoordinationService,
@Inject(InteractionCoordinationService)
private readonly coordination: InteractionCoordinationService,
) {}
@Post('handoff')
async handoff(
@Body() request: CreateMosHandoffDto,
@Body() request: CreateHandoffDto,
@CurrentUser() user: AuthenticatedUserLike,
@Headers('x-correlation-id') correlationId?: string,
): Promise<MosCoordinationResponseDto> {
): Promise<InteractionCoordinationResponseDto> {
return { receipt: await this.coordination.handoff(request, this.context(user, correlationId)) };
}
@@ -43,7 +45,7 @@ export class MosCoordinationController {
@Param('handoffId') handoffId: string,
@CurrentUser() user: AuthenticatedUserLike,
@Headers('x-correlation-id') correlationId?: string,
): Promise<MosCoordinationObservationDto> {
): Promise<InteractionCoordinationObservationDto> {
return {
observation: await this.coordination.observe(handoffId, this.context(user, correlationId)),
};
@@ -54,7 +56,7 @@ export class MosCoordinationController {
@Param('handoffId') handoffId: string,
@CurrentUser() user: AuthenticatedUserLike,
@Headers('x-correlation-id') correlationId?: string,
): Promise<MosCoordinationResultDto> {
): Promise<InteractionCoordinationResultDto> {
return { result: await this.coordination.result(handoffId, this.context(user, correlationId)) };
}

View File

@@ -1,25 +1,25 @@
import type {
CoordinationObservation,
CoordinationResult,
MosHandoffReceipt,
HandoffReceipt,
} from '@mosaicstack/coord';
/** Input accepted at the gateway coordination boundary. Agent identity is not caller-controlled. */
export interface CreateMosHandoffDto {
export interface CreateHandoffDto {
idempotencyKey: string;
summary: string;
context?: string;
missionId?: string;
}
export interface MosCoordinationResponseDto {
receipt: MosHandoffReceipt;
export interface InteractionCoordinationResponseDto {
receipt: HandoffReceipt;
}
export interface MosCoordinationObservationDto {
export interface InteractionCoordinationObservationDto {
observation: CoordinationObservation;
}
export interface MosCoordinationResultDto {
export interface InteractionCoordinationResultDto {
result: CoordinationResult;
}

View File

@@ -0,0 +1,88 @@
import 'reflect-metadata';
import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
import { Global, Module } from '@nestjs/common';
import { Test } from '@nestjs/testing';
import { FastifyAdapter, type NestFastifyApplication } from '@nestjs/platform-fastify';
import { AUTH } from '../auth/auth.tokens.js';
import { AuthGuard } from '../auth/auth.guard.js';
import { InteractionCoordinationController } from './interaction-coordination.controller.js';
import { InteractionCoordinationService } from './interaction-coordination.service.js';
@Global()
@Module({
providers: [
{
provide: AUTH,
useValue: {
api: {
getSession: vi.fn(async ({ headers }: { headers: Headers }) =>
headers.get('cookie') === 'session=trusted'
? { user: { id: 'operator-1', tenantId: 'tenant-1' }, session: { id: 'session-1' } }
: null,
),
},
},
},
AuthGuard,
],
exports: [AUTH, AuthGuard],
})
class AuthenticatedRequestModule {}
describe('InteractionCoordinationController route aliases', (): void => {
let app: NestFastifyApplication | undefined;
const coordination = {
handoff: vi.fn(async () => ({ handoffId: 'handoff-1' })),
observe: vi.fn(async () => ({ status: 'running' })),
result: vi.fn(async () => ({ status: 'completed' })),
};
beforeAll(async (): Promise<void> => {
const moduleRef = await Test.createTestingModule({
imports: [AuthenticatedRequestModule],
controllers: [InteractionCoordinationController],
providers: [{ provide: InteractionCoordinationService, useValue: coordination }],
}).compile();
app = moduleRef.createNestApplication<NestFastifyApplication>(new FastifyAdapter());
await app.init();
await app.getHttpAdapter().getInstance().ready();
});
afterAll(async (): Promise<void> => app?.close());
it('routes handoff, observe, and result through the same AuthGuard-protected service for both prefixes', async (): Promise<void> => {
if (!app) throw new Error('test app was not initialized');
for (const prefix of ['/api/coord/interaction', '/api/coord/mos']) {
const headers = { cookie: 'session=trusted', 'x-correlation-id': `corr-${prefix}` };
expect(
(
await app.inject({
method: 'POST',
url: `${prefix}/handoff`,
headers,
payload: { idempotencyKey: `key-${prefix}`, summary: 'handoff' },
})
).statusCode,
).toBe(201);
expect(
(await app.inject({ method: 'GET', url: `${prefix}/handoff-1/observe`, headers }))
.statusCode,
).toBe(200);
expect(
(await app.inject({ method: 'GET', url: `${prefix}/handoff-1/result`, headers }))
.statusCode,
).toBe(200);
}
expect(coordination.handoff).toHaveBeenCalledTimes(2);
expect(coordination.observe).toHaveBeenCalledTimes(2);
expect(coordination.result).toHaveBeenCalledTimes(2);
expect(
(
await app.inject({
method: 'POST',
url: '/api/coord/interaction/handoff',
payload: { idempotencyKey: 'denied', summary: 'x' },
})
).statusCode,
).toBe(401);
});
});

View File

@@ -1,15 +1,15 @@
import { describe, expect, it, vi } from 'vitest';
import {
InMemoryMosCoordinationPort,
type MosCoordinationPort,
type MosHandoff,
InMemoryInteractionCoordinationPort,
type InteractionCoordinationPort,
type Handoff,
} from '@mosaicstack/coord';
import type { RuntimeProviderRequestContext } from '../agent/runtime-provider-registry.service.js';
import {
MosCoordinationService,
type MosCoordinationConfig,
type MosCoordinationGatewayError,
} from './mos-coordination.service.js';
InteractionCoordinationService,
type InteractionCoordinationConfig,
type InteractionCoordinationGatewayError,
} from './interaction-coordination.service.js';
const context: RuntimeProviderRequestContext = {
actorScope: { userId: 'operator-1', tenantId: 'tenant-a' },
@@ -17,28 +17,28 @@ const context: RuntimeProviderRequestContext = {
correlationId: 'corr-1',
};
const config: MosCoordinationConfig = {
const config: InteractionCoordinationConfig = {
interactionAgentId: 'Nova',
orchestrationAgentId: 'Conductor',
};
function service(
port: MosCoordinationPort = new InMemoryMosCoordinationPort(),
port: InteractionCoordinationPort = new InMemoryInteractionCoordinationPort(),
options: {
config?: MosCoordinationConfig;
config?: InteractionCoordinationConfig;
handoffIdFactory?: () => string;
} = {},
): MosCoordinationService {
return new MosCoordinationService(
): InteractionCoordinationService {
return new InteractionCoordinationService(
port,
options.config ?? config,
options.handoffIdFactory ?? (() => 'handoff-1'),
);
}
describe('MosCoordinationService authority boundary', (): void => {
describe('InteractionCoordinationService authority boundary', (): void => {
it('derives identity and actor/tenant scope server-side, then round-trips the native adapter', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const coordination = service(adapter);
await expect(
@@ -53,8 +53,8 @@ describe('MosCoordinationService authority boundary', (): void => {
correlationId: 'corr-1',
});
adapter.recordActivity('handoff-1', 'running', 'Mos accepted the request');
adapter.recordResult('handoff-1', 'completed', 'Merged by Mos');
adapter.recordActivity('handoff-1', 'running', 'Orchestrator accepted the request');
adapter.recordResult('handoff-1', 'completed', 'Merged by orchestrator');
const followUpContext = { ...context, correlationId: 'corr-2' };
await expect(coordination.observe('handoff-1', followUpContext)).resolves.toMatchObject({
@@ -64,12 +64,12 @@ describe('MosCoordinationService authority boundary', (): void => {
await expect(coordination.result('handoff-1', followUpContext)).resolves.toMatchObject({
targetAgentId: 'Conductor',
status: 'completed',
summary: 'Merged by Mos',
summary: 'Merged by orchestrator',
});
});
it('fails closed without calling a port when the interaction requester is unconfigured', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const handoff = vi.spyOn(adapter, 'handoff');
const coordination = service(adapter, {
config: { interactionAgentId: '', orchestrationAgentId: 'Conductor' },
@@ -82,12 +82,12 @@ describe('MosCoordinationService authority boundary', (): void => {
),
).rejects.toMatchObject({
code: 'unconfigured_requester',
} satisfies Partial<MosCoordinationGatewayError>);
} satisfies Partial<InteractionCoordinationGatewayError>);
expect(handoff).not.toHaveBeenCalled();
});
it('rejects self-delegation configuration before delivering work', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const handoff = vi.spyOn(adapter, 'handoff');
const coordination = service(adapter, {
config: { interactionAgentId: 'Nova', orchestrationAgentId: 'Nova' },
@@ -103,7 +103,7 @@ describe('MosCoordinationService authority boundary', (): void => {
});
it('denies cross-tenant observe and result before calling the adapter', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const observe = vi.spyOn(adapter, 'observe');
const result = vi.spyOn(adapter, 'result');
const coordination = service(adapter);
@@ -118,10 +118,10 @@ describe('MosCoordinationService authority boundary', (): void => {
};
await expect(coordination.observe('handoff-1', otherTenant)).rejects.toMatchObject({
code: 'cross_tenant_forbidden',
} satisfies Partial<MosCoordinationGatewayError>);
} satisfies Partial<InteractionCoordinationGatewayError>);
await expect(coordination.result('handoff-1', otherTenant)).rejects.toMatchObject({
code: 'cross_tenant_forbidden',
} satisfies Partial<MosCoordinationGatewayError>);
} satisfies Partial<InteractionCoordinationGatewayError>);
expect(observe).not.toHaveBeenCalled();
expect(result).not.toHaveBeenCalled();
});
@@ -132,8 +132,8 @@ describe('MosCoordinationService authority boundary', (): void => {
const delivered = new Promise<void>((resolve: () => void): void => {
release = resolve;
});
const adapter: MosCoordinationPort = {
handoff: vi.fn(async (handoff: MosHandoff) => {
const adapter: InteractionCoordinationPort = {
handoff: vi.fn(async (handoff: Handoff) => {
await delivered;
return {
handoffId: handoff.handoffId,
@@ -169,7 +169,7 @@ describe('MosCoordinationService authority boundary', (): void => {
});
it('rejects idempotency-key payload drift and malformed handoff input before delivery', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const handoff = vi.spyOn(adapter, 'handoff');
const coordination = service(adapter);
await coordination.handoff(
@@ -181,23 +181,23 @@ describe('MosCoordinationService authority boundary', (): void => {
coordination.handoff({ idempotencyKey: 'request-1', summary: 'Different work' }, context),
).rejects.toMatchObject({
code: 'handoff_conflict',
} satisfies Partial<MosCoordinationGatewayError>);
} satisfies Partial<InteractionCoordinationGatewayError>);
await expect(
coordination.handoff({ idempotencyKey: 'request-2', summary: '' }, context),
).rejects.toMatchObject({
code: 'invalid_request',
} satisfies Partial<MosCoordinationGatewayError>);
} satisfies Partial<InteractionCoordinationGatewayError>);
await expect(
coordination.handoff({ idempotencyKey: 'request-3', summary: 'x'.repeat(2_049) }, context),
).rejects.toMatchObject({
code: 'invalid_request',
} satisfies Partial<MosCoordinationGatewayError>);
} satisfies Partial<InteractionCoordinationGatewayError>);
expect(handoff).toHaveBeenCalledTimes(1);
});
it('fails closed when the port reports a target that drifts from configuration', async (): Promise<void> => {
const adapter: MosCoordinationPort = {
handoff: vi.fn(async (handoff: MosHandoff) => ({
const adapter: InteractionCoordinationPort = {
handoff: vi.fn(async (handoff: Handoff) => ({
handoffId: handoff.handoffId,
targetAgentId: 'Unexpected',
status: 'accepted' as const,

View File

@@ -1,18 +1,18 @@
import { Inject, Injectable } from '@nestjs/common';
import {
MosCoordinationClient,
InteractionCoordinationClient,
type CoordinationObservation,
type CoordinationResult,
type CoordinationScope,
type MosCoordinationIdentity,
type MosCoordinationPort,
type MosHandoffReceipt,
type InteractionCoordinationIdentity,
type InteractionCoordinationPort,
type HandoffReceipt,
} from '@mosaicstack/coord';
import type { RuntimeProviderRequestContext } from '../agent/runtime-provider-registry.service.js';
import type { CreateMosHandoffDto } from './mos-coordination.dto.js';
import type { CreateHandoffDto } from './interaction-coordination.dto.js';
export const MOS_COORDINATION_PORT = Symbol('MOS_COORDINATION_PORT');
export const MOS_COORDINATION_CONFIG = Symbol('MOS_COORDINATION_CONFIG');
export const COORDINATION_PORT = Symbol('COORDINATION_PORT');
export const COORDINATION_CONFIG = Symbol('COORDINATION_CONFIG');
const HANDOFF_TRACKING_TTL_MS = 60 * 60 * 1_000;
const MAX_TRACKED_HANDOFFS = 1_000;
@@ -21,7 +21,7 @@ const MAX_SUMMARY_LENGTH = 2_048;
const MAX_CONTEXT_LENGTH = 8_192;
const MAX_MISSION_ID_LENGTH = 128;
export interface MosCoordinationConfig {
export interface InteractionCoordinationConfig {
interactionAgentId?: string;
orchestrationAgentId?: string;
}
@@ -34,7 +34,7 @@ interface HandoffOwner {
expiresAt: number;
}
interface NormalizedMosHandoffRequest {
interface NormalizedHandoffRequest {
idempotencyKey: string;
summary: string;
context?: string;
@@ -42,31 +42,31 @@ interface NormalizedMosHandoffRequest {
}
interface TrackedHandoff {
request: NormalizedMosHandoffRequest;
receipt: Promise<MosHandoffReceipt>;
request: NormalizedHandoffRequest;
receipt: Promise<HandoffReceipt>;
expiresAt: number;
}
/**
* Gateway authority boundary for the interaction agent. It derives requester,
* actor, and tenant from trusted server configuration and authentication; no
* channel request can name a target or gain Mos-owned orchestration verbs.
* channel request can name a target or gain orchestrator-owned orchestration verbs.
*/
@Injectable()
export class MosCoordinationService {
export class InteractionCoordinationService {
private readonly owners = new Map<string, HandoffOwner>();
private readonly handoffsByIdempotencyKey = new Map<string, TrackedHandoff>();
constructor(
@Inject(MOS_COORDINATION_PORT) private readonly port: MosCoordinationPort,
@Inject(MOS_COORDINATION_CONFIG) private readonly config: MosCoordinationConfig,
@Inject(COORDINATION_PORT) private readonly port: InteractionCoordinationPort,
@Inject(COORDINATION_CONFIG) private readonly config: InteractionCoordinationConfig,
private readonly handoffIdFactory: () => string = (): string => crypto.randomUUID(),
) {}
async handoff(
request: CreateMosHandoffDto,
request: CreateHandoffDto,
context: RuntimeProviderRequestContext,
): Promise<MosHandoffReceipt> {
): Promise<HandoffReceipt> {
this.pruneExpiredTracking();
const normalized = this.normalizeRequest(request);
const scope = this.scope(context);
@@ -74,9 +74,9 @@ export class MosCoordinationService {
const existing = this.handoffsByIdempotencyKey.get(idempotencyKey);
if (existing !== undefined) {
if (!sameRequest(existing.request, normalized)) {
throw new MosCoordinationGatewayError(
throw new InteractionCoordinationGatewayError(
'handoff_conflict',
'Mos handoff idempotency key is already bound to different immutable input',
'Handoff idempotency key is already bound to different immutable input',
);
}
return existing.receipt;
@@ -122,9 +122,9 @@ export class MosCoordinationService {
private async deliverHandoff(
handoffId: string,
request: NormalizedMosHandoffRequest,
request: NormalizedHandoffRequest,
scope: CoordinationScope,
): Promise<MosHandoffReceipt> {
): Promise<HandoffReceipt> {
const receipt = await this.client((): string => handoffId).handoff(request, scope);
const owner: HandoffOwner = {
actorId: scope.actorId,
@@ -135,9 +135,9 @@ export class MosCoordinationService {
};
const existing = this.owners.get(receipt.handoffId);
if (existing !== undefined && !sameOwner(existing, owner)) {
throw new MosCoordinationGatewayError(
throw new InteractionCoordinationGatewayError(
'handoff_conflict',
'Mos handoff ID is already bound to a different authenticated scope',
'Handoff ID is already bound to a different authenticated scope',
);
}
this.owners.set(receipt.handoffId, owner);
@@ -145,21 +145,21 @@ export class MosCoordinationService {
return receipt;
}
private client(handoffIdFactory?: () => string): MosCoordinationClient {
return new MosCoordinationClient(this.identity(), this.port, handoffIdFactory);
private client(handoffIdFactory?: () => string): InteractionCoordinationClient {
return new InteractionCoordinationClient(this.identity(), this.port, handoffIdFactory);
}
private identity(): MosCoordinationIdentity {
private identity(): InteractionCoordinationIdentity {
const interactionAgentId = this.config.interactionAgentId?.trim();
const orchestrationAgentId = this.config.orchestrationAgentId?.trim();
if (!interactionAgentId) {
throw new MosCoordinationGatewayError(
throw new InteractionCoordinationGatewayError(
'unconfigured_requester',
'Interaction agent identity is not configured',
);
}
if (!orchestrationAgentId) {
throw new MosCoordinationGatewayError(
throw new InteractionCoordinationGatewayError(
'unconfigured_target',
'Orchestration agent identity is not configured',
);
@@ -177,9 +177,12 @@ export class MosCoordinationService {
});
}
private normalizeRequest(request: CreateMosHandoffDto): NormalizedMosHandoffRequest {
private normalizeRequest(request: CreateHandoffDto): NormalizedHandoffRequest {
if (typeof request !== 'object' || request === null) {
throw new MosCoordinationGatewayError('invalid_request', 'Mos handoff request is invalid');
throw new InteractionCoordinationGatewayError(
'invalid_request',
'Handoff request is invalid',
);
}
const idempotencyKey = this.requiredString(
request.idempotencyKey,
@@ -203,14 +206,17 @@ export class MosCoordinationService {
private requiredString(value: unknown, field: string, maximumLength: number): string {
if (typeof value !== 'string') {
throw new MosCoordinationGatewayError(
throw new InteractionCoordinationGatewayError(
'invalid_request',
`Mos handoff ${field} must be a string`,
`Handoff ${field} must be a string`,
);
}
const normalized = value.trim();
if (normalized.length === 0 || normalized.length > maximumLength) {
throw new MosCoordinationGatewayError('invalid_request', `Mos handoff ${field} is invalid`);
throw new InteractionCoordinationGatewayError(
'invalid_request',
`Handoff ${field} is invalid`,
);
}
return normalized;
}
@@ -245,23 +251,23 @@ export class MosCoordinationService {
private ownerFor(handoffId: string, scope: CoordinationScope): HandoffOwner {
const owner = this.owners.get(handoffId);
if (owner === undefined) {
throw new MosCoordinationGatewayError('not_found', 'Mos handoff was not found');
throw new InteractionCoordinationGatewayError('not_found', 'Handoff was not found');
}
if (
owner.tenantId !== scope.tenantId ||
owner.actorId !== scope.actorId ||
owner.requesterAgentId !== scope.requesterAgentId
) {
throw new MosCoordinationGatewayError(
throw new InteractionCoordinationGatewayError(
'cross_tenant_forbidden',
'Mos handoff is outside the authenticated scope',
'Handoff is outside the authenticated scope',
);
}
return owner;
}
}
export type MosCoordinationGatewayErrorCode =
export type InteractionCoordinationGatewayErrorCode =
| 'cross_tenant_forbidden'
| 'handoff_conflict'
| 'invalid_request'
@@ -277,10 +283,7 @@ function sameOwner(left: HandoffOwner, right: HandoffOwner): boolean {
);
}
function sameRequest(
left: NormalizedMosHandoffRequest,
right: NormalizedMosHandoffRequest,
): boolean {
function sameRequest(left: NormalizedHandoffRequest, right: NormalizedHandoffRequest): boolean {
return (
left.idempotencyKey === right.idempotencyKey &&
left.summary === right.summary &&
@@ -289,12 +292,12 @@ function sameRequest(
);
}
export class MosCoordinationGatewayError extends Error {
export class InteractionCoordinationGatewayError extends Error {
constructor(
readonly code: MosCoordinationGatewayErrorCode,
readonly code: InteractionCoordinationGatewayErrorCode,
message: string,
) {
super(message);
this.name = MosCoordinationGatewayError.name;
this.name = InteractionCoordinationGatewayError.name;
}
}

View File

@@ -10,9 +10,9 @@
**Statement:** Ship a self-hosted, multi-user AI agent platform that consolidates the user's disparate jarvis-brain usage across home and USC workstations into a single coherent system reachable via three first-class surfaces — webUI, TUI, and CLI — with federation as the data-layer mechanism that makes cross-host agent sessions work in real time without copying user data across the boundary.
**Phase:** Execution (workstream W1 in planning-complete state)
**Current Workstream:** W1 — Federation v1
**Progress:** 0 / 1 declared workstreams complete (more workstreams will be declared as scope is refined)
**Progress:** 0 / 3 declared workstreams complete (more workstreams will be declared as scope is refined)
**Status:** active (continuous since 2026-03-13)
**Last Updated:** 2026-04-19 (manifest authored at the rollup level; install-ux-v2 archived; W1 federation planning landed via PR #468)
**Last Updated:** 2026-07-14 (W3 Native Kanban/SOT canon independently approved under issue #751)
**Source PRD:** [docs/PRD.md](./PRD.md) — Mosaic Stack v0.1.0
**Scratchpad:** [docs/scratchpads/mvp-20260312.md](./scratchpads/mvp-20260312.md) (active since 2026-03-13; 14 prior sessions of phase-based execution)
@@ -67,11 +67,12 @@ 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 | TESS | Tess interaction agent | planning-complete | [docs/tess/MISSION-MANIFEST.md](./tess/MISSION-MANIFEST.md) | 5 milestones; issue #706; M1 issue #707 ready |
| W3 | KBN | Native Kanban and canonical task SOT | planning-complete | [docs/native-kanban-sot/MISSION-MANIFEST.md](./native-kanban-sot/MISSION-MANIFEST.md) | P0P3; issue #751; implementation held until canon merge |
| W4+ | TBD | (additional workstreams declared as scoped) | — | — | Scope creep is expected and explicitly accommodated |
### Likely Additional Workstreams (Not Yet Declared)

43
docs/SITEMAP.md Normal file
View File

@@ -0,0 +1,43 @@
# Documentation Sitemap
## Native Kanban and canonical task SOT
- [Canonical requirements](requirements/native-kanban-sot.md) — ratified P0P3 requirements and acceptance criteria.
- [Workstream index](native-kanban-sot/INDEX.md) — artifact map, lane partition, and delivery order.
- [Mission manifest](native-kanban-sot/MISSION-MANIFEST.md) — scope, authority, invariants, and gate model.
- [Task decomposition](native-kanban-sot/TASKS.md) — dependency-ordered implementation slices and ownership boundaries.
- [Frozen shared contract](native-kanban-sot/SHARED-CONTRACT.md) — schema, API, Coordinator, health, recovery, and migration contracts.
- [Initial independent review](reports/native-kanban-sot/canon-initial-review-no-go.md) — KCR-001016 findings that blocked the first draft.
- [Final independent re-review](reports/native-kanban-sot/canon-final-rereview-go.md) — closure evidence and GO verdict.
- [Ultron final gate](reports/native-kanban-sot/ultron-final-go.md) — final requirements, authority, schema, migration, recovery, and evidence review.
## Tess interaction agent
### Operator guides
- [User guide](tess/USER-GUIDE.md) — authorized session, attach, send, stop, and handoff workflows.
- [Admin guide](tess/ADMIN-GUIDE.md) — deployment configuration, policy, and approval controls.
- [Developer guide](tess/DEVELOPER-GUIDE.md) — provider contracts, scope boundaries, and test workflow.
- [Plugin guide](tess/PLUGIN-GUIDE.md) — adapter, redaction, and identity-as-data requirements.
- [Operations guide](tess/OPERATIONS-GUIDE.md) — readiness, recovery, and incident-safe procedures.
### Architecture and security
- [Architecture](tess/ARCHITECTURE.md)
- [Threat model](tess/THREAT-MODEL.md)
- [Mos coordination boundary](tess/MOS-COORDINATION.md)
- [Hermes runtime adapter design](tess/hermes-runtime-adapter-design.md)
- [Operator plugin sketch](tess/M4-003-OPERATOR-PLUGIN-SKETCH.md)
### API contract
- [Tess OpenAPI contract](openapi-tess.yaml)
### Migration and qualification
- [Migration inventory](tess/M5-MIGRATION-INVENTORY.md)
- [Cutover procedure](tess/M5-MIGRATION-CUTOVER.md)
- [Rollback procedure](tess/M5-MIGRATION-ROLLBACK.md)
- [Retention and deprecation evidence](tess/M5-MIGRATION-RETENTION-DEPRECATION.md)
- [Verification matrix](tess/VERIFICATION-MATRIX.md)
- [Documentation checklist](tess/M5-003-DOCUMENTATION-CHECKLIST.md)

View File

@@ -14,10 +14,11 @@
## 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; M2M7 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; M2M7 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 |
| W3 | planning-complete | Native Kanban/SOT | 0 / 4 phases | [docs/native-kanban-sot/TASKS.md](./native-kanban-sot/TASKS.md) | Issue #751; canon independently approved; implementation held until canon merges |
## Cross-Cutting Tracking

View File

@@ -0,0 +1,36 @@
# Documentation Completion Checklist — Native Kanban/SOT Canon
**Tracking:** Mosaic Stack issue #751
**Scope:** Requirements and contract publication only; runtime implementation follows in separate slices.
## Required artifacts
- [x] Project `docs/PRD.md` exists; the workstream requirements refine its task/project-management scope.
- [x] Canonical workstream requirements published at `docs/requirements/native-kanban-sot.md`.
- [x] Mission manifest, task decomposition, frozen shared contract, and typed contract declarations included.
- [x] `docs/SITEMAP.md` updated.
- [x] Independent initial review and final GO report stored under `docs/reports/native-kanban-sot/`.
- [x] Task scratchpad stored under `docs/scratchpads/`.
- [ ] User/Admin/Developer guides — N/A for canon-only publication; required in implementation slices that change behavior or operations.
- [ ] OpenAPI and endpoint index — N/A until KBN-105 freezes implementation-ready endpoint contracts.
## Structural and root hygiene
- [x] Canonical requirements are under `docs/requirements/`.
- [x] Workstream artifacts are under `docs/native-kanban-sot/`.
- [x] Review reports are under `docs/reports/native-kanban-sot/`.
- [x] No new unscoped document was added to the `docs/` root.
- [x] Root mission/task rollups link to the workstream.
## Review gate
- [x] Author and independent reviewer are different agents.
- [x] KCR-001016 closure was independently verified.
- [x] Ultron final gate returned GO with zero BLOCKER/HIGH findings.
- [x] Formatter, lint, typecheck, strict contract TypeScript, link, scope, and invariant publication validation passed in the current Stack toolchain.
- [ ] PR review, CI, squash merge, and issue closure remain required before publication completion.
## Publishing
- [x] Canonical source remains in-repository.
- [x] No external publishing platform is required for this internal architecture contract.

View File

@@ -0,0 +1,64 @@
# Native Kanban/SOT Canon
**Status:** KCR-001016 independently cleared; canonical publication is in progress under issue [#751](https://git.mosaicstack.dev/mosaicstack/stack/issues/751)
**Date:** 2026-07-14
**Implementation hold:** no feature implementation starts until this canon is squash-merged to `main` with terminal-green CI; after merge, every slice remains held until its KBN prerequisite graph is satisfied.
## Artifacts
| Artifact | Purpose |
| ---------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Canonical requirements](../requirements/native-kanban-sot.md) | Canonical P0P3 requirements, all seven ratified decisions, fixed invariants, thin MVP, recovery tiers, non-goals, and per-requirement acceptance criteria |
| [`MISSION-MANIFEST.md`](./MISSION-MANIFEST.md) | Mission/authority boundaries, exact role chain, gate model, mandatory SecReview triggers, Certifier final/no-merge rule, and collision-free slice ownership |
| [`TASKS.md`](./TASKS.md) | Dependency-ordered, bounded P0P3 slices with IN/OUT scope, dependencies, shared contracts, file ownership, evidence, and USC coder2/3/4/5 parallelization |
| [`SHARED-CONTRACT.md`](./SHARED-CONTRACT.md) | Remediated v1 integration contract: proof authority, exact failures/routes/DTOs/MCP ownership, concrete current-main field migration map, relational invariants, Coordinator split, recovery delivery |
| [`contracts/kanban-schema.v1.ts`](./contracts/kanban-schema.v1.ts) | Drizzle target declarations including exact owner/principal membership, project congruence, tags/archive, proposals, persisted assignments, monotonic fences, durable retry, immutable evidence/audit |
| [`contracts/mechanical-coordinator.v1.ts`](./contracts/mechanical-coordinator.v1.ts) | Pure snapshot decision engine separated from persistence/service adapter; ID-bound approvals, bigint-safe fences, durable retry/quarantine, artifact-backed checkpoints, exact failures |
| [`contracts/health-state.v1.ts`](./contracts/health-state.v1.ts) | Discriminated public health, separate branded transaction-local write proof, and non-overlapping denial/transport/version-conflict mappings |
| [`contracts/recovery-posture.v1.ts`](./contracts/recovery-posture.v1.ts) | Provider-neutral shape schema plus normative runtime refinement, cross-field constraints, and Lite/Standard/High-assurance defaults |
| [`tsconfig.json`](./tsconfig.json) | Strict no-emit project scope for linting and compiling the four frozen TypeScript contracts against the current Stack Drizzle declarations |
| [`DOCUMENTATION-CHECKLIST.md`](./DOCUMENTATION-CHECKLIST.md) | Publication documentation gate and implementation-slice deferrals |
| [Initial independent review](../reports/native-kanban-sot/canon-initial-review-no-go.md) | KCR-001016 findings that blocked the first draft |
| [Final independent re-review](../reports/native-kanban-sot/canon-final-rereview-go.md) | Closure matrix, reproducible validation evidence, and GO verdict |
| [Ultron final gate](../reports/native-kanban-sot/ultron-final-go.md) | Final requirements, authority, schema, migration, recovery, decomposition, and evidence review GO |
## Recommended USC lane partition
| Lane | Natural seam | Exclusive ownership |
| ---------- | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **coder2** | Schema + migrations + recovery slice | Unified Drizzle schema, migration SQL/meta/journal/tests, then recovery parser/mechanism/runbook files |
| **coder3** | Domain + Gateway + MCP server | Workspace-safe repositories, DTOs/controllers/services, exact `apps/gateway/src/mcp/**` files, health proof, proposals, Coordinator persistence adapter |
| **coder4** | Pure Coordinator + tooling | `packages/coord` mechanical engine, CLI/MCP consumers, generated projection, one-way importer and cutover tooling; lane-serialized internally |
| **coder5** | Web | Tasks/Projects Kanban/List/detail and later Coordinator/migration-review UI |
| **Mos** | Serialized integration | Canon publication, frozen-contract changes, shared-root/exports, integration gates, merge authority |
The safe order is KBN-010 → KBN-100 → KBN-105, then coder3 Gateway/MCP server, coder4 CLI/projection, coder5 web, and coder2 recovery can proceed on disjoint files. coder4 then runs pure Coordinator → importer → cutover tooling serially. No two active slices edit the same files.
## Recovery defaults
| Tier | RPO / RTO | WAL / PITR | Base backup | Restore / break-glass | Off-cluster |
| -------------- | ------------ | ------------------- | ----------- | ----------------------- | ----------------------------------------------- |
| Lite | 24h / 24h | disabled / disabled | daily | quarterly / annual | encrypted separate target |
| Standard | 1h / 8h | q15m / 14d | daily | quarterly / semiannual | encrypted separate object storage |
| High-assurance | **15m / 4h** | **q5m / 35d** | **daily** | **monthly / quarterly** | **encrypted base+WAL, separate failure domain** |
These knobs affect recovery posture only. PostgreSQL remains the sole writable SOT in every tier. Fail-closed writes, generated-file non-authority, attributable post-recovery proposals, non-LLM Coordinator limits, and Certifier final-gate/no-merge authority are fixed for every tier.
## Non-blocking implementation sub-decisions for Mos
The source plan and ratified seven decisions resolve all build-blocking product choices. The following implementation-local selections remain for the owning slices/Mos and must not weaken v1:
1. Exact PostgreSQL write-health probe SQL and bounded proof lifetime; authority and failures are frozen.
2. Dependency-cycle serialization mechanism (recursive CTE plus transaction/advisory lock or equivalent); required behavior is frozen.
3. Whether RLS lands in the first migration or immediately after the tested session-context pattern; workspace constraints/repository authorization are required from migration one.
4. Concrete off-cluster backup provider/bucket and selected production recovery tier; High-assurance minima are frozen if selected.
5. Cutover reconciliation thresholds and stabilization duration, to be owner-approved before P3 execution.
None authorizes a second writer, dual sync, LLM scheduling, Coordinator gate waiver/merge, or Certifier merge authority.
## Publication validation evidence
- Concrete TypeScript contracts are formatted with repository Prettier.
- All four contracts pass strict TypeScript no-emit checking against the current Stack Drizzle toolchain.
- Contract remediation and KCR-001016 traceability are recorded in the issue scratchpad and linked review reports.
- Independent re-review returned GO with KCR-001016 closed; implementation remains held until canon merge and the dependency-ordered KBN prerequisites complete.

