Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1a871524d7 | ||
|
|
de0adb9207 | ||
|
|
ff50cbdb61 | ||
|
|
adb1d7f80e | ||
|
|
a57933a4c4 | ||
|
|
9d0822570c | ||
|
|
a5e88a8d97 | ||
|
|
eccf9e9a7d | ||
|
|
cc84bbe734 | ||
|
|
353296d3cf | ||
|
|
7bada88e4b | ||
|
|
cec20461f0 | ||
|
|
f4cae29d0d | ||
|
|
a96fb8f425 | ||
|
|
7fad4d9ac2 | ||
|
|
79e18343ca | ||
|
|
9e59016171 | ||
|
|
a221b82537 | ||
|
|
603f91b242 | ||
|
|
7984c8a3c8 | ||
|
|
5c61d1f1a5 | ||
|
|
5f36e4eba6 | ||
|
|
93f6a9567e | ||
|
|
ebf5d65a53 | ||
|
|
4df478cdd1 | ||
|
|
b8844e1ff0 | ||
|
|
906ad8dc30 | ||
|
|
193331544d | ||
|
|
495f73bfdb | ||
|
|
b96cc7982a | ||
|
|
0883fb91ec | ||
|
|
56787fabf1 | ||
|
|
940ae3cc41 | ||
|
|
c25a551c28 | ||
|
|
94d6538061 | ||
|
|
a3c1ab923c | ||
|
|
838701bde2 |
@@ -46,10 +46,6 @@ steps:
|
||||
# [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
|
||||
# Hermetic regression for issue-close.sh (#1081): mocks tea/curl onto PATH
|
||||
# and sandboxes a throwaway git repo, so it resolves no real credentials and
|
||||
# joins CI directly rather than the exclusions file.
|
||||
- bash packages/mosaic/framework/tools/git/test-issue-close-fail-closed.sh
|
||||
|
||||
# Blocking gate (#791): a framework upgrade must never write or delete an
|
||||
# operator-owned path. The HARD GATE proves an unanticipated operator sentinel
|
||||
|
||||
+104
-5
@@ -1,5 +1,5 @@
|
||||
# Build, publish npm packages, and push Docker images
|
||||
# Runs only on main branch push/tag
|
||||
# Runs on main for stable publishes and on next for integration-line prereleases/images
|
||||
|
||||
variables:
|
||||
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
|
||||
@@ -23,9 +23,21 @@ 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]
|
||||
- branch: [main, next]
|
||||
event: [push, manual, tag]
|
||||
|
||||
steps:
|
||||
@@ -103,6 +115,84 @@ 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 $RESOLVED_VERSION"
|
||||
depends_on:
|
||||
- build
|
||||
|
||||
# TODO: Uncomment when ready to publish to npmjs.org
|
||||
# publish-npmjs:
|
||||
# image: *node_image
|
||||
@@ -134,8 +224,17 @@ steps:
|
||||
- echo "{\"auths\":{\"git.mosaicstack.dev\":{\"username\":\"$REGISTRY_USER\",\"password\":\"$REGISTRY_PASS\"}}}" > /kaniko/.docker/config.json
|
||||
- |
|
||||
DESTINATIONS="--destination git.mosaicstack.dev/mosaicstack/stack/gateway:sha-${CI_COMMIT_SHA:0:7}"
|
||||
if [ "$CI_COMMIT_BRANCH" = "main" ]; then
|
||||
if [ "$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 [ "$CI_COMMIT_BRANCH" = "main" ]; then
|
||||
DESTINATIONS="$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"
|
||||
@@ -146,7 +245,7 @@ steps:
|
||||
|
||||
build-appservice:
|
||||
image: gcr.io/kaniko-project/executor:debug
|
||||
when: *image_build_when
|
||||
when: *main_image_build_when
|
||||
environment:
|
||||
REGISTRY_USER:
|
||||
from_secret: gitea_username
|
||||
@@ -172,7 +271,7 @@ steps:
|
||||
|
||||
build-web:
|
||||
image: gcr.io/kaniko-project/executor:debug
|
||||
when: *image_build_when
|
||||
when: *main_image_build_when
|
||||
environment:
|
||||
REGISTRY_USER:
|
||||
from_secret: gitea_username
|
||||
|
||||
@@ -30,6 +30,16 @@ 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
|
||||
@@ -60,14 +70,6 @@ The launcher verifies your config, checks for `SOUL.md`, injects your `AGENTS.md
|
||||
|
||||
Pi launches default to a token-lean skill posture: `mosaic pi` passes `--no-skills` so Pi does not preload every global skill description into the system prompt. Use `MOSAIC_PI_SKILL_MODE=all mosaic pi` for the legacy all-skills catalog, or `MOSAIC_PI_SKILL_MODE=discover mosaic pi` to let Pi use its native settings/project skill discovery.
|
||||
|
||||
Mosaic also loads its Pi extensions from `~/.config/mosaic/runtime/pi/`. Inside Pi,
|
||||
`/goal set <statement>` starts a bounded persistent loop that checks every turn and successful
|
||||
compaction, requires two evidence-bearing completion reports, and can be inspected or stopped with
|
||||
`/goal status`, `/goal pause`, `/goal resume`, and `/goal cancel`. Controller-owned goal-state
|
||||
entries redact common credential shapes, but Pi's model/tool-call history is separate, so goals and
|
||||
evidence must never contain secrets or raw sensitive output. Mosaic does not install this extension
|
||||
into `~/.pi/agent/extensions/`.
|
||||
|
||||
### TUI & Gateway
|
||||
|
||||
```bash
|
||||
@@ -369,7 +371,9 @@ 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 --ref v1.0 # Install from a specific git ref
|
||||
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 --yes # Non-interactive, accept all defaults
|
||||
bash tools/install.sh --no-auto-launch # Skip auto-launch of wizard
|
||||
```
|
||||
|
||||
@@ -0,0 +1,519 @@
|
||||
/**
|
||||
* 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,
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -1,9 +1,11 @@
|
||||
import { Controller, Get, Inject, UseGuards } from '@nestjs/common';
|
||||
import { Controller, Get, Inject, Optional, 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';
|
||||
|
||||
@@ -14,6 +16,9 @@ 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()
|
||||
@@ -55,6 +60,14 @@ 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 {
|
||||
|
||||
@@ -72,13 +72,13 @@ const mockChatGateway = {
|
||||
broadcastSessionInfo: vi.fn(),
|
||||
};
|
||||
|
||||
function buildService(): CommandExecutorService {
|
||||
function buildService(redis: typeof mockRedis | null = mockRedis): CommandExecutorService {
|
||||
return new CommandExecutorService(
|
||||
mockRegistry as never,
|
||||
mockAgentService as never,
|
||||
mockSystemOverride as never,
|
||||
mockSessionGC as never,
|
||||
mockRedis as never,
|
||||
redis as never,
|
||||
mockBrain as never,
|
||||
null,
|
||||
mockChatGateway as never,
|
||||
@@ -131,6 +131,22 @@ 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 };
|
||||
|
||||
@@ -23,7 +23,10 @@ export class CommandExecutorService {
|
||||
@Inject(AgentService) private readonly agentService: AgentService,
|
||||
@Inject(SystemOverrideService) private readonly systemOverride: SystemOverrideService,
|
||||
@Inject(SessionGCService) private readonly sessionGC: SessionGCService,
|
||||
@Inject(COMMANDS_REDIS) private readonly redis: QueueHandle['redis'],
|
||||
// On Local tier COMMANDS_REDIS is null — provider login caching is skipped.
|
||||
@Optional()
|
||||
@Inject(COMMANDS_REDIS)
|
||||
private readonly redis: QueueHandle['redis'] | null,
|
||||
@Inject(BRAIN) private readonly brain: Brain,
|
||||
@Optional()
|
||||
@Inject(forwardRef(() => ReloadService))
|
||||
@@ -443,14 +446,16 @@ export class CommandExecutorService {
|
||||
byte.toString(16).padStart(2, '0'),
|
||||
).join('');
|
||||
const key = `mosaic:auth:poll:${tokenHash}`;
|
||||
// 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,
|
||||
);
|
||||
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,
|
||||
);
|
||||
}
|
||||
return {
|
||||
command: 'provider',
|
||||
success: true,
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
import { forwardRef, Inject, Module, type OnApplicationShutdown } from '@nestjs/common';
|
||||
import { forwardRef, Inject, Module, Optional, 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';
|
||||
@@ -16,13 +18,17 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
|
||||
providers: [
|
||||
{
|
||||
provide: COMMANDS_QUEUE_HANDLE,
|
||||
useFactory: (): QueueHandle => {
|
||||
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;
|
||||
return createQueue();
|
||||
},
|
||||
inject: [MOSAIC_CONFIG],
|
||||
},
|
||||
{
|
||||
provide: COMMANDS_REDIS,
|
||||
useFactory: (handle: QueueHandle) => handle.redis,
|
||||
useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
|
||||
inject: [COMMANDS_QUEUE_HANDLE],
|
||||
},
|
||||
CommandRegistryService,
|
||||
@@ -38,9 +44,13 @@ const COMMANDS_QUEUE_HANDLE = 'COMMANDS_QUEUE_HANDLE';
|
||||
],
|
||||
})
|
||||
export class CommandsModule implements OnApplicationShutdown {
|
||||
constructor(@Inject(COMMANDS_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
|
||||
constructor(
|
||||
@Optional()
|
||||
@Inject(COMMANDS_QUEUE_HANDLE)
|
||||
private readonly handle: QueueHandle | null,
|
||||
) {}
|
||||
|
||||
async onApplicationShutdown(): Promise<void> {
|
||||
await this.handle.close().catch(() => {});
|
||||
await this.handle?.close().catch(() => {});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -245,21 +245,9 @@ describe('EnrollmentService.createToken', () => {
|
||||
const after = Date.now();
|
||||
|
||||
const expiresMs = new Date(result.expiresAt).getTime();
|
||||
|
||||
// The property under test is CLAMPING: a 9999s request must come back as 900s.
|
||||
// The gap between clamped and unclamped is 9_099_000 ms, so the tolerance below
|
||||
// only has to exceed CI scheduling jitter — it does not need to be tight to keep
|
||||
// the assertion discriminating. A 5s allowance consumes 0.05% of that margin and
|
||||
// an unclamped result still misses by three orders of magnitude.
|
||||
//
|
||||
// It was 100ms and failed on a loaded agent at 900_106 — 6ms over (#1090). A
|
||||
// wall-clock budget sized to a fast machine is a flake, not a tighter test.
|
||||
const CI_JITTER_MS = 5_000;
|
||||
expect(expiresMs - before).toBeLessThanOrEqual(900_000 + CI_JITTER_MS);
|
||||
// Should be at most 900s from now
|
||||
expect(expiresMs - before).toBeLessThanOrEqual(900_000 + 100);
|
||||
expect(expiresMs - after).toBeGreaterThanOrEqual(0);
|
||||
// Explicitly pin the clamp itself, independent of any timing allowance:
|
||||
// unclamped (9999s) would exceed this by ~9_099_000 ms.
|
||||
expect(expiresMs - before).toBeLessThan(1_000_000);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -5,6 +5,8 @@ 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';
|
||||
@@ -12,7 +14,13 @@ import { ListController } from './server/verbs/list.controller.js';
|
||||
import { FederationListQueryService } from './server/verbs/list-query.service.js';
|
||||
|
||||
@Module({
|
||||
controllers: [EnrollmentController, FederationController, CapabilitiesController, ListController],
|
||||
controllers: [
|
||||
EnrollmentController,
|
||||
FederationController,
|
||||
CapabilitiesController,
|
||||
ListController,
|
||||
GetController,
|
||||
],
|
||||
providers: [
|
||||
AdminGuard,
|
||||
CaService,
|
||||
@@ -23,6 +31,7 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
|
||||
FederationAuthGuard,
|
||||
FederationScopeService,
|
||||
FederationListQueryService,
|
||||
FederationGetQueryService,
|
||||
],
|
||||
exports: [
|
||||
CaService,
|
||||
@@ -33,6 +42,7 @@ import { FederationListQueryService } from './server/verbs/list-query.service.js
|
||||
FederationAuthGuard,
|
||||
FederationScopeService,
|
||||
FederationListQueryService,
|
||||
FederationGetQueryService,
|
||||
],
|
||||
})
|
||||
export class FederationModule {}
|
||||
|
||||
@@ -0,0 +1,348 @@
|
||||
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',
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,207 @@
|
||||
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();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,311 @@
|
||||
/**
|
||||
* 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 };
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,100 @@
|
||||
/**
|
||||
* 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 } };
|
||||
}
|
||||
}
|
||||
@@ -1,5 +1,7 @@
|
||||
import { Module, type OnApplicationShutdown, Inject } from '@nestjs/common';
|
||||
import { Module, type OnApplicationShutdown, Inject, Optional } 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';
|
||||
|
||||
@@ -9,13 +11,17 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
|
||||
providers: [
|
||||
{
|
||||
provide: GC_QUEUE_HANDLE,
|
||||
useFactory: (): QueueHandle => {
|
||||
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;
|
||||
return createQueue();
|
||||
},
|
||||
inject: [MOSAIC_CONFIG],
|
||||
},
|
||||
{
|
||||
provide: REDIS,
|
||||
useFactory: (handle: QueueHandle) => handle.redis,
|
||||
useFactory: (handle: QueueHandle | null) => handle?.redis ?? null,
|
||||
inject: [GC_QUEUE_HANDLE],
|
||||
},
|
||||
SessionGCService,
|
||||
@@ -23,9 +29,13 @@ const GC_QUEUE_HANDLE = 'GC_QUEUE_HANDLE';
|
||||
exports: [SessionGCService],
|
||||
})
|
||||
export class GCModule implements OnApplicationShutdown {
|
||||
constructor(@Inject(GC_QUEUE_HANDLE) private readonly handle: QueueHandle) {}
|
||||
constructor(
|
||||
@Optional()
|
||||
@Inject(GC_QUEUE_HANDLE)
|
||||
private readonly handle: QueueHandle | null,
|
||||
) {}
|
||||
|
||||
async onApplicationShutdown(): Promise<void> {
|
||||
await this.handle.close().catch(() => {});
|
||||
await this.handle?.close().catch(() => {});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -119,6 +119,19 @@ 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');
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { Inject, Injectable } from '@nestjs/common';
|
||||
import { Inject, Injectable, Optional } from '@nestjs/common';
|
||||
import type { QueueHandle } from '@mosaicstack/queue';
|
||||
import type { LogService } from '@mosaicstack/log';
|
||||
import { LOG_SERVICE } from '../log/log.tokens.js';
|
||||
@@ -21,7 +21,10 @@ function escapeRedisGlobLiteral(value: string): string {
|
||||
@Injectable()
|
||||
export class SessionGCService {
|
||||
constructor(
|
||||
@Inject(REDIS) private readonly redis: QueueHandle['redis'],
|
||||
// Local tier has no Redis; lifecycle cleanup still demotes this session's logs.
|
||||
@Optional()
|
||||
@Inject(REDIS)
|
||||
private readonly redis: QueueHandle['redis'] | null,
|
||||
@Inject(LOG_SERVICE) private readonly logService: LogService,
|
||||
) {}
|
||||
|
||||
@@ -29,8 +32,10 @@ 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 {
|
||||
@@ -47,12 +52,14 @@ export class SessionGCService {
|
||||
async collect(sessionId: string): Promise<GCResult> {
|
||||
const result: GCResult = { sessionId, cleaned: {} };
|
||||
|
||||
// 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;
|
||||
// 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;
|
||||
}
|
||||
}
|
||||
|
||||
// 2. PG: demote hot-tier agent logs for this session only.
|
||||
|
||||
@@ -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: Worker<MosaicJobData>[] = [];
|
||||
private readonly registeredWorkers: Array<Worker<MosaicJobData>> = [];
|
||||
|
||||
constructor(
|
||||
@Inject(SummarizationService) private readonly summarization: SummarizationService,
|
||||
@@ -26,6 +26,12 @@ 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
|
||||
|
||||
@@ -39,7 +45,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
|
||||
const summarizationWorker = this.queueService.registerWorker(QUEUE_SUMMARIZATION, async () => {
|
||||
await this.summarization.runSummarization();
|
||||
});
|
||||
this.registeredWorkers.push(summarizationWorker);
|
||||
if (summarizationWorker) this.registeredWorkers.push(summarizationWorker);
|
||||
|
||||
// M6-005: Tier management repeatable job
|
||||
await this.queueService.addRepeatableJob(
|
||||
@@ -51,7 +57,7 @@ export class CronService implements OnModuleInit, OnModuleDestroy {
|
||||
const tierWorker = this.queueService.registerWorker(QUEUE_TIER_MANAGEMENT, async () => {
|
||||
await this.summarization.runTierManagement();
|
||||
});
|
||||
this.registeredWorkers.push(tierWorker);
|
||||
if (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.
|
||||
|
||||
@@ -0,0 +1,23 @@
|
||||
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');
|
||||
});
|
||||
});
|
||||
@@ -1,6 +1,8 @@
|
||||
import { Injectable, Logger } from '@nestjs/common';
|
||||
import { Inject, Injectable, Logger, Optional, type OnApplicationShutdown } 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}`;
|
||||
@@ -15,16 +17,45 @@ interface OverrideFragment {
|
||||
addedAt: number;
|
||||
}
|
||||
|
||||
@Injectable()
|
||||
export class SystemOverrideService {
|
||||
private readonly logger = new Logger(SystemOverrideService.name);
|
||||
private readonly handle: QueueHandle;
|
||||
interface LocalOverrideEntry {
|
||||
condensed: string;
|
||||
fragments: OverrideFragment[];
|
||||
}
|
||||
|
||||
constructor() {
|
||||
this.handle = createQueue();
|
||||
@Injectable()
|
||||
export class SystemOverrideService implements OnApplicationShutdown {
|
||||
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>();
|
||||
|
||||
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(() => {});
|
||||
}
|
||||
|
||||
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
|
||||
@@ -54,10 +85,14 @@ export class SystemOverrideService {
|
||||
}
|
||||
|
||||
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);
|
||||
@@ -65,6 +100,11 @@ export class SystemOverrideService {
|
||||
}
|
||||
|
||||
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),
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
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.',
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -8,7 +8,9 @@ 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';
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
@@ -108,21 +110,42 @@ 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.connection = getConnection();
|
||||
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;
|
||||
}
|
||||
|
||||
onModuleInit(): void {
|
||||
this.logger.log('QueueService initialised (BullMQ)');
|
||||
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',
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
async onModuleDestroy(): Promise<void> {
|
||||
await this.closeAll();
|
||||
if (this.enabled) {
|
||||
await this.closeAll();
|
||||
}
|
||||
}
|
||||
|
||||
// -------------------------------------------------------------------------
|
||||
@@ -131,8 +154,10 @@ 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> {
|
||||
getQueue<T extends MosaicJobData = MosaicJobData>(name: string): Queue<T> | null {
|
||||
if (!this.enabled) return null;
|
||||
let queue = this.queues.get(name) as Queue<T> | undefined;
|
||||
if (!queue) {
|
||||
queue = new Queue<T>(name, { connection: this.connection });
|
||||
@@ -144,6 +169,7 @@ 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,
|
||||
@@ -151,7 +177,13 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
|
||||
data: T,
|
||||
cronExpression: string,
|
||||
): Promise<void> {
|
||||
const queue = this.getQueue<T>(queueName);
|
||||
if (!this.enabled) {
|
||||
this.logger.debug(
|
||||
`Skipping repeatable job "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
|
||||
);
|
||||
return;
|
||||
}
|
||||
const queue = this.getQueue<T>(queueName)!;
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (queue as Queue<any>).add(jobName, data, {
|
||||
repeat: { pattern: cronExpression },
|
||||
@@ -167,7 +199,14 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
|
||||
* safe retirement of previously registered system-wide jobs.
|
||||
*/
|
||||
async removeRepeatableJobs(queueName: string, jobName: string): Promise<number> {
|
||||
if (!this.enabled) {
|
||||
this.logger.debug(
|
||||
`Skipping repeatable-job removal for "${jobName}" on "${queueName}" (local tier — BullMQ disabled)`,
|
||||
);
|
||||
return 0;
|
||||
}
|
||||
const queue = this.getQueue(queueName);
|
||||
if (!queue) return 0;
|
||||
const jobs = await queue.getRepeatableJobs();
|
||||
const matchingJobs = jobs.filter((job) => job.name === jobName);
|
||||
await Promise.all(matchingJobs.map((job) => queue.removeRepeatableByKey(job.key)));
|
||||
@@ -182,8 +221,18 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
|
||||
/**
|
||||
* Register a Worker for the given queue name with error handling and
|
||||
* exponential backoff.
|
||||
* Returns null on Local tier where BullMQ is disabled.
|
||||
*/
|
||||
registerWorker<T extends MosaicJobData>(queueName: string, handler: JobHandler<T>): Worker<T> {
|
||||
registerWorker<T extends MosaicJobData>(
|
||||
queueName: string,
|
||||
handler: JobHandler<T>,
|
||||
): Worker<T> | null {
|
||||
if (!this.enabled) {
|
||||
this.logger.debug(
|
||||
`Skipping worker registration for "${queueName}" (local tier — BullMQ disabled)`,
|
||||
);
|
||||
return null;
|
||||
}
|
||||
const worker = new Worker<T>(
|
||||
queueName,
|
||||
async (job) => {
|
||||
@@ -240,8 +289,12 @@ 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;
|
||||
|
||||
@@ -272,8 +325,10 @@ 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]
|
||||
@@ -300,8 +355,10 @@ 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>".' };
|
||||
@@ -333,6 +390,7 @@ 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 "${name}" not found.` };
|
||||
await queue.pause();
|
||||
@@ -344,6 +402,7 @@ export class QueueService implements OnModuleInit, OnModuleDestroy {
|
||||
* Resume a paused queue by name.
|
||||
*/
|
||||
async resumeQueue(name: string): Promise<{ ok: boolean; message: string }> {
|
||||
if (!this.enabled) return { ok: false, message: 'BullMQ is disabled on local tier.' };
|
||||
const queue = this.queues.get(name);
|
||||
if (!queue) return { ok: false, message: `Queue "${name}" not found.` };
|
||||
await queue.resume();
|
||||
|
||||
-184
@@ -102,128 +102,6 @@ Context compaction, session replacement, and same-PID runtime reloads can leave
|
||||
|
||||
---
|
||||
|
||||
## Pi Persistent Goal Loop (#1150)
|
||||
|
||||
### Problem and objective
|
||||
|
||||
A Pi agent can stop after a plausible-looking answer even when the operator's broader objective is
|
||||
not complete, and ordinary compaction can weaken or omit the original objective. Mosaic needs an
|
||||
optional, operator-controlled goal loop that keeps a Pi session oriented, checks progress at native
|
||||
lifecycle boundaries, and resumes work until completion is verified or a bounded safety state is
|
||||
reached.
|
||||
|
||||
The objective is a Mosaic-owned Pi extension deployed from the framework into
|
||||
`~/.config/mosaic/runtime/pi/`. It must not install into or depend on `~/.pi/agent/extensions/`.
|
||||
|
||||
### Scope
|
||||
|
||||
#### In scope
|
||||
|
||||
1. `PGL-REQ-01`: The framework SHALL ship a dedicated Pi goal extension under
|
||||
`packages/mosaic/framework/runtime/pi/`, seed it under `$MOSAIC_HOME/runtime/pi/`, and make
|
||||
`mosaic pi` load it alongside the core Mosaic extension when present.
|
||||
2. `PGL-REQ-02`: `/goal` SHALL support setting a goal plus status, pause, resume, cancel, and help
|
||||
operations without silently replacing an active goal.
|
||||
3. `PGL-REQ-03`: Active branch-specific goal state SHALL be persisted in Pi custom session entries,
|
||||
restored on session start and tree navigation, and never rely on a compaction summary as its
|
||||
source of truth.
|
||||
4. `PGL-REQ-04`: A hidden goal contract SHALL be injected through Pi's `context` event before every
|
||||
model request so it remains effective across tool turns, retries, and post-compaction requests.
|
||||
5. `PGL-REQ-05`: The harness SHALL inspect every `turn_end` and successful `session_compact` event.
|
||||
A structured terminating goal-report tool SHALL capture `continue`, evidence-bearing `achieved`,
|
||||
or `blocked` status without requiring a redundant model turn.
|
||||
6. `PGL-REQ-06`: An achievement claim SHALL remain provisional until a second consecutive
|
||||
evidence-bearing verification report. Any continuation report or successful compaction during
|
||||
verification SHALL reset the verification sequence.
|
||||
7. `PGL-REQ-07`: Continuation SHALL be initiated at safe lifecycle boundaries, primarily
|
||||
`agent_settled`; manual compaction and restored active sessions may schedule a deferred idle
|
||||
continuation without re-entering compaction handlers.
|
||||
8. `PGL-REQ-08`: The loop SHALL have operator cancellation plus bounded turn and repeated-no-progress
|
||||
limits. Exhausted or blocked goals pause rather than continuing indefinitely.
|
||||
9. `PGL-REQ-09`: Framework installation and update SHALL preserve normal manifest ownership: the
|
||||
goal extension is framework-owned under `runtime/**`, while no goal extension or configuration
|
||||
asset is created or modified under the operator's main Pi configuration. Pi remains the owner of
|
||||
its native session files used by `appendEntry()`.
|
||||
|
||||
#### Out of scope
|
||||
|
||||
1. A mathematical guarantee that an arbitrary natural-language goal is semantically complete.
|
||||
2. Automatically executing user-supplied shell predicates or accepting executable validation code in
|
||||
`/goal` arguments.
|
||||
3. Restarting Pi after process, host, or supervisor failure; the existing Mosaic fleet/runtime
|
||||
supervisor owns process durability.
|
||||
4. Gateway, database, web UI, Discord, or cross-harness goal orchestration in this slice.
|
||||
|
||||
### User and stakeholder requirements
|
||||
|
||||
- An operator can start a goal from Pi and see its current phase, evidence, limits, and latest report.
|
||||
- The agent remains oriented after each turn and compaction until verified, paused, blocked,
|
||||
exhausted, or cancelled.
|
||||
- Local testing uses a file under `~/.config/mosaic/runtime/pi/`; the feature never writes an
|
||||
extension asset to `~/.pi/agent/extensions/`.
|
||||
- Framework updates deploy the same reviewed extension source through Mosaic's existing manifest
|
||||
sync path.
|
||||
|
||||
### Non-functional requirements
|
||||
|
||||
1. **Safety:** bounded continuation, explicit cancellation, no arbitrary command execution, and no
|
||||
completion without non-empty reported evidence.
|
||||
2. **Reliability:** serialized continuation scheduling, branch-aware restoration, compaction-safe
|
||||
context injection, and stale-timer cancellation on session shutdown.
|
||||
3. **Performance:** no extra nested judge-model request on every turn; structured reporting uses the
|
||||
active agent's final terminating tool call.
|
||||
4. **Observability:** Pi status/notifications expose phase and bounded counters without recording
|
||||
credentials or hidden model reasoning.
|
||||
5. **Maintainability:** the state machine is deterministic and behavior-tested independently from Pi
|
||||
provider/network access.
|
||||
|
||||
### Acceptance criteria
|
||||
|
||||
1. `AC-PGL-01`: A framework-sync fixture installs the extension at
|
||||
`$MOSAIC_HOME/runtime/pi/goal-extension.ts`, and launcher tests prove both Mosaic Pi extensions are
|
||||
emitted in deterministic order while absent optional files remain backward-compatible.
|
||||
2. `AC-PGL-02`: Command tests prove set/status/pause/resume/cancel behavior, active-goal replacement
|
||||
refusal, and bounded input handling.
|
||||
3. `AC-PGL-03`: Lifecycle tests prove every turn is recorded, active context is injected on every
|
||||
request, two evidence-bearing achievement reports are required, and `agent_settled` continues an
|
||||
unmet goal without duplicate scheduling.
|
||||
4. `AC-PGL-04`: Compaction and restoration tests prove goal state survives, verification is reset and
|
||||
rechecked after compaction, manual compaction continuation is deferred until idle, and tree/session
|
||||
branch state is reconstructed correctly.
|
||||
5. `AC-PGL-05`: Limit tests prove max-turn and repeated-no-progress exhaustion stop autonomous
|
||||
continuation, while pause/cancel/blocked states do not restart.
|
||||
6. `AC-PGL-06`: Focused tests, package typecheck/lint/test, repository quality gates, a local Pi load
|
||||
smoke test from `~/.config/mosaic/runtime/pi/`, independent review, and terminal-green CI pass before
|
||||
issue #1150 closes.
|
||||
|
||||
### Constraints, risks, and assumptions
|
||||
|
||||
- Dependency: Pi's extension API must continue to provide `registerCommand`, `registerTool`,
|
||||
`context`, `turn_end`, `agent_settled`, `session_compact`, session custom entries, and terminating
|
||||
tool results.
|
||||
- Risk: the working agent can overstate completion. Mitigation: structured evidence, a mandatory
|
||||
second verification pass, explicit semantic limitations, and operator-visible reports.
|
||||
- Risk: an impossible goal can consume unbounded resources. Mitigation: hard turn/no-progress bounds
|
||||
and paused terminal states.
|
||||
- Risk: automatic continuation can race compaction or session replacement. Mitigation: drive from
|
||||
`agent_settled`, defer idle restarts, generation-check timers, and clear timers on shutdown.
|
||||
- `ASSUMPTION:` Two consecutive evidence-bearing reports are the initial local verification policy;
|
||||
rationale: it provides a real recheck without doubling every turn's model cost. Future policy may
|
||||
add independent or deterministic validators.
|
||||
- `ASSUMPTION:` Default limits are 40 turns and 6 repeated no-progress reports, configurable only by
|
||||
bounded Mosaic environment settings; rationale: useful persistence with a finite autonomous budget.
|
||||
- `ASSUMPTION:` Documentation remains canonical in-repo for this slice; no external docs publication
|
||||
is requested.
|
||||
|
||||
### Testing and delivery intent
|
||||
|
||||
Use TDD for the deterministic controller and lifecycle invariants. Test with fake Pi lifecycle
|
||||
objects first, then run a local load/smoke test from the deployed Mosaic path. Deliver source, tests,
|
||||
launcher wiring, framework/runtime documentation, user/developer guides, and sitemap updates in one
|
||||
reviewed squash PR to `main` with terminal-green CI.
|
||||
|
||||
---
|
||||
|
||||
## Fleet Declarative Configuration Management Workstream (FCM, #758)
|
||||
|
||||
### Problem and objective
|
||||
@@ -268,68 +146,6 @@ lands. M0 consists only of these normative requirements, the complete task DAG,
|
||||
documentation IA checklist, and the legacy example/profile disposition inventory. Subsequent cards
|
||||
are defined in [docs/TASKS.md](./TASKS.md) and must remain one card/one PR.
|
||||
|
||||
### Fleet git identity launch propagation (#1043)
|
||||
|
||||
#### Problem and objective
|
||||
|
||||
A fleet seat can have a registered per-agent Git credential while its launched runtime process lacks
|
||||
`MOSAIC_GIT_IDENTITY`. The credential resolver then cannot select the seat identity reliably, which
|
||||
blocks repository operations on fail-closed estates and can fall through to an unrelated identity on
|
||||
estates where that refusal is not active. The objective is to make Git identity a deterministic,
|
||||
roster-derived part of the generated launch projection and prove it reaches the launched process.
|
||||
|
||||
#### Normative requirements
|
||||
|
||||
1. `FGI-REQ-01`: Every generated fleet agent projection SHALL declare
|
||||
`MOSAIC_GIT_IDENTITY=<MOSAIC_AGENT_NAME>`; a differing or unsafe identity SHALL fail closed before
|
||||
tmux launch.
|
||||
2. `FGI-REQ-02`: The clean `/usr/bin/env -i` pane boundary SHALL pass every variable declared by the
|
||||
generated projection, including `MOSAIC_GIT_IDENTITY`, to the launched runtime process.
|
||||
3. `FGI-REQ-03`: A behavioral integration test SHALL set-compare the complete generated projection
|
||||
against the launched process environment. Source-text/string-presence assertions are insufficient.
|
||||
4. `FGI-REQ-04`: Verification SHALL include RED-first evidence and a delete-the-subject mutation that
|
||||
removes Git-identity pane propagation and makes the behavioral test fail.
|
||||
|
||||
#### Acceptance criteria
|
||||
|
||||
1. `AC-FGI-01`: A launched seat process contains every key/value pair declared by its generated
|
||||
environment projection, including the roster-derived Git identity.
|
||||
2. `AC-FGI-02`: Missing, unsafe, or split Git identity is rejected before a tmux session is created.
|
||||
3. `AC-FGI-03`: Focused launcher and generated-environment tests, repository quality gates,
|
||||
independent review, and the required RED/green/R7 evidence are recorded before push.
|
||||
|
||||
### Framework shell assertion portability (#1098)
|
||||
|
||||
#### Problem and objective
|
||||
|
||||
The blocking framework-shell chain can report that a pane command omitted `/usr/bin/env -i` even when
|
||||
`-i` matched successfully. A short-circuiting `grep -q` under `set -o pipefail` may close its pipe after
|
||||
the match and cause an upstream producer to exit with SIGPIPE, turning a valid semantic result into a
|
||||
nonzero aggregate pipeline. The objective is to inspect the captured NUL-delimited argv directly and
|
||||
make failures carry the observed records needed for diagnosis.
|
||||
|
||||
#### Normative requirements
|
||||
|
||||
1. `FSP-REQ-01`: The pane-boundary test SHALL validate an adjacent `/usr/bin/env`, `-i` argv pair from
|
||||
the authoritative NUL-delimited tmux capture without a short-circuit pipeline whose upstream status
|
||||
can override a successful match.
|
||||
2. `FSP-REQ-02`: Missing, reversed, or non-adjacent boundary tokens SHALL fail, while valid boundaries
|
||||
SHALL remain valid regardless of trailing argv size, pipe capacity, process scheduling, or host/CI
|
||||
utility implementation.
|
||||
3. `FSP-REQ-03`: A failed boundary check SHALL print stable indexed, shell-escaped observed argv records
|
||||
before exiting nonzero; the fixture SHALL continue to contain generated non-secret launch data only.
|
||||
4. `FSP-REQ-04`: Verification SHALL include RED-first large-payload evidence, negative token-order
|
||||
controls, the complete focused launcher suite, canonical Woodpecker CI, and independent review.
|
||||
|
||||
#### Acceptance criteria
|
||||
|
||||
1. `AC-FSP-01`: A large captured argv with adjacent `/usr/bin/env`, `-i` passes even when the former
|
||||
`grep -q` pipeline returns nonzero from an upstream SIGPIPE.
|
||||
2. `AC-FSP-02`: Missing executable, missing flag, and detached/reversed flag fixtures return nonzero and
|
||||
emit the indexed observed argv.
|
||||
3. `AC-FSP-03`: The focused suite passes on the development host and CI image, and the merged-main
|
||||
Woodpecker pipeline is terminal green before #1098 closes.
|
||||
|
||||
---
|
||||
|
||||
## Exact Cross-Harness Fleet Communications Contract (#766)
|
||||
|
||||
@@ -14,13 +14,6 @@
|
||||
- [Skill registration user guide](guides/user-guide.md#claude-code-skill-registration) — register, unregister, list statuses, automatic install/update reconciliation, and Claude reload behavior.
|
||||
- [Skill bridge developer guide](guides/dev-guide.md#claude-code-skill-bridge) — path-validation, ownership, clobber-protection, install/update wiring, tests, and Pi/Codex scope notes.
|
||||
|
||||
## Pi persistent goals
|
||||
|
||||
- [Persistent goal user guide](guides/user-guide.md#pi-persistent-goals) — `/goal` commands, verification behavior, limits, compaction/resume semantics, and limitations.
|
||||
- [Goal extension developer guide](guides/dev-guide.md#pi-persistent-goal-extension) — framework ownership, launcher ordering, lifecycle design, tests, and local Mosaic-path smoke workflow.
|
||||
- [Goal loop operations](guides/admin-guide.md#pi-goal-loop-operations) — deployment ownership, bounded settings, pause/resume procedures, and supervisor boundary.
|
||||
- [Pi runtime reference](../packages/mosaic/framework/runtime/pi/RUNTIME.md#extensions) — deployed paths, command summary, and bounded environment settings.
|
||||
|
||||
## Fleet configuration management
|
||||
|
||||
- [Fleet configuration entry point](fleet/README.md) — desired-versus-observed decision tree and complete operator link map.
