checkpoint: Working on getting gemini cli to actually have parity with gemini api.

ai_client.py

@@ -13,6 +13,7 @@ during chat creation to avoid massive history bloat.
 # ai_client.py
 import tomllib
 import json
+import sys
 import time
 import datetime
 import hashlib
@@ -267,7 +268,16 @@ def _classify_deepseek_error(exc: Exception) -> ProviderError:
 def set_provider(provider: str, model: str):
     global _provider, _model
     _provider = provider
-    _model = model
+    
+    if provider == "gemini_cli":
+        valid_models = _list_gemini_cli_models()
+        # If model is invalid or belongs to another provider (like deepseek), force default
+        if model not in valid_models or model.startswith("deepseek"):
+            _model = "gemini-3-flash-preview"
+        else:
+            _model = model
+    else:
+        _model = model
 
 
 
@@ -298,6 +308,7 @@ def reset_session():
     _gemini_cache_created_at = None
     if _gemini_cli_adapter:
         _gemini_cli_adapter.session_id = None
+    _gemini_cli_adapter = None
     _anthropic_client = None
     with _anthropic_history_lock:
         _anthropic_history = []
@@ -336,9 +347,26 @@ def list_models(provider: str) -> list[str]:
         return _list_anthropic_models()
     elif provider == "deepseek":
         return _list_deepseek_models(creds["deepseek"]["api_key"])
+    elif provider == "gemini_cli":
+        return _list_gemini_cli_models()
     return []
 
 
+def _list_gemini_cli_models() -> list[str]:
+    """
+    List available Gemini models for the CLI.
+    Since the CLI doesn't have a direct 'list models' command yet,
+    we return a curated list of supported models based on CLI metadata.
+    """
+    return [
+        "gemini-3-flash-preview",
+        "gemini-3.1-pro-preview",
+        "gemini-2.5-pro",
+        "gemini-2.5-flash",
+        "gemini-2.5-flash-lite",
+    ]
+
+
 def _list_gemini_models(api_key: str) -> list[str]:
 
     try:
@@ -844,33 +872,45 @@ def _send_gemini_cli(md_content: str, user_message: str, base_dir: str,
     try:
         if _gemini_cli_adapter is None:
             _gemini_cli_adapter = GeminiCliAdapter(binary_path="gemini")
+        
+        adapter = _gemini_cli_adapter
 
         mcp_client.configure(file_items or [], [base_dir])
 
-        # If it's a new session (session_id is None), we should ideally send the context.
+        # Construct the system instruction, combining the base system prompt and the current context.
+        sys_instr = f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"
+        safety_settings = [{'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'threshold': 'BLOCK_ONLY_HIGH'}]
+
+        # Initial payload for the first message
         payload = user_message
-        if _gemini_cli_adapter.session_id is None:
-            # Prepend context and discussion history to the first message
-            full_prompt = f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>\n\n"
+        if adapter.session_id is None:
             if discussion_history:
-                full_prompt += f"[DISCUSSION HISTORY]\n\n{discussion_history}\n\n---\n\n"
-            full_prompt += user_message
-            payload = full_prompt
+                payload = f"[DISCUSSION HISTORY]\n\n{discussion_history}\n\n---\n\n{user_message}"
 
         all_text = []
         _cumulative_tool_bytes = 0
 
         for r_idx in range(MAX_TOOL_ROUNDS + 2):
+            if adapter is None:
+                break
+
             events.emit("request_start", payload={"provider": "gemini_cli", "model": _model, "round": r_idx})
             _append_comms("OUT", "request", {"message": f"[CLI] [round {r_idx}] [msg {len(payload)}]"})
 
-            resp_data = _gemini_cli_adapter.send(payload)
+            resp_data = adapter.send(payload, safety_settings=safety_settings, system_instruction=sys_instr, model=_model)
+            
+            # Log any stderr from the CLI for transparency
+            cli_stderr = resp_data.get("stderr", "")
+            if cli_stderr:
+                sys.stderr.write(f"\n--- Gemini CLI stderr ---\n{cli_stderr}\n-------------------------\n")
+                sys.stderr.flush()
+
             txt = resp_data.get("text", "")
             if txt: all_text.append(txt)
 
             calls = resp_data.get("tool_calls", [])
-            usage = _gemini_cli_adapter.last_usage or {}
-            latency = _gemini_cli_adapter.last_latency
+            usage = adapter.last_usage or {}
+            latency = adapter.last_latency
 
             events.emit("response_received", payload={"provider": "gemini_cli", "model": _model, "usage": usage, "latency": latency, "round": r_idx})