Deleted unnecessary files

DEBUGGING_REPORT.md

@@ -1,114 +0,0 @@
-# Task Debugging Report
-
-## Summary
-All 45 tasks (15 easy + 15 medium + 15 hard) are working correctly. The failures observed in the inference run were due to the LLM model (llama-3.1-8b-instant) not generating correct code fixes, not due to bugs in the task definitions or grading system.
-
-## Issues Found and Fixed
-
-### 1. **Inference Script Error Handling** ✅ FIXED
-**Issue**: When the `/step` endpoint returned a 500 error, the inference script caught the exception but didn't pass the error details to the LLM for the next attempt.
-
-**Fix**: Modified `inference.py` line 200-208 to capture the error message and pass it as feedback to the LLM:
-```python
-except Exception as e:
-    error_msg = str(e)[:200]
-    log_step(step=attempt, action="step_failed",
-             reward=0.0, done=False, error=error_msg[:60])
-    rewards.append(0.0)
-    # Pass error feedback to LLM for next attempt
-    last_feedback = f"❌ Server Error: {error_msg}\n\nYour code likely caused a runtime error or timeout..."
-    continue
-```
-
-### 2. **Server Error Logging** ✅ IMPROVED
-**Issue**: When errors occurred in the `/step` endpoint, there was no server-side logging to help debug issues.
-
-**Fix**: Added logging and improved TimeoutError handling in `server/app.py`:
-```python
-except TimeoutError as e:
-    import traceback
-    print(f"[ERROR] TimeoutError in step: {e}\n{traceback.format_exc()}", flush=True)
-    # Now includes current task info instead of "unknown"
-    ...
-except Exception as e:
-    import traceback
-    print(f"[ERROR] Exception in step: {e}\n{traceback.format_exc()}", flush=True)
-    ...
-```
-
-## Test Results
-
-### Comprehensive Task Verification ✅
-Ran `test_all_tasks.py` to verify all 45 tasks:
-- **Easy Tasks**: 15/15 PASSED (100%)
-- **Medium Tasks**: 15/15 PASSED (100%)
-- **Hard Tasks**: 15/15 PASSED (100%)
-
-All tasks achieve reward=1.00 when provided with their correct `fixed_code` solutions.
-
-### Edge Case Testing ✅
-Ran `test_edge_cases.py` to verify grader robustness:
-- ✅ Syntax errors: Properly caught and reported
-- ✅ Runtime errors: Properly caught and reported
-- ✅ Missing return statements: Properly detected
-- ✅ Timeout/infinite loops: Handled gracefully (on Unix with SIGALRM)
-- ✅ Empty input edge cases: Properly tested
-
-## Root Cause Analysis
-
-### Why did easy_014 fail?
-The task `easy_014` (longest_word_length) received incorrect fixes from the LLM across attempts 1-3. On attempts 4-5, the LLM-generated code likely caused a server error (infinite loop, exception, or timeout), resulting in 500 errors from the Hugging Face Space.
-
-**Task is correct** ✅ - When given the proper fix (`max` instead of `min`), it passes all tests.
-
-### Why did hard_010 get 0.00 reward?
-The task `hard_010` (BFS shortest path) likely received fixes that:
-1. Failed the test cases (70% of reward = 0)
-2. Had missing or poor explanations (30% of reward = 0)
-
-**Task is correct** ✅ - When given the proper fix (adding `visited` set) and a good explanation, it achieves reward=1.00.
