testing training

.gitignore

@@ -66,3 +66,7 @@ test_*.py
 
 # Nomad data
 /tmp/NomadClient*/
+
+*.egg-info*
+wandb
+logs

environments/hermes_base_env.py

@@ -45,7 +45,7 @@ if _env_path.exists():
 # This patches SwerexModalEnvironment to use a background thread instead of
 # asyncio.run(), which would deadlock inside Atropos. Safe for normal CLI too.
 from environments.patches import apply_patches
-apply_patches()
+# apply_patches()  # DISABLED: sglang patch breaks native vLLM /generate
 
 from atroposlib.envs.base import (
     BaseEnv,
@@ -270,6 +270,12 @@ class HermesAgentBaseEnv(BaseEnv):
     # =========================================================================
 
     def _use_managed_server(self) -> bool:
+        import sys
+        result = self._use_managed_server_inner()
+        print(f"HERMES_DEBUG _use_managed_server={result}, servers={len(self.server.servers) if hasattr(self.server, 'servers') else 'N/A'}, type={type(self.server.servers[0]).__name__ if hasattr(self.server, 'servers') and self.server.servers else 'N/A'}", file=sys.stderr, flush=True)
+        return result
+
+    def _use_managed_server_inner(self) -> bool:
         """
         Determine if we should use ManagedServer (Phase 2) or direct server (Phase 1).
 

environments/patches.py

@@ -173,6 +173,8 @@ def _patch_swerex_modal():
 
 def _patch_vllm_server_for_sglang():
     """
+    (Mainly for Runpod serverless compat)
+    
     Monkey patch VLLMServer._tokens_and_logprobs_completion_wrapper to handle
     SGLang's /generate response format.
 
@@ -302,6 +304,6 @@ def apply_patches():
         return
 
     _patch_swerex_modal()
-    _patch_vllm_server_for_sglang()
+    # _patch_vllm_server_for_sglang()
 
     _patches_applied = True

environments/swe_smith_oracle_env.py

@@ -156,7 +156,7 @@ class SweSmithOracleEnv(HermesAgentBaseEnv):
                 model_name=model,
                 base_url=base_url,
                 api_key=api_key,
-                server_type="openai",
+                server_type="vllm",
                 health_check=False,
                 timeout=int(os.getenv("ATROPOS_SERVER_TIMEOUT_S") or "300"),
             ),