mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-02 03:42:36 +02:00
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.
This commit is contained in:
cybermaggedon
GitHub
parent
9332089b3d
commit
d35473f7f7
377 changed files with 6868 additions and 5785 deletions
|
|
@ -6,9 +6,9 @@ import re
|
|||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
def make_safe_collection_name(user, collection, prefix):
|
||||
def make_safe_collection_name(workspace, collection, prefix):
|
||||
"""
|
||||
Create a safe Milvus collection name from user/collection parameters.
|
||||
Create a safe Milvus collection name from workspace/collection parameters.
|
||||
Milvus only allows letters, numbers, and underscores.
|
||||
"""
|
||||
def sanitize(s):
|
||||
|
|
@ -23,10 +23,10 @@ def make_safe_collection_name(user, collection, prefix):
|
|||
safe = 'default'
|
||||
return safe
|
||||
|
||||
safe_user = sanitize(user)
|
||||
safe_workspace = sanitize(workspace)
|
||||
safe_collection = sanitize(collection)
|
||||
|
||||
return f"{prefix}_{safe_user}_{safe_collection}"
|
||||
return f"{prefix}_{safe_workspace}_{safe_collection}"
|
||||
|
||||
class DocVectors:
|
||||
|
||||
|
|
@ -49,26 +49,26 @@ class DocVectors:
|
|||
self.next_reload = time.time() + self.reload_time
|
||||
logger.debug(f"Reload at {self.next_reload}")
|
||||
|
||||
def collection_exists(self, user, collection):
|
||||
def collection_exists(self, workspace, collection):
|
||||
"""
|
||||
Check if any collection exists for this user/collection combination.
|
||||
Check if any collection exists for this workspace/collection combination.
|
||||
Since collections are dimension-specific, this checks if ANY dimension variant exists.
|
||||
"""
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
prefix = f"{base_name}_"
|
||||
all_collections = self.client.list_collections()
|
||||
return any(coll.startswith(prefix) for coll in all_collections)
|
||||
|
||||
def create_collection(self, user, collection, dimension=384):
|
||||
def create_collection(self, workspace, collection, dimension=384):
|
||||
"""
|
||||
No-op for explicit collection creation.
|
||||
Collections are created lazily on first insert with actual dimension.
|
||||
"""
|
||||
logger.info(f"Collection creation requested for {user}/{collection} - will be created lazily on first insert")
|
||||
logger.info(f"Collection creation requested for {workspace}/{collection} - will be created lazily on first insert")
|
||||
|
||||
def init_collection(self, dimension, user, collection):
|
||||
def init_collection(self, dimension, workspace, collection):
|
||||
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
collection_name = f"{base_name}_{dimension}"
|
||||
|
||||
pkey_field = FieldSchema(
|
||||
|
|
@ -116,15 +116,15 @@ class DocVectors:
|
|||
index_params=index_params
|
||||
)
|
||||
|
||||
self.collections[(dimension, user, collection)] = collection_name
|
||||
self.collections[(dimension, workspace, collection)] = collection_name
|
||||
logger.info(f"Created Milvus collection {collection_name} with dimension {dimension}")
|
||||
|
||||
def insert(self, embeds, chunk_id, user, collection):
|
||||
def insert(self, embeds, chunk_id, workspace, collection):
|
||||
|
||||
dim = len(embeds)
|
||||
|
||||
if (dim, user, collection) not in self.collections:
|
||||
self.init_collection(dim, user, collection)
|
||||
if (dim, workspace, collection) not in self.collections:
|
||||
self.init_collection(dim, workspace, collection)
|
||||
|
||||
data = [
|
||||
{
|
||||
|
|
@ -134,25 +134,25 @@ class DocVectors:
|
|||
]
|
||||
|
||||
self.client.insert(
|
||||
collection_name=self.collections[(dim, user, collection)],
|
||||
collection_name=self.collections[(dim, workspace, collection)],
|
||||
data=data
|
||||
)
|
||||
|
||||
def search(self, embeds, user, collection, fields=["chunk_id"], limit=10):
|
||||
def search(self, embeds, workspace, collection, fields=["chunk_id"], limit=10):
|
||||
|
||||
dim = len(embeds)
|
||||
|
||||
# Check if collection exists - return empty if not
|
||||
if (dim, user, collection) not in self.collections:
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
if (dim, workspace, collection) not in self.collections:
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
collection_name = f"{base_name}_{dim}"
|
||||
if not self.client.has_collection(collection_name):
|
||||
logger.info(f"Collection {collection_name} does not exist, returning empty results")
|
||||
return []
|
||||
# Collection exists but not in cache, add it
|
||||
self.collections[(dim, user, collection)] = collection_name
|
||||
self.collections[(dim, workspace, collection)] = collection_name
|
||||
|
||||
coll = self.collections[(dim, user, collection)]
|
||||
coll = self.collections[(dim, workspace, collection)]
|
||||
|
||||
logger.debug("Loading...")
