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: Auto-correct for --model.name
Kilian Lieret2033104e7358
diff --git a/sweagent/run/run_single.py b/sweagent/run/run_single.pyindex 780fb971..5b177424 100644--- a/sweagent/run/run_single.py+++ b/sweagent/run/run_single.py@@ -98,6 +98,7 @@ class RunSingleConfig(BaseSettings, cli_implicit_flags=False):return [ACS("model", "agent.model.name"),ACS("agent.model", "agent.model.name"),+ ACS("model.name", "agent.model.name"),ACS("per_instance_cost_limit", "agent.model.per_instance_cost_limit"),ACS("model.per_instance_cost_limit", "agent.model.per_instance_cost_limit"),ACS("config_file", "config"),