View File

@@ -0,0 +1,394 @@
# KBN-010 — Threat, Authorization, and Constraint-Impact Gate
- **Issue:** [#753](https://git.mosaicstack.dev/mosaicstack/stack/issues/753)
- **Gate status:** **BLOCKED**
- **Reviewed baseline:** `origin/main` at `49e8a54` (2026-07-14)
- **Frozen target:** `SHARED-CONTRACT.md` v1.0.0-rc.3 and `contracts/*.v1.ts`
- **Scope:** documentation and future-test planning only; no runtime, schema, migration, API, configuration, dependency, CI, or deployment change
## 1. Decision
KBN-010 cannot pass. The frozen schema contract has one unresolved schema impact:
- **KBN010-SI-001 — invalid mission composite-FK candidate key.** `missionsV1` declares a primary key on `id` and a unique key on `(workspace_id, project_id, id)`, but not a candidate key on `(workspace_id, id)`. Both `artifacts_workspace_mission_fk` and `approval_decisions_workspace_mission_fk` reference exactly `(missions.workspace_id, missions.id)`. PostgreSQL requires the referenced column list of a foreign key to match a non-partial unique/primary candidate key; uniqueness of `id` alone does not satisfy a two-column `(workspace_id, id)` reference. KBN-100 therefore cannot create the frozen DDL as written.
The contract authority must choose and version one of these semantics before KBN-100 starts:
1. add a frozen unique candidate key on `missions(workspace_id, id)`; or
2. add `project_id` to each child relation and use project-congruent `(workspace_id, project_id, mission_id)` foreign keys.
This document does **not** choose or apply either amendment. All other findings below are mapped to controls and future evidence, but the gate remains blocked until the frozen contract is amended and independently re-reviewed.
## 2. Method and trust boundaries
### 2.1 Inputs inspected
- Canonical requirements: `docs/requirements/native-kanban-sot.md`.
- Workstream manifest and read-only task plan.
- Frozen health, schema, Mechanical Coordinator, and recovery contracts in full.
- Actual current-main schema, Better Auth guard/scope helpers, project/task/mission/team controllers and repositories, fleet backlog, and `TASKS.md` parser/writer.
- Issue #753 through the Mosaic provider wrapper.
### 2.2 Current-main exposure that the target must replace, not inherit
| Current-main fact | Constraint on future implementation |
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- |
| Teams are global; projects, missions, tasks, agents, and fleet backlog have no `workspace_id`. | KBN-100 must add the workspace boundary and KBN-110 must query by server-derived workspace in every repository operation. |
| `AuthGuard` authenticates a Better Auth user, while `scopeFromUser` falls back through optional tenant/team/org claims and finally user ID. | Kanban tenancy must derive from an authenticated **active workspace membership**, not this compatibility fallback or caller data. |
| Team list/get/member endpoints return global team data to any authenticated user. | New Kanban endpoints must use a uniform no-oracle denial and must not reuse global team lookup as authorization. |
| Project/task repositories load and mutate by bare IDs; controller checks are separate and sometimes distinguish not-found from forbidden. | Workspace predicates and authorization must be inside the authoritative transaction/repository command path. |
| Tasks can have nullable project/mission links, free-text assignee, JSON tags, no aggregate version, and no fence. | Expand/backfill/quarantine must precede NOT NULL/composite constraints; new commands cannot trust legacy fields. |
| `mission_tasks.status` is a second status writer. | Pre-expand must prohibit it as a write source and later retire it only after N-1 evidence. |
| Fleet `backlog` has global JSON dependencies and TTL claims without workspace, assignment, approval, session, or fencing. | It must be frozen and imported as non-dispatching shadow data; it cannot be adapted into the canonical lease path. |
| `packages/coord/src/tasks-file.ts` parses and mutates `TASKS.md`. | KBN-120 must replace production use with generated, read-only projection code and prove there is no import/mutation path. |
| No Kanban transaction-local health proof, semantic audit/event chain, change proposals, canonical outbox, approval binding, or fenced lease model exists. | These are new frozen invariants, not behaviors that may be inferred from current endpoints. |
## 3. Authorization matrix
The exact route/DTO freeze belongs to KBN-105. This matrix fixes the minimum authorization behavior that freeze and later implementation must preserve.
| Principal/state | Permitted authority | Required authoritative checks | Explicit denials |
| -------------------------------------------------- | ------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
| Unauthenticated caller | Public health observation only, if deployment exposes it | Health DTO validation; no proof field accepted | All canonical reads/mutations; health observation never authorizes a write |
| Active workspace `owner`/`admin` user | Policy-allowed workspace administration and domain commands | Better Auth session; active membership; server-derived workspace; command-family role; expected version/idempotency | Foreign workspace, suspended workspace, revoked membership, caller workspace override |
| Active workspace `member` user | Policy-allowed project/task/proposal commands | Active membership plus project/team capability and target checks in the same transaction | Admin, approval, purge, service-only Coordinator, and unrelated project commands |
| Active workspace `auditor` user | Workspace-scoped reads and audit/evidence inspection | Active membership and read capability | Every mutation, approval, lease, token issuance, purge |
| Active workspace `service` identity | Only explicitly issued command families | Credential maps to workspace+agent+session; agent enabled; session live; role/capability allowlist; token expiry/audience; DB recheck per command | Raw DB credentials, user/admin fallback, cross-workspace scope, command families absent from token and registry |
| Enabled agent with live session | Agent commands matching its declared and policy-approved specialist role/capabilities | Exact workspace+agent+session binding, heartbeat/state, assignment target, lease, current decimal-string fence | Ended/offline/degraded session where policy disallows; disabled agent; another assignment/session/fence |
| Mechanical Coordinator engine | Pure eligibility/order/expiry decisions from immutable snapshots | Complete workspace-local snapshot and policy revision | Authentication, ID loading, SQL, proof minting, scope invention, approval, certification, merge |
| Coordinator persistence service | Service-only assignment/lease/checkpoint/recovery commands | Fresh transaction-local proof; locks; current assignment/approval/task/session/policy/fence | Public/user proof-by-value, stale approval/policy, direct completion/certification/merge |
| Reviewer/SecReview/Certifier | Attributable evidence decisions allowed by gate policy | Active authority, author differs from reviewer, mandatory SecReview classification, immutable artifacts | Self-review; missing evidence; Certifier merge/issue-close/release |
| Break-glass retention operator | Narrow, time-bounded purge procedure only | Separate break-glass authority, reason, scope, approvals, immutable pre-purge evidence, semantic audit, post-action reconciliation | Normal application role DELETE/UPDATE, bulk unscoped purge, unaudited hard delete |
| Revoked/expired/disabled identity or ended session | None beyond policy-permitted public observation | Revocation/lifecycle checked from PostgreSQL on every command | Cached token/Valkey state cannot preserve authority |
**No-oracle rule:** authentication may return 401, but once authenticated, a foreign-workspace, nonexistent, inaccessible, or wrong-project identifier must follow the one KBN-105-frozen 404/403 policy with the same response shape and no foreign metadata, timing-derived detail, or WebSocket/MCP discrepancy.
## 4. Threat matrix
Every disposition is against the frozen target, not a claim about current-main behavior.
| ID | Attacker or failure | Asset | Precondition and abuse path | Frozen preventive/detective control | Required schema/API/negative-test evidence | Future owner | Residual risk | Disposition |
| --- | --------------------------------------------------------------------------------------- | --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------- | ------------------------------------------------------------------- | ----------------------------------- |
| T01 | Authenticated user supplies a foreign workspace/resource ID | Tenant confidentiality and integrity | Caller knows or guesses project/task/mission/team IDs and probes REST, MCP, WebSocket, repository, or Coordinator paths | `workspace_id` on every canonical row; composite relations; server-derived tenant; uniform no-oracle denial | Composite FK/unique DDL; every repository predicate includes workspace; N100-01/02, N110-01..05, N130-01 | KBN-100, 105, 110, 130 | Timing/volume side channels require operational review | Controlled after evidence |
| T02 | Revoked or inactive member retains an old session | Ownership and mutation authority | Authentication remains valid after workspace membership revocation | Active membership rechecked in the authoritative transaction for owners, principals, proposers, and decision actors | Active/inactive membership fixtures; N100-03, N110-06/07; no cached membership authority | KBN-100, 110 | Better Auth session may remain valid for unrelated features | Controlled after evidence |
| T03 | User joins/forges a team relation outside its workspace | Team-owned projects and tasks | Global-current-main team behavior or a stale membership is reused | Team is intra-workspace only; workspace/team composites; active workspace membership precedes team authorization | Cross-workspace team/member/owner insert and command denials; N100-04/05, N110-08 | KBN-100, 110 | Team-role policy mistakes remain possible | Controlled after evidence |
| T04 | Same-workspace IDs from a different project are combined | Planning hierarchy integrity | Valid mission/milestone/parent/current-milestone UUIDs are substituted | Project-congruent composite relations and serialized hierarchy validation | Mission/milestone/parent/current milestone mismatch and parent-cycle tests; N100-06..10, N110-09 | KBN-100, 110 | Deep hierarchy checks can be expensive | Controlled after evidence |
| T05 | Foreign or unrelated evidence/link/artifact IDs are attached | Review and audit truth | Caller has a valid same-workspace or foreign artifact UUID | Workspace-aware joins; immutable artifact digest/revision; semantic same-target validation in authoritative transaction | Mixed-workspace and same-workspace wrong-task/mission checkpoint/approval evidence tests; N100-11..14, N210-15/16 | KBN-100, 110, 210 | Same-workspace semantic validation is application-enforced | Controlled after evidence |
| T06 | Stolen, over-scoped, or replayed service token | Coordinator and task mutation authority | Service credential is accepted as admin/user or claims are trusted without DB state | Command-family least privilege; agent/session workspace binding; no raw DB credentials; enabled/live state checked per command | Auth registry fixtures prove audience/expiry/role/capability; revoked agent and ended session denials; N105-01, N110-10..13, N210-01/02 | KBN-105, 110, 210 | Credential theft until expiry/revocation check | Controlled after evidence |
| T07 | Caller forges public `healthy` or replays a stale health response | Sole-writer/fail-closed invariant | Public health body or caller field reaches mutation context | Public DTO is observation only; public DTOs reject proof/health fields; Gateway mints internal proof after live PG transaction probe | Contradictory union and forbidden-field tests; N105-02, N110-14..17 | KBN-105, 110, 140 | Health endpoint can still be used for reconnaissance | Controlled after evidence |
| T08 | Internal stale, wrong-policy, or wrong-transaction proof is reused | Transaction integrity | A branded value leaks or an adapter fails to revalidate it | Non-exported brand; transaction identity, `checkedAt <= now < validUntil`, and policy revision revalidated immediately before mutation | Wrong transaction, expiry boundary, future timestamp, policy mismatch, commit-after-expiry tests; N110-18..22 | KBN-110, 140 | In-process code can bypass TypeScript; runtime checks are mandatory | Controlled after evidence |
| T09 | DB/transport uncertainty is mislabeled as deliberate denial or conflict | Safe retry and exactly-once result | Timeout occurs before/after commit and client changes key or retries 503 | Exact 503/502/504/timeout/409 union; unknown outcome retries only with same idempotency key | Exhaustive fixture mapping and commit-before-timeout replay; N105-03, N110-23..27, N120-01/02 | KBN-105, 110, 120, 140 | External client may ignore retry rules | Controlled after evidence |
| T10 | Assignment payload forges task version, target agent/session, role, expiry, or proposer | Work routing authority | Lease service trusts command DTO rather than persisted assignment | Persisted assignment identity; exactly-one principal/proposer; exact agent/session composite; acquire accepts IDs then reloads+locks | Cross-workspace and same-workspace target substitutions, stale task version, invalid role, expired assignment; N100-15..18, N210-03..08 | KBN-100, 200, 210 | Compromised authorized proposer can make harmful proposals | Controlled by approval/audit |
| T11 | Approval proof is forged by value or borrowed from another assignment | Gate integrity | Caller submits `approved=true`, unrelated decision ID, stale policy, or self-approval | Relational approval bound to assignment; lock/reload; policy revision; author≠reviewer and mandatory SecReview | No proof-by-value DTO; wrong assignment/task/workspace/policy/actor/decision tests; N105-04, N210-09..14, N230-01 | KBN-105, 210, 230 | Colluding principals remain an organizational risk | Controlled after evidence |
| T12 | Revoked policy or expired proposal/assignment is raced against lease acquisition | Routing policy | Approval and lease transactions do not lock/revalidate current rows | Lock assignment, approval, task, target session; compare current policy and expiry inside fresh-proof transaction | Concurrent revoke/expire/acquire tests with one valid terminal result; N210-17..19 | KBN-210, 230 | Clock skew if DB time is not canonical | Controlled after evidence |
| T13 | Stale worker sends ack/heartbeat/checkpoint/review after reassignment | Canonical task and evidence state | Old process retains task/session IDs | Task-row-locked atomic monotonic bigint fence; every worker command carries exact lease/session/fence | Lower, expired, future, and other-task fences denied; old worker loses after new lease; N100-19/20, N210-20..24 | KBN-100, 210, 230 | Signed bigint exhaustion is theoretical | Controlled after evidence |
| T14 | JavaScript precision truncates a fence | Stale-worker exclusion | bigint token is serialized as number above `2^53-1` | Drizzle bigint and decimal-string wire type only | `9007199254740993` and near-`int8` boundary round trips; numeric JSON rejected; N105-05, N210-25 | KBN-105, 210 | Nonconforming external clients | Controlled after evidence |
| T15 | Checkpoint/evidence from another lease/task/session is submitted | Recovery and certification evidence | Same-workspace valid IDs are mixed | Exact lease composite binds workspace+task+assignment/session+fence; checkpoint composite binds lease+fence; evidence join plus semantic artifact-owner check | Same-workspace mismatched task/assignment/lease/session/checkpoint/artifact tests; N100-21..23, N210-26..31 | KBN-100, 210 | Artifact URI target may disappear outside DB | Controlled with digest/retention |
| T16 | Outage note or pending/rejected proposal mutates/orders work | Sole SOT and gate integrity | Importer/UI treats note/proposal as task state | Proposals are inert; only explicit accept invokes normal typed command after recovery | Row/outbox/task counts unchanged for pending/rejected; no readiness/dependency/lease effect; N110-28..31 | KBN-110, 140 | Humans may act outside Mosaic operationally | Accepted as attributable residual |
| T17 | Submission event is missing, foreign, or for another proposal | Proposal audit chain | Caller supplies an existing event UUID | Preallocated proposal ID; event-first same transaction; workspace composite FK; exact event type/aggregate/version semantic check | Missing/foreign/wrong-type/wrong-proposal event rolls back event+proposal; N100-24/25, N110-32..36 | KBN-100, 110 | Semantic checks are transaction code, not only FK | Controlled after evidence |
| T18 | Acceptance borrows an unrelated command event | Proposal and target integrity | Same-workspace event exists for another target/command/proposal | Accept locks proposal+target, executes normal command, requires workspace/target match, causation=submission event, payload proposal ID | Foreign, wrong target/type/command/causation/payload event aborts target/event/proposal atomically; N100-26, N110-37..43 | KBN-100, 110 | Event payload schema drift | Controlled by KBN-105 fixtures |
| T19 | Application role updates/deletes audit, approval evidence, checkpoint, or artifact | Nonrepudiation | Broad DB grants or parent cascade exists | INSERT/SELECT-only application roles; RESTRICT parent deletes; archive/cancel normal lifecycle | Role-level UPDATE/DELETE denied; parent delete RESTRICT; digest unchanged; N100-27..31 | KBN-100 | DB superuser can alter state | Break-glass/infra audit residual |
| T20 | Break-glass purge is used as routine deletion or erases its own evidence | Retention and incident forensics | Elevated credential available | Separate audited retention procedure, bounded scope, reason, pre/post evidence, authority separation | Normal role denied; expired/missing approval denied; purge cannot delete its authorizing audit package; N115-01, N230-02/03 | KBN-115, 230 | Privileged DBA compromise | Accepted operational residual |
| T21 | PostgreSQL unavailable or partitioned | Canonical state | Public health/Valkey remains live while transaction probe fails | Fail closed; no alternate writer/hidden queue; 503 only for proven not-applied; transport uncertainty remains unknown | Fault injection proves DB rows/outbox/files/Valkey unchanged on deliberate denial; commit-unknown replay; N110-44..48, N140-01 | KBN-110, 140, 230 | Availability loss is intentional | Accepted by Option A |
| T22 | Valkey unavailable, duplicated, stale, or partitioned | Scheduling notifications | Queue wake is treated as truth or publication fails | Valkey derived/expendable; transactional outbox in PG; idempotent publisher; recovery from PG | Commit with Valkey down leaves pending outbox; replay publishes once logically; stale wake reloads PG; N110-49, N140-02, N230-04..06 | KBN-110, 210, 230 | Duplicate at-least-once delivery | Consumers must be idempotent |
| T23 | Coordinator restarts between assignment, lease, checkpoint, or outbox steps | Durable orchestration truth | Process-local cache is treated as authority | PostgreSQL stores assignments, execution state, leases, fences, checkpoints, events, outbox; `recoverFromPostgres` | Restart at every transaction boundary reconstructs identical active/expired/pending sets without Valkey/files; N210-32..36, N230-07 | KBN-210, 230 | Recovery latency | Controlled after evidence |
| T24 | Dependency cycle or concurrent reciprocal edge | Readiness and dispatch safety | Two transactions each see an acyclic graph before inserting | Unique directed edge; no self-edge; serialized recursive cycle check; readiness evaluates all blockers | Self/duplicate/cycle and concurrent A→B/B→A tests; all predecessor property test; N100-32..35, N200-01/02 | KBN-100, 200, 230 | Very large DAG performance | Bounded operational residual |
| T25 | Parent-task cycle or project-incongruent relation | Planning hierarchy | Valid same-workspace IDs are arranged into an invalid tree | Project-congruent composites; serialized parent-cycle/orphan validation required by REQ-PLAN-001 | Self/indirect parent cycle, orphan, and cross-project mission/milestone/parent tests; N100-06..10 | KBN-100, 110 | Cycle validation is service/transaction enforced | Controlled after evidence |
| T26 | Concurrent update, duplicate retry, or idempotency payload drift | Aggregate consistency | Two clients use same version/key with different payloads | Expected-version check; semantic event and outbox in same transaction; key returns prior immutable result only for identical command | One update wins; stale gets 409; duplicate identical returns prior; payload drift rejected; N110-50..54, N140-03 | KBN-105, 110, 140 | Long-lived clients face visible conflicts | Intentional user-visible residual |
| T27 | State/event/outbox partial commit | Audit and notification consistency | Separate transactions or exception after state write | One PostgreSQL transaction for state+semantic event+outbox | Failure injected after each insert rolls all three back; success revisions align; N110-55..58 | KBN-110, 140 | Outbox publication remains asynchronous | Controlled after evidence |
| T28 | Malicious/incorrect importer injects foreign workspace data or dispatchable work | Migration integrity | Source keys collide, lineage is absent, or importer has direct DB authority | Immutable source snapshots/checksums; one-way Gateway/migration-only port; workspace-safe idempotent modes; shadow records cannot dispatch | Foreign/malformed/duplicate/partial-resume/lineage checksum and no-dispatch tests; N300-01..08 | KBN-300, 330 | Source data may be semantically ambiguous | Quarantine and owner sign-off |
| T29 | Cutover leaves legacy writer or forward/reverse sync active | Sole-writer invariant | Credentials/processes survive switch or rollback is improvised | Writer inventory, freeze, final delta, Gateway switch, credential shutdown, no dual write; rollback authority changes after first DB mutation | Process/credential inventory; concurrent-writer assertion; before/after-mutation rollback rehearsal; N320-01..06, N330-01 | KBN-320, 330, 340 | Missed external automation | Owner-gated residual |
| T30 | Generated `TASKS.md`/`mission.json` is edited or parsed into DB | Canonical state | Current-main parser/writer remains reachable or file watcher imports changes | Generated non-authoritative header/IDs/time/revision; no production importer; regenerate/overwrite only | Static import search, tamper/regeneration, read-only permission, source-revision parity; N120-03..07, N140-04 | KBN-120, 140 | Humans may mistake snapshots for live data | Header and docs mitigate |
| T31 | N-1 compatibility copies legacy ambiguity into canonical authority | Data integrity | Nullable/global/current-main fields are guessed during backfill | Nullable-first expand; deterministic mapping or quarantine; checksums; no new-only status before switch; legacy fields retained | Production-shape, ambiguous owner/assignee, status shadow, JSON/config/digest, rollback tests; N100-36..44 | KBN-100 | Quarantined records require human decision | Controlled by signed reconciliation |
| T32 | Recovery posture claims durability not provided by mechanisms | Availability and audit retention | Shape-only validation or optimistic RPO is accepted | Normative validator; WAL/PITR/RPO/storage/high-assurance constraints; mechanism and restore evidence | Unknown/impossible/weakened configuration plus actual mechanism/restore tests; N115-02..08 | KBN-115 | Backup operator or storage compromise | Separate failure domain residual |
| T33 | Frozen DDL cannot create mission-scoped evidence/approval FKs | Tenant/evidence relational integrity | KBN-100 generates DDL from current contract | Intended workspace-aware mission FKs exist, but referenced `(workspace_id,id)` candidate key is absent | PostgreSQL migration test must fail before amendment; after amendment, empty/prod migration and cross-workspace FK tests must pass | Contract authority, then KBN-100 | None acceptable before schema release | **BLOCKER KBN010-SI-001** |
## 5. Constraint-impact matrix
| Impact ID | Required invariant | Frozen schema impact | API/transaction impact | Required evidence | Owner | Status |
| --------- | ------------------------------------------- | ------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------- | ------------------------------------------- | ------------------------------------- |
| CI-01 | Hard workspace tenancy and no oracle | `workspace_id`, workspace-aware unique/FKs on all canonical rows | Server-derived workspace; uniform denial on all surfaces | N100-01..14; N110-01..09; N130-01 | KBN-100/105/110/130 | Resolved by frozen controls |
| CI-02 | Active user membership | Membership row plus unique `(workspace_id,user_id)`; active state retained | Recheck active membership in same authoritative transaction | N100-03; N110-06/07 | KBN-100/110 | Resolved; not FK-only |
| CI-03 | Service identity least privilege/revocation | Agent/session workspace, lifecycle, state, roles, capabilities | Token maps to exact agent/session; command-family allowlist; DB recheck; no admin/raw DB fallback | N105-01; N110-10..13; N210-01/02 | KBN-105/110/210 | Resolved at auth/API layer |
| CI-04 | Project-congruent hierarchy | Composite project/mission/milestone/parent/current-milestone relations | Lock/serialized parent-cycle and orphan validation | N100-06..10 | KBN-100/110 | Resolved; cycle behavior required |
| CI-05 | Health-proof authority | Internal branded proof has transaction/time/policy fields | Probe and revalidate on same PG transaction; no public field | N105-02/03; N110-14..27 | KBN-105/110 | Resolved by frozen controls |
| CI-06 | Assignment/approval identity | Exactly-one principal/proposer, exact agent/session assignment, relational approval | Reload+lock all IDs; compare version/target/state/expiry/policy/decision | N100-15..18; N210-03..19 | KBN-100/210 | Resolved by frozen controls |
| CI-07 | Monotonic bigint fencing | Durable bigint counter, exact lease/fence keys, one active lease | Atomic increment/RETURNING; decimal-string DTO; reject every stale worker command | N100-19..23; N210-20..31 | KBN-100/105/210 | Resolved by frozen controls |
| CI-08 | Proposal event chain | Both workspace-aware event FKs; event table created first | Exact submission/acceptance semantic checks in one transaction | N100-24..26; N110-28..43 | KBN-100/110 | Resolved; semantic checks not FK-only |
| CI-09 | Immutable audit/evidence retention | RESTRICT parents; INSERT/SELECT-only immutable tables | Archive/cancel normal flow; separately authorized purge | N100-27..31; N115-01; N230-02/03 | KBN-100/115/230 | Resolved by frozen controls |
| CI-10 | DB/Valkey/outbox/restart semantics | PG outbox and durable orchestration rows | Fail closed; same-key uncertainty retry; Valkey reloads PG; restart from PG | N110-44..49; N140-01/02; N230-04..07 | KBN-110/210/230 | Resolved by frozen controls |
| CI-11 | DAG/race/idempotency/version | Unique edge; self check; event idempotency; aggregate versions | Serialized recursive cycle check; payload binding; expected-version conflict | N100-32..35; N110-50..58; N200-01/02 | KBN-100/110/200 | Resolved by frozen controls |
| CI-12 | Import/cutover trust boundary | Lineage/artifact/event fields; shadow state cannot dispatch | One-way scoped importer, freeze, no direct DB/file authority, no dual writer | N300-01..08; N320-01..06 | KBN-300/320/330 | Resolved by frozen controls |
| CI-13 | Generated-file no-import | No canonical file schema/import contract | Projection-only package; static reachability check removes current parser from production Kanban paths | N120-03..07; N140-04 | KBN-120/140 | Resolved by frozen controls |
| CI-14 | Mission-scoped artifact and approval FKs | **Missing unique candidate key `(workspace_id,id)` on `missionsV1` for two frozen composite FKs** | No API control can make invalid migration DDL creatable | Amendment plus empty/prod migration proof and foreign-workspace tests | Contract authority; KBN-100 after amendment | **UNRESOLVED / BLOCKER** |
## 6. Exact future negative-test catalog
These names are normative evidence identifiers for future slices. Equivalent test-file names are acceptable only if traceability retains these IDs and expected outcomes.
### KBN-100 — schema and migration
- **N100-01** reject every canonical child row whose `workspace_id` differs from its parent.
- **N100-02** reject foreign-workspace link, artifact, proposal target, dependency, assignment, lease, checkpoint, approval, and event relationships.
- **N100-03** reject an inactive/revoked member as accountable owner, proposer, decision actor, archive actor, or user principal in the authoritative command transaction.
- **N100-04** reject a team/project relation crossing workspaces.
- **N100-05** reject a team authorization path when the user lacks active membership in the team's workspace.
- **N100-06** reject task→mission project mismatch.
- **N100-07** reject task→milestone and project→current-milestone project mismatch.
- **N100-08** reject task→parent project mismatch and self-parent.
- **N100-09** reject indirect parent cycles under concurrent transactions.
- **N100-10** reject mission→milestone project mismatch/orphan.
- **N100-11** reject checkpoint artifact from another workspace.
- **N100-12** reject checkpoint artifact owned by another same-workspace task/mission unless an explicitly frozen evidence rule permits it.
- **N100-13** reject approval evidence from another workspace.
- **N100-14** reject same-workspace approval evidence unrelated to the approval target.
- **N100-15** reject zero/multiple assignment principals and zero/multiple proposers.
- **N100-16** reject target session without its exact target agent.
- **N100-17** reject assignment task/agent/session crossing workspaces.
- **N100-18** reject non-positive task version and expired assignment acquisition.
- **N100-19** concurrent lease insert permits one active lease and returns one winner.
- **N100-20** successive leases return strictly increasing bigint fences.
- **N100-21** reject checkpoint with another task, lease, or fence.
- **N100-22** reject duplicate/non-monotonic checkpoint sequence.
- **N100-23** reject evidence join for a mismatched checkpoint/task.
- **N100-24** proposal insert without exact submission event fails atomically.
- **N100-25** foreign/wrong-type/wrong-proposal submission event fails atomically.
- **N100-26** foreign/wrong-target/unrelated acceptance event fails atomically.
- **N100-27** application role cannot UPDATE/DELETE `task_events`.
- **N100-28** application role cannot UPDATE/DELETE checkpoints/artifacts/evidence joins.
- **N100-29** parent hard delete is RESTRICTed while audit/evidence children exist.
- **N100-30** archive does not alter canonical lifecycle status.
- **N100-31** purge without break-glass authority/evidence is denied.
- **N100-32** reject dependency self-edge and duplicate directed pair regardless of type.
- **N100-33** reject direct and indirect dependency cycles.
- **N100-34** concurrent reciprocal dependency inserts cannot both commit.
- **N100-35** readiness remains false until every blocking predecessor and completion condition passes.
- **N100-36** empty DB migration succeeds after the contract amendment.
- **N100-37** production-shape expand retains all legacy declarations.
- **N100-38** crash/resume backfill is idempotent and checksum-stable.
- **N100-39** ambiguous workspace/owner/assignee is quarantined, never guessed.
- **N100-40** no `ready`/`in_review` status is emitted to N-1 readers before switch.
- **N100-41** `mission_tasks.status` cannot remain a write source.
- **N100-42** tags/assignee/date/mission JSON/config/description/agent fields reconcile without loss.
- **N100-43** claimed fleet backlog rows are quarantined and imported rows cannot dispatch.
- **N100-44** pre-switch rollback works while post-first-mutation rollback requires freeze/reconciliation.
- **N100-45** before amendment, PostgreSQL rejects both mission composite FKs for lack of a matching `(workspace_id,id)` candidate key; after amendment, both DDL relations and foreign-workspace denials pass.
### KBN-105/KBN-110/KBN-120/KBN-130/KBN-140 — API and P1
- **N105-01** every route has an explicit user/service command-family policy; user/admin tokens cannot call service-only Coordinator mutations.
- **N105-02** public DTO validation rejects `writeProof`, internal context, body `workspaceId`, and caller-asserted health.
- **N105-03** fixture exhaustiveness prevents 503, 502/504/timeout, and 409 cross-mapping.
- **N105-04** approval DTO accepts an ID and decision command only, never approval proof-by-value.
- **N105-05** all fence fields accept/emit decimal strings and reject JSON numbers.
- **N110-01** listing with a foreign `workspaceId` or foreign filter ID follows the frozen no-oracle denial and returns no rows/counts/cursors.
- **N110-02** get by foreign or nonexistent aggregate ID has the same frozen denial shape and no foreign metadata.
- **N110-03** create/update/archive with a foreign owner, parent, project, mission, milestone, tag, or target ID is denied before mutation.
- **N110-04** dependency/proposal commands with foreign target IDs are denied with unchanged state/event/outbox counts.
- **N110-05** REST, MCP, WebSocket, and internal Coordinator paths produce equivalent no-oracle behavior for the same foreign ID.
- **N110-06** a revoked/inactive owner is denied even with a still-valid Better Auth session.
- **N110-07** stale membership/team cache cannot authorize a proposer, decision actor, archive actor, or principal after revocation.
- **N110-08** a team ID from another workspace cannot authorize or own the command target.
- **N110-09** same-workspace but wrong-project mission/milestone/parent IDs are denied inside the transaction.
- **N110-10** an expired service token is denied before repository access.
- **N110-11** an audience- or workspace-mismatched service token is denied without an existence oracle.
- **N110-12** an over-scoped service token cannot call a command family absent from its role/capability allowlist.
- **N110-13** disabled agent or ended session revokes service-token command authority immediately on PostgreSQL recheck.
- **N110-14** contradictory public health state/boolean combinations fail validation.
- **N110-15** Valkey-only liveness cannot mint or substitute a PostgreSQL write proof.
- **N110-16** caller-forged public `healthy` cannot enter internal mutation context.
- **N110-17** public REST/MCP/CLI bodies containing health/proof fields are rejected.
- **N110-18** an expired internal proof produces no state/event/outbox write.
- **N110-19** a future-dated or not-yet-valid proof produces no write.
- **N110-20** a policy-revision-mismatched proof produces no write.
- **N110-21** a proof minted on another transaction/connection produces no write.
- **N110-22** a proof that expires before the final pre-mutation check produces no write.
- **N110-23** deliberate read-only/write-unavailable denial maps only to authoritative 503/not-applied/non-retryable.
- **N110-24** timeout before commit maps to transport-unknown and permits only same-key retry.
- **N110-25** timeout after commit maps to transport-unknown and same-key retry returns the committed canonical result once.
- **N110-26** expected-version mismatch maps only to 409/not-applied/non-retryable.
- **N110-27** recovery replay with a changed idempotency key cannot masquerade as the original uncertain request.
- **N110-28** pending proposal cannot alter target fields/status/rank/version.
- **N110-29** rejected proposal cannot affect readiness, dependencies, or gates.
- **N110-30** pending/rejected proposal cannot create an assignment or lease.
- **N110-31** direct proposal-row state manipulation cannot bypass normal command execution.
- **N110-32** proposal submission without a submission event rolls back fully.
- **N110-33** foreign-workspace submission event rolls back fully.
- **N110-34** wrong aggregate/event type submission event rolls back fully.
- **N110-35** same-workspace event for another proposal rolls back fully.
- **N110-36** submission event with wrong previous/new version semantics rolls back fully.
- **N110-37** foreign-workspace acceptance event rolls back proposal, target, event, and outbox.
- **N110-38** same-workspace event for another target aggregate rolls back acceptance.
- **N110-39** event from an unrelated normal command rolls back acceptance.
- **N110-40** event caused by a different submission event rolls back acceptance.
- **N110-41** event whose payload lacks or changes `changeProposalId` rolls back acceptance.
- **N110-42** event for another proposal with the same target/command rolls back acceptance.
- **N110-43** missing accepted-command event after target handling rolls back the entire transaction.
- **N110-44** read-only-degraded denial changes no DB row/outbox/file/Valkey/provider state.
- **N110-45** write-unavailable denial changes no DB row/outbox/file/Valkey/provider state.
- **N110-46** PostgreSQL disconnect cannot redirect a command to any fallback writer.
- **N110-47** commit uncertainty remains `unknown` and never becomes a fabricated 503/not-applied result.
- **N110-48** same-key replay after recovery returns one canonical result with no duplicate event/outbox row.
- **N110-49** Valkey publication failure leaves committed PG outbox pending and replayable.
- **N110-50** two same-version updates produce one winner and one visible 409 loser.
- **N110-51** identical duplicate key+payload returns the prior immutable result without another event/outbox row.
- **N110-52** same key with payload/command drift is rejected as an idempotency conflict.
- **N110-53** the same key in another workspace cannot reveal or reuse the first workspace's result.
- **N110-54** stale reconnect/update cannot silently overwrite a newer aggregate revision.
- **N110-55** failure after state write but before semantic event rolls back state.
- **N110-56** failure after semantic event but before outbox rolls back state and event.
- **N110-57** failure after outbox insert but before commit rolls back state, event, and outbox.
- **N110-58** success commits matching aggregate/event/outbox revisions and correlation/causation.
- **N120-01** CLI never retries an authoritative 503 deliberate denial.
- **N120-02** CLI retries only transport-unknown outcomes and preserves the exact idempotency key.
- **N120-03** generated projection header contains non-authoritative warning, workspace/project IDs, generated time, and source revision.
- **N120-04** projection revision and records match the API snapshot revision exactly.
- **N120-05** hand-tampering is overwritten or rejected by regeneration and never mutates PostgreSQL.
- **N120-06** static/runtime reachability finds no parser/import path from `TASKS.md`, `mission.json`, or another export.
- **N120-07** projection writer has no domain mutation/raw SQL/Valkey authority.
- **N130-01** UI foreign/no-access/not-found state follows the frozen no-oracle response and renders no stale foreign data.
- **N140-01** real-Gateway DB fault journey proves fail-closed no-fallback behavior.
- **N140-02** real-Gateway Valkey-loss journey proves pending outbox replay.
- **N140-03** real-Gateway concurrent update/retry journey proves version and idempotency semantics.
- **N140-04** generated-file tamper journey proves projection parity and no import.
### KBN-115/KBN-200/KBN-210/KBN-230 — recovery and coordination
- **N115-01** retention purge without current break-glass authority, reason, immutable evidence, or bounded scope is denied and audited.
- **N115-02** recovery posture with an unknown top-level or storage field is rejected.
- **N115-03** PITR retention without WAL archival is rejected.
- **N115-04** WAL archival with zero PITR retention is rejected.
- **N115-05** claimed RPO better than the configured backup/WAL mechanism is rejected.
- **N115-06** unencrypted, optional, or same-failure-domain storage is rejected.
- **N115-07** weakened high-assurance values are rejected.
- **N115-08** shape-only validation cannot pass without normative mechanism and restore evidence.
- **N200-01** cyclic/incomplete dependency snapshots never become eligible.
- **N200-02** identical immutable snapshot+policy+time returns identical ordering and explanation with no I/O/model import.
- **N210-01** disabled agent cannot claim, ack, heartbeat, checkpoint, or submit review.
- **N210-02** ended/offline/mismatched session cannot claim, ack, heartbeat, checkpoint, or submit review.
- **N210-03** foreign-workspace task is rejected after lock/reload without an oracle.
- **N210-04** stale task version is rejected before fence increment.
- **N210-05** assignment target agent mismatch is rejected.
- **N210-06** target session mismatch is rejected.
- **N210-07** expired assignment is rejected.
- **N210-08** assignment in rejected/released/expired/superseded/leased-invalid state is rejected.
- **N210-09** missing approval is rejected.
- **N210-10** rejected/escalated/requested approval is rejected as approval authority.
- **N210-11** stale policy-revision approval is rejected.
- **N210-12** foreign-workspace approval is rejected without an oracle.
- **N210-13** approval for another assignment is rejected.
- **N210-14** author self-approval/review is rejected when independence is required.
- **N210-15** foreign-workspace artifact evidence is rejected.
- **N210-16** same-workspace artifact unrelated to the assignment/task/gate is rejected.
- **N210-17** concurrent policy revocation versus acquire cannot produce a lease under the revoked revision.
- **N210-18** concurrent assignment expiry versus acquire cannot produce a lease after expiry.
- **N210-19** concurrent session end versus acquire cannot produce a lease for the ended session.
- **N210-20** lower fencing token is rejected without writes.
- **N210-21** token from an older lease is rejected without writes.
- **N210-22** token paired with another task is rejected without writes.
- **N210-23** token paired with another session is rejected without writes.
- **N210-24** token on an expired/revoked/released lease is rejected without writes.
- **N210-25** fences above JavaScript safe integer round-trip exactly as decimal strings.
- **N210-26** lease task does not match assignment task and is rejected.
- **N210-27** lease agent/session does not match assignment target and is rejected.
- **N210-28** checkpoint task does not match lease task and is rejected.
- **N210-29** checkpoint fence does not match exact lease fence and is rejected.
- **N210-30** checkpoint sequence duplicate/regression is rejected.
- **N210-31** checkpoint artifact does not match workspace/task/evidence semantics and is rejected.
- **N210-32** restart after assignment persistence reconstructs the pending assignment.
- **N210-33** restart after lease commit reconstructs exact active lease and fence.
- **N210-34** restart after checkpoint commit reconstructs checkpoint/recovery state.
- **N210-35** restart during expiry/retry/quarantine reconstructs durable disposition and eligibility.
- **N210-36** restart with pending outbox reconstructs publication work without Valkey/files.
- **N230-01** author=self-review and missing mandatory SecReview cannot certify or complete.
- **N230-02** normal application role cannot execute retention purge.
- **N230-03** break-glass purge cannot delete or alter its own authorization/evidence chain.
- **N230-04** Valkey down leaves canonical work in PostgreSQL/outbox.
- **N230-05** duplicate wake produces one logical effect after PostgreSQL reload/idempotency.
- **N230-06** stale wake cannot revive an expired/revoked assignment or lease.
- **N230-07** restart with no Valkey/files reconstructs leases/retry/quarantine/outbox exactly.
### KBN-300/KBN-320/KBN-330/KBN-340 — migration and cutover
- **N300-01** source record targeting another workspace is denied/quarantined without an oracle.
- **N300-02** malformed source record is rejected with attributable reject evidence.
- **N300-03** duplicate source system/key/batch replay is idempotent.
- **N300-04** source snapshot/checksum drift aborts apply/verify.
- **N300-05** partial import resumes from durable lineage without duplicating state/events.
- **N300-06** imported shadow record cannot become ready, assigned, or leased automatically.
- **N300-07** missing source key/file/checksum/batch lineage prevents apply/sign-off.
- **N300-08** importer cannot use direct DB, generated file, Valkey, or provider issue as canonical write authority.
- **N320-01** cutover without a verified write freeze fails safe.
- **N320-02** active legacy writer process or credential blocks cutover.
- **N320-03** reverse and forward synchronization cannot run concurrently.
- **N320-04** failed final delta/reconciliation blocks client switch.
- **N320-05** rollback before first canonical DB mutation may switch authority back only after freeze assertion.
- **N320-06** rollback after first canonical mutation requires freeze, DB-delta export/reconciliation, and owner decision.
- **N330-01** rehearsal cannot sign off while counts/checksums/exceptions/writer inventory differ.
- **N340-01** cutover cannot proceed without owner authorization, terminal evidence, scoped identities, and zero active legacy writers.
## 7. Requirements traceability
| Requirement | Threats/impacts | Planned evidence |
| ---------------- | ---------------------------- | --------------------------------------------------------------- |
| REQ-SOT-001 | T16, T21, T22, T27, T29, T30 | N110-28..31, N110-44..49, N110-55..58, N120-03..07, N320-01..06 |
| REQ-SOT-002 | T07, T08, T09, T21 | N105-02/03, N110-14..27, N110-44..48 |
| REQ-SOT-003 | T30 | N120-03..07, N140-04 |
| REQ-SOT-004 | T16..18 | N100-24..26, N110-28..43 |
| REQ-TEN-001 | T01..05, T15, T33 | N100-01..14, N110-01..09, N210-15/16, N100-45 |
| REQ-ID-001 | T02, T03, T06, T10..12 | N105-01, N110-06..13, N210-01..19 |
| REQ-PLAN-001 | T04, T25 | N100-06..10 |
| REQ-TASK-001 | T13, T26, T31 | N100-20, N100-37..42, N110-50..54 |
| REQ-TASK-002 | T16, T24 | N110-28..31, N100-35, N200-01 |
| REQ-DEP-001 | T24 | N100-32..35, N200-01 |
| REQ-ASN-001 | T10..12 | N100-15..18, N210-03..19 |
| REQ-AUD-001 | T17..20, T22, T27 | N100-24..31, N110-32..43, N110-49, N110-55..58 |
| REQ-API-001 | T01, T06..18, T26 | N105-01..05 plus KBN-110 catalog |
| REQ-UI-002/003 | T01, T15, T26 | N130-01 and real-Gateway KBN-140 journeys |
| REQ-COORD-001 | T22..24 | N200-01/02, N210-32..36 |
| REQ-COORD-002 | T10..12, T16 | N210-03..19, N110-28..31 |
| REQ-COORD-003 | T13..15, T23 | N100-19..23, N210-20..36 |
| REQ-COORD-004 | T23, T26 | N210-32..36, N230-07 |
| REQ-GATE-001/002 | T11, T19, T20 | N210-09..14, N230-01..03 |
| REQ-REC-001 | T20, T32 | N115-01..08 |
| REQ-MIG-001/002 | T28, T29, T31 | N100-37..44, N300-01..08, N320-01..06, N330-01, N340-01 |
REQ-UI-001 and REQ-UI-004 are downstream functional/accessibility requirements rather than schema-threat controls; they remain owned by KBN-130/KBN-140. Their security-relevant tenancy, conflict, and stale-reconnect portions are covered above.
## 8. Issue #753 acceptance mapping
| Issue requirement/criterion | Evidence in this document | Result |
| --------------------------------------------------------------- | ----------------------------------------------- | ------------------------- |
| Cross-workspace owners, principals, evidence, project hierarchy | T01T05, T15, T25; CI-0104 | Mapped |
| Active membership and service-token boundaries | Authorization matrix; T02, T03, T06; CI-02/03 | Mapped |
| Stale/forged health and transaction-local proof | T07T09, T21; CI-05 | Mapped |
| Assignment/approval forgery and monotonic fencing | T10T15; CI-06/07 | Mapped |
| Change-proposal abuse and event binding | T16T18; CI-08 | Mapped |
| Immutable audit and break-glass | T19/T20; CI-09 | Mapped |
| PostgreSQL/Valkey failures | T21T23; CI-10 | Mapped |
| Dependency/idempotency/version races | T24T27; CI-11 | Mapped |
| Import/cutover and generated-file boundary | T28T31; CI-12/13 | Mapped |
| Every schema/API/test impact explicit | Constraint matrix and negative-test catalog | Mapped |
| No unresolved schema impact | CI-14 / KBN010-SI-001 | **Failed — blocker** |
| Independent SecReview | Must occur after contract-authority disposition | Pending; gate cannot pass |
## 9. UNRESOLVED SCHEMA IMPACTS
**KBN010-SI-001 — `missions(workspace_id,id)` is not a declared candidate key for two frozen composite foreign keys.**
Affected frozen declarations in `contracts/kanban-schema.v1.ts`:
- `missions_workspace_project_id_uidx` is `(workspace_id, project_id, id)`.
- `artifacts_workspace_mission_fk` references `(workspace_id, mission_id)``missions(workspace_id, id)`.
- `approval_decisions_workspace_mission_fk` references `(workspace_id, mission_id)``missions(workspace_id, id)`.
**Required disposition:** contract authority must amend/version the frozen schema, update this gate's frozen-input digest/reference, and obtain independent schema/SecReview. KBN-100 remains held. No worker may silently add an index or alter child keys during implementation.
## 10. Residual risk and handoff
- Even after schema amendment, active membership, polymorphic targets, same-task evidence semantics, parent/DAG cycle checks, token scope, and no-oracle behavior depend on authoritative transaction code and must not be treated as FK-only guarantees.
- DB superuser and break-glass compromise cannot be eliminated by application constraints; separation of duties, immutable external backup/audit evidence, drills, and monitoring remain required.
- PostgreSQL unavailability intentionally sacrifices writes for integrity. Transport-unknown outcomes remain safe only when clients preserve the exact idempotency key.
- Imported ambiguous records remain quarantined until owner sign-off; no automated mapping may convert ambiguity into authority.
**Handoff status:** BLOCKED. Contract authority action is required before independent SecReview can return PASS and before KBN-100 is released.

