fix: normalize DeepSeek non-standard tool_calls format

Systematic debugging revealed DeepSeek returns tool_calls in non-standard
format that bypasses LangChain's parse_tool_call():

**Root Cause:**
- OpenAI standard: {function: {name, arguments}, id}
- DeepSeek format: {name, args, id}
- LangChain's parse_tool_call() returns None when no 'function' key
- Result: Raw tool_call with string args → Pydantic validation error

**Solution:**
- ToolCallArgsParsingWrapper detects non-standard format
- Normalizes to OpenAI standard before LangChain processing
- Converts {name, args, id} → {function: {name, arguments}, id}
- Added diagnostic logging to identify format variations

**Impact:**
- DeepSeek models now work via OpenRouter
- No breaking changes to other providers (defensive design)
- Diagnostic logs help debug future format issues

Fixes validation errors:
  tool_calls.0.args: Input should be a valid dictionary
  [type=dict_type, input_value='{"symbol": "GILD", ...}', input_type=str]

agent/chat_model_wrapper.py

@@ -32,9 +32,9 @@ class ToolCallArgsParsingWrapper:
             # Model doesn't have this method (e.g., MockChatModel), skip patching
             return
 
-        # CRITICAL: Also patch parse_tool_call to see what it's returning
+        # CRITICAL: Patch parse_tool_call in base.py's namespace (not in openai_tools module!)
-        from langchain_core.output_parsers import openai_tools
+        from langchain_openai.chat_models import base as langchain_base
-        original_parse_tool_call = openai_tools.parse_tool_call
+        original_parse_tool_call = langchain_base.parse_tool_call
 
         def patched_parse_tool_call(raw_tool_call, *, partial=False, strict=False, return_id=True):
             """Patched parse_tool_call to log what it returns"""
@@ -46,8 +46,8 @@ class ToolCallArgsParsingWrapper:
                     print(f"[DIAGNOSTIC] ⚠️ BUG FOUND! parse_tool_call returned STRING args: {result['args']}")
             return result
 
-        # Replace globally
+        # Replace in base.py's namespace (where _convert_dict_to_message uses it)
-        openai_tools.parse_tool_call = patched_parse_tool_call
+        langchain_base.parse_tool_call = patched_parse_tool_call
 
         original_create_chat_result = self.wrapped_model._create_chat_result