Method test_full_pipeline

tests/test_compiler.py:1151–1221

(self, tmp_path)

class TestCompileShortDoc:
    @pytest.mark.asyncio
    async def test_full_pipeline(self, tmp_path):
        # Setup KB structure
        wiki = tmp_path / "wiki"
        (wiki / "sources").mkdir(parents=True)
        (wiki / "summaries").mkdir(parents=True)
        (wiki / "concepts").mkdir(parents=True)
        (wiki / "index.md").write_text(
            "# Index\n\n## Documents\n\n## Concepts\n\n## Explorations\n",
            encoding="utf-8",
        )
        source_path = wiki / "sources" / "test-doc.md"
        source_path.write_text("# Test Doc\n\nSome content about transformers.", encoding="utf-8")
        (tmp_path / ".openkb").mkdir()
        (tmp_path / "raw").mkdir()
        (tmp_path / "raw" / "test-doc.pdf").write_bytes(b"fake")

        summary_response = json.dumps(
            {
                "description": "Discusses transformers",
                "content": "# Summary\n\nThis document discusses transformers.",
            }
        )
        concepts_list_response = json.dumps(
            {
                "create": [{"name": "transformer", "title": "Transformer"}],
                "update": [],
                "related": [],
            }
        )
        # The rewrite step (third sync call) returns raw Markdown.
        summary_rewrite_response = "# Summary\n\nThis document discusses [[concepts/transformer]]."
        concept_page_response = json.dumps(
            {
                "brief": "NN architecture using self-attention",
                "content": "# Transformer\n\nA neural network architecture.",
            }
        )

        with patch("openkb.agent.compiler.litellm") as mock_litellm:
            mock_litellm.completion = MagicMock(
                side_effect=_mock_completion(
                    [
                        summary_response,
                        concepts_list_response,
                        summary_rewrite_response,
                    ]
                )
            )
            mock_litellm.acompletion = AsyncMock(
                side_effect=_mock_acompletion([concept_page_response])
            )
            await compile_short_doc("test-doc", source_path, tmp_path, "gpt-4o-mini")

        # Verify summary written
        summary_path = wiki / "summaries" / "test-doc.md"
        assert summary_path.exists()
        summary_text = summary_path.read_text()
        assert 'full_text: "sources/test-doc.md"' in summary_text