-
-## Recommendations
-
-### For Better LLM Performance:
-1. **Use a more capable model**: Consider switching from `llama-3.1-8b-instant` to:
-   - `gpt-4o-mini` (default, better at code debugging)
-   - `gpt-4o` (best performance)
-   - `claude-3.5-sonnet` (excellent at code understanding)
-
-2. **Improve the system prompt**: The current prompt could be enhanced with:
-   - More examples of common bug patterns
-   - Better emphasis on reading test feedback
-   - Specific guidance for each difficulty level
-
-3. **Increase temperature on retries**: Already implemented - uses 0.2 for first attempt, 0.5 for retries
-
-### For Server Resilience:
-1. ✅ **Added error logging** to help debug future issues
-2. ✅ **Improved error feedback** to LLM when step fails
-3. Consider adding rate limiting if deployed publicly
-4. Consider adding per-session timeout limits
-
-## Files Modified
-
-1. **`inference.py`**: 
-   - Improved error handling to pass server errors as feedback to LLM
-
-2. **`server/app.py`**:
-   - Enhanced error logging
-   - Improved TimeoutError response with current task context
-
-## Files Created (for testing)
-
-1. **`test_debug.py`**: Tests specific failing tasks (easy_014, hard_010)
-2. **`test_edge_cases.py`**: Tests grader robustness with bad inputs
-3. **`test_all_tasks.py`**: Comprehensive verification of all 45 tasks
-
-## Conclusion
-
-**All tasks are working correctly.** The observed failures were due to:
-1. LLM model limitations (llama-3.1-8b-instant struggled with some tasks)
-2. Missing error feedback loop (now fixed)
-3. Potential server-side issues on Hugging Face Space (addressed with better logging)
-
-The codebase is now more robust with better error handling and logging.

DEBUGGING_REPORT_FINAL.md

@@ -1,247 +0,0 @@
-# Task Debugging Report - FINAL
-
-## Executive Summary
-
-✅ **All 45 tasks work correctly** when given proper fixes  
-❌ **LLM (llama-3.1-8b-instant) struggles with medium/hard tasks**  
-✅ **All improvements implemented** to make system more robust
-
----
-
-## Latest Inference Run Analysis
-
-| Task | Difficulty | Result | Reason |
-|------|-----------|---------|---------|
-| easy_013 | Easy | ✅ SUCCESS (1.00) | LLM fixed title case bug on first attempt |
-| medium_005 | Medium | ❌ FAILURE (500 errors) | LLM generated code causing server crashes after 2 failed attempts |
-| hard_011 | Hard | ❌ FAILURE (0.00 all steps) | LLM couldn't fix DP algorithm or provide good explanations |
-
-**Success Rate**: 1/3 tasks (33%) - **Easy tasks work, medium/hard fail**
-
----
-
-## Improvements Implemented
-
-### 1. ✅ Enhanced LLM Prompts (`inference.py`)
-
-**Added difficulty-specific guidance**:
-
-```python
-MEDIUM TASK TIPS:
-- Look for EXACTLY TWO bugs (not one, not three)
-- Common patterns: swapped if/else branches, += vs =, wrong comparison operator
-- Example: "if item in freq: freq[item] = 1" should be += 1
-
-HARD TASK TIPS:
-- Algorithmic bugs: iteration order, loop bounds, missing state tracking
-- Common patterns: forward vs backward iteration (DP), missing visited set (graphs)
-- Explanation MUST mention specific concepts: "backward iteration", "visited set", etc.
-```
-
-**Impact**: Better guidance for LLM on what to look for
-
----
-
-### 2. ✅ Grading Error Handling (`server/environment.py`)
-
-**Wrapped grader calls to prevent 500 errors**:
-
-```python
-try:
-    reward, passed, total, feedback, _ = grader(...)
-except Exception as e:
-    print(f"[ERROR] Grading failed: {e}", flush=True)
-    return DebugObservation(
-        reward=0.0,
-        feedback=f"❌ Grading Error: {type(e).__name__}...",
-        done=done
-    )
-```
-
-**Impact**: Server doesn't crash when LLM generates problematic code - returns helpful error message instead
-
----
-
-### 3. ✅ Error Feedback Loop (`inference.py`)
-
-**Pass 500 errors to LLM as learning feedback**:
-
-```python
-except Exception as e:
-    error_msg = str(e)[:200]
-    last_feedback = f"❌ Server Error: {error_msg}\n\n" \
-                    "Your code likely caused a runtime error or timeout..."
