fixes applied

Dockerfile

@@ -7,6 +7,6 @@ RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
-EXPOSE 8000
+EXPOSE 5000
 
-CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "5000"]

inference.py

@@ -40,7 +40,7 @@ def get_environment_config() -> Dict[str, str]:
         "api_base_url": os.getenv("API_BASE_URL", "http://localhost:11434/v1"),
         "model_name": os.getenv("MODEL_NAME", "llama2"),
         "hf_token": os.getenv("HF_TOKEN", ""),
-        "env_url": os.getenv("ENV_URL", "http://localhost:5001"),  # ✅ FIXED: Changed from 5000 to 5001
+        "env_url": os.getenv("ENV_URL", "http://localhost:5000"),  # Fixed to match server default port
         "api_key": os.getenv("HF_TOKEN", "not-needed-for-local"),
     }
     return config
@@ -618,149 +618,125 @@ def run_inference(config: Optional[Dict[str, str]] = None) -> None:
         except Exception as e:
             print(f"Warning: Could not initialize LLM client: {e}", file=sys.stderr)
 
-    # Initialize variables for error handling
-    rewards = []
-    step_num = 0
-    action_str = "initialization"
+    episode_count = 3
 
-    try:
-        # Reset environment
-        reset_response = requests.post(
-            f"{env_url}/reset",
-            timeout=10
-        )
-        reset_response.raise_for_status()
-        reset_data = reset_response.json()
+    for episode_idx in range(1, episode_count + 1):
+        rewards = []
+        step_num = 0
+        action_str = "initialization"
 
-        observation = reset_data.get("observation", {})
-        task_name = observation.get("email_id", "email_workflow")
-        email_subject = observation.get("subject", "")
-        email_body = observation.get("body", "")
-        customer_history = observation.get("customer_history", "")
-        workflow_context = observation.get("previous_decisions", {})  # ✅ FIXED: Changed from "workflow_context" to "previous_decisions"
+        try:
+            # Reset environment
+            reset_response = requests.post(
+                f"{env_url}/reset",
+                timeout=10
+            )
+            reset_response.raise_for_status()
+            reset_data = reset_response.json()
+
+            observation = reset_data.get("observation", {})
+            task_name = observation.get("email_id", f"email_workflow_{episode_idx}")
+            email_subject = observation.get("subject", "")
+            email_body = observation.get("body", "")
+            customer_history = observation.get("customer_history", "")
+            workflow_context = observation.get("previous_decisions", {})
+
+            # Log start
+            log_start(task_name, env_name, model_name)
+
+            done = False
+
+            # Multi-step workflow loop
+            while not done and step_num < 5:
+                step_num += 1
+
+                # Generate action based on current step
+                if step_num == 1:
+                    action = generate_classification_action(
+                        email_subject, email_body, customer_history, client, model_name
+                    )
+                elif step_num == 2:
+                    classification = workflow_context.get("classification", "tech")
+                    action = generate_prioritization_action(
+                        email_subject, email_body, customer_history, classification, client, model_name
+                    )
+                elif step_num == 3:
+                    classification = workflow_context.get("classification", "tech")
+                    priority = workflow_context.get("priority", "medium")
+                    sentiment = observation.get("customer_sentiment", "neutral")
+                    action = generate_strategy_action(
+                        email_subject, email_body, customer_history, classification, priority, sentiment, client, model_name
+                    )
+                elif step_num == 4:
+                    classification = workflow_context.get("classification", "tech")
+                    priority = workflow_context.get("priority", "medium")
+                    strategy = workflow_context.get("strategy", "auto_resolve")
+                    action = generate_response_action(
+                        email_subject, email_body, customer_history, classification, priority, strategy, workflow_context, client, model_name
+                    )
+                elif step_num == 5:
+                    action = generate_escalation_action(
+                        workflow_context, email_subject, email_body, customer_history, client, model_name
+                    )
+                    if action is None:
+                        # No escalation needed, end episode
+                        done = True
+                        break
+
+                # Convert action to string for logging
+                if action["action_type"] == "escalate":
+                    action_str = f"escalate_{action['content'].get('escalation_level', 'unknown')}"
+                else:
+                    content_preview = str(action["content"])[:50].replace("\n", " ")
+                    action_str = f"{action['action_type']}:{content_preview}"
+
+                # Step environment
+                step_response = requests.post(
+                    f"{env_url}/step",
+                    json=action,
+                    timeout=15
+                )
+                step_response.raise_for_status()
+                step_data = step_response.json()
 
-        # Log start
-        log_start(task_name, env_name, model_name)
+                reward = step_data.get("reward", 0.0)
+                done = step_data.get("done", True)
+                info = step_data.get("info", {})
 
-        rewards = []
-        step_num = 0
-        done = False
+                # Update workflow context for next step
+                workflow_context = info.get("workflow_state", workflow_context)
 
-        # Multi-step workflow loop
-        while not done and step_num < 5:
-            step_num += 1
+                rewards.append(reward)
 
