фиксирую состояние

tests/unit_tests/rag/test_docs_indexing_pipeline.py

@@ -1,4 +1,8 @@
+import logging
+
 from app.core.rag.contracts.enums import RagLayer
+from app.core.rag.indexing.docs.chunkers.markdown_chunker import SectionChunk
+from app.core.rag.indexing.docs.integration_extractor import DocsIntegrationExtractor
 from app.core.rag.indexing.docs.pipeline import DocsIndexingPipeline
 
 
@@ -153,3 +157,150 @@ Create invoice
     assert integration_doc.metadata["target"] == "db.billing.invoices"
     assert integration_doc.metadata["target_type"] == "db"
     assert integration_doc.metadata["details"]["transaction"] == "required"
+
+
+def test_docs_integration_extractor_keeps_valid_blocks() -> None:
+    extractor = DocsIntegrationExtractor()
+    sections = [
+        SectionChunk(
+            section_path="Details > Интеграции > Billing DB",
+            section_title="Billing DB",
+            content=(
+                "- target: db.billing.invoices\n"
+                "- target_type: db\n"
+                "- direction: outbound\n"
+                "- interaction: writes\n"
+                "- via: invoice repository\n"
+                "- purpose: persist created invoices\n"
+                "- details:\n"
+                "  - transaction: required\n"
+                "  - tables:\n"
+                "      - invoices\n"
+                "      - invoice_items\n"
+            ),
+            order=0,
+        )
+    ]
+
+    records = extractor.extract(sections, path="docs/billing/create_invoice.md")
+
+    assert len(records) == 1
+    assert records[0].target == "db.billing.invoices"
+    assert records[0].details["transaction"] == "required"
+    assert records[0].details["tables"] == ["invoices", "invoice_items"]
+
+
+def test_docs_integration_extractor_soft_fails_on_markdown_like_yaml(caplog) -> None:
+    extractor = DocsIntegrationExtractor()
+    sections = [
+        SectionChunk(
+            section_path="Details > Интеграции > Runtime health provider",
+            section_title="Runtime health provider",
+            content=(
+                "- target: runtime.health_provider\n"
+                "- target_type: service\n"
+                "- direction: outbound\n"
+                "- interaction: depends_on\n"
+                "- via: async callback `health_provider()`\n"
+                "- purpose: получить агрегированный health runtime\n"
+                "- details:\n"
+                "  - timeout_ms: 5000\n"
+                "  - response_type: `HealthPayload`\n"
+            ),
+            order=0,
+        )
+    ]
+
+    with caplog.at_level(logging.WARNING):
+        records = extractor.extract(sections, path="docs/api/health-endpoint.md")
+
+    assert len(records) == 1
+    assert records[0].target == "runtime.health_provider"
+    assert records[0].via == "async callback `health_provider()`"
+    assert records[0].details == {}
+    assert "docs integration parse warning" in caplog.text
+    assert "docs/api/health-endpoint.md" in caplog.text
+
+
+def test_docs_pipeline_keeps_other_layers_when_integration_block_is_invalid(caplog) -> None:
+    pipeline = DocsIndexingPipeline()
+    content = """---
+id: api.runtime.health
+type: api_method
+doc_type: api_method
+name: runtime_health
+title: Runtime Health API
+module: runtime
+domain: platform
+sub_domain: observability
+layer: application
+status: active
+related_docs: []
+links:
+  uses_logic:
+    - logic.runtime.health
+---
+# Runtime Health API
+
+## Summary
+
+Returns current runtime health.
+
+## Details
+
+### Описание
+
+Возвращает агрегированное состояние runtime.
+
+### Сценарий
+
+**Название:**
+Read health
+
+**Предусловия:**
+- runtime is running
+
+**Триггер:**
+- client calls health endpoint
+
+**Основной сценарий:**
+1. Read current state.
+2. Return payload.
+
+### Входные параметры
+
+| field | type | required |
+| --- | --- | --- |
+| verbose | boolean | no |
+
+### Интеграции
+
+#### Runtime health provider
+- target: runtime.health_provider
+- target_type: service
+- direction: outbound
+- interaction: depends_on
+- via: async callback `health_provider()`
+- purpose: получить агрегированный health runtime
+- details:
+  - timeout_ms: 5000
+  - response_type: `HealthPayload`
+"""
+
+    with caplog.at_level(logging.WARNING):
+        docs = pipeline.index_file(
+            repo_id="acme/proj",
+            commit_sha="abc123",
+            path="docs/api/health-endpoint.md",
+            content=content,
+        )
+
+    layers = {doc.layer for doc in docs}
+    assert RagLayer.DOCS_DOCUMENT_CATALOG in layers
+    assert RagLayer.DOCS_DOC_CHUNKS in layers
+    assert RagLayer.DOCS_FACT_INDEX in layers
+    assert RagLayer.DOCS_WORKFLOW_INDEX in layers
+    assert RagLayer.DOCS_RELATION_GRAPH in layers
+    assert RagLayer.DOCS_INTEGRATION_INDEX in layers
+    assert "docs integration parse warning" in caplog.text
+    assert all(doc.source.path == "docs/api/health-endpoint.md" for doc in docs)

tests/unit_tests/rag/test_retrieval_statement_builder.py

@@ -45,6 +45,23 @@ def test_retrieve_builder_adds_prefer_bonus_sorting() -> None:
     assert params["prefer_like_0"] == "%/test\\_%.py"
 
 
+def test_retrieve_builder_adds_metadata_filters() -> None:
+    builder = RetrievalStatementBuilder()
+
+    sql, params = builder.build_retrieve(
+        "rag-1",
+        [0.1, 0.2],
+        query_text="notification flow",
+        metadata_domain="notifications",
+        metadata_subdomain="delivery_loop",
+    )
+
+    assert "metadata_json->>'domain'" in sql
+    assert "metadata_json->>'subdomain'" in sql
+    assert params["metadata_domain"] == "notifications"
+    assert params["metadata_subdomain"] == "delivery_loop"
+
+
 def test_lexical_builder_omits_test_filters_when_not_requested() -> None:
     builder = RetrievalStatementBuilder()