Commit graph

3 commits

Author SHA1 Message Date
335efc5514 feat: Implement enhanced action economy for LLM agent orchestration (#156)
- Add action economy system with free (LOOK, SPEAK) vs turn-ending (GO, WAIT, TAKE) actions
- Implement LOOK action with detailed descriptions for doors, objects, entities, directions
- Add SPEAK/ANNOUNCE speech system with room-wide and proximity-based message delivery
- Create multi-tile pathing with FOV interrupt detection (path cancels when new entity visible)
- Implement TAKE action with adjacency requirement and clear error messages
- Add conversation history and error feedback loop so agents learn from failed actions
- Create structured simulation logging for offline viewer replay
- Document offline viewer requirements in OFFLINE_VIEWER_SPEC.md
- Fix import path in 1_multi_agent_demo.py for standalone execution

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-28 20:50:00 -05:00
de739037f0 feat: Add TurnOrchestrator for multi-turn LLM simulation (addresses #156)
TurnOrchestrator: Coordinates multi-agent turn-based simulation
- Perspective switching with FOV layer updates
- Screenshot capture per agent per turn
- Pluggable LLM query callback
- SimulationStep/SimulationLog for full context capture
- JSON save/load with replay support

New demos:
- 2_integrated_demo.py: WorldGraph + action execution integration
- 3_multi_turn_demo.py: Complete multi-turn simulation with logging

Updated 1_multi_agent_demo.py with action parser/executor integration.

Tested with Qwen2.5-VL-32B: agents successfully navigate based on
WorldGraph descriptions and VLM visual input.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-14 12:53:48 -05:00
4713b62535 feat: Add VLLM integration demos for multi-agent research (#156)
- 0_basic_vllm_demo.py: Single agent with FOV, grounded text, VLLM query
- 1_multi_agent_demo.py: Three agents with perspective cycling

Features demonstrated:
- Headless step() + screenshot() for AI-driven gameplay
- ColorLayer.apply_perspective() for per-agent fog of war
- Grounded text generation based on entity visibility
- Sequential VLLM queries with vision model support
- Proper FOV reset between perspective switches

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-02 09:21:25 -05:00