McRogueFace/tests/vllm_demo
John McCardle 2890528e21 feat: Add action parser and executor for LLM agent actions
ActionParser: Extracts structured actions from LLM text responses
- Regex patterns for GO, WAIT, LOOK, TAKE, DROP, PUSH, USE, etc.
- Direction normalization (N→NORTH, UP→NORTH)
- Handles "Action: GO EAST" and fallback patterns
- 12 unit tests covering edge cases

ActionExecutor: Executes parsed actions in the game world
- Movement with collision detection (walls, entities)
- Boundary checking
- ActionResult with path data for animation replay

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-14 12:53:39 -05:00
..
0_basic_vllm_demo.py feat: Add VLLM integration demos for multi-agent research (#156) 2025-12-02 09:21:25 -05:00
1_multi_agent_demo.py feat: Add VLLM integration demos for multi-agent research (#156) 2025-12-02 09:21:25 -05:00
action_executor.py feat: Add action parser and executor for LLM agent actions 2025-12-14 12:53:39 -05:00
action_parser.py feat: Add action parser and executor for LLM agent actions 2025-12-14 12:53:39 -05:00
test_action_parser.py feat: Add action parser and executor for LLM agent actions 2025-12-14 12:53:39 -05:00
test_world_graph.py feat: Add WorldGraph for deterministic room descriptions (closes #155) 2025-12-14 12:53:30 -05:00
world_graph.py feat: Add WorldGraph for deterministic room descriptions (closes #155) 2025-12-14 12:53:30 -05:00