Fix research pipeline provider failures

tests/test_backend_pipeline_repairs.py

@@ -0,0 +1,107 @@
+"""Regression tests for the deployed backend research pipeline fixes."""
+
+from __future__ import annotations
+
+import asyncio
+from uuid import uuid4
+
+import httpx
+from unittest.mock import AsyncMock
+
+from nsct.config import AppSettings, AudioConfig, DatabaseConfig, LLMConfig, VisionConfig
+from nsct.orchestration.orchestrator import ResearchOrchestrator
+from nsct.orchestration.state import ResearchRunState
+from nsct.providers.llm import _LLMProviderImpl
+from nsct.providers.metrics import ProviderMetrics
+from nsct.providers.searxng import SearXNGProvider
+
+
+def _config(*, searxng_base_url: str | None = "http://searxng:8080") -> AppSettings:
+    return AppSettings(
+        llm=LLMConfig(base_url="http://llm.example/v1", model="test-model"),
+        vision=VisionConfig(base_url="http://vision.example/v1", model="vision"),
+        audio=AudioConfig(base_url="http://audio.example/v1"),
+        postgres=DatabaseConfig(url="sqlite+aiosqlite://"),
+        searxng_base_url=searxng_base_url,
+    )
+
+
+def test_llm_base_url_does_not_duplicate_existing_v1() -> None:
+    provider = _LLMProviderImpl(_config(), ProviderMetrics())
+    provider._api_key = "test-key"
+    client = provider._create_client()
+    try:
+        assert str(client.base_url) == "http://llm.example/v1/"
+    finally:
+        asyncio.run(client.close())
+
+
+def test_searxng_provider_normalizes_json_results() -> None:
+    async def run() -> None:
+        provider = SearXNGProvider("http://searxng:8080")
+        provider._client = httpx.AsyncClient(
+            transport=httpx.MockTransport(
+                lambda request: httpx.Response(
+                    200,
+                    json={
+                        "results": [
+                            {"url": "https://example.org/a", "title": "A", "content": "Snippet"},
+                            {"url": "mailto:invalid@example.org", "title": "Invalid"},
+                        ]
+                    },
+                )
+            )
+        )
+        try:
+            results = await provider.search("test")
+            assert len(results) == 1
+            assert results[0].provider == "searxng"
+            assert results[0].url == "https://example.org/a"
+            assert results[0].snippet == "Snippet"
+            assert provider._client is not None
+        finally:
+            await provider._client.aclose()
+
+    asyncio.run(run())
+
+
+def test_orchestrator_registers_searxng_provider() -> None:
+    orchestrator = ResearchOrchestrator(_config(), uuid4(), "test")
+    provider = orchestrator._get_multi_search().get_provider("searxng")
+    assert isinstance(provider, SearXNGProvider)
+
+
+def test_pipeline_executes_extracting_between_fetching_and_analyzing() -> None:
+    async def run() -> None:
+        orchestrator = ResearchOrchestrator(_config(), uuid4(), "test")
+        orchestrator._comparison_data = {}
+        for step in ("planning", "searching", "fetching", "extracting", "analyzing", "comparing", "synthesizing"):
+            async def handler(target: str = step) -> dict[str, object]:
+                orchestrator._transition_to(target)
+                return {"success": True, "data": {}}
+
+            setattr(orchestrator, f"_step_{step}", AsyncMock(side_effect=handler))
+
+        result = await orchestrator.run()
+
+        assert result["success"] is True
+        assert orchestrator._step_extracting.await_count == 1
+        assert orchestrator.state is ResearchRunState.COMPLETED
+
+    asyncio.run(run())
+
+
+def test_no_search_provider_marks_run_failed_with_reason() -> None:
+    async def run() -> None:
+        orchestrator = ResearchOrchestrator(_config(searxng_base_url=None), uuid4(), "test")
+        await orchestrator.start()
+        orchestrator._step_planning = AsyncMock(return_value={"success": True, "data": {}})
+
+        result = await orchestrator.run()
+
+        assert result["success"] is False
+        assert result["failed_step"] == "searching"
+        assert "No search provider" in result["error"]
+        assert orchestrator.state is ResearchRunState.FAILED
+
+    asyncio.run(run())