-    # LLM sees this on next attempt
-```
-
-**Impact**: LLM learns from its mistakes instead of repeating them
-
----
-
-### 4. ✅ Comprehensive Logging (`server/app.py` + `environment.py`)
-
-**Added detailed logging for debugging**:
-- TimeoutError with full stack trace
-- Grading exceptions with task context  
-- Server-side error tracking
-
-**Impact**: Easy to diagnose issues in production
-
----
-
-## Test Results
-
-### ✅ All Tasks Verified Working
-
-```bash
-python test_all_tasks.py
-```
-
-**Results**:
-- Easy Tasks: 15/15 PASSED (100%)
-- Medium Tasks: 15/15 PASSED (100%)
-- Hard Tasks: 15/15 PASSED (100%)
-
-**Conclusion**: Tasks are correct, failures are LLM-generated
-
----
-
-### ⚠️ Edge Case Analysis
-
-#### medium_005 (Count Frequency)
-**Task**: Count element frequency with 2 bugs (swapped if/else + wrong operation)
-
-**Potential Issues**:
-- Unhashable types `[{}, []]` → TypeError (handled by grader)
-- KeyError from bad LLM code (handled by grader)
-- Empty list `[]` → Works correctly
-
-#### hard_011 (0/1 Knapsack)
-**Task**: DP knapsack with iteration order bug (forward vs backward)
-
-**Potential Issues**:
-- Mismatched array lengths → IndexError (handled by grader)
-- Negative capacity → IndexError (handled by grader)
-- Very large capacity → MemoryError (timeout mechanism)
-- Missing/poor explanation → 0% explanation score
-
----
-
-## Root Cause: LLM Limitations
-
-### Why Easy Tasks Succeed:
-- ✅ Single bug (simple comparison, operator, return value)
-- ✅ Clear patterns (`==` vs `!=`, `<` vs `>`, `+1` vs `-1`)
-- ✅ LLM can spot these easily
-
-### Why Medium Tasks Fail:
-- ❌ **TWO bugs** to find simultaneously
-- ❌ Swapped logic (if/else reversed) - harder to spot
-- ❌ Need to trace through code more carefully
-- ❌ llama-3.1-8b-instant struggles with multi-bug analysis
-
-### Why Hard Tasks Fail:
-- ❌ **Algorithmic understanding** required (DP, graphs, etc.)
-- ❌ **Explanation requirement** (30% of reward)
-- ❌ Must use specific keywords ("backward iteration", "visited set")
-- ❌ llama-3.1-8b-instant not trained deeply on algorithms
-
-**Example - hard_011**:
-```python
-# Buggy: forward iteration
-for w in range(weights[i], capacity + 1):  # ❌ Wrong
-    dp[w] = max(dp[w], dp[w - weights[i]] + values[i])
-
-# Fixed: backward iteration  
-for w in range(capacity, weights[i] - 1, -1):  # ✅ Correct
-    dp[w] = max(dp[w], dp[w - weights[i]] + values[i])
-```
-
-**Explanation needed**: "The inner loop must iterate backward to prevent using the same item multiple times, which would turn this into an unbounded knapsack instead of 0/1 knapsack."
-
-→ llama-3.1-8b-instant doesn't understand this algorithmic nuance
-
----
-
-## Recommendations
-
-### 🚀 IMMEDIATE FIX: Use Better Model
-
-**Replace** `llama-3.1-8b-instant` with:
-
-| Model | Speed | Quality | Best For |
-|-------|-------|---------|----------|
-| **gpt-4o-mini** | Fast | Good | Balanced choice ⭐ |
-| gpt-4o | Medium | Excellent | Best results |
-| claude-3.5-sonnet | Medium | Excellent | Code understanding |
-| gpt-4-turbo | Medium | Very Good | Good balance |
-
-**Expected improvement**: 33% → 70%+ success rate
-
----
-
-### 📝 Prompt Improvements (Already Implemented)
-
-✅ Added common bug patterns  
-✅ Added difficulty-specific tips  
-✅ Added algorithmic guidance for hard tasks  
-✅ Error feedback loop
-
----
-
-### 🔧 Configuration Tweaks
-
-**In `inference.py`**:
-```python
-# Current
-temperature=0.2 if attempt == 1 else 0.5
-max_tokens=1500
-
-# Recommended
-temperature=0.1 if attempt == 1 else 0.3  # More deterministic
-max_tokens=2000  # More space for explanations
-```
-
----
-
-### 📊 Testing Before Deployment
-
-```bash
-# Verify all tasks
-python test_all_tasks.py
-
-# Test specific problems
-python test_specific_tasks.py
-
-# Check edge cases  
-python test_edge_cases.py
-```
-
----
-
-## Files Modified
-
-| File | Changes | Impact |
-|------|---------|--------|
-| `inference.py` | Enhanced prompts, error feedback, medium/hard tips | Better LLM guidance |
-| `server/environment.py` | Grading error handling, logging | Prevents 500 crashes |
-| `server/app.py` | Timeout error handling, logging | Better error messages |
-
----
-
-## Conclusion
-
-### ✅ What's Working:
-- All 45 tasks are correctly implemented
-- Grading system is robust and handles errors gracefully
-- Error logging helps debug issues
-- Enhanced prompts guide LLM better
-
-### ❌ What's Not Working:
-- LLM model (llama-3.1-8b-instant) is too weak for medium/hard tasks
-- Success rate: 33% (only easy tasks)
-
-### 💡 Solution:
-**Switch to gpt-4o-mini or better** → Expected 70%+ success rate
-
-The infrastructure is solid. The bottleneck is the LLM model's capability.

