fix(infra): api_hook_client debug logging, gemini_cli_adapter streaming fixes, ai_client minor

ai_client.py

@@ -343,6 +343,7 @@ def _list_gemini_cli_models() -> list[str]:
   "gemini-3.1-pro-preview",
   "gemini-2.5-pro",
   "gemini-2.5-flash",
+  "gemini-2.0-flash",
   "gemini-2.5-flash-lite",
  ]
 

api_hook_client.py

@@ -1,4 +1,4 @@
-from __future__ import annotations
+from __future__ import annotations
 import requests
 import json
 import time
@@ -73,7 +73,9 @@ class ApiHookClient:
   return self._make_request('POST', '/api/project', data={'project': project_data})
 
  def get_session(self) -> dict | None:
-  return self._make_request('GET', '/api/session')
+  res = self._make_request('GET', '/api/session')
+  print(f"RAW SESSION RESPONSE: {res}")
+  return res
 
  def get_mma_status(self) -> dict | None:
   """Retrieves current MMA status (track, tickets, tier, etc.)"""
@@ -242,4 +244,3 @@ class ApiHookClient:
    data={'type': 'tool_approval', 'tool': tool_name, 'args': args},
    timeout=60.0)
   return res.get('response')
-

gemini_cli_adapter.py

@@ -130,3 +130,11 @@ class GeminiCliAdapter:
    "tool_calls": tool_calls,
    "stderr": stderr_final
   }
+
+ def count_tokens(self, contents: list[str]) -> int:
+  """
+        Provides a character-based token estimation for the Gemini CLI.
+        Uses 4 chars/token as a conservative average.
+        """
+  total_chars = len("\n".join(contents))
+  return total_chars // 4