feat(agent): mid-turn message injection for responsive follow-ups (#2985)

* feat(agent): add mid-turn message injection for responsive follow-ups

Allow user messages sent during an active agent turn to be injected
into the running LLM context instead of being queued behind a
per-session lock. Inspired by Claude Code's mid-turn queue drain
mechanism (query.ts:1547-1643).

Key design decisions:
- Messages are injected as natural user messages between iterations,
  no tool cancellation or special system prompt needed
- Two drain checkpoints: after tool execution and after final LLM
  response ("last-mile" to prevent dropping late arrivals)
- Bounded by MAX_INJECTION_CYCLES (5) to prevent consuming the
  iteration budget on rapid follow-ups
- had_injections flag bypasses _sent_in_turn suppression so follow-up
  responses are always delivered

Closes #1609

* fix(agent): harden mid-turn injection with streaming fix, bounded queue, and message safety

- Fix streaming protocol violation: Checkpoint 2 now checks for injections
  BEFORE calling on_stream_end, passing resuming=True when injections found
  so streaming channels (Feishu) don't prematurely finalize the card
- Bound pending queue to maxsize=20 with QueueFull handling
- Add warning log when injection batch exceeds _MAX_INJECTIONS_PER_TURN
- Re-publish leftover queue messages to bus in _dispatch finally block to
  prevent silent message loss on early exit (max_iterations, tool_error, cancel)
- Fix PEP 8 blank line before dataclass and logger.info indentation
- Add 12 new tests covering drain, checkpoints, cycle cap, queue routing,
  cleanup, and leftover re-publish

tests/agent/test_hook_composite.py

@@ -307,7 +307,7 @@ async def test_agent_loop_extra_hook_receives_calls(tmp_path):
     )
     loop.tools.get_definitions = MagicMock(return_value=[])
 
-    content, tools_used, messages, _ = await loop._run_agent_loop(
+    content, tools_used, messages, _, _ = await loop._run_agent_loop(
         [{"role": "user", "content": "hi"}]
     )
 
@@ -331,7 +331,7 @@ async def test_agent_loop_extra_hook_error_isolation(tmp_path):
     )
     loop.tools.get_definitions = MagicMock(return_value=[])
 
-    content, _, _, _ = await loop._run_agent_loop(
+    content, _, _, _, _ = await loop._run_agent_loop(
         [{"role": "user", "content": "hi"}]
     )
 
@@ -373,7 +373,7 @@ async def test_agent_loop_no_hooks_backward_compat(tmp_path):
     loop.tools.execute = AsyncMock(return_value="ok")
     loop.max_iterations = 2
 
-    content, tools_used, _, _ = await loop._run_agent_loop([])
+    content, tools_used, _, _, _ = await loop._run_agent_loop([])
     assert content == (
         "I reached the maximum number of tool call iterations (2) "
         "without completing the task. You can try breaking the task into smaller steps."