Compare commits

..
378 changed files with 1656 additions and 56965 deletions
-1
View File
@@ -8,7 +8,6 @@ coverage
.env.local
*.tsbuildinfo
.pnpm-store
__pycache__/
docs/reports/
# Step-CA dev password — real file is gitignored; commit only the .example
+1 -1
View File
@@ -1 +1 @@
pnpm preflight && pnpm typecheck && pnpm lint && pnpm format:check
pnpm typecheck && pnpm lint && pnpm format:check
+4 -4
View File
@@ -1,5 +1,5 @@
@mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/
# HOME resolves to /root in the ci-base image, preserving its warmed-store path.
# Non-root checkouts use their own HOME. Override without editing this file via
# NPM_CONFIG_STORE_DIR (pnpm's environment form of the store-dir setting).
store-dir=${HOME}/.local/share/pnpm/store
# Pin the pnpm store to the same path the ci-base image warms (Dockerfile.ci),
# so the pipeline `pnpm install --prefer-offline` consumes the baked store
# instead of repopulating a fresh one.
store-dir=/root/.local/share/pnpm/store
-9
View File
@@ -4,15 +4,6 @@ pnpm-lock.yaml
**/node_modules
**/drizzle
**/.next
# Python build/test artifacts — same category as node_modules/dist/.next above.
# Prettier must never scan generated trees; without these a local venv poisons
# `pnpm format:check` with thousands of third-party files.
**/venv
**/__pycache__
**/.mypy_cache
**/.pytest_cache
**/htmlcov
.claude/
docs/tess/TASKS.md
docs/scratchpads/
packages/mosaic/src/fleet/testdata/documentation-publication-v1/inline-migration-v1.json
-11
View File
@@ -41,11 +41,6 @@ steps:
# (Constitution + dispatcher + each RUNTIME.md slice). See DESIGN §7 / R9.
- bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh --self-test
- bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh
# Test-membership guard (#1017): also first link of test:framework-shell.
# Invoked from BOTH surfaces it audits (F2, PR #1018) — the guard is link
# [0] of the pnpm chain, so severing that chain would silence it together
# with everything it guards; this direct line keeps one instrument running.
- bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.sh
# Blocking gate (#791): a framework upgrade must never write or delete an
# operator-owned path. The HARD GATE proves an unanticipated operator sentinel
@@ -103,12 +98,6 @@ steps:
DATABASE_URL: postgresql://mosaic:mosaic@ci-postgres:5432/mosaic
commands:
- *enable_pnpm
# openssl (#912) is the wake HMAC signer: the digest H1/H2, beacon B12,
# and install I8 legs hard-require it in CI. It is baked into ci-base via
# Dockerfile.ci, but ci-base only rebuilds on push-to-main/tag — this
# `apk add` guarantees openssl is present on PR pipelines too (and is a
# fast no-op once the rebuilt image already ships it).
- apk add --no-cache openssl
# postgresql-client (pg_isready) is baked into ci-base.
# Wait up to 60s for CI postgres to be ready; fail fast if it never comes up.
- |
+5 -104
View File
@@ -1,5 +1,5 @@
# Build, publish npm packages, and push Docker images
# Runs on main for stable publishes and on next for integration-line prereleases/images
# Runs only on main branch push/tag
variables:
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
@@ -23,21 +23,9 @@ variables:
- 'docs/**'
- '**/*.md'
- '.woodpecker/**'
- event: [push, manual]
branch: next
- &main_image_build_when
- event: tag
- event: [push, manual]
branch: main
path:
exclude:
- 'packages/mosaic/**'
- 'docs/**'
- '**/*.md'
- '.woodpecker/**'
when:
- branch: [main, next]
- branch: [main]
event: [push, manual, tag]
steps:
@@ -115,84 +103,6 @@ steps:
depends_on:
- build
publish-next-npm:
image: *node_image
# Durable @next integration-line publish. Runs only on next; never writes
# the latest dist-tag and never commits the computed prerelease versions.
when:
- event: [push, manual]
branch: next
environment:
NPM_TOKEN:
from_secret: gitea_token
CI_COMMIT_BRANCH: ${CI_COMMIT_BRANCH}
CI_PIPELINE_NUMBER: ${CI_PIPELINE_NUMBER}
commands:
- *enable_pnpm
- |
if [ "$CI_COMMIT_BRANCH" != "next" ]; then
echo "[publish-next] FATAL: publish-next-npm may only run on next (got '$CI_COMMIT_BRANCH')" >&2
exit 1
fi
if [ -z "$CI_PIPELINE_NUMBER" ]; then
echo "[publish-next] FATAL: CI_PIPELINE_NUMBER is required for prerelease versioning" >&2
exit 1
fi
echo "//git.mosaicstack.dev/api/packages/mosaicstack/npm/:_authToken=$NPM_TOKEN" > ~/.npmrc
echo "@mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/" >> ~/.npmrc
DIST_TAGS_JSON="$(npm view @mosaicstack/mosaic dist-tags --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/ --json)"
DIST_TAGS_JSON="$DIST_TAGS_JSON" node -e 'const tags = JSON.parse(process.env.DIST_TAGS_JSON || "{}"); if (!tags || typeof tags !== "object" || !Object.hasOwn(tags, "latest")) { throw new Error("Gitea npm registry did not return a usable dist-tags object"); } console.log("[publish-next] registry dist-tags OK: latest=" + tags.latest);'
node <<'NODE'
const fs = require('node:fs');
const path = require('node:path');
const pipelineNumber = process.env.CI_PIPELINE_NUMBER;
const roots = ['apps', 'packages', 'plugins'];
const updated = [];
function walk(dir) {
if (!fs.existsSync(dir)) return;
for (const entry of fs.readdirSync(dir, { withFileTypes: true })) {
if (entry.name === 'node_modules' || entry.name === 'dist' || entry.name === '.turbo') continue;
const fullPath = path.join(dir, entry.name);
if (entry.isDirectory()) {
const packagePath = path.join(fullPath, 'package.json');
if (fs.existsSync(packagePath)) updatePackage(packagePath);
walk(fullPath);
}
}
}
function updatePackage(packagePath) {
const manifest = JSON.parse(fs.readFileSync(packagePath, 'utf8'));
if (!manifest.name?.startsWith('@mosaicstack/') || manifest.private) return;
const stableMatch = /^(\d+)\.(\d+)\.(\d+)(?:[-+].*)?$/.exec(manifest.version);
if (!stableMatch) {
throw new Error(manifest.name + " has unsupported semver version '" + manifest.version + "'");
}
const [, major, minor, patch] = stableMatch;
const oldVersion = manifest.version;
manifest.version = major + '.' + minor + '.' + (Number(patch) + 1) + '-next.' + pipelineNumber;
fs.writeFileSync(packagePath, JSON.stringify(manifest, null, 2) + '\n');
updated.push(manifest.name + ' ' + oldVersion + ' -> ' + manifest.version);
}
for (const root of roots) walk(root);
if (updated.length === 0) throw new Error('No publishable @mosaicstack/* packages found');
console.log('[publish-next] computed prerelease versions for ' + updated.length + ' packages:');
for (const line of updated) console.log('[publish-next] ' + line);
NODE
pnpm --filter "@mosaicstack/*" --filter "!@mosaicstack/web" --filter "!@mosaicstack/mosaic-as" publish --no-git-checks --access public --tag next
EXPECTED_VERSION="$(node -p "require('./packages/mosaic/package.json').version")"
RESOLVED_VERSION="$(npm view @mosaicstack/mosaic@next version --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/)"
if [ "$RESOLVED_VERSION" != "$EXPECTED_VERSION" ]; then
echo "[publish-next] FATAL: @mosaicstack/mosaic@next resolved '$RESOLVED_VERSION', expected '$EXPECTED_VERSION'" >&2
exit 1
fi
echo "[publish-next] @mosaicstack/mosaic@next resolves to $RESOLVED_VERSION"
depends_on:
- build
# TODO: Uncomment when ready to publish to npmjs.org
# publish-npmjs:
# image: *node_image
@@ -224,17 +134,8 @@ steps:
- echo "{\"auths\":{\"git.mosaicstack.dev\":{\"username\":\"$REGISTRY_USER\",\"password\":\"$REGISTRY_PASS\"}}}" > /kaniko/.docker/config.json
- |
DESTINATIONS="--destination git.mosaicstack.dev/mosaicstack/stack/gateway:sha-${CI_COMMIT_SHA:0:7}"
if [ "$CI_COMMIT_BRANCH" = "next" ]; then
if [ -n "$CI_COMMIT_TAG" ]; then
echo "[publish] FATAL: next gateway publish must be sha-only; refusing tag '$CI_COMMIT_TAG'" >&2
exit 1
fi
echo "[publish] next gateway publish is sha-only"
elif [ "$CI_COMMIT_BRANCH" = "main" ]; then
if [ "$CI_COMMIT_BRANCH" = "main" ]; then
DESTINATIONS="$DESTINATIONS --destination git.mosaicstack.dev/mosaicstack/stack/gateway:latest"
elif [ -z "$CI_COMMIT_TAG" ]; then
echo "[publish] FATAL: gateway image publish may only run for main, next, or tag events" >&2
exit 1
fi
if [ -n "$CI_COMMIT_TAG" ]; then
DESTINATIONS="$DESTINATIONS --destination git.mosaicstack.dev/mosaicstack/stack/gateway:$CI_COMMIT_TAG"
@@ -245,7 +146,7 @@ steps:
build-appservice:
image: gcr.io/kaniko-project/executor:debug
when: *main_image_build_when
when: *image_build_when
environment:
REGISTRY_USER:
from_secret: gitea_username
@@ -271,7 +172,7 @@ steps:
build-web:
image: gcr.io/kaniko-project/executor:debug
when: *main_image_build_when
when: *image_build_when
environment:
REGISTRY_USER:
from_secret: gitea_username
+1 -4
View File
@@ -25,10 +25,7 @@ FROM node:24-alpine
# postgresql-client used by the test step's pg_isready readiness probe. `bash`,
# `git`, and `jq` are baked here too — framework shell tests and the shipped
# Codex review wrappers require them without per-run installation in ci.yml.
# `openssl` (#912) is the non-circular HMAC signer for the wake trust layer:
# the digest H1/H2, beacon B12, and install I8 legs hard-require it in CI so the
# §4 G6 evidence comes from an actually-run HMAC leg, not a skipped one.
RUN apk add --no-cache python3 make g++ postgresql-client bash git jq openssl
RUN apk add --no-cache python3 make g++ postgresql-client bash git jq
# Pin pnpm to the repo's packageManager version via corepack.
RUN corepack enable && corepack prepare [email protected] --activate
+1 -27
View File
@@ -30,16 +30,6 @@ This installs both components:
| **Framework** | Bash launcher, guides, runtime configs, tools, skills | `~/.config/mosaic/` |
| **@mosaicstack/mosaic** | Unified `mosaic` CLI — TUI, gateway client, wizard, auto-updater | `~/.npm-global/bin/` |
### Install lanes
| Lane | Command | Use when | Source |
| ------------------------ | ------------------------------------- | ----------------------------------------------------- | ----------------------------------------------------------------------- |
| Stable | `bash tools/install.sh` | You want the released Mosaic CLI/framework | npm registry `@mosaicstack/mosaic@latest` + framework archive at `main` |
| Prerelease integration | `bash tools/install.sh --next` | You want the current `next` integration branch | Build-from-source at `next` |
| Contributor/source build | `bash tools/install.sh --dev --ref X` | You are testing a branch before release; `--ref` wins | Build-from-source at the requested ref |
`--next` is shorthand for the prerelease integration lane: it enables source-build mode and uses `next` unless an explicit `--ref` or `MOSAIC_REF` is provided.
After install, the wizard runs automatically or you can invoke it manually:
```bash
@@ -211,21 +201,8 @@ git clone [email protected]:mosaicstack/stack.git
cd stack
# Install dependencies. The local tier uses in-process PGlite; leave DATABASE_URL unset.
# The pnpm store defaults to $HOME/.local/share/pnpm/store. Override it without
# editing the checkout with NPM_CONFIG_STORE_DIR=$HOME/another-store if needed.
pnpm install
# Verify dependencies and generated state before running source-quality gates.
# Missing dependencies exit 42; stale/foreign apps/web/.next state exits 43.
# The web build certifies its exact standalone symlink manifest; added, removed,
# retargeted, or manifest-only-tampered generated links also exit 43. This detects
# accidental, independent, stale, and foreign-residue mutation—the class exposed by
# a five-month-stale .next that produced 19 phantom TS2307 errors.
# It does NOT defend against a same-UID actor that can rewrite both manifest and
# marker consistently (CWE-345). RM-59 tracks the required executor/spine-side
# trust anchor outside worktree authority.
pnpm preflight
# Optional local queue service only. This does not start PostgreSQL.
docker compose up -d valkey
@@ -253,7 +230,6 @@ Gateway start command until KBN-101-02 makes that state fail closed.
### Quality Gates
```bash
pnpm preflight # Checkout/dependency/generated-state validation
pnpm typecheck # TypeScript type checking (all packages)
pnpm lint # ESLint (all packages)
pnpm test # Vitest (all packages)
@@ -371,9 +347,7 @@ The CLI also performs a background update check on every invocation (cached for
bash tools/install.sh --check # Version check only
bash tools/install.sh --framework # Framework only (skip npm CLI)
bash tools/install.sh --cli # npm CLI only (skip framework)
bash tools/install.sh --next # Prerelease lane: source build from next
bash tools/install.sh --dev # Contributor lane: source build at --ref/main
bash tools/install.sh --ref v1.0 # Install from a specific git ref (--ref wins over --next)
bash tools/install.sh --ref v1.0 # Install from a specific git ref
bash tools/install.sh --yes # Non-interactive, accept all defaults
bash tools/install.sh --no-auto-launch # Skip auto-launch of wizard
```
@@ -1,519 +0,0 @@
/**
* Federation M3 single-gateway integration tests (FED-M3-10).
*
* Covers MILESTONES.md M3 acceptance:
* - #6: malformed certificate OIDs fail with 401; valid cert + revoked grant fails with 403.
* - #7: max_rows_per_query caps list results.
*
* Strategy:
* - Real PostgreSQL via @mosaicstack/db.
* - Mocked TLS context/Fastify request shim for FederationAuthGuard.
* - Direct controller calls using the real POST /api/federation/v1/list/:resource contract.
*
* Run:
* FEDERATED_INTEGRATION=1 pnpm --filter @mosaicstack/gateway test -- \
* src/__tests__/integration/federation-m3-list.integration.test.ts
*/
import 'reflect-metadata';
import * as crypto from 'node:crypto';
import type { ExecutionContext } from '@nestjs/common';
import { Test, type TestingModule } from '@nestjs/testing';
import type { FastifyReply, FastifyRequest } from 'fastify';
import {
and,
createDb,
eq,
federationGrants,
federationPeers,
inArray,
missionTasks,
missions,
projects,
tasks,
teamMembers,
teams,
type Db,
type DbHandle,
users,
} from '@mosaicstack/db';
import { afterAll, beforeAll, describe, expect, it } from 'vitest';
import { DB } from '../../database/database.module.js';
import { GrantsService } from '../../federation/grants.service.js';
import { FederationAuthGuard } from '../../federation/server/federation-auth.guard.js';
import { FederationScopeService } from '../../federation/server/scope.service.js';
import { FederationListQueryService } from '../../federation/server/verbs/list-query.service.js';
import { ListController } from '../../federation/server/verbs/list.controller.js';
import {
makeMosaicIssuedCert,
makeSelfSignedCert,
} from '../../federation/__tests__/helpers/test-cert.js';
const run = process.env['FEDERATED_INTEGRATION'] === '1';
const PG_URL = process.env['DATABASE_URL'] ?? 'postgresql://mosaic:mosaic@localhost:5433/mosaic';
const RUN_ID = `fed-m3-10-${crypto.randomUUID()}`;
const CERT_SERIAL_HEX = crypto.randomUUID().replace(/-/g, '').toUpperCase();
interface TestIds {
readonly subjectUserId: string;
readonly otherUserId: string;
readonly peerId: string;
readonly revokedPeerId: string;
readonly activeGrantId: string;
readonly revokedGrantId: string;
readonly subjectProjectId: string;
readonly subjectMissionId: string;
readonly otherProjectId: string;
readonly teamId: string;
readonly unauthorizedTeamId: string;
readonly teamProjectId: string;
readonly taskIds: readonly string[];
readonly excludedTaskIds: readonly string[];
readonly subjectNoteId: string;
readonly otherUserNoteId: string;
}
function pemToDer(pem: string): Buffer {
return Buffer.from(
pem
.replace(/-----BEGIN CERTIFICATE-----/, '')
.replace(/-----END CERTIFICATE-----/, '')
.replace(/\s+/g, ''),
'base64',
);
}
function makeFederationRequest(certPem: string): FastifyRequest {
return {
raw: {
socket: {
getPeerCertificate: () => ({
raw: pemToDer(certPem),
serialNumber: CERT_SERIAL_HEX,
}),
},
},
} as unknown as FastifyRequest;
}
function makeGuardContext(request: FastifyRequest): {
readonly context: ExecutionContext;
readonly sent: { statusCode?: number; payload?: unknown };
} {
const sent: { statusCode?: number; payload?: unknown } = {};
const reply = {
status: (statusCode: number) => {
sent.statusCode = statusCode;
return {
header: () => ({
send: (payload: unknown) => {
sent.payload = payload;
},
}),
};
},
} as unknown as FastifyReply;
const context = {
switchToHttp: () => ({
getRequest: () => request,
getResponse: () => reply,
}),
} as unknown as ExecutionContext;
return { context, sent };
}
async function insertUser(db: Db, id: string, label: string): Promise<void> {
await db.insert(users).values({
id,
name: `${RUN_ID}-${label}`,
email: `${RUN_ID}-${label}@federation-test.invalid`,
emailVerified: false,
});
}
async function seedFixtures(db: Db): Promise<TestIds> {
const subjectUserId = `${RUN_ID}-subject`;
const otherUserId = `${RUN_ID}-other`;
const peerId = crypto.randomUUID();
const revokedPeerId = crypto.randomUUID();
const activeGrantId = crypto.randomUUID();
const revokedGrantId = crypto.randomUUID();
const subjectProjectId = crypto.randomUUID();
const subjectMissionId = crypto.randomUUID();
const otherProjectId = crypto.randomUUID();
const teamId = crypto.randomUUID();
const unauthorizedTeamId = crypto.randomUUID();
const teamProjectId = crypto.randomUUID();
const taskIds = [crypto.randomUUID(), crypto.randomUUID(), crypto.randomUUID()] as const;
const excludedTaskIds = [crypto.randomUUID(), crypto.randomUUID()] as const;
const subjectNoteId = crypto.randomUUID();
const otherUserNoteId = crypto.randomUUID();
await insertUser(db, subjectUserId, 'subject');
await insertUser(db, otherUserId, 'other');
await db.insert(teams).values([
{
id: teamId,
name: `${RUN_ID} allowed team`,
slug: `${RUN_ID}-allowed-team`,
ownerId: subjectUserId,
managerId: subjectUserId,
},
{
id: unauthorizedTeamId,
name: `${RUN_ID} unauthorized team`,
slug: `${RUN_ID}-unauthorized-team`,
ownerId: otherUserId,
managerId: otherUserId,
},
]);
await db.insert(teamMembers).values([
{ teamId, userId: subjectUserId, role: 'member' },
{ teamId: unauthorizedTeamId, userId: subjectUserId, role: 'member' },
]);
await db.insert(projects).values([
{
id: subjectProjectId,
name: `${RUN_ID} subject personal project`,
ownerType: 'user',
ownerId: subjectUserId,
},
{
id: otherProjectId,
name: `${RUN_ID} other personal project`,
ownerType: 'user',
ownerId: otherUserId,
},
{
id: teamProjectId,
name: `${RUN_ID} unauthorized team project`,
ownerType: 'team',
teamId: unauthorizedTeamId,
},
]);
await db.insert(missions).values({
id: subjectMissionId,
name: `${RUN_ID} subject mission`,
projectId: subjectProjectId,
userId: subjectUserId,
});
await db.insert(tasks).values([
{
id: taskIds[0],
title: `${RUN_ID} visible task 1`,
missionId: subjectMissionId,
createdAt: new Date('2026-06-25T03:00:00.000Z'),
updatedAt: new Date('2026-06-25T03:00:00.000Z'),
},
{
id: taskIds[1],
title: `${RUN_ID} visible task 2`,
projectId: subjectProjectId,
createdAt: new Date('2026-06-25T02:00:00.000Z'),
updatedAt: new Date('2026-06-25T02:00:00.000Z'),
},
{
id: taskIds[2],
title: `${RUN_ID} visible task 3`,
projectId: subjectProjectId,
createdAt: new Date('2026-06-25T01:00:00.000Z'),
updatedAt: new Date('2026-06-25T01:00:00.000Z'),
},
{
id: excludedTaskIds[0],
title: `${RUN_ID} other user task`,
projectId: otherProjectId,
createdAt: new Date('2026-06-25T04:00:00.000Z'),
updatedAt: new Date('2026-06-25T04:00:00.000Z'),
},
{
id: excludedTaskIds[1],
title: `${RUN_ID} unauthorized team task`,
projectId: teamProjectId,
createdAt: new Date('2026-06-25T05:00:00.000Z'),
updatedAt: new Date('2026-06-25T05:00:00.000Z'),
},
]);
await db.insert(missionTasks).values([
{
id: subjectNoteId,
missionId: subjectMissionId,
userId: subjectUserId,
notes: `${RUN_ID} subject visible note`,
createdAt: new Date('2026-06-25T03:30:00.000Z'),
updatedAt: new Date('2026-06-25T03:30:00.000Z'),
},
{
id: otherUserNoteId,
missionId: subjectMissionId,
userId: otherUserId,
notes: `${RUN_ID} other user note on subject mission`,
createdAt: new Date('2026-06-25T04:30:00.000Z'),
updatedAt: new Date('2026-06-25T04:30:00.000Z'),
},
]);
await db.insert(federationPeers).values([
{
id: peerId,
commonName: `${RUN_ID}-active-peer`,
displayName: `${RUN_ID} Active Peer`,
certPem: '-----BEGIN CERTIFICATE-----\nMOCK\n-----END CERTIFICATE-----\n',
certSerial: CERT_SERIAL_HEX,
certNotAfter: new Date(Date.now() + 86_400_000),
state: 'active',
},
{
id: revokedPeerId,
commonName: `${RUN_ID}-revoked-peer`,
displayName: `${RUN_ID} Revoked Peer`,
certPem: '-----BEGIN CERTIFICATE-----\nMOCK\n-----END CERTIFICATE-----\n',
certSerial: `${CERT_SERIAL_HEX}${RUN_ID.replace(/-/g, '').slice(0, 8).toUpperCase()}`,
certNotAfter: new Date(Date.now() + 86_400_000),
state: 'active',
},
]);
await db.insert(federationGrants).values([
{
id: activeGrantId,
peerId,
subjectUserId,
status: 'active',
scope: {
resources: ['tasks', 'notes'],
excluded_resources: [],
filters: {
tasks: { include_personal: true, include_teams: [] },
notes: { include_personal: true, include_teams: [] },
},
max_rows_per_query: 2,
},
},
{
id: revokedGrantId,
peerId,
subjectUserId,
status: 'revoked',
revokedAt: new Date(),
revokedReason: `${RUN_ID} revoked grant fixture`,
scope: {
resources: ['tasks'],
excluded_resources: [],
max_rows_per_query: 2,
},
},
]);
return {
subjectUserId,
otherUserId,
peerId,
revokedPeerId,
activeGrantId,
revokedGrantId,
subjectProjectId,
subjectMissionId,
otherProjectId,
teamId,
unauthorizedTeamId,
teamProjectId,
taskIds,
excludedTaskIds,
subjectNoteId,
otherUserNoteId,
};
}
async function cleanupFixtures(db: Db, ids: TestIds | undefined): Promise<void> {
if (!ids) {
return;
}
await db
.delete(missionTasks)
.where(inArray(missionTasks.id, [ids.subjectNoteId, ids.otherUserNoteId]))
.catch(() => {});
await db
.delete(tasks)
.where(inArray(tasks.id, [...ids.taskIds, ...ids.excludedTaskIds]))
.catch(() => {});
await db
.delete(missions)
.where(eq(missions.id, ids.subjectMissionId))
.catch(() => {});
await db
.delete(projects)
.where(inArray(projects.id, [ids.subjectProjectId, ids.otherProjectId, ids.teamProjectId]))
.catch(() => {});
await db
.delete(teamMembers)
.where(
and(
eq(teamMembers.userId, ids.subjectUserId),
inArray(teamMembers.teamId, [ids.teamId, ids.unauthorizedTeamId]),
),
)
.catch(() => {});
await db
.delete(teams)
.where(inArray(teams.id, [ids.teamId, ids.unauthorizedTeamId]))
.catch(() => {});
await db
.delete(federationGrants)
.where(inArray(federationGrants.id, [ids.activeGrantId, ids.revokedGrantId]))
.catch(() => {});
await db
.delete(federationPeers)
.where(inArray(federationPeers.id, [ids.peerId, ids.revokedPeerId]))
.catch(() => {});
await db
.delete(users)
.where(inArray(users.id, [ids.subjectUserId, ids.otherUserId]))
.catch(() => {});
}
describe.skipIf(!run)('federation M3 list verb — single-gateway integration', () => {
let handle: DbHandle;
let db: Db;
let moduleRef: TestingModule;
let guard: FederationAuthGuard;
let listController: ListController;
let ids: TestIds | undefined;
beforeAll(async () => {
handle = createDb(PG_URL);
db = handle.db;
ids = await seedFixtures(db);
moduleRef = await Test.createTestingModule({
controllers: [ListController],
providers: [
{ provide: DB, useValue: db },
GrantsService,
FederationAuthGuard,
FederationScopeService,
FederationListQueryService,
],
}).compile();
guard = moduleRef.get(FederationAuthGuard);
listController = moduleRef.get(ListController);
}, 30_000);
afterAll(async () => {
await moduleRef?.close().catch((e: unknown) => console.error('[fed-m3-10 cleanup]', e));
await cleanupFixtures(db, ids).catch((e: unknown) => console.error('[fed-m3-10 cleanup]', e));
await handle?.close().catch((e: unknown) => console.error('[fed-m3-10 cleanup]', e));
});
it('#6 — rejects a client cert with malformed/missing Mosaic OIDs with 401', async () => {
const malformedOidCert = await makeSelfSignedCert();
const request = makeFederationRequest(malformedOidCert);
const { context, sent } = makeGuardContext(request);
await expect(guard.canActivate(context)).resolves.toBe(false);
expect(sent.statusCode).toBe(401);
expect(sent.payload).toMatchObject({
error: {
code: 'unauthorized',
message: expect.stringContaining('missing required OID'),
},
});
expect(request.federationContext).toBeUndefined();
});
it('#6 — rejects a valid client cert when its grant is revoked with 403', async () => {
expect(ids).toBeDefined();
const revokedCert = await makeMosaicIssuedCert({
grantId: ids!.revokedGrantId,
subjectUserId: ids!.subjectUserId,
});
const request = makeFederationRequest(revokedCert);
const { context, sent } = makeGuardContext(request);
await expect(guard.canActivate(context)).resolves.toBe(false);
expect(sent.statusCode).toBe(403);
expect(sent.payload).toMatchObject({
error: {
code: 'forbidden',
message: 'Federation access denied',
},
});
expect(request.federationContext).toBeUndefined();
});
it('#7 — enforces max_rows_per_query on POST /api/federation/v1/list/:resource', async () => {
expect(ids).toBeDefined();
const activeCert = await makeMosaicIssuedCert({
grantId: ids!.activeGrantId,
subjectUserId: ids!.subjectUserId,
});
const request = makeFederationRequest(activeCert);
const { context } = makeGuardContext(request);
await expect(guard.canActivate(context)).resolves.toBe(true);
const response = await listController.list('tasks', request, { limit: 100 });
const returnedIds = response.items.map((item) => item['id']);
expect(response.items).toHaveLength(2);
expect(response._truncated).toBe(true);
expect(response.nextCursor).toEqual(expect.any(String));
expect(returnedIds).toEqual([ids!.taskIds[0], ids!.taskIds[1]]);
expect(returnedIds).not.toContain(ids!.taskIds[2]);
for (const excludedId of ids!.excludedTaskIds) {
expect(returnedIds).not.toContain(excludedId);
}
expect(response.items.every((item) => item._source === 'local')).toBe(true);
});
it('excludes another user mission task notes on the same authorized mission', async () => {
expect(ids).toBeDefined();
const activeCert = await makeMosaicIssuedCert({
grantId: ids!.activeGrantId,
subjectUserId: ids!.subjectUserId,
});
const request = makeFederationRequest(activeCert);
const { context } = makeGuardContext(request);
await expect(guard.canActivate(context)).resolves.toBe(true);
const response = await listController.list('notes', request, { limit: 10 });
const returnedIds = response.items.map((item) => item['id']);
expect(returnedIds).toEqual([ids!.subjectNoteId]);
expect(returnedIds).not.toContain(ids!.otherUserNoteId);
expect(response.items.every((item) => item._source === 'local')).toBe(true);
});
it('fails closed for unsupported list resources', async () => {
expect(ids).toBeDefined();
const activeCert = await makeMosaicIssuedCert({
grantId: ids!.activeGrantId,
subjectUserId: ids!.subjectUserId,
});
const request = makeFederationRequest(activeCert);
const { context } = makeGuardContext(request);
await expect(guard.canActivate(context)).resolves.toBe(true);
await expect(listController.list('widgets', request, {})).rejects.toMatchObject({
response: {
error: {
code: 'scope_violation',
message: 'Requested federation resource is not supported',
},
},
status: 403,
});
});
});
@@ -1,11 +1,9 @@
import { Controller, Get, Inject, Optional, UseGuards } from '@nestjs/common';
import { Controller, Get, Inject, UseGuards } from '@nestjs/common';
import { sql, type Db } from '@mosaicstack/db';
import { createQueue } from '@mosaicstack/queue';
import type { MosaicConfig } from '@mosaicstack/config';
import { DB } from '../database/database.module.js';
import { AgentService } from '../agent/agent.service.js';
import { ProviderService } from '../agent/provider.service.js';
import { MOSAIC_CONFIG } from '../config/config.module.js';
import { AdminGuard } from './admin.guard.js';
import type { HealthStatusDto, ServiceStatusDto } from './admin.dto.js';
@@ -16,9 +14,6 @@ export class AdminHealthController {
@Inject(DB) private readonly db: Db,
@Inject(AgentService) private readonly agentService: AgentService,
@Inject(ProviderService) private readonly providerService: ProviderService,
@Optional()
@Inject(MOSAIC_CONFIG)
private readonly mosaicConfig: MosaicConfig | null,
) {}
@Get()
@@ -60,14 +55,6 @@ export class AdminHealthController {
}
private async checkCache(): Promise<ServiceStatusDto> {
// On Local tier there is no Redis. The cache is intentionally absent, which
// is a healthy state for this tier — report 'ok' rather than opening a new
// ioredis connection on every admin health check (which would spam
// ECONNREFUSED and create/destroy a connection per request). latencyMs 0
// signals "no cache backend to measure" for this tier.
if (this.mosaicConfig?.queue?.type === 'local') {
return { status: 'ok', latencyMs: 0 };
}
const start = Date.now();
const handle = createQueue();
try {
@@ -1,4 +1,3 @@
import { Logger } from '@nestjs/common';
import { describe, it, expect, vi, beforeEach } from 'vitest';
import { CommandExecutorService } from './command-executor.service.js';
import type { SlashCommandPayload } from '@mosaicstack/types';
@@ -13,7 +12,6 @@ const mockRegistry = {
{ name: 'agent', aliases: ['a'], scope: 'agent', execution: 'socket', available: true },
{ name: 'prdy', aliases: [], scope: 'agent', execution: 'socket', available: true },
{ name: 'tools', aliases: [], scope: 'agent', execution: 'socket', available: true },
{ name: 'mcp', aliases: [], scope: 'agent', execution: 'socket', available: true },
],
skills: [],
})),
@@ -74,24 +72,17 @@ const mockChatGateway = {
broadcastSessionInfo: vi.fn(),
};
function buildService(
redis: typeof mockRedis | null = mockRedis,
mcpClient: {
reconnectServer: ReturnType<typeof vi.fn>;
getServerStatuses: ReturnType<typeof vi.fn>;
getToolDefinitions: ReturnType<typeof vi.fn>;
} | null = null,
): CommandExecutorService {
function buildService(): CommandExecutorService {
return new CommandExecutorService(
mockRegistry as never,
mockAgentService as never,
mockSystemOverride as never,
mockSessionGC as never,
redis as never,
mockRedis as never,
mockBrain as never,
null,
mockChatGateway as never,
mcpClient as never,
null,
);
}
@@ -140,22 +131,6 @@ describe('CommandExecutorService — P8-012 commands', () => {
expect(ttl).toBe(300);
});
it('/provider login remains available without Redis on the local tier', async () => {
const localService = buildService(null);
const payload: SlashCommandPayload = {
command: 'provider',
args: 'login anthropic',
conversationId,
};
const result = await localService.execute(payload, userScope);
expect(result.success).toBe(true);
expect(result.message).not.toContain('token=');
expect(result.data).toEqual({ provider: 'anthropic' });
expect(mockRedis.set).not.toHaveBeenCalled();
});
// /provider with no args — returns usage
it('/provider with no args returns usage message', async () => {
const payload: SlashCommandPayload = { command: 'provider', conversationId };
@@ -267,124 +242,4 @@ describe('CommandExecutorService — P8-012 commands', () => {
expect(result.command).toBe('tools');
expect(result.message).toContain('tools');
});
// Top-level catch sanitization (P3-4 re-review finding #1): a rejected
// Redis `set` inside /provider login is the only reachable path into the
// top-level catch in `execute()`. The raw exception must be logged
// server-side but never handed back to the socket client.
it('sanitizes the top-level command catch, logging the raw exception but never returning it to the client', async () => {
const distinctiveRawFailure = 'ECONNREFUSED distinctive-raw-redis-failure-token-9f31';
const rawError = new Error(distinctiveRawFailure);
const failingRedis = {
set: vi.fn().mockRejectedValue(rawError),
get: vi.fn(),
del: vi.fn(),
};
const failingService = buildService(failingRedis as unknown as typeof mockRedis);
const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
const payload: SlashCommandPayload = {
command: 'provider',
args: 'login anthropic',
conversationId,
};
const result = await failingService.execute(payload, userScope);
expect(result.success).toBe(false);
expect(result.command).toBe('provider');
expect(result.message).toBe('Command failed due to an internal error.');
expect(result.message).not.toContain(distinctiveRawFailure);
expect(result.message).not.toContain('ECONNREFUSED');
// The real exception is still logged server-side, as the raw Error
// object itself (not stringified/interpolated into the log message).
expect(loggerErrorSpy).toHaveBeenCalled();
const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(rawError));
expect(loggedRawError).toBe(true);
loggerErrorSpy.mockRestore();
});
// Inner catch sanitization (P3-5 operator ruling): every catch in
// command-executor.service.ts that returns a SlashCommandResultPayload
// must sanitize the client-facing message the same way the top-level
// catch does, while still logging the raw exception server-side.
it('/agent new sanitizes agent-creation failures, logging the raw exception but never returning it to the client', async () => {
const marker = new Error('distinctive-agent-create-failure-token-A17f');
mockBrain.agents.create.mockRejectedValueOnce(marker);
const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
const payload: SlashCommandPayload = {
command: 'agent',
args: 'new my-new-agent',
conversationId,
};
const result = await service.execute(payload, userScope);
expect(result.success).toBe(false);
expect(result.command).toBe('agent');
expect(result.message).toBe('Failed to create agent due to an internal error.');
expect(result.message).not.toContain('distinctive-agent-create-failure-token-A17f');
expect(loggerErrorSpy).toHaveBeenCalled();
const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
expect(loggedRawError).toBe(true);
loggerErrorSpy.mockRestore();
});
it('/agent <name> switch sanitizes agent-lookup failures, logging the raw exception but never returning it to the client', async () => {
const marker = new Error('distinctive-agent-switch-failure-token-B29c');
mockBrain.agents.findByName.mockRejectedValueOnce(marker);
const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
const payload: SlashCommandPayload = {
command: 'agent',
args: 'some-other-agent',
conversationId,
};
const result = await service.execute(payload, userScope);
expect(result.success).toBe(false);
expect(result.command).toBe('agent');
expect(result.message).toBe('Failed to switch agent due to an internal error.');
expect(result.message).not.toContain('distinctive-agent-switch-failure-token-B29c');
expect(loggerErrorSpy).toHaveBeenCalled();
const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
expect(loggedRawError).toBe(true);
loggerErrorSpy.mockRestore();
});
it('/mcp reconnect sanitizes MCP client failures, logging the raw exception but never returning it to the client', async () => {
const marker = new Error('distinctive-mcp-reconnect-failure-token-C33e');
const mockMcpClient = {
reconnectServer: vi.fn().mockRejectedValue(marker),
getServerStatuses: vi.fn(() => []),
getToolDefinitions: vi.fn(() => []),
};
const mcpService = buildService(mockRedis, mockMcpClient);
const loggerErrorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
const payload: SlashCommandPayload = {
command: 'mcp',
args: 'reconnect my-server',
conversationId,
};
const result = await mcpService.execute(payload, userScope);
expect(result.success).toBe(false);
expect(result.command).toBe('mcp');
expect(result.message).toBe(
'Failed to reconnect MCP server "my-server" due to an internal error.',
);
expect(result.message).not.toContain('distinctive-mcp-reconnect-failure-token-C33e');
expect(loggerErrorSpy).toHaveBeenCalled();
const loggedRawError = loggerErrorSpy.mock.calls.some((call) => call.includes(marker));
expect(loggedRawError).toBe(true);
loggerErrorSpy.mockRestore();
});
});
@@ -23,10 +23,7 @@ export class CommandExecutorService {
@Inject(AgentService) private readonly agentService: AgentService,
@Inject(SystemOverrideService) private readonly systemOverride: SystemOverrideService,
@Inject(SessionGCService) private readonly sessionGC: SessionGCService,
// On Local tier COMMANDS_REDIS is null — provider login caching is skipped.
