fix: add missing Responses API parameters for Codex provider

Adds tool_choice, parallel_tool_calls, and prompt_cache_key to the
Codex Responses API request kwargs — matching what the official Codex
CLI sends.

- tool_choice: 'auto' — enables the model to proactively call tools.
  Without this, the model may default to not using tools, which explains
  reports of the agent claiming it lacks shell access (#747).
- parallel_tool_calls: True — allows the model to issue multiple tool
  calls in a single turn for efficiency.
- prompt_cache_key: session_id — enables server-side prompt caching
  across turns in the same session, reducing latency and cost.

Refs #747

run_agent.py

@@ -2340,7 +2340,10 @@ class AIAgent:
                 "instructions": instructions,
                 "input": self._chat_messages_to_responses_input(payload_messages),
                 "tools": self._responses_tools(),
+                "tool_choice": "auto",
+                "parallel_tool_calls": True,
                 "store": False,
+                "prompt_cache_key": self.session_id,
             }
 
             if reasoning_enabled: