auto-coder 0.1.334__py3-none-any.whl → 0.1.340__py3-none-any.whl

autocoder/agent/agentic_edit_tools/write_to_file_tool_resolver.py

@@ -0,0 +1,98 @@
+import os
+import re
+from typing import Dict, Any, Optional, List, Tuple
+from .base_tool_resolver import BaseToolResolver
+from autocoder.agent.agentic_edit_types import WriteToFileTool, ToolResult  # Import ToolResult from types
+from loguru import logger
+
+
+class WriteToFileToolResolver(BaseToolResolver):
+    def __init__(self, agent: Optional[Any], tool: WriteToFileTool, args: Dict[str, Any]):
+        super().__init__(agent, tool, args)
+        self.tool: WriteToFileTool = tool  # For type hinting
+
+    def parse_diff(self, diff_content: str) -> List[Tuple[str, str]]:
+        """
+        Parses the diff content into a list of (search_block, replace_block) tuples.
+        """
+        blocks = []
+        # Regex to find SEARCH/REPLACE blocks, handling potential variations in line endings
+        pattern = re.compile(r"<<<<<<< SEARCH\r?\n(.*?)\r?\n=======\r?\n(.*?)\r?\n>>>>>>> REPLACE", re.DOTALL)
+        matches = pattern.findall(diff_content)
+        for search_block, replace_block in matches:
+            blocks.append((search_block, replace_block))
+        if not matches and diff_content.strip():
+            logger.warning(f"Could not parse any SEARCH/REPLACE blocks from diff: {diff_content}")
+        return blocks
+
+    def resolve(self) -> ToolResult:
+        file_path = self.tool.path
+        content = self.tool.content
+        source_dir = self.args.source_dir or "."
+        absolute_path = os.path.abspath(os.path.join(source_dir, file_path))
+
+        # Security check: ensure the path is within the source directory
+        if not absolute_path.startswith(os.path.abspath(source_dir)):
+            return ToolResult(success=False, message=f"Error: Access denied. Attempted to write file outside the project directory: {file_path}")
+
+        try:
+            # Create directories if they don't exist
+            os.makedirs(os.path.dirname(absolute_path), exist_ok=True)
+
+            # Check if the content contains SEARCH/REPLACE blocks
+            parsed_blocks = self.parse_diff(content)
+            if parsed_blocks:
+                # If file exists, read its current content
+                if os.path.exists(absolute_path):
+                    try:
+                        with open(absolute_path, 'r', encoding='utf-8', errors='replace') as f:
+                            original_content = f.read()
+                    except Exception as e:
+                        logger.error(f"Error reading existing file '{file_path}' for diff apply: {str(e)}")
+                        return ToolResult(success=False, message=f"An error occurred while reading the existing file: {str(e)}")
+                else:
+                    # If file does not exist, start with empty content
+                    original_content = ""
+
+                current_content = original_content
+                applied_count = 0
+                errors = []
+
+                for i, (search_block, replace_block) in enumerate(parsed_blocks):
+                    start_index = current_content.find(search_block)
+                    if start_index != -1:
+                        current_content = (
+                            current_content[:start_index]
+                            + replace_block
+                            + current_content[start_index + len(search_block):]
+                        )
+                        applied_count += 1
+                        logger.info(f"Applied SEARCH/REPLACE block {i+1} in file {file_path}")
+                    else:
+                        error_message = f"SEARCH block {i+1} not found in current content. Search block:\n---\n{search_block}\n---"
+                        logger.warning(error_message)
+                        errors.append(error_message)
+                        # Continue with next block
+
+                try:
+                    with open(absolute_path, 'w', encoding='utf-8') as f:
+                        f.write(current_content)
+                    message = f"Successfully applied {applied_count}/{len(parsed_blocks)} changes to file: {file_path}."
+                    if errors:
+                        message += "\nWarnings:\n" + "\n".join(errors)
+                    logger.info(message)
+                    return ToolResult(success=True, message=message, content=current_content)
+                except Exception as e:
+                    logger.error(f"Error writing replaced content to file '{file_path}': {str(e)}")
+                    return ToolResult(success=False, message=f"An error occurred while writing the modified file: {str(e)}")
+            else:
+                # No diff blocks detected, treat as full content overwrite
+                with open(absolute_path, 'w', encoding='utf-8') as f:
+                    f.write(content)
+
+                logger.info(f"Successfully wrote to file: {file_path}")
+                return ToolResult(success=True, message=f"Successfully wrote to file: {file_path}", content=content)
+
+        except Exception as e:
+            logger.error(f"Error writing to file '{file_path}': {str(e)}")
+            return ToolResult(success=False, message=f"An error occurred while writing to the file: {str(e)}")

autocoder/agent/agentic_edit_types.py

@@ -0,0 +1,124 @@
+from pydantic import BaseModel
+from typing import List, Dict, Any, Callable, Optional, Type
+from pydantic import SkipValidation
+
+
+# Result class used by Tool Resolvers
+class ToolResult(BaseModel):
+    success: bool
+    message: str
+    content: Any = None # Can store file content, command output, etc.
+
+# Pydantic Models for Tools
+class BaseTool(BaseModel):
+    pass
+
+class ExecuteCommandTool(BaseTool):
+    command: str
+    requires_approval: bool
+
+class ReadFileTool(BaseTool):
+    path: str
+
+class WriteToFileTool(BaseTool):
+    path: str
+    content: str
+
+class ReplaceInFileTool(BaseTool):
+    path: str
+    diff: str
+
+class SearchFilesTool(BaseTool):
+    path: str
+    regex: str
+    file_pattern: Optional[str] = None
+
+class ListFilesTool(BaseTool):
+    path: str
+    recursive: Optional[bool] = False
+
+class ListCodeDefinitionNamesTool(BaseTool):
+    path: str
+
+class AskFollowupQuestionTool(BaseTool):
+    question: str
+    options: Optional[List[str]] = None
+
+class AttemptCompletionTool(BaseTool):
+    result: str
+    command: Optional[str] = None
+
+class PlanModeRespondTool(BaseTool):
+    response: str
+    options: Optional[List[str]] = None
+
+class UseMcpTool(BaseTool):
+    server_name: str
+    tool_name: str
+    arguments: Dict[str, Any]
+
+class PlainTextOutput(BaseModel):
+    text: str
+
+
+# Mapping from tool tag names to Pydantic models
+TOOL_MODEL_MAP: Dict[str, Type[BaseTool]] = {
+    "execute_command": ExecuteCommandTool,
+    "read_file": ReadFileTool,
+    "write_to_file": WriteToFileTool,
+    "replace_in_file": ReplaceInFileTool,
+    "search_files": SearchFilesTool,
+    "list_files": ListFilesTool,
+    "list_code_definition_names": ListCodeDefinitionNamesTool,
+    "ask_followup_question": AskFollowupQuestionTool,
+    "attempt_completion": AttemptCompletionTool,
+    "plan_mode_respond": PlanModeRespondTool,
+    "use_mcp_tool": UseMcpTool,
+}
+
+
+class AgenticEditRequest(BaseModel):
+    user_input: str
+
+
+class FileOperation(BaseModel):
+    path: str
+    operation: str  # e.g., "MODIFY", "REFERENCE", "ADD", "REMOVE"
+class MemoryConfig(BaseModel):
+    """
+    A model to encapsulate memory configuration and operations.
+    """
+
+    memory: Dict[str, Any]
+    save_memory_func: SkipValidation[Callable]
+
+    class Config:
+        arbitrary_types_allowed = True
+
+
+class CommandConfig(BaseModel):
+    coding: SkipValidation[Callable]
+    chat: SkipValidation[Callable]
+    add_files: SkipValidation[Callable]
+    remove_files: SkipValidation[Callable]
+    index_build: SkipValidation[Callable]
+    index_query: SkipValidation[Callable]
+    list_files: SkipValidation[Callable]
+    ask: SkipValidation[Callable]
+    revert: SkipValidation[Callable]
+    commit: SkipValidation[Callable]
+    help: SkipValidation[Callable]
+    exclude_dirs: SkipValidation[Callable]
+    summon: SkipValidation[Callable]
+    design: SkipValidation[Callable]
+    mcp: SkipValidation[Callable]
+    models: SkipValidation[Callable]
+    lib: SkipValidation[Callable]
+    execute_shell_command: SkipValidation[Callable]
+    generate_shell_command: SkipValidation[Callable]
+    conf_export: SkipValidation[Callable]
+    conf_import: SkipValidation[Callable]
+    index_export: SkipValidation[Callable]
+    index_import: SkipValidation[Callable]
+    exclude_files: SkipValidation[Callable]
+

