apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-05-20 12:55:13 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Add multi-pattern orchestrator with plan-then-execute and supervisor (#739)

Browse source 
Introduce an agent orchestrator service that supports three
execution patterns (ReAct, plan-then-execute, supervisor) with
LLM-based meta-routing to select the appropriate pattern and task
type per request. Update the agent schema to support
orchestration fields (correlation, sub-agents, plan steps) and
remove legacy response fields (answer, thought, observation).
This commit is contained in:
cybermaggedon 2026-03-31 00:32:49 +01:00 • committed by GitHub
parent 7af1d60db8
commit 849987f0e6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 3006 additions and 172 deletions
Download patch file Download diff file Expand all files Collapse all files

17
trustgraph-base/trustgraph/api/socket_client.py
View file

@ -402,23 +402,6 @@ class SocketClient:
content=resp.get("content", ""),
end_of_message=resp.get("end_of_message", False)
)
# Non-streaming agent format: chunk_type is empty but has thought/observation/answer fields
elif resp.get("thought"):
return AgentThought(
content=resp.get("thought", ""),
end_of_message=resp.get("end_of_message", False)
)
elif resp.get("observation"):
return AgentObservation(
content=resp.get("observation", ""),
end_of_message=resp.get("end_of_message", False)
)
elif resp.get("answer"):
return AgentAnswer(
content=resp.get("answer", ""),
end_of_message=resp.get("end_of_message", False),
end_of_dialog=resp.get("end_of_dialog", False)
)
else:
content = resp.get("response", resp.get("chunk", resp.get("text", "")))
return RAGChunk(