feat(api): implement dynamic max tokens handling for various providers

- Added _max_tokens_param method in AIAgent to return appropriate max tokens parameter based on the provider (OpenAI vs. others).
- Updated API calls in AIAgent to utilize the new max tokens handling.
- Introduced auxiliary_max_tokens_param function in auxiliary_client for consistent max tokens management across auxiliary clients.
- Refactored multiple tools to use auxiliary_max_tokens_param for improved compatibility with different models and providers.

tools/browser_tool.py

@@ -812,10 +812,11 @@ def _extract_relevant_content(
         )
 
     try:
+        from agent.auxiliary_client import auxiliary_max_tokens_param
         response = _aux_vision_client.chat.completions.create(
             model=EXTRACTION_MODEL,
             messages=[{"role": "user", "content": extraction_prompt}],
-            max_tokens=4000,
+            **auxiliary_max_tokens_param(4000),
             temperature=0.1,
         )
         return response.choices[0].message.content
@@ -1283,6 +1284,7 @@ def browser_vision(question: str, task_id: Optional[str] = None) -> str:
         )
 
         # Use the sync auxiliary vision client directly
+        from agent.auxiliary_client import auxiliary_max_tokens_param
         response = _aux_vision_client.chat.completions.create(
             model=EXTRACTION_MODEL,
             messages=[
@@ -1294,7 +1296,7 @@ def browser_vision(question: str, task_id: Optional[str] = None) -> str:
                     ],
                 }
             ],
-            max_tokens=2000,
+            **auxiliary_max_tokens_param(2000),
             temperature=0.1,
         )
         

tools/session_search_tool.py

@@ -170,7 +170,7 @@ async def _summarize_session(
     max_retries = 3
     for attempt in range(max_retries):
         try:
-            from agent.auxiliary_client import get_auxiliary_extra_body
+            from agent.auxiliary_client import get_auxiliary_extra_body, auxiliary_max_tokens_param
             _extra = get_auxiliary_extra_body()
             response = await _async_aux_client.chat.completions.create(
                 model=_SUMMARIZER_MODEL,
@@ -180,7 +180,7 @@ async def _summarize_session(
                 ],
                 **({} if not _extra else {"extra_body": _extra}),
                 temperature=0.1,
-                max_tokens=MAX_SUMMARY_TOKENS,
+                **auxiliary_max_tokens_param(MAX_SUMMARY_TOKENS),
             )
             return response.choices[0].message.content.strip()
         except Exception as e:

tools/vision_tools.py

@@ -314,13 +314,13 @@ async def vision_analyze_tool(
         logger.info("Processing image with %s...", model)
         
         # Call the vision API
-        from agent.auxiliary_client import get_auxiliary_extra_body
+        from agent.auxiliary_client import get_auxiliary_extra_body, auxiliary_max_tokens_param
         _extra = get_auxiliary_extra_body()
         response = await _aux_async_client.chat.completions.create(
             model=model,
             messages=messages,
             temperature=0.1,
-            max_tokens=2000,
+            **auxiliary_max_tokens_param(2000),
             **({} if not _extra else {"extra_body": _extra}),
         )
         

tools/web_tools.py

@@ -242,7 +242,7 @@ Create a markdown summary that captures all key information in a well-organized,
             if _aux_async_client is None:
                 logger.warning("No auxiliary model available for web content processing")
                 return None
-            from agent.auxiliary_client import get_auxiliary_extra_body
+            from agent.auxiliary_client import get_auxiliary_extra_body, auxiliary_max_tokens_param
             _extra = get_auxiliary_extra_body()
             response = await _aux_async_client.chat.completions.create(
                 model=model,
@@ -251,7 +251,7 @@ Create a markdown summary that captures all key information in a well-organized,
                     {"role": "user", "content": user_prompt}
                 ],
                 temperature=0.1,
-                max_tokens=max_tokens,
+                **auxiliary_max_tokens_param(max_tokens),
                 **({} if not _extra else {"extra_body": _extra}),
             )
             return response.choices[0].message.content.strip()
@@ -365,7 +365,7 @@ Create a single, unified markdown summary."""
                 fallback = fallback[:max_output_size] + "\n\n[... truncated ...]"
             return fallback
 
-        from agent.auxiliary_client import get_auxiliary_extra_body
+        from agent.auxiliary_client import get_auxiliary_extra_body, auxiliary_max_tokens_param
         _extra = get_auxiliary_extra_body()
         response = await _aux_async_client.chat.completions.create(
             model=model,
@@ -374,7 +374,7 @@ Create a single, unified markdown summary."""
                 {"role": "user", "content": synthesis_prompt}
             ],
             temperature=0.1,
-            max_tokens=4000,
+            **auxiliary_max_tokens_param(4000),
             **({} if not _extra else {"extra_body": _extra}),
         )
         final_summary = response.choices[0].message.content.strip()