test: repair full suite — hang fix, stale-test updates, patch hygiene, timeout backstop

Suite went from 27 failures plus one permanent hang (never finished) to
1846 passed / 0 failed in ~85s, including under FORCE_COLOR.

- office_shutdown_lifecycle: construct WSHandler via the real __init__
  (helper) instead of hand-copied __new__ stubs that drift from the
  constructor (#11 added _runtime_status_sync_task and the stubs hung);
  the formerly-hanging wait now has a 5s wait_for.
- import-time patch hygiene: company_recruiter / company_reorg /
  engine_session_defaults replaced module-level permanent
  tempfile.TemporaryDirectory monkeypatching with paired
  setUpModule/tearDownModule, fixing order-dependent sqlite failures in
  transcript_pagination during full runs.
- stale tests updated to current product semantics: resume stubs use
  status="done" (failed is deliberately non-resumable), fix4 asserts the
  native review contract through build_company_work_item_contract,
  delivery fixture carries user_visible/feedback_scope=final, ownership
  doc names progress_log, session compression calls
  maybe_compact_session(force=True) explicitly, hard delete removes the
  work item row, parallel-isolation asserts delegate rebind and stubs
  _get_project_delegate, role update goes through OrgService on an
  editable custom org (plus read-only rejection case), collab_rpc patches
  the single os.name decision point instead of poisoning pathlib, codex
  no-pty builds inside the patch, identity-guard false positives reworded.
- cli_board actions rewritten against the real OfficeServiceFactory seam
  with a tempdir OPC_HOME (old direct-engine stubs were never consulted
  and the tests wrote into the real OPC home).
- cli_app assertions strip ANSI via _plain_output so a color-forcing
  shell (FORCE_COLOR) cannot break plain-text expectations.
- deleted never-runnable test_org_concurrency (pytest.mark.asyncio
  without the plugin, stdlib-only assertions) and three dead skipped
  filesystem-handoff tests.
- pyproject: dev extra (pytest, pytest-timeout) and a 300s per-test
  timeout backstop so a wedged test fails instead of stalling the suite.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/test_cli_app.py

@@ -4,6 +4,7 @@ import asyncio
 import importlib
 import json
 import os
+import re
 import sqlite3
 import tempfile
 import unittest
@@ -58,6 +59,17 @@ from opc.plugins.office_ui.services.project import ProjectService
 from opc.plugins.office_ui.services.session import SessionService
 from opc.plugins.office_ui.services.work_item import WorkItemService
 
+_ANSI_ESCAPE_RE = re.compile(r"\x1b\[[0-9;]*[A-Za-z]")
+
+
+def _plain_output(text: str) -> str:
+    """CLI output with ANSI styling stripped.
+
+    Keeps plain-text assertions stable when the invoking shell forces
+    color (e.g. FORCE_COLOR) onto rich/typer output.
+    """
+    return _ANSI_ESCAPE_RE.sub("", text)
+
 
 class CliEscalationFormattingTests(unittest.TestCase):
     def setUp(self) -> None:
@@ -305,7 +317,7 @@ class CliInitProjectTests(unittest.TestCase):
                 result = runner.invoke(app, ["init", "dupe"])
 
             self.assertNotEqual(result.exit_code, 0)
-            self.assertIn("Project 'dupe' already exists", result.output)
+            self.assertIn("Project 'dupe' already exists", _plain_output(result.output))
             self.assertFalse((opc_home / "projects" / "dupe").exists())
 
     def test_init_existing_config_cancel_preserves_config_and_does_not_create_project(self) -> None:
@@ -3119,7 +3131,7 @@ class CliChannelCommandTests(unittest.TestCase):
 
         self.assertEqual(result.exit_code, 0)
         mock_kill.assert_called_once()
-        self.assertIn("PID 4321", result.stdout)
+        self.assertIn("PID 4321", _plain_output(result.stdout))
 
     def test_channels_status_reports_runtime_and_capabilities(self) -> None:
         config = OPCConfig()
@@ -3165,9 +3177,10 @@ class CliAutomationCommandTests(unittest.TestCase):
         result = self.runner.invoke(app, ["exec", "--help"])
 
         self.assertEqual(result.exit_code, 0)
-        self.assertIn("--session-id", result.output)
-        self.assertIn("--resume", result.output)
-        self.assertIn("--stream-json", result.output)
+        help_text = _plain_output(result.output)
+        self.assertIn("--session-id", help_text)
+        self.assertIn("--resume", help_text)
+        self.assertIn("--stream-json", help_text)
 
     def test_exec_rejects_json_and_stream_json_together(self) -> None:
         result = self.runner.invoke(app, ["exec", "hello", "--json", "--stream-json"])
@@ -3207,9 +3220,9 @@ class CliTalentCommandTests(unittest.TestCase):
             self.assertEqual(import_result.exit_code, 0)
             self.assertEqual(hire_result.exit_code, 0)
             self.assertEqual(list_result.exit_code, 0)
-            self.assertIn("Imported 1 talent templates", import_result.stdout)
-            self.assertIn("Bea Backend", hire_result.stdout)
-            self.assertIn("engineering-backend-architect", list_result.stdout)
+            self.assertIn("Imported 1 talent templates", _plain_output(import_result.stdout))
+            self.assertIn("Bea Backend", _plain_output(hire_result.stdout))
+            self.assertIn("engineering-backend-architect", _plain_output(list_result.stdout))
 
             config = OPCConfig.load(opc_home / "config")
             self.assertEqual(config.org.talent_templates, [])