mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-29 10:26:21 +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.
153 lines
5.3 KiB
Python
153 lines
5.3 KiB
Python
"""
|
|
Handler for storage services to process collection configuration from config push
|
|
"""
|
|
|
|
import json
|
|
import logging
|
|
from typing import Dict, Set
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class CollectionConfigHandler:
|
|
"""
|
|
Handles collection configuration from config push messages for storage services.
|
|
|
|
Storage services should:
|
|
1. Inherit from this class along with their service base class
|
|
2. Call register_config_handler(self.on_collection_config) in __init__
|
|
3. Implement create_collection(workspace, collection, metadata) method
|
|
4. Implement delete_collection(workspace, collection) method
|
|
"""
|
|
|
|
def __init__(self, **kwargs):
|
|
# Track known collections: {(workspace, collection): metadata_dict}
|
|
self.known_collections: Dict[tuple, dict] = {}
|
|
# Pass remaining kwargs up the inheritance chain
|
|
super().__init__(**kwargs)
|
|
|
|
async def on_collection_config(
|
|
self, workspace: str, config: dict, version: int
|
|
):
|
|
"""
|
|
Handle config push messages and extract collection information
|
|
for a single workspace.
|
|
|
|
Args:
|
|
workspace: Workspace the config applies to
|
|
config: Configuration dictionary from ConfigPush message
|
|
version: Configuration version number
|
|
"""
|
|
logger.info(
|
|
f"Processing collection configuration "
|
|
f"(version {version}, workspace {workspace})"
|
|
)
|
|
|
|
# Extract collections from config (treat missing key as empty).
|
|
# Each config key IS the collection name — config is already
|
|
# partitioned by workspace, so no workspace prefix is needed
|
|
# on the key.
|
|
collection_config = config.get("collection", {})
|
|
|
|
# Track which collections we've seen in this config
|
|
current_collections: Set[tuple] = set()
|
|
|
|
for collection, value_json in collection_config.items():
|
|
try:
|
|
current_collections.add((workspace, collection))
|
|
|
|
metadata = json.loads(value_json)
|
|
|
|
key = (workspace, collection)
|
|
if key not in self.known_collections:
|
|
logger.info(
|
|
f"New collection detected: {workspace}/{collection}"
|
|
)
|
|
await self.create_collection(
|
|
workspace, collection, metadata
|
|
)
|
|
self.known_collections[key] = metadata
|
|
else:
|
|
if self.known_collections[key] != metadata:
|
|
logger.info(
|
|
f"Collection metadata updated: "
|
|
f"{workspace}/{collection}"
|
|
)
|
|
self.known_collections[key] = metadata
|
|
|
|
except Exception as e:
|
|
logger.error(
|
|
f"Error processing collection config for "
|
|
f"{workspace}/{collection}: {e}",
|
|
exc_info=True,
|
|
)
|
|
|
|
# Find collections for THIS workspace that were deleted (in
|
|
# known but not in current). Only compare collections owned by
|
|
# this workspace — other workspaces' collections are not
|
|
# affected by this config update.
|
|
known_for_ws = {
|
|
(w, c) for (w, c) in self.known_collections.keys()
|
|
if w == workspace
|
|
}
|
|
deleted_collections = known_for_ws - current_collections
|
|
for ws, collection in deleted_collections:
|
|
logger.info(f"Collection deleted: {ws}/{collection}")
|
|
try:
|
|
# Remove from known_collections FIRST to immediately
|
|
# reject new writes
|
|
del self.known_collections[(ws, collection)]
|
|
await self.delete_collection(ws, collection)
|
|
except Exception as e:
|
|
logger.error(
|
|
f"Error deleting collection {ws}/{collection}: {e}",
|
|
exc_info=True,
|
|
)
|
|
|
|
logger.debug(
|
|
f"Collection config processing complete. "
|
|
f"Known collections: {len(self.known_collections)}"
|
|
)
|
|
|
|
async def create_collection(
|
|
self, workspace: str, collection: str, metadata: dict,
|
|
):
|
|
"""
|
|
Create a collection in the storage backend.
|
|
|
|
Subclasses must implement this method.
|
|
|
|
Args:
|
|
workspace: Workspace ID
|
|
collection: Collection ID
|
|
metadata: Collection metadata dictionary
|
|
"""
|
|
raise NotImplementedError(
|
|
"Storage service must implement create_collection method"
|
|
)
|
|
|
|
async def delete_collection(self, workspace: str, collection: str):
|
|
"""
|
|
Delete a collection from the storage backend.
|
|
|
|
Subclasses must implement this method.
|
|
|
|
Args:
|
|
workspace: Workspace ID
|
|
collection: Collection ID
|
|
"""
|
|
raise NotImplementedError(
|
|
"Storage service must implement delete_collection method"
|
|
)
|
|
|
|
def collection_exists(self, workspace: str, collection: str) -> bool:
|
|
"""
|
|
Check if a collection is known to exist.
|
|
|
|
Args:
|
|
workspace: Workspace ID
|
|
collection: Collection ID
|
|
|
|
Returns:
|
|
True if collection exists, False otherwise
|
|
"""
|
|
return (workspace, collection) in self.known_collections
|