refactor(ai_client,openai_schemas): migrate API response + _repair_minimax (Phase 5 part 2)

Phase 5: ChatMessage (part 2)
Before: 6 .get('content'/'role'/'tool_calls'/'tool_call_id') sites
After:  0
Delta:  -6

Migrates:
1. _send_deepseek API response parsing (lines 2321-2324):
   - message.get('content', '')        -> message.content or ''
   - message.get('tool_calls', [])     -> [tc.to_dict() for tc in message.tool_calls]
   - message.get('reasoning_content')  -> kept as choice.get('message', {}).get('reasoning_content', '')
     (reasoning_content is NOT a ChatMessage field)

2. _repair_minimax_history generator (line 2454):
   - m.get('role') == 'tool'           -> _CM.from_dict(m).role == 'tool'
   - m.get('tool_call_id')             -> _CM.from_dict(m).tool_call_id
   Used inline conversion because the generator iterates over a
   dict list and reads 2 fields. Inline conversion avoids an
   intermediate list comprehension.

openai_schemas.py:
- ChatMessage.from_dict() now provides defaults for required fields
  ('role' -> 'assistant', 'content' -> '') when the input dict is
  missing them. This handles the case where DeepSeek's API returns
  an empty {} for 'message' (e.g., finish_reason='length' with no
  content). Without this default, ChatMessage.__init__() raises
  TypeError.

Tests: 46/46 pass (test_ai_client_result, test_ai_client_tool_loop,
test_deepseek_provider, test_openai_schemas, test_minimax_provider).

src/ai_client.py

@@ -2318,10 +2318,11 @@ def _send_deepseek(md_content: str, user_message: str, base_dir: str,
      _append_comms("IN", "response", {"round": round_idx, "text": "(No choices returned)", "usage": response_data.get("usage", {})})
      break
     choice = choices[0]
-    message = choice.get("message", {})
-    assistant_text = message.get("content", "")
-    tool_calls_raw = message.get("tool_calls", [])
-    reasoning_content = message.get("reasoning_content", "")
+    from src.openai_schemas import ChatMessage as _CM
+    message = _CM.from_dict(choice.get("message", {}))
+    assistant_text = message.content or ""
+    tool_calls_raw = [tc.to_dict() for tc in message.tool_calls] if message.tool_calls else []
+    reasoning_content = choice.get("message", {}).get("reasoning_content", "")
     finish_reason = choice.get("finish_reason", "stop")
     usage = response_data.get("usage", {})
 
@@ -2451,7 +2452,8 @@ def _repair_minimax_history(history: list[Metadata]) -> None:
   elif isinstance(tc, dict) and tc.get("id"): call_ids.append(tc["id"])
  
  for cid in call_ids:
-  already_has = any(m.get("role") == "tool" and m.get("tool_call_id") == cid for m in history[-len(call_ids)-1:])
+  from src.openai_schemas import ChatMessage as _CM
+  already_has = any(_CM.from_dict(m).role == "tool" and _CM.from_dict(m).tool_call_id == cid for m in history[-len(call_ids)-1:])
   if not already_has:
    history.append({
      "role":         "tool",

src/openai_schemas.py

@@ -78,7 +78,12 @@ class ChatMessage:
   tool_calls = None
   if raw_tool_calls is not None:
    tool_calls = tuple(ToolCall.from_dict(tc) for tc in raw_tool_calls)
-  return cls(**{**_from_dict_filter(cls, data), "tool_calls": tool_calls})
+  filtered = _from_dict_filter(cls, data)
+  if "role" not in filtered:
+   filtered["role"] = "assistant"
+  if "content" not in filtered:
+   filtered["content"] = ""
+  return cls(**{**filtered, "tool_calls": tool_calls})
 
 
 @dataclass(frozen=True)