feat: add context compress (#590)

* feat:Add context compress

* feat: Add unit test

* feat: add unit test for context manager

* feat: add postprocessor param && code format

* feat: add configuration guide

* fix: fix the configuration_guide

* fix: fix the unit test

* fix: fix the default value

* feat: add test and log for context_manager

src/llms/llm.py

@@ -67,6 +67,10 @@ def _create_llm_use_conf(llm_type: LLMType, conf: Dict[str, Any]) -> BaseChatMod
     # Merge configurations, with environment variables taking precedence
     merged_conf = {**llm_conf, **env_conf}
 
+    # Remove unnecessary parameters when initializing the client
+    if "token_limit" in merged_conf:
+        merged_conf.pop("token_limit")
+
     if not merged_conf:
         raise ValueError(f"No configuration found for LLM type: {llm_type}")
 
@@ -174,6 +178,25 @@ def get_configured_llm_models() -> dict[str, list[str]]:
         return {}
 
 
+def get_llm_token_limit_by_type(llm_type: str) -> int:
+    """
+    Get the maximum token limit for a given LLM type.
+
+    Args:
+        llm_type (str): The type of LLM.
+
+    Returns:
+        int: The maximum token limit for the specified LLM type.
+    """
+
+    llm_type_config_keys = _get_llm_type_config_keys()
+    config_key = llm_type_config_keys.get(llm_type)
+
+    conf = load_yaml_config(_get_config_file_path())
+    llm_max_token = conf.get(config_key, {}).get("token_limit")
+    return llm_max_token
+
+
 # In the future, we will use reasoning_llm and vl_llm for different purposes
 # reasoning_llm = get_llm_by_type("reasoning")
 # vl_llm = get_llm_by_type("vision")