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
# 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.
|
||||
+10
-13
@@ -5,14 +5,14 @@ Generated environment files are rebuildable projections, not an operator-editabl
|
||||
|
||||
## Launch chain
|
||||
|
||||
| Layer | Responsibility |
|
||||
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Roster | `fleet/roster.yaml` supplies the agent name, class, supported runtime, model, reasoning, tool policy, workdir, and tmux socket; Git identity is derived from the exact agent name. |
|
||||
| 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. |
|
||||
| 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. |
|
||||
| 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. |
|
||||
|
||||
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,
|
||||
@@ -24,7 +24,6 @@ secret-like key names, duplicate keys, comments, quoted/export syntax, and unsaf
|
||||
|
||||
```dotenv
|
||||
MOSAIC_AGENT_NAME=<roster name>
|
||||
MOSAIC_GIT_IDENTITY=<roster name>
|
||||
MOSAIC_AGENT_CLASS=<roster class>
|
||||
MOSAIC_AGENT_RUNTIME=<roster runtime>
|
||||
MOSAIC_AGENT_MODEL=<roster model hint>
|
||||
@@ -34,10 +33,8 @@ MOSAIC_AGENT_WORKDIR=<absolute roster work directory>
|
||||
MOSAIC_TMUX_SOCKET=<roster socket or empty>
|
||||
```
|
||||
|
||||
`MOSAIC_GIT_IDENTITY` is not independently configurable: it must equal `MOSAIC_AGENT_NAME`, preventing
|
||||
split runtime and repository identity authority. 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 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.
|
||||
|
||||
|
||||
@@ -3,12 +3,11 @@
|
||||
The launcher consumes validated data, not shell configuration.
|
||||
|
||||
1. Read and validate the canonical roster.
|
||||
2. Render deterministic <name>.env.generated data from that roster, including `MOSAIC_GIT_IDENTITY` derived exactly from the roster agent name.
|
||||
2. Render deterministic <name>.env.generated data from that roster.
|
||||
3. Parse optional <name>.env.local through a strict allowlist.
|
||||
4. Reject generated-key shadowing, unknown or sensitive-looking keys, unsafe paths/values, duplicates, malformed lines, shell syntax, and command overrides.
|
||||
5. Reject a Git identity that is unsafe or differs from the generated agent name.
|
||||
6. Derive the runtime command from validated runtime/model/reasoning data and pass every generated projection entry through the clean process environment boundary.
|
||||
7. Target only the exact configured tmux socket and roster session after ownership checks.
|
||||
5. Derive the runtime command from validated runtime/model/reasoning data.
|
||||
6. Target only the exact configured tmux socket and roster session after ownership checks.
|
||||
|
||||
## File precedence and ownership
|
||||
|
||||
|
||||
@@ -35,7 +35,6 @@ values, credential material, or command text.
|
||||
|
||||
```dotenv
|
||||
MOSAIC_AGENT_NAME=<roster name>
|
||||
MOSAIC_GIT_IDENTITY=<roster name>
|
||||
MOSAIC_AGENT_CLASS=<roster class>
|
||||
MOSAIC_AGENT_RUNTIME=<roster runtime>
|
||||
MOSAIC_AGENT_MODEL=<roster model hint>
|
||||
@@ -45,9 +44,8 @@ MOSAIC_AGENT_WORKDIR=<absolute roster work directory>
|
||||
MOSAIC_TMUX_SOCKET=<roster socket or empty>
|
||||
```
|
||||
|
||||
`MOSAIC_GIT_IDENTITY` is derived from and must equal `MOSAIC_AGENT_NAME`; it is not a separate
|
||||
operator-controlled identity authority. The generated launch contract supports only `claude`, `codex`,
|
||||
`opencode`, and `pi`. fleet add uses that same runtime authority and rejects any other runtime before it writes the roster or changes
|
||||
The generated launch contract supports only `claude`, `codex`, `opencode`, and `pi`. fleet add
|
||||
uses that same runtime authority and rejects any other runtime before it writes the roster or changes
|
||||
projection, local, or quarantine files. The legacy dogfood stub on its separate `mosaic-factory`
|
||||
socket remains an observability canary; it has no generated-launch adapter and cannot be added through
|
||||
this projection path.
|
||||
|
||||
@@ -7,8 +7,7 @@
|
||||
3. [Provider Configuration](#provider-configuration)
|
||||
4. [MCP Server Configuration](#mcp-server-configuration)
|
||||
5. [Environment Variables Reference](#environment-variables-reference)
|
||||
6. [Pi Goal Loop Operations](#pi-goal-loop-operations)
|
||||
7. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
6. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
|
||||
---
|
||||
|
||||
@@ -265,16 +264,6 @@ Each OIDC provider requires its client ID, client secret, and issuer URL togethe
|
||||
| `AGENT_SYSTEM_PROMPT` | — | Platform-level system prompt injected into all sessions |
|
||||
| `AGENT_USER_TOOLS` | all tools | Comma-separated allowlist of tools for non-admin users |
|
||||
|
||||
### Mosaic Pi goal loop
|
||||
|
||||
| Variable | Default | Description |
|
||||
| ----------------------------- | ------- | -------------------------------------------------------------------- |
|
||||
| `MOSAIC_GOAL_MAX_TURNS` | `40` | Per-goal autonomous turn limit; accepted range `1..500` |
|
||||
| `MOSAIC_GOAL_MAX_NO_PROGRESS` | `6` | Consecutive identical progress-report limit; accepted range `1..100` |
|
||||
|
||||
These variables are consumed by the framework-owned Pi goal extension at goal creation. Invalid or
|
||||
out-of-range values fall back to the defaults; they do not disable the bounds.
|
||||
|
||||
### Providers
|
||||
|
||||
| Variable | Default | Description |
|
||||
@@ -385,29 +374,3 @@ Session cleanup is scoped to one session identifier and only removes that sessio
|
||||
| Variable | Default | Description |
|
||||
| ----------------------- | ----------------------------- | ------------------------------------------ |
|
||||
| `MOSAIC_WORKSPACE_ROOT` | monorepo root (auto-detected) | Root path for mission workspace operations |
|
||||
|
||||
---
|
||||
|
||||
## Pi Goal Loop Operations
|
||||
|
||||
The reviewed runtime asset is deployed at
|
||||
`~/.config/mosaic/runtime/pi/goal-extension.ts` by framework install/update. Do not install another
|
||||
copy under `~/.pi/agent/extensions/`; duplicate registration can create suffixed commands and two
|
||||
competing lifecycle controllers.
|
||||
|
||||
Operational checks:
|
||||
|
||||
1. Run `mosaic pi` and verify `/goal help` is available.
|
||||
2. Use `/goal status` to inspect phase, turn/no-progress limits, compaction checks, and evidence.
|
||||
Reports persist in Pi session data; controller-owned state redacts common credential shapes, but
|
||||
Pi's model/tool-call history is separate. Operators must not place secrets or raw sensitive output
|
||||
in goals, pause reasons, or evidence.
|
||||
3. Use `/goal pause <reason>` before planned maintenance or manual investigation. Pause and cancel
|
||||
abort the current goal-driven run when Pi is busy.
|
||||
4. Use `/goal resume` only after addressing a blocker; counters restart with the configured bounds.
|
||||
5. Use `/goal cancel` before replacing an unfinished goal.
|
||||
|
||||
A blocked or exhausted goal remains stopped and visible; Mosaic does not automatically raise its
|
||||
limits or restart the process. Framework sync owns file deployment, while Pi's native session file
|
||||
owns branch replay. Process/host restart remains the responsibility of the existing runtime or fleet
|
||||
supervisor.
|
||||
|
||||
+13
-82
@@ -9,9 +9,8 @@
|
||||
5. [Adding New MCP Tools](#adding-new-mcp-tools)
|
||||
6. [Database Schema and Migrations](#database-schema-and-migrations)
|
||||
7. [Claude Code Skill Bridge](#claude-code-skill-bridge)
|
||||
8. [Pi Persistent Goal Extension](#pi-persistent-goal-extension)
|
||||
9. [API Endpoint Reference](#api-endpoint-reference)
|
||||
10. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
8. [API Endpoint Reference](#api-endpoint-reference)
|
||||
9. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
|
||||
---
|
||||
|
||||
@@ -196,6 +195,17 @@ pnpm format:check && pnpm typecheck && pnpm lint
|
||||
|
||||
A pre-push hook enforces this mechanically.
|
||||
|
||||
### CI Publish Channels
|
||||
|
||||
Woodpecker `.woodpecker/publish.yml` keeps stable and integration-line artifacts separate:
|
||||
|
||||
| Source | npm packages | Gateway image |
|
||||
| --------------------------------- | ------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
|
||||
| `main` push/manual or release tag | committed package versions published to Gitea npm without changing the dist-tag workflow | `gateway:sha-<short>` plus `gateway:latest` on `main`, and the release tag on tag events |
|
||||
| `next` push/manual | CI-computed prereleases, `<target-stable>-next.<CI_PIPELINE_NUMBER>`, published with `npm publish --tag next` | `gateway:sha-<short>` only |
|
||||
|
||||
`next` never publishes npm `latest` or Docker `latest`. The next npm publish step verifies that `@mosaicstack/mosaic@next` resolves to the computed prerelease before the pipeline can pass.
|
||||
|
||||
---
|
||||
|
||||
## Adding New Agent Tools
|
||||
@@ -386,85 +396,6 @@ M1 intentionally manages Claude Code only. Pi's Mosaic launcher can discover the
|
||||
canonical root directly. Codex still relies on the existing full skill-sync
|
||||
linker and needs separate parity analysis before this lifecycle API is extended.
|
||||
|
||||
## Pi Persistent Goal Extension
|
||||
|
||||
The source of the Mosaic-owned Pi goal controller is:
|
||||
|
||||
```text
|
||||
packages/mosaic/framework/runtime/pi/goal-extension.ts
|
||||
```
|
||||
|
||||
The framework manifest classifies `runtime/**` as framework-owned. Both the bash installer and the
|
||||
TypeScript file adapter therefore deploy the same reviewed source to:
|
||||
|
||||
```text
|
||||
$MOSAIC_HOME/runtime/pi/goal-extension.ts
|
||||
# default: ~/.config/mosaic/runtime/pi/goal-extension.ts
|
||||
```
|
||||
|
||||
Do not copy or link this extension into `~/.pi/agent/extensions/`. The launcher function
|
||||
`discoverPiExtensionArgs()` emits the core `mosaic-extension.ts` first and the optional
|
||||
`goal-extension.ts` second, preserving compatibility with an older installed framework that does
|
||||
not have the goal file yet.
|
||||
|
||||
### Lifecycle design
|
||||
|
||||
| Pi API | Goal-controller responsibility |
|
||||
| ------------------------------ | --------------------------------------------------------------------------------- |
|
||||
| `registerCommand('goal')` | Set, inspect, pause, resume, or cancel one branch-specific goal |
|
||||
| `registerTool(...)` | Record a terminating structured progress report with evidence |
|
||||
| `context` | Inject the active goal contract before every provider request |
|
||||
| `turn_end` | Record every turn, reject mixed final reports, and enforce the turn bound |
|
||||
| `agent_settled` | Start one deduplicated continuation only after Pi has no retry/compact/queue work |
|
||||
| `session_compact` | Record the compact check, reset provisional verification, and defer idle work |
|
||||
| `session_start`/`session_tree` | Rebuild state from custom entries on the active branch |
|
||||
| `session_shutdown` | Invalidate deferred callbacks and clear UI state |
|
||||
|
||||
State is appended as `mosaic-goal-state` custom entries, which do not enter model context. The
|
||||
`context` hook creates a fresh hidden `mosaic-goal-context` message for each request instead of
|
||||
trusting compaction summaries. The `mosaic_goal_report` result uses `terminate: true`; when it is the
|
||||
sole final tool call, Pi avoids an unnecessary model response before the controller decides whether
|
||||
to verify, continue, or stop.
|
||||
|
||||
Before state is appended or displayed, the controller applies bounded credential-pattern redaction
|
||||
to the goal statement, report summary/evidence/next step, and stop reason. Fingerprints are computed
|
||||
over redacted report content. Pi session entries are append-only, so a credential-bearing legacy
|
||||
entry cannot honestly be erased by the extension: restoration fails closed, emits a warning, and
|
||||
requires removal of the affected session before setting a new goal. This is defense-in-depth rather
|
||||
than a secret-storage contract, and it does not rewrite Pi's separate model-message/tool-call
|
||||
history. Goal prompts tell the agent not to submit credentials or raw sensitive output, and tests use
|
||||
canaries to prove known forms do not reach new custom entries, status text, context, or tool details
|
||||
while ordinary typed fields such as `token: string` remain intact.
|
||||
|
||||
Completion remains evidence-gated but semantic: two consecutive `achieved` reports are required,
|
||||
and the second run is explicitly a verification pass. This avoids an extra judge-model request after
|
||||
every turn. Deterministic validator commands are intentionally not accepted as `/goal` input in this
|
||||
slice, so never describe this mechanism as proof of arbitrary natural-language completion.
|
||||
|
||||
### Tests and local smoke workflow
|
||||
|
||||
```bash
|
||||
pnpm --filter @mosaicstack/mosaic exec vitest run \
|
||||
src/runtime/pi-goal-extension.spec.ts \
|
||||
src/commands/launch.spec.ts \
|
||||
src/config/file-adapter.test.ts
|
||||
|
||||
bash packages/mosaic/framework/tools/quality/scripts/test-install-migration.sh
|
||||
```
|
||||
|
||||
For an additive local smoke test without reseeding unrelated live framework files:
|
||||
|
||||
```bash
|
||||
install -D -m 0644 \
|
||||
packages/mosaic/framework/runtime/pi/goal-extension.ts \
|
||||
~/.config/mosaic/runtime/pi/goal-extension.ts
|
||||
|
||||
pi --extension ~/.config/mosaic/runtime/pi/goal-extension.ts
|
||||
```
|
||||
|
||||
Use `/goal help`, `/goal set ...`, and `/goal status` in that test session. A released framework
|
||||
sync installs the file, and a released Mosaic CLI loads it automatically through `mosaic pi`.
|
||||
|
||||
## API Endpoint Reference
|
||||
|
||||
All endpoints are served by the gateway at `http://localhost:14242` by default.
|
||||
|
||||
+15
-57
@@ -8,10 +8,9 @@
|
||||
4. [Tasks](#tasks)
|
||||
5. [Settings](#settings)
|
||||
6. [CLI Usage](#cli-usage)
|
||||
7. [Pi Persistent Goals](#pi-persistent-goals)
|
||||
8. [Sub-package Commands](#sub-package-commands)
|
||||
9. [Telemetry](#telemetry)
|
||||
10. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
7. [Sub-package Commands](#sub-package-commands)
|
||||
8. [Telemetry](#telemetry)
|
||||
9. [Local Fleet Canary](./fleet-local-canary.md)
|
||||
|
||||
---
|
||||
|
||||
@@ -176,8 +175,18 @@ Or use the direct URL:
|
||||
bash <(curl -fsSL https://git.mosaicstack.dev/mosaicstack/stack/raw/branch/main/tools/install.sh)
|
||||
```
|
||||
|
||||
The installer places the `mosaic` binary at `~/.npm-global/bin/mosaic`. Flags for
|
||||
non-interactive use:
|
||||
The installer places the `mosaic` binary at `~/.npm-global/bin/mosaic`.
|
||||
|
||||
Install lanes:
|
||||
|
||||
| Lane | Command | Source |
|
||||
| ------------------------ | ------------------------------------- | -------------------------------------------------------------------------------------------- |
|
||||
| Stable | `bash tools/install.sh` | npm `@mosaicstack/mosaic@latest` + `main` |
|
||||
| Prerelease integration | `bash tools/install.sh --next` | Fast npm `@mosaicstack/mosaic@next` + `@mosaicstack/gateway@next`; source fallback at `next` |
|
||||
| Contributor/source build | `bash tools/install.sh --dev --ref X` | Build-from-source at the requested ref |
|
||||
|
||||
`--next` is fast-by-default from the Gitea npm `next` dist-tag and falls back to a source build at the permanent `next` branch if the dist-tag is missing or unreachable. Explicit `--ref` or `MOSAIC_REF` still wins and uses the source path.
|
||||
Flags for non-interactive use:
|
||||
|
||||
```bash
|
||||
--yes # Accept all defaults
|
||||
@@ -308,57 +317,6 @@ mosaic prdy
|
||||
mosaic quality-rails
|
||||
```
|
||||
|
||||
## Pi Persistent Goals
|
||||
|
||||
`mosaic pi` loads a Mosaic-owned goal extension from
|
||||
`~/.config/mosaic/runtime/pi/goal-extension.ts`. It is deliberately not installed in
|
||||
`~/.pi/agent/extensions/`; framework installation and updates manage it with the rest of the Mosaic
|
||||
runtime assets.
|
||||
|
||||
Start Pi, then set a goal:
|
||||
|
||||
```text
|
||||
/goal set Deliver the feature, tests, documentation, and verification evidence
|
||||
# Shorthand:
|
||||
/goal Deliver the feature, tests, documentation, and verification evidence
|
||||
```
|
||||
|
||||
Control and inspect the loop with:
|
||||
|
||||
| Command | Behavior |
|
||||
| ---------------------- | ------------------------------------------------------------------ |
|
||||
| `/goal status` | Show phase, limits, compaction checks, latest report, and evidence |
|
||||
| `/goal pause [reason]` | Stop autonomous continuation while preserving the goal |
|
||||
| `/goal resume` | Resume with fresh turn and no-progress counters |
|
||||
| `/goal cancel` | Cancel the goal and remove its active status |
|
||||
| `/goal help` | Show command help |
|
||||
|
||||
While a goal is active, Mosaic injects its contract before every Pi model request and checks every
|
||||
completed model/tool turn. The agent ends each work cycle with the structured
|
||||
`mosaic_goal_report` tool. `achieved` is provisional until a second consecutive report rechecks the
|
||||
whole goal with evidence. A continuation report or a successful compaction resets provisional
|
||||
verification.
|
||||
|
||||
Goal statements and reports are stored in Pi session data. Mosaic redacts common credential shapes
|
||||
before appending its goal-state entries and before goal tool output or `/goal status`, but
|
||||
pattern-based redaction is not a secret store. Pi's own model-message and tool-call records are
|
||||
outside that redactor. Never put tokens, passwords, private keys, connection strings, or raw
|
||||
sensitive output in a goal or report; cite the command, artifact, and pass/fail result instead.
|
||||
|
||||
The loop stops instead of running forever when it is paused, blocked, cancelled, verified, reaches
|
||||
its turn limit, or repeats the same no-progress report too many times. Defaults are 40 turns and 6
|
||||
repeated no-progress reports. Operators may lower or raise them within enforced bounds before
|
||||
launching Pi:
|
||||
|
||||
```bash
|
||||
MOSAIC_GOAL_MAX_TURNS=60 MOSAIC_GOAL_MAX_NO_PROGRESS=8 mosaic pi
|
||||
```
|
||||
|
||||
Goal state is branch-specific Pi session data. It survives compaction and session resume, but Pi's
|
||||
process still must be relaunched or supervised after a process/host failure. This initial verifier
|
||||
checks structured evidence twice; it cannot mathematically prove every arbitrary natural-language
|
||||
goal. Use explicit acceptance criteria and inspect `/goal status` for consequential work.
|
||||
|
||||
---
|
||||
|
||||
### Claude Code Skill Registration
|
||||
|
||||
@@ -1,72 +0,0 @@
|
||||
# #1099 pipefail + early-exit sweep
|
||||
|
||||
Baseline: `df4c591ab42aa1ae62c12935fdc0e772684864a0`
|
||||
|
||||
This is a site inventory, not a risk count. `FIXED` means the early-exiting consumer no longer has a piped upstream process whose SIGPIPE can become the result under `pipefail`. `NOT-LOAD-BEARING` means the pipeline status is explicitly discarded. `UNREACHABLE-AND-WHY` describes designed input, not a payload-size safety claim.
|
||||
|
||||
## Tranche 1 — runtime and general scripts
|
||||
|
||||
| Baseline site | Verdict | Construction / reason |
|
||||
| --- | --- | --- |
|
||||
| `tools/matrix-presence-harness/run.sh:38` | FIXED | nullglob array selects the first path; no pipeline |
|
||||
| `tools/e2e-install-test.sh:139` | FIXED | capture help completely, then grep via redirection |
|
||||
| `tools/install.sh:312` | FIXED | NUL `mapfile` reads all roots; count != 1 reaches the named malformed-archive diagnostic |
|
||||
| `scripts/analysis/reflect-board-history.sh:76` | FIXED | capture Git history completely, then grep via redirection |
|
||||
| `scripts/analysis/reflect-git-history.sh:67` | FIXED | grep reads from a here-string |
|
||||
| `scripts/analysis/reflect-git-history.sh:69` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/authentik/user-create.sh:72` | FIXED | jq `first(...)` reads the response directly |
|
||||
| `packages/mosaic/framework/tools/git/mutate-push-guard.sh:87` | FIXED | grep `-m1` reads the file directly; downstream `cut` consumes its complete scalar output |
|
||||
| `packages/mosaic/framework/tools/orchestrator/session-resume.sh:94` | FIXED | `mapfile` plus bounded indexed loop replaces `head` pipeline |
|
||||
| `packages/mosaic/framework/tools/prdy/prdy-status.sh:69` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:172` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:173` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:174` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:175` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:176` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:177` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/reflect-stop-hook.sh:178` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/qa/typecheck-hook.sh:16` | FIXED | Bash regex extracts the first field without a pipeline |
|
||||
| `packages/mosaic/framework/tools/qa/typecheck-hook.sh:56` | FIXED | grep and bounded sed each read from a here-string |
|
||||
| `packages/mosaic/framework/tools/tmux/send-message.sh:113` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/tmux/send-message.sh:124` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/wake/detector.sh:126` | FIXED | one awk reads the manifest directly and exits after the first exact key |
|
||||
| `packages/mosaic/framework/tools/wake/detector.sh:270` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/wake/detector.sh:278` | FIXED | grep reads from a here-string |
|
||||
| `packages/mosaic/framework/tools/wake/digest.sh:647` | FIXED | capture complete locator output, then select first line by parameter expansion |
|
||||
| `packages/mosaic/framework/tools/wake/reconcile.sh:149` | FIXED | one awk reads the manifest directly and exits after the first exact key |
|
||||
|
||||
## Explicit withdrawn / non-load-bearing sites
|
||||
|
||||
| Baseline site | Verdict | Reason |
|
||||
| --- | --- | --- |
|
||||
| `tools/install.sh:182` | NOT-LOAD-BEARING | `|| true` explicitly discards lookup status |
|
||||
| `tools/install.sh:356` | UNREACHABLE-AND-WHY | `pnpm pack` writes one matching CLI tarball into a fresh directory immediately before lookup; citation withdrawn in #1099 |
|
||||
| `tools/install.sh:357` | UNREACHABLE-AND-WHY | same fresh-directory invariant for gateway tarball; citation withdrawn in #1099 |
|
||||
| `tools/install.sh:627` | NOT-LOAD-BEARING | `|| true` explicitly discards lookup status |
|
||||
| `scripts/agent/session-start.sh:70` | NOT-LOAD-BEARING | optional scratchpad lookup has `|| true` |
|
||||
| `packages/mosaic/framework/templates/repo/scripts/agent/session-start.sh:58` | NOT-LOAD-BEARING | optional scratchpad lookup has `|| true` |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:25` | UNREACHABLE-AND-WHY | withdrawn in #1099 after designed-input reachability measurement; preserved without re-litigation |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:27` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:30` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:32` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
| `packages/mosaic/framework/tools/qa/qa-hook-stdin.sh:34` | UNREACHABLE-AND-WHY | same withdrawn designed-input finding |
|
||||
|
||||
## Tranche 2 — non-wake test harnesses
|
||||
|
||||
All 22 baseline sites below are `FIXED`; the checked-in tranche fixture is passed through the same scanner and asserts all 22 occurrences and 21 normalized identities (the same response-split line occurs twice).
|
||||
|
||||
| Baseline site(s) | Verdict | Construction |
|
||||
| --- | --- | --- |
|
||||
| `systemd/user/test-fleet-units.sh:148` | FIXED | capture tmux output, then grep via redirection |
|
||||
| `git/test-issue-comment-readback.sh:283,302` | FIXED | parameter expansion splits status/body without `head` |
|
||||
| `git/test-pr-review-gitea-comment.sh:228` | FIXED | parameter expansion splits status/body |
|
||||
| `git/test-lane-brief-pr-linkage.sh:72` | FIXED | grep reads from a here-string |
|
||||
| `git/test-pr-review-repo-host-override.sh:225-226` | FIXED | grep reads from a here-string |
|
||||
| `orchestrator/smoke-test.sh:67,72` | FIXED | parameter expansion selects first line |
|
||||
| `orchestrator/test-board-roll.sh:99-100` | FIXED | grep reads from a here-string |
|
||||
| `quality/scripts/test-upgrade-durable-snapshot.sh:180` | FIXED | complete sorted output is read with `mapfile`, then indexed |
|
||||
| `quality/scripts/test-upgrade-rollback.sh:339,356` | FIXED | direct `grep -m1` file reads; cleanup captures before testing |
|
||||
| `tmux/test-send-message-socket.sh:37,38,44-46,68,72` | FIXED | capture commands complete before redirected grep assertions |
|
||||
| `tmux/test-send-message-verdict.sh:34` | FIXED | grep reads from a here-string |
|
||||
|
||||
Remaining wake-validation sites are intentionally deferred to the final review-sized tranche and are not yet assigned a safety verdict here.
|
||||
@@ -1,229 +0,0 @@
|
||||
# #1043 — Fleet pane git-identity propagation
|
||||
|
||||
## Objective
|
||||
|
||||
Ensure a fleet seat's launched runtime process receives its roster-derived `MOSAIC_GIT_IDENTITY`, and lock the complete generated-environment propagation boundary with an enumerated set comparison.
|
||||
|
||||
## Tracking
|
||||
|
||||
- External issue: `mosaicstack/stack#1043`
|
||||
- Branch: `fix/1043-pane-git-identity`
|
||||
- Coordinator: `tl-mosaic`
|
||||
- `docs/TASKS.md`: read-only by project worker contract; not modified.
|
||||
|
||||
## Constraints
|
||||
|
||||
- RED-first bug reproducer is mandatory.
|
||||
- R7 delete-the-subject mutation must turn the behavioral test red.
|
||||
- Assert launched-process environment, not source text.
|
||||
- One push only; do not poll CI after push.
|
||||
- Run the CI queue guard immediately before push and report its `state=` line as state, not evidence.
|
||||
- Do not modify a live host launcher or obtain/copy another credential.
|
||||
- Self-post the PR, verify provider attribution, then stop.
|
||||
- Final status wording: `believed-fixed, pending jarvis validation`.
|
||||
|
||||
## Scope inventory
|
||||
|
||||
Re-derived against `origin/main` at `85d2108e`:
|
||||
|
||||
- Launch consumer: `packages/mosaic/framework/tools/fleet/start-agent-session.sh`
|
||||
- Behavioral launch test: `packages/mosaic/framework/tools/fleet/test-start-agent-session.sh`
|
||||
- Generated-environment contract/parser: `packages/mosaic/src/fleet/generated-env-boundary.ts`
|
||||
- Roster projection producers:
|
||||
- `packages/mosaic/src/commands/fleet.ts`
|
||||
- `packages/mosaic/src/fleet/fleet-reconciler.ts`
|
||||
- `packages/mosaic/src/fleet/fleet-agent-crud.ts`
|
||||
- `packages/mosaic/src/fleet/v1-v2-migration.ts`
|
||||
- Contract and producer tests discovered by repository search.
|
||||
- Generated-environment operator/developer docs and their executable documentation contract test.
|
||||
|
||||
Discrepancy sent to `tl-mosaic`: current main no longer contains the charter's `PANE_SHELL_SNIPPET`; #772 replaced it with an `/usr/bin/env -i` argv launch boundary, and current generated projections do not declare git identity. Code-read inventory is **NOT MEASURED** behavior.
|
||||
|
||||
## Plan
|
||||
|
||||
1. Add the process-environment set-comparison regression first and record RED.
|
||||
2. Add roster-derived `MOSAIC_GIT_IDENTITY=<agent name>` to the complete generated projection contract.
|
||||
3. Validate identity syntax and equality with `MOSAIC_AGENT_NAME`; pass it through the clean pane environment.
|
||||
4. Update affected projection tests and generated-environment docs.
|
||||
5. Run focused and baseline gates.
|
||||
6. Perform R7 by deleting the pane propagation entry, prove RED, restore, and prove GREEN.
|
||||
7. Run independent review, remediate, commit, queue guard, one push, self-post PR, verify provider attribution, and stop without CI polling.
|
||||
|
||||
## Budget
|
||||
|
||||
No explicit token cap was provided. Working cap: one narrow logical unit, no dependency installation unless existing tooling requires it, no unrelated refactor.
|
||||
|
||||
## Evidence log
|
||||
|
||||
### TDD and mutation evidence
|
||||
|
||||
- RED-first, repository launcher: `bash packages/mosaic/framework/tools/fleet/test-start-agent-session.sh` exited 64 on pre-fix source with `code=unknown-key key=MOSAIC_GIT_IDENTITY`. The generated seat could not launch with the required declared identity.
|
||||
- GREEN: the same repository launcher test emitted `ok - start-agent-session generated environment boundary`.
|
||||
- R7 delete-the-subject: removed only `"MOSAIC_GIT_IDENTITY=$MOSAIC_GIT_IDENTITY"` from the repository launch array; the same test exited 1 with `FAIL: runtime pane omitted or changed generated environment keys: MOSAIC_GIT_IDENTITY`.
|
||||
- R7 restoration: restored that launch entry; the same test returned green.
|
||||
- Launcher under test is explicitly `packages/mosaic/framework/tools/fleet/start-agent-session.sh` through the test's `$START`, **not** the stale installed host copy.
|
||||
|
||||
### Situational and focused tests
|
||||
|
||||
- Repository launcher boundary: green, including set comparison of all nine generated projection entries and fail-before-tmux cases for missing, unsafe, mismatched, and local-shadow Git identity.
|
||||
- Fleet systemd launcher integration: `bash packages/mosaic/framework/systemd/user/test-fleet-units.sh` — green.
|
||||
- Focused Mosaic Vitest set: 6 files, 311 tests — green.
|
||||
- `bash -n` on changed shell files — green.
|
||||
- `git diff --check` — green.
|
||||
|
||||
### Baseline gates
|
||||
|
||||
- `pnpm typecheck` — 45/45 tasks green.
|
||||
- `pnpm lint` — 25/25 tasks green.
|
||||
- `pnpm format:check` — green.
|
||||
- `pnpm test:checkout` — green.
|
||||
- Repository-wide Vitest under a hermetic current-version npm prefix: Mosaic 81/81 files and 1510/1510 tests green; other workspace test tasks shown green before the framework-shell phase.
|
||||
- Canonical `pnpm test` is not fully green on this host for unrelated environment-sensitive gates:
|
||||
1. the first two runs exposed the globally installed Mosaic 0.0.48 update banner in three CLI smoke tests expecting empty stderr;
|
||||
2. after isolating that global-version input, the framework wake assertion aborted at the known `#973` Bash `BASH_LINENO` convention check (exit 97; observed `[3 5]`, expected `[3 4]`).
|
||||
No tests were weakened or bypassed; focused changed-surface tests are green. CI remains the canonical clean-environment result and is intentionally not polled after push per charter.
|
||||
|
||||
### Independent review
|
||||
|
||||
- Codex code review first pass: request changes for missing shell rejection-path coverage.
|
||||
- Remediation: added table-driven missing/unsafe/mismatch/local-shadow launcher cases, each asserting no tmux call.
|
||||
- Codex code re-review: **approve**, no findings, confidence 0.88.
|
||||
- Codex security review: risk `none`, no findings, confidence 0.97.
|
||||
|
||||
### Acceptance criteria mapping
|
||||
|
||||
| Acceptance criterion | Evidence |
|
||||
| --- | --- |
|
||||
| AC-FGI-01: launched process receives every generated key/value | Repository launcher process-environment `comm -23` set comparison; GREEN and R7 RED evidence above |
|
||||
| AC-FGI-02: missing, unsafe, or split identity fails before tmux | Table-driven shell cases plus TypeScript generated-boundary tests |
|
||||
| AC-FGI-03: focused/baseline/review evidence recorded | Commands and review outcomes above; host-sensitive full-suite limitations stated explicitly |
|
||||
|
||||
### Documentation checklist
|
||||
|
||||
- PRD updated with #1043 requirements and acceptance criteria.
|
||||
- Fleet launch runbook, generated-env concept, and generated-env reference updated.
|
||||
- No API/OpenAPI, sitemap, user publishing target, deployment, or external docs publication change applies.
|
||||
- `docs/TASKS.md` remains unmodified per its single-writer project contract.
|
||||
|
||||
## Round 2 — PR #1073 review 97 remediation
|
||||
|
||||
### Review blocker
|
||||
|
||||
The launched-process suite was signed-excluded from CI enumeration. Manual GREEN/R7 evidence therefore did not prove a PR workflow could detect regression.
|
||||
|
||||
### RED-first and canonical wiring
|
||||
|
||||
1. Removed the suite's signed exclusion before adding a CI execution path.
|
||||
2. `check-test-enumeration.sh` went RED with exact `UNENUMERATED` output for `test-start-agent-session.sh`: population 49, enumerated 30, excluded 18.
|
||||
3. Added both `framework/tools/fleet/test-start-agent-session.sh` and `framework/systemd/user/test-fleet-units.sh` to `@mosaicstack/mosaic`'s canonical `test:framework-shell` chain.
|
||||
4. The guard returned GREEN: population 49, enumerated 32, excluded 18, surfaces 45. The systemd suite is outside the guard's tools-only population but now has the same explicit canonical execution disposition.
|
||||
|
||||
### Workflow-level R7
|
||||
|
||||
- Deleted only the pane launch entry `"MOSAIC_GIT_IDENTITY=$MOSAIC_GIT_IDENTITY"`.
|
||||
- Ran the exact `.woodpecker/ci.yml` test-step command, `pnpm test`, with only a temporary PATH-scoped npm shim reporting the checkout's current 0.0.49 version so the unrelated global 0.0.48 banner could not preempt the shell chain.
|
||||
- Result: exit 1 at `@mosaicstack/mosaic#test`, with the enumeration guard GREEN followed by `FAIL: runtime pane omitted or changed generated environment keys: MOSAIC_GIT_IDENTITY`.
|
||||
- Restored the launch entry. The canonical `test:framework-shell` chain then reached both newly wired suites and printed both GREEN markers before the known unrelated #973 host-only `BASH_LINENO` abort.
|
||||
- An actual provider PR workflow on the intentionally broken mutant is **NOT MEASURED**: the one-push constraint forbids pushing a red mutant and then a repaired head. Local execution proves the exact PR workflow command and dependency chain go RED on the subject deletion; CI on the repaired pushed head remains canonical.
|
||||
|
||||
### Workflow population
|
||||
|
||||
- **DEFINED:** 3 workflows (`ci.yml`, `ci-image.yml`, `publish.yml`).
|
||||
- **ELIGIBLE for `pull_request`:** 1/3 (`ci.yml`), based on top-level `when:` clauses.
|
||||
- **REPORTED:** Round-1 exact-head provider read reported 1/1 eligible context (`ci/woodpecker/pr/ci`). Post-remediation-head reported count is **NOT MEASURED** by this seat because CI polling is prohibited; workflow definitions and eligibility did not change.
|
||||
|
||||
### Independent remediation review
|
||||
|
||||
- First Round-2 review identified a CI-image blocker: the newly wired launcher suite used Perl, which the Alpine CI base does not install.
|
||||
- Replaced the suite's three Perl-only fixture mutations with POSIX/BusyBox-compatible `sed -i` substitutions; production behavior and assertions are unchanged.
|
||||
- Codex re-review: **APPROVE**, confidence 0.93, no findings.
|
||||
|
||||
### Vitest denominator reconciliation
|
||||
|
||||
The PR's `311/311` is correct for its explicitly named six-file command at both the original and remediation worktrees:
|
||||
|
||||
- generated environment boundary: 24
|
||||
- fleet documentation: 23
|
||||
- Tess service profile: 6
|
||||
- fleet regen command: 27
|
||||
- fleet agent CRUD command: 22
|
||||
- fleet command: 209
|
||||
- total: **311**
|
||||
|
||||
Review 97 reported 312/312 without naming its six files. That is a different or miscounted population and cannot replace the command-scoped 311 denominator; the PR follow-up will name the exact files and arithmetic.
|
||||
|
||||
## Round 3 — Alpine stale-marker portability
|
||||
|
||||
### Objective and plan
|
||||
|
||||
- Replace the GNU-only relative-date fixture with a deterministic POSIX/BusyBox timestamp while preserving the required stale-marker assertion.
|
||||
- Re-run the launcher suite in the canonical `ci-base:latest` Alpine image, then run applicable repository gates and independent review.
|
||||
- Update the PR body to name the repeated GNU-host/Alpine-CI portability pattern, run the mandatory queue guard, push once, verify provider attribution, and stop without CI polling.
|
||||
- Working budget: 8K tokens; scope is one fixture line plus delivery evidence. No production behavior changes.
|
||||
|
||||
### RED-first evidence
|
||||
|
||||
Before the fix, the canonical CI image command
|
||||
`docker run --rm -v "$PWD:/work" -w /work git.mosaicstack.dev/mosaicstack/stack/ci-base:latest bash packages/mosaic/framework/tools/fleet/test-start-agent-session.sh`
|
||||
exited 1 at the stale-marker setup with exact BusyBox output
|
||||
`touch: invalid date '10 seconds ago'`. The prior fresh-marker assertions had already executed, matching pipeline 2233's failure location.
|
||||
|
||||
### Root cause and fix
|
||||
|
||||
The test used GNU `touch -d` relative-date parsing although the PR workflow runs on Alpine/BusyBox. The fixture now uses POSIX `touch -t 200001010000.00`, a fixed timestamp that is unconditionally stale; the stale assertion remains mandatory and was not made tolerant of missing timestamp metadata.
|
||||
|
||||
### Structural pattern
|
||||
|
||||
This is the third GNU-host/Alpine-CI portability defect in the lane: GNU `grep` multi-match counting, Perl-only fixture mutation, and GNU `touch -d` date parsing. The repeated cause is shell suites authored on a GNU host but executed in an Alpine CI image; durable prevention belongs in CI-image execution or portability lint, not assertion weakening.
|
||||
|
||||
### GREEN and quality evidence
|
||||
|
||||
- Focused launcher suite in `ci-base:latest`: exit 0, `ok - start-agent-session generated environment boundary`.
