Add Rich token streaming: server SSE + CLI live display + CLI container

Server (agent.py):
- _stream_queues: per-session asyncio.Queue for token chunks
- _push_stream_chunk() / _end_stream() helpers
- Medium tier: astream() with <think> block filtering — real token streaming
- Light tier: full reply pushed as single chunk then [DONE]
- Complex tier: full reply pushed after agent completes then [DONE]
- GET /stream/{session_id} SSE endpoint (data: <chunk>\n\n, data: [DONE]\n\n)
- medium_model promoted to module-level global for astream() access

CLI (cli.py):
- stream_reply(): reads /stream/ SSE, renders tokens live with Rich Live (transient)
- Final reply rendered as Markdown after stream completes
- os.getlogin() replaced with os.getenv("USER") for container compatibility

Dockerfile.cli + docker-compose cli service (profiles: tools):
- Run: docker compose --profile tools run --rm -it cli

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cli.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
 """
-Adolf CLI — interactive REPL for the multi-channel gateway.
+Adolf CLI — interactive REPL with Rich streaming display.
 
 Usage:
-    python3 cli.py [--url http://localhost:8000] [--session cli-alvis]
+    python3 cli.py [--url http://deepagents:8000] [--session cli-alvis]
 """
 
 import argparse
@@ -12,7 +12,13 @@ import os
 import sys
 import urllib.request
 
-GATEWAY = "http://localhost:8000"
+from rich.console import Console
+from rich.live import Live
+from rich.markdown import Markdown
+from rich.text import Text
+
+GATEWAY = "http://deepagents:8000"
+console = Console()
 
 
 def post_message(gateway: str, text: str, session_id: str) -> None:
@@ -20,7 +26,7 @@ def post_message(gateway: str, text: str, session_id: str) -> None:
         "text": text,
         "session_id": session_id,
         "channel": "cli",
-        "user_id": os.getlogin(),
+        "user_id": os.getenv("USER", "user"),
     }).encode()
     req = urllib.request.Request(
         f"{gateway}/message",
@@ -30,33 +36,49 @@ def post_message(gateway: str, text: str, session_id: str) -> None:
     )
     with urllib.request.urlopen(req, timeout=10) as r:
         if r.status != 202:
-            print(f"[error] gateway returned {r.status}", file=sys.stderr)
+            console.print(f"[red][error] gateway returned {r.status}[/red]")
             sys.exit(1)
 
 
-def wait_for_reply(gateway: str, session_id: str, timeout: int = 400) -> str:
-    """Open SSE stream and return first data event."""
+def stream_reply(gateway: str, session_id: str, timeout: int = 400) -> str:
+    """
+    Open the /stream/{session_id} SSE endpoint and display tokens live with
+    Rich. Returns the full assembled reply text.
+    """
     req = urllib.request.Request(
-        f"{gateway}/reply/{session_id}",
+        f"{gateway}/stream/{session_id}",
         headers={"Accept": "text/event-stream"},
     )
+    buffer = ""
     with urllib.request.urlopen(req, timeout=timeout + 5) as r:
-        for raw_line in r:
-            line = raw_line.decode("utf-8").rstrip("\n")
-            if line.startswith("data:"):
-                return line[5:].strip().replace("\\n", "\n")
-    return ""
+        with Live(Text(""), console=console, refresh_per_second=20, transient=True) as live:
+            for raw_line in r:
+                line = raw_line.decode("utf-8").rstrip("\n")
+                if not line.startswith("data:"):
+                    continue
+                chunk = line[5:].strip()
+                if chunk == "[DONE]":
+                    break
+                chunk = chunk.replace("\\n", "\n")
+                buffer += chunk
+                live.update(Text(buffer))
+
+    # Render the complete reply as Markdown once streaming is done
+    console.print(Markdown(buffer))
+    return buffer
 
 
 def main():
     parser = argparse.ArgumentParser(description="Adolf CLI")
     parser.add_argument("--url", default=GATEWAY, help="Gateway URL")
-    parser.add_argument("--session", default=f"cli-{os.getlogin()}", help="Session ID")
+    parser.add_argument("--session", default=f"cli-{os.getenv('USER', 'user')}",
+                        help="Session ID")
     parser.add_argument("--timeout", type=int, default=400, help="Reply timeout (seconds)")
     args = parser.parse_args()
 
-    print(f"Adolf CLI  (session={args.session}, gateway={args.url})")
-    print("Type your message and press Enter. Ctrl+C or Ctrl+D to exit.\n")
+    console.print(f"[bold]Adolf CLI[/bold]  (session=[cyan]{args.session}[/cyan], "
+                  f"gateway=[cyan]{args.url}[/cyan])")
+    console.print("Type your message and press Enter. Ctrl+C or Ctrl+D to exit.\n")
 
     try:
         while True:
@@ -68,12 +90,11 @@ def main():
                 continue
 
             post_message(args.url, text, args.session)
-            print("...", end="", flush=True)
-            reply = wait_for_reply(args.url, args.session, timeout=args.timeout)
-            print(f"\r{reply}\n")
+            stream_reply(args.url, args.session, timeout=args.timeout)
+            console.print()
 
     except KeyboardInterrupt:
-        print("\nbye")
+        console.print("\n[dim]bye[/dim]")
 
 
 if __name__ == "__main__":