# Hours 3-4: Integration and Multi-Turn Demo

**Issues**: #154, #155, #156 (integration)
**Goal**: Complete turn-based simulation with proper context and logging
**Dependencies**: Hour 1 (Action Parser/Executor), Hour 2 (WorldGraph)

---

## Hour 3: Integration

### Goal
Wire WorldGraph into the demo so agents receive proper IF-style descriptions.

### Deliverables

1. `2_integrated_demo.py` - New demo combining WorldGraph + Action execution
2. Enhanced `ActionExecutor` with room-aware movement

---

### File: `2_integrated_demo.py`

```python
#!/usr/bin/env python3
"""
Integrated VLLM Demo
====================

Combines:
- WorldGraph for structured room descriptions (#155)
- Action parsing and execution (#156)
- Per-agent perspective rendering

This is the foundation for multi-turn simulation.
"""

import mcrfpy
from mcrfpy import automation
import sys
import os
import requests
import base64

from world_graph import WorldGraph, Room, Door, WorldObject, Direction, AgentInfo, create_two_room_scenario
from action_parser import parse_action, ActionType
from action_executor import ActionExecutor

# Configuration
VLLM_URL = "http://192.168.1.100:8100/v1/chat/completions"
SCREENSHOT_DIR = "/tmp/vllm_integrated"

# Sprite constants
FLOOR_TILE = 0
WALL_TILE = 40
WIZARD_SPRITE = 84
KNIGHT_SPRITE = 96


class Agent:
    """Agent wrapper with WorldGraph integration."""

    def __init__(self, name: str, display_name: str, entity, world: WorldGraph):
        self.name = name
        self.display_name = display_name
        self.entity = entity
        self.world = world
        self.message_history = []  # For speech system

    @property
    def pos(self) -> tuple:
        return (int(self.entity.pos[0]), int(self.entity.pos[1]))

    @property
    def current_room(self) -> str:
        room = self.world.room_at(*self.pos)
        return room.name if room else None

    def get_context(self, visible_agents: list) -> dict:
        """Build complete context for LLM query."""
        room_name = self.current_room

        # Convert to AgentInfo for WorldGraph
        agent_infos = [
            AgentInfo(a.name, a.display_name, a.pos, is_player=(a.name == self.name))
            for a in visible_agents
        ]

        return {
            "location": self.world.describe_room(
                room_name,
                visible_agents=agent_infos,
                observer_name=self.name
            ),
            "available_actions": self.world.get_available_actions(room_name),
            "recent_messages": self.message_history[-5:],
        }


def file_to_base64(file_path):
    with open(file_path, 'rb') as f:
        return base64.b64encode(f.read()).decode('utf-8')


def llm_chat_completion(messages: list):
    try:
        response = requests.post(VLLM_URL, json={'messages': messages}, timeout=60)
        return response.json()
    except requests.exceptions.RequestException as e:
        return {"error": str(e)}


def message_with_image(text, image_path):
    image_data = file_to_base64(image_path)
    return {
        "role": "user",
        "content": [
            {"type": "text", "text": text},
            {"type": "image_url", "image_url": {"url": "data:image/png;base64," + image_data}}
        ]
    }


def setup_scene(world: WorldGraph):
    """Create scene from WorldGraph."""
    mcrfpy.createScene("integrated_demo")
    mcrfpy.setScene("integrated_demo")
    ui = mcrfpy.sceneUI("integrated_demo")

    texture = mcrfpy.Texture("assets/kenney_TD_MR_IP.png", 16, 16)

    # Create grid sized for the world
    grid = mcrfpy.Grid(
        grid_size=(25, 15),
        texture=texture,
        pos=(5, 5),
        size=(1014, 700)
    )
    grid.fill_color = mcrfpy.Color(20, 20, 30)
    grid.zoom = 2.0
    ui.append(grid)

    # Initialize all as walls
    for x in range(25):
        for y in range(15):
            point = grid.at(x, y)
            point.tilesprite = WALL_TILE
            point.walkable = False
            point.transparent = False

    # Carve out rooms from WorldGraph
    for room in world.rooms.values():
        for rx in range(room.x, room.x + room.width):
            for ry in range(room.y, room.y + room.height):
                if 0 <= rx < 25 and 0 <= ry < 15:
                    point = grid.at(rx, ry)
                    point.tilesprite = FLOOR_TILE
                    point.walkable = True
                    point.transparent = True

    # Place doors
    for door in world.doors:
        dx, dy = door.position
        if 0 <= dx < 25 and 0 <= dy < 15:
            point = grid.at(dx, dy)
            point.tilesprite = FLOOR_TILE
            point.walkable = not door.locked
            point.transparent = True

    # Create FOV layer
    fov_layer = grid.add_layer('color', z_index=10)
    fov_layer.fill(mcrfpy.Color(0, 0, 0, 255))

    return grid, fov_layer


def create_agents(grid, world: WorldGraph, texture) -> list:
    """Create agent entities in their starting rooms."""
    agents = []

    # Agent A: Wizard in guard_room
    guard_room = world.rooms["guard_room"]
    wizard_entity = mcrfpy.Entity(
        grid_pos=guard_room.center,
        texture=texture,
        sprite_index=WIZARD_SPRITE
    )
    grid.entities.append(wizard_entity)
    agents.append(Agent("Wizard", "a wizard", wizard_entity, world))

    # Agent B: Knight in armory
    armory = world.rooms["armory"]
    knight_entity = mcrfpy.Entity(
        grid_pos=armory.center,
        texture=texture,
        sprite_index=KNIGHT_SPRITE
    )
    grid.entities.append(knight_entity)
    agents.append(Agent("Knight", "a knight", knight_entity, world))

    return agents


def switch_perspective(grid, fov_layer, agent):
    """Switch view to agent's perspective."""
    fov_layer.fill(mcrfpy.Color(0, 0, 0, 255))
    fov_layer.apply_perspective(
        entity=agent.entity,
        visible=mcrfpy.Color(0, 0, 0, 0),
        discovered=mcrfpy.Color(40, 40, 60, 180),
        unknown=mcrfpy.Color(0, 0, 0, 255)
    )
    agent.entity.update_visibility()

    px, py = agent.pos
    grid.center = (px * 16 + 8, py * 16 + 8)


def get_visible_agents(grid, observer, all_agents) -> list:
    """Get agents visible to the observer."""
    visible = []
    for agent in all_agents:
        if agent.name == observer.name:
            continue
        ax, ay = agent.pos
        if grid.is_in_fov(ax, ay):
            visible.append(agent)
    return visible


def query_agent_llm(agent, screenshot_path, context) -> str:
    """Query VLLM for agent's action."""

    system_prompt = f"""You are {agent.display_name} in a roguelike dungeon game.
You see the world through screenshots and receive text descriptions.
Your goal is to explore and interact with your environment.
Always end your response with a clear action declaration: "Action: <ACTION>"
"""

    # Build the user prompt with WorldGraph context
    actions_str = ", ".join(context["available_actions"])

    user_prompt = f"""{context["location"]}

Available actions: {actions_str}

Look at the screenshot showing your current view. The dark areas are outside your field of vision.

What would you like to do? State your reasoning briefly (1-2 sentences), then declare your action.
Example: "I see a key on the ground that might be useful. Action: TAKE brass_key"
"""

    messages = [
        {"role": "system", "content": system_prompt},
        message_with_image(user_prompt, screenshot_path)
    ]

    resp = llm_chat_completion(messages)

    if "error" in resp:
        return f"[VLLM Error: {resp['error']}]"
    return resp.get('choices', [{}])[0].get('message', {}).get('content', 'No response')


def run_single_turn(grid, fov_layer, agents, executor, turn_num):
    """Execute one turn for all agents."""
    print(f"\n{'='*70}")
    print(f"TURN {turn_num}")
    print("=" * 70)

    results = []

    for agent in agents:
        print(f"\n--- {agent.name}'s Turn ---")
        print(f"Position: {agent.pos} | Room: {agent.current_room}")

        # Switch perspective
        switch_perspective(grid, fov_layer, agent)
        mcrfpy.step(0.016)

        # Screenshot
        screenshot_path = os.path.join(SCREENSHOT_DIR, f"turn{turn_num}_{agent.name.lower()}.png")
        automation.screenshot(screenshot_path)

        # Get context using WorldGraph
        visible = get_visible_agents(grid, agent, agents)
        context = agent.get_context(visible + [agent])  # Include self for filtering

        print(f"Context: {context['location']}")
        print(f"Actions: {context['available_actions']}")

        # Query LLM
        print(f"\nQuerying VLLM...")
        response = query_agent_llm(agent, screenshot_path, context)
        print(f"Response: {response[:200]}...")

        # Parse and execute
        action = parse_action(response)
        print(f"Parsed: {action.type.value} {action.args}")

        result = executor.execute(agent, action)
        print(f"Result: {'SUCCESS' if result.success else 'FAILED'} - {result.message}")

        results.append({
            "agent": agent.name,
            "context": context,
            "response": response,
            "action": action,
            "result": result
        })

    return results


def run_demo():
    """Main demo: single integrated turn."""
    print("=" * 70)
    print("Integrated WorldGraph + Action Demo")
    print("=" * 70)

    os.makedirs(SCREENSHOT_DIR, exist_ok=True)

    # Create world from WorldGraph
    world = create_two_room_scenario()

    # Setup scene
    grid, fov_layer = setup_scene(world)

    # Create agents
    texture = mcrfpy.Texture("assets/kenney_TD_MR_IP.png", 16, 16)
    agents = create_agents(grid, world, texture)

    # Create executor
    executor = ActionExecutor(grid)

    # Run one turn
    results = run_single_turn(grid, fov_layer, agents, executor, turn_num=1)

    print("\n" + "=" * 70)
    print("Demo Complete")
    print("=" * 70)

    return True


if __name__ == "__main__":
    try:
        success = run_demo()
        sys.exit(0 if success else 1)
    except Exception as e:
        import traceback
        traceback.print_exc()
        sys.exit(1)
```

---

## Hour 4: Multi-Turn Demo

### Goal
Run multiple turns with simulation logging for replay.

### Deliverables

1. `turn_orchestrator.py` - Turn management and logging
2. `3_multi_turn_demo.py` - Complete multi-turn simulation
3. `simulation_log.json` - Saved output for replay

---

### File: `turn_orchestrator.py`

```python
"""
Turn Orchestrator
=================

Manages multi-turn simulation with logging for replay.
"""

import json
import os
from dataclasses import dataclass, asdict
from typing import List, Dict, Any, Optional
from datetime import datetime

from world_graph import WorldGraph
from action_parser import Action, ActionType, parse_action
from action_executor import ActionExecutor, ActionResult


@dataclass
class SimulationStep:
    """Record of one agent's turn."""
    turn: int
    agent_id: str
    agent_position: tuple
    room: str
    perception: Dict[str, Any]      # Context shown to LLM
    llm_response: str               # Raw LLM output
    parsed_action_type: str         # Action type as string
    parsed_action_args: tuple       # Action arguments
    result_success: bool
    result_message: str
    new_position: Optional[tuple] = None
    path: Optional[List[tuple]] = None  # For animation
    timestamp: str = ""

    def __post_init__(self):
        if not self.timestamp:
            self.timestamp = datetime.now().isoformat()


@dataclass
class SimulationLog:
    """Complete simulation record."""
    metadata: Dict[str, Any]
    steps: List[SimulationStep]

    def save(self, path: str):
        """Save log to JSON file."""
        data = {
            "metadata": self.metadata,
            "steps": [asdict(s) for s in self.steps]
        }
        with open(path, 'w') as f:
            json.dump(data, f, indent=2, default=str)

    @classmethod
    def load(cls, path: str) -> 'SimulationLog':
        """Load log from JSON file."""
        with open(path) as f:
            data = json.load(f)
        steps = [SimulationStep(**s) for s in data["steps"]]
        return cls(metadata=data["metadata"], steps=steps)


class TurnOrchestrator:
    """
    Orchestrates multi-turn simulation.

    Handles:
    - Turn sequencing
    - Perspective switching
    - LLM queries
    - Action execution
    - Simulation logging
    """

    def __init__(self, grid, fov_layer, world: WorldGraph, agents: list,
                 screenshot_dir: str, llm_query_fn):
        self.grid = grid
        self.fov_layer = fov_layer
        self.world = world
        self.agents = agents
        self.screenshot_dir = screenshot_dir
        self.llm_query_fn = llm_query_fn  # Function to query LLM

        self.executor = ActionExecutor(grid)
        self.turn_number = 0
        self.steps: List[SimulationStep] = []

        os.makedirs(screenshot_dir, exist_ok=True)

    def run_turn(self) -> List[SimulationStep]:
        """Execute one full turn (all agents act once)."""
        self.turn_number += 1
        turn_steps = []

        for agent in self.agents:
            step = self._run_agent_turn(agent)
            turn_steps.append(step)
            self.steps.append(step)

        return turn_steps

    def run_simulation(self, max_turns: int = 10,
                       stop_condition=None) -> SimulationLog:
        """
        Run complete simulation.

        Args:
            max_turns: Maximum number of turns to run
            stop_condition: Optional callable(orchestrator) -> bool

        Returns:
            SimulationLog with all steps
        """
        print(f"\nStarting simulation: max {max_turns} turns")
        print("=" * 50)

        for turn in range(max_turns):
            print(f"\n--- Turn {turn + 1}/{max_turns} ---")

            self.run_turn()

            # Check stop condition
            if stop_condition and stop_condition(self):
                print(f"Stop condition met at turn {turn + 1}")
                break

        # Create log
        log = SimulationLog(
            metadata={
                "total_turns": self.turn_number,
                "num_agents": len(self.agents),
                "agent_names": [a.name for a in self.agents],
                "timestamp": datetime.now().isoformat(),
                "world_rooms": list(self.world.rooms.keys()),
            },
            steps=self.steps
        )

        return log

    def _run_agent_turn(self, agent) -> SimulationStep:
        """Execute one agent's turn."""
        from mcrfpy import automation
        import mcrfpy

        # Switch perspective
        self._switch_perspective(agent)
        mcrfpy.step(0.016)

        # Screenshot
        screenshot_path = os.path.join(
            self.screenshot_dir,
            f"turn{self.turn_number}_{agent.name.lower()}.png"
        )
        automation.screenshot(screenshot_path)

        # Build context
        visible_agents = self._get_visible_agents(agent)
        context = agent.get_context(visible_agents + [agent])

        # Query LLM
        llm_response = self.llm_query_fn(agent, screenshot_path, context)

        # Parse and execute
        action = parse_action(llm_response)
        result = self.executor.execute(agent, action)

        # Log
        print(f"  {agent.name}: {action.type.value} -> {result.message}")

        return SimulationStep(
            turn=self.turn_number,
            agent_id=agent.name,
            agent_position=agent.pos,
            room=agent.current_room,
            perception=context,
            llm_response=llm_response,
            parsed_action_type=action.type.value,
            parsed_action_args=action.args,
            result_success=result.success,
            result_message=result.message,
            new_position=result.new_position,
            path=result.path
        )

    def _switch_perspective(self, agent):
        """Switch grid view to agent's perspective."""
        import mcrfpy

        self.fov_layer.fill(mcrfpy.Color(0, 0, 0, 255))
        self.fov_layer.apply_perspective(
            entity=agent.entity,
            visible=mcrfpy.Color(0, 0, 0, 0),
            discovered=mcrfpy.Color(40, 40, 60, 180),
            unknown=mcrfpy.Color(0, 0, 0, 255)
        )
        agent.entity.update_visibility()

        px, py = agent.pos
        self.grid.center = (px * 16 + 8, py * 16 + 8)

    def _get_visible_agents(self, observer) -> list:
        """Get agents visible to observer."""
        visible = []
        for agent in self.agents:
            if agent.name == observer.name:
                continue
            ax, ay = agent.pos
            if self.grid.is_in_fov(ax, ay):
                visible.append(agent)
        return visible
```

---

### File: `3_multi_turn_demo.py`

```python
#!/usr/bin/env python3
"""
Multi-Turn Simulation Demo
==========================

Runs multiple turns of agent interaction with full logging.
This is the Phase 1 implementation from issue #154.
"""

import mcrfpy
from mcrfpy import automation
import sys
import os
import requests
import base64

from world_graph import create_two_room_scenario, AgentInfo
from action_parser import parse_action
from action_executor import ActionExecutor
from turn_orchestrator import TurnOrchestrator, SimulationLog

# Configuration
VLLM_URL = "http://192.168.1.100:8100/v1/chat/completions"
SCREENSHOT_DIR = "/tmp/vllm_multi_turn"
LOG_PATH = "/tmp/vllm_multi_turn/simulation_log.json"
MAX_TURNS = 5

# Sprites
FLOOR_TILE = 0
WALL_TILE = 40
WIZARD_SPRITE = 84
KNIGHT_SPRITE = 96


class Agent:
    """Agent with WorldGraph integration."""
    def __init__(self, name, display_name, entity, world):
        self.name = name
        self.display_name = display_name
        self.entity = entity
        self.world = world
        self.message_history = []

    @property
    def pos(self):
        return (int(self.entity.pos[0]), int(self.entity.pos[1]))

    @property
    def current_room(self):
        room = self.world.room_at(*self.pos)
        return room.name if room else None

    def get_context(self, visible_agents):
        room_name = self.current_room
        agent_infos = [
            AgentInfo(a.name, a.display_name, a.pos, is_player=(a.name == self.name))
            for a in visible_agents
        ]
        return {
            "location": self.world.describe_room(room_name, agent_infos, self.name),
            "available_actions": self.world.get_available_actions(room_name),
            "recent_messages": self.message_history[-5:],
        }


def file_to_base64(path):
    with open(path, 'rb') as f:
        return base64.b64encode(f.read()).decode('utf-8')


def llm_query(agent, screenshot_path, context) -> str:
    """Query VLLM for agent action."""
    system = f"""You are {agent.display_name} exploring a dungeon.
You receive visual and text information about your surroundings.
Always end with: Action: <YOUR_ACTION>"""

    actions_str = ", ".join(context["available_actions"])
    user = f"""{context["location"]}

Available: {actions_str}

[Screenshot attached showing your view]

What do you do? Brief reasoning, then Action: <action>"""

    messages = [
        {"role": "system", "content": system},
        {
            "role": "user",
            "content": [
                {"type": "text", "text": user},
                {"type": "image_url", "image_url": {
                    "url": "data:image/png;base64," + file_to_base64(screenshot_path)
                }}
            ]
        }
    ]

    try:
        resp = requests.post(VLLM_URL, json={'messages': messages}, timeout=60)
        data = resp.json()
        if "error" in data:
            return f"[Error: {data['error']}]"
        return data.get('choices', [{}])[0].get('message', {}).get('content', 'No response')
    except Exception as e:
        return f"[Error: {e}]"


def setup_scene(world):
    """Create scene from WorldGraph."""
    mcrfpy.createScene("multi_turn")
    mcrfpy.setScene("multi_turn")
    ui = mcrfpy.sceneUI("multi_turn")

    texture = mcrfpy.Texture("assets/kenney_TD_MR_IP.png", 16, 16)

    grid = mcrfpy.Grid(
        grid_size=(25, 15),
        texture=texture,
        pos=(5, 5),
