trustgraph/trustgraph-flow/trustgraph/agent/react
cybermaggedon 03cc5ac80f
Per-flow librarian clients and per-workspace response queues (#865)
Replace singleton LibrarianClient with per-flow instances via the new
LibrarianSpec, giving each flow its own librarian tied to the
workspace-scoped request/response queues from the blueprint.

Move all workspace-scoped services (config, flow, librarian, knowledge)
from a single base-queue response producer to per-workspace response
producers created alongside the existing per-workspace request
consumers.  Update the gateway dispatcher and bootstrapper flow client
to subscribe to the matching workspace-scoped response queues.

Fix WorkspaceInit to register workspaces through the IAM
create-workspace API so they appear in __workspaces__ and are visible
to the gateway.  Simplify the bootstrapper gate to only check
config-svc reachability.

Updated tests accordingly.
2026-05-06 12:01:01 +01:00
..
__init__.py Feature/agent manager (#146) 2024-11-10 11:44:01 +00:00
__main__.py Feature/agent manager (#146) 2024-11-10 11:44:01 +00:00
agent_manager.py Add agent explainability instrumentation and unify envelope field naming (#795) 2026-04-13 16:16:42 +01:00
README.md Feature/agent manager (#146) 2024-11-10 11:44:01 +00:00
service.py Per-flow librarian clients and per-workspace response queues (#865) 2026-05-06 12:01:01 +01:00
streaming_parser.py Streaming rag responses (#568) 2025-11-26 19:47:39 +00:00
tools.py feat: workspace-based multi-tenancy, replacing user as tenancy axis (#840) 2026-04-21 23:23:01 +01:00
types.py Add agent explainability instrumentation and unify envelope field naming (#795) 2026-04-13 16:16:42 +01:00

agent-manager-react
-p pulsar://localhost:6650
--tool-type
shuttle=knowledge-query:query
cats=knowledge-query:query
compute=text-completion:computation
--tool-description
shuttle="Query a knowledge base with information about the space shuttle. The query should be a simple natural language question"
cats="Query a knowledge base with information about Mark's cats. The query should be a simple natural language question"
compute="A computation engine which can answer questions about maths and computation"
--tool-argument
cats="query:string:The search query string"
shuttle="query:string:The search query string"
compute="computation:string:The computation to solve"

--context 'The space shuttle challenger final mission was 58-L'