synth-ai 0.2.4.dev6__py3-none-any.whl → 0.2.4.dev7__py3-none-any.whl

synth_ai/environments/examples/enron/environment.py

@@ -1,26 +1,27 @@
 # environment.py
 from __future__ import annotations
-from typing import List, Optional, Dict, Any, Union
-from pydantic import BaseModel, Field
 
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import BaseModel, Field
+from synth_ai.environments.environment.shared_engine import (
+    GetObservationCallable,
+    InternalObservation,
+)
 from synth_ai.environments.environment.tools import (
+    TOOL_REGISTRY,
     EnvToolCall,
     ToolResult,
-    TOOL_REGISTRY,
     register_tool,
 )
-from synth_ai.environments.environment.shared_engine import (
-    GetObservationCallable,
-    InternalObservation,
-)
-from synth_ai.environments.stateful.core import StatefulEnvironment
 from synth_ai.environments.examples.enron.engine import (
-    EnronEngine,
-    ACTION_SEARCH,
-    ACTION_READ,
     ACTION_ANSWER,
+    ACTION_READ,
+    ACTION_SEARCH,
+    EnronEngine,
 )
 from synth_ai.environments.examples.enron.taskset import EnronTaskInstance
+from synth_ai.environments.stateful.core import StatefulEnvironment
 
 
 # -------- pydantic schemas (used by agent / LLM function calls)

synth_ai/environments/examples/enron/taskset.py

@@ -1,20 +1,20 @@
 # taskset.py
 from __future__ import annotations
+
 import asyncio
-from uuid import uuid4
 import os
+from dataclasses import asdict, dataclass
+from uuid import uuid4
 
 from datasets import load_dataset
-from dataclasses import dataclass, asdict
-
 from synth_ai.environments.tasks.core import (
+    Impetus,
+    Intent,
+    SplitInfo,
     Task,
     TaskInstance,
-    TaskInstanceSet,
     TaskInstanceMetadata,
-    SplitInfo,
-    Impetus,
-    Intent,
+    TaskInstanceSet,
 )
 
 enron_task = Task(

synth_ai/environments/examples/minigrid/__init__.py

@@ -5,23 +5,23 @@ with full state management, tool-based interaction, and task generation.
 """
 
 from synth_ai.environments.examples.minigrid.engine import (
+    MiniGridCheckpointObservationCallable,
     MiniGridEngine,
-    MiniGridPublicState,
-    MiniGridPrivateState,
     MiniGridGoalReachedComponent,
-    MiniGridStepPenaltyComponent,
     MiniGridObservationCallable,
-    MiniGridCheckpointObservationCallable,
+    MiniGridPrivateState,
+    MiniGridPublicState,
+    MiniGridStepPenaltyComponent,
 )
 from synth_ai.environments.examples.minigrid.environment import (
+    MiniGridActionInput,
     MiniGridEnvironment,
     MiniGridInteractTool,
-    MiniGridActionInput,
 )
 from synth_ai.environments.examples.minigrid.taskset import (
+    DEFAULT_MINIGRID_TASK,
     MiniGridTaskInstance,
     MiniGridTaskInstanceMetadata,
-    DEFAULT_MINIGRID_TASK,
     create_minigrid_taskset,
     taskset,
 )

synth_ai/environments/examples/minigrid/engine.py

@@ -8,25 +8,25 @@ from __future__ import annotations
 
 import json
 from dataclasses import dataclass, field
-from typing import Any, Dict, Optional, Tuple, Union, List
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 import gymnasium as gym
 import numpy as np
-from minigrid.core.constants import OBJECT_TO_IDX, COLOR_TO_IDX, STATE_TO_IDX
+from minigrid.core.constants import COLOR_TO_IDX, OBJECT_TO_IDX, STATE_TO_IDX
 
