ssg-kstewart
commented
3 weeks ago For additional context, it appears as though the tool calls are not occurring successfully as the response body results in a IndexError here. Messages with the response body injected appear as shown:
[
{
"role": "user",
"content": "REDACTED"
},
{
"role": "assistant",
"content": "REDACTED"
},
{
"role": "user",
"content": "RESPONSEBODY: {'id': 'msg_bdrk_018qmbt8JrxDnLUhEY7XbCtd', 'type': 'message', 'role': 'assistant', 'model': 'claude-3-sonnet-20240229', 'content': [], 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 531, 'output_tokens': 3}}"
},
{
"role": "assistant",
"content": "REDACTED"
},
{
"role": "user",
"content": "RESPONSEBODY: {'id': 'msg_bdrk_01Ww79eCr8Bz1ZsSyrkgbSUH', 'type': 'message', 'role': 'assistant', 'model': 'claude-3-sonnet-20240229', 'content': [], 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 796, 'output_tokens': 3}}"
}
]EDIT: Note, this is after forcing an alternating message pattern using the following logic. Without alternating, I run into the same issue requiring the alternation. Ultimately, it looks as though tools are not actually being called successfully.
for i in range(1, len(messages)):
if messages[i]['role'] == messages[i - 1]['role']:
messages[i]['role'] = 'assistant' if messages[i - 1]['role'] == 'user' else 'user'
I am attempting to use ChatBedrock with an Anthropic Claude Sonnet model (anthropic.claude-3-sonnet-20240229-v1:0) in an implementation of LangGraph's collaborative multi-agent system. I am receiving an error as shown in a below stack trace where there is an expectation that roles must alternate. Messages passed in to
_prepare_input_and_invokeare structured as so (with the message content redacted):I assume this is expected behavior in regards to the multi-agent system and see similar message structure when using ChatOpenAI in place of ChatBedrock where there are multiple messages of type "ai" in succession.