Compare commits

..

2 Commits

Author SHA1 Message Date
ms-lead-reviewer
23cbdaf8df chore(orchestrator): fix pre-existing #868 README prettier drift
All checks were successful
ci/woodpecker/pr/ci Pipeline was successful
packages/mosaic/framework/tools/orchestrator/README.md fails
`pnpm format:check` on origin/main as-is (confirmed against the
unmodified origin/main blob directly, unrelated to this branch's
Patch-3 change). The repo-wide mandatory pre-push hook
(`pnpm typecheck && pnpm lint && pnpm format:check`) blocks any push
based on current main until this is fixed.

Whitespace/table-alignment only via `prettier --write` -- no content
change. Kept as its own commit so blame stays clean and this no-ops
cleanly whenever #868's own fix lands on main first.
2026-07-23 11:42:23 -05:00
ms-lead-reviewer
cd67042184 fix(tools/git): ci-queue-wait.sh treats 404 branch-absent as queue-clear
gitea_get_branch_head_sha() looked up a branch's head SHA via
`curl -fsSL .../branches/<branch>`. For a branch not yet pushed to the
remote, Gitea returns 404, curl -f fails, stdin is empty, and the
downstream `json.load` raises JSONDecodeError -- crashing the guard.
Since ci-queue-wait.sh is a mandatory pre-push check, every new feature
branch's first push was blocked.

Capture the HTTP status via `curl -sS -w '\n%{http_code}'`:
- 404  -> echo __BRANCH_ABSENT__, return 0 (no in-flight pipeline on a
          branch that doesn't exist yet -- queue is clear).
- non-200 -> return 1 (still fail-closed on a genuine API error).
- 200  -> parse the JSON as before (existing-branch behavior unchanged).

The caller checks for the __BRANCH_ABSENT__ sentinel and exits 0 with a
"branch not yet on remote -- queue clear" message.

ci-queue-wait.ps1 had the same bug (Invoke-RestMethod throws on any
non-2xx, including 404, and the catch block exited 1) -- ported the
equivalent fix there via the caught exception's HTTP status code.

Adds a red-first regression harness (test-ci-queue-wait-branch-absent.sh)
covering: 404 branch-absent -> queue clear; 200 existing branch with a
terminal CI state -> unchanged behavior; 500 genuine API error -> still
fail-closed. Verified failing against the unpatched script (crashes with
JSONDecodeError) and passing after the fix. Wired into
package.json's test:framework-shell alongside the existing git-wrapper
regression tests.

Upstreams Mos host-local tooling-patch kit (2026-07-23), Patch 3.
2026-07-23 11:36:10 -05:00
8 changed files with 183 additions and 515 deletions

View File

@@ -1,22 +0,0 @@
[Unit]
Description=Mosaic lease broker daemon (framework tools/lease-broker/daemon.py)
Documentation=https://git.mosaicstack.dev/mosaicstack/stack
After=default.target
[Service]
Type=simple
# The broker socket lives under the runtime directory so it disappears with
# the user session instead of surviving as stale state across logins.
# daemon.py's secure_parent() fails closed unless this directory is exactly
# 0700, so RuntimeDirectoryMode is not cosmetic.
RuntimeDirectory=mosaic-lease
RuntimeDirectoryMode=0700
# Remove loader and noninteractive-shell controls before ExecStart loads env,
# matching the tmux fleet units in this same directory.
UnsetEnvironment=LD_PRELOAD BASH_ENV ENV
ExecStart=/usr/bin/env -i HOME=%h PATH=/usr/bin:/bin XDG_RUNTIME_DIR=%t /bin/bash --noprofile --norc %h/.config/mosaic/tools/lease-broker/start-lease-broker.sh
Restart=on-failure
RestartSec=1
[Install]
WantedBy=default.target