|
||||
self.client.load_collection(
|
||||
|
|
@ -181,12 +181,12 @@ class DocVectors:
|
|||
|
||||
return res
|
||||
|
||||
def delete_collection(self, user, collection):
|
||||
def delete_collection(self, workspace, collection):
|
||||
"""
|
||||
Delete all dimension variants of the collection for the given user/collection.
|
||||
Delete all dimension variants of the collection for the given workspace/collection.
|
||||
Since collections are created with dimension suffixes, we need to find and delete all.
|
||||
"""
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
prefix = f"{base_name}_"
|
||||
|
||||
# Get all collections and filter for matches
|
||||
|
|
@ -199,10 +199,10 @@ class DocVectors:
|
|||
for collection_name in matching_collections:
|
||||
self.client.drop_collection(collection_name)
|
||||
logger.info(f"Deleted Milvus collection: {collection_name}")
|
||||
logger.info(f"Deleted {len(matching_collections)} collection(s) for {user}/{collection}")
|
||||
logger.info(f"Deleted {len(matching_collections)} collection(s) for {workspace}/{collection}")
|
||||
|
||||
# Remove from our local cache
|
||||
keys_to_remove = [key for key in self.collections.keys() if key[1] == user and key[2] == collection]
|
||||
keys_to_remove = [key for key in self.collections.keys() if key[1] == workspace and key[2] == collection]
|
||||
for key in keys_to_remove:
|
||||
del self.collections[key]
|
||||
|
||||
|
|
|
|||
|
|
@ -6,9 +6,9 @@ import re
|
|||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
def make_safe_collection_name(user, collection, prefix):
|
||||
def make_safe_collection_name(workspace, collection, prefix):
|
||||
"""
|
||||
Create a safe Milvus collection name from user/collection parameters.
|
||||
Create a safe Milvus collection name from workspace/collection parameters.
|
||||
Milvus only allows letters, numbers, and underscores.
|
||||
"""
|
||||
def sanitize(s):
|
||||
|
|
@ -23,10 +23,10 @@ def make_safe_collection_name(user, collection, prefix):
|
|||
safe = 'default'
|
||||
return safe
|
||||
|
||||
safe_user = sanitize(user)
|
||||
safe_workspace = sanitize(workspace)
|
||||
safe_collection = sanitize(collection)
|
||||
|
||||
return f"{prefix}_{safe_user}_{safe_collection}"
|
||||
return f"{prefix}_{safe_workspace}_{safe_collection}"
|
||||
|
||||
class EntityVectors:
|
||||
|
||||
|
|
@ -49,26 +49,26 @@ class EntityVectors:
|
|||
self.next_reload = time.time() + self.reload_time
|
||||
logger.debug(f"Reload at {self.next_reload}")
|
||||
|
||||
def collection_exists(self, user, collection):
|
||||
def collection_exists(self, workspace, collection):
|
||||
"""
|
||||
Check if any collection exists for this user/collection combination.
|
||||
Check if any collection exists for this workspace/collection combination.
|
||||
Since collections are dimension-specific, this checks if ANY dimension variant exists.
|
||||
"""
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
prefix = f"{base_name}_"
|
||||
all_collections = self.client.list_collections()
|
||||
return any(coll.startswith(prefix) for coll in all_collections)
|
||||
|
||||
def create_collection(self, user, collection, dimension=384):
|
||||
def create_collection(self, workspace, collection, dimension=384):
|
||||
"""
|
||||
No-op for explicit collection creation.
|
||||
Collections are created lazily on first insert with actual dimension.