View File

@@ -0,0 +1,195 @@
# Mission Manifest — Mosaic Native Kanban and Canonical Task SOT P0P3
**Mission status:** CANON INDEPENDENTLY APPROVED; publication in progress under issue [#751](https://git.mosaicstack.dev/mosaicstack/stack/issues/751)
**Date:** 2026-07-14
**Human decision owner:** Jason
**Orchestrator/publication owner:** web1 control plane (`mos-claude`; `mosaic-100` acting during Claude quota outage)
**Execution topology:** USC web1, partitioned across collision-free GPT coder2/3/4/5 lanes
**Canonical requirements:** [`../requirements/native-kanban-sot.md`](../requirements/native-kanban-sot.md)
**Frozen integration contract:** `SHARED-CONTRACT.md` and `contracts/*.v1.ts`
## 1. Mission statement
Extend current `mosaicstack/stack` main into the sole native control plane for workspace-scoped project, mission, milestone, task, dependency, assignment, lease, approval, evidence, and audit state. First deliver a thin writable Kanban/List vertical slice; then add deterministic mechanical coordination and execute a one-way migration/cutover from jarvis-brain/Vikunja project/task stores.
Success means every user, agent, orchestrator, specialist, and UI sees and mutates the same PostgreSQL aggregate revisions through typed Gateway commands, with no writable fallback and no hidden second authority.
## 2. Scope boundaries
### In scope
- Current Drizzle/PostgreSQL schema extension and migrations.
- Workspace tenancy and authorization from the first migration.
- Projects, missions, milestones, tasks, normalized tags, dependencies, assignments, durable execution/quarantine state, links, immutable artifacts/evidence joins, outage change proposals, events, approvals, leases, checkpoints, and transactional outbox.
- NestJS Gateway queries and explicit lifecycle commands.
- MCP/CLI agent surfaces and generated read-only projections.
- Thin writable Next.js Tasks Kanban/List, task detail, minimal Projects CRUD, filters, dependency readiness, ownership/lease separation, and audit timeline.
- Non-LLM Mechanical Coordinator eligibility, proposal, approval-policy, lease/fence, heartbeat, retry, expiry, quarantine, and restart recovery.
- Planning, Enhance, Coder, Review, SecReview, PR-Monitor, and Certifier role/gate representation.
- One-way shadow importer, reconciliation, write freeze, final delta, cutover, rollback package, and legacy read-only stabilization.
- Recovery-posture configuration and health-state/fail-closed contract.
### Out of scope
- Greenfield services, Prisma runtime revival, or jarvis-brain flat files as runtime storage.
- Writable Markdown/JSON/Valkey/browser/provider fallback.
- Gitea issue/PR replacement or generic bidirectional provider sync.
- Calendar, email, GLPI cache, CRM, billing, time tracking, personal-brain migration.
- LLM scheduling or scope interpretation by the Coordinator.
- Autonomous gate waiver, certification, merge, release, deployment, or issue closure by Coordinator.
- Merge authority for Certifier.
- P4 full portfolio/mission designer and P5 fleet-scale policy unless separately released.
## 3. Fixed invariants
Every deployment MUST preserve all of the following:
1. PostgreSQL is the sole writable SOT.
2. Drizzle on current stack main is the only persistence foundation.
3. Mutations fail closed when DB write-health cannot be proven `healthy`.
4. No file, Valkey, browser, queue, provider, or human note becomes a fallback writer.
5. `TASKS.md`, `mission.json`, and every file export are generated, read-only, non-authoritative, and never import sources.
6. Human outage notes become attributable post-recovery proposals only.
7. Workspace is the hard tenant; Team is intra-workspace authorization.
8. Valkey is expendable; PostgreSQL owns state, leases, fencing, audit, and outbox.
9. Mechanical Coordinator is deterministic/non-LLM and cannot invent scope, waive gates, certify, or merge.
10. Certifier is the final independent quality gate and has no merge authority.
11. Mutations use idempotency and optimistic aggregate versions; worker commands also require a current fencing token.
12. Recovery tier changes only backup/recovery posture, never authority or gate semantics.
## 4. Configurable recovery posture
Deployments select Lite, Standard, or High-assurance defaults from [`../requirements/native-kanban-sot.md`](../requirements/native-kanban-sot.md) and `contracts/recovery-posture.v1.ts`. Configurable fields are limited to:
- backup/base-backup cadence;
- RPO and RTO targets;
- PITR retention;
- WAL archive cadence;
- restore-test frequency;
- break-glass drill frequency;
- encrypted off-cluster storage.
High-assurance defaults are fixed reference values: RPO 15 minutes, RTO 4 hours, encrypted off-cluster WAL every 5 minutes with 35-day PITR, daily base backup, monthly restore test, and quarterly break-glass drill.
## 5. Canonical role map
```text
User
↓ objectives, constraints, ratified decisions
Interaction Layer
↓ workspace/project context; no scheduling authority
Portfolio Orchestrator
↓ approved mission, cross-project priority/capacity
Project Sub-Orchestrator
↓ decomposition, DAG, acceptance, release, routing policy, overrides
Gateway
↓ authenticated/authorized typed commands
Project/Task Domain Services
↓ transactional state + semantic event + outbox
Mechanical Coordinator
↓ deterministic eligibility/proposal/lease/fence/retry/quarantine
Specialists
Planning → Enhance → Coder → Review → conditional SecReview → remediation
↓ complete evidence bundle
Certifier
↓ final pass/reject/escalate; NO merge authority
Project Sub-Orchestrator / control plane
↓ merge authority after all gates
Post-merge validation
```
### Authority table
| Role/layer | Owns | Explicitly cannot do |
| ------------------------ | ----------------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
| User | Objectives, constraints, Jason-owned decisions | Direct DB/file authority bypass |
| Interaction | Conversation and context resolution | Schedule, approve, lease, certify |
| Portfolio Orchestrator | Mission approval, cross-project priority/capacity/global holds | Implement or self-certify specialist work |
| Project Sub-Orchestrator | Task decomposition/DAG/acceptance, release to ready, routing policy, overrides, remediation, merge go-ahead | Bypass required independent gates |
| Gateway | Identity, tenancy, DTO validation, commands, state-machine enforcement | Accept file edits or client SQL as mutations |
| Domain services | Transactional business invariants, semantic events/outbox | Depend on Valkey/files for committed truth |
| Mechanical Coordinator | Eligibility, dependencies, proposal, approved routing, lease/fence, heartbeat, retry/quarantine | Invent/alter scope, waive gates, certify, merge |
| Specialists | Bounded planning/implementation/review artifacts under a task lease | Modify another lane's owned files or self-approve |
| Certifier | Final independent evidence/traceability/gate decision | Merge, close provider issue, release, waive policy |
## 6. Gate model
### Mandatory gates
1. Requirements/contract freeze before parallel implementation.
2. P0 schema/authority threat model and tenant isolation review.
3. Author and reviewer MUST be different principals/sessions.
4. Functional review validates requirements, endpoint registry, concurrency, and negative paths.
5. **Mandatory SecReview (`secrev`)** for any auth, authorization, tenant, service-token, secret, database schema/migration, data-integrity, import/cutover, audit, lease/fencing, recovery, or destructive-retirement surface.
6. Review findings enter bounded remediation owned by the implementation lane.
7. Raising reviewer re-verifies remediation.
8. Certifier performs the final independent evidence and traceability gate.
9. Merge authority remains with `mos-claude`/Project Sub-Orchestrator control plane after gates pass.
10. Post-merge CI and situational validation must be terminal green before closure.
### Gate outcomes
- **PASS:** evidence complete; next authority may proceed.
- **REJECT:** findings are explicit and route to remediation.
- **ESCALATE:** policy/owner decision required; no implicit waiver.
No role can transform a missing gate into a warning by changing status, editing a projection, or writing Valkey.
## 7. Slice ownership rules
1. USC web1 is the sole execution environment; coder2/3/4/5 are independent bounded lanes under Mos.
2. Every slice has one named file-tree owner and an explicit IN/OUT boundary in `TASKS.md`.
3. Two active slices MUST NOT edit the same source file, migration file, generated snapshot, lockfile, or API contract.
4. coder2 exclusively owns `packages/db/src/schema.ts`, `packages/db/drizzle/**`, migration journal/meta/tests, then its disjoint recovery-parser/runbook slice. All schema requests serialize through coder2.
5. Frozen `contracts/*.v1.ts` are read-only inputs during implementation. Contract changes require Mos approval, a version bump/amendment, and coordinated rebase before work resumes.
6. coder3 exclusively owns Gateway DTO/controllers/services and the enumerated `apps/gateway/src/mcp/**` server files. coder4 owns CLI/projection clients and never edits MCP server files. Web consumers use the exact KBN-105 endpoint/DTO freeze.
7. coder4 executes one lane order: CLI/projection → pure Coordinator → importer → cutover. The pure Coordinator under `packages/coord` does not load IDs or access DB, Gateway, Valkey, recovery I/O, or web files; coder3 owns the persistence/service adapter.
8. Migration/import tooling calls Gateway/migration-only approved ports and does not add a second database model.
9. Each lane commits only its owned files and reports any needed cross-slice change as a contract-change request instead of editing another lane's tree.
10. Cross-review is mandatory: no lane reviews its own changes. Recommended ring is coder2 ← coder5, coder3 ← coder2, coder4 ← coder3, coder5 ← coder4, followed by independent SecReview where triggered and Certifier final.
11. Integration-only edits are a separate serialized slice after component lanes are green; no opportunistic merge-conflict resolution may alter semantics.
## 8. Delivery phases and exit gates
### P0 — Canon and authority foundation
- Publish this canon, frozen schema/ports/health/recovery contracts, threat model, authorization matrix, exact endpoint/DTO registry, concrete current-main field-by-field migration map, and standards amendment.
- Build hold remains active until independent author≠reviewer re-review returns GO on health proof/failures, approval binding, fencing, tenant relationships, proposals, migration map, slice ordering/API freeze, recovery validation, and vocabulary alignment.
- Exit: no unresolved second writer or contract blocker, tenant boundary frozen, all seven decisions traceable, and independent re-review GO recorded.
### P1 — Thin native MVP
- Schema/migration, tenant-safe Gateway, CLI/MCP/projection, writable Kanban/List/Projects, dependencies/readiness/audit.
- Exit: same revision across web/CLI/MCP/projection; cross-workspace tests fail closed; generated files cannot mutate state.
### P2 — Mechanical coordination
- Agent/session registry, deterministic engine, approval queue, PostgreSQL leases/fencing/checkpoints/outbox, retry/quarantine, operations UI.
- Exit: one lease winner, stale tokens rejected, dependencies/approvals enforced, DB/Valkey fault semantics proven, Certifier gate has no merge authority.
### P3 — Shadow migration and cutover
- Importer, lineage, reconciliation, reviewer UI, write freeze, final delta, Gateway switch, legacy read-only, stabilization and rollback package.
- Exit: signed reconciliation, zero active legacy writers, scoped Gateway identities, imported backlog cannot dispatch accidentally.
## 9. Evidence required for mission closure
- Requirement-to-test/evidence matrix.
- Schema/migration and N-1 rolling-deploy proof.
- Cross-workspace API/repository/import/Coordinator negative tests.
- Health-state and fail-closed fault injection.
- Valkey-loss/outbox replay and Coordinator restart tests.
- Concurrent lease and stale fencing tests.
- Endpoint-registry alignment across web/CLI/MCP/Gateway.
- Accessible real-Gateway Kanban journeys.
- Generated projection tamper/no-import proof.
- One-way migration dry-run/apply/verify and field reconciliation.
- Author-independent functional review and required SecReview.
- Certifier final decision and evidence bundle.
- Merged main SHA, terminal green CI, closed linked task/issue, and post-merge situational validation under orchestrator ownership.
## 10. Change control
This manifest is derived from the ratified source plan. Any change to SOT authority, workspace tenancy, fixed statuses, Coordinator/Certifier authority, health-state semantics, schema v1, migration direction, or recovery-tier field set is a contract change. Contract changes require Jason/Mos authorization and cannot be inferred by an implementation lane.
No coder lane may start while the build hold is active. KBN-010 must complete before KBN-100; KBN-105 exact endpoint/DTO freeze must complete before any API consumer implementation.

View File

@@ -0,0 +1,219 @@
# Native Kanban/SOT — Remediated Shared Contract v1
**Status:** INDEPENDENT REVIEW GO; freezes as v1 when issue #751 canon merges to `main`
**Version:** 1.0.0-rc.3
**Date:** 2026-07-14
**Change authority:** Mosaic control plane/Jason only
## 1. Authority
Concrete contracts are the four `contracts/*.v1.ts` files. PostgreSQL/current-main Drizzle is the sole writable SOT. Public health, Valkey, files, exports, providers, browser state, and outage notes cannot authorize/reconstruct writes. Mechanical Coordinator is non-LLM with no scope/gate/certification/merge authority. Certifier is final independent gate with no merge authority. No feature lane starts until this canon merges and the KBN-010/KBN-105 prerequisites are satisfied.
## 2. Health proof and exact failures
`KanbanHealthResponseV1` is a discriminated union:
| State | read | write | Capability |
| -------------------- | ----: | ----: | --------------------------------------------------- |
| `healthy` | true | true | reads; public state still cannot authorize mutation |
| `read-only-degraded` | true | false | reads only |
| `write-unavailable` | false | false | diagnostics only |
Every response has `checkedAt`, `validUntil`, `policyRevision`; contradictory booleans fail validation.
For a mutation, Gateway opens the PostgreSQL transaction, executes the live write probe on that transaction/connection, mints the internal branded `PostgresWriteHealthProofV1`, and revalidates time/policy/transaction identity immediately before mutation. Public REST/MCP/CLI DTOs never accept health/proof fields. Valkey/caller assertions cannot mint proof. Pure Coordinator takes `KanbanEvaluationContextV1`; persistence takes `InternalKanbanMutationContextV1` or probes internally.
| Case | HTTP | Frozen result | Retry |
| ---------------------------- | --------------------------: | ------------------------------------------------------------------- | -------------------- |
| degraded write | 503 | `KANBAN_WRITE_HEALTH_UNPROVEN`, `read-only-degraded`, `not_applied` | false |
| write unavailable | 503 | `KANBAN_WRITE_UNAVAILABLE`, `write-unavailable`, `not_applied` | false |
| version conflict | 409 | `AGGREGATE_VERSION_CONFLICT`, actual version, `not_applied` | false |
| timeout/unreachable | timeout/502/504 | `retryable_transport_error`, `unknown` | same idempotency key |
| stale fence/session/approval | coordinator rejection union | `not_applied` | false |
Required negatives: contradictory state, expired/policy-mismatched/wrong-transaction proof, Valkey-only health, forged healthy, and exhaustive non-cross-mapping of 503 vs 502/504/timeout vs 409.
## 3. Canonical schema invariants
Complete declaration: `contracts/kanban-schema.v1.ts`.
- Tables: tenant/identity (`workspaces`, members, teams/members, agents/sessions); planning (`projects`, `milestones`, current-milestone join, `missions`, mission-milestones, `tasks`, normalized tags, dependencies); orchestration (`task_assignments`, durable execution state, leases, checkpoints/evidence); governance (`change_proposals`, immutable artifacts/evidence, events, approvals, outbox, external links).
- Task statuses: `backlog | ready | in_progress | blocked | in_review | done | cancelled`.
- Assignment states everywhere: `awaiting_approval | policy_pre_authorized | approved | rejected | leased | released | expired | superseded`.
- Specialist roles everywhere: `planning | enhance | coder | review | security-review | pr-monitor | certifier`.
- Owner uses exactly-one user/team; assignment principal exactly-one user/team/agent; users require active membership; agent/session and all evidence are workspace-bound.
- Task→mission/milestone/parent, mission→milestone, and project→current-milestone are project-congruent composite relations.
- Dependency identity is workspace+predecessor+successor independent of type.
- Approval evidence and checkpoint evidence are workspace-scoped joins to immutable artifacts, never JSON ID arrays.
- Proposal audit links are composite relations: `(workspace_id, submitted_audit_event_id)` and `(workspace_id, accepted_command_audit_event_id)` reference `task_events(workspace_id, id)` with RESTRICT deletion.
- Assignment is persisted with task/version, exact target/session, expiry/state/policy/proposer/reason. Approval relates to assignment. Lease acquisition accepts IDs, then reloads/locks and validates every relation.
- `tasks.fencing_counter` is bigint; locked atomic increment/RETURNING creates a decimal-string lease token. Lease/checkpoint composites bind exact workspace+task+assignment/session+fence.
- `task_execution_states` durably records retry/quarantine/exhaustion.
- Tags are normalized; legacy `tasks.tags` remains through N-1. Archive is explicit actor/reason/time and does not change lifecycle.
- Canonical parents use RESTRICT. Events/checkpoints/artifacts/evidence are INSERT/SELECT-only for application roles. Normal flow archives/cancels; purge is audited break-glass retention work.
## 4. Outage proposal contract
`change_proposals` stores workspace, active-member proposer, source-note digest, target/version, typed command/payload, idempotency, lifecycle, decision actor/reason/time, proposal version, and submit/accepted event IDs. Both event IDs are workspace-aware composite foreign keys to `task_events(workspace_id, id)`; a bare UUID is never sufficient.
Submission preallocates the proposal ID. One transaction inserts `change_proposal.submitted` with the proposal workspace, `aggregate_type='change_proposal'`, `aggregate_id=<new proposal ID>`, `previous_version=NULL`, and `new_version=1`, then inserts the proposal referencing that event. Missing, foreign-workspace, wrong-type, or unrelated-proposal events abort the transaction.
Submit/list/get/accept/reject are explicit Gateway commands. Pending/rejected proposals are inert: no scheduling, dependency/gate satisfaction, or direct target mutation. Acceptance locks proposal+target, obtains fresh transaction-local proof, verifies pending/expected version, invokes the normal command handler, and atomically stores the emitted normal-command event ID. That event must share the proposal workspace, match `target_aggregate_type` and `target_aggregate_id`, use `causation_id=submitted_audit_event_id`, and carry `payload.changeProposalId=<locked proposal ID>`. Missing, foreign-workspace, unrelated-target, unrelated-proposal, or unrelated-command events abort acceptance.
## 5. Concrete current-main N-1 migration delta
**Inspected:** `origin/main:packages/db/src/schema.ts` at `e72388b2cbfe400842fe940fa6cabf984ed43711` (2026-07-13). It has global teams/no workspace keys, legacy project/mission/task statuses, nullable task project/mission, `tasks.assignee/tags/due_date`, mission JSON/config, duplicated `mission_tasks.status`, legacy agent fields, and separate fleet `backlog` claims.
Legacy columns remain declared in unified `schema.ts` for expand + full N-1/rollback window. Generation must not infer early drops.
### 5.1 Ordered phases
1. **Pre-expand:** N-1 patch stops `mission_tasks.status` as write source; inventory writers; backup/checksum.
2. **Expand:** add enums/tables and nullable-first columns; retain legacy declarations/uniques; emit no v1-only status.
3. **Backfill:** bootstrap workspace; bounded idempotent cursor/checksum batches; quarantine ambiguous rows.
4. **Validate:** no null tenant, cross-project link, ambiguous owner; status/tag/date/config retention; then constraints/NOT NULL.
5. **Compatibility:** N-1 reads legacy; same-DB transaction mirrors only unavoidable fields; never file/Valkey dual write.
6. **Switch:** stop N-1 writers; Gateway sole command boundary; enable canonical statuses.
7. **Contract release:** later release after rollback/N-1; remove compatibility/global uniques/legacy fields.
### 5.2 New audit/proposal DDL order
KBN-100 migration DDL must execute in this order:
1. create `task_events` and its unique `(workspace_id, id)` key;
2. create `change_proposals` with nullable acceptance-event ID and required submission-event ID;
3. add `change_proposals_workspace_submitted_event_fk` from `(workspace_id, submitted_audit_event_id)` to `task_events(workspace_id, id)` with `ON DELETE RESTRICT`;
4. add `change_proposals_workspace_accepted_command_event_fk` from `(workspace_id, accepted_command_audit_event_id)` to the same composite key with `ON DELETE RESTRICT`;
5. install application-role immutability privileges and same-transaction semantic validation before enabling proposal commands.
The submission transaction inserts the event first using a preallocated proposal UUID, then the proposal. Acceptance inserts the normal command event before updating the locked proposal. Neither FK is omitted or replaced by a bare UUID/index check.
### 5.3 Field map
| Current | Expand/backfill | N-1 compatibility | Switch/contract |
| ---------------------------------------------- | -------------------------------------------------------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------- |
| global `teams`, `team_members` | add workspace nullable; bootstrap; validate active owners | retain global slug/FKs | workspace composites; global unique contracts later |
| `projects.status` | add `canonical_status`; map active/paused/completed/archived | mirror representable values; no `planning` | canonical authority; legacy contracts later |
| project `owner_id/team_id/owner_type` | add exact accountable user/team; deterministic map or quarantine | preserve old reads and compare drift | canonical exact-one; remove legacy after parity |
| current milestone | create milestones then join table (no circular DDL) | absent to N-1 | join is authority |
| nullable `missions.project_id` | derive workspace/project; null/orphan exception, never guess | keep nullable legacy read | canonical required; validate/set NOT NULL later |
| mission `description` | add objective; preserve description; reviewed nonblank mapping | N-1 description | objective authority; retain until signed review |
| `missions.status` | add canonical; planning→draft, active/paused/completed/failed same | no new-only statuses emitted | canonical authority |
| mission `milestones` JSON | normalize with source digest; preserve malformed/original | N-1 reads JSON; no reverse sync | normalized authority; JSON removed after checksum sign-off |
| mission config/metadata/phase/user | retain all; map known typed policy only | all remain declared | remove only by signed consumer inventory |
| nullable `tasks.project_id` | derive explicit/mission project; orphan quarantine | retain nullable read/write during compatibility | canonical required; NOT NULL later |
| `tasks.mission_id` | add project-congruent composite | old relation readable | composite authority |
| `tasks.status` | canonical: not-started→backlog, in-progress→in_progress, others same | no ready/in_review emission | canonical authority |
| `tasks.assignee` | deterministic active user/team/agent assignment; raw value preserved if ambiguous | mirror text only if unambiguous | canonical owner/assignment; remove after no-loss sign-off |
| `tasks.tags` JSON | normalize trim/case/dedupe with original digest | transactionally mirror normalized rows | normalized authority; JSON later removed |
| `tasks.due_date` | copy exactly to `due_at` | mirror | due_at authority; legacy later |
| task common fields | preserve metadata byte-for-byte; add criteria/rank/retry/archive/version/fence | old reads valid | new fields canonical |
| `mission_tasks.status` | keep; prohibit as write source; linked status ignored; unlinked becomes task or reject | read-only compatibility value | membership uses task mission; status dropped after no readers |
| mission-task notes/PR/user | map to metadata/artifact/event/link/attribution; preserve | read-only | remove after parity |
| `agents.status` | add workspace/lifecycle/runtime/roles; status remains presence | retain all legacy fields | lifecycle/roles authority; status may remain telemetry |
| agent project/owner/prompt/tools/skills/config | preserve; validate tenant; derive typed capabilities without loss | N-1 reads | removal only by separate inventory |
| fleet `backlog` | map to designated-project tasks; edges; claimed rows quarantine | freeze claims before switch; read-only compare | task/lease authority; retire after stabilization |
### 5.4 Required migration tests
Empty DB; exact production-shape snapshot; crash/resume; rollback before switch; N-1 startup/read/write; workspace/member negatives; status-shadow/no premature new status; `mission_tasks.status` write prohibition; tags/assignee/date/mission JSON/config/description/agent checksum; project congruence/current-milestone order; backlog freeze/no dispatch; and proof legacy declarations persist until contract release.
Proposal-specific negatives must attempt: missing submission event, foreign-workspace submission event, foreign-workspace acceptance event, same-workspace event for another proposal, event for another target aggregate, and unrelated normal-command event. Every attempt must fail atomically with no accepted proposal and no target mutation.
## 6. Ownership and Coordinator split
coder2 solely owns `packages/db/src/schema.ts`, `packages/db/drizzle/**`, journal/metadata, and migration tests. No other lane generates migrations. Expand is additive; no drop/rename/narrow; constraints validate before NOT NULL; compatibility is same-DB only; contract is later.
KBN-200/coder4 owns pure `MechanicalCoordinatorDecisionEngineV1`: complete immutable snapshots in, deterministic eligibility/proposal/retry decisions out; no ID loading, SQL, Gateway, Valkey, proof, persistence, restart I/O, or LLM.
KBN-210/coder3 owns `MechanicalCoordinatorServicePortV1`: ID loading, locks, fresh proof, assignment/approval persistence, atomic fencing, lease/checkpoint/outbox, Valkey wakes, durable retry/quarantine, and `recoverFromPostgres`. Cycle: load snapshots → pure decision → persist assignment → authoritative approval/policy → acquire by IDs/locks → increment fence → lease → ack/heartbeat/checkpoint → submit to review or durable retry/quarantine. No completion/certification/merge method exists.
## 7. Exact Gateway/DTO freeze for KBN-105
### 7.1 Common wire rules
Base is `/api/v1/workspaces/:workspaceId`. Mutations require header `Idempotency-Key` (1128 chars). Existing-aggregate mutations also require `If-Match-Version` (positive integer); create and privileged assignment-cycle requests are the only exceptions, while proposal submission carries `expectedTargetVersion` in its body. Body workspace fields are forbidden. Tenant denial follows one 404/403 policy without foreign existence detail.
```ts
interface SuccessEnvelopeV1<T> {
contractVersion: '1.0.0';
data: T;
aggregateRevision: string;
correlationId: string;
}
interface ListEnvelopeV1<T> extends SuccessEnvelopeV1<T[]> {
page: { cursor: string | null; nextCursor: string | null; limit: number };
}
```
Errors are the exact health/transport/version unions in §2 plus validation/auth/not-found. Public DTOs never expose/accept internal write proof.
### 7.2 Exact route registry
| Method/path | Request body/query | Success data |
| ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `GET /kanban-health` | none | `KanbanHealthResponseV1` |
| `GET /projects` | `status,ownerUserId,ownerTeamId,cursor,limit` | project list |
| `POST /projects` | `name,key,description,status,priority,ownerUserId XOR ownerTeamId,metadata` | project |
| `GET /projects/:projectId` | none | project |
| `PATCH /projects/:projectId` | editable create fields + expected header | project |
| `POST /projects/:projectId/archive` | `reason` | project |
| `GET /tasks` | `projectId,missionId,milestoneId,status,priority,ownerUserId,ownerTeamId,specialistRole,tag,dueState,archived,cursor,limit` | task summary list |
| `POST /tasks` | `projectId,missionId?,milestoneId?,parentTaskId?,title,description?,acceptanceCriteria[],status,priority,rank,ownerUserId XOR ownerTeamId,specialistRole?,dueAt?,notBeforeAt?,estimateMinutes?,retryPolicy?,tagIds[],metadata` | task detail |
| `GET /tasks/:taskId` | none | task detail including readiness/dependencies/assignment/lease/events |
| `PATCH /tasks/:taskId` | editable non-transition fields | task detail |
| `POST /tasks/:taskId/transition` | `toStatus,reason?` | task detail |
| `POST /tasks/:taskId/move` | `toStatus?,beforeTaskId?,afterTaskId?` | task detail with persisted rank |
| `POST /tasks/:taskId/archive` | `reason` | task detail |
| `PUT /tasks/:taskId/tags` | `tagIds[]` | task detail |
| `POST /tasks/:taskId/dependencies` | `predecessorTaskId,type` | dependency |
| `DELETE /tasks/:taskId/dependencies/:predecessorTaskId` | no body | deleted dependency ID |
| `GET /tasks/:taskId/events` | `cursor,limit` | event list |
| `GET /tags` | `query,cursor,limit` | tag list |
| `POST /tags` | `name,color?` | tag |
| `GET /change-proposals` | `state,targetType,targetId,cursor,limit` | proposal list |
| `POST /change-proposals` | `sourceNoteDigest,targetType,targetId,expectedTargetVersion,commandType,commandPayload` | inert proposal |
| `GET /change-proposals/:proposalId` | none | proposal |
| `POST /change-proposals/:proposalId/accept` | `reason` | proposal + normal command result |
| `POST /change-proposals/:proposalId/reject` | `reason` | proposal |
| `GET /coordinator/eligibility` | `projectId?,missionId?,cursor,limit` | `EligibilityDecisionV1[]` |
| `POST /coordinator/assignment-cycles` | `limit` | assignment proposals; privileged internal |
| `POST /coordinator/assignments/:assignmentId/approve` | `decision,reason,policyRevision,artifactIds[]` | approval decision |
| `POST /coordinator/leases/acquire` | `taskId,assignmentId,approvalDecisionId,targetSessionId,leaseTtlSeconds` | lease with decimal-string fence |
| `POST /coordinator/leases/:leaseId/ack` | `taskId,sessionId,fencingToken` | lease |
| `POST /coordinator/leases/:leaseId/heartbeat` | `taskId,sessionId,fencingToken,extendSeconds` | lease |
| `POST /coordinator/leases/:leaseId/checkpoints` | `taskId,sessionId,fencingToken,sequence,resumableSummary,artifactIds[],contextUsagePercent` | checkpoint |
| `POST /coordinator/leases/:leaseId/submit-review` | `taskId,sessionId,fencingToken,artifactIds[],summary` | task in `in_review` |
All Coordinator mutations except human approval are service-identity-only. Generic task PATCH cannot perform claim/heartbeat/checkpoint/review/certification/completion shortcuts. Completion after certification uses a separately gated lifecycle command owned by the Portfolio/Sub-Orchestrator flow, not the Coordinator.
### 7.3 DTO invariants
Task summary/detail use exact schema vocabularies, owner union, `version: number`, `fencingCounter: string`, explicit `archivedAt/by/reason`, normalized tags, computed readiness, and separate assignment/lease. Assignment DTO includes one persisted ID, task/version, exact principal/agent/session, role, state, expiry, policy, proposer/reason. Lease/checkpoint DTOs serialize every fence as decimal string. Proposal DTO exposes no hidden write authority.
### 7.4 MCP ownership and mapping
coder3 exclusively owns:
- `apps/gateway/src/mcp/mcp.dto.ts`
- `mcp.controller.ts`
- `mcp.service.ts`
- `mcp.module.ts`
- `mcp.tokens.ts`
- `mcp.service.spec.ts`
MCP tools are thin maps: `mosaic_projects_{list,get,create,update,archive}`, `mosaic_tasks_{list,get,create,update,transition,move,archive,set_tags,add_dependency,remove_dependency}`, and `mosaic_change_proposals_{list,get,submit,accept,reject}` to the exact routes above. coder4 owns CLI/projection clients only and must not edit Gateway MCP files.
KBN-105 publishes route+DTO fixture digest before KBN-110/120/130. Every web/CLI/MCP call must match this registry and the generated client.
## 8. Recovery contract and bounded delivery slice
Runtime must invoke normative `validateRecoveryPostureV1`; JSON Schema alone is insufficient. It rejects unknown fields, PITR/WAL mismatch, RPO better than mechanism, unsafe storage, and weakened High-assurance. High-assurance is RPO 15m/RTO 4h, WAL ≤5m, PITR ≥35d, base ≤24h, restore test ≤30d, break-glass ≤90d, encrypted separate-failure-domain storage.
KBN-115/coder2 owns `packages/config/src/recovery-posture.ts`, tests, and recovery runbook. It wires parser/refinement, override audit, mechanism assertions, restore test, and break-glass evidence. Any deployment manifest is separately enumerated and Mos-serialized. Recovery config has no SOT/gate/Coordinator authority fields.
## 9. Integration, security, and hold
Required release evidence includes empty/prod/partial/rollback/N-1 migration tests; cross-workspace and same-workspace wrong-project negatives; active-membership owners/principals; proposal inertness/normal acceptance; exact failure mapping; concurrent monotonic bigint fences; relational lease/checkpoint/evidence mismatch; immutability privileges/RESTRICT; recovery validation/mechanism evidence; endpoint registry alignment; accessible web journeys; author≠reviewer; mandatory SecReview; final Certifier pass/no merge authority.
The build hold remains active until independent re-review reports GO for KCR-001016. Mos alone releases waves and serializes integration roots.

