test(openai_compatible): red phase for shared send helper (6 failing tests)

6 failing tests in tests/test_openai_compatible.py that establish the
core behaviors of the new send_openai_compatible() shared helper:

1. test_send_non_streaming_returns_normalized_response: blocking call
   returns text, empty tool_calls, and correct usage token counts
2. test_send_streaming_aggregates_chunks: streaming call aggregates
   deltas into final text and fires stream_callback per chunk
3. test_tool_call_detection_in_response: tool_calls from the response
   are converted to dicts with id/type/function/arguments fields
4. test_vision_multimodal_message: messages with multimodal content
   (text + image_url) are passed through unchanged to the client
5. test_error_classification_429_to_rate_limit: RateLimitError from
   openai SDK is caught and re-raised as ProviderError(kind='rate_limit')
6. test_normalized_response_is_frozen_dataclass: NormalizedResponse is
   a frozen dataclass (FrozenInstanceError on attribute assignment)

All 6 tests fail with ModuleNotFoundError: No module named
'src.openai_compatible' (confirmed via pytest). The implementation file
will be created in the next commit (Green phase).

ProviderError confirmed importable from src.ai_client (no stub needed).

tests/test_openai_compatible.py

@@ -0,0 +1,88 @@
+from unittest.mock import MagicMock
+import pytest
+from src.openai_compatible import (
+ NormalizedResponse,
+ OpenAICompatibleRequest,
+ send_openai_compatible,
+)
+from src.vendor_capabilities import VendorCapabilities, register
+
+@pytest.fixture
+def caps() -> VendorCapabilities:
+ return VendorCapabilities(vendor="test", model="test-model", context_window=8192, cost_input_per_mtok=1.0, cost_output_per_mtok=2.0)
+
+def _mock_completion(text: str = "hello", tool_calls=None, usage_input: int = 10, usage_output: int = 5):
+ m = MagicMock()
+ m.choices = [MagicMock()]
+ m.choices[0].message.content = text
+ m.choices[0].message.tool_calls = tool_calls or []
+ m.usage.prompt_tokens = usage_input
+ m.usage.completion_tokens = usage_output
+ m.usage.prompt_tokens_details = None
+ m.usage.completion_tokens_details = None
+ return m
+
+def test_send_non_streaming_returns_normalized_response(caps: VendorCapabilities) -> None:
+ client = MagicMock()
+ client.chat.completions.create.return_value = _mock_completion("hi", usage_input=20, usage_output=10)
+ request = OpenAICompatibleRequest(messages=[{"role": "user", "content": "ping"}], model="m", max_tokens=100)
+ response = send_openai_compatible(client, request, capabilities=caps)
+ assert response.text == "hi"
+ assert response.tool_calls == []
+ assert response.usage_input_tokens == 20
+ assert response.usage_output_tokens == 10
+
+def test_send_streaming_aggregates_chunks(caps: VendorCapabilities) -> None:
+ client = MagicMock()
+ chunks = [
+  MagicMock(choices=[MagicMock(delta=MagicMock(content="hel", tool_calls=None))]),
+  MagicMock(choices=[MagicMock(delta=MagicMock(content="lo", tool_calls=None))]),
+  MagicMock(choices=[MagicMock(delta=MagicMock(content="", tool_calls=None))], usage=MagicMock(prompt_tokens=15, completion_tokens=5)),
+ ]
+ client.chat.completions.create.return_value = iter(chunks)
+ received: list = []
+ request = OpenAICompatibleRequest(messages=[{"role": "user", "content": "ping"}], model="m", stream=True, stream_callback=received.append)
+ response = send_openai_compatible(client, request, capabilities=caps)
+ assert response.text == "hello"
+ assert received == ["hel", "lo"]
+ assert response.usage_input_tokens == 15
+
+def test_tool_call_detection_in_response(caps: VendorCapabilities) -> None:
+ tool_call = MagicMock()
+ tool_call.id = "call_1"
+ tool_call.function.name = "read_file"
+ tool_call.function.arguments = '{"path": "/tmp/x"}'
+ completion = _mock_completion(text="", tool_calls=[tool_call])
+ client = MagicMock()
+ client.chat.completions.create.return_value = completion
+ request = OpenAICompatibleRequest(messages=[{"role": "user", "content": "ping"}], model="m")
+ response = send_openai_compatible(client, request, capabilities=caps)
+ assert len(response.tool_calls) == 1
+ assert response.tool_calls[0]["function"]["name"] == "read_file"
+ assert response.tool_calls[0]["id"] == "call_1"
+
+def test_vision_multimodal_message(caps: VendorCapabilities) -> None:
+ client = MagicMock()
+ client.chat.completions.create.return_value = _mock_completion("looks like a cat")
+ messages = [{"role": "user", "content": [{"type": "text", "text": "what is this?"}, {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}}]}]
+ request = OpenAICompatibleRequest(messages=messages, model="m")
+ response = send_openai_compatible(client, request, capabilities=caps)
+ sent_messages = client.chat.completions.create.call_args.kwargs["messages"]
+ assert sent_messages[0]["content"] == messages[0]["content"]
+ assert response.text == "looks like a cat"
+
+def test_error_classification_429_to_rate_limit(caps: VendorCapabilities) -> None:
+ from openai import RateLimitError
+ from src.ai_client import ProviderError
+ client = MagicMock()
+ client.chat.completions.create.side_effect = RateLimitError("rate limited", response=MagicMock(status_code=429), body=None)
+ request = OpenAICompatibleRequest(messages=[{"role": "user", "content": "ping"}], model="m")
+ with pytest.raises(ProviderError) as exc_info:
+  send_openai_compatible(client, request, capabilities=caps)
+ assert exc_info.value.kind == "rate_limit"
+
+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)
+ with pytest.raises(FrozenInstanceError):
+  r.text = "y"