View File

@@ -185,6 +185,16 @@ switch ($platform) {
$headSha = ($branchPayload.commit.id | Out-String).Trim() $headSha = ($branchPayload.commit.id | Out-String).Trim()
} }
catch { catch {
# A not-yet-pushed feature branch has no in-flight pipeline, so the
# pre-push queue guard must treat 404 as "queue clear", not crash.
$statusCode = $null
if ($_.Exception.Response) {
$statusCode = [int]$_.Exception.Response.StatusCode
}
if ($statusCode -eq 404) {
Write-Host "[ci-queue-wait] branch $Branch not yet on remote — no in-flight pipeline; queue clear."
exit 0
}
Write-Error "Could not resolve $Branch head SHA from Gitea API." Write-Error "Could not resolve $Branch head SHA from Gitea API."
exit 1 exit 1
} }

View File

@@ -137,7 +137,21 @@ gitea_get_branch_head_sha() {
local branch="$3" local branch="$3"
local token="$4" local token="$4"
local url="https://${host}/api/v1/repos/${repo}/branches/${branch}" local url="https://${host}/api/v1/repos/${repo}/branches/${branch}"
curl -fsSL -H "User-Agent: curl/8" -H "Authorization: token ${token}" "$url" | python3 -c ' # Capture HTTP status so an absent branch (404) is distinguished from an API
# error. A not-yet-pushed feature branch has no in-flight pipeline, so the
# pre-push queue guard must treat 404 as "queue clear", not crash.
local resp code body
resp=$(curl -sS -H "User-Agent: curl/8" -H "Authorization: token ${token}" -w $'\n%{http_code}' "$url")
code="${resp##*$'\n'}"
body="${resp%$'\n'*}"
if [[ "$code" == "404" ]]; then
echo "__BRANCH_ABSENT__"
return 0
fi
if [[ "$code" != "200" ]]; then
return 1
fi
printf '%s' "$body" | python3 -c '
import json, sys import json, sys
data = json.load(sys.stdin) data = json.load(sys.stdin)
commit = data.get("commit") or {} commit = data.get("commit") or {}
@@ -219,6 +233,10 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
exit 1 exit 1
} }
HEAD_SHA=$(gitea_get_branch_head_sha "$HOST" "$OWNER/$REPO" "$BRANCH" "$TOKEN") HEAD_SHA=$(gitea_get_branch_head_sha "$HOST" "$OWNER/$REPO" "$BRANCH" "$TOKEN")
if [[ "$HEAD_SHA" == "__BRANCH_ABSENT__" ]]; then
echo "[ci-queue-wait] branch ${BRANCH} not yet on remote — no in-flight pipeline; queue clear."
exit 0
fi
if [[ -z "$HEAD_SHA" ]]; then if [[ -z "$HEAD_SHA" ]]; then
echo "Error: Could not resolve ${BRANCH} head SHA." >&2 echo "Error: Could not resolve ${BRANCH} head SHA." >&2
exit 1 exit 1