@Optional()
@Inject(COMMANDS_REDIS)
private readonly redis: QueueHandle['redis'] | null,
@Inject(COMMANDS_REDIS) private readonly redis: QueueHandle['redis'],
@Inject(BRAIN) private readonly brain: Brain,
@Optional()
@Inject(forwardRef(() => ReloadService))
@@ -159,13 +156,8 @@ export class CommandExecutorService {
};
}
} catch (err) {
this.logger.error(`Command /${command} failed`, err);
return {
command,
conversationId,
success: false,
message: 'Command failed due to an internal error.',
};
this.logger.error(`Command /${command} failed: ${err}`);
return { command, conversationId, success: false, message: String(err) };
}
}
@@ -341,11 +333,11 @@ export class CommandExecutorService {
data: { agentId: newAgent.id, agentName: newAgent.name },
};
} catch (err) {
this.logger.error(`Failed to create agent "${namePart}" for user ${userId}`, err);
this.logger.error(`Failed to create agent: ${err}`);
return {
command: 'agent',
success: false,
message: 'Failed to create agent due to an internal error.',
message: `Failed to create agent: ${String(err)}`,
conversationId,
};
}
@@ -396,11 +388,11 @@ export class CommandExecutorService {
data: { agentId: agentConfig.id, agentName: agentConfig.name, model: agentConfig.model },
};
} catch (err) {
this.logger.error(`Failed to switch agent "${agentName}"`, err);
this.logger.error(`Failed to switch agent "${agentName}": ${err}`);
return {
command: 'agent',
success: false,
message: 'Failed to switch agent due to an internal error.',
message: `Failed to switch agent: ${String(err)}`,
conversationId,
};
}
@@ -451,16 +443,14 @@ export class CommandExecutorService {
byte.toString(16).padStart(2, '0'),
).join('');
const key = `mosaic:auth:poll:${tokenHash}`;
if (this.redis) {
// Persist only a short-lived token digest. The raw token is delivered only by
// the authenticated dashboard flow, never in chat output or command metadata.
await this.redis.set(
key,
JSON.stringify({ status: 'pending', provider: providerName, userId }),
'EX',
300,
);
}
// Persist only a short-lived token digest. The raw token is delivered only by
// the authenticated dashboard flow, never in chat output or command metadata.
await this.redis.set(
key,
JSON.stringify({ status: 'pending', provider: providerName, userId }),
'EX',
300,
);
return {
command: 'provider',
success: true,
@@ -613,12 +603,11 @@ export class CommandExecutorService {
message: `MCP server "${serverName}" reconnected successfully.`,
};
} catch (err) {
this.logger.error(`Failed to reconnect MCP server "${serverName}"`, err);
return {
command: 'mcp',
conversationId,
success: false,
message: `Failed to reconnect MCP server "${serverName}" due to an internal error.`,
message: `Failed to reconnect MCP server "${serverName}": ${err instanceof Error ? err.message : String(err)}`,
};
}
}
+5 -15
View File
@@ -1,7 +1,5 @@
import { forwardRef, Inject, Module, Optional, type OnApplicationShutdown } from '@nestjs/common';
import { forwardRef, Inject, Module, type OnApplicationShutdown } from '@nestjs/common';
import { createQueue, type QueueHandle } from '@mosaicstack/queue';
import type { MosaicConfig } from '@mosaicstack/config';
import { MOSAIC_CONFIG } from '../config/config.module.js';
import { ChatModule } from '../chat/chat.module.js';
import { GCModule } from '../gc/gc.module.js';
import { ReloadModule } from '../reload/reload.module.js';
@@ -18,17 +16,13 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
providers: [
{
provide: COMMANDS_QUEUE_HANDLE,
useFactory: (config: MosaicConfig | null): QueueHandle | null => {
// On Local tier there is no Redis — skip the ioredis connection.
// CommandExecutorService falls back to no-cache for /provider login on local.
if (config?.queue?.type === 'local') return null;
useFactory: (): QueueHandle => {
return createQueue();
},
inject: [MOSAIC_CONFIG],
},
{
provide: COMMANDS_REDIS,
useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
useFactory: (handle: QueueHandle) => handle.redis,
inject: [COMMANDS_QUEUE_HANDLE],
},
CommandRegistryService,
@@ -44,13 +38,9 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
],
})
export class CommandsModule implements OnApplicationShutdown {
constructor(
@Optional()
@Inject(COMMANDS_QUEUE_HANDLE)
private readonly handle: QueueHandle | null,
) {}
constructor(@Inject(COMMANDS_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
async onApplicationShutdown(): Promise<void> {
await this.handle?.close().catch(() => {});
await this.handle.close().catch(() => {});
}
}
@@ -5,8 +5,6 @@ import { EnrollmentController } from './enrollment.controller.js';
import { EnrollmentService } from './enrollment.service.js';
import { FederationController } from './federation.controller.js';
import { CapabilitiesController } from './server/verbs/capabilities.controller.js';
import { GetController } from './server/verbs/get.controller.js';
import { FederationGetQueryService } from './server/verbs/get-query.service.js';
import { GrantsService } from './grants.service.js';
import { FederationClientService, QuerySourceService } from './client/index.js';
import { FederationAuthGuard, FederationScopeService } from './server/index.js';
@@ -14,13 +12,7 @@ import { ListController } from './server/verbs/list.controller.js';
import { FederationListQueryService } from './server/verbs/list-query.service.js';
@Module({
controllers: [
EnrollmentController,
FederationController,
CapabilitiesController,
ListController,
GetController,
],
controllers: [EnrollmentController, FederationController, CapabilitiesController, ListController],
providers: [
AdminGuard,
CaService,
@@ -31,7 +23,6 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
FederationAuthGuard,
FederationScopeService,
FederationListQueryService,
FederationGetQueryService,
],
exports: [
CaService,
@@ -42,7 +33,6 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
FederationAuthGuard,
FederationScopeService,
FederationListQueryService,
FederationGetQueryService,
],
})
export class FederationModule {}
@@ -1,348 +0,0 @@
import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest';
import {
createPgliteDb,
missionTasks,
missions,
projects,
runPgliteMigrations,
teams,
users,
type Db,
type DbHandle,
} from '@mosaicstack/db';
import type { FederationScopeQueryFilter } from '../../scope.service.js';
import { FederationGetQueryService } from '../get-query.service.js';
const CREDENTIAL_FILTER: FederationScopeQueryFilter = {
resource: 'credentials',
subjectUserId: 'user-1',
includePersonal: true,
teamIds: [],
limit: 1,
maxRowsPerQuery: 25,
};
const SUBJECT_USER_ID = 'fed-m3-06-subject';
const OTHER_USER_ID = 'fed-m3-06-other';
const TEAM_ID = '06000000-0000-4000-8000-000000000001';
const UNAUTHORIZED_TEAM_ID = '06000000-0000-4000-8000-000000000002';
const PERSONAL_PROJECT_ID = '06000000-0000-4000-8000-000000000101';
const TEAM_PROJECT_ID = '06000000-0000-4000-8000-000000000102';
const UNAUTHORIZED_PROJECT_ID = '06000000-0000-4000-8000-000000000103';
const PERSONAL_MISSION_ID = '06000000-0000-4000-8000-000000000201';
const TEAM_MISSION_ID = '06000000-0000-4000-8000-000000000202';
const UNAUTHORIZED_MISSION_ID = '06000000-0000-4000-8000-000000000203';
const SUBJECT_TEAM_NOTE_ID = '06000000-0000-4000-8000-000000000301';
const OTHER_TEAM_NOTE_ID = '06000000-0000-4000-8000-000000000302';
const SUBJECT_PERSONAL_NOTE_ID = '06000000-0000-4000-8000-000000000303';
const SUBJECT_UNAUTHORIZED_NOTE_ID = '06000000-0000-4000-8000-000000000304';
let dbHandle: DbHandle | undefined;
function makeService() {
return new FederationGetQueryService({} as Db);
}
function makeDbService() {
if (!dbHandle) {
throw new Error('test DB not initialized');
}
return new FederationGetQueryService(dbHandle.db);
}
async function seedNotesFixture() {
if (!dbHandle) {
throw new Error('test DB not initialized');
}
await dbHandle.db.insert(users).values([
{
id: SUBJECT_USER_ID,
name: 'Federation Subject',
email: `${SUBJECT_USER_ID}@example.test`,
emailVerified: false,
},
{
id: OTHER_USER_ID,
name: 'Federation Other',
email: `${OTHER_USER_ID}@example.test`,
emailVerified: false,
},
]);
await dbHandle.db.insert(teams).values([
{
id: TEAM_ID,
name: 'FED-M3-06 Team',
slug: 'fed-m3-06-team',
ownerId: SUBJECT_USER_ID,
managerId: SUBJECT_USER_ID,
},
{
id: UNAUTHORIZED_TEAM_ID,
name: 'FED-M3-06 Unauthorized Team',
slug: 'fed-m3-06-unauthorized-team',
ownerId: OTHER_USER_ID,
managerId: OTHER_USER_ID,
},
]);
await dbHandle.db.insert(projects).values([
{
id: PERSONAL_PROJECT_ID,
name: 'FED-M3-06 Personal Project',
ownerId: SUBJECT_USER_ID,
ownerType: 'user',
},
{
id: TEAM_PROJECT_ID,
name: 'FED-M3-06 Team Project',
teamId: TEAM_ID,
ownerType: 'team',
},
{
id: UNAUTHORIZED_PROJECT_ID,
name: 'FED-M3-06 Unauthorized Project',
teamId: UNAUTHORIZED_TEAM_ID,
ownerType: 'team',
},
]);
await dbHandle.db.insert(missions).values([
{
id: PERSONAL_MISSION_ID,
name: 'FED-M3-06 Personal Mission',
projectId: PERSONAL_PROJECT_ID,
userId: SUBJECT_USER_ID,
},
{
id: TEAM_MISSION_ID,
name: 'FED-M3-06 Team Mission',
projectId: TEAM_PROJECT_ID,
userId: SUBJECT_USER_ID,
},
{
id: UNAUTHORIZED_MISSION_ID,
name: 'FED-M3-06 Unauthorized Mission',
projectId: UNAUTHORIZED_PROJECT_ID,
userId: SUBJECT_USER_ID,
},
]);
await dbHandle.db.insert(missionTasks).values([
{
id: SUBJECT_TEAM_NOTE_ID,
missionId: TEAM_MISSION_ID,
userId: SUBJECT_USER_ID,
notes: 'subject note on team mission',
createdAt: new Date('2026-06-24T03:00:00.000Z'),
updatedAt: new Date('2026-06-24T03:00:00.000Z'),
},
{
id: OTHER_TEAM_NOTE_ID,
missionId: TEAM_MISSION_ID,
userId: OTHER_USER_ID,
notes: 'other user note on team mission',
createdAt: new Date('2026-06-24T02:00:00.000Z'),
updatedAt: new Date('2026-06-24T02:00:00.000Z'),
},
{
id: SUBJECT_PERSONAL_NOTE_ID,
missionId: PERSONAL_MISSION_ID,
userId: SUBJECT_USER_ID,
notes: 'subject note on personal mission',
createdAt: new Date('2026-06-24T01:00:00.000Z'),
updatedAt: new Date('2026-06-24T01:00:00.000Z'),
},
{
id: SUBJECT_UNAUTHORIZED_NOTE_ID,
missionId: UNAUTHORIZED_MISSION_ID,
userId: SUBJECT_USER_ID,
notes: 'subject note outside grant-visible missions',
createdAt: new Date('2026-06-24T04:00:00.000Z'),
updatedAt: new Date('2026-06-24T04:00:00.000Z'),
},
]);
}
describe('FederationGetQueryService', () => {
beforeAll(async () => {
dbHandle = createPgliteDb(`memory://fed-m3-06-get-${Date.now()}`);
await runPgliteMigrations(dbHandle);
await seedNotesFixture();
});
afterAll(async () => {
await dbHandle?.close();
dbHandle = undefined;
});
it('denies sensitive resources in native RBAC for M3 get reads', async () => {
const service = makeService();
await expect(
service.evaluateReadAccess({
grantId: 'grant-1',
peerId: 'peer-1',
subjectUserId: 'user-1',
resource: 'credentials',
}),
).resolves.toMatchObject({
allowed: false,
reason: 'credentials federation get access is not implemented in M3',
});
});
it('allows personal memory reads without requiring team lookup', async () => {
const service = makeService();
await expect(
service.evaluateReadAccess({
grantId: 'grant-1',
peerId: 'peer-1',
subjectUserId: 'user-1',
resource: 'memory',
}),
).resolves.toEqual({
allowed: true,
access: { includePersonal: true, teamIds: [] },
});
});
it('uses subject team membership as the native RBAC upper bound for task and note reads', async () => {
const service = makeService();
const listSubjectTeamIds = vi.fn().mockResolvedValue(['team-1', 'team-2']);
(
service as unknown as {
listSubjectTeamIds: (subjectUserId: string) => Promise<string[]>;
}
).listSubjectTeamIds = listSubjectTeamIds;
await expect(
service.evaluateReadAccess({
grantId: 'grant-1',
peerId: 'peer-1',
subjectUserId: 'user-1',
resource: 'tasks',
}),
).resolves.toEqual({
allowed: true,
access: { includePersonal: true, teamIds: ['team-1', 'team-2'] },
});
expect(listSubjectTeamIds).toHaveBeenCalledWith('user-1');
});
it('does not query storage for sensitive get resources even if scope allowed them', async () => {
const service = makeService();
await expect(service.get({ filter: CREDENTIAL_FILTER, id: 'cred-1' })).resolves.toEqual({
status: 'denied',
reason: 'credentials federation get is not implemented',
});
});
it('fails closed for unsupported resources instead of returning undefined', async () => {
const service = makeService();
await expect(
service.get({
filter: {
...CREDENTIAL_FILTER,
resource: 'unknown-resource' as FederationScopeQueryFilter['resource'],
},
id: 'row-1',
}),
).resolves.toEqual({
status: 'denied',
reason: 'Unsupported federation get resource: unknown-resource',
});
});
it('does not leak another user mission task note through team-scoped get reads', async () => {
const service = makeDbService();
await expect(
service.get({
filter: {
resource: 'notes',
subjectUserId: SUBJECT_USER_ID,
includePersonal: false,
teamIds: [TEAM_ID],
limit: 1,
maxRowsPerQuery: 10,
},
id: OTHER_TEAM_NOTE_ID,
}),
).resolves.toEqual({
status: 'denied',
reason: 'Note is outside the federated scope',
});
});
it('does not return subject notes from missions outside the grant-visible project set', async () => {
const service = makeDbService();
await expect(
service.get({
filter: {
resource: 'notes',
subjectUserId: SUBJECT_USER_ID,
includePersonal: true,
teamIds: [TEAM_ID],
limit: 1,
maxRowsPerQuery: 10,
},
id: SUBJECT_UNAUTHORIZED_NOTE_ID,
}),
).resolves.toEqual({
status: 'denied',
reason: 'Note is outside the federated scope',
});
});
it('returns a subject note only when subject ownership and authorized mission intersect', async () => {
const service = makeDbService();
await expect(
service.get({
filter: {
resource: 'notes',
subjectUserId: SUBJECT_USER_ID,
includePersonal: false,
teamIds: [TEAM_ID],
limit: 1,
maxRowsPerQuery: 10,
},
id: SUBJECT_TEAM_NOTE_ID,
}),
).resolves.toMatchObject({
status: 'found',
item: {
id: SUBJECT_TEAM_NOTE_ID,
missionId: TEAM_MISSION_ID,
content: 'subject note on team mission',
},
});
});
it('does not return subject personal notes when includePersonal is false', async () => {
const service = makeDbService();
await expect(
service.get({
filter: {
resource: 'notes',
subjectUserId: SUBJECT_USER_ID,
includePersonal: false,
teamIds: [TEAM_ID],
limit: 1,
maxRowsPerQuery: 10,
},
id: SUBJECT_PERSONAL_NOTE_ID,
}),
).resolves.toEqual({
status: 'denied',
reason: 'Note is outside the federated scope',
});
});
});
@@ -1,207 +0,0 @@
import 'reflect-metadata';
import { RequestMethod } from '@nestjs/common';
import type { FastifyRequest } from 'fastify';
import { beforeEach, describe, expect, it, vi } from 'vitest';
import { FederationAuthGuard } from '../../federation-auth.guard.js';
import type {
FederationScopeEvaluationResult,
FederationScopeQueryFilter,
} from '../../scope.service.js';
import { GetController } from '../get.controller.js';
import type { FederationGetQueryResult } from '../get-query.service.js';
const FEDERATION_CONTEXT = {
grantId: 'grant-1',
peerId: 'peer-1',
subjectUserId: 'user-1',
scope: { resources: ['tasks'], max_rows_per_query: 25 },
};
const TASK_FILTER: FederationScopeQueryFilter = {
resource: 'tasks',
subjectUserId: 'user-1',
includePersonal: true,
teamIds: ['team-1'],
limit: 1,
maxRowsPerQuery: 25,
};
function makeRequest(): FastifyRequest {
return { federationContext: FEDERATION_CONTEXT } as unknown as FastifyRequest;
}
function allowedScope(
filter: FederationScopeQueryFilter = TASK_FILTER,
): FederationScopeEvaluationResult {
return { allowed: true, filter };
}
function makeController(opts?: {
scopeResult?: FederationScopeEvaluationResult;
queryResult?: FederationGetQueryResult;
}) {
const scope = {
evaluateAccess: vi.fn().mockResolvedValue(opts?.scopeResult ?? allowedScope()),
};
const query = {
evaluateReadAccess: vi.fn(),
get: vi.fn().mockResolvedValue(
opts?.queryResult ?? {
status: 'found',
item: {
id: 'task-1',
title: 'Federated task',
createdAt: new Date('2026-06-24T00:00:00.000Z'),
},
},
),
};
return {
controller: new GetController(scope as never, query as never),
scope,
query,
};
}
describe('GetController', () => {
beforeEach(() => {
vi.clearAllMocks();
});
it('declares POST /api/federation/v1/get/:resource/:id protected only by FederationAuthGuard', () => {
expect(Reflect.getMetadata('path', GetController)).toBe('api/federation/v1/get');
expect(Reflect.getMetadata('path', GetController.prototype.get)).toBe(':resource/:id');
expect(Reflect.getMetadata('method', GetController.prototype.get)).toBe(RequestMethod.POST);
expect(Reflect.getMetadata('__guards__', GetController)).toEqual([FederationAuthGuard]);
});
it('runs AuthGuard context through ScopeService and returns one local-source tagged row', async () => {
const { controller, scope, query } = makeController();
const response = await controller.get('tasks', 'task-1', makeRequest());
expect(scope.evaluateAccess).toHaveBeenCalledWith({
context: FEDERATION_CONTEXT,
resource: 'tasks',
requestedLimit: 1,
nativeRbac: query,
});
expect(query.get).toHaveBeenCalledWith({ filter: TASK_FILTER, id: 'task-1' });
expect(response).toEqual({
item: {
id: 'task-1',
title: 'Federated task',
createdAt: new Date('2026-06-24T00:00:00.000Z'),
_source: 'local',
},
});
});
it('returns a federation error envelope when auth guard context is missing', async () => {
const { controller, scope, query } = makeController();
await expect(
controller.get('tasks', 'task-1', {} as unknown as FastifyRequest),
).rejects.toMatchObject({
response: {
error: {
code: 'unauthorized',
message: 'Federation context missing',
},
},
status: 401,
});
expect(scope.evaluateAccess).not.toHaveBeenCalled();
expect(query.get).not.toHaveBeenCalled();
});
it('returns a federation error envelope when scope evaluation denies access', async () => {
const { controller, query } = makeController({
scopeResult: {
allowed: false,
deny: {
code: 'resource_excluded',
stage: 'resource_exclusion',
statusCode: 403,
message: 'Requested federation resource is explicitly excluded by grant scope',
grantId: 'grant-1',
peerId: 'peer-1',
subjectUserId: 'user-1',
resource: 'credentials',
},
},
});
await expect(controller.get('credentials', 'cred-1', makeRequest())).rejects.toMatchObject({
response: {
error: {
code: 'scope_violation',
message: 'Requested federation resource is explicitly excluded by grant scope',
},
},
status: 403,
});
expect(query.get).not.toHaveBeenCalled();
});
it('returns 404 when the scoped query layer cannot find the resource id', async () => {
const { controller } = makeController({ queryResult: { status: 'not_found' } });
await expect(controller.get('tasks', 'missing-task', makeRequest())).rejects.toMatchObject({
response: { error: { code: 'not_found' } },
status: 404,
});
});
it('returns 403 when the resource exists outside the RBAC/scope intersection', async () => {
const { controller } = makeController({
queryResult: { status: 'denied', reason: 'Task is outside the federated scope' },
});
await expect(controller.get('tasks', 'task-2', makeRequest())).rejects.toMatchObject({
response: {
error: {
code: 'scope_violation',
message: 'Task is outside the federated scope',
},
},
status: 403,
});
});
it('fails closed when the query layer denies an unsupported resource', async () => {
const unsupportedFilter: FederationScopeQueryFilter = {
...TASK_FILTER,
resource: 'unknown-resource' as FederationScopeQueryFilter['resource'],
};
const { controller } = makeController({
scopeResult: allowedScope(unsupportedFilter),
queryResult: {
status: 'denied',
reason: 'Unsupported federation get resource: unknown-resource',
},
});
await expect(controller.get('unknown-resource', 'row-1', makeRequest())).rejects.toMatchObject({
response: {
error: {
code: 'scope_violation',
message: 'Unsupported federation get resource: unknown-resource',
},
},
status: 403,
});
});
it('rejects empty ids before evaluating scope', async () => {
const { controller, scope, query } = makeController();
await expect(controller.get('tasks', ' ', makeRequest())).rejects.toMatchObject({
response: { error: { code: 'invalid_request' } },
status: 400,
});
expect(scope.evaluateAccess).not.toHaveBeenCalled();
expect(query.get).not.toHaveBeenCalled();
});
});
@@ -1,311 +0,0 @@
/**
* Federation get query layer (FED-M3-06).
*
* Read-only DB adapter used by GetController after FederationAuthGuard and
* FederationScopeService have established the subject user, allowed resource,
* native-RBAC intersection, and row cap. Audit writes are intentionally
* deferred to M4.
*/
import { Inject, Injectable } from '@nestjs/common';
import {
and,
eq,
inArray,
insights,
or,
missionTasks,
missions,
preferences,
projects,
tasks,
teamMembers,
type Db,
} from '@mosaicstack/db';
import { DB } from '../../../database/database.module.js';
import type {
FederationNativeRbacEvaluator,
FederationNativeRbacRequest,
FederationNativeRbacResult,
FederationScopeQueryFilter,
} from '../scope.service.js';
export interface FederationGetQueryRequest {
readonly filter: FederationScopeQueryFilter;
readonly id: string;
}
export interface FederationGetQueryFoundResult<T extends object = Record<string, unknown>> {
readonly status: 'found';
readonly item: T;
}
export interface FederationGetQueryNotFoundResult {
readonly status: 'not_found';
}
export interface FederationGetQueryDeniedResult {
readonly status: 'denied';
readonly reason: string;
}
export type FederationGetQueryResult<T extends object = Record<string, unknown>> =
| FederationGetQueryFoundResult<T>
| FederationGetQueryNotFoundResult
| FederationGetQueryDeniedResult;
type RowObject = Record<string, unknown>;
function firstRow<T>(rows: T[]): T | undefined {
return rows[0];
}
function rowBelongsToAccessibleProjectOrMission(
row: { projectId?: string | null; missionId?: string | null },
projectIds: readonly string[],
missionIds: readonly string[],
): boolean {
return (
(typeof row.projectId === 'string' && projectIds.includes(row.projectId)) ||
(typeof row.missionId === 'string' && missionIds.includes(row.missionId))
);
}
@Injectable()
export class FederationGetQueryService implements FederationNativeRbacEvaluator {
constructor(@Inject(DB) private readonly db: Db) {}
async evaluateReadAccess(
request: FederationNativeRbacRequest,
): Promise<FederationNativeRbacResult> {
if (request.resource === 'credentials' || request.resource === 'api_keys') {
return {
allowed: false,
reason: `${request.resource} federation get access is not implemented in M3`,
details: { resource: request.resource },
};
}
if (request.resource === 'memory') {
return { allowed: true, access: { includePersonal: true, teamIds: [] } };
}
const teamIds = await this.listSubjectTeamIds(request.subjectUserId);
return { allowed: true, access: { includePersonal: true, teamIds } };
}
async get<T extends RowObject = RowObject>(
request: FederationGetQueryRequest,
): Promise<FederationGetQueryResult<T>> {
return this.getByResource(request.filter, request.id) as Promise<FederationGetQueryResult<T>>;
}
private async getByResource(
filter: FederationScopeQueryFilter,
id: string,
): Promise<FederationGetQueryResult> {
switch (filter.resource) {
case 'tasks':
return this.getTask(filter, id);
case 'notes':
return this.getNote(filter, id);
case 'memory':
return this.getMemory(filter, id);
case 'credentials':
case 'api_keys':
return { status: 'denied', reason: `${filter.resource} federation get is not implemented` };
default:
return {
status: 'denied',
reason: `Unsupported federation get resource: ${String(filter.resource)}`,
};
}
}
private async listSubjectTeamIds(subjectUserId: string): Promise<string[]> {
const rows = await this.db
.select({ teamId: teamMembers.teamId })
.from(teamMembers)
.where(eq(teamMembers.userId, subjectUserId));
return rows.map((row) => row.teamId);
}
private async listAccessibleProjectIds(filter: FederationScopeQueryFilter): Promise<string[]> {
const clauses = [];
if (filter.includePersonal) {
clauses.push(and(eq(projects.ownerType, 'user'), eq(projects.ownerId, filter.subjectUserId)));
}
if (filter.teamIds.length > 0) {
// Project team ownership follows TeamsService.canAccessProject: team-owned
// rows are authorized through projects.teamId, while ownerId remains the
// user who created/bootstrapped the project.
clauses.push(
and(eq(projects.ownerType, 'team'), inArray(projects.teamId, [...filter.teamIds])),
);
}
if (clauses.length === 0) {
return [];
}
const rows = await this.db
.select({ id: projects.id })
.from(projects)
.where(clauses.length === 1 ? clauses[0] : or(...clauses));
return rows.map((row) => row.id);
}
private async listMissionIds(projectIds: readonly string[]): Promise<string[]> {
if (projectIds.length === 0) {
return [];
}
const rows = await this.db
.select({ id: missions.id })
.from(missions)
.where(inArray(missions.projectId, [...projectIds]));
return rows.map((row) => row.id);
}
private async getTask(
filter: FederationScopeQueryFilter,
id: string,
): Promise<FederationGetQueryResult> {
const row = firstRow(
await this.db
.select({
id: tasks.id,
title: tasks.title,
description: tasks.description,
status: tasks.status,
priority: tasks.priority,
projectId: tasks.projectId,
missionId: tasks.missionId,
assignee: tasks.assignee,
tags: tasks.tags,
dueDate: tasks.dueDate,
metadata: tasks.metadata,
createdAt: tasks.createdAt,
updatedAt: tasks.updatedAt,
})
.from(tasks)
.where(eq(tasks.id, id))
.limit(1),
);
if (!row) {
return { status: 'not_found' };
}
const projectIds = await this.listAccessibleProjectIds(filter);
const missionIds = await this.listMissionIds(projectIds);
if (!rowBelongsToAccessibleProjectOrMission(row, projectIds, missionIds)) {
return { status: 'denied', reason: 'Task is outside the federated scope' };
}
return { status: 'found', item: row as RowObject };
}
private async getNote(
filter: FederationScopeQueryFilter,
id: string,
): Promise<FederationGetQueryResult> {
const row = firstRow(
await this.db
.select({
id: missionTasks.id,
missionId: missionTasks.missionId,
taskId: missionTasks.taskId,
userId: missionTasks.userId,
status: missionTasks.status,
content: missionTasks.notes,
createdAt: missionTasks.createdAt,
updatedAt: missionTasks.updatedAt,
})
.from(missionTasks)
.where(eq(missionTasks.id, id))
.limit(1),
);
if (!row || row.content === null || row.content === '') {
return { status: 'not_found' };
}
const projectIds = await this.listAccessibleProjectIds(filter);
const missionIds = await this.listMissionIds(projectIds);
// mission_tasks rows are user-scoped even when the mission belongs to a team.
// Scope-visible missions must intersect with subject ownership; team scope
// narrows mission IDs but never widens note reads to another user's rows.
if (row.userId !== filter.subjectUserId || !missionIds.includes(row.missionId)) {
return { status: 'denied', reason: 'Note is outside the federated scope' };
}
const item = { ...row } as RowObject;
delete item['userId'];
return { status: 'found', item };
}
private async getMemory(
filter: FederationScopeQueryFilter,
id: string,
): Promise<FederationGetQueryResult> {
const [insightRow, preferenceRow] = await Promise.all([
this.db
.select({
id: insights.id,
userId: insights.userId,
kind: insights.source,
content: insights.content,
category: insights.category,
relevanceScore: insights.relevanceScore,
metadata: insights.metadata,
createdAt: insights.createdAt,
updatedAt: insights.updatedAt,
})
.from(insights)
.where(eq(insights.id, id))
.limit(1)
.then(firstRow),
this.db
.select({
id: preferences.id,
userId: preferences.userId,
kind: preferences.category,
key: preferences.key,
value: preferences.value,
source: preferences.source,
mutable: preferences.mutable,
createdAt: preferences.createdAt,
updatedAt: preferences.updatedAt,
})
.from(preferences)
.where(eq(preferences.id, id))
.limit(1)
.then(firstRow),
]);
const candidates = [insightRow, preferenceRow].filter(
(row): row is NonNullable<typeof row> => row !== undefined,
);
if (candidates.length === 0) {
return { status: 'not_found' };
}
if (!filter.includePersonal) {
return { status: 'denied', reason: 'Memory personal rows are outside the federated scope' };
}
const accessible = candidates.find((row) => row.userId === filter.subjectUserId);
if (!accessible) {
return { status: 'denied', reason: 'Memory row belongs to another subject user' };
}
const item = { ...accessible } as RowObject;
delete item['userId'];
return { status: 'found', item };
}
}
@@ -1,100 +0,0 @@
/**
* Federation get verb (FED-M3-06).
*
* POST /api/federation/v1/get/:resource/:id
*
* Pipeline: FederationAuthGuard attaches the active grant context, then
* FederationScopeService enforces grant scope + native RBAC intersection, then
* the read-only query layer fetches one local row and tags it with `_source`.
* Read audit-log writes are deferred to M4; this controller does not persist
* request or response bodies.
*/
import { Controller, HttpException, Inject, Param, Post, Req, UseGuards } from '@nestjs/common';
import type { FastifyRequest } from 'fastify';
import {
FederationInvalidRequestError,
FederationNotFoundError,
FederationScopeViolationError,
FederationUnauthorizedError,
SOURCE_LOCAL,
type FederationGetResponse,
type SourceTag,
} from '@mosaicstack/types';
import { FederationAuthGuard } from '../federation-auth.guard.js';
import '../federation-context.js';
import { FederationScopeService } from '../scope.service.js';
import { FederationGetQueryService } from './get-query.service.js';
type FederatedRow = Record<string, unknown> & SourceTag;
function scopeDenyToHttpException(deny: {
readonly statusCode: 400 | 403;
readonly message: string;
}): HttpException {
const ErrorClass =
deny.statusCode === 400 ? FederationInvalidRequestError : FederationScopeViolationError;
return new HttpException(new ErrorClass(deny.message, deny).toEnvelope(), deny.statusCode);
}
@Controller('api/federation/v1/get')
@UseGuards(FederationAuthGuard)
export class GetController {
constructor(
@Inject(FederationScopeService) private readonly scope: FederationScopeService,
@Inject(FederationGetQueryService) private readonly query: FederationGetQueryService,
) {}
@Post(':resource/:id')
async get(
@Param('resource') resource: string,
@Param('id') id: string,
@Req() request: FastifyRequest,
): Promise<FederationGetResponse<FederatedRow>> {
if (!request.federationContext) {
throw new HttpException(
new FederationUnauthorizedError('Federation context missing').toEnvelope(),
401,
);
}
if (id.trim().length === 0) {
throw new HttpException(
new FederationInvalidRequestError('Federation get id must not be empty').toEnvelope(),
400,
);
}
const scopeResult = await this.scope.evaluateAccess({
context: request.federationContext,
resource,
requestedLimit: 1,
nativeRbac: this.query,
});
if (!scopeResult.allowed) {
throw scopeDenyToHttpException(scopeResult.deny);
}
const result = await this.query.get({ filter: scopeResult.filter, id });
if (result.status === 'not_found') {
throw new HttpException(
new FederationNotFoundError('Requested federation resource was not found').toEnvelope(),
404,
);
}
if (result.status === 'denied') {
throw new HttpException(
new FederationScopeViolationError(result.reason, {
resource,
id,
grantId: request.federationContext.grantId,
peerId: request.federationContext.peerId,
subjectUserId: request.federationContext.subjectUserId,
}).toEnvelope(),
403,
);
}
return { item: { ...result.item, _source: SOURCE_LOCAL } };
}
}
+5 -15
View File
@@ -1,7 +1,5 @@
import { Module, type OnApplicationShutdown, Inject, Optional } from '@nestjs/common';
import { Module, type OnApplicationShutdown, Inject } from '@nestjs/common';
import { createQueue, type QueueHandle } from '@mosaicstack/queue';
import type { MosaicConfig } from '@mosaicstack/config';
import { MOSAIC_CONFIG } from '../config/config.module.js';
import { SessionGCService } from './session-gc.service.js';
import { REDIS } from './gc.tokens.js';
@@ -11,17 +9,13 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
providers: [
{
provide: GC_QUEUE_HANDLE,
useFactory: (config: MosaicConfig | null): QueueHandle | null => {
// On Local tier there is no Redis — skip the ioredis connection entirely.
// The Valkey GC sweep is a no-op on Local (no session keys stored there).
if (config?.queue?.type === 'local') return null;
useFactory: (): QueueHandle => {
return createQueue();
},
inject: [MOSAIC_CONFIG],
},
{
provide: REDIS,
useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
useFactory: (handle: QueueHandle) => handle.redis,
inject: [GC_QUEUE_HANDLE],
},
SessionGCService,
@@ -29,13 +23,9 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
exports: [SessionGCService],
})
export class GCModule implements OnApplicationShutdown {
constructor(
@Optional()
@Inject(GC_QUEUE_HANDLE)
private readonly handle: QueueHandle | null,
) {}
constructor(@Inject(GC_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
async onApplicationShutdown(): Promise<void> {
await this.handle?.close().catch(() => {});
await this.handle.close().catch(() => {});
}
}
@@ -119,19 +119,6 @@ describe('SessionGCService', () => {
).resolves.toEqual({ allowed: true });
});
it('collect() skips Valkey but still demotes only the requested session on local tier', async () => {
const localService = new SessionGCService(null, mockLogService as unknown as LogService);
const result = await localService.collect('local-session');
expect(result.sessionId).toBe('local-session');
expect(result.cleaned.valkeyKeys).toBeUndefined();
expect(mockLogService.logs.promoteSessionToWarm).toHaveBeenCalledWith(
'local-session',
expect.any(Date),
);
});
it('collect() returns sessionId in result', async () => {
const result = await service.collect('test-session-id');
expect(result.sessionId).toBe('test-session-id');
+8 -15
View File
@@ -1,4 +1,4 @@
import { Inject, Injectable, Optional } from '@nestjs/common';
import { Inject, Injectable } from '@nestjs/common';
import type { QueueHandle } from '@mosaicstack/queue';
import type { LogService } from '@mosaicstack/log';
import { LOG_SERVICE } from '../log/log.tokens.js';
@@ -21,10 +21,7 @@ function escapeRedisGlobLiteral(value: string): string {
@Injectable()
export class SessionGCService {
constructor(
// Local tier has no Redis; lifecycle cleanup still demotes this session's logs.
@Optional()
@Inject(REDIS)
private readonly redis: QueueHandle['redis'] | null,
@Inject(REDIS) private readonly redis: QueueHandle['redis'],
@Inject(LOG_SERVICE) private readonly logService: LogService,
) {}
@@ -32,10 +29,8 @@ export class SessionGCService {
* Scan Valkey for all keys matching a pattern using SCAN (non-blocking).
* KEYS is avoided because it blocks the Valkey event loop for the full scan
* duration, which can cause latency spikes under production key volumes.
* Returns an empty population on the Local tier where Redis is disabled.
*/
private async scanKeys(pattern: string): Promise<string[]> {
if (!this.redis) return [];
const collected: string[] = [];
let cursor = '0';
do {
@@ -52,14 +47,12 @@ export class SessionGCService {
async collect(sessionId: string): Promise<GCResult> {
const result: GCResult = { sessionId, cleaned: {} };
// 1. Valkey: delete all session-scoped keys (skipped on Local tier).
if (this.redis) {
const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
const valkeyKeys = await this.scanKeys(pattern);
if (valkeyKeys.length > 0) {
await this.redis.del(...valkeyKeys);
result.cleaned.valkeyKeys = valkeyKeys.length;
}
// 1. Valkey: delete all session-scoped keys
const pattern = `mosaic:session:${escapeRedisGlobLiteral(sessionId)}:*`;
const valkeyKeys = await this.scanKeys(pattern);
if (valkeyKeys.length > 0) {
await this.redis.del(...valkeyKeys);
result.cleaned.valkeyKeys = valkeyKeys.length;
}
// 2. PG: demote hot-tier agent logs for this session only.
+3 -9
View File
@@ -18,7 +18,7 @@ import type { MosaicJobData } from '../queue/queue.service.js';
@Injectable()
export class CronService implements OnModuleInit, OnModuleDestroy {
private readonly logger = new Logger(CronService.name);
private readonly registeredWorkers: Array<Worker<MosaicJobData>> = [];
private readonly registeredWorkers: Worker<MosaicJobData>[] = [];
constructor(
@Inject(SummarizationService) private readonly summarization: SummarizationService,
@@ -26,12 +26,6 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
) {}
async onModuleInit(): Promise<void> {
// Local tier deliberately has no BullMQ consumers or repeatable jobs.
if (!this.queueService.isEnabled()) {
this.logger.log('CronService: BullMQ disabled on local tier — no jobs will be scheduled');
return;
}
const summarizationSchedule = process.env['SUMMARIZATION_CRON'] ?? '0 */6 * * *'; // every 6 hours
const tierManagementSchedule = process.env['TIER_MANAGEMENT_CRON'] ?? '0 3 * * *'; // daily at 3am
@@ -45,7 +39,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
const summarizationWorker = this.queueService.registerWorker(QUEUE_SUMMARIZATION, async () => {
await this.summarization.runSummarization();
});
if (summarizationWorker) this.registeredWorkers.push(summarizationWorker);
this.registeredWorkers.push(summarizationWorker);
// M6-005: Tier management repeatable job
await this.queueService.addRepeatableJob(
@@ -57,7 +51,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
const tierWorker = this.queueService.registerWorker(QUEUE_TIER_MANAGEMENT, async () => {
await this.summarization.runTierManagement();
});
if (tierWorker) this.registeredWorkers.push(tierWorker);
this.registeredWorkers.push(tierWorker);
// Retire any repeatable global GC schedule created by older deployments.
// Session cleanup is now triggered only by an authorized session lifecycle operation.
@@ -1,44 +0,0 @@
import { Logger } from '@nestjs/common';
import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { McpClientService } from './mcp-client.service.js';
const MCP_LEAK_MARKER = 'MCP_LEAK_MARKER /srv/secret';
describe('McpClientService — failed connect error sanitization', () => {
const originalMcpServers = process.env['MCP_SERVERS'];
beforeEach(() => {
process.env['MCP_SERVERS'] = JSON.stringify([
{ name: 'leaky-server', url: 'http://localhost:9999/mcp' },
]);
});
afterEach(() => {
vi.restoreAllMocks();
if (originalMcpServers === undefined) {
delete process.env['MCP_SERVERS'];
} else {
process.env['MCP_SERVERS'] = originalMcpServers;
}
});
it('stores a generic serverEntry.error while logging the raw exception server-side', async () => {
vi.spyOn(Client.prototype, 'connect').mockRejectedValue(new Error(MCP_LEAK_MARKER));
const errorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
const service = new McpClientService();
await service.onModuleInit();
const statuses = service.getServerStatuses();
expect(statuses).toHaveLength(1);
expect(statuses[0]?.connected).toBe(false);
expect(statuses[0]?.error).toBe('Connection failed (see server logs).');
expect(statuses[0]?.error).not.toContain(MCP_LEAK_MARKER);
const loggedRawMarker = errorSpy.mock.calls.some((call) =>
call.some((arg) => typeof arg === 'string' && arg.includes(MCP_LEAK_MARKER)),
);
expect(loggedRawMarker).toBe(true);
});
});
@@ -189,7 +189,7 @@ export class McpClientService implements OnModuleInit, OnModuleDestroy {
);
} catch (err) {
const message = err instanceof Error ? err.message : String(err);
serverEntry.error = 'Connection failed (see server logs).';
serverEntry.error = message;
serverEntry.connected = false;
this.logger.error(`Failed to connect to MCP server "${config.name}": ${message}`);
}
@@ -1,23 +0,0 @@
import { describe, expect, it } from 'vitest';
import type { MosaicConfig } from '@mosaicstack/config';
import { SystemOverrideService } from './system-override.service.js';
const localConfig = { queue: { type: 'local' } } as MosaicConfig;
describe('SystemOverrideService local tier', () => {
it('keeps ephemeral overrides isolated by tenant and user scope', async () => {
const service = new SystemOverrideService(localConfig);
const firstScope = { tenantId: 'tenant-a', userId: 'user-a' };
const secondScope = { tenantId: 'tenant-b', userId: 'user-b' };
await service.set('shared-session', 'first override', firstScope);
await service.set('shared-session', 'second override', secondScope);
await expect(service.get('shared-session', firstScope)).resolves.toBe('first override');
await expect(service.get('shared-session', secondScope)).resolves.toBe('second override');
await service.clear('shared-session', firstScope);
await expect(service.get('shared-session', firstScope)).resolves.toBeNull();
await expect(service.get('shared-session', secondScope)).resolves.toBe('second override');
});
});
@@ -1,8 +1,6 @@
import { Inject, Injectable, Logger, Optional, type OnApplicationShutdown } from '@nestjs/common';
import { Injectable, Logger } from '@nestjs/common';
import { createQueue, type QueueHandle } from '@mosaicstack/queue';
import type { MosaicConfig } from '@mosaicstack/config';
import type { ActorTenantScope } from '../auth/session-scope.js';
import { MOSAIC_CONFIG } from '../config/config.module.js';
const scopedSessionId = (sessionId: string, scope: ActorTenantScope) =>
`${scope.tenantId}:${scope.userId}:${sessionId}`;
@@ -17,45 +15,16 @@ interface OverrideFragment {
addedAt: number;
}
interface LocalOverrideEntry {
condensed: string;
fragments: OverrideFragment[];
}
@Injectable()
export class SystemOverrideService implements OnApplicationShutdown {
export class SystemOverrideService {
private readonly logger = new Logger(SystemOverrideService.name);
private readonly handle: QueueHandle | null;
/** Local-tier fallback, keyed by the same tenant/user/session scope as Redis. */
private readonly localStore = new Map<string, LocalOverrideEntry>();
private readonly handle: QueueHandle;
constructor(
@Optional()
@Inject(MOSAIC_CONFIG)
private readonly mosaicConfig: MosaicConfig | null,
) {
this.handle = this.mosaicConfig?.queue?.type === 'local' ? null : createQueue();
}
async onApplicationShutdown(): Promise<void> {
await this.handle?.close().catch(() => {});
constructor() {
this.handle = createQueue();
}
async set(sessionId: string, override: string, scope: ActorTenantScope): Promise<void> {
if (!this.handle) {
const key = scopedSessionId(sessionId, scope);
const entry = this.localStore.get(key) ?? { condensed: '', fragments: [] };
entry.fragments.push({ text: override, addedAt: Date.now() });
entry.condensed = await this.condenseOverrides(
entry.fragments.map((fragment) => fragment.text),
);
this.localStore.set(key, entry);
this.logger.debug(
`Set system override for session ${sessionId} (local, ${entry.fragments.length} fragment(s))`,
);
return;
}
// Load existing fragments
const existing = await this.handle.redis.get(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope));
const fragments: OverrideFragment[] = existing
@@ -85,14 +54,10 @@ export class SystemOverrideService implements OnApplicationShutdown {
}
async get(sessionId: string, scope: ActorTenantScope): Promise<string | null> {
if (!this.handle) {
return this.localStore.get(scopedSessionId(sessionId, scope))?.condensed ?? null;
}
return this.handle.redis.get(SESSION_SYSTEM_KEY(sessionId, scope));
}
async renew(sessionId: string, scope: ActorTenantScope): Promise<void> {
if (!this.handle) return;
const pipeline = this.handle.redis.pipeline();
pipeline.expire(SESSION_SYSTEM_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
pipeline.expire(SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope), SYSTEM_OVERRIDE_TTL_SECONDS);
@@ -100,11 +65,6 @@ export class SystemOverrideService implements OnApplicationShutdown {
}
async clear(sessionId: string, scope: ActorTenantScope): Promise<void> {
if (!this.handle) {
this.localStore.delete(scopedSessionId(sessionId, scope));
this.logger.debug(`Cleared system override for session ${sessionId} (local)`);
return;
}
await this.handle.redis.del(
SESSION_SYSTEM_KEY(sessionId, scope),
SESSION_SYSTEM_FRAGMENTS_KEY(sessionId, scope),
@@ -1,36 +0,0 @@
import { describe, expect, it, vi } from 'vitest';
import type { MosaicConfig } from '@mosaicstack/config';
import { QueueService } from './queue.service.js';
const localConfig = {
queue: { type: 'local' },
} as MosaicConfig;
describe('QueueService local tier', () => {
it('disables BullMQ and treats queue operations as local no-ops', async () => {
const service = new QueueService(null, localConfig);
expect(service.isEnabled()).toBe(false);
expect(service.getQueue('mosaic-test')).toBeNull();
expect(service.registerWorker('mosaic-test', vi.fn())).toBeNull();
await expect(
service.addRepeatableJob('mosaic-test', 'local-noop', {}, '* * * * *'),
).resolves.toBeUndefined();
await expect(service.removeRepeatableJobs('mosaic-test', 'local-noop')).resolves.toBe(0);
await expect(service.getHealthStatus()).resolves.toEqual({ queues: {}, healthy: true });
await expect(service.listJobs()).resolves.toEqual([]);
await expect(service.retryJob('mosaic-test__1')).resolves.toEqual({
ok: false,
message: 'BullMQ is disabled on local tier.',
});
await expect(service.pauseQueue('mosaic-test')).resolves.toEqual({
ok: false,
message: 'BullMQ is disabled on local tier.',
});
await expect(service.resumeQueue('mosaic-test')).resolves.toEqual({
ok: false,
message: 'BullMQ is disabled on local tier.',
});
});
});
+6 -65
View File
@@ -8,9 +8,7 @@ import {
} from '@nestjs/common';
import { Queue, Worker, type Job, type ConnectionOptions } from 'bullmq';
import type { LogService } from '@mosaicstack/log';
import type { MosaicConfig } from '@mosaicstack/config';
import { LOG_SERVICE } from '../log/log.tokens.js';
import { MOSAIC_CONFIG } from '../config/config.module.js';
import type { JobDto, JobStatus } from './queue-admin.dto.js';
// ---------------------------------------------------------------------------
@@ -110,42 +108,21 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
private readonly connection: ConnectionOptions;
private readonly queues = new Map<string, Queue<MosaicJobData>>();
private readonly workers = new Map<string, Worker<MosaicJobData>>();
/** False on Local tier — BullMQ/Redis operations become no-ops. */
private readonly enabled: boolean;
constructor(
@Optional()
@Inject(LOG_SERVICE)
private readonly logService: LogService | null,
@Optional()
@Inject(MOSAIC_CONFIG)
private readonly mosaicConfig: MosaicConfig | null,
) {
this.enabled = this.mosaicConfig?.queue?.type !== 'local';
this.connection = this.enabled
? getConnection()
: ({ host: '127.0.0.1', port: 6380 } as ConnectionOptions);
}
/** Returns true when BullMQ/Redis is active (Standalone and Federated tiers). */
isEnabled(): boolean {
return this.enabled;
this.connection = getConnection();
}
onModuleInit(): void {
if (this.enabled) {
this.logger.log('QueueService initialised (BullMQ)');
} else {
this.logger.log(
'QueueService: BullMQ disabled for local tier — no Redis connections will be opened',
);
}
this.logger.log('QueueService initialised (BullMQ)');
}
async onModuleDestroy(): Promise<void> {
if (this.enabled) {
await this.closeAll();
}
await this.closeAll();
}
// -------------------------------------------------------------------------
@@ -154,10 +131,8 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
/**
* Get or create a BullMQ Queue for the given queue name.
* Returns null on Local tier where BullMQ is disabled.
*/
getQueue<T extends MosaicJobData = MosaicJobData>(name: string): Queue<T> | null {
if (!this.enabled) return null;
getQueue<T extends MosaicJobData = MosaicJobData>(name: string): Queue<T> {
let queue = this.queues.get(name) as Queue<T> | undefined;
if (!queue) {
queue = new Queue<T>(name, { connection: this.connection });
@@ -169,7 +144,6 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
/**
* Add a BullMQ repeatable job (cron-style).
* Uses `jobId` as a deterministic key so duplicate registrations are idempotent.
* No-op on Local tier.
*/
async addRepeatableJob<T extends MosaicJobData>(
queueName: string,
@@ -177,13 +151,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
data: T,
cronExpression: string,
): Promise<void> {
if (!this.enabled) {
this.logger.debug(
`Skipping repeatable job "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
);
return;
}
const queue = this.getQueue<T>(queueName)!;
const queue = this.getQueue<T>(queueName);
// eslint-disable-next-line @typescript-eslint/no-explicit-any
await (queue as Queue<any>).add(jobName, data, {
repeat: { pattern: cronExpression },
@@ -199,14 +167,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
* safe retirement of previously registered system-wide jobs.
*/
async removeRepeatableJobs(queueName: string, jobName: string): Promise<number> {
if (!this.enabled) {
this.logger.debug(
`Skipping repeatable-job removal for "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
);
return 0;
}
const queue = this.getQueue(queueName);
if (!queue) return 0;
const jobs = await queue.getRepeatableJobs();
const matchingJobs = jobs.filter((job) => job.name === jobName);
await Promise.all(matchingJobs.map((job) => queue.removeRepeatableByKey(job.key)));
@@ -221,18 +182,8 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
/**
* Register a Worker for the given queue name with error handling and
* exponential backoff.
* Returns null on Local tier where BullMQ is disabled.
*/
registerWorker<T extends MosaicJobData>(
queueName: string,
handler: JobHandler<T>,
): Worker<T> | null {
if (!this.enabled) {
this.logger.debug(
`Skipping worker registration for "${queueName}" (local tier — BullMQ disabled)`,
);
return null;
}
registerWorker<T extends MosaicJobData>(queueName: string, handler: JobHandler<T>): Worker<T> {
const worker = new Worker<T>(
queueName,
async (job) => {
@@ -289,12 +240,8 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
/**
* Return queue health statistics for all managed queues.
* Returns an empty healthy result on Local tier.
*/
async getHealthStatus(): Promise<QueueHealthStatus> {
if (!this.enabled) {
return { queues: {}, healthy: true };
}
const queues: QueueHealthStatus['queues'] = {};
let healthy = true;
@@ -325,10 +272,8 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
/**
* List jobs across all managed queues, optionally filtered by status.
* BullMQ jobs are fetched by state type from each queue.
* Returns empty array on Local tier.
*/
async listJobs(status?: JobStatus): Promise<JobDto[]> {
if (!this.enabled) return [];
const jobs: JobDto[] = [];
const states: JobStatus[] = status
? [status]
@@ -355,10 +300,8 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
* Retry a specific failed job by its BullMQ job ID (format: "queueName:id").
* The caller passes "<queueName>__<jobId>" as the composite ID because BullMQ
* job IDs are not globally unique — they are scoped to their queue.
* Returns an error on Local tier.
*/
async retryJob(compositeId: string): Promise<{ ok: boolean; message: string }> {
if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
const sep = compositeId.lastIndexOf('__');
if (sep === -1) {
return { ok: false, message: 'Invalid job id format. Expected "<queue>__<jobId>".' };
@@ -390,7 +333,6 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
* Pause a queue by name.
*/
async pauseQueue(name: string): Promise<{ ok: boolean; message: string }> {
if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
const queue = this.queues.get(name);
if (!queue) return { ok: false, message: `Queue "${name}" not found.` };
await queue.pause();
@@ -402,7 +344,6 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
* Resume a paused queue by name.
*/
async resumeQueue(name: string): Promise<{ ok: boolean; message: string }> {
if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
const queue = this.queues.get(name);
if (!queue) return { ok: false, message: `Queue "${name}" not found.` };
await queue.resume();
@@ -1,8 +1,5 @@
import { Logger } from '@nestjs/common';
import { describe, expect, it, vi } from 'vitest';
import type { SlashCommandPayload, SystemReloadPayload } from '@mosaicstack/types';
import { ReloadService } from './reload.service.js';
import { CommandExecutorService } from '../commands/command-executor.service.js';
function createMockCommandRegistry() {
return {
@@ -107,79 +104,3 @@ describe('ReloadService', () => {
expect(() => service.registerPlugin('my-plugin', {})).not.toThrow();
});
});
describe('ReloadService — /reload command sanitizes plugin errors', () => {
it('generic per-plugin errors reach the chat surface while raw markers stay server-side only', async () => {
const registry = {
getManifest: vi.fn().mockReturnValue({
version: 1,
commands: [
{ name: 'reload', aliases: [], scope: 'core', execution: 'socket', available: true },
],
skills: [],
}),
};
const reloadService = new ReloadService(registry as never);
const RELOAD_LOAD_LEAK_MARKER = 'RELOAD_LOAD_LEAK_MARKER /srv/load-secret';
const RELOAD_UNLOAD_LEAK_MARKER = 'RELOAD_UNLOAD_LEAK_MARKER /srv/unload-secret';
reloadService.registerPlugin('unload-fails', {
pluginName: 'unload-fails',
onLoad: vi.fn().mockResolvedValue(undefined),
onUnload: vi.fn().mockRejectedValue(new Error(RELOAD_UNLOAD_LEAK_MARKER)),
});
reloadService.registerPlugin('load-fails', {
pluginName: 'load-fails',
onLoad: vi.fn().mockRejectedValue(new Error(RELOAD_LOAD_LEAK_MARKER)),
onUnload: vi.fn().mockResolvedValue(undefined),
});
const errorSpy = vi.spyOn(Logger.prototype, 'error').mockImplementation(() => undefined);
const broadcastReload = vi.fn();
const mockChatGateway = { broadcastReload };
const mockAgentService = { getSession: vi.fn(), applyAgentConfig: vi.fn() };
const mockSystemOverride = { set: vi.fn(), get: vi.fn(), clear: vi.fn() };
const mockSessionGC = { sweepOrphans: vi.fn() };
const mockBrain = { agents: { findByName: vi.fn(), findById: vi.fn(), create: vi.fn() } };
const executor = new CommandExecutorService(
registry as never,
mockAgentService as never,
mockSystemOverride as never,
mockSessionGC as never,
null,
mockBrain as never,
reloadService,
mockChatGateway as never,
null,
);
const payload: SlashCommandPayload = { command: 'reload', conversationId: 'conv-1' };
const result = await executor.execute(payload, { userId: 'user-1', tenantId: 'user-1' });
expect(result.success).toBe(true);
expect(result.message).toContain('unload-fails: unload failed (internal error)');
expect(result.message).toContain('load-fails: load failed (internal error)');
expect(result.message).not.toContain(RELOAD_UNLOAD_LEAK_MARKER);
expect(result.message).not.toContain(RELOAD_LOAD_LEAK_MARKER);
expect(broadcastReload).toHaveBeenCalledOnce();
const broadcastPayload = broadcastReload.mock.calls[0]?.[0] as SystemReloadPayload;
expect(broadcastPayload.message).toContain('unload-fails: unload failed (internal error)');
expect(broadcastPayload.message).toContain('load-fails: load failed (internal error)');
expect(broadcastPayload.message).not.toContain(RELOAD_UNLOAD_LEAK_MARKER);
expect(broadcastPayload.message).not.toContain(RELOAD_LOAD_LEAK_MARKER);
const loggedUnloadMarker = errorSpy.mock.calls.some((call) =>
call.some((arg) => typeof arg === 'string' && arg.includes(RELOAD_UNLOAD_LEAK_MARKER)),
);
const loggedLoadMarker = errorSpy.mock.calls.some((call) =>
call.some((arg) => typeof arg === 'string' && arg.includes(RELOAD_LOAD_LEAK_MARKER)),
);
expect(loggedUnloadMarker).toBe(true);
expect(loggedLoadMarker).toBe(true);
errorSpy.mockRestore();
});
});
+2 -4
View File
@@ -58,8 +58,7 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
await plugin.onUnload();
reloaded.push(name);
} catch (err) {
this.logger.error(`Plugin "${name}" failed during onUnload: ${err}`);
errors.push(`${name}: unload failed (internal error)`);
errors.push(`${name}: unload failed — ${err}`);
}
}
}
@@ -70,8 +69,7 @@ export class ReloadService implements OnApplicationBootstrap, OnApplicationShutd
try {
await plugin.onLoad();
} catch (err) {
this.logger.error(`Plugin "${name}" failed during onLoad: ${err}`);
errors.push(`${name}: load failed (internal error)`);
errors.push(`${name}: load failed ${err}`);
}
}
}
@@ -1,104 +0,0 @@
import 'reflect-metadata';
import {
type CanActivate,
type ExecutionContext,
type INestApplication,
ValidationPipe,
} from '@nestjs/common';
import { FastifyAdapter, type NestFastifyApplication } from '@nestjs/platform-fastify';
import { Test } from '@nestjs/testing';
import request from 'supertest';
import { afterAll, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
import { AuthGuard } from '../auth/auth.guard.js';
import { ProjectBootstrapService } from './project-bootstrap.service.js';
import { WorkspaceController } from './workspace.controller.js';
const bootstrapMock = vi.fn(() =>
Promise.resolve({
projectId: 'project-1',
workspacePath: '/opt/mosaic/.workspaces/users/user-1/project-1',
}),
);
const authGuard: CanActivate = {
canActivate(context: ExecutionContext): boolean {
const requestContext = context.switchToHttp().getRequest<{ user?: { id: string } }>();
requestContext.user = { id: 'user-1' };
return true;
},
};
describe('POST /api/workspaces repoUrl validation', () => {
let app: INestApplication;
beforeAll(async () => {
const moduleRef = await Test.createTestingModule({
controllers: [WorkspaceController],
providers: [
{
provide: ProjectBootstrapService,
useValue: { bootstrap: bootstrapMock },
},
],
})
.overrideGuard(AuthGuard)
.useValue(authGuard)
.compile();
app = moduleRef.createNestApplication<NestFastifyApplication>(new FastifyAdapter());
app.useGlobalPipes(
new ValidationPipe({
whitelist: true,
forbidNonWhitelisted: true,
transform: true,
}),
);
await app.init();
await app.getHttpAdapter().getInstance().ready();
});
beforeEach(() => {
bootstrapMock.mockClear();
});
afterAll(async () => {
await app.close();
});
it.each([
['a leading-dash value', '--upload-pack=sh -c id'],
['an ext remote helper', 'ext::sh -c id'],
['a file URL', 'file:///tmp/repository'],
['an unparseable value', 'not a url'],
['an SSH shorthand', '[email protected]:acme/repository.git'],
['a scheme without //', 'https:example.com/acme/repository.git'],
['a hostless git URL', 'git:///tmp/repository'],
])('returns 400 for %s', async (_description, repoUrl) => {
const response = await request(app.getHttpServer())
.post('/api/workspaces')
.send({ name: 'Example', repoUrl })
.set('Content-Type', 'application/json');
expect(response.status).toBe(400);
expect(bootstrapMock).not.toHaveBeenCalled();
});
it.each([
['a plain HTTPS repository URL', 'https://example.com/acme/repository.git'],
['a git protocol repository URL', 'git://example.com/acme/repository.git'],
])('accepts %s', async (_description, repoUrl) => {
const response = await request(app.getHttpServer())
.post('/api/workspaces')
.send({ name: 'Example', repoUrl })
.set('Content-Type', 'application/json');
expect(response.status).toBe(201);
expect(bootstrapMock).toHaveBeenCalledWith({
name: 'Example',
description: undefined,
userId: 'user-1',
teamId: undefined,
repoUrl,
});
});
});
@@ -1,11 +1,7 @@
import { Body, Controller, Post, UseGuards } from '@nestjs/common';
import { AuthGuard } from '../auth/auth.guard.js';
import { CurrentUser } from '../auth/current-user.decorator.js';
import {
ProjectBootstrapService,
type BootstrapProjectResult,
} from './project-bootstrap.service.js';
import { CreateWorkspaceDto } from './workspace.dto.js';
import { ProjectBootstrapService } from './project-bootstrap.service.js';
@Controller('api/workspaces')
@UseGuards(AuthGuard)
@@ -15,14 +11,20 @@ export class WorkspaceController {
@Post()
async create(
@CurrentUser() user: { id: string },
@Body() dto: CreateWorkspaceDto,
): Promise<BootstrapProjectResult> {
@Body()
body: {
name: string;
description?: string;
teamId?: string;
repoUrl?: string;
},
) {
return this.bootstrap.bootstrap({
name: dto.name,
description: dto.description,
name: body.name,
description: body.description,
userId: user.id,
teamId: dto.teamId,
repoUrl: dto.repoUrl,
teamId: body.teamId,
repoUrl: body.repoUrl,
});
}
}
@@ -1,33 +0,0 @@
import { IsOptional, IsString, IsUrl, Matches, MaxLength } from 'class-validator';
export class CreateWorkspaceDto {
@IsString()
@MaxLength(255)
name!: string;
@IsOptional()
@IsString()
@MaxLength(10_000)
description?: string;
@IsOptional()
@IsString()
teamId?: string;
@IsOptional()
@IsString()
@Matches(/^(?:https|git):\/\//i, {
message: 'repoUrl must be a valid https:// or git:// URL',
})
@IsUrl(
{
protocols: ['https', 'git'],
require_host: true,
require_protocol: true,
require_tld: false,
require_valid_protocol: true,
},
{ message: 'repoUrl must be a valid https:// or git:// URL' },
)
repoUrl?: string;
}
@@ -1,33 +1,11 @@
import { BadRequestException } from '@nestjs/common';
import fs from 'node:fs/promises';
import os from 'node:os';
import path from 'node:path';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { describe, it, expect, beforeEach } from 'vitest';
import { WorkspaceService } from './workspace.service.js';
type ExecFileMock = (
command: string,
args: readonly string[],
options: { cwd: string },
callback: (error: Error | null, stdout: string, stderr: string) => void,
) => void;
const { execFileMock } = vi.hoisted(() => ({
execFileMock: vi.fn<ExecFileMock>(),
}));
vi.mock('node:child_process', () => ({
execFile: execFileMock,
}));
import path from 'node:path';
describe('WorkspaceService', () => {
let service: WorkspaceService;
beforeEach(() => {
execFileMock.mockReset();
execFileMock.mockImplementation((_command, _args, _options, callback) => {
callback(null, '', '');
});
service = new WorkspaceService();
});
@@ -98,69 +76,4 @@ describe('WorkspaceService', () => {
}
});
});
describe('create', () => {
const project = {
id: 'project-1',
ownerType: 'user',
userId: 'user-1',
teamId: null,
} as const;
let originalRoot: string | undefined;
let temporaryRoot: string;
beforeEach(async () => {
originalRoot = process.env['MOSAIC_ROOT'];
temporaryRoot = await fs.mkdtemp(path.join(os.tmpdir(), 'mosaic-workspace-'));
process.env['MOSAIC_ROOT'] = temporaryRoot;
service = new WorkspaceService();
});
afterEach(async () => {
if (originalRoot === undefined) {
delete process.env['MOSAIC_ROOT'];
} else {
process.env['MOSAIC_ROOT'] = originalRoot;
}
await fs.rm(temporaryRoot, { recursive: true, force: true });
});
it.each([
['a leading-dash URL', '--upload-pack=sh -c id'],
['an ext remote helper', 'ext::sh -c id'],
['a file URL', 'file:///tmp/repository'],
['an unparseable value', 'not a url'],
['an SSH shorthand', '[email protected]:acme/repository.git'],
['a scheme without //', 'https:example.com/acme/repository.git'],
['a hostless git URL', 'git:///tmp/repository'],
])('rejects %s before invoking git', async (_description, repoUrl) => {
await expect(service.create(project, repoUrl)).rejects.toBeInstanceOf(BadRequestException);
expect(execFileMock).not.toHaveBeenCalled();
});
it.each([
['an HTTPS URL', 'https://example.com/acme/repository.git'],
['a git protocol URL', 'git://example.com/acme/repository.git'],
])('accepts %s and invokes hardened git clone arguments', async (_description, repoUrl) => {
const workspacePath = await service.create(project, repoUrl);
expect(execFileMock).toHaveBeenCalledOnce();
expect(execFileMock).toHaveBeenCalledWith(
'git',
[
'-c',
'protocol.ext.allow=never',
'-c',
'protocol.file.allow=never',
'clone',
'--',
repoUrl,
'.',
],
{ cwd: workspacePath },
expect.any(Function),
);
});
});
});
@@ -1,30 +1,10 @@
import { BadRequestException, Injectable, Logger } from '@nestjs/common';
import { Injectable, Logger } from '@nestjs/common';
import fs from 'node:fs/promises';
import path from 'node:path';
import { execFile } from 'node:child_process';
import { promisify } from 'node:util';
const execFileAsync = promisify(execFile);
const allowedRepositoryProtocols = new Set(['https:', 'git:']);
const repositoryUrlPrefixPattern = /^(?:https|git):\/\//i;
const repositoryUrlError = 'repoUrl must be a valid https:// or git:// URL';
function assertAllowedRepositoryUrl(repoUrl: string): void {
if (repoUrl.startsWith('-') || !repositoryUrlPrefixPattern.test(repoUrl)) {
throw new BadRequestException(repositoryUrlError);
}
let parsedUrl: URL;
try {
parsedUrl = new URL(repoUrl);
} catch {
throw new BadRequestException(repositoryUrlError);
}
if (!allowedRepositoryProtocols.has(parsedUrl.protocol) || parsedUrl.hostname.length === 0) {
throw new BadRequestException(repositoryUrlError);
}
}
export interface WorkspaceProject {
id: string;
@@ -59,32 +39,14 @@ export class WorkspaceService {
* If repoUrl is provided, clone instead of init.
*/
async create(project: WorkspaceProject, repoUrl?: string): Promise<string> {
if (repoUrl !== undefined) {
assertAllowedRepositoryUrl(repoUrl);
}
const workspacePath = this.resolvePath(project);
// Create directory
await fs.mkdir(workspacePath, { recursive: true });
if (repoUrl !== undefined) {
// Clone existing repo. Defense in depth keeps dangerous local helpers
// disabled and terminates option parsing before positional arguments.
await execFileAsync(
'git',
[
'-c',
'protocol.ext.allow=never',
'-c',
'protocol.file.allow=never',
'clone',
'--',
repoUrl,
'.',
],
{ cwd: workspacePath },
);
if (repoUrl) {
// Clone existing repo
await execFileAsync('git', ['clone', repoUrl, '.'], { cwd: workspacePath });
this.logger.log(`Cloned ${repoUrl} into workspace ${workspacePath}`);
} else {
// Init new git repo
-30
View File
@@ -1,30 +0,0 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Mosaic</title>
<meta name="description" content="Mosaic Stack Dashboard" />
<link rel="preconnect" href="https://fonts.googleapis.com" />
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
<link
rel="stylesheet"
href="https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;500;600;700&family=Fira+Code:wght@400;500&display=swap"
/>
<script>
// set data-theme before first paint so the stored theme never flashes
(function () {
try {
var theme = window.localStorage.getItem('mosaic-theme') || 'dark';
document.documentElement.setAttribute('data-theme', theme === 'light' ? 'light' : 'dark');
} catch (error) {
document.documentElement.setAttribute('data-theme', 'dark');
}
})();
</script>
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/main.tsx"></script>
</body>
</html>
+2 -8
View File
@@ -3,10 +3,8 @@
"version": "0.0.2",
"private": true,
"scripts": {
"build": "node ../../scripts/build-web.mjs",
"build:vite": "vite build",
"build": "next build",
"dev": "next dev",
"dev:vite": "vite",
"lint": "eslint src",
"typecheck": "tsc --noEmit",
"test": "vitest run --passWithNoTests",
@@ -15,14 +13,12 @@
},
"dependencies": {
"@mosaicstack/design-tokens": "workspace:^",
"@mosaicstack/types": "workspace:^",
"better-auth": "^1.5.5",
"clsx": "^2.1.0",
"next": "^16.0.0",
"react": "^19.0.0",
"react-dom": "^19.0.0",
"react-markdown": "^10.1.0",
"react-router-dom": "^7.18.2",
"socket.io-client": "^4.8.0",
"tailwind-merge": "^3.5.0"
},
@@ -32,11 +28,9 @@
"@types/node": "^22.0.0",
"@types/react": "^19.0.0",
"@types/react-dom": "^19.0.0",
"@vitejs/plugin-react": "^6.0.5",
"jsdom": "^29.0.0",
"tailwindcss": "^4.0.0",
"typescript": "^5.8.0",
"vite": "^8.2.1",
"vitest": "^3.2.7"
"vitest": "^2.0.0"
}
}
@@ -3,56 +3,41 @@
import Link from 'next/link';
import { useEffect, useState } from 'react';
import { useParams, useSearchParams } from 'next/navigation';
import { api } from '@/lib/api';
import { resolveAuthCallbackURL } from '@/lib/auth-redirect';
import { signIn } from '@/lib/auth-client';
import type { SsoProviderDiscovery } from '@/lib/sso';
import { getSsoProvider } from '@/lib/sso-providers';
export default function AuthProviderRedirectPage(): React.ReactElement {
const params = useParams<{ provider: string }>();
const searchParams = useSearchParams();
const providerId = typeof params.provider === 'string' ? params.provider : '';
const requestedCallbackURL = searchParams.get('callbackURL');
const [providerName, setProviderName] = useState<string | null>(null);
const provider = getSsoProvider(providerId);
const callbackURL = searchParams.get('callbackURL') ?? '/chat';
const [error, setError] = useState<string | null>(null);
useEffect(() => {
const currentProvider = provider;
if (!currentProvider) {
setError('Unknown SSO provider.');
return;
}
if (!currentProvider.enabled) {
setError(`${currentProvider.buttonLabel} is not enabled in this deployment.`);
return;
}
const activeProvider = currentProvider;
let cancelled = false;
async function redirectToProvider(): Promise<void> {
try {
const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
if (cancelled) return;
const result = await signIn.oauth2({
providerId: activeProvider.id,
callbackURL,
});
const provider = providers.find((candidate) => candidate.id === providerId);
if (!provider) {
setError('Unknown SSO provider.');
return;
}
setProviderName(provider.name);
if (!provider.configured) {
setError(`${provider.name} is not enabled in this deployment.`);
return;
}
if (provider.loginMode !== 'oidc') {
setError(`${provider.name} is not available for OIDC sign in.`);
return;
}
const result = await signIn.oauth2({
providerId: provider.id,
callbackURL,
});
if (!cancelled && result?.error) {
setError(result.error.message ?? `${provider.name} sign in failed.`);
}
} catch (caught: unknown) {
if (!cancelled) {
setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
}
if (!cancelled && result?.error) {
setError(result.error.message ?? `${activeProvider.buttonLabel} sign in failed.`);
}
}
@@ -61,22 +46,19 @@ export default function AuthProviderRedirectPage(): React.ReactElement {
return () => {
cancelled = true;
};
}, [providerId, requestedCallbackURL]);
}, [callbackURL, provider]);
return (
<div className="mx-auto flex min-h-[50vh] max-w-md flex-col justify-center">
<h1 className="text-2xl font-semibold text-text-primary">Single sign-on</h1>
<p className="mt-2 text-sm text-text-secondary">
{providerName
? `Redirecting you to ${providerName}...`
{provider
? `Redirecting you to ${provider.buttonLabel.replace('Continue with ', '')}...`
: 'Preparing your sign-in request...'}
</p>
{error ? (
<div
role="alert"
className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
>
<div className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error">
<p>{error}</p>
<Link
href="/login"
-57
View File
@@ -1,57 +0,0 @@
import { afterEach, describe, expect, it, vi } from 'vitest';
import { api } from './api';
describe('api', () => {
afterEach(() => {
vi.unstubAllGlobals();
});
it('fetches the supplied relative path with credentials and a JSON body', async () => {
const fetchMock = vi.fn<typeof fetch>();
fetchMock.mockResolvedValue(
new Response(JSON.stringify({ ok: true }), {
status: 200,
headers: { 'Content-Type': 'application/json' },
}),
);
vi.stubGlobal('fetch', fetchMock);
await expect(
api<{ ok: boolean }>('/api/projects', {
method: 'POST',
body: { name: 'Mosaic' },
}),
).resolves.toEqual({ ok: true });
expect(fetchMock).toHaveBeenCalledOnce();
expect(fetchMock).toHaveBeenCalledWith(
'/api/projects',
expect.objectContaining({
method: 'POST',
credentials: 'include',
body: JSON.stringify({ name: 'Mosaic' }),
headers: expect.objectContaining({
Accept: 'application/json',
'Content-Type': 'application/json',
}),
}),
);
});
it('throws the gateway JSON error with its statusCode', async () => {
const fetchMock = vi.fn<typeof fetch>();
fetchMock.mockResolvedValue(
new Response(JSON.stringify({ statusCode: 403, message: 'Forbidden' }), {
status: 403,
headers: { 'Content-Type': 'application/json' },
}),
);
vi.stubGlobal('fetch', fetchMock);
await expect(api('/api/admin/users')).rejects.toMatchObject({
name: 'Error',
message: 'Forbidden',
statusCode: 403,
});
});
});
+3 -1
View File
@@ -1,3 +1,5 @@
const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
export interface ApiRequestInit extends Omit<RequestInit, 'body'> {
body?: unknown;
}
@@ -23,7 +25,7 @@ export async function api<T>(path: string, init?: ApiRequestInit): Promise<T> {
headers['Content-Type'] = 'application/json';
}
const res = await fetch(path, {
const res = await fetch(`${GATEWAY_URL}${path}`, {
credentials: 'include',
...rest,
headers,
-29
View File
@@ -1,29 +0,0 @@
import { afterEach, describe, expect, it, vi } from 'vitest';
describe('auth client origin contract', () => {
afterEach(() => {
vi.unstubAllGlobals();
vi.resetModules();
});
it('uses the same-origin BetterAuth mount at /api/auth', async () => {
const fetchMock = vi.fn<typeof fetch>();
fetchMock.mockResolvedValue(
new Response(JSON.stringify({ session: null, user: null }), {
status: 200,
headers: { 'Content-Type': 'application/json' },
}),
);
vi.stubGlobal('fetch', fetchMock);
const { authClient } = await import('./auth-client');
await authClient.getSession();
expect(fetchMock).toHaveBeenCalledOnce();
const firstCall = fetchMock.mock.calls.at(0);
expect(firstCall).toBeDefined();
const requestURL = new URL(String(firstCall?.[0]), window.location.origin);
expect(requestURL.origin).toBe(window.location.origin);
expect(requestURL.pathname).toBe('/api/auth/get-session');
});
});
+1 -2
View File
@@ -1,9 +1,8 @@
import { createAuthClient } from 'better-auth/react';
import { adminClient, genericOAuthClient } from 'better-auth/client/plugins';
// The gateway and BetterAuth client both use /api/auth. Omitting baseURL keeps
// every browser request on the current origin in development and production.
export const authClient = createAuthClient({
baseURL: process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242',
plugins: [adminClient(), genericOAuthClient()],
});
-30
View File
@@ -1,30 +0,0 @@
import { describe, expect, it } from 'vitest';
import { resolveAuthCallbackURL } from './auth-redirect';
const CURRENT_ORIGIN = 'https://mosaic.example';
describe('resolveAuthCallbackURL', () => {
it('preserves a canonical same-origin path with search and hash', () => {
expect(resolveAuthCallbackURL('/projects?view=active#current', CURRENT_ORIGIN)).toBe(
'/projects?view=active#current',
);
});
it.each([
null,
'chat',
'//evil.example',
'/..//evil.com',
'/..//evil.com/x',
'/./..//evil.com',
'/../..//evil.com',
'/foo/..//evil.com',
'/\\evil.example',
'/\n//evil.example',
'/\r//evil.example',
'/\t//evil.example',
'https://evil.example/phish',
])('falls back to chat for an unsafe callback target %#', (candidate) => {
expect(resolveAuthCallbackURL(candidate, CURRENT_ORIGIN)).toBe('/chat');
});
});
-23
View File
@@ -1,23 +0,0 @@
const DEFAULT_AUTH_CALLBACK_URL = '/chat';
/**
* Return a canonical same-origin path for post-auth navigation.
