Split Analysis into Analysis+ToolUse and Observation, add message_id (#747)

Refactor agent provenance so that the decision (thought + tool
selection) and the result (observation) are separate DAG entities:

  Question ← Analysis+ToolUse ← Observation ← ... ← Conclusion

Analysis gains tg:ToolUse as a mixin RDF type and is emitted
before tool execution via an on_action callback in react().
This ensures sub-traces (e.g. GraphRAG) appear after their
parent Analysis in the streaming event order.

Observation becomes a standalone prov:Entity with tg:Observation
type, emitted after tool execution. The linear DAG chain runs
through Observation — subsequent iterations and the Conclusion
derive from it, not from the Analysis.

message_id is populated on streaming AgentResponse for thought
and observation chunks, using the provenance URI of the entity
being built. This lets clients group streamed chunks by entity.

Wire changes:
- provenance/agent.py: Add ToolUse type, new
  agent_observation_triples(), remove observation from iteration
- agent_manager.py: Add on_action callback between reason() and
  tool execution
- orchestrator/pattern_base.py: Split emit, wire message_id,
  chain through observation URIs
- orchestrator/react_pattern.py: Emit Analysis via on_action
  before tool runs
- agent/react/service.py: Same for non-orchestrator path
- api/explainability.py: New Observation class, updated dispatch
  and chain walker
- api/types.py: Add message_id to AgentThought/AgentObservation
- cli: Render Observation separately, [analysis: tool] labels
This commit is contained in:
cybermaggedon 2026-03-31 17:51:22 +01:00 committed by GitHub
parent 89e13a756a
commit 153ae9ad30
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 661 additions and 350 deletions

View file

@ -5,6 +5,7 @@ from .. schema import GraphRagQuery, GraphRagResponse
class GraphRagClient(RequestResponse):
async def rag(self, query, user="trustgraph", collection="default",
chunk_callback=None, explain_callback=None,
parent_uri="",
timeout=600):
"""
Execute a graph RAG query with optional streaming callbacks.
@ -50,6 +51,7 @@ class GraphRagClient(RequestResponse):
query = query,
user = user,
collection = collection,
parent_uri = parent_uri,
),
timeout=timeout,
recipient=recipient,