View File

@@ -0,0 +1,263 @@
# Native Kanban/SOT P0P3 — Dependency-Ordered Build Slices
**Status:** CANON INDEPENDENTLY APPROVED; PUBLICATION IN PROGRESS
**Tracking:** [Mosaic Stack issue #751](https://git.mosaicstack.dev/mosaicstack/stack/issues/751)
**Execution:** USC web1 only; collision-free GPT coder2/3/4/5 lanes
**Contract:** `SHARED-CONTRACT.md` + four `contracts/*.v1.ts` files
**Implementation hold:** no feature slice starts until the canon PR is merged to `main` with terminal-green CI; after merge, each slice remains held until every declared KBN prerequisite is complete.
> This publication file is not a runtime task authority. After cutover, repository `TASKS.md` is generated read-only and never imported.
## Execution invariants
- PostgreSQL is the sole writable SOT; current-main Drizzle is the persistence foundation.
- Mutations require fresh internal PostgreSQL transaction-local write proof and fail closed otherwise.
- Public health DTOs, Valkey, files, browser state, providers, and outage notes cannot authorize writes.
- Outage notes return only through attributable `change_proposals`; proposal acceptance executes the normal command.
- Mechanical Coordinator is non-LLM and cannot invent scope, waive gates, certify, or merge.
- Certifier is final independent gate with no merge authority.
- Workspace is the hard tenant. Project hierarchy is project-congruent. Assignment, approval, lease, fence, checkpoint, and evidence are relationally bound.
- Recovery tiers change recovery posture only.
## 1. Collision-free ownership
| USC lane | Exclusive ownership | Must not edit |
| ------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- |
| **coder2 — schema/recovery** | `packages/db/src/schema.ts`; `packages/db/drizzle/**`; DB tests; `packages/config/src/recovery-posture.ts`; `packages/config/src/recovery-posture.spec.ts`; `docs/runbooks/kanban-postgres-recovery.md` | Gateway, Brain repositories, Coordinator, web, CLI/importer |
| **coder3 — domain/Gateway/MCP server** | Kanban repositories under `packages/brain/src/`; Gateway workspace/project/mission/milestone/task/kanban/health/coord modules; **exact MCP files:** `apps/gateway/src/mcp/mcp.dto.ts`, `mcp.controller.ts`, `mcp.service.ts`, `mcp.module.ts`, `mcp.tokens.ts`, `mcp.service.spec.ts`; Gateway root wiring/tests | DB schema/migrations, `packages/coord`, web, CLI/importer |
| **coder4 — CLI → pure Coordinator → migration tooling** | In this one fixed lane order: KBN-120 (`packages/mosaic` CLI/projection) → KBN-200 (`packages/coord/src/mechanical/**`) → KBN-300/320 (`scripts/kanban-migration/**`) | DB, Gateway/MCP server, web |
| **coder5 — web** | `apps/web/src/app/(dashboard)/{tasks,projects}/**`; `apps/web/src/components/{tasks,projects}/**`; Kanban web API/types; later Coordinator/migration-review routes | DB, Gateway, Coordinator, CLI/importer |
| **Mos — publication/integration** | Contract amendments, exact endpoint registry publication, serialized root exports/manifests/lockfiles, integration gates | Active lane feature files |
Shared roots, package exports/manifests, lockfiles, and generated artifacts are integration-serialized. Contract changes stop affected lanes and require Mos approval.
## 2. Parallelization legend
- **SERIAL:** prerequisite must be complete and reviewed.
- **PARALLEL-GROUP:** disjoint files and exact frozen contract permit concurrent work.
- **LANE-SERIAL:** one lane's stated order cannot change.
- **INTEGRATION-SERIAL:** component heads green first; semantic findings return to owner.
## 3. Corrected dependency graph
```text
KBN-000 canon remediation
-> KBN-010 threat/auth/constraint-impact gate (MUST COMPLETE)
-> KBN-100 schema + concrete N-1 migration implementation
├─ KBN-105 exact endpoint/DTO/error/registry freeze (SERIAL)
│ ├─ KBN-110 domain + Gateway + MCP server implementation
│ ├─ KBN-120 CLI/projection implementation [coder4 first]
│ └─ KBN-130 web MVP implementation
└─ KBN-115 recovery parser/mechanism slice [coder2 lane-serial]
KBN-110 + KBN-120 + KBN-130 + KBN-115
-> KBN-140 P1 integration/SIT
-> KBN-200 pure decision engine [coder4 after KBN-120]
-> KBN-210 persistence/service adapter + approval/lease binding
-> KBN-220 Coordinator operations UI
-> KBN-230 P2 concurrency/fault/gate integration
KBN-230
-> KBN-300 importer dry-run/apply/verify [coder4 after KBN-200]
├─ KBN-310 migration reviewer UI
└─ KBN-320 cutover/rollback tooling [coder4 after KBN-300]
KBN-310 + KBN-320
-> KBN-330 rehearsal/reconciliation
-> KBN-340 owner-gated cutover/stabilization
```
No consumer implementation begins before KBN-105. No schema work begins before KBN-010 completes. The coder4 order is always KBN-120 → KBN-200 → KBN-300 → KBN-320.
## 4. P0 — Canon, threat gate, schema, and exact API freeze
### KBN-000 — Remediate and publish canon
- **Status:** COMPLETE — PR #752 squash-merged as `49e8a54`; issue #751 closed; post-merge pipeline #1798 terminal success.
- **Owner:** Mosaic publication control plane.
- **Mode:** SERIAL; completed.
- **IN:** Resolve KCR-001016 in requirements, schema, health, Coordinator, recovery, migration map, and slices; independent re-review.
- **OUT:** Feature implementation.
- **Depends on:** none.
- **Contract surfaces:** all canon.
- **Evidence:** strict TS; Prettier; per-finding traceability; independent author≠reviewer GO; Ultron GO; terminal-green CI.
### KBN-010 — Threat, authorization, and constraint-impact gate
- **Status:** IN PROGRESS — issue [#753](https://git.mosaicstack.dev/mosaicstack/stack/issues/753).
- **Owner:** `kbn-coder3`; independent `secrev`.
- **Mode:** SERIAL prerequisite of KBN-100.
- **Exclusive files:** `docs/native-kanban-sot/KBN-010-THREAT-AUTH-CONSTRAINT-GATE.md` and task scratchpad only.
- **IN:** Cross-workspace owners/principals/evidence; active membership; stale/forged health; approval forgery; fence monotonicity; audit retention; proposal target/audit-event forgery; service tokens; DB/Valkey outage.
- **OUT:** Runtime/schema edits.
- **Depends on:** KBN-000 independent re-review GO.
- **Contract surfaces:** schema constraints, health proof, exact errors, command-family authorization.
- **Evidence:** signed constraint-impact matrix; no unresolved schema-impact finding; SecReview pass.
### KBN-100 — Unified Drizzle schema and concrete N-1 migration
- **Owner:** **coder2**.
- **Mode:** SERIAL.
- **Exclusive files:** `packages/db/src/schema.ts`, `packages/db/drizzle/**`, DB tests.
- **IN:** All frozen tables/joins/enums; workspace/project-congruent constraints; owners/principals; tags/archive; change proposals with both workspace-aware task-event composite FKs and frozen event-before-proposal DDL order; assignment approvals; durable execution/quarantine; monotonic bigint fence; exact checkpoint/evidence joins; RESTRICT/immutability; concrete current-main expand/backfill/switch/contract map.
- **OUT:** Repositories, Gateway, Coordinator behavior, UI, importer.
- **Depends on:** **KBN-010 completed**.
- **Contract surfaces:** `kanban-schema.v1.ts`; SHARED-CONTRACT current-main delta map.
- **Evidence:** reviewed SQL; empty/prod-shape/partial-resume/rollback tests; N-1 app safety; legacy columns remain declared; workspace/project mismatch negatives; proposal event-FK missing/foreign-workspace tests; one active lease; monotonic fence; parent-delete RESTRICT; immutability privileges; SecReview.
### KBN-105 — Exact Gateway/MCP endpoint, DTO, and error freeze
- **Owner:** Mos + coder3 contract author; independent endpoint-alignment reviewer.
- **Mode:** SERIAL after KBN-100; prerequisite for KBN-110/120/130.
- **Exclusive files:** canonical endpoint-registry/DTO contract docs; no implementation.
- **IN:** Exact routes and methods from SHARED-CONTRACT §8; request/success/error fields; status codes; pagination/filter/revision envelopes; idempotency/expected-version headers/fields; proposal commands; health proof exclusion from public DTOs; MCP tool-to-route map.
- **OUT:** Controller/service/client implementation.
- **Depends on:** KBN-100.
- **Contract surfaces:** health/error unions; schema IDs/statuses; Gateway DTO freeze.
- **Evidence:** every FE/CLI/MCP call maps 1:1 to a route; 503/502-504/409 non-cross-map fixtures; contract digest published.
### KBN-115 — Recovery posture parser, mechanisms, and evidence
- **Owner:** **coder2**, lane-serial after KBN-100.
- **Mode:** PARALLEL with KBN-110/120/130 after KBN-105.
- **Exclusive files:** `packages/config/src/recovery-posture.ts`, `.spec.ts`, `docs/runbooks/kanban-postgres-recovery.md`; deployment-specific backup manifest changes are a separately enumerated Mos integration patch.
- **IN:** Wire normative `validateRecoveryPostureV1`; override audit; backup/WAL/PITR mechanism assertions; off-cluster encryption/failure-domain checks; restore and break-glass evidence procedure.
- **OUT:** SOT/gate/Coordinator policy knobs; DB business schema.
- **Depends on:** KBN-100, KBN-105.
- **Contract surfaces:** `recovery-posture.v1.ts` only.
- **Evidence:** impossible-combination tests; High-assurance weakening tests; selected-tier mechanism verification; restore and break-glass evidence; SecReview.
## 5. P1 — Thin native MVP
### KBN-110 — Workspace-safe domain, Gateway, MCP server, and proposal commands
- **Owner:** **coder3**.
- **Mode:** PARALLEL-GROUP P1-A after KBN-105.
- **Exclusive files:** ownership map, including all exact MCP server files listed there.
- **IN:** Workspace-safe repositories; project/task/dependency/tag/archive CRUD; transitions; exact owners; assignment/approval/link/artifact queries; submit/query/accept/reject change proposals; health endpoint; internal write-proof mint/revalidation; event/outbox atomicity; frozen DTOs/routes.
- **OUT:** Scheduling algorithm, web, CLI, DB schema.
- **Depends on:** KBN-100, KBN-105.
- **Contract surfaces:** all four TypeScript contracts and exact registry.
- **Evidence:** DTO/service/controller/integration tests; active-membership and no-oracle negatives; proposal cannot mutate directly; submission event is the new proposal's exact `change_proposal.submitted` event; acceptance links the executed normal command for the locked proposal and same workspace/target; missing, foreign-workspace, unrelated-proposal/target/command event negatives; exact failure mapping; endpoint registry; SecReview.
### KBN-120 — CLI, MCP client mapping, and generated projection
- **Owner:** **coder4**; first coder4 slice.
- **Mode:** PARALLEL-GROUP P1-A after KBN-105.
- **Exclusive files:** `packages/mosaic/src/commands/{kanban,tasks,projects}.ts`; `packages/mosaic/src/projections/**`; tests. **No `apps/gateway/src/mcp/**` edits.\*\*
- **IN:** Frozen query/mutation routes; proposal commands; compact context; generated `TASKS.md`; deliberate denial/transport/conflict handling.
- **OUT:** Gateway/MCP server, file importer, raw SQL/Valkey, Coordinator.
- **Depends on:** KBN-105; runtime integration later requires KBN-110.
- **Evidence:** contract fixtures; same revision; no import parser; same idempotency key on transport retry; 503 never auto-retried.
### KBN-130 — Writable Kanban/List and minimal Projects UI
- **Owner:** **coder5**.
- **Mode:** PARALLEL-GROUP P1-A after KBN-105.
- **Exclusive files:** web ownership map.
- **IN:** Workspace context; projects; tasks; tags; explicit archive; detail; accessible move/reorder; filters; dependency/readiness; owner/assignment/lease; audit; proposal visibility; conflict/loading/error/reconnect.
- **OUT:** Gateway/schema, Coordinator operations UI, migration UI.
- **Depends on:** KBN-105; runtime integration later requires KBN-110.
- **Evidence:** frozen contract mocks; real-Gateway journeys; keyboard/non-drag; tags/archive semantics; no-oracle tenant negatives; 503/transport/409 distinct UI.
### KBN-140 — P1 integration and situational gate
- **Owner:** Mos integration; independent reviewer/SecReview/Certifier.
- **Mode:** INTEGRATION-SERIAL.
- **IN:** KBN-110/120/130/115; unavoidable root exports only.
- **OUT:** P2 behavior.
- **Depends on:** KBN-110, KBN-120, KBN-130, KBN-115.
- **Evidence:** clean migration; web/CLI/MCP/projection revision parity; forged/expired health negatives; change-proposal event-chain success plus missing/foreign/unrelated-event negatives; tag/archive; tenant negatives; endpoint registry; author-independent review; Certifier pass.
## 6. P2 — Mechanical Coordinator
### KBN-200 — Pure deterministic decision engine
- **Owner:** **coder4**; second coder4 slice, strictly after KBN-120.
- **Mode:** SERIAL in coder4 lane.
- **Exclusive files:** `packages/coord/src/mechanical/**` and pure tests.
- **IN:** `MechanicalCoordinatorDecisionEngineV1`; complete immutable snapshots; eligibility/explanation; fairness/order; capability matching; expiry/retry/quarantine decisions.
- **OUT:** ID loading, PostgreSQL, Drizzle, Gateway, Valkey, health-proof minting, persistence, `recoverFromPostgres`, LLM calls.
- **Depends on:** KBN-140 (or Mos may release after KBN-120 + frozen types if no P1 semantic risk remains).
- **Evidence:** deterministic/property tests; snapshot completeness; no I/O/model imports; no authority methods.
### KBN-210 — Coordinator persistence/service adapter and approval-bound leases
- **Owner:** **coder3**.
- **Mode:** SERIAL after KBN-200.
- **Exclusive files:** Gateway `coord` and repositories.
- **IN:** `MechanicalCoordinatorServicePortV1`; snapshot loading; proposal persistence; manual/versioned policy approval; acquire by IDs; reload+lock task/assignment/approval/session; fresh txn-local write proof; atomic task fence increment; lease/ack/heartbeat/checkpoint/submit; durable retry/quarantine; outbox/Valkey wake; restart recovery.
- **OUT:** Pure algorithm, UI, DB schema.
- **Depends on:** KBN-110, KBN-200.
- **Evidence:** forged/stale approval rejection; target/session/version/expiry/policy checks; concurrent monotonic fences; same-workspace mismatch negatives; bigint precision; stale worker rejection; DB/Valkey faults; SecReview.
### KBN-220 — Coordinator operations UI
- **Owner:** **coder5**.
- **Mode:** after KBN-210 exact DTO freeze.
- **IN:** Roster; eligibility; persisted assignment state; approvals/overrides; exact lease/fence; durable retry/quarantine; role/gate/Certifier visibility.
- **OUT:** Scheduling decisions, schema, merge control for Certifier.
- **Depends on:** KBN-210.
- **Evidence:** authorized journeys; reason required; stale refresh; no Certifier merge; endpoint alignment/accessibility.
### KBN-230 — P2 concurrency/fault/gate integration
- **Owner:** Mos integration; independent reviewer/SecReview/Certifier.
- **Mode:** INTEGRATION-SERIAL.
- **Depends on:** KBN-200, KBN-210, KBN-220.
- **Evidence:** one lease; monotonic fences; exact relational mismatches rejected; expired proof; forged healthy; approval binding; restart; durable quarantine; outbox recovery; author≠reviewer; Certifier final/no merge.
## 7. P3 — Shadow migration and cutover
### KBN-300 — One-way importer dry-run/apply/verify
- **Owner:** **coder4**; third coder4 slice.
- **Mode:** after KBN-230.
- **Exclusive files:** `scripts/kanban-migration/import/**`.
- **IN:** Immutable jarvis-brain/Vikunja snapshots; deterministic mapping; source digest/lineage; Gateway writes; rejects; no dispatch.
- **OUT:** Bidirectional sync, direct DB/file canonical writes, unrelated brain data.
- **Depends on:** KBN-230.
- **Evidence:** idempotency; counts/fields; malformed/foreign rejects; no dispatch; SecReview.
### KBN-310 — Shadow reviewer UI
- **Owner:** **coder5**.
- **Mode:** PARALLEL-GROUP P3-A after KBN-300 report freeze.
- **IN:** Read-only counts/diffs/rejects/lineage/sign-off.
- **OUT:** Apply/cutover mutations.
- **Depends on:** KBN-300.
- **Evidence:** read-only and tenant tests; pagination/accessibility.
### KBN-320 — Cutover/rollback tooling
- **Owner:** **coder4**; fourth coder4 slice, after KBN-300.
- **Mode:** PARALLEL-GROUP P3-A with KBN-310.
- **Exclusive files:** `scripts/kanban-migration/cutover/**`.
- **IN:** Freeze assertion; backup/checksum; final delta; client switch; legacy writer/credential shutdown; rollback delta; stabilization.
- **OUT:** Destructive deletion, reverse sync, ungated production execution.
- **Depends on:** KBN-300.
- **Evidence:** fail-safe rehearsal; no dual writer; rollback authority; SecReview.
### KBN-330 — Migration rehearsal/reconciliation
- **Owner:** Mos + coder4 support + independent data reviewer.
- **Mode:** INTEGRATION-SERIAL.
- **Depends on:** KBN-310, KBN-320.
- **Evidence:** signed exceptions; selected-tier restore; backlog hold; no legacy changes; Certifier readiness.
### KBN-340 — Final cutover/stabilization
- **Owner:** Mos/control plane; owner-gated operation.
- **Mode:** SERIAL.
- **Depends on:** KBN-330 PASS and Jason authorization.
- **Evidence:** no legacy writer; scoped Gateway identities; no accidental dispatch; terminal green health/CI; Certifier evidence; owner retirement approval.
## 8. Consistent USC wave schedule
| Wave | coder2 | coder3 | coder4 | coder5 |
| ---- | ------------------------- | -------------------------------------- | ------------------------------ | ------------------------------ |
| 0 | Wait | **KBN-010** | Wait | Wait |
| 1 | **KBN-100** | Review constraint implementation | Wait | Wait |
| 2 | **KBN-115** after KBN-100 | **KBN-105** exact freeze, then KBN-110 | **KBN-120** only after KBN-105 | **KBN-130** only after KBN-105 |
| 3 | Review support | Finish KBN-110 | **KBN-200 after KBN-120** | Finish KBN-130 |
| 4 | — | **KBN-210 after KBN-200** | Review/support | **KBN-220 after KBN-210 DTOs** |
| 5 | — | P2 remediation | **KBN-300 then KBN-320** | **KBN-310** |
Mos alone releases slices and lifts the build hold after independent re-review GO.

View File

@@ -0,0 +1,206 @@
/**
* Mosaic Native Kanban — frozen health/error contract v1.
* Publication contract only; no runtime implementation is included here.
*
* PostgreSQL is the sole writable SOT. Public health DTOs are observations,
* never write authority. Only an internal transaction-local proof produced by
* the PostgreSQL adapter may authorize a mutation.
*/
export const KANBAN_CONTRACT_VERSION = '1.0.0' as const;
export const kanbanHealthStates = ['healthy', 'read-only-degraded', 'write-unavailable'] as const;
export type KanbanHealthState = (typeof kanbanHealthStates)[number];
interface KanbanHealthBaseV1 {
contractVersion: typeof KANBAN_CONTRACT_VERSION;
checkedAt: string;
/** Observation expires at this RFC 3339 instant; it still never authorizes writes. */
validUntil: string;
policyRevision: string;
reasons: string[];
}
export interface HealthyKanbanHealthResponseV1 extends KanbanHealthBaseV1 {
state: 'healthy';
readHealthProven: true;
writeHealthProven: true;
}
export interface ReadOnlyDegradedKanbanHealthResponseV1 extends KanbanHealthBaseV1 {
state: 'read-only-degraded';
readHealthProven: true;
writeHealthProven: false;
}
export interface WriteUnavailableKanbanHealthResponseV1 extends KanbanHealthBaseV1 {
state: 'write-unavailable';
readHealthProven: false;
writeHealthProven: false;
}
/** Public, discriminated observation. Contradictory combinations are unrepresentable. */
export type KanbanHealthResponseV1 =
| HealthyKanbanHealthResponseV1
| ReadOnlyDegradedKanbanHealthResponseV1
| WriteUnavailableKanbanHealthResponseV1;
/** Pure evaluation context. It cannot authorize a mutation. */
export interface KanbanEvaluationContextV1 {
contractVersion: typeof KANBAN_CONTRACT_VERSION;
workspaceId: string;
correlationId: string;
now: string;
policyRevision: string;
observedHealth: KanbanHealthResponseV1;
}
/**
* Non-exported brand: public DTO deserialization cannot construct this type.
* The PostgreSQL adapter mints it only after a fresh write probe inside the same
* transaction and validates checkedAt <= now < validUntil and policy revision.
*/
declare const postgresWriteHealthProofBrand: unique symbol;
export interface PostgresWriteHealthProofV1 {
readonly [postgresWriteHealthProofBrand]: true;
readonly source: 'postgres-transaction-local-write-probe';
readonly transactionId: string;
readonly checkedAt: string;
readonly validUntil: string;
readonly policyRevision: string;
}
/** Internal mutation context; MUST NOT appear in REST/MCP/CLI request DTOs. */
export interface InternalKanbanMutationContextV1 {
contractVersion: typeof KANBAN_CONTRACT_VERSION;
workspaceId: string;
correlationId: string;
causationId?: string;
idempotencyKey: string;
now: string;
expectedPolicyRevision: string;
writeProof: PostgresWriteHealthProofV1;
}
interface MutationFailureBaseV1 {
contractVersion: typeof KANBAN_CONTRACT_VERSION;
retryable: false;
requestOutcome: 'not_applied';
idempotencyKey: string;
correlationId: string;
message: string;
}
/** KCR-016: code/state pairing is exact and cannot cross-map. */
export interface ReadOnlyWriteHealthDenialV1 extends MutationFailureBaseV1 {
kind: 'deliberate_fail_closed_denial';
code: 'KANBAN_WRITE_HEALTH_UNPROVEN';
healthState: 'read-only-degraded';
checkedAt: string;
}
export interface WriteUnavailableDenialV1 extends MutationFailureBaseV1 {
kind: 'deliberate_fail_closed_denial';
code: 'KANBAN_WRITE_UNAVAILABLE';
healthState: 'write-unavailable';
checkedAt: string;
}
export type DeliberateWriteDenialV1 = ReadOnlyWriteHealthDenialV1 | WriteUnavailableDenialV1;
export const transportErrorCodes = [
'GATEWAY_UNREACHABLE',
'GATEWAY_TIMEOUT',
'UPSTREAM_BAD_GATEWAY',
] as const;
export type TransportErrorCode = (typeof transportErrorCodes)[number];
/** Client-normalized transport uncertainty; never an authoritative 503 body. */
export interface RetryableTransportErrorV1 {
contractVersion: typeof KANBAN_CONTRACT_VERSION;
kind: 'retryable_transport_error';
code: TransportErrorCode;
retryable: true;
requestOutcome: 'unknown';
/** Retry MUST reuse this exact key. */
idempotencyKey: string;
correlationId: string;
message: string;
}
export interface VersionConflictV1 {
contractVersion: typeof KANBAN_CONTRACT_VERSION;
kind: 'version_conflict';
code: 'AGGREGATE_VERSION_CONFLICT';
retryable: false;
requestOutcome: 'not_applied';
aggregateType: 'project' | 'mission' | 'milestone' | 'task' | 'change_proposal';
aggregateId: string;
expectedVersion: number;
actualVersion: number;
idempotencyKey: string;
correlationId: string;
message: string;
}
export type KanbanMutationFailureV1 =
| DeliberateWriteDenialV1
| RetryableTransportErrorV1
| VersionConflictV1;
export const kanbanHealthCapabilities: Readonly<
Record<KanbanHealthState, { canonicalReads: boolean; mutations: boolean }>
> = {
healthy: { canonicalReads: true, mutations: true },
'read-only-degraded': { canonicalReads: true, mutations: false },
'write-unavailable': { canonicalReads: false, mutations: false },
};
/** Exact HTTP/error normalization freeze; 503, transport, and 409 cannot cross-map. */
export const kanbanFailureHttpMapV1 = {
KANBAN_WRITE_HEALTH_UNPROVEN: {
httpStatus: 503,
kind: 'deliberate_fail_closed_denial',
requestOutcome: 'not_applied',
retryable: false,
},
KANBAN_WRITE_UNAVAILABLE: {
httpStatus: 503,
kind: 'deliberate_fail_closed_denial',
requestOutcome: 'not_applied',
retryable: false,
},
AGGREGATE_VERSION_CONFLICT: {
httpStatus: 409,
kind: 'version_conflict',
requestOutcome: 'not_applied',
retryable: false,
},
GATEWAY_UNREACHABLE: {
httpStatus: 502,
kind: 'retryable_transport_error',
requestOutcome: 'unknown',
retryable: true,
},
GATEWAY_TIMEOUT: {
httpStatus: 504,
kind: 'retryable_transport_error',
requestOutcome: 'unknown',
retryable: true,
},
UPSTREAM_BAD_GATEWAY: {
httpStatus: 502,
kind: 'retryable_transport_error',
requestOutcome: 'unknown',
retryable: true,
},
} as const;
/**
* Required negative contract tests:
* - contradictory state/proof booleans fail type/schema validation;
* - expired internal proof and policy mismatch deny before mutation;
* - Valkey-only liveness cannot mint PostgresWriteHealthProofV1;
* - public/caller-forged `healthy` cannot enter InternalKanbanMutationContextV1;
* - authoritative 503, transport 502/504/timeout, and 409 mappings are exhaustive.
*/