-            # Generate action based on current step
-            if step_num == 1:
-                action = generate_classification_action(
-                    email_subject, email_body, customer_history, client, model_name
-                )
-            elif step_num == 2:
-                classification = workflow_context.get("classification", "tech")
-                action = generate_prioritization_action(
-                    email_subject, email_body, customer_history, classification, client, model_name
-                )
-            elif step_num == 3:
-                classification = workflow_context.get("classification", "tech")
-                priority = workflow_context.get("priority", "medium")
-                sentiment = observation.get("customer_sentiment", "neutral")  # ✅ FIXED: Use actual sentiment from observation
-                action = generate_strategy_action(
-                    email_subject, email_body, customer_history, classification, priority, sentiment, client, model_name
-                )
-            elif step_num == 4:
-                classification = workflow_context.get("classification", "tech")
-                priority = workflow_context.get("priority", "medium")
-                strategy = workflow_context.get("strategy", "auto_resolve")
-                action = generate_response_action(
-                    email_subject, email_body, customer_history, classification, priority, strategy, workflow_context, client, model_name
-                )
-            elif step_num == 5:
-                action = generate_escalation_action(
-                    workflow_context, email_subject, email_body, customer_history, client, model_name
-                )
-                if action is None:
-                    # No escalation needed, end episode
-                    break
-
-            # Convert action to string for logging
-            if action["action_type"] == "escalate":
-                action_str = f"escalate_{action['content'].get('escalation_level', 'unknown')}"
-            else:
-                content_preview = str(action["content"])[:50].replace("\n", " ")
-                action_str = f"{action['action_type']}:{content_preview}"
-
-            # Step environment
-            step_response = requests.post(
-                f"{env_url}/step",
-                json=action,
-                timeout=15
-            )
-            step_response.raise_for_status()
-            step_data = step_response.json()
-
-            reward = step_data.get("reward", 0.0)
-            done = step_data.get("done", True)
-            info = step_data.get("info", {})
-
-            # Update workflow context for next step
-            workflow_context = info.get("workflow_state", workflow_context)
-
-            rewards.append(reward)
-
-            # Log step
-            log_step(step_num, action_str, reward, done, None)
-
-        # Prepare final metrics
-        total_score = sum(rewards)
-        success = total_score > 2.0  # Threshold for successful multi-step completion
-
-        # CRITICAL FIX: Normalize score to [0,1] range as per OpenEnv spec
-        MAX_POSSIBLE_REWARD = 2.5  # Maximum theoretical score across all steps
-        normalized_score = total_score / MAX_POSSIBLE_REWARD
-        normalized_score = min(max(normalized_score, 0.0), 1.0)
-
-        # Log end
-        log_end(success, step_num, normalized_score, rewards)
-
-    except requests.exceptions.RequestException as e:
-        error_msg = f"Step {step_num} failed: {str(e)}"
-        log_step(step_num, action_str, 0.0, False, error_msg)
-        rewards.append(0.0)
-        # Prepare final metrics after error
-        total_score = sum(rewards)
-        success = False
-        normalized_score = 0.0
-        log_end(success, step_num, normalized_score, rewards)
-        print(f"Error: {error_msg}", file=sys.stderr)
-        return  # Exit function instead of break
-
-    except Exception as e:
-        error_msg = f"Step {step_num} error: {str(e)}"
-        log_step(step_num, action_str, 0.0, False, error_msg)
-        rewards.append(0.0)
-        # Prepare final metrics after error
-        total_score = sum(rewards)
-        success = False
-        normalized_score = 0.0
-        log_end(success, step_num, normalized_score, rewards)
-        print(f"Error: {error_msg}", file=sys.stderr)
-        return  # Exit function instead of break
-
-    except requests.exceptions.RequestException as e:
-        error_msg = f"Environment request failed: {str(e)}"
-        log_start("error", env_name, model_name)
-        log_step(1, "error", 0.0, False, error_msg)
-        log_end(False, 1, 0.0, [0.0])
-        print(f"Error: {error_msg}", file=sys.stderr)
-        sys.exit(1)
-
-    except Exception as e:
-        error_msg = f"Inference failed: {str(e)}"
-        log_start("error", env_name, model_name)
-        log_step(1, "error", 0.0, False, error_msg)
-        log_end(False, 1, 0.0, [0.0])
-        print(f"Error: {error_msg}", file=sys.stderr)
-        sys.exit(1)
+                # Log step
+                log_step(step_num, action_str, reward, done, None)
+
+            # Prepare final metrics
+            total_score = sum(rewards)
+            MAX_POSSIBLE_REWARD = 2.5
+            normalized_score = total_score / MAX_POSSIBLE_REWARD
+            normalized_score = min(max(normalized_score, 0.0), 1.0)
+            success = normalized_score >= 0.7
+
+            log_end(success, step_num, normalized_score, rewards)
+
+        except requests.exceptions.RequestException as e:
+            error_msg = f"Step {step_num} failed: {str(e)}"
+            log_step(step_num, action_str, 0.0, False, error_msg)
+            rewards.append(0.0)
+            normalized_score = 0.0
+            log_end(False, step_num, normalized_score, rewards)
+            print(f"Error: {error_msg}", file=sys.stderr)
+            continue
+
+        except Exception as e:
+            error_msg = f"Step {step_num} error: {str(e)}"
+            log_step(step_num, action_str, 0.0, False, error_msg)
+            rewards.append(0.0)
+            normalized_score = 0.0
+            log_end(False, step_num, normalized_score, rewards)
+            print(f"Error: {error_msg}", file=sys.stderr)
+            continue
 
 
 if __name__ == "__main__":

server/app.py

@@ -156,7 +156,7 @@ def root() -> Dict[str, str]:
 def main():
     """Main entry point for running the server."""
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=5001)
+    uvicorn.run(app, host="0.0.0.0", port=5000)
 
 
 if __name__ == "__main__":