mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-06-17 10:55:14 +02:00
115e325071
Workspace identity is now determined by queue infrastructure instead of message body fields, closing a privilege-escalation vector where a caller could spoof workspace in the request payload. - Add WorkspaceProcessor base class: discovers workspaces from config at startup, creates per-workspace consumers (queue:workspace), and manages consumer lifecycle on workspace create/delete events - Roll out to librarian, flow-svc, and knowledge cores - Remove workspace field from request schemas (FlowRequest, LibrarianRequest, KnowledgeRequest, CollectionManagementRequest) and from DocumentMetadata / ProcessingMetadata — table stores now accept workspace as an explicit parameter for Cassandra partition keys - Strip workspace encode/decode from all message translators and gateway serializers - Config service gets a dual-queue regime: a system queue for cross-workspace ops (getvalues-all-ws, bootstrapper writes to __workspaces__) and per-workspace queues for tenant-scoped ops, with workspace discovery from its own Cassandra store - Gateway enforces workspace requirement for workspace dispatchers — config moves from system_dispatchers to workspace_dispatchers so the gateway can never route to the system config queue - Add workspace lifecycle hooks to AsyncProcessor so any processor can react to workspace create/delete without subclassing WorkspaceProcessor
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
from typing import Dict, Any, Optional
|
|
from ...schema import DocumentMetadata, ProcessingMetadata
|
|
from .base import Translator
|
|
from .primitives import SubgraphTranslator
|
|
|
|
|
|
class DocumentMetadataTranslator(Translator):
|
|
"""Translator for DocumentMetadata schema objects"""
|
|
|
|
def __init__(self):
|
|
self.subgraph_translator = SubgraphTranslator()
|
|
|
|
def decode(self, data: Dict[str, Any]) -> DocumentMetadata:
|
|
metadata = data.get("metadata", [])
|
|
return DocumentMetadata(
|
|
id=data.get("id"),
|
|
time=data.get("time"),
|
|
kind=data.get("kind"),
|
|
title=data.get("title"),
|
|
comments=data.get("comments"),
|
|
metadata=self.subgraph_translator.decode(metadata) if metadata is not None else [],
|
|
tags=data.get("tags"),
|
|
parent_id=data.get("parent-id", ""),
|
|
document_type=data.get("document-type", "source"),
|
|
)
|
|
|
|
def encode(self, obj: DocumentMetadata) -> Dict[str, Any]:
|
|
result = {}
|
|
|
|
if obj.id:
|
|
result["id"] = obj.id
|
|
if obj.time:
|
|
result["time"] = obj.time
|
|
if obj.kind:
|
|
result["kind"] = obj.kind
|
|
if obj.title:
|
|
result["title"] = obj.title
|
|
if obj.comments:
|
|
result["comments"] = obj.comments
|
|
if obj.metadata is not None:
|
|
result["metadata"] = self.subgraph_translator.encode(obj.metadata)
|
|
if obj.tags is not None:
|
|
result["tags"] = obj.tags
|
|
if obj.parent_id:
|
|
result["parent-id"] = obj.parent_id
|
|
if obj.document_type:
|
|
result["document-type"] = obj.document_type
|
|
|
|
return result
|
|
|
|
|
|
class ProcessingMetadataTranslator(Translator):
|
|
"""Translator for ProcessingMetadata schema objects"""
|
|
|
|
def decode(self, data: Dict[str, Any]) -> ProcessingMetadata:
|
|
return ProcessingMetadata(
|
|
id=data.get("id"),
|
|
document_id=data.get("document-id"),
|
|
time=data.get("time"),
|
|
flow=data.get("flow"),
|
|
collection=data.get("collection"),
|
|
tags=data.get("tags")
|
|
)
|
|
|
|
def encode(self, obj: ProcessingMetadata) -> Dict[str, Any]:
|
|
result = {}
|
|
|
|
if obj.id:
|
|
result["id"] = obj.id
|
|
if obj.document_id:
|
|
result["document-id"] = obj.document_id
|
|
if obj.time:
|
|
result["time"] = obj.time
|
|
if obj.flow:
|
|
result["flow"] = obj.flow
|
|
if obj.collection:
|
|
result["collection"] = obj.collection
|
|
if obj.tags is not None:
|
|
result["tags"] = obj.tags
|
|
|
|
return result
|