mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-07 06:12:38 +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.
167 lines
4.3 KiB
Python
167 lines
4.3 KiB
Python
"""
|
|
List all explainability sessions (GraphRAG and Agent) in a collection.
|
|
|
|
Queries for all questions stored in the retrieval graph and displays them
|
|
with their session IDs, type (GraphRAG or Agent), and timestamps.
|
|
|
|
Examples:
|
|
tg-list-explain-traces -U trustgraph -C default
|
|
tg-list-explain-traces --limit 20 --format json
|
|
"""
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
import sys
|
|
from tabulate import tabulate
|
|
from trustgraph.api import Api, ExplainabilityClient
|
|
|
|
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'
|
|
|
|
# Retrieval graph
|
|
RETRIEVAL_GRAPH = "urn:graph:retrieval"
|
|
|
|
|
|
def truncate_text(text, max_len=60):
|
|
"""Truncate text to max length with ellipsis."""
|
|
if not text:
|
|
return ""
|
|
if len(text) <= max_len:
|
|
return text
|
|
return text[:max_len - 3] + "..."
|
|
|
|
|
|
def print_table(sessions):
|
|
"""Print sessions as a table."""
|
|
if not sessions:
|
|
print("No explainability sessions found.")
|
|
return
|
|
|
|
rows = []
|
|
for session in sessions:
|
|
rows.append([
|
|
session["id"],
|
|
session.get("type", "Unknown"),
|
|
truncate_text(session["question"], 45),
|
|
session.get("time", "")
|
|
])
|
|
|
|
headers = ["Session ID", "Type", "Question", "Time"]
|
|
print(tabulate(rows, headers=headers, tablefmt="simple"))
|
|
|
|
|
|
def print_json(sessions):
|
|
"""Print sessions as JSON."""
|
|
print(json.dumps(sessions, indent=2))
|
|
|
|
|
|
# Map type names for display
|
|
TYPE_DISPLAY = {
|
|
"graphrag": "GraphRAG",
|
|
"docrag": "DocRAG",
|
|
"agent": "Agent",
|
|
}
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(
|
|
prog='tg-list-explain-traces',
|
|
description=__doc__,
|
|
formatter_class=argparse.RawDescriptionHelpFormatter,
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-u', '--api-url',
|
|
default=default_url,
|
|
help=f'API URL (default: {default_url})',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-t', '--token',
|
|
default=default_token,
|
|
help='Auth token (default: $TRUSTGRAPH_TOKEN)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-w', '--workspace',
|
|
default=default_workspace,
|
|
help=f'Workspace (default: {default_workspace})',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-C', '--collection',
|
|
default=default_collection,
|
|
help=f'Collection (default: {default_collection})',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-f', '--flow-id',
|
|
default='default',
|
|
help='Flow ID (default: default)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--limit',
|
|
type=int,
|
|
default=50,
|
|
help='Max results (default: 50)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--format',
|
|
choices=['table', 'json'],
|
|
default='table',
|
|
help='Output format: table (default), json',
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
try:
|
|
api = Api(args.api_url, token=args.token, workspace=args.workspace)
|
|
socket = api.socket()
|
|
flow = socket.flow(args.flow_id)
|
|
explain_client = ExplainabilityClient(flow)
|
|
|
|
try:
|
|
# List all sessions — uses persistent websocket via SocketClient
|
|
questions = explain_client.list_sessions(
|
|
graph=RETRIEVAL_GRAPH,
|
|
collection=args.collection,
|
|
limit=args.limit,
|
|
)
|
|
|
|
# detect_session_type is mostly a fast URI pattern check,
|
|
# only falls back to network calls for unrecognised URIs
|
|
sessions = []
|
|
for q in questions:
|
|
session_type = explain_client.detect_session_type(
|
|
q.uri,
|
|
graph=RETRIEVAL_GRAPH,
|
|
collection=args.collection
|
|
)
|
|
|
|
sessions.append({
|
|
"id": q.uri,
|
|
"type": TYPE_DISPLAY.get(session_type, session_type.title()),
|
|
"question": q.query,
|
|
"time": q.timestamp,
|
|
})
|
|
|
|
if args.format == 'json':
|
|
print_json(sessions)
|
|
else:
|
|
print_table(sessions)
|
|
|
|
finally:
|
|
socket.close()
|
|
|
|
except Exception as e:
|
|
print(f"Error: {e}", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|