-from synth_ai.environments.stateful.engine import StatefulEngine, StatefulEngineSnapshot
-from synth_ai.environments.reproducibility.core import IReproducibleEngine
 from synth_ai.environments.environment.rewards.core import RewardComponent, RewardStack
 from synth_ai.environments.environment.shared_engine import (
     GetObservationCallable,
     InternalObservation,
 )
-from synth_ai.environments.tasks.core import TaskInstance
 from synth_ai.environments.examples.minigrid.environment_mapping import (
-    get_environment_from_seed,
     get_difficulty_from_seed,
+    get_environment_from_seed,
     validate_environment_name,
 )
+from synth_ai.environments.reproducibility.core import IReproducibleEngine
+from synth_ai.environments.stateful.engine import StatefulEngine, StatefulEngineSnapshot
+from synth_ai.environments.tasks.core import TaskInstance
 
 
 @dataclass

synth_ai/environments/examples/minigrid/environment.py

@@ -12,20 +12,20 @@ from typing import Any, Callable, Dict, List, Optional, Union
 import numpy as np
 from pydantic import BaseModel, Field
 
-from synth_ai.environments.environment.tools import AbstractTool, EnvToolCall, ToolResult
-from synth_ai.environments.stateful.core import StatefulEnvironment
-from synth_ai.environments.reproducibility.core import ReproducibleEnvironment
 from synth_ai.environments.environment.shared_engine import (
     GetObservationCallable,
     InternalObservation,
 )
+from synth_ai.environments.environment.tools import AbstractTool, EnvToolCall, ToolResult
 from synth_ai.environments.examples.minigrid.engine import (
+    MiniGridCheckpointObservationCallable,
     MiniGridEngine,
-    MiniGridPublicState,
-    MiniGridPrivateState,
     MiniGridObservationCallable,
-    MiniGridCheckpointObservationCallable,
+    MiniGridPrivateState,
+    MiniGridPublicState,
 )
+from synth_ai.environments.reproducibility.core import ReproducibleEnvironment
+from synth_ai.environments.stateful.core import StatefulEnvironment
 from synth_ai.environments.tasks.core import TaskInstance
 
 

synth_ai/environments/examples/minigrid/puzzle_loader.py

@@ -6,8 +6,9 @@ with deterministic seed-based selection and difficulty filtering.
 """
 
 import logging
-from dataclasses import dataclass, asdict
-from typing import Dict, List, Optional, Tuple, Any
+from dataclasses import asdict, dataclass
+from typing import Any, Dict, List, Optional, Tuple
+
 from synth_ai.environments.examples.minigrid.environment_mapping import ENVIRONMENT_MAPPING
 
 logger = logging.getLogger(__name__)

synth_ai/environments/examples/minigrid/taskset.py

@@ -12,24 +12,24 @@ from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional, Set, Tuple
 from uuid import uuid4
 
-from synth_ai.environments.tasks.api import (
-    Task,
-    TaskInstance,
-    TaskInstanceMetadata,
-    TaskInstanceSet,
-    SplitInfo,
-    Impetus,
-    Intent,
-)
 from synth_ai.environments.examples.minigrid.environment_mapping import (
-    get_environment_from_seed,
-    get_difficulty_from_seed,
     get_all_environments,
+    get_difficulty_from_seed,
+    get_environment_from_seed,
 )
 from synth_ai.environments.examples.minigrid.puzzle_loader import (
-    get_puzzle_loader,
-    get_puzzle_by_seed,
     MiniGridPuzzle,
+    get_puzzle_by_seed,
+    get_puzzle_loader,
+)
+from synth_ai.environments.tasks.api import (
+    Impetus,
+    Intent,
+    SplitInfo,
+    Task,
+    TaskInstance,
+    TaskInstanceMetadata,
+    TaskInstanceSet,
 )
 
 

synth_ai/environments/examples/nethack/achievements.py

@@ -2,8 +2,8 @@
 
 import json
 import os
-from typing import Dict, Any, Optional, Tuple
 from dataclasses import dataclass, field
+from typing import Any, Dict, Optional, Tuple
 
 
 # Exact copy of Balrog's Progress class

synth_ai/environments/examples/nethack/engine.py

@@ -4,27 +4,28 @@ from __future__ import annotations
 
 import asyncio
 import base64
+import logging
 from dataclasses import dataclass, field
-from typing import Dict, Any, Optional, Tuple, List, TYPE_CHECKING, cast
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, cast
+
 import numpy as np
-import logging
 
