feat(tools): introduce plugin-based tool discovery and runtime context protocol

This commit implements a progressive refactoring of the tool system to support
plugin discovery, scoped loading, and protocol-driven runtime context injection.

Key changes:
- Add Tool ABC metadata (tool_name, _scopes) and ToolContext dataclass for
dependency injection.
- Introduce ToolLoader with pkgutil-based builtin discovery and
entry_points-based third-party plugin loading.
- Add scope filtering (core/subagent/memory) so different contexts load
appropriate tool sets.
- Introduce ContextAware protocol and RequestContext dataclass to replace
hardcoded per-tool context injection in AgentLoop.
- Add RuntimeState / MutableRuntimeState protocols to decouple MyTool from
AgentLoop.
- Migrate all built-in tools to declare scopes and implement create()/enabled()
hooks.
- Migrate MessageTool, SpawnTool, CronTool, and MyTool to ContextAware.
- Refactor AgentLoop to use ToolLoader and protocol-driven context injection.
- Refactor SubagentManager to use ToolLoader(scope="subagent") with per-run
FileStates isolation.
- Register all built-in tools via pyproject.toml entry_points.
- Add comprehensive tests for loader scopes, entry_points, ContextAware,
subagent tools, and runtime state sync.

tests/tools/test_message_tool.py

@@ -83,7 +83,8 @@ async def test_message_tool_inherits_metadata_for_same_target() -> None:
 
     tool = MessageTool(send_callback=_send)
     slack_meta = {"slack": {"thread_ts": "111.222", "channel_type": "channel"}}
-    tool.set_context("slack", "C123", metadata=slack_meta)
+    from nanobot.agent.tools.context import RequestContext
+    tool.set_context(RequestContext(channel="slack", chat_id="C123", metadata=slack_meta))
 
     await tool.execute(content="thread reply")
 
@@ -98,10 +99,13 @@ async def test_message_tool_does_not_inherit_metadata_for_cross_target() -> None
         sent.append(msg)
 
     tool = MessageTool(send_callback=_send)
+    from nanobot.agent.tools.context import RequestContext
     tool.set_context(
-        "slack",
-        "C123",
-        metadata={"slack": {"thread_ts": "111.222", "channel_type": "channel"}},
+        RequestContext(
+            channel="slack",
+            chat_id="C123",
+            metadata={"slack": {"thread_ts": "111.222", "channel_type": "channel"}},
+        ),
     )
 
     await tool.execute(content="channel reply", channel="slack", chat_id="C999")