refactor: remove _nr_to_assistant_message shim + fix flush_memories guard

NormalizedResponse and ToolCall now have backward-compat properties
so the agent loop can read them directly without the shim:

  ToolCall: .type, .function (returns self), .call_id, .response_item_id
  NormalizedResponse: .reasoning_content, .reasoning_details,
                      .codex_reasoning_items

This eliminates the 35-line shim and its 4 call sites in run_agent.py.

Also changes flush_memories guard from hasattr(response, 'choices')
to self.api_mode in ('chat_completions', 'bedrock_converse') so it
works with raw boto3 dicts too.

WS1 items 3+4 of Cycle 2 (#14418).

agent/anthropic_adapter.py

@@ -17,7 +17,6 @@ import os
 from pathlib import Path
 
 from hermes_constants import get_hermes_home
-from types import SimpleNamespace
 from typing import Any, Dict, List, Optional, Tuple
 from utils import normalize_proxy_env_vars
 
@@ -1599,64 +1598,4 @@ def build_anthropic_kwargs(
     return kwargs
 
 
-def normalize_anthropic_response(
-    response,
-    strip_tool_prefix: bool = False,
-) -> "NormalizedResponse":
-    """Normalize Anthropic response to NormalizedResponse.
 
-    Returns a NormalizedResponse with content, tool_calls, finish_reason,
-    reasoning, and provider_data fields.
-
-    When *strip_tool_prefix* is True, removes the ``mcp_`` prefix that was
-    added to tool names for OAuth Claude Code compatibility.
-    """
-    from agent.transports.types import NormalizedResponse, ToolCall
-
-    text_parts = []
-    reasoning_parts = []
-    reasoning_details = []
-    tool_calls = []
-
-    for block in response.content:
-        if block.type == "text":
-            text_parts.append(block.text)
-        elif block.type == "thinking":
-            reasoning_parts.append(block.thinking)
-            block_dict = _to_plain_data(block)
-            if isinstance(block_dict, dict):
-                reasoning_details.append(block_dict)
-        elif block.type == "tool_use":
-            name = block.name
-            if strip_tool_prefix and name.startswith(_MCP_TOOL_PREFIX):
-                name = name[len(_MCP_TOOL_PREFIX):]
-            tool_calls.append(
-                ToolCall(
-                    id=block.id,
-                    name=name,
-                    arguments=json.dumps(block.input),
-                )
-            )
-
-    stop_reason_map = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
-    }
-    finish_reason = stop_reason_map.get(response.stop_reason, "stop")
-
-    provider_data = {}
-    if reasoning_details:
-        provider_data["reasoning_details"] = reasoning_details
-
-    return NormalizedResponse(
-        content="\n".join(text_parts) if text_parts else None,
-        tool_calls=tool_calls or None,
-        finish_reason=finish_reason,
-        reasoning="\n\n".join(reasoning_parts) if reasoning_parts else None,
-        usage=None,
-        provider_data=provider_data or None,
-    )

agent/auxiliary_client.py

@@ -616,20 +616,11 @@ class _AnthropicCompletionsAdapter:
             response, strip_tool_prefix=self._is_oauth
         )
 
-        # Map NormalizedResponse → OpenAI-compatible SimpleNamespace
-        tool_calls = None
-        if _nr.tool_calls:
-            tool_calls = [
-                SimpleNamespace(
-                    id=tc.id,
-                    type="function",
-                    function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
-                )
-                for tc in _nr.tool_calls
-            ]
+        # ToolCall already duck-types as OpenAI shape (.type, .function.name,
+        # .function.arguments) via properties, so no wrapping needed.
         assistant_message = SimpleNamespace(
             content=_nr.content,
-            tool_calls=tool_calls,
+            tool_calls=_nr.tool_calls,
             reasoning=_nr.reasoning,
         )
         finish_reason = _nr.finish_reason

agent/transports/anthropic.py

@@ -78,12 +78,55 @@ class AnthropicTransport(ProviderTransport):
     def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
         """Normalize Anthropic response to NormalizedResponse.
 