|
||||
- Canonical test step in `ci-base:latest` with the pipeline's `pgvector/pgvector:pg17` service, readiness check, migration, and `pnpm test`: exit 0; 46/46 Turbo tasks; Mosaic 81/81 files and 1510/1510 tests; Gateway 57 passed/5 skipped files and 629 passed/11 skipped tests; enumeration 49 population / 32 enumerated / 18 signed exclusions / 45 named surfaces.
|
||||
- The first image-only `pnpm test` attempt lacked the pipeline PostgreSQL service and failed only on connection refusal after the launcher suite was GREEN. The rerun supplied the canonical service precondition and passed.
|
||||
- Canonical-image baseline: typecheck 45/45 tasks, lint 25/25 tasks, format check GREEN; `git diff --check` GREEN.
|
||||
- Independent Codex code review: APPROVE, confidence 0.96, 2/2 Round-3 files, no findings.
|
||||
- Independent Codex security review: risk none, confidence 0.99, 2/2 Round-3 files, no findings.
|
||||
|
||||
### Re-derived inventory and denominators
|
||||
|
||||
- Round-3 git delta: **2/2 files** — launcher suite and task scratchpad; 25 insertions / 1 deletion before evidence finalization.
|
||||
- Full PR path inventory against `origin/main` at `85d2108e`: **19/19 changed paths**; Round 3 adds no new PR path.
|
||||
- Workflow definition population: **1/3 pull-request-eligible** (`ci.yml` of `ci.yml`, `ci-image.yml`, `publish.yml`).
|
||||
- Do not re-litigate the settled 311/312 populations; both are valid for their separately named Tess6 and CRUD-core7 sets.
|
||||
|
||||
## Round 4 — bound stale-marker observation
|
||||
|
||||
### Objective and plan
|
||||
|
||||
- Make the heartbeat assertion discriminate an initially stale native marker from a fresh marker without changing the production staleness threshold or shortening the polling window.
|
||||
- Freeze only the sidecar's numeric observation clock during the stale-fixture arm so elapsed assertion time cannot turn a fresh mutant stale.
|
||||
- Prove two independent mutants RED: disable production stale-marker detection while retaining the stale fixture; replace the stale fixture with a fresh marker. Restore the tree and prove GREEN in the canonical Alpine image.
|
||||
- Re-derive the changed-path inventory, run applicable quality and independent review gates, commit with environment-only author/committer identity, queue-guard, push once, verify provider attribution using curl stdin config, and stop without CI polling.
|
||||
- Working budget: 8K tokens. Scope is the launcher test and its scratchpad evidence; production launcher behavior remains unchanged.
|
||||
|
||||
### Root cause and bounded observation
|
||||
|
||||
The 30 × 0.1-second assertion window overlaps the production `now - marker > interval * 2 + 1` threshold at interval 1. Depending on second boundaries and load, a fresh marker can age past the threshold before the assertion ends. A focused pre-fix fresh-mutant attempt returned RED while Review 101's full-suite run returned GREEN; the differing result is itself timing dependence, not a discriminating assertion.
|
||||
|
||||
The test now supplies a fixed numeric epoch only to the stale-fixture sidecar. Its real marker mtime is still read from the filesystem, but assertion runtime cannot advance `now`. Date formatting still delegates to the image's real `/bin/date`. Neither the production threshold nor the 30 × 0.1-second polling window changed.
|
||||
|
||||
### Two-mutant RED / restored GREEN
|
||||
|
||||
All three runs used `git.mosaicstack.dev/mosaicstack/stack/ci-base:latest`:
|
||||
|
||||
1. **Stale-detection mutant RED:** replaced only the production stale-age predicate with `false` while retaining the fixed stale marker; suite exit 1 with `FAIL: heartbeat sidecar did not resume after native marker became stale or absent`.
|
||||
2. **Fresh-marker mutant RED:** replaced only `touch -t 200001010000.00` with fresh `touch`; suite exit 1 with the same failed stale-resumption assertion. The fixed observation epoch kept the mutant fresh throughout all 30 polls.
|
||||
3. **Restored tree GREEN:** suite exit 0 with `ok - start-agent-session generated environment boundary`.
|
||||
|
||||
### Re-derived inventory
|
||||
|
||||
- Round-4 delta: **2/2 files** — launcher test plus task scratchpad; production launcher delta is empty.
|
||||
- Full PR inventory against `origin/main`: **19/19 paths**; Round 4 adds no path.
|
||||
- Production stale threshold remains `now - marker > iv * 2 + 1`; assertion polling remains 30 × 0.1 seconds.
|
||||
- Review 101's confirmed enumeration/workflow/CI and attribution evidence is accepted without re-polling or re-derivation.
|
||||
|
||||
## Residual risk
|
||||
|
||||
- Landing on `main` does not update the currently installed host launcher. Host framework installation/reseed and Jarvis live-seat validation are separate downstream events.
|
||||
- Canonical CI result is pending and will not be polled by this seat.
|
||||
@@ -1,97 +0,0 @@
|
||||
# #1098 — Framework shell portability / red main
|
||||
|
||||
## Objective
|
||||
|
||||
Restore terminal-green `main` by making the `test-start-agent-session.sh` clean-environment assertion semantic and portable without removing either newly enumerated framework-shell suite.
|
||||
|
||||
## Scope
|
||||
|
||||
- Tracking issue: `mosaicstack/stack#1098`
|
||||
- Branch: `fix/framework-shell-portability`
|
||||
- Base: `origin/main` at `4fa2768962702d53e16e8b67ee6ad52ebcb0910e`
|
||||
- Primary file: `packages/mosaic/framework/tools/fleet/test-start-agent-session.sh`
|
||||
- Requirements source: `docs/PRD.md` § Framework shell assertion portability (#1098)
|
||||
- Out of scope: deployed files under `~/.config/mosaic`, pnpm-store cleanup, checkout deletion, and changes to the launcher’s `/usr/bin/env -i` behavior.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
1. The test inspects the captured NUL-delimited tmux argv semantically and accepts an adjacent `/usr/bin/env`, `-i` pair regardless of trailing payload size or pipe scheduling.
|
||||
2. Missing `/usr/bin/env`, missing `-i`, and non-adjacent `-i` remain failures.
|
||||
3. Failure output includes the observed argv records with stable indexes and shell escaping; it exposes no credentials because this fixture supplies only generated non-secret launch data.
|
||||
4. The focused suite passes on the dev host and in the repository CI image; the blocking PR/main pipeline returns terminal green.
|
||||
5. Independent review passes; PR is squash-merged and #1098 is closed only after merged-main CI is terminal green.
|
||||
|
||||
## Budget
|
||||
|
||||
- ASSUMPTION: 30K-token working budget; rationale: one shell-test defect plus full PR/CI lifecycle.
|
||||
- Auto-reduction: focused shell and package gates first; rely on canonical Woodpecker for the full monorepo suite rather than duplicating a dependency install under constrained `/home`.
|
||||
- Disk baseline before clone/build: `/home` 7.1G free (99% used), `/tmp` 2.4G free (92% used).
|
||||
|
||||
## Investigation
|
||||
|
||||
### First-hand CI evidence
|
||||
|
||||
- Public log: `GET https://ci.mosaicstack.dev/api/repos/47/logs/2269/53041`
|
||||
- Decoded 1,436 entries (11 null `data` entries treated as empty log rows), 190,756 bytes.
|
||||
- Failure: `FAIL: pane command did not clear its environment` immediately after the expected pane-PID warning.
|
||||
- BusyBox primitives, complete assertion pipeline, real CI image, stale/current image digests, Turbo cache masking, gateway failure, and heartbeat-sidecar concurrent writing were independently excluded.
|
||||
|
||||
### Root cause
|
||||
|
||||
The assertion ends in:
|
||||
|
||||
```bash
|
||||
printf '%s\n' "$pane_args" | tail -n +"$after_pane_env" | grep -qxF -- '-i'
|
||||
```
|
||||
|
||||
The script has `set -o pipefail`. `grep -q` exits as soon as it finds the valid `-i` record. Upstream `tail`/`printf` can then receive SIGPIPE, making the aggregate pipeline nonzero even though grep returned 0 and the semantic property is true. This depends on payload size, pipe capacity, and scheduling, explaining a local/image pass with a CI failure.
|
||||
|
||||
Discriminating stress control with `/usr/bin/env` followed immediately by `-i`:
|
||||
|
||||
- 8,192-byte trailing payload: `printf=0 tail=0 grep=0`, aggregate 0.
|
||||
- 16,384-byte trailing payload: `printf=0 tail=141 grep=0`, aggregate 141.
|
||||
- 32,768+ bytes: `printf=141 tail=141 grep=0`, aggregate 141.
|
||||
- A full-reading `grep -xF` control remained 0 for every payload.
|
||||
|
||||
This is a third branch omitted by the earlier present-vs-corrupted split: the pair can be present and intact while `pipefail` reports an upstream SIGPIPE.
|
||||
|
||||
## TDD plan
|
||||
|
||||
1. RED: preserve the one-off stress reproducer above and add an automated large-argv semantic regression that fails under the current pipeline implementation.
|
||||
2. GREEN: parse the authoritative NUL-delimited capture into a Bash array and search for an adjacent `/usr/bin/env`, `-i` pair without a short-circuit pipeline.
|
||||
3. Add negative controls for missing, detached, and reversed tokens.
|
||||
4. On failure, print indexed `%q` argv records before returning nonzero.
|
||||
5. Run focused suite, mutation controls, shell syntax/format checks, then repository baseline gates feasible without dependency installation.
|
||||
6. Independent review, queue guard, push, PR, CI, coordinator merge authorization, squash merge, merged-main CI, issue close.
|
||||
|
||||
## Progress
|
||||
|
||||
- [x] Checkout created and based on `origin/main` `4fa27689`.
|
||||
- [x] CI log decoded directly.
|
||||
- [x] Root-cause stress control reproduced semantic match + aggregate pipeline failure.
|
||||
- [x] RED evidence: intact `/usr/bin/env`, `-i` fixture produced component statuses `0/141/0` and aggregate 141 under the former `grep -q` pipeline; full-reading semantic control stayed 0.
|
||||
- [x] GREEN implementation: direct NUL-argv adjacency parser, indexed diagnostics, and full-reading scalar predicates replace all load-bearing early-exit pipelines in this test.
|
||||
- [x] Baseline/situational tests:
|
||||
- focused launcher suite: PASS on GNU host and cached Alpine CI image;
|
||||
- paired `test-fleet-units.sh`: PASS;
|
||||
- enumeration guard: PASS (`population=53`, `enumerated=36`, `excluded=18`), 14/14 mutation needles;
|
||||
- `bash -n`, ShellCheck, `git diff --check`: PASS;
|
||||
- static denominator after change: zero load-bearing `grep -q`/`head`/`-m1` pipeline candidates in `test-start-agent-session.sh`;
|
||||
- delete-the-subject mutation removing production `-i`: RED with 78 indexed argv records, byte count, and explicit boundary failure.
|
||||
- [x] Independent review:
|
||||
- first Codex review: request changes — negative fixtures did not each assert diagnostics;
|
||||
- remediation: centralized predicate + diagnostic wrapper and exercised all four negative fixtures;
|
||||
- second Codex review: APPROVE, 0 blockers/should-fix/suggestions;
|
||||
- Codex security review: risk none, 0 findings.
|
||||
- [ ] PR CI, formal fleet review, merge, merged-main CI, issue closure.
|
||||
|
||||
## Documentation disposition
|
||||
|
||||
- Updated canonical `docs/PRD.md` with FSP requirements and acceptance criteria.
|
||||
- This is an internal test/reliability change with no API, user workflow, deployment, navigation, or publishing-surface change; no user/admin/API/sitemap update is required.
|
||||
- `docs/TASKS.md` remains unchanged because the project contract makes it orchestrator-only.
|
||||
|
||||
## Risks
|
||||
|
||||
- The CI failure did not print its captured argv, so the exact CI payload is unavailable. The stress control proves the assertion is non-portable and can emit the exact false verdict; branch CI is the canonical confirmation that replacing it resolves pipeline 2269’s failure class.
|
||||
- Printing fixture argv is safe only while this test’s projection remains non-secret. The diagnostic must stay scoped to the test capture and shell-escaped.
|
||||
@@ -1,37 +0,0 @@
|
||||
# #1099 — pipefail + early-exit sweep
|
||||
|
||||
## Scope and decisions
|
||||
|
||||
- Baseline `df4c591ab42aa1ae62c12935fdc0e772684864a0`, after #1100 removed its 35 sites.
|
||||
- Split into review-sized non-closing tranches: runtime/general; tmux/git/quality tests; wake validation/tests.
|
||||
- Do not equate class membership with demonstrated risk. Do not use payload size or pipeline stage count as a safety proxy.
|
||||
- Preserve the issue's withdrawn findings for `qa-hook-stdin.sh` and the two fresh-directory `pnpm pack` lookups. Fix `install.sh:312` because malformed multi-root input must reach its named handler.
|
||||
|
||||
## Tranche 1 TDD
|
||||
|
||||
RED-first control: `node --test scripts/pipefail-early-exit.test.mjs` reported exactly 26 non-accepted runtime/general sites, including `install.sh:312`, and exited 1. A checked-in fixture generated from immutable baseline `df4c591a` records all 26 normalized sites; the control passes every fixture entry through the same scanner, asserts exact identity/count/uniqueness, and separately requires zero findings in the current tree. It also inventories accepted sites rather than silently excluding whole files.
|
||||
|
||||
Construction choices:
|
||||
|
||||
- here-string/file redirection for scalar grep assertions;
|
||||
- full capture then parameter expansion for first-line selection;
|
||||
- arrays/`mapfile` for complete populations;
|
||||
- direct jq/awk/grep selection where one tool can express the property;
|
||||
- no `|| true` added to a load-bearing assertion.
|
||||
|
||||
Site-by-site verdicts: `docs/reports/quality/1099-pipefail-sweep.md`.
|
||||
|
||||
## Tranche 2 TDD
|
||||
|
||||
Expanded the unconditional scanner over 11 non-wake test harnesses. RED named exactly 22 source lines; a second immutable-baseline fixture now asserts those 22 entries through the same scanner. Rewrites preserve command status by capturing producers before redirected assertions, use parameter expansion for line selection, and use complete `mapfile` populations where ordering matters. Current-tree finding count is zero for tranches 1 and 2.
|
||||
|
||||
## Verification so far
|
||||
|
||||
- `bash -n` on every changed shell script: pass.
|
||||
- structural Node control: pass.
|
||||
- `test-mutate-push-guard.sh`: 8/8 pass.
|
||||
- `test-send-message-verdict.sh`: 3/3 pass.
|
||||
- `test-send-message-socket.sh`: pass.
|
||||
- Independent review 143 found two semantic regressions: a help-probe `|| true` changed the failure truth table, and an unguarded Git capture changed non-Git data-dir behavior from rc 0 + JSON to silent rc 128. Both received RED-first regressions before correction; help status is now separate and required, and Git status remains condition-guarded.
|
||||
- Wake detector/reconcile/digest/preimage suites terminate at their existing fail-closed #973 `BASH_LINENO` environment probe (exit 97, observed `[3 5]`, expected `[3 4]`) before subject tests. No bypass or skip was used; canonical CI remains required.
|
||||
- ShellCheck reports only pre-existing source-following, unused-variable, and untouched `ls | head` findings; no new diagnostic was introduced.
|
||||
@@ -1,156 +0,0 @@
|
||||
# #1150 — Pi persistent goal extension
|
||||
|
||||
- **Task ID:** ISSUE-1150 (no `docs/TASKS.md` row; that file is orchestrator-only)
|
||||
- **Issue:** #1150 — `pi: add persistent /goal controller extension to Mosaic framework`
|
||||
- **Branch:** `feat/1150-pi-goal-extension`
|
||||
- **Mode:** Delivery
|
||||
- **Status:** in progress
|
||||
|
||||
## Objective
|
||||
|
||||
Build and locally validate a Mosaic-owned Pi `/goal` extension. Source must ship from
|
||||
`packages/mosaic/framework/runtime/pi/`, framework sync must deploy it under
|
||||
`~/.config/mosaic/runtime/pi/`, and no extension/configuration asset may be written into `~/.pi`.
|
||||
Pi's native session manager remains the owner of session entries.
|
||||
|
||||
## Scope and acceptance source
|
||||
|
||||
- Canonical requirements: `docs/PRD.md`, section **Pi Persistent Goal Loop (#1150)**.
|
||||
- User intent: continuous goal orientation and status checking after each Pi turn and compaction,
|
||||
tested locally before framework delivery.
|
||||
- Documentation target: canonical in-repo user/developer/runtime docs; no external publication.
|
||||
|
||||
## Assumptions
|
||||
|
||||
- `ASSUMPTION:` Initial semantic verification uses two consecutive structured, evidence-bearing
|
||||
reports from the working agent rather than a second model request after every turn. This keeps the
|
||||
loop testable and avoids doubling model cost while making the limitation explicit.
|
||||
- `ASSUMPTION:` Default autonomous bounds are 40 turns and 6 repeated no-progress reports, with only
|
||||
bounded numeric environment overrides.
|
||||
- `ASSUMPTION:` A local smoke copy to `~/.config/mosaic/runtime/pi/goal-extension.ts` is authorized by
|
||||
the user's explicit request. Full framework reseed into the live home is not required for the smoke
|
||||
test and would touch unrelated framework-owned files.
|
||||
|
||||
## Budget
|
||||
|
||||
- Working estimate: 30K implementation/review tokens.
|
||||
- Hard user cap: none stated.
|
||||
- Cost control: deterministic fake-Pi tests; no nested evaluator calls; only bounded arithmetic/load
|
||||
smoke workflows against the installed runtime.
|
||||
|
||||
## Plan
|
||||
|
||||
1. Update PRD and create tracking/scratchpad artifacts.
|
||||
2. Read launcher, installer ownership, Pi extension, and documentation surfaces.
|
||||
3. TDD: add fake-Pi behavior tests for commands, state restoration, turn checks, compaction, limits,
|
||||
verification, and continuation deduplication.
|
||||
4. Implement `runtime/pi/goal-extension.ts` and deterministic launcher discovery.
|
||||
5. Add framework-sync/deployment acceptance coverage.
|
||||
6. Update user, developer, runtime, framework README, and sitemap documentation.
|
||||
7. Run focused tests, local Mosaic-path smoke test, then baseline repository gates.
|
||||
8. Run independent review, remediate, commit, push/PR/CI/merge/issue closure per delivery gates.
|
||||
|
||||
## TDD decision
|
||||
|
||||
Applied. The continuation state machine and lifecycle scheduling are control-path logic where a race
|
||||
or false terminal state can cause unbounded work or premature completion.
|
||||
|
||||
## Progress checkpoints
|
||||
|
||||
- [x] Issue #1150 created through Mosaic wrapper.
|
||||
- [x] Isolated worktree created from `origin/main`.
|
||||
- [x] PRD requirements and acceptance criteria added.
|
||||
- [x] Task scratchpad created.
|
||||
- [x] RED controller and security-regression tests written and observed failing before implementation.
|
||||
- [x] Goal controller, launcher discovery, framework deployment coverage, and bounded state machine
|
||||
implemented.
|
||||
- [x] User, admin, developer, runtime, adapter, README, and sitemap documentation updated.
|
||||
- [x] Final source copied additively to `~/.config/mosaic/runtime/pi/goal-extension.ts`; source and
|
||||
deployed SHA-256 are identical.
|
||||
- [x] Live Pi RPC smoke from the exact Mosaic path reached `achieved` with two verification passes and
|
||||
no extension errors.
|
||||
- [x] Baseline and situational checks completed, except the explicitly documented unavailable
|
||||
PostgreSQL-only root integration case.
|
||||
- [x] Independent code and OWASP/security reviews completed; all findings remediated and re-reviewed.
|
||||
- [ ] Commit, push, PR, terminal-green CI, squash merge, and issue closure complete.
|
||||
|
||||
## Tests and evidence
|
||||
|
||||
### Situational
|
||||
|
||||
- `pnpm --filter @mosaicstack/mosaic exec vitest run src/runtime/pi-goal-extension.spec.ts`
|
||||
- final: 25 passed.
|
||||
- Covers commands, per-turn checks, context injection, two-pass verification, mixed-report
|
||||
rejection, bounded limits, compaction, branch restore, stale timers, credential redaction,
|
||||
typed-field false-positive protection, and append-only legacy-state fail-closed behavior.
|
||||
- Final focused launcher/controller/file-adapter run: 3 files / 67 tests passed.
|
||||
- Final V8 coverage for `framework/runtime/pi/goal-extension.ts`:
|
||||
- 99.17% statements/lines, 93.78% branches, 100% functions.
|
||||
- Installer migration fixture: 24 passed and byte-compared the deployed framework asset.
|
||||
- Standalone extension TypeScript check against installed Pi 0.84.1 types passed:
|
||||
`pnpm --filter @mosaicstack/mosaic exec tsc --noEmit --pretty false --module NodeNext
|
||||
--moduleResolution NodeNext --target ES2022 --skipLibCheck framework/runtime/pi/goal-extension.ts`.
|
||||
- Live deployment/load evidence:
|
||||
- source/deployed SHA-256:
|
||||
`1f0a3806e0948ad5f49684273a7e535e9880c148f7fd16d13ee487fcd601f637`.
|
||||
- `get_commands` identified `/goal` as an extension command sourced from
|
||||
`~/.config/mosaic/runtime/pi/goal-extension.ts`; `/goal help` succeeded; zero extension errors.
|
||||
- live arithmetic goal ended `achieved`, verification `2/2`, with 3 goal reports / 3 agent starts
|
||||
and zero extension errors.
|
||||
- no goal extension exists under `~/.pi` extension paths.
|
||||
|
||||
### Baseline
|
||||
|
||||
- `pnpm build`: passed before the final framework-only redaction remediation; the extension is not a
|
||||
package build input and its final source passed the standalone Pi type check.
|
||||
- `pnpm typecheck`: 45/45 tasks passed.
|
||||
- `pnpm lint`: 25/25 tasks passed.
|
||||
- `pnpm format:check`: passed.
|
||||
- Final Mosaic package components:
|
||||
- Vitest: 82 files / 1,539 tests passed.
|
||||
- full `test:framework-shell` harness passed.
|
||||
- the discovered pre-existing tmux loader-marker race was reproduced with constructor PID
|
||||
evidence, fixed with a pane readiness/FIFO barrier, passed 3 consecutive focused runs, and passed
|
||||
in the full shell harness.
|
||||
- one combined rerun encountered the separate existing real-lease probe TOCTOU in
|
||||
`install-ordering-guard.spec.ts`; an earlier final Vitest run was fully green and the changed
|
||||
focused suites remained green.
|
||||
- Gateway safe baseline excluding the prohibited PostgreSQL-only fixture: 55 files / 600 tests passed
|
||||
(6 files / 12 tests skipped by their existing environment gates).
|
||||
- Root `pnpm test` reached 43 successful workspace tasks and all changed-package Vitest tests, but
|
||||
the unchanged `apps/gateway/src/__tests__/cross-user-isolation.test.ts` afterAll hook retried a
|
||||
PostgreSQL connection and failed authentication (`28P01`). This checkout explicitly forbids local
|
||||
PostgreSQL startup/access; the failure is unrelated to #1150 and cannot be remediated by starting
|
||||
the database. The gateway suite excluding that PostgreSQL-only file and required CI are used as
|
||||
the safe verification paths.
|
||||
|
||||
### Independent review
|
||||
|
||||
- Codex code review: approved, 0 findings across 15 files.
|
||||
- Initial Codex security review: one medium CWE-532/A09 finding for raw report persistence.
|
||||
- Remediation added central credential-pattern redaction, prompt/docs guidance, canary tests, typed
|
||||
field false-positive guards, and sticky fail-closed restore for credential-bearing append-only
|
||||
history.
|
||||
- Codex security re-review: risk `none`, 0 findings, confidence 0.87.
|
||||
- Focused remediation review findings were fixed; final focused re-review verdict: `APPROVE`.
|
||||
- Focused independent review of the tmux readiness barrier: `APPROVE`, no actionable findings.
|
||||
|
||||
## Risks and blockers
|
||||
|
||||
- Live `~/.config/mosaic` is shared by active Pi/fleet processes. Local deployment remained a single
|
||||
additive framework file and did not reload or restart unrelated sessions.
|
||||
- Completion verification is semantic, not mathematical: the active agent supplies structured
|
||||
evidence twice. Operators must still inspect consequential outcomes.
|
||||
- Credential redaction is pattern-based defense-in-depth, not a secret store. It covers
|
||||
controller-owned state/status/tool details, not Pi's separate model-message/tool-call history.
|
||||
Goals and reports must never contain real secrets or raw sensitive output. Because Pi session
|
||||
entries are append-only, a detected credential-bearing legacy branch fails closed and the affected
|
||||
session must be removed.
|
||||
- Current installed Pi is newer than the repository's historical gateway Pi dependency. The
|
||||
extension was checked and smoke-tested against installed Pi 0.84.1 using stable documented APIs.
|
||||
- Local root testing cannot safely execute the unchanged PostgreSQL-only integration fixture under
|
||||
the checkout's explicit database safety constraints. Terminal-green PR CI remains mandatory before
|
||||
merge.
|
||||
- The unchanged real-lease default-probe test can observe different broker availability across its two
|
||||
sequential probes; one combined package rerun hit that existing TOCTOU. The same final Vitest suite
|
||||
passed in a separate run, and CI remains the merge authority.
|
||||
@@ -0,0 +1,38 @@
|
||||
# Scratchpad — FED-M3-06 get verb
|
||||
|
||||
## Objective
|
||||
|
||||
Implement `POST /api/federation/v1/get/:resource/:id` for M3 inbound federation reads.
|
||||
|
||||
## Scope
|
||||
|
||||
- `apps/gateway/src/federation/server/verbs/get.controller.ts`
|
||||
- `apps/gateway/src/federation/server/verbs/get-query.service.ts`
|
||||
- Unit coverage for controller pipeline + query service RBAC guardrails
|
||||
- Register controller/service in `FederationModule`
|
||||
|
||||
## Plan
|
||||
|
||||
1. Mirror the list verb pipeline: `FederationAuthGuard` → `FederationScopeService` → read-only query service.
|
||||
2. Return one `_source: "local"` tagged item on success.
|
||||
3. Return federation error envelopes:
|
||||
- `404 not_found` when the resource id does not exist.
|
||||
- `403 scope_violation` when the row exists but falls outside native RBAC/scope intersection.
|
||||
- `400 invalid_request` for malformed ids/scope requests.
|
||||
4. Keep read audit persistence deferred to M4; no body or response persistence in M3.
|
||||
|
||||
## Verification Evidence
|
||||
|
||||
- Rebased onto `origin/main` at `86e106fcc9a1dfa3a18f7846bb477be128794aad` after M3-05 merged; resolved `FederationModule` by registering both list and get verb controllers/services.
|
||||
- Review-change coverage added for comment 15971:
|
||||
- get note access now requires subject ownership AND authorized mission intersection.
|
||||
- missing federation context returns structured `401 unauthorized` envelope.
|
||||
- unsupported get resources fail closed with structured denial.
|
||||
- PGlite regressions cover cross-user note exclusion and subject-note unauthorized-mission exclusion.
|
||||
- `pnpm --filter @mosaicstack/gateway test -- src/federation/server/verbs/__tests__/get.controller.spec.ts src/federation/server/verbs/__tests__/get-query.service.spec.ts` — pass (2 files / 17 tests; re-run after review changes).
|
||||
- `pnpm --filter @mosaicstack/gateway build` — pass (re-run after review changes).
|
||||
- `pnpm build` — pass (23 successful tasks before review changes).
|
||||
- `pnpm typecheck` — pass (41 successful tasks; re-run after review changes).
|
||||
- `pnpm lint` — pass (23 successful tasks; re-run after review changes).
|
||||
- `pnpm format:check` — pass (re-run after review changes).
|
||||
- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings after review changes.
|
||||
@@ -0,0 +1,82 @@
|
||||
# B1 / @next Durable Publish Pipeline — Design
|
||||
|
||||
## Objective
|
||||
|
||||
Make `next` a durable integration line that publishes the artifacts required by downstream federation boot tests without manual builds.
|
||||
|
||||
Every merge to `next` publishes:
|
||||
|
||||
1. **npm prerelease packages** to the Gitea npm registry with dist-tag `next`.
|
||||
2. **Gateway container image** tagged only as `gateway:sha-<short>`.
|
||||
|
||||
The existing stable release behavior remains isolated to `main` / tags.
|
||||
|
||||
## Registry verification
|
||||
|
||||
Target registry: `https://git.mosaicstack.dev/api/packages/mosaicstack/npm/`.
|
||||
|
||||
Pre-implementation checks:
|
||||
|
||||
- `npm view @mosaicstack/mosaic dist-tags --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/ --json` returned a dist-tags object (`latest: 0.0.48`).
|
||||
- `npm view @mosaicstack/mosaic@latest version --registry https://git.mosaicstack.dev/api/packages/mosaicstack/npm/` resolved `0.0.48`.
|
||||
- `@next` currently returns 404 because no `next` dist-tag exists yet; this is expected before the first next prerelease publish.
|
||||
|
||||
Pipeline design includes a post-publish verification that `npm view @mosaicstack/mosaic@next version` resolves to the exact CI-computed prerelease version. If Gitea fails to honor the `next` dist-tag, the pipeline fails closed.
|
||||
|
||||
## Version scheme
|
||||
|
||||
The prerelease version is computed at publish time only; no `package.json` version changes are committed.
|
||||
|
||||
For each non-private `@mosaicstack/*` package:
|
||||
|
||||
```text
|
||||
<target-stable>-next.<CI_PIPELINE_NUMBER>
|
||||
```
|
||||
|
||||
Where:
|
||||
|
||||
- `CI_PIPELINE_NUMBER` is Woodpecker's monotonic pipeline number.
|
||||
- `target-stable` is the package's current committed stable version with the patch component incremented.
|
||||
- Example: `@mosaicstack/mosaic` `0.0.48` publishes as `0.0.49-next.1626`.
|
||||
- Example: `@mosaicstack/gateway` `0.0.6` publishes as `0.0.7-next.1626`.
|
||||
|
||||
Rationale:
|
||||
|
||||
- npm semver sorts `0.0.49-next.1627` above `0.0.49-next.1626`.
|
||||
- The prerelease does not overtake the future stable `0.0.49`.
|
||||
- The monotonic pipeline number avoids conflicts across repeated `next` merges.
|
||||
|
||||
## Branch and tag guardrails
|
||||
|
||||
| Pipeline path | Branch/event | Publishes | Forbidden |
|
||||
| --------------------- | ------------------------------ | ------------------------------------------------------- | ---------------------- |
|
||||
| stable npm publish | `main` push/manual or tag | package versions already committed in package manifests | `@next` dist-tag |
|
||||
| next npm publish | `next` push/manual only | CI-computed prereleases with `--tag next` | `latest` dist-tag |
|
||||
| gateway image | `main` push/manual or tag | `sha-<short>` + `latest` on main + tag on tag events | next prerelease npm |
|
||||
| gateway image | `next` push/manual only | `sha-<short>` only | `latest` |
|
||||
| appservice/web images | `main` push/manual or tag only | existing stable image behavior | next image publication |
|
||||
|
||||
The pipeline has explicit branch checks inside the publish commands as a second fail-closed layer beyond Woodpecker `when` clauses.
|
||||
|
||||
## Implementation plan
|
||||
|
||||
1. Widen `.woodpecker/publish.yml` top-level `when` to include `next` so the publish pipeline runs on next merges.
|
||||
2. Keep existing `publish-npm` on `main` / tags only.
|
||||
3. Add `publish-next-npm` for `next` push/manual only:
|
||||
- configure Gitea npm auth from existing `gitea_token` secret as `NPM_TOKEN`;
|
||||
- preflight registry dist-tag metadata;
|
||||
- compute prerelease versions in CI by temporarily editing package manifests in the workspace;
|
||||
- run `pnpm publish ... --tag next` against non-private `@mosaicstack/*` packages;
|
||||
- verify `@mosaicstack/mosaic@next` resolves to the computed version.
|
||||
4. Split image `when` anchors:
|
||||
- `image_build_when` includes `next` and is used by `build-gateway`;
|
||||
- `main_image_build_when` keeps appservice/web on main/tags only.
|
||||
5. Keep gateway next image destinations to `sha-<short>` only; no `latest` on next.
|
||||
|
||||
## Risk controls
|
||||
|
||||
- Auth/registry failures are fatal.
|
||||
- No manual image build/push path is introduced.
|
||||
- No production `latest` tags are touched from `next`.
|
||||
- No `@latest` npm dist-tags are touched from `next`.
|
||||
- All changes live in CI config and docs; no runtime source behavior changes.
|
||||
@@ -0,0 +1,34 @@
|
||||
# B2 — Fresh-install skills sync path
|
||||
|
||||
## Problem
|
||||
|
||||
Greenfield wizard on `next` reported:
|
||||
|
||||
```text
|
||||
Skills sync script not found at ~/.config/mosaic/bin/mosaic-sync-skills
|
||||
Skills: install failed
|
||||
```
|
||||
|
||||
## Diagnosis
|
||||
|
||||
The framework install migration removed the legacy `~/.config/mosaic/bin/` directory and now installs framework helper scripts under:
|
||||
|
||||
```text
|
||||
~/.config/mosaic/tools/_scripts/
|
||||
```
|
||||
|
||||
`packages/mosaic/src/stages/finalize.ts` still resolved wizard helper scripts from `mosaicHome/bin`, so wizard-selected skills failed even though `mosaic-sync-skills` was present in the current framework layout.
|
||||
|
||||
## Fix
|
||||
|
||||
- Resolve framework helper scripts through `tools/_scripts/<name>` first.
|
||||
- Keep a legacy `bin/<name>` fallback for pre-migration installs.
|
||||
- Point missing-script warnings at the current `tools/_scripts` layout.
|
||||
- Update the finalize skills test fixture to model the fresh framework layout.
|
||||
- Update framework README examples from legacy `bin/` helper paths to `tools/_scripts/`.
|
||||
|
||||
## Verification
|
||||
|
||||
- Unit: `pnpm --filter @mosaicstack/mosaic test -- finalize-skills`
|
||||
- Gates: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, `pnpm build`
|
||||
- Fresh path: ran `packages/mosaic/framework/install.sh` with a temp `MOSAIC_HOME` and `MOSAIC_SYNC_ONLY=1`; verified `tools/_scripts/mosaic-sync-skills` exists, legacy `bin/mosaic-sync-skills` does not, and the script installs a selected fake `lint` skill into Mosaic + Pi runtime skill directories.
|
||||
@@ -0,0 +1,36 @@
|
||||
# B3 — Wizard completion ordering
|
||||
|
||||
## Problem
|
||||
|
||||
The wizard printed the success summary / `Mosaic is ready.` during `finalizeStage`, before the gateway configuration stage had completed its daemon health check. If the gateway health gate later failed, the user could see a success claim followed by a gateway failure.
|
||||
|
||||
## Diagnosis
|
||||
|
||||
`finalizeStage` handled both mutation work and terminal success messaging. Wizard paths then ran `gatewayConfigStage` and `gatewayBootstrapStage` afterward:
|
||||
|
||||
1. finalize writes config, links runtime assets, syncs skills, runs doctor;
|
||||
2. finalize prints `Installation Summary` + `Mosaic is ready.`;
|
||||
3. gateway config starts/waits for daemon health;
|
||||
4. gateway bootstrap runs.
|
||||
|
||||
The summary needed to be deferred until after the gateway readiness gates.
|
||||
|
||||
## Fix
|
||||
|
||||
- `finalizeStage` now returns a `showSummary()` callback and supports `deferSummary`.
|
||||
- Wizard/quick-start paths call finalize with `deferSummary: true`.
|
||||
- `showSummary()` is called only after gateway config reports ready and bootstrap completes, or immediately when the caller explicitly skips gateway setup.
|
||||
- If gateway health/config reports not ready, the wizard returns/aborts without printing the success summary.
|
||||
- Folded in adjacent runtime install hint fix for Pi: `curl -fsSL https://pi.dev/install.sh | sh`.
|
||||
|
||||
## Verification
|
||||
|
||||
- Added unified-wizard coverage for summary-after-health and no-summary-on-health-failure.
|
||||
- Targeted: `pnpm --filter @mosaicstack/mosaic test -- unified-wizard finalize-skills`
|
||||
- `pnpm format:check`
|
||||
- `pnpm typecheck`
|
||||
- `pnpm lint`
|
||||
- `pnpm build`
|
||||
- `pnpm test`
|
||||
- Codex code review: approve.
|
||||
- Codex security review: one low finding on the requested Pi `curl | sh` install hint; no security finding in the wizard completion-ordering change.
|
||||
@@ -0,0 +1,36 @@
|
||||
# B4 — Wizard step deduplication
|
||||
|
||||
## Problem
|
||||
|
||||
Greenfield wizard testing showed completed wizard steps could be executed again after the menu marked them `[done]`. In practice this made the Providers/API-key flow and Skills flow appear twice in one wizard run.
|
||||
|
||||
There was a second related API-key duplication path: when the Providers step was completed with no key, `gatewayConfigStage` still prompted for `ANTHROPIC_API_KEY` during Finish because it only skipped the gateway API-key prompt when `providerKey` was non-empty.
|
||||
|
||||
## Diagnosis
|
||||
|
||||
- `runMenuLoop` labeled completed sections with `[done]`, but still dispatched the selected step again if the user selected that row.
|
||||
- Quick Start ran Providers and Skills but did not mark those sections complete in `completedSections`.
|
||||
- `runFinishPath`/`quickStartPath` defaulted `providerType` to `none` for gateway config, which made it impossible for `gatewayConfigStage` to distinguish:
|
||||
- provider step completed and user intentionally skipped the key, vs.