View File

@@ -0,0 +1,153 @@
#!/usr/bin/env bash
# Regression harness for ci-queue-wait.sh's 404-branch-absent handling.
#
# gitea_get_branch_head_sha() resolves a branch's head SHA before the
# pre-push queue guard runs. A branch that has never been pushed doesn't
# exist on the remote yet, so Gitea's branches/<branch> endpoint 404s.
# Before the fix, `curl -fsSL` failed on the 404, its empty stdout was piped
# into `python3 -c 'json.load(sys.stdin)'`, and the resulting
# JSONDecodeError crashed the guard -- blocking every new feature branch's
# first push. The fix must treat 404 as "no in-flight pipeline" (queue
# clear) while still failing closed on a genuine API error.
#
# Covers:
# (a) 404 branch-absent -> exit 0, "queue clear" message.
# (b) 200 existing branch + a terminal CI state -> unchanged behavior.
# (c) genuine API error (500) -> still fail-closed (nonzero exit).
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/ci-queue-wait-branch-absent}"
REPO_DIR="$WORK_DIR/repo"
STUB_DIR="$WORK_DIR/stubs"
rm -rf "$WORK_DIR"
mkdir -p "$REPO_DIR" "$STUB_DIR"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.example.test/acme/widgets.git
# Minimal curl stub. Selects a canned response by inspecting which Gitea
# endpoint is being hit (branches/<branch> vs commits/<sha>/status) and
# whether -w '%{http_code}' was requested. Only the patched branch-lookup
# call passes -w; the unpatched call and the (unchanged) status call both
# use plain `curl -fsSL` semantics -- exit nonzero and print nothing on a
# non-2xx response. This lets the same stub exercise both the pre-fix and
# post-fix branch-lookup code paths faithfully.
cat > "$STUB_DIR/curl" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
has_w=0
url=""
for arg in "$@"; do
case "$arg" in
-w) has_w=1 ;;
http://*|https://*) url="$arg" ;;
esac
done
case "$url" in
*/branches/*) mode="${MOSAIC_STUB_BRANCH_MODE:?MOSAIC_STUB_BRANCH_MODE not set}" ;;
*/status) mode="${MOSAIC_STUB_STATUS_MODE:-terminal-success}" ;;
*)
echo "curl stub: unrecognized URL: $url" >&2
exit 2
;;
esac
case "$mode" in
404) code=404; body="" ;;
200) code=200; body='{"commit":{"id":"deadbeefcafef00d0123456789abcdef01234567"}}' ;;
500) code=500; body='{"message":"internal server error"}' ;;
no-status) code=200; body='{}' ;;
terminal-success) code=200; body='{"state":"success"}' ;;
*)
echo "curl stub: unknown mode=$mode" >&2
exit 2
;;
esac
if [[ "$has_w" == 1 ]]; then
printf '%s\n%s' "$body" "$code"
exit 0
fi
# Unpatched branch-lookup call / status-endpoint call: real curl -fsSL
# exits nonzero and emits nothing on stdout for a non-2xx response.
if [[ "$code" != "200" ]]; then
exit 22
fi
printf '%s' "$body"
SH
chmod +x "$STUB_DIR/curl"
run_ci_queue_wait() {
local branch="$1"
(
cd "$REPO_DIR"
export PATH="$STUB_DIR:$PATH"
export MOSAIC_CREDENTIALS_FILE="$WORK_DIR/no-credentials.json"
export GITEA_TOKEN="stub-token"
export GITEA_URL="https://git.example.test"
"$SCRIPT_DIR/ci-queue-wait.sh" -B "$branch" --purpose push -t 5 -i 1
)
}
fail=0
# (a) 404 branch-absent -> queue clear, exit 0.
set +e
out_a=$(MOSAIC_STUB_BRANCH_MODE=404 run_ci_queue_wait "feat/not-pushed-yet" 2>&1)
status_a=$?
set -e
if [[ "$status_a" -ne 0 ]]; then
echo "FAIL(a): expected exit 0 for 404 branch-absent, got $status_a" >&2
echo "$out_a" >&2
fail=1
elif [[ "$out_a" != *"queue clear"* ]]; then
echo "FAIL(a): expected a queue-clear message, got:" >&2
echo "$out_a" >&2
fail=1
fi
# (b) 200 existing branch + terminal CI state -> unchanged behavior, exit 0.
set +e
out_b=$(MOSAIC_STUB_BRANCH_MODE=200 MOSAIC_STUB_STATUS_MODE=terminal-success run_ci_queue_wait "main" 2>&1)
status_b=$?
set -e
if [[ "$status_b" -ne 0 ]]; then
echo "FAIL(b): expected exit 0 for existing branch with terminal status, got $status_b" >&2
echo "$out_b" >&2
fail=1
elif [[ "$out_b" != *"sha=deadbeefcafef00d0123456789abcdef01234567"* ]]; then
echo "FAIL(b): expected the resolved HEAD SHA to be logged, got:" >&2
echo "$out_b" >&2
fail=1
elif [[ "$out_b" == *"queue clear"* ]]; then
echo "FAIL(b): an existing branch must not take the branch-absent path" >&2
echo "$out_b" >&2
fail=1
fi
# (c) genuine API error (500) -> still fail-closed, exit nonzero.
set +e
out_c=$(MOSAIC_STUB_BRANCH_MODE=500 run_ci_queue_wait "feat/some-branch" 2>&1)
status_c=$?
set -e
if [[ "$status_c" -eq 0 ]]; then
echo "FAIL(c): expected a nonzero exit for a genuine 500 API error, got 0" >&2
echo "$out_c" >&2
fail=1
elif [[ "$out_c" == *"queue clear"* ]]; then
echo "FAIL(c): a genuine API error must not be reported as queue-clear" >&2
echo "$out_c" >&2
fail=1
fi
if [[ "$fail" -eq 0 ]]; then
echo "ci-queue-wait branch-absent regression passed (3/3 cases)"
fi
exit "$fail"

View File

@@ -1,31 +0,0 @@
#!/usr/bin/env bash
# Supervisor entry point for the Mosaic lease broker daemon (issue #869, C3).
#
# Resolves the broker socket path with the SAME precedence as
# `defaultLeaseBrokerSocket` in `packages/mosaic/src/commands/launch.ts`, so a
# gated runtime launched through that client always finds the socket this
# supervisor creates:
# 1. an explicit MOSAIC_LEASE_BROKER_SOCKET
# 2. "$XDG_RUNTIME_DIR/mosaic-lease/broker.sock"
# 3. "/run/user/<uid>/mosaic-lease/broker.sock"
#
# The state file is colocated next to the socket (same directory,
# "state.json"), mirroring how the broker already colocates its per-session
# generation files beside the socket.
#
# This script never installs, enables, or starts the systemd unit that calls
# it; it is only ever invoked BY that unit (or by a human/test harness that
# passes its own HOME/XDG_RUNTIME_DIR).
set -euo pipefail
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
if [ -n "${MOSAIC_LEASE_BROKER_SOCKET:-}" ]; then
SOCKET="$MOSAIC_LEASE_BROKER_SOCKET"
else
RUNTIME_DIR="${XDG_RUNTIME_DIR:-/run/user/$(id -u)}"
SOCKET="$RUNTIME_DIR/mosaic-lease/broker.sock"
fi
STATE="$(dirname -- "$SOCKET")/state.json"
exec python3 "$SCRIPT_DIR/daemon.py" --socket "$SOCKET" --state "$STATE"

View File

@@ -25,7 +25,7 @@
"lint": "eslint src", "lint": "eslint src",
"typecheck": "tsc --noEmit", "typecheck": "tsc --noEmit",
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell", "test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
"test:framework-shell": "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 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" "test:framework-shell": "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 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-ci-queue-wait-branch-absent.sh"
}, },
"dependencies": { "dependencies": {
"@mosaicstack/brain": "workspace:*", "@mosaicstack/brain": "workspace:*",

View File

@@ -1,237 +0,0 @@
import { createServer, type Server } from 'node:net';
import { mkdir, mkdtemp, readFile, rm, stat, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, describe, expect, it } from 'vitest';
import {
applyBrokerSupervisor,
checkBrokerSupervisorHealth,
isBrokerSupervisorHealthy,
resolveBrokerSupervisorPaths,
resolveLeaseBrokerSocketPath,
type BrokerSupervisorPaths,
} from './broker-supervisor.js';
const REAL_FRAMEWORK_ROOT = new URL('../../framework/', import.meta.url).pathname;
const cleanupDirs: string[] = [];
const cleanupServers: Server[] = [];
async function tempDir(prefix: string): Promise<string> {
const dir = await mkdtemp(join(tmpdir(), prefix));
cleanupDirs.push(dir);
return dir;
}
afterEach(async () => {
for (const server of cleanupServers.splice(0)) {
await new Promise<void>((resolve) => server.close(() => resolve()));
}
for (const dir of cleanupDirs.splice(0)) {
await rm(dir, { recursive: true, force: true });
}
});
describe('resolveLeaseBrokerSocketPath', () => {
it('honors an explicit MOSAIC_LEASE_BROKER_SOCKET override', () => {
expect(resolveLeaseBrokerSocketPath({ MOSAIC_LEASE_BROKER_SOCKET: '/tmp/explicit.sock' })).toBe(
'/tmp/explicit.sock',
);
});
it('falls back to $XDG_RUNTIME_DIR/mosaic-lease/broker.sock', () => {
expect(resolveLeaseBrokerSocketPath({ XDG_RUNTIME_DIR: '/run/user/1000' })).toBe(
join('/run/user/1000', 'mosaic-lease', 'broker.sock'),
);
});
it('falls back to /run/user/<uid>/mosaic-lease/broker.sock as a last resort', () => {
expect(resolveLeaseBrokerSocketPath({}, 4242)).toBe(
join('/run/user', '4242', 'mosaic-lease', 'broker.sock'),
);
});
it('prefers the explicit override over XDG_RUNTIME_DIR', () => {
expect(
resolveLeaseBrokerSocketPath({
MOSAIC_LEASE_BROKER_SOCKET: '/explicit.sock',
XDG_RUNTIME_DIR: '/run/user/1000',
}),
).toBe('/explicit.sock');
});
});
describe('resolveBrokerSupervisorPaths', () => {
it('colocates the state file next to the resolved socket', () => {
const paths = resolveBrokerSupervisorPaths({
mosaicHome: '/home/x/.config/mosaic',
frameworkRoot: '/repo/framework',
env: { XDG_RUNTIME_DIR: '/run/user/1000' },
});
expect(paths.socketPath).toBe(join('/run/user/1000', 'mosaic-lease', 'broker.sock'));
expect(paths.statePath).toBe(join('/run/user/1000', 'mosaic-lease', 'state.json'));
});
it('targets the systemd --user dir under the given home, not mosaicHome', () => {
const paths = resolveBrokerSupervisorPaths({
mosaicHome: '/somewhere-else/.config/mosaic',
frameworkRoot: '/repo/framework',
homeDir: '/home/canary',
env: {},
uid: 0,
});
expect(paths.systemdUserDir).toBe(join('/home/canary', '.config', 'systemd', 'user'));
expect(paths.unitTargetPath).toBe(
join('/home/canary', '.config', 'systemd', 'user', 'mosaic-lease-broker.service'),
);
});
it('is a pure function: identical options resolve to identical paths', () => {
const options = {
mosaicHome: '/h/.config/mosaic',
frameworkRoot: '/repo/framework',
env: { XDG_RUNTIME_DIR: '/run/user/1000' },
};
expect(resolveBrokerSupervisorPaths(options)).toEqual(resolveBrokerSupervisorPaths(options));
});
});
describe('applyBrokerSupervisor', () => {
async function fakePaths(): Promise<BrokerSupervisorPaths> {
const home = await tempDir('mosaic-broker-supervisor-home-');
const mosaicHome = join(home, '.config', 'mosaic');
const runtimeDir = await tempDir('mosaic-broker-supervisor-runtime-');
return resolveBrokerSupervisorPaths({
mosaicHome,
frameworkRoot: REAL_FRAMEWORK_ROOT,
homeDir: home,
env: { XDG_RUNTIME_DIR: runtimeDir },
});
}
it('renders a unit that references the installed wrapper script and hardens the runtime dir', async () => {
const paths = await fakePaths();
const unitSource = await readFile(paths.unitSourcePath, 'utf8');
expect(unitSource).toContain('ExecStart=');
expect(unitSource).toContain('%h/.config/mosaic/tools/lease-broker/start-lease-broker.sh');
expect(unitSource).toContain('RuntimeDirectory=mosaic-lease');
expect(unitSource).toContain('RuntimeDirectoryMode=0700');
expect(unitSource).toContain('Restart=on-failure');
expect(unitSource).toContain('WantedBy=default.target');
// No ambient environment file preload, matching the other fleet units'
// strict-parsing convention.
expect(unitSource).not.toMatch(/^Environment(File)?=/m);
});
it('materializes the unit, wrapper script, and daemon sources on first apply', async () => {
const paths = await fakePaths();
const result = await applyBrokerSupervisor(paths);
expect(result.installedFiles).toContain(paths.unitTargetPath);
expect(result.installedFiles).toContain(paths.wrapperTargetPath);
for (const target of paths.daemonTargetPaths) {
expect(result.installedFiles).toContain(target);
}
const unitTargetContent = await readFile(paths.unitTargetPath, 'utf8');
const unitSourceContent = await readFile(paths.unitSourcePath, 'utf8');
expect(unitTargetContent).toBe(unitSourceContent);
const wrapperMode = (await stat(paths.wrapperTargetPath)).mode & 0o777;
expect(wrapperMode).toBe(0o755);
for (const target of paths.daemonTargetPaths) {
await expect(stat(target)).resolves.toBeDefined();
}
});
it('is idempotent: applying twice reproduces identical files with no error', async () => {
const paths = await fakePaths();
await applyBrokerSupervisor(paths);
const firstUnit = await readFile(paths.unitTargetPath, 'utf8');
const firstWrapper = await readFile(paths.wrapperTargetPath, 'utf8');
const firstWrapperMode = (await stat(paths.wrapperTargetPath)).mode & 0o777;
await expect(applyBrokerSupervisor(paths)).resolves.toBeDefined();
const secondUnit = await readFile(paths.unitTargetPath, 'utf8');
const secondWrapper = await readFile(paths.wrapperTargetPath, 'utf8');
const secondWrapperMode = (await stat(paths.wrapperTargetPath)).mode & 0o777;
expect(secondUnit).toBe(firstUnit);
expect(secondWrapper).toBe(firstWrapper);
expect(secondWrapperMode).toBe(firstWrapperMode);
});
it('never touches the real host: only writes under the supplied temp dirs', async () => {
const paths = await fakePaths();
await applyBrokerSupervisor(paths);
expect(paths.systemdUserDir.startsWith(tmpdir())).toBe(true);
expect(paths.mosaicHome.startsWith(tmpdir())).toBe(true);
});
});
describe('checkBrokerSupervisorHealth / isBrokerSupervisorHealthy', () => {
async function fakeHealthPaths(): Promise<
Pick<BrokerSupervisorPaths, 'unitTargetPath' | 'socketPath'>
> {
const runtimeDir = await tempDir('mosaic-broker-supervisor-health-');
await mkdir(join(runtimeDir, 'systemd-user'), { recursive: true });
return {
unitTargetPath: join(runtimeDir, 'systemd-user', 'mosaic-lease-broker.service'),
socketPath: join(runtimeDir, 'broker.sock'),
};
}
it('reports unhealthy when neither the unit nor the socket exist', async () => {
const paths = await fakeHealthPaths();
const health = await checkBrokerSupervisorHealth(paths);
expect(health).toEqual({ unitInstalled: false, socketPresent: false, healthy: false });
expect(await isBrokerSupervisorHealthy(paths)).toBe(false);
});
it('reports unhealthy when the unit is installed but no socket is listening', async () => {
const paths = await fakeHealthPaths();
await writeFile(paths.unitTargetPath, '[Unit]\n');
const health = await checkBrokerSupervisorHealth(paths);
expect(health.unitInstalled).toBe(true);
expect(health.socketPresent).toBe(false);
expect(health.healthy).toBe(false);
});
it('reports healthy=true once a real Unix socket exists at the resolved path, and false again once removed', async () => {
const paths = await fakeHealthPaths();
const server = createServer();
cleanupServers.push(server);
await new Promise<void>((resolve, reject) => {
server.once('error', reject);
server.listen(paths.socketPath, resolve);
});
expect(await isBrokerSupervisorHealthy(paths)).toBe(true);
const health = await checkBrokerSupervisorHealth(paths);
expect(health.socketPresent).toBe(true);
expect(health.healthy).toBe(true);
await new Promise<void>((resolve) => server.close(() => resolve()));
await rm(paths.socketPath, { force: true });
expect(await isBrokerSupervisorHealthy(paths)).toBe(false);
});
it('does not confuse a stale regular file at the socket path with a live socket', async () => {
const paths = await fakeHealthPaths();
await writeFile(paths.socketPath, 'not actually a socket');
expect(await isBrokerSupervisorHealthy(paths)).toBe(false);
});
});