*
* Parsing before comparing origins rejects protocol-relative URLs, backslash
* variants, and control characters that the WHATWG parser normalizes away.
*/
export function resolveAuthCallbackURL(candidate: string | null, currentOrigin: string): string {
if (!candidate?.startsWith('/')) return DEFAULT_AUTH_CALLBACK_URL;
try {
const expectedOrigin = new URL(currentOrigin).origin;
const resolved = new URL(candidate, expectedOrigin);
if (resolved.origin !== expectedOrigin || resolved.pathname.startsWith('//')) {
return DEFAULT_AUTH_CALLBACK_URL;
}
return `${resolved.pathname}${resolved.search}${resolved.hash}`;
} catch {
return DEFAULT_AUTH_CALLBACK_URL;
}
}
-61
View File
@@ -1,61 +0,0 @@
// Centralizes the type-only import of the shared `/chat` Socket.IO contract from
// the public `@mosaicstack/types` package. `import type` is erased at compile
// time, so this introduces no runtime dependency — it only reuses the exact
// payload shapes instead of redeclaring them.
import type { Socket } from 'socket.io-client';
import type {
AbortPayload,
AgentEndPayload,
AgentStartPayload,
AgentTextPayload,
AgentThinkingPayload,
ChatMessagePayload,
ClientToServerEvents,
CommandDef,
CommandManifest,
CommandManifestPayload,
ErrorPayload,
MessageAckPayload,
RoutingDecisionInfo,
ServerToClientEvents,
SessionInfoPayload,
SessionUsagePayload,
SetThinkingPayload,
SkillCommandDef,
SlashCommandApprovalResultPayload,
SlashCommandPayload,
SlashCommandResultPayload,
SystemReloadPayload,
ToolEndPayload,
ToolStartPayload,
} from '@mosaicstack/types';
export type {
AbortPayload,
AgentEndPayload,
AgentStartPayload,
AgentTextPayload,
AgentThinkingPayload,
ChatMessagePayload,
ClientToServerEvents,
CommandDef,
CommandManifest,
CommandManifestPayload,
ErrorPayload,
MessageAckPayload,
RoutingDecisionInfo,
ServerToClientEvents,
SessionInfoPayload,
SessionUsagePayload,
SetThinkingPayload,
SkillCommandDef,
SlashCommandApprovalResultPayload,
SlashCommandPayload,
SlashCommandResultPayload,
SystemReloadPayload,
ToolEndPayload,
ToolStartPayload,
};
/** The `/chat` namespace socket, narrowed to the exact typed event contract. */
export type ChatSocket = Socket<ServerToClientEvents, ClientToServerEvents>;
-98
View File
@@ -1,98 +0,0 @@
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
const { ioMock } = vi.hoisted(() => ({
ioMock: vi.fn(),
}));
vi.mock('socket.io-client', () => ({
io: ioMock,
}));
import { destroySocket, getSocket } from './socket';
interface MockChatSocket {
on: ReturnType<typeof vi.fn>;
offAny: ReturnType<typeof vi.fn>;
disconnect: ReturnType<typeof vi.fn>;
/** Test-only helper: fires every handler registered for `event` via
* `.on`, mirroring how a real socket.io-client instance invokes its own
* listeners (e.g. calling the registered `disconnect` handler(s) on a
* real transient disconnect). */
trigger(event: string): void;
}
function createMockSocket(): MockChatSocket {
const handlers = new Map<string, Set<() => void>>();
const mockSocket: MockChatSocket = {
on: vi.fn((event: string, handler: () => void) => {
if (!handlers.has(event)) handlers.set(event, new Set());
handlers.get(event)?.add(handler);
return mockSocket;
}),
offAny: vi.fn(() => mockSocket),
disconnect: vi.fn(() => mockSocket),
trigger(event: string): void {
for (const handler of handlers.get(event) ?? []) handler();
},
};
return mockSocket;
}
let currentMock!: MockChatSocket;
describe('chat socket', () => {
beforeEach(() => {
ioMock.mockReset();
// A fresh object per io() call so identity assertions (same singleton vs.
// a genuinely new instance) are meaningful.
ioMock.mockImplementation(() => {
currentMock = createMockSocket();
return currentMock;
});
});
afterEach(() => {
destroySocket();
});
it('creates one same-origin /chat namespace socket', () => {
const first = getSocket();
const second = getSocket();
expect(first).toBe(second);
expect(ioMock).toHaveBeenCalledOnce();
expect(ioMock).toHaveBeenCalledWith('/chat', {
withCredentials: true,
autoConnect: false,
transports: ['websocket', 'polling'],
});
});
it('keeps the same singleton instance across a transient disconnect', () => {
const first = getSocket();
// socket.ts must not react to a real socket's `disconnect` event by
// nulling the singleton — it registers no such handler at all now.
// Actually fire every handler registered via `.on('disconnect', ...)`
// (mirroring a real socket.io-client reconnect) instead of merely
// calling getSocket() again: this is what makes the test fail if
// production reintroduces `socket.on('disconnect', () => { socket =
// null; })`, since that handler would run here and null the singleton
// before the next getSocket() call.
currentMock.trigger('disconnect');
const second = getSocket();
expect(second).toBe(first);
expect(ioMock).toHaveBeenCalledOnce();
});
it('only creates a new singleton after an explicit destroySocket()', () => {
const first = getSocket();
destroySocket();
const second = getSocket();
expect(second).not.toBe(first);
expect(ioMock).toHaveBeenCalledTimes(2);
});
});
+13 -17
View File
@@ -1,27 +1,23 @@
import { io } from 'socket.io-client';
import type { ChatSocket } from './chat-contract';
import { io, type Socket } from 'socket.io-client';
let socket: ChatSocket | null = null;
const GATEWAY_URL = process.env['NEXT_PUBLIC_GATEWAY_URL'] ?? 'http://localhost:14242';
export function getSocket(): ChatSocket {
let socket: Socket | null = null;
export function getSocket(): Socket {
if (!socket) {
// socket.io-client 4.8.3's `io()` factory declaration always returns the
// default unparameterized Socket (it accepts no <ListenEvents, EmitEvents>
// generics), so this one cast is the unavoidable boundary between that and the
// typed `/chat` contract. Every other call site uses the resulting ChatSocket
// with no further assertions.
socket = io('/chat', {
socket = io(`${GATEWAY_URL}/chat`, {
withCredentials: true,
autoConnect: false,
transports: ['websocket', 'polling'],
}) as unknown as ChatSocket;
});
// A transient `disconnect` (network blip, server restart) must NOT null
// the singleton: socket.io-client auto-reconnects this same instance,
// and its listeners stay registered across that reconnect. Nulling here
// previously orphaned those listeners on the next getSocket() call by
// handing back a brand-new, unconnected instance. Only destroySocket()
// (an explicit, intentional teardown) may reset the singleton.
// Reset singleton reference when socket is fully closed so the next
// getSocket() call creates a fresh instance instead of returning a
// closed/dead socket.
socket.on('disconnect', () => {
socket = null;
});
}
return socket;
}
+48
View File
@@ -0,0 +1,48 @@
import { afterEach, describe, expect, it, vi } from 'vitest';
import { getEnabledSsoProviders, getSsoProvider } from './sso-providers';
describe('sso-providers', () => {
afterEach(() => {
vi.unstubAllEnvs();
});
it('returns the enabled providers in login button order', () => {
vi.stubEnv('NEXT_PUBLIC_WORKOS_ENABLED', 'true');
vi.stubEnv('NEXT_PUBLIC_KEYCLOAK_ENABLED', 'true');
expect(getEnabledSsoProviders()).toEqual([
{
id: 'workos',
buttonLabel: 'Continue with WorkOS',
description: 'Enterprise SSO via WorkOS',
enabled: true,
href: '/auth/provider/workos',
},
{
id: 'keycloak',
buttonLabel: 'Continue with Keycloak',
description: 'Enterprise SSO via Keycloak',
enabled: true,
href: '/auth/provider/keycloak',
},
]);
});
it('marks disabled providers without exposing them in the enabled list', () => {
vi.stubEnv('NEXT_PUBLIC_WORKOS_ENABLED', 'true');
vi.stubEnv('NEXT_PUBLIC_KEYCLOAK_ENABLED', 'false');
expect(getEnabledSsoProviders().map((provider) => provider.id)).toEqual(['workos']);
expect(getSsoProvider('keycloak')).toEqual({
id: 'keycloak',
buttonLabel: 'Continue with Keycloak',
description: 'Enterprise SSO via Keycloak',
enabled: false,
href: '/auth/provider/keycloak',
});
});
it('returns null for unknown providers', () => {
expect(getSsoProvider('authentik')).toBeNull();
});
});
+53
View File
@@ -0,0 +1,53 @@
export type SsoProviderId = 'workos' | 'keycloak';
export interface SsoProvider {
id: SsoProviderId;
buttonLabel: string;
description: string;
enabled: boolean;
href: string;
}
const PROVIDER_METADATA: Record<SsoProviderId, Omit<SsoProvider, 'enabled' | 'href'>> = {
workos: {
id: 'workos',
buttonLabel: 'Continue with WorkOS',
description: 'Enterprise SSO via WorkOS',
},
keycloak: {
id: 'keycloak',
buttonLabel: 'Continue with Keycloak',
description: 'Enterprise SSO via Keycloak',
},
};
export function getEnabledSsoProviders(): SsoProvider[] {
return (Object.keys(PROVIDER_METADATA) as SsoProviderId[])
.map((providerId) => getSsoProvider(providerId))
.filter((provider): provider is SsoProvider => provider?.enabled === true);
}
export function getSsoProvider(providerId: string): SsoProvider | null {
if (!isSsoProviderId(providerId)) {
return null;
}
return {
...PROVIDER_METADATA[providerId],
enabled: isSsoProviderEnabled(providerId),
href: `/auth/provider/${providerId}`,
};
}
function isSsoProviderId(value: string): value is SsoProviderId {
return value === 'workos' || value === 'keycloak';
}
function isSsoProviderEnabled(providerId: SsoProviderId): boolean {
switch (providerId) {
case 'workos':
return process.env['NEXT_PUBLIC_WORKOS_ENABLED'] === 'true';
case 'keycloak':
return process.env['NEXT_PUBLIC_KEYCLOAK_ENABLED'] === 'true';
}
}
-19
View File
@@ -1,19 +0,0 @@
import { StrictMode } from 'react';
import { createRoot } from 'react-dom/client';
import { RouterProvider } from 'react-router-dom';
import { ThemeProvider } from '@/providers/theme-provider';
import { createAppRouter } from '@/routes';
import '@/app/globals.css';
const container = document.getElementById('root');
if (!container) {
throw new Error('missing #root element');
}
createRoot(container).render(
<StrictMode>
<ThemeProvider>
<RouterProvider router={createAppRouter()} />
</ThemeProvider>
</StrictMode>,
);
-51
View File
@@ -1,51 +0,0 @@
import type { ReactElement } from 'react';
import { createBrowserRouter, Navigate, Outlet, type RouteObject } from 'react-router-dom';
import { LoginPage } from '@/spa/pages/login';
import { RegisterPage } from '@/spa/pages/register';
import { SsoCallbackPage } from '@/spa/pages/sso-callback';
import { ChatPage } from '@/spa/pages/chat';
import { ChatRouteErrorBoundary } from '@/spa/pages/chat-error-boundary';
import { AuthGuard, GuestGuard } from '@/spa/guards';
import { Placeholder } from '@/spa/placeholder';
function GuestLayout(): ReactElement {
return (
<div className="flex min-h-screen items-center justify-center bg-surface-bg px-4 py-8">
<div className="w-full max-w-md rounded-xl border border-surface-border bg-surface-card p-8 shadow-lg">
<Outlet />
</div>
</div>
);
}
export const routes: RouteObject[] = [
{
element: <GuestGuard />,
children: [
{
element: <GuestLayout />,
children: [
{ path: '/login', element: <LoginPage /> },
{ path: '/register', element: <RegisterPage /> },
{ path: '/auth/provider/:provider', element: <SsoCallbackPage /> },
],
},
],
},
{
element: <AuthGuard />,
children: [
{ path: '/', element: <Navigate to="/chat" replace /> },
{ path: '/chat', element: <ChatPage />, errorElement: <ChatRouteErrorBoundary /> },
{ path: '/projects', element: <Placeholder title="Projects" /> },
{ path: '/projects/:id', element: <Placeholder title="Project" /> },
{ path: '/tasks', element: <Placeholder title="Tasks" /> },
{ path: '/settings', element: <Placeholder title="Settings" /> },
{ path: '/admin', element: <Placeholder title="Admin" /> },
],
},
];
export function createAppRouter(): ReturnType<typeof createBrowserRouter> {
return createBrowserRouter(routes);
}
@@ -1,280 +0,0 @@
import { act } from 'react';
import { createRoot, type Root } from 'react-dom/client';
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
import { CommandsPanel } from './commands-panel';
beforeAll(() => {
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
configurable: true,
value: true,
});
});
afterAll(() => {
Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
});
let root: Root | null;
let container: HTMLElement | null;
async function render(node: Parameters<Root['render']>[0]): Promise<void> {
container = document.createElement('div');
document.body.append(container);
root = createRoot(container);
await act(async () => {
root?.render(node);
});
}
afterEach(async () => {
await act(async () => {
root?.unmount();
});
document.body.replaceChildren();
root = null;
container = null;
});
describe('CommandsPanel', () => {
it('shows the frozen local pendingApproval args in the confirmation area, regardless of misleading server message text', async () => {
await render(
<CommandsPanel
manifest={null}
results={[]}
approval={{
conversationId: 'c1',
command: 'deploy', // matches pendingApproval — this is a legitimately approved request
success: true,
approvalId: 'ap1',
expiresAt: '2026-01-01T00:00:00.000Z',
// Free-text server message claims a different, less alarming target
// than what will actually be sent — the UI must not rely on this.
message: 'This will only affect the staging environment.',
}}
pendingApproval={{ command: 'deploy', args: 'prod' }}
hasConversation
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
// The exact frozen combined action is visible...
expect(container?.textContent).toContain('/deploy');
expect(container?.textContent).toContain('prod');
// ...and the misleading server free-text is never shown next to it.
expect(container?.textContent).not.toContain('staging environment');
});
it('does not throw when a manifest commands entry is null', async () => {
const manifest = {
commands: [
null,
{
name: 'model',
aliases: [],
description: 'Change the active model',
scope: 'core',
execution: 'socket',
available: true,
},
],
skills: [null],
version: 1,
} as unknown as Parameters<typeof CommandsPanel>[0]['manifest'];
await expect(
render(
<CommandsPanel
manifest={manifest}
results={[]}
approval={null}
pendingApproval={null}
hasConversation={false}
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
),
).resolves.not.toThrow();
expect(container?.textContent).toContain('model');
});
it('shows an explicit no-args fallback when the frozen pendingApproval has no args', async () => {
await render(
<CommandsPanel
manifest={null}
results={[]}
approval={{
conversationId: 'c1',
command: 'deploy',
success: true,
approvalId: 'ap1',
expiresAt: '2026-01-01T00:00:00.000Z',
}}
pendingApproval={{ command: 'deploy' }}
hasConversation
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
expect(container?.textContent?.toLowerCase()).toContain('no args');
});
it('renders skills from a skills-only manifest', async () => {
await render(
<CommandsPanel
manifest={{
commands: [],
skills: [{ name: 'brave-search', description: 'Search the web', available: true }],
version: 1,
}}
results={[]}
approval={null}
pendingApproval={null}
hasConversation={false}
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
expect(container?.textContent).toContain('brave-search');
expect(container?.textContent).toContain('Search the web');
});
it('does not show the Run affordance when approval.success/approvalId are objects, even though command matches pendingApproval', async () => {
const approval = {
conversationId: 'c1',
command: 'deploy',
success: { truthy: 'object' },
approvalId: { also: 'object' },
} as unknown as Parameters<typeof CommandsPanel>[0]['approval'];
await render(
<CommandsPanel
manifest={null}
results={[]}
approval={approval}
pendingApproval={{ command: 'deploy', args: 'prod' }}
hasConversation
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
expect(
[...(container?.querySelectorAll('button') ?? [])].some((button) =>
button.textContent?.includes('Run approved command'),
),
).toBe(false);
});
it('shows the guarded server-provided denial reason for a denied approval', async () => {
await render(
<CommandsPanel
manifest={null}
results={[]}
approval={{
conversationId: 'c1',
command: 'deploy',
success: false,
message: 'Not authorized',
}}
pendingApproval={{ command: 'deploy', args: 'prod' }}
hasConversation
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
expect(container?.textContent).toContain('Not authorized');
});
it('falls back to a stable "Denied." copy when a denial has no usable message', async () => {
await render(
<CommandsPanel
manifest={null}
results={[]}
approval={{ conversationId: 'c1', command: 'deploy', success: false }}
pendingApproval={{ command: 'deploy', args: 'prod' }}
hasConversation
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
expect(container?.textContent).toContain('Denied.');
});
it('shows the guarded contract-provided reason for a failed command result, falling back to a stable copy only when absent', async () => {
await render(
<CommandsPanel
manifest={null}
results={[
{ conversationId: 'c1', command: 'model', success: false, message: 'Unknown model' },
{ conversationId: 'c1', command: 'deploy', success: false },
]}
approval={null}
pendingApproval={null}
hasConversation={false}
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
expect(container?.textContent).toContain('Unknown model');
expect(container?.textContent).toContain('Command failed.');
});
it('bounds an oversized command result message at the render site as defense-in-depth', async () => {
const hostileMessage = 'y'.repeat(50_000);
await render(
<CommandsPanel
manifest={null}
results={[
{ conversationId: 'c1', command: 'model', success: false, message: hostileMessage },
]}
approval={null}
pendingApproval={null}
hasConversation={false}
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
);
const text = container?.textContent ?? '';
expect(text.length).toBeLessThan(hostileMessage.length);
});
it('does not throw when the manifest fields are malformed (non-array commands/skills)', async () => {
const manifest = {
commands: 'not-an-array',
skills: null,
version: 1,
} as unknown as Parameters<typeof CommandsPanel>[0]['manifest'];
await expect(
render(
<CommandsPanel
manifest={manifest}
results={[]}
approval={null}
pendingApproval={null}
hasConversation={false}
onExecute={vi.fn()}
onApprove={vi.fn()}
onRunApproved={vi.fn()}
/>,
),
).resolves.not.toThrow();
});
});
-164
View File
@@ -1,164 +0,0 @@
import { useState, type ReactElement } from 'react';
import type { PendingApproval } from './use-chat-connection';
import { MAX_COMMAND_MESSAGE_CHARS } from './limits';
import { asNonEmptyString, asString } from './runtime-guards';
import type {
CommandManifest,
SlashCommandApprovalResultPayload,
SlashCommandResultPayload,
} from '@/lib/chat-contract';
/** Stable fallback copy shown for a failed command only when the server's
* own guarded, non-empty `message` (e.g. "Unknown model") is absent or
* malformed — the structured contract reason itself is otherwise shown
* directly, never a raw thrown exception, stack trace, or object value. */
const COMMAND_FAILURE_COPY = 'Command failed.';
/** Render-site defense-in-depth: `use-chat-connection.ts` already bounds a
* stored command:result message at ingestion, but this component must never
* assume every caller went through that path — bounding again here means a
* hostile/oversized message can never force an unbounded render. */
function boundMessage(value: string): string {
return value.length > MAX_COMMAND_MESSAGE_CHARS
? value.slice(0, MAX_COMMAND_MESSAGE_CHARS)
: value;
}
interface CommandsPanelProps {
manifest: CommandManifest | null;
results: SlashCommandResultPayload[];
approval: SlashCommandApprovalResultPayload | null;
pendingApproval: PendingApproval | null;
hasConversation: boolean;
onExecute: (input: { command: string; args?: string }) => void;
onApprove: (input: { command: string; args?: string }) => void;
onRunApproved: () => void;
}
export function CommandsPanel({
manifest,
results,
approval,
pendingApproval,
hasConversation,
onExecute,
onApprove,
onRunApproved,
}: CommandsPanelProps): ReactElement {
const [command, setCommand] = useState('');
const [args, setArgs] = useState('');
// Defense-in-depth: the reducer already normalizes success/approvalId
// before storing `approval`, but a matching command string alone must
// never be trusted here either — require the literal boolean `true` and a
// non-empty string approvalId, not merely truthy values.
const canRunApproved =
approval?.success === true &&
typeof approval.approvalId === 'string' &&
approval.approvalId.length > 0 &&
!!pendingApproval &&
pendingApproval.command === approval.command;
// A manifest arrives from the server as untyped JSON at runtime — guard
// both collections before mapping so a malformed manifest cannot throw.
const commands = Array.isArray(manifest?.commands) ? manifest.commands : [];
const skills = Array.isArray(manifest?.skills) ? manifest.skills : [];
return (
<section aria-label="Commands" className="flex flex-col gap-2 border-b px-4 py-3 text-xs">
{commands.length > 0 ? (
<ul aria-label="Available commands" className="flex flex-col gap-1">
{commands.map((cmd, index) => (
<li key={asString(cmd?.name) || `cmd-${index}`}>
<strong>/{asString(cmd?.name)}</strong> {asString(cmd?.description)}
</li>
))}
</ul>
) : null}
{skills.length > 0 ? (
<ul aria-label="Available skills" className="flex flex-col gap-1">
{skills.map((skill, index) => (
<li key={asString(skill?.name) || `skill-${index}`}>
<strong>/skill:{asString(skill?.name)}</strong> {asString(skill?.description)}
</li>
))}
</ul>
) : null}
<div className="flex flex-wrap items-center gap-2">
<input
aria-label="Command name"
value={command}
onChange={(event) => setCommand(event.target.value)}
placeholder="command"
/>
<input
aria-label="Command arguments"
value={args}
onChange={(event) => setArgs(event.target.value)}
placeholder="args (optional)"
/>
<button
type="button"
disabled={!hasConversation || !command.trim()}
onClick={() => onExecute({ command: command.trim(), args: args.trim() || undefined })}
>
Run command
</button>
<button
type="button"
disabled={!hasConversation || !command.trim()}
onClick={() => onApprove({ command: command.trim(), args: args.trim() || undefined })}
>
Request approval
</button>
</div>
{approval ? (
<div role={approval.success ? 'status' : 'alert'} className="flex items-center gap-2">
{/* A successful approval shows stable client copy only — never
the server-controlled approval.message or echoed
approval.command as the primary confirmation. The frozen local
pendingApproval below (not this line) is the sole authoritative
statement of what will run. A denial, by contrast, is not an
execution authority and safely surfaces the guarded structured
reason the server gave (e.g. "Not authorized"), falling back to
a stable copy only when absent/malformed. */}
<span>
{approval.success ? 'Approved.' : asNonEmptyString(approval.message, 'Denied.')}
</span>
{canRunApproved && pendingApproval ? (
<>
{/* Authoritative frozen local command+args — what the click below
will actually emit. The server's `approval` above is display-only
and must never be trusted to represent the executed payload. */}
<span>
Will run: /{pendingApproval.command}{' '}
{pendingApproval.args ? pendingApproval.args : '(no args)'}
</span>
<button type="button" onClick={onRunApproved}>
Run approved command
</button>
</>
) : null}
</div>
) : null}
{results.length > 0 ? (
<ul aria-label="Command results" className="flex flex-col gap-1">
{results.map((result, index) => (
<li key={`${result.command}-${index}`} role={result.success ? 'status' : 'alert'}>
/{asString(result.command)}: {result.success ? 'success' : 'failed'}
{result.success
? typeof result.message === 'string' && result.message
? `${boundMessage(result.message)}`
: ''
: `${boundMessage(asNonEmptyString(result.message, COMMAND_FAILURE_COPY))}`}
</li>
))}
</ul>
) : null}
</section>
);
}
-98
View File
@@ -1,98 +0,0 @@
import { useState, type KeyboardEvent, type ReactElement } from 'react';
interface ComposerProps {
onSend: (input: { content: string; provider?: string; modelId?: string }) => void;
onStop: () => void;
streaming: boolean;
/** True from local send time through server turn startup/ack and
* throughout streaming — a superset of `streaming` that also covers the
* pre-ack window where a second send could otherwise slip through. */
sending: boolean;
hasConversation: boolean;
}
export function Composer({
onSend,
onStop,
streaming,
sending,
hasConversation,
}: ComposerProps): ReactElement {
const [content, setContent] = useState('');
const [provider, setProvider] = useState('');
const [modelId, setModelId] = useState('');
const busy = streaming || sending;
function submit(): void {
if (busy) return;
const trimmed = content.trim();
if (!trimmed) return;
onSend({
content: trimmed,
provider: provider.trim() || undefined,
modelId: modelId.trim() || undefined,
});
setContent('');
}
function handleKeyDown(event: KeyboardEvent<HTMLTextAreaElement>): void {
if (event.key === 'Enter' && !event.shiftKey) {
event.preventDefault();
submit();
}
}
return (
<form
onSubmit={(event) => {
event.preventDefault();
submit();
}}
className="flex flex-col gap-2 border-t p-4"
>
<div className="flex flex-wrap gap-2">
<input
aria-label="Provider"
value={provider}
onChange={(event) => setProvider(event.target.value)}
placeholder="Provider (optional)"
className="rounded border px-2 py-1 text-xs"
/>
<input
aria-label="Model"
value={modelId}
onChange={(event) => setModelId(event.target.value)}
placeholder="Model (optional)"
className="rounded border px-2 py-1 text-xs"
/>
</div>
<div className="flex items-end gap-2">
<textarea
aria-label="Message"
value={content}
onChange={(event) => setContent(event.target.value)}
onKeyDown={handleKeyDown}
rows={2}
placeholder="Message… (Enter to send, Shift+Enter for a new line)"
className="flex-1 resize-none rounded border px-3 py-2 text-sm"
/>
<button
type="submit"
disabled={!content.trim() || busy}
className="rounded px-3 py-2 text-sm font-medium"
>
Send
</button>
<button
type="button"
aria-label="Stop"
disabled={!hasConversation || !streaming}
onClick={onStop}
className="rounded px-3 py-2 text-sm font-medium"
>
Stop
</button>
</div>
</form>
);
}
-22
View File
@@ -1,22 +0,0 @@
/**
* Bounds on server-fed chat state. A hostile or malfunctioning gateway can
* flood any of these collections; caps keep memory/render cost flat instead
* of growing unboundedly for the lifetime of the connection.
*/
/** Max characters retained for the in-flight streamed text/thinking buffers. */
export const MAX_STREAM_CHARS = 20_000;
/** Max transcript turns retained (oldest dropped first). */
export const MAX_MESSAGES = 500;
/** Max tool-call entries (including anomaly entries) retained per turn history. */
export const MAX_TOOLS = 200;
/** Max slash-command results retained. */
export const MAX_COMMAND_RESULTS = 200;
/** Max commands/skills accepted from a single manifest push. */
export const MAX_MANIFEST_ITEMS = 500;
/** Max executed approval IDs remembered for single-flight dedup. */
export const MAX_EXECUTED_APPROVAL_IDS = 200;
/** Max characters retained for a single command:result message — a hostile
* or malfunctioning gateway must not be able to push an unbounded curated
* success/failure reason into state (or, defensively, onto the page). */
export const MAX_COMMAND_MESSAGE_CHARS = 1_000;
@@ -1,39 +0,0 @@
import type { ReactElement } from 'react';
import type { ChatTranscriptMessage } from './use-chat-connection';
interface MessageTranscriptProps {
messages: ChatTranscriptMessage[];
streaming: boolean;
text: string;
}
export function MessageTranscript({
messages,
streaming,
text,
}: MessageTranscriptProps): ReactElement {
return (
<div
role="log"
aria-live="polite"
aria-label="Conversation"
className="flex flex-1 flex-col gap-3 overflow-y-auto p-4"
>
{messages.map((message) => (
<div key={message.id} data-role={message.role} className="whitespace-pre-wrap text-sm">
<span className="font-medium">{message.role === 'user' ? 'You' : 'Assistant'}: </span>
<span>{message.text}</span>
{message.thinking ? (
<div className="pt-1 text-xs italic opacity-70">{message.thinking}</div>
) : null}
</div>
))}
{streaming ? (
<div data-role="assistant-streaming" className="whitespace-pre-wrap text-sm">
<span className="font-medium">Assistant: </span>
<span>{text || 'Thinking…'}</span>
</div>
) : null}
</div>
);
}
-49
View File
@@ -1,49 +0,0 @@
/**
* Socket.IO payloads are only statically typed at the call site — a
* misbehaving or compromised gateway can send anything at runtime. These
* guards protect the dereference sites that would otherwise throw (`.map` on
* a non-array, `.toFixed` on a non-number) or render an object as a React
* child.
*/
export function asString(value: unknown, fallback = ''): string {
return typeof value === 'string' ? value : fallback;
}
/** Like `asString`, but an empty string also falls back — used for guarded
* contract-provided reason strings (e.g. a denial or failure message) where
* an empty string is not a meaningful value to display in place of the
* stable fallback copy. */
export function asNonEmptyString(value: unknown, fallback: string): string {
return typeof value === 'string' && value.length > 0 ? value : fallback;
}
export function asFiniteNumber(value: unknown, fallback = 0): number {
return typeof value === 'number' && Number.isFinite(value) ? value : fallback;
}
/** Like `asFiniteNumber`, but returns `null` on failure instead of a numeric
* fallback — callers that must not fabricate a plausible-looking value (e.g.
* `0 tokens` / `$0.0000` for genuinely unknown usage) use this to render an
* honest "unavailable" label instead. */
export function asFiniteNumberOrNull(value: unknown): number | null {
return typeof value === 'number' && Number.isFinite(value) ? value : null;
}
export function asStringArray(value: unknown): string[] {
return Array.isArray(value) && value.every((item) => typeof item === 'string') ? value : [];
}
export function isRecord(value: unknown): value is Record<string, unknown> {
return typeof value === 'object' && value !== null;
}
/** The single point of truth for what counts as a valid conversation ID
* anywhere a scoped server event may adopt one into state — a non-empty
* string, nothing else. Every site that establishes or compares
* `state.conversationId` against a raw socket payload must route through
* this guard so a malformed first frame (null/object/number/empty string)
* can never be adopted verbatim. */
export function asConversationId(value: unknown): string | null {
return typeof value === 'string' && value.length > 0 ? value : null;
}
-68
View File
@@ -1,68 +0,0 @@
import type { ReactElement } from 'react';
import type { SessionInfoPayload } from '@/lib/chat-contract';
import { MAX_MANIFEST_ITEMS } from './limits';
import { asString, asStringArray } from './runtime-guards';
interface SessionPanelProps {
sessionInfo: SessionInfoPayload | null;
onSetThinking: (level: string) => void;
}
const THINKING_LEVEL_UNAVAILABLE = '';
export function SessionPanel({
sessionInfo,
onSetThinking,
}: SessionPanelProps): ReactElement | null {
if (!sessionInfo) return null;
// The reducer already caps this before storing it, but the render site
// defends independently — a hostile payload must never be able to force
// this <select> to lay out an unbounded number of options.
const availableThinkingLevels = asStringArray(sessionInfo.availableThinkingLevels).slice(
0,
MAX_MANIFEST_ITEMS,
);
const hasThinkingLevels = availableThinkingLevels.length > 0;
return (
<section
aria-label="Session info"
className="flex flex-wrap items-center gap-3 border-b px-4 py-2 text-xs"
>
<span>{asString(sessionInfo.provider, 'unknown')}</span>
<span>{asString(sessionInfo.modelId, 'unknown')}</span>
<label className="flex items-center gap-2">
<span>Thinking level</span>
<select
aria-label="Thinking level"
value={
hasThinkingLevels ? asString(sessionInfo.thinkingLevel) : THINKING_LEVEL_UNAVAILABLE
}
onChange={(event) => {
// The placeholder option is not a real, settable level — a
// malformed availableThinkingLevels list must never let the
// client emit set:thinking for it.
if (!hasThinkingLevels) return;
onSetThinking(event.target.value);
}}
>
{hasThinkingLevels ? (
availableThinkingLevels.map((level) => (
<option key={level} value={level}>
{level}
</option>
))
) : (
<option value={THINKING_LEVEL_UNAVAILABLE}>Thinking level unavailable</option>
)}
</select>
</label>
{sessionInfo.routingDecision ? (
<span title={asString(sessionInfo.routingDecision.ruleName)}>
{asString(sessionInfo.routingDecision.reason)}
</span>
) : null}
</section>
);
}
@@ -1,125 +0,0 @@
import { vi } from 'vitest';
import type { ClientToServerEvents, ServerToClientEvents } from '@/lib/chat-contract';
type ServerEvent = keyof ServerToClientEvents;
type ClientEvent = keyof ClientToServerEvents;
type ServerHandler<K extends ServerEvent> = ServerToClientEvents[K];
type ClientPayload<K extends ClientEvent> = Parameters<ClientToServerEvents[K]>[0];
export interface EmittedEvent<K extends ClientEvent = ClientEvent> {
event: K;
payload: ClientPayload<K>;
}
/** The subset of a Socket.IO `ChatSocket` that `useChatConnection` drives. */
export interface FakeChatSocket {
connected: boolean;
connect(): FakeChatSocket;
on<K extends ServerEvent>(event: K, handler: ServerHandler<K>): FakeChatSocket;
off<K extends ServerEvent>(event: K, handler: ServerHandler<K>): FakeChatSocket;
emit<K extends ClientEvent>(event: K, payload: ClientPayload<K>): FakeChatSocket;
}
/**
* A typed in-memory stand-in for `getSocket()`. Unlike a bare
* `(event: string, payload: unknown) => void` mock, every public method here is
* checked against the real `/chat` contract — a typo'd event name or a payload
* missing a required field fails to compile instead of silently no-op'ing at
* runtime.
