Hermes Atropos Environments

Atropos BaseEnv (atroposlib/envs/base.py)
    └── HermesAgentBaseEnv (environments/hermes_base_env.py)
            ├── Handles agent loop orchestration
            ├── Handles tool resolution per group
            ├── Handles ToolContext for reward verification
            └── YOUR ENVIRONMENT (environments/your_env.py)
                    Only implements: setup, get_next_item, format_prompt,
                                    compute_reward, evaluate, wandb_log

async def setup(self) -> None:
    """Called once at startup. Load datasets, initialize state."""
    # Try HuggingFace first, fallback to built-in samples
    try:
        from datasets import load_dataset
        ds = load_dataset("your/dataset", split="test")
        self._items = [...]
    except Exception:
        self._items = BUILTIN_SAMPLES

    # Always split into train/eval
    random.shuffle(self._items)
    eval_size = max(20, int(len(self._items) * 0.1))
    self._eval_items = self._items[:eval_size]
    self._items = self._items[eval_size:]

async def get_next_item(self) -> dict:
    """Return next item, cycling through dataset."""
    item = self._items[self._index % len(self._items)]
    self._index += 1
    return item

def format_prompt(self, item: dict) -> str:
    """Convert a dataset item into the user-facing prompt."""
    return f"Research this question: {item['question']}"

async def compute_reward(self, item, result: AgentResult, ctx: ToolContext) -> float:
    # Extract final response (last assistant message with content)
    final_response = ""
    tools_used = []
    for msg in reversed(result.messages):
        if msg.get("role") == "assistant" and msg.get("content") and not final_response:
            final_response = msg["content"]
        if msg.get("role") == "assistant" and msg.get("tool_calls"):
            for tc in msg["tool_calls"]:
                fn = tc.get("function", {}) if isinstance(tc, dict) else {}
                name = fn.get("name", "")
                if name:
                    tools_used.append(name)

    # Score using LLM judge, heuristic, or ToolContext verification
    correctness = await self._llm_judge(item, final_response)
    return correctness

# Run tests in the agent's sandbox
result = ctx.terminal("pytest /workspace/test.py")
return 1.0 if result["exit_code"] == 0 else 0.0

async def evaluate(self, *args, **kwargs) -> None:
    import time, uuid
    from environments.agent_loop import HermesAgentLoop
    from environments.tool_context import ToolContext

    start_time = time.time()
    tools, valid_names = self._resolve_tools_for_group()
    samples = []

    for item in self._eval_items[:self.config.eval_size]:
        task_id = str(uuid.uuid4())
        messages = []
        if self.config.system_prompt:
            messages.append({"role": "system", "content": self.config.system_prompt})
        messages.append({"role": "user", "content": self.format_prompt(item)})

        agent = HermesAgentLoop(
            server=self.server,
            tool_schemas=tools,
            valid_tool_names=valid_names,
            max_turns=self.config.max_agent_turns,
            task_id=task_id,
            temperature=0.0,  # Deterministic for eval
            max_tokens=self.config.max_token_length,
            extra_body=self.config.extra_body,
        )
        result = await agent.run(messages)

        ctx = ToolContext(task_id)
        try:
            reward = await self.compute_reward(item, result, ctx)
        finally:
            ctx.cleanup()

        samples.append({"prompt": ..., "response": ..., "reward": reward})

    eval_metrics = {"eval/mean_reward": ...}
    await self.evaluate_log(metrics=eval_metrics, samples=samples,
                            start_time=start_time, end_time=time.time())

async def wandb_log(self, wandb_metrics=None):
    if wandb_metrics is None:
        wandb_metrics = {}
    if self._reward_buffer:
        n = len(self._reward_buffer)
        wandb_metrics["train/mean_reward"] = sum(self._reward_buffer) / n
        self._reward_buffer.clear()
    await super().wandb_log(wandb_metrics)  # MUST call super

# SERVE — Full training loop (connects to Atropos API server)
python environments/my_env.py serve --openai.base_url http://localhost:8000/v1

# PROCESS — Offline data generation (saves JSONL)
python environments/my_env.py process --env.total_steps 10 --env.group_size 1 \
    --env.use_wandb false --env.data_path_to_save_groups output.jsonl \
    --openai.base_url "<USER_BASE_URL>" \
    --openai.model_name "<USER_MODEL>" \
    --openai.server_type <USER_SERVER_TYPE> --openai.health_check false

# EVALUATE — Standalone eval (runs setup + evaluate only)
python environments/my_env.py evaluate --env.eval_size 20 \
    --env.data_dir_to_save_evals /tmp/eval_results \
    --openai.base_url "<USER_BASE_URL>" \
    --openai.model_name "<USER_MODEL>" \
    --openai.server_type <USER_SERVER_TYPE> --openai.health_check false