-from synth_ai.environments.stateful.engine import StatefulEngine, StatefulEngineSnapshot
-from synth_ai.environments.reproducibility.core import IReproducibleEngine
-from synth_ai.environments.environment.rewards.core import RewardStack, RewardComponent
+from synth_ai.environments.environment.rewards.core import RewardComponent, RewardStack
 from synth_ai.environments.environment.shared_engine import (
     GetObservationCallable,
     InternalObservation,
 )
+from synth_ai.environments.reproducibility.core import IReproducibleEngine
+from synth_ai.environments.stateful.engine import StatefulEngine, StatefulEngineSnapshot
 from synth_ai.environments.tasks.core import TaskInstance
 
 logger = logging.getLogger(__name__)
 
 # NLE imports are required
 try:
-    from .helpers.nle_wrapper import NLEWrapper
-    from .helpers.action_mapping import convert_action_to_nle
     from .achievements import NetHackAchievements, calculate_balrog_reward
+    from .helpers.action_mapping import convert_action_to_nle
+    from .helpers.nle_wrapper import NLEWrapper
 except ImportError as e:
     raise ImportError(
         "NLE (NetHack Learning Environment) is required but not installed. "

synth_ai/environments/examples/nethack/environment.py

@@ -3,30 +3,31 @@
 from __future__ import annotations
 
 import json
-from typing import Dict, Any, Optional, List, Union
+from typing import Any, Dict, List, Optional, Union
+
 from pydantic import BaseModel
 
-from synth_ai.environments.stateful.core import StatefulEnvironment
-from synth_ai.environments.reproducibility.core import ReproducibleEnvironment
-from synth_ai.environments.environment.tools import AbstractTool, EnvToolCall, ToolResult
 from synth_ai.environments.environment.shared_engine import (
     GetObservationCallable,
     InternalObservation,
 )
+from synth_ai.environments.environment.tools import AbstractTool, EnvToolCall, ToolResult
+from synth_ai.environments.reproducibility.core import ReproducibleEnvironment
+from synth_ai.environments.stateful.core import StatefulEnvironment
 from synth_ai.environments.tasks.core import TaskInstance
 
 from .engine import (
+    NetHackCheckpointObservationCallable,
     NetHackEngine,
     NetHackObservationCallable,
-    NetHackCheckpointObservationCallable,
-    NetHackPublicState,
     NetHackPrivateState,
+    NetHackPublicState,
 )
 from .helpers import (
-    validate_action,
-    get_action_description,
-    NETHACK_ACTIONS,
     MENU_ACTIONS,
+    NETHACK_ACTIONS,
+    get_action_description,
+    validate_action,
 )
 
 

synth_ai/environments/examples/nethack/helpers/__init__.py

@@ -1,24 +1,23 @@
 """Helper utilities for NetHack environment."""
 
 from .action_mapping import (
-    NETHACK_ACTIONS,
-    MENU_ACTIONS,
-    ALL_ACTIONS,
     ACTION_CATEGORIES,
-    validate_action,
+    ALL_ACTIONS,
+    MENU_ACTIONS,
+    NETHACK_ACTIONS,
+    convert_action_to_nle,
     get_action_description,
     get_actions_for_context,
-    convert_action_to_nle,
     parse_compound_action,
+    validate_action,
 )
-
 from .observation_utils import (
-    format_observation_for_llm,
-    parse_ascii_map,
     extract_game_context,
-    simplify_observation,
     extract_inventory_from_message,
+    format_observation_for_llm,
     identify_item_type,
+    parse_ascii_map,
+    simplify_observation,
 )
 
 __all__ = [

synth_ai/environments/examples/nethack/helpers/action_mapping.py

@@ -1,7 +1,7 @@
 """Action mapping and validation for NetHack."""
 
-from typing import Dict, List, Optional, Tuple
 from dataclasses import dataclass
+from typing import Dict, List, Optional, Tuple
 
 
 @dataclass

synth_ai/environments/examples/nethack/helpers/nle_wrapper.py

@@ -1,6 +1,7 @@
 """NLE integration wrapper for NetHack environment."""
 
-from typing import Dict, Any, Optional, Tuple, List
+from typing import Any, Dict, List, Optional, Tuple
+
 import numpy as np
 
 try:

synth_ai/environments/examples/nethack/helpers/observation_utils.py

@@ -1,7 +1,7 @@
 """Observation processing utilities for NetHack."""
 