*/
/** Socket.IO's built-in connection-state events. Not part of the app-level
* ServerToClientEvents contract, but real sockets always support them and
* `useChatConnection` registers a `disconnect` handler on the real socket. */
type LifecycleEvent = 'connect' | 'disconnect';
export function createFakeChatSocket(): {
socket: FakeChatSocket;
listeners: Map<ServerEvent, Set<(payload: never) => void>>;
emitted: EmittedEvent[];
serverEmit<K extends ServerEvent>(
event: K,
payload: Parameters<ServerToClientEvents[K]>[0],
): void;
/** Escape hatch for malformed-payload tests: bypasses the compile-time
* payload contract to simulate a genuinely untrusted runtime value from the
* server, e.g. a `session:info` with a non-array `availableThinkingLevels`. */
serverEmitRaw(event: ServerEvent, payload: unknown): void;
/** Simulates a transient Socket.IO `disconnect` — fires any handler(s)
* registered via `socket.on('disconnect', ...)` without clearing any
* listeners, mirroring how a real reconnecting socket behaves. */
simulateDisconnect(): void;
/** Simulates socket.io-client's automatic reconnect of the *same*
* instance after a transient disconnect: marks the socket connected again
* and fires any handler(s) registered via `socket.on('connect', ...)`,
* without clearing or replacing any listeners. */
simulateReconnect(): void;
} {
const listeners = new Map<ServerEvent, Set<(payload: never) => void>>();
const emitted: EmittedEvent[] = [];
// Internal storage is intentionally keyed loosely (the per-event handler shape
// varies by K, which a single Map can't express); the generic signatures on the
// exported `socket`/`serverEmit` above and below are what keep test call sites
// type-checked against ServerToClientEvents/ClientToServerEvents.
const socket = {
connected: false,
connect: vi.fn(function connect(this: void) {
socket.connected = true;
return socket;
}),
on: vi.fn(function on(this: void, event: ServerEvent, handler: (payload: never) => void) {
if (!listeners.has(event)) listeners.set(event, new Set());
listeners.get(event)?.add(handler);
return socket;
}),
off: vi.fn(function off(this: void, event: ServerEvent, handler: (payload: never) => void) {
listeners.get(event)?.delete(handler);
return socket;
}),
emit: vi.fn(function emit(this: void, event: ClientEvent, payload: unknown) {
emitted.push({ event, payload } as EmittedEvent);
return socket;
}),
} as unknown as FakeChatSocket;
function serverEmit<K extends ServerEvent>(
event: K,
payload: Parameters<ServerToClientEvents[K]>[0],
): void {
for (const handler of listeners.get(event) ?? []) {
(handler as (payload: Parameters<ServerToClientEvents[K]>[0]) => void)(payload);
}
}
function serverEmitRaw(event: ServerEvent, payload: unknown): void {
for (const handler of listeners.get(event) ?? []) {
(handler as (payload: unknown) => void)(payload);
}
}
function simulateDisconnect(): void {
socket.connected = false;
const lifecycleKey = 'disconnect' satisfies LifecycleEvent as unknown as ServerEvent;
for (const handler of listeners.get(lifecycleKey) ?? []) {
(handler as () => void)();
}
}
function simulateReconnect(): void {
socket.connected = true;
const lifecycleKey = 'connect' satisfies LifecycleEvent as unknown as ServerEvent;
for (const handler of listeners.get(lifecycleKey) ?? []) {
(handler as () => void)();
}
}
return {
socket,
listeners,
emitted,
serverEmit,
serverEmitRaw,
simulateDisconnect,
simulateReconnect,
};
}
@@ -1,63 +0,0 @@
import { act } from 'react';
import { createRoot, type Root } from 'react-dom/client';
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
import { ToolCallList } from './tool-call-list';
beforeAll(() => {
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
configurable: true,
value: true,
});
});
afterAll(() => {
Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
});
let root: Root | null;
let container: HTMLElement | null;
async function render(node: Parameters<Root['render']>[0]): Promise<void> {
container = document.createElement('div');
document.body.append(container);
root = createRoot(container);
await act(async () => {
root?.render(node);
});
}
afterEach(async () => {
await act(async () => {
root?.unmount();
});
document.body.replaceChildren();
root = null;
container = null;
});
describe('ToolCallList', () => {
it('renders two entries independently, without a duplicate-key warning, when a valid toolCallId is shared', async () => {
const consoleError = vi.spyOn(console, 'error').mockImplementation(() => {});
await render(
<ToolCallList
tools={[
{ toolCallId: 'dup', toolName: 'search', status: 'success' },
{ toolCallId: 'dup', toolName: 'search', status: 'running' },
]}
/>,
);
const items = [...(container?.querySelectorAll('li') ?? [])];
expect(items).toHaveLength(2);
expect(items[0]?.textContent).toContain('success');
expect(items[1]?.textContent).toContain('running');
const duplicateKeyWarning = consoleError.mock.calls.some((args) =>
args.some((arg) => typeof arg === 'string' && arg.includes('same key')),
);
expect(duplicateKeyWarning).toBe(false);
consoleError.mockRestore();
});
});
-24
View File
@@ -1,24 +0,0 @@
import type { ReactElement } from 'react';
import type { ToolCallState } from './use-chat-connection';
export function ToolCallList({ tools }: { tools: ToolCallState[] }): ReactElement | null {
if (tools.length === 0) return null;
return (
<ul aria-label="Tool calls" className="flex flex-col gap-1 px-4 pb-2 text-xs">
{tools.map((tool, index) => (
<li
// A valid server-controlled toolCallId can legitimately repeat
// (e.g. two tool:start events sharing one id) — keying on it alone
// would give React two identical keys. Pairing it with its
// (stable, append-only) render index keeps every key unique.
key={`${tool.toolCallId}-${index}`}
role={tool.status === 'error' || tool.status === 'anomaly' ? 'alert' : 'status'}
>
{tool.toolName} {' '}
{tool.status === 'anomaly' ? 'unexpected end (unknown tool call)' : tool.status}
</li>
))}
</ul>
);
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
-135
View File
@@ -1,135 +0,0 @@
import { act } from 'react';
import { createRoot, type Root } from 'react-dom/client';
import { createMemoryRouter, RouterProvider, type RouteObject } from 'react-router-dom';
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
const { useSessionMock } = vi.hoisted(() => ({
useSessionMock: vi.fn(),
}));
vi.mock('@/lib/auth-client', () => ({
useSession: useSessionMock,
}));
import { AuthGuard, GuestGuard } from './guards';
interface RenderedRouter {
container: HTMLDivElement;
router: ReturnType<typeof createMemoryRouter>;
}
const mountedRoots: Root[] = [];
beforeAll(() => {
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
configurable: true,
value: true,
});
});
afterAll(() => {
Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
});
async function renderRouter(
routeObjects: RouteObject[],
initialEntry: string,
): Promise<RenderedRouter> {
const container = document.createElement('div');
document.body.append(container);
const router = createMemoryRouter(routeObjects, { initialEntries: [initialEntry] });
const root = createRoot(container);
mountedRoots.push(root);
await act(async () => {
root.render(<RouterProvider router={router} />);
});
return { container, router };
}
afterEach(async () => {
for (const root of mountedRoots.splice(0)) {
await act(async () => {
root.unmount();
});
}
document.body.replaceChildren();
useSessionMock.mockReset();
});
const guestRoutes: RouteObject[] = [
{
path: '/login',
element: <GuestGuard />,
children: [{ index: true, element: <p>Guest page</p> }],
},
{ path: '/chat', element: <p>Chat page</p> },
];
const authenticatedRoutes: RouteObject[] = [
{
path: '/chat',
element: <AuthGuard />,
children: [{ index: true, element: <p>Private page</p> }],
},
{ path: '/login', element: <p>Login page</p> },
];
describe('GuestGuard', () => {
it('renders the guest outlet while session lookup is pending', async () => {
useSessionMock.mockReturnValue({ data: null, isPending: true });
const view = await renderRouter(guestRoutes, '/login');
expect(view.container.textContent).toContain('Guest page');
expect(view.router.state.location.pathname).toBe('/login');
});
it('renders the guest outlet when no session exists', async () => {
useSessionMock.mockReturnValue({ data: null, isPending: false });
const view = await renderRouter(guestRoutes, '/login');
expect(view.container.textContent).toContain('Guest page');
expect(view.router.state.location.pathname).toBe('/login');
});
it('redirects an authenticated session to chat', async () => {
useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
const view = await renderRouter(guestRoutes, '/login');
expect(view.container.textContent).toContain('Chat page');
expect(view.router.state.location.pathname).toBe('/chat');
});
});
describe('AuthGuard', () => {
it('renders the existing loading treatment while session lookup is pending', async () => {
useSessionMock.mockReturnValue({ data: null, isPending: true });
const view = await renderRouter(authenticatedRoutes, '/chat');
expect(view.container.textContent).toContain('Loading...');
expect(view.router.state.location.pathname).toBe('/chat');
});
it('redirects an unauthenticated visitor to login', async () => {
useSessionMock.mockReturnValue({ data: null, isPending: false });
const view = await renderRouter(authenticatedRoutes, '/chat');
expect(view.container.textContent).toContain('Login page');
expect(view.router.state.location.pathname).toBe('/login');
});
it('renders the authenticated outlet when a session exists', async () => {
useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
const view = await renderRouter(authenticatedRoutes, '/chat');
expect(view.container.textContent).toContain('Private page');
expect(view.router.state.location.pathname).toBe('/chat');
});
});
-23
View File
@@ -1,23 +0,0 @@
import type { ReactElement } from 'react';
import { Navigate, Outlet } from 'react-router-dom';
import { useSession } from '@/lib/auth-client';
export function GuestGuard(): ReactElement {
const { data: session } = useSession();
return session ? <Navigate to="/chat" replace /> : <Outlet />;
}
export function AuthGuard(): ReactElement {
const { data: session, isPending } = useSession();
if (isPending) {
return (
<div className="flex min-h-screen items-center justify-center">
<div className="text-sm text-text-muted">Loading...</div>
</div>
);
}
return session ? <Outlet /> : <Navigate to="/login" replace />;
}
@@ -1,87 +0,0 @@
import { act } from 'react';
import { createRoot, type Root } from 'react-dom/client';
import { createMemoryRouter, RouterProvider, type RouteObject } from 'react-router-dom';
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from 'vitest';
const { useSessionMock } = vi.hoisted(() => ({
useSessionMock: vi.fn(),
}));
vi.mock('@/lib/auth-client', () => ({
useSession: useSessionMock,
}));
import { routes } from '@/routes';
beforeAll(() => {
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
configurable: true,
value: true,
});
});
afterAll(() => {
Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
});
function Boom(): never {
throw new Error('render blew up');
}
/** Recursively clones the real exported route table, replacing only the
* `/chat` route's `element` with `<Boom />` every other route (including
* the real `AuthGuard` nesting and the real `/chat` `errorElement`) is left
* exactly as exported. This is what makes the test fail if a future change
* removes the real route's `errorElement`, unlike a hand-built independent
* route tree that could drift from production undetected. */
function replaceChatElementWithBoom(nodes: RouteObject[]): RouteObject[] {
return nodes.map((node) => {
const cloned: RouteObject = { ...node };
if (cloned.path === '/chat') {
cloned.element = <Boom />;
}
if (cloned.children) {
cloned.children = replaceChatElementWithBoom(cloned.children);
}
return cloned;
});
}
let root: Root | null;
let container: HTMLElement;
afterEach(async () => {
await act(async () => {
root?.unmount();
});
document.body.replaceChildren();
root = null;
useSessionMock.mockReset();
});
describe('ChatRouteErrorBoundary', () => {
it('renders a recoverable, non-blank fallback when the /chat route element throws during render', async () => {
useSessionMock.mockReturnValue({ data: { user: { id: 'user-1' } }, isPending: false });
const routeObjects = replaceChatElementWithBoom(routes);
const router = createMemoryRouter(routeObjects, { initialEntries: ['/chat'] });
container = document.createElement('div');
document.body.append(container);
root = createRoot(container);
const consoleErrorSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
try {
await act(async () => {
root?.render(<RouterProvider router={router} />);
});
expect(consoleErrorSpy).toHaveBeenCalled();
} finally {
consoleErrorSpy.mockRestore();
}
expect(container.textContent).not.toBe('');
expect(container.querySelector('[role="alert"]')).toBeTruthy();
});
});
@@ -1,22 +0,0 @@
import type { ReactElement } from 'react';
import { useRouteError } from 'react-router-dom';
/**
* `/chat` renders live, server-driven state (streamed text, tool calls,
* manifests) that can carry malformed payloads no compile-time contract can
* fully rule out at every dereference site. This is the last line of
* defense: if something still throws during render, show a recoverable
* alert instead of leaving the user on a blank/white screen.
*/
export function ChatRouteErrorBoundary(): ReactElement {
useRouteError();
return (
<div role="alert" className="flex min-h-screen flex-col items-center justify-center gap-3 p-8">
<p className="text-sm font-medium">Something went wrong loading chat.</p>
<a href="/chat" className="text-sm underline">
Reload chat
</a>
</div>
);
}
-636
View File
@@ -1,636 +0,0 @@
import { act } from 'react';
import { createRoot, type Root } from 'react-dom/client';
import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
import { createFakeChatSocket } from '@/spa/chat/test-support/fake-chat-socket';
import { MAX_MANIFEST_ITEMS } from '@/spa/chat/limits';
const { getSocketMock, destroySocketMock } = vi.hoisted(() => ({
getSocketMock: vi.fn(),
destroySocketMock: vi.fn(),
}));
vi.mock('@/lib/socket', () => ({
getSocket: getSocketMock,
destroySocket: destroySocketMock,
}));
import { ChatPage } from './chat';
function setValue(el: HTMLInputElement | HTMLTextAreaElement, value: string): void {
const proto =
el instanceof HTMLTextAreaElement ? HTMLTextAreaElement.prototype : HTMLInputElement.prototype;
const setter = Object.getOwnPropertyDescriptor(proto, 'value')?.set;
setter?.call(el, value);
el.dispatchEvent(new Event('input', { bubbles: true }));
}
function selectValue(el: HTMLSelectElement, value: string): void {
const setter = Object.getOwnPropertyDescriptor(HTMLSelectElement.prototype, 'value')?.set;
setter?.call(el, value);
el.dispatchEvent(new Event('change', { bubbles: true }));
}
function findButton(container: HTMLElement, text: string): HTMLButtonElement {
const button = [...container.querySelectorAll('button')].find((candidate) =>
candidate.textContent?.includes(text),
);
if (!button) throw new Error(`Button with text "${text}" not found`);
return button;
}
let fake: ReturnType<typeof createFakeChatSocket>;
let root: Root | null;
let container: HTMLElement;
beforeAll(() => {
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
configurable: true,
value: true,
});
});
afterAll(() => {
Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
});
beforeEach(async () => {
fake = createFakeChatSocket();
getSocketMock.mockReset().mockReturnValue(fake.socket);
destroySocketMock.mockReset();
container = document.createElement('div');
document.body.append(container);
root = createRoot(container);
await act(async () => {
root?.render(<ChatPage />);
});
});
afterEach(async () => {
await act(async () => {
root?.unmount();
});
document.body.replaceChildren();
});
describe('ChatPage', () => {
it('streams agent:text and agent:thinking, shows tool status, and finalizes on agent:end with usage', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('agent:start', { conversationId: 'c1' });
});
await act(async () => {
fake.serverEmit('agent:thinking', { conversationId: 'c1', text: 'pondering…' });
fake.serverEmit('agent:text', { conversationId: 'c1', text: 'Hel' });
fake.serverEmit('agent:text', { conversationId: 'c1', text: 'lo!' });
fake.serverEmit('agent:tool:start', {
conversationId: 'c1',
toolCallId: 't1',
toolName: 'web_search',
});
});
expect(container.textContent).toContain('pondering…');
expect(container.textContent).toContain('Hello!');
expect(container.textContent).toContain('web_search');
expect(container.textContent).toMatch(/running/i);
await act(async () => {
fake.serverEmit('agent:tool:end', {
conversationId: 'c1',
toolCallId: 't1',
toolName: 'web_search',
isError: false,
});
fake.serverEmit('agent:end', {
conversationId: 'c1',
usage: {
provider: 'anthropic',
modelId: 'claude',
thinkingLevel: 'medium',
tokens: { input: 12, output: 34, cacheRead: 0, cacheWrite: 0, total: 46 },
cost: 0.02,
context: { percent: 3, window: 200000 },
},
});
});
expect(container.textContent).toMatch(/success/i);
expect(container.textContent).toContain('Hello!');
expect(container.textContent).toMatch(/46/);
});
it('renders the commands manifest and session info, and lets the user pick a thinking level', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('commands:manifest', {
manifest: {
commands: [
{
name: 'model',
aliases: ['m'],
description: 'Change the active model',
scope: 'core',
execution: 'socket',
available: true,
},
],
skills: [],
version: 1,
},
});
fake.serverEmit('session:info', {
conversationId: 'c1',
provider: 'anthropic',
modelId: 'claude',
thinkingLevel: 'medium',
availableThinkingLevels: ['low', 'medium', 'high'],
routingDecision: {
model: 'claude',
provider: 'anthropic',
ruleName: 'default',
reason: 'default routing',
},
});
});
expect(container.textContent).toContain('model');
expect(container.textContent).toContain('Change the active model');
expect(container.textContent).toContain('anthropic');
expect(container.textContent).toContain('default routing');
const select = container.querySelector(
'select[aria-label="Thinking level"]',
) as HTMLSelectElement;
expect(select).toBeTruthy();
expect([...select.options].map((o) => o.value)).toEqual(['low', 'medium', 'high']);
await act(async () => {
selectValue(select, 'high');
});
expect(fake.emitted).toContainEqual({
event: 'set:thinking',
payload: { conversationId: 'c1', level: 'high' },
});
});
it('executes and approves commands with exact payloads and surfaces the approval affordance', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
});
const commandInput = container.querySelector(
'input[aria-label="Command name"]',
) as HTMLInputElement;
const argsInput = container.querySelector(
'input[aria-label="Command arguments"]',
) as HTMLInputElement;
await act(async () => {
setValue(commandInput, 'model');
setValue(argsInput, 'gpt-5');
});
await act(async () => {
findButton(container, 'Run command').click();
});
expect(fake.emitted).toContainEqual({
event: 'command:execute',
payload: { conversationId: 'c1', command: 'model', args: 'gpt-5' },
});
await act(async () => {
setValue(commandInput, 'deploy');
setValue(argsInput, 'prod');
});
await act(async () => {
findButton(container, 'Request approval').click();
});
expect(fake.emitted).toContainEqual({
event: 'command:approve',
payload: { conversationId: 'c1', command: 'deploy', args: 'prod' },
});
await act(async () => {
fake.serverEmit('command:approval', {
conversationId: 'c1',
command: 'deploy',
success: true,
approvalId: 'ap1',
expiresAt: '2026-01-01T00:00:00.000Z',
});
});
expect(container.textContent).toMatch(/approved/i);
await act(async () => {
findButton(container, 'Run approved command').click();
});
expect(fake.emitted).toContainEqual({
event: 'command:execute',
payload: { conversationId: 'c1', command: 'deploy', args: 'prod', approvalId: 'ap1' },
});
});
it('shows visible alert surfaces for a server error and the structured contract reason for a failed command result', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('error', { conversationId: 'c1', error: 'The model is unavailable' });
fake.serverEmit('command:result', {
conversationId: 'c1',
command: 'model',
success: false,
message: 'Unknown model',
});
});
const alerts = [...container.querySelectorAll('[role="alert"]')];
const alertText = alerts.map((node) => node.textContent).join(' ');
expect(alertText).toContain('The model is unavailable');
// The structured, contract-provided denial reason is visibly rendered.
expect(alertText).toContain('Unknown model');
});
it('falls back to a stable "Command failed." copy when a failed command result has no usable message', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmitRaw('command:result', {
conversationId: 'c1',
command: 'model',
success: false,
message: { bad: 'object' },
});
});
const alerts = [...container.querySelectorAll('[role="alert"]')];
const alertText = alerts.map((node) => node.textContent).join(' ');
expect(alertText).toContain('Command failed.');
});
it('caps availableThinkingLevels before storing and rendering a hostile session payload', async () => {
const hostileLevels = Array.from({ length: MAX_MANIFEST_ITEMS + 50 }, (_, i) => `level-${i}`);
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('session:info', {
conversationId: 'c1',
provider: 'anthropic',
modelId: 'claude',
thinkingLevel: 'level-0',
availableThinkingLevels: hostileLevels,
});
});
const select = container.querySelector(
'select[aria-label="Thinking level"]',
) as HTMLSelectElement;
expect(select).toBeTruthy();
expect(select.options.length).toBeLessThanOrEqual(MAX_MANIFEST_ITEMS);
});
it('renders a safe fallback when session:info arrives with a malformed (non-array) availableThinkingLevels, without throwing', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmitRaw('session:info', {
conversationId: 'c1',
provider: 'anthropic',
modelId: 'claude',
thinkingLevel: 'medium',
availableThinkingLevels: null,
});
});
expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
const select = container.querySelector(
'select[aria-label="Thinking level"]',
) as HTMLSelectElement;
expect(select).toBeTruthy();
// A malformed level list still shows a visible, safe placeholder option
// rather than a silently empty select.
expect([...select.options]).toHaveLength(1);
expect(select.options[0]?.textContent).toMatch(/unavailable/i);
await act(async () => {
selectValue(select, '');
});
expect(fake.emitted.filter((e) => e.event === 'set:thinking')).toHaveLength(0);
});
it('renders honest unavailable labels — not fabricated zeros — when agent:end usage has malformed/missing numeric fields', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('agent:start', { conversationId: 'c1' });
fake.serverEmitRaw('agent:end', {
conversationId: 'c1',
usage: {
provider: { nested: 'object' },
modelId: undefined,
thinkingLevel: 'medium',
tokens: { total: 'not-a-number' },
cost: undefined,
context: { percent: null, window: 200000 },
},
});
});
const usage = container.querySelector('[aria-label="Usage"]');
expect(usage).toBeTruthy();
expect(usage?.textContent).toContain('tokens unavailable');
expect(usage?.textContent).toContain('cost unavailable');
expect(usage?.textContent).not.toContain('0 tokens');
expect(usage?.textContent).not.toContain('$0.0000');
expect(usage?.textContent).toContain('unknown/unknown');
});
it('renders a safe fallback for message:ack when messageId is a malformed non-string value, without throwing', async () => {
await expect(
act(async () => {
fake.serverEmitRaw('message:ack', { conversationId: 'c1', messageId: { bad: 'object' } });
}),
).resolves.not.toThrow();
const status = [...container.querySelectorAll('[role="status"]')].find((node) =>
node.textContent?.includes('Message accepted'),
);
expect(status).toBeTruthy();
// A malformed messageId gets a stable, visible fallback — never blank,
// never the raw object.
expect(status?.textContent).toContain('unknown');
});
it('renders safely and does not throw when system:reload.message is a malformed non-string value', async () => {
await expect(
act(async () => {
fake.serverEmitRaw('system:reload', {
commands: [],
skills: [],
providers: [],
message: { bad: 'object' },
});
}),
).resolves.not.toThrow();
const status = container.querySelector('[role="status"]');
expect(status).toBeTruthy();
// A malformed reload message renders a stable, visible fallback rather
// than a silently empty status line.
expect(status?.textContent).toContain('Commands reloaded.');
});
it('renders safely and does not throw when a scoped error carries a malformed non-string error value', async () => {
await expect(
act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmitRaw('error', { conversationId: 'c1', error: ['not', 'a', 'string'] });
}),
).resolves.not.toThrow();
expect(container.querySelector('[role="alert"]')).toBeTruthy();
});
it('sends a message with optional provider/model fields and emits abort from the Stop control', async () => {
const textarea = container.querySelector(
'textarea[aria-label="Message"]',
) as HTMLTextAreaElement;
const providerInput = container.querySelector(
'input[aria-label="Provider"]',
) as HTMLInputElement;
const modelInput = container.querySelector('input[aria-label="Model"]') as HTMLInputElement;
const stopButtonBefore = container.querySelector(
'button[aria-label="Stop"]',
) as HTMLButtonElement;
expect(stopButtonBefore.disabled).toBe(true);
await act(async () => {
setValue(textarea, 'hello there');
setValue(providerInput, 'anthropic');
setValue(modelInput, 'claude');
});
await act(async () => {
textarea.dispatchEvent(
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
);
});
expect(fake.emitted).toContainEqual({
event: 'message',
payload: {
conversationId: undefined,
content: 'hello there',
provider: 'anthropic',
modelId: 'claude',
},
});
expect(container.textContent).toContain('hello there');
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('agent:start', { conversationId: 'c1' });
});
const stopButtonDuring = container.querySelector(
'button[aria-label="Stop"]',
) as HTMLButtonElement;
expect(stopButtonDuring.disabled).toBe(false);
await act(async () => {
stopButtonDuring.click();
});
expect(fake.emitted).toContainEqual({ event: 'abort', payload: { conversationId: 'c1' } });
});
it('renders the session panel from a pre-ack session:info and keeps it visible after the later ack', async () => {
const textarea = container.querySelector(
'textarea[aria-label="Message"]',
) as HTMLTextAreaElement;
await act(async () => {
setValue(textarea, 'hello');
});
await act(async () => {
textarea.dispatchEvent(
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
);
});
await act(async () => {
fake.serverEmit('session:info', {
conversationId: 'c1',
provider: 'anthropic',
modelId: 'claude',
thinkingLevel: 'medium',
availableThinkingLevels: ['low', 'medium', 'high'],
});
});
expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
expect(container.textContent).toContain('anthropic');
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
});
expect(container.querySelector('section[aria-label="Session info"]')).toBeTruthy();
expect(container.textContent).toContain('anthropic');
});
it('surfaces a pre-ack error as an alert without leaving the Stop control stuck active', async () => {
const textarea = container.querySelector(
'textarea[aria-label="Message"]',
) as HTMLTextAreaElement;
await act(async () => {
setValue(textarea, 'hello');
});
await act(async () => {
textarea.dispatchEvent(
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
);
});
await act(async () => {
fake.serverEmit('error', {
conversationId: 'c1',
error: 'Failed to start agent session. Please try again.',
});
});
const alerts = [...container.querySelectorAll('[role="alert"]')];
expect(alerts.some((node) => node.textContent?.includes('Failed to start agent session'))).toBe(
true,
);
const stopButton = container.querySelector('button[aria-label="Stop"]') as HTMLButtonElement;
expect(stopButton.disabled).toBe(true);
});
it('shows an accessible status once the message is acknowledged', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
});
const statuses = [...container.querySelectorAll('[role="status"]')];
expect(statuses.some((node) => node.textContent?.includes('m1'))).toBe(true);
});
it('renders finalized thinking text in the transcript after agent:end, not only while streaming', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('agent:start', { conversationId: 'c1' });
fake.serverEmit('agent:thinking', { conversationId: 'c1', text: 'reasoning about it' });
fake.serverEmit('agent:text', { conversationId: 'c1', text: 'Done.' });
});
expect(container.textContent).toContain('reasoning about it');
await act(async () => {
fake.serverEmit('agent:end', { conversationId: 'c1' });
});
expect(container.textContent).toContain('reasoning about it');
expect(container.textContent).toContain('Done.');
});
it('ignores a concurrent approval request and only executes the approved command once', async () => {
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
});
const commandInput = container.querySelector(
'input[aria-label="Command name"]',
) as HTMLInputElement;
const argsInput = container.querySelector(
'input[aria-label="Command arguments"]',
) as HTMLInputElement;
await act(async () => {
setValue(commandInput, 'deploy');
setValue(argsInput, 'prod');
});
await act(async () => {
findButton(container, 'Request approval').click();
});
await act(async () => {
setValue(argsInput, 'staging');
});
await act(async () => {
findButton(container, 'Request approval').click();
});
expect(fake.emitted.filter((e) => e.event === 'command:approve')).toHaveLength(1);
expect(fake.emitted).toContainEqual({
event: 'command:approve',
payload: { conversationId: 'c1', command: 'deploy', args: 'prod' },
});
await act(async () => {
fake.serverEmit('command:approval', {
conversationId: 'c1',
command: 'deploy',
success: true,
approvalId: 'ap1',
expiresAt: '2026-01-01T00:00:00.000Z',
});
});
await act(async () => {
findButton(container, 'Run approved command').click();
findButton(container, 'Run approved command').click();
});
expect(fake.emitted.filter((e) => e.event === 'command:execute')).toHaveLength(1);
expect(fake.emitted).toContainEqual({
event: 'command:execute',
payload: { conversationId: 'c1', command: 'deploy', args: 'prod', approvalId: 'ap1' },
});
});
it('disables sending a second message while a turn is streaming', async () => {
const textarea = container.querySelector(
'textarea[aria-label="Message"]',
) as HTMLTextAreaElement;
await act(async () => {
setValue(textarea, 'first');
});
await act(async () => {
textarea.dispatchEvent(
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
);
});
await act(async () => {
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
fake.serverEmit('agent:start', { conversationId: 'c1' });
});
const sendButton = findButton(container, 'Send');
expect(sendButton.disabled).toBe(true);
await act(async () => {
setValue(textarea, 'second');
});
await act(async () => {
textarea.dispatchEvent(
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
);
});
expect(fake.emitted.filter((e) => e.event === 'message')).toHaveLength(1);
});
it('removes socket handlers and tears down the socket on unmount, with no network calls', async () => {
expect(fake.listeners.size).toBeGreaterThan(0);
await act(async () => {
root?.unmount();
});
root = null;
for (const [, handlers] of fake.listeners) {
expect(handlers.size).toBe(0);
}
expect(destroySocketMock).toHaveBeenCalledOnce();
});
});
-92
View File
@@ -1,92 +0,0 @@
import type { ReactElement } from 'react';
import { CommandsPanel } from '@/spa/chat/commands-panel';
import { Composer } from '@/spa/chat/composer';
import { MessageTranscript } from '@/spa/chat/message-transcript';
import { asFiniteNumberOrNull, asString } from '@/spa/chat/runtime-guards';
import { SessionPanel } from '@/spa/chat/session-panel';
import { ToolCallList } from '@/spa/chat/tool-call-list';
import { useChatConnection } from '@/spa/chat/use-chat-connection';
/** Renders a real value normally, but an honest "unavailable" label instead
* of a fabricated `0` for a missing/malformed count a real `0 tokens` and
* an unknown token count must never look the same. */
function formatTokens(value: unknown): string {
const tokens = asFiniteNumberOrNull(value);
return tokens === null ? 'tokens unavailable' : `${tokens} tokens`;
}
/** Same honesty guarantee as `formatTokens`, for cost. */
function formatCost(value: unknown): string {
const cost = asFiniteNumberOrNull(value);
return cost === null ? 'cost unavailable' : `$${cost.toFixed(4)}`;
}
export function ChatPage(): ReactElement {
const { state, actions } = useChatConnection();
const hasConversation = state.conversationId !== null;
return (
<div className="flex h-[calc(100vh-3.5rem)] min-h-0 flex-col overflow-hidden md:h-screen">
<header className="border-b px-4 py-3">
<h1 className="text-lg font-semibold">Chat</h1>
</header>
{state.systemReload ? (
<div role="status" className="border-b px-4 py-2 text-sm">
{asString(state.systemReload.message)}
</div>
) : null}
{state.error ? (
<div role="alert" className="border-b px-4 py-2 text-sm">
{asString(state.error)}
</div>
) : null}
{state.ack ? (
<div role="status" className="border-b px-4 py-1 text-xs opacity-70">
Message accepted · conversation {asString(state.ack.conversationId, 'unknown')} · id{' '}
{asString(state.ack.messageId, 'unknown')}
</div>
) : null}
<SessionPanel sessionInfo={state.sessionInfo} onSetThinking={actions.setThinking} />
<MessageTranscript messages={state.messages} streaming={state.streaming} text={state.text} />
{state.thinking ? (
<section aria-label="Thinking" className="px-4 pb-2 text-xs italic opacity-80">
{state.thinking}
</section>
) : null}
<ToolCallList tools={state.tools} />
{state.usage ? (
<div aria-label="Usage" className="px-4 pb-2 text-xs opacity-80">
{formatTokens(state.usage.tokens?.total)} · {formatCost(state.usage.cost)} ·{' '}
{asString(state.usage.provider, 'unknown')}/{asString(state.usage.modelId, 'unknown')}
</div>
) : null}
<CommandsPanel
manifest={state.manifest}
results={state.commandResults}
approval={state.approval}
pendingApproval={state.pendingApproval}
hasConversation={hasConversation}
onExecute={actions.executeCommand}
onApprove={actions.approveCommand}
onRunApproved={actions.runApprovedCommand}
/>
<Composer
onSend={actions.sendMessage}
onStop={actions.abort}
streaming={state.streaming}
sending={state.sending}
hasConversation={hasConversation}
/>
</div>
);
}
-152
View File
@@ -1,152 +0,0 @@
import { useEffect, useState, type FormEvent, type ReactElement } from 'react';
import { Link, useNavigate } from 'react-router-dom';
import { SsoProviderButtons } from '@/components/auth/sso-provider-buttons';
import { api } from '@/lib/api';
import { authClient, signIn } from '@/lib/auth-client';
import type { SsoProviderDiscovery } from '@/lib/sso';
export function LoginPage(): ReactElement {
const navigate = useNavigate();
const [error, setError] = useState<string | null>(null);
const [loading, setLoading] = useState(false);
const [ssoProviders, setSsoProviders] = useState<SsoProviderDiscovery[]>([]);
const [ssoLoadingProviderId, setSsoLoadingProviderId] = useState<
SsoProviderDiscovery['id'] | null
>(null);
useEffect(() => {
let active = true;
void api<SsoProviderDiscovery[]>('/api/sso/providers').then(
(providers) => {
if (active) setSsoProviders(providers.filter((provider) => provider.configured));
},
() => {
if (active) setSsoProviders([]);
},
);
return () => {
active = false;
};
}, []);
async function handleSubmit(event: FormEvent<HTMLFormElement>): Promise<void> {
event.preventDefault();
setError(null);
setLoading(true);
const form = new FormData(event.currentTarget);
const email = String(form.get('email') ?? '');
const password = String(form.get('password') ?? '');
try {
const result = await signIn.email({ email, password });
if (result.error) {
setError(result.error.message ?? 'Sign in failed');
return;
}
navigate('/chat', { replace: true });
} catch (caught: unknown) {
setError(caught instanceof Error ? caught.message : 'Sign in failed');
} finally {
setLoading(false);
}
}
async function handleSsoSignIn(providerId: SsoProviderDiscovery['id']): Promise<void> {
setError(null);
setSsoLoadingProviderId(providerId);
try {
const result = await authClient.signIn.oauth2({
providerId,
callbackURL: '/chat',
newUserCallbackURL: '/chat',
});
if (result.error) {
setError(result.error.message ?? `Sign in with ${providerId} failed`);
setSsoLoadingProviderId(null);
}
} catch (caught: unknown) {
setError(caught instanceof Error ? caught.message : `Sign in with ${providerId} failed`);
setSsoLoadingProviderId(null);
}
}
return (
<div>
<h1 className="text-2xl font-semibold">Sign in</h1>
<p className="mt-1 text-sm text-text-secondary">Sign in to your Mosaic account</p>
{error ? (
<div
role="alert"
className="mt-4 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
>
{error}
</div>
) : null}
<form className="mt-6 space-y-4" onSubmit={handleSubmit}>
<div>
<label htmlFor="email" className="block text-sm font-medium text-text-secondary">
Email
</label>
<input
id="email"
name="email"
type="email"
autoComplete="email"
required
disabled={loading}
className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
placeholder="[email protected]"
/>
</div>
<div>
<label htmlFor="password" className="block text-sm font-medium text-text-secondary">
Password
</label>
<input
id="password"
name="password"
type="password"
autoComplete="current-password"
required
disabled={loading}
className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
placeholder="••••••••"
/>
</div>
<button
type="submit"
disabled={loading}
className="w-full rounded-lg bg-blue-600 px-4 py-2.5 text-sm font-medium text-white transition-colors hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 focus:ring-offset-surface-card disabled:opacity-50"
>
{loading ? 'Signing in...' : 'Sign in'}
</button>
</form>
<SsoProviderButtons
providers={ssoProviders}
loadingProviderId={ssoLoadingProviderId}
onOidcSignIn={(providerId) => {
void handleSsoSignIn(providerId);
}}
/>
<p className="mt-4 text-center text-sm text-text-muted">
Don&apos;t have an account?{' '}
<Link to="/register" className="text-blue-400 hover:text-blue-300">
Sign up
</Link>
</p>
</div>
);
}
-116
View File
@@ -1,116 +0,0 @@
import { useState, type FormEvent, type ReactElement } from 'react';
import { Link, useNavigate } from 'react-router-dom';
import { signUp } from '@/lib/auth-client';
export function RegisterPage(): ReactElement {
const navigate = useNavigate();
const [error, setError] = useState<string | null>(null);
const [loading, setLoading] = useState(false);
async function handleSubmit(event: FormEvent<HTMLFormElement>): Promise<void> {
event.preventDefault();
setError(null);
setLoading(true);
const form = new FormData(event.currentTarget);
const name = String(form.get('name') ?? '');
const email = String(form.get('email') ?? '');
const password = String(form.get('password') ?? '');
try {
const result = await signUp.email({ name, email, password });
if (result.error) {
setError(result.error.message ?? 'Registration failed');
return;
}
navigate('/chat', { replace: true });
} catch (caught: unknown) {
setError(caught instanceof Error ? caught.message : 'Registration failed');
} finally {
setLoading(false);
}
}
return (
<div>
<h1 className="text-2xl font-semibold">Create account</h1>
<p className="mt-1 text-sm text-text-secondary">Get started with Mosaic</p>
{error ? (
<div
role="alert"
className="mt-4 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
>
{error}
</div>
) : null}
<form className="mt-6 space-y-4" onSubmit={handleSubmit}>
<div>
<label htmlFor="name" className="block text-sm font-medium text-text-secondary">
Name
</label>
<input
id="name"
name="name"
type="text"
autoComplete="name"
required
disabled={loading}
className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
placeholder="Your name"
/>
</div>
<div>
<label htmlFor="email" className="block text-sm font-medium text-text-secondary">
Email
</label>
<input
id="email"
name="email"
type="email"
autoComplete="email"
required
disabled={loading}
className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
placeholder="[email protected]"
/>
</div>
<div>
<label htmlFor="password" className="block text-sm font-medium text-text-secondary">
Password
</label>
<input
id="password"
name="password"
type="password"
autoComplete="new-password"
required
disabled={loading}
className="mt-1 block w-full rounded-lg border border-surface-border bg-surface-elevated px-3 py-2 text-sm text-text-primary placeholder:text-text-muted focus:border-blue-500 focus:outline-none focus:ring-1 focus:ring-blue-500 disabled:opacity-50"
placeholder="••••••••"
/>
</div>
<button
type="submit"
disabled={loading}
className="w-full rounded-lg bg-blue-600 px-4 py-2.5 text-sm font-medium text-white transition-colors hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 focus:ring-offset-surface-card disabled:opacity-50"
>
{loading ? 'Creating account...' : 'Create account'}
</button>
</form>
<p className="mt-4 text-center text-sm text-text-muted">
Already have an account?{' '}
<Link to="/login" className="text-blue-400 hover:text-blue-300">
Sign in
</Link>
</p>
</div>
);
}
@@ -1,90 +0,0 @@
import { act } from 'react';
import { createRoot, type Root } from 'react-dom/client';
import { createMemoryRouter, RouterProvider } from 'react-router-dom';
import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
const { apiMock, oauth2Mock } = vi.hoisted(() => ({
apiMock: vi.fn(),
oauth2Mock: vi.fn(),
}));
vi.mock('@/lib/api', () => ({
api: apiMock,
}));
vi.mock('@/lib/auth-client', () => ({
signIn: { oauth2: oauth2Mock },
}));
import { SsoCallbackPage } from './sso-callback';
const mountedRoots: Root[] = [];
beforeAll(() => {
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
configurable: true,
value: true,
});
});
beforeEach(() => {
apiMock.mockResolvedValue([
{
id: 'authentik',
name: 'Authentik',
protocols: ['oidc'],
configured: true,
loginMode: 'oidc',
callbackPath: '/api/auth/oauth2/callback/authentik',
teamSync: { enabled: false, claim: null },
samlFallback: { configured: false, loginUrl: null },
warnings: [],
},
]);
oauth2Mock.mockResolvedValue({ data: null, error: null });
});
afterEach(async () => {
for (const root of mountedRoots.splice(0)) {
await act(async () => {
root.unmount();
});
}
document.body.replaceChildren();
apiMock.mockReset();
oauth2Mock.mockReset();
});
afterAll(() => {
Reflect.deleteProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT');
});
describe('SsoCallbackPage', () => {
it('rejects a control-character callback that normalizes to an external origin', async () => {
const router = createMemoryRouter(
[
{
path: '/auth/provider/:provider',
element: <SsoCallbackPage />,
},
],
{
initialEntries: ['/auth/provider/authentik?callbackURL=%2F%0A%2F%2Fevil.example'],
},
);
const container = document.createElement('div');
document.body.append(container);
const root = createRoot(container);
mountedRoots.push(root);
await act(async () => {
root.render(<RouterProvider router={router} />);
await new Promise((resolve) => setTimeout(resolve, 0));
});
expect(oauth2Mock).toHaveBeenCalledWith({
providerId: 'authentik',
callbackURL: '/chat',
});
});
});
-91
View File
@@ -1,91 +0,0 @@
import { useEffect, useState, type ReactElement } from 'react';
import { Link, useParams, useSearchParams } from 'react-router-dom';
import { api } from '@/lib/api';
import { resolveAuthCallbackURL } from '@/lib/auth-redirect';
import { signIn } from '@/lib/auth-client';
import type { SsoProviderDiscovery } from '@/lib/sso';
export function SsoCallbackPage(): ReactElement {
const { provider: providerId = '' } = useParams<'provider'>();
const [searchParams] = useSearchParams();
const requestedCallbackURL = searchParams.get('callbackURL');
const [providerName, setProviderName] = useState<string | null>(null);
const [error, setError] = useState<string | null>(null);
useEffect(() => {
let cancelled = false;
async function redirectToProvider(): Promise<void> {
try {
const callbackURL = resolveAuthCallbackURL(requestedCallbackURL, window.location.origin);
const providers = await api<SsoProviderDiscovery[]>('/api/sso/providers');
if (cancelled) return;
const provider = providers.find((candidate) => candidate.id === providerId);
if (!provider) {
setError('Unknown SSO provider.');
return;
}
setProviderName(provider.name);
if (!provider.configured) {
setError(`${provider.name} is not enabled in this deployment.`);
return;
}
if (provider.loginMode !== 'oidc') {
setError(`${provider.name} is not available for OIDC sign in.`);
return;
}
const result = await signIn.oauth2({
providerId: provider.id,
callbackURL,
});
if (!cancelled && result?.error) {
setError(result.error.message ?? `${provider.name} sign in failed.`);
}
} catch (caught: unknown) {
if (!cancelled) {
setError(caught instanceof Error ? caught.message : 'Unable to start single sign-on.');
}
}
}
void redirectToProvider();
return () => {
cancelled = true;
};
}, [providerId, requestedCallbackURL]);
return (
<div className="mx-auto flex min-h-[50vh] max-w-md flex-col justify-center">
<h1 className="text-2xl font-semibold text-text-primary">Single sign-on</h1>
<p className="mt-2 text-sm text-text-secondary">
{providerName
? `Redirecting you to ${providerName}...`
: 'Preparing your sign-in request...'}
</p>
{error ? (
<div
role="alert"
className="mt-6 rounded-lg border border-error/30 bg-error/10 px-4 py-3 text-sm text-error"
>
<p>{error}</p>
<Link
to="/login"
className="mt-3 inline-block font-medium text-blue-400 hover:text-blue-300"
>
Return to login
</Link>
</div>
) : (
<div className="mt-6 rounded-lg border border-surface-border bg-surface-elevated px-4 py-3 text-sm text-text-secondary">
If the redirect does not start automatically, return to the login page and try again.
