fix: Windows unicode output and config model names

- Force UTF-8 stdout/stderr on Windows to handle LLM unicode output
- Replace ─ (U+2500) with - for Windows cp1251 compatibility
- Sanitize em-dash in session filenames
- Update default model to glm-5.1 in all roles

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

meeting_room/cli.py

@@ -10,6 +10,12 @@ import os
 import sys
 from datetime import datetime
 
+# Force UTF-8 output on Windows (cp1251 can't handle LLM unicode output)
+if sys.stdout.encoding != "utf-8":
+    sys.stdout.reconfigure(encoding="utf-8", errors="replace")
+if sys.stderr.encoding != "utf-8":
+    sys.stderr.reconfigure(encoding="utf-8", errors="replace")
+
 from meeting_room.api_client import APIClient
 from meeting_room.config import find_workspace_config, load_config, load_discussion_config
 from meeting_room.engine import DiscussionEngine
@@ -201,7 +207,7 @@ def save_session(conversation: list[dict], scenario_name: str, sessions_dir: str
     """Save discussion result to a JSON file."""
     os.makedirs(sessions_dir, exist_ok=True)
     timestamp = datetime.now().strftime("%Y-%m-%d_%H%M%S")
-    safe_name = scenario_name.replace(" ", "-").lower()
+    safe_name = scenario_name.replace(" ", "-").replace("—", "-").lower()
     filename = f"{timestamp}_{safe_name}.json"
     filepath = os.path.join(sessions_dir, filename)
 
@@ -253,7 +259,7 @@ def _subscribe_cli_handlers(bus: EventEmitter, max_rounds: int) -> None:
             print()
 
         print(f"{BOLD}Rounds:{RESET} {data['rounds']}")
-        print(f"{DIM}{'─' * 60}{RESET}\n")
+        print(f"{DIM}{'-' * 60}{RESET}\n")
 
     def on_round_start(event) -> None:
         data = event.data
@@ -285,7 +291,7 @@ def _subscribe_cli_handlers(bus: EventEmitter, max_rounds: int) -> None:
         print(f"  [Error: {data['error']}]")
 
     def on_round_end(event) -> None:
-        print(f"{DIM}{'─' * 60}{RESET}\n")
+        print(f"{DIM}{'-' * 60}{RESET}\n")
 
     def on_discussion_end(event) -> None:
         data = event.data

meeting_room/config/config.yaml

@@ -37,7 +37,7 @@ roles:
   moderator:
     name: "Moderator"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 0.7
     tools: "none"
     system_prompt: |
@@ -49,7 +49,7 @@ roles:
   skeptic:
     name: "Skeptic"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 0.9
     tools: "readonly"
     system_prompt: |
@@ -61,7 +61,7 @@ roles:
   idea_generator:
     name: "Idea Generator"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 1.0
     tools: "web"
     system_prompt: |
@@ -74,7 +74,7 @@ roles:
   analyst:
     name: "Analyst"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 0.5
     tools: "all"
     system_prompt: |
@@ -88,7 +88,7 @@ roles:
   defender:
     name: "Defender"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 0.6
     tools: "readonly"
     system_prompt: |
@@ -100,7 +100,7 @@ roles:
   attacker:
     name: "Attacker"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 0.9
     tools: "readonly"
     system_prompt: |
@@ -113,7 +113,7 @@ roles:
   security:
     name: "Security"
     provider: ollama_cloud
-    model: "gpt-4o-mini"
+    model: "glm-5.1"
     temperature: 0.4
     tools: "web"
     system_prompt: |