mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-30 09:45:13 +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.
208 lines
6.2 KiB
Python
208 lines
6.2 KiB
Python
"""
|
|
Uses the RowsQuery service to execute GraphQL queries against structured data
|
|
"""
|
|
|
|
import argparse
|
|
import os
|
|
import json
|
|
import sys
|
|
import csv
|
|
import io
|
|
from trustgraph.api import Api
|
|
from tabulate import tabulate
|
|
|
|
default_url = os.getenv("TRUSTGRAPH_URL", 'http://localhost:8088/')
|
|
default_token = os.getenv("TRUSTGRAPH_TOKEN", None)
|
|
default_workspace = os.getenv("TRUSTGRAPH_WORKSPACE", "default")
|
|
default_collection = 'default'
|
|
|
|
def format_output(data, output_format, token=None, workspace="default"):
|
|
"""Format GraphQL response data in the specified format"""
|
|
if not data:
|
|
return "No data returned"
|
|
|
|
# Handle case where data contains multiple query results
|
|
if len(data) == 1:
|
|
# Single query result - extract the list
|
|
query_name, result_list = next(iter(data.items()))
|
|
if isinstance(result_list, list):
|
|
return format_table_data(result_list, query_name, output_format)
|
|
|
|
# Multiple queries or non-list data - use JSON format
|
|
if output_format == 'json':
|
|
return json.dumps(data, indent=2)
|
|
else:
|
|
return json.dumps(data, indent=2) # Fallback to JSON
|
|
|
|
def format_table_data(rows, table_name, output_format):
|
|
"""Format a list of rows in the specified format"""
|
|
if not rows:
|
|
return f"No {table_name} found"
|
|
|
|
if output_format == 'json':
|
|
return json.dumps({table_name: rows}, indent=2)
|
|
|
|
elif output_format == 'csv':
|
|
# Get field names in order from first row, then add any missing ones
|
|
fieldnames = list(rows[0].keys()) if rows else []
|
|
# Add any additional fields from other rows that might be missing
|
|
all_fields = set(fieldnames)
|
|
for row in rows:
|
|
for field in row.keys():
|
|
if field not in all_fields:
|
|
fieldnames.append(field)
|
|
all_fields.add(field)
|
|
|
|
# Create CSV string
|
|
output = io.StringIO()
|
|
writer = csv.DictWriter(output, fieldnames=fieldnames)
|
|
writer.writeheader()
|
|
writer.writerows(rows)
|
|
return output.getvalue().rstrip()
|
|
|
|
elif output_format == 'table':
|
|
# Get field names in order from first row, then add any missing ones
|
|
fieldnames = list(rows[0].keys()) if rows else []
|
|
# Add any additional fields from other rows that might be missing
|
|
all_fields = set(fieldnames)
|
|
for row in rows:
|
|
for field in row.keys():
|
|
if field not in all_fields:
|
|
fieldnames.append(field)
|
|
all_fields.add(field)
|
|
|
|
# Create table data
|
|
table_data = []
|
|
for row in rows:
|
|
table_row = [row.get(field, '') for field in fieldnames]
|
|
table_data.append(table_row)
|
|
|
|
return tabulate(table_data, headers=fieldnames, tablefmt='pretty')
|
|
|
|
else:
|
|
return json.dumps({table_name: rows}, indent=2)
|
|
|
|
def rows_query(
|
|
url, flow_id, query, collection, variables, operation_name, output_format='table', token=None, workspace="default"
|
|
):
|
|
|
|
api = Api(url, token=token, workspace=workspace).flow().id(flow_id)
|
|
|
|
# Parse variables if provided as JSON string
|
|
parsed_variables = {}
|
|
if variables:
|
|
try:
|
|
parsed_variables = json.loads(variables)
|
|
except json.JSONDecodeError as e:
|
|
print(f"Error parsing variables JSON: {e}", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
resp = api.rows_query(
|
|
query=query,
|
|
collection=collection,
|
|
variables=parsed_variables if parsed_variables else None,
|
|
operation_name=operation_name
|
|
)
|
|
|
|
# Check for GraphQL errors
|
|
if "errors" in resp and resp["errors"]:
|
|
print("GraphQL Errors:", file=sys.stderr)
|
|
for error in resp["errors"]:
|
|
print(f" - {error.get('message', 'Unknown error')}", file=sys.stderr)
|
|
if "path" in error and error["path"]:
|
|
print(f" Path: {error['path']}", file=sys.stderr)
|
|
# Still print data if available
|
|
if "data" in resp and resp["data"]:
|
|
print(format_output(resp["data"], output_format))
|
|
sys.exit(1)
|
|
|
|
# Print the data
|
|
if "data" in resp:
|
|
print(format_output(resp["data"], output_format))
|
|
else:
|
|
print("No data returned", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
def main():
|
|
|
|
parser = argparse.ArgumentParser(
|
|
prog='tg-invoke-rows-query',
|
|
description=__doc__,
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-u', '--url',
|
|
default=default_url,
|
|
help=f'API URL (default: {default_url})',
|
|
)
|
|
parser.add_argument(
|
|
'-t', '--token',
|
|
default=default_token,
|
|
help='Authentication token (default: $TRUSTGRAPH_TOKEN)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-w', '--workspace',
|
|
default=default_workspace,
|
|
help=f'Workspace (default: {default_workspace})',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-f', '--flow-id',
|
|
default="default",
|
|
help=f'Flow ID (default: default)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-q', '--query',
|
|
required=True,
|
|
help='GraphQL query to execute',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-C', '--collection',
|
|
default=default_collection,
|
|
help=f'Collection ID (default: {default_collection})'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-v', '--variables',
|
|
help='GraphQL variables as JSON string (e.g., \'{"limit": 5}\')'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-o', '--operation-name',
|
|
help='Operation name for multi-operation GraphQL documents'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--format',
|
|
choices=['table', 'json', 'csv'],
|
|
default='table',
|
|
help='Output format (default: table)'
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
try:
|
|
|
|
rows_query(
|
|
url=args.url,
|
|
flow_id=args.flow_id,
|
|
query=args.query,
|
|
collection=args.collection,
|
|
variables=args.variables,
|
|
operation_name=args.operation_name,
|
|
output_format=args.format,
|
|
token=args.token,
|
|
workspace=args.workspace,
|
|
|
|
)
|
|
|
|
except Exception as e:
|
|
|
|
print("Exception:", e, flush=True, file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|