-        Delegates directly to the adapter which now returns NormalizedResponse.
+        Parses content blocks (text, thinking, tool_use), maps stop_reason
+        to OpenAI finish_reason, and collects reasoning_details in provider_data.
         """
-        from agent.anthropic_adapter import normalize_anthropic_response
+        import json
+        from agent.anthropic_adapter import _to_plain_data
+        from agent.transports.types import ToolCall
 
         strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
-        return normalize_anthropic_response(response, strip_tool_prefix)
+        _MCP_PREFIX = "mcp_"
+
+        text_parts = []
+        reasoning_parts = []
+        reasoning_details = []
+        tool_calls = []
+
+        for block in response.content:
+            if block.type == "text":
+                text_parts.append(block.text)
+            elif block.type == "thinking":
+                reasoning_parts.append(block.thinking)
+                block_dict = _to_plain_data(block)
+                if isinstance(block_dict, dict):
+                    reasoning_details.append(block_dict)
+            elif block.type == "tool_use":
+                name = block.name
+                if strip_tool_prefix and name.startswith(_MCP_PREFIX):
+                    name = name[len(_MCP_PREFIX):]
+                tool_calls.append(
+                    ToolCall(
+                        id=block.id,
+                        name=name,
+                        arguments=json.dumps(block.input),
+                    )
+                )
+
+        finish_reason = self._STOP_REASON_MAP.get(response.stop_reason, "stop")
+
+        provider_data = {}
+        if reasoning_details:
+            provider_data["reasoning_details"] = reasoning_details
+
+        return NormalizedResponse(
+            content="\n".join(text_parts) if text_parts else None,
+            tool_calls=tool_calls or None,
+            finish_reason=finish_reason,
+            reasoning="\n\n".join(reasoning_parts) if reasoning_parts else None,
+            usage=None,
+            provider_data=provider_data or None,
+        )
 
     def validate_response(self, response: Any) -> bool:
         """Check Anthropic response structure is valid.

agent/transports/types.py

@@ -37,6 +37,30 @@ class ToolCall:
     arguments: str  # JSON string
     provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
 
+    # ── Backward compatibility ──────────────────────────────────
+    # The agent loop reads tc.function.name / tc.function.arguments
+    # throughout run_agent.py (45+ sites).  These properties let
+    # NormalizedResponse pass through without the _nr_to_assistant_message
+    # shim, while keeping ToolCall's canonical fields flat.
+    @property
+    def type(self) -> str:
+        return "function"
+
+    @property
+    def function(self) -> "ToolCall":
+        """Return self so tc.function.name / tc.function.arguments work."""
+        return self
+
+    @property
+    def call_id(self) -> Optional[str]:
+        """Codex call_id from provider_data, accessed via getattr by _build_assistant_message."""
+        return (self.provider_data or {}).get("call_id")
+
+    @property
+    def response_item_id(self) -> Optional[str]:
+        """Codex response_item_id from provider_data."""
+        return (self.provider_data or {}).get("response_item_id")
+
 
 @dataclass
 class Usage:
@@ -70,6 +94,24 @@ class NormalizedResponse:
     usage: Optional[Usage] = None
     provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
 
+    # ── Backward compatibility ──────────────────────────────────
+    # The shim _nr_to_assistant_message() mapped these from provider_data.
+    # These properties let NormalizedResponse pass through directly.
+    @property
+    def reasoning_content(self) -> Optional[str]:
+        pd = self.provider_data or {}
+        return pd.get("reasoning_content")
+
+    @property
+    def reasoning_details(self):
+        pd = self.provider_data or {}
+        return pd.get("reasoning_details")
+
+    @property
+    def codex_reasoning_items(self):
+        pd = self.provider_data or {}
+        return pd.get("codex_reasoning_items")
+
 
 # ---------------------------------------------------------------------------
 # Factory helpers