trustgraph/tests/unit/test_agent
cybermaggedon d2751553a3
Add agent explainability instrumentation and unify envelope field naming (#795)
Addresses recommendations from the UX developer's agent experience report.
Adds provenance predicates, DAG structure changes, error resilience, and
a published OWL ontology.

Explainability additions:

- Tool candidates: tg:toolCandidate on Analysis events lists the tools
  visible to the LLM for each iteration (names only, descriptions in config)
- Termination reason: tg:terminationReason on Conclusion/Synthesis events
  (final-answer, plan-complete, subagents-complete)
- Step counter: tg:stepNumber on iteration events
- Pattern decision: new tg:PatternDecision entity in the DAG between
  session and first iteration, carrying tg:pattern and tg:taskType
- Latency: tg:llmDurationMs on Analysis events, tg:toolDurationMs on
  Observation events
- Token counts on events: tg:inToken/tg:outToken/tg:llmModel on
  Grounding, Focus, Synthesis, and Analysis events
- Tool/parse errors: tg:toolError on Observation events with tg:Error
  mixin type. Parse failures return as error observations instead of
  crashing the agent, giving it a chance to retry.

Envelope unification:

- Rename chunk_type to message_type across AgentResponse schema,
  translator, SDK types, socket clients, CLI, and all tests.
  Agent and RAG services now both use message_type on the wire.

Ontology:

- specs/ontology/trustgraph.ttl — OWL vocabulary covering all 26 classes,
  7 object properties, and 36+ datatype properties including new predicates.

DAG structure tests:

- tests/unit/test_provenance/test_dag_structure.py verifies the
  wasDerivedFrom chain for GraphRAG, DocumentRAG, and all three agent
  patterns (react, plan, supervisor) including the pattern-decision link.
2026-04-13 16:16:42 +01:00
..
__init__.py Extending test coverage (#434) 2025-07-14 17:54:04 +01:00
conftest.py Extending test coverage (#434) 2025-07-14 17:54:04 +01:00
test_agent_service_non_streaming.py Add agent explainability instrumentation and unify envelope field naming (#795) 2026-04-13 16:16:42 +01:00
test_agent_step_arguments.py MCP auth for the simple case (#557) 2025-11-11 12:28:53 +00:00
test_aggregator.py Update tests for agent-orchestrator (#745) 2026-03-31 13:12:26 +01:00
test_callback_message_id.py Add agent explainability instrumentation and unify envelope field naming (#795) 2026-04-13 16:16:42 +01:00
test_completion_dispatch.py Update tests for agent-orchestrator (#745) 2026-03-31 13:12:26 +01:00
test_conversation_state.py Extending test coverage (#434) 2025-07-14 17:54:04 +01:00
test_explainability_parsing.py Additional agent DAG tests (#750) 2026-04-01 13:59:58 +01:00
test_mcp_tool_auth.py MCP auth for the simple case (#557) 2025-11-11 12:28:53 +00:00
test_meta_router.py Expose LLM token usage across all service layers (#782) 2026-04-13 14:38:34 +01:00
test_on_action_callback.py Additional agent DAG tests (#750) 2026-04-01 13:59:58 +01:00
test_orchestrator_provenance_integration.py Add agent explainability instrumentation and unify envelope field naming (#795) 2026-04-13 16:16:42 +01:00
test_parse_chunk_message_id.py Add agent explainability instrumentation and unify envelope field naming (#795) 2026-04-13 16:16:42 +01:00
test_pattern_base_subagent.py Update tests for agent-orchestrator (#745) 2026-03-31 13:12:26 +01:00
test_provenance_triples.py Split Analysis into Analysis+ToolUse and Observation, add message_id (#747) 2026-03-31 17:51:22 +01:00
test_react_processor.py master -> 1.5 (README updates) (#552) 2025-10-11 11:46:03 +01:00
test_reasoning_engine.py Extending test coverage (#434) 2025-07-14 17:54:04 +01:00
test_tool_coordination.py Extending test coverage (#434) 2025-07-14 17:54:04 +01:00
test_tool_filter.py Feature/tool group (#484) 2025-09-03 23:39:49 +01:00
test_tool_service.py Tool services - dynamically pluggable tool implementations for agent frameworks (#658) 2026-03-04 14:51:32 +00:00
test_tool_service_lifecycle.py Updated test suite for explainability & provenance (#696) 2026-03-13 14:27:42 +00:00