test: add tool-inventory smoke test asserting the 23-tool surface

Every PR in the non-custodial-split series is supposed to preserve
`tools/list` returning 23 tools with identical schemas, but nothing
enforced it — PRs 2, 6, 7 and 8 will restructure and rename tool
families, and a snapshot only means something if it's taken before
that starts. Boot the built server, call listTools(), and assert both
the count and the exact sorted name list against a checked-in
baseline captured from a live run on this branch. Failures report
which names were added/removed rather than a bare array-diff.

Reuses startServer()/stopServer() from test/setup.ts; does not call
getMnemonic(), so it needs no wallet. Wired into CI as a new step
after the unit tests. Also raises the server-start timeout in
setup.ts from 15s to 60s — the Cardano WASM import makes cold starts
slow enough that 15s was flaky on the smoke test's first CI run.

test:smoke is intentionally separate from test:unit (which does not
build) since startServer() spawns build/index.js.

.github/workflows/ci.yml

@@ -29,3 +29,8 @@ jobs:
         run: npm run test:unit
         env:
           NODE_OPTIONS: --max-old-space-size=12288
+
+      - name: Tool inventory smoke test
+        run: npm run test:smoke
+        env:
+          NODE_OPTIONS: --max-old-space-size=12288

package.json

@@ -14,7 +14,8 @@
     "start": "node build/index.js",
     "test": "npm run test:unit",
     "test:unit": "node --import tsx --test test/unit/*.test.ts",
-    "test:integration": "npm run build && node --import tsx --test test/integration/*.test.ts"
+    "test:integration": "npm run build && node --import tsx --test test/integration/*.test.ts",
+    "test:smoke": "npm run build && node --import tsx --test test/smoke/*.test.ts"
   },
   "files": [
     "build"

test/setup.ts

@@ -31,7 +31,7 @@ export async function startServer(): Promise<ServerContext> {
   });
 
   await new Promise<void>((resolve, reject) => {
-    const timeout = setTimeout(() => reject(new Error('Server start timeout (15s)')), 15_000);
+    const timeout = setTimeout(() => reject(new Error('Server start timeout (60s)')), 60_000);
     child.stderr!.on('data', (chunk: Buffer) => {
       if (chunk.toString().includes('listening on port')) {
         clearTimeout(timeout);

test/smoke/tool-inventory.test.ts

@@ -0,0 +1,75 @@
+import { describe, test, before, after } from 'node:test';
+import assert from 'node:assert/strict';
+import { startServer, stopServer, ServerContext } from '../setup.ts';
+
+/**
+ * Snapshot of the pre-migration tool surface (23 tools), captured from a real
+ * `listTools()` call against a built server on the `ci/harness-and-gitignore`
+ * branch. This is the baseline for the non-custodial split series
+ * (see docs/architecture/non-custodial-split.md) — PRs 2, 6, 7 and 8
+ * deliberately restructure and rename tool families, and each of those PRs is
+ * expected to update this list deliberately, not accidentally. No wallet,
+ * no network beyond localhost — this never needs a mnemonic.
+ */
+const EXPECTED_TOOLS = [
+  'vector_build_transaction',
+  'vector_deploy_contract',
+  'vector_deregister_agent',
+  'vector_discover_agents',
+  'vector_dry_run',
+  'vector_get_address',
+  'vector_get_agent_profile',
+  'vector_get_balance',
+  'vector_get_spend_limits',
+  'vector_get_transaction_history',
+  'vector_get_utxos',
+  'vector_interact_contract',
+  'vector_message_agent',
+  'vector_register_agent',
+  'vector_self_improvement_analyze_metrics',
+  'vector_self_improvement_browse',
+  'vector_self_improvement_critique',
+  'vector_self_improvement_endorse',
+  'vector_self_improvement_submit_proposal',
+  'vector_send_apex',
+  'vector_send_tokens',
+  'vector_transfer_agent',
+  'vector_update_agent',
+];
+
+let ctx: ServerContext;
+let actualNames: string[];
+
+before(async () => {
+  ctx = await startServer();
+  const result = await ctx.client.listTools();
+  actualNames = result.tools.map((t) => t.name).sort();
+});
+
+after(async () => {
+  await stopServer(ctx);
+});
+
+describe('tool inventory smoke test', () => {
+  test('exposes exactly 23 tools', () => {
+    assert.equal(
+      actualNames.length,
+      23,
+      `expected 23 tools, got ${actualNames.length}: ${JSON.stringify(actualNames)}`
+    );
+  });
+
+  test('tool names match the checked-in inventory exactly', () => {
+    const added = actualNames.filter((name) => !EXPECTED_TOOLS.includes(name));
+    const removed = EXPECTED_TOOLS.filter((name) => !actualNames.includes(name));
+
+    assert.deepEqual(
+      actualNames,
+      EXPECTED_TOOLS,
+      'Tool inventory drifted from the checked-in snapshot in test/smoke/tool-inventory.test.ts.\n' +
+        `  added:   ${added.length ? JSON.stringify(added) : '(none)'}\n` +
+        `  removed: ${removed.length ? JSON.stringify(removed) : '(none)'}\n` +
+        'If this drift is intentional, update EXPECTED_TOOLS in this file to match.'
+    );
+  });
+});