feat: extract in-process MCP action layer, concurrent task dispatch, and spawn/reconcile hardening

- Extract device action execution into artemis/mcp action layer:
  typed ActionResult, capability manifest with startup validation,
  AdbActuator as the single physical implementation, in-memory
  ActionSession (replaces stdio subprocess MCP in validator), and
  McpActionExecutor preserving the legacy executor contract.
  adb_server keeps its external stdio/SSE surface unchanged and now
  reuses the actuator implementation; import-time side effects moved
  into configure_stdio_mode().
- Capability-gated prompt assembly (prompt_assembly.py): tool enums and
  teaching segments render per available backend tools; full-set output
  is byte-identical to the previous static text (locked by tests).
- Admin console task queue: serial worker replaced by a per-device
  concurrent dispatcher (ARTEMIS_CONCURRENCY_MODE=global restores
  serial semantics), per-session cancellation, strict device binding on
  enqueue, unified stdio piping with tee to trace stdout.log, and
  shutdown cleanup of all active runs. Fix _pid_exists exception order
  so PermissionError is treated as alive.
- mcp_server reliability: spawn watchdog kills runners stuck before
  interpreter startup and releases device reservations; task state
  reconcile uses psutil liveness, prefers runner-reported pids, and
  adds a 45s startup grace to stop false failure reports on Windows;
  conversation_id is now optional end-to-end; explicit device_serial is
  validated at submission.
- CLI install now writes ~/.claude/rules/artemis.md for Claude Code and
  migrates/removes the legacy CLAUDE.md injection block; ~/.claude.json
  is never rewritten when it fails to parse.
- Tests: Windows-portable stdio lifecycle and path assertions; new
  suites for action layer, prompt assembly, spawn watchdog, and task
  reconcile (895 passed, 3 skipped).

tests/unit/data_engine/test_latency_optimizations_deep.py

@@ -392,10 +392,12 @@ async def test_validator_pre_execution_loop_reverted_to_exact_safety_contract(
     mock_artemis_ctx.data_engine = MagicMock()
 
     node = ValidatorNode(mock_artemis_ctx)
+    # The Validator now talks to the in-process unified action session.
     session = MagicMock()
-    session.call_tool = AsyncMock(
-        return_value=MagicMock(content=[MagicMock(text="ZHVtbXlfZGF0YQ==")])
-    )
+    session.started = True
+    session.screenshot_b64 = AsyncMock(return_value="ZHVtbXlfZGF0YQ==")
+    session.ui_hierarchy = AsyncMock(return_value=[])
+    session.call = AsyncMock()
 
     decisions = json.dumps(
         [
@@ -421,6 +423,10 @@ async def test_validator_pre_execution_loop_reverted_to_exact_safety_contract(
     )
 
     with (
+        patch(
+            "artemis.agents.validator.validator.get_action_session",
+            AsyncMock(return_value=session),
+        ),
         patch.object(
             ValidatorNode, "_get_initial_screenshot", new_callable=AsyncMock
         ) as mock_get_screen,