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
..
benchmarks	Tests for cached rendering performance	2025-11-28 23:28:13 -05:00
demo	docs: Update grid demo and regenerate API docs	2025-12-02 09:21:43 -05:00
geometry_demo	fix: Refine geometry demos for 1024x768 and fix animations	2025-11-26 04:54:13 -05:00
integration	Squashed commit of the following: [alpha_presentable]	2025-07-15 21:30:49 -04:00
notes	feat: Exit on first Python callback exception (closes #133)	2025-11-26 10:26:30 -05:00
regression	feat: Migrate Grid to user-driven layer rendering (closes #150)	2025-11-28 23:04:09 -05:00
unit	Add warning when starting benchmark in headless mode	2025-12-01 22:20:19 -05:00
vllm_demo	feat: Add action parser and executor for LLM agent actions	2025-12-14 12:53:39 -05:00
run_tests.py	refactor: comprehensive test suite overhaul and demo system	2025-11-25 23:37:05 -05:00