Upload folder using huggingface_hub

m.py

@@ -0,0 +1,144 @@
+import asyncio
+import os
+import textwrap
+from typing import List, Optional
+
+from openai import OpenAI
+
+from my_env_v4 import MyEnvV4Action, MyEnvV4Env
+IMAGE_NAME = os.getenv("IMAGE_NAME") # If you are using docker image 
+API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY")
+
+API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
+MODEL_NAME = os.getenv("MODEL_NAME") or "Qwen/Qwen2.5-72B-Instruct"
+TASK_NAME = os.getenv("MY_ENV_V4_TASK", "echo")
+BENCHMARK = os.getenv("MY_ENV_V4_BENCHMARK", "my_env_v4")
+MAX_STEPS = 8
+TEMPERATURE = 0.7
+MAX_TOKENS = 150
+SUCCESS_SCORE_THRESHOLD = 0.1  # normalized score in [0, 1]
+
+# Max possible reward: each token contributes 0.1, across all steps
+_MAX_REWARD_PER_STEP = MAX_TOKENS * 0.1
+MAX_TOTAL_REWARD = MAX_STEPS * _MAX_REWARD_PER_STEP
+
+SYSTEM_PROMPT = textwrap.dedent(
+    """
+    You are interacting with a simple echo environment.
+    Each turn you must send a message. The environment will echo it back.
+    Reward is proportional to message length: reward = len(message) * 0.1
+    Your goal is to maximize total reward by sending meaningful, substantive messages.
+    Reply with exactly one message string — no quotes, no prefixes, just the message text.
+    """
+).strip()
+
+
+def log_start(task: str, env: str, model: str) -> None:
+    print(f"[START] task={task} env={env} model={model}", flush=True)
+
+
+def log_step(step: int, action: str, reward: float, done: bool, error: Optional[str]) -> None:
+    error_val = error if error else "null"
+    done_val = str(done).lower()
+    print(
+        f"[STEP] step={step} action={action} reward={reward:.2f} done={done_val} error={error_val}",
+        flush=True,
+    )
+
+
+def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
+    rewards_str = ",".join(f"{r:.2f}" for r in rewards)
+    print(f"[END] success={str(success).lower()} steps={steps} score={score:.3f} rewards={rewards_str}", flush=True)
+
+
+def build_user_prompt(step: int, last_echoed: str, last_reward: float, history: List[str]) -> str:
+    history_block = "\n".join(history[-4:]) if history else "None"
+    return textwrap.dedent(
+        f"""
+        Step: {step}
+        Last echoed message: {last_echoed!r}
+        Last reward: {last_reward:.2f}
+        Previous steps:
+        {history_block}
+        Send your next message.
+        """
+    ).strip()
+
+
+def get_model_message(client: OpenAI, step: int, last_echoed: str, last_reward: float, history: List[str]) -> str:
+    user_prompt = build_user_prompt(step, last_echoed, last_reward, history)
+    try:
+        completion = client.chat.completions.create(
+            model=MODEL_NAME,
+            messages=[
+                {"role": "system", "content": SYSTEM_PROMPT},
+                {"role": "user", "content": user_prompt},
+            ],
+            temperature=TEMPERATURE,
+            max_tokens=MAX_TOKENS,
+            stream=False,
+        )
+        text = (completion.choices[0].message.content or "").strip()
+        return text if text else "hello"
+    except Exception as exc:
+        print(f"[DEBUG] Model request failed: {exc}", flush=True)
+        return "hello"
+
+
+async def main() -> None:
+    client = OpenAI(base_url=API_BASE_URL, api_key=API_KEY)
+
+    env = await MyEnvV4Env.from_docker_image(IMAGE_NAME)
+
+    history: List[str] = []
+    rewards: List[float] = []
+    steps_taken = 0
+    score = 0.0
+    success = False
+
+    log_start(task=TASK_NAME, env=BENCHMARK, model=MODEL_NAME)
+
+    try:
+        result = await env.reset() # OpenENV.reset()
+        last_echoed = result.observation.echoed_message
+        last_reward = 0.0
+
+        for step in range(1, MAX_STEPS + 1):
+            if result.done:
+                break
+
+            message = get_model_message(client, step, last_echoed, last_reward, history)
+
+            result = await env.step(MyEnvV4Action(message=message))
+            obs = result.observation
+
+            reward = result.reward or 0.0
+            done = result.done
+            error = None
+
+            rewards.append(reward)
+            steps_taken = step
+            last_echoed = obs.echoed_message
+            last_reward = reward
+
+            log_step(step=step, action=message, reward=reward, done=done, error=error)
+
+            history.append(f"Step {step}: {message!r} -> reward {reward:+.2f}")
+
+            if done:
+                break
+
+        score = sum(rewards) / MAX_TOTAL_REWARD if MAX_TOTAL_REWARD > 0 else 0.0
+        score = min(max(score, 0.0), 1.0)  # clamp to [0, 1]
+        success = score >= SUCCESS_SCORE_THRESHOLD
+
+    finally:
+        try:
+            await env.close()
+        except Exception as e:
+            print(f"[DEBUG] env.close() error (container cleanup): {e}", flush=True)
+        log_end(success=success, steps=steps_taken, score=score, rewards=rewards)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

server/PharmaDDIEnv_environment.py

@@ -163,7 +163,8 @@ class PharmaDDIEnvironment(Environment):
         raw_score, feedback = self._grade_submission(action)
 
         # Clamp raw_score to avoid exact 0.0 or 1.0 (validation requirement)
-        clamped_score = min(max(raw_score, 0.01), 0.99)
+        clamped_score = min(max(raw_score, 0.0), 1.0)
+        
 
         # Reward = improvement over best score so far
         improvement = max(0.0, clamped_score - self._best_score)
@@ -310,8 +311,9 @@ class PharmaDDIEnvironment(Environment):
                 0.10 * completeness -
                 critical_penalty
             )
-
-        final_score = min(max(raw_score, 0.01), 0.99)
+        ##############################################################################################################################
+        #final_score = min(max(raw_score, 0.01), 0.99)
+        final_score = min(max(raw_score, 0.0), 1.0)
 
         # Build summary feedback
         summary = (