tatlock/tests/ollama/test_provider.py

"""
Tests for TatlockOllamaProvider configuration and wiring.

Every assertion here goes through `provider.client` — the property
pydantic_ai actually reads. The previous version asserted on
`_openai_client`, a lookalike attribute nobody read, and stayed green
for the whole period the sanitizer was bypassed in production (T-6):
a test whose subject is not the real thing cannot fail for the real
reason.
"""

import pytest

from src.core.config import config
from src.ollama import provider as provider_module
from src.ollama.provider import (
    TatlockOllamaProvider,
    _parent_chat,
    _sanitize_messages,
    _SanitizedAsyncOpenAI,
    _SanitizedCompletions,
)


@pytest.mark.unit
class TestClientWiring:
    """The sanitized client must be the one the provider serves (T-6)."""

    def test_provider_serves_the_sanitized_client(self):
        provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")

        assert isinstance(provider.client, _SanitizedAsyncOpenAI)

    def test_the_full_chain_reaches_completions(self):
        # Walks provider.client -> sanitized chat -> parent lookup ->
        # completions. Under openai's cached_property `chat`, the old
        # hardcoded `.fget` access raised AttributeError right here.
        provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")

        assert provider.client.chat.completions is not None

    def test_parent_lookup_survives_either_descriptor_shape(self):
        from openai import AsyncOpenAI

        descriptor = AsyncOpenAI.__dict__["chat"]
        assert hasattr(descriptor, "func") or hasattr(
            descriptor, "fget"
        ), "AsyncOpenAI.chat exposes neither getter; _parent_chat needs updating"
        client = _SanitizedAsyncOpenAI(base_url="http://localhost:11434/v1")
        parent = _parent_chat(client)
        assert parent is not None
        assert (
            type(parent).__name__ != "_SanitizedChat"
        ), "parent lookup must not recurse into the override"


@pytest.mark.unit
class TestProviderTimeout:
    """Timeout configuration on the client the provider actually serves."""

    def test_openai_client_timeout_from_config(self):
        provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")

        assert provider.client.timeout == float(config.OLLAMA_TIMEOUT)

    def test_timeout_is_not_sdk_default(self):
        provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")

        # The OpenAI SDK defaults to 600s; the configured cap must win
        assert provider.client.timeout < 600


@pytest.mark.unit
class TestMessageSanitization:
    """Null content sanitization for Ollama compatibility."""

    def test_null_content_with_tool_calls_becomes_empty_string(self):
        messages = [
            {
                "role": "assistant",
                "content": None,
                "tool_calls": [{"id": "call_1", "type": "function"}],
            }
        ]

        sanitized = _sanitize_messages(messages)

        assert sanitized[0]["content"] == ""

    def test_regular_messages_unchanged(self):
        messages = [
            {"role": "user", "content": "Hello"},
            {"role": "assistant", "content": "Good day, sir."},
        ]

        assert _sanitize_messages(messages) == messages


class _StubLogger:
    def __init__(self):
        self.calls = []

    def info(self, event, **kwargs):
        self.calls.append(("info", event, kwargs))

    def warning(self, event, **kwargs):
        self.calls.append(("warning", event, kwargs))


class _BusyResponse:
    def __init__(self):
        self.model_extra = {
            "balancing": [{"parked": "librarian"}],
            "compaction_due": True,
        }


class _QuietResponse:
    def __init__(self):
        self.model_extra = {"balancing": [], "compaction_due": False}


@pytest.mark.unit
class TestWrapperSignals:
    """The wrapper's body signals must not pass silently (T-4/T-6).

    Read from the parsed body's model_extra: an httpx event-hook
    variant demonstrably never fires under the openai SDK.
    """

    def test_busy_response_logs_balancing_and_compaction(self, monkeypatch):
        stub = _StubLogger()
        monkeypatch.setattr(provider_module, "logger", stub)

        provider_module._log_wrapper_signals(_BusyResponse())

        assert any(kind == "info" and event == "backend_balancing" for kind, event, _ in stub.calls)
        assert any(kind == "warning" for kind, _, _ in stub.calls)

    def test_quiet_response_logs_nothing(self, monkeypatch):
        stub = _StubLogger()
        monkeypatch.setattr(provider_module, "logger", stub)

        provider_module._log_wrapper_signals(_QuietResponse())

        assert stub.calls == []

    async def test_create_surfaces_the_signals(self, monkeypatch):
        # The read must sit in the request path, not merely exist:
        # removing the call from create() has to fail this test.
        stub = _StubLogger()
        monkeypatch.setattr(provider_module, "logger", stub)

        class FakeOriginal:
            async def create(self, **kwargs):
                return _BusyResponse()

        completions = _SanitizedCompletions(FakeOriginal())
        await completions.create(messages=[{"role": "user", "content": "hi"}])

        assert any(event == "backend_balancing" for _, event, _ in stub.calls)