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,419 @@
/**
* Mosaic Native Kanban — frozen Mechanical Coordinator contracts v1.
*
* The pure decision engine and persistence/orchestration service are separate.
* Neither surface can create scope, edit acceptance, waive gates, certify,
* merge, release a deployment, or close a provider issue.
*/
import type {
DeliberateWriteDenialV1,
InternalKanbanMutationContextV1,
KanbanEvaluationContextV1,
KanbanMutationFailureV1,
RetryableTransportErrorV1,
VersionConflictV1,
} from './health-state.v1.js';
export const COORDINATOR_CONTRACT_VERSION = '1.0.0' as const;
export type Uuid = string;
export type IsoTimestamp = string;
/** PostgreSQL bigint-safe decimal string; never a JavaScript number. */
export type FencingTokenV1 = string;
export const specialistRoles = [
'planning',
'enhance',
'coder',
'review',
'security-review',
'pr-monitor',
'certifier',
] as const;
export type SpecialistRole = (typeof specialistRoles)[number];
/** One vocabulary shared with task_assignment_state_v1 in the Drizzle schema. */
export const assignmentStates = [
'awaiting_approval',
'policy_pre_authorized',
'approved',
'rejected',
'leased',
'released',
'expired',
'superseded',
] as const;
export type AssignmentStateV1 = (typeof assignmentStates)[number];
export const readinessStates = [
'dependency-gated',
'schedule-gated',
'policy-gated',
'lease-available',
'leased',
'retry-delayed',
'exhausted',
'quarantined',
] as const;
export type ReadinessState = (typeof readinessStates)[number];
export interface RetryStateSnapshotV1 {
disposition: 'available' | 'retry_delayed' | 'quarantined' | 'exhausted';
attemptCount: number;
maxAttempts: number;
nextEligibleAt: IsoTimestamp | null;
idempotent: boolean;
terminalReason: string | null;
version: number;
}
export interface TaskEligibilitySnapshotV1 {
workspaceId: Uuid;
taskId: Uuid;
taskVersion: number;
projectId: Uuid;
projectActive: boolean;
missionId: Uuid | null;
missionActive: boolean;
status: 'ready';
priority: 'critical' | 'high' | 'medium' | 'low';
boardRank: string;
dueAt: IsoTimestamp | null;
notBeforeAt: IsoTimestamp | null;
createdAt: IsoTimestamp;
requiredRole: SpecialistRole;
requiredCapabilities: readonly string[];
blockingDependencies: readonly {
taskId: Uuid;
done: boolean;
completionConditionSatisfied: boolean;
}[];
releaseApproval: {
decisionId: Uuid;
approved: boolean;
policyRevision: string;
} | null;
activeLeaseId: Uuid | null;
retry: RetryStateSnapshotV1;
}
export interface AgentSessionSnapshotV1 {
workspaceId: Uuid;
agentId: Uuid;
sessionId: Uuid;
state: 'available' | 'busy';
roles: readonly SpecialistRole[];
capabilities: readonly string[];
capacity: number;
activeLeaseCount: number;
heartbeatAt: IsoTimestamp;
}
export interface EligibilityExplanationV1 {
taskId: Uuid;
eligible: boolean;
readiness: ReadinessState;
reasons: readonly {
gate:
| 'status'
| 'project'
| 'mission'
| 'dependency'
| 'schedule'
| 'retry'
| 'approval'
| 'lease'
| 'capability'
| 'capacity'
| 'health';
satisfied: boolean;
code: string;
detail: string;
}[];
policyRevision: string;
evaluatedAt: IsoTimestamp;
}
export interface AssignmentProposalDecisionV1 {
workspaceId: Uuid;
taskId: Uuid;
taskVersion: number;
targetAgentId: Uuid;
targetSessionId: Uuid;
specialistRole: SpecialistRole;
initialState: 'awaiting_approval' | 'policy_pre_authorized';
policyRevision: string;
explanation: EligibilityExplanationV1;
expiresAt: IsoTimestamp;
}
export interface AssignmentCycleSnapshotV1 {
context: KanbanEvaluationContextV1;
tasks: readonly TaskEligibilitySnapshotV1[];
sessions: readonly AgentSessionSnapshotV1[];
workspaceFairness: Readonly<Record<Uuid, number>>;
limit: number;
}
export interface AssignmentCycleDecisionV1 {
evaluatedTaskCount: number;
proposals: readonly AssignmentProposalDecisionV1[];
explanations: readonly EligibilityExplanationV1[];
}
export interface LeaseExpirySnapshotV1 {
workspaceId: Uuid;
taskId: Uuid;
taskVersion: number;
leaseId: Uuid;
assignmentId: Uuid;
sessionId: Uuid;
fencingToken: FencingTokenV1;
state: 'pending_ack' | 'active';
acknowledgeBy: IsoTimestamp;
expiresAt: IsoTimestamp;
lastHeartbeatAt: IsoTimestamp | null;
retry: RetryStateSnapshotV1;
}
export interface LeaseExpiryDecisionV1 {
leaseId: Uuid;
action: 'retain' | 'release' | 'retry' | 'quarantine' | 'exhaust';
reason: string;
nextEligibleAt: IsoTimestamp | null;
}
/** Pure package owned by KBN-200. It receives complete immutable snapshots. */
export interface MechanicalCoordinatorDecisionEngineV1 {
evaluateAssignmentCycle(snapshot: AssignmentCycleSnapshotV1): AssignmentCycleDecisionV1;
explainEligibility(
context: KanbanEvaluationContextV1,
task: TaskEligibilitySnapshotV1,
sessions: readonly AgentSessionSnapshotV1[],
): EligibilityExplanationV1;
decideLeaseExpiry(
context: KanbanEvaluationContextV1,
lease: LeaseExpirySnapshotV1,
): LeaseExpiryDecisionV1;
}
export interface PersistedAssignmentV1 {
assignmentId: Uuid;
workspaceId: Uuid;
taskId: Uuid;
taskVersion: number;
targetAgentId: Uuid;
targetSessionId: Uuid;
specialistRole: SpecialistRole;
state: AssignmentStateV1;
policyRevision: string;
proposedBy: { kind: 'user' | 'agent'; id: Uuid };
reason: string;
createdAt: IsoTimestamp;
expiresAt: IsoTimestamp;
}
export interface TaskLeaseV1 {
leaseId: Uuid;
workspaceId: Uuid;
taskId: Uuid;
taskVersion: number;
assignmentId: Uuid;
agentId: Uuid;
sessionId: Uuid;
state: 'pending_ack' | 'active';
fencingToken: FencingTokenV1;
attempt: number;
acquiredAt: IsoTimestamp;
acknowledgeBy: IsoTimestamp;
lastHeartbeatAt: IsoTimestamp | null;
expiresAt: IsoTimestamp;
}
interface ServiceCommandBaseV1 {
context: InternalKanbanMutationContextV1;
taskId: Uuid;
expectedTaskVersion: number;
}
export interface AcquireApprovedLeaseCommandV1 extends ServiceCommandBaseV1 {
assignmentId: Uuid;
approvalDecisionId: Uuid;
targetSessionId: Uuid;
leaseTtlSeconds: number;
}
export interface LeaseCommandV1 extends ServiceCommandBaseV1 {
leaseId: Uuid;
sessionId: Uuid;
fencingToken: FencingTokenV1;
}
export interface HeartbeatLeaseCommandV1 extends LeaseCommandV1 {
extendSeconds: number;
}
export interface CheckpointCommandV1 extends LeaseCommandV1 {
sequence: number;
resumableSummary: string;
artifactIds: readonly Uuid[];
contextUsagePercent: number;
}
export interface SubmitForReviewCommandV1 extends LeaseCommandV1 {
artifactIds: readonly Uuid[];
summary: string;
}
export interface ReleaseLeaseCommandV1 extends LeaseCommandV1 {
reason:
| 'worker_requested'
| 'ack_timeout'
| 'heartbeat_timeout'
| 'task_submitted'
| 'policy_revoked'
| 'shutdown';
}
export interface AssignmentCycleCommandV1 {
context: InternalKanbanMutationContextV1;
limit: number;
}
export interface ExpirySweepCommandV1 {
context: InternalKanbanMutationContextV1;
limit: number;
}
export interface RecoverCoordinatorCommandV1 {
context: InternalKanbanMutationContextV1;
}
interface CoordinatorRejectionBaseV1 {
kind: 'coordinator_rejection';
retryable: false;
requestOutcome: 'not_applied';
correlationId: Uuid;
idempotencyKey: string;
message: string;
}
export type CoordinatorPolicyRejectionV1 =
| (CoordinatorRejectionBaseV1 & { code: 'WORKSPACE_MISMATCH' })
| (CoordinatorRejectionBaseV1 & {
code: 'TASK_NOT_ELIGIBLE';
explanation: EligibilityExplanationV1;
})
| (CoordinatorRejectionBaseV1 & { code: 'APPROVAL_REQUIRED' })
| (CoordinatorRejectionBaseV1 & { code: 'APPROVAL_STALE' })
| (CoordinatorRejectionBaseV1 & { code: 'ASSIGNMENT_STALE' })
| (CoordinatorRejectionBaseV1 & { code: 'ASSIGNMENT_TARGET_MISMATCH' })
| (CoordinatorRejectionBaseV1 & { code: 'POLICY_REVISION_MISMATCH' })
| (CoordinatorRejectionBaseV1 & { code: 'ARTIFACT_WORKSPACE_MISMATCH' })
| (CoordinatorRejectionBaseV1 & { code: 'LEASE_ALREADY_ACTIVE' })
| (CoordinatorRejectionBaseV1 & { code: 'LEASE_NOT_FOUND' })
| (CoordinatorRejectionBaseV1 & { code: 'LEASE_NOT_ACTIVE' })
| (CoordinatorRejectionBaseV1 & {
code: 'ACK_DEADLINE_EXPIRED';
expiredAt: IsoTimestamp;
})
| (CoordinatorRejectionBaseV1 & {
code: 'FENCING_TOKEN_STALE';
currentFencingToken: FencingTokenV1;
})
| (CoordinatorRejectionBaseV1 & { code: 'SESSION_MISMATCH' })
| (CoordinatorRejectionBaseV1 & {
code: 'HEARTBEAT_EXPIRED';
expiredAt: IsoTimestamp;
})
| (CoordinatorRejectionBaseV1 & {
code: 'CHECKPOINT_SEQUENCE_CONFLICT';
currentSequence: number;
})
| (CoordinatorRejectionBaseV1 & { code: 'RETRY_EXHAUSTED' })
| (CoordinatorRejectionBaseV1 & {
code: 'NON_IDEMPOTENT_RETRY_REQUIRES_ORCHESTRATOR';
});
/** Explicit mapping to the Gateway mutation failure union; no arbitrary booleans. */
export type CoordinatorFailureV1 =
| DeliberateWriteDenialV1
| VersionConflictV1
| RetryableTransportErrorV1
| CoordinatorPolicyRejectionV1;
export interface CoordinatorSuccessV1<T> {
ok: true;
value: T;
correlationId: Uuid;
}
export interface CoordinatorFailureResultV1 {
ok: false;
failure: CoordinatorFailureV1;
}
export type CoordinatorResultV1<T> = CoordinatorSuccessV1<T> | CoordinatorFailureResultV1;
export interface ExpirySweepResultV1 {
examined: number;
released: readonly Uuid[];
retryScheduled: readonly Uuid[];
quarantined: readonly Uuid[];
exhausted: readonly Uuid[];
}
export interface RestartRecoveryResultV1 {
activeLeaseIds: readonly Uuid[];
expiredLeaseIds: readonly Uuid[];
pendingAssignmentIds: readonly Uuid[];
pendingOutboxEventIds: readonly Uuid[];
}
/** Persistence/Gateway adapter owned by KBN-210. */
export interface MechanicalCoordinatorServicePortV1 {
/** Loads immutable snapshots, invokes pure engine, and persists proposals atomically. */
runAssignmentCycle(
command: AssignmentCycleCommandV1,
): Promise<CoordinatorResultV1<{ assignments: readonly PersistedAssignmentV1[] }>>;
/** Query path loads by ID; public health observation cannot authorize mutation. */
getEligibilityExplanation(
context: KanbanEvaluationContextV1,
taskId: Uuid,
): Promise<CoordinatorResultV1<EligibilityExplanationV1>>;
/**
* Accepts IDs only. Implementation reloads and locks assignment + approval +
* task + target session in PostgreSQL, then verifies workspace, task version,
* target agent/session, state, expiry, policy revision, and current approval.
*/
acquireApprovedLease(
command: AcquireApprovedLeaseCommandV1,
): Promise<CoordinatorResultV1<TaskLeaseV1>>;
acknowledgeLease(command: LeaseCommandV1): Promise<CoordinatorResultV1<TaskLeaseV1>>;
heartbeatLease(command: HeartbeatLeaseCommandV1): Promise<CoordinatorResultV1<TaskLeaseV1>>;
appendCheckpoint(
command: CheckpointCommandV1,
): Promise<CoordinatorResultV1<{ checkpointId: Uuid }>>;
submitForReview(
command: SubmitForReviewCommandV1,
): Promise<CoordinatorResultV1<{ taskVersion: number; status: 'in_review' }>>;
releaseLease(command: ReleaseLeaseCommandV1): Promise<CoordinatorResultV1<{ released: true }>>;
expireAndRecover(
command: ExpirySweepCommandV1,
): Promise<CoordinatorResultV1<ExpirySweepResultV1>>;
recoverFromPostgres(
command: RecoverCoordinatorCommandV1,
): Promise<CoordinatorResultV1<RestartRecoveryResultV1>>;
}
/** Compile-time mapping guarantee: Coordinator Gateway failures are Kanban failures or exact policy rejections. */
export function isKanbanMutationFailureV1(
failure: CoordinatorFailureV1,
): failure is KanbanMutationFailureV1 {
return (
failure.kind === 'deliberate_fail_closed_denial' ||
failure.kind === 'retryable_transport_error' ||
failure.kind === 'version_conflict'
);
}

View File

@@ -0,0 +1,369 @@
/**
* Mosaic Native Kanban — frozen recovery-posture contract v1.
* Recovery posture is configurable; SOT, write-health, Coordinator authority,
* and gate semantics are not fields and cannot be overridden.
*/
export const RECOVERY_POSTURE_CONTRACT_VERSION = '1.0.0' as const;
export const recoveryTiers = ['lite', 'standard', 'high-assurance'] as const;
export type RecoveryTier = (typeof recoveryTiers)[number];
export interface OffClusterStorageV1 {
required: true;
encrypted: true;
separateFailureDomain: true;
minimumCopies: number;
storageClass: 'encrypted-object-storage' | 'encrypted-backup-target';
}
export interface RecoveryPostureV1 {
contractVersion: typeof RECOVERY_POSTURE_CONTRACT_VERSION;
tier: RecoveryTier;
targetRpoMinutes: number;
targetRtoMinutes: number;
baseBackupIntervalHours: number;
/** null means WAL archival/PITR is disabled. */
walArchiveIntervalMinutes: number | null;
/** 0 means PITR is disabled. */
pitrRetentionDays: number;
restoreTestIntervalDays: number;
breakGlassDrillIntervalDays: number;
offClusterStorage: OffClusterStorageV1;
}
export const recoveryPostureDefaults: Readonly<Record<RecoveryTier, RecoveryPostureV1>> = {
lite: {
contractVersion: RECOVERY_POSTURE_CONTRACT_VERSION,
tier: 'lite',
targetRpoMinutes: 24 * 60,
targetRtoMinutes: 24 * 60,
baseBackupIntervalHours: 24,
walArchiveIntervalMinutes: null,
pitrRetentionDays: 0,
restoreTestIntervalDays: 90,
breakGlassDrillIntervalDays: 365,
offClusterStorage: {
required: true,
encrypted: true,
separateFailureDomain: true,
minimumCopies: 1,
storageClass: 'encrypted-backup-target',
},
},
standard: {
contractVersion: RECOVERY_POSTURE_CONTRACT_VERSION,
tier: 'standard',
targetRpoMinutes: 60,
targetRtoMinutes: 8 * 60,
baseBackupIntervalHours: 24,
walArchiveIntervalMinutes: 15,
pitrRetentionDays: 14,
restoreTestIntervalDays: 90,
breakGlassDrillIntervalDays: 180,
offClusterStorage: {
required: true,
encrypted: true,
separateFailureDomain: true,
minimumCopies: 1,
storageClass: 'encrypted-object-storage',
},
},
'high-assurance': {
contractVersion: RECOVERY_POSTURE_CONTRACT_VERSION,
tier: 'high-assurance',
targetRpoMinutes: 15,
targetRtoMinutes: 4 * 60,
baseBackupIntervalHours: 24,
walArchiveIntervalMinutes: 5,
pitrRetentionDays: 35,
restoreTestIntervalDays: 30,
breakGlassDrillIntervalDays: 90,
offClusterStorage: {
required: true,
encrypted: true,
separateFailureDomain: true,
minimumCopies: 1,
storageClass: 'encrypted-object-storage',
},
},
};
/** Shape schema. Normative cross-field semantics are enforced by validateRecoveryPostureV1. */
export const recoveryPostureJsonSchemaV1 = {
$id: 'https://mosaicstack.dev/contracts/recovery-posture.v1.schema.json',
$schema: 'https://json-schema.org/draft/2020-12/schema',
type: 'object',
additionalProperties: false,
required: [
'contractVersion',
'tier',
'targetRpoMinutes',
'targetRtoMinutes',
'baseBackupIntervalHours',
'walArchiveIntervalMinutes',
'pitrRetentionDays',
'restoreTestIntervalDays',
'breakGlassDrillIntervalDays',
'offClusterStorage',
],
properties: {
contractVersion: { const: RECOVERY_POSTURE_CONTRACT_VERSION },
tier: { enum: recoveryTiers },
targetRpoMinutes: { type: 'integer', minimum: 1 },
targetRtoMinutes: { type: 'integer', minimum: 1 },
baseBackupIntervalHours: { type: 'integer', minimum: 1 },
walArchiveIntervalMinutes: {
anyOf: [{ type: 'integer', minimum: 1 }, { type: 'null' }],
},
pitrRetentionDays: { type: 'integer', minimum: 0 },
restoreTestIntervalDays: { type: 'integer', minimum: 1 },
breakGlassDrillIntervalDays: { type: 'integer', minimum: 1 },
offClusterStorage: {
type: 'object',
additionalProperties: false,
required: ['required', 'encrypted', 'separateFailureDomain', 'minimumCopies', 'storageClass'],
properties: {
required: { const: true },
encrypted: { const: true },
separateFailureDomain: { const: true },
minimumCopies: { type: 'integer', minimum: 1 },
storageClass: {
enum: ['encrypted-object-storage', 'encrypted-backup-target'],
},
},
},
},
} as const;
export const recoveryValidationCodes = [
'INVALID_SHAPE',
'UNKNOWN_FIELD',
'PITR_REQUIRES_WAL',
'WAL_REQUIRES_PITR',
'RPO_BETTER_THAN_MECHANISM',
'OFF_CLUSTER_REQUIRED',
'HIGH_ASSURANCE_WEAKENED',
] as const;
export type RecoveryValidationCode = (typeof recoveryValidationCodes)[number];
export interface RecoveryValidationIssueV1 {
code: RecoveryValidationCode;
path: string;
message: string;
}
export type RecoveryValidationResultV1 =
| { ok: true; value: RecoveryPostureV1 }
| { ok: false; issues: RecoveryValidationIssueV1[] };
const topLevelFields = new Set([
'contractVersion',
'tier',
'targetRpoMinutes',
'targetRtoMinutes',
'baseBackupIntervalHours',
'walArchiveIntervalMinutes',
'pitrRetentionDays',
'restoreTestIntervalDays',
'breakGlassDrillIntervalDays',
'offClusterStorage',
]);
const storageFields = new Set([
'required',
'encrypted',
'separateFailureDomain',
'minimumCopies',
'storageClass',
]);
function isRecord(value: unknown): value is Record<string, unknown> {
return typeof value === 'object' && value !== null && !Array.isArray(value);
}
function isPositiveInteger(value: unknown): value is number {
return Number.isInteger(value) && Number(value) > 0;
}
function isNonnegativeInteger(value: unknown): value is number {
return Number.isInteger(value) && Number(value) >= 0;
}
/**
* Normative parser/refinement. Deployment code MUST call this function (or a
* byte-for-byte behaviorally equivalent generated validator), not JSON Schema
* shape validation alone.
*/
export function validateRecoveryPostureV1(input: unknown): RecoveryValidationResultV1 {
const issues: RecoveryValidationIssueV1[] = [];
if (!isRecord(input)) {
return {
ok: false,
issues: [{ code: 'INVALID_SHAPE', path: '$', message: 'posture must be an object' }],
};
}
for (const key of Object.keys(input)) {
if (!topLevelFields.has(key)) {
issues.push({ code: 'UNKNOWN_FIELD', path: `$.${key}`, message: 'unknown field' });
}
}
const tier = input['tier'];
const storage = input['offClusterStorage'];
const integerFields = [
'targetRpoMinutes',
'targetRtoMinutes',
'baseBackupIntervalHours',
'restoreTestIntervalDays',
'breakGlassDrillIntervalDays',
] as const;
if (input['contractVersion'] !== RECOVERY_POSTURE_CONTRACT_VERSION) {
issues.push({
code: 'INVALID_SHAPE',
path: '$.contractVersion',
message: `must equal ${RECOVERY_POSTURE_CONTRACT_VERSION}`,
});
}
if (!recoveryTiers.includes(tier as RecoveryTier)) {
issues.push({ code: 'INVALID_SHAPE', path: '$.tier', message: 'unknown recovery tier' });
}
for (const field of integerFields) {
if (!isPositiveInteger(input[field])) {
issues.push({
code: 'INVALID_SHAPE',
path: `$.${field}`,
message: 'must be a positive integer',
});
}
}
if (!isNonnegativeInteger(input['pitrRetentionDays'])) {
issues.push({
code: 'INVALID_SHAPE',
path: '$.pitrRetentionDays',
message: 'must be a nonnegative integer',
});
}
if (
input['walArchiveIntervalMinutes'] !== null &&
!isPositiveInteger(input['walArchiveIntervalMinutes'])
) {
issues.push({
code: 'INVALID_SHAPE',
path: '$.walArchiveIntervalMinutes',
message: 'must be null or a positive integer',
});
}
if (!isRecord(storage)) {
issues.push({
code: 'INVALID_SHAPE',
path: '$.offClusterStorage',
message: 'must be an object',
});
} else {
for (const key of Object.keys(storage)) {
if (!storageFields.has(key)) {
issues.push({
code: 'UNKNOWN_FIELD',
path: `$.offClusterStorage.${key}`,
message: 'unknown field',
});
}
}
if (
storage['required'] !== true ||
storage['encrypted'] !== true ||
storage['separateFailureDomain'] !== true
) {
issues.push({
code: 'OFF_CLUSTER_REQUIRED',
path: '$.offClusterStorage',
message: 'storage must be required, encrypted, and in a separate failure domain',
});
}
if (!isPositiveInteger(storage['minimumCopies'])) {
issues.push({
code: 'INVALID_SHAPE',
path: '$.offClusterStorage.minimumCopies',
message: 'must be a positive integer',
});
}
if (
storage['storageClass'] !== 'encrypted-object-storage' &&
storage['storageClass'] !== 'encrypted-backup-target'
) {
issues.push({
code: 'INVALID_SHAPE',
path: '$.offClusterStorage.storageClass',
message: 'unsupported storage class',
});
}
}
const wal = input['walArchiveIntervalMinutes'];
const pitr = input['pitrRetentionDays'];
if (pitr !== 0 && wal === null) {
issues.push({
code: 'PITR_REQUIRES_WAL',
path: '$.pitrRetentionDays',
message: 'PITR retention requires WAL archival',
});
}
if (wal !== null && pitr === 0) {
issues.push({
code: 'WAL_REQUIRES_PITR',
path: '$.walArchiveIntervalMinutes',
message: 'WAL archival requires positive PITR retention',
});
}
if (
isPositiveInteger(input['targetRpoMinutes']) &&
isPositiveInteger(input['baseBackupIntervalHours']) &&
(wal === null || isPositiveInteger(wal))
) {
const mechanismMinutes = wal === null ? input['baseBackupIntervalHours'] * 60 : wal;
if (mechanismMinutes > input['targetRpoMinutes']) {
issues.push({
code: 'RPO_BETTER_THAN_MECHANISM',
path: '$.targetRpoMinutes',
message: `configured mechanism can only support ${mechanismMinutes} minutes`,
});
}
}
if (tier === 'high-assurance') {
const weakened =
!isPositiveInteger(input['targetRpoMinutes']) ||
input['targetRpoMinutes'] > 15 ||
!isPositiveInteger(input['targetRtoMinutes']) ||
input['targetRtoMinutes'] > 4 * 60 ||
!isPositiveInteger(input['baseBackupIntervalHours']) ||
input['baseBackupIntervalHours'] > 24 ||
!isPositiveInteger(wal) ||
wal > 5 ||
!isNonnegativeInteger(pitr) ||
pitr < 35 ||
!isPositiveInteger(input['restoreTestIntervalDays']) ||
input['restoreTestIntervalDays'] > 30 ||
!isPositiveInteger(input['breakGlassDrillIntervalDays']) ||
input['breakGlassDrillIntervalDays'] > 90;
if (weakened) {
issues.push({
code: 'HIGH_ASSURANCE_WEAKENED',
path: '$',
message: 'high-assurance posture may be strengthened but not weakened',
});
}
}
if (issues.length > 0) return { ok: false, issues };
return { ok: true, value: input as unknown as RecoveryPostureV1 };
}
export interface RecoveryPostureOverrideAuditV1 {
actorId: string;
reason: string;
effectiveAt: string;
policyRevision: string;
previous: RecoveryPostureV1;
next: RecoveryPostureV1;
}

View File

@@ -0,0 +1,16 @@
{
"extends": "../../tsconfig.base.json",
"compilerOptions": {
"noEmit": true,
"incremental": false,
"declaration": false,
"declarationMap": false,
"sourceMap": false,
"baseUrl": ".",
"paths": {
"drizzle-orm": ["../../packages/db/node_modules/drizzle-orm/index.d.ts"],
"drizzle-orm/pg-core": ["../../packages/db/node_modules/drizzle-orm/pg-core/index.d.ts"]
}
},
"include": ["contracts/*.ts"]
}

View File

@@ -124,7 +124,7 @@ paths:
{
summary: Submit Mos handoff,
parameters: [{ $ref: '#/components/parameters/correlation' }],
requestBody: { $ref: '#/components/requestBodies/MosHandoff' },
requestBody: { $ref: '#/components/requestBodies/Handoff' },
responses: { '200': { description: Receipt } },
},
}
@@ -261,7 +261,7 @@ components:
},
},
}
MosHandoff:
Handoff:
{
required: true,
content:

View File

@@ -0,0 +1,59 @@
VERDICT: GO
# Native Kanban/SOT canon independent re-review 2
Independent read-only re-review of the complete updated staged canon. Prior proposal-audit blocker is closed; no KCR-001016 regression or new blocker found.
## Prior blocker closure
- `contracts/kanban-schema.v1.ts:836-837` declares the required unique `task_events(workspace_id,id)` key before proposal declaration.
- `contracts/kanban-schema.v1.ts:885-894` adds both composite proposal audit FKs—submission and accepted-command event—to that exact workspace-aware key with `RESTRICT`.
- Declaration/migration order is executable and explicit in `SHARED-CONTRACT.md:79-91`: events/key first, proposal table second, both FKs third/fourth, then command enablement. This avoids forward-reference/circular-DDL ambiguity.
- Submission/acceptance semantics are frozen in `SHARED-CONTRACT.md:87-91`: preallocate proposal ID; create exact `change_proposal.submitted` event and proposal in one transaction; on acceptance lock proposal/target, execute the normal command, and bind only a same-workspace/target event with submission causation and `payload.changeProposalId` equal to the locked proposal.
- Required missing, foreign-workspace, unrelated-proposal, unrelated-target, and unrelated-command negatives are explicit in `REQUIREMENTS.md` REQ-SOT-004 and `SHARED-CONTRACT.md:121`; KBN-100/110/140 own migration, service, and integration evidence.
## KCR closure matrix
| KCR | Status |
| ------------------------------------------------------ | ------ |
| 001 health/proof | CLOSED |
| 002 error discrimination | CLOSED |
| 003 approval/assignment binding | CLOSED |
| 004 monotonic fencing/composites | CLOSED |
| 005 tenant-safe relations | CLOSED |
| 006 outage proposal persistence/commands/audit binding | CLOSED |
| 007 dependency/API freeze sequencing | CLOSED |
| 008 concrete N-1 map | CLOSED |
| 009 dependency uniqueness | CLOSED |
| 010 project congruence | CLOSED |
| 011 immutable audit retention | CLOSED |
| 012 retry/quarantine/vocabulary | CLOSED |
| 013 archive/tags target semantics | CLOSED |
| 014 recovery validator/owner slice | CLOSED |
| 015 pure Coordinator split | CLOSED |
| 016 health code/state pairing | CLOSED |
Fixed invariants remain consistent: PostgreSQL is sole writable SOT; writes require transaction-local proof and fail closed; exports never import sources; notes are attributable proposals only; Coordinator has no scope/gate/certify/merge authority; Certifier has no merge authority.
## Reproducible validation evidence
Executed read-only with current-stack config/toolchain `/src/mosaic-mono-v1`:
```text
./node_modules/.bin/prettier --config /src/mosaic-mono-v1/.prettierrc --check <all 9 publication artifacts>
PASS: All matched files use Prettier code style.
strict TypeScript --noEmit --strict --skipLibCheck --target ES2022 --module NodeNext --moduleResolution NodeNext <four contract copies with current Drizzle node_modules resolution>
PASS
cascade/TODO/TBD/stale-hold grep plus composite-FK/semantic-marker invariant checks
PASS
```
The TypeScript check used a disposable copy under `/home/hermes/agent-work` solely to provide external-file NodeNext dependency resolution; the reviewed staging artifacts were not modified.
## Residual findings
None blocking. Implementation must execute the frozen KBN-100/KBN-110/KBN-140 proposal-event-chain tests and SecReview evidence before feature release, as already required by the canon.
No artifact source repository, branch, PR, or provider state was modified.

