refactor(agent): simplify subagent concurrency with rejection over semaphore

Replace the asyncio.Semaphore queueing approach with a simple count
check in SpawnTool.execute(). When the concurrency limit is reached,
the tool returns an error string so the agent can perceive the reason
and adjust its behavior instead of silently queueing.

- Remove max_concurrent_subagents parameter threading through
  AgentLoop, commands.py, and nanobot.py
- SubagentManager reads the limit directly from AgentDefaults
- SpawnTool checks get_running_count() before calling spawn()
- Simplify tests to verify rejection behavior

tests/agent/tools/test_subagent_tools.py

@@ -93,6 +93,75 @@ async def test_subagent_uses_configured_max_iterations(tmp_path):
     mgr.runner.run.assert_awaited_once()
 
 
+@pytest.mark.asyncio
+async def test_spawn_tool_rejects_when_at_concurrency_limit(tmp_path):
+    """SpawnTool should return an error string when the concurrency limit is reached."""
+    from nanobot.agent.subagent import SubagentManager
+    from nanobot.agent.tools.spawn import SpawnTool
+    from nanobot.bus.queue import MessageBus
+
+    bus = MessageBus()
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+    mgr = SubagentManager(
+        provider=provider,
+        workspace=tmp_path,
+        bus=bus,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    )
+    mgr._announce_result = AsyncMock()
+
+    # Block the first subagent so it stays "running"
+    release = asyncio.Event()
+
+    async def fake_run(spec):
+        await release.wait()
+        return SimpleNamespace(
+            stop_reason="done",
+            final_content="done",
+            error=None,
+            tool_events=[],
+        )
+
+    mgr.runner.run = AsyncMock(side_effect=fake_run)
+
+    tool = SpawnTool(mgr)
+    tool.set_context("test", "c1", "test:c1")
+
+    # First spawn succeeds
+    result = await tool.execute(task="first task")
+    assert "started" in result
+
+    # Second spawn should be rejected (default limit is 1)
+    result = await tool.execute(task="second task")
+    assert "Cannot spawn subagent" in result
+    assert "concurrency limit reached" in result
+
+    # Release the first subagent
+    release.set()
+    # Allow cleanup
+    await asyncio.gather(*mgr._running_tasks.values(), return_exceptions=True)
+
+
+def test_subagent_default_max_concurrent_matches_agent_defaults(tmp_path):
+    """Direct SubagentManager construction should use the agent default concurrency limit."""
+    from nanobot.agent.subagent import SubagentManager
+    from nanobot.bus.queue import MessageBus
+
+    bus = MessageBus()
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+
+    mgr = SubagentManager(
+        provider=provider,
+        workspace=tmp_path,
+        bus=bus,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    )
+
+    assert mgr.max_concurrent_subagents == AgentDefaults().max_concurrent_subagents
+
+
 def test_subagent_default_max_iterations_matches_agent_defaults(tmp_path):
     """Direct SubagentManager construction should use the agent default limit."""
     from nanobot.agent.subagent import SubagentManager

tests/test_tool_contextvars.py

@@ -49,6 +49,11 @@ async def test_spawn_tool_keeps_task_local_context() -> None:
     release = asyncio.Event()
 
     class _Manager:
+        max_concurrent_subagents = 1
+
+        def get_running_count(self) -> int:
+            return 0
+
         async def spawn(
             self,
             *,
@@ -156,6 +161,11 @@ async def test_spawn_tool_basic_set_context_and_execute() -> None:
     seen: list[tuple[str, str, str]] = []
 
     class _Manager:
+        max_concurrent_subagents = 1
+
+        def get_running_count(self) -> int:
+            return 0
+
         async def spawn(
             self,
             *,
@@ -183,6 +193,11 @@ async def test_spawn_tool_default_values_without_set_context() -> None:
     seen: list[tuple[str, str, str]] = []
 
     class _Manager:
+        max_concurrent_subagents = 1
+
+        def get_running_count(self) -> int:
+            return 0
+
         async def spawn(
             self,
             *,