Per-workspace queue routing for workspace-scoped services (#862)

Workspace identity is now determined by queue infrastructure instead of
message body fields, closing a privilege-escalation vector where a caller
could spoof workspace in the request payload.

- Add WorkspaceProcessor base class: discovers workspaces from config at
  startup, creates per-workspace consumers (queue:workspace), and manages
  consumer lifecycle on workspace create/delete events
- Roll out to librarian, flow-svc, knowledge cores, and config-svc
- Config service gets a dual-queue regime: a system queue for
  cross-workspace ops (getvalues-all-ws, bootstrapper writes to
  __workspaces__) and per-workspace queues for tenant-scoped ops, with
  workspace discovery from its own Cassandra store
- Remove workspace field from request schemas (FlowRequest,
  LibrarianRequest, KnowledgeRequest, CollectionManagementRequest) and
  from DocumentMetadata / ProcessingMetadata — table stores now accept
  workspace as an explicit parameter
- Strip workspace encode/decode from all message translators and gateway
  serializers
- Gateway enforces workspace existence: reject requests targeting
  non-existent workspaces instead of routing to queues with no consumer
- Config service provisions new workspaces from __template__ on creation
- Add workspace lifecycle hooks to AsyncProcessor so any processor can
  react to workspace create/delete without subclassing WorkspaceProcessor

trustgraph-cli/trustgraph/cli/show_flow_state.py

@@ -22,15 +22,15 @@ def dump_status(metrics_url, api_url, flow_id, token=None,
 
     print()
     print(f"Flow {flow_id}")
-    show_processors(metrics_url, flow_id)
+    show_processors(metrics_url, flow_id, token=token)
 
     print()
     print(f"Blueprint {blueprint_name}")
-    show_processors(metrics_url, blueprint_name)
+    show_processors(metrics_url, blueprint_name, token=token)
 
     print()
 
-def show_processors(metrics_url, flow_label):
+def show_processors(metrics_url, flow_label, token=None):
 
     url = f"{metrics_url}/query"
 
@@ -40,7 +40,11 @@ def show_processors(metrics_url, flow_label):
         "query": "consumer_state{" + expr + "}"
     }
 
-    resp = requests.get(url, params=params)
+    headers = {}
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+
+    resp = requests.get(url, params=params, headers=headers)
 
     obj = resp.json()
 

trustgraph-cli/trustgraph/cli/show_processor_state.py

@@ -2,16 +2,22 @@
 Dump out TrustGraph processor states.
 """
 
+import os
 import requests
 import argparse
 
 default_metrics_url = "http://localhost:8088/api/metrics"
+DEFAULT_TOKEN = os.getenv("TRUSTGRAPH_TOKEN", None)
 
-def dump_status(url):
+def dump_status(metrics_url, token=None):
 
-    url = f"{url}/query?query=processor_info"
+    url = f"{metrics_url}/query?query=processor_info"
 
-    resp = requests.get(url)
+    headers = {}
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+
+    resp = requests.get(url, headers=headers)
 
     obj = resp.json()
 
@@ -39,11 +45,17 @@ def main():
         help=f'Metrics URL (default: {default_metrics_url})',
     )
 
+    parser.add_argument(
+        '-t', '--token',
+        default=DEFAULT_TOKEN,
+        help=f'Bearer token for authentication (default: TRUSTGRAPH_TOKEN env var)',
+    )
+
     args = parser.parse_args()
 
     try:
 
-        dump_status(args.metrics_url)
+        dump_status(args.metrics_url, args.token)
 
     except Exception as e:
 

trustgraph-cli/trustgraph/cli/show_token_rate.py

@@ -3,12 +3,14 @@ Dump out a stream of token rates, input, output and total.  This is averaged
 across the time since tg-show-token-rate is started.
 """
 
+import os
 import requests
 import argparse
 import json
 import time
 
 default_metrics_url = "http://localhost:8088/api/metrics"
+DEFAULT_TOKEN = os.getenv("TRUSTGRAPH_TOKEN", None)
 
 class Collate:
 
@@ -36,16 +38,20 @@ class Collate:
 
         return delta/time, self.total/self.time
 
-def dump_status(metrics_url, number_samples, period):
+def dump_status(metrics_url, number_samples, period, token=None):
 
     input_url = f"{metrics_url}/query?query=input_tokens_total"
     output_url = f"{metrics_url}/query?query=output_tokens_total"
 
-    resp = requests.get(input_url)
+    headers = {}
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+
+    resp = requests.get(input_url, headers=headers)
     obj = resp.json()
     input = Collate(obj)
 
-    resp = requests.get(output_url)
+    resp = requests.get(output_url, headers=headers)
     obj = resp.json()
     output = Collate(obj)
 
@@ -56,20 +62,20 @@ def dump_status(metrics_url, number_samples, period):
 
         time.sleep(period)
 
-        resp = requests.get(input_url)
+        resp = requests.get(input_url, headers=headers)
         obj = resp.json()
         inr, inl = input.record(obj, period)
 
-        resp = requests.get(output_url)
+        resp = requests.get(output_url, headers=headers)
         obj = resp.json()
         outr, outl = output.record(obj, period)
-        
+
         print(f"{inl:10.1f} {outl:10.1f} {inl+outl:10.1f}")
 
 def main():
 
     parser = argparse.ArgumentParser(
-        prog='tg-show-processor-state',
+        prog='tg-show-token-rate',
         description=__doc__,
     )
 
@@ -93,6 +99,12 @@ def main():
         help=f'Metrics period (default: 100)',
     )
 
+    parser.add_argument(
+        '-t', '--token',
+        default=DEFAULT_TOKEN,
+        help=f'Bearer token for authentication (default: TRUSTGRAPH_TOKEN env var)',
+    )
+
     args = parser.parse_args()
 
     try: