test: isolate runtime state and PTY integration

src/session.ts

@@ -180,6 +180,8 @@ export function isAltScreenStripMode(mode: SessionMode): boolean {
 const DEFAULT_PTY_COLS = 120;
 const DEFAULT_PTY_ROWS = 40;
 const TMUX_DISPLAY_TIMEOUT_MS = 2000;
+const IS_TEST_MODE = !!process.env.VITEST;
+const TEST_PTY_SCRIPT = 'process.stdin.pipe(process.stdout);';
 /** Delay before the in-container Claude CLI version probe (lets the container start). */
 const DOCKER_CLI_VERSION_PROBE_DELAY_MS = 3000;
 
@@ -1248,16 +1250,23 @@ export class Session extends EventEmitter {
       // No extra sleep — createSession() already waits for tmux readiness
     }
 
-    // Attach to the mux session via PTY
-    // Prevent tmux from letting the newest browser attach dictate global window
-    // size; accepted Codeman resize events update it explicitly below.
-    mux.setManualWindowSize?.(this._muxSession!.muxName);
+    // Integration tests need a live input/output transport without attaching to
+    // the host's tmux server or agent CLI. Production still uses the real mux.
+    if (!IS_TEST_MODE) {
+      // Prevent tmux from letting the newest browser attach dictate global window
+      // size; accepted Codeman resize events update it explicitly below.
+      mux.setManualWindowSize?.(this._muxSession!.muxName);
+    }
     // Query existing tmux window size so re-attach matches (avoids flicker from 120x40 default).
     // MUST go through the dedicated socket (mux.muxSocket); a bare `tmux display` hits the
     // default server, always fails for our socketed sessions, and silently falls back to 120x40.
-    const { cols: ptyCols, rows: ptyRows } = queryTmuxWindowSize(this._muxSession!.muxName, mux.muxSocket);
+    const { cols: ptyCols, rows: ptyRows } = IS_TEST_MODE
+      ? { cols: DEFAULT_PTY_COLS, rows: DEFAULT_PTY_ROWS }
+      : queryTmuxWindowSize(this._muxSession!.muxName, mux.muxSocket);
+    const attachCommand = IS_TEST_MODE ? process.execPath : mux.getAttachCommand();
+    const attachArgs = IS_TEST_MODE ? ['-e', TEST_PTY_SCRIPT] : mux.getAttachArgs(this._muxSession!.muxName);
     try {
-      this.ptyProcess = pty.spawn(mux.getAttachCommand(), mux.getAttachArgs(this._muxSession!.muxName), {
+      this.ptyProcess = pty.spawn(attachCommand, attachArgs, {
         name: 'xterm-256color',
         cols: ptyCols,
         rows: ptyRows,
@@ -2683,7 +2692,7 @@ export class Session extends EventEmitter {
     if (this.ptyProcess && (dimsChanged || options.force)) {
       this._ptyCols = cols;
       this._ptyRows = rows;
-      if (this._mux && this._muxSession) {
+      if (!IS_TEST_MODE && this._mux && this._muxSession) {
         this._mux.resizeWindow?.(this._muxSession.muxName, cols, rows);
       }
       this.ptyProcess.resize(cols, rows);

test/quick-start.test.ts

@@ -1,19 +1,36 @@
 import { describe, it, expect, beforeAll, afterAll, beforeEach, afterEach } from 'vitest';
-import { WebServer } from '../src/web/server.js';
-import { existsSync, rmSync, mkdirSync } from 'node:fs';
+import type { WebServer } from '../src/web/server.js';
+import { existsSync, rmSync, mkdirSync, mkdtempSync } from 'node:fs';
 import { join } from 'node:path';
-import { homedir } from 'node:os';
+import { tmpdir } from 'node:os';
 
 const TEST_PORT = 3099;
-const CASES_DIR = join(homedir(), 'codeman-cases');
+const ORIGINAL_HOME = process.env.HOME;
+const TEST_HOME = mkdtempSync(join(tmpdir(), 'codeman-quick-start-'));
+const CASES_DIR = join(TEST_HOME, 'codeman-cases');
+let webServerModule: Promise<typeof import('../src/web/server.js')> | undefined;
+
+process.env.HOME = TEST_HOME;
+
+async function createTestServer(port: number): Promise<WebServer> {
+  webServerModule ??= import('../src/web/server.js');
+  const { WebServer: TestWebServer } = await webServerModule;
+  return new TestWebServer(port, false, true);
+}
+
+afterAll(() => {
+  if (ORIGINAL_HOME === undefined) delete process.env.HOME;
+  else process.env.HOME = ORIGINAL_HOME;
+  rmSync(TEST_HOME, { recursive: true, force: true });
+});
 
 describe('Quick Start API', () => {
   let server: WebServer;
   let baseUrl: string;
   const createdCases: string[] = [];
 
   beforeAll(async () => {
-    server = new WebServer(TEST_PORT, false, true);
+    server = await createTestServer(TEST_PORT);
     await server.start();
     baseUrl = `http://localhost:${TEST_PORT}`;
   });
@@ -147,7 +164,7 @@ describe('Session Management', () => {
   let baseUrl: string;
 
   beforeAll(async () => {
-    server = new WebServer(TEST_PORT + 1, false, true);
+    server = await createTestServer(TEST_PORT + 1);
     await server.start();
     baseUrl = `http://localhost:${TEST_PORT + 1}`;
   });
@@ -206,7 +223,7 @@ describe('Case Management', () => {
   const createdCases: string[] = [];
 
   beforeAll(async () => {
-    server = new WebServer(TEST_PORT + 2, false, true);
+    server = await createTestServer(TEST_PORT + 2);
     await server.start();
     baseUrl = `http://localhost:${TEST_PORT + 2}`;
   });

test/setup.ts

@@ -1,16 +1,36 @@
 /**
  * @fileoverview Global test setup for Codeman tests
  *
- * SAFETY: TmuxManager has built-in test mode detection
- * (via process.env.VITEST) that makes ALL shell commands no-ops.
- * This means tests CANNOT kill, create, or interact with real tmux
- * sessions regardless of what the test code does.
+ * SAFETY: The suite gets a temporary HOME and explicitly enables runtime test
+ * mode before application modules load. Tests therefore cannot touch the real
+ * Codeman state/cases tree or launch external tmux-backed agent sessions.
  *
  * This setup file strips shell-level auth configuration that can leak from a
  * running Codeman instance, then handles mock/timer cleanup between tests.
  */
 
-import { afterEach, vi } from 'vitest';
+import { mkdtempSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { afterAll, afterEach, vi } from 'vitest';
+
+const originalHome = process.env.HOME;
+const originalUserProfile = process.env.USERPROFILE;
+const originalVitest = process.env.VITEST;
+const originalPlaywrightBrowsersPath = process.env.PLAYWRIGHT_BROWSERS_PATH;
+const testHome = mkdtempSync(join(tmpdir(), 'codeman-vitest-'));
+
+if (originalPlaywrightBrowsersPath === undefined && originalHome) {
+  process.env.PLAYWRIGHT_BROWSERS_PATH =
+    process.platform === 'darwin'
+      ? join(originalHome, 'Library', 'Caches', 'ms-playwright')
+      : process.platform === 'win32'
+        ? join(process.env.LOCALAPPDATA || originalHome, 'ms-playwright')
+        : join(originalHome, '.cache', 'ms-playwright');
+}
+process.env.HOME = testHome;
+process.env.USERPROFILE = testHome;
+process.env.VITEST = 'true';
 
 delete process.env.CODEMAN_PASSWORD;
 delete process.env.CODEMAN_USERNAME;
@@ -23,3 +43,19 @@ afterEach(() => {
   vi.clearAllMocks();
   vi.useRealTimers();
 });
+
+afterAll(() => {
+  if (originalHome === undefined) delete process.env.HOME;
+  else process.env.HOME = originalHome;
+
+  if (originalUserProfile === undefined) delete process.env.USERPROFILE;
+  else process.env.USERPROFILE = originalUserProfile;
+
+  if (originalVitest === undefined) delete process.env.VITEST;
+  else process.env.VITEST = originalVitest;
+
+  if (originalPlaywrightBrowsersPath === undefined) delete process.env.PLAYWRIGHT_BROWSERS_PATH;
+  else process.env.PLAYWRIGHT_BROWSERS_PATH = originalPlaywrightBrowsersPath;
+
+  rmSync(testHome, { recursive: true, force: true });
+});