fix(llm): unify JSON output handling across providers and fix tool+json_output compatibility
- Remove redundant `response_format` injection for VOLCANO provider since it's unsupported; rely on system prompt injection instead - Extend system prompt JSON injection logic to cover VOLCANO and tool-enabled cases universally - Simplify model parameter construction by removing redundant `params["model_kwargs"] = model_kwargs` assignments - Refactor `CompatibleChatOpenAI._get_request_payload` to strip `response_format` when tools are present, avoiding strict validation errors in langchain_openai - Fix timestamp calculation order in `datetime_tool.py` to avoid integer truncation before multiplication
This commit is contained in:
@@ -253,9 +253,9 @@ class DateTimeTool(BuiltinTool):
|
||||
return {
|
||||
"datetime": input_value,
|
||||
"timezone": timezone_str,
|
||||
"timestamp": int(dt.timestamp()) * 1000,
|
||||
"timestamp": int(dt.timestamp() * 1000),
|
||||
"iso_format": dt.isoformat(),
|
||||
"result_data": int(dt.timestamp()) * 1000
|
||||
"result_data": int(dt.timestamp() * 1000)
|
||||
}
|
||||
|
||||
def _calculate_datetime(self, kwargs) -> dict:
|
||||
|
||||
Reference in New Issue
Block a user