test_all_tasks.py

@@ -1,108 +0,0 @@
-#!/usr/bin/env python3
-"""Comprehensive test to verify all tasks can be solved correctly"""
-
-from server.tasks.task_easy import EASY_TASKS
-from server.tasks.task_medium import MEDIUM_TASKS  
-from server.tasks.task_hard import HARD_TASKS
-from server.graders.grader_easy import grade_easy
-from server.graders.grader_medium import grade_medium
-from server.graders.grader_hard import grade_hard
-
-def test_all_easy_tasks():
-    print("="*70)
-    print("TESTING ALL EASY TASKS")
-    print("="*70)
-    failed = []
-    for task in EASY_TASKS:
-        task_id = task['task_id']
-        try:
-            reward, passed, total, feedback, _ = grade_easy(task['fixed_code'], task)
-            if reward < 1.0:
-                failed.append((task_id, reward, f"{passed}/{total} tests passed"))
-                print(f"❌ {task_id}: reward={reward:.2f} ({passed}/{total})")
-            else:
-                print(f"✅ {task_id}: reward={reward:.2f} ({passed}/{total})")
-        except Exception as e:
-            failed.append((task_id, 0.0, str(e)))
-            print(f"💥 {task_id}: ERROR - {e}")
-    
-    print(f"\n{'='*70}")
-    print(f"EASY TASKS: {len(EASY_TASKS) - len(failed)}/{len(EASY_TASKS)} passed")
-    if failed:
-        print("Failed tasks:")
-        for task_id, reward, reason in failed:
-            print(f"  - {task_id}: {reason}")
-    print("="*70)
-    return len(failed) == 0
-
-def test_all_medium_tasks():
-    print("\n" + "="*70)
-    print("TESTING ALL MEDIUM TASKS")
-    print("="*70)
-    failed = []
-    for task in MEDIUM_TASKS:
-        task_id = task['task_id']
-        try:
-            reward, passed, total, feedback, _ = grade_medium(task['fixed_code'], task)
-            if reward < 1.0:
-                failed.append((task_id, reward, f"{passed}/{total} tests passed"))
-                print(f"❌ {task_id}: reward={reward:.2f} ({passed}/{total})")
-            else:
-                print(f"✅ {task_id}: reward={reward:.2f} ({passed}/{total})")
-        except Exception as e:
-            failed.append((task_id, 0.0, str(e)))
-            print(f"💥 {task_id}: ERROR - {e}")
-    
-    print(f"\n{'='*70}")
-    print(f"MEDIUM TASKS: {len(MEDIUM_TASKS) - len(failed)}/{len(MEDIUM_TASKS)} passed")
-    if failed:
-        print("Failed tasks:")
-        for task_id, reward, reason in failed:
-            print(f"  - {task_id}: {reason}")
-    print("="*70)
-    return len(failed) == 0
-
-def test_all_hard_tasks():
-    print("\n" + "="*70)
-    print("TESTING ALL HARD TASKS")
-    print("="*70)
-    failed = []
-    for task in HARD_TASKS:
-        task_id = task['task_id']
-        try:
-            # Create a good explanation that matches keywords
-            keywords = task.get('explanation_keywords', [])
-            explanation = f"The bug involved issues with {', '.join(keywords[:3])}. The fix addresses these problems."