autocoder/agent/agentic_filter.py

@@ -259,8 +259,8 @@ class AgenticFilter:
         3.  **深入分析**:
             *   使用 `read_files` 读取关键文件的内容进行确认。如果文件过大，使用 `line_ranges` 参数分段读取。
             *   如有必要，使用 `run_python` 或 `execute_shell_command` 执行代码或命令进行更复杂的分析。
-        4.  **迭代决策**: 根据工具的返回结果，你可能需要多次调用不同的工具来逐步缩小范围或获取更多信息。
-        5.  **最终响应**: 当你确定了所有需要参考和修改的文件后，**必须**调用 `output_result` 工具，并提供符合其要求格式的JSON字符串作为其 `response` 参数。
+        4.  **迭代决策**: 根据工具的返回结果，你可能需要多次调用不同的工具来逐步缩小范围或获取更多信息。        
+        6.  **最终响应**: 当你确定了所有需要参考和修改的文件后，**必须**调用 `output_result` 工具，并提供符合其要求格式的JSON字符串作为其 `response` 参数。
             该json格式要求为：
             ```json
             {
@@ -273,9 +273,17 @@ class AgenticFilter:
                 "reasoning": "详细说明你是如何通过分析和使用工具得出这个文件列表的。"
             }
             ```
-
-
-        """
+        
+        {% if enable_active_context %}
+        ** 非常非常重要的提示 **
+        每一个目录都有一个描述信息，比如 {{ project_path }}/src/abc/bbc 的目录描述信息会放在 {{ project_path }}/.auto-coder/active-context/src/abc/bbc/active.md 文件中。
+        你可以使用 read_files 函数读取，从而帮助你更好的挑选要详细阅读哪个文件。值得注意的是，active.md 并不会包含该目录下所有的文件信息，只保存最近发生变更的文件的信息。
+        {% endif %}
+        """        
+        return {
+            "project_path": os.path.abspath(self.args.source_dir),
+            "enable_active_context": self.args.enable_active_context,
+        }
 
     @byzerllm.prompt()
     def _execute_command_result(self, result: str) -> str:
@@ -590,8 +598,7 @@ class AgenticFilter:
          - 如果未找到匹配项，会返回提示信息
 
         </usage>
-        </command>
-
+        </command>        
         <command>
         <n>execute_mcp_server</n>
         <description>执行MCP服务器</description>

autocoder/auto_coder.py

@@ -52,6 +52,11 @@ from autocoder.privacy.model_filter import ModelPathFilter
 from autocoder.common.result_manager import ResultManager
 from autocoder.events.event_manager_singleton import get_event_manager
 from autocoder.events import event_content as EventContentCreator
+from autocoder.common.mcp_server import get_mcp_server
+from autocoder.common.mcp_server_types import (
+    McpRequest, McpInstallRequest, McpRemoveRequest, McpListRequest, 
+    McpListRunningRequest, McpRefreshRequest
+)
 
 console = Console()
 
@@ -261,7 +266,8 @@ def main(input_args: Optional[List[str]] = None):
                     "saas.base_url": model_info["base_url"],
                     "saas.api_key": model_info["api_key"],
                     "saas.model": model_info["model_name"],
-                    "saas.is_reasoning": model_info["is_reasoning"]
+                    "saas.is_reasoning": model_info["is_reasoning"],
+                    "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                 }
             )                                                    
 