</div>
)}
</div>
);
}
-9
View File
@@ -1,9 +0,0 @@
import type { ReactElement } from 'react';
export function Placeholder({ title }: { title: string }): ReactElement {
return (
<main className="flex min-h-screen items-center justify-center">
<h1 className="text-xl font-medium">{title}</h1>
</main>
);
}
-70
View File
@@ -1,70 +0,0 @@
import { isValidElement } from 'react';
import { describe, expect, it } from 'vitest';
import type { RouteObject } from 'react-router-dom';
import { routes } from '@/routes';
import { Placeholder } from '@/spa/placeholder';
import { ChatPage } from '@/spa/pages/chat';
function collectPaths(routeObjects: RouteObject[]): string[] {
return routeObjects.flatMap((route) => [
...(route.path ? [route.path] : []),
...(route.children ? collectPaths(route.children) : []),
]);
}
function findRoute(routeObjects: RouteObject[], path: string): RouteObject | undefined {
for (const route of routeObjects) {
if (route.path === path) return route;
const nested = route.children ? findRoute(route.children, path) : undefined;
if (nested) return nested;
}
return undefined;
}
describe('SPA route table', () => {
it('covers every v1 parity route from the Phase P RFC', () => {
expect(collectPaths(routes).sort()).toEqual(
[
'/',
'/admin',
'/auth/provider/:provider',
'/chat',
'/login',
'/projects',
'/projects/:id',
'/register',
'/settings',
'/tasks',
].sort(),
);
});
it('separates guest and authenticated route groups', () => {
const guestPaths = collectPaths(routes.at(0)?.children ?? []);
const authPaths = collectPaths(routes.at(1)?.children ?? []);
expect(guestPaths).toContain('/login');
expect(guestPaths).not.toContain('/chat');
expect(authPaths).toContain('/chat');
});
it.each(['/login', '/register', '/auth/provider/:provider'])(
'renders a real guest page instead of the P1 placeholder at %s',
(path) => {
const element = findRoute(routes, path)?.element;
expect(isValidElement(element)).toBe(true);
if (!isValidElement(element)) throw new Error(`Missing route element for ${path}`);
expect(element.type).not.toBe(Placeholder);
},
);
it('renders the real chat page instead of the P1 placeholder at /chat, inside the authenticated group', () => {
const authPaths = collectPaths(routes.at(1)?.children ?? []);
expect(authPaths).toContain('/chat');
const element = findRoute(routes, '/chat')?.element;
expect(isValidElement(element)).toBe(true);
if (!isValidElement(element)) throw new Error('Missing route element for /chat');
expect(element.type).not.toBe(Placeholder);
expect(element.type).toBe(ChatPage);
});
});
-14
View File
@@ -1,14 +0,0 @@
import { describe, expect, it } from 'vitest';
describe('Vitest abort-controller realm', () => {
it('provides a global signal accepted by Node native Request', () => {
const controller = new AbortController();
const request = new Request('https://mosaic.invalid/navigation', {
signal: controller.signal,
});
expect(request.signal).toBeInstanceOf(AbortSignal);
controller.abort();
expect(request.signal.aborted).toBe(true);
});
});
-23
View File
@@ -1,23 +0,0 @@
import { transferableAbortController } from 'node:util';
// jsdom installs realm-local abort constructors while Node's undici Request
// remains native. React Router passes a global AbortSignal to Request, so both
// constructors must come from Node's native realm during tests.
const nativeController = transferableAbortController();
const nativeAbortController = nativeController.constructor;
const nativeAbortSignal = nativeController.signal.constructor;
for (const target of [globalThis, window]) {
Object.defineProperties(target, {
AbortController: {
configurable: true,
writable: true,
value: nativeAbortController,
},
AbortSignal: {
configurable: true,
writable: true,
value: nativeAbortSignal,
},
});
}
-24
View File
@@ -1,24 +0,0 @@
import { fileURLToPath } from 'node:url';
import react from '@vitejs/plugin-react';
import { defineConfig } from 'vite';
// The proxy exists only in dev; in production the SPA is same-origin with the gateway
// (served by it under Candidate A, or behind one FQDN under Candidate B) and every
// request uses a relative path, so no origin may ever be configured here or in src/.
const gatewayTarget = 'http://localhost:14242';
export default defineConfig({
plugins: [react()],
resolve: {
alias: {
'@': fileURLToPath(new URL('./src', import.meta.url)),
},
},
server: {
port: 3100,
proxy: {
'/api': gatewayTarget,
'/socket.io': { target: gatewayTarget, ws: true },
},
},
});
-12
View File
@@ -1,21 +1,9 @@
import { fileURLToPath } from 'node:url';
import { defineConfig } from 'vitest/config';
export default defineConfig({
resolve: {
alias: {
'@': fileURLToPath(new URL('./src', import.meta.url)),
},
},
// tsconfig uses "jsx": "preserve" for Next; tests need esbuild to compile it
esbuild: {
jsx: 'automatic',
},
test: {
globals: true,
environment: 'jsdom',
setupFiles: ['./src/test/setup.ts'],
isolate: true,
exclude: ['e2e/**', 'node_modules/**'],
},
});
+4 -17
View File
@@ -10,8 +10,6 @@ COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
COPY apps/gateway/package.json ./apps/gateway/
COPY packages/ ./packages/
COPY plugins/ ./plugins/
# the root prepare script runs scripts/install-hooks.mjs on install
COPY scripts/ ./scripts/
RUN pnpm install --frozen-lockfile
COPY . .
# Build gateway and all of its workspace dependencies via turbo dependency graph
@@ -23,22 +21,11 @@ RUN pnpm --filter @mosaicstack/gateway --prod deploy --legacy /deploy
FROM base AS runner
WORKDIR /app
ENV NODE_ENV=production
# WorkspaceService shells out to git at runtime and roots workspaces at
# $MOSAIC_ROOT/.workspaces (apps/gateway/src/workspace/workspace.service.ts);
# mount a volume over /opt/mosaic to persist workspaces across container restarts.
# Intentionally unpinned: Alpine's signed repository is the trust anchor; pinning
# git was declined so routine base-image security updates remain maintainable.
RUN apk add --no-cache git \
&& mkdir -p /opt/mosaic/.workspaces \
&& chown -R node:node /opt/mosaic /app
ENV MOSAIC_ROOT=/opt/mosaic
# Use the pnpm deploy output — resolves all deps into a flat, self-contained node_modules
COPY --chown=node:node --from=builder /deploy/node_modules ./node_modules
COPY --chown=node:node --from=builder /deploy/package.json ./package.json
COPY --from=builder /deploy/node_modules ./node_modules
COPY --from=builder /deploy/package.json ./package.json
# dist is declared in package.json "files" so pnpm deploy copies it into /deploy;
# copy from builder explicitly as belt-and-suspenders
COPY --chown=node:node --from=builder /app/apps/gateway/dist ./dist
# gateway defaults to port 14242 (apps/gateway/src/main.ts)
EXPOSE 14242
USER node
COPY --from=builder /app/apps/gateway/dist ./dist
EXPOSE 4000
CMD ["node", "dist/main.js"]
+1 -3
View File
@@ -8,11 +8,9 @@ WORKDIR /app
COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
COPY apps/web/package.json ./apps/web/
COPY packages/ ./packages/
# the root prepare script runs scripts/install-hooks.mjs on install
COPY scripts/ ./scripts/
RUN pnpm install --frozen-lockfile
COPY . .
RUN pnpm --filter @mosaicstack/web build
RUN pnpm --filter @mosaic/web build
FROM base AS runner
WORKDIR /app
-23
View File
@@ -79,29 +79,6 @@ Jarvis (v0.2.0) is a self-hosted AI assistant with a Python FastAPI backend and
---
## Compaction Refresh Trust Lifecycle (M1, #827#830)
### Problem and objective
Context compaction, session replacement, and same-PID runtime reloads can leave a previously VERIFIED runtime lease attached to stale directives. M1 must revoke that authority mechanically for Claude (including Claudex) and Pi without trusting caller-asserted identity or forking the external broker state machine.
### Requirements
1. `CR-REQ-01`: Claude `PreCompact` and `SessionStart` with matcher `compact`, plus Pi `session_before_compact` and the first post-`session_compact` `context`, SHALL independently revoke the active broker lease.
2. `CR-REQ-02`: Runtime generation increases—including same-PID Pi reload/new/resume/fork and Claude resume/clear—SHALL monotonically replace the prior broker incarnation and inherit no VERIFIED lease.
3. `CR-REQ-03`: A fired observer that cannot confirm broker revocation SHALL fail closed through lifecycle cancellation, a private local generation fence, and/or a runtime-local tool latch. The existing all-tools broker gate remains authoritative.
4. `CR-REQ-04`: The lease TTL SHALL remain monotonic and capped at 300 seconds. If both observers are missed, within-TTL consequential actions remain allowed and after-TTL actions are denied. This named bounded residual stale window SHALL be documented without claiming a mutator-action bound inside the window.
5. `CR-REQ-05`: Hook descendants SHALL use the broker-minted session and owner-only current-generation state inherited from register-before-exec. Caller-minted sessions and parallel lease state machines remain forbidden.
### Acceptance criteria
1. `AC-CR-01`: Real-socket tests prove each Claude observer revokes, Pi lifecycle tests prove both observer paths, and Claudex isolated settings preserve and install the mandatory hooks.
2. `AC-CR-02`: A same-PID generation test proves the old generation is stale and the replacement generation is UNVERIFIED across reload/resume/fork-equivalent lifecycle events.
3. `AC-CR-03`: RED-first T12b/T30 evidence explicitly reports dual-hook miss within TTL as **ALLOWED** and after TTL as **DENIED**.
4. `AC-CR-04`: Attributable executable coverage is at least 85%, the full repository suite is green on deterministic main, and independent code/security review completes before merge.
---
## Fleet Declarative Configuration Management Workstream (FCM, #758)
### Problem and objective
+5 -26
View File
@@ -3,11 +3,9 @@
## Compaction refresh lease broker
- [Internal broker protocol](architecture/lease-broker-protocol.md) — kernel identity, ancestry and generation invariants, framed requests, responses, and persisted cycle bindings.
- [Broker operations](guides/lease-broker-operations.md) — protected paths, startup, constrained recovery, fail-closed posture, distinct-principal deployment, and residual risk.
- [Constrained recovery skill](../packages/mosaic/framework/skills/mosaic-context-refresh/SKILL.md) — source-resident thin wrapper, receipt scope, C4 replay boundary, and T-C middle-drop disclosure.
- [Broker operations](guides/lease-broker-operations.md) — protected paths, startup, fail-closed recovery posture, distinct-principal deployment, and residual risk.
- [Lease-broker security notes](architecture/lease-broker-security.md) — identity, whole-class authorization, threat boundaries, and coordinator review requirements.
- [Whole mutator-class gate](architecture/mutator-class-gate.md) — default-deny policy, revoke-first/promote-last state machine, TTL, runtime adapters, and T-B/T-C assurance boundary.
- [Compaction revocation lifecycle](architecture/compaction-revocation.md) — Claude/Pi observer matrix, same-PID generation rollover, failure fencing, and the named bounded residual stale window.
## CLI and skill management
@@ -16,24 +14,10 @@
## Fleet configuration management
- [Fleet configuration entry point](fleet/README.md) — desired-versus-observed decision tree and complete operator link map.
- [Desired, derived, and observed state](fleet/concepts/desired-vs-observed-state.md) — roster authority, generation, ownership, and drift.
- [Identity, class, and runtime](fleet/concepts/identity-class-runtime.md) — stable name, display alias, class, runtime, provider, and model separation.
- [Role authority and leases](fleet/concepts/role-authority-and-leases.md) — validator/merge-gate separation and bounded lease authority.
- [Generated launch chain](fleet/concepts/generated-env-launch-chain.md) — strict data parsing, precedence, and quarantine.
- [Roster v2 structural contract](fleet/reference/roster-v2-fields.md) — schema, supported values, required fields, defaults, and constraints.
- [Fleet CLI reference](fleet/reference/cli.md) — local desired-state commands, JSON/exit behavior, and gateway-catalog separation.
- [Lifecycle transitions](fleet/reference/lifecycle-transitions.md) — create/apply/reboot/migration/rollback boundaries.
- [Status and drift](fleet/reference/status-and-drift.md) — desired/managed/observed state and current/future classifications.
- [Safe agent CRUD](fleet/how-to/create-update-delete-agent.md) — expected generation, dry-run, and partial-failure recovery.
- [Local lifecycle operations](fleet/how-to/start-stop-restart.md) — persisted versus one-shot actions.
- [Configurable interaction instance](fleet/how-to/configure-tess-interaction.md) and [validator instance](fleet/how-to/configure-ultron-validator.md) — generic identities and protected limits.
- [Reconcile and recover](fleet/operations/reconcile-and-recover.md) — plan/apply lock and recovery behavior.
- [Environment quarantine](fleet/operations/env-quarantine.md) — private evidence and value-free diagnostics.
- [Systemd/tmux troubleshooting](fleet/operations/systemd-tmux-troubleshooting.md) — socket, holder, unmanaged-session, and lock decisions.
- [Backup/restore boundary](fleet/operations/backup-restore.md) and [upgrade-assets hold](fleet/operations/upgrade-assets.md).
- [v1-to-v2 migration preview](fleet/migration/v1-to-v2.md) and [executable artifact dispositions](fleet/migration/example-profile-disposition.md).
- [FCM M5 closure evidence](reports/documentation/758-fleet-config-ia-closure.md) and [approved deferrals](reports/deferred/758-fleet-config-deferrals.md).
- [Generated environment boundary](fleet/reference/generated-env-boundary.md) — roster-derived launch projection, strict local data, legacy quarantine, and downstream interface evidence.
- [Roster v2 structural contract](fleet/reference/roster-v2-fields.md) — local-tmux schema v2 parsing and structural validation.
- [Role classes and authority](fleet/reference/role-classes.md) — canonical role resolver and protected authority boundaries.
- [Executable asset dispositions](fleet/migration/example-profile-disposition.md) — shipped v1 fixture/profile/service validation posture.
## Official channel plugins
@@ -96,8 +80,3 @@
- [Logical identity and connector lease/fencing implementation](https://git.mosaicstack.dev/mosaicstack/stack/issues/755)
- [M1 logical identity and fencing architecture](architecture/mos-runtime-portability-m1.md)
- [M1 connector lease operations](guides/mos-connector-lease-operations.md)
## Comms evolution — Matrix-native MACP (design, draft)
- [RFC-001 — MACP: a Mosaic-native, Matrix-native comms layer](rfcs/RFC-001-MACP-MATRIX-NATIVE.md) — Synapse + Mosaic appservice backbone, MACP v1 protocol, presence/escalation, federation, strangler migration off the Hermes MCP bridge.
- [RFC-002 — Install, configuration & topology for the Matrix/MACP comms system](rfcs/RFC-002-INSTALL-CONFIG-TOPOLOGY.md) — open-source install topology modes, ACME cert provisioning, pluggable secret backend, and config precedence.
+14 -14
View File
@@ -52,20 +52,20 @@ Active workstream is **W1 — Federation v1**. Workers should:
> the repository quality gates, independent code and security review, terminal-green CI, and
> the applicable acceptance evidence before merge. Issue #758 remains open until M5 closes.
| id | status | description | issue | agent | repo | branch | depends_on | estimate | notes |
| ---------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | ------------- | ----------------- | --------------------------------------- | ---------------------------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FCM-M0-001 | done | Publish normative PRD requirements/acceptance criteria, this M0M5 DAG, docs-IA checklist, and legacy example/profile disposition inventory; no implementation changes | #758 | sonnet | mosaicstack/stack | `docs/758-fleet-config-management` | — | 18K | Merged via #760 (`c32d85a`); parent #758 intentionally remains open through M5 |
| FCM-M1-001 | done | Implement narrow local-tmux v2 roster structural contract/compiler with YAML/JSON canonicalization and schema/parser parity tests | #758 | coder0 | mosaicstack/stack | `feat/758-roster-v2-compiler` | FCM-M0-001 | 30K | #764 squash `aa5b43b`; exact-head RoR and PR/main terminal-green CI; no lifecycle or live mutation |
| FCM-M1-002 | done | Reuse existing profile/persona/provision resolver for roster semantics; add canonical class/authority validation and approved aliases | #758 | native-sonnet | mosaicstack/stack | `feat/758-shared-role-resolution` | FCM-M0-001 | 25K | #768 squash `a5e8e55`; shared resolver and canonical authority/alias validation delivered |
| FCM-M1-003 | done | Convert the M0 legacy inventory into executable example/profile/service-preset validation and explicit v1-version/retirement checks | #758 | codex | mosaicstack/stack | `test/758-example-profile-dispositions` | FCM-M1-001, FCM-M1-002 | 20K | #770 squash `e9c4aa3`; shipped artifact disposition validation delivered |
| FCM-M2-001 | done | Migrate generic launch chain to deterministic `.env.generated` plus strict data-only `.env.local`; quarantine forbidden legacy keys | #758 | codex | mosaicstack/stack | `feat/758-generated-env-boundary` | FCM-M1-001, FCM-M1-002 | 30K | #772 squash `191efae`; generated/local boundary and private quarantine delivered |
| FCM-M2-002 | done | Add generation-guarded local fleet agent create/get/update/delete mutations with plan/dry-run, atomic roster writes, and recovery output | #758 | codex | mosaicstack/stack | `feat/758-fleet-agent-crud` | FCM-M1-001, FCM-M2-001 | 30K | #773 squash `bc5e736`; generation-guarded atomic CRUD and recovery contracts delivered |
| FCM-M3-001 | done | Implement local roster-owned reconcile/apply plus lifecycle/status/verify/doctor contracts and stable JSON/exit codes | #758 | codex | mosaicstack/stack | `feat/758-local-reconciler` | FCM-M2-001, FCM-M2-002 | 35K | #785 squash `4990905`; exact roster-owned systemd/tmux reconcile and lifecycle contracts delivered |
| FCM-M3-002 | in-progress | Add isolated systemd/tmux lifecycle, drift, socket, unmanaged-session, crash, and rollback acceptance coverage | #758 | sonnet | mosaicstack/stack | `test/758-reconciler-lifecycle-gates` | FCM-M3-001 | 25K | Canonical v2 named-socket + legacy-v1 default-server boundaries; fake adapters/temp fixtures only |
| FCM-M4-001 | done | Implement field-complete v1-to-v2 inventory/preview/migrator with alias, lifecycle, env-quarantine, and remote/connector disposition evidence | #758 | codex | mosaicstack/stack | `feat/758-v1-v2-migrator` | FCM-M1-003, FCM-M3-001 | 35K | PR #788; final head `d63bb0206a1d312ab8352ec1d3ca3631146b0baa`; tree `4da210da9a71b035130d4160a4a2e691bdfde2da`; squash `9745bc3f29c26b021a478b7ad03cfb494f6c9de3`; descendant-main pipeline 1855 terminal success |
| FCM-M4-002 | not-started | Add reversible canary migration, rollback, stale-projection/orphan classification, and current-host 9-managed/3-unmanaged fixture coverage | #758 | sonnet | mosaicstack/stack | `test/758-migration-rollback-gates` | FCM-M4-001, FCM-M3-002 | 25K | HOLD: never starts a previously stopped agent or kills an unproven unmanaged session; not authorized by FCM-M5-001 |
| FCM-M5-001 | done | Deliver the accepted fleet documentation IA, how-to/operations/migration references, and link/example validation | #758 | haiku | mosaicstack/stack | `docs/758-fleet-config-operator-docs` | FCM-M1-003, FCM-M2-002, FCM-M3-001, FCM-M4-001 | 24K | #789 content squash 627cf2bb; de-flake repair PR#851/#849 squash 77c9a826; completion proof wp1937 @aa999daf push/ci step 49632 recovery_runtime_unittest.py 3/3 OK (closes wp1932 step 49576 Errno111) |
| FCM-M5-002 | not-started | Package/update asset-drift checks, rolling local canary, independent validation certificate, and release evidence | #758 | sonnet | mosaicstack/stack | `feat/758-fleet-config-release-gate` | FCM-M3-002, FCM-M4-002, FCM-M5-001 | 30K | HOLD: final #758 gate; quality, independent code/security review, validator certificate, merge-gate approval, and green CI remain out of M5-001 |
| id | status | description | issue | agent | repo | branch | depends_on | estimate | notes |
| ---------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | ------------- | ----------------- | --------------------------------------- | ---------------------------------------------- | -------- | ---------------------------------------------------------------------------------------------------------------- |
| FCM-M0-001 | done | Publish normative PRD requirements/acceptance criteria, this M0M5 DAG, docs-IA checklist, and legacy example/profile disposition inventory; no implementation changes | #758 | sonnet | mosaicstack/stack | `docs/758-fleet-config-management` | — | 18K | Merged via #760 (`c32d85a`); parent #758 intentionally remains open through M5 |
| FCM-M1-001 | done | Implement narrow local-tmux v2 roster structural contract/compiler with YAML/JSON canonicalization and schema/parser parity tests | #758 | coder0 | mosaicstack/stack | `feat/758-roster-v2-compiler` | FCM-M0-001 | 30K | #764 squash `aa5b43b`; exact-head RoR and PR/main terminal-green CI; no lifecycle or live mutation |
| FCM-M1-002 | done | Reuse existing profile/persona/provision resolver for roster semantics; add canonical class/authority validation and approved aliases | #758 | native-sonnet | mosaicstack/stack | `feat/758-shared-role-resolution` | FCM-M0-001 | 25K | #768 squash `a5e8e55`; shared resolver and canonical authority/alias validation delivered |
| FCM-M1-003 | done | Convert the M0 legacy inventory into executable example/profile/service-preset validation and explicit v1-version/retirement checks | #758 | codex | mosaicstack/stack | `test/758-example-profile-dispositions` | FCM-M1-001, FCM-M1-002 | 20K | #770 squash `e9c4aa3`; shipped artifact disposition validation delivered |
| FCM-M2-001 | done | Migrate generic launch chain to deterministic `.env.generated` plus strict data-only `.env.local`; quarantine forbidden legacy keys | #758 | codex | mosaicstack/stack | `feat/758-generated-env-boundary` | FCM-M1-001, FCM-M1-002 | 30K | #772 squash `191efae`; generated/local boundary and private quarantine delivered |
| FCM-M2-002 | done | Add generation-guarded local fleet agent create/get/update/delete mutations with plan/dry-run, atomic roster writes, and recovery output | #758 | codex | mosaicstack/stack | `feat/758-fleet-agent-crud` | FCM-M1-001, FCM-M2-001 | 30K | #773 squash `bc5e736`; generation-guarded atomic CRUD and recovery contracts delivered |
| FCM-M3-001 | done | Implement local roster-owned reconcile/apply plus lifecycle/status/verify/doctor contracts and stable JSON/exit codes | #758 | codex | mosaicstack/stack | `feat/758-local-reconciler` | FCM-M2-001, FCM-M2-002 | 35K | #785 squash `4990905`; exact roster-owned systemd/tmux reconcile and lifecycle contracts delivered |
| FCM-M3-002 | in-progress | Add isolated systemd/tmux lifecycle, drift, socket, unmanaged-session, crash, and rollback acceptance coverage | #758 | sonnet | mosaicstack/stack | `test/758-reconciler-lifecycle-gates` | FCM-M3-001 | 25K | Canonical v2 named-socket + legacy-v1 default-server boundaries; fake adapters/temp fixtures only |
| FCM-M4-001 | not-started | Implement field-complete v1-to-v2 inventory/preview/migrator with alias, lifecycle, env-quarantine, and remote/connector disposition evidence | #758 | codex | mosaicstack/stack | `feat/758-v1-v2-migrator` | FCM-M1-003, FCM-M3-001 | 35K | Preview first; no unreviewed lifecycle inference |
| FCM-M4-002 | not-started | Add reversible canary migration, rollback, stale-projection/orphan classification, and current-host 9-managed/3-unmanaged fixture coverage | #758 | sonnet | mosaicstack/stack | `test/758-migration-rollback-gates` | FCM-M4-001, FCM-M3-002 | 25K | Never starts a previously stopped agent or kills an unproven unmanaged session |
| FCM-M5-001 | not-started | Deliver the accepted fleet documentation IA, how-to/operations/migration references, and link/example validation | #758 | haiku | mosaicstack/stack | `docs/758-fleet-config-operator-docs` | FCM-M1-003, FCM-M2-002, FCM-M3-001, FCM-M4-001 | 24K | Must close every checklist item or record an approved deferral |
| FCM-M5-002 | not-started | Package/update asset-drift checks, rolling local canary, independent validation certificate, and release evidence | #758 | sonnet | mosaicstack/stack | `feat/758-fleet-config-release-gate` | FCM-M3-002, FCM-M4-002, FCM-M5-001 | 30K | Final #758 gate: quality, independent code/security review, validator certificate, merge-gate approval, green CI |
## Thin-core prompt diet (#528) — feat/contract-thin-core
@@ -1,59 +0,0 @@
# Compaction observer revocation and runtime generations
WI-3 connects Claude and Pi compaction/session lifecycle events to the existing authenticated lease-broker state machine. It does not add a second lease store or let runtime hooks assert identity. Each observer inherits the broker-minted session, resolves the current private runtime generation, and sends the existing `revoke_lease` action over the authenticated Unix socket.
## Observer matrix
| Runtime | Lifecycle signal | Action |
| ---------------- | ---------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| Claude / Claudex | `PreCompact` | Revoke the current lease before compaction. A non-zero hook result blocks the lifecycle transition. |
| Claude / Claudex | `SessionStart` with matcher `compact` | Revoke again after compacted context starts. |
| Claude / Claudex | `SessionStart` with matcher `resume\|clear` | Atomically advance the private generation, then revoke the replacement incarnation. |
| Pi | `session_before_compact` | Revoke before compaction; return `{ cancel: true }` if revocation cannot be confirmed. |
| Pi | `session_compact` then the first `context` | Arm and run an independent post-compaction revoke. A failed post observer blocks later tools locally until a retry succeeds. |
| Pi | `session_start` with reason `reload`, `new`, `resume`, or `fork` | Atomically advance the private generation, then revoke the replacement incarnation before reuse. |
The first observer that reaches the broker deletes pending promotion tokens and makes the lease `UNVERIFIED`. The second compaction observer is deliberate redundancy, not a prerequisite for the first. Claudex receives the same mandatory hooks in its isolated `CLAUDE_CONFIG_DIR`; hook merging preserves unrelated isolated settings and rejects malformed or symlinked settings fail-closed.
## Private generation authority
`launch-runtime.py` still registers before `exec`, preserving the kernel-authenticated PID/starttime anchor. It now also creates `generation-<broker-session>.state` beside the broker socket. The file is owner-only mode `0600` under the broker's mode-`0700` directory. Hook descendants read that file instead of relying only on an immutable inherited environment value.
Generation changes use an exclusive file lock, validate owner/type/mode/size, increment monotonically, truncate and write the complete new value, and `fsync` before contacting the broker. Therefore reload, new-session, resume, and fork events may retain the same PID/starttime while still becoming a new broker incarnation. The higher generation causes the broker to atomically discard prior tokens and lease authority; the replacement generation inherits no VERIFIED lease.
If an observer fires while broker transport is unavailable, `revoke-lease.py` advances the private generation as a local fence before returning non-zero. Every later all-tools gate reads that higher value. When the broker is reachable again, authentication of that value performs the same old-generation revocation before authorization. Pi also keeps a process-local post-compaction/rollover failure latch that blocks tool calls. An unsafe or unreadable generation file itself makes both lifecycle revocation and tool authorization fail closed.
## Threat contract and stopping boundary
### BOUNDED RESIDUAL STALE WINDOW
If **both** pre- and post-compaction observers are missed entirely, no revocation signal exists. During the remaining unexpired lease, **within-TTL consequential actions are allowed**. Their count and timing are **bounded by lease expiry, not by the mutator gate**. WI-3 makes no claim that it bounds mutator actions inside this stale interval. The broker's monotonic lease TTL is capped at 300 seconds; after expiry, the next consequential tool is denied with `LEASE_EXPIRED`.
This is the named D2-v5 T-A residual. It is distinct from an observer that fires but cannot contact the broker: the latter creates a local generation fence and fails closed. It is also distinct from T-C total rot, where the lifecycle observers and the all-tools gate are both absent or replaced. Server-side branch protection, required CI, and independent review remain the irreducible backstop for T-C.
| Condition | Result |
| --------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
| Either compaction observer succeeds | Existing lease and pending promotion tokens are revoked immediately. |
| Observer runs but broker confirmation fails | Lifecycle transition is denied where supported; local generation fence and runtime latch prevent inherited authority. |
| Both observers are missed, lease unexpired | **ALLOWED** inside the bounded residual stale window. No within-window mutator bound is claimed. |
| Both observers are missed, lease expired | **DENIED** by monotonic TTL expiry. |
| Generation advances on reload/new/resume/fork | Prior incarnation revoked; replacement starts `UNVERIFIED`. |
| Lifecycle observers and all-tools gate both fail or are removed | T-C total-hook-miss residual; protected-branch controls remain required. |
## T-C server-side branch-protection posture
The required posture is that `main` is push-blocked and PR-only-merge is **MANDATORY**, regardless
of client-gate state. The client-side gate narrows the exposure window only; it is not the T-C
guarantee. The server-side protected-branch configuration is the irreducible guarantee for protected
repository actions. Status-check enforcement and approval enforcement are **RECOMMENDED**.
## Current-vs-required gap (recorded, not enacted)
The current empirical configuration is recorded here without re-probing or mutating live branch
protection. `enable_push=False` (push-block present), so the mandatory push-block/PR-only-merge core
holds. `require_approvals=0` (approvals not enforced), `enable_status_check=False` (status checks not
enforced), and `block_on_official_review=False` (official review not enforced). Those recommended
merge-quality controls are the current gap; changing them is a separate, owner-gated operations
decision and is not enacted by this documentation change.
The permanent T12b/T30 acceptance case prints both required outcomes: dual-hook miss within TTL is **ALLOWED**, and the same lease after TTL is **DENIED**. Separate real-socket tests prove each Claude observer and same-PID generation rollover; Pi lifecycle tests exercise pre/post observers, all four replacement reasons, and local failure closure.
+3 -14
View File
@@ -13,23 +13,12 @@ Each connection carries exactly one UTF-8 JSON object followed by one newline, c
- `mint_token`: authenticated identity plus `binding` containing exactly `compaction_epoch`, `request_epoch`, `h_source`, `h_payload`, and `schema_version`.
- `consume_token`: authenticated identity plus `token`.
- `begin_verification`: authenticated identity, runtime (`claude` or `pi`), cycle `binding`, and a TTL no greater than 300 seconds. The broker revokes existing authority first, enters `PENDING_VERIFICATION`, and returns a single-use promotion token.
- `begin_recovery`: the constrained recovery entrypoint. It rejects caller-provided receipt/challenge fields and delegates to the same `begin_verification` transition, but reports `PENDING_DELIVERY` and marks the volatile cycle as recovery-owned.
- `complete_recovery`: authenticated identity only. It rejects caller-provided receipt/challenge fields, obtains the current recovery challenge only from broker state, and delegates to the same trusted-observer → evidence → consume → promote sequence. An observation failure revokes recovery authority; retry starts a fresh challenge.
The daemon owns a second protected production observer socket (mode `0600`) unless a private `--test-observer-file` fixture is selected. That transport accepts only the exact `record_runtime_observation` schema after kernel `SO_PEERCRED` plus the existing anchor/ancestry authentication; it validates the pending runtime/generation before storing one finalized assistant entry for the in-process `RuntimeReceiptObserver`. It is **not** a broker request action. Claude sends its latest assistant entry from the Stop-hook transport; Pi sends only finalized `message_end` assistant content. The public broker socket continues to reject request-supplied `latest_assistant_message` in begin, observe, and complete paths.
- `promote_lease`: authenticated identity plus the exact pending promotion token. The broker commits token consumption before making `VERIFIED` visible.
- `revoke_lease`: authenticated observer signal; deletes pending tokens and makes the session `UNVERIFIED` immediately. WI-3 Claude/Pi hooks send this existing action; `runtime` and bounded `reason` fields are diagnostic input only and never identity authority.
