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.
This commit is contained in:
cybermaggedon 2026-04-13 16:16:42 +01:00 committed by GitHub
parent 14e49d83c7
commit d2751553a3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
42 changed files with 1577 additions and 205 deletions

View file

@ -304,14 +304,14 @@ class TestStreamingTypes:
assert chunk.content == "thinking..."
assert chunk.end_of_message is False
assert chunk.chunk_type == "thought"
assert chunk.message_type == "thought"
def test_agent_observation_creation(self):
"""Test creating AgentObservation chunk"""
chunk = AgentObservation(content="observing...", end_of_message=False)
assert chunk.content == "observing..."
assert chunk.chunk_type == "observation"
assert chunk.message_type == "observation"
def test_agent_answer_creation(self):
"""Test creating AgentAnswer chunk"""
@ -324,7 +324,7 @@ class TestStreamingTypes:
assert chunk.content == "answer"
assert chunk.end_of_message is True
assert chunk.end_of_dialog is True
assert chunk.chunk_type == "final-answer"
assert chunk.message_type == "final-answer"
def test_rag_chunk_creation(self):
"""Test creating RAGChunk"""