        size=(1014, 700)
    )
    grid.fill_color = mcrfpy.Color(20, 20, 30)
    grid.zoom = 2.0
    ui.append(grid)

    # Walls everywhere first
    for x in range(25):
        for y in range(15):
            p = grid.at(x, y)
            p.tilesprite = WALL_TILE
            p.walkable = False
            p.transparent = False

    # Carve rooms
    for room in world.rooms.values():
        for rx in range(room.x, room.x + room.width):
            for ry in range(room.y, room.y + room.height):
                if 0 <= rx < 25 and 0 <= ry < 15:
                    p = grid.at(rx, ry)
                    p.tilesprite = FLOOR_TILE
                    p.walkable = True
                    p.transparent = True

    # Place doors
    for door in world.doors:
        dx, dy = door.position
        if 0 <= dx < 25 and 0 <= dy < 15:
            p = grid.at(dx, dy)
            p.tilesprite = FLOOR_TILE
            p.walkable = not door.locked
            p.transparent = True

    # FOV layer
    fov_layer = grid.add_layer('color', z_index=10)
    fov_layer.fill(mcrfpy.Color(0, 0, 0, 255))

    return grid, fov_layer, texture


def create_agents(grid, world, texture):
    """Create agents in starting positions."""
    agents = []

    # Wizard in guard_room
    room_a = world.rooms["guard_room"]
    wizard = mcrfpy.Entity(grid_pos=room_a.center, texture=texture, sprite_index=WIZARD_SPRITE)
    grid.entities.append(wizard)
    agents.append(Agent("Wizard", "a wizard", wizard, world))

    # Knight in armory
    room_b = world.rooms["armory"]
    knight = mcrfpy.Entity(grid_pos=room_b.center, texture=texture, sprite_index=KNIGHT_SPRITE)
    grid.entities.append(knight)
    agents.append(Agent("Knight", "a knight", knight, world))

    return agents


def run_demo():
    """Run multi-turn simulation."""
    print("=" * 70)
    print("Multi-Turn Simulation Demo")
    print(f"Running {MAX_TURNS} turns with 2 agents")
    print("=" * 70)

    os.makedirs(SCREENSHOT_DIR, exist_ok=True)

    # Setup
    world = create_two_room_scenario()
    grid, fov_layer, texture = setup_scene(world)
    agents = create_agents(grid, world, texture)

    # Create orchestrator
    orchestrator = TurnOrchestrator(
        grid=grid,
        fov_layer=fov_layer,
        world=world,
        agents=agents,
        screenshot_dir=SCREENSHOT_DIR,
        llm_query_fn=llm_query
    )

    # Run simulation
    log = orchestrator.run_simulation(max_turns=MAX_TURNS)

    # Save log
    log.save(LOG_PATH)
    print(f"\nSimulation log saved to: {LOG_PATH}")

    # Summary
    print("\n" + "=" * 70)
    print("SIMULATION SUMMARY")
    print("=" * 70)
    print(f"Total turns: {log.metadata['total_turns']}")
    print(f"Total steps: {len(log.steps)}")

    # Per-agent summary
    for agent_name in log.metadata['agent_names']:
        agent_steps = [s for s in log.steps if s.agent_id == agent_name]
        successes = sum(1 for s in agent_steps if s.result_success)
        print(f"\n{agent_name}:")
        print(f"  Actions: {len(agent_steps)}")
        print(f"  Successful: {successes}")
        print(f"  Final position: {agent_steps[-1].new_position or agent_steps[-1].agent_position}")

    return True


if __name__ == "__main__":
    try:
        success = run_demo()
        print("\nPASS" if success else "\nFAIL")
        sys.exit(0 if success else 1)
    except Exception as e:
        import traceback
        traceback.print_exc()
        sys.exit(1)
```