-            
-            reward, passed, total, feedback, _ = grade_hard(task['fixed_code'], task, explanation)
-            if reward < 0.95:  # Allow for some explanation variance
-                failed.append((task_id, reward, f"{passed}/{total} tests passed"))
-                print(f"❌ {task_id}: reward={reward:.2f} ({passed}/{total})")
-            else:
-                print(f"✅ {task_id}: reward={reward:.2f} ({passed}/{total})")
-        except Exception as e:
-            failed.append((task_id, 0.0, str(e)))
-            print(f"💥 {task_id}: ERROR - {e}")
-    
-    print(f"\n{'='*70}")
-    print(f"HARD TASKS: {len(HARD_TASKS) - len(failed)}/{len(HARD_TASKS)} passed")
-    if failed:
-        print("Failed tasks:")
-        for task_id, reward, reason in failed:
-            print(f"  - {task_id}: {reason}")
-    print("="*70)
-    return len(failed) == 0
-
-if __name__ == "__main__":
-    easy_ok = test_all_easy_tasks()
-    medium_ok = test_all_medium_tasks()
-    hard_ok = test_all_hard_tasks()
-    
-    print("\n" + "="*70)
-    print("FINAL SUMMARY")
-    print("="*70)
-    print(f"Easy tasks:   {'✅ PASS' if easy_ok else '❌ FAIL'}")
-    print(f"Medium tasks: {'✅ PASS' if medium_ok else '❌ FAIL'}")
-    print(f"Hard tasks:   {'✅ PASS' if hard_ok else '❌ FAIL'}")
-    print(f"\nOverall:      {'✅ ALL TASKS WORKING' if (easy_ok and medium_ok and hard_ok) else '❌ SOME TASKS FAILING'}")
-    print("="*70)

test_debug.py

@@ -1,62 +0,0 @@
-#!/usr/bin/env python3
-"""Test script to debug failing tasks"""
-
-from server.tasks.task_easy import get_task_by_id
-from server.tasks.task_hard import get_task_by_id as get_hard_task_by_id
-from server.graders.grader_easy import grade_easy
-from server.graders.grader_hard import grade_hard
-
-# Test easy_014
-print("="*60)
-print("Testing easy_014")
-print("="*60)
-task_easy = get_task_by_id('easy_014')
-print(f"Task ID: {task_easy['task_id']}")
-print(f"Test cases: {task_easy['test_cases']}")
-
-try:
-    buggy_code = task_easy['buggy_code']
-    reward, passed, total, feedback, results = grade_easy(buggy_code, task_easy)
-    print(f"\nBuggy code result: {passed}/{total}, reward={reward}")
-except Exception as e:
-    print(f"\nERROR with buggy code: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-try:
-    fixed_code = task_easy['fixed_code']
-    reward, passed, total, feedback, results = grade_easy(fixed_code, task_easy)
-    print(f"\nFixed code result: {passed}/{total}, reward={reward}")
-    print(f"Feedback:\n{feedback}")
-except Exception as e:
-    print(f"\nERROR with fixed code: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-# Test hard_010
-print("\n" + "="*60)
-print("Testing hard_010")
-print("="*60)
-task_hard = get_hard_task_by_id('hard_010')
-print(f"Task ID: {task_hard['task_id']}")
-print(f"Test cases: {task_hard['test_cases']}")
-
-try:
-    buggy_code = task_hard['buggy_code']
-    reward, passed, total, feedback, results = grade_hard(buggy_code, task_hard, explanation=None)
-    print(f"\nBuggy code result (no explanation): {passed}/{total}, reward={reward}")
-except Exception as e:
-    print(f"\nERROR with buggy code: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-try:
-    fixed_code = task_hard['fixed_code']
-    explanation = "The bug was that there was no visited set to track already visited nodes, which caused infinite loops in graphs with cycles."
-    reward, passed, total, feedback, results = grade_hard(fixed_code, task_hard, explanation=explanation)
-    print(f"\nFixed code result (with explanation): {passed}/{total}, reward={reward}")
-    print(f"Feedback:\n{feedback}")
-except Exception as e:
-    print(f"\nERROR with fixed code: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()

test_specific_tasks.py

@@ -1,128 +0,0 @@
-#!/usr/bin/env python3
-"""Test medium_005 and hard_011 specifically"""
-
-from server.tasks.task_medium import get_task_by_id as get_medium_task
-from server.tasks.task_hard import get_task_by_id as get_hard_task
-from server.graders.grader_medium import grade_medium
-from server.graders.grader_hard import grade_hard
-
-print("="*70)
-print("Testing MEDIUM_005")
-print("="*70)
-task = get_medium_task('medium_005')
-print(f"Task ID: {task['task_id']}")
-print(f"Instructions: {task['instructions']}")
-print(f"\nBuggy code:")
-print(task['buggy_code'])
-print(f"\nFixed code:")
-print(task['fixed_code'])
-print(f"\nTest cases: {task['test_cases']}")
-
-# Test with buggy code
-print("\n--- Testing BUGGY code ---")
-try:
-    reward, passed, total, feedback, results = grade_medium(task['buggy_code'], task)
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-    print(f"Feedback:\n{feedback}")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-# Test with fixed code
-print("\n--- Testing FIXED code ---")
-try:
-    reward, passed, total, feedback, results = grade_medium(task['fixed_code'], task)
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-    for r in results:
-        print(f"  Test {r['test_id']}: {'✅' if r['passed'] else '❌'}")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-print("\n" + "="*70)
-print("Testing HARD_011")
-print("="*70)
-task = get_hard_task('hard_011')
-print(f"Task ID: {task['task_id']}")
-print(f"Instructions: {task['instructions']}")
-print(f"\nBuggy code:")
-print(task['buggy_code'])
-print(f"\nFixed code:")
-print(task['fixed_code'])
-print(f"\nTest cases: {task['test_cases']}")
-print(f"\nExplanation keywords: {task['explanation_keywords']}")
-
-# Test with buggy code (no explanation)
-print("\n--- Testing BUGGY code (no explanation) ---")
-try:
-    reward, passed, total, feedback, results = grade_hard(task['buggy_code'], task, explanation=None)
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-    print(f"Feedback:\n{feedback[:300]}...")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-# Test with fixed code and good explanation
-print("\n--- Testing FIXED code (with good explanation) ---")
-explanation = "The bug was in the iteration order. The inner loop must iterate backward (from capacity down to weights[i]) to prevent using the same item multiple times, which would turn this into an unbounded knapsack instead of 0/1 knapsack."
-try:
-    reward, passed, total, feedback, results = grade_hard(task['fixed_code'], task, explanation=explanation)
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-    for r in results:
-        print(f"  Test {r['test_id']}: {'✅' if r['passed'] else '❌'}")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")
-    import traceback
-    traceback.print_exc()
-
-# Test some potentially problematic LLM-generated code
-print("\n" + "="*70)
-print("Testing POTENTIALLY BAD LLM CODE for medium_005")
-print("="*70)
-
-bad_code_1 = """
-def count_frequency(lst):
-    freq = {}
-    for item in lst:
-        freq[item] = freq.get(item, 0) + 1
-    return freq
-"""
-print("Testing: Using .get() method (should work)")
-try:
-    reward, passed, total, feedback, results = grade_medium(bad_code_1, get_medium_task('medium_005'))
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")
-
-bad_code_2 = """
-def count_frequency(lst):
-    from collections import Counter
-    return dict(Counter(lst))
-"""
-print("\nTesting: Using Counter (should work)")
-try:
-    reward, passed, total, feedback, results = grade_medium(bad_code_2, get_medium_task('medium_005'))
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")
-
-bad_code_3 = """
-def count_frequency(lst):
-    freq = {}
-    for item in lst:
-        if item in freq:
-            freq[item] = freq[item] + 1  # Still wrong - should be +=
-        else:
-            freq[item] = freq[item] + 1  # This will cause KeyError!
-    return freq
-"""
-print("\nTesting: Code with KeyError (should fail gracefully)")
-try:
-    reward, passed, total, feedback, results = grade_medium(bad_code_3, get_medium_task('medium_005'))
-    print(f"Result: {passed}/{total}, reward={reward:.2f}")
-    print(f"Feedback: {feedback[:200]}...")
-except Exception as e:
-    print(f"ERROR: {type(e).__name__}: {e}")