trustgraph/tests/unit/test_retrieval/test_document_rag_service.py
cybermaggedon 312174eb88
Adding explainability to the ReACT agent (#689)
* Added tech spec

* Add provenance recording to React agent loop

Enables agent sessions to be traced and debugged using the same
explainability infrastructure as GraphRAG. Agent traces record:
- Session start with query and timestamp
- Each iteration's thought, action, arguments, and observation
- Final answer with derivation chain

Changes:
- Add session_id and collection fields to AgentRequest schema
- Add agent predicates (TG_THOUGHT, TG_ACTION, etc.) to namespaces
- Create agent provenance triple generators in provenance/agent.py
- Register explainability producer in agent service
- Emit provenance triples during agent execution
- Update CLI tools to detect and render agent traces alongside GraphRAG

* Updated explainability taxonomy:

GraphRAG: tg:Question → tg:Exploration → tg:Focus → tg:Synthesis

Agent: tg:Question → tg:Analysis(s) → tg:Conclusion

All entities also have their PROV-O type (prov:Activity or prov:Entity).

Updated commit message:

Add provenance recording to React agent loop

Enables agent sessions to be traced and debugged using the same
explainability infrastructure as GraphRAG.

Entity types follow human reasoning patterns:
- tg:Question - the user's query (shared with GraphRAG)
- tg:Analysis - each think/act/observe cycle
- tg:Conclusion - the final answer

Also adds explicit TG types to GraphRAG entities:
- tg:Question, tg:Exploration, tg:Focus, tg:Synthesis

All types retain their PROV-O base types (prov:Activity, prov:Entity).

Changes:
- Add session_id and collection fields to AgentRequest schema
- Add explainability entity types to namespaces.py
- Create agent provenance triple generators
- Register explainability producer in agent service
- Emit provenance triples during agent execution
- Update CLI tools to detect and render both trace types

* Document RAG explainability is now complete. Here's a summary of the
changes made:

Schema Changes:
- trustgraph-base/trustgraph/schema/services/retrieval.py: Added
  explain_id and explain_graph fields to DocumentRagResponse
- trustgraph-base/trustgraph/messaging/translators/retrieval.py:
  Updated translator to handle explainability fields

Provenance Changes:
- trustgraph-base/trustgraph/provenance/namespaces.py: Added
  TG_CHUNK_COUNT and TG_SELECTED_CHUNK predicates
- trustgraph-base/trustgraph/provenance/uris.py: Added
  docrag_question_uri, docrag_exploration_uri, docrag_synthesis_uri
  generators
- trustgraph-base/trustgraph/provenance/triples.py: Added
  docrag_question_triples, docrag_exploration_triples,
  docrag_synthesis_triples builders
- trustgraph-base/trustgraph/provenance/__init__.py: Exported all
  new Document RAG functions and predicates

Service Changes:
- trustgraph-flow/trustgraph/retrieval/document_rag/document_rag.py:
  Added explainability callback support and triple emission at each
  phase (Question → Exploration → Synthesis)
- trustgraph-flow/trustgraph/retrieval/document_rag/rag.py:
  Registered explainability producer and wired up the callback

Documentation:
- docs/tech-specs/agent-explainability.md: Added Document RAG entity
  types and provenance model documentation

Document RAG Provenance Model:
Question (urn:trustgraph:docrag:{uuid})
    │
    │  tg:query, prov:startedAtTime
    │  rdf:type = prov:Activity, tg:Question
    │
    ↓ prov:wasGeneratedBy
    │
Exploration (urn:trustgraph:docrag:{uuid}/exploration)
    │
    │  tg:chunkCount, tg:selectedChunk (multiple)
    │  rdf:type = prov:Entity, tg:Exploration
    │
    ↓ prov:wasDerivedFrom
    │
Synthesis (urn:trustgraph:docrag:{uuid}/synthesis)
    │
    │  tg:content = "The answer..."
    │  rdf:type = prov:Entity, tg:Synthesis

* Specific subtype that makes the retrieval mechanism immediately
obvious:

System: GraphRAG
TG Types on Question: tg:Question, tg:GraphRagQuestion
URI Pattern: urn:trustgraph:question:{uuid}
────────────────────────────────────────
System: Document RAG
TG Types on Question: tg:Question, tg:DocRagQuestion
URI Pattern: urn:trustgraph:docrag:{uuid}
────────────────────────────────────────
System: Agent
TG Types on Question: tg:Question, tg:AgentQuestion
URI Pattern: urn:trustgraph:agent:{uuid}
Files modified:
- trustgraph-base/trustgraph/provenance/namespaces.py - Added
TG_GRAPH_RAG_QUESTION, TG_DOC_RAG_QUESTION, TG_AGENT_QUESTION
- trustgraph-base/trustgraph/provenance/triples.py - Added subtype to
question_triples and docrag_question_triples
- trustgraph-base/trustgraph/provenance/agent.py - Added subtype to
agent_session_triples
- trustgraph-base/trustgraph/provenance/__init__.py - Exported new types
- docs/tech-specs/agent-explainability.md - Documented the subtypes

