feat(gateway): cache AIAgent per session for prompt caching

The gateway created a fresh AIAgent per message, rebuilding the system
prompt (including memory, skills, context files) every turn. This broke
prompt prefix caching — providers like Anthropic charge ~10x more for
uncached prefixes.

Now caches AIAgent instances per session_key with a config signature.
The cached agent is reused across messages in the same session,
preserving the frozen system prompt and tool schemas. Cache is
invalidated when:
- Config changes (model, provider, toolsets, reasoning, ephemeral
  prompt) — detected via signature mismatch
- /new, /reset, /clear — explicit session reset
- /model — global model change clears all cached agents
- /reasoning — global reasoning change clears all cached agents

Per-message state (callbacks, stream consumers, progress queues) is
set on the agent instance before each run_conversation() call.

This matches CLI behavior where a single AIAgent lives across all turns
in a session, with _cached_system_prompt built once and reused.

tests/gateway/test_run_progress_topics.py

@@ -56,7 +56,7 @@ class ProgressCaptureAdapter(BasePlatformAdapter):
 
 class FakeAgent:
     def __init__(self, **kwargs):
-        self.tool_progress_callback = kwargs["tool_progress_callback"]
+        self.tool_progress_callback = kwargs.get("tool_progress_callback")
         self.tools = []
 
     def run_conversation(self, message, conversation_history=None, task_id=None):