refactor(ai_client): migrate _send_deepseek history loop to ChatMessage (Phase 5 part 1)

Phase 5: ChatMessage (part 1)
Before: 6 .get('role'/'content'/'tool_calls'/'tool_call_id') sites in _send_deepseek
After:  0
Delta:  -6

Migrates _send_deepseek's history transformation loop from
dict-style access to ChatMessage direct field access:

  msg = _ChatMessage.from_dict(msg_raw)
  msg.role           (was msg.get('role'))
  msg.content        (was msg.get('content'))
  msg.tool_calls     (was msg.get('tool_calls') / msg['tool_calls'])
  msg.tool_call_id   (was msg.get('tool_call_id'))

The api_msg dict (output for the DeepSeek API) is constructed via
direct field access. The tool_calls list is converted to dicts via
tc.to_dict() (preserves the existing API payload format).

Notes:
- msg_raw.get('reasoning_content') is preserved as-is because
  reasoning_content is NOT a ChatMessage field.
- Local import 'from src.openai_schemas import ChatMessage as _ChatMessage'
  follows the existing pattern in this file (lazy imports inside functions).

Tests: 36/36 pass (test_ai_client_result, test_ai_client_tool_loop,
test_deepseek_provider, test_openai_schemas).

src/ai_client.py

@@ -2202,29 +2202,26 @@ def _send_deepseek(md_content: str, user_message: str, base_dir: str,
     current_api_messages.append(sys_msg)
    
    with history.lock:
-    for i, msg in enumerate(history):
+    from src.openai_schemas import ChatMessage as _ChatMessage
-     # Create a clean copy of the message for the API
+    for i, msg_raw in enumerate(history):
-     role = msg.get("role")
+     msg = _ChatMessage.from_dict(msg_raw)
-     api_msg = {"role": role}
+     api_msg = {"role": msg.role}
      
-     content = msg.get("content")
+     content = msg.content
      if i == 0 and is_reasoner:
-      # Prepend system instructions to the first user message for R1
       content = f"System Instructions:\n{_get_combined_system_prompt()}\n\nContext:\n{md_content}\n\n---\n\n{content}"
      
-     if role == "assistant":
+     if msg.role == "assistant":
-      # OpenAI/DeepSeek: content MUST be a string if tool_calls is absent
+      if msg.tool_calls:
-      # If tool_calls is present, content can be null
-      if msg.get("tool_calls"):
        api_msg["content"] = content or None
-       api_msg["tool_calls"] = msg["tool_calls"]
+       api_msg["tool_calls"] = [tc.to_dict() for tc in msg.tool_calls]
       else:
        api_msg["content"] = content or ""
-      if msg.get("reasoning_content"):
+      if msg_raw.get("reasoning_content"):
-       api_msg["reasoning_content"] = msg["reasoning_content"]
+       api_msg["reasoning_content"] = msg_raw["reasoning_content"]
-     elif role == "tool":
+     elif msg.role == "tool":
       api_msg["content"] = content or ""
-      api_msg["tool_call_id"] = msg.get("tool_call_id")
+      api_msg["tool_call_id"] = msg.tool_call_id
      else:
       api_msg["content"] = content or ""