fix: reset all retry counters at start of run_conversation()

_incomplete_scratchpad_retries and _codex_incomplete_retries were not
reset at the start of run_conversation(). In CLI mode, where the same
AIAgent instance is reused across conversations, stale counters from
a previous conversation could carry over, causing premature retry
exhaustion and partial responses.

run_agent.py

@@ -2884,6 +2884,8 @@ class AIAgent:
         self._invalid_tool_retries = 0
         self._invalid_json_retries = 0
         self._empty_content_retries = 0
+        self._incomplete_scratchpad_retries = 0
+        self._codex_incomplete_retries = 0
         self._last_content_with_tools = None
         self._turns_since_memory = 0
         self._iters_since_skill = 0