fix(tui): stop a stream outlived by /new from leaking into the next conversation

_finish_stream appended the completed reply to self.history - whatever
list that name currently pointed at - not to the conversation the
stream was actually answering. /new reassigns self.history to a fresh
list; a stream still running when that happens finished by silently
appending the old conversation's trailing reply onto the new one, which
then rides along in that new conversation's next /chat/stream history
payload. The conversation_id was already captured by closure for this
exact reason (see the tool-denial path); self.history needed the same
treatment.

nexusos_cli/cli.py

@@ -24,10 +24,8 @@ from . import ncp as services
 CONFIG_SCHEMA = {
     "home": "path",
     "api_url": "url",
-    "memory_url": "url",
     "bind_host": "text",
     "backend_port": "port",
-    "memory_port": "port",
     "provider": "provider",
     "provider_url": "url",
     "provider_timeout": "positive_int",
@@ -39,8 +37,6 @@ CONFIG_SCHEMA = {
 }
 
 LEGACY_TARGETS = {
-    "-m": "memory",
-    "--memory": "memory",
     "-b": "backend",
     "--backend": "backend",
     "-f": "frontend",
@@ -303,14 +299,13 @@ def diagnostics() -> dict:
     )
     add(
         "service ports",
-        all(1 <= port <= 65535 for port in (settings.backend_port, settings.memory_port)),
-        f"backend={settings.backend_port}, memory={settings.memory_port}",
+        1 <= settings.backend_port <= 65535,
+        f"backend={settings.backend_port}",
     )
     for module in ("fastapi", "uvicorn", "httpx", "pydantic", "yaml"):
         add(f"import:{module}", _check_import(module), module)
 
     add("backend", _http_ok(settings.api_url + "/status"), settings.api_url, required=False)
-    add("memory service", _http_ok(settings.memory_url + "/"), settings.memory_url, required=False)
     provider = _provider_payload()
     add("provider", provider["reachable"], provider["url"], required=False)
     if settings.manage_ollama:
@@ -362,7 +357,7 @@ def cmd_doctor(args) -> int:
 
 def service_status() -> dict:
     payload = {}
-    for key in ("backend", "memory", "frontend"):
+    for key in ("backend", "frontend"):
         svc = services.SERVICES[key]
         pid = services.read_pid(svc)
         payload[key] = {
@@ -380,7 +375,7 @@ def cmd_status(args) -> int:
         _emit(payload, True)
         return 0
     print("Nexus Service Status:\n")
-    for key in ("backend", "memory", "frontend"):
+    for key in ("backend", "frontend"):
         info = payload[key]
         suffix = f" (PID {info['pid']})" if info["pid"] else ""
         print(f"  {key:<10} {'RUNNING' if info['running'] else 'STOPPED'}{suffix}  {info['url']}")
@@ -418,7 +413,6 @@ def cmd_tui(args) -> int:
 
 def _target_flag(target: str | None):
     return {
-        "memory": "--memory",
         "backend": "--backend",
         "frontend": "--frontend",
         "ai": "--ai",
@@ -503,18 +497,14 @@ def cmd_serve(args) -> int:
         return 2
 
     settings.backend_port = args.port
-    settings.memory_port = args.memory_port
     settings.bind_host = host
     settings.api_url = f"http://127.0.0.1:{args.port}"
-    settings.memory_url = f"http://127.0.0.1:{args.memory_port}"
     os.environ["NEXUS_BACKEND_PORT"] = str(args.port)
-    os.environ["NEXUS_MEMORY_PORT"] = str(args.memory_port)
     os.environ["NEXUS_BIND_HOST"] = host
     for origin_host in ("localhost", "127.0.0.1"):
-        for port in (args.port, args.memory_port):
-            origin = f"http://{origin_host}:{port}"
-            if origin not in config.ALLOWED_ORIGINS:
-                config.ALLOWED_ORIGINS.append(origin)
+        origin = f"http://{origin_host}:{args.port}"
+        if origin not in config.ALLOWED_ORIGINS:
+            config.ALLOWED_ORIGINS.append(origin)
     if args.allow_lan:
         # Widen to the addresses this bind actually answers on - NOT "*".
         # ALLOWED_HOSTS drives TrustedHostMiddleware, which is the DNS-rebinding
@@ -526,10 +516,9 @@ def cmd_serve(args) -> int:
         for name in names:
             if name not in config.ALLOWED_HOSTS:
                 config.ALLOWED_HOSTS.append(name)
-            for port in (args.port, args.memory_port):
-                origin = f"http://{_origin_host(name)}:{port}"
-                if origin not in config.ALLOWED_ORIGINS:
-                    config.ALLOWED_ORIGINS.append(origin)
+            origin = f"http://{_origin_host(name)}:{args.port}"
+            if origin not in config.ALLOWED_ORIGINS:
+                config.ALLOWED_ORIGINS.append(origin)
         os.environ.setdefault("NEXUS_ALLOWED_HOSTS", ",".join(config.ALLOWED_HOSTS))
         os.environ.setdefault("NEXUS_ALLOWED_ORIGINS", ",".join(config.ALLOWED_ORIGINS))
         print(
@@ -538,35 +527,13 @@ def cmd_serve(args) -> int:
             " has full admin and data access."
         )
 
-    memory_proc = None
-    memory_log = None
-    try:
-        if not args.no_memory and not _http_ok(settings.memory_url + "/"):
-            log_path = settings.runtime_dir / "memory.log"
-            log_path.parent.mkdir(parents=True, exist_ok=True)
-            memory_log = open(log_path, "ab")
-            memory_proc = subprocess.Popen(
-                [sys.executable, "-m", "uvicorn", "synapse.memory.service:app",
-                 "--host", host, "--port", str(args.memory_port)],
-                stdout=memory_log, stderr=subprocess.STDOUT, stdin=subprocess.DEVNULL,
-            )
-            print(f"Memory service starting on {host}:{args.memory_port} (log: {log_path})")
-        print(f"NexusOS serving on http://{host}:{args.port}")
-        import uvicorn
-        uvicorn.run(
-            "synapse.main:sio_app", host=host, port=args.port,
-            reload=bool(args.reload and settings.source_checkout),
-            log_level=args.log_level,
-        )
-    finally:
-        if memory_proc is not None and memory_proc.poll() is None:
-            memory_proc.terminate()
-            try:
-                memory_proc.wait(timeout=5)
-            except subprocess.TimeoutExpired:
-                memory_proc.kill()
-        if memory_log is not None:
-            memory_log.close()
+    print(f"NexusOS serving on http://{host}:{args.port}")
+    import uvicorn
+    uvicorn.run(
+        "synapse.main:sio_app", host=host, port=args.port,
+        reload=bool(args.reload and settings.source_checkout),
+        log_level=args.log_level,
+    )
     return 0
 
 
@@ -626,7 +593,7 @@ def cmd_nvidia_reqs(_args) -> int:
 
 
 def cmd_logs(args) -> int:
-    keys = ("backend", "memory", "frontend") if args.target == "all" else (args.target,)
+    keys = ("backend", "frontend") if args.target == "all" else (args.target,)
     paths = [services.SERVICES[key].log_file for key in keys]
     for path in paths:
         print(f"=== {path.name} ===")
@@ -779,8 +746,7 @@ def build_parser() -> argparse.ArgumentParser:
 
     p = sub.add_parser("serve", help="run NexusOS in the foreground")
     p.add_argument("--host"); p.add_argument("--port", type=_port, default=settings.backend_port)
-    p.add_argument("--memory-port", type=_port, default=settings.memory_port)
-    p.add_argument("--no-memory", action="store_true"); p.add_argument("--allow-lan", action="store_true")
+    p.add_argument("--allow-lan", action="store_true")
     p.add_argument("--reload", action="store_true"); p.add_argument("--log-level", default="info")
     p.set_defaults(fn=cmd_serve)
 
@@ -789,7 +755,7 @@ def build_parser() -> argparse.ArgumentParser:
         ("stop", cmd_stop, "stop background services"),
     ):
         p = sub.add_parser(name, help=help_text)
-        p.add_argument("target", nargs="?", choices=["all", "backend", "memory", "frontend", "ai"], default="all")
+        p.add_argument("target", nargs="?", choices=["all", "backend", "frontend", "ai"], default="all")
         p.set_defaults(fn=fn)
     sub.add_parser("restart", aliases=["refresh"], help="restart all services").set_defaults(fn=cmd_refresh)
     sub.add_parser("kill", help="force-stop NexusOS-owned processes").set_defaults(fn=lambda _a: services.cmd_kill() or 0)
@@ -799,7 +765,7 @@ def build_parser() -> argparse.ArgumentParser:
     sub.add_parser("web", help="legacy desktop alias for open").set_defaults(fn=cmd_web)
     sub.add_parser("panel", help="launch the legacy desktop control panel").set_defaults(fn=cmd_panel)
     p = sub.add_parser("logs", help="read or follow service logs")
-    p.add_argument("target", nargs="?", choices=["all", "backend", "memory", "frontend"], default="all")
+    p.add_argument("target", nargs="?", choices=["all", "backend", "frontend"], default="all")
     p.add_argument("--lines", type=int, choices=range(1, 10001), default=50, metavar="1..10000")
     p.add_argument("--follow", "-f", action="store_true"); p.set_defaults(fn=cmd_logs)
     sub.add_parser("clean", help="remove runtime logs and stale PID files").set_defaults(fn=cmd_clean)