@@ -284,7 +290,8 @@ def main(input_args: Optional[List[str]] = None):
                                 "saas.base_url": model_info["base_url"],
                                 "saas.api_key": model_info["api_key"],
                                 "saas.model": model_info["model_name"],
-                                "saas.is_reasoning": model_info["is_reasoning"]
+                                "saas.is_reasoning": model_info["is_reasoning"],
+                                "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                             }
                         )
                         models.append(code_model)
@@ -302,7 +309,8 @@ def main(input_args: Optional[List[str]] = None):
                             "saas.base_url": model_info["base_url"],
                             "saas.api_key": model_info["api_key"],
                             "saas.model": model_info["model_name"],
-                            "saas.is_reasoning": model_info["is_reasoning"]
+                            "saas.is_reasoning": model_info["is_reasoning"],
+                            "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                         }
                     )
                     llm.setup_sub_client("code_model", code_model)
@@ -323,7 +331,8 @@ def main(input_args: Optional[List[str]] = None):
                                 "saas.base_url": model_info["base_url"],
                                 "saas.api_key": model_info["api_key"],
                                 "saas.model": model_info["model_name"],
-                                "saas.is_reasoning": model_info["is_reasoning"]
+                                "saas.is_reasoning": model_info["is_reasoning"],
+                                "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                             }
                         )
                         models.append(rerank_model)
@@ -341,7 +350,8 @@ def main(input_args: Optional[List[str]] = None):
                             "saas.base_url": model_info["base_url"],
                             "saas.api_key": model_info["api_key"],
                             "saas.model": model_info["model_name"],
-                            "saas.is_reasoning": model_info["is_reasoning"]
+                            "saas.is_reasoning": model_info["is_reasoning"],
+                            "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                         }
                     )
                     llm.setup_sub_client("generate_rerank_model", rerank_model)
@@ -358,7 +368,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("inference_model", inference_model)                 
@@ -375,7 +386,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("index_filter_model", index_filter_model)            
@@ -541,7 +553,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("chat_model", chat_model)
@@ -558,7 +571,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("vl_model", vl_model)
@@ -575,7 +589,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("index_model", index_model)    
@@ -592,7 +607,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("sd_model", sd_model)
@@ -609,7 +625,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("text2voice_model", text2voice_model)
@@ -626,7 +643,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("voice2text_model", voice2text_model)
@@ -643,7 +661,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("planner_model", planner_model)
@@ -660,7 +679,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("commit_model", commit_model)    
@@ -677,7 +697,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("designer_model", designer_model)
@@ -694,7 +715,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("emb_model", emb_model)
@@ -1254,7 +1276,6 @@ def main(input_args: Optional[List[str]] = None):
                 v = (item for item in response)
                 
             elif "mcp" in commands_info: 
-                from autocoder.common.mcp_server import get_mcp_server, McpRequest, McpInstallRequest, McpRemoveRequest, McpListRequest, McpListRunningRequest, McpRefreshRequest                               
                 mcp_server = get_mcp_server()
                 
                 pos_args = commands_info["mcp"].get("args", [])

autocoder/auto_coder_rag.py

@@ -636,7 +636,8 @@ def main(input_args: Optional[List[str]] = None):
                     "saas.base_url": model_info["base_url"],
                     "saas.api_key": model_info["api_key"],
                     "saas.model": model_info["model_name"],
-                    "saas.is_reasoning": model_info["is_reasoning"]
+                    "saas.is_reasoning": model_info["is_reasoning"],
+                    "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                 }
             )
 
@@ -652,7 +653,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("recall_model", recall_model)
@@ -668,7 +670,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("chunk_model", chunk_model)
@@ -684,7 +687,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("qa_model", qa_model)
@@ -700,7 +704,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": False
+                        "saas.is_reasoning": False,
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
                 llm.setup_sub_client("emb_model", emb_model)
@@ -792,7 +797,8 @@ def main(input_args: Optional[List[str]] = None):
                     "saas.base_url": model_info["base_url"],
                     "saas.api_key": model_info["api_key"],
                     "saas.model": model_info["model_name"],
-                    "saas.is_reasoning": model_info["is_reasoning"]
+                    "saas.is_reasoning": model_info["is_reasoning"],
+                    "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                 }
             )
 
@@ -806,7 +812,8 @@ def main(input_args: Optional[List[str]] = None):
                     "saas.base_url": model_info["base_url"],
                     "saas.api_key": model_info["api_key"],
                     "saas.model": model_info["model_name"],
-                    "saas.is_reasoning": False
+                    "saas.is_reasoning": False,
+                    "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                 }
             )
             llm.setup_sub_client("emb_model", emb_model)
@@ -852,7 +859,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )
 
@@ -882,7 +890,8 @@ def main(input_args: Optional[List[str]] = None):
                         "saas.base_url": model_info["base_url"],
                         "saas.api_key": model_info["api_key"],
                         "saas.model": model_info["model_name"],
-                        "saas.is_reasoning": model_info["is_reasoning"]
+                        "saas.is_reasoning": model_info["is_reasoning"],
+                        "saas.max_output_tokens": model_info.get("max_output_tokens", 8096)
                     }
                 )