View File

@@ -1,223 +0,0 @@
/**
* Activation-side supervisor for the Mosaic lease broker (issue #869, Point-1
* C3). #828 shipped fail-closed enforcement hooks (`mutator-gate.py`,
* `receipt-observer-client.py`) with nothing that guaranteed `daemon.py` was
* running or that its socket existed before a gated runtime started. This
* module:
*
* - resolves the broker socket/state paths and the on-disk locations of the
* supervisor artifacts, deterministically and consistently with
* `defaultLeaseBrokerSocket` in `../commands/launch.ts`;
* - idempotently applies (materializes) a systemd `--user` unit plus the
* wrapper script and daemon sources it execs, mirroring the tmux fleet
* unit convention in `framework/systemd/user/`;
* - exposes a health predicate other cards (e.g. the C1 activation probe)
* can call to learn whether a broker supervisor is present and healthy.
*
* `applyBrokerSupervisor` only writes files under the paths it is given. It
* never runs `systemctl`, never starts `daemon.py`, and never touches a real
* host's `~/.config` unless the caller explicitly resolves paths there.
* Enabling/starting the unit is a separate, later, out-of-scope step.
*/
import { chmod, copyFile, mkdir, stat } from 'node:fs/promises';
import { homedir } from 'node:os';
import { dirname, join } from 'node:path';
const UNIT_NAME = 'mosaic-lease-broker.service';
const WRAPPER_SCRIPT_NAME = 'start-lease-broker.sh';
/** Co-located modules `daemon.py` imports at runtime; kept alongside it. */
const DAEMON_SOURCE_FILE_NAMES = [
'daemon.py',
'lease_generation.py',
'normative_fragments.py',
'receipt_challenge.py',
'receipt_observer.py',
] as const;
export interface ResolveBrokerSupervisorPathsOptions {
/** `~/.config/mosaic` (or an override) — where installed tool copies live. */
mosaicHome: string;
/** Root of the checked-out `framework/` directory (canonical file source). */
frameworkRoot: string;
/** Defaults to `process.env`; pass a fake for tests. */
env?: NodeJS.ProcessEnv;
/** Defaults to `os.homedir()`; pass a temp dir in tests. */
homeDir?: string;
/** Defaults to `process.getuid()` (or 0); pass a fake for tests. */
uid?: number;
}
export interface BrokerSupervisorPaths {
readonly mosaicHome: string;
readonly frameworkRoot: string;
readonly systemdUserDir: string;
readonly leaseBrokerToolsDir: string;
readonly unitSourcePath: string;
readonly unitTargetPath: string;
readonly wrapperSourcePath: string;
readonly wrapperTargetPath: string;
readonly daemonSourcePaths: readonly string[];
readonly daemonTargetPaths: readonly string[];
/**
* Resolved with the same precedence as `defaultLeaseBrokerSocket` in
* `../commands/launch.ts`: an explicit `MOSAIC_LEASE_BROKER_SOCKET`, else
* `$XDG_RUNTIME_DIR/mosaic-lease/broker.sock`, else
* `/run/user/<uid>/mosaic-lease/broker.sock`.
*/
readonly socketPath: string;
/** Colocated next to the socket, matching the broker's own generation-file convention. */
readonly statePath: string;
}
/**
* Resolve the lease broker socket path alone, with the same precedence as
* `defaultLeaseBrokerSocket` in `../commands/launch.ts`. Exported so callers
* (and tests) can assert the two stay in agreement without importing the CLI
* command module.
*/
export function resolveLeaseBrokerSocketPath(
env: NodeJS.ProcessEnv = process.env,
uid: number = typeof process.getuid === 'function' ? process.getuid() : 0,
): string {
const explicit = env['MOSAIC_LEASE_BROKER_SOCKET'];
if (explicit) return explicit;
const runtimeDir = env['XDG_RUNTIME_DIR'];
if (runtimeDir) return join(runtimeDir, 'mosaic-lease', 'broker.sock');
return join('/run/user', String(uid), 'mosaic-lease', 'broker.sock');
}
/** Resolve every path the supervisor apply/health functions need, deterministically. */
export function resolveBrokerSupervisorPaths(
options: ResolveBrokerSupervisorPathsOptions,
): BrokerSupervisorPaths {
const { mosaicHome, frameworkRoot } = options;
const env = options.env ?? process.env;
const homeDir = options.homeDir ?? homedir();
const systemdUserDir = join(homeDir, '.config', 'systemd', 'user');
const leaseBrokerToolsDir = join(mosaicHome, 'tools', 'lease-broker');