|
||||
- provider step was never run.
|
||||
|
||||
## Fix
|
||||
|
||||
- Added a shared menu section key helper and a completed-step guard in `runMenuLoop`.
|
||||
- Completed menu steps now log a skip message instead of re-running their stage.
|
||||
- Quick Start marks Providers and Skills complete after running them.
|
||||
- Finish/Quick Start now pass `state.providerType` as-is to gateway config instead of defaulting to `none`.
|
||||
- `gatewayConfigStage` treats `providerType: 'none'` as an explicit completed provider setup with no key and skips the second gateway API-key prompt.
|
||||
|
||||
## Verification
|
||||
|
||||
- Added unified wizard regression coverage asserting repeated Providers/Skills menu selections only execute each stage once.
|
||||
- Added gateway config coverage asserting `providerType: 'none'` does not prompt for a gateway API key and writes no API key env var.
|
||||
- Targeted: `pnpm --filter @mosaicstack/mosaic test -- unified-wizard gateway-config`
|
||||
- `pnpm format:check`
|
||||
- `pnpm typecheck`
|
||||
- `pnpm lint`
|
||||
- `pnpm build`
|
||||
- `pnpm test`
|
||||
- Codex code review: approve.
|
||||
- Codex security review: no findings.
|
||||
@@ -0,0 +1,60 @@
|
||||
# FED-M3-10 — Federation M3 Integration Tests
|
||||
|
||||
## Objective
|
||||
|
||||
Add single-gateway gateway integration tests for M3 acceptance #6 and #7.
|
||||
|
||||
## Branch / base
|
||||
|
||||
- Branch: `feat/federation-m3-integration`
|
||||
- Base: `origin/next` (`838701bd` after M3-06/#683 merge)
|
||||
- PR base when unblocked: `next`
|
||||
|
||||
## Scope
|
||||
|
||||
- Real PostgreSQL via `@mosaicstack/db`.
|
||||
- Mocked TLS context / Fastify request shim for `FederationAuthGuard`.
|
||||
- Direct controller calls using the real M3 route contract: `POST /api/federation/v1/list/:resource` with body `{ limit?, cursor? }`.
|
||||
- Gated by `FEDERATED_INTEGRATION=1`.
|
||||
- No federation harness dependency.
|
||||
|
||||
## Fixture notes
|
||||
|
||||
Aligned with the B2 seed design vocabulary:
|
||||
|
||||
- `tasks` visibility uses personal `projects` + `missions` chain.
|
||||
- `notes` are `mission_tasks.notes`; the integration suite asserts subject-only note visibility on an authorized mission.
|
||||
- Seed includes a second user and unauthorized team/project tasks to prove exclusion from the max-row-cap list result.
|
||||
- Grants/peers are direct DB fixtures; cert auth still runs through `FederationAuthGuard` using real X.509 certs generated by existing test helpers.
|
||||
|
||||
## Current implementation
|
||||
|
||||
Added `apps/gateway/src/__tests__/integration/federation-m3-list.integration.test.ts` covering:
|
||||
|
||||
1. M3 #6 — cert missing Mosaic OIDs returns 401 federation `unauthorized` envelope.
|
||||
2. M3 #6 — valid cert whose grant row is `revoked` returns 403 federation `forbidden` envelope.
|
||||
3. M3 #7 — active grant with `max_rows_per_query: 2` caps `list tasks`, returns `_truncated` + `nextCursor`, source-tags rows, and excludes other-user / unauthorized-team tasks.
|
||||
4. Cross-user notes invariant — subject can list their own `mission_tasks.notes` row while another user's note on the same authorized mission is excluded.
|
||||
5. Unsupported-resource invariant — `list widgets` fails closed with a federation `scope_violation` envelope.
|
||||
|
||||
## Verification
|
||||
|
||||
- `pnpm --filter @mosaicstack/types build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/db build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/storage build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/brain build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/queue build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/config build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/auth build` — PASS.
|
||||
- `pnpm --filter @mosaicstack/gateway test -- src/__tests__/integration/federation-m3-list.integration.test.ts` — PASS skipped when `FEDERATED_INTEGRATION` unset (5 skipped).
|
||||
- `FEDERATED_INTEGRATION=1 pnpm --filter @mosaicstack/gateway test -- src/__tests__/integration/federation-m3-list.integration.test.ts` — PASS (5 tests) after local `docker compose up -d postgres` + `pnpm --filter @mosaicstack/db db:push`.
|
||||
- `pnpm --filter @mosaicstack/gateway typecheck` — PASS.
|
||||
- `pnpm --filter @mosaicstack/gateway lint` — PASS.
|
||||
- `pnpm format:check` — PASS.
|
||||
- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — PASS; approve, no findings.
|
||||
- `~/.config/mosaic/tools/codex/codex-security-review.sh --uncommitted` — PASS; risk level none, no findings.
|
||||
|
||||
## Push / PR
|
||||
|
||||
- #683 landed in `next`; branch rebased onto `origin/next` before push.
|
||||
- CI is serialized; run queue guard before push.
|
||||
@@ -0,0 +1,40 @@
|
||||
# Installer `--next` fast npm lane — 2026-06-25
|
||||
|
||||
## Scope
|
||||
|
||||
Flip `tools/install.sh --next` from source-build-first to fast npm `@next` first, with source fallback.
|
||||
|
||||
## Registry reality check
|
||||
|
||||
Gitea npm registry: `https://git.mosaicstack.dev/api/packages/mosaicstack/npm/`
|
||||
|
||||
Verified before implementation:
|
||||
|
||||
- `@mosaicstack/mosaic@next` resolves to `0.0.49-next.1633`.
|
||||
- `@mosaicstack/gateway@next` resolves to `0.0.7-next.1633`.
|
||||
- `@mosaicstack/gateway` dist-tags include `latest: 0.0.6` and `next: 0.0.7-next.1633`.
|
||||
- `apps/gateway/package.json` is non-private and has Gitea npm `publishConfig`.
|
||||
|
||||
Conclusion: the installer can fast-install both CLI and gateway npm packages for `--next`. The gateway Docker `gateway:sha-<short>` remains the deployment/harness artifact; the npm gateway package is valid for the installer global package path.
|
||||
|
||||
## Behavior
|
||||
|
||||
- `--next` with no explicit ref:
|
||||
1. framework archive from `next`;
|
||||
2. resolve `@mosaicstack/gateway@next` and `@mosaicstack/mosaic@next`;
|
||||
3. require both resolved versions to share the same `next.<pipeline>` suffix;
|
||||
4. install the exact resolved package versions;
|
||||
5. set `MOSAIC_GATEWAY_SKIP_NPM_INSTALL=1` so wizard does not overwrite the prerelease gateway;
|
||||
6. if either package is missing/unreachable/mismatched/fails, fall back to existing source build at `next`.
|
||||
- `--dev` remains pure source build.
|
||||
- explicit `--ref` / `MOSAIC_REF` still wins over `--next` and uses the source path for that exact ref.
|
||||
|
||||
## Install detail
|
||||
|
||||
The installer writes the scoped npmrc mapping (`@mosaicstack:registry=...`) and then runs npm install without overriding npm's default registry. Passing `--registry=<gitea>` to `npm install` forces public transitive dependencies (for example `@anthropic-ai/sdk`) to resolve from Gitea and breaks the fast path; the scoped npmrc mapping is the correct split-registry behavior.
|
||||
|
||||
## Verification notes
|
||||
|
||||
- Added `tools/install-next-lane.test.sh` with a fake npm/source harness for exact-version fast install, registry failure source fallback, explicit-ref precedence, and mismatched suffix warning.
|
||||
- Wired the installer harness into `pnpm test` via `pnpm run test:installer`.
|
||||
- Real temp-prefix fast install succeeded with `@mosaicstack/[email protected]` and `@mosaicstack/[email protected]`.
|
||||
@@ -0,0 +1,35 @@
|
||||
# Scratchpad — installer `--next` lane
|
||||
|
||||
## Objective
|
||||
|
||||
Add a prerelease installer lane for the permanent `next` integration branch.
|
||||
|
||||
## Scope
|
||||
|
||||
- `tools/install.sh`
|
||||
- README/install documentation
|
||||
- Follow-up design note for future npm `@next` prerelease publishing
|
||||
|
||||
## Plan
|
||||
|
||||
1. Add `--next` and `MOSAIC_NEXT=1` as source-build shorthand for `next`.
|
||||
2. Preserve explicit ref precedence: `MOSAIC_REF` and `--ref` win over `--next`.
|
||||
3. Update installer source display/help text.
|
||||
4. Document three lanes:
|
||||
- stable npm `@latest`
|
||||
- prerelease `--next`
|
||||
- contributor `--dev --ref X`
|
||||
5. Run shell and repo gates locally, then hold before push/PR until runner serialization greenlight.
|
||||
|
||||
## Verification
|
||||
|
||||
- `bash -n tools/install.sh` — pass.
|
||||
- `docker run --rm -v "$PWD:/mnt" -w /mnt koalaman/shellcheck:stable tools/install.sh` — pass.
|
||||
- `bash tools/install.sh --check --framework --next` — source display shows `ref: next, --next prerelease lane`.
|
||||
- `bash tools/install.sh --check --cli --next --ref feature-x` — source display shows explicit ref wins.
|
||||
- `MOSAIC_NEXT=1 MOSAIC_REF=feature-env bash tools/install.sh --check --cli` — source display shows explicit env ref wins.
|
||||
- `pnpm install --frozen-lockfile --prefer-offline --store-dir /home/jarvis/.local/share/pnpm/store` — pass (local override for repo `.npmrc` CI store path).
|
||||
- `pnpm typecheck` — pass (41 successful tasks).
|
||||
- `pnpm lint` — pass (23 successful tasks).
|
||||
- `pnpm format:check` — pass.
|
||||
- `bash tools/e2e-install-test.sh` — attempted; current baseline fails during gateway health after stable registry install because Valkey is unavailable in the clean container. The `tools/install.sh --yes --no-auto-launch` stage itself completed before the downstream gateway verification failure.
|
||||
@@ -0,0 +1,93 @@
|
||||
# W-B — Measure Pi's real tool registry
|
||||
|
||||
- **Task / internal ref:** W-B from the lease-remediation orchestrator brief (no matching `docs/TASKS.md` row; workers do not modify that file)
|
||||
- **Objective:** identify the exact tool names emitted as `event.toolName` by the installed Pi runtime and compare them with the broker's Pi read-only carve-out.
|
||||
- **Scope:** measurement and report only; no broker or runtime source changes. W-C is out of scope.
|
||||
- **Budget:** no explicit token cap; constrained to this scratchpad and one local commit.
|
||||
- **Installed runtime:** `@earendil-works/pi-coding-agent` / `pi` `0.84.1`.
|
||||
|
||||
## Method
|
||||
|
||||
I created a throwaway extension at `/tmp/measure-pi-tool-registry.ts` (not in the worktree). On `session_start` it recorded `pi.getAllTools()` and `pi.getActiveTools()`; on every `tool_call` it appended the exact `event.toolName`. I then launched an isolated, ephemeral Pi session with all built-ins explicitly selected:
|
||||
|
||||
```text
|
||||
PI_OFFLINE=1 pi --mode print --no-session --no-approve \
|
||||
--no-context-files --no-skills --no-prompt-templates --no-extensions \
|
||||
-e /tmp/measure-pi-tool-registry.ts \
|
||||
--tools read,bash,edit,write,grep,find,ls <deterministic probe prompt>
|
||||
```
|
||||
|
||||
The prompt exercised file read, content search, file search, directory listing, shell execution, file write, and file edit. Pi exited `0`; every selected tool produced one `tool_call`. The write/edit control artifact ended with exact content `after`, proving the mutating calls executed in order.
|
||||
|
||||
This runtime observation was cross-checked against the installed distribution's canonical registry at `dist/core/tools/index.js:17`, which declares the same seven names. The gate consumes the measured field directly at `packages/mosaic/framework/runtime/pi/mosaic-extension.ts:368`.
|
||||
|
||||
## Exact distinct built-in set
|
||||
|
||||
The installed Pi built-in registry is exactly:
|
||||
|
||||
```text
|
||||
{bash, edit, find, grep, ls, read, write}
|
||||
```
|
||||
|
||||
| Tool | Runtime registry observation | `tool_call` observation | Installed definition |
|
||||
| --- | --- | --- | --- |
|
||||
| `read` | `<builtin:read>` | observed once | `dist/core/tools/read.js:138` |
|
||||
| `bash` | `<builtin:bash>` | observed once | `dist/core/tools/bash.js:231` |
|
||||
| `edit` | `<builtin:edit>` | observed once | `dist/core/tools/edit.js:170` |
|
||||
| `write` | `<builtin:write>` | observed once | `dist/core/tools/write.js:138` |
|
||||
| `grep` | `<builtin:grep>` | observed once | `dist/core/tools/grep.js:79` |
|
||||
| `find` | `<builtin:find>` | observed once | `dist/core/tools/find.js:79` |
|
||||
| `ls` | `<builtin:ls>` | observed once | `dist/core/tools/ls.js:61` |
|
||||
|
||||
The raw distinct `event.toolName` result was:
|
||||
|
||||
```json
|
||||
["bash", "edit", "find", "grep", "ls", "read", "write"]
|
||||
```
|
||||
|
||||
Pi registers all seven, but its default active set is only `read`, `bash`, `edit`, and `write` (`dist/core/sdk.js:132`). The probe explicitly activated all seven so the three search/list tools could be observed at the hook.
|
||||
|
||||
## Positive control
|
||||
|
||||
The known `read` tool was the control. The method surfaced it twice:
|
||||
|
||||
1. `pi.getAllTools()` returned `read` with source path `<builtin:read>`.
|
||||
2. Reading `/tmp/pi-registry-probe/seed.txt`, which contained `CONTROL_TOKEN`, produced one hook record with `event.toolName === "read"`.
|
||||
|
||||
The control was therefore positive; the seven-name result is measured, not an empty-probe inference.
|
||||
|
||||
## Carve-out comparison and collision result
|
||||
|
||||
The broker currently declares `{"read", "grep", "find", "ls"}` at `packages/mosaic/framework/tools/lease-broker/daemon.py:54`.
|
||||
|
||||
- `read`: real built-in.
|
||||
- `grep`: real built-in.
|
||||
- `find`: real built-in.
|
||||
- `ls`: real built-in.
|
||||
|
||||
All four carve-out names are exact, case-sensitive Pi tool names.
|
||||
|
||||
The general execution/writing tool names are `bash`, `edit`, and `write`. Their intersection with the carve-out is empty:
|
||||
|
||||
```text
|
||||
{bash, edit, write} ∩ {read, grep, find, ls} = ∅
|
||||
```
|
||||
|
||||
Therefore no general shell-exec or file-mutating Pi tool shares a name with a carve-out entry. `grep` and `find` may invoke constrained search helpers internally, but neither exposes an arbitrary command interface; the arbitrary command tool is distinctly named `bash`.
|
||||
|
||||
The Mosaic extension separately registers the non-built-in custom tool `mosaic_context_recover` at `packages/mosaic/framework/runtime/pi/mosaic-extension.ts:379`; the broker handles that identity through its dedicated recovery exemption rather than the read-only set (`daemon.py:722`). Unknown or third-party custom tools are not part of Pi's built-in seven-name registry and remain outside the carve-out.
|
||||
|
||||
## Verification evidence
|
||||
|
||||
- `pi --version` → `0.84.1`.
|
||||
- Isolated probe exit → `0`.
|
||||
- Runtime `getAllTools()` count → `7`, all with `sourceInfo.source === "builtin"`.
|
||||
- Distinct hook names → `bash`, `edit`, `find`, `grep`, `ls`, `read`, `write`.
|
||||
- Hook counts → exactly one call for each of the seven names.
|
||||
- Mutation artifact after `write` then `edit` → exact content `after`.
|
||||
- Installed registry source → `allToolNames = new Set(["read", "bash", "edit", "write", "grep", "find", "ls"])`.
|
||||
|
||||
## Risks / limitations
|
||||
|
||||
- The probe deliberately disabled all other extensions, so extension-defined third-party tools were excluded from the built-in registry measurement. The production gate still receives those names and treats names outside the broker carve-out as mutating/fail-closed.
|
||||
- Explicit `--tools` activation was required to exercise `grep`, `find`, and `ls`; this does not imply they are active in Pi's default four-tool configuration.
|
||||
+2
-1
@@ -10,7 +10,8 @@
|
||||
"clean:generated": "node scripts/clean-generated.mjs",
|
||||
"typecheck": "pnpm preflight && turbo run typecheck",
|
||||
"test:checkout": "node --test scripts/*.test.mjs",
|
||||
"test": "pnpm test:checkout && turbo run test",
|
||||
"test": "pnpm test:checkout && turbo run test && pnpm run test:installer",
|
||||
"test:installer": "bash tools/install-next-lane.test.sh",
|
||||
"format": "prettier --write \"**/*.{ts,tsx,js,jsx,json,md}\"",
|
||||
"format:check": "prettier --check \"**/*.{ts,tsx,js,jsx,json,md}\"",
|
||||
"prepare": "node scripts/install-hooks.mjs"
|
||||
|
||||
@@ -11,9 +11,37 @@ import { join } from 'node:path';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { HeadlessPrompter } from '../../src/prompter/headless-prompter.js';
|
||||
import { createConfigService } from '../../src/config/config-service.js';
|
||||
import type { SelectOption } from '../../src/prompter/interface.js';
|
||||
import type { MenuSection, WizardState } from '../../src/types.js';
|
||||
|
||||
const gatewayConfigMock = vi.fn();
|
||||
const gatewayBootstrapMock = vi.fn();
|
||||
const providerSetupMock = vi.fn();
|
||||
const skillsSelectMock = vi.fn();
|
||||
|
||||
class SequencedMenuPrompter extends HeadlessPrompter {
|
||||
constructor(
|
||||
answers: Record<string, string | boolean | string[]>,
|
||||
private readonly menuChoices: string[],
|
||||
) {
|
||||
super(answers);
|
||||
}
|
||||
|
||||
override async select<T>(opts: {
|
||||
message: string;
|
||||
options: SelectOption<T>[];
|
||||
initialValue?: T;
|
||||
}): Promise<T> {
|
||||
if (opts.message === 'What would you like to configure?') {
|
||||
const next = this.menuChoices.shift();
|
||||
if (!next) throw new Error('No queued menu choice left');
|
||||
const match = opts.options.find((o) => String(o.value) === next);
|
||||
if (!match) throw new Error(`Queued menu choice not available: ${next}`);
|
||||
return match.value;
|
||||
}
|
||||
return super.select(opts);
|
||||
}
|
||||
}
|
||||
|
||||
vi.mock('../../src/stages/gateway-config.js', () => ({
|
||||
gatewayConfigStage: (...args: unknown[]) => gatewayConfigMock(...args),
|
||||
@@ -23,6 +51,14 @@ vi.mock('../../src/stages/gateway-bootstrap.js', () => ({
|
||||
gatewayBootstrapStage: (...args: unknown[]) => gatewayBootstrapMock(...args),
|
||||
}));
|
||||
|
||||
vi.mock('../../src/stages/provider-setup.js', () => ({
|
||||
providerSetupStage: (...args: unknown[]) => providerSetupMock(...args),
|
||||
}));
|
||||
|
||||
vi.mock('../../src/stages/skills-select.js', () => ({
|
||||
skillsSelectStage: (...args: unknown[]) => skillsSelectMock(...args),
|
||||
}));
|
||||
|
||||
// Import AFTER the mocks so runWizard picks up the mocked stage modules.
|
||||
import { runWizard } from '../../src/wizard.js';
|
||||
|
||||
@@ -44,6 +80,16 @@ describe('Unified wizard (runWizard with default skipGateway)', () => {
|
||||
}
|
||||
gatewayConfigMock.mockReset();
|
||||
gatewayBootstrapMock.mockReset();
|
||||
providerSetupMock.mockReset();
|
||||
skillsSelectMock.mockReset();
|
||||
providerSetupMock.mockImplementation(async (_p: HeadlessPrompter, state: WizardState) => {
|
||||
state.providerType = 'none';
|
||||
state.completedSections?.add('providers' satisfies MenuSection);
|
||||
});
|
||||
skillsSelectMock.mockImplementation(async (_p: HeadlessPrompter, state: WizardState) => {
|
||||
state.selectedSkills = [];
|
||||
state.completedSections?.add('skills' satisfies MenuSection);
|
||||
});
|
||||
// Pretend we're on an interactive TTY so the wizard's headless-abort
|
||||
// branch does not call `process.exit(1)` during these tests.
|
||||
Object.defineProperty(process.stdin, 'isTTY', { value: true, configurable: true });
|
||||
@@ -98,8 +144,12 @@ describe('Unified wizard (runWizard with default skipGateway)', () => {
|
||||
expect(bootstrapCall[2]).toMatchObject({ host: 'localhost', port: 14242 });
|
||||
});
|
||||
|
||||
it('does not invoke bootstrap when config stage reports not ready', async () => {
|
||||
gatewayConfigMock.mockResolvedValue({ ready: false });
|
||||
it('prints the success summary only after gateway health succeeds', async () => {
|
||||
gatewayConfigMock.mockImplementation(async (p: HeadlessPrompter) => {
|
||||
p.log('Gateway is healthy.');
|
||||
return { ready: true, host: 'localhost', port: 14242 };
|
||||
});
|
||||
gatewayBootstrapMock.mockResolvedValue({ completed: true });
|
||||
|
||||
const prompter = new HeadlessPrompter({
|
||||
'Installation mode': 'quick',
|
||||
@@ -118,6 +168,43 @@ describe('Unified wizard (runWizard with default skipGateway)', () => {
|
||||
skipGatewayNpmInstall: true,
|
||||
});
|
||||
|
||||
const logs = prompter.getLogs();
|
||||
const healthIndex = logs.findIndex((line) => line.includes('Gateway is healthy.'));
|
||||
const summaryIndex = logs.findIndex((line) => line.includes('Installation Summary'));
|
||||
const readyIndex = logs.findIndex((line) => line.includes('Mosaic is ready.'));
|
||||
|
||||
expect(healthIndex).toBeGreaterThanOrEqual(0);
|
||||
expect(summaryIndex).toBeGreaterThan(healthIndex);
|
||||
expect(readyIndex).toBeGreaterThan(summaryIndex);
|
||||
});
|
||||
|
||||
it('does not claim success when gateway health reports not ready', async () => {
|
||||
gatewayConfigMock.mockImplementation(async (p: HeadlessPrompter) => {
|
||||
p.warn('Gateway did not become healthy within 30 seconds.');
|
||||
return { ready: false };
|
||||
});
|
||||
|
||||
const prompter = new HeadlessPrompter({
|
||||
'Installation mode': 'quick',
|
||||
'What name should agents use?': 'TestBot',
|
||||
'Communication style': 'direct',
|
||||
'Your name': 'Tester',
|
||||
'Your pronouns': 'They/Them',
|
||||
'Your timezone': 'UTC',
|
||||
});
|
||||
|
||||
await runWizard({
|
||||
mosaicHome: tmpDir,
|
||||
sourceDir: tmpDir,
|
||||
prompter,
|
||||
configService: createConfigService(tmpDir, tmpDir),
|
||||
skipGatewayNpmInstall: true,
|
||||
});
|
||||
|
||||
const logs = prompter.getLogs();
|
||||
expect(logs.some((line) => line.includes('Gateway did not become healthy'))).toBe(true);
|
||||
expect(logs.some((line) => line.includes('Installation Summary'))).toBe(false);
|
||||
expect(logs.some((line) => line.includes('Mosaic is ready.'))).toBe(false);
|
||||
expect(gatewayConfigMock).toHaveBeenCalledTimes(1);
|
||||
expect(gatewayBootstrapMock).not.toHaveBeenCalled();
|
||||
});
|
||||
@@ -143,4 +230,34 @@ describe('Unified wizard (runWizard with default skipGateway)', () => {
|
||||
expect(gatewayConfigMock).not.toHaveBeenCalled();
|
||||
expect(gatewayBootstrapMock).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('does not re-run completed provider or skills menu steps', async () => {
|
||||
const prompter = new SequencedMenuPrompter(
|
||||
{
|
||||
'What name should agents use?': 'TestBot',
|
||||
'Communication style': 'direct',
|
||||
'Your name': 'Tester',
|
||||
'Your pronouns': 'They/Them',
|
||||
'Your timezone': 'UTC',
|
||||
},
|
||||
['providers', 'providers', 'skills', 'skills', 'finish'],
|
||||
);
|
||||
|
||||
await runWizard({
|
||||
mosaicHome: tmpDir,
|
||||
sourceDir: tmpDir,
|
||||
prompter,
|
||||
configService: createConfigService(tmpDir, tmpDir),
|
||||
skipGateway: true,
|
||||
});
|
||||
|
||||
expect(providerSetupMock).toHaveBeenCalledTimes(1);
|
||||
expect(skillsSelectMock).toHaveBeenCalledTimes(1);
|
||||
expect(prompter.getLogs()).toEqual(
|
||||
expect.arrayContaining([
|
||||
expect.stringContaining('Providers [done] is already complete; skipping.'),
|
||||
expect.stringContaining('Skills [done] is already complete; skipping.'),
|
||||
]),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -13,8 +13,7 @@ Pi is the native Mosaic agent runtime. The `mosaic pi` launcher:
|
||||
|
||||
1. Injects the full runtime contract via `--append-system-prompt`
|
||||
2. Loads Mosaic skills via `--skill` flags
|
||||
3. Loads framework-owned `mosaic-extension.ts` and `goal-extension.ts` from
|
||||
`~/.config/mosaic/runtime/pi/` via ordered `--extension` flags
|
||||
3. Loads the Mosaic extension via `--extension` for lifecycle hooks
|
||||
4. Detects active missions and injects initial prompts
|
||||
|
||||
## Capabilities vs Other Runtimes
|
||||
@@ -23,7 +22,6 @@ Pi is the native Mosaic agent runtime. The `mosaic pi` launcher:
|
||||
- Native thinking levels replace sequential-thinking MCP
|
||||
- Native skill discovery compatible with Mosaic SKILL.md format
|
||||
- Native extension system for lifecycle hooks (TypeScript, not bash shims)
|
||||
- Bounded persistent `/goal` loop with per-turn, post-compaction, and two-pass evidence checks
|
||||
- Native session persistence and resume
|
||||
- Model-agnostic (Anthropic, OpenAI, Google, Ollama, custom providers)
|
||||
|
||||
|
||||
@@ -43,6 +43,16 @@ The installer:
|
||||
- Runs a health audit
|
||||
- Detects existing installs and preserves local files (SOUL.md, USER.md, etc.)
|
||||
|
||||
### Install lanes
|
||||
|
||||
| Lane | Command | Use when | Source |
|
||||
| ------------------------ | ------------------------------------- | ---------------------------------------------- | -------------------------------------------------------------------------------------------- |
|
||||
| Stable | `bash tools/install.sh` | You want the released framework and CLI | npm `@mosaicstack/mosaic@latest` + `main` |
|
||||
| Prerelease integration | `bash tools/install.sh --next` | You want the permanent `next` integration lane | Fast npm `@mosaicstack/mosaic@next` + `@mosaicstack/gateway@next`; source fallback at `next` |
|
||||
| Contributor/source build | `bash tools/install.sh --dev --ref X` | You are validating a branch before release | Build-from-source at the requested git ref |
|
||||
|
||||
`--next` is fast-by-default from the Gitea npm `next` dist-tag and falls back to a source build at the permanent `next` branch if the dist-tag is missing or unreachable. Explicit `--ref` or `MOSAIC_REF` wins and uses the source path.
|
||||
|
||||
## First Run
|
||||
|
||||
After install, open a new terminal (or `source ~/.bashrc`) and run:
|
||||
@@ -94,14 +104,7 @@ The launcher:
|
||||
1. Verifies `~/.config/mosaic` exists
|
||||
2. Verifies `SOUL.md` exists (auto-runs `mosaic init` if missing)
|
||||
3. Injects `AGENTS.md` into the runtime
|
||||
4. For Pi, loads the framework-owned core and persistent-goal extensions from
|
||||
`~/.config/mosaic/runtime/pi/`
|
||||
5. Forwards all arguments to the runtime CLI
|
||||
|
||||
Inside `mosaic pi`, `/goal set <statement>` starts a bounded persistent goal loop. Use `/goal status`,
|
||||
`/goal pause`, `/goal resume`, or `/goal cancel` to control it. The extension remains part of Mosaic
|
||||
under `~/.config/mosaic/runtime/pi/goal-extension.ts`; it is not installed in Pi's main extension
|
||||
directory.
|
||||
4. Forwards all arguments to the runtime CLI
|
||||
|
||||
You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtime adapters will tell the agent to read `~/.config/mosaic/AGENTS.md`.
|
||||
|
||||
@@ -115,13 +118,13 @@ You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtim
|
||||
├── TOOLS.md ← Machine-level tool reference (generated by mosaic init)
|
||||
├── STANDARDS.md ← Machine-wide standards
|
||||
├── guides/ ← Operational guides (E2E delivery, PRD, docs, etc.)
|
||||
├── bin/ ← CLI tools (mosaic launcher, mosaic-init, mosaic-doctor, etc.)
|
||||
├── tools/ ← Tool suites: git, orchestrator, prdy, quality, etc.
|
||||
│ └── _scripts/ ← Framework helper scripts (sync skills, doctor, runtime links)
|
||||
├── runtime/ ← Runtime adapters + runtime-specific references
|
||||
│ ├── claude/ ← CLAUDE.md, RUNTIME.md, settings.json, hooks
|
||||
│ ├── codex/ ← instructions.md, RUNTIME.md
|
||||
│ ├── opencode/ ← AGENTS.md, RUNTIME.md
|
||||
│ ├── pi/ ← RUNTIME.md, mosaic-extension.ts, goal-extension.ts
|
||||
│ ├── pi/ ← RUNTIME.md, mosaic-extension.ts
|
||||
│ └── mcp/ ← MCP server configs
|
||||
├── skills/ ← Universal skills (synced from mosaic/agent-skills)
|
||||
├── skills-local/ ← Local cross-runtime skills
|
||||
@@ -133,7 +136,7 @@ You can still launch runtimes directly (`claude`, `codex`, etc.) — thin runtim
|
||||
|
||||
| Launch method | Injection mechanism |
|
||||
| ------------------- | ----------------------------------------------------------------------------------------- |
|
||||
| `mosaic pi` | `--append-system-prompt` with composed runtime contract + skills + Mosaic extensions |
|
||||
| `mosaic pi` | `--append-system-prompt` with composed runtime contract + skills + extension |
|
||||
| `mosaic claude` | `--append-system-prompt` with composed runtime contract (`AGENTS.md` + runtime reference) |
|
||||
| `mosaic codex` | Writes composed runtime contract to `~/.codex/instructions.md` before launch |
|
||||
| `mosaic opencode` | Writes composed runtime contract to `~/.config/opencode/AGENTS.md` before launch |
|
||||
@@ -181,7 +184,9 @@ The installer preserves local `SOUL.md`, `USER.md`, `TOOLS.md`, and `memory/` by
|
||||
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 --ref v1.0 # Install from a specific git ref
|
||||
bash tools/install.sh --next # Prerelease lane: npm @next, source fallback
|
||||
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)
|
||||
```
|
||||
|
||||
The installer rejects unrecognized flags or positional arguments before making changes and prints the supported-option usage.
|
||||
@@ -191,10 +196,11 @@ The installer rejects unrecognized flags or positional arguments before making c
|
||||
The installer syncs skills from `mosaic/agent-skills` into `~/.config/mosaic/skills/`. Install, wizard finalization, and `mosaic update` automatically reconcile every canonical skill into Claude Code's `~/.claude/skills/` directory.
|
||||
|
||||
```bash
|
||||
mosaic sync # Full canonical catalog sync
|
||||
mosaic skill list # Show registered, missing, dangling, and foreign entries
|
||||
mosaic skill register <name> # Register or repair one canonical Claude link
|
||||
mosaic skill unregister <name> # Remove one Mosaic-owned Claude link
|
||||
mosaic sync # Full canonical catalog sync
|
||||
~/.config/mosaic/tools/_scripts/mosaic-sync-skills --link-only # Re-link only
|
||||
mosaic skill list # Show registered, missing, dangling, and foreign entries
|
||||
mosaic skill register <name> # Register or repair one canonical Claude link
|
||||
mosaic skill unregister <name> # Remove one Mosaic-owned Claude link
|
||||
```
|
||||
|
||||
Skill names are direct children using `[A-Za-z0-9][A-Za-z0-9._-]*`, not paths. Registration rejects traversal/control characters and never replaces foreign files, directories, or symlinks; unregister removes only links that point inside the canonical Mosaic skill root. After registering during a running Claude Code session, use `/reload-skills` or start a new session.
|
||||
@@ -204,8 +210,8 @@ M1 lifecycle management targets Claude Code. Pi can discover the canonical Mosai
|
||||
## Health Audit
|
||||
|
||||
```bash
|
||||
mosaic doctor # Standard audit
|
||||
~/.config/mosaic/bin/mosaic-doctor --fail-on-warn # Strict mode
|
||||
mosaic doctor # Standard audit
|
||||
~/.config/mosaic/tools/_scripts/mosaic-doctor --fail-on-warn # Strict mode
|
||||
```
|
||||
|
||||
## MCP Registration
|
||||
@@ -216,8 +222,8 @@ sequential-thinking MCP is required for Mosaic Stack. The installer registers it
|
||||
To verify or re-register manually:
|
||||
|
||||
```bash
|
||||
~/.config/mosaic/bin/mosaic-ensure-sequential-thinking
|
||||
~/.config/mosaic/bin/mosaic-ensure-sequential-thinking --check
|
||||
~/.config/mosaic/tools/_scripts/mosaic-ensure-sequential-thinking
|
||||
~/.config/mosaic/tools/_scripts/mosaic-ensure-sequential-thinking --check
|
||||
```
|
||||
|
||||
### Claude Code MCP Registration
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
Mosaic lease promotion was processed mechanically; no action is needed.
|
||||
@@ -32,6 +32,18 @@
|
||||
]
|
||||
}
|
||||
],
|
||||
"UserPromptSubmit": [
|
||||
{
|
||||
"matcher": "^/mosaic-promote$",
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "python3 ~/.config/mosaic/tools/lease-broker/promote-begin.py",
|
||||
"timeout": 15
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"PreToolUse": [
|
||||
{
|
||||
"matcher": ".*",
|
||||
@@ -81,8 +93,8 @@
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "python3 ~/.config/mosaic/tools/lease-broker/receipt-observer-client.py --runtime claude --latest-entry",
|
||||
"timeout": 3
|
||||
"command": "python3 ~/.config/mosaic/tools/lease-broker/receipt-observer-client.py --runtime claude --latest-entry; observer_status=$?; python3 ~/.config/mosaic/tools/lease-broker/promote-complete.py; exit $observer_status",
|
||||
"timeout": 15
|
||||
},
|
||||
{
|
||||
"type": "command",
|
||||
|
||||
@@ -51,26 +51,12 @@ Skills are discovered from:
|
||||
|
||||
### Extensions
|
||||
|
||||
`mosaic pi` loads framework-owned extensions directly from `~/.config/mosaic/runtime/pi/` in this
|
||||
order:
|
||||
The Mosaic Pi extension (`~/.config/mosaic/runtime/pi/mosaic-extension.ts`) handles:
|
||||
|
||||
1. `mosaic-extension.ts` — session lifecycle, mission context, memory routing, lease/mutator gates,
|
||||
and fleet heartbeat reporting.
|
||||
2. `goal-extension.ts` — optional persistent `/goal` controller with per-turn and post-compaction
|
||||
checks.
|
||||
|
||||
The goal extension is deployed by Mosaic and MUST NOT be copied into `~/.pi/agent/extensions/`.
|
||||
Use `/goal set <statement>` (or `/goal <statement>`) to start, then `/goal status`, `/goal pause`,
|
||||
`/goal resume`, or `/goal cancel` to control it. An active goal is injected before every model
|
||||
request, restored from branch-specific session entries, and considered achieved only after two
|
||||
consecutive evidence-bearing reports. Common credential shapes are redacted before controller-owned
|
||||
goal-state entries are persisted or
|
||||
displayed; Pi's own model/tool-call history is separate. Goals and reports must contain references
|
||||
and pass/fail summaries rather than secrets or raw sensitive output.
|
||||
|
||||
- `MOSAIC_GOAL_MAX_TURNS` — autonomous turn limit, default `40`, accepted range `1..500`.
|
||||
- `MOSAIC_GOAL_MAX_NO_PROGRESS` — identical no-progress report limit, default `6`, accepted range
|
||||
`1..100`.
|
||||
- Session start/end lifecycle hooks
|
||||
- Active mission detection and context injection
|
||||
- Memory routing to `~/.config/mosaic/memory/`
|
||||
- MACP queue status reporting
|
||||
|
||||
### Sessions
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -66,10 +66,7 @@ if command -v tmux >/dev/null 2>&1 && command -v cc >/dev/null 2>&1; then
|
||||
trap 'tmux -L "$TEST_SOCKET" kill-server >/dev/null 2>&1 || true; rm -rf "$TEST_ROOT"' EXIT
|
||||
MARKER="$TEST_ROOT/loader-marker"
|
||||
LIBRARY="$TEST_ROOT/marker.so"
|
||||
FIXTURE_READY="$TEST_ROOT/loader-ready"
|
||||
FIXTURE_FIFO="$TEST_ROOT/loader-block"
|
||||
HOLDER_HOME="$TEST_ROOT/holder-home"
|
||||
mkfifo "$FIXTURE_FIFO"
|
||||
mkdir -p "$HOLDER_HOME/.config/mosaic/fleet/run"
|
||||
chmod 700 "$HOLDER_HOME/.config" "$HOLDER_HOME/.config/mosaic" \
|
||||
"$HOLDER_HOME/.config/mosaic/fleet" "$HOLDER_HOME/.config/mosaic/fleet/run"
|
||||
@@ -90,17 +87,7 @@ __attribute__((constructor)) static void mark_loader(void) {
|
||||
EOF
|
||||
cc -shared -fPIC -o "$LIBRARY" "$TEST_ROOT/marker.c"
|
||||
MOSAIC_LOADER_MARKER="$MARKER" LD_PRELOAD="$LIBRARY" \
|
||||
tmux -L "$TEST_SOCKET" new-session -d -s _holder \
|
||||
"touch '$FIXTURE_READY'; read _ < '$FIXTURE_FIFO'"
|
||||
# tmux starts the pane asynchronously. Wait until its contaminated shell has
|
||||
# loaded the constructor and reached a builtin-only FIFO barrier before
|
||||
# clearing the marker; otherwise that expected constructor can race with the
|
||||
# clean holder assertion below and create a false failure.
|
||||
for _attempt in {1..100}; do
|
||||
[ -e "$FIXTURE_READY" ] && break
|
||||
sleep 0.01
|
||||
done
|
||||
[ -e "$FIXTURE_READY" ] || fail "contaminated fixture pane did not become ready"
|
||||
tmux -L "$TEST_SOCKET" new-session -d -s _holder 'sleep 60'
|
||||
[ -s "$MARKER" ] || fail "contaminated fixture did not execute loader constructor"
|
||||
server_pid=$(tmux -L "$TEST_SOCKET" display-message -p '#{pid}')
|
||||
: > "$MARKER"
|
||||
@@ -125,7 +112,6 @@ EOF
|
||||
chmod 700 "$AGENT_HOME/fleet/agents"
|
||||
cat > "$AGENT_HOME/fleet/agents/$AGENT_NAME.env.generated" <<EOF
|
||||
MOSAIC_AGENT_NAME=$AGENT_NAME
|
||||
MOSAIC_GIT_IDENTITY=$AGENT_NAME
|
||||
MOSAIC_AGENT_CLASS=code
|
||||
MOSAIC_AGENT_RUNTIME=pi
|
||||
MOSAIC_AGENT_MODEL=
|
||||
@@ -158,8 +144,7 @@ EOF
|
||||
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin \
|
||||
MOSAIC_TMUX_SOCKET="$TEST_SOCKET" MOSAIC_TMUX_HOLDER=_holder "$HOLDER_START"
|
||||
tmux -L "$TEST_SOCKET" has-session -t '=_holder:0.0' || fail "fresh holder was not created"
|
||||
ld_preload_env="$(tmux -L "$TEST_SOCKET" show-environment -g LD_PRELOAD 2>/dev/null)" || true
|
||||
if grep -q '^LD_PRELOAD=' <<<"$ld_preload_env"; then
|
||||
if tmux -L "$TEST_SOCKET" show-environment -g LD_PRELOAD 2>/dev/null | grep -q '^LD_PRELOAD='; then
|
||||
fail "fresh holder retained LD_PRELOAD"
|
||||
fi
|
||||
/usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
||||
|
||||
@@ -233,6 +233,14 @@ for runtime_file in \
|
||||
copy_file_managed "$src" "$HOME/.claude/$runtime_file"
|
||||
done
|
||||
|
||||
if [[ -d "$MOSAIC_HOME/runtime/claude/commands" ]]; then
|
||||
mkdir -p "$HOME/.claude/commands"
|
||||
for command_file in "$MOSAIC_HOME/runtime/claude/commands/"*; do
|
||||
[[ -f "$command_file" ]] || continue
|
||||
copy_file_managed "$command_file" "$HOME/.claude/commands/$(basename "$command_file")"
|
||||
done
|
||||
fi
|
||||
|
||||
# OpenCode runtime adapter (thin pointer to AGENTS.md)
|
||||
opencode_adapter="$MOSAIC_HOME/runtime/opencode/AGENTS.md"
|
||||
if [[ -f "$opencode_adapter" ]]; then
|
||||
|
||||
@@ -153,7 +153,24 @@ if [[ $link_only -eq 1 ]]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Skills are linked into the MOSAIC-OWNED harness homes, never a base install.
|
||||
# Paths mirror the config-dir env vars the launcher injects (HARNESS_HOME_ENV in
|
||||
# commands/launch.js):
|
||||
# claude CLAUDE_CONFIG_DIR -> <home>/skills
|
||||
# pi PI_CODING_AGENT_DIR -> <home>/skills (replaces ~/.pi/agent)
|
||||
# codex CODEX_HOME -> <home>/skills
|
||||
# opencode XDG_CONFIG_HOME -> <home>/opencode/skills (XDG adds a level)
|
||||
link_targets=(
|
||||
"$MOSAIC_HOME/.claude/skills"
|
||||
"$MOSAIC_HOME/.codex/skills"
|
||||
"$MOSAIC_HOME/.opencode/opencode/skills"
|
||||
"$MOSAIC_HOME/.pi/skills"
|
||||
)
|
||||
|
||||
# Pre-isolation installs planted the same symlink farm directly in the operator's
|
||||
# base installs. Those are now orphaned: the launcher no longer reads them, but
|
||||
# they persist and make a "clean" base install look mosaic-managed.
|
||||
legacy_link_targets=(
|
||||
"$HOME/.claude/skills"
|
||||
"$HOME/.codex/skills"
|
||||
"$HOME/.config/opencode/skills"
|
||||
@@ -245,13 +262,72 @@ prune_stale_links_in_target() {
|
||||
# -m resolves lexical dangling targets too. If resolution fails, ownership
|
||||
# is unproven and the link must be preserved.
|
||||
resolved="$(readlink -m "$link_path" 2>/dev/null || true)"
|
||||
if [[ -n "$resolved" && "$resolved" == "$canonical_real/"* ]]; then
|
||||
# $canonical_real must be length-checked BEFORE use as a prefix: if it were
|
||||
# ever empty, "$resolved" == "$canonical_real/"* collapses to == "/"* and
|
||||
# matches every absolute path. Combined with the is_mosaic_skill_name skip
|
||||
# above, that inverts the function precisely — it would delete exactly the
|
||||
# FOREIGN symlinks and keep the mosaic ones. (#1087, reported by mos-claude.)
|
||||
if [[ -n "$resolved" && -n "$canonical_real" && "$resolved" == "$canonical_real/"* ]]; then
|
||||
rm -f "$link_path"
|
||||
echo "[mosaic-skills] Removed stale retired skill link: $link_path"
|
||||
fi
|
||||
done < <(find "$target_dir" -mindepth 1 -maxdepth 1 -type l -print0)
|
||||
}
|
||||
|
||||
# Remove mosaic-owned symlinks left in a base install by a pre-isolation sync.
|
||||
#
|
||||
# Ownership is proven by RESOLUTION, not by name: only links resolving inside the
|
||||
# canonical or local skills dirs are removed. Anything else — a real directory, a
|
||||
# link elsewhere, an unresolvable link — is left untouched. This mirrors the
|
||||
# refusal in commands/skill.js ("only symlinks pointing inside the Mosaic skills
|
||||
# directory are managed") and preserves e.g. codex's own `.system` dir.
|
||||
#
|
||||
# The directory itself is kept: mosaic-doctor warns when ~/.pi/agent/skills is
|
||||
# missing, and an empty dir is the correct end state, not an absent one.
|
||||
cleanup_legacy_target() {
|
||||
local target_dir="$1"
|
||||
local removed=0 kept=0
|
||||
|
||||
[[ -d "$target_dir" ]] || return 0
|
||||
|
||||
while IFS= read -r -d '' link_path; do
|
||||
local resolved owned=0
|
||||
resolved="$(readlink -m "$link_path" 2>/dev/null || true)"
|
||||
|
||||
# Guard the empty-prefix trap: an unset *_real would make "$resolved" == "/"*
|
||||
# match every absolute path and delete foreign links.
|
||||
if [[ -n "$resolved" ]]; then
|
||||
if [[ -n "$canonical_real" && "$resolved" == "$canonical_real/"* ]]; then
|
||||
owned=1
|
||||
elif [[ -n "$local_real" && "$resolved" == "$local_real/"* ]]; then
|
||||
owned=1
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ $owned -eq 1 ]]; then
|
||||
rm -f "$link_path"
|
||||
removed=$((removed + 1))
|
||||
else
|
||||
kept=$((kept + 1))
|
||||
fi
|
||||
done < <(find "$target_dir" -mindepth 1 -maxdepth 1 -type l -print0)
|
||||
|
||||
if [[ $removed -gt 0 ]]; then
|
||||
echo "[mosaic-skills] Legacy cleanup: removed $removed mosaic symlink(s) from $target_dir (preserved $kept foreign)"
|
||||
fi
|
||||
}
|
||||
|
||||
for legacy in "${legacy_link_targets[@]}"; do
|
||||
# Skip anything that is also a current target, so isolation can never
|
||||
# self-destruct if the two lists ever overlap.
|
||||
skip=0
|
||||
for target in "${link_targets[@]}"; do
|
||||
[[ "$legacy" == "$target" ]] && skip=1
|
||||
done
|
||||
[[ $skip -eq 1 ]] && continue
|
||||
cleanup_legacy_target "$legacy"
|
||||
done
|
||||
|
||||
for target in "${link_targets[@]}"; do
|
||||
mkdir -p "$target"
|
||||
|
||||
|
||||
@@ -69,7 +69,7 @@ if [[ -n "$GROUP" ]]; then
|
||||
group_response=$(curl -sk \
|
||||
-H "Authorization: Bearer $TOKEN" \
|
||||
"${AUTHENTIK_URL}/api/v3/core/groups/?search=${GROUP}")
|
||||
group_pk=$(jq -r "first(.results[] | select(.name == \"$GROUP\") | .pk) // empty" <<<"$group_response")
|
||||
group_pk=$(echo "$group_response" | jq -r ".results[] | select(.name == \"$GROUP\") | .pk" | head -1)
|
||||
if [[ -n "$group_pk" ]]; then
|
||||
payload=$(echo "$payload" | jq --arg gk "$group_pk" '. + {groups: [$gk]}')
|
||||
else
|
||||
|
||||
@@ -97,7 +97,7 @@ is_sensitive_key() {
|
||||
|
||||
is_generated_key() {
|
||||
case "$1" in
|
||||
MOSAIC_AGENT_NAME|MOSAIC_GIT_IDENTITY|MOSAIC_AGENT_CLASS|MOSAIC_AGENT_RUNTIME|MOSAIC_AGENT_MODEL|MOSAIC_AGENT_REASONING|MOSAIC_AGENT_TOOL_POLICY|MOSAIC_AGENT_WORKDIR|MOSAIC_TMUX_SOCKET) return 0 ;;
|
||||
MOSAIC_AGENT_NAME|MOSAIC_AGENT_CLASS|MOSAIC_AGENT_RUNTIME|MOSAIC_AGENT_MODEL|MOSAIC_AGENT_REASONING|MOSAIC_AGENT_TOOL_POLICY|MOSAIC_AGENT_WORKDIR|MOSAIC_TMUX_SOCKET) return 0 ;;
|
||||
*) return 1 ;;
|
||||
esac
|
||||
}
|
||||
@@ -114,7 +114,6 @@ validate_generated_value() {
|
||||
local value="$2"
|
||||
case "$key" in
|
||||
MOSAIC_AGENT_NAME) safe_agent_name "$value" || fail_env unsafe-agent-name "$key" "$value" ;;
|
||||
MOSAIC_GIT_IDENTITY) safe_agent_name "$value" || fail_env unsafe-git-identity "$key" "$value" ;;
|
||||
MOSAIC_AGENT_CLASS) safe_policy_name "$value" || fail_env unsafe-class "$key" "$value" ;;
|
||||
MOSAIC_AGENT_RUNTIME)
|
||||
case "$value" in claude|codex|opencode|pi) ;; *) fail_env unsupported-runtime "$key" "$value" ;; esac
|
||||
@@ -176,7 +175,7 @@ load_environment_file() {
|
||||
|
||||
load_environment_file "$GENERATED_ENV" generated
|
||||
for required_key in \
|
||||
MOSAIC_AGENT_NAME MOSAIC_GIT_IDENTITY MOSAIC_AGENT_CLASS MOSAIC_AGENT_RUNTIME MOSAIC_AGENT_MODEL \
|
||||
MOSAIC_AGENT_NAME MOSAIC_AGENT_CLASS MOSAIC_AGENT_RUNTIME MOSAIC_AGENT_MODEL \
|
||||
MOSAIC_AGENT_REASONING MOSAIC_AGENT_TOOL_POLICY MOSAIC_AGENT_WORKDIR MOSAIC_TMUX_SOCKET; do
|
||||
[ -n "${GENERATED_VALUES[$required_key]+set}" ] || fail_env missing-key "$required_key" ''
|
||||
done
|
||||
@@ -184,15 +183,12 @@ load_environment_file "$LOCAL_ENV" local
|
||||
|
||||
[ "${GENERATED_VALUES[MOSAIC_AGENT_NAME]}" = "$AGENT_NAME" ] || \
|
||||
fail_env agent-name-mismatch MOSAIC_AGENT_NAME "${GENERATED_VALUES[MOSAIC_AGENT_NAME]}"
|
||||
[ "${GENERATED_VALUES[MOSAIC_GIT_IDENTITY]}" = "$AGENT_NAME" ] || \
|
||||
fail_env git-identity-mismatch MOSAIC_GIT_IDENTITY "${GENERATED_VALUES[MOSAIC_GIT_IDENTITY]}"
|
||||
|
||||
MOSAIC_TMUX_SOCKET=${GENERATED_VALUES[MOSAIC_TMUX_SOCKET]}
|
||||
MOSAIC_AGENT_RUNTIME=${GENERATED_VALUES[MOSAIC_AGENT_RUNTIME]}
|
||||
MOSAIC_AGENT_MODEL=${GENERATED_VALUES[MOSAIC_AGENT_MODEL]}
|
||||
MOSAIC_AGENT_REASONING=${GENERATED_VALUES[MOSAIC_AGENT_REASONING]}
|
||||
MOSAIC_AGENT_WORKDIR=${GENERATED_VALUES[MOSAIC_AGENT_WORKDIR]}
|
||||
MOSAIC_GIT_IDENTITY=${GENERATED_VALUES[MOSAIC_GIT_IDENTITY]}
|
||||
MOSAIC_AGENT_CLASS=${GENERATED_VALUES[MOSAIC_AGENT_CLASS]}
|
||||
MOSAIC_AGENT_TOOL_POLICY=${GENERATED_VALUES[MOSAIC_AGENT_TOOL_POLICY]}
|
||||
MOSAIC_RUNTIME_BIN=${LOCAL_VALUES[MOSAIC_RUNTIME_BIN]:-}
|
||||
@@ -347,7 +343,6 @@ LAUNCH_ENV=(
|
||||
"PATH=$PANE_PATH"
|
||||
"MOSAIC_HOME=$MOSAIC_HOME"
|
||||
"MOSAIC_AGENT_NAME=$AGENT_NAME"
|
||||
"MOSAIC_GIT_IDENTITY=$MOSAIC_GIT_IDENTITY"
|
||||
"MOSAIC_AGENT_CLASS=$MOSAIC_AGENT_CLASS"
|
||||
"MOSAIC_AGENT_RUNTIME=$MOSAIC_AGENT_RUNTIME"
|
||||
"MOSAIC_AGENT_MODEL=$MOSAIC_AGENT_MODEL"
|
||||
|
||||
@@ -14,82 +14,6 @@ fail() {
|
||||
exit 1
|
||||
}
|
||||
|
||||
pane_command_clears_environment() {
|
||||
local calls_file="$1"
|
||||
local -a argv=()
|
||||
local index
|
||||
mapfile -d '' -t argv < "$calls_file"
|
||||
for ((index = 0; index + 1 < ${#argv[@]}; index++)); do
|
||||
if [ "${argv[$index]}" = /usr/bin/env ] && [ "${argv[$((index + 1))]}" = -i ]; then
|
||||
return 0
|
||||
fi
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
print_pane_argv() {
|
||||
local calls_file="$1"
|
||||
local -a argv=()
|
||||
local bytes index
|
||||
mapfile -d '' -t argv < "$calls_file"
|
||||
bytes=$(wc -c < "$calls_file")
|
||||
printf 'observed pane argv: records=%s bytes=%s\n' "${#argv[@]}" "$bytes" >&2
|
||||
for ((index = 0; index < ${#argv[@]}; index++)); do
|
||||
printf ' [%03d] %q\n' "$index" "${argv[$index]}" >&2
|
||||
done
|
||||
}
|
||||
|
||||
check_pane_environment_boundary() {
|
||||
local calls_file="$1"
|
||||
if pane_command_clears_environment "$calls_file"; then
|
||||
return 0
|
||||
fi
|
||||
print_pane_argv "$calls_file"
|
||||
return 1
|
||||
}
|
||||
|
||||
contains_literal() {
|
||||
grep -F -- "$2" <<< "$1" >/dev/null
|
||||
}
|
||||
|
||||
contains_line() {
|
||||
grep -xF -- "$2" <<< "$1" >/dev/null
|
||||
}
|
||||
|
||||
# Portability regression: inspect the authoritative NUL-delimited argv instead
|
||||
# of piping a newline reconstruction through `grep -q` under pipefail. The old
|
||||
# pipeline could report failure after a successful match when an upstream
|
||||
# producer received SIGPIPE. A large trailing argument keeps that failure class
|
||||
# covered without making stream size part of the semantic contract.
|
||||
PORTABILITY_CALLS="$ROOT/portability-calls"
|
||||
printf -v PORTABILITY_PADDING '%*s' 32768 ''
|
||||
PORTABILITY_PADDING=${PORTABILITY_PADDING// /x}
|
||||
printf '%s\0' /usr/bin/env -i "$PORTABILITY_PADDING" > "$PORTABILITY_CALLS"
|
||||
pane_command_clears_environment "$PORTABILITY_CALLS" || \
|
||||
fail "valid large pane argv was rejected by the environment-boundary assertion"
|
||||
|
||||
assert_pane_boundary_rejected() {
|
||||
local case_name="$1"
|
||||
local expected_records="$2"
|
||||
local diagnostic
|
||||
if diagnostic=$(check_pane_environment_boundary "$PORTABILITY_CALLS" 2>&1); then
|
||||
fail "pane boundary accepted invalid $case_name fixture"
|
||||
fi
|
||||
contains_literal "$diagnostic" "records=$expected_records bytes=" || \
|
||||
fail "pane argv diagnostic omitted counts for $case_name fixture"
|
||||
contains_literal "$diagnostic" '[000]' || \
|
||||
fail "pane argv diagnostic omitted indexed arguments for $case_name fixture"
|
||||
}
|
||||
|
||||
printf '%s\0' tmux -i > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected missing-env 2
|
||||
printf '%s\0' /usr/bin/env HOME=/untrusted > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected missing-i 2
|
||||
printf '%s\0' /usr/bin/env HOME=/untrusted -i > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected non-adjacent-i 3
|
||||
printf '%s\0' -i /usr/bin/env > "$PORTABILITY_CALLS"
|
||||
assert_pane_boundary_rejected reversed-boundary 2
|
||||
|
||||
cat > "$FAKE_BIN/tmux" <<'SHIM'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
@@ -138,19 +62,6 @@ env -0 > "${MOSAIC_HOME:?}/fleet/pane-environment"
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/mosaic"
|
||||
|
||||
# Freeze numeric epoch reads only when a test arm supplies an observation bound.
|
||||
# Formatting reads still use the real BusyBox/POSIX date implementation.
|
||||
cat > "$FAKE_BIN/date" <<'SHIM'
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
if [ -n "${MOSAIC_TEST_FIXED_EPOCH:-}" ] && [ "${1:-}" = '+%s' ]; then
|
||||
printf '%s\n' "$MOSAIC_TEST_FIXED_EPOCH"
|
||||
exit 0
|
||||
fi
|
||||
exec /bin/date "$@"
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/date"
|
||||
|
||||
write_generated() {
|
||||
local home="$1"
|
||||
local agent="$2"
|
||||
@@ -160,7 +71,6 @@ write_generated() {
|
||||
chmod 600 "$home/fleet/run/holder-owner"
|
||||
cat > "$home/fleet/agents/$agent.env.generated" <<EOF
|
||||
MOSAIC_AGENT_NAME=$agent
|
||||
MOSAIC_GIT_IDENTITY=$agent
|
||||
MOSAIC_AGENT_CLASS=code
|
||||
MOSAIC_AGENT_RUNTIME=pi
|
||||
MOSAIC_AGENT_MODEL=openai-codex/gpt-5.6-sol
|
||||
@@ -178,7 +88,6 @@ run_start() {
|
||||
local agent="$2"
|
||||
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
||||
MOSAIC_TEST_FIXED_EPOCH="${MOSAIC_TEST_FIXED_EPOCH:-}" \
|
||||
MOSAIC_TEST_HOME="$home" \
|
||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||
MOSAIC_HOME="$home" "$START" "$agent"
|
||||
@@ -191,55 +100,19 @@ AGENT_VALID="coder0"
|
||||
write_generated "$HOME_VALID" "$AGENT_VALID"
|
||||
run_start "$HOME_VALID" "$AGENT_VALID"
|
||||
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_literal "$valid_args" new-session || fail "valid generated projection did not reach tmux"
|
||||
contains_literal "$valid_args" mosaic || fail "fixed mosaic launcher command missing"
|
||||
contains_literal "$valid_args" yolo || fail "fixed yolo launcher command missing"
|
||||
contains_literal "$valid_args" pi || fail "roster runtime missing"
|
||||
if contains_literal "$valid_args" 'bash -c'; then
|
||||
echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
|
||||
echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
|
||||
echo "$valid_args" | grep -qF 'yolo' || fail "fixed yolo launcher command missing"
|
||||
echo "$valid_args" | grep -qF 'pi' || fail "roster runtime missing"
|
||||
if echo "$valid_args" | grep -qF 'bash -c'; then
|
||||
fail "launcher constructed a shell command payload"
|
||||
fi
|
||||
|
||||
# The pane must start through an absolute clean-environment boundary. Its
|
||||
# runtime command remains an argv vector, but no holder/session environment
|
||||
# control variable can pass through the pane command.
|
||||
check_pane_environment_boundary "$TMUX_CALLS" || \
|
||||
fail "pane command did not use an adjacent /usr/bin/env -i boundary"
|
||||
|
||||
# Git identity is generated authority, not an optional or independently mutable
|
||||
# local value. Each invalid form must fail before fake tmux receives a call.
|
||||
assert_git_identity_rejected() {
|
||||
local case_name="$1"
|
||||
local expected_code="$2"
|
||||
local home="$ROOT/git-identity-$case_name"
|
||||
local agent="coder-git-identity-$case_name"
|
||||
local generated="$home/fleet/agents/$agent.env.generated"
|
||||
write_generated "$home" "$agent"
|
||||
|
||||
case "$case_name" in
|
||||
missing) grep -v '^MOSAIC_GIT_IDENTITY=' "$generated" > "$generated.next" && mv "$generated.next" "$generated" ;;
|
||||
unsafe) sed -i 's|^MOSAIC_GIT_IDENTITY=.*$|MOSAIC_GIT_IDENTITY=bad/identity|' "$generated" ;;
|
||||
mismatch) sed -i 's|^MOSAIC_GIT_IDENTITY=.*$|MOSAIC_GIT_IDENTITY=other-agent|' "$generated" ;;
|
||||
local-shadow)
|
||||
printf 'MOSAIC_GIT_IDENTITY=%s\n' "$agent" > "$home/fleet/agents/$agent.env.local"
|
||||
chmod 600 "$home/fleet/agents/$agent.env.local"
|
||||
;;
|
||||
*) fail "unknown Git identity rejection case: $case_name" ;;
|
||||
esac
|
||||
chmod 600 "$generated"
|
||||
|
||||
: > "$TMUX_CALLS"
|
||||
if output=$(run_start "$home" "$agent" 2>&1); then
|
||||
fail "Git identity case $case_name was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before Git identity $case_name rejection"
|
||||
contains_literal "$output" "code=$expected_code" || \
|
||||
fail "Git identity $case_name diagnostic omitted code $expected_code"
|
||||
}
|
||||
|
||||
assert_git_identity_rejected missing missing-key
|
||||
assert_git_identity_rejected unsafe unsafe-git-identity
|
||||
assert_git_identity_rejected mismatch git-identity-mismatch
|
||||
assert_git_identity_rejected local-shadow generated-key-shadow
|
||||
echo "$valid_args" | grep -qxF '/usr/bin/env' || fail "pane does not use absolute env"
|
||||
echo "$valid_args" | grep -qxF -- '-i' || fail "pane environment is not cleared"
|
||||
|
||||
# The generated-file parent is a security boundary too: even a private regular
|
||||
# file is untrusted if its parent can be replaced or written by another user.
|
||||
@@ -252,7 +125,7 @@ if output=$(run_start "$HOME_UNSAFE_PARENT" coder-parent 2>&1); then
|
||||
fail "generated file under a world-writable parent was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before unsafe parent rejection"
|
||||
contains_literal "$output" 'code=unsafe-permissions' || fail "unsafe parent diagnostic missing"
|
||||
echo "$output" | grep -qF 'code=unsafe-permissions' || fail "unsafe parent diagnostic missing"
|
||||
|
||||
: > "$TMUX_CALLS"
|
||||
HOME_SYMLINK_PARENT="$ROOT/symlink-parent"
|
||||
@@ -263,7 +136,7 @@ if output=$(run_start "$HOME_SYMLINK_PARENT" coder-symlink-parent 2>&1); then
|
||||
fail "generated file under a symlinked parent was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before symlinked parent rejection"
|
||||
contains_literal "$output" 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
|
||||
echo "$output" | grep -qF 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
|
||||
|
||||
# Every managed ancestor is a boundary: MOSAIC_HOME, fleet, and agents. A
|
||||
# symlink or group/world-writable ancestor must fail before environment parsing,
|
||||
@@ -301,8 +174,8 @@ assert_managed_ancestor_rejected() {
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before $hazard $ancestor rejection"
|
||||
[ ! -e "$home/work" ] || fail "workdir was created before $hazard $ancestor rejection"
|
||||
contains_literal "$output" 'code=unsafe-' || fail "managed ancestor diagnostic missing"
|
||||
if contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND'; then
|
||||
echo "$output" | grep -qF "code=unsafe-" || fail "managed ancestor diagnostic missing"
|
||||
if echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND'; then
|
||||
fail "environment parsing ran before $hazard $ancestor rejection"
|
||||
fi
|
||||
}
|
||||
@@ -323,9 +196,9 @@ if output=$(run_start "$HOME_SHADOW" coder1 2>&1); then
|
||||
fail "generated-key shadow was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before generated-key shadow rejection"
|
||||
contains_literal "$output" 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
|
||||
contains_literal "$output" 'sha256=' || fail "shadow diagnostic omitted hash"
|
||||
if contains_literal "$output" codex; then
|
||||
echo "$output" | grep -qF 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
|
||||
echo "$output" | grep -qF 'sha256=' || fail "shadow diagnostic omitted hash"
|
||||
if echo "$output" | grep -qF 'codex'; then
|
||||
fail "shadow diagnostic leaked value"
|
||||
fi
|
||||
|
||||
@@ -341,9 +214,9 @@ if output=$(run_start "$HOME_COMMAND" coder2 2>&1); then
|
||||
fail "arbitrary command override was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before command rejection"
|
||||
contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
|
||||
contains_literal "$output" 'sha256=' || fail "command diagnostic omitted hash"
|
||||
if contains_literal "$output" "$COMMAND_VALUE"; then
|
||||
echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
|
||||
echo "$output" | grep -qF 'sha256=' || fail "command diagnostic omitted hash"
|
||||
if echo "$output" | grep -qF "$COMMAND_VALUE"; then
|
||||
fail "command diagnostic leaked command value"
|
||||
fi
|
||||
|
||||
@@ -357,7 +230,7 @@ if output=$(run_start "$HOME_PERMS" coder3 2>&1); then
|
||||
fail "world-readable local input was accepted"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before permissions rejection"
|
||||
contains_literal "$output" 'code=unsafe-permissions' || fail "permission diagnostic missing"
|
||||
echo "$output" | grep -qF 'code=unsafe-permissions' || fail "permission diagnostic missing"
|
||||
|
||||
# A unit/holder-like clean bootstrap must yield a pane with trusted HOME and
|
||||
# computed PATH only. The pane command itself must not carry loader, shell
|
||||
@@ -387,35 +260,25 @@ PATH="$PANE_STALE_PATH" \
|
||||
MOSAIC_TEST_EXECUTE_PANE=1 \
|
||||
"$START" coder-pane-boundary
|
||||
pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_line "$pane_args" "HOME=$PANE_TRUSTED_HOME" || \
|
||||
echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||
fail "pane did not restore trusted HOME"
|
||||
contains_literal "$pane_args" "HOME=$PANE_STALE_HOME" && \
|
||||
echo "$pane_args" | grep -qF "HOME=$PANE_STALE_HOME" && \
|
||||
fail "pane inherited stale HOME"
|
||||
contains_literal "$pane_args" "$PANE_STALE_PATH" && fail "pane inherited stale PATH"
|
||||
echo "$pane_args" | grep -qF "$PANE_STALE_PATH" && fail "pane inherited stale PATH"
|
||||
for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
|
||||
contains_literal "$pane_args" "$blocked" && fail "pane inherited $blocked"
|
||||
echo "$pane_args" | grep -qF "$blocked" && fail "pane inherited $blocked"
|
||||
done
|
||||
|
||||
check_pane_environment_boundary "$TMUX_CALLS" || \
|
||||
fail "pane command did not use an adjacent /usr/bin/env -i boundary"
|
||||
after_pane_env=$(printf '%s\n' "$pane_args" | grep -n -m1 -F '/usr/bin/env' | cut -d: -f1)
|
||||
[ -n "$after_pane_env" ] || fail "pane command did not use absolute env"
|
||||
printf '%s\n' "$pane_args" | tail -n +"$after_pane_env" | grep -qxF -- '-i' || \
|
||||
fail "pane command did not clear its environment"
|
||||
pane_environment=$(tr '\0' '\n' < "$HOME_PANE_BOUNDARY/fleet/pane-environment")
|
||||
# Exercise the repository launcher at $START, not the independently installed
|
||||
# host copy. Set-compare every declared generated projection entry with the
|
||||
# launched process environment so a newly declared identity cannot be omitted
|
||||
# by a hand-maintained per-variable assertion.
|
||||
declared_generated_environment=$(sort "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.generated")
|
||||
missing_or_changed_generated_environment=$(comm -23 \
|
||||
<(printf '%s\n' "$declared_generated_environment") \
|
||||
<(printf '%s\n' "$pane_environment" | sort))
|
||||
if [ -n "$missing_or_changed_generated_environment" ]; then
|
||||
missing_or_changed_keys=$(printf '%s\n' "$missing_or_changed_generated_environment" | cut -d= -f1 | paste -sd, -)
|
||||
fail "runtime pane omitted or changed generated environment keys: $missing_or_changed_keys"
|
||||
fi
|
||||
contains_line "$pane_environment" "HOME=$PANE_TRUSTED_HOME" || \
|
||||
echo "$pane_environment" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||
fail "runtime pane did not receive trusted HOME"
|
||||
contains_literal "$pane_environment" "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
|
||||
echo "$pane_environment" | grep -qF "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
|
||||
for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
|
||||
contains_literal "$pane_environment" "$blocked" && fail "runtime pane received $blocked"
|
||||
echo "$pane_environment" | grep -qF "$blocked" && fail "runtime pane received $blocked"
|
||||
done
|
||||
|
||||
write_interaction_generated() {
|
||||
@@ -427,7 +290,6 @@ write_interaction_generated() {
|
||||
chmod 600 "$home/fleet/run/holder-owner"
|
||||
cat > "$home/fleet/agents/$agent.env.generated" <<EOF
|
||||
MOSAIC_AGENT_NAME=$agent
|
||||
MOSAIC_GIT_IDENTITY=$agent
|
||||
MOSAIC_AGENT_CLASS=operator-interaction
|
||||
MOSAIC_AGENT_RUNTIME=pi
|
||||
MOSAIC_AGENT_MODEL=openai/gpt-5.6-sol
|
||||
@@ -490,12 +352,8 @@ write_generated "$HOME_NATIVE_STALE" "coder-native-stale"
|
||||
write_heartbeat_local "$HOME_NATIVE_STALE" "coder-native-stale"
|
||||
STALE_HB="$HOME_NATIVE_STALE/run/coder-native-stale.hb"
|
||||
printf 'ts=native\npid=1\nstatus=busy\nmodel=stale-model\n' > "$STALE_HB"
|
||||
touch -t 200001010000.00 "$STALE_HB.native"
|
||||
# Hold the sidecar's observation epoch constant: assertion runtime must not age
|
||||
# a fresh-marker mutant into the stale state that this fixture must distinguish.
|
||||
STALE_OBSERVATION_EPOCH=$(date +%s)
|
||||
MOSAIC_TEST_FIXED_EPOCH="$STALE_OBSERVATION_EPOCH" \
|
||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_NATIVE_STALE" coder-native-stale
|
||||
touch -d '10 seconds ago' "$STALE_HB.native"
|
||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_NATIVE_STALE" coder-native-stale
|
||||
wait_for_sidecar_status "$STALE_HB"
|
||||
|
||||
HOME_NATIVE_ABSENT="$ROOT/native-absent"
|
||||
@@ -516,22 +374,22 @@ if output=$(run_interaction "$HOME_INTERACTION_MALFORMED" interaction-malformed
|
||||
fail "interaction wrapper accepted malformed generated data"
|
||||
fi
|
||||
[ ! -s "$TMUX_CALLS" ] || fail "tmux ran before interaction strict-parser rejection"
|
||||
contains_literal "$output" 'code=unknown-key' || fail "interaction did not use shared strict parser first"
|
||||
echo "$output" | grep -qF 'code=unknown-key' || fail "interaction did not use shared strict parser first"
|
||||
|
||||
# A syntactically valid but policy-incompatible projection reaches the pinned
|
||||
# interaction policy check only after strict parsing and never starts tmux.
|
||||
: > "$TMUX_CALLS"
|
||||
HOME_INTERACTION_POLICY="$ROOT/interaction-policy"
|
||||
write_interaction_generated "$HOME_INTERACTION_POLICY" "interaction-policy"
|
||||
sed -i 's|^MOSAIC_AGENT_RUNTIME=pi$|MOSAIC_AGENT_RUNTIME=codex|' \
|
||||
perl -0pi -e 's/MOSAIC_AGENT_RUNTIME=pi/MOSAIC_AGENT_RUNTIME=codex/' \
|
||||
"$HOME_INTERACTION_POLICY/fleet/agents/interaction-policy.env.generated"
|
||||
if output=$(run_interaction "$HOME_INTERACTION_POLICY" interaction-policy 2>&1); then
|
||||
fail "interaction wrapper accepted a policy-incompatible projection"
|
||||
fi
|
||||
interaction_policy_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_literal "$interaction_policy_args" new-session && \
|
||||
echo "$interaction_policy_args" | grep -qF 'new-session' && \
|
||||
fail "interaction pinned-policy rejection created a tmux session"
|
||||
contains_literal "$output" 'operator interaction service requires runtime pi' || \
|
||||
echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
|
||||
fail "interaction pinned-policy check did not follow strict parsing"
|
||||
|
||||
# Exact stop derives the socket exclusively from the validated generated
|
||||
@@ -544,10 +402,10 @@ HOME="$HOME_STOP" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||
MOSAIC_HOME="$HOME_STOP" MOSAIC_TMUX_SOCKET=ambient-socket "$START" --stop coder-stop
|
||||
stop_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
contains_line "$stop_args" mosaic-test || fail "exact stop did not use the validated generated socket"
|
||||
contains_line "$stop_args" kill-session || fail "exact stop did not request session termination"
|
||||
contains_line "$stop_args" '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
|
||||
if contains_literal "$stop_args" ambient-socket; then
|
||||
echo "$stop_args" | grep -qxF 'mosaic-test' || fail "exact stop did not use the validated generated socket"
|
||||
echo "$stop_args" | grep -qxF 'kill-session' || fail "exact stop did not request session termination"
|
||||
echo "$stop_args" | grep -qxF '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
|
||||
if echo "$stop_args" | grep -qF 'ambient-socket'; then
|
||||
fail "exact stop trusted an ambient socket"
|
||||
fi
|
||||
|
||||
|
||||
@@ -5,10 +5,7 @@
|
||||
|
||||
detect_platform() {
|
||||
local remote_url
|
||||
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
|
||||
# kills the CALLER before the -z check below can run, so the error message that is
|
||||
# already written here was unreachable. Same idiom as get_gitea_repo_args() below.
|
||||
remote_url=$(git remote get-url origin 2>/dev/null) || true
|
||||
remote_url=$(git remote get-url origin 2>/dev/null)
|
||||
|
||||
if [[ -z "$remote_url" ]]; then
|
||||
echo "error: not a git repository or no origin remote" >&2
|
||||
@@ -42,10 +39,7 @@ detect_platform() {
|
||||
|
||||
get_repo_info() {
|
||||
local remote_url
|
||||
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
|
||||
# kills the CALLER before the -z check below can run, so the error message that is
|
||||
# already written here was unreachable. Same idiom as get_gitea_repo_args() below.
|
||||
remote_url=$(git remote get-url origin 2>/dev/null) || true
|
||||
remote_url=$(git remote get-url origin 2>/dev/null)
|
||||
|
||||
if [[ -z "$remote_url" ]]; then
|
||||
echo "error: not a git repository or no origin remote" >&2
|
||||
@@ -246,21 +240,6 @@ PY
|
||||
} >&2
|
||||
}
|
||||
|
||||
# Explain tea's most misleading failure. `user does not exist [uid: 0, name: ]` reads
|
||||
# as a missing account; it almost always means a REVOKED OR STALE TOKEN. `tea login`
|
||||
# keeps its OWN COPY of the token, so rotating the credential store does not update it.
|
||||
# Diagnostic only -- stderr, no control flow, no exit.
|
||||
explain_tea_user_does_not_exist() {
|
||||
cat >&2 <<'MSG'
|
||||
NOTE: `user does not exist [uid: 0, name: ]` from tea usually means a REVOKED OR STALE TOKEN,
|
||||
not a missing account. A `tea login` stores its OWN COPY of the token; rotating the
|
||||
credential store does NOT update it.
