trustgraph/tests/unit
Cyber MacGeddon 2e83413cbe Add agent explainability instrumentation and unify envelope field naming
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 16:12:45 +01:00
..
test_agent Add agent explainability instrumentation and unify envelope field naming 2026-04-13 16:12:45 +01:00
test_base Fix RabbitMQ request/response race and chunker Flow API drift (#779) 2026-04-11 01:29:38 +01:00
test_chunking Fix RabbitMQ request/response race and chunker Flow API drift (#779) 2026-04-11 01:29:38 +01:00
test_cli Fix/tests (#647) 2026-02-23 22:01:47 +00:00
test_clients Pub/sub abstraction: decouple from Pulsar (#751) 2026-04-01 20:16:53 +01:00
test_concurrency Subscriber resilience and RabbitMQ fixes (#765) 2026-04-07 14:51:14 +01:00
test_config Structure data mvp (#452) 2025-08-07 20:47:20 +01:00
test_cores Remove redundant metadata (#685) 2026-03-11 10:51:39 +00:00
test_decoding RabbitMQ pub/sub backend with topic exchange architecture (#752) 2026-04-02 12:47:16 +01:00
test_direct Updated test suite for explainability & provenance (#696) 2026-03-13 14:27:42 +00:00
test_embeddings Updated test suite for explainability & provenance (#696) 2026-03-13 14:27:42 +00:00
test_extract Expose LLM token usage across all service layers (#782) 2026-04-13 14:38:34 +01:00
test_gateway Add agent explainability instrumentation and unify envelope field naming 2026-04-13 16:12:45 +01:00
test_knowledge_graph Remove schema:subjectOf edges from KG extraction (#695) 2026-03-13 12:11:21 +00:00
test_librarian Add universal document decoder with multi-format support (#705) 2026-03-23 12:56:35 +00:00
test_provenance Add agent explainability instrumentation and unify envelope field naming 2026-04-13 16:12:45 +01:00
test_pubsub Refactor: Derive consumer behaviour from queue class (#772) 2026-04-09 09:55:41 +01:00
test_query SPARQL query service (#754) 2026-04-02 17:21:39 +01:00
test_rdf Pub/sub abstraction: decouple from Pulsar (#751) 2026-04-01 20:16:53 +01:00
test_reliability Pub/sub abstraction: decouple from Pulsar (#751) 2026-04-01 20:16:53 +01:00
test_retrieval Expose LLM token usage across all service layers (#782) 2026-04-13 14:38:34 +01:00
test_rev_gateway Fix tests (#593) 2025-12-19 08:53:21 +00:00
test_storage Remove redundant metadata (#685) 2026-03-11 10:51:39 +00:00
test_structured_data Updated test suite for explainability & provenance (#696) 2026-03-13 14:27:42 +00:00
test_tables Fix Metadata/EntityEmbeddings schema migration tail and add regression tests (#777) 2026-04-10 20:43:45 +01:00
test_text_completion Feat: Auto-pull missing Ollama models (#757) 2026-04-06 11:10:53 +01:00
test_translators Fix Metadata/EntityEmbeddings schema migration tail and add regression tests (#777) 2026-04-10 20:43:45 +01:00
__init__.py Test suite executed from CI pipeline (#433) 2025-07-14 14:57:44 +01:00
test_prompt_manager.py Feature/prompts jsonl (#619) 2026-01-26 17:38:00 +00:00
test_prompt_manager_edge_cases.py Update to enable knowledge extraction using the agent framework (#439) 2025-07-21 14:31:57 +01:00
test_python_api_client.py Add agent explainability instrumentation and unify envelope field naming 2026-04-13 16:12:45 +01:00