View File

@@ -0,0 +1,357 @@
# Independent Review — Native Kanban/SOT Canon
**Reviewer:** `enhance-sol` (independent of author `planner-sol`)
**Date:** 2026-07-13
**Review mode:** design/contract only; read-only against the staged canon
**Source plan:** `/home/hermes/agent-work/planning/mosaic-native-kanban-sot-plan.md` (`sha256:96ea4fb91436ec9a53f371d27276e27f62ecf817662599ff9152df0db55296e5`)
**Canon reviewed:** every listed artifact under `/home/hermes/agent-work/planning/kanban-canon/`, including the four TypeScript contracts; the author scratchpad was also read as validation context.
## Executive verdict
# NO-GO
The canon is not freeze-ready. I found **8 BLOCKERs**, **7 MAJORs**, and **1 MINOR**. The prose preserves the ratified authority model well, but the frozen types/schema leave concrete fail-closed, approval, fencing, tenant, outage-proposal, migration, and parallelization gaps. Those gaps would force implementation lanes either to invent contract semantics or to ship paths that violate fixed invariants.
### Blocking findings
1. Health/write authorization can be represented as contradictory, stale, or caller-asserted state.
2. Coordinator failures collapse authoritative denial, unknown transport outcome, and version conflict into one permissive shape.
3. Assignment proposals and approval proofs have no authoritative relational binding; lease acquisition accepts a forgeable proof DTO.
4. Fencing uniqueness is present, but monotonic fencing and same-task lease/checkpoint binding are not.
5. Workspace-safe accountable-owner, assignment-principal, and evidence/artifact relationships are not frozen.
6. Attributable post-recovery proposals have neither a canonical table nor command contract.
7. The slice graph starts schema/UI work before prerequisite threat and exact API/DTO freezes and contradicts coder4 lane order.
8. P0 claims a migration map while publishing only generic rules; the concrete N-1 transition from current `origin/main` is absent.
---
## Findings
### KCR-001 — BLOCKER — “Healthy” is not a proof and can be contradictory or stale
**Location**
- `contracts/health-state.v1.ts:21-31``KanbanHealthResponseV1` permits every combination of `state`, `readHealthProven`, and `writeHealthProven`.
- `contracts/mechanical-coordinator.v1.ts:40-49``CoordinatorContextV1` accepts a caller-supplied `healthState` enum only.
- `contracts/mechanical-coordinator.v1.ts:255-293` — every Coordinator operation, including mutating operations, accepts that context.
- `SHARED-CONTRACT.md:171-184` — mutations are allowed only after live PostgreSQL read/write probes.
**Violation**
Fixed invariant 2 / `REQ-SOT-002`: mutations must fail closed unless write health is positively proven. The current type permits `{ state: 'healthy', writeHealthProven: false }`, and the Coordinator mutation boundary can be invoked with a stale or fabricated `{ healthState: 'healthy' }`. A Valkey/client-derived enum could therefore be mistaken for write authorization.
**Minimal fix**
1. Make `KanbanHealthResponseV1` a discriminated union with only these legal combinations: `healthy => read=true/write=true`, `read-only-degraded => read=true/write=false`, and `write-unavailable => read=false/write=false`.
2. Do not accept write authority from a public DTO. Require Gateway/domain code to obtain and revalidate a fresh internal PostgreSQL write-health proof at mutation time (including `checkedAt`, bounded validity/policy revision, and transaction-local enforcement).
3. Split pure evaluation context from mutation context; mutation methods must accept only an unforgeable/internal healthy context or perform the probe themselves.
4. Add negative contract tests for contradictory state, expired proof, Valkey-only liveness, and caller-forged `healthy`.
### KCR-002 — BLOCKER — Coordinator error shape can conflate denial, unknown outcome, and conflict
**Location**
- `contracts/mechanical-coordinator.v1.ts:184-216` — one `CoordinatorFailureV1` allows every code to pair with arbitrary `retryable` and either `requestOutcome` value.
- `contracts/health-state.v1.ts:51-106` — the Gateway health contract correctly distinguishes deliberate denial, transport uncertainty, and version conflict.
- `SHARED-CONTRACT.md:177-216` — frozen client semantics require those cases not to be conflated.
**Violation**
Charter E and `REQ-SOT-002`. The current Coordinator result can legally encode `WRITE_HEALTH_UNPROVEN` as `retryable: true, requestOutcome: 'unknown'`, or `VERSION_CONFLICT` as retryable. That permits blind retry or a false “unknown” outcome after an authoritative fail-closed denial.
**Minimal fix**
Replace `CoordinatorFailureV1` with a discriminated union keyed by code/kind:
- deliberate health denial: `not_applied`, `retryable:false`;
- version conflict: `not_applied`, `retryable:false`, current version;
- stale fence/session/eligibility/approval failures: exact non-retry semantics;
- transport failure: a separate `retryable_transport_error`, `unknown`, same idempotency key.
Reuse or map explicitly to `KanbanMutationFailureV1`, and add exhaustive client tests proving 503 authoritative bodies, 502/504/timeouts, and 409 cannot cross-map.
### KCR-003 — BLOCKER — Approval proof is forgeable and is not linked to the persisted proposal
**Location**
- `contracts/mechanical-coordinator.v1.ts:107-137` — proposal and approval DTOs.
- `contracts/mechanical-coordinator.v1.ts:265-270``acquireApprovedLease` accepts the entire `ApprovalProofV1` by value.
- `contracts/kanban-schema.v1.ts:650-688``task_assignments` has no proposal expiry, task version, session binding, or proposal/approval FK.
- `contracts/kanban-schema.v1.ts:823-863``approval_decisions` can target only a task or mission and has no proposal/assignment relation.
- `SHARED-CONTRACT.md:128-137` — lease acquisition requires authoritative approval under the exact policy revision.
**Violation**
Fixed invariant 5 and `REQ-COORD-002/003`. A caller can construct an `ApprovalProofV1`; the schema cannot prove that it belongs to the proposal, workspace, task version, agent/session, unexpired policy revision, or still-current approval. The DTO state vocabulary (`awaiting_approval | policy_pre_authorized`) also does not map directly to the persisted assignment states (`proposed | approved | ...`).
**Minimal fix**
Persist one authoritative proposal/assignment identity with task version, target agent/session, expiry, state, and policy revision. Add a workspace-aware approval relation to that identity. Change lease acquisition to accept IDs, then reload and lock proposal + approval + task inside PostgreSQL and verify workspace, current version, target session, state, expiry, and policy revision before creating the lease. Freeze one state vocabulary across schema and DTOs.
### KCR-004 — BLOCKER — Fencing is unique but not monotonically increasing; relational binding is incomplete
**Location**
- `contracts/kanban-schema.v1.ts:694-743``task_leases` has positive/unique fencing tokens but no monotonic per-task counter.
- `contracts/kanban-schema.v1.ts:748-784` — checkpoints independently carry task, lease, and fencing token.
- `contracts/kanban-schema.v1.ts:905-910` — token equality is deferred to prose; same-task lease binding is not stated.
- `contracts/mechanical-coordinator.v1.ts:140-175` — worker commands depend on fencing safety.
**Violation**
Fixed invariant 12 / `REQ-COORD-003`. Uniqueness permits token 10 followed by token 9. A lease can reference assignment A while naming task B in the same workspace, and a checkpoint can reference lease A while naming task B. `bigint(..., { mode: 'number' })` also eventually loses integer precision in JavaScript.
**Minimal fix**
Add a durable per-task fencing counter (or equivalent PostgreSQL sequence row) incremented atomically under task lock and use the returned value for every new lease. Add workspace-aware composite constraints tying lease to its exact task+assignment and checkpoint to exact task+lease+fence. Use bigint-safe representation (`bigint`/serialized decimal), and test monotonicity, concurrent claims, stale lower tokens, and mismatched same-workspace IDs.
### KCR-005 — BLOCKER — Hard tenant boundary is not frozen for several polymorphic relationships
**Location**
- `contracts/kanban-schema.v1.ts:315-318` and `475-478` — project/task accountable owners are unvalidated `(kind, text id)` pairs.
- `contracts/kanban-schema.v1.ts:659-663` — assignment principals are unvalidated `(kind, text id)` pairs.
- `contracts/kanban-schema.v1.ts:758` and `841` — checkpoint/evidence artifact relationships are JSON arrays without workspace-aware FKs.
- `SHARED-CONTRACT.md:89-96` — only selected polymorphic checks are delegated to domain transactions; owner/principal/evidence checks are not included.
- `REQUIREMENTS.md:101-108` — every relationship must reject cross-workspace IDs.
**Violation**
Fixed invariant 7 / `REQ-TEN-001` and `REQ-ID-001`. The frozen schema can name a team or agent from another workspace as owner/assignee, and can embed foreign-workspace artifact IDs in checkpoint or approval evidence arrays. A global user ID is also insufficient without active workspace membership validation.
**Minimal fix**
Use workspace-aware owner/assignment join tables or separate nullable user/team/agent columns with exactly-one checks and composite FKs where possible. Model checkpoint/evidence artifact links as workspace-scoped join rows, or freeze explicit transaction checks for every ID. Require active workspace membership for user principals and workspace-agent/session consistency for agent principals. Add DB/repository/API/Coordinator cross-workspace negative tests without existence oracles.
### KCR-006 — BLOCKER — Post-recovery outage proposals have no canonical persistence or command surface
**Location**
- `REQUIREMENTS.md:93-99` — proposal submission and authorized accept/reject are required.
- `SHARED-CONTRACT.md:26-29` — outage notes may return only as authenticated proposals.
- `SHARED-CONTRACT.md:243-267` — the thin command/query contract contains no proposal submit/get/accept/reject operations.
- `contracts/kanban-schema.v1.ts:1-916` — no proposal table captures proposed command, target/version, attribution, lifecycle, or decision.
- `TASKS.md:99-108` — KBN-110 does not own an outage-proposal command path.
**Violation**
Fixed invariant 4 / `REQ-SOT-004`. An implementation lane would have to invent storage or misuse artifacts/approval gates. Either path risks silently applying an outage note or creating shadow state.
**Minimal fix**
Add a workspace-scoped `change_proposals`/`outage_proposals` contract with authenticated proposer, source note digest, target aggregate, expected version, proposed typed command/payload, pending/accepted/rejected state, decision actor/reason/time, idempotency key, and audit linkage. Add explicit submit/query/accept/reject Gateway commands. Acceptance must execute the normal command in a healthy transaction; a proposal itself can never claim, order, satisfy a gate, or mutate the target.
### KCR-007 — BLOCKER — Parallel slice ordering is not freeze-safe and contains a direct lane-order contradiction
**Location**
- `TASKS.md:43-60` — dependency graph makes KBN-010 and KBN-100 siblings.
- `TASKS.md:88-97` — KBN-100 nevertheless depends on KBN-010 threat findings that alter constraints.
- `SHARED-CONTRACT.md:243` and `INDEX.md:44-50` — exact route names/DTO placement remain unresolved.
- `TASKS.md:110-130` — KBN-120/130 depend on a frozen endpoint/DTO contract, while mocks may begin before KBN-110 lands.
- `TASKS.md:145-153` — KBN-200 says lane-serial after KBN-120.
- `TASKS.md:248-254` — wave table runs KBN-200 before KBN-120.
**Violation**
Charter C and the mandatory freeze-before-parallelize gate. Schema can begin before tenant/threat findings are complete; web/CLI consumers have only semantic operations, not exact DTO/endpoint contracts; coder4 has two opposite legal orders. This does not create same-file edits immediately, but it guarantees contract invention or rework across active lanes.
**Minimal fix**
1. Make KBN-010 (or an explicit constraint-impact gate from it) a completed prerequisite of KBN-100.
2. Add a small serialized KBN-105 endpoint/DTO/endpoint-registry freeze, with exact request/response/error DTOs, before KBN-120 and KBN-130 implementation.
3. Choose one coder4 lane order and use it consistently in slice text, graph, and wave table.
4. Name the exact MCP-owned files or assign their Gateway changes to coder3 before coder4 starts.
### KCR-008 — BLOCKER — Claimed P0 migration map is absent; concrete N-1 hazards remain unresolved
**Location**
- `MISSION-MANIFEST.md:153-157` — P0 says to publish a migration map and states the build hold is lifted at line 3.
- `SHARED-CONTRACT.md:101-121` — only generic expand/backfill/contract rules are supplied.
- `contracts/kanban-schema.v1.ts:1-916` — target-state declarations reuse live table names and make target fields required.
- Current foundation evidence: `origin/main:packages/db/src/schema.ts:120-301` has no workspace keys, nullable project/mission links, legacy text status vocabularies, `tasks.tags`, `tasks.assignee`, `tasks.due_date`, mission JSON milestones/config, `mission_tasks.status`, and legacy agent fields.
**Violation**
Charter D / `REQ-MIG-001` and the P0 exit claim. The generic rule is correct, but coder2 lacks the required field-by-field transition map. A direct Drizzle reconciliation could attempt type narrowing/status conversion, add required workspace/project/owner columns too early, or drop legacy columns before N-1 readers and writers are retired.
**Minimal fix**
Publish a concrete current-main delta map before lifting the hold. For each existing table/column, specify expand, backfill, compatibility read/write, switch, and contract release. At minimum cover:
- nullable-first `workspace_id`, required project/owner fields, and workspace backfill;
- legacy task/project/mission status aliases or shadow columns before v1 emission;
- `mission_tasks.status` read retirement and write-source prohibition;
- mapping/retention for tags, assignee, due date, mission description/config/milestones, and agent fields;
- current milestone circular FK ordering;
- empty, production-shape, partial-resume, and rollback/downgrade tests already named in §4.
Explicitly require legacy columns to remain in the unified Drizzle declaration during the expand/N-1 window.
### KCR-009 — MAJOR — Dependency uniqueness permits parallel duplicate edges
**Location**
- `contracts/kanban-schema.v1.ts:561-567` — unique key includes `dependencyType`.
- `SHARED-CONTRACT.md:47-49` — calls for a unique directed edge.
- `REQUIREMENTS.md:142-149` — duplicate edge attempts must fail.
**Violation**
`REQ-DEP-001`. The same predecessor/successor pair can be inserted three times, once per dependency type. That is not a unique directed edge and complicates readiness semantics.
**Minimal fix**
Make `(workspace_id, predecessor_task_id, successor_task_id)` unique independent of type, or explicitly redefine the requirement as one edge per type and freeze deterministic multi-edge completion semantics. The source plan says unique directed edge, so the former is the minimal faithful fix.
### KCR-010 — MAJOR — Same-workspace planning relationships can contradict the project hierarchy
**Location**
- `contracts/kanban-schema.v1.ts:325``projects.currentMilestoneId` has no FK in the declaration.
- `contracts/kanban-schema.v1.ts:427-448` — mission/milestone association checks workspace but not common project.
- `contracts/kanban-schema.v1.ts:490-516` — a tasks project, mission, milestone, and parent only need share a workspace, not a project.
- `contracts/kanban-schema.v1.ts:905-908` — only current milestone is mentioned as a deferred invariant.
**Violation**
`REQ-PLAN-001` and schema correctness. A task in project A can point to a mission/milestone/parent task from project B in the same workspace. A mission can associate a milestone from another project despite having one required project.
**Minimal fix**
Add project-congruent composite keys/FKs (or freeze mandatory transaction checks) for task→mission, task→milestone, task→parent, mission→milestone, and project→current milestone. Add same-workspace/same-project negative tests.
### KCR-011 — MAJOR — Immutable/append-only records can be erased by parent cascades
**Location**
- `contracts/kanban-schema.v1.ts:798-818``task_events` is described as append-only but remains under a workspace cascade.
- `contracts/kanban-schema.v1.ts:911` — only application-role UPDATE/DELETE privilege removal is stated.
- Numerous canonical relationships use `onDelete('cascade')`, including workspace roots and artifact/checkpoint/event owners.
- `REQUIREMENTS.md:41-43` and `154-170` — audit must be append-only, attributable, and reconstructable.
**Violation**
`REQ-AUD-001`. Revoking direct DELETE on `task_events` does not prevent a parent delete from cascading into the audit log. Checkpoints and immutable artifacts also lack explicit append-only privilege/retention semantics.
**Minimal fix**
Use lifecycle/archive states and `RESTRICT` for canonical parent deletion during normal operation. Freeze a separate, audited retention/break-glass purge procedure. Apply INSERT/SELECT-only or equivalent immutability controls to task events, checkpoints, and immutable artifacts, and test that parent deletion cannot silently erase them.
### KCR-012 — MAJOR — Coordinator persistence lacks durable quarantine/retry state and DTO/schema alignment
**Location**
- `contracts/mechanical-coordinator.v1.ts:239-244` — expiry returns `quarantined` IDs.
- `contracts/kanban-schema.v1.ts:457-490` — task has only untyped `retryPolicy` metadata and no quarantine/execution disposition.
- `contracts/mechanical-coordinator.v1.ts:173``evidenceIds` has no corresponding evidence table/type; schema has artifacts.
- `contracts/kanban-schema.v1.ts:479`, `663`, and agent role JSON — specialist roles are free text despite the frozen role vocabulary in `mechanical-coordinator.v1.ts:19-29`.
**Violation**
`REQ-COORD-004` and internal consistency. PostgreSQL cannot deterministically reconstruct why/when a task was quarantined, its bounded retry state, or which typed evidence was submitted. Free-text roles allow the schema and engine to disagree.
**Minimal fix**
Freeze a durable execution/retry/quarantine record (attempt count, next eligibility, terminal reason, actor/policy, timestamps, version) or typed task columns with events. Align `evidenceIds` to artifact IDs or add a real evidence entity. Use one specialist-role enum/check across tasks, assignments, agents/sessions, DTOs, and Coordinator.
### KCR-013 — MAJOR — Thin MVP promises task archive and tag filtering without target-state semantics
**Location**
- `REQUIREMENTS.md:182-193` — users must archive tasks and filter by tags.
- `SHARED-CONTRACT.md:252-267` — mutations include cancel but not archive task.
- `contracts/kanban-schema.v1.ts:457-490` — no task archive field and no typed tags field/table.
- Current `origin/main` already has `tasks.tags`, making omission from the target declaration a migration-loss hazard.
**Violation**
`REQ-UI-001/002` and internal acceptance consistency. “Archive” cannot be implemented without inventing whether it means cancelled, hidden, or soft-deleted; tag filtering has no frozen storage/query contract.
**Minimal fix**
Either remove task archive/tag acceptance from P1, or add explicit non-lifecycle archival semantics (`archived_at/by/reason`) and a workspace-safe tags model/query contract. Preserve/migrate the current tags column until the selected model is live.
### KCR-014 — MAJOR — Recovery contract states critical rules only in comments and has no owning implementation slice
**Location**
- `contracts/recovery-posture.v1.ts:97-147` — exported JSON Schema validates only local field shapes.
- `contracts/recovery-posture.v1.ts:150-156` — PITR/WAL, effective RPO, off-cluster, high-assurance minima, and audit rules are comments only.
- `REQUIREMENTS.md:270-277` — parser rejection of impossible combinations is acceptance-critical.
- `TASKS.md:75-244` — no bounded slice owns recovery config parsing, override audit, backup/WAL setup, or restore/break-glass evidence.
**Violation**
`REQ-REC-001`. A consumer using the advertised JSON Schema can accept weakened high-assurance values, PITR without WAL, or an impossible RPO. The task plan has no lane accountable for closing that acceptance criterion.
**Minimal fix**
Export a normative `validateRecoveryPostureV1`/schema refinement with machine-testable cross-field checks and add a bounded Infra/recovery slice (serialized if it touches shared config) owning config parsing, override audit, mechanism verification, restore test, and break-glass evidence. Recovery config must continue to expose no authority/gate knobs.
### KCR-015 — MAJOR — Pure Coordinator slice cannot implement two frozen methods without persistence access
**Location**
- `contracts/mechanical-coordinator.v1.ts:259-263``explainEligibility` receives only `taskId`, not a structured snapshot.
- `contracts/mechanical-coordinator.v1.ts:289-293``recoverFromPostgres` explicitly reads PostgreSQL.
- `TASKS.md:145-153` — KBN-200 is a pure engine with no SQL, Drizzle, Gateway, or Valkey.
- `TASKS.md:157-164` — persistence belongs to coder3/KBN-210.
**Violation**
Charter C and internal consistency. coder4 cannot implement the frozen port in a pure package without crossing coder3s persistence boundary. If coder3 implements the port instead, KBN-200s acceptance and ownership are misassigned.
**Minimal fix**
Split the contract into a pure decision engine that receives complete immutable snapshots and a persistence/orchestration service port implemented by KBN-210. Move `recoverFromPostgres` and ID-based loading to the adapter/service; make pure explanation accept a snapshot.
### KCR-016 — MINOR — Health denial code/state pairs are not correlated by type
**Location**
- `contracts/health-state.v1.ts:35-61` — either denial code can pair with either degraded state.
- `SHARED-CONTRACT.md:188-190` — prose defines `KANBAN_WRITE_UNAVAILABLE` specifically for `write-unavailable`.
**Violation**
Health contract precision. A client can receive a semantically inconsistent authoritative body even after KCR-001s broader state fix.
**Minimal fix**
Make deliberate denial a two-variant union with exact code/state pairing.
---
## Clean checks / invariants that do hold
The review did **not** find a gap in these areas:
- The canon consistently selects current `mosaicstack/stack` + Drizzle/PostgreSQL and rejects greenfield/Prisma revival.
- Every artifact states PostgreSQL is the sole writable SOT and Valkey/files are non-authoritative.
- Generated `TASKS.md`, `mission.json`, and exports are consistently declared read-only and never import sources. KBN-300s importer is scoped to immutable legacy JSON/Vikunja snapshots, not generated projections.
- Recovery config exposes recovery fields only; it contains no direct fail-open, SOT, Coordinator-authority, or gate-waiver knob.
- The Coordinator interface contains no `createTask`, acceptance-edit, gate-waive, certify, merge, release, or provider-close method. `submitForReview` is type-limited to `in_review`, not `done` or `certified`.
- Certifier is consistently final independent gate with no merge authority.
- The seven canonical task status values match across requirements, shared prose, schema, and Coordinators ready/in-review surfaces.
- One-active-lease partial uniqueness, no-self-edge, outbox aggregate-revision/event-type uniqueness, optimistic task/project/mission/milestone versions, and N-1 test categories are explicitly present.
- The file-tree partition is mostly well separated once the ordering/freeze defects in KCR-007 are corrected.
## Required re-review scope
After remediation, re-review at minimum:
1. health/coordinator discriminated unions and mutation-time health proof;
2. proposal/approval/assignment/lease relational model;
3. monotonic fencing and composite bindings;
4. tenant-safe polymorphic relationships;
5. outage-proposal persistence and commands;
6. concrete current-main migration map;
7. corrected dependency graph and exact API/DTO freeze;
8. recovery validator/owner slice;
9. all schema and DTO vocabulary alignment.
## Overall verdict
**NO-GO — 8 BLOCKERs must be resolved before the v1 contract is frozen or parallel implementation begins.**

View File

@@ -0,0 +1,38 @@
# #751 Native Kanban/SOT canonical publication — Ultron final gate
**Verdict: GO** — zero BLOCKER/HIGH findings.
## Scope / integrity
- Reviewed `/home/hermes/agent-work/stack-kanban-canon` staged delta only: exactly 16 documentation/contract artifacts; no unstaged delta; `git diff --cached --check` passes.
- This is a publication canon, not a runtime implementation. The explicit implementation hold prevents feature work until canon merge and prerequisite release (`docs/requirements/native-kanban-sot.md:8-9`; `docs/native-kanban-sot/TASKS.md:45-67`).
## Acceptance mapping and findings
| Requirement area | Final evidence / result |
| ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Sole PostgreSQL SOT, generated projections, outage proposals | Requirements D3/D4 and fixed invariants prohibit alternate writers and import (`docs/requirements/native-kanban-sot.md:22-23,32-44`). Health contract keeps public observation separate from branded transaction-local proof (`contracts/health-state.v1.ts:44-84`) and freezes 503/409/502/504 mappings (`:91-184`). Proposal table uses workspace-aware event FKs (`contracts/kanban-schema.v1.ts:847-908`); exact submission/acceptance transaction semantics are specified (`SHARED-CONTRACT.md:81-89`). PASS. |
| Workspace tenancy, planning, assignments, evidence | Workspace-composite task and proposal relations plus active-member rules are explicit (`SHARED-CONTRACT.md:40-48`; `kanban-schema.v1.ts:587-637,875-908`). Lease/checkpoint relations bind workspace/task/assignment/session/fence, with one active lease and bigint fencing (`:1062-1114`). PASS. |
| Coordinator, gates, concurrency/recovery | Pure Coordinator has snapshot-only decision methods (`mechanical-coordinator.v1.ts:186-198`); persistence port owns locked ID validation and recovery (`:371-407`). Requirements forbid Coordinator scope/gate/certification/merge authority and Certifier merge authority (`requirements:39-40`; `MISSION-MANIFEST.md` authority table). Recovery validator rejects unknown fields, PITR/WAL/RPO/storage/high-assurance violations (`recovery-posture.v1.ts:193-369`). PASS. |
| Migration/N-1/API/task decomposition | N-1 expand/backfill/compatibility/switch/contract order and proposal DDL sequence are concrete (`SHARED-CONTRACT.md:69-115`). Frozen exact Gateway/DTO registry and non-overlapping lane ownership/prerequisites are present (`SHARED-CONTRACT.md:244-282`; `TASKS.md:45-67,81-259`). PASS. |
| Documentation / seven owner decisions / evidence | D1D7 are all explicitly ratified (`requirements:20-26`); all 26 REQ sections contain acceptance criteria. Index/manifest/task graph link requirements, frozen contracts, ownership, and evidence. Relative-link audit passes. PASS. |
## Independent verification performed
```text
git diff --cached --check PASS
./node_modules/.bin/prettier --check <all publication paths> PASS
./node_modules/.bin/tsc --noEmit --strict <health/coordinator/recovery> PASS
Python relative Markdown link audit PASS (0 errors)
Python requirement acceptance audit PASS (26 requirements; 0 missing acceptance sections)
Static staged scope/status check PASS (16 staged docs-only; no unstaged delta)
```
The full schema-contract strict type check cannot resolve `drizzle-orm` from this docs-only worktree; this is an environment dependency-resolution limitation, not a contract diagnostic. Independent external publication validation and final re-review record the strict all-four-contract check against the current Stack Drizzle toolchain as PASS.
## Residual items
- **LOW:** implementation must deliver the declared KBN-100/KBN-110/KBN-140 proposal-event-chain, tenant, failure-mapping, and SecReview evidence before P0/P1 release. This is a forward implementation obligation already frozen in the canon, not a publication defect.
- **LOW:** selected infrastructure backup provider/recovery tier and migration/cutover thresholds remain owner-controlled implementation decisions, bounded by the normative recovery contract and change control.
No source, staging, commit, provider, CI, or deployment state was mutated.

View File

@@ -0,0 +1,368 @@
# Native Kanban and Canonical Task SOT — Canonical Requirements
**Status:** RATIFIED and independently approved for canonical publication under issue [#751](https://git.mosaicstack.dev/mosaicstack/stack/issues/751)
**Date:** 2026-07-14
**Decision owner:** Jason
**Publication owner:** web1 control plane (`mos-claude`; `mosaic-100` acting during Claude quota outage)
**Implementation foundation:** current `mosaicstack/stack` main only
**Implementation hold:** no feature implementation begins until this canon is squash-merged to `main` with terminal-green CI.
## 1. Purpose
Deliver Mosaic Stack's native project/task control plane and thin writable Kanban on one authoritative PostgreSQL model. This document formalizes the ratified source plan; it does not create a parallel design.
Normative terms **MUST**, **MUST NOT**, **SHOULD**, and **MAY** are binding as used here.
## 2. Ratified decisions
| # | Ratified decision | Canonical result |
| --- | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| D1 | Foundation | Extend current `mosaicstack/stack` main with its existing Drizzle/PostgreSQL, NestJS Gateway, Next.js, Better Auth, and Valkey/BullMQ conventions. No greenfield service and no Prisma revival. |
| D2 | Tenant boundary | `workspace_id` is the hard tenant boundary from the first migration. Teams are authorization groups inside a workspace, never tenant substitutes. |
| D3 | Outage authority — Option A with amendment | PostgreSQL is the sole writable SOT and mutations fail closed whenever DB write-health cannot be proven. The amendment permits deployment-specific **recovery posture only**; it does not permit an alternate writer. Human outage notes are attributable post-recovery proposals, never shadow state. |
| D4 | Generated files | `TASKS.md`, `mission.json`, and any file export are generated, read-only, non-authoritative, and never import sources. Generate on demand; commit only where repository review policy requires a snapshot. |
| D5 | Status model | Task statuses are `backlog`, `ready`, `in_progress`, `blocked`, `in_review`, `done`, `cancelled`. Runtime readiness is orthogonal and computed. |
| D6 | Coordinator approval | Hybrid: manual Project Sub-Orchestrator approval by default; automatic routing only under an explicit, approved, versioned low-risk policy. |
| D7 | Initial migration scope | Project, mission, milestone, task, tags/archive, dependency, assignment, outage proposal, evidence/link, and orchestration state only. Calendar, email, GLPI cache, and personal-brain features remain out of scope. |
## 3. Fixed invariants — every deployment
These are not tier settings and cannot be weakened by deployment configuration.
1. PostgreSQL is the **sole writable source of truth**.
2. The implementation uses Drizzle on current stack main.
3. Kanban and orchestration mutations **fail closed** unless DB write-health is positively proven `healthy`.
4. No failed mutation is redirected to Markdown, JSON, browser storage, Valkey, queue payloads, scratchpads, or provider issues.
5. `TASKS.md` and all file exports are generated, read-only, non-authoritative, and never parsed for import.
6. Human notes created during an outage become attributable proposals only after recovery. They do not reserve work, change status, satisfy a gate, or establish ordering.
7. Valkey is derived, expendable coordination infrastructure. PostgreSQL retains task truth, leases, fencing, audit, and the transactional outbox.
8. The Mechanical Coordinator is non-LLM and deterministic. It may evaluate eligibility, dependencies, approval policy, leases, fencing, heartbeat, retry, expiry, and quarantine. It cannot invent scope, alter acceptance criteria, waive gates, certify, or merge.
9. **Certifier** is the final independent quality-gate role. Certifier may pass, reject, or escalate with evidence; it has no merge authority.
10. Every business and orchestration record is workspace-scoped; cross-workspace relationships are rejected.
11. Every mutation is idempotent and expected-version checked where it changes an aggregate.
12. Stale worker mutations are rejected by monotonically increasing fencing tokens.
13. Audit events are append-only and attributable; authoritative state is reconstructable from PostgreSQL without Valkey or files.
## 4. Configurable recovery posture only
Deployment tiers configure durability and operational recovery targets. They never configure SOT authority, fail-open writes, or gate bypass.
### 4.1 Tier defaults
| Setting | Lite | Standard | High-assurance |
| --------------------------- | --------------------------------------: | ------------------------------------------------------------: | ----------------------------------------------------------------------: |
| Target RPO | 24 hours | 1 hour | **15 minutes** |
| Target RTO | 24 hours | 8 hours | **4 hours** |
| Base backup cadence | Daily | Daily | **Daily** |
| WAL archive cadence | Disabled | Every 15 minutes | **Every 5 minutes** |
| PITR retention | 0 days / disabled | 14 days | **35 days** |
| Restore test frequency | Quarterly | Quarterly | **Monthly** |
| Break-glass drill frequency | Annually | Semiannually | **Quarterly** |
| Off-cluster storage | One encrypted off-cluster backup target | Encrypted off-cluster object storage, separate failure domain | **Encrypted off-cluster base backups and WAL, separate failure domain** |
A deployment MAY override defaults only through the validated recovery-posture contract. An override MUST record actor, reason, effective time, and policy revision. A claimed RPO MUST be no smaller than the actual backup/WAL mechanism can support. Enabling PITR requires WAL archival and off-cluster storage.
## 5. Functional requirements and acceptance criteria
### REQ-SOT-001 — Sole writable PostgreSQL authority
**Requirement:** All project, mission, milestone, task/tag/archive, dependency, assignment, execution/quarantine, lease, checkpoint, approval, outage proposal, event, link, artifact, and outbox mutations MUST commit through Gateway domain services into PostgreSQL.
**Acceptance:**
- Mutation journey tests show web, CLI, MCP, and agents invoke typed Gateway commands.
- Static/process inventory finds no file, Valkey, browser, or provider issue writer acting as canonical state.
- PostgreSQL state survives Valkey loss and reconstructs the same aggregate revisions.
### REQ-SOT-002 — Fail-closed mutation health
**Requirement:** A mutation MUST execute only while health state is `healthy`. `read-only-degraded` and `write-unavailable` MUST return the frozen deliberate-denial error contract and MUST NOT enqueue a hidden write.
**Acceptance:**
- Public health response is a discriminated union; contradictory state/proof combinations fail contract validation.
- Mutation methods accept only a fresh internal PostgreSQL transaction-local write proof, never caller-asserted/public health state.
- Negative tests reject expired proofs, policy-revision mismatch, Valkey-only liveness, and caller-forged `healthy`.
- Fault tests force both degraded states and prove row counts, outbox, files, and Valkey remain unchanged.
- Exact failure mapping proves authoritative 503 denial, retryable 502/504/timeout uncertainty, and 409 version conflict cannot cross-map.
- Replaying the same idempotency key after recovery returns one canonical result.
### REQ-SOT-003 — Generated projections
**Requirement:** `TASKS.md`, `mission.json`, and other exports MUST contain a non-authoritative header, workspace/project IDs, generated time, and source revision. No production parser may mutate DB from an export.
**Acceptance:**
- Generated output matches the API snapshot revision.
- Hand editing a projection fails CI validation or is overwritten by regeneration.
- Repository search finds no import path from generated projections.
### REQ-SOT-004 — Attributable outage proposals
**Requirement:** Human outage notes MAY be captured outside the system but, after recovery, can enter Mosaic only through workspace-scoped `change_proposals` attributed to an authenticated active member. A proposal stores source-note digest, target aggregate/version, typed command/payload, idempotency, lifecycle, decision actor/reason/time, and audit links. It MUST NOT silently change canonical state.
**Acceptance:**
- `(workspace_id, submitted_audit_event_id)` and `(workspace_id, accepted_command_audit_event_id)` are composite foreign keys to `task_events(workspace_id, id)`; missing and foreign-workspace event IDs fail before commit.
- Submission preallocates the proposal ID and atomically inserts `change_proposal.submitted` for that exact workspace/proposal with the new proposal referencing it.
- Accept locks proposal and target, obtains fresh write proof, checks expected version, executes the normal typed command, and atomically links that command's event for the same workspace/target and proposal causation.
- Negative tests reject missing submission events, foreign-workspace submission/acceptance events, and same-workspace events for an unrelated proposal, aggregate, target, or command.
- Tests prove a pending/rejected proposal cannot claim/order work, satisfy a dependency/gate, or mutate any target directly.
### REQ-TEN-001 — Workspace hard tenancy
**Requirement:** Every canonical business/orchestration row MUST carry `workspace_id`. Workspace-aware constraints and authorization MUST prevent cross-tenant relationships and reads/writes.
**Acceptance:**
- API, repository, import, WebSocket, and Coordinator negative tests reject foreign-workspace IDs without existence oracles.
- Project/task owners use exactly-one user/team references; assignment principals use exactly-one user/team/agent reference; agent/session targets are workspace-consistent.
- User owners, principals, proposers, and decision actors require ACTIVE workspace membership in the authoritative transaction.
- Dependency, project hierarchy, assignment, lease, checkpoint, approval-evidence, link, artifact, proposal target, and both proposal-audit-event composite relationships reject mixed workspaces.
- Tenant context is derived from authenticated authority, never accepted blindly from request data.
### REQ-ID-001 — Workspace identity and service scope
**Requirement:** Users, teams, agents, and agent sessions MUST be bound to a workspace with explicit role/capability scope. Agents MUST NOT receive raw DB credentials.
**Acceptance:**
- Workspace membership and service-identity tests enforce command-family scope.
- Revoked/disabled agents and ended sessions cannot claim, heartbeat, or submit.
### REQ-PLAN-001 — Normalized planning hierarchy
**Requirement:** Canonical planning entities are projects, milestones, missions, mission-milestone associations, and tasks. A task belongs to one required project and at most one mission/milestone/parent task.
**Acceptance:**
- CRUD tests preserve workspace, hierarchy, versions, and lifecycle constraints.
- Mission membership does not duplicate task status.
- Composite project-congruent constraints reject task→mission, task→milestone, task→parent, mission→milestone, and project→current-milestone mismatches.
- Parent and association constraints reject cycles/orphans where applicable.
### REQ-TASK-001 — Canonical task fields
**Requirement:** Tasks MUST support title, description, structured acceptance criteria, canonical status, priority, fractional board rank, accountable owner, assigned specialist role, due/not-before dates, estimate, progress, explicit blocker, retry policy, normalized workspace tags, non-lifecycle archival (`archived_at/by/reason`), metadata, monotonic fencing counter, and optimistic version.
**Acceptance:**
- API and UI round-trip every field without silent loss.
- Current `tasks.tags`, `assignee`, and `due_date` remain declared/preserved during N-1 and backfill to the canonical model without loss.
- Archive hides work without changing its canonical lifecycle status and requires actor/reason/time.
- Invalid status, rank, progress, date, owner, tag, archive, or retry data is rejected.
- Concurrent expected-version updates produce a visible conflict.
### REQ-TASK-002 — Fixed lifecycle and computed readiness
**Requirement:** Human workflow status MUST use the seven ratified values. Dependency/schedule/policy/lease/retry conditions MUST be exposed as computed readiness, not hidden status rewrites.
**Acceptance:**
- A dependency becoming incomplete changes readiness but does not silently rewrite the Kanban column.
- Readiness explanation identifies all active gates.
- State-machine tests reject illegal transitions and require reasons for blocked/cancelled paths.
### REQ-DEP-001 — Dependency DAG
**Requirement:** Workspace-local directed dependencies MUST be unique and acyclic. A task is dependency-eligible only after every blocking predecessor is `done` and completion conditions pass.
**Acceptance:**
- `(workspace_id, predecessor_task_id, successor_task_id)` is unique independent of dependency type.
- Cycle, duplicate, self-edge, and cross-workspace attempts fail before commit.
- Property/concurrency tests prove all blocking predecessors are evaluated.
- UI displays dependency and readiness errors accessibly.
### REQ-ASN-001 — Assignment is not a lease
**Requirement:** Assignment history and execution leases MUST be separate records. One persisted assignment identity freezes task version, exact target agent/session (or exactly-one non-agent principal), specialist role, expiry, state, policy revision, proposer, reason, and timestamps. Approval decisions relate to that assignment with workspace-aware constraints.
**Acceptance:**
- One assignment-state vocabulary is identical across schema, DTO, and engine.
- Lease acquisition accepts IDs only, then reloads and locks assignment, approval, task, and target session to verify workspace, current task version, exact target, state, expiry, and policy revision.
- Reassignment preserves history; assignment may exist without a lease; lease expiry does not erase ownership/evidence.
### REQ-AUD-001 — Semantic audit and outbox
**Requirement:** Mutating commands MUST append semantic `task_events` with actor, correlation, causation, idempotency key, and aggregate versions in the same transaction as state. Notifications MUST flow from a transactional outbox.
**Acceptance:**
- Atomicity tests prove state/event/outbox commit or roll back together.
- Proposal submission and acceptance tests prove their workspace-bound event links identify the exact submission and executed normal command, not merely an existing event UUID.
- Duplicate idempotency keys return the prior result without duplicate events.
- `task_events`, checkpoints, immutable artifacts, and evidence joins are INSERT/SELECT-only for application roles; parent hard deletes are RESTRICTed.
- Normal lifecycle uses archive/cancel, never hard delete; retention purge requires audited break-glass authority and evidence.
- Valkey outage leaves outbox pending and later replayable.
### REQ-API-001 — Typed Gateway command boundary
**Requirement:** Gateway MUST expose workspace-safe project/task/dependency/assignment/link/artifact/change-proposal queries and explicit lifecycle commands. Generic patching MUST NOT bypass claim, heartbeat, review, certify, proposal acceptance, or completion invariants.
**Acceptance:**
- KBN-105 freezes exact route, request, success, denial, conflict, and transport-normalization DTOs before CLI/web implementation.
- DTO validation, authorization, contract, and integration tests cover each command.
- Exact MCP-owned Gateway files are coder3-owned; coder4 consumes only frozen Gateway contracts.
- Endpoint registry aligns web, CLI, MCP, and generated client paths.
- Direct SQL and raw Valkey writes are absent from clients.
### REQ-UI-001 — Writable thin Kanban/List MVP
**Requirement:** Existing Tasks and Projects surfaces MUST become a real-data writable MVP with one shared query contract.
**Acceptance:**
- Users can create/edit/cancel/archive tasks, open task detail, and move cards within/across columns.
- Server validates transition and persists fractional board rank.
- Refresh, reconnect, CLI, MCP, and generated projection show the same revision.
### REQ-UI-002 — Tenant and work context
**Requirement:** UI MUST show workspace context and support filters for project, mission, milestone, status, priority, owner/specialist, due state, and tags.
**Acceptance:**
- Context is visible on every mutation surface.
- Filter tests cannot expose foreign-workspace data.
- Empty/loading/error states are explicit.
### REQ-UI-003 — Dependency, ownership, lease, and audit visibility
**Requirement:** Task detail MUST separate accountable owner, specialist assignment, active session/lease expiry, dependencies/readiness, acceptance criteria, blocker, external links, and audit timeline.
**Acceptance:**
- Each concept renders from its canonical endpoint.
- A lease is never displayed as ownership or completion.
- Conflict and stale-reconnect states require refresh rather than silent overwrite.
### REQ-UI-004 — Accessible interaction
**Requirement:** Kanban MUST support keyboard-accessible moves, non-drag alternatives, responsive layout, and semantic status/error announcements.
**Acceptance:**
- Keyboard journey performs every card transition available by drag.
- Automated accessibility checks and manual responsive checks pass.
### REQ-COORD-001 — Non-LLM Mechanical Coordinator
**Requirement:** Coordinator decisions MUST be deterministic from structured data and versioned policy. It MUST NOT invoke an LLM to interpret scope or acceptance criteria.
**Acceptance:**
- Pure decision engine receives complete immutable snapshots and performs no ID loading, SQL, Gateway, Valkey, or recovery I/O.
- Persistence/service adapter owns ID loading, transaction-local write proof, locking, persistence, and `recoverFromPostgres`.
- Same snapshot and policy revision produce the same eligibility/order explanation.
- Dependency, schedule, durable retry/quarantine, approval, role, and capacity inputs are auditable.
- Code/config inspection finds no model/provider dependency in the scheduling engine.
### REQ-COORD-002 — Eligibility and approval routing
**Requirement:** Only `ready` tasks under active project/mission, passed dependencies/schedule/retry/release policy, and without active lease may be proposed. Manual approval is default; auto-route requires an explicit approved policy revision.
**Acceptance:**
- Unapproved or gated tasks are never leased.
- Every persisted assignment proposal includes task version, exact target agent/session, expiry, state, deterministic reasons, and policy revision.
- Approval is relationally bound to the assignment identity and cannot be supplied as a forgeable proof-by-value DTO.
- Override/reject/reassign requires an attributable reason.
### REQ-COORD-003 — Atomic lease, heartbeat, fencing, and recovery
**Requirement:** Lease acquisition MUST be atomic in PostgreSQL, permit at most one active lease per task, atomically increment the durable per-task fencing counter under task lock, use bigint-safe tokens, require timely acknowledgement/heartbeat, and reject stale workers. Lease and checkpoint relations MUST bind the exact workspace+task+assignment/session+fence.
**Acceptance:**
- Concurrent claim tests yield one winner and strictly increasing fencing tokens.
- Lower/expired tokens and mismatched same-workspace task/assignment/lease/checkpoint IDs fail.
- Token values round-trip as bigint/decimal strings without JavaScript precision loss.
- Coordinator restart reconstructs lease/retry/quarantine state from PostgreSQL alone.
### REQ-COORD-004 — Retry and quarantine
**Requirement:** Missing acknowledgement, agent loss, or execution failure MUST produce a deterministic release, bounded backoff retry, or quarantine outcome according to retry policy. Ambiguous/non-idempotent work requires Sub-Orchestrator action.
**Acceptance:**
- Durable execution state records disposition, attempt/max, next eligibility, terminal reason, actor/policy, timestamps, and version.
- Retry budget/backoff are bounded and tested.
- Exhausted or non-idempotent failures quarantine with workspace-scoped artifact evidence.
- One specialist-role vocabulary is enforced across schema, sessions, assignments, DTOs, and engine.
- No task loops indefinitely or silently returns to ready.
### REQ-GATE-001 — Role and authority chain
**Requirement:** Canonical flow is User → Interaction → Portfolio Orchestrator → Project Sub-Orchestrator → Gateway → domain services → Mechanical Coordinator → specialists → Certifier.
**Acceptance:**
- Role bindings and approvals are queryable and audited.
- Coordinator cannot create scope or waive gates.
- Certifier cannot merge or close provider artifacts.
### REQ-GATE-002 — Independent review and certification
**Requirement:** Author and reviewer MUST differ. Auth, security, tenant, secrets, and data-integrity surfaces MUST receive mandatory SecReview. Certifier is the final quality gate after remediation.
**Acceptance:**
- Gate tests reject author self-review and missing required SecReview.
- Certifier receives complete traceability/evidence and returns pass/reject/escalate.
- A Certifier pass does not grant merge authority.
### REQ-REC-001 — Recovery posture validation
**Requirement:** A deployment MUST select a validated Lite, Standard, or High-assurance posture and MAY override only recovery knobs.
**Acceptance:**
- Runtime invokes normative `validateRecoveryPostureV1`, not shape-only JSON Schema validation.
- Validator rejects PITR/WAL mismatch, impossible RPO, unknown fields, non-encrypted/non-separated storage, and weakened High-assurance values.
- A bounded recovery/infra slice owns parser wiring, override audit, mechanism verification, restore test, and break-glass evidence.
- High-assurance defaults equal RPO 15m/RTO 4h, encrypted off-cluster WAL every 5m, 35d PITR, daily base backup, monthly restore test, and quarterly break-glass.
### REQ-MIG-001 — One-way shadow migration
**Requirement:** Migration from jarvis-brain/Vikunja MUST use inventory, immutable source snapshots/checksums, one-way shadow import, read reconciliation, write freeze, final delta, cutover, and read-only stabilization. Dual writes are forbidden.
**Acceptance:**
- P0 publishes the current `origin/main` field-by-field expand/backfill/compatibility/switch/contract map before any schema lane starts.
- Legacy columns remain in the unified Drizzle declaration for the entire expand/N-1 window.
- Dry-run/apply/verify modes are idempotent and workspace-safe.
- Import lineage preserves source system/key/file/checksum/batch and rejected-record reports.
- Empty DB, production-shape, partial-resume, downgrade/rollback, status-shadow, workspace-backfill, and `mission_tasks.status` retirement tests pass.
- Shadow records cannot auto-dispatch.
### REQ-MIG-002 — Cutover and rollback safety
**Requirement:** Cutover MUST disable legacy writers and switch all clients to Gateway. Before first DB mutation rollback may switch authority back; afterward rollback requires freeze, DB-delta export/reconciliation, and owner decision.
**Acceptance:**
- Process inventory proves no active jarvis-brain/Vikunja project/task writer.
- Cutover rehearsal meets signed reconciliation thresholds.
- No reverse and forward sync run concurrently.
## 6. Explicit non-goals
The P0P3 canon does not authorize:
- replacing Gitea issue/PR storage;
- calendar, email, GLPI cache, CRM, billing, time tracking, or personal-brain migration;
- arbitrary custom workflows/statuses/fields;
- a writable offline/file/Valkey/browser fallback;
- direct client database access;
- LLM scheduling or autonomous scope invention;
- Coordinator gate waiver, certification, merge, release, or provider issue closure;
- Certifier merge authority;
- full mission designer, portfolio analytics, critical-path UX, or advanced board customization in the thin MVP;
- P4/P5 features unless separately released.
## 7. Global release evidence
P0P3 may close only when requirements traceability maps every requirement above to automated and situational evidence, including cross-workspace denials, DB/Valkey fault injection, concurrent leases, stale fencing, generated-file immutability, UI conflict/reconnect behavior, migration reconciliation, independent review, mandatory SecReview, and final Certifier evidence.