- `revoke_lease`: authenticated observer signal; deletes pending tokens and makes the session `UNVERIFIED` immediately.
- `authorize_tool`: authenticated identity, runtime, and exact runtime-reported tool name. The broker returns an explicit allow/deny decision from the whole-class policy and current lease.
A higher generation for the same anchor atomically replaces the stored incarnation and deletes all prior tokens and lease authority for that session. A lower generation is stale. Runtime descendants resolve the current generation from an owner-only, locked generation file created by the register-before-exec launcher; reload/new/resume/fork observers advance and `fsync` it before broker revocation. This supports generation replacement even when PID/starttime do not change. Tokens are 256-bit values from the operating-system cryptographic RNG and are single use. At most 256 pending tokens may be persisted; another mint fails with `TOKEN_CAPACITY` before mutation. Successful consumption deletes the token, while a replay still fails with `TOKEN_REPLAY`. Live v1 token records retain the existing `consumed: false` schema.
A higher generation for the same anchor atomically replaces the stored incarnation and deletes all prior tokens and lease authority for that session. A lower generation is stale. Tokens are 256-bit values from the operating-system cryptographic RNG and are single use. At most 256 pending tokens may be persisted; another mint fails with `TOKEN_CAPACITY` before mutation. Successful consumption deletes the token, while a replay still fails with `TOKEN_REPLAY`. Live v1 token records retain the existing `consumed: false` schema.
VERIFIED leases are volatile and monotonic-time bounded: broker restart, generation change, explicit observer revocation, or expiry returns the session to `UNVERIFIED`. `begin_verification` always revokes before minting a new prerequisite. `begin_recovery` reuses that exact transition and mints a new challenge, so a normal-path receipt/challenge cannot be replayed through recovery. `promote_lease` is valid only from the matching pending cycle; persistence failure rolls token and lease state back, while post-rename durability uncertainty terminates the broker. The WI-1 token is the atomic promotion prerequisite substrate.
## Receipt boundary and T-C residual (R1)
Receipt evidence is a T-A delivery/liveness prerequisite only; it cannot replace the mechanical
mutator gate as safety authority. The receipt detects an **ABSENT** or **PREFIX-TRUNCATED** terminal
token. A **MIDDLE-DROP** that preserves the tail is a T-C contract violation that is **NOT receipt-detectable**. It is covered by server-side protected-branch controls, **NOT** by the receipt; no category-wide receipt-detection claim is made for that tail-preserving transformation.
VERIFIED leases are volatile and monotonic-time bounded: broker restart, generation change, explicit observer revocation, or expiry returns the session to `UNVERIFIED`. `begin_verification` always revokes before minting a new prerequisite. `promote_lease` is valid only from the matching pending cycle; persistence failure rolls token and lease state back, while post-rename durability uncertainty terminates the broker. The WI-1 token is the atomic promotion prerequisite substrate. A later receipt implementation must satisfy that prerequisite but cannot replace the mechanical mutator gate as safety authority.
State replacement serializes and enforces the 4 MiB maximum before opening a temporary file, then uses a mode-`0600` temporary file, `fsync`, atomic rename, and parent-directory `fsync`. Every broker mutation snapshots the prior v1 state. A commit failure before rename restores that snapshot and leaves durable state unchanged. A failure after rename makes durability uncertain, so the store is poisoned without rolling memory back and the daemon terminates rather than serving with divergent state. Existing state is opened without following symlinks, must be a bounded regular file at mode `0600`, and is fully schema- and invariant-validated before use. Persisted tokens must be unconsumed, match their session's current generation, and remain within the 256-token cap. Session identity is uniquely keyed by `(anchor_pid,anchor_starttime)`; duplicate logical sessions for one anchor refuse startup. State integrity or mode failures refuse startup. The daemon does not log session IDs or tokens.
+2 -14
View File
@@ -2,25 +2,13 @@
- Trusted identity comes only from Linux `SO_PEERCRED` plus `/proc` starttime, never request identity fields.
- Descendant authorization is anchored to `(pid,starttime)` and uses a complete second starttime pass to fail closed on disappearance or PID-reuse races.
- Runtime generations are monotonic per anchor; a bump revokes prior-incarnation tokens before persistence commits. WI-3 stores the live generation in an owner-only locked file so same-PID Pi reload/new/resume/fork and Claude resume/clear transitions cannot inherit a VERIFIED lease.
- Runtime generations are monotonic per anchor; a bump revokes prior-incarnation tokens before persistence commits.
- Session IDs and cycle tokens use the OS cryptographic RNG. `Math.random` and model output are not token sources.
- Framing and persistence failures fail closed. Sensitive tokens are not logged.
- Built-in `0700`/`0600` filesystem modes provide same-principal hardening only, not socket authenticity against the same UID. WI-1 provides no distinct-principal isolation. That stronger deployment requires an external protected proxy, ACL, or service boundary, and the boundary must preserve authenticated client identity for the broker's `SO_PEERCRED` and ancestry authorization rather than substituting a shared proxy identity.
- WI-2 whole-class authorization denies every consequential, unknown, and custom tool while UNVERIFIED; it does not inspect shell strings or trust wrapper selection. First-class Claude/Pi, both Claudex dispatch modes, PRDY, QA remediation, coord, orchestrator, and fleet starts converge on broker register-before-exec; Claudex additionally installs the mandatory all-tools hook inside its preserved isolated config and fails closed on unsafe settings.
- The permanent `check-runtime-launches.py` suite/CI guard scans production source for direct literal, absolute-path, process-API, command-array, and dynamic Claude/Pi launches. It has no bypass allowlist: an unrecognized launch form fails CI until routed through the common boundary.
- WI-2 promotion consumes a WI-1 cycle token before VERIFIED becomes visible. Observer revocation, runtime-generation replacement, broker restart, and monotonic TTL expiry remove authority.
- WI-3 wires redundant Claude `PreCompact`/`SessionStart(compact)` and Pi `session_before_compact`/post-`session_compact` `context` observers to that same revoke action. If broker confirmation fails after an observer fires, the revoker advances the private generation as a local fence; subsequent authorization revokes the stale broker incarnation before any consequential allow.
- Dual observer absence while a lease remains live is the named **bounded residual stale window**: consequential tools remain allowed until monotonic expiry, with no claimed within-window action bound. After expiry they are denied. Total observer-plus-gate absence remains T-C.
- Receipt observation, payload construction, and constrained recovery implementation remain later surfaces. A receipt can become a promotion prerequisite but is never the safety mechanism.
## Named residual: promote-lease-lost-ACK (WI-3 D2-v5)
A valid `promote_lease` can leave a session `VERIFIED` in the broker while the client never learns of it. This is a named, bounded D2-v5 T-A residual — an **authority-observability divergence, not an authority divergence, not an ALLOW-risk, and not a retry double-apply**. It is disclosed here, not laundered.
**Window — where it can occur.** The broker commits token consumption and durable `VERIFIED` state _before_ the success reply becomes visible (see the promotion order in `lease-broker-protocol.md`). The residual is confined to the interval after that commit+fsync when the broker→client reply or peer-ACK is lost — for example an extreme-contention send failure or peer disconnect after `handle()` has already mutated and persisted state (the #838 fail-closed transport path). The lease mutation is already durable broker-side; only the acknowledgement to the client is lost. No uncommitted or partially-applied state is involved: the commit either happened (and is authoritative) or it did not (and no lease exists).
**Fail-safe direction — the client can only under-claim.** Broker intent is the ceiling; client authority is always ≤ broker intent, never more. Client-side authority-belief is granted only by a _received_ acknowledgement; a lost acknowledgement conveys nothing, so the client cannot conclude "verified" and continues to treat itself as `UNVERIFIED` (it re-verifies or recovers). If the client retries `promote_lease` with the same token, the token is already consumed and the broker rejects the retry (`PROMOTION_TOKEN_MISMATCH` / `INVALID_LEASE_TRANSITION`); there is no double-apply. The committed `VERIFIED` state the broker holds is authority the lease _legitimately earned_ from a real promotion — the broker authorizing consequential tools under it is correct, not inflation. Divergence is therefore strictly toward _less_ client authority than the broker granted; it never produces authority the broker did not grant.
**Bound — TTL plus the observer/gen-bump revoke backstop, self-healing.** The orphaned `VERIFIED` lease is indistinguishable to the broker from any other legitimately verified lease, so the identical D2-v5 revocation backstops dispose of it: any compaction observer (`PreCompact` / `SessionStart(compact)` for Claude; `session_before_compact` / post-`session_compact` `context` for Pi), any same-PID runtime-generation bump (reload/new/resume/fork), broker restart, or monotonic-time expiry returns the session to `UNVERIFIED`. Monotonic TTL expiry (capped at 300 seconds) is **unconditional** — it requires no observer at all — so the maximum exposure of the orphaned lease is one TTL, ≤ 300 s, after which the next consequential tool is denied with `LEASE_EXPIRED`. Any observer that fires shortens the window further. The residual self-heals: "≥1 observer fires OR expiry ⇒ revoke" catches the lost-ACK lease on the same terms as every other stale lease. As with the dual-observer-miss stale window, WI-3 makes no claim that the mutator gate bounds actions inside the residual interval; the interval is bounded by TTL and the revoke backstop, and the server-side branch-protection / required-CI / independent-review line remains the irreducible backstop for protected-repository mutations.
- Receipt observation, payload construction, compaction observers, and constrained recovery implementation remain later surfaces. A receipt can become a promotion prerequisite but is never the safety mechanism.
Coordinator security review must rerun the real socket/peercred and mutator-gate acceptance suites on an unrestricted Linux runner and obtain the mandated independent Opus-SECREV review before integration.
+2 -2
View File
@@ -21,13 +21,13 @@ The authenticated broker is the sole lease writer:
3. Token consumption commits before the volatile lease becomes VERIFIED. Promotion is last and cannot be reached directly from UNVERIFIED.
4. `revoke_lease`, a runtime-generation increase, broker restart, or monotonic expiry removes mutator authority.
The initial TTL is capped at the ratified 300-second maximum. A caller may request a shorter positive TTL but cannot lengthen the maximum. WI-3 installs the [compaction observer and generation lifecycle](compaction-revocation.md). Dual compaction-hook miss within an unexpired lease remains the ratified bounded T-A residual: consequential tools are allowed until expiry, with no claimed within-window action bound; once either observer revokes or TTL expires, the next consequential tool is denied.
The initial TTL is capped at the ratified 300-second maximum. A caller may request a shorter positive TTL but cannot lengthen the maximum. Dual compaction-hook miss within an unexpired lease remains the ratified bounded T-A residual; once either observer revokes or TTL expires, the next consequential tool is denied.
A receipt is only a future promotion prerequisite. It is not an obedience, residency, or safety proof and never replaces this mechanical gate.
## Runtime adapters
`launch-runtime.py` registers itself with the broker and then `exec`s Claude or Pi so PID/starttime remain the authenticated parent anchor. It exports the broker-minted session ID and an owner-only generation-file reference to descendants; lifecycle hooks advance that file for same-PID replacement generations.
`launch-runtime.py` registers itself with the broker and then `exec`s Claude or Pi so PID/starttime remain the authenticated parent anchor. It exports only the broker-minted session ID and current generation to descendants.
- Claude installs `mutator-gate.py` as an all-tools (`.*`) `PreToolUse` hook.
- `mosaic claudex` and `mosaic yolo claudex` preserve their isolated `CLAUDE_CONFIG_DIR`, merge the mandatory hook into that isolated `settings.json`, and use the same register-before-exec launcher. Malformed or symlinked isolated settings deny launch.
@@ -0,0 +1,109 @@
# Gate0 Charter Amendment — Probe-3 (D4) Evidence-Class EXECUTION Authorization
**Status:** DRAFT (revision 2) — supersedes prior candidate pin `8fca5b7a`; pending Mos re-scope-verify BEFORE
re-pin is ratified. Revised per Mos adjudication directive (2026-07-18): §3 = D4-focused Option A; §1 = explicit binding model.
**Amendment type:** Additive durable-authority amendment (does NOT mutate any ratified pinned doc in place).
**Milestone:** 188 — Compaction-Refresh Mechanism · **Issue:** Gitea #827 (WI-0 Gate0) · gates WI-3 #830 merge.
---
## 1. Authorized source (why this amendment is valid)
Per the Mosaic governance principle (OpenBrain `f0cb61b6`, permanent; fail-closed / DO-178C): a durable
Gate0 execution-hold clears ONLY by **(i) explicit user (owner) authorization** OR **(ii) a durable-authority
amendment from an authorized source**. A runtime coordinator's verbal GO does NOT qualify.
- **Owner authorization (i):** Jason (owner / north-star) directed in `#mos` **2026-07-18 17:28Z** — *"amend the
charter"* (option **B** from the WI-3 escalation), quoting the escalation back. This is the direct-user
authorization artifact that homelab's durable-Gate0 objection (2026-07-18 06:34:56Z) explicitly named as a
valid resolution condition (*"user artifact OR auth amendment"*). Relayed + authenticity-adjudicated by Mos
(`web1:mos-claude`). Owner outranks any peer-lane durable authority.
- **Amendment (ii):** this document, authorized BY that owner directive.
Both qualifying conditions are therefore satisfied. Homelab's stated condition is met by the owner artifact;
homelab is NOTIFIED as a transparency step (it holds durable-Gate0 standing and raised the original catch),
but its co-sign is not a gate (owner > peer).
**Binding model (explicit — how this SHA is authorized).** The authority binding for this amendment's pinned
bytes is the composition of two distinct acts:
1. **Owner class-authorization (PRE-SHA):** Jason (owner) authorized the *class of action* — "amend the
charter" (option B), `#mos` 2026-07-18 17:28Z. This occurred **before** these amendment bytes (and hence
this SHA256) existed; the owner authorized the amendment, not a specific hash.
2. **Independent-adjudicator byte-verification:** Mos (`web1:mos-claude`), acting as the independent
adjudicator (author ≠ verifier — MS-LEAD authored, Mos verifies), scope-verifies the **exact bytes** of
this document and confirms they express only the owner-authorized narrow scope.
There is therefore **NO single "Jason-signs-the-SHA" artifact, and none is required** under this binding
model: owner-authorized-class + independent-adjudicator-byte-verify **is** the binding. This is the durable,
inspectable chain of custody for the pin.
## 2. Charter provisions amended (sha-pinned, unmutated)
This amendment attaches to — and does NOT rewrite — the ratified Gate0 charter provisions:
- `compaction-refresh-BUILD-BRIEF.md` §5 / R4 "Gate0 = BUILD-ADMISSION GATE", specifically the item:
*"Same-PID `runtime_generation` bump on reload/resume/fork revokes prior lease (D4)."*
sha256 `89fdbc27ed0e5050dc7b52f3ef2ddaea691edf17fd89d51b15e26fb5ed47171b` (intact/unchanged).
- `compaction-refresh-SPEC-RATIFICATION.md` R4.
sha256 `bac58319c9c4028b5b40e1129e0033cdb5a6b7b02033c25f06f4cb77d7779c67` (intact/unchanged).
The two pinned docs remain byte-identical; this amendment is the delta of record.
## 3. What is authorized (NARROW — D4-focused harness ONLY)
Adjudicator ruling (Mos, `web1:mos-claude`): "D4-only" against the existing runner is non-executable — the
only runner (`pi_gate0_run.py`) drives P2+P5+P6+D4 in one flow, and D4 intrinsically requires a
promoted-to-VERIFIED baseline (spec L219: "P3 immediately follows the valid P2 promotion so reload must
revoke a genuinely VERIFIED prior gen") to revoke a genuine prior generation. Therefore authorize EXACTLY the
minimal executable form (Option A) required as WI-3 (#830) merge-gate (2):
- **D4-focused harness:** spawns **ONLY** `p3_generation_broker.py` (not the full `pi_gate0_run.py` runner).
- **Minimal promotion-to-VERIFIED, as a FIXTURE PRECONDITION ONLY:** established solely so the D4 revoke has a
genuine `VERIFIED` target. This is **NOT** authorization to bank P2 as an independent evidence class.
- **D4 same-PID `runtime_generation`-bump revoke observation:** new generation → `MUTATOR_UNVERIFIED`;
prior (superseded) generation → `STALE_GENERATION`.
- **Explicitly EXCLUDED:** P5 (missing / oversize / hash-invalidation) and P6 (atomic-observation) — not
needed for the WI-3 D4 gate and **not authorized** by this amendment.
- **Isolation / integrity (per §4/§5):** 3× repeated, isolated runs; hardened deterministic harness;
non-destructive; launches broker/socket/state artifacts in an isolated fixture ONLY; **does NOT touch
production**, mutates no live lease/broker/deployment, creates no durable side effect outside the fixture;
a **FAIL** returns to planner — no retry-launder.
**Intrinsic-precondition boundary (verbatim):** the promotion step is a D4 test fixture, not a P2
evidence-gathering authorization; P5/P6 remain unauthorized.
## 4. What is NOT authorized (all other holds remain in force)
- This is **NOT** a blanket Gate0-execution release. Every other Gate0 execution item and every standing
execution hold remains exactly as-is.
- No live mutation, migration, canary, deployment, systemd, tmux-fleet, or connector/socket/Hermes action is
authorized by this amendment.
- Authorizes producing THIS evidence class once (3× isolation is the evidence-integrity requirement, not a
license to re-run on failure): a **FAIL** returns to planner — **no retry-launder**, no severity-laundering.
## 5. Preserved fail-closed / DO-178C invariants (verbatim, unchanged)
- Producing probe evidence **EXECUTES** the Gate0 mechanism (launches processes, creates socket/state
artifacts, exercises revocation transitions); "isolated + non-destructive" does **not** make it
non-execution. This amendment authorizes that execution for the narrow class in §3 — it does not redefine
execution as non-execution.
- A sha-pinned DURABLE authority OUTRANKS a runtime coordinator's verbal GO; when they conflict the durable
artifact wins. This amendment derives its authority from the OWNER, not from a coordinator.
- Card-advancement gates and execution-holds are distinct; this amendment lifts ONLY the §3 execution-hold,
not any advancement/review/SECREV gate. WI-3's independent-review + Opus-SECREV + green-suite gates stand.
## 6. Effect on WI-3 (#830) merge chain
On this amendment being pinned (Mos-verified + Jason-shown): a fresh lane (ms-rev-826) executes the §3
probe-3 evidence class (3× isolation) → PASS/FAIL reported to Mos. **On PASS**, and only after re-confirming
WI-3 head `f4008307` UNMOVED + FIRE-PRECONDITION-0 (fresh `mosaic-context-refresh` attestation for
mosaic-100 + planner-opus), the existing chain runs: CI queue-guard → push → PR → mirror RoR → relay full-40
head + pr/ci# → Mos independent 6-check → squash `closes #830` → chain WI-4→7. **On FAIL**: planner-return.
---
**Amendment author:** MS-LEAD (`web1:mosaic-100`), Gate0 governance interface / charter custodian.
**Pin protocol:** this file's sha256 becomes the amendment pin ONLY after Mos re-scope-verify. Reported to Mos
before any ratification/publication, per the transparency checkpoint on a durable-authority change. Ratification
and durable publication (to a homelab-inspectable provider ref) are the adjudicator's (Mos), NOT the author's
(MS-LEAD) — the author does not self-ratify and does not publish.
@@ -0,0 +1,49 @@
# Gate0 Probe-3 Amendment — Owner Transparency Window (durable record)
**Purpose.** Durable evidence (defined duration + closure) that the owner-transparency window on the
probe-3 amendment **scope-correction** has a bounded, inspectable lifecycle — per homelab's GATE-A
requirement (2026-07-18 18:13:14Z). This is NOT the owner's core authorization (that is durable in the
amendment §1); it is the objection-window on the narrowing disclosed afterward.
## What was disclosed
The owner (Jason) explicitly authorized the amendment **class** — "amend the charter" (option B),
`#mos` 2026-07-18 17:28Z (amendment §1). My initial narrowing was "D4-only"; on adjudication that proved
non-executable (D4 intrinsically needs a promoted-to-VERIFIED baseline). The **corrected** scope
(rev 2, pin `9ac9ff87`, §3) adds a *minimal promotion-to-VERIFIED as a test fixture only* (P5/P6 still
excluded, P2 not banked as evidence). Because this adds a fixture step beyond the "D4-only" I first told
the owner, I disclosed the correction to him for transparency.
## Window (bounded, durable)
- **Opened:** 2026-07-18T18:00:25Z — anchored to the adjudicator's Discord scope-correction disclosure to the
owner (message id `1528099140100296736`, snowflake-decoded; not an informal estimate).
- **Duration:** 2 hours (defined).
- **Scheduled closure:** 2026-07-18T20:00:25Z.
- **Closure condition (fail-closed):**
- No owner objection received by scheduled closure → window **CLOSED-CLEAR** (the disclosed correction
stands; it is within the already-granted class authorization).
- Any owner objection before closure → window does **NOT** clear → re-adjudicate the corrected scope.
- An affirmative owner "proceed" before closure → **early CLOSED-CLEAR** (recorded here).
## Closure attestation
Closure will be confirmed by a dated adjudicator tick appended below (and to the orchestration ledger)
at/after 2026-07-18T20:00:25Z. Until that attestation exists, GATE A is OPEN and probe-3 execution stays HELD.
- [x] **CLOSED-CLEAR attestation — recorded 2026-07-18T20:08Z by adjudicator Mos (`web1:mos-claude`).**
### CLOSED-CLEAR attestation (2026-07-18T20:08Z)
The owner-transparency window on the probe-3 amendment scope-correction is **CLOSED-CLEAR**.
- **Scheduled closure:** 2026-07-18T20:00:25Z — reached (authoritative UTC at attestation: 2026-07-18T20:07Z, past closure).
- **Closure condition met:** *No owner objection received by scheduled closure.* Verified fail-closed against the
**durable Discord #mos record** (not memory): the channel's last message is the scope-correction disclosure itself
(`id 1528099140100296736`, 2026-07-18T18:00:25.709Z). From window-open (18:00:25Z) through closure (20:00:25Z) and
to this attestation, there are **zero owner (jetrich) messages** — no objection, no affirmative early-GO. The last
owner message preceding the window was the class authorization *"Amend the charter"* (17:28Z, amendment §1).
- **Effect:** the disclosed corrected scope (rev 2, pin `9ac9ff87`, §3 — minimal promotion-to-VERIFIED as a D4 test
fixture only; P5/P6 excluded; P2 not banked as evidence) **stands**, within the already-granted class authorization.
- **GATE A is now CLOSED.** Probe-3 execution proceeds ONLY under the full remaining chain: GATE-B fresh §3-review PASS
(concurred @839d156f, author≠reviewer) + adjudicator explicit FIRE GO. No other Gate0 hold is lifted by this tick.
*Adjudicator: Mos (`web1:mos-claude`). This record is durable and provider-inspectable alongside the
amendment (`9ac9ff87`) and its RATIFICATION.md.*
@@ -0,0 +1,37 @@
# Gate0 Probe-3 (D4) Amendment — Adjudicator Ratification Record
**Ratifies pin:** `9ac9ff873fad41a6e15763cc89cb94d0bc4a6b0cf9b6770561d1781b03f63276`
(`GATE0-PROBE3-EXEC-AMENDMENT.md`, 7699 bytes, this branch).
**Supersedes:** prior candidate pin `8fca5b7a` (never executed against; withdrawn on scope + durability grounds).
## Re-scope-verify — PASSED
Verified by **Mos (`web1:mos-claude`)**, acting as independent adjudicator (author ≠ verifier: MS-LEAD
authored, Mos verified), 2026-07-18. SHA256 recomputed = pin (exact). Scope checks, all PASS:
- §3 = Option A, D4-focused: harness spawns ONLY `p3_generation_broker.py`; minimal promotion-to-VERIFIED
is a FIXTURE PRECONDITION only (not P2 evidence-banking); D4 gen-bump revoke observation
(new→`MUTATOR_UNVERIFIED`, prior→`STALE_GENERATION`); **P5/P6 explicitly excluded + unauthorized**;
verbatim intrinsic-precondition boundary line present.
- §1 binding model explicit; §2 charter provisions pinned unmutated; §4/§5 invariants intact.
- No scope creep beyond the owner-authorized narrow class.
## Authority binding
- **Owner class-authorization (PRE-SHA):** Jason (owner) — "amend the charter" (option B), `#mos`
2026-07-18 17:28Z. Authorized the amendment class before these bytes existed.
- **Independent-adjudicator byte-verification:** Mos scope-verified the exact bytes.
- No single "Jason-signs-the-SHA" artifact exists or is required under this binding model.
## Round-trip integrity (this branch/commit)
All three files fetched back via the Gitea raw API and SHA-matched (each > 200B, no not-found sentinel):
- `GATE0-PROBE3-EXEC-AMENDMENT.md``9ac9ff87…f63276`
- `charter-BUILD-BRIEF.md``89fdbc27…71b`
- `charter-SPEC-RATIFICATION.md``bac58319…67`
## Status: RATIFIED — probe-3 execution remains HELD
Publication here closes the governance-infra gap (the charter provisions were previously local-only,
not inspectable). Probe-3 execution stays HELD pending both: (1) homelab independent verification of
these published bytes; (2) owner transparency window. On both clearing → ms-rev-826 builds + runs the
§3 D4-focused harness (3× isolation, non-destructive) → PASS/FAIL to Mos → WI-3 (#830) chain per §6.
*Note: the amendment file's own status line reads "DRAFT (revision 2)"; that internal text is
superseded by THIS external ratification record (the pinned bytes are deliberately not edited, so the
SHA stays stable). Ratification status lives here, not in the pinned artifact.*
@@ -0,0 +1,106 @@
# Compaction-Refresh Mechanism — BUILD BRIEF (Mos → MS-LEAD)
**Status:** STAGED — do NOT dispatch until PR #826 (#824 skill-CLI bridge) MERGES. Mos routes this to
MS-LEAD at #824 land. PLAN phase COMPLETE + RATIFIED; this is the BUILD-execution brief.
**Routed by:** Mos (main orchestrator). **Owner:** MS-LEAD (mosaic-100). **Runtime scope M1:** Claude + Pi.
## 1. AUTHORITY (sha256-pinned — build AGAINST these, do not re-derive)
| Artifact | Path | SHA-256 |
|---|---|---|
| **Ratification record (SSOT)** | `~/agent-work/reviews/compaction-refresh-SPEC-RATIFICATION.md` | `bac58319c9c4028b5b40e1129e0033cdb5a6b7b02033c25f06f4cb77d7779c67` |
| Ratified SPEC v5 | `~/agent-work/reviews/compaction-refresh-SPEC-v5.md` | `a6d07ade835758e8488ca10d3b0631caf0beb93ea3a6733631f151b0c2f01433` |
| sol FINAL red-team (GO) | `~/agent-work/reviews/compaction-refresh-SPEC-v5-redteam-sol.md` | `3da326a4ea91767b731e128a93b13194e8002358101e30de3fcb8ca2f8f54faa` |
The coder MUST verify these hashes before building. The in-context working spec is DERIVED and
compaction-fragile — the sha256'd records above are the recovery SSOT (durable-authority discipline).
## 2. TARGET & SCOPE
- **Framework-native `packages/mosaic/…`** in `mosaicstack/stack`. NOT jarvis-brain. NOT
`~/.config/mosaic/` directly (that tree is WIPED on framework upgrade — durable home is SOURCE).
- **M1 = Claude + Pi orchestrators only.** Codex/other runtimes = scope-note only.
- **Hard dependency (now satisfied at dispatch):** the `mosaic skill` register/list + install/upgrade
symlink auto-sync (#824 / PR #826) — so the durable `mosaic-context-refresh` skill ships REACHABLE
(auto-symlinked into `~/.claude/skills/`). Do not dispatch before #826 merges.
## 3. DELIVERABLES (locked architecture — from the ratification record; do NOT redesign)
1. **Authenticated external lease broker** bound to kernel `SO_PEERCRED` `(pid, starttime,
runtime_generation)` — the only unforgeable identity on a same-uid tmux fleet. Broker **MINTS** the
logical `session_id` at first peercred contact (NEVER caller-asserted). Distinct-principal /
protected socket.
2. **Whole mutator-class gate** (not per-wrapper): no consequential mutator succeeds without a valid
VERIFIED lease. **Revoke-first / promote-last.**
3. **Compaction observers → revoke:** Claude `PreCompact` + `SessionStart(matcher=compact)`; Pi
`session_before_compact`/`context` equivalents. Any `runtime_generation` bump (reload/resume/fork,
same PID included) auto-revokes the prior incarnation.
4. **Verbatim-hashed normative fragments:** `B_payload` (exact fragments + deterministic metadata) and
`H_payload = SHA256(domain_sep ‖ length_framed(B_payload))` — NO self-reference (byte-identical
across the Claude and Pi builders).
5. **Receipt-challenge protocol (promotion prerequisite, NOT the safety mechanism):** broker mints a
single-use `receipt_challenge` per cycle bound to `(session_id, runtime_generation,
compaction_epoch, request_epoch, H_source, H_payload, schema_version)`. **COMPUTE = broker**
(observes latest-assistant message, computes the binding incl `H(latest-assistant-message)`);
**COPY = model** (verbatim copy of challenge + `H_payload` — an LLM cannot hash its own output;
T29). Observed in the EXACT latest assistant message (Claude: latest assistant entry + pending
challenge, NO transcript grep; Pi: `message_end`, NOT `after_provider_response`). Single-use,
consumed before the tool batch. Broker transition order (mandatory): `revoke → build
B_payload/H_payload → PENDING_DELIVERY(mint unique challenge) → deliver → observe exact receipt →
evidence commit → consume challenge → promote VERIFIED (last)`.
6. **Constrained recovery command** = the single ungated mutator; the `mosaic-context-refresh` skill
is its wrapper (uses a newly-minted challenge + identical protocol; cannot replay normal-path
receipt). Durable skill lands here, symlink-reachable via #824.
7. **T-C server-side line = branch protection** (the irreducible guarantee; client gate is
window-narrowing only). If ops-config rather than code, DOCUMENT the required posture explicitly.
## 4. BINDING BUILD CONDITIONS R1R6 (MANDATORY — verbatim from ratification record)
- **R1 (honesty):** state that the receipt detects ABSENT or PREFIX-TRUNCATED terminal token, but a
MIDDLE-DROP preserving the tail is a **T-C contract violation, NOT receipt-detectable** (covered by
server-side). No over-claim.
- **R2 (atomicity):** evidence-commit → consume-challenge → promote-VERIFIED is ONE atomic broker
transaction; a crash leaves neither VERIFIED-with-live-challenge nor consumed-with-ambiguous-promote;
recovery mints a NEW challenge, never reuses.
- **R3 (parsing):** exact single current-cycle receipt parse — no unbounded grep; reject
quoted/tool-output receipts, wrong generation/epoch, unknown/stale challenge, multiple receipts.
- **R4 (Gate0 = BUILD-ADMISSION GATE):** see §5 — runtime evidence BEFORE build admission; a failed
Gate0 item RETURNS the design to planner review, it is NOT waived by the GO.
- **R5 (TTL):** 300 s MAX lease TTL + soak-tighten; soak may only SHORTEN, never lengthen. Mos-accepted.
- **R6 (receipt semantics):** receipt = T-A delivery/liveness ONLY, never obedience/safety/residency.
Permanent invariant.
## 5. R4 GATE0 — RUNTIME EVIDENCE BEFORE BUILD ADMISSION (WI-0, do this FIRST)
Structure the build like gitwatch: **WI-0 is a Gate0 runtime-evidence probe; no feature build admitted
until every item produces POSITIVE runtime evidence** (not a design assertion). A failed item RETURNS
to planner — do not paper over:
- Launcher `exec`/parent topology + supported-hook ancestry (D1); broker authenticates the launcher
chain, rejects sibling-substitution.
- Pi lifecycle: last-position invariant (last-or-closed), per-tool nonce → tool-call-id map (D5).
- Same-PID `runtime_generation` bump on reload/resume/fork revokes prior lease (D4).
- Broker socket authenticity posture (protected / distinct-principal); `SO_PEERCRED` returns the true
`(pid, starttime)`.
- Source-invalidation fail-closed (missing/oversize/hash-mismatch fragment → no promotion).
- Claude `additionalContext` + Pi `context` inject atomically (A-v5-1) — the transport assumption
T27 rests on; verify or class the gap T-C.
## 6. ACCEPTANCE TESTS (red-first TDD)
Carry all v4 ACs + T12b; add **T24T30**: T24 hash-construction no-self-reference byte-identical across
builders · T25 replay rejected · T26 transcript-stale-match cannot promote · T27 partial-delivery
(prefix-trunc/tail-only/middle-drop/malformed) none promote · T28 single-use (no renew/reopen) · T29
model copies not computes · T30 dual-hook-miss matches AMENDED threat table within+after TTL.
Acceptance = full green suite + Gate0 evidence pack.
## 7. REVIEW & MERGE DISCIPLINE
- **This IS an Opus-SECREV-mandatory surface** — UNLIKE #824 (local same-uid FS). The broker is an
authentication/identity/authorization mechanism (peercred binding, session_id minting, mutator-class
gating, receipt protocol). Security review = **Opus-SECREV, no GPT/terra substitute** on the
broker/gate/receipt/socket surfaces. Functional/non-security parts may take GPT review.
- **Author ≠ reviewer**, independent review, no self-merge, exact-head RoR (reviewed-SHA=merged-SHA),
`closes #<issue>` close-keyword, full 40-char head. Never edit tests to pass / never force-merge red
/ never `--no-verify`.
- **Mos merges** (per ratification record) after Opus-SECREV + independent review pass + green suite +
Gate0 pack. Decompose into work-items (WI-0 Gate0 first); likely a milestone, not one monolithic PR.
## 8. SEQUENCING
#826 (#824 bridge) MERGES → Mos routes this brief → MS-LEAD decomposes (WI-0 Gate0 first) → build M1
(Claude+Pi) → Gate0 evidence pack (failed item → planner) → Opus-SECREV + independent review → Mos
merges → durable `mosaic-context-refresh` skill lands symlink-reachable → jarvis-brain `CLAUDE.md`
mandate PR aligns to the shipped receipt/hash contract. Interim skill + CLAUDE.md mandate stay LIVE
until the mechanism ships.
@@ -0,0 +1,75 @@
# Compaction-Refresh Mechanism — SPEC RATIFICATION RECORD
**Ratifier:** Mos (main fleet orchestrator, `mos-claude`)
**Date:** 2026-07-17 ~22:2xZ
**Decision:** ✅ **RATIFIED — GO WITH BINDING CONDITIONS R1R6.** Architecture converged v1→v5 via
oppositional adversarial planning (planner-opus authors / planner-sol red-teams). No v6 required.
## Authenticated authority artifacts (sha256-pinned)
| Artifact | Path | SHA-256 |
|---|---|---|
| Ratified SPEC v5 | `~/agent-work/reviews/compaction-refresh-SPEC-v5.md` | `a6d07ade835758e8488ca10d3b0631caf0beb93ea3a6733631f151b0c2f01433` |
| sol FINAL red-team (GO) | `~/agent-work/reviews/compaction-refresh-SPEC-v5-redteam-sol.md` | `3da326a4ea91767b731e128a93b13194e8002358101e30de3fcb8ca2f8f54faa` |
| (base) SPEC v4 | `~/agent-work/reviews/compaction-refresh-SPEC-v4.md` | `a5e9c261a613974fc0d853d69ad76f616f5f1c3b6b63a436daecdd15b4a72b80` |
| (base) sol v4 red-team | `~/agent-work/reviews/compaction-refresh-SPEC-v4-redteam-sol.md` | `1e76ee5942241d9520b9ff8f39a628488578ec2d9b91cc09b9f0e7cc6091ef2f` |
| Ratification-Input (R1-R6 + rulings, provenance-clean) | `~/agent-work/reviews/compaction-refresh-SPEC-RATIFICATION-INPUT.md` | `d01411a5c966f513e992a941deef0ff5cc6f29d37adab97ea2fbd3c5e6aef266` |
## Convergence trail
v1 NO-GO (9 architectural) → v2 NO-GO (7 enforcement, arch accepted) → v3 NO-GO (5 surgical, arch
locked) → v4 NO-GO (narrow; echo-lock narrowing APPROVED) → **v5 GO-with-conditions**.
## Locked architecture (do not redesign)
Authenticated external **lease broker** bound to kernel `SO_PEERCRED` (pid, starttime,
runtime_generation) — the only unforgeable identity fact on a same-uid tmux fleet. Broker MINTS the
logical session_id at first peercred contact (never caller-asserted). **Revoke-first / promote-last.**
Whole **mutator-class gate** (not per-wrapper). Verbatim-hashed normative fragments. Single
**constrained recovery command** = the only ungated mutator; the `mosaic-context-refresh` skill is its
wrapper. **Threat tiers:** T-A honest-stale → client gate · T-B compromised-tool → mutator-class · T-C
fully-rotted → **server-side branch-protection = the irreducible line** (client gate is
window-narrowing, NOT a complete guarantee).
**Delivery-receipt (echo-lock, sol §8-final):** broker mints a single-use `receipt_challenge` per
cycle bound to (session, runtime_generation, epochs, H_source, H_payload); **COMPUTE = broker**
(observes + computes the full binding incl H(latest-assistant-message) as the cycle-audit fact),
**COPY = model** (copies challenge + H_payload verbatim — model never computes a hash; sol T29
copy-not-compute preserved). Receipt is a **one-cycle T-A delivery/liveness proof ONLY — never an
obedience, residency, or safety proof.** The mechanical mutator-class gate remains THE safety
mechanism; §8 intact for T-B/T-C.
