Adding endless terminal environment after rebase:

environments/endless_terminals/default.yaml

@@ -0,0 +1,66 @@
+# Endless Terminals Environment -- Default Configuration
+#
+# Trains agents on terminal tasks from the Endless Terminals HuggingFace dataset.
+# Each task includes a pre-built Apptainer container and pytest-based verification.
+#
+# Dataset: https://huggingface.co/datasets/obiwan96/endless-terminals-train
+#
+# Prerequisites:
+#   1. Download dataset: huggingface-cli download obiwan96/endless-terminals-train \
+#        --repo-type dataset --local-dir ~/endless-terminals-data \
+#        --local-dir-use-symlinks False
+#   2. Install Apptainer/Singularity (for test execution)
+#   3. Set TASKS_BASE_DIR environment variable or configure tasks_base_dir below
+#
+# Usage:
+#   python environments/endless_terminals/endless_terminals_env.py process \
+#       --config environments/endless_terminals/default.yaml
+
+env:
+  # Toolsets
+  enabled_toolsets: ["terminal", "file"]
+
+  # Agent configuration
+  max_agent_turns: 32
+  max_token_length: 4096
+  agent_temperature: 1.0
+
+  # Terminal backend
+  terminal_backend: "local"  # Change to "modal" or "docker" for cloud isolation
+
+  # Dataset settings
+  use_dataset: true
+  dataset_name: "obiwan96/endless-terminals-train"
+  dataset_split: "train"
+  dataset_cache_dir: "~/.cache/huggingface/datasets"
+  tasks_base_dir: ""  # Set to directory containing task_* folders (e.g., ~/endless-terminals-data)
+
+  # Test execution
+  test_timeout_s: 60
+
+  # Training configuration
+  group_size: 4
+  total_steps: 1000
+  steps_per_eval: 100
+
+  # Tool call parsing (for Phase 2 VLLM training)
+  tool_call_parser: "hermes"
+  tokenizer_name: "NousResearch/Hermes-3-Llama-3.1-8B"
+
+  # Logging
+  use_wandb: true
+  wandb_name: "endless-terminals"
+
+  # System prompt
+  system_prompt: >
+    You are a skilled Linux system administrator and programmer.
+    You have access to a terminal and file tools to complete system administration
+    and programming tasks. Use the tools effectively to solve the given task,
+    and verify your solution works correctly before finishing.
+
+openai:
+  base_url: "http://localhost:8000/v1"
+  model_name: "NousResearch/Hermes-3-Llama-3.1-8B"
+  server_type: "openai"
+  api_key: ""
+  health_check: false