View File

@@ -0,0 +1,43 @@
# #747 — De-hardcode orchestrator and interaction agent names
## Objective
Replace branded Mos/Tess symbols, filenames, DI tokens, and error prose with role-neutral orchestrator/interaction vocabulary without changing env-driven runtime identity behavior. Add optional roster `alias` and `provider` fields and show aliases in `mosaic fleet ps` with name fallback.
## Scope and constraints
- Requirements: `/home/hermes/agent-work/reviews/747-wsa-dehardcode-brief.md`.
- Branch: `feat/747-dehardcode-orchestrator-interaction-names` from `main` at `e72388b2`.
- Keep `MOSAIC_AGENT_NAME` and `MOSAIC_ORCHESTRATOR_AGENT_NAME` unchanged.
- Sample/test data may retain operator display names.
- No behavior change beyond optional roster metadata and alias display.
- Budget: no explicit cap; conservative mechanical-rename scope only.
- TDD: optional and skipped because this is a mechanical rename with existing focused coverage; add focused alias/schema regression coverage before completion.
## Plan
1. Rename coordination and durable-session files and symbols using canonical vocabulary.
2. Scrub branded symbol names and error prose in the assigned source trees while preserving allowed sample data.
3. Extend roster schema with optional `alias` and `provider`; update fleet roster typing/rendering and focused tests.
4. Run grep-clean verification, build, typecheck, lint/format, focused coord/durable-session/fleet tests, and roster validation.
5. Commit, queue-guard, push, open a Gitea PR closing #747, and report to the coordinator.
## Progress
- 2026-07-13: Task resumed from coordinator brief; repository clean at `e72388b2`.
- Renamed coordination and durable-session files, exports, gateway DI symbols, DTOs, services, repositories, and tests.
- Replaced branded authority/error prose while preserving the existing `/api/coord/mos` compatibility route and env-variable identity inputs.
- Added optional roster `alias`/`provider` support and alias-first `fleet ps` display with canonical-name fallback.
## Verification
- `pnpm typecheck`: passed (42 tasks).
- `pnpm build`: passed (23 tasks).
- `pnpm lint`: passed (23 tasks).
- `pnpm format:check`: passed.
- Coordination tests: 7 passed.
- Agent durable-session/runtime tests: 23 passed.
- Gateway coordination/durable-session/integration tests: 20 passed.
- Full `fleet.spec.ts`: 192 passed, including alias/provider parsing and alias display.
- JSON Schema 2020 validation: legacy minimal roster and extended alias/provider roster passed; `alias` and `provider` remain absent from `required`.
- Grep verification: no branded symbol/type/file/DI names or error prose remain in assigned source trees; one allowed `Tess Owner` test-data display name remains.

View File

@@ -0,0 +1,152 @@
# Issue #751 — Native Kanban/SOT canonical publication
## Objective
Publish the owner-ratified P0P3 requirements, mission manifest, task decomposition, and frozen shared contracts before feature implementation.
## Authority and decisions
- Owner: Jason
- Plan owner/orchestrator: web1 control plane; takeover by mosaic-100 during Claude quota outage
- Tracking: Mosaic Stack issue #751
- Foundation: current Stack main + Drizzle/PostgreSQL
- Fixed invariants: PostgreSQL sole writable SOT; writes fail closed; exports never import; outage notes become attributable proposals; mechanical Coordinator has no scope/gate/certify/merge authority; Certifier has no merge authority.
- Recovery posture only is configurable through Lite, Standard, and High-assurance profiles.
## Execution log
- 2026-07-14: Existing planner-sol canon remediation reviewed from staging. KCR-001016 claimed resolved; static checks passed.
- 2026-07-14: Independent GPT/Terra re-review dispatched to rev1.
- 2026-07-14: Re-review returned NO-GO: proposal audit-event IDs were not workspace-bound, leaving attribution forgeable; formatter evidence was not reproducible. Focused remediation round 2 routed to planner-sol.
- 2026-07-14: Remediation bound proposal audit links to `task_events(workspace_id,id)`, froze same-transaction semantic validation and negative tests, and made formatter/type/static checks reproducible.
- 2026-07-14: Independent rev1 re-review returned GO with KCR-001016 closed and no new blocker. Canon copied into the issue #751 publication worktree; feature implementation remains held until merge.
- 2026-07-14: Independent publication validation returned FAIL on formatting/trailing whitespace, stale staging wording, ignored review evidence, and missing worktree dependencies. Bounded publication remediation routed to planner-sol; no runtime source change authorized.
- 2026-07-14: Publication remediation installed locked dependencies outside the repository cache, fixed formatting and wording, and preserved docs-only scope. Independent gaterun revalidation returned PASS across staged scope, formatting, lint, typecheck, strict contract compile, links, rollups, review artifacts, and fixed invariants.
- 2026-07-14: Ultron final gate returned GO with zero BLOCKER/HIGH findings; residual LOW items remain explicit implementation obligations.
- 2026-07-14: First commit attempt was correctly blocked by the lint-staged hook because docs contract `.ts` files were outside TypeScript project-service scope. Added a strict no-emit workstream `tsconfig.json` with exact Drizzle declaration paths; targeted contract TSC, contract ESLint, format, full lint/typecheck, strictness, and docs-only scope independently passed.
## Verification evidence
- Initial review: `docs/reports/native-kanban-sot/canon-initial-review-no-go.md`
- Final GO: `docs/reports/native-kanban-sot/canon-final-rereview-go.md`
- Ultron GO: `docs/reports/native-kanban-sot/ultron-final-go.md`
- Pending: PR gates, squash merge, terminal-green CI, and issue closure.
## Publication remediation session — planner-sol
**Assignment:** Remediate only issue #751 publication blockers from `/home/hermes/agent-work/reviews/751-kanban-canon-publication-validation.md`; no source, package, lock, provider, CI, build, deploy, commit, or push action.
**Plan:**
1. Install the locked pnpm dependencies without modifying package metadata.
2. Replace only stale publication/staging wording while retaining the canon-merge and KBN prerequisite implementation hold.
3. Format all changed candidate Markdown and contract TypeScript; remove trailing whitespace.
4. Run worktree `format:check`, `lint`, `typecheck`, strict no-emit contract compilation, tracked/untracked whitespace checks, and static invariants.
5. Verify package/lock/source paths are unchanged and append exact evidence here.
**Budget:** No explicit token cap; bounded docs-only remediation, no exploratory/runtime work.
**TDD:** Not applicable—documentation/contract-publication formatting and wording only; strict/static validation is the primary gate.
## Publication remediation results
### Changes
- `docs/native-kanban-sot/INDEX.md`: replaced staging/pending-GO wording with current publication and independent-GO wording; retained the merge hold and dependency-ordered KBN prerequisite hold.
- `docs/native-kanban-sot/TASKS.md`: replaced “Mos using this staging set” with “Mos / publication control plane”; made the post-merge KBN prerequisite hold explicit.
- Formatted all changed candidate Markdown and four contract TypeScript files with current-worktree Prettier 3.8.1.
- Removed trailing whitespace from candidate Markdown, including both linked review reports.
- Preserved both review reports and their links; they remain ignored by `.gitignore:11` for coordinator force-tracking.
### Dependency installation
The first target-worktree install attempt used the environment's default root-owned pnpm store and failed without changing package metadata:
```text
cd /home/hermes/agent-work/stack-kanban-canon && pnpm install --frozen-lockfile
EACCES: permission denied, open '/root/.local/share/pnpm/store/v10/server/server.json'
```
Successful locked install using an authorized cache outside the repository:
```bash
cd /home/hermes/agent-work/stack-kanban-canon
pnpm install --frozen-lockfile --store-dir /home/hermes/agent-work/pnpm-store
```
Result: PASS, 1,240 packages installed; lockfile resolution skipped as up to date. `node_modules` remains ignored. Tool versions: pnpm 10.6.2, Prettier 3.8.1, TypeScript 5.9.3, Drizzle ORM 0.45.1, Turbo 2.8.16.
### Exact quality-gate results
```text
pnpm format:check
PASS — All matched files use Prettier code style.
pnpm lint
PASS — 23 successful lint tasks.
pnpm typecheck
PASS — 42 successful tasks. Turbo invoked configured dependency build prerequisites as part of the repository's exact typecheck graph; no standalone build command was run.
```
Candidate formatting commands:
```bash
pnpm exec prettier --write <3 tracked rollups + 9 native-kanban artifacts + requirements + scratchpad>
pnpm exec prettier --check <same files>
pnpm exec prettier --ignore-path /dev/null --write \
docs/reports/native-kanban-sot/canon-initial-review-no-go.md \
docs/reports/native-kanban-sot/canon-final-rereview-go.md
pnpm exec prettier --ignore-path /dev/null --check \
docs/reports/native-kanban-sot/canon-initial-review-no-go.md \
docs/reports/native-kanban-sot/canon-final-rereview-go.md
```
Result: PASS. The explicit `/dev/null` ignore path is required because `docs/reports/` is intentionally ignored pending coordinator force-tracking.
Tracked and untracked whitespace checks:
```text
git diff --check
PASS
git diff --no-index --check /dev/null <each untracked/ignored candidate>
PASS for all candidates
```
Strict contract compilation initially could not resolve pnpm-isolated `drizzle-orm` from the external docs directory. A temporary, removed dependency-context symlink made current-worktree resolution explicit:
```bash
LINK=docs/native-kanban-sot/node_modules
ln -s ../../packages/db/node_modules "$LINK"
trap 'unlink "$LINK"' EXIT
pnpm exec tsc \
--noEmit \
--strict \
--skipLibCheck \
--target ES2022 \
--module NodeNext \
--moduleResolution NodeNext \
docs/native-kanban-sot/contracts/*.ts
```
Result: `strict-contract-noemit=PASS`; temporary link removed.
Static result:
```text
proposal-audit-links=PASS
kcr-invariant-regression=PASS
publication-wording=PASS
vocabulary-alignment=PASS
```
### Scope-integrity evidence
Baseline and final hashes are identical:
```text
package.json 93a50eaefc7a0446a56234e427df03f6a2256f8da17c0bede17c22206928c8c0
pnpm-lock.yaml 8b6448d51ac7797c8f782af52a080c0e38ab8bf364f32624f94e636bf5743229
```
`tracked-package-lock-source-unchanged=PASS`: every tracked/untracked nonignored change remains under `docs/`; no package, lock, application source, plugin source, configuration, CI trigger, standalone build/deploy, container, provider, commit, or push action occurred.

View File

@@ -0,0 +1,55 @@
# Issue #753 — KBN-010 threat, authorization, and constraint-impact gate
## Objective
Complete the mandatory threat/auth/constraint-impact analysis that gates KBN-100 schema implementation.
## Scope
- In: threat matrix, frozen-control mapping, schema/API/test impact inventory, security evidence plan.
- Out: runtime, schema, migration, API, dependency, CI, deployment, and secret changes.
- Canonical requirements: `docs/requirements/native-kanban-sot.md`.
- Frozen contract: `docs/native-kanban-sot/SHARED-CONTRACT.md` and `contracts/*.v1.ts`.
- Tracking: Mosaic Stack issue #753.
## Plan
1. Independently inspect current-main implementation and frozen canon.
2. Enumerate tenant, identity, health-proof, approval, fencing, proposal, audit, token, and outage threats.
3. Map every threat to required constraints, command behavior, negative tests, and owning future slice.
4. Surface any unresolved schema impact as a blocker; do not silently amend the frozen contract.
5. Run documentation/static validation and submit for independent SecReview.
## Execution log
- 2026-07-14: KBN-000 completed through PR #752 and post-merge pipeline #1798.
- 2026-07-14: KBN-010 issue #753 created; task marked in progress; fresh GPT worker pending dispatch.
## Verification evidence
Pending worker validation, independent SecReview, Ultron gate, PR merge, post-merge CI, and issue closure.
## 2026-07-14 worker analysis checkpoint
- Inspected issue #753, canonical requirements, all frozen v1 contracts, and actual `origin/main` at `49e8a54` across DB schema, Better Auth scope, project/task/mission/team repositories/controllers, fleet backlog, and `TASKS.md` parsing/writing.
- Confirmed the worker branch has no source/runtime/schema delta from `origin/main`; orchestrator-owned `.mosaic` state remains dirty and untouched.
- Authored the threat, authorization, constraint-impact, negative-test, and requirements-traceability analysis in `docs/native-kanban-sot/KBN-010-THREAT-AUTH-CONSTRAINT-GATE.md`.
- Gate decision: **BLOCKED** by `KBN010-SI-001`. `missionsV1` lacks a unique candidate key on `(workspace_id, id)`, while `artifacts_workspace_mission_fk` and `approval_decisions_workspace_mission_fk` both reference that exact pair. PostgreSQL cannot create the frozen composite foreign keys as declared.
- Decision: do not select or apply a schema fix. Contract authority must version either a `(workspace_id, id)` mission candidate key or project-congruent child keys, then obtain independent re-review before KBN-100.
- Additional risks are controlled by frozen transaction/API behavior but require the exact future negative tests cataloged in the deliverable, especially active membership, service-token revocation, same-workspace semantic evidence checks, no-oracle behavior, and serialized parent/DAG cycle checks.
- OpenBrain startup recall was attempted but unavailable because `/home/hermes/.config/mosaic/credentials.json` is absent; no project state was written to an alternate memory silo.
- TDD: not applicable; this slice changes documentation/test-plan analysis only and implements no runtime behavior.
## Validation log
- `pnpm exec prettier --check docs/native-kanban-sot/KBN-010-THREAT-AUTH-CONSTRAINT-GATE.md docs/scratchpads/753-kbn010-threat-gate.md` — PASS.
- Changed-doc link validator — PASS (`relative_links=0`, one external issue link); `curl -fsSIL https://git.mosaicstack.dev/mosaicstack/stack/issues/753` — PASS.
- The first inline link-validator invocation had a Python f-string syntax error; corrected once and rerun successfully without changing the deliverable.
- `pnpm format:check` — PASS.
- `pnpm lint` — PASS (23 tasks successful).
- `pnpm typecheck` — PASS (42 tasks successful).
- `pnpm exec tsc -p docs/native-kanban-sot/tsconfig.json --noEmit` — PASS.
- Scoped diff review — PASS: authored delta is limited to the exclusive deliverable and this scratchpad; no runtime/schema/config/dependency/CI/deployment file is changed, and `docs/native-kanban-sot/TASKS.md` has no worker worktree delta from tracking commit `9b55de0`.
- Independent SecReview remains pending and cannot return PASS until contract authority resolves `KBN010-SI-001`.
- Final formatting/diff/test-ID completeness review — PASS (all catalog prefixes contiguous with no duplicate IDs).
- Remaining: scoped commit, queue guard, and push.

View File

@@ -18,12 +18,12 @@ Implement a transport-neutral coordination contract allowing a configured intera
## Design checkpoint — 2026-07-12
Created `docs/tess/MOS-COORDINATION.md`. Mos approved the design and selected the native in-process `InMemoryMosCoordinationPort` for M4. Fleet/tmux remains a documented M5 adapter seam; no Mos-side consumer is built in this task.
Created `docs/tess/MOS-COORDINATION.md`. Mos approved the design and selected the native in-process `InMemoryInteractionCoordinationPort` for M4. Fleet/tmux remains a documented M5 adapter seam; no Mos-side consumer is built in this task.
## Progress checkpoint — 2026-07-13
- Implemented `MosCoordinationPort` with handoff/observe/result only, an authority-checking client, and deterministic native adapter in `@mosaicstack/coord`.
- Implemented the gateway `MosCoordinationService`, deriving requester identity from trusted configuration and actor/tenant/correlation from authenticated context.
- Implemented `InteractionCoordinationPort` with handoff/observe/result only, an authority-checking client, and deterministic native adapter in `@mosaicstack/coord`.
- Implemented the gateway `InteractionCoordinationService`, deriving requester identity from trusted configuration and actor/tenant/correlation from authenticated context.
- Added contract and gateway boundary tests for configurable identities, native round-trip, unconfigured requester, self-delegation, target drift, and cross-tenant observe/result denial before adapter invocation.
- Did not modify `apps/gateway/src/commands/command-authorization.service.ts`.

View File

@@ -54,7 +54,7 @@ Termination is fail-closed: a runtime approval verifier consumes a one-time, exa
### Mos Coordination Boundary
`@mosaicstack/coord` exposes only the transport-neutral `MosCoordinationPort`
`@mosaicstack/coord` exposes only the transport-neutral `InteractionCoordinationPort`
verbs `handoff`, `observe`, and `result`. Gateway derives the actor, tenant,
correlation, and interaction-agent identity from authenticated context plus
trusted configuration; callers never provide an orchestration target. It

View File

@@ -6,7 +6,7 @@ This procedure is evidence-bound. It does not authorize a production cutover unt
2. Query the normalized runtime capability surface, not a Hermes API directly. Confirm the session capabilities required for the operation are advertised.
3. Query the transitional matrix through `RuntimeProviderService.transitionalCapabilityMatrix` (`apps/gateway/src/agent/runtime-provider-registry.service.ts`). Kanban, skills, memory, tools, and cron must remain `unsupported`; stop rather than route those operations through Hermes.
4. Route new memory activity through the Mosaic operator-memory plugin path; there is no landed Hermes memory import.
5. Use `MosCoordinationService` for orchestration handoff. Tess does not take Mos authority.
5. Use `InteractionCoordinationService` (`apps/gateway/src/coord/interaction-coordination.service.ts`) for orchestration handoff. The interaction agent does not take configured orchestrator authority.
6. Record the qualification evidence and only then update an external deployment/channel binding through its separately authorized operational process.
No claim here authorizes bulk transcript copying, data-schema migration, or enabling an unsupported transitional capability.

View File

@@ -7,5 +7,5 @@ Hermes is a reference adapter, not a Mosaic core dependency. `packages/agent/src
| sessions, hierarchy, streaming, send/attach/terminate | `HermesRuntimeProvider` plus `hermes-runtime-provider.test.ts` | adapted |
| Kanban, skills, memory, tools, cron | normalized matrix in `HermesRuntimeProvider.transitionalCapabilityMatrix`; each is `unsupported` and `assertTransitionalCapability` denies before a transport call | deferred / fail-closed |
| operator memory | `packages/memory/src/operator-memory-plugin.ts`, constructed by `apps/gateway/src/memory/memory.module.ts` and session-scoped by `apps/gateway/src/agent/agent.service.ts` | native Mosaic path |
| orchestration handoff | `apps/gateway/src/coord/mos-coordination.service.ts` retains authenticated handoff/observe/result ownership checks | native Mosaic path |
| orchestration handoff | `InteractionCoordinationService` in `apps/gateway/src/coord/interaction-coordination.service.ts` retains authenticated handoff/observe/result ownership checks | native Mosaic path |
| transcripts, profiles, preferences | no Hermes importer/schema mapping landed | no automatic migration |

View File

@@ -6,5 +6,5 @@ Rollback is configuration/binding reversal, not a database rollback: no Hermes s
2. Keep the gateway registration and core contracts unchanged unless a reviewed code rollback is required; `AgentRuntimeProviderRegistry` registration is explicit and non-replacing (`packages/agent/src/runtime-provider-registry.ts`).
3. Do not replay an unsupported Kanban, skills, memory, tools, or cron operation. The transitional matrix is intentionally fail-closed.
4. Preserve Mosaic audit, session, and operator-memory records under their normal scoped retention rules; do not copy them into Hermes as a rollback shortcut.
5. For an in-flight coordination request, use the owned handoff observation/result flow in `MosCoordinationService`; do not create a second orchestrator path.
5. For an in-flight coordination request, use the owned handoff observation/result flow in `InteractionCoordinationService` (`apps/gateway/src/coord/interaction-coordination.service.ts`); do not create a second orchestrator path.
6. Capture the binding reversal, affected scope, correlation IDs, and reason in the approved operational record before retrying a cutover.

View File

@@ -20,29 +20,29 @@ interface CoordinationScope {
readonly requesterAgentId: string; // trusted gateway/configuration data
}
interface MosHandoffRequest {
interface HandoffRequest {
readonly idempotencyKey: string;
readonly summary: string;
readonly context?: string;
readonly missionId?: string;
}
interface MosHandoffReceipt {
interface HandoffReceipt {
readonly handoffId: string;
readonly targetAgentId: string;
readonly status: 'accepted' | 'queued';
readonly correlationId: string;
}
interface MosHandoff {
interface Handoff {
readonly handoffId: string;
readonly targetAgentId: string;
readonly request: MosHandoffRequest;
readonly request: HandoffRequest;
readonly scope: CoordinationScope;
}
interface MosCoordinationPort {
handoff(handoff: MosHandoff): Promise<MosHandoffReceipt>;
interface InteractionCoordinationPort {
handoff(handoff: Handoff): Promise<HandoffReceipt>;
observe(handoffId: string, scope: CoordinationScope): Promise<CoordinationObservation>;
result(handoffId: string, scope: CoordinationScope): Promise<CoordinationResult>;
}
@@ -52,22 +52,26 @@ The port deliberately omits generic orchestrator verbs. It is tenant- and
correlation-scoped; its gateway implementation obtains `actorId`, `tenantId`,
and the requester agent from trusted authentication/configuration only.
## HTTP routes
`/api/coord/interaction` is the canonical HTTP coordination prefix for handoff, observe, and result. `/api/coord/mos` remains a backward-compatible alias with the same handlers and DTOs; new integrations use the neutral canonical prefix.
## Enforcement point
`apps/gateway` owns a `MosCoordinationService` boundary that compares the
`apps/gateway` owns an `InteractionCoordinationService` (`apps/gateway/src/coord/interaction-coordination.service.ts`) boundary that compares the
trusted configured requester/target identities and rejects all of the following
before calling a transport: unconfigured requester, self-delegation, target
identity drift, cross-tenant observe/result lookup, and attempts to observe or
receive a result for a handoff outside the originating tenant. The service exposes handoff, observe,
and result only, and delegates delivery to an injected adapter.
M4 ships a native in-process `InMemoryMosCoordinationPort` as the concrete,
M4 ships a native in-process `InMemoryInteractionCoordinationPort` as the concrete,
deterministic adapter. It preserves the immutable handoff ID, tenant, requester
identity, and correlation ID while demonstrating the handoff → observe → result
round trip. It is a queue/port adapter, not a Mos-side consumer.
A future fleet/tmux adapter is a documented M5 deployment seam and must
implement the same `MosCoordinationPort`; no channel client or interaction
implement the same `InteractionCoordinationPort`; no channel client or interaction
runtime calls a transport directly.
## Required tests

View File

@@ -33,14 +33,18 @@ Trust boundaries: Discord→plugin, CLI→gateway, plugin→gateway service iden
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
## Closed Prerequisite Findings
- 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.
The original M1 findings below are closed by landed controls and retained for audit traceability.
These are tracked as M1 security prerequisites and must pass independent security review before Tess ingress is enabled.
| Former finding | Closed evidence |
| ------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Command scope/role enforcement | `apps/gateway/src/commands/command-authorization.service.ts` and its authorization tests enforce the server-side approval boundary. |
| Cross-owner session access | Gateway session ownership tests cover server-derived owner and tenant scope. |
| Caller-controlled MCP identity | MCP tools derive actor and tenant from authenticated gateway context. |
| Missing Discord ingress allowlists | `apps/gateway/src/plugin/plugin.module.ts` requires the guild, channel, and user allowlist environment values; `apps/gateway/src/plugin/discord-ingress.security.spec.ts` exercises denial and configured ingress. |
| Missing redaction before persistence/egress | Gateway and log redaction coverage verifies sensitive content is classified before durable storage or channel delivery. |
| In-memory-only restart safety | `packages/agent/src/durable-session.test.ts` reconstructs durable identity, inbox/outbox, checkpoints, and handoffs after simulated restart. |
| Globally scoped session GC | `apps/gateway/src/gc/session-gc.service.spec.ts` verifies session-only collection and the absence of automatic global collection entry points. |
These controls remain subject to the runtime's independent review and release qualification gates.

