fix(lease): raise capability-probe timeout to 10s on both halves (#869) (#1207)

packages/mosaic/src/commands/lease-activation-probe.spec.ts

@@ -7,11 +7,13 @@ import { fileURLToPath } from 'node:url';
 import {
   LEASE_ACTIVATION_CAPABILITY,
   LEASE_CAPABILITY_PROBE_COMMAND,
+  LEASE_CAPABILITY_PROBE_TIMEOUT_MS,
   defaultCapabilityProbe,
   defaultResolveCliEntry,
   defaultSupervisorProbe,
   leaseEnforcementActivatable,
   registerLeaseCapabilityProbe,
+  type CapabilityProbeExecFile,
   type LeaseActivationCapability,
   type SupervisorProbeResult,
 } from './lease-activation-probe.js';
@@ -35,6 +37,17 @@ const presentSupervisor: SupervisorProbeResult = {
   socketPath: '/run/user/1000/mosaic-lease/broker.sock',
 };
 
+function withScratchCli<T>(run: (cliPath: string) => T): T {
+  const scratchDir = mkdtempSync(join(tmpdir(), 'mosaic-lease-capability-probe-'));
+  try {
+    const cliPath = join(scratchDir, 'cli.js');
+    writeFileSync(cliPath, '// isolated fake; injected execFile means this is never executed\n');
+    return run(cliPath);
+  } finally {
+    rmSync(scratchDir, { recursive: true, force: true });
+  }
+}
+
 describe('leaseEnforcementActivatable', () => {
   it('is false when the activation capability is absent (null)', () => {
     const result = leaseEnforcementActivatable({
@@ -100,15 +113,6 @@ describe('leaseEnforcementActivatable', () => {
     });
     expect(result).toBe(true);
   });
-
-  it('uses the real default probes when no deps are injected (does not throw)', () => {
-    // No live broker / built CLI is guaranteed in a test environment, so this
-    // only asserts the predicate degrades to a safe boolean rather than
-    // throwing — the fail-closed behavior itself is covered by the injected
-    // cases above.
-    expect(() => leaseEnforcementActivatable()).not.toThrow();
-    expect(typeof leaseEnforcementActivatable()).toBe('boolean');
-  });
 });
 
 describe('defaultCapabilityProbe', () => {
@@ -127,6 +131,61 @@ describe('defaultCapabilityProbe', () => {
     expect(result).toBeNull();
   });
 
+  it('passes the exact ten-second timeout to the injected child-process transport', () => {
+    withScratchCli((cliPath) => {
+      let captured:
+        | {
+            file: string;
+            args: string[];
+            options: Parameters<CapabilityProbeExecFile>[2];
+          }
+        | undefined;
+      const execFile: CapabilityProbeExecFile = (file, args, options) => {
+        captured = { file, args, options };
+        return JSON.stringify(LEASE_ACTIVATION_CAPABILITY);
+      };
+
+      const result = defaultCapabilityProbe({ resolveCliEntry: () => cliPath, execFile });
+
+      expect(result).toEqual(LEASE_ACTIVATION_CAPABILITY);
+      expect(captured).toEqual({
+        file: process.execPath,
+        args: [cliPath, LEASE_CAPABILITY_PROBE_COMMAND],
+        options: {
+          encoding: 'utf-8',
+          timeout: 10_000,
+          stdio: ['ignore', 'pipe', 'ignore'],
+        },
+      });
+      expect(captured?.options.timeout).toBe(LEASE_CAPABILITY_PROBE_TIMEOUT_MS);
+    });
+  });
+
+  it.each([
+    ['timeout', Object.assign(new Error('timed out'), { code: 'ETIMEDOUT' })],
+    ['spawn error', Object.assign(new Error('spawn failed'), { code: 'ENOENT' })],
+    ['nonzero exit', Object.assign(new Error('child exited 1'), { status: 1 })],
+  ])('returns null (fail-closed) on child-process %s', (_failure, error) => {
+    withScratchCli((cliPath) => {
+      const execFile: CapabilityProbeExecFile = () => {
+        throw error;
+      };
+
+      expect(defaultCapabilityProbe({ resolveCliEntry: () => cliPath, execFile })).toBeNull();
+    });
+  });
+
+  it.each([
+    ['unparseable JSON', 'not-json'],
+    ['malformed object', JSON.stringify({ name: LEASE_ACTIVATION_CAPABILITY.name })],
+  ])('returns null (fail-closed) on %s output', (_failure, output) => {
+    withScratchCli((cliPath) => {
+      const execFile: CapabilityProbeExecFile = () => output;
+
+      expect(defaultCapabilityProbe({ resolveCliEntry: () => cliPath, execFile })).toBeNull();
+    });
+  });
+
   describe('positive path — injected resolver, isolated scratch dir (never the real dist/)', () => {
     // A prior version of this test staged the stub cli.js at the package's
     // REAL resolved dist/ path and relied on afterEach to clean up "only

packages/mosaic/src/commands/lease-activation-probe.ts

@@ -55,6 +55,19 @@ export const LEASE_ACTIVATION_CAPABILITY: LeaseActivationCapability = {
 /** Hidden CLI probe subcommand name — wired via {@link registerLeaseCapabilityProbe}. */
 export const LEASE_CAPABILITY_PROBE_COMMAND = '__lease-capability';
 
+/**
+ * Budget for the out-of-process capability probe. The probe launches a fresh
+ * Node process on the built CLI entrypoint, whose cold start alone measures
+ * 2.2-2.3s on a mid-range workstation (sb-it-1-dt, 2026-08-13) — so the
+ * previous 2s budget made the probe time out and report NO capability on
+ * such hosts, failing every launch with the #869 skew message even though
+ * the capability matched. The timeout only bounds the pathological hang
+ * case; the happy path returns as soon as the probe exits. Mirrors
+ * PROBE_TIMEOUT_SECONDS in the enforcement half
+ * (framework/tools/lease-broker/activation_version_gate.py).
+ */
+export const LEASE_CAPABILITY_PROBE_TIMEOUT_MS = 10_000;
+
 function capabilityMatches(candidate: LeaseActivationCapability | null): boolean {
   return (
     candidate !== null &&
@@ -110,12 +123,28 @@ export function defaultResolveCliEntry(
   return join(dirname(mainEntry), 'cli.js');
 }
 
+/** Narrow injectable seam for the synchronous child process used by the
+ * capability probe. */
+export type CapabilityProbeExecFile = (
+  file: string,
+  args: string[],
+  options: {
+    encoding: BufferEncoding;
+    timeout: number;
+    stdio: ['ignore', 'pipe', 'ignore'];
+  },
+) => string;
+
 /** Injectable inputs for {@link defaultCapabilityProbe}. */
 export interface CapabilityProbeDeps {
   /** Resolve the CLI entrypoint (`cli.js`) to probe. Defaults to
    * {@link defaultResolveCliEntry}. Inject to point at an isolated scratch
    * location in tests — never at the real package's `dist/`. */
   resolveCliEntry?: () => string;
+  /** Execute the resolved CLI entrypoint. Defaults to the real
+   * `execFileSync`. Inject so transport behavior and options can be tested
+   * without spawning a process. */
+  execFile?: CapabilityProbeExecFile;
 }
 
 /**
@@ -139,9 +168,10 @@ export function defaultCapabilityProbe(
     const cliEntry = resolveCliEntry();
     if (!existsSync(cliEntry)) return null;
 
-    const output = execFileSync(process.execPath, [cliEntry, LEASE_CAPABILITY_PROBE_COMMAND], {
+    const execFile: CapabilityProbeExecFile = deps.execFile ?? execFileSync;
+    const output = execFile(process.execPath, [cliEntry, LEASE_CAPABILITY_PROBE_COMMAND], {
       encoding: 'utf-8',
-      timeout: 2000,
+      timeout: LEASE_CAPABILITY_PROBE_TIMEOUT_MS,
       stdio: ['ignore', 'pipe', 'ignore'],
     });