mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-07-01 17:39:39 +02:00
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.
154 lines
5.1 KiB
Python
154 lines
5.1 KiB
Python
from typing import Dict, Any, Tuple
|
|
from ...schema import (
|
|
DocumentEmbeddingsRequest, DocumentEmbeddingsResponse,
|
|
GraphEmbeddingsRequest, GraphEmbeddingsResponse,
|
|
RowEmbeddingsRequest, RowEmbeddingsResponse, RowIndexMatch
|
|
)
|
|
from .base import MessageTranslator
|
|
from .primitives import ValueTranslator
|
|
|
|
|
|
class DocumentEmbeddingsRequestTranslator(MessageTranslator):
|
|
"""Translator for DocumentEmbeddingsRequest schema objects"""
|
|
|
|
def decode(self, data: Dict[str, Any]) -> DocumentEmbeddingsRequest:
|
|
return DocumentEmbeddingsRequest(
|
|
vector=data["vector"],
|
|
limit=int(data.get("limit", 10)),
|
|
collection=data.get("collection", "default")
|
|
)
|
|
|
|
def encode(self, obj: DocumentEmbeddingsRequest) -> Dict[str, Any]:
|
|
return {
|
|
"vector": obj.vector,
|
|
"limit": obj.limit,
|
|
"collection": obj.collection
|
|
}
|
|
|
|
|
|
class DocumentEmbeddingsResponseTranslator(MessageTranslator):
|
|
"""Translator for DocumentEmbeddingsResponse schema objects"""
|
|
|
|
def decode(self, data: Dict[str, Any]) -> DocumentEmbeddingsResponse:
|
|
raise NotImplementedError("Response translation to Pulsar not typically needed")
|
|
|
|
def encode(self, obj: DocumentEmbeddingsResponse) -> Dict[str, Any]:
|
|
result = {}
|
|
|
|
if obj.chunks is not None:
|
|
result["chunks"] = [
|
|
{
|
|
"chunk_id": chunk.chunk_id,
|
|
"score": chunk.score
|
|
}
|
|
for chunk in obj.chunks
|
|
]
|
|
|
|
return result
|
|
|
|
def encode_with_completion(self, obj: DocumentEmbeddingsResponse) -> Tuple[Dict[str, Any], bool]:
|
|
"""Returns (response_dict, is_final)"""
|
|
return self.encode(obj), True
|
|
|
|
|
|
class GraphEmbeddingsRequestTranslator(MessageTranslator):
|
|
"""Translator for GraphEmbeddingsRequest schema objects"""
|
|
|
|
def decode(self, data: Dict[str, Any]) -> GraphEmbeddingsRequest:
|
|
return GraphEmbeddingsRequest(
|
|
vector=data["vector"],
|
|
limit=int(data.get("limit", 10)),
|
|
collection=data.get("collection", "default")
|
|
)
|
|
|
|
def encode(self, obj: GraphEmbeddingsRequest) -> Dict[str, Any]:
|
|
return {
|
|
"vector": obj.vector,
|
|
"limit": obj.limit,
|
|
"collection": obj.collection
|
|
}
|
|
|
|
|
|
class GraphEmbeddingsResponseTranslator(MessageTranslator):
|
|
"""Translator for GraphEmbeddingsResponse schema objects"""
|
|
|
|
def __init__(self):
|
|
self.value_translator = ValueTranslator()
|
|
|
|
def decode(self, data: Dict[str, Any]) -> GraphEmbeddingsResponse:
|
|
raise NotImplementedError("Response translation to Pulsar not typically needed")
|
|
|
|
def encode(self, obj: GraphEmbeddingsResponse) -> Dict[str, Any]:
|
|
result = {}
|
|
|
|
if obj.entities is not None:
|
|
result["entities"] = [
|
|
{
|
|
"entity": self.value_translator.encode(match.entity),
|
|
"score": match.score
|
|
}
|
|
for match in obj.entities
|
|
]
|
|
|
|
return result
|
|
|
|
def encode_with_completion(self, obj: GraphEmbeddingsResponse) -> Tuple[Dict[str, Any], bool]:
|
|
"""Returns (response_dict, is_final)"""
|
|
return self.encode(obj), True
|
|
|
|
|
|
class RowEmbeddingsRequestTranslator(MessageTranslator):
|
|
"""Translator for RowEmbeddingsRequest schema objects"""
|
|
|
|
def decode(self, data: Dict[str, Any]) -> RowEmbeddingsRequest:
|
|
return RowEmbeddingsRequest(
|
|
vector=data["vector"],
|
|
limit=int(data.get("limit", 10)),
|
|
collection=data.get("collection", "default"),
|
|
schema_name=data.get("schema_name", ""),
|
|
index_name=data.get("index_name")
|
|
)
|
|
|
|
def encode(self, obj: RowEmbeddingsRequest) -> Dict[str, Any]:
|
|
result = {
|
|
"vector": obj.vector,
|
|
"limit": obj.limit,
|
|
"collection": obj.collection,
|
|
"schema_name": obj.schema_name,
|
|
}
|
|
if obj.index_name:
|
|
result["index_name"] = obj.index_name
|
|
return result
|
|
|
|
|
|
class RowEmbeddingsResponseTranslator(MessageTranslator):
|
|
"""Translator for RowEmbeddingsResponse schema objects"""
|
|
|
|
def decode(self, data: Dict[str, Any]) -> RowEmbeddingsResponse:
|
|
raise NotImplementedError("Response translation to Pulsar not typically needed")
|
|
|
|
def encode(self, obj: RowEmbeddingsResponse) -> Dict[str, Any]:
|
|
result = {}
|
|
|
|
if obj.error is not None:
|
|
result["error"] = {
|
|
"type": obj.error.type,
|
|
"message": obj.error.message
|
|
}
|
|
|
|
if obj.matches is not None:
|
|
result["matches"] = [
|
|
{
|
|
"index_name": match.index_name,
|
|
"index_value": match.index_value,
|
|
"text": match.text,
|
|
"score": match.score
|
|
}
|
|
for match in obj.matches
|
|
]
|
|
|
|
return result
|
|
|
|
def encode_with_completion(self, obj: RowEmbeddingsResponse) -> Tuple[Dict[str, Any], bool]:
|
|
"""Returns (response_dict, is_final)"""
|
|
return self.encode(obj), True
|