|
||||
"""
|
||||
logger.info(f"Collection creation requested for {user}/{collection} - will be created lazily on first insert")
|
||||
logger.info(f"Collection creation requested for {workspace}/{collection} - will be created lazily on first insert")
|
||||
|
||||
def init_collection(self, dimension, user, collection):
|
||||
def init_collection(self, dimension, workspace, collection):
|
||||
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
collection_name = f"{base_name}_{dimension}"
|
||||
|
||||
pkey_field = FieldSchema(
|
||||
|
|
@ -122,15 +122,15 @@ class EntityVectors:
|
|||
index_params=index_params
|
||||
)
|
||||
|
||||
self.collections[(dimension, user, collection)] = collection_name
|
||||
self.collections[(dimension, workspace, collection)] = collection_name
|
||||
logger.info(f"Created Milvus collection {collection_name} with dimension {dimension}")
|
||||
|
||||
def insert(self, embeds, entity, user, collection, chunk_id=""):
|
||||
def insert(self, embeds, entity, workspace, collection, chunk_id=""):
|
||||
|
||||
dim = len(embeds)
|
||||
|
||||
if (dim, user, collection) not in self.collections:
|
||||
self.init_collection(dim, user, collection)
|
||||
if (dim, workspace, collection) not in self.collections:
|
||||
self.init_collection(dim, workspace, collection)
|
||||
|
||||
data = [
|
||||
{
|
||||
|
|
@ -141,25 +141,25 @@ class EntityVectors:
|
|||
]
|
||||
|
||||
self.client.insert(
|
||||
collection_name=self.collections[(dim, user, collection)],
|
||||
collection_name=self.collections[(dim, workspace, collection)],
|
||||
data=data
|
||||
)
|
||||
|
||||
def search(self, embeds, user, collection, fields=["entity"], limit=10):
|
||||
def search(self, embeds, workspace, collection, fields=["entity"], limit=10):
|
||||
|
||||
dim = len(embeds)
|
||||
|
||||
# Check if collection exists - return empty if not
|
||||
if (dim, user, collection) not in self.collections:
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
if (dim, workspace, collection) not in self.collections:
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
collection_name = f"{base_name}_{dim}"
|
||||
if not self.client.has_collection(collection_name):
|
||||
logger.info(f"Collection {collection_name} does not exist, returning empty results")
|
||||
return []
|
||||
# Collection exists but not in cache, add it
|
||||
self.collections[(dim, user, collection)] = collection_name
|
||||
self.collections[(dim, workspace, collection)] = collection_name
|
||||
|
||||
coll = self.collections[(dim, user, collection)]
|
||||
coll = self.collections[(dim, workspace, collection)]
|
||||
|
||||
logger.debug("Loading...")
|
||||
self.client.load_collection(
|
||||
|
|
@ -188,12 +188,12 @@ class EntityVectors:
|
|||
|
||||
return res
|
||||
|
||||
def delete_collection(self, user, collection):
|
||||
def delete_collection(self, workspace, collection):
|
||||
"""
|
||||
Delete all dimension variants of the collection for the given user/collection.
|
||||
Delete all dimension variants of the collection for the given workspace/collection.
|
||||
Since collections are created with dimension suffixes, we need to find and delete all.
|
||||
"""
|
||||
base_name = make_safe_collection_name(user, collection, self.prefix)
|
||||
base_name = make_safe_collection_name(workspace, collection, self.prefix)
|
||||
prefix = f"{base_name}_"
|
||||
|
||||
# Get all collections and filter for matches
|
||||
|
|
@ -206,10 +206,10 @@ class EntityVectors:
|
|||
for collection_name in matching_collections:
|
||||
self.client.drop_collection(collection_name)
|
||||
logger.info(f"Deleted Milvus collection: {collection_name}")
|
||||
logger.info(f"Deleted {len(matching_collections)} collection(s) for {user}/{collection}")
|
||||
logger.info(f"Deleted {len(matching_collections)} collection(s) for {workspace}/{collection}")
|
||||
|
||||
# Remove from our local cache
|
||||
keys_to_remove = [key for key in self.collections.keys() if key[1] == user and key[2] == collection]
|
||||
keys_to_remove = [key for key in self.collections.keys() if key[1] == workspace and key[2] == collection]
|
||||
for key in keys_to_remove:
|
||||
del self.collections[key]
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue