trustgraph/specs/api/paths/flow/agent.yaml
cybermaggedon d35473f7f7
feat: workspace-based multi-tenancy, replacing user as tenancy axis (#840)
Introduces `workspace` as the isolation boundary for config, flows,
library, and knowledge data. Removes `user` as a schema-level field
throughout the code, API specs, and tests; workspace provides the
same separation more cleanly at the trusted flow.workspace layer
rather than through client-supplied message fields.

Design
------
- IAM tech spec (docs/tech-specs/iam.md) documents current state,
  proposed auth/access model, and migration direction.
- Data ownership model (docs/tech-specs/data-ownership-model.md)
  captures the workspace/collection/flow hierarchy.

Schema + messaging
------------------
- Drop `user` field from AgentRequest/Step, GraphRagQuery,
  DocumentRagQuery, Triples/Graph/Document/Row EmbeddingsRequest,
  Sparql/Rows/Structured QueryRequest, ToolServiceRequest.
- Keep collection/workspace routing via flow.workspace at the
  service layer.
- Translators updated to not serialise/deserialise user.

API specs
---------
- OpenAPI schemas and path examples cleaned of user fields.
- Websocket async-api messages updated.
- Removed the unused parameters/User.yaml.

Services + base
---------------
- Librarian, collection manager, knowledge, config: all operations
  scoped by workspace. Config client API takes workspace as first
  positional arg.
- `flow.workspace` set at flow start time by the infrastructure;
  no longer pass-through from clients.
- Tool service drops user-personalisation passthrough.

CLI + SDK
---------
- tg-init-workspace and workspace-aware import/export.
- All tg-* commands drop user args; accept --workspace.
- Python API/SDK (flow, socket_client, async_*, explainability,
  library) drop user kwargs from every method signature.

MCP server
----------
- All tool endpoints drop user parameters; socket_manager no longer
  keyed per user.

Flow service
------------
- Closure-based topic cleanup on flow stop: only delete topics
  whose blueprint template was parameterised AND no remaining
  live flow (across all workspaces) still resolves to that topic.
  Three scopes fall out naturally from template analysis:
    * {id} -> per-flow, deleted on stop
    * {blueprint} -> per-blueprint, kept while any flow of the
      same blueprint exists
    * {workspace} -> per-workspace, kept while any flow in the
      workspace exists
    * literal -> global, never deleted (e.g. tg.request.librarian)
  Fixes a bug where stopping a flow silently destroyed the global
  librarian exchange, wedging all library operations until manual
  restart.

RabbitMQ backend
----------------
- heartbeat=60, blocked_connection_timeout=300. Catches silently
  dead connections (broker restart, orphaned channels, network
  partitions) within ~2 heartbeat windows, so the consumer
  reconnects and re-binds its queue rather than sitting forever
  on a zombie connection.

Tests
-----
- Full test refresh: unit, integration, contract, provenance.
- Dropped user-field assertions and constructor kwargs across
  ~100 test files.
- Renamed user-collection isolation tests to workspace-collection.
2026-04-21 23:23:01 +01:00

143 lines
4.9 KiB
YAML

post:
tags:
- Flow Services
summary: Agent service - conversational AI with reasoning
description: |
AI agent that can understand questions, reason about them, and take actions.
## Agent Overview
The agent service provides a conversational AI that:
- Understands natural language questions
- Reasons about problems using thoughts
- Takes actions to gather information
- Provides coherent answers
## Request Format
Send a question with optional:
- **state**: Continue from previous conversation
- **history**: Previous agent steps for context
- **group**: Collaborative agent identifiers
- **streaming**: Enable streaming responses
## Response Modes
### Streaming Mode (streaming: true)
Responses arrive as chunks with `chunk-type`:
- `thought`: Agent's reasoning process
- `action`: Action being taken
- `observation`: Result from action
- `answer`: Final response to user
- `explain`: Provenance event with inline triples (`explain_triples`)
- `error`: Error occurred
Each chunk may have multiple messages. Check flags:
- `end-of-message`: Current chunk type complete
- `end-of-dialog`: Entire conversation complete
### Legacy Mode (streaming: false)
Single response with:
- `answer`: Complete answer
- `thought`: Reasoning (if any)
- `observation`: Observations (if any)
## Multi-turn Conversations
Include `history` array with previous steps to maintain context.
Each step has: thought, action, arguments, observation.
operationId: agentService
security:
- bearerAuth: []
parameters:
- name: flow
in: path
required: true
schema:
type: string
description: Flow instance ID
example: my-flow
requestBody:
required: true
content:
application/json:
schema:
$ref: '../../components/schemas/agent/AgentRequest.yaml'
examples:
simpleQuestion:
summary: Simple question
value:
question: What is the capital of France?
streamingQuestion:
summary: Question with streaming enabled
value:
question: Explain quantum computing
streaming: true
conversationWithHistory:
summary: Multi-turn conversation
value:
question: And what about its population?
history:
- thought: User is asking about the capital of France
action: search
arguments:
query: "capital of France"
observation: "Paris is the capital of France"
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '../../components/schemas/agent/AgentResponse.yaml'
examples:
streamingThought:
summary: Streaming thought chunk
value:
chunk-type: thought
content: I need to search for information about quantum computing
end-of-message: false
end-of-dialog: false
streamingAnswer:
summary: Streaming answer chunk
value:
chunk-type: answer
content: Quantum computing uses quantum mechanics principles...
end-of-message: false
end-of-dialog: false
streamingComplete:
summary: Streaming complete marker
value:
chunk-type: answer
content: ""
end-of-message: true
end-of-dialog: true
explainEvent:
summary: Explain event with inline provenance triples
value:
chunk-type: explain
content: ""
explain_id: urn:trustgraph:agent:abc123
explain_graph: urn:graph:retrieval
explain_triples:
- s: {t: i, i: "urn:trustgraph:agent:abc123"}
p: {t: i, i: "http://www.w3.org/1999/02/22-rdf-syntax-ns#type"}
o: {t: i, i: "https://trustgraph.ai/ns/AgentSession"}
- s: {t: i, i: "urn:trustgraph:agent:abc123"}
p: {t: i, i: "https://trustgraph.ai/ns/query"}
o: {t: l, v: "Explain quantum computing"}
end-of-message: true
end-of-dialog: false
legacyResponse:
summary: Legacy non-streaming response
value:
answer: Paris is the capital of France.
thought: User is asking about the capital of France
observation: ""
end-of-message: false
end-of-dialog: false
'401':
$ref: '../../components/responses/Unauthorized.yaml'
'500':
$ref: '../../components/responses/Error.yaml'