SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Enh: Fix warning message for sonnet 3.7/4
Kilian Lieret6eeabb451937
diff --git a/sweagent/agent/models.py b/sweagent/agent/models.pyindex 4e799d81..a0e1abc6 100644--- a/sweagent/agent/models.py+++ b/sweagent/agent/models.py@@ -589,7 +589,7 @@ class LiteLLMModel(AbstractModel):if is_claude_3_7 and not has_128k_beta_header:self.model_max_output_tokens = 64000self.logger.warning(- "Claude 3.7 models do not support 128k context by default. "+ "Claude 3.7/4 models do not support 128k context by default. ""Setting max output tokens to 64k. To enable 128k context, please set the ""completion_kwargs to {'extra_headers': {'anthropic-beta': 'output-128k-2025-02-19'}}.")