const frameworkLeaseBrokerDir = join(frameworkRoot, 'tools', 'lease-broker');
const socketPath = resolveLeaseBrokerSocketPath(env, options.uid);
const statePath = join(dirname(socketPath), 'state.json');
return {
mosaicHome,
frameworkRoot,
systemdUserDir,
leaseBrokerToolsDir,
unitSourcePath: join(frameworkRoot, 'systemd', 'user', UNIT_NAME),
unitTargetPath: join(systemdUserDir, UNIT_NAME),
wrapperSourcePath: join(frameworkLeaseBrokerDir, WRAPPER_SCRIPT_NAME),
wrapperTargetPath: join(leaseBrokerToolsDir, WRAPPER_SCRIPT_NAME),
daemonSourcePaths: DAEMON_SOURCE_FILE_NAMES.map((name) => join(frameworkLeaseBrokerDir, name)),
daemonTargetPaths: DAEMON_SOURCE_FILE_NAMES.map((name) => join(leaseBrokerToolsDir, name)),
socketPath,
statePath,
};
}
export interface ApplyBrokerSupervisorResult {
readonly installedFiles: readonly string[];
}
/**
* Idempotently materialize the supervisor unit, its wrapper script, and the
* daemon sources it execs. Safe to call on every reseed: every write is a
* deterministic overwrite of the same target path from the same source, so a
* second call reproduces identical bytes/modes and never errors.
*
* Never runs `systemctl`; the caller decides separately whether/when to
* `daemon-reload`/`enable`/`start` the installed unit.
*/
export async function applyBrokerSupervisor(
paths: BrokerSupervisorPaths,
): Promise<ApplyBrokerSupervisorResult> {
await mkdir(paths.leaseBrokerToolsDir, { recursive: true });
await mkdir(paths.systemdUserDir, { recursive: true });
const installedFiles: string[] = [];
for (let index = 0; index < paths.daemonSourcePaths.length; index += 1) {
const source = paths.daemonSourcePaths[index];
const target = paths.daemonTargetPaths[index];
if (source === undefined || target === undefined) continue;
await copyFile(source, target);
await chmod(target, 0o644);
installedFiles.push(target);
}
await copyFile(paths.wrapperSourcePath, paths.wrapperTargetPath);
await chmod(paths.wrapperTargetPath, 0o755);
installedFiles.push(paths.wrapperTargetPath);
await copyFile(paths.unitSourcePath, paths.unitTargetPath);
await chmod(paths.unitTargetPath, 0o644);
installedFiles.push(paths.unitTargetPath);
return { installedFiles };
}
export interface BrokerSupervisorHealth {
/** Whether the systemd unit file has been materialized at its target path. */
readonly unitInstalled: boolean;
/** Whether a Unix domain socket currently exists at the resolved socket path. */
readonly socketPresent: boolean;
/**
* The signal other cards (e.g. C1's activation probe) should treat as
* "a broker supervisor is present and healthy". Presence of a live socket
* is the authoritative signal: a gated runtime can only ever succeed by
* connecting to it, so this is what fail-closed callers must check.
*/
readonly healthy: boolean;
}
/**
* Report the supervisor's on-disk/health signals. Never throws for an
* absent unit or socket — both simply report `false`; unexpected filesystem
* errors (permission issues, etc.) still propagate.
*/
export async function checkBrokerSupervisorHealth(
paths: Pick<BrokerSupervisorPaths, 'unitTargetPath' | 'socketPath'>,
): Promise<BrokerSupervisorHealth> {
const [unitInstalled, socketPresent] = await Promise.all([
pathExists(paths.unitTargetPath),
isUnixSocket(paths.socketPath),
]);
return { unitInstalled, socketPresent, healthy: socketPresent };
}
/** Convenience boolean form of {@link checkBrokerSupervisorHealth} for simple call sites. */
export async function isBrokerSupervisorHealthy(
paths: Pick<BrokerSupervisorPaths, 'unitTargetPath' | 'socketPath'>,
): Promise<boolean> {
return (await checkBrokerSupervisorHealth(paths)).healthy;
}
async function pathExists(path: string): Promise<boolean> {
try {
await stat(path);
return true;
} catch (error) {
if (isEnoent(error)) return false;
throw error;
}
}
async function isUnixSocket(path: string): Promise<boolean> {
try {
const info = await stat(path);
return info.isSocket();
} catch (error) {
if (isEnoent(error)) return false;
throw error;
}
}
function isEnoent(error: unknown): boolean {
return (
typeof error === 'object' &&
error !== null &&
'code' in error &&
(error as NodeJS.ErrnoException).code === 'ENOENT'
);
}