This allows:
- Query all questions: ?q rdf:type tg:Question
- Query only GraphRAG: ?q rdf:type tg:GraphRagQuestion
- Query only Document RAG: ?q rdf:type tg:DocRagQuestion
- Query only Agent: ?q rdf:type tg:AgentQuestion

* Fixed tests
2026-03-11 15:28:15 +00:00

132 lines
No EOL
5 KiB
Python

"""
Unit test for DocumentRAG service parameter passing fix.
Tests that user and collection parameters from the message are correctly
passed to the DocumentRag.query() method.
"""
import pytest
from unittest.mock import MagicMock, AsyncMock, patch, ANY
from trustgraph.retrieval.document_rag.rag import Processor
from trustgraph.schema import DocumentRagQuery, DocumentRagResponse
class TestDocumentRagService:
"""Test DocumentRAG service parameter passing"""
@patch('trustgraph.retrieval.document_rag.rag.DocumentRag')
@pytest.mark.asyncio
async def test_user_and_collection_parameters_passed_to_query(self, mock_document_rag_class):
"""
Test that user and collection from message are passed to DocumentRag.query().
This is a regression test for the bug where user/collection parameters
were ignored, causing wrong collection names like 'd_trustgraph_default_384'
instead of 'd_my_user_test_coll_1_384'.
"""
# Setup processor
processor = Processor(
taskgroup=MagicMock(),
id="test-processor",
doc_limit=10
)
# Setup mock DocumentRag instance
mock_rag_instance = AsyncMock()
mock_document_rag_class.return_value = mock_rag_instance
mock_rag_instance.query.return_value = "test response"
# Setup message with custom user/collection
msg = MagicMock()
msg.value.return_value = DocumentRagQuery(
query="test query",
user="my_user", # Custom user (not default "trustgraph")
collection="test_coll_1", # Custom collection (not default "default")
doc_limit=5
)
msg.properties.return_value = {"id": "test-id"}
# Setup flow mock
consumer = MagicMock()
flow = MagicMock()
# Mock flow to return AsyncMock for clients and response producer
mock_producer = AsyncMock()
def flow_router(service_name):
if service_name == "response":
return mock_producer
return AsyncMock() # embeddings, doc-embeddings, prompt clients
flow.side_effect = flow_router
# Execute
await processor.on_request(msg, consumer, flow)
# Verify: DocumentRag.query was called with correct parameters
mock_rag_instance.query.assert_called_once_with(
"test query",
user="my_user", # Must be from message, not hardcoded default
collection="test_coll_1", # Must be from message, not hardcoded default
doc_limit=5,
explain_callback=ANY, # Explainability callback is always passed
)
# Verify response was sent
mock_producer.send.assert_called_once()
sent_response = mock_producer.send.call_args[0][0]
assert isinstance(sent_response, DocumentRagResponse)
assert sent_response.response == "test response"
assert sent_response.error is None
@patch('trustgraph.retrieval.document_rag.rag.DocumentRag')
@pytest.mark.asyncio
async def test_non_streaming_mode_sets_end_of_stream_true(self, mock_document_rag_class):
"""
Test that non-streaming mode sets end_of_stream=True in response.
This is a regression test for the bug where non-streaming responses
didn't set end_of_stream, causing clients to hang waiting for more data.
"""
# Setup processor
processor = Processor(
taskgroup=MagicMock(),
id="test-processor",
doc_limit=10
)
# Setup mock DocumentRag instance
mock_rag_instance = AsyncMock()
mock_document_rag_class.return_value = mock_rag_instance
mock_rag_instance.query.return_value = "A document about cats."
# Setup message with non-streaming request
msg = MagicMock()
msg.value.return_value = DocumentRagQuery(
query="What is a cat?",
user="trustgraph",
collection="default",
doc_limit=10,
streaming=False # Non-streaming mode
)
msg.properties.return_value = {"id": "test-id"}
# Setup flow mock
consumer = MagicMock()
flow = MagicMock()
mock_producer = AsyncMock()
def flow_router(service_name):
if service_name == "response":
return mock_producer
return AsyncMock()
flow.side_effect = flow_router
# Execute
await processor.on_request(msg, consumer, flow)
# Verify: response was sent with end_of_stream=True
mock_producer.send.assert_called_once()
sent_response = mock_producer.send.call_args[0][0]
assert isinstance(sent_response, DocumentRagResponse)
assert sent_response.response == "A document about cats."
assert sent_response.end_of_stream is True, "Non-streaming response must have end_of_stream=True"
assert sent_response.error is None