refactor(schemas): remove NormalizedResponse backward-compat __init__; use canonical API

src/ai_client.py

@@ -2025,6 +2025,7 @@ def _send_gemini_cli(md_content: str, user_message: str, base_dir: str,
  stream_callback: Optional[Callable[[str], None]] = None,
  patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> Result[str]:
  from src.openai_compatible import OpenAICompatibleRequest, NormalizedResponse
+ from src.openai_schemas import UsageStats
  """
   [C: src/ai_server.py:_handle_send]
   Functional Purpose: Sends requests to Gemini via the headless Gemini CLI subprocess adapter.
@@ -2051,7 +2052,7 @@ def _send_gemini_cli(md_content: str, user_message: str, base_dir: str,
 
   def _send(r_idx: int) -> NormalizedResponse:
    if adapter is None:
-    return NormalizedResponse(text="(adapter unavailable)", tool_calls=[], usage_input_tokens=0, usage_output_tokens=0, usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=None)
+    return NormalizedResponse(text="(adapter unavailable)", tool_calls=[], usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0), raw_response=None)
    send_result = _send_cli_round_result(r_idx, adapter, payload, safety_settings, sys_instr, stream_callback)
    if not send_result.ok:
     raise cast(Exception, send_result.errors[0].original) from None
@@ -2085,7 +2086,7 @@ def _send_gemini_cli(md_content: str, user_message: str, base_dir: str,
       "kind": "history_add",
       "payload": {"role": "AI", "content": txt}
      })
-   return NormalizedResponse(text=txt, tool_calls=calls, usage_input_tokens=usage.get("prompt_tokens", 0), usage_output_tokens=usage.get("completion_tokens", 0), usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=resp_data)
+   return NormalizedResponse(text=txt, tool_calls=calls, usage=UsageStats(input_tokens=usage.get("prompt_tokens", 0), output_tokens=usage.get("completion_tokens", 0), cache_read_tokens=0, cache_creation_tokens=0), raw_response=resp_data)
 
   def _pre_dispatch(r_idx: int, calls: list[Metadata]) -> list[Metadata]:
    nonlocal payload, cumulative_tool_bytes, file_items
@@ -2569,7 +2570,7 @@ 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
+ from src.openai_schemas import ChatMessage, UsageStats
  try:
   client = _ensure_grok_client()
   tools: list[Metadata] | None = _get_deepseek_tools() or None

src/openai_schemas.py

@@ -16,7 +16,7 @@ CONVENTION: 1-space indentation. NO COMMENTS.
 """
 from __future__ import annotations
 
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import Any, Callable, Optional
 
 from src.type_aliases import JsonValue
@@ -72,35 +72,12 @@ class UsageStats:
  cache_creation_tokens: int = 0
 
 
-@dataclass(frozen=True, init=False)
+@dataclass(frozen=True)
 class NormalizedResponse:
  text: str
- tool_calls: tuple[ToolCall, ...]
- usage: UsageStats
- raw_response: Any
-
- def __init__(
-  self,
-  text: str,
-  tool_calls: tuple[ToolCall, ...] = (),
-  usage: UsageStats | None = None,
-  raw_response: Any = None,
-  usage_input_tokens: int | None = None,
-  usage_output_tokens: int | None = None,
-  usage_cache_read_tokens: int | None = None,
-  usage_cache_creation_tokens: int | None = None,
- ) -> None:
-  if usage is None:
-   usage = UsageStats(
-    input_tokens=usage_input_tokens if usage_input_tokens is not None else 0,
-    output_tokens=usage_output_tokens if usage_output_tokens is not None else 0,
-    cache_read_tokens=usage_cache_read_tokens if usage_cache_read_tokens is not None else 0,
-    cache_creation_tokens=usage_cache_creation_tokens if usage_cache_creation_tokens is not None else 0,
-   )
-  object.__setattr__(self, "text", text)
-  object.__setattr__(self, "tool_calls", tool_calls)
-  object.__setattr__(self, "usage", usage)
-  object.__setattr__(self, "raw_response", raw_response)
+ tool_calls: tuple[ToolCall, ...] = ()
+ usage: UsageStats = field(default_factory=lambda: UsageStats(input_tokens=0, output_tokens=0))
+ raw_response: Any = None
 
  def to_legacy_dict(self) -> JsonValue:
   return {