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

tests/test_ai_client_tool_loop.py

@@ -18,6 +18,7 @@ from unittest.mock import MagicMock, patch
 import pytest
 from src.result_types import Result
 from src.openai_compatible import NormalizedResponse, OpenAICompatibleRequest
+from src.openai_schemas import UsageStats
 from src.ai_client import run_with_tool_loop
 from src.vendor_capabilities import VendorCapabilities
 
@@ -28,8 +29,7 @@ def caps() -> VendorCapabilities:
 def _make_normalized_response(text: str = "ok", tool_calls: list[dict[str, Any]] | None = None) -> Result[NormalizedResponse]:
  return Result(data=NormalizedResponse(
   text=text, tool_calls=tool_calls or [],
-  usage_input_tokens=10, usage_output_tokens=5,
-  usage_cache_read_tokens=0, usage_cache_creation_tokens=0,
+  usage=UsageStats(input_tokens=10, output_tokens=5, cache_read_tokens=0, cache_creation_tokens=0),
   raw_response=None,
  ))
 

tests/test_ai_client_tool_loop_builder.py

@@ -8,6 +8,7 @@ from __future__ import annotations
 from typing import Any
 from unittest.mock import MagicMock, patch
 from src.openai_compatible import NormalizedResponse, OpenAICompatibleRequest
+from src.openai_schemas import UsageStats
 from src.ai_client import run_with_tool_loop
 from src.result_types import Result
 from src.vendor_capabilities import VendorCapabilities
@@ -15,8 +16,7 @@ from src.vendor_capabilities import VendorCapabilities
 def _make_normalized_response(text: str = "ok", tool_calls: list[dict[str, Any]] | None = None) -> NormalizedResponse:
  return NormalizedResponse(
   text=text, tool_calls=tool_calls or [],
-  usage_input_tokens=10, usage_output_tokens=5,
-  usage_cache_read_tokens=0, usage_cache_creation_tokens=0,
+  usage=UsageStats(input_tokens=10, output_tokens=5, cache_read_tokens=0, cache_creation_tokens=0),
   raw_response=None,
  )
 

tests/test_ai_client_tool_loop_send_func.py

@@ -7,14 +7,14 @@ from __future__ import annotations
 from typing import Any
 from unittest.mock import MagicMock, patch
 from src.openai_compatible import NormalizedResponse
+from src.openai_schemas import UsageStats
 from src.ai_client import run_with_tool_loop
 from src.vendor_capabilities import VendorCapabilities
 
 def _make_normalized_response(text: str = "ok", tool_calls: list[dict[str, Any]] | None = None) -> NormalizedResponse:
  return NormalizedResponse(
   text=text, tool_calls=tool_calls or [],
-  usage_input_tokens=10, usage_output_tokens=5,
-  usage_cache_read_tokens=0, usage_cache_creation_tokens=0,
+  usage=UsageStats(input_tokens=10, output_tokens=5, cache_read_tokens=0, cache_creation_tokens=0),
   raw_response=None,
  )
 

tests/test_ai_loop_regressions_20260614.py

@@ -19,6 +19,7 @@ from src import ai_client
 from src import thinking_parser
 from src.gui_2 import App
 from src.events import UserRequestEvent
+from src.openai_schemas import UsageStats
 from src.result_types import Result, ErrorInfo, ErrorKind
 
 
@@ -206,10 +207,7 @@ def test_fr3_minimax_thinking_in_returned_text() -> None:
   return Result(data=MagicMock(
    text="The final answer is 42",
    tool_calls=[],
-   usage_input_tokens=0,
-   usage_output_tokens=0,
-   usage_cache_read_tokens=0,
-   usage_cache_creation_tokens=0,
+   usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0),
    raw_response=fake_raw,
   ))
 

tests/test_grok_provider.py

@@ -30,10 +30,11 @@ def test_grok_2_vision_supports_image() -> None:
 def test_grok_web_search_adds_search_parameters_to_extra_body() -> None:
  """caps.web_search=True should populate search_parameters.mode=auto in extra_body."""
  from src import openai_compatible as oc
+ from src.openai_schemas import UsageStats
  captured_kwargs: list[dict] = []
  def _fake_send(client, request, *, capabilities):
   captured_kwargs.append({"extra_body": request.extra_body, "model": request.model})
-  return MagicMock(text="ok", tool_calls=[], usage_input_tokens=0, usage_output_tokens=0, usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=None)
+  return MagicMock(text="ok", tool_calls=[], usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0), raw_response=None)
  with patch.object(oc, "send_openai_compatible", side_effect=_fake_send), \
       patch("src.ai_client._ensure_grok_client", return_value=MagicMock()), \
       patch("src.ai_client._get_deepseek_tools", return_value=[]):
@@ -43,12 +44,13 @@ def test_grok_web_search_adds_search_parameters_to_extra_body() -> None:
 def test_grok_x_search_adds_x_source_to_extra_body() -> None:
  """caps.x_search=True should add sources=[{type:x}] to search_parameters."""
  from src import openai_compatible as oc
+ from src.openai_schemas import UsageStats
  captured_kwargs: list[dict] = []
  def _fake_send(client, request, *, capabilities):
   captured_kwargs.append({"extra_body": request.extra_body})
-  return MagicMock(text="ok", tool_calls=[], usage_input_tokens=0, usage_output_tokens=0, usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=None)
+  return MagicMock(text="ok", tool_calls=[], usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0), raw_response=None)
  with patch.object(oc, "send_openai_compatible", side_effect=_fake_send), \
       patch("src.ai_client._ensure_grok_client", return_value=MagicMock()), \
       patch("src.ai_client._get_deepseek_tools", return_value=[]):
   ai_client._send_grok("system", "user", ".", None, "", False, None, None, None)
- assert captured_kwargs[0]["extra_body"]["search_parameters"]["sources"] == [{"type": "x"}]
+ assert captured_kwargs[0]["extra_body"]["search_parameters"]["sources"] == [{"type": "x"}] 

tests/test_minimax_provider.py

@@ -37,10 +37,11 @@ def test_minimax_credentials_template() -> None:
 def test_minimax_reasoning_extractor_used_when_caps_reasoning_true() -> None:
  """caps.reasoning=True (M2.5/M2.7) should pass the reasoning_extractor to run_with_tool_loop."""
  from src import openai_compatible as oc
+ from src.openai_schemas import UsageStats
  captured_kwargs: list[dict] = []
  def _fake_send(client, request, *, capabilities):
   captured_kwargs.append({"model": request.model})
-  return MagicMock(text="ok", tool_calls=[], usage_input_tokens=0, usage_output_tokens=0, usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=None)
+  return MagicMock(text="ok", tool_calls=[], usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0), raw_response=None)
  from src.vendor_capabilities import register, VendorCapabilities
  register(VendorCapabilities(vendor='minimax', model='MiniMax-M2.5', reasoning=True))
  with patch.object(oc, "send_openai_compatible", side_effect=_fake_send), \
@@ -52,17 +53,18 @@ def test_minimax_reasoning_extractor_used_when_caps_reasoning_true() -> None:
 def test_minimax_reasoning_extractor_omitted_when_caps_reasoning_false() -> None:
  """caps.reasoning=False (M2/M2.1) should NOT pass the reasoning_extractor (avoid useless getattr)."""
  from src import openai_compatible as oc
+ from src.openai_schemas import UsageStats
  from src.vendor_capabilities import register, VendorCapabilities
  register(VendorCapabilities(vendor='minimax', model='MiniMax-M2', reasoning=False))
  captured_kwargs: list[dict] = []
  def _fake_send(client, request, *, capabilities):
   captured_kwargs.append({"model": request.model})
-  return MagicMock(text="ok", tool_calls=[], usage_input_tokens=0, usage_output_tokens=0, usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=None)
+  return MagicMock(text="ok", tool_calls=[], usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0), raw_response=None)
  with patch.object(oc, "send_openai_compatible", side_effect=_fake_send), \
       patch("src.ai_client._ensure_minimax_client", return_value=MagicMock()), \
       patch("src.ai_client._get_deepseek_tools", return_value=[]):
   ai_client._send_minimax("system", "user", ".", None, "", False, None, None, None)
- assert len(captured_kwargs) >= 1
+ assert len(captured_kwargs) >= 1 
 
 def test_minimax_ensure_client_instantiation() -> None:
  """Verify that _ensure_minimax_client instantiates the OpenAI client with correct credentials and base URL."""

tests/test_openai_compatible.py

@@ -86,6 +86,7 @@ def test_error_classification_429_to_rate_limit(caps: VendorCapabilities) -> Non
 
 def test_normalized_response_is_frozen_dataclass() -> None:
  from dataclasses import FrozenInstanceError
- r = NormalizedResponse(text="x", tool_calls=[], usage_input_tokens=0, usage_output_tokens=0, usage_cache_read_tokens=0, usage_cache_creation_tokens=0, raw_response=None)
+ from src.openai_schemas import UsageStats
+ r = NormalizedResponse(text="x", tool_calls=[], usage=UsageStats(input_tokens=0, output_tokens=0, cache_read_tokens=0, cache_creation_tokens=0), raw_response=None)
  with pytest.raises(FrozenInstanceError):
   r.text = "y"