expose tunings.

ai_client.py

@@ -19,7 +19,14 @@ import file_cache
 import mcp_client
 
 _provider: str = "gemini"
-_model: str = "gemini-2.0-flash"
+_model: str = "gemini-2.5-flash"
+_temperature: float = 0.0
+_max_tokens: int = 8192
+
+def set_model_params(temp: float, max_tok: int):
+    global _temperature, _max_tokens
+    _temperature = temp
+    _max_tokens = max_tok
 
 _gemini_client = None
 _gemini_chat = None
@@ -445,7 +452,13 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str, file_items:
             _append_comms("OUT", "request", {"message": "[CONTEXT CHANGED] Rebuilding cache and chat session..."})
 
         if not _gemini_chat:
-            chat_config = types.GenerateContentConfig(system_instruction=sys_instr, tools=tools_decl)
+            chat_config = types.GenerateContentConfig(
+                system_instruction=sys_instr,
+                tools=tools_decl,
+                temperature=_temperature,
+                max_output_tokens=_max_tokens,
+                safety_settings=[types.SafetySetting(category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="BLOCK_ONLY_HIGH")]
+            )
             try:
                 # Gemini requires 1024 (Flash) or 4096 (Pro) tokens to cache.
                 _gemini_cache = _gemini_client.caches.create(
@@ -456,7 +469,12 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str, file_items:
                         ttl="3600s",
                     )
                 )
-                chat_config = types.GenerateContentConfig(cached_content=_gemini_cache.name)
+                chat_config = types.GenerateContentConfig(
+                    cached_content=_gemini_cache.name,
+                    temperature=_temperature,
+                    max_output_tokens=_max_tokens,
+                    safety_settings=[types.SafetySetting(category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="BLOCK_ONLY_HIGH")]
+                )
                 _append_comms("OUT", "request", {"message": f"[CACHE CREATED] {_gemini_cache.name}"})
             except Exception as e:
                 # Fallback if under token limit or API error
@@ -771,7 +789,8 @@ def _send_anthropic(md_content: str, user_message: str, base_dir: str, file_item
 
             response = _anthropic_client.messages.create(
                 model=_model,
-                max_tokens=16384,
+                max_tokens=_max_tokens,
+                temperature=_temperature,
                 system=system_blocks,
                 tools=_build_anthropic_tools(),
                 messages=_anthropic_history,