|
||||
CHECK: the login's cached copy (`tea login list` -- read the FULL table, never `| head`),
|
||||
then re-register that login against the current token.
|
||||
DO NOT probe capability with a mutating request; a POST is the action, not a check.
|
||||
MSG
|
||||
}
|
||||
|
||||
get_gitea_login_for_host() {
|
||||
local host="${1:-}"
|
||||
local login
|
||||
|
||||
@@ -91,32 +91,13 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
|
||||
GITEA_LOGIN_NAME=$(get_gitea_login || true)
|
||||
if [[ -n "$GITEA_LOGIN_NAME" ]]; then
|
||||
if [[ -n "$COMMENT" ]]; then
|
||||
# `tea issue comment` is NOT a subcommand -- tea 0.11.x lists only
|
||||
# list/create/edit/reopen/close under `tea issue`. Comments are the
|
||||
# TOP-LEVEL `tea comment`, which takes the same --repo/--login flags.
|
||||
# The old call therefore always failed, was unchecked, and the script
|
||||
# closed the issue anyway, losing the record of WHY.
|
||||
#
|
||||
# Use `tea comment` rather than the API helper so the comment and the
|
||||
# close are made by the SAME principal ($GITEA_LOGIN_NAME). Routing the
|
||||
# comment through the token-authenticated helper here would attribute the
|
||||
# comment to the token holder and the close to the tea login -- two
|
||||
# principals for one operation.
|
||||
tea comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME" || {
|
||||
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
|
||||
exit 1
|
||||
}
|
||||
tea issue comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
||||
fi
|
||||
tea issue close "$ISSUE_NUMBER" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
|
||||
else
|
||||
echo "No tea login configured for $(get_remote_host); using authenticated Gitea API fallback." >&2
|
||||
if [[ -n "$COMMENT" ]]; then
|
||||
# Fail closed here too: an unchecked comment lets the issue close without its
|
||||
# audit trail, which is the same defect as the tea path above.
|
||||
gitea_issue_comment_api || {
|
||||
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
|
||||
exit 1
|
||||
}
|
||||
gitea_issue_comment_api
|
||||
fi
|
||||
gitea_issue_close_api
|
||||
fi
|
||||
|
||||
@@ -156,7 +156,6 @@ case "$PLATFORM" in
|
||||
exit 0
|
||||
fi
|
||||
echo "Warning: tea issue create failed, trying Gitea API fallback..." >&2
|
||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
||||
fi
|
||||
gitea_issue_create_api
|
||||
;;
|
||||
|
||||
@@ -71,7 +71,6 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
|
||||
exit 0
|
||||
fi
|
||||
echo "Warning: tea issue view failed, trying Gitea API fallback..." >&2
|
||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
||||
fi
|
||||
gitea_issue_view_api
|
||||
else
|
||||
|
||||
@@ -84,7 +84,7 @@ cp "$TARGET" "$BAK"
|
||||
export MOSAIC_TEST_WORK_DIR="$WORK/.work"
|
||||
|
||||
# --- where the prose lives: usage() { ... EOF ---------------------------------
|
||||
PROSE_LO="$(grep -n -m1 '^usage() {' "$BAK" | cut -d: -f1)"
|
||||
PROSE_LO="$(grep -n '^usage() {' "$BAK" | head -1 | cut -d: -f1)"
|
||||
PROSE_HI="$(awk -v lo="$PROSE_LO" 'NR > lo && /^EOF$/ { print NR; exit }' "$BAK")"
|
||||
if [[ -z "$PROSE_LO" || -z "$PROSE_HI" ]]; then
|
||||
echo "!! cannot locate the usage() heredoc -- the prose guard would be inert; refusing" >&2
|
||||
|
||||
@@ -219,7 +219,6 @@ case "$PLATFORM" in
|
||||
exit 0
|
||||
fi
|
||||
echo "Warning: tea pr create failed, trying Gitea API fallback..." >&2
|
||||
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
|
||||
gitea_pr_create_api
|
||||
;;
|
||||
*)
|
||||
|
||||
@@ -1,58 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Regression: detect_platform / get_repo_info must FAIL LOUDLY outside a git repo,
|
||||
# not kill the caller silently.
|
||||
#
|
||||
# Both functions already contained the right error path:
|
||||
# if [[ -z "$remote_url" ]]; then echo "error: not a git repository..." >&2; return 1; fi
|
||||
# but under `set -e` -- which every wrapper in this directory uses -- the preceding
|
||||
# assignment `remote_url=$(git remote get-url origin 2>/dev/null)` returns git's 128
|
||||
# outside a repo and terminates the CALLER first. The message was unreachable.
|
||||
#
|
||||
# Observed cost: pr-review.sh invoked from a non-repo cwd exits 128 with NO stdout and
|
||||
# NO stderr, even when -r/--repo and -H/--host are supplied -- the flags documented as
|
||||
# "skips git-remote inference". Two reviewer seats hit this and correctly reported
|
||||
# `blocked` with no diagnostic to report.
|
||||
#
|
||||
# The control that matters is the LOUD one: asserting "rc != 0" passes on the broken
|
||||
# build too, because 128 is also non-zero. The test must assert the MESSAGE.
|
||||
set -uo pipefail
|
||||
fail=0
|
||||
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
|
||||
|
||||
run_outside() { # $1=function name -> "rc:sawmessage"
|
||||
local fn="$1" out rc
|
||||
out=$( cd "$TMP" && bash -c "set -e; source '$HERE/detect-platform.sh'; $fn" 2>&1 ); rc=$?
|
||||
printf '%s:%s' "$rc" "$(grep -qi 'not a git repository' <<<"$out" && echo yes || echo no)"
|
||||
}
|
||||
check() { if [ "$2" = "$3" ]; then echo " PASS $1 ($2)"; else echo " FAIL $1: got $2, want $3"; fail=1; fi; }
|
||||
|
||||
# $TMP must not be inside a git repo. Do not SKIP on failure: be-coder-07 showed the
|
||||
# original SKIP exited 0, so pointing TMPDIR beneath a git worktree made this test PASS
|
||||
# against unchanged main. A skip that exits 0 is indistinguishable from a pass.
|
||||
# GIT_CEILING_DIRECTORIES stops git walking above $TMP, making the condition hold
|
||||
# regardless of where TMPDIR lives, rather than merely detecting when it does not.
|
||||
# GIT_CEILING_DIRECTORIES is matched against the PHYSICAL path -- a symlinked TMPDIR
|
||||
# (/tmp is commonly one) makes the logical path never match, and the ceiling silently
|
||||
# does nothing. Resolve it before exporting.
|
||||
TMP="$(cd "$TMP" && pwd -P)"
|
||||
export GIT_CEILING_DIRECTORIES="$TMP"
|
||||
if ( cd "$TMP" && git rev-parse --git-dir >/dev/null 2>&1 ); then
|
||||
echo " FAIL scratch dir is inside a git repo even with GIT_CEILING_DIRECTORIES set;"
|
||||
echo " the outside-a-repo precondition cannot be established -- refusing to report a result"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "== outside a git repo: rc=1 AND the diagnostic is emitted =="
|
||||
check "detect_platform" "$(run_outside detect_platform)" "1:yes"
|
||||
check "get_repo_info" "$(run_outside get_repo_info)" "1:yes"
|
||||
|
||||
echo "== inside a git repo the functions still work =="
|
||||
git init -q "$TMP/repo" 2>/dev/null
|
||||
git -C "$TMP/repo" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git 2>/dev/null
|
||||
out=$( cd "$TMP/repo" && bash -c "set -e; source '$HERE/detect-platform.sh'; detect_platform" 2>&1 ); rc=$?
|
||||
if [ "$rc" -eq 0 ] && grep -qi 'gitea' <<<"$out"; then echo " PASS detect_platform in-repo (rc=0, $out)"
|
||||
else echo " FAIL detect_platform in-repo: rc=$rc out=$out"; fail=1; fi
|
||||
|
||||
[ "$fail" -eq 0 ] && echo "OK detect-platform fails loudly outside a repo" || echo "FAILED"
|
||||
exit "$fail"
|
||||
@@ -1,64 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Regression: the tea-failure diagnostic must be STATUS-NEUTRAL.
|
||||
#
|
||||
# Found by be-coder-08 reviewing PR #1086. At all three call sites the diagnostic is emitted
|
||||
# immediately BEFORE the Gitea API fallback. Written as the last command of an && list:
|
||||
# declare -F explain_... >/dev/null && explain_...
|
||||
# under `set -e` a FAILING diagnostic exits and the fallback never runs -- a diagnostic that
|
||||
# suppresses the recovery path it exists to explain. It misbehaves ONLY when the helper is
|
||||
# PRESENT, so the helper-absent path (pre-#1086 behaviour) keeps working and reads as a
|
||||
# passing control.
|
||||
#
|
||||
# TWO DEFECTS IN THE FIRST VERSION OF THIS TEST, both found by be-coder-08:
|
||||
# 1. `out=$( ... ) 2>"$errto"` applies the redirection to the ASSIGNMENT, not to the
|
||||
# command substitution, so the probe's stderr was never actually pointed at /dev/full
|
||||
# and the /dev/full rows proved nothing. Verified: `out=$(echo x >&2) 2>/dev/full`
|
||||
# leaks to the terminal and returns 0; the redirect must be INSIDE the substitution.
|
||||
# 2. `eval "$CONSTRUCT"` changes `set -e` semantics for a bare && list, so the probe did
|
||||
# not exercise the construct as the shipped file executes it. It now writes the line
|
||||
# into a real script and runs it -- same parse, same set -e rules, no eval.
|
||||
# The construct is still LIFTED FROM THE SHIPPED FILE: retyping the fixed form makes the
|
||||
# probe pass on a build whose real call sites still carry the bare && form.
|
||||
set -uo pipefail
|
||||
fail=0
|
||||
GIT_DIR_UNDER_TEST="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
|
||||
|
||||
probe() { # $1=present|absent $2=stderr target $3=source file -> "rc:fallback"
|
||||
local helper="$1" errto="$2" src="$3" construct script out rc
|
||||
construct=$(grep -m1 'explain_tea_user_does_not_exist' "$GIT_DIR_UNDER_TEST/$src" | sed 's/^[[:space:]]*//')
|
||||
[ -n "$construct" ] || { printf 'no-construct:no'; return; }
|
||||
script="$TMP/probe.sh"
|
||||
{
|
||||
echo '#!/bin/bash'
|
||||
echo 'set -e'
|
||||
echo 'explain_tea_user_does_not_exist() { echo "diagnostic" >&2; }'
|
||||
[ "$helper" = absent ] && echo 'unset -f explain_tea_user_does_not_exist'
|
||||
echo "$construct" # the shipped line, parsed by a real shell
|
||||
echo 'echo FALLBACK_REACHED'
|
||||
} > "$script"
|
||||
# redirect INSIDE the substitution so the subshell's stderr really is $errto
|
||||
out=$( bash "$script" 2>"$errto" ); rc=$?
|
||||
printf '%s:%s' "$rc" "$(grep -q FALLBACK_REACHED <<<"$out" && echo yes || echo no)"
|
||||
}
|
||||
|
||||
check() { if [ "$2" = "$3" ]; then echo " PASS $1 ($2)"; else echo " FAIL $1: got $2, want $3"; fail=1; fi; }
|
||||
|
||||
echo "== diagnostic must not alter exit status or skip the fallback =="
|
||||
# /dev/full makes every stderr write fail -- the real-world shape is a closed or full fd.
|
||||
for src in pr-create.sh issue-view.sh issue-create.sh; do
|
||||
check "$src stderr OK / helper present" "$(probe present /dev/null "$src")" "0:yes"
|
||||
check "$src stderr OK / helper absent " "$(probe absent /dev/null "$src")" "0:yes"
|
||||
check "$src stderr FAILING / helper present" "$(probe present /dev/full "$src")" "0:yes"
|
||||
check "$src stderr FAILING / helper absent " "$(probe absent /dev/full "$src")" "0:yes"
|
||||
done
|
||||
|
||||
echo "== all three call sites use the status-neutral form =="
|
||||
for f in pr-create.sh issue-view.sh issue-create.sh; do
|
||||
p="$GIT_DIR_UNDER_TEST/$f"
|
||||
grep -q '{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true' "$p" \
|
||||
&& echo " PASS $f guarded" || { echo " FAIL $f: diagnostic is not status-neutral"; fail=1; }
|
||||
done
|
||||
|
||||
[ "$fail" -eq 0 ] && echo "OK diagnostic is status-neutral" || echo "FAILED"
|
||||
exit "$fail"
|
||||
@@ -1,150 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression: issue-close.sh must NOT close an issue when the closing comment could not
|
||||
# be posted, and comment+close must be made by ONE principal.
|
||||
#
|
||||
# Guards two defects fixed together (see #1081):
|
||||
# 1. `tea issue comment` is not a subcommand -- tea exposes comments as the TOP-LEVEL
|
||||
# `tea comment`. The old call always failed, was unchecked, and the issue closed
|
||||
# anyway, losing the record of WHY it was closed.
|
||||
# 2. Routing the comment through the token-authenticated API helper while the close
|
||||
# used --login would attribute one operation to two principals.
|
||||
#
|
||||
# SAFETY (rev-974, #1085 review 130): this test previously ran under `set -uo pipefail`
|
||||
# with unchecked mkdir/redirect/cd, then prepended a possibly-nonexistent $MOCK_BIN to
|
||||
# PATH -- while `git remote add origin` names the REAL repository. Forcing setup failure
|
||||
# with an unwritable AGENT_WORK_ROOT made it `git init` in its CALLER's directory and
|
||||
# invoke the real, provider-mutating issue-close.sh. Setup now fails closed, and both
|
||||
# `tea` and `curl` are asserted to resolve INSIDE $MOCK_BIN before any target run.
|
||||
set -euo pipefail
|
||||
# NOTE: with `set -e`, `grep -q X && fail "..."` is a trap -- the ABSENT case (grep rc=1,
|
||||
# which is the PASSING case for a must-not-appear assertion) is the last command of an &&
|
||||
# list and silently terminates the script with no message. Every must-not-appear check
|
||||
# below is therefore an if-block. This is the same set -e + &&-list defect be-coder-08
|
||||
# found in #1086, reintroduced here by adding `set -e` for the sandbox-safety fix.
|
||||
|
||||
WORK_ROOT="${AGENT_WORK_ROOT:-${TMPDIR:-/tmp}}"
|
||||
SANDBOX="$WORK_ROOT/issue-close-fail-closed-test-$$"
|
||||
MOCK_BIN="$SANDBOX/bin"; REPO_DIR="$SANDBOX/repo"; CALLS="$SANDBOX/calls.log"
|
||||
cleanup() { rm -rf "$SANDBOX"; }
|
||||
trap cleanup EXIT
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TARGET="$SCRIPT_DIR/issue-close.sh"
|
||||
[ -f "$TARGET" ] || { echo "FAIL: issue-close.sh not found beside this test"; exit 1; }
|
||||
fail() { echo "FAIL: $*"; exit 1; }
|
||||
|
||||
# Every setup step is checked. Under `set -e` these abort; the explicit || fail keeps the
|
||||
# reason legible instead of a bare non-zero exit.
|
||||
mkdir -p "$MOCK_BIN" "$REPO_DIR" || fail "setup: cannot create sandbox under $WORK_ROOT"
|
||||
: > "$CALLS" || fail "setup: cannot write calls log at $CALLS"
|
||||
cd "$REPO_DIR" || fail "setup: cannot cd into $REPO_DIR"
|
||||
git init -q || fail "setup: git init failed"
|
||||
git remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git || fail "setup: git remote add failed"
|
||||
export PATH="$MOCK_BIN:$PATH" CALLS
|
||||
export GITEA_URL="https://git.mosaicstack.dev"
|
||||
export GITEA_TOKEN="redacted-test-token"
|
||||
|
||||
cat > "$MOCK_BIN/curl" <<'EOF'
|
||||
#!/bin/bash
|
||||
method=GET; url=""
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
-X) method="$2"; shift 2 ;;
|
||||
http*|https*) url="$1"; shift ;;
|
||||
*) shift ;;
|
||||
esac
|
||||
done
|
||||
printf 'curl %s %s\n' "$method" "$url" >> "$CALLS"
|
||||
[ "${MOCK_CURL_FAIL:-}" = "1" ] && [ "$method" = "POST" ] && exit 22
|
||||
exit 0
|
||||
EOF
|
||||
chmod +x "$MOCK_BIN/curl"
|
||||
|
||||
mk_tea() { # $1 = exit code for a comment attempt; $2 = login list (empty => no login)
|
||||
local rc="$1" login="${2-}"
|
||||
cat > "$MOCK_BIN/tea" <<EOF
|
||||
#!/bin/bash
|
||||
printf 'tea %s\n' "\$*" >> "$CALLS"
|
||||
if [[ "\$*" == *"login list"* ]]; then
|
||||
printf '%s\n' '${login}'; exit 0
|
||||
fi
|
||||
# Fail ANY comment attempt -- both the correct top-level \`tea comment\` and the broken
|
||||
# \`tea issue comment\` -- so an unfixed script exercises the DEFECT rather than tripping
|
||||
# a setup assertion.
|
||||
if [[ "\$1" == "comment" || ( "\$1" == "issue" && "\$2" == "comment" ) ]]; then exit $rc; fi
|
||||
exit 0
|
||||
EOF
|
||||
chmod +x "$MOCK_BIN/tea"
|
||||
}
|
||||
LOGIN_JSON='[{"name":"git.mosaicstack.dev","url":"https://git.mosaicstack.dev"}]'
|
||||
|
||||
# The mocks must be the ones that run. Without this, a failed setup silently falls through
|
||||
# to the real tea/curl and the "test" mutates the real provider.
|
||||
assert_mocked() {
|
||||
local w
|
||||
for w in tea curl; do
|
||||
p=$(command -v "$w" || true)
|
||||
[ -n "$p" ] || fail "SAFETY: $w does not resolve at all"
|
||||
case "$p" in
|
||||
"$MOCK_BIN"/*) : ;;
|
||||
*) fail "SAFETY: $w resolves to $p, OUTSIDE the sandbox -- refusing to invoke the target" ;;
|
||||
esac
|
||||
done
|
||||
}
|
||||
|
||||
run_target() { # never let a target failure abort the test; we assert on rc
|
||||
# Call sites MUST use `rc=0; run_target ... || rc=$?` -- a bare `run_target ...; rc=$?`
|
||||
# lets the non-zero RETURN trip set -e in the CALLER before rc is ever read.
|
||||
set +e; bash "$TARGET" "$@" >/dev/null 2>&1; local rc=$?; set -e; return $rc
|
||||
}
|
||||
|
||||
# ── tea path ────────────────────────────────────────────────────────────────────────
|
||||
# 1. NEGATIVE (the regression): comment fails => must NOT close, must exit non-zero
|
||||
mk_tea 1 "$LOGIN_JSON"; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 -c "closing note" || rc=$?
|
||||
grep -qE 'tea (issue )?comment' "$CALLS" || fail "no comment attempt -- setup did not reach the tea branch"
|
||||
if grep -q 'tea issue close' "$CALLS"; then fail "ISSUE CLOSED AFTER THE COMMENT FAILED -- the regression"; fi
|
||||
[ "$rc" -ne 0 ] || fail "comment failed but issue-close exited 0 -- FAIL-OPEN"
|
||||
|
||||
# 2. POSITIVE: comment succeeds => close proceeds, exit 0
|
||||
mk_tea 0 "$LOGIN_JSON"; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 -c "closing note" || rc=$?
|
||||
[ "$rc" -eq 0 ] || fail "comment succeeded but issue-close exited $rc"
|
||||
grep -q 'tea issue close' "$CALLS" || fail "issue not closed even though the comment succeeded"
|
||||
|
||||
# 3. must use top-level `tea comment`, never `tea issue comment`
|
||||
if grep -q 'tea issue comment' "$CALLS"; then fail "used 'tea issue comment' -- not a valid subcommand"; fi
|
||||
|
||||
# 4. ONE PRINCIPAL: comment and close must carry the SAME --login
|
||||
c=$(grep -m1 '^tea comment' "$CALLS" | grep -o -- '--login [^ ]*' | awk '{print $2}')
|
||||
k=$(grep -m1 '^tea issue close' "$CALLS" | grep -o -- '--login [^ ]*' | awk '{print $2}')
|
||||
[ -n "$c" ] || fail "comment carried no --login"
|
||||
[ "$c" = "$k" ] || fail "MIXED PRINCIPALS: comment=$c close=$k"
|
||||
|
||||
# ── no-login / API fallback path ────────────────────────────────────────────────────
|
||||
# rev-974: the delta also adds fail-closed behaviour to this branch, and the suite never
|
||||
# reached it -- replacing the whole fallback contract with an unconditional close still
|
||||
# passed. These assert the POSTCONDITION (which HTTP calls happened, in what order),
|
||||
# not merely that a command ran.
|
||||
# 5. no login + comment FAILS => POST attempted, NO PATCH, non-zero
|
||||
mk_tea 0 ""; : > "$CALLS"; assert_mocked
|
||||
rc=0; MOCK_CURL_FAIL=1 run_target -i 42 -c "closing note" || rc=$?
|
||||
grep -q 'curl POST' "$CALLS" || fail "API path: no comment POST attempted"
|
||||
if grep -q 'curl PATCH' "$CALLS"; then fail "API path: ISSUE CLOSED (PATCH) AFTER THE COMMENT POST FAILED"; fi
|
||||
[ "$rc" -ne 0 ] || fail "API path: comment failed but exited 0 -- FAIL-OPEN"
|
||||
|
||||
# 6. no login + comment SUCCEEDS => POST strictly BEFORE PATCH, exit 0
|
||||
mk_tea 0 ""; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 -c "closing note" || rc=$?
|
||||
[ "$rc" -eq 0 ] || fail "API path: comment succeeded but exited $rc"
|
||||
order=$(grep -oE 'curl (POST|PATCH)' "$CALLS" | awk '{print $2}' | paste -sd, -)
|
||||
[ "$order" = "POST,PATCH" ] || fail "API path: expected POST,PATCH -- got '${order:-<none>}'"
|
||||
|
||||
# 7. no login + NO comment => PATCH only, never a POST
|
||||
mk_tea 0 ""; : > "$CALLS"; assert_mocked
|
||||
rc=0; run_target -i 42 || rc=$?
|
||||
[ "$rc" -eq 0 ] || fail "API path: no-comment close exited $rc"
|
||||
if grep -q 'curl POST' "$CALLS"; then fail "API path: posted a comment when none was requested"; fi
|
||||
grep -q 'curl PATCH' "$CALLS" || fail "API path: issue not closed when no comment was requested"
|
||||
|
||||
echo "issue-close.sh fail-closed + single-principal regression passed"
|
||||
@@ -280,10 +280,7 @@ print("201")
|
||||
print(json.dumps(record))
|
||||
PY
|
||||
)
|
||||
response_status="${result%%$'\n'*}"
|
||||
response_body=""
|
||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
||||
write_response "$response_status" "$response_body"
|
||||
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||
elif [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_BASE"/issues/comments/* ]]; then
|
||||
result=$(ISSUE_COMMENT_GET_ID="${path##*/}" python3 - <<'PY'
|
||||
import json
|
||||
@@ -302,10 +299,7 @@ else:
|
||||
print(json.dumps(match))
|
||||
PY
|
||||
)
|
||||
response_status="${result%%$'\n'*}"
|
||||
response_body=""
|
||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
||||
write_response "$response_status" "$response_body"
|
||||
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||
else
|
||||
echo "Unexpected curl request: $method $url" >&2
|
||||
exit 97
|
||||
|
||||
@@ -69,7 +69,7 @@ section_nums() { # $1 = output $2 = header-prefix
|
||||
}
|
||||
|
||||
fail() { echo "FAIL: $1" >&2; exit 1; }
|
||||
contains() { grep -qx "$2" <<<"$1"; }
|
||||
contains() { printf '%s\n' "$1" | grep -qx "$2"; }
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Fixed (current) script behavior
|
||||
|
||||
@@ -225,10 +225,7 @@ write_response() {
|
||||
emit() {
|
||||
# Split a two-line "status\n<json body>" python result into the response.
|
||||
local result="$1"
|
||||
response_status="${result%%$'\n'*}"
|
||||
response_body=""
|
||||
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
|
||||
write_response "$response_status" "$response_body"
|
||||
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
|
||||
}
|
||||
|
||||
mode="${PR_REVIEW_TEST_MODE:-}"
|
||||
|
||||
@@ -222,8 +222,8 @@ grep -q 'Unknown action: bogus-action' "$OUTPUT_FILE"
|
||||
|
||||
# --- Case 2: -h/--help documents both overrides.
|
||||
HELP_TEXT="$("$SCRIPT_DIR/pr-review.sh" -h)"
|
||||
grep -q -- '-r, --repo' <<<"$HELP_TEXT"
|
||||
grep -q -- '-H, --host' <<<"$HELP_TEXT"
|
||||
echo "$HELP_TEXT" | grep -q -- '-r, --repo'
|
||||
echo "$HELP_TEXT" | grep -q -- '-H, --host'
|
||||
|
||||
# --- Case 3 (comment): a TRUE no-git-origin dir + -r/-H must not silently die
|
||||
# and must not fail with "not a git repository or no origin remote" either.
|
||||
|
||||
@@ -39,7 +39,7 @@ MAX_FRAME: Final = 64 * 1024
|
||||
MAX_STATE: Final = 4 * 1024 * 1024
|
||||
MAX_PENDING_TOKENS: Final = 256
|
||||
MAX_IN_FLIGHT_CONNECTIONS: Final = 16
|
||||
MAX_LEASE_TTL_SECONDS: Final = 300
|
||||
MAX_LEASE_TTL_SECONDS: Final = 3600
|
||||
STATE_VERSION: Final = 1
|
||||
READ_DEADLINE_SECONDS: Final = 1.0
|
||||
HANDLE_QUEUE_TIMEOUT_SECONDS: Final = 1.0
|
||||
@@ -50,8 +50,8 @@ LEASE_PENDING: Final = "PENDING_VERIFICATION"
|
||||
LEASE_PENDING_PROMOTION: Final = "PENDING_PROMOTION"
|
||||
LEASE_VERIFIED: Final = "VERIFIED"
|
||||
READ_ONLY_TOOLS: Final = {
|
||||
"claude": frozenset({"Read", "Grep", "Glob", "Ls", "Find"}),
|
||||
"pi": frozenset({"read", "grep", "find", "ls"}),
|
||||
"claude": frozenset({"Read", "Grep", "Glob"}),
|
||||
"pi": frozenset({"read", "ls"}),
|
||||
}
|
||||
RECOVERY_TOOL: Final = "mosaic_context_recover"
|
||||
|
||||
|
||||
@@ -8,7 +8,9 @@ import json
|
||||
import os
|
||||
import socket
|
||||
import sys
|
||||
import time
|
||||
from collections.abc import Callable, Mapping, Sequence
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Final
|
||||
|
||||
@@ -53,6 +55,48 @@ def broker_request(socket_path: Path, request: dict[str, object]) -> dict[str, o
|
||||
return value
|
||||
|
||||
|
||||
def _self_starttime() -> str | None:
|
||||
"""Field 22 of our own /proc stat — the anchor starttime the broker records.
|
||||
|
||||
Read past the comm field's parens, since a process name may contain them.
|
||||
"""
|
||||
try:
|
||||
raw = Path(f"/proc/{os.getpid()}/stat").read_text()
|
||||
return raw.rsplit(")", 1)[1].split()[19]
|
||||
except (OSError, IndexError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
def _append_launch_record(environ: Mapping[str, str], record: dict[str, object]) -> None:
|
||||
"""Append one NDJSON event to the #797 Runtime Session Ledger.
|
||||
|
||||
`fleet/run/sessions/` is operator-classified in framework-manifest.txt and is
|
||||
already covered by test-upgrade-manifest-guard.sh, so an upgrade can neither
|
||||
overwrite nor prune it. Files 0600 under a 0700 dir, matching what that guard
|
||||
asserts.
|
||||
|
||||
Never raises: a launch must not be denied over bookkeeping. But it also never
|
||||
fails silently — a missing record is exactly the kind of gap that made the
|
||||
2026-08-06 MUTATOR_UNVERIFIED investigation cost a day.
|
||||
"""
|
||||
try:
|
||||
mosaic_home = environ.get("MOSAIC_HOME") or str(Path.home() / ".config" / "mosaic")
|
||||
directory = Path(mosaic_home) / "fleet" / "run" / "sessions"
|
||||
directory.mkdir(parents=True, exist_ok=True)
|
||||
os.chmod(directory, 0o700)
|
||||
framed = {
|
||||
"seq": time.time_ns() // 1_000_000,
|
||||
"ts": datetime.now(timezone.utc).isoformat(),
|
||||
**record,
|
||||
}
|
||||
path = directory / "events.ndjson"
|
||||
descriptor = os.open(path, os.O_WRONLY | os.O_CREAT | os.O_APPEND, 0o600)
|
||||
with os.fdopen(descriptor, "w") as handle:
|
||||
handle.write(json.dumps(framed, separators=(",", ":")) + "\n")
|
||||
except (OSError, ValueError, TypeError) as error:
|
||||
print(f"[mosaic] WARNING: launch record not written: {error}", file=sys.stderr)
|
||||
|
||||
|
||||
def main(
|
||||
argv: Sequence[str] | None = None,
|
||||
*,
|
||||
@@ -94,8 +138,9 @@ def main(
|
||||
# silent pass and never folded into the generic registration-failure
|
||||
# branch.
|
||||
try:
|
||||
activation_capability = probe_activation_capability(source_environment)
|
||||
assert_activation_capability_matches(
|
||||
probe_activation_capability(source_environment),
|
||||
activation_capability,
|
||||
expected_activation_capability,
|
||||
)
|
||||
except VersionCouplingError as version_error:
|
||||
@@ -128,6 +173,32 @@ def main(
|
||||
print("Mosaic lease broker registration failed; runtime launch denied.", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
# Immutable launch record, half two. `mosaic` wrote `session.launch` with the
|
||||
# config/provenance it knows; only this process knows the broker session id
|
||||
# and the activation capability it just asserted. os.execvpe preserves the
|
||||
# PID, so this PID is BOTH the anchor pid and the join key back to that
|
||||
# record. Never fatal — bookkeeping must not deny a launch — but never
|
||||
# silent either.
|
||||
_append_launch_record(
|
||||
source_environment,
|
||||
{
|
||||
"kind": "lease.register",
|
||||
# Joins back to `mosaic`'s session.launch record. NOT pid: execRuntime()
|
||||
# spawns rather than execs, so this process is a CHILD of mosaic with a
|
||||
# different pid. This pid IS the broker anchor pid (os.execvpe below
|
||||
# preserves it), which is a separate and still-useful fact.
|
||||
"launch_id": source_environment.get("MOSAIC_LAUNCH_ID"),
|
||||
"pid": os.getpid(),
|
||||
"runtime": arguments.runtime,
|
||||
"session_id": session_id,
|
||||
"runtime_generation": generation,
|
||||
"generation_file": str(generation_file),
|
||||
"anchor_starttime": _self_starttime(),
|
||||
"activation_capability": activation_capability,
|
||||
"command": Path(command[0]).name,
|
||||
},
|
||||
)
|
||||
|
||||
environment = dict(source_environment)
|
||||
environment["MOSAIC_LEASE_SESSION_ID"] = session_id
|
||||
environment["MOSAIC_RUNTIME_GENERATION"] = str(generation)
|
||||
|
||||
@@ -0,0 +1,337 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Lease promotion client — the half the enforcement toolkit never shipped.
|
||||
|
||||
The enforcement half (``daemon.py`` + ``mutator-gate.py``) ships and denies. The
|
||||
promotion half has no production caller anywhere in the package: as of 0.0.48,
|
||||
0.0.49 and 0.0.50-next.2207, ``begin_verification`` / ``observe_receipt`` /
|
||||
``promote_lease`` are invoked only by ``broker-test-client.ts``, the acceptance
|
||||
spec, unit tests, and two probes under ``docs/``. Consequence: **no lease on any
|
||||
host can reach VERIFIED**, so every mutator is denied ``MUTATOR_UNVERIFIED`` by a
|
||||
gate nothing can satisfy.
|
||||
|
||||
THE PROTOCOL (``daemon.py:578-754``)
|
||||
------------------------------------
|
||||
1. ``begin_verification`` — broker revokes, mints a challenge, and returns the
|
||||
exact ``receipt`` text the MODEL must emit
|
||||
2. *the model emits that text verbatim as its ENTIRE latest message*
|
||||
3. the runtime adapter ships that message to the daemon-owned observer socket
|
||||
4. ``observe_receipt`` -> ``PENDING_PROMOTION``
|
||||
5. ``promote_lease`` -> ``VERIFIED``
|
||||
|
||||
THIS MODULE IMPLEMENTS 1, 4 AND 5 — NEVER 2
|
||||
-------------------------------------------
|
||||
Step 2 is the security property, not a formality. ``is_verbatim_receipt`` uses
|
||||
``hmac.compare_digest`` against the exact minted string — explicitly "not a
|
||||
transcript substring" (``receipt_challenge.py``). Promotion therefore requires a
|
||||
live model that received the challenge in its context and echoed it exactly.
|
||||
|
||||
``receipt-observer-client.py`` will post ANY string as the latest assistant
|
||||
message. A promotion client that posted its own receipt would satisfy the broker
|
||||
while proving nothing — a gate-disabler indistinguishable from a working fix
|
||||
unless someone looks for it. **This module never posts a receipt.** Emitting it
|
||||
belongs to the runtime adapter, where a real model turn happens.
|
||||
|
||||
The construction binds the exact normative source bytes. ``h_source`` /
|
||||
``h_payload`` are derived by the framework's own
|
||||
``normative_fragments.build_payload`` rather than reimplemented: the broker
|
||||
derives them the same way and any divergence yields ``PAYLOAD_BINDING_MISMATCH``.
|
||||
There must be exactly one implementation.
|
||||
|
||||
WHAT THE BINDING DOES *NOT* PROVE
|
||||
---------------------------------
|
||||
It is tempting to read a VERIFIED lease as "this agent is running THIS law".
|
||||
**It does not mean that**, and writing it down that way is how the belief spread.
|
||||
The broker holds no reference copy of any normative source and never opens one;
|
||||
it recomputes ``h_source`` / ``h_payload`` from the fragment bytes THIS CLIENT
|
||||
sent and compares them to the binding THIS CLIENT sent (``daemon.py:602-616``).
|
||||
Both sides of that comparison originate here, so it detects corruption in
|
||||
transit and nothing else. What the binding actually asserts is "the client
|
||||
claims these bytes, self-consistently".
|
||||
|
||||
Making it mean the stronger thing requires the broker to re-read the on-disk
|
||||
sources itself, against a manifest the agent cannot rewrite — i.e. broker code
|
||||
attestation under its own uid. Until then, do not cite a VERIFIED lease as
|
||||
evidence of law integrity.
|
||||
|
||||
Usage
|
||||
-----
|
||||
lease_promote.py --begin # prints the receipt the MODEL must emit
|
||||
lease_promote.py --complete <challenge> # after the adapter observed it
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import socket
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Final
|
||||
|
||||
# Isolated (`python -I`) adapter invocations must still import co-located
|
||||
# framework modules; never depend on the caller's PYTHONPATH.
|
||||
_MODULE_DIRECTORY = str(Path(__file__).resolve().parent)
|
||||
if _MODULE_DIRECTORY not in sys.path:
|
||||
sys.path.insert(0, _MODULE_DIRECTORY)
|
||||
|
||||
from normative_fragments import NormativeFragment, build_payload # noqa: E402
|
||||
|
||||
MAX_FRAME: Final = 64 * 1024
|
||||
BROKER_TIMEOUT_SECONDS: Final = 3.0
|
||||
SCHEMA_VERSION: Final = 1
|
||||
MANIFEST_VERSION: Final = 1
|
||||
GENERATOR_VERSION: Final = "mosaic/lease_promote@1"
|
||||
DEFAULT_TTL_SECONDS: Final = 3600
|
||||
|
||||
# Normative sources whose exact bytes bind the lease, in binding order. Order is
|
||||
# load-bearing: ``h_source`` frames the resolved sequence, so reordering changes
|
||||
# the derivation. Never fabricate a source that is not on disk.
|
||||
FRAGMENT_SOURCES: Final = (
|
||||
"CONSTITUTION.md",
|
||||
"AGENTS.md",
|
||||
"SOUL.md",
|
||||
"USER.md",
|
||||
"STANDARDS.md",
|
||||
"TOOLS.md",
|
||||
)
|
||||
|
||||
# Framework-owned sources, reconciled on every upgrade — `install.sh:76`
|
||||
# FRAMEWORK_OWNED and `config/file-adapter.ts` FRAMEWORK_OWNED_FILES — plus the
|
||||
# per-runtime contract shipped under `framework/runtime/<runtime>/`. A deployment
|
||||
# missing one of these is broken, not minimal, so their absence is refused rather
|
||||
# than silently dropped from the binding.
|
||||
#
|
||||
# SOUL.md and USER.md are deliberately excluded: install.sh does not seed them
|
||||
# ("intentionally NOT seeded here — they are generated by `mosaic init`"), so a
|
||||
# fresh install legitimately lacks both. TOOLS.md is user-seeded on first install
|
||||
# only. Absence of those three is reported, not fatal.
|
||||
REQUIRED_SOURCES: Final = frozenset({"CONSTITUTION.md", "AGENTS.md", "STANDARDS.md"})
|
||||
|
||||
|
||||
class IncompleteBinding(RuntimeError):
|
||||
"""A source that must bind this lease could not be read.
|
||||
|
||||
**Never downgrade this to a skip.** The broker recomputes the hashes from the
|
||||
fragments it is sent, so an omitted fragment is internally consistent and
|
||||
``PAYLOAD_BINDING_MISMATCH`` cannot fire — a partial law promotes exactly like
|
||||
a complete one, and nothing downstream can tell the difference. Dropping an
|
||||
unreadable source therefore does not degrade the binding, it forges a smaller
|
||||
one. Fail here, where the omission is still visible.
|
||||
"""
|
||||
|
||||
|
||||
def mosaic_home() -> Path:
|
||||
return Path(os.environ.get("MOSAIC_HOME") or Path.home() / ".config" / "mosaic")
|
||||
|
||||
|
||||
def broker_socket() -> Path:
|
||||
value = os.environ.get("MOSAIC_LEASE_BROKER_SOCKET")
|
||||
if value:
|
||||
return Path(value)
|
||||
runtime_dir = os.environ.get("XDG_RUNTIME_DIR")
|
||||
if runtime_dir:
|
||||
return Path(runtime_dir) / "mosaic-lease" / "broker.sock"
|
||||
return Path(f"/run/user/{os.getuid()}/mosaic-lease/broker.sock")
|
||||
|
||||
|
||||
def session_identity() -> tuple[str, int, str]:
|
||||
"""Session id, CURRENT generation, runtime.
|
||||
|
||||
The generation file wins over the env var, matching ``lease_generation.py``.
|
||||
Sending a generation HIGHER than the broker's would revoke this session's own
|
||||
authority (``daemon.py:342-344``), so this never guesses.
|
||||
"""
|
||||
session_id = os.environ["MOSAIC_LEASE_SESSION_ID"]
|
||||
runtime = os.environ["MOSAIC_LEASE_RUNTIME"]
|
||||
state_file = os.environ.get("MOSAIC_LEASE_GENERATION_FILE")
|
||||
if state_file:
|
||||
try:
|
||||
return session_id, int(Path(state_file).read_text().strip()), runtime
|
||||
except (OSError, ValueError):
|
||||
pass
|
||||
return session_id, int(os.environ["MOSAIC_RUNTIME_GENERATION"]), runtime
|
||||
|
||||
|
||||
def build_construction(runtime: str) -> tuple[dict[str, object], object]:
|
||||
"""Assemble the wire construction and derive its hashes with the sole builder."""
|
||||
runtime_contract = f"runtime/{runtime}/RUNTIME.md"
|
||||
sources = list(FRAGMENT_SOURCES) + [runtime_contract]
|
||||
required = REQUIRED_SOURCES | {runtime_contract}
|
||||
wire_fragments: list[dict[str, str]] = []
|
||||
objects: list[NormativeFragment] = []
|
||||
absent: list[str] = []
|
||||
|
||||
for source_id in sources:
|
||||
try:
|
||||
content = (mosaic_home() / source_id).read_bytes()
|
||||
except FileNotFoundError:
|
||||
# Genuinely not on disk. Legitimate only for operator-owned sources.
|
||||
if source_id in required:
|
||||
raise IncompleteBinding(
|
||||
f"required normative source is absent: {source_id}"
|
||||
) from None
|
||||
absent.append(source_id)
|
||||
continue
|
||||
except OSError as exc:
|
||||
# The path resolves but will not read — EACCES, EIO, EISDIR, ELOOP.
|
||||
# That is an anomaly for EVERY source, optional ones included: an
|
||||
# unreadable file is not an un-configured one, and treating it as
|
||||
# absent is what lets a permission change quietly shrink the law.
|
||||
raise IncompleteBinding(
|
||||
f"normative source is present but unreadable: {source_id} "
|
||||
f"({type(exc).__name__})"
|
||||
) from exc
|
||||
|
||||
digest = hashlib.sha256(content).hexdigest()
|
||||
wire_fragments.append(
|
||||
{
|
||||
"source_id": source_id,
|
||||
"content_base64": base64.b64encode(content).decode("ascii"),
|
||||
"expected_sha256": digest,
|
||||
}
|
||||
)
|
||||
objects.append(NormativeFragment(source_id, content, digest))
|
||||
|
||||
if not wire_fragments:
|
||||
raise IncompleteBinding("no normative sources found — refusing an empty binding")
|
||||
|
||||
# Absence is legitimate here but never invisible. The omission is already
|
||||
# baked into h_source (the framed source sequence differs), but nothing
|
||||
# compares h_source to an expected value, so this line is the only place a
|
||||
# human learns the binding was narrower than the full set.
|
||||
if absent:
|
||||
print(
|
||||
f"lease_promote: binding omits absent operator sources: {', '.join(absent)}",
|
||||
file=sys.stderr,
|
||||
)
|
||||
|
||||
result = build_payload(
|
||||
manifest_version=MANIFEST_VERSION,
|
||||
generator_version=GENERATOR_VERSION,
|
||||
fragments=objects,
|
||||
)
|
||||
if result.injectionDecision != "ACCEPTED" or not result.promotion:
|
||||
raise RuntimeError(f"construction refused locally: {result.source_reason}")
|
||||
|
||||
return (
|
||||
{
|
||||
"manifest_version": MANIFEST_VERSION,
|
||||
"generator_version": GENERATOR_VERSION,
|
||||
"fragments": wire_fragments,
|
||||
},
|
||||
result,
|
||||
)
|
||||
|
||||
|
||||
def broker_request(payload: dict[str, object]) -> dict[str, object]:
|
||||
raw = (json.dumps(payload, separators=(",", ":")) + "\n").encode()
|
||||
if len(raw) > MAX_FRAME:
|
||||
raise ValueError(
|
||||
f"request too large ({len(raw)} bytes); broker frame cap is {MAX_FRAME}"
|
||||
)
|
||||
response = bytearray()
|
||||
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as connection:
|
||||
connection.settimeout(BROKER_TIMEOUT_SECONDS)
|
||||
connection.connect(str(broker_socket()))
|
||||
connection.sendall(raw)
|
||||
connection.shutdown(socket.SHUT_WR)
|
||||
while len(response) <= MAX_FRAME:
|
||||
chunk = connection.recv(4096)
|
||||
if not chunk:
|
||||
break
|
||||
response.extend(chunk)
|
||||
if len(response) > MAX_FRAME or not response.endswith(b"\n"):
|
||||
raise ValueError("invalid broker reply")
|
||||
value = json.loads(response)
|
||||
if not isinstance(value, dict):
|
||||
raise ValueError("invalid broker reply")
|
||||
return value
|
||||
|
||||
|
||||
def begin(
|
||||
ttl_seconds: int = DEFAULT_TTL_SECONDS,
|
||||
compaction_epoch: int = 0,
|
||||
request_epoch: int = 0,
|
||||
) -> dict[str, object]:
|
||||
"""Step 1. Returns the broker reply, including the exact ``receipt`` text."""
|
||||
session_id, generation, runtime = session_identity()
|
||||
construction, derived = build_construction(runtime)
|
||||
return broker_request(
|
||||
{
|
||||
"action": "begin_verification",
|
||||
"session_id": session_id,
|
||||
"runtime_generation": generation,
|
||||
"runtime": runtime,
|
||||
"ttl_seconds": ttl_seconds,
|
||||
"binding": {
|
||||
"compaction_epoch": compaction_epoch,
|
||||
"request_epoch": request_epoch,
|
||||
"h_source": derived.h_source,
|
||||
"h_payload": derived.h_payload,
|
||||
"schema_version": SCHEMA_VERSION,
|
||||
},
|
||||
"construction": construction,
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def complete(challenge: str) -> dict[str, object]:
|
||||
"""Steps 4-5. Assumes the model already emitted the receipt and the adapter
|
||||
shipped it to the observer socket."""
|
||||
session_id, generation, _ = session_identity()
|
||||
observed = broker_request(
|
||||
{
|
||||
"action": "observe_receipt",
|
||||
"session_id": session_id,
|
||||
"runtime_generation": generation,
|
||||
"receipt_challenge": challenge,
|
||||
}
|
||||
)
|
||||
if observed.get("ok") is not True or observed.get("state") != "PENDING_PROMOTION":
|
||||
return {"stage": "observe_receipt", **observed}
|
||||
promoted = broker_request(
|
||||
{
|
||||
"action": "promote_lease",
|
||||
"session_id": session_id,
|
||||
"runtime_generation": generation,
|
||||
"receipt_challenge": challenge,
|
||||
}
|
||||
)
|
||||
return {"stage": "promote_lease", **promoted}
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser(description="Mosaic lease promotion client.")
|
||||
group = parser.add_mutually_exclusive_group(required=True)
|
||||
group.add_argument(
|
||||
"--begin",
|
||||
action="store_true",
|
||||
help="mint a challenge; prints the receipt the MODEL must emit verbatim",
|
||||
)
|
||||
group.add_argument(
|
||||
"--complete",
|
||||
metavar="CHALLENGE",
|
||||
help="observe the emitted receipt and promote the lease",
|
||||
)
|
||||
parser.add_argument("--ttl-seconds", type=int, default=DEFAULT_TTL_SECONDS)
|
||||
arguments = parser.parse_args(argv)
|
||||
|
||||
try:
|
||||
if arguments.begin:
|
||||
print(json.dumps(begin(ttl_seconds=arguments.ttl_seconds), indent=2))
|
||||
else:
|
||||
print(json.dumps(complete(arguments.complete), indent=2))
|
||||
except KeyError as exc:
|
||||
print(f"missing lease environment: {exc}; not a lease-gated session", file=sys.stderr)
|
||||
return 2
|
||||
except (OSError, ValueError, RuntimeError, json.JSONDecodeError) as exc:
|
||||
print(f"{type(exc).__name__}: {exc}", file=sys.stderr)
|
||||
return 2
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,399 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Claude UserPromptSubmit hook for operator-triggered lease promotion."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import importlib.util
|
||||
import json
|
||||
import os
|
||||
import secrets
|
||||
import stat
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from collections.abc import Callable, Mapping
|
||||
from pathlib import Path
|
||||
from typing import Final, TextIO
|
||||
|
||||
_MODULE_DIRECTORY = str(Path(__file__).resolve().parent)
|
||||
if _MODULE_DIRECTORY not in sys.path:
|
||||
sys.path.insert(0, _MODULE_DIRECTORY)
|
||||
|
||||
from receipt_challenge import receipt_for # noqa: E402
|
||||
|
||||
_observer_spec = importlib.util.spec_from_file_location(
|
||||
"mosaic_receipt_observer_client", Path(__file__).resolve().with_name("receipt-observer-client.py")
|
||||
)
|
||||
if _observer_spec is None or _observer_spec.loader is None:
|
||||
raise RuntimeError("unable to load receipt observer client")
|
||||
_observer_module = importlib.util.module_from_spec(_observer_spec)
|
||||
_observer_spec.loader.exec_module(_observer_module)
|
||||
observer_request = _observer_module.observer_request
|
||||
|
||||
MAX_FRAME: Final = 64 * 1024
|
||||
PENDING_MAX_AGE_SECONDS: Final = 60 * 60
|
||||
PROMOTER_TIMEOUT_SECONDS: Final = 10.0
|
||||
PROMOTION_PROMPT: Final = "/mosaic-promote"
|
||||
PROMOTER: Final = Path(__file__).resolve().with_name("lease_promote.py")
|
||||
PENDING_DIRECTORY: Final = "mosaic-lease"
|
||||
AUTHORIZATION_DIRECTORY: Final = "authorizations"
|
||||
AUTHORIZATION_TTL_SECONDS: Final = 60
|
||||
LEASE_TTL_SECONDS: Final = 60 * 60
|
||||
LOCK_FILE: Final = "promotion.lock"
|
||||
RESULT_FILE: Final = "last-result.json"
|
||||
EXPECTED_BEGIN_KEYS: Final = frozenset(
|
||||
{"ok", "state", "receipt_challenge", "receipt", "binding"}
|
||||
)
|
||||
EXPECTED_BINDING_KEYS: Final = frozenset(
|
||||
{
|
||||
"compaction_epoch",
|
||||
"request_epoch",
|
||||
"h_source",
|
||||
"h_payload",
|
||||
"runtime_generation",
|
||||
"schema_version",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
class PromotionAlreadyInProgress(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def reject_duplicate_json_keys(pairs: list[tuple[str, object]]) -> dict[str, object]:
|
||||
value: dict[str, object] = {}
|
||||
for key, item in pairs:
|
||||
if key in value:
|
||||
raise ValueError("duplicate promoter JSON key")
|
||||
value[key] = item
|
||||
return value
|
||||
|
||||
|
||||
def read_hook_input(stream: object) -> dict[str, object]:
|
||||
raw = getattr(stream, "buffer", stream).read(MAX_FRAME + 1)
|
||||
if not isinstance(raw, bytes) or len(raw) > MAX_FRAME:
|
||||
raise ValueError("invalid UserPromptSubmit input")
|
||||
value = json.loads(raw, object_pairs_hook=reject_duplicate_json_keys)
|
||||
if not isinstance(value, dict):
|
||||
raise ValueError("invalid UserPromptSubmit input")
|
||||
return value
|
||||
|
||||
|
||||
def emit_context(stream: TextIO, message: str) -> None:
|
||||
json.dump(
|
||||
{
|
||||
"hookSpecificOutput": {
|
||||
"hookEventName": "UserPromptSubmit",
|
||||
"additionalContext": message,
|
||||
}
|
||||
},
|
||||
stream,
|
||||
separators=(",", ":"),
|
||||
)
|
||||
stream.write("\n")
|
||||
|
||||
|
||||
def session_pending_name(environ: Mapping[str, str]) -> tuple[Path, str]:
|
||||
runtime_dir = Path(environ["XDG_RUNTIME_DIR"])
|
||||
session_id = environ["MOSAIC_LEASE_SESSION_ID"]
|
||||
if not runtime_dir.is_absolute():
|
||||
raise ValueError("XDG_RUNTIME_DIR must be absolute")
|
||||
if len(session_id) != 64 or any(character not in "0123456789abcdef" for character in session_id):
|
||||
raise ValueError("invalid lease session id")
|
||||
return runtime_dir, f"pending-{session_id}"
|
||||
|
||||
|
||||
def open_pending_directory(runtime_dir: Path) -> int:
|
||||
directory_flags = (
|
||||
os.O_RDONLY
|
||||
| getattr(os, "O_CLOEXEC", 0)
|
||||
| getattr(os, "O_DIRECTORY", 0)
|
||||
| getattr(os, "O_NOFOLLOW", 0)
|
||||
)
|
||||
runtime_descriptor = os.open(runtime_dir, directory_flags)
|
||||
try:
|
||||
runtime_metadata = os.fstat(runtime_descriptor)
|
||||
if (
|
||||
not stat.S_ISDIR(runtime_metadata.st_mode)
|
||||
or runtime_metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(runtime_metadata.st_mode) != 0o700
|
||||
):
|
||||
raise ValueError("unsafe XDG runtime directory")
|
||||
try:
|
||||
os.mkdir(PENDING_DIRECTORY, mode=0o700, dir_fd=runtime_descriptor)
|
||||
except FileExistsError:
|
||||
pass
|
||||
descriptor = os.open(PENDING_DIRECTORY, directory_flags, dir_fd=runtime_descriptor)
|
||||
finally:
|
||||
os.close(runtime_descriptor)
|
||||
|
||||
metadata = os.fstat(descriptor)
|
||||
if (
|
||||
not stat.S_ISDIR(metadata.st_mode)
|
||||
or metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(metadata.st_mode) != 0o700
|
||||
):
|
||||
os.close(descriptor)
|
||||
raise ValueError("unsafe promotion pending directory")
|
||||
return descriptor
|
||||
|
||||
|
||||
def acquire_lock(directory_descriptor: int) -> int:
|
||||
flags = (
|
||||
os.O_RDWR
|
||||
| os.O_CREAT
|
||||
| getattr(os, "O_CLOEXEC", 0)
|
||||
| getattr(os, "O_NOFOLLOW", 0)
|
||||
)
|
||||
descriptor = os.open(LOCK_FILE, flags, 0o600, dir_fd=directory_descriptor)
|
||||
metadata = os.fstat(descriptor)
|
||||
if (
|
||||
not stat.S_ISREG(metadata.st_mode)
|
||||
or metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(metadata.st_mode) != 0o600
|
||||
):
|
||||
os.close(descriptor)
|
||||
raise ValueError("unsafe promotion lock file")
|
||||
try:
|
||||
fcntl.flock(descriptor, fcntl.LOCK_EX | fcntl.LOCK_NB)
|
||||
except BlockingIOError as error:
|
||||
os.close(descriptor)
|
||||
raise PromotionAlreadyInProgress() from error
|
||||
return descriptor
|
||||
|
||||
|
||||
def sweep_stale_pending(directory_descriptor: int, current_time: float) -> None:
|
||||
cutoff = current_time - PENDING_MAX_AGE_SECONDS
|
||||
removed = False
|
||||
with os.scandir(directory_descriptor) as entries:
|
||||
for candidate in entries:
|
||||
if not (
|
||||
candidate.name.startswith("pending-")
|
||||
or candidate.name.startswith(".pending-")
|
||||
):
|
||||
continue
|
||||
try:
|
||||
metadata = candidate.stat(follow_symlinks=False)
|
||||
if metadata.st_mtime < cutoff and not stat.S_ISDIR(metadata.st_mode):
|
||||
os.unlink(candidate.name, dir_fd=directory_descriptor)
|
||||
removed = True
|
||||
except FileNotFoundError:
|
||||
continue
|
||||
if removed:
|
||||
os.fsync(directory_descriptor)
|
||||
|
||||
|
||||
def consume_authorization(directory_descriptor: int, session_id: str, wall_clock: float) -> str | None:
|
||||
flags = os.O_RDONLY | getattr(os, "O_CLOEXEC", 0) | getattr(os, "O_DIRECTORY", 0) | getattr(os, "O_NOFOLLOW", 0)
|
||||
try:
|
||||
authorization_descriptor = os.open(AUTHORIZATION_DIRECTORY, flags, dir_fd=directory_descriptor)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
try:
|
||||
metadata = os.fstat(authorization_descriptor)
|
||||
if not stat.S_ISDIR(metadata.st_mode) or metadata.st_uid != os.getuid() or stat.S_IMODE(metadata.st_mode) != 0o700:
|
||||
raise ValueError("unsafe promotion authorization directory")
|
||||
name = f"{session_id}.auth"
|
||||
try:
|
||||
descriptor = os.open(name, os.O_RDONLY | getattr(os, "O_CLOEXEC", 0) | getattr(os, "O_NOFOLLOW", 0), dir_fd=authorization_descriptor)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
try:
|
||||
token_metadata = os.fstat(descriptor)
|
||||
if not stat.S_ISREG(token_metadata.st_mode) or token_metadata.st_uid != os.getuid() or stat.S_IMODE(token_metadata.st_mode) != 0o600 or token_metadata.st_size <= 0 or token_metadata.st_size > MAX_FRAME:
|
||||
raise ValueError("unsafe promotion authorization")
|
||||
raw = os.read(descriptor, MAX_FRAME + 1)
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
os.unlink(name, dir_fd=authorization_descriptor)
|
||||
os.fsync(authorization_descriptor)
|
||||
token = json.loads(raw, object_pairs_hook=reject_duplicate_json_keys)
|
||||
if not isinstance(token, dict) or set(token) != {"nonce", "seat", "session_id", "expires_at", "ts"}:
|
||||
return None
|
||||
nonce = token.get("nonce")
|
||||
expires_at = token.get("expires_at")
|
||||
issued_at = token.get("ts")
|
||||
if token.get("session_id") != session_id or not isinstance(token.get("seat"), str) or not isinstance(nonce, str) or len(nonce) != 64 or any(char not in "0123456789abcdef" for char in nonce) or type(expires_at) not in (int, float) or type(issued_at) not in (int, float) or expires_at <= wall_clock or expires_at > issued_at + AUTHORIZATION_TTL_SECONDS:
|
||||
return None
|
||||
return nonce
|
||||
finally:
|
||||
os.close(authorization_descriptor)
|
||||
|
||||
|
||||
def write_result(directory_descriptor: int, attempt_id: str, verified: bool, reason: str | None, session_id: str, wall_clock: float) -> None:
|
||||
temporary = f".{RESULT_FILE}.tmp-{secrets.token_hex(8)}"
|
||||
descriptor = os.open(temporary, os.O_WRONLY | os.O_CREAT | os.O_EXCL | getattr(os, "O_CLOEXEC", 0) | getattr(os, "O_NOFOLLOW", 0), 0o600, dir_fd=directory_descriptor)
|
||||
try:
|
||||
os.fchmod(descriptor, 0o600)
|
||||
with os.fdopen(descriptor, "w", encoding="utf-8", closefd=False) as stream:
|
||||
json.dump({"attempt_id": attempt_id, "expires_at_wallclock": wall_clock + LEASE_TTL_SECONDS if verified else None, "reason": reason, "session_id": session_id, "ts": wall_clock, "verified": verified}, stream, separators=(",", ":"), sort_keys=True)
|
||||
stream.flush(); os.fsync(stream.fileno())
|
||||
os.replace(temporary, RESULT_FILE, src_dir_fd=directory_descriptor, dst_dir_fd=directory_descriptor)
|
||||
os.fsync(directory_descriptor)
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
|
||||
|
||||
def write_pending(directory_descriptor: int, name: str, challenge: str) -> None:
|
||||
temporary = f".{name}.tmp-{secrets.token_hex(8)}"
|
||||
flags = (
|
||||
os.O_WRONLY
|
||||
| os.O_CREAT
|
||||
| os.O_EXCL
|
||||
| getattr(os, "O_CLOEXEC", 0)
|
||||
| getattr(os, "O_NOFOLLOW", 0)
|
||||
)
|
||||
descriptor = os.open(temporary, flags, 0o600, dir_fd=directory_descriptor)
|
||||
try:
|
||||
os.fchmod(descriptor, 0o600)
|
||||
with os.fdopen(descriptor, "w", encoding="utf-8", closefd=False) as stream:
|
||||
stream.write(challenge)
|
||||
stream.flush()
|
||||
os.fsync(stream.fileno())
|
||||
os.replace(
|
||||
temporary,
|
||||
name,
|
||||
src_dir_fd=directory_descriptor,
|
||||
dst_dir_fd=directory_descriptor,
|
||||
)
|
||||
os.fsync(directory_descriptor)
|
||||
except Exception:
|
||||
try:
|
||||
os.unlink(temporary, dir_fd=directory_descriptor)
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
raise
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
|
||||
|
||||
def parse_begin_reply(
|
||||
completed: subprocess.CompletedProcess[str],
|
||||
) -> tuple[str, dict[str, object] | None]:
|
||||
if completed.returncode != 0:
|
||||
return f"PROMOTER_EXIT_{completed.returncode}", None
|
||||
try:
|
||||
value = json.loads(
|
||||
completed.stdout,
|
||||
object_pairs_hook=reject_duplicate_json_keys,
|
||||
)
|
||||
except (json.JSONDecodeError, RecursionError, TypeError, ValueError):
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
if not isinstance(value, dict):
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
if value.get("ok") is False and set(value) == {"ok", "code"}:
|
||||
code = value.get("code")
|
||||
return code if isinstance(code, str) and code else "PROMOTION_BEGIN_REFUSED", value
|
||||
if set(value) != EXPECTED_BEGIN_KEYS or value.get("ok") is not True:
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
if value.get("state") != "PENDING_VERIFICATION":
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
challenge = value.get("receipt_challenge")
|
||||
receipt = value.get("receipt")
|
||||
binding = value.get("binding")
|
||||
if (
|
||||
not isinstance(challenge, str)
|
||||
or len(challenge) != 64
|
||||
or any(character not in "0123456789abcdef" for character in challenge)
|
||||
or not isinstance(receipt, str)
|
||||
or not isinstance(binding, dict)
|
||||
or set(binding) != EXPECTED_BINDING_KEYS
|
||||
):
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
integer_fields = (
|
||||
"compaction_epoch",
|
||||
"request_epoch",
|
||||
"runtime_generation",
|
||||
"schema_version",
|
||||
)
|
||||
if any(type(binding.get(field)) is not int or binding[field] < 0 for field in integer_fields):
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
if not all(
|
||||
isinstance(binding.get(field), str)
|
||||
and len(binding[field]) == 64
|
||||
and all(character in "0123456789abcdef" for character in binding[field])
|
||||
for field in ("h_source", "h_payload")
|
||||
):
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
if not secrets.compare_digest(
|
||||
receipt.encode("utf-8"),
|
||||
receipt_for(challenge, binding).encode("utf-8"),
|
||||
):
|
||||
return "INVALID_PROMOTER_REPLY", None
|
||||
return "", value
|
||||
|
||||
|
||||
def main(
|
||||
*,
|
||||
environ: Mapping[str, str] | None = None,
|
||||
stdin: object | None = None,
|
||||
stdout: TextIO | None = None,
|
||||
stderr: TextIO | None = None,
|
||||
run: Callable[..., subprocess.CompletedProcess[str]] = subprocess.run,
|
||||
now: Callable[[], float] = time.time,
|
||||
) -> int:
|
||||
source_environment = os.environ if environ is None else environ
|
||||
input_stream = sys.stdin if stdin is None else stdin
|
||||
output_stream = sys.stdout if stdout is None else stdout
|
||||
error_stream = sys.stderr if stderr is None else stderr
|
||||
|
||||
try:
|
||||
hook_input = read_hook_input(input_stream)
|
||||
except (OSError, RecursionError, ValueError, json.JSONDecodeError) as error:
|
||||
print(f"Mosaic promotion trigger ignored invalid hook input: {error}", file=error_stream)
|
||||
return 0
|
||||
if hook_input.get("prompt") != PROMOTION_PROMPT:
|
||||
return 0
|
||||
|
||||
directory_descriptor: int | None = None
|
||||
lock_descriptor: int | None = None
|
||||
try:
|
||||
runtime_dir, pending_name = session_pending_name(source_environment)
|
||||
session_id = source_environment["MOSAIC_LEASE_SESSION_ID"]
|
||||
directory_descriptor = open_pending_directory(runtime_dir)
|
||||
lock_descriptor = acquire_lock(directory_descriptor)
|
||||
wall_clock = now()
|
||||
nonce = consume_authorization(directory_descriptor, session_id, wall_clock)
|
||||
if nonce is None:
|
||||
write_result(directory_descriptor, "0" * 64, False, "NOT_AUTHORIZED", session_id, wall_clock)
|
||||
print("Mosaic promotion denied: NOT_AUTHORIZED.", file=error_stream)
|
||||
return 0
|
||||
sweep_stale_pending(directory_descriptor, wall_clock)
|
||||
completed = run([sys.executable, "-I", "-S", "-B", str(PROMOTER), "--begin"], check=False, capture_output=True, text=True, env=dict(source_environment), timeout=PROMOTER_TIMEOUT_SECONDS)
|
||||
code, reply = parse_begin_reply(completed)
|
||||
if code or reply is None:
|
||||
write_result(directory_descriptor, nonce, False, code or "PROMOTION_BEGIN_FAILED", session_id, now())
|
||||
return 0
|
||||
challenge = str(reply["receipt_challenge"])
|
||||
observation = observer_request(
|
||||
Path(source_environment["MOSAIC_RECEIPT_OBSERVER_SOCKET"]),
|
||||
{"action": "record_runtime_observation", "session_id": session_id, "runtime_generation": int(source_environment["MOSAIC_RUNTIME_GENERATION"]), "runtime": "claude", "latest_assistant_message": reply["receipt"]},
|
||||
)
|
||||
if set(observation) != {"ok"} or observation.get("ok") is not True:
|
||||
write_result(directory_descriptor, challenge, False, "OBSERVATION_REJECTED", session_id, now())
|
||||
return 0
|
||||
completion = run([sys.executable, "-I", "-S", "-B", str(PROMOTER), "--complete", challenge], check=False, capture_output=True, text=True, env=dict(source_environment), timeout=PROMOTER_TIMEOUT_SECONDS)
|
||||
try:
|
||||
outcome = json.loads(completion.stdout, object_pairs_hook=reject_duplicate_json_keys)
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
outcome = None
|
||||
if completion.returncode == 0 and isinstance(outcome, dict) and outcome.get("stage") == "promote_lease" and outcome.get("ok") is True and outcome.get("state") == "VERIFIED":
|
||||
write_result(directory_descriptor, challenge, True, None, session_id, now())
|
||||
else:
|
||||
reason = outcome.get("code") if isinstance(outcome, dict) and isinstance(outcome.get("code"), str) else "PROMOTION_INCOMPLETE"
|
||||
write_result(directory_descriptor, challenge, False, reason, session_id, now())
|
||||
except PromotionAlreadyInProgress:
|
||||
print("Mosaic promotion denied: PROMOTION_ALREADY_IN_PROGRESS.", file=error_stream)
|
||||
except (KeyError, OSError, RecursionError, ValueError, subprocess.SubprocessError) as error:
|
||||
print(f"Mosaic promotion begin failed: {type(error).__name__}: {error}", file=error_stream)
|
||||
finally:
|
||||
if lock_descriptor is not None:
|
||||
os.close(lock_descriptor)
|
||||
if directory_descriptor is not None:
|
||||
os.close(directory_descriptor)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,361 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Claude Stop hook that completes a pending operator-triggered promotion."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import json
|
||||
import os
|
||||
import secrets
|
||||
import stat
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from collections.abc import Callable, Mapping
|
||||
from pathlib import Path
|
||||
from typing import Final, NamedTuple, TextIO
|
||||
|
||||
MAX_FRAME: Final = 64 * 1024
|
||||
PROMOTER_TIMEOUT_SECONDS: Final = 10.0
|
||||
LEASE_TTL_SECONDS: Final = 60 * 60
|
||||
PROMOTER: Final = Path(__file__).resolve().with_name("lease_promote.py")
|
||||
PENDING_DIRECTORY: Final = "mosaic-lease"
|
||||
LOCK_FILE: Final = "promotion.lock"
|
||||
RESULT_FILE: Final = "last-result.json"
|
||||
TERMINAL_FAILURE_CODES: Final = frozenset(
|
||||
{
|
||||
"RECEIPT_REPLAY",
|
||||
"RECEIPT_MISMATCH",
|
||||
"INVALID_LEASE_TRANSITION",
|
||||
"PROMOTION_TOKEN_INVALID",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
class PendingChallenge(NamedTuple):
|
||||
value: str
|
||||
device: int
|
||||
inode: int
|
||||
|
||||
|
||||
def reject_duplicate_json_keys(pairs: list[tuple[str, object]]) -> dict[str, object]:
|
||||
value: dict[str, object] = {}
|
||||
for key, item in pairs:
|
||||
if key in value:
|
||||
raise ValueError("duplicate promoter JSON key")
|
||||
value[key] = item
|
||||
return value
|
||||
|
||||
|
||||
def session_pending_name(environ: Mapping[str, str]) -> tuple[Path, str]:
|
||||
runtime_dir = Path(environ["XDG_RUNTIME_DIR"])
|
||||
session_id = environ["MOSAIC_LEASE_SESSION_ID"]
|
||||
if not runtime_dir.is_absolute():
|
||||
raise ValueError("XDG_RUNTIME_DIR must be absolute")
|
||||
if len(session_id) != 64 or any(character not in "0123456789abcdef" for character in session_id):
|
||||
raise ValueError("invalid lease session id")
|
||||
return runtime_dir, f"pending-{session_id}"
|
||||
|
||||
|
||||
def open_pending_directory(runtime_dir: Path) -> int | None:
|
||||
directory_flags = (
|
||||
os.O_RDONLY
|
||||
| getattr(os, "O_CLOEXEC", 0)
|
||||
| getattr(os, "O_DIRECTORY", 0)
|
||||
| getattr(os, "O_NOFOLLOW", 0)
|
||||
)
|
||||
try:
|
||||
runtime_descriptor = os.open(runtime_dir, directory_flags)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
try:
|
||||
runtime_metadata = os.fstat(runtime_descriptor)
|
||||
if (
|
||||
not stat.S_ISDIR(runtime_metadata.st_mode)
|
||||
or runtime_metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(runtime_metadata.st_mode) != 0o700
|
||||
):
|
||||
raise ValueError("unsafe XDG runtime directory")
|
||||
try:
|
||||
descriptor = os.open(PENDING_DIRECTORY, directory_flags, dir_fd=runtime_descriptor)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
finally:
|
||||
os.close(runtime_descriptor)
|
||||
|
||||
metadata = os.fstat(descriptor)
|
||||
if (
|
||||
not stat.S_ISDIR(metadata.st_mode)
|
||||
or metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(metadata.st_mode) != 0o700
|
||||
):
|
||||
os.close(descriptor)
|
||||
raise ValueError("unsafe promotion pending directory")
|
||||
return descriptor
|
||||
|
||||
|
||||
def acquire_lock(directory_descriptor: int) -> int:
|
||||
flags = (
|
||||
os.O_RDWR
|
||||
| os.O_CREAT
|
||||
| getattr(os, "O_CLOEXEC", 0)
|
||||
| getattr(os, "O_NOFOLLOW", 0)
|
||||
)
|
||||
descriptor = os.open(LOCK_FILE, flags, 0o600, dir_fd=directory_descriptor)
|
||||
metadata = os.fstat(descriptor)
|
||||
if (
|
||||
not stat.S_ISREG(metadata.st_mode)
|
||||
or metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(metadata.st_mode) != 0o600
|
||||
):
|
||||
os.close(descriptor)
|
||||
raise ValueError("unsafe promotion lock file")
|
||||
try:
|
||||
fcntl.flock(descriptor, fcntl.LOCK_EX | fcntl.LOCK_NB)
|
||||
except BlockingIOError:
|
||||
os.close(descriptor)
|
||||
raise
|
||||
return descriptor
|
||||
|
||||
|
||||
def read_pending(directory_descriptor: int, name: str) -> PendingChallenge | None:
|
||||
flags = os.O_RDONLY | getattr(os, "O_CLOEXEC", 0) | getattr(os, "O_NOFOLLOW", 0)
|
||||
try:
|
||||
descriptor = os.open(name, flags, dir_fd=directory_descriptor)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
try:
|
||||
metadata = os.fstat(descriptor)
|
||||
if (
|
||||
not stat.S_ISREG(metadata.st_mode)
|
||||
or metadata.st_uid != os.getuid()
|
||||
or stat.S_IMODE(metadata.st_mode) != 0o600
|
||||
or metadata.st_size <= 0
|
||||
or metadata.st_size > MAX_FRAME
|
||||
):
|
||||
raise ValueError("unsafe promotion pending file")
|
||||
raw = os.read(descriptor, MAX_FRAME + 1)
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
if len(raw) > MAX_FRAME:
|
||||
raise ValueError("oversized promotion challenge")
|
||||
challenge = raw.decode("utf-8")
|
||||
if (
|
||||
len(challenge) != 64
|
||||
or any(character not in "0123456789abcdef" for character in challenge)
|
||||
):
|
||||
raise ValueError("invalid promotion challenge")
|
||||
return PendingChallenge(challenge, metadata.st_dev, metadata.st_ino)
|
||||
|
||||
|
||||
def write_result(
|
||||
directory_descriptor: int,
|
||||
attempt_id: str,
|
||||
verified: bool,
|
||||
reason: str | None,
|
||||
session_id: str,
|
||||
wall_clock: float,
|
||||
) -> None:
|
||||
result = {
|
||||
"attempt_id": attempt_id,
|
||||
"expires_at_wallclock": wall_clock + LEASE_TTL_SECONDS if verified else None,
|
||||
"reason": reason,
|
||||
"session_id": session_id,
|
||||
"ts": wall_clock,
|
||||
"verified": verified,
|
||||
}
|
||||
temporary = f".{RESULT_FILE}.tmp-{secrets.token_hex(8)}"
|
||||
flags = (
|
||||
os.O_WRONLY
|
||||
| os.O_CREAT
|
||||
| os.O_EXCL
|
||||
| getattr(os, "O_CLOEXEC", 0)
|
||||
| getattr(os, "O_NOFOLLOW", 0)
|
||||
)
|
||||
descriptor = os.open(temporary, flags, 0o600, dir_fd=directory_descriptor)
|
||||
try:
|
||||
os.fchmod(descriptor, 0o600)
|
||||
with os.fdopen(descriptor, "w", encoding="utf-8", closefd=False) as stream:
|
||||
json.dump(result, stream, separators=(",", ":"), sort_keys=True)
|
||||
stream.flush()
|
||||
os.fsync(stream.fileno())
|
||||
os.replace(
|
||||
temporary,
|
||||
RESULT_FILE,
|
||||
src_dir_fd=directory_descriptor,
|
||||
dst_dir_fd=directory_descriptor,
|
||||
)
|
||||
os.fsync(directory_descriptor)
|
||||
except Exception:
|
||||
try:
|
||||
os.unlink(temporary, dir_fd=directory_descriptor)
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
raise
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
|
||||
|
||||
def delete_pending_if_unchanged(
|
||||
directory_descriptor: int,
|
||||
name: str,
|
||||
pending: PendingChallenge,
|
||||
error_stream: TextIO,
|
||||
) -> None:
|
||||
quarantine = f".{name}.delete-{secrets.token_hex(8)}"
|
||||
try:
|
||||
os.rename(
|
||||
name,
|
||||
quarantine,
|
||||
src_dir_fd=directory_descriptor,
|
||||
dst_dir_fd=directory_descriptor,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return
|
||||
except OSError as error:
|
||||
print(f"Mosaic promotion could not quarantine pending file: {error}", file=error_stream)
|
||||
return
|
||||
|
||||
try:
|
||||
moved = os.stat(
|
||||
quarantine,
|
||||
dir_fd=directory_descriptor,
|
||||
follow_symlinks=False,
|
||||
)
|
||||
if (moved.st_dev, moved.st_ino) == (pending.device, pending.inode):
|
||||
os.unlink(quarantine, dir_fd=directory_descriptor)
|
||||
os.fsync(directory_descriptor)
|
||||
return
|
||||
|
||||
print("Mosaic promotion pending file changed; preserving replacement.", file=error_stream)
|
||||
try:
|
||||
os.link(
|
||||
quarantine,
|
||||
name,
|
||||
src_dir_fd=directory_descriptor,
|
||||
dst_dir_fd=directory_descriptor,
|
||||
follow_symlinks=False,
|
||||
)
|
||||
except FileExistsError:
|
||||
print(
|
||||
f"Mosaic promotion preserved replacement as {quarantine}.",
|
||||
file=error_stream,
|
||||
)
|
||||
else:
|
||||
os.unlink(quarantine, dir_fd=directory_descriptor)
|
||||
os.fsync(directory_descriptor)
|
||||
except OSError as error:
|
||||
print(f"Mosaic promotion could not resolve pending file: {error}", file=error_stream)
|
||||
|
||||
|
||||
def parse_reply(completed: subprocess.CompletedProcess[str]) -> dict[str, object] | None:
|
||||
if completed.returncode != 0:
|
||||
return None
|
||||
try:
|
||||
value = json.loads(
|
||||
completed.stdout,
|
||||
object_pairs_hook=reject_duplicate_json_keys,
|
||||
)
|
||||
except (json.JSONDecodeError, RecursionError, TypeError, ValueError):
|
||||
return None
|
||||
if not isinstance(value, dict):
|
||||
return None
|
||||
if set(value) == {"stage", "ok", "state"}:
|
||||
if (
|
||||
value.get("stage") == "promote_lease"
|
||||
and value.get("ok") is True
|
||||
and value.get("state") == "VERIFIED"
|
||||
):
|
||||
return value
|
||||
return None
|
||||
if set(value) == {"stage", "ok", "code"}:
|
||||
if (
|
||||
value.get("stage") in {"observe_receipt", "promote_lease"}
|
||||
and value.get("ok") is False
|
||||
and isinstance(value.get("code"), str)
|
||||
and value.get("code")
|
||||
):
|
||||
return value
|
||||
return None
|
||||
|
||||
|
||||
def main(
|
||||
*,
|
||||
environ: Mapping[str, str] | None = None,
|
||||
stderr: TextIO | None = None,
|
||||
run: Callable[..., subprocess.CompletedProcess[str]] = subprocess.run,
|
||||
now: Callable[[], float] = time.time,
|
||||
) -> int:
|
||||
source_environment = os.environ if environ is None else environ
|
||||
error_stream = sys.stderr if stderr is None else stderr
|
||||
directory_descriptor: int | None = None
|
||||
lock_descriptor: int | None = None
|
||||
|
||||
try:
|
||||
runtime_dir, pending_name = session_pending_name(source_environment)
|
||||
session_id = source_environment["MOSAIC_LEASE_SESSION_ID"]
|
||||
directory_descriptor = open_pending_directory(runtime_dir)
|
||||
if directory_descriptor is None:
|
||||
return 0
|
||||
try:
|
||||
lock_descriptor = acquire_lock(directory_descriptor)
|
||||
except (BlockingIOError, FileNotFoundError):
|
||||
print("Mosaic promotion completion deferred: promotion is in progress.", file=error_stream)
|
||||
return 0
|
||||
pending = read_pending(directory_descriptor, pending_name)
|
||||
if pending is None:
|
||||
return 0
|
||||
completed = run(
|
||||
[
|
||||
sys.executable,
|
||||
"-I",
|
||||
"-S",
|
||||
"-B",
|
||||
str(PROMOTER),
|
||||
"--complete",
|
||||
pending.value,
|
||||
],
|
||||
check=False,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
env=dict(source_environment),
|
||||
timeout=PROMOTER_TIMEOUT_SECONDS,
|
||||
)
|
||||
reply = parse_reply(completed)
|
||||
if reply is not None and reply.get("ok") is True:
|
||||
write_result(directory_descriptor, pending.value, True, None, session_id, now())
|
||||
delete_pending_if_unchanged(
|
||||
directory_descriptor,
|
||||
pending_name,
|
||||
pending,
|
||||
error_stream,
|
||||
)
|
||||
print("Mosaic lease promotion completed.", file=error_stream)
|
||||
return 0
|
||||
|
||||
if reply is not None:
|
||||
code = str(reply["code"])
|
||||
print(f"Mosaic promotion incomplete: {code}.", file=error_stream)
|
||||
if code in TERMINAL_FAILURE_CODES:
|
||||
write_result(directory_descriptor, pending.value, False, code, session_id, now())
|
||||
delete_pending_if_unchanged(
|
||||
directory_descriptor,
|
||||
pending_name,
|
||||
pending,
|
||||
error_stream,
|
||||
)
|
||||
else:
|
||||
diagnostic = completed.stderr.strip() or f"promoter exit {completed.returncode}"
|
||||
print(f"Mosaic promotion retryable failure: {diagnostic}.", file=error_stream)
|
||||
except (KeyError, OSError, RecursionError, UnicodeError, ValueError, subprocess.SubprocessError) as error:
|
||||
print(f"Mosaic promotion completion deferred: {type(error).__name__}: {error}", file=error_stream)
|
||||
finally:
|
||||
if lock_descriptor is not None:
|
||||
os.close(lock_descriptor)
|
||||
if directory_descriptor is not None:
|
||||
os.close(directory_descriptor)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -22,13 +22,23 @@ from typing import Final
|
||||
MAX_FRAME: Final = 64 * 1024
|
||||
BROKER_TIMEOUT_SECONDS: Final = 1.5
|
||||
MAX_TRANSCRIPT_BYTES: Final = 4 * 1024 * 1024
|
||||
BENIGN_OBSERVATION_UNAVAILABLE_CODE: Final = "OBSERVATION_UNAVAILABLE"
|
||||
|
||||
|
||||
def reject_duplicate_json_keys(pairs: list[tuple[str, object]]) -> dict[str, object]:
|
||||
value: dict[str, object] = {}
|
||||
for key, item in pairs:
|
||||
if key in value:
|
||||
raise ValueError("duplicate observer JSON key")
|
||||
value[key] = item
|
||||
return value
|
||||
|
||||
|
||||
def read_json(stream: object) -> dict[str, object]:
|
||||
raw = getattr(stream, "buffer", stream).read(MAX_FRAME + 1)
|
||||
if not isinstance(raw, bytes) or len(raw) > MAX_FRAME:
|
||||
raise ValueError("invalid observer input")
|
||||
value = json.loads(raw)
|
||||
value = json.loads(raw, object_pairs_hook=reject_duplicate_json_keys)
|
||||
if not isinstance(value, dict):
|
||||
raise ValueError("invalid observer input")
|
||||
return value
|
||||
@@ -100,9 +110,9 @@ def observer_request(socket_path: Path, request: dict[str, object]) -> dict[str,
|
||||
if not chunk:
|
||||
break
|
||||
response.extend(chunk)
|
||||
if len(response) > MAX_FRAME or not response.endswith(b"\n"):
|
||||
if len(response) > MAX_FRAME or response.count(b"\n") != 1 or not response.endswith(b"\n"):
|
||||
raise ValueError("invalid observer reply")
|
||||
value = json.loads(response)
|
||||
value = json.loads(response[:-1], object_pairs_hook=reject_duplicate_json_keys)
|
||||
if not isinstance(value, dict):
|
||||
raise ValueError("invalid observer reply")
|
||||
return value
|
||||
@@ -119,7 +129,12 @@ def main(argv: Sequence[str] | None = None, *, environ: Mapping[str, str] | None
|
||||
if arguments.runtime == "claude":
|
||||
if not arguments.latest_entry:
|
||||
raise ValueError("Claude observer requires --latest-entry")
|
||||
message = claude_latest_entry(source)
|
||||
if "last_assistant_message" in source:
|
||||
message = source["last_assistant_message"]
|
||||
if not isinstance(message, str):
|
||||
raise ValueError("invalid Claude observer input")
|
||||
else:
|
||||
message = claude_latest_entry(source)
|
||||
else:
|
||||
if arguments.latest_entry:
|
||||
raise ValueError("Pi observer is message_end only")
|
||||
@@ -133,10 +148,18 @@ def main(argv: Sequence[str] | None = None, *, environ: Mapping[str, str] | None
|
||||
"runtime": arguments.runtime,
|
||||
"latest_assistant_message": message,
|
||||
})
|
||||
except (KeyError, OSError, ValueError, json.JSONDecodeError) as error:
|
||||
except (KeyError, OSError, RecursionError, ValueError, json.JSONDecodeError) as error:
|
||||
print(f"Mosaic receipt observer refused: {error}", file=sys.stderr)
|
||||
return 2
|
||||
return 0 if reply == {"ok": True} else 2
|
||||
if set(reply) == {"ok"} and reply.get("ok") is True:
|
||||
return 0
|
||||
if (
|
||||
set(reply) == {"ok", "code"}
|
||||
and reply.get("ok") is False
|
||||
and reply.get("code") == BENIGN_OBSERVATION_UNAVAILABLE_CODE
|
||||
):
|
||||
return 0
|
||||
return 2
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -33,7 +33,7 @@ def is_verbatim_receipt(message: str, challenge: str, binding: dict[str, object]
|
||||
"""Require the exact one current-cycle receipt, not a transcript substring."""
|
||||
|
||||
expected = receipt_for(challenge, binding)
|
||||
return hmac.compare_digest(message, expected)
|
||||
return hmac.compare_digest(message.encode("utf-8"), expected.encode("utf-8"))
|
||||
|
||||
|
||||
def latest_assistant_digest(message: str) -> str:
|
||||
|
||||
@@ -91,12 +91,10 @@ fi
|
||||
|
||||
if [[ -n "$dirty_files" ]]; then
|
||||
echo " Modified files:"
|
||||
mapfile -t dirty_lines <<<"$dirty_files"
|
||||
file_count="${#dirty_lines[@]}"
|
||||
display_count=$((file_count < 20 ? file_count : 20))
|
||||
for ((i = 0; i < display_count; i++)); do
|
||||
echo " ${dirty_lines[$i]}"
|
||||
echo "$dirty_files" | head -20 | while IFS= read -r line; do
|
||||
echo " $line"
|
||||
done
|
||||
file_count="$(echo "$dirty_files" | wc -l)"
|
||||
if (( file_count > 20 )); then
|
||||
echo " ... and $(( file_count - 20 )) more"
|
||||
fi
|
||||
|
||||
@@ -64,12 +64,12 @@ if jq -e '.next_task == "T-001"' "$capsule_file" >/dev/null 2>&1; then pass_case
|
||||
if grep -Fq 'Target runtime:** codex' <<< "$codex_continue_output"; then pass_case "continue prompt contains target runtime codex"; else fail_case "continue prompt contains target runtime codex"; fi
|
||||
|
||||
codex_run_prompt="$(MOSAIC_COORD_RUNTIME=codex bash "$SCRIPT_DIR/session-run.sh" --project "$tmp_project" --print)"
|
||||
if [[ "${codex_run_prompt%%$'\n'*}" == "Now initiating Orchestrator mode..." ]]; then pass_case "codex run prompt first line is mode declaration"; else fail_case "codex run prompt first line is mode declaration"; fi
|
||||
if [[ "$(printf '%s\n' "$codex_run_prompt" | head -n1)" == "Now initiating Orchestrator mode..." ]]; then pass_case "codex run prompt first line is mode declaration"; else fail_case "codex run prompt first line is mode declaration"; fi
|
||||
if grep -Fq 'Do NOT ask clarifying questions before your first tool actions' <<< "$codex_run_prompt"; then pass_case "codex run prompt includes no-questions hard gate"; else fail_case "codex run prompt includes no-questions hard gate"; fi
|
||||
if grep -Fq '"next_task": "T-001"' <<< "$codex_run_prompt"; then pass_case "codex run prompt embeds capsule json"; else fail_case "codex run prompt embeds capsule json"; fi
|
||||
|
||||
claude_run_prompt="$(MOSAIC_COORD_RUNTIME=claude bash "$SCRIPT_DIR/session-run.sh" --project "$tmp_project" --print)"
|
||||
if [[ "${claude_run_prompt%%$'\n'*}" == "## Continuation Mission" ]]; then pass_case "claude run prompt remains continuation prompt format"; else fail_case "claude run prompt remains continuation prompt format"; fi
|
||||
if [[ "$(printf '%s\n' "$claude_run_prompt" | head -n1)" == "## Continuation Mission" ]]; then pass_case "claude run prompt remains continuation prompt format"; else fail_case "claude run prompt remains continuation prompt format"; fi
|
||||
|
||||
echo ""
|
||||
echo "Smoke test summary: pass=$PASS fail=$FAIL"
|
||||
|
||||
@@ -96,8 +96,8 @@ L="$WORK/live5.md"; G="$WORK/ledger5.md"; echo "# LEDGER" > "$G"
|
||||
make_board "$L" 6 1 400
|
||||
before_l=$(cat "$L"); before_g=$(cat "$G")
|
||||
out=$(bash "$SUT" --live "$L" --ledger "$G" --cap 2000 --dry-run 2>&1) || note "dry-run exited nonzero: $out"
|
||||
grep -qi "dry run" <<<"$out" || note "dry-run did not announce itself"
|
||||
grep -q "would roll" <<<"$out" || note "dry-run did not report a plan"
|
||||
echo "$out" | grep -qi "dry run" || note "dry-run did not announce itself"
|
||||
echo "$out" | grep -q "would roll" || note "dry-run did not report a plan"
|
||||
[[ "$(cat "$L")" == "$before_l" ]] || note "dry-run modified LIVE"
|
||||
[[ "$(cat "$G")" == "$before_g" ]] || note "dry-run modified LEDGER"
|
||||
|
||||
|
||||
@@ -66,7 +66,7 @@ present=0
|
||||
|
||||
for entry in "${PRDY_REQUIRED_SECTIONS[@]}"; do
|
||||
pattern="${entry#*|}"
|
||||
if grep -qiE "$pattern" <<<"$PRD_CONTENT"; then
|
||||
if echo "$PRD_CONTENT" | grep -qiE "$pattern"; then
|
||||
present=$((present + 1))
|
||||
fi
|
||||
done
|
||||
|
||||
@@ -169,13 +169,13 @@ main() {
|
||||
# classify_surface PATH → surface name (highest-risk match wins, mirrors TS)
|
||||
classify_surface() {
|
||||
local p="$1"
|
||||
if grep -qiE 'auth|login|session|token|permission|rbac|credential|secret' <<<"$p"; then echo auth; return; fi
|
||||
if grep -qiE 'migration|prisma|schema|\.sql|entity|repository|seed' <<<"$p"; then echo data; return; fi
|
||||
if grep -qiE 'docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform' <<<"$p"; then echo infra; return; fi
|
||||
if grep -qiE 'package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite' <<<"$p"; then echo build; return; fi
|
||||
if grep -qE '\.tsx|\.css|components/|apps/web/' <<<"$p"; then echo ui; return; fi
|
||||
if grep -qE '\.spec\.|\.test\.|__tests__/' <<<"$p"; then echo test; return; fi
|
||||
if grep -qE '\.md$|docs/' <<<"$p"; then echo docs; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'auth|login|session|token|permission|rbac|credential|secret'; then echo auth; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'migration|prisma|schema|\.sql|entity|repository|seed'; then echo data; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform'; then echo infra; return; fi
|
||||
if printf '%s' "$p" | grep -qiE 'package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite'; then echo build; return; fi
|
||||
if printf '%s' "$p" | grep -qE '\.tsx|\.css|components/|apps/web/'; then echo ui; return; fi
|
||||
if printf '%s' "$p" | grep -qE '\.spec\.|\.test\.|__tests__/'; then echo test; return; fi
|
||||
if printf '%s' "$p" | grep -qE '\.md$|docs/'; then echo docs; return; fi
|
||||
echo none
|
||||
}
|
||||
|
||||
|
||||
@@ -13,12 +13,7 @@ JSON_INPUT=$(cat)
|
||||
if command -v jq &>/dev/null; then
|
||||
FILE_PATH=$(echo "$JSON_INPUT" | jq -r '.tool_input.file_path // .tool_response.filePath // .file_path // empty' 2>/dev/null || echo "")
|
||||
else
|
||||
file_path_pattern='"file_path"[[:space:]]*:[[:space:]]*"([^"]*)"'
|
||||
if [[ "$JSON_INPUT" =~ $file_path_pattern ]]; then
|
||||
FILE_PATH="${BASH_REMATCH[1]}"
|
||||
else
|
||||
FILE_PATH=""
|
||||
fi
|
||||
FILE_PATH=$(echo "$JSON_INPUT" | grep -o '"file_path"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"\([^"]*\)"$/\1/' | head -1)
|
||||
fi
|
||||
|
||||
# Only check TypeScript files
|
||||
@@ -58,7 +53,7 @@ OUTPUT=$(npx tsc --noEmit --pretty --maxNodeModuleJsDepth 0 2>&1) || STATUS=$?
|
||||
if [ "${STATUS:-0}" -ne 0 ]; then
|
||||
# Filter output to only show errors related to the edited file (if possible)
|
||||
BASENAME=$(basename "$FILE_PATH")
|
||||
RELEVANT=$(grep -A2 "$BASENAME" <<<"$OUTPUT" 2>/dev/null || sed -n '1,20p' <<<"$OUTPUT")
|
||||
RELEVANT=$(echo "$OUTPUT" | grep -A2 "$BASENAME" 2>/dev/null || echo "$OUTPUT" | head -20)
|
||||
|
||||
echo "TypeScript type errors detected after editing $FILE_PATH:"
|
||||
echo "$RELEVANT"
|
||||
|
||||
@@ -26,9 +26,6 @@ chk "F1 fresh: CONSTITUTION/AGENTS/STANDARDS/TOOLS seeded" \
|
||||
"[ -f '$T1/CONSTITUTION.md' ] && [ -f '$T1/AGENTS.md' ] && [ -f '$T1/STANDARDS.md' ] && [ -f '$T1/TOOLS.md' ]"
|
||||
chk "F1 fresh: AGENTS == shipped default" "cmp -s '$T1/AGENTS.md' '$DEFA/AGENTS.md'"
|
||||
chk "F1 fresh: framework-version stamped 3" "[ \"\$(cat '$T1/.framework-version' 2>/dev/null)\" = 3 ]"
|
||||
chk "F1 fresh: Pi goal extension deploys under Mosaic runtime" \
|
||||
"cmp -s '$T1/runtime/pi/goal-extension.ts' '$FW/runtime/pi/goal-extension.ts'"
|
||||
chk "F1 fresh: installer creates no nested main Pi config" "[ ! -e '$T1/.pi' ]"
|
||||
|
||||
# F2 — legacy install with a user-edited AGENTS.md (the sanctioned pre-constitution customization)
|
||||
T2=$(mktemp -d); mkdir -p "$T2/credentials"
|
||||
@@ -92,8 +89,6 @@ chk "F6 reseed: per-agent env bytes survive" "cmp -s '$T6/fleet/agents/coder0.en
|
||||
chk "F6 reseed: heartbeat bytes survive" "cmp -s '$T6/fleet/run/coder0.hb' '$E6/run.expected'"
|
||||
chk "F6 reseed: framework examples are refreshed" "grep -q orchestrator '$T6/fleet/examples/general.yaml'"
|
||||
chk "F6 reseed: framework roster schema is refreshed" "cmp -s '$T6/fleet/roster.schema.json' '$FW/fleet/roster.schema.json'"
|
||||
chk "F6 reseed: Pi goal extension is refreshed from framework source" \
|
||||
"cmp -s '$T6/runtime/pi/goal-extension.ts' '$FW/runtime/pi/goal-extension.ts'"
|
||||
|
||||
rm -rf "$T1" "$T2" "$T3" "$T4" "$T5" "$T6" "$E6"
|
||||
echo
|
||||
|
||||
@@ -176,12 +176,8 @@ run_snap() {
|
||||
|
||||
# Resolve the single pre-update-* snapshot dir under a state dir (newest if many).
|
||||
snap_dir() {
|
||||
local -a snapshots=()
|
||||
mapfile -t snapshots < <(
|
||||
find "$1/mosaic/backups" -maxdepth 1 -type d -name 'pre-update-*' 2>/dev/null \
|
||||
| LC_ALL=C sort -r
|
||||
)
|
||||
printf '%s\n' "${snapshots[0]:-}"
|
||||
find "$1/mosaic/backups" -maxdepth 1 -type d -name 'pre-update-*' 2>/dev/null \
|
||||
| LC_ALL=C sort -r | head -1
|
||||
}
|
||||
|
||||
echo "── Part 1/2/3: durable snapshot scope, perms, no-leak ──────────────────"
|
||||
|
||||
@@ -336,7 +336,7 @@ chk "[reset-fail] the manual-recovery pointer is emitted (not a silent set -e ex
|
||||
"grep -q 'Snapshot restore could not reset' '$OUTG'"
|
||||
chk "[reset-fail] the recovery message points at a preserved snapshot dir" \
|
||||
"grep -q 'preserved at: .*mosaic-snapshot' '$OUTG'"
|
||||
SNAP_E="$(grep -m1 -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTG")"
|
||||
SNAP_E="$(grep -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTG" | head -1)"
|
||||
chk "[reset-fail] the named snapshot directory actually survives for recovery" \
|
||||
"[ -n '$SNAP_E' ] && [ -d '$SNAP_E' ]"
|
||||
chk "[reset-fail] operator secret value never appears in installer output" \
|
||||
@@ -353,8 +353,7 @@ chk "[control] without the D2 recovery line the operator gets no snapshot pointe
|
||||
"! grep -q 'Snapshot restore could not reset' '$OUTH'"
|
||||
[ -n "${SNAP_E:-}" ] && rm -rf "$SNAP_E"
|
||||
# Reap any snapshot the reset-fail runs left in /tmp (reset failed → never cleaned).
|
||||
orphan_snapshot="$(grep -m1 -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTH" 2>/dev/null || true)"
|
||||
[ -n "$orphan_snapshot" ] && rm -rf "$orphan_snapshot"
|
||||
grep -o '/[^ ]*mosaic-snapshot[^ ]*' "$OUTH" 2>/dev/null | head -1 | while read -r s; do rm -rf "$s"; done
|
||||
|
||||
# Cleanup (generated installer controls are also removed by the EXIT trap).
|
||||
for d in "$HA" "$REFA" "$HB" "$REFB" "$HC" "$HD" "$HE" "$REFE" "$HF" "$REFF" "$HG" "$HH"; do rm -rf "$d"; done
|
||||
|
||||
@@ -32,6 +32,7 @@ packages/mosaic/framework/tools/tmux/test-send-message-socket.sh | requires a re
|
||||
packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh | requires real tmux-pane fixtures on a throwaway socket; CI image ships no tmux; #1017 burndown (same condition as its sibling)
|
||||
|
||||
# --- single-suite directories: unmeasured in CI ---
|
||||
packages/mosaic/framework/tools/fleet/test-start-agent-session.sh | unmeasured in CI image; stubs tmux via a fake bin dir, likely CI-fit; #1017 burndown
|
||||
packages/mosaic/framework/tools/glpi/test-list-http-status.sh | unmeasured in CI image; stub-based (#807 regression harness), likely CI-fit; #1017 burndown
|
||||
packages/mosaic/framework/tools/orchestrator/test-board-roll.sh | unmeasured in CI image; file-fixture based, likely CI-fit; #1017 burndown
|
||||
packages/mosaic/framework/tools/woodpecker/test-ci-wait-exit-matrix.sh | unmeasured in CI image; drives ci-wait.sh against a stub pipeline-status.sh, likely CI-fit; #1017 burndown
|
||||
|
||||
@@ -110,7 +110,7 @@ for attempt in $(seq 1 $((RETRIES + 1))); do
|
||||
sleep 1.2
|
||||
pane=$("${tmux_cmd[@]}" capture-pane -t "$EFFECTIVE_TARGET" -p 2>/dev/null)
|
||||
|
||||
if grep -qF "$QUEUED_RE" <<<"$pane"; then
|
||||
if printf '%s' "$pane" | grep -qF "$QUEUED_RE"; then
|
||||
status="queued"; break
|
||||
fi
|
||||
# Locate the REPL input box (prompt glyph). If we cannot see it, we have NO
|
||||
@@ -121,7 +121,7 @@ for attempt in $(seq 1 $((RETRIES + 1))); do
|
||||
fi
|
||||
# Input box located AND still carrying our tail => unsubmitted draft. Flush + retry.
|
||||
# (Submitted messages scroll up into history; a draft stays on the ❯ line.)
|
||||
if [ -n "$snippet" ] && grep -qF "$snippet" <<<"$promptline"; then
|
||||
if [ -n "$snippet" ] && printf '%s' "$promptline" | grep -qF "$snippet"; then
|
||||
status="draft"; continue
|
||||
fi
|
||||
# Input box located AND clear of our tail => positively submitted. This is the
|
||||
|
||||
@@ -34,20 +34,16 @@ tmux new-session -d -s "$DEFAULT_TARGET" -c "$TMPDIR" 'PS1="❯ " exec bash --no
|
||||
|
||||
"$SEND_MESSAGE" -L "$SOCKET" -t "=$TARGET" -m "named socket hello" >/tmp/send-message-named.out
|
||||
sleep 0.2
|
||||
named_pane="$(capture_named)" || fail "could not capture named socket pane"
|
||||
grep -qF "named socket hello" <<<"$named_pane" || fail "send-message.sh did not deliver to named socket"
|
||||
default_pane="$(capture_default)" || fail "could not capture default socket pane"
|
||||
if grep -qF "named socket hello" <<<"$default_pane"; then
|
||||
capture_named | grep -qF "named socket hello" || fail "send-message.sh did not deliver to named socket"
|
||||
if capture_default | grep -qF "named socket hello"; then
|
||||
fail "send-message.sh leaked named-socket message to default tmux server"
|
||||
fi
|
||||
|
||||
"$AGENT_SEND" -L "$SOCKET" -S "tester:source" -s "=$TARGET" -m "agent socket hello" >/tmp/agent-send-named.out
|
||||
sleep 0.2
|
||||
named_pane="$(capture_named)" || fail "could not capture named socket pane"
|
||||
grep -qF "[tester:source ->" <<<"$named_pane" || fail "agent-send.sh did not include preamble"
|
||||
grep -qF "agent socket hello" <<<"$named_pane" || fail "agent-send.sh did not deliver to named socket"
|
||||
default_pane="$(capture_default)" || fail "could not capture default socket pane"
|
||||
if grep -qF "agent socket hello" <<<"$default_pane"; then
|
||||
capture_named | grep -qF "[tester:source ->" || fail "agent-send.sh did not include preamble"
|
||||
capture_named | grep -qF "agent socket hello" || fail "agent-send.sh did not deliver to named socket"
|
||||
if capture_default | grep -qF "agent socket hello"; then
|
||||
fail "agent-send.sh leaked named-socket message to default tmux server"
|
||||
fi
|
||||
|
||||
@@ -69,11 +65,11 @@ done
|
||||
sleep 0.2
|
||||
for i in $(seq 1 "$CONC_N"); do
|
||||
pane=$(tmux -L "$SOCKET" capture-pane -t "=conc-$i:0.0" -p)
|
||||
grep -qF "CONCPAYLOAD-${i}-END" <<<"$pane" \
|
||||
printf '%s' "$pane" | grep -qF "CONCPAYLOAD-${i}-END" \
|
||||
|| fail "concurrent send dropped payload for pane conc-$i"
|
||||
for j in $(seq 1 "$CONC_N"); do
|
||||
[ "$j" = "$i" ] && continue
|
||||
if grep -qF "CONCPAYLOAD-${j}-END" <<<"$pane"; then
|
||||
if printf '%s' "$pane" | grep -qF "CONCPAYLOAD-${j}-END"; then
|
||||
fail "concurrent send cross-delivered payload $j to pane conc-$i"
|
||||
fi
|
||||
done
|
||||
|
||||
@@ -31,7 +31,7 @@ tmux -L "$SOCKET" new-session -d -s repl -c "$TMP" \
|
||||
'PS1="❯ " exec bash --noprofile --norc -i'
|
||||
sleep 0.3
|
||||
out=$("$SEND" -L "$SOCKET" -t "=repl" -m "verdict fixture one delivered ok" 2>"$TMP/e1"); rc=$?
|
||||
if [ "$rc" -eq 0 ] && grep -qF "✓ delivered" <<<"$out"; then
|
||||
if [ "$rc" -eq 0 ] && printf '%s' "$out" | grep -qF "✓ delivered"; then
|
||||
ok "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered"
|
||||
else
|
||||
no "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered" "rc=$rc out=[$out] err=[$(cat "$TMP/e1")]"
|
||||
|
||||
@@ -123,7 +123,7 @@ _manifest_val() {
|
||||
# _manifest_val KEY — echo VALUE for KEY=VALUE in the manifest (blank if none).
|
||||
local key="$1"
|
||||
[ -f "$MANIFEST" ] || return 0
|
||||
awk -v key="$key" 'index($0, key "=") == 1 { sub(/^[^=]*=/, ""); gsub(/[[:space:]]/, ""); print; exit }' "$MANIFEST"
|
||||
sed -n "s/^${key}=//p" "$MANIFEST" | head -n1 | tr -d '[:space:]'
|
||||
}
|
||||
|
||||
# _load_watchlist — validate the watch-list path + JSON + schema_version range.
|
||||
@@ -267,7 +267,7 @@ _poll_source() {
|
||||
if snap_json="$(jq -ce '.' <<<"$rawmeta" 2>/dev/null)"; then
|
||||
snap_sha="$(jq -r 'if (.snapshot_sha|type) == "string" then .snapshot_sha else "" end' <<<"$snap_json")"
|
||||
snap_ts="$(jq -r 'if (.snapshot_ts|type) == "number" then (.snapshot_ts|floor|tostring) else "" end' <<<"$snap_json")"
|
||||
if [ -n "$snap_sha" ] && ! grep -Eq '^[0-9a-f]{7,64}$' <<<"$snap_sha"; then
|
||||
if [ -n "$snap_sha" ] && ! printf '%s' "$snap_sha" | grep -Eq '^[0-9a-f]{7,64}$'; then
|
||||
echo "detector.sh: source '$kind/$id' snapshot_sha rejected (not a 7-64 char lowercase-hex git sha) — snapshot metadata DROPPED, poll continues (#940)." >&2
|
||||
snap_sha=""
|
||||
snap_ts=""
|
||||
@@ -275,7 +275,7 @@ _poll_source() {
|
||||
# A ts must be a sane positive epoch BEFORE any arithmetic touches it: a
|
||||
# negative or absurdly large value would make the shell integer comparison
|
||||
# below error out and silently KEEP the bad ts — validate first, compare after.
|
||||
if [ -n "$snap_ts" ] && ! grep -Eq '^[0-9]{1,12}$' <<<"$snap_ts"; then
|
||||
if [ -n "$snap_ts" ] && ! printf '%s' "$snap_ts" | grep -Eq '^[0-9]{1,12}$'; then
|
||||
echo "detector.sh: source '$kind/$id' snapshot_ts rejected (not a sane positive epoch) — snapshot_ts DROPPED, poll continues (#940)." >&2
|
||||
snap_ts=""
|
||||
fi
|
||||
|
||||
@@ -644,8 +644,7 @@ cmd_render() {
|
||||
oseq="$(jq -r '.observed_seq // "?"' <<<"$line")"
|
||||
oclass="$(jq -r '.class // "actionable"' <<<"$line")"
|
||||
oloc="$(jq -c '.locators // {}' <<<"$line")"
|
||||
olabel="$(_locator_line "$oloc")"
|
||||
olabel="${olabel%%$'\n'*}"
|
||||
olabel="$(_locator_line "$oloc" | head -n1)"
|
||||
printf ' * seq %s [%s] %s\n' "$oseq" "$(_scrub_inline "$oclass")" "$olabel"
|
||||
done <<<"$pending"
|
||||
fi
|
||||
|
||||
@@ -146,7 +146,7 @@ EOF
|
||||
_manifest_val() {
|
||||
local key="$1"
|
||||
[ -f "$MANIFEST" ] || return 0
|
||||
awk -v key="$key" 'index($0, key "=") == 1 { sub(/^[^=]*=/, ""); gsub(/[[:space:]]/, ""); print; exit }' "$MANIFEST"
|
||||
sed -n "s/^${key}=//p" "$MANIFEST" | head -n1 | tr -d '[:space:]'
|
||||
}
|
||||
|
||||
# _load_watchlist — validate path + JSON + shape + Gate B schema range (mirrors
|
||||
|
||||
@@ -25,7 +25,7 @@
|
||||
"lint": "eslint src",
|
||||
"typecheck": "tsc --noEmit",
|
||||
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
|
||||
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && bash framework/tools/fleet/test-start-agent-session.sh && bash framework/systemd/user/test-fleet-units.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/git/test-explain-diagnostic-status-neutral.sh && bash framework/tools/git/test-detect-platform-outside-repo.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh"
|
||||
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh"
|
||||
},
|
||||
"dependencies": {
|
||||
"@mosaicstack/brain": "workspace:*",
|
||||
|
||||
@@ -15,6 +15,7 @@ import { registerAgentCommand } from './commands/agent.js';
|
||||
import { registerInteractionCommand } from './commands/interaction.js';
|
||||
import { registerConfigCommand } from './commands/config.js';
|
||||
import { registerFleetCommand } from './commands/fleet.js';
|
||||
import { registerPromoteCommand } from './commands/promote.js';
|
||||
import { registerMissionCommand } from './commands/mission.js';
|
||||
import { registerUninstallCommand } from './commands/uninstall.js';
|
||||
import { registerRestoreCommand } from './commands/restore.js';
|
||||
@@ -370,6 +371,7 @@ registerInteractionCommand(program);
|
||||
// ─── fleet ─────────────────────────────────────────────────────────────
|
||||
|
||||
registerFleetCommand(program);
|
||||
registerPromoteCommand(program);
|
||||
|
||||
// ─── config ────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
@@ -131,14 +131,13 @@ async function exists(path: string): Promise<boolean> {
|
||||
}
|
||||
|
||||
describe('projectRosterV2AgentGeneratedEnv', (): void => {
|
||||
it('maps a roster-v2 agent to exactly the nine generated projection keys', (): void => {
|
||||
it('maps a roster-v2 agent to exactly the eight generated projection keys', (): void => {
|
||||
const roster = parseRosterV2(rosterYaml, 'yaml');
|
||||
const agent = roster.agents.find((candidate) => candidate.name === 'coder0');
|
||||
expect(agent).toBeDefined();
|
||||
const values = projectRosterV2AgentGeneratedEnv(roster, agent!);
|
||||
expect(values).toEqual({
|
||||
MOSAIC_AGENT_NAME: 'coder0',
|
||||
MOSAIC_GIT_IDENTITY: 'coder0',
|
||||
MOSAIC_AGENT_CLASS: 'code',
|
||||
MOSAIC_AGENT_RUNTIME: 'pi',
|
||||
MOSAIC_AGENT_MODEL: 'gpt-5.6-sol',
|
||||
|
||||
@@ -422,7 +422,6 @@ describe('fleet roster parsing', () => {
|
||||
expect(generateAgentEnv(roster, getRosterAgent(roster, 'coder0'))).toBe(
|
||||
[
|
||||
'MOSAIC_AGENT_NAME=coder0',
|
||||
'MOSAIC_GIT_IDENTITY=coder0',
|
||||
// Reflects the roster's canonicalized compatibility class (A3a).
|
||||
'MOSAIC_AGENT_CLASS=code',
|
||||
'MOSAIC_AGENT_RUNTIME=codex',
|
||||
@@ -3800,7 +3799,6 @@ describe('fleet add command', () => {
|
||||
'utf8',
|
||||
);
|
||||
expect(envContent).toContain('MOSAIC_AGENT_NAME=coder0');
|
||||
expect(envContent).toContain('MOSAIC_GIT_IDENTITY=coder0');
|
||||
expect(envContent).toContain('MOSAIC_AGENT_RUNTIME=codex');
|
||||
});
|
||||
|
||||
|
||||
@@ -484,7 +484,6 @@ function generateAgentEnvValues(
|
||||
const workingDirectory = agent.workingDirectory ?? roster.defaults.workingDirectory;
|
||||
return {
|
||||
MOSAIC_AGENT_NAME: agent.name,
|
||||
MOSAIC_GIT_IDENTITY: agent.name,
|
||||
MOSAIC_AGENT_CLASS: agent.className,
|
||||
MOSAIC_AGENT_RUNTIME: agent.runtime,
|
||||
MOSAIC_AGENT_MODEL: agent.modelHint ?? '',
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user