SkillOpt v0.1.0: initial release

- Skill optimization framework with training loop analogy
- 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen)
- WebUI for browser-based training control
- Pluggable architecture for extending benchmarks and backends

skillopt/envs/alfworld/vendor/memory.py

@@ -0,0 +1,87 @@
+# Vendored from SkillRL (Apache-2.0 License)
+# Original: agent_system/memory/base.py + agent_system/memory/memory.py
+# Merged into a single file for simplicity.
+
+from abc import ABC, abstractmethod
+from typing import List, Dict, Any, Tuple
+
+
+class BaseMemory(ABC):
+    """Base class for memory management."""
+
+    @abstractmethod
+    def __len__(self):
+        pass
+
+    @abstractmethod
+    def __getitem__(self, idx: int):
+        pass
+
+    @abstractmethod
+    def reset(self, batch_size: int):
+        pass
+
+    @abstractmethod
+    def store(self, record: Dict[str, List[Any]]):
+        pass
+
+    @abstractmethod
+    def fetch(self, step: int):
+        pass
+
+
+class SimpleMemory(BaseMemory):
+    """Per-environment history buffer for storing observations and actions."""
+
+    def __init__(self):
+        self._data = None
+        self.keys = None
+        self.batch_size = 0
+
+    def __len__(self):
+        return len(self._data)
+
+    def __getitem__(self, idx):
+        return self._data[idx]
+
+    def reset(self, batch_size: int):
+        if self._data is not None:
+            self._data.clear()
+        self._data = [[] for _ in range(batch_size)]
+        self.batch_size = batch_size
+        self.keys = None
+
+    def store(self, record: Dict[str, List[Any]]):
+        if self.keys is None:
+            self.keys = list(record.keys())
+        assert self.keys == list(record.keys())
+
+        for env_idx in range(self.batch_size):
+            self._data[env_idx].append({k: record[k][env_idx] for k in self.keys})
+
+    def fetch(
+        self,
+        history_length: int,
+        obs_key: str = "text_obs",
+        action_key: str = "action",
+    ) -> Tuple[List[str], List[int]]:
+        memory_contexts, valid_lengths = [], []
+
+        for env_idx in range(self.batch_size):
+            recent = self._data[env_idx][-history_length:]
+            valid_len = len(recent)
+            start_idx = len(self._data[env_idx]) - valid_len
+
+            lines = []
+            for j, rec in enumerate(recent):
+                step_num = start_idx + j + 1
+                act = rec[action_key]
+                obs = rec[obs_key]
+                lines.append(
+                    f"[Observation {step_num}: '{obs}', Action {step_num}: '{act}']"
+                )
+
+            memory_contexts.append("\n".join(lines))
+            valid_lengths.append(valid_len)
+
+        return memory_contexts, valid_lengths