View File

@@ -3,7 +3,7 @@ import {
DurableSessionCoordinator,
InMemoryDurableSessionStore,
type DurableSessionIdentity,
} from './tess-durable-session.js';
} from './durable-session.js';
const IDENTITY: DurableSessionIdentity = {
agentName: 'Nova',

View File

@@ -102,7 +102,7 @@ export interface DurableSessionStore {
export class DurableSessionNotFoundError extends Error {
constructor(sessionId: string) {
super(`Durable Tess session not found: ${sessionId}`);
super(`Durable session not found: ${sessionId}`);
this.name = 'DurableSessionNotFoundError';
}
}
@@ -212,11 +212,11 @@ export class DurableSessionCoordinator {
async resumeHandoff(handoffId: string): Promise<DurableHandoffRecovery> {
const handoff = await this.store.findHandoff(handoffId);
if (!handoff) throw new Error(`Durable Tess handoff not found: ${handoffId}`);
if (!handoff) throw new Error(`Durable handoff not found: ${handoffId}`);
const snapshot = await this.snapshot(handoff.sessionId);
const checkpoint = await this.store.findCheckpoint(handoff.sessionId, handoff.checkpointId);
if (!checkpoint) {
throw new Error(`Durable Tess handoff checkpoint is unavailable: ${handoff.checkpointId}`);
throw new Error(`Durable handoff checkpoint is unavailable: ${handoff.checkpointId}`);
}
return { identity: snapshot.identity, checkpoint, handoff };
}
@@ -257,7 +257,7 @@ export class InMemoryDurableSessionStore implements DurableSessionStore {
const existing = this.sessions.get(identity.sessionId);
if (existing) {
if (!sameEnrollmentScope(existing.identity, identity)) {
throw new Error(`Durable Tess session identity conflict: ${identity.sessionId}`);
throw new Error(`Durable session identity conflict: ${identity.sessionId}`);
}
existing.identity.providerId = identity.providerId;
existing.identity.runtimeSessionId = identity.runtimeSessionId;
@@ -290,7 +290,7 @@ export class InMemoryDurableSessionStore implements DurableSessionStore {
const existing = state.inbox.get(input.idempotencyKey);
if (existing) {
if (!sameInbox(existing, input)) {
throw new Error(`Durable Tess inbox idempotency conflict: ${input.idempotencyKey}`);
throw new Error(`Durable inbox idempotency conflict: ${input.idempotencyKey}`);
}
return { accepted: false, status: existing.status };
}
@@ -323,7 +323,7 @@ export class InMemoryDurableSessionStore implements DurableSessionStore {
const existing = state.outbox.get(input.idempotencyKey);
if (existing) {
if (!sameOutbox(existing, input)) {
throw new Error(`Durable Tess outbox idempotency conflict: ${input.idempotencyKey}`);
throw new Error(`Durable outbox idempotency conflict: ${input.idempotencyKey}`);
}
return { accepted: false, status: existing.status };
}
@@ -364,7 +364,7 @@ export class InMemoryDurableSessionStore implements DurableSessionStore {
const checkpoints = this.require(input.sessionId).checkpoints;
const existing = checkpoints.get(input.checkpointId);
if (existing && !sameCheckpoint(existing, input)) {
throw new Error(`Durable Tess checkpoint identity conflict: ${input.checkpointId}`);
throw new Error(`Durable checkpoint identity conflict: ${input.checkpointId}`);
}
if (!existing) checkpoints.set(input.checkpointId, { ...input });
}
@@ -377,11 +377,11 @@ export class InMemoryDurableSessionStore implements DurableSessionStore {
async handoff(input: DurableHandoffInput): Promise<void> {
const state = this.require(input.sessionId);
if (!state.checkpoints.has(input.checkpointId)) {
throw new Error(`Durable Tess handoff checkpoint is unavailable: ${input.checkpointId}`);
throw new Error(`Durable handoff checkpoint is unavailable: ${input.checkpointId}`);
}
const existing = state.handoffs.get(input.handoffId);
if (existing && !sameHandoff(existing, input)) {
throw new Error(`Durable Tess handoff identity conflict: ${input.handoffId}`);
throw new Error(`Durable handoff identity conflict: ${input.handoffId}`);
}
if (!existing) state.handoffs.set(input.handoffId, { ...input });
}
@@ -413,7 +413,7 @@ export class InMemoryDurableSessionStore implements DurableSessionStore {
kind: string,
): T {
const entry = records.get(idempotencyKey);
if (!entry) throw new Error(`Durable Tess ${kind} entry not found: ${idempotencyKey}`);
if (!entry) throw new Error(`Durable ${kind} entry not found: ${idempotencyKey}`);
return entry;
}
}

View File

@@ -4,4 +4,4 @@ export * from './runtime-provider-registry.js';
export * from './tmux-fleet-runtime-provider.js';
export * from './hermes-runtime-provider.js';
export * from './matrix-native-runtime-provider.js';
export * from './tess-durable-session.js';
export * from './durable-session.js';

View File

@@ -117,7 +117,7 @@ class DenyMatrixWriteAuthority implements MatrixWriteAuthority {
async assertAuthorized(): Promise<void> {
throw new MatrixRuntimeProviderError(
'forbidden',
'Matrix runtime writes require Mos authority',
'Matrix runtime writes require orchestrator authority',
);
}
}

View File

@@ -202,7 +202,7 @@ describe('TmuxFleetRuntimeProvider security policy', (): void => {
expect(fleet.terminate).not.toHaveBeenCalled();
});
it('rejects an unverified target before consulting Mos write authority', async (): Promise<void> => {
it('rejects an unverified target before consulting orchestrator write authority', async (): Promise<void> => {
const fleet = transport();
fleet.verifySession = vi.fn(async (): Promise<FleetRuntimeTarget> => {
throw new Error('target identity mismatch');
@@ -220,7 +220,20 @@ describe('TmuxFleetRuntimeProvider security policy', (): void => {
expect(fleet.sendMessage).not.toHaveBeenCalled();
});
it('passes an exact session ID to the fleet transport only through authorized Mos writes', async (): Promise<void> => {
it('uses the role-neutral interaction source label by default', async (): Promise<void> => {
const fleet = transport();
const writeAuthority: FleetWriteAuthority = {
canWrite: vi.fn(async (): Promise<boolean> => true),
assertAuthorized: vi.fn(async (): Promise<void> => undefined),
};
const provider = new TmuxFleetRuntimeProvider({ transport: fleet, writeAuthority });
await provider.sendMessage('coder0', { content: 'hello', idempotencyKey: 'message-1' }, scope);
expect(fleet.sendMessage).toHaveBeenCalledWith('coder0', 'hello', 'interaction');
});
it('passes an exact session ID to the fleet transport only through orchestrator-authorized writes', async (): Promise<void> => {
const fleet = transport();
const writeAuthority: FleetWriteAuthority = {
canWrite: vi.fn(async (): Promise<boolean> => true),
@@ -228,7 +241,7 @@ describe('TmuxFleetRuntimeProvider security policy', (): void => {
};
const provider = new TmuxFleetRuntimeProvider({
transport: fleet,
sourceLabel: 'tess',
sourceLabel: 'operator',
writeAuthority,
});
@@ -246,7 +259,7 @@ describe('TmuxFleetRuntimeProvider security policy', (): void => {
scope,
approvalRef: 'approval-1',
});
expect(fleet.sendMessage).toHaveBeenCalledWith('coder0', 'hello', 'tess');
expect(fleet.sendMessage).toHaveBeenCalledWith('coder0', 'hello', 'operator');
expect(fleet.terminate).toHaveBeenCalledWith('coder0');
});

View File

@@ -64,14 +64,14 @@ export interface FleetWriteAuthorization {
}
/**
* Mos is the only authority that may permit Tess write/control requests to a
* The orchestrator is the only authority that may permit interaction-plane write/control requests to a
* fleet peer. Gateway records the request and denial/success around provider
* invocation; the default authority prevents direct Tess writes by design.
* invocation; the default authority prevents direct interaction-plane writes by design.
*/
export interface FleetWriteAuthority {
/** Non-consuming preflight used before probing the fleet transport. */
canWrite(authorization: FleetWriteAuthorization): Promise<boolean>;
/** Final exact-target authorization; may consume a Mos grant. */
/** Final exact-target authorization; may consume an orchestrator grant. */
assertAuthorized(authorization: FleetWriteAuthorization): Promise<void>;
}
@@ -116,7 +116,7 @@ class DenyFleetWriteAuthority implements FleetWriteAuthority {
async assertAuthorized(_authorization: FleetWriteAuthorization): Promise<void> {
throw new FleetRuntimeProviderError(
'forbidden',
'Fleet writes require an explicit Mos authority decision',
'Fleet writes require an explicit orchestrator authority decision',
);
}
}
@@ -124,7 +124,7 @@ class DenyFleetWriteAuthority implements FleetWriteAuthority {
/**
* A capability-limited provider for rostered local fleet peers. It never
* permits raw tmux socket/target selection, interactive control attach, or
* direct Tess writes; all side effects pass through exact transport checks.
* direct interaction-plane writes; all side effects pass through exact transport checks.
*/
export class TmuxFleetRuntimeProvider implements AgentRuntimeProvider {
readonly id = FLEET_PROVIDER_ID;
@@ -139,7 +139,7 @@ export class TmuxFleetRuntimeProvider implements AgentRuntimeProvider {
constructor(private readonly options: TmuxFleetRuntimeProviderOptions) {
this.readAuthority = options.readAuthority ?? new DenyFleetReadAuthority();
this.writeAuthority = options.writeAuthority ?? new DenyFleetWriteAuthority();
this.sourceLabel = options.sourceLabel ?? 'tess';
this.sourceLabel = options.sourceLabel ?? 'interaction';
this.attachmentIdFactory = options.attachmentIdFactory ?? randomUUID;
this.now = options.now ?? (() => new Date());
this.attachmentTtlMs = options.attachmentTtlMs ?? ATTACHMENT_TTL_MS;

View File

@@ -1,10 +1,10 @@
import { describe, expect, it, vi } from 'vitest';
import {
InMemoryMosCoordinationPort,
MosCoordinationClient,
InMemoryInteractionCoordinationPort,
InteractionCoordinationClient,
type CoordinationScope,
type MosCoordinationAuthorityError,
type MosCoordinationPort,
type InteractionCoordinationAuthorityError,
type InteractionCoordinationPort,
} from '../index.js';
const scope: CoordinationScope = {
@@ -15,19 +15,19 @@ const scope: CoordinationScope = {
};
function client(
port: MosCoordinationPort,
port: InteractionCoordinationPort,
handoffIdFactory: () => string = (): string => 'handoff-1',
): MosCoordinationClient {
return new MosCoordinationClient(
): InteractionCoordinationClient {
return new InteractionCoordinationClient(
{ interactionAgentId: 'Nova', orchestrationAgentId: 'Conductor' },
port,
handoffIdFactory,
);
}
describe('MosCoordinationClient', (): void => {
describe('InteractionCoordinationClient', (): void => {
it('round-trips handoff, observation, and result through the native port with identities as data', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const coordination = client(adapter);
await expect(
@@ -42,8 +42,8 @@ describe('MosCoordinationClient', (): void => {
correlationId: 'corr-1',
});
adapter.recordActivity('handoff-1', 'running', 'Mos accepted the request');
adapter.recordResult('handoff-1', 'completed', 'Merged by Mos');
adapter.recordActivity('handoff-1', 'running', 'Orchestrator accepted the request');
adapter.recordResult('handoff-1', 'completed', 'Merged by orchestrator');
await expect(coordination.observe('handoff-1', scope)).resolves.toMatchObject({
status: 'completed',
@@ -59,7 +59,7 @@ describe('MosCoordinationClient', (): void => {
targetAgentId: 'Conductor',
status: 'completed',
correlationId: 'corr-1',
summary: 'Merged by Mos',
summary: 'Merged by orchestrator',
});
expect(coordination).not.toHaveProperty('dispatch');
@@ -69,8 +69,8 @@ describe('MosCoordinationClient', (): void => {
expect(coordination).not.toHaveProperty('cancel');
});
it('fails closed before delivery when an unconfigured agent requests Mos work', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
it('fails closed before delivery when an unconfigured agent requests orchestrator work', async (): Promise<void> => {
const adapter = new InMemoryInteractionCoordinationPort();
await expect(
client(adapter).handoff(
@@ -79,31 +79,31 @@ describe('MosCoordinationClient', (): void => {
),
).rejects.toMatchObject({
code: 'requester_forbidden',
} satisfies Partial<MosCoordinationAuthorityError>);
} satisfies Partial<InteractionCoordinationAuthorityError>);
});
it('rejects self-delegation configuration before constructing a client', (): void => {
expect(
(): MosCoordinationClient =>
new MosCoordinationClient(
(): InteractionCoordinationClient =>
new InteractionCoordinationClient(
{ interactionAgentId: 'Nova', orchestrationAgentId: 'Nova' },
new InMemoryMosCoordinationPort(),
new InMemoryInteractionCoordinationPort(),
),
).toThrow('Interaction and orchestration identities must differ');
});
it('rejects whitespace-equivalent self-delegation identities', (): void => {
expect(
(): MosCoordinationClient =>
new MosCoordinationClient(
(): InteractionCoordinationClient =>
new InteractionCoordinationClient(
{ interactionAgentId: 'Nova ', orchestrationAgentId: 'Nova' },
new InMemoryMosCoordinationPort(),
new InMemoryInteractionCoordinationPort(),
),
).toThrow('Interaction and orchestration identities must differ');
});
it('does not expose another tenant handoff to observe or result', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort();
const adapter = new InMemoryInteractionCoordinationPort();
const coordination = client(adapter);
await coordination.handoff(
{ idempotencyKey: 'handoff-request-1', summary: 'Implement the requested feature' },
@@ -120,7 +120,7 @@ describe('MosCoordinationClient', (): void => {
});
it('bounds native handoff retention by evicting the oldest handoff', async (): Promise<void> => {
const adapter = new InMemoryMosCoordinationPort({ maxHandoffs: 1 });
const adapter = new InMemoryInteractionCoordinationPort({ maxHandoffs: 1 });
const first = client(adapter, (): string => 'handoff-1');
const second = client(adapter, (): string => 'handoff-2');
await first.handoff({ idempotencyKey: 'handoff-request-1', summary: 'First request' }, scope);
@@ -131,7 +131,7 @@ describe('MosCoordinationClient', (): void => {
});
it('fails closed when a transport reports target drift', async (): Promise<void> => {
const adapter: MosCoordinationPort = {
const adapter: InteractionCoordinationPort = {
handoff: vi.fn(async () => ({
handoffId: 'handoff-1',
targetAgentId: 'Unexpected',
@@ -149,6 +149,6 @@ describe('MosCoordinationClient', (): void => {
),
).rejects.toMatchObject({
code: 'target_drift',
} satisfies Partial<MosCoordinationAuthorityError>);
} satisfies Partial<InteractionCoordinationAuthorityError>);
});
});

View File

@@ -2,25 +2,25 @@ import {
type CoordinationObservation,
type CoordinationResult,
type CoordinationScope,
type MosCoordinationActivity,
type MosCoordinationPort,
type MosHandoff,
type MosHandoffReceipt,
type MosHandoffStatus,
} from './mos-coordination.js';
type InteractionCoordinationActivity,
type InteractionCoordinationPort,
type Handoff,
type HandoffReceipt,
type HandoffStatus,
} from './interaction-coordination.js';
const DEFAULT_HANDOFF_TTL_MS = 60 * 60 * 1_000;
const DEFAULT_MAX_HANDOFFS = 1_000;
interface StoredHandoff {
readonly handoff: MosHandoff;
status: MosHandoffStatus;
readonly activity: MosCoordinationActivity[];
readonly handoff: Handoff;
status: HandoffStatus;
readonly activity: InteractionCoordinationActivity[];
readonly expiresAt: number;
result?: CoordinationResult;
}
export interface InMemoryMosCoordinationPortOptions {
export interface InMemoryInteractionCoordinationPortOptions {
now?: () => Date;
handoffTtlMs?: number;
maxHandoffs?: number;
@@ -29,21 +29,21 @@ export interface InMemoryMosCoordinationPortOptions {
/**
* Native deterministic queue/port adapter for the coordination boundary.
* It intentionally has no fleet/tmux dependency. A future deployment adapter
* implements MosCoordinationPort without changing interaction-plane callers.
* implements InteractionCoordinationPort without changing interaction-plane callers.
*/
export class InMemoryMosCoordinationPort implements MosCoordinationPort {
export class InMemoryInteractionCoordinationPort implements InteractionCoordinationPort {
private readonly handoffs = new Map<string, StoredHandoff>();
private readonly now: () => Date;
private readonly handoffTtlMs: number;
private readonly maxHandoffs: number;
constructor(options: InMemoryMosCoordinationPortOptions = {}) {
constructor(options: InMemoryInteractionCoordinationPortOptions = {}) {
this.now = options.now ?? (() => new Date());
this.handoffTtlMs = options.handoffTtlMs ?? DEFAULT_HANDOFF_TTL_MS;
this.maxHandoffs = options.maxHandoffs ?? DEFAULT_MAX_HANDOFFS;
}
async handoff(handoff: MosHandoff): Promise<MosHandoffReceipt> {
async handoff(handoff: Handoff): Promise<HandoffReceipt> {
this.pruneExpiredHandoffs();
const existing = this.handoffs.get(handoff.handoffId);
if (existing !== undefined) {
@@ -88,14 +88,14 @@ export class InMemoryMosCoordinationPort implements MosCoordinationPort {
}
/** Host-side progression seam; interaction clients never receive this capability. */
recordActivity(handoffId: string, status: MosHandoffStatus, summary: string): void {
recordActivity(handoffId: string, status: HandoffStatus, summary: string): void {
this.pruneExpiredHandoffs();
const stored = this.requireHandoff(handoffId);
stored.status = status;
stored.activity.push(activity(status, summary, this.now));
}
/** Host-side result seam for deterministic qualification; not a Mos consumer. */
/** Host-side result seam for deterministic qualification; not an orchestrator consumer. */
recordResult(handoffId: string, status: 'completed' | 'failed', summary: string): void {
this.pruneExpiredHandoffs();
const stored = this.requireHandoff(handoffId);
@@ -110,7 +110,7 @@ export class InMemoryMosCoordinationPort implements MosCoordinationPort {
};
}
private receipt(handoff: MosHandoff, status: MosHandoffStatus): MosHandoffReceipt {
private receipt(handoff: Handoff, status: HandoffStatus): HandoffReceipt {
return {
handoffId: handoff.handoffId,
targetAgentId: handoff.targetAgentId,
@@ -141,7 +141,7 @@ export class InMemoryMosCoordinationPort implements MosCoordinationPort {
stored.handoff.scope.actorId !== scope.actorId ||
stored.handoff.scope.requesterAgentId !== scope.requesterAgentId
) {
throw new InMemoryMosCoordinationError('forbidden', 'Handoff scope does not match');
throw new InMemoryInteractionCoordinationError('forbidden', 'Handoff scope does not match');
}
return stored;
}
@@ -149,12 +149,12 @@ export class InMemoryMosCoordinationPort implements MosCoordinationPort {
private requireHandoff(handoffId: string): StoredHandoff {
const stored = this.handoffs.get(handoffId);
if (stored === undefined) {
throw new InMemoryMosCoordinationError('not_found', 'Handoff was not found');
throw new InMemoryInteractionCoordinationError('not_found', 'Handoff was not found');
}
return stored;
}
private assertSameHandoff(existing: MosHandoff, incoming: MosHandoff): void {
private assertSameHandoff(existing: Handoff, incoming: Handoff): void {
if (
existing.targetAgentId !== incoming.targetAgentId ||
existing.request.idempotencyKey !== incoming.request.idempotencyKey ||
@@ -166,7 +166,7 @@ export class InMemoryMosCoordinationPort implements MosCoordinationPort {
existing.scope.correlationId !== incoming.scope.correlationId ||
existing.scope.requesterAgentId !== incoming.scope.requesterAgentId
) {
throw new InMemoryMosCoordinationError(
throw new InMemoryInteractionCoordinationError(
'conflict',
'Handoff ID is already bound to different immutable input',
);
@@ -174,31 +174,31 @@ export class InMemoryMosCoordinationPort implements MosCoordinationPort {
}
}
export type InMemoryMosCoordinationErrorCode = 'conflict' | 'forbidden' | 'not_found';
export type InMemoryInteractionCoordinationErrorCode = 'conflict' | 'forbidden' | 'not_found';
export class InMemoryMosCoordinationError extends Error {
export class InMemoryInteractionCoordinationError extends Error {
constructor(
readonly code: InMemoryMosCoordinationErrorCode,
readonly code: InMemoryInteractionCoordinationErrorCode,
message: string,
) {
super(message);
this.name = InMemoryMosCoordinationError.name;
this.name = InMemoryInteractionCoordinationError.name;
}
}
function activity(
status: MosHandoffStatus,
status: HandoffStatus,
summary: string,
now: () => Date,
): MosCoordinationActivity {
): InteractionCoordinationActivity {
return { occurredAt: now().toISOString(), status, summary };
}
function copyActivity(entry: MosCoordinationActivity): MosCoordinationActivity {
function copyActivity(entry: InteractionCoordinationActivity): InteractionCoordinationActivity {
return { ...entry };
}
function snapshotHandoff(handoff: MosHandoff): MosHandoff {
function snapshotHandoff(handoff: Handoff): Handoff {
return Object.freeze({
handoffId: handoff.handoffId,
targetAgentId: handoff.targetAgentId,

View File

@@ -3,22 +3,25 @@ export { parseTasksFile, updateTaskStatus, writeTasksFile } from './tasks-file.j
export { runTask, resumeTask } from './runner.js';
export { getMissionStatus, getTaskStatus } from './status.js';
export {
InMemoryMosCoordinationError,
InMemoryMosCoordinationPort,
} from './in-memory-mos-coordination-port.js';
export { MosCoordinationAuthorityError, MosCoordinationClient } from './mos-coordination.js';
InMemoryInteractionCoordinationError,
InMemoryInteractionCoordinationPort,
} from './in-memory-interaction-coordination-port.js';
export {
InteractionCoordinationAuthorityError,
InteractionCoordinationClient,
} from './interaction-coordination.js';
export type {
CoordinationObservation,
CoordinationResult,
CoordinationScope,
MosCoordinationActivity,
MosCoordinationIdentity,
MosCoordinationPort,
MosHandoff,
MosHandoffReceipt,
MosHandoffRequest,
MosHandoffStatus,
} from './mos-coordination.js';
InteractionCoordinationActivity,
InteractionCoordinationIdentity,
InteractionCoordinationPort,
Handoff,
HandoffReceipt,
HandoffRequest,
HandoffStatus,
} from './interaction-coordination.js';
export type {
CreateMissionOptions,
Mission,

View File

@@ -1,4 +1,4 @@
export type MosHandoffStatus = 'queued' | 'accepted' | 'running' | 'completed' | 'failed';
export type HandoffStatus = 'queued' | 'accepted' | 'running' | 'completed' | 'failed';
export interface CoordinationScope {
readonly actorId: string;
@@ -8,44 +8,44 @@ export interface CoordinationScope {
readonly requesterAgentId: string;
}
export interface MosCoordinationIdentity {
export interface InteractionCoordinationIdentity {
readonly interactionAgentId: string;
readonly orchestrationAgentId: string;
}
export interface MosHandoffRequest {
export interface HandoffRequest {
readonly idempotencyKey: string;
readonly summary: string;
readonly context?: string;
readonly missionId?: string;
}
export interface MosHandoff {
export interface Handoff {
readonly handoffId: string;
readonly targetAgentId: string;
readonly request: MosHandoffRequest;
readonly request: HandoffRequest;
readonly scope: CoordinationScope;
}
export interface MosHandoffReceipt {
export interface HandoffReceipt {
readonly handoffId: string;
readonly targetAgentId: string;
readonly status: 'queued' | 'accepted';
readonly correlationId: string;
}
export interface MosCoordinationActivity {
export interface InteractionCoordinationActivity {
readonly occurredAt: string;
readonly status: MosHandoffStatus;
readonly status: HandoffStatus;
readonly summary: string;
}
export interface CoordinationObservation {
readonly handoffId: string;
readonly targetAgentId: string;
readonly status: MosHandoffStatus;
readonly status: HandoffStatus;
readonly correlationId: string;
readonly activity: readonly MosCoordinationActivity[];
readonly activity: readonly InteractionCoordinationActivity[];
}
export interface CoordinationResult {
@@ -61,25 +61,25 @@ export interface CoordinationResult {
* its progress/result, but it cannot issue worker, review, merge, or other
* general orchestration commands.
*/
export interface MosCoordinationPort {
handoff(handoff: MosHandoff): Promise<MosHandoffReceipt>;
export interface InteractionCoordinationPort {
handoff(handoff: Handoff): Promise<HandoffReceipt>;
observe(handoffId: string, scope: CoordinationScope): Promise<CoordinationObservation>;
result(handoffId: string, scope: CoordinationScope): Promise<CoordinationResult>;
}
export type MosCoordinationAuthorityErrorCode =
export type InteractionCoordinationAuthorityErrorCode =
| 'invalid_identity'
| 'requester_forbidden'
| 'target_drift'
| 'correlation_drift';
export class MosCoordinationAuthorityError extends Error {
export class InteractionCoordinationAuthorityError extends Error {
constructor(
readonly code: MosCoordinationAuthorityErrorCode,
readonly code: InteractionCoordinationAuthorityErrorCode,
message: string,
) {
super(message);
this.name = MosCoordinationAuthorityError.name;
this.name = InteractionCoordinationAuthorityError.name;
}
}
@@ -87,20 +87,20 @@ export class MosCoordinationAuthorityError extends Error {
* Enforces the interaction-to-orchestration authority boundary before a
* transport is reached. Identity names remain configuration data.
*/
export class MosCoordinationClient {
private readonly identity: MosCoordinationIdentity;
export class InteractionCoordinationClient {
private readonly identity: InteractionCoordinationIdentity;
constructor(
identity: MosCoordinationIdentity,
private readonly port: MosCoordinationPort,
identity: InteractionCoordinationIdentity,
private readonly port: InteractionCoordinationPort,
private readonly handoffIdFactory: () => string = (): string => crypto.randomUUID(),
) {
this.identity = normalizeIdentity(identity);
}
async handoff(request: MosHandoffRequest, scope: CoordinationScope): Promise<MosHandoffReceipt> {
async handoff(request: HandoffRequest, scope: CoordinationScope): Promise<HandoffReceipt> {
this.assertRequester(scope);
const handoff: MosHandoff = {
const handoff: Handoff = {
handoffId: this.handoffIdFactory(),
targetAgentId: this.identity.orchestrationAgentId,
request: snapshotRequest(request),
@@ -111,15 +111,15 @@ export class MosCoordinationClient {
receipt.handoffId !== handoff.handoffId ||
receipt.targetAgentId !== handoff.targetAgentId
) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'target_drift',
'Mos coordination transport returned a mismatched handoff target',
'Interaction coordination transport returned a mismatched handoff target',
);
}
if (receipt.correlationId !== handoff.scope.correlationId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'correlation_drift',
'Mos coordination transport returned a mismatched correlation ID',
'Interaction coordination transport returned a mismatched correlation ID',
);
}
return receipt;
@@ -137,7 +137,7 @@ export class MosCoordinationClient {
private assertRequester(scope: CoordinationScope): void {
if (scope.requesterAgentId !== this.identity.interactionAgentId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'requester_forbidden',
'Requester is not the configured interaction agent',
);
@@ -149,15 +149,15 @@ export class MosCoordinationClient {
scope: CoordinationScope,
): CoordinationObservation {
if (observation.targetAgentId !== this.identity.orchestrationAgentId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'target_drift',
'Mos coordination transport returned an unexpected observation target',
'Interaction coordination transport returned an unexpected observation target',
);
}
if (observation.correlationId !== scope.correlationId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'correlation_drift',
'Mos coordination transport returned a mismatched observation correlation ID',
'Interaction coordination transport returned a mismatched observation correlation ID',
);
}
return observation;
@@ -165,32 +165,34 @@ export class MosCoordinationClient {
private assertResult(result: CoordinationResult, scope: CoordinationScope): CoordinationResult {
if (result.targetAgentId !== this.identity.orchestrationAgentId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'target_drift',
'Mos coordination transport returned an unexpected result target',
'Interaction coordination transport returned an unexpected result target',
);
}
if (result.correlationId !== scope.correlationId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'correlation_drift',
'Mos coordination transport returned a mismatched result correlation ID',
'Interaction coordination transport returned a mismatched result correlation ID',
);
}
return result;
}
}
function normalizeIdentity(identity: MosCoordinationIdentity): MosCoordinationIdentity {
function normalizeIdentity(
identity: InteractionCoordinationIdentity,
): InteractionCoordinationIdentity {
const interactionAgentId = identity.interactionAgentId.trim();
const orchestrationAgentId = identity.orchestrationAgentId.trim();
if (interactionAgentId.length === 0 || orchestrationAgentId.length === 0) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'invalid_identity',
'Interaction and orchestration identities are required',
);
}
if (interactionAgentId === orchestrationAgentId) {
throw new MosCoordinationAuthorityError(
throw new InteractionCoordinationAuthorityError(
'invalid_identity',
'Interaction and orchestration identities must differ',
);
@@ -198,7 +200,7 @@ function normalizeIdentity(identity: MosCoordinationIdentity): MosCoordinationId
return Object.freeze({ interactionAgentId, orchestrationAgentId });
}
function snapshotRequest(request: MosHandoffRequest): MosHandoffRequest {
function snapshotRequest(request: HandoffRequest): HandoffRequest {
return Object.freeze({ ...request });
}

View File

@@ -2,10 +2,10 @@
The **operator-interaction** role is the authorized human interaction plane for
Mosaic. It presents runtime and fleet state, mediates approved actions, and
hands coding or general orchestration work to Mos.
hands coding or general orchestration work to the orchestrator.
## Boundaries
- It does not claim Mos-owned coding or general orchestration work.
- It does not claim orchestrator-owned coding or general orchestration work.
- It exposes only the configured, observable tool policy.
- It does not receive or surface credentials in its effective policy.

View File

@@ -75,6 +75,14 @@
"type": "string",
"pattern": "^[A-Za-z0-9_.-]+$"
},
"alias": {
"description": "Optional operator-defined display name for the agent.",
"type": "string"
},
"provider": {
"description": "Optional agent runtime provider identifier such as openai-codex.",
"type": "string"
},
"runtime": {
"type": "string"
},

View File

@@ -189,6 +189,36 @@ describe('fleet roster parsing', () => {
expect(getRosterAgent(roster, 'canary-pi').runtime).toBe('pi');
});
it('accepts optional agent alias and provider metadata without requiring them', async () => {
cleanup = await tempDir();
const rosterPath = join(cleanup, 'roster.yaml');
await writeFile(
rosterPath,
[
'version: 1',
'transport: tmux',
'agents:',
' - name: interaction',
' alias: Friday',
' provider: openai-codex',
' runtime: pi',
' - name: worker0',
' runtime: codex',
].join('\n'),
);
const roster = await loadFleetRoster(rosterPath);
expect(getRosterAgent(roster, 'interaction')).toMatchObject({
name: 'interaction',
alias: 'Friday',
provider: 'openai-codex',
});
expect(getRosterAgent(roster, 'worker0')).toMatchObject({ name: 'worker0' });
expect(getRosterAgent(roster, 'worker0').alias).toBeUndefined();
expect(getRosterAgent(roster, 'worker0').provider).toBeUndefined();
});
it('socketArgs: named socket → -L <name>; empty → no -L (default socket)', () => {
expect(socketArgs('mosaic-fleet')).toEqual(['-L', 'mosaic-fleet']);
expect(socketArgs('')).toEqual([]);
@@ -1872,7 +1902,61 @@ describe('fleet ps — tenant and host', () => {
});
});
describe('fleet ps — JSON output shape (FR-6)', () => {
describe('fleet ps — aliases and JSON output shape (FR-6)', () => {
it('shows an agent alias in table output and falls back to name when absent', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');
await mkdir(join(home, 'fleet'), { recursive: true });
await writeFile(
rosterPath,
[
'version: 1',
'transport: tmux',
'agents:',
' - name: interaction',
' alias: Friday',
' runtime: pi',
' - name: worker0',
' runtime: codex',
].join('\n'),
);
const runner: CommandRunner = async (command, args) => {
const fullArgs = [command, ...args].join(' ');
if (fullArgs.includes('list-sessions')) {
return { stdout: 'interaction\nworker0\n', stderr: '', exitCode: 0 };
}
return {
stdout: fullArgs.includes('systemctl')
? 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n'
: '12345 pi 0 0 0 0\n',
stderr: '',
exitCode: 0,
};
};
const lines: string[] = [];
const origLog = console.log;
console.log = (msg: string) => {
lines.push(msg);
};
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { runner, mosaicHome: home });
try {
await program.parseAsync(['node', 'mosaic', 'fleet', 'ps']);
} finally {
console.log = origLog;
await rm(home, { recursive: true, force: true });
}
const output = lines.join('\n');
expect(output).toContain('Friday');
expect(output).toContain('worker0');
});
it('produces --json records including tenant_id and host for each agent', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');

View File

@@ -81,6 +81,8 @@ interface RawFleetRoster {
runtimes?: Record<string, { reset_command?: unknown; resetCommand?: unknown }>;
agents?: Array<{
name?: unknown;
alias?: unknown;
provider?: unknown;
runtime?: unknown;
class?: unknown;
working_directory?: unknown;
@@ -102,6 +104,8 @@ interface RawFleetRoster {
export interface FleetAgent {
name: string;
alias?: string;
provider?: string;
runtime: string;
className: string;
workingDirectory?: string;
@@ -1074,6 +1078,7 @@ export interface HeartbeatInfo {
export interface AgentPsRow {
name: string;
alias?: string;
tenant_id: string;
host: string;
runtime: string;
@@ -1755,6 +1760,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
rows.push({
name: agent.name,
alias: agent.alias,
tenant_id,
host,
runtime: agent.runtime,
@@ -1888,7 +1894,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
console.log(
[
row.name.padEnd(18),
(row.alias ?? row.name).padEnd(18),
row.tenant_id.padEnd(12),
row.host.padEnd(12),
row.runtime.padEnd(10),
@@ -2494,6 +2500,8 @@ function normalizeAgent(raw: NonNullable<RawFleetRoster['agents']>[number]): Fle
assertObject(raw, 'Fleet roster agent');
assertKnownKeys(raw, 'Fleet roster agent', [
'name',
'alias',
'provider',
'runtime',
'class',
'working_directory',
@@ -2525,6 +2533,8 @@ function normalizeAgent(raw: NonNullable<RawFleetRoster['agents']>[number]): Fle
}
return {
name,
alias: optionalString(raw.alias, `Fleet roster agent "${name}" alias`),
provider: optionalString(raw.provider, `Fleet roster agent "${name}" provider`),
runtime,
className: stringValue(raw.class, 'worker', `Fleet roster agent "${name}" class`),
workingDirectory: optionalString(
@@ -2827,6 +2837,12 @@ export function serializeRosterToYaml(roster: FleetRoster): string {
runtime: agent.runtime,
class: agent.className,
};
if (agent.alias !== undefined) {
raw['alias'] = agent.alias;
}
if (agent.provider !== undefined) {
raw['provider'] = agent.provider;
}
if (agent.workingDirectory !== undefined) {
raw['working_directory'] = agent.workingDirectory;
}

View File

@@ -414,7 +414,7 @@ function readFleetToolPolicyBlock(policy: string | undefined): string {
'',
'Permitted: authorized conversation, status, retrieval, and safe diagnostics.',
'Denied by default: coding/general orchestration claims, direct fleet control, destructive actions, and credential access.',
'Delegate Mos-owned work through the authorized handoff boundary.',
'Delegate orchestrator-owned work through the authorized handoff boundary.',
].join('\n');
}

View File

@@ -0,0 +1,61 @@
import { afterEach, describe, expect, it, vi } from 'vitest';
import {
attachInteractionSession,
sendInteractionMessage,
stopInteractionSession,
} from './gateway-api.js';
const gateway = 'https://gateway.example.test';
const cookie = 'session=test';
const base = { agentName: 'Nova', correlationId: 'corr-1', sessionId: 'session-1' };
afterEach(() => vi.unstubAllGlobals());
/** Unit coverage: the TUI preserves a non-success gateway response in its CLI error. */
describe('interaction gateway error mapping', (): void => {
it.each([
{
name: 'attach unauthorized',
response: { status: 401, message: 'Invalid or expired session' },
invoke: (): Promise<unknown> => attachInteractionSession(gateway, cookie, base),
expected:
'Failed to attach interaction session (401): {"message":"Invalid or expired session"}',
},
{
name: 'send invalid request',
response: { status: 403, message: 'Content and idempotency key are required' },
invoke: (): Promise<unknown> =>
sendInteractionMessage(gateway, cookie, {
...base,
content: 'hello',
idempotencyKey: 'message-1',
}),
expected:
'Failed to send interaction message (403): {"message":"Content and idempotency key are required"}',
},
{
name: 'stop forbidden',
response: { status: 403, message: 'Runtime termination approval denied' },
invoke: (): Promise<unknown> =>
stopInteractionSession(gateway, cookie, { ...base, approvalRef: 'approval-1' }),
expected:
'Failed to stop interaction session (403): {"message":"Runtime termination approval denied"}',
},
])(
'$name preserves the typed gateway denial in the CLI error',
async ({ response, invoke, expected }) => {
vi.stubGlobal(
'fetch',
vi.fn(
async () =>
new Response(JSON.stringify({ message: response.message }), {
status: response.status,
headers: { 'Content-Type': 'application/json' },
}),
),
);
await expect(invoke()).rejects.toThrow(expected);
},
);
});