## Binding ratification conditions (R1R6) — MANDATORY for build acceptance
- **R1 (honesty / T27 amendment):** state honestly that the receipt detects an ABSENT or
PREFIX-TRUNCATED terminal token, but a MIDDLE-DROP that preserves the tail token is a **T-C
contract violation, NOT receipt-detectable** (covered by server-side, not the receipt). No
over-claim. Fold as a doc amendment — no v6.
- **R2 (atomicity):** evidence-commit → consume-challenge → promote-VERIFIED is ONE atomic broker
transaction. A crash leaves NEITHER a VERIFIED-with-live-challenge NOR a
consumed-with-ambiguous-promotion state; recovery mints a **NEW** challenge, never reuses one.
- **R3 (parsing):** exact single current-cycle receipt parse — no unbounded grep; reject
quoted/tool-output receipts, wrong generation/epoch, unknown/stale challenge, and multiple receipts.
- **R4 (Gate0 runtime evidence — BUILD-ADMISSION GATE):** launcher-ancestry/D1,
sibling-substitution rejection, Pi last-or-closed, same-PID runtime_generation bump,
nonce→tool-call-id map, socket/authenticity posture, and source-invalidation fail-closed require
**runtime Gate0 evidence BEFORE build admission**, not design assertion. **A failed Gate0 item
RETURNS the design to planner review — it is NOT waived by this GO.**
- **R5 (TTL — RATIFIER ACCEPTED):** proposed **300s MAX lease TTL + soak-tighten** is **ACCEPTED by
Mos (ratifier)**. Safe-direction default: soak data may only SHORTEN it, never lengthen. Operator
(Jason) may tighten at will; flagged for operator awareness, non-blocking (not an escalation
trigger — a proposed max that only tightens).
- **R6 (receipt semantics — REAFFIRMED):** receipt remains T-A delivery/liveness ONLY, never
obedience/safety proof. Reaffirmed as a permanent invariant of the design.
## Build sequencing (PLAN-ONLY until these clear)
1. **HARD DEP:** `mosaic skill` register/unregister/list + generic install/upgrade symlink auto-sync
(mosaicstack/stack **#824**, in flight on ms-824) MUST land first — else the durable
`mosaic-context-refresh` skill ships unreachable (no `~/.claude/skills/` bridge symlink).
2. Then MS-LEAD builds the mechanism in **packages/mosaic** (M1 = Claude + Pi orchestrators) against
THIS ratified spec + R1R6, producing R4 Gate0 evidence. Author≠reviewer independent review; no
self-merge; Mos merges.
3. The durable `mosaic-context-refresh` skill (+ jarvis-brain CLAUDE.md mandate PR) lands aligned to
the ratified receipt/hash contract, AFTER the #824 bridge exists.
**Interim protection (live now, until the mechanism ships):** `mosaic-context-refresh` skill
(fail-closed 7-line residency attestation) + jarvis-brain CLAUDE.md "Directive Freshness After
Compaction" mandate — self-run manual re-read + attestation. Symlink hand-created this session; loads
and attests 7/7.
@@ -1,228 +0,0 @@
#!/usr/bin/env python3
"""P5 Gate0 replay probe; BUILT ONLY, execution is Mos-gated.
Run only under fresh-executor authorization:
python3 -I -S -B docs/compaction-refresh/probes/p5_receipt_replay.py
Each of the default three isolated runs launches the shipped lease-broker daemon
in a distinct private temporary directory. This driver never changes broker
state directly and does not replace the promote gate: every transition is sent
over the daemon's real Unix socket. It proves the shipped order is
PENDING_DELIVERY -> observe/evidence commit -> consume -> VERIFIED and that a
consumed challenge cannot be replayed or reopen/renew its lease.
"""
from __future__ import annotations
import argparse
import base64
import importlib.util
import json
import os
import shutil
import socket
import subprocess
import sys
import tempfile
import time
from pathlib import Path
HERE = Path(__file__).resolve().parent
REPOSITORY = HERE.parents[2]
TOOLS = REPOSITORY / "packages/mosaic/framework/tools/lease-broker"
DAEMON = TOOLS / "daemon.py"
FRAGMENTS = TOOLS / "normative_fragments.py"
def load_shipped_fragments():
if not FRAGMENTS.is_file():
raise RuntimeError(f"shipped normative construction missing: {FRAGMENTS}")
spec = importlib.util.spec_from_file_location("p5_shipped_normative_fragments", FRAGMENTS)
if spec is None or spec.loader is None:
raise RuntimeError("unable to load shipped normative construction")
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
def request(socket_path: Path, value: dict[str, object]) -> dict[str, object]:
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as connection:
connection.settimeout(3.0)
connection.connect(str(socket_path))
connection.sendall((json.dumps(value, separators=(",", ":")) + "\n").encode())
connection.shutdown(socket.SHUT_WR)
response = bytearray()
while True:
chunk = connection.recv(4096)
if not chunk:
break
response.extend(chunk)
if not response.endswith(b"\n") or response.count(b"\n") != 1:
raise AssertionError(f"unframed broker reply: {bytes(response)!r}")
parsed = json.loads(response[:-1])
if not isinstance(parsed, dict):
raise AssertionError(f"non-object broker reply: {parsed!r}")
return parsed
def wait_ready(process: subprocess.Popen[str], socket_path: Path) -> None:
deadline = time.monotonic() + 5.0
while time.monotonic() < deadline:
if socket_path.exists():
return
if process.poll() is not None:
output = process.stdout.read() if process.stdout is not None else ""
raise RuntimeError(f"shipped daemon exited before READY: {output}")
time.sleep(0.02)
raise TimeoutError("shipped daemon did not create private probe socket")
def expect_refused(reply: dict[str, object], code: str) -> None:
if reply != {"ok": False, "code": code}:
raise AssertionError(f"expected refusal {code}, got {reply!r}")
def run_once(index: int) -> str:
fragments = load_shipped_fragments()
root = Path(tempfile.mkdtemp(prefix=f"mosaic-p5-replay-{index}-"))
os.chmod(root, 0o700)
socket_path = root / "broker.sock"
state_path = root / "state.json"
observer_path = root / "test-observer.json"
process = subprocess.Popen(
[
sys.executable, "-I", "-S", "-B", str(DAEMON), "--socket", str(socket_path),
"--state", str(state_path), "--test-observer-file", str(observer_path),
],
stdin=subprocess.DEVNULL,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
text=True,
)
try:
wait_ready(process, socket_path)
registered = request(socket_path, {"action": "register_anchor", "runtime_generation": 1})
if registered.get("ok") is not True or not isinstance(registered.get("session_id"), str):
raise AssertionError(f"registration failed: {registered!r}")
session_id = registered["session_id"]
construction = fragments.build_payload(
manifest_version=1,
generator_version="p5-replay-probe",
fragments=[
fragments.NormativeFragment(
"authority/probe",
b"P5 shipped transition driver\n",
"63537df1a6cb0d80195a96757ab11d629e5b5e1f23be167218b84cb195b1c1d6",
),
],
)
if construction.injectionDecision != "ACCEPTED" or not construction.promotion:
raise AssertionError("shipped normative construction refused P5 fixture")
binding = {
"compaction_epoch": index,
"request_epoch": index + 100,
"h_source": construction.h_source,
"h_payload": construction.h_payload,
"schema_version": 1,
}
construction_request = {
"manifest_version": 1,
"generator_version": "p5-replay-probe",
"fragments": [{
"source_id": "authority/probe",
"content_base64": base64.b64encode(b"P5 shipped transition driver\n").decode("ascii"),
"expected_sha256": "63537df1a6cb0d80195a96757ab11d629e5b5e1f23be167218b84cb195b1c1d6",
}],
}
pending = request(socket_path, {
"action": "begin_verification",
"session_id": session_id,
"runtime_generation": 1,
"runtime": "pi",
"binding": binding,
"construction": construction_request,
})
if pending.get("ok") is not True or pending.get("state") != "PENDING_VERIFICATION":
raise AssertionError(f"shipped pending-delivery transition failed: {pending!r}")
challenge = pending.get("receipt_challenge")
receipt = pending.get("receipt")
if not isinstance(challenge, str) or not isinstance(receipt, str):
raise AssertionError(f"shipped broker did not mint a receipt challenge: {pending!r}")
# Promotion before observation/evidence/consumption is forbidden.
expect_refused(request(socket_path, {
"action": "promote_lease",
"session_id": session_id,
"runtime_generation": 1,
"receipt_challenge": challenge,
}), "INVALID_LEASE_TRANSITION")
observer_path.write_text(json.dumps({
"session_id": session_id,
"runtime_generation": 1,
"latest_assistant_message": receipt,
}), encoding="utf-8")
os.chmod(observer_path, 0o600)
observed = request(socket_path, {
"action": "observe_receipt",
"session_id": session_id,
"runtime_generation": 1,
"receipt_challenge": challenge,
})
if observed.get("ok") is not True or observed.get("state") != "PENDING_PROMOTION":
raise AssertionError(f"shipped evidence transition failed: {observed!r}")
durable = json.loads(state_path.read_text(encoding="utf-8"))
evidence = durable["tokens"][challenge].get("evidence")
if not isinstance(evidence, dict) or not isinstance(evidence.get("h_latest_assistant"), str):
raise AssertionError("shipped receipt evidence was not committed before consume/promote")
promoted = request(socket_path, {
"action": "promote_lease",
"session_id": session_id,
"runtime_generation": 1,
"receipt_challenge": challenge,
})
if promoted.get("ok") is not True or promoted.get("state") != "VERIFIED":
raise AssertionError(f"shipped consume-before-promote transition failed: {promoted!r}")
# T25/T28: the actual consumed challenge, re-presented through the
# shipped daemon, can neither be observed again nor re-promote/reopen.
expect_refused(request(socket_path, {
"action": "observe_receipt",
"session_id": session_id,
"runtime_generation": 1,
"receipt_challenge": challenge,
}), "RECEIPT_REPLAY")
expect_refused(request(socket_path, {
"action": "promote_lease",
"session_id": session_id,
"runtime_generation": 1,
"receipt_challenge": challenge,
}), "RECEIPT_REPLAY")
return challenge
finally:
if process.poll() is None:
process.terminate()
try:
process.wait(timeout=3.0)
except subprocess.TimeoutExpired:
process.kill()
process.wait()
shutil.rmtree(root, ignore_errors=True)
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--runs", type=int, default=3)
arguments = parser.parse_args()
if arguments.runs != 3:
raise SystemExit("P5 requires exactly three isolated runs")
challenges = [run_once(index) for index in range(arguments.runs)]
if len(set(challenges)) != arguments.runs:
raise AssertionError("separate shipped cycles did not mint unique challenges")
print("P5 receipt replay probe PASS: 3 isolated shipped-daemon runs")
if __name__ == "__main__":
main()
@@ -1,255 +0,0 @@
#!/usr/bin/env python3
"""P6 constrained-recovery probe; BUILT ONLY and Mos-gated.
DO NOT self-fire. Under Mos authorization only:
python3 -I -S -B docs/compaction-refresh/probes/p6_constrained_recovery.py
The default three isolated runs launch the shipped daemon plus its production
observer transport on private sockets. The driver invokes the shipped recovery
command and adapter gate identity; it never resets broker state, mocks promote,
or taps a live model-output stream.
"""
from __future__ import annotations
import argparse
import base64
import hashlib
import importlib.util
import json
import os
import shutil
import socket
import subprocess
import sys
import tempfile
import time
from pathlib import Path
HERE = Path(__file__).resolve().parent
REPOSITORY = HERE.parents[2]
TOOLS = REPOSITORY / "packages/mosaic/framework/tools/lease-broker"
DAEMON = TOOLS / "daemon.py"
GATE = TOOLS / "mutator-gate.py"
RECOVERY_COMMAND = TOOLS / "recover-context.py"
OBSERVER_CLIENT = TOOLS / "receipt-observer-client.py"
FRAGMENTS = TOOLS / "normative_fragments.py"
CLAUDE_SETTINGS = REPOSITORY / "packages/mosaic/framework/runtime/claude/settings.json"
PI_EXTENSION = REPOSITORY / "packages/mosaic/framework/runtime/pi/mosaic-extension.ts"
def load_shipped_fragments():
spec = importlib.util.spec_from_file_location("p6_shipped_fragments", FRAGMENTS)
if spec is None or spec.loader is None:
raise RuntimeError("shipped normative construction unavailable")
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
def request(socket_path: Path, value: dict[str, object]) -> dict[str, object]:
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as connection:
connection.settimeout(3.0)
connection.connect(str(socket_path))
connection.sendall((json.dumps(value, separators=(",", ":")) + "\n").encode())
connection.shutdown(socket.SHUT_WR)
response = bytearray()
while True:
chunk = connection.recv(4096)
if not chunk:
break
response.extend(chunk)
if not response.endswith(b"\n") or response.count(b"\n") != 1:
raise AssertionError(f"unframed broker reply: {bytes(response)!r}")
reply = json.loads(response[:-1])
if not isinstance(reply, dict):
raise AssertionError("broker reply is not an object")
return reply
def wait_ready(process: subprocess.Popen[str], socket_path: Path) -> None:
deadline = time.monotonic() + 5.0
while time.monotonic() < deadline:
if socket_path.exists():
return
if process.poll() is not None:
output = process.stdout.read() if process.stdout is not None else ""
raise RuntimeError(f"shipped daemon exited before READY: {output}")
time.sleep(0.02)
raise TimeoutError("shipped daemon did not create private probe socket")
def run_json(command: list[str], environment: dict[str, str], input_value: object | None = None) -> dict[str, object]:
completed = subprocess.run(
command,
input=None if input_value is None else json.dumps(input_value),
text=True,
capture_output=True,
env=environment,
check=False,
)
if not completed.stdout.endswith("\n"):
raise AssertionError(f"command omitted framed result: {completed.stderr!r}")
reply = json.loads(completed.stdout)
if not isinstance(reply, dict):
raise AssertionError("command result is not an object")
return reply
def gate_recovery(runtime: str, phase: str, environment: dict[str, str]) -> None:
command = [sys.executable, "-I", "-S", "-B", str(GATE), "--runtime", runtime]
if runtime == "claude":
command.extend(["--recovery-command", str(RECOVERY_COMMAND)])
recovery_invocation = (
f"python3 {RECOVERY_COMMAND} begin --construction /tmp/p6.json "
"--compaction-epoch 1 --request-epoch 1"
if phase == "begin"
else f"python3 {RECOVERY_COMMAND} complete"
)
value = {"tool_name": "Bash", "tool_input": {"command": recovery_invocation}}
else:
value = {"tool_name": "mosaic_context_recover"}
completed = subprocess.run(command, input=json.dumps(value), text=True, capture_output=True, env=environment, check=False)
if completed.returncode != 0:
raise AssertionError(f"{runtime} recovery invocation remained gated: {completed.stderr!r}")
def record_production_observation(runtime: str, message: str, root: Path, environment: dict[str, str]) -> None:
command = [sys.executable, "-I", "-S", "-B", str(OBSERVER_CLIENT), "--runtime", runtime]
if runtime == "claude":
transcript = root / "claude-transcript.jsonl"
transcript.write_text(json.dumps({"message": {"role": "assistant", "content": message}}) + "\n", encoding="utf-8")
payload = {"transcript_path": str(transcript)}
command.append("--latest-entry")
else:
payload = {"latest_assistant_message": message}
completed = subprocess.run(command, input=json.dumps(payload), text=True, capture_output=True, env=environment, check=False)
if completed.returncode != 0:
raise AssertionError(f"{runtime} production observer transport refused: {completed.stderr!r}")
def run_once(index: int, runtime: str) -> None:
# Parity guard: drive the shipped command and the repaired adapter/observer
# bytes, not a shadow receipt or promotion implementation.
recovery_source = RECOVERY_COMMAND.read_text(encoding="utf-8")
if '"action": "begin_recovery"' not in recovery_source or '"action": "complete_recovery"' not in recovery_source:
raise AssertionError("P6 parity guard: recovery command no longer drives shipped broker entrypoints")
gate_source = GATE.read_text(encoding="utf-8")
if "--recovery-command" not in CLAUDE_SETTINGS.read_text(encoding="utf-8"):
raise AssertionError("P6 parity guard: Claude recovery mapping is missing")
if "_SHELL_ACTIVE" not in gate_source or "argv[1] != str(recovery_command)" not in gate_source:
raise AssertionError("P6 parity guard: Claude mapping is not literal-only")
if "const RECOVERY_TOOL = 'mosaic_context_recover'" not in PI_EXTENSION.read_text(encoding="utf-8"):
raise AssertionError("P6 parity guard: Pi recovery tool mapping is missing")
fragments = load_shipped_fragments()
root = Path(tempfile.mkdtemp(prefix=f"mosaic-p6-recovery-{index}-"))
os.chmod(root, 0o700)
socket_path = root / "broker.sock"
observer_socket = root / "observer.sock"
state_path = root / "state.json"
construction_path = root / "construction.json"
content = b"P6 constrained recovery fixture\n"
construction = {
"manifest_version": 1,
"generator_version": "p6-constrained-recovery",
"fragments": [{
"source_id": "authority/p6",
"content_base64": base64.b64encode(content).decode("ascii"),
"expected_sha256": hashlib.sha256(content).hexdigest(),
}],
}
construction_path.write_text(json.dumps(construction), encoding="utf-8")
os.chmod(construction_path, 0o600)
process = subprocess.Popen(
[sys.executable, "-I", "-S", "-B", str(DAEMON), "--socket", str(socket_path),
"--state", str(state_path), "--observer-socket", str(observer_socket)],
stdin=subprocess.DEVNULL,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
text=True,
)
try:
wait_ready(process, socket_path)
registered = request(socket_path, {"action": "register_anchor", "runtime_generation": 1})
session_id = registered.get("session_id")
if registered.get("ok") is not True or not isinstance(session_id, str):
raise AssertionError(f"broker anchor registration failed: {registered!r}")
built = fragments.build_payload_from_wire(construction)
normal = request(socket_path, {
"action": "begin_verification", "session_id": session_id, "runtime_generation": 1,
"runtime": runtime, "construction": construction,
"binding": {"compaction_epoch": index, "request_epoch": index + 100,
"h_source": built.h_source, "h_payload": built.h_payload, "schema_version": 1},
})
normal_challenge = normal.get("receipt_challenge")
normal_receipt = normal.get("receipt")
if not isinstance(normal_challenge, str) or not isinstance(normal_receipt, str):
raise AssertionError("normal path did not mint a receipt challenge")
environment = {
**os.environ,
"MOSAIC_LEASE_BROKER_SOCKET": str(socket_path),
"MOSAIC_RECEIPT_OBSERVER_SOCKET": str(observer_socket),
"MOSAIC_LEASE_SESSION_ID": session_id,
"MOSAIC_RUNTIME_GENERATION": "1",
"MOSAIC_LEASE_RUNTIME": runtime,
}
gate_recovery(runtime, "begin", environment)
recovery = run_json([
sys.executable, "-I", "-S", "-B", str(RECOVERY_COMMAND), "begin", "--construction", str(construction_path),
"--compaction-epoch", str(index + 10), "--request-epoch", str(index + 110),
], environment)
challenge = recovery.get("receipt_challenge")
receipt = recovery.get("receipt")
if recovery.get("state") != "PENDING_DELIVERY" or not isinstance(challenge, str) or not isinstance(receipt, str):
raise AssertionError(f"recovery command did not drive pending delivery: {recovery!r}")
if challenge == normal_challenge:
raise AssertionError("recovery reused a normal-path challenge")
# C4: production observer content is still exact-current-cycle only.
record_production_observation(runtime, normal_receipt, root, environment)
refused = run_json([sys.executable, "-I", "-S", "-B", str(RECOVERY_COMMAND), "complete"], environment)
if refused.get("ok") is not False or refused.get("code") != "RECEIPT_MISMATCH":
raise AssertionError(f"normal-path receipt replay was not refused: {refused!r}")
gate_recovery(runtime, "begin", environment)
recovery = run_json([
sys.executable, "-I", "-S", "-B", str(RECOVERY_COMMAND), "begin", "--construction", str(construction_path),
"--compaction-epoch", str(index + 20), "--request-epoch", str(index + 120),
], environment)
receipt = recovery.get("receipt")
if recovery.get("state") != "PENDING_DELIVERY" or not isinstance(receipt, str):
raise AssertionError(f"fresh recovery retry did not pend: {recovery!r}")
record_production_observation(runtime, receipt, root, environment)
gate_recovery(runtime, "complete", environment)
promoted = run_json([sys.executable, "-I", "-S", "-B", str(RECOVERY_COMMAND), "complete"], environment)
if promoted.get("ok") is not True or promoted.get("state") != "VERIFIED":
raise AssertionError(f"recovery consume-before-promote failed: {promoted!r}")
replay = run_json([sys.executable, "-I", "-S", "-B", str(RECOVERY_COMMAND), "complete"], environment)
if replay.get("ok") is not False or replay.get("code") != "INVALID_LEASE_TRANSITION":
raise AssertionError(f"consumed recovery challenge re-promoted: {replay!r}")
finally:
if process.poll() is None:
process.terminate()
try:
process.wait(timeout=3.0)
except subprocess.TimeoutExpired:
process.kill()
process.wait()
shutil.rmtree(root, ignore_errors=True)
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--runs", type=int, default=3)
arguments = parser.parse_args()
if arguments.runs != 3:
raise SystemExit("P6 requires exactly three isolated runs")
for index, runtime in enumerate(("pi", "claude", "pi")):
run_once(index, runtime)
print("P6 constrained recovery probe PASS: 3 isolated shipped recovery-command runs")
if __name__ == "__main__":
main()
@@ -1,63 +0,0 @@
# npm `@next` prerelease lane
Status: **IMPLEMENTED**
## Current behavior
`tools/install.sh --next` provides the prerelease integration lane for the permanent `next` branch.
The lane is fast-by-default:
1. Install framework files from the `next` source archive.
2. Resolve the Gitea npm registry `next` dist-tag for the globally installed packages:
```bash
npm view @mosaicstack/gateway@next version
npm view @mosaicstack/mosaic@next version
```
3. Require both resolved versions to share the same `next.<pipeline>` suffix, then install the exact resolved versions.
4. If either `@next` package is missing, unreachable, mismatched, or fails to install, fall back to the source-build path at `next`.
`--next` never hard-fails solely because the prerelease npm dist-tag is unavailable.
## Published packages
The `next` publish pipeline publishes non-private `@mosaicstack/*` packages to the Mosaic Gitea npm registry:
```text
https://git.mosaicstack.dev/api/packages/mosaicstack/npm/
```
Observed `next` dist-tags after enabling the pipeline:
```text
@mosaicstack/mosaic@next -> 0.0.49-next.1633
@mosaicstack/gateway@next -> 0.0.7-next.1633
```
The gateway also publishes a Docker image as `gateway:sha-<short>` on `next` merges. The installer fast path uses the npm gateway package when available; the Docker image is for deployed gateway/runtime harness flows.
## Explicit source lanes
Source builds remain available and are still the authority for explicit ref validation:
- `--dev` always builds from source.
- `--ref <ref>` / `MOSAIC_REF=<ref>` wins over `--next` and uses the source path for that exact ref.
## Pipeline shape
1. Trigger on `next` merges.
2. Compute the next prerelease version from the upcoming stable version plus the Woodpecker pipeline number (`<target-stable>-next.<CI_PIPELINE_NUMBER>`).
3. Build and publish non-private packages in CI.
4. Publish to the Mosaic Gitea npm registry with dist-tag `next`.
5. Keep `latest` untouched; only main/release promotion can update `latest`.
6. Publish gateway Docker images from `next` as `gateway:sha-<short>` only.
## Guardrails
- `@next` is mutable prerelease convenience, not a deployment pin.
- Stable installs continue to use `@latest`.
- Contributor validation remains available through `--dev --ref <branch>`.
- Pipeline output traces every prerelease package back to the source commit on `next`.
- The installer falls back to source rather than hard-failing on prerelease registry issues.
+31 -23
View File
@@ -5,17 +5,28 @@
This checklist is an acceptance contract for documentation and examples. It does not authorize
schema, runtime, systemd, role, profile, or live-fleet changes. An item is complete only when its
named artifact exists, is linked from the fleet documentation entry point, and its evidence is
recorded in the M5 closure report and linked deferral evidence.
recorded in the M0 task/PR.
## M0 baseline acceptance
- [x] `docs/PRD.md` states the roster as desired-state SSOT; generated environment, systemd, tmux, and heartbeat artifacts as non-authoritative projections; and fail-closed handling of unsupported or quarantined legacy input.
- [x] `docs/PRD.md` defines the required classes and authority boundary: `validator` certifies but does not merge; `merge-gate` remains sole approve-to-land/merge authority; `team-leader` capacity is lease-bounded; `interaction` is request/status only; instance names such as Tess and Ultron remain configurable.
- [x] `docs/PRD.md` defines local lifecycle semantics for `enabled`, persisted desired state, and observed state, including stopped-state preservation through migration, apply, and reboot.
- [x] `docs/PRD.md` defines the generated-env/local-override boundary, explicitly denies arbitrary command overrides in M1M5, and requires key-name/hash-only quarantine diagnostics.
- [x] `docs/PRD.md` identifies the M1M5 local-tmux scope and excludes remote reconciliation, connector mutation, secret references, arbitrary commands/channels, gateway convergence, and UI configuration storage.
- [x] `docs/TASKS.md` contains the complete M0M5 one-card/one-PR dependency DAG for #758 with agent tier, branch, dependency, estimate, and evidence expectations.
- [x] `docs/fleet/LEGACY-EXAMPLE-PROFILE-DISPOSITION-INVENTORY.md` classifies every current shipped fleet example, profile, and service preset before M1 implementation starts.
- [ ] `docs/PRD.md` states the roster as desired-state SSOT; generated environment, systemd,
tmux, and heartbeat artifacts as non-authoritative projections; and fail-closed handling of
unsupported or quarantined legacy input.
- [ ] `docs/PRD.md` defines the required classes and authority boundary: `validator` certifies but
does not merge; `merge-gate` remains sole approve-to-land/merge authority; `team-leader`
capacity is lease-bounded; `interaction` is request/status only; instance names such as Tess
and Ultron remain configurable.
- [ ] `docs/PRD.md` defines local lifecycle semantics for `enabled`, persisted desired state, and
observed state, including stopped-state preservation through migration, apply, and reboot.
- [ ] `docs/PRD.md` defines the generated-env/local-override boundary, explicitly denies arbitrary
command overrides in M1M5, and requires key-name/hash-only quarantine diagnostics.
- [ ] `docs/PRD.md` identifies the M1M5 local-tmux scope and excludes remote reconciliation,
connector mutation, secret references, arbitrary commands/channels, gateway convergence, and
UI configuration storage.
- [ ] `docs/TASKS.md` contains the complete M0M5 one-card/one-PR dependency DAG for #758 with
agent tier, branch, dependency, estimate, and evidence expectations.
- [ ] `docs/fleet/LEGACY-EXAMPLE-PROFILE-DISPOSITION-INVENTORY.md` classifies every current shipped
fleet example, profile, and service preset before M1 implementation starts.
## Required documentation IA for M1M5
@@ -61,18 +72,15 @@ recorded in the M5 closure report and linked deferral evidence.
## Cross-cutting evidence gates
- [x] Every retained or migrated YAML/JSON example, profile, and service preset validates through the same declared executable production parser/resolver path recorded by the disposition inventory; versioned v1 fixtures are not forced through the v2 compiler.
- [x] Every retired example/profile/service preset has a replacement link and deprecation note; no unresolved legacy class or tool-policy alias remains silently shipped.
- [x] Documentation examples contain no secret values, arbitrary command override, or product-hardcoded Tess/Ultron identity.
- [x] CLI snippets distinguish local fleet desired-state commands from the separate gateway-backed mosaic agent catalog.
- [x] Migration, quarantine, lifecycle, status, and troubleshooting documentation state that values of legacy sensitive keys are never printed.
- [x] M5 documentation validation verifies required IA paths, local file and heading-fragment links, the canonical roster through the production compiler/resolver, and fenced/canonical-example safety checks.
- [ ] FCM-M5-001 does not deterministically assert owner/evidence/deferral metadata for every checklist row. Closure and deferral reports provide human-reviewable evidence only; broader assertion coverage remains unclaimed.
## Held downstream gates
These unchecked items are intentionally outside FCM-M5-001 and are not authorized by this checklist:
- [ ] FCM-M4-002 executes and evidences live cutover, canary, stopped-state preservation, and rollback.
- [ ] FCM-M5-002 completes independent exact-head review and issues the validator certificate.
- [ ] The exact PR head reaches terminal-green CI after independent review.
- [ ] Every retained or migrated YAML/JSON example, profile, and service preset validates through the
same executable schema and shared baseline-plus-`roles.local` resolver used by the CLI.
- [ ] Every retired example/profile/service preset has a replacement link and deprecation note; no
unresolved legacy class or tool-policy alias remains silently shipped.
- [ ] Documentation examples contain no secret values, arbitrary command override, or product-hardcoded
Tess/Ultron identity.
- [ ] CLI snippets distinguish local fleet desired-state commands from the separate gateway-backed
`mosaic agent` catalog.
- [ ] Migration, quarantine, lifecycle, status, and troubleshooting documentation state that values of
legacy sensitive keys are never printed.
- [ ] M5 release review verifies links, schema/example validation, and that all checklist rows have
owner/evidence or an explicit approved deferral.
+11 -11
View File
@@ -8,11 +8,11 @@ Generated environment files are rebuildable projections, not an operator-editabl
| Layer | Responsibility |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| Roster | `fleet/roster.yaml` supplies the agent name, class, supported runtime, model, reasoning, tool policy, workdir, and tmux socket. |
| Projection writer | Renders deterministic fleet/agents/<name>.env.generated from the roster. |
| Optional local data | Reads a strict, data-only fleet/agents/<name>.env.local; it cannot shadow generated keys. |
| systemd | Starts the launcher with env -i and fixed bootstrap data. It does not preload either environment file. |
| Projection writer | Renders deterministic `fleet/agents/<name>.env.generated` from the roster. |
| Optional local data | Reads a strict, data-only `fleet/agents/<name>.env.local`; it cannot shadow generated keys. |
| systemd | Starts the launcher with `env -i` and fixed bootstrap data. It does not preload either environment file. |
| session launcher | Validates generated and local data before it queries, creates, or stops an exact tmux session. |
| runtime launch | Derives the fixed mosaic yolo <runtime> argument array from validated roster data, then seeds the runtime contract. |
| runtime launch | Derives the fixed `mosaic yolo <runtime>` argument array from validated roster data, then seeds the runtime contract. |
The launcher never `source`s or `eval`s an environment file and never accepts an environment-supplied
command. `MOSAIC_AGENT_COMMAND`, command/channel overrides, unknown keys, generated-key shadowing,
@@ -20,7 +20,7 @@ secret-like key names, duplicate keys, comments, quoted/export syntax, and unsaf
## Generated and local files
<name>.env.generated is complete, deterministic, and written only by Mosaic. Its ordered keys are:
`<name>.env.generated` is complete, deterministic, and written only by Mosaic. Its ordered keys are:
```dotenv
MOSAIC_AGENT_NAME=<roster name>
@@ -33,12 +33,12 @@ MOSAIC_AGENT_WORKDIR=<absolute roster work directory>
MOSAIC_TMUX_SOCKET=<roster socket or empty>
```
The generated launch contract supports `claude`, `codex`, `opencode`, and `pi`. mosaic fleet add
The generated launch contract supports `claude`, `codex`, `opencode`, and `pi`. `mosaic fleet add`
rejects another runtime before it writes the roster or modifies generated, local, or quarantine state.
The legacy dogfood stub remains an observability-only canary on its separate `mosaic-factory` socket;
it has no generated-launch adapter and cannot be added through this path.
<name>.env.local is optional and may contain only non-secret machine data:
`<name>.env.local` is optional and may contain only non-secret machine data:
- `MOSAIC_RUNTIME_BIN`
- `MOSAIC_HEARTBEAT_RUN_DIR`
@@ -52,9 +52,9 @@ private, non-symlink paths. Violations fail closed before tmux interaction.
## Legacy input and diagnostics
A legacy <name>.env is input only during projection generation. Roster-owned keys are regenerated;
A legacy `<name>.env` is input only during projection generation. Roster-owned keys are regenerated;
valid allowed local data can move to `.env.local`; invalid legacy input is privately retained at
<name>.env.quarantine. Neither legacy nor quarantine files are launch authority.
`<name>.env.quarantine`. Neither legacy nor quarantine files are launch authority.
Diagnostics expose only rule code, key name, and a SHA-256 content hash. They do not reveal command
text, credentials, or other values.
@@ -62,11 +62,11 @@ text, credentials, or other values.
## Launch and stop behavior
The launcher obtains the agent's socket only from the validated generated projection. It creates or
checks the exact =<agent-name> tmux target; it never uses an ambient socket or fuzzy session match.
checks the exact `=<agent-name>` tmux target; it never uses an ambient socket or fuzzy session match.
The same strict parser runs before exact-stop behavior. A fresh native Pi heartbeat remains authoritative;
the shell sidecar only provides fallback state when the native marker is stale or absent.
mosaic agent comms-block <exact-member> can inspect that exact roster member's resolved Fleet-Comms
`mosaic agent comms-block <exact-member>` can inspect that exact roster member's resolved Fleet-Comms
block. It is a read-only inspection tool and fails loudly for an unknown exact member or missing roster.
On Linux, the installed roster, TOOLS contract, and executable helper are opened through a held
descriptor chain rooted at `/`; every managed path component uses no-follow traversal, and content plus
@@ -14,7 +14,7 @@ parallel resolver. The current executable implementation and per-artifact outcom
| Shipped file | Current class evidence | M0 disposition decision | Required M1/M4 evidence |
| ---------------------------------------------------- | ------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- |
| `framework/fleet/examples/coding.yaml` | `orchestrator`, `enhancer`, `implementer`, `reviewer` | Migrate: implementer → code, reviewer → review; retain orchestration/enhancer intent | v2 fixture validates; role aliases and authority matrix tested |
| `framework/fleet/examples/coding.yaml` | `orchestrator`, `enhancer`, `implementer`, `reviewer` | Migrate: `implementer → code`, `reviewer → review`; retain orchestration/enhancer intent | v2 fixture validates; role aliases and authority matrix tested |
| `framework/fleet/examples/general.yaml` | `orchestrator`, `enhancer`, `worker` | Migrate only after operator chooses a concrete canonical role for `worker`; no implicit conversion | Explicit replacement class, or versioned v1 fixture/retirement note |
| `framework/fleet/examples/hybrid.yaml` | `orchestrator`, `enhancer`, `implementer`, `researcher`, `reviewer` | Migrate aliases; resolve `researcher` through existing role resolver or retain/version | Shared resolver validation; no ad-hoc class scanner |
| `framework/fleet/examples/local-canary.yaml` | `orchestrator`, `implementer`, `reviewer` | Migrate aliases; preserve its local-tmux canary purpose | v2 fixture validates and preserves safe stopped/running behavior |
@@ -34,14 +34,14 @@ parallel resolver. The current executable implementation and per-artifact outcom
## Service presets
| Shipped file | Current policy evidence | M0 disposition decision | Required M1/M4 evidence |
| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `framework/fleet/services/operator-interaction.yaml` | Generic policy only: runtime: pi, model: openai/gpt-5.6-sol, reasoning: high, tool_policy: operator-interaction; provisioning supplies the agent name as data | Retain as a generic service policy, not a Tess identity. Migrate tool_policy: operator-interaction only through the approved interaction tool-policy alias/semantic resolver; do not infer a class or machine name from this file. | Service-policy fixture validates runtime/model/reasoning and alias behavior; generic provisioning proves a configured interaction instance is supplied without a hardcoded Tess name. |
| Shipped file | Current policy evidence | M0 disposition decision | Required M1/M4 evidence |
| ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `framework/fleet/services/operator-interaction.yaml` | Generic policy only: `runtime: pi`, `model: openai/gpt-5.6-sol`, `reasoning: high`, `tool_policy: operator-interaction`; provisioning supplies the agent name as data | Retain as a generic service policy, not a Tess identity. Migrate `tool_policy: operator-interaction` only through the approved interaction tool-policy alias/semantic resolver; do not infer a class or machine name from this file. | Service-policy fixture validates runtime/model/reasoning and alias behavior; generic provisioning proves a configured interaction instance is supplied without a hardcoded Tess name. |
## Required disposition controls
1. **No silent aliasing:** only implementer → code, reviewer → review, and
operator-interaction → interaction are approved deterministic aliases in this M0 baseline.
1. **No silent aliasing:** only `implementer → code`, `reviewer → review`, and
`operator-interaction → interaction` are approved deterministic aliases in this M0 baseline.
`worker`, `analyst`, `canary`, and domain-specific classes require resolver evidence or an
explicit version/retirement decision.
2. **No identity hardcoding:** Tess and Ultron are optional instance/display names. An example/profile
+1 -1
View File
@@ -33,7 +33,7 @@ The Mosaic Backlog is the backlog of record + dispatch engine, built on Mosaic's
- **AC-NS-4** — TTL is enforced on claims; token caps remain advisory until a real meter exists.
- **AC-NS-5** — Flipping fleet/run/PAUSED halts dispatch and merges within one tick.
- **AC-NS-6** — A user can declare a system type and the fleet provisions the matching persona roster + topology from the baseline library, with no code change.
- **AC-NS-7** — A user-customized persona (edited or added via the orchestrator) survives mosaic update: baseline reseed never clobbers user overrides.
- **AC-NS-7** — A user-customized persona (edited or added via the orchestrator) survives `mosaic update`: baseline reseed never clobbers user overrides.
## Workstreams

Some files were not shown because too many files have changed in this diff Show More