---

## Success Criteria

### Hour 3 Integration
- [ ] WorldGraph generates scene tiles correctly
- [ ] Agents receive IF-style room descriptions from WorldGraph
- [ ] Available actions list appears in LLM prompt
- [ ] Actions are parsed and executed
- [ ] Single turn completes successfully

### Hour 4 Multi-Turn
- [ ] TurnOrchestrator cycles through all agents
- [ ] Multiple turns run sequentially
- [ ] SimulationLog captures all steps
- [ ] Log saves to JSON correctly
- [ ] Log can be loaded back
- [ ] Summary shows agent actions and positions

---

## Example Output

```
======================================================================
Multi-Turn Simulation Demo
Running 5 turns with 2 agents
======================================================================

Starting simulation: max 5 turns
==================================================

--- Turn 1/5 ---
  Wizard: GO EAST -> Moved east to (6, 4)
  Knight: WAIT -> Waited and observed surroundings

--- Turn 2/5 ---
  Wizard: GO EAST -> Moved east to (7, 4)
  Knight: GO WEST -> Moved west to (14, 4)

[... more turns ...]

======================================================================
SIMULATION SUMMARY
======================================================================
Total turns: 5
Total steps: 10

Wizard:
  Actions: 5
  Successful: 4
  Final position: (9, 4)

Knight:
  Actions: 5
  Successful: 3
  Final position: (11, 4)

Simulation log saved to: /tmp/vllm_multi_turn/simulation_log.json

PASS
```

---

## Next Steps (Future Sessions)

After Hours 3-4 are complete:

1. **Speech System** - Add ANNOUNCE/SPEAK actions with message passing
2. **Button-Door Puzzle** - Use `create_button_door_scenario()` for coordination test
3. **Animated Replay** - Play back simulation with movement animations
4. **NPC Behaviors** - Add scripted entities (patrol, flee, etc.)
5. **Affordance Learning** - Track what agents discover about objects