-from typing import Dict, Any, List, Optional, Tuple
 import re
+from typing import Any, Dict, List, Optional, Tuple
 
 
 def format_observation_for_llm(observation: Dict[str, Any]) -> str:

synth_ai/environments/examples/nethack/helpers/recording_wrapper.py

@@ -1,15 +1,14 @@
 """Environment wrapper that adds trajectory recording capabilities."""
 
-from typing import Dict, Any, Optional, Tuple
-from pathlib import Path
 import logging
+from pathlib import Path
+from typing import Any, Dict, Optional, Tuple
 
+from src.synth_env.environment.tools import EnvToolCall
 from src.synth_env.examples.nethack.environment import NetHackEnvironment
 from src.synth_env.examples.nethack.helpers.trajectory_recorder import (
     TrajectoryRecorder,
 )
-from src.synth_env.environment.tools import EnvToolCall
-
 
 logger = logging.getLogger(__name__)
 

synth_ai/environments/examples/nethack/helpers/trajectory_recorder.py

@@ -1,14 +1,15 @@
 """Trajectory recording and replay functionality for NetHack."""
 
+import base64
+import gzip
 import json
 import pickle
-import gzip
-from pathlib import Path
-from typing import Dict, Any, List, Optional, Tuple
+from dataclasses import asdict, dataclass
 from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
 import numpy as np
-from dataclasses import dataclass, asdict
-import base64
 
 
 @dataclass

synth_ai/environments/examples/nethack/helpers/visualization/replay_viewer.py

@@ -1,19 +1,19 @@
 """Interactive replay viewer for NetHack trajectories."""
 
+import gzip
+import json
 import os
 import sys
-from pathlib import Path
-from typing import List, Dict, Any, Optional, Tuple
-import json
-import gzip
 from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
 
 # Add parent directory to path for imports
 sys.path.append(str(Path(__file__).parent.parent.parent.parent.parent.parent))
 
 from src.synth_env.examples.nethack.helpers.trajectory_recorder import (
-    TrajectoryRecorder,
     TrajectoryFrame,
+    TrajectoryRecorder,
 )
 from src.synth_env.examples.nethack.helpers.visualization.visualizer import (
     NetHackVisualizer,

synth_ai/environments/examples/nethack/helpers/visualization/visualizer.py

@@ -1,14 +1,15 @@
 """Visualization tools for NetHack trajectories."""
 
-import numpy as np
-from typing import List, Dict, Any, Optional, Tuple
+import json
+from datetime import datetime
 from pathlib import Path
-import matplotlib.pyplot as plt
+from typing import Any, Dict, List, Optional, Tuple
+
 import matplotlib.animation as animation
-from matplotlib.patches import Rectangle
+import matplotlib.pyplot as plt
+import numpy as np
 import seaborn as sns
-from datetime import datetime
-import json
+from matplotlib.patches import Rectangle
 
 try:
     from PIL import Image, ImageDraw, ImageFont

synth_ai/environments/examples/nethack/taskset.py

@@ -3,17 +3,17 @@
 from __future__ import annotations
 
 import random
-from uuid import uuid4
 from dataclasses import dataclass
-from typing import Dict, Any, List, Optional, Set
+from typing import Any, Dict, List, Optional, Set
+from uuid import uuid4
 
 from synth_ai.environments.tasks.core import (
-    TaskInstance,
-    TaskInstanceMetadata,
-    TaskInstanceSet,
     Impetus,
     Intent,
     SplitInfo,
+    TaskInstance,
+    TaskInstanceMetadata,
+    TaskInstanceSet,
 )
 
 

synth_ai/environments/examples/red/engine.py

@@ -1,25 +1,26 @@
 from __future__ import annotations
+
 import logging
-from pathlib import Path
-from typing import Dict, Any, Optional, List
 from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, List, Optional
 
-# Import logging configuration first to suppress JAX debug messages
+from synth_ai.environments.environment.rewards.core import RewardStack
+from synth_ai.environments.reproducibility.core import IReproducibleEngine
 
+# Import logging configuration first to suppress JAX debug messages
 from synth_ai.environments.stateful.engine import StatefulEngine, StatefulEngineSnapshot
-from synth_ai.environments.reproducibility.core import IReproducibleEngine
-from synth_ai.environments.environment.rewards.core import RewardStack
 from synth_ai.environments.tasks.core import TaskInstance
 
-from .engine_helpers.state_extraction import extract_game_state
 from .engine_helpers.reward_components import (
     BadgeRewardComponent,
-    MapTransitionComponent,
     BattleVictoryComponent,
     LevelUpComponent,
-    XPGainComponent,
+    MapTransitionComponent,
     StepPenaltyComponent,
+    XPGainComponent,
 )
+from .engine_helpers.state_extraction import extract_game_state
 
 try:
     from pyboy import PyBoy

synth_ai/environments/examples/red/engine_helpers/reward_components.py

@@ -1,5 +1,6 @@
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class BadgeRewardComponent(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/__init__.py

@@ -4,17 +4,17 @@ Pokemon Red Reward Library
 Comprehensive collection of reward components organized by category.
 """
 
-from .pallet_town_rewards import *
-from .exploration_rewards import *
-from .social_rewards import *
-from .pokemon_rewards import *
+from .adaptive_rewards import *
 from .battle_rewards import *
-from .story_rewards import *
+from .composite_rewards import *
 from .economy_rewards import *
 from .efficiency_rewards import *
+from .exploration_rewards import *
 from .novelty_rewards import *
-from .adaptive_rewards import *
-from .composite_rewards import *
+from .pallet_town_rewards import *
+from .pokemon_rewards import *
+from .social_rewards import *
+from .story_rewards import *
 
 __all__ = [
     # Pallet Town Early Game

synth_ai/environments/examples/red/engine_helpers/reward_library/adaptive_rewards.py

@@ -4,8 +4,9 @@ Adaptive & Learning Reward Components
 Rewards for improvement over time and meta-learning.
 """
 
+from typing import Any, Dict
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any
 
 
 class MistakeRecoveryReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/battle_rewards.py

@@ -4,8 +4,9 @@ Battle & Combat Reward Components
 Rewards for battle victories, combat strategy, and battle efficiency.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class WildPokemonDefeatedReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/composite_rewards.py

@@ -4,8 +4,9 @@ Composite & Milestone Reward Components
 Rewards for achievement combinations and progression streaks.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class PerfectGymRunReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/economy_rewards.py

@@ -4,8 +4,9 @@ Economy & Resource Management Reward Components
 Rewards for money management and inventory optimization.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class FirstEarningsReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/efficiency_rewards.py

@@ -4,8 +4,9 @@ Efficiency & Optimization Reward Components
 Rewards for optimal play, routing, and game knowledge.
 """
 
+from typing import Any, Dict
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any
 
 
 class FastTravelUsageReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/exploration_rewards.py

@@ -4,8 +4,9 @@ Exploration & Discovery Reward Components
 Rewards for map exploration, item discovery, and world interaction.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class NewAreaDiscoveryReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/novelty_rewards.py

@@ -4,8 +4,9 @@ Novelty & Exploration Bonus Reward Components
 Rewards for first-time experiences and curiosity.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class FirstBattleReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/pallet_town_rewards.py

@@ -5,8 +5,9 @@ Rewards specifically designed for the first 50 steps of Pokemon Red,
 focusing on house exploration, town discovery, and story triggers.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class LeaveStartingRoomReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/pokemon_rewards.py

@@ -4,8 +4,9 @@ Pokemon Collection & Management Reward Components
 Rewards for catching Pokemon, Pokedex progress, and Pokemon development.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class FirstPokemonCaughtReward(RewardComponent):

synth_ai/environments/examples/red/engine_helpers/reward_library/social_rewards.py

@@ -4,8 +4,9 @@ Social & NPC Interaction Reward Components
 Rewards for dialogue, information gathering, and NPC interactions.
 """
 
+from typing import Any, Dict, Set
+
 from synth_ai.environments.environment.rewards.core import RewardComponent
-from typing import Dict, Any, Set
 
 
 class NewNPCConversationReward(RewardComponent):