Initial project scaffold: dataset schema, 31 seed training examples, Mineflayer bot framework, and 7-phase roadmap

- IDEA.md: project scope (Minecraft ops AI assistant via qwen3-coder LoRA/SFT) - PLAN.md: complete roadmap with prior art analysis, architecture, phased plan, dev server docs - data/schema.json: training example JSON Schema with negative_output support - data/processed/seed_dataset.jsonl: 31 validated examples from repair code, prayer logs, session history - data/validate_dataset.py: schema validator with summary statistics - ingame/: Mineflayer bot framework (test_connect, spawn_bots, aware_bots with full event logging) - Directory structure for knowledge/, eval/, training/, agent/ (Phase 1.3+ work)
2026-03-18 01:51:28 -04:00
commit 827850b8d7
21 changed files with 1136 additions and 0 deletions
@@ -0,0 +1,95 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "Minecraft Ops Training Example",
+  "type": "object",
+  "required": ["id", "source", "category", "input", "output"],
+  "properties": {
+    "id": {
+      "type": "string",
+      "description": "Unique identifier (UUID or sequential)"
+    },
+    "source": {
+      "type": "string",
+      "enum": ["repair_pattern", "prayer_log", "sudo_log", "bug_report", "session_history", "manual", "synthetic"],
+      "description": "Where this example was extracted from"
+    },
+    "category": {
+      "type": "string",
+      "enum": ["command_gen", "troubleshoot", "info", "safety", "negative"],
+      "description": "Task category for evaluation bucketing"
+    },
+    "input": {
+      "type": "object",
+      "required": ["user_message"],
+      "properties": {
+        "user_message": {
+          "type": "string",
+          "description": "The player request or prompt"
+        },
+        "server_context": {
+          "type": "object",
+          "properties": {
+            "server_type": { "type": "string", "enum": ["vanilla", "paper"] },
+            "version": { "type": "string" },
+            "online_players": { "type": "array", "items": { "type": "string" } },
+            "player_position": {
+              "type": "object",
+              "properties": {
+                "x": { "type": "number" },
+                "y": { "type": "number" },
+                "z": { "type": "number" }
+              }
+            },
+            "recent_log_lines": { "type": "array", "items": { "type": "string" } }
+          }
+        }
+      }
+    },
+    "output": {
+      "type": "object",
+      "required": ["commands"],
+      "properties": {
+        "reasoning": {
+          "type": "string",
+          "description": "Chain-of-thought explanation of why these commands are correct"
+        },
+        "commands": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "Correct RCON commands (no leading slash)"
+        },
+        "message": {
+          "type": "string",
+          "description": "Response text to player (for god mode; empty for sudo)"
+        },
+        "safety_flags": {
+          "type": "array",
+          "items": { "type": "string", "enum": ["destructive", "teleport", "op_required", "affects_all_players"] },
+          "description": "Safety annotations for command validation"
+        }
+      }
+    },
+    "negative_output": {
+      "type": "object",
+      "description": "What the model ACTUALLY produced (wrong). Present only in negative/repair examples.",
+      "properties": {
+        "commands": {
+          "type": "array",
+          "items": { "type": "string" }
+        },
+        "error": {
+          "type": "string",
+          "description": "Why the original output was wrong"
+        }
+      }
+    },
+    "metadata": {
+      "type": "object",
+      "properties": {
+        "difficulty": { "type": "string", "enum": ["easy", "medium", "hard"] },
+        "validated": { "type": "boolean" },
+        "extracted_from": { "type": "string", "description": "Source file and line/function reference" }
+      }
+    }
+  }
+}