Merge branch 'tier2/phase2_4_5_call_site_completion_20260621' into tier2/code_path_audit_20260607

src/ai_client.py

@@ -2568,6 +2568,7 @@ def _send_grok(md_content: str, user_message: str, base_dir: str,
    Runs synchronously in the caller thread; synchronizes Grok history using _grok_history_lock.
  """
  from src.openai_compatible import OpenAICompatibleRequest, _classify_openai_compatible_error
+ from src.openai_schemas import ChatMessage
  try:
   client = _ensure_grok_client()
   tools: list[Metadata] | None = _get_deepseek_tools() or None
@@ -2584,8 +2585,9 @@ def _send_grok(md_content: str, user_message: str, base_dir: str,
     _grok_history.append({"role": "user", "content": user_content})
   def _build_grok_request(_round_idx: int) -> OpenAICompatibleRequest:
    with _grok_history_lock:
-    messages: list[Metadata] = [{"role": "system", "content": f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"}]
-    messages.extend(_grok_history)
+    history_msgs: list[ChatMessage] = [ChatMessage(role=m["role"], content=m["content"]) for m in _grok_history]
+    messages: list[ChatMessage] = [ChatMessage(role="system", content=f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>")]
+    messages.extend(history_msgs)
    extra_body: Metadata = {}
    if caps.web_search:
     extra_body["search_parameters"] = {"mode": "auto"}
@@ -2653,6 +2655,7 @@ def _send_minimax(md_content: str, user_message: str, base_dir: str,
    Runs synchronously in the caller thread; synchronizes MiniMax history using _minimax_history_lock.
  """
  from src.openai_compatible import OpenAICompatibleRequest
+ from src.openai_schemas import ChatMessage
  try:
   _ensure_minimax_client()
   tools: list[Metadata] | None = _get_deepseek_tools() or None
@@ -2663,8 +2666,9 @@ def _send_minimax(md_content: str, user_message: str, base_dir: str,
    _minimax_history.append({"role": "user", "content": user_message})
   def _build_minimax_request(_round_idx: int) -> OpenAICompatibleRequest:
    with _minimax_history_lock:
-    messages: list[Metadata] = [{"role": "system", "content": f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"}]
-    messages.extend(_minimax_history)
+    history_msgs: list[ChatMessage] = [ChatMessage(role=m["role"], content=m["content"]) for m in _minimax_history]
+    messages: list[ChatMessage] = [ChatMessage(role="system", content=f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>")]
+    messages.extend(history_msgs)
    return OpenAICompatibleRequest(
     messages=messages, model=_model, temperature=_temperature, top_p=_top_p,
     max_tokens=min(_max_tokens, 8192), stream=stream, stream_callback=stream_callback,
@@ -2893,6 +2897,7 @@ def _send_llama(md_content: str, user_message: str, base_dir: str,
    Runs synchronously in the caller thread; synchronizes history using _llama_history_lock.
  """
  from src.openai_compatible import OpenAICompatibleRequest, _classify_openai_compatible_error
+ from src.openai_schemas import ChatMessage
  try:
   if "localhost" in _llama_base_url or "127.0.0.1" in _llama_base_url:
    return _send_llama_native(md_content, user_message, base_dir, file_items, discussion_history, stream, pre_tool_callback, qa_callback, stream_callback, patch_callback)
@@ -2910,8 +2915,9 @@ def _send_llama(md_content: str, user_message: str, base_dir: str,
     _llama_history.append({"role": "user", "content": user_content})
   def _build_llama_request(_round_idx: int) -> OpenAICompatibleRequest:
    with _llama_history_lock:
-    messages: list[Metadata] = [{"role": "system", "content": f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"}]
-    messages.extend(_llama_history)
+    history_msgs: list[ChatMessage] = [ChatMessage(role=m["role"], content=m["content"]) for m in _llama_history]
+    messages: list[ChatMessage] = [ChatMessage(role="system", content=f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>")]
+    messages.extend(history_msgs)
    return OpenAICompatibleRequest(
     messages=messages, model=_model, temperature=_temperature, top_p=_top_p,
     max_tokens=_max_tokens, stream=stream, stream_callback=stream_callback,