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 2026-04-21 23:23:01 +01:00 committed by GitHub
parent 9332089b3d
commit d35473f7f7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
377 changed files with 6868 additions and 5785 deletions

View file

@ -109,7 +109,8 @@ class TestListConfigItems:
url='http://custom.com',
config_type='prompt',
format_type='json',
token=None
token=None,
workspace='default'
)
def test_list_main_uses_defaults(self):
@ -128,7 +129,8 @@ class TestListConfigItems:
url='http://localhost:8088/',
config_type='prompt',
format_type='text',
token=None
token=None,
workspace='default'
)
@ -196,7 +198,8 @@ class TestGetConfigItem:
config_type='prompt',
key='template-1',
format_type='json',
token=None
token=None,
workspace='default'
)
@ -253,7 +256,8 @@ class TestPutConfigItem:
config_type='prompt',
key='new-template',
value='Custom prompt: {input}',
token=None
token=None,
workspace='default'
)
def test_put_main_with_stdin_arg(self):
@ -278,7 +282,8 @@ class TestPutConfigItem:
config_type='prompt',
key='stdin-template',
value=stdin_content,
token=None
token=None,
workspace='default'
)
def test_put_main_mutually_exclusive_args(self):
@ -334,7 +339,8 @@ class TestDeleteConfigItem:
url='http://custom.com',
config_type='prompt',
key='old-template',
token=None
token=None,
workspace='default'
)

View file

@ -48,7 +48,7 @@ def knowledge_loader():
return KnowledgeLoader(
files=["test.ttl"],
flow="test-flow",
user="test-user",
workspace="test-user",
collection="test-collection",
document_id="test-doc-123",
url="http://test.example.com/",
@ -64,7 +64,7 @@ class TestKnowledgeLoader:
loader = KnowledgeLoader(
files=["file1.ttl", "file2.ttl"],
flow="my-flow",
user="user1",
workspace="user1",
collection="col1",
document_id="doc1",
url="http://example.com/",
@ -73,7 +73,7 @@ class TestKnowledgeLoader:
assert loader.files == ["file1.ttl", "file2.ttl"]
assert loader.flow == "my-flow"
assert loader.user == "user1"
assert loader.workspace == "user1"
assert loader.collection == "col1"
assert loader.document_id == "doc1"
assert loader.url == "http://example.com/"
@ -126,7 +126,7 @@ ex:mary ex:knows ex:bob .
loader = KnowledgeLoader(
files=[f.name],
flow="test-flow",
user="test-user",
workspace="test-user",
collection="test-collection",
document_id="test-doc",
url="http://test.example.com/"
@ -151,7 +151,7 @@ ex:mary ex:knows ex:bob .
loader = KnowledgeLoader(
files=[temp_turtle_file],
flow="test-flow",
user="test-user",
workspace="test-user",
collection="test-collection",
document_id="test-doc",
url="http://test.example.com/",
@ -163,7 +163,8 @@ ex:mary ex:knows ex:bob .
# Verify Api was created with correct parameters
mock_api_class.assert_called_once_with(
url="http://test.example.com/",
token="test-token"
token="test-token",
workspace="test-user"
)
# Verify bulk client was obtained
@ -174,7 +175,6 @@ ex:mary ex:knows ex:bob .
call_args = mock_bulk.import_triples.call_args
assert call_args[1]['flow'] == "test-flow"
assert call_args[1]['metadata']['id'] == "test-doc"
assert call_args[1]['metadata']['user'] == "test-user"
assert call_args[1]['metadata']['collection'] == "test-collection"
# Verify import_entity_contexts was called
@ -198,7 +198,7 @@ class TestCLIArgumentParsing:
'tg-load-knowledge',
'-i', 'doc-123',
'-f', 'my-flow',
'-U', 'my-user',
'-w', 'my-user',
'-C', 'my-collection',
'-u', 'http://custom.example.com/',
'-t', 'my-token',
@ -216,7 +216,7 @@ class TestCLIArgumentParsing:
token='my-token',
flow='my-flow',
files=['file1.ttl', 'file2.ttl'],
user='my-user',
workspace='my-user',
collection='my-collection'
)
@ -242,7 +242,7 @@ class TestCLIArgumentParsing:
# Verify defaults were used
call_args = mock_loader_class.call_args[1]
assert call_args['flow'] == 'default'
assert call_args['user'] == 'trustgraph'
assert call_args['workspace'] == 'default'
assert call_args['collection'] == 'default'
assert call_args['url'] == 'http://localhost:8088/'
assert call_args['token'] is None
@ -287,7 +287,7 @@ class TestErrorHandling:
loader = KnowledgeLoader(
files=[temp_turtle_file],
flow="test-flow",
user="test-user",
workspace="test-user",
collection="test-collection",
document_id="test-doc",
url="http://test.example.com/"

View file

@ -145,7 +145,8 @@ class TestSetToolStructuredQuery:
group=None,
state=None,
applicable_states=None,
token=None
token=None,
workspace='default'
)
def test_set_main_structured_query_no_arguments_needed(self):
@ -326,7 +327,8 @@ class TestSetToolRowEmbeddingsQuery:
group=None,
state=None,
applicable_states=None,
token=None
token=None,
workspace='default'
)
def test_valid_types_includes_row_embeddings_query(self):
@ -471,7 +473,7 @@ class TestShowToolsStructuredQuery:
show_main()
mock_show.assert_called_once_with(url='http://custom.com', token=None)
mock_show.assert_called_once_with(url='http://custom.com', token=None, workspace='default')
class TestShowToolsRowEmbeddingsQuery: