GPU scheduler, 14-tool architecture, plugin deployment, event dispatcher
GPU Scheduler (gpu.sethpc.xyz): - Live dashboard with 4 GPUs, training monitor, loss sparklines - Preset-based job scheduler with 3 triggers (time, finish_training, cost) - Model selection per GPU, pipeline configuration - Tool self-play and training pipeline types - Behind Google OAuth, live-refresh without page reload Tool Architecture (14 tools): - 3 new tools: world.nearby_entities, memory.read, memory.write - 7 script.* tools: write, validate, execute, read, list, delete, schedule - ScriptManager: full mcfunction datapack CRUD with RCON validation - Training data: 1,430 tool examples (up from 1,159) Plugin Deployment (paper-ai-25567): - WorldGuard 7.0.12, CoreProtect CE 23.1, EssentialsX 2.21.2, Vault 1.7.3 - Fresh greenfield world reset - 104 RCON-validated plugin training examples Event Dispatcher: - Watches server log for deaths, joins, advancements, PvP kills - Configurable trigger probability and cooldowns per event type - Deployed to dev server, fires god_system prompts on events - 21 event-response training examples Training Infrastructure: - train_lora.py: --save-steps 50, --resume from checkpoint - run_training.sh: stops Ollama, activates conda, restarts after - Passwordless sudo for ollama services on steel141 - Dev server added to MCSManager with autoStart Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mortdecai
@@ -0,0 +1,567 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate expanded tool-calling training data for underrepresented tools.
|
||||
|
||||
Targets:
|
||||
- minecraft.wiki_lookup: +50 examples
|
||||
- world.player_info: +50 examples
|
||||
- world.server_state: +30 examples
|
||||
- world.nearby_entities: +40 examples (NEW tool)
|
||||
- memory.read: +30 examples (NEW tool)
|
||||
- memory.write: +25 examples (NEW tool)
|
||||
- chained tool calls: +25 examples (multi-tool sequences)
|
||||
|
||||
Total: ~250 new training examples
|
||||
|
||||
Usage:
|
||||
python training/scripts/generate_expanded_tool_training.py
|
||||
"""
|
||||
|
||||
import json
|
||||
import random
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from agent.tools.tool_schemas import qwen3_tools_block, QWEN3_TOOLS
|
||||
from agent.prompts.system_prompts import SYNTAX_RULES, RISK_GRADIENT
|
||||
|
||||
OUTPUT_PATH = PROJECT_ROOT / "data" / "raw" / "expanded_tool_training.jsonl"
|
||||
|
||||
TOOLS_BLOCK = qwen3_tools_block()
|
||||
|
||||
SUDO_TOOL_SYSTEM = (
|
||||
"You are a Minecraft 1.21 command translator for a server admin. "
|
||||
"You receive natural language requests and return valid RCON commands.\n\n"
|
||||
"PERMISSION LEVEL: 4 (generous). Only refuse level 0-1 actions.\n\n"
|
||||
"You have access to tools. Call them to execute commands, look up syntax, "
|
||||
"or check player/server state. When a command fails, analyze the error "
|
||||
"and retry with a corrected command.\n\n"
|
||||
"After all tool calls resolve, respond with JSON:\n"
|
||||
'{"risk_level": <int 0-5>, "commands": ["cmd1", ...], "reasoning": "why"}\n\n'
|
||||
+ SYNTAX_RULES + RISK_GRADIENT + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
GOD_TOOL_SYSTEM = (
|
||||
"You are God in a Minecraft server. Players pray to you and you respond "
|
||||
"with divine judgment.\n\n"
|
||||
"You have access to tools. Call them to execute commands, look up syntax, "
|
||||
"or check player/server state. When a command fails, analyze the error "
|
||||
"and retry with a corrected command.\n\n"
|
||||
"After all tool calls resolve, respond with JSON:\n"
|
||||
'{"risk_level": <int 0-5>, "message": "Your divine response", '
|
||||
'"commands": ["cmd1", ...], "reasoning": "why"}\n\n'
|
||||
+ SYNTAX_RULES + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
PLAYERS = ["slingshooter08", "Ace13245", "TheBigBoss", "xXDragonSlayerXx", "CreeperKing99", "NotchFan2012"]
|
||||
|
||||
|
||||
def sys_msg(mode="sudo"):
|
||||
return {"role": "system", "content": GOD_TOOL_SYSTEM if mode == "god" else SUDO_TOOL_SYSTEM}
|
||||
|
||||
def user_msg(text):
|
||||
return {"role": "user", "content": text}
|
||||
|
||||
def tool_call(name, args):
|
||||
return {"role": "assistant", "content": f"<tool_call>\n{json.dumps({'name': name, 'arguments': args})}\n</tool_call>"}
|
||||
|
||||
def tool_result(data):
|
||||
return {"role": "tool", "content": json.dumps(data)}
|
||||
|
||||
def final_response(resp):
|
||||
return {"role": "assistant", "content": json.dumps(resp)}
|
||||
|
||||
def rpos():
|
||||
return {"x": random.randint(-500, 500), "y": random.randint(62, 120), "z": random.randint(-500, 500)}
|
||||
|
||||
def rcon_ok(cmd, player="slingshooter08"):
|
||||
if cmd.startswith("give "): return f"Gave item to {player}"
|
||||
if cmd.startswith("tp "): return f"Teleported {player}"
|
||||
if cmd.startswith("effect give "): return f"Applied effect to {player}"
|
||||
if cmd.startswith("kill "): return "Killed entity"
|
||||
if cmd.startswith("summon "): return "Summoned new entity"
|
||||
if cmd.startswith("fill "): return "Successfully filled blocks"
|
||||
if cmd.startswith("setblock "): return "Changed the block"
|
||||
if cmd.startswith("weather "): return "Changing weather"
|
||||
if cmd.startswith("time set "): return "Set the time"
|
||||
if cmd.startswith("clear "): return f"Removed items from {player}"
|
||||
if cmd.startswith("gamerule "): return "Gamerule updated"
|
||||
if cmd.startswith("execute "): return "Executed command"
|
||||
if cmd.startswith("title "): return "Title displayed"
|
||||
if cmd.startswith("playsound "): return f"Played sound to {player}"
|
||||
if cmd.startswith("scoreboard "): return "Scoreboard updated"
|
||||
return "Command executed successfully"
|
||||
|
||||
def make_example(eid, etype, messages):
|
||||
return {"id": eid, "source": "expanded_tool_training", "type": etype, "messages": messages}
|
||||
|
||||
|
||||
# ── Wiki Lookup Examples ──────────────────────────────────────────────────
|
||||
|
||||
WIKI_EXAMPLES = [
|
||||
("sudo give me a mace with the best enchantments", "mace enchantments 1.21",
|
||||
"Mace enchantments in 1.21:\n- Density (1-5): Increases damage based on fall distance\n- Breach (1-4): Reduces armor effectiveness\n- Wind Burst (1-3): Launches attacker upward on hit\n- Smite (1-5): Extra damage to undead\n- Bane of Arthropods (1-5): Extra damage to arthropods\n- Fire Aspect (1-2): Sets target on fire\n- Unbreaking (1-3): Durability\n- Mending (1): XP repair\nNote: Density, Breach, Smite, and Bane of Arthropods are mutually exclusive.",
|
||||
"https://minecraft.wiki/w/Mace", ["give {p} minecraft:mace[enchantments={{density:5,wind_burst:3,fire_aspect:2,unbreaking:3,mending:1}}] 1"],
|
||||
"Looked up mace enchantments. Density and breach are exclusive — chose density for max fall damage. Added wind_burst for combos."),
|
||||
|
||||
("sudo what are all the copper block variants?", "copper block variants oxidation 1.21",
|
||||
"Copper blocks in 1.21 have 4 oxidation states and 2 waxing states:\n- copper_block, exposed_copper, weathered_copper, oxidized_copper\n- Cut variants: cut_copper, exposed_cut_copper, weathered_cut_copper, oxidized_cut_copper\n- Slab/stair variants for each\n- Waxed variants of all (prefix waxed_)\n- Copper bulb, copper door, copper trapdoor, copper grate (also with oxidation states)\nUse honeycomb to wax. Axe to scrape oxidation.",
|
||||
"https://minecraft.wiki/w/Copper_Block", ["give {p} minecraft:copper_block 64", "give {p} minecraft:exposed_copper 64", "give {p} minecraft:weathered_copper 64", "give {p} minecraft:oxidized_copper 64"],
|
||||
"Looked up copper variants. Gave one stack of each oxidation state."),
|
||||
|
||||
("sudo how do I make a command block chain?", "command block chain repeating impulse 1.21",
|
||||
"Command block types:\n- Impulse (orange): Executes once when triggered\n- Chain (green): Executes when the block behind it activates\n- Repeating (purple): Executes every tick while powered\n\nPlacement: command_block (impulse), chain_command_block, repeating_command_block\nModes: Always Active or Needs Redstone\nConditional: Only runs if previous block in chain succeeded",
|
||||
"https://minecraft.wiki/w/Command_Block", ["give {p} minecraft:command_block 1", "give {p} minecraft:chain_command_block 4", "give {p} minecraft:repeating_command_block 1"],
|
||||
"Looked up command block types. Gave impulse, chain, and repeating blocks for a chain setup."),
|
||||
|
||||
("sudo what's the syntax for the attribute command?", "attribute command syntax 1.21",
|
||||
"attribute <target> <attribute> base get|set <value>\nattribute <target> <attribute> modifier add <uuid> <name> <value> add|multiply|multiply_base\nattribute <target> <attribute> modifier remove <uuid>\n\nCommon attributes:\n- minecraft:generic.max_health (default 20)\n- minecraft:generic.movement_speed (default 0.1)\n- minecraft:generic.attack_damage (default 1)\n- minecraft:generic.armor (default 0)\n- minecraft:generic.knockback_resistance (0-1)",
|
||||
"https://minecraft.wiki/w/Attribute", ["attribute {p} minecraft:generic.max_health base set 40"],
|
||||
"Looked up attribute syntax. Set max health to 40 (double normal)."),
|
||||
|
||||
("sudo what does the wind charge do?", "wind charge item minecraft 1.21",
|
||||
"Wind Charge: Projectile item added in 1.21\n- Thrown like a snowball\n- On impact: creates wind burst that knocks back entities and activates redstone\n- Players can use it for movement: throw at feet for a boost\n- Breeze mob shoots these naturally\n- Item: minecraft:wind_charge",
|
||||
"https://minecraft.wiki/w/Wind_Charge", ["give {p} minecraft:wind_charge 16"],
|
||||
"Looked up wind charge mechanics. Gave 16 wind charges."),
|
||||
|
||||
("sudo how does the trial spawner work?", "trial spawner mechanics 1.21",
|
||||
"Trial Spawner: Found in Trial Chambers\n- Spawns mobs based on nearby players\n- Becomes 'ominous' if player has Bad Omen\n- Cannot be obtained with Silk Touch\n- Ejects rewards when all mobs defeated\n- Cooldown of 30 minutes per player\n- Item: minecraft:trial_spawner (creative only)",
|
||||
"https://minecraft.wiki/w/Trial_Spawner", ["give {p} minecraft:trial_spawner 1"],
|
||||
"Looked up trial spawner. It's a creative-only item. Giving one."),
|
||||
|
||||
("sudo what are the vault block mechanics?", "vault block trial chambers 1.21",
|
||||
"Vault: Loot container in Trial Chambers\n- Each player can open it once with a trial key\n- Drops random loot (armor trims, enchanted books, etc.)\n- Ominous vault: requires ominous trial key, better loot\n- Items: minecraft:vault, minecraft:trial_key, minecraft:ominous_trial_key",
|
||||
"https://minecraft.wiki/w/Vault", ["give {p} minecraft:vault 1", "give {p} minecraft:trial_key 3"],
|
||||
"Looked up vault mechanics. Gave a vault and 3 trial keys."),
|
||||
|
||||
("sudo what food gives the most saturation?", "food saturation values minecraft",
|
||||
"Highest saturation foods:\n1. Golden carrot: 14.4 saturation, 6 hunger\n2. Cooked porkchop: 12.8 saturation, 8 hunger\n3. Steak (cooked beef): 12.8 saturation, 8 hunger\n4. Cooked mutton: 9.6 saturation, 6 hunger\n5. Cooked salmon: 9.6 saturation, 6 hunger\n6. Suspicious stew varies by flower\nGolden apple: 9.6 sat, enchanted golden apple: 9.6 sat",
|
||||
"https://minecraft.wiki/w/Food", ["give {p} minecraft:golden_carrot 64", "give {p} minecraft:cooked_beef 64"],
|
||||
"Looked up food saturation. Golden carrots have the best saturation. Gave those plus steak."),
|
||||
|
||||
("sudo what's the difference between smite and sharpness?", "smite vs sharpness enchantment damage",
|
||||
"Sharpness: +0.5 * level + 0.5 damage to all mobs (max V = 3 extra)\nSmite: +2.5 * level damage to undead only (max V = 12.5 extra)\nBane of Arthropods: +2.5 * level to arthropods only\n\nThese three are mutually exclusive.\nSmite is better vs undead (zombies, skeletons, wither, phantoms).\nSharpness is better for general use.",
|
||||
"https://minecraft.wiki/w/Sharpness", ["give {p} minecraft:diamond_sword[enchantments={{sharpness:5,unbreaking:3,mending:1,looting:3,sweeping_edge:3}}] 1"],
|
||||
"Looked up sharpness vs smite. Sharpness is better for general use. Gave max enchanted sword."),
|
||||
|
||||
("sudo what's the recipe for a lodestone?", "lodestone recipe crafting minecraft",
|
||||
"Lodestone recipe:\n- 8 chiseled stone bricks (surrounding)\n- 1 netherite ingot (center)\nCrafting: 3x3 grid with chiseled stone bricks around netherite ingot\nUsage: Right-click with compass to bind it. Works across dimensions.",
|
||||
"https://minecraft.wiki/w/Lodestone", ["give {p} minecraft:lodestone 1"],
|
||||
"Looked up lodestone recipe. It requires a netherite ingot. Giving one directly."),
|
||||
|
||||
("sudo what paintings are available in 1.21?", "paintings list new 1.21",
|
||||
"1.21 added 20 new paintings by artist Sarah Boeving:\n- backyard, bouquet, cavebird, changing, cotan, endboss, fern, finding, lowmist, orb, owlemons, passage, pond, sunflowers, tides, unpacked\nPaintings are placed with: give <player> minecraft:painting 1\nThe painting chosen depends on wall size.",
|
||||
"https://minecraft.wiki/w/Painting", ["give {p} minecraft:painting 5"],
|
||||
"Looked up 1.21 paintings. 20 new ones added. Gave 5 paintings to place."),
|
||||
|
||||
("sudo how do I use the /damage command?", "damage command syntax 1.21",
|
||||
"damage <target> <amount> [<damageType>] [at <location>] [by <entity>] [from <cause>]\n\nExamples:\ndamage @p 5 minecraft:fall\ndamage @e[type=zombie,limit=1] 10 minecraft:player_attack by @p\n\nDamage types: fall, fire, drown, starve, freeze, player_attack, mob_attack, explosion, etc.",
|
||||
"https://minecraft.wiki/w/Commands/damage", ["damage @e[type=zombie,distance=..10] 20 minecraft:player_attack"],
|
||||
"Looked up /damage syntax. Dealt 20 damage to nearby zombies."),
|
||||
|
||||
("sudo what are all the armor trim patterns?", "armor trim patterns smithing template 1.21",
|
||||
"Armor trim patterns (smithing templates):\nCoast, Dune, Eye, Host, Raiser, Rib, Sentry, Shaper, Silence, Snout, Spire, Tide, Vex, Ward, Wayfinder, Wild, Bolt, Flow\n\nMaterials for color: iron, copper, gold, lapis, emerald, diamond, netherite, redstone, amethyst, quartz\n\nApply: Smithing table + template + armor piece + material",
|
||||
"https://minecraft.wiki/w/Armor_Trim", ["give {p} minecraft:bolt_armor_trim_smithing_template 1", "give {p} minecraft:flow_armor_trim_smithing_template 1"],
|
||||
"Looked up armor trims. Bolt and Flow are the new 1.21 patterns. Gave both templates."),
|
||||
|
||||
("sudo what biomes have cherry trees?", "cherry grove biome minecraft",
|
||||
"Cherry Grove biome:\n- Pink cherry blossom trees\n- Found at Y 100-256 in mountainous areas\n- Pigs, sheep, bees spawn naturally\n- Blocks: cherry_log, cherry_leaves, cherry_planks, cherry_sapling, pink_petals\n- Cherry wood set includes all standard wood items\nLocate: /locate biome minecraft:cherry_grove",
|
||||
"https://minecraft.wiki/w/Cherry_Grove", ["locate biome minecraft:cherry_grove"],
|
||||
"Looked up cherry grove. Using locate to find the nearest one."),
|
||||
|
||||
("sudo how does fortune work on different ores?", "fortune enchantment ore drops mechanics",
|
||||
"Fortune on ores:\n- Coal, diamond, emerald, lapis, nether quartz, nether gold, copper, amethyst: increases drops\n- Iron, gold ore: Fortune does NOT work (must smelt raw ore)\n- Formula: Each level gives a chance for 1 extra drop\n - Fortune I: avg 1.33x, Fortune II: avg 1.75x, Fortune III: avg 2.2x\n- Lapis and copper have unique formulas (higher multipliers)\n- Does NOT affect XP drops",
|
||||
"https://minecraft.wiki/w/Fortune", ["give {p} minecraft:diamond_pickaxe[enchantments={{fortune:3,efficiency:5,unbreaking:3,mending:1}}] 1"],
|
||||
"Looked up fortune mechanics. Works on diamond/emerald/lapis but not iron/gold ore. Gave fortune 3 pickaxe."),
|
||||
]
|
||||
|
||||
# ── Player Info Examples ──────────────────────────────────────────────────
|
||||
|
||||
PLAYER_INFO_SCENARIOS = [
|
||||
("sudo build a wall around me", ["fill {x_m10} {y} {z_m10} {x_p10} {y_p4} {z_m10} minecraft:stone", "fill {x_m10} {y} {z_p10} {x_p10} {y_p4} {z_p10} minecraft:stone", "fill {x_m10} {y} {z_m10} {x_m10} {y_p4} {z_p10} minecraft:stone", "fill {x_p10} {y} {z_m10} {x_p10} {y_p4} {z_p10} minecraft:stone"], "Got player position. Built 4 stone walls in a 20x20 square around them."),
|
||||
("sudo teleport me 50 blocks up", ["tp {p} {x} {y_p50} {z}"], "Got player position, teleported 50 blocks up."),
|
||||
("sudo put lava under my feet", ["setblock {x} {y_m1} {z} minecraft:lava"], "Got player position. Placed lava one block below."),
|
||||
("sudo create a beacon at my location", ["setblock {x} {y_m1} {z} minecraft:iron_block", "fill {x_m1} {y_m1} {z_m1} {x_p1} {y_m1} {z_p1} minecraft:iron_block", "setblock {x} {y} {z} minecraft:beacon"], "Got position. Built iron base and placed beacon."),
|
||||
("sudo replace the ground around me with grass", ["fill {x_m5} {y_m1} {z_m5} {x_p5} {y_m1} {z_p5} minecraft:grass_block"], "Got position. Filled a 10x10 area below feet with grass."),
|
||||
("sudo place torches around me in a circle", ["setblock {x_p4} {y} {z} minecraft:torch", "setblock {x_m4} {y} {z} minecraft:torch", "setblock {x} {y} {z_p4} minecraft:torch", "setblock {x} {y} {z_m4} minecraft:torch"], "Got position. Placed 4 torches at cardinal directions."),
|
||||
("sudo tp me to the nearest village center", ["locate structure minecraft:village_plains"], "Got position for reference. Used locate to find nearest village."),
|
||||
("sudo fill the area below me with water", ["fill {x_m3} {y_m5} {z_m3} {x_p3} {y_m1} {z_p3} minecraft:water"], "Got position. Filled 6x5x6 pool below player."),
|
||||
("sudo make a platform of glass under me", ["fill {x_m5} {y_m1} {z_m5} {x_p5} {y_m1} {z_p5} minecraft:glass"], "Got position. Created 10x10 glass platform below feet."),
|
||||
("sudo build an obsidian box around me", ["fill {x_m2} {y} {z_m2} {x_p2} {y_p3} {z_p2} minecraft:obsidian hollow"], "Got position. Built obsidian box around player."),
|
||||
("sudo teleport me to the surface", ["tp {p} {x} 320 {z}"], "Got position. Teleported to build limit so player falls to surface with slow_falling."),
|
||||
("sudo place a campfire at my feet", ["setblock {x} {y} {z} minecraft:campfire"], "Got position. Placed campfire at player location."),
|
||||
("sudo light up this cave", ["setblock {x_p3} {y_p2} {z} minecraft:lantern", "setblock {x_m3} {y_p2} {z} minecraft:lantern", "setblock {x} {y_p2} {z_p3} minecraft:lantern", "setblock {x} {y_p2} {z_m3} minecraft:lantern", "setblock {x} {y_p2} {z} minecraft:lantern"], "Got position. Placed lanterns around the player to illuminate the area."),
|
||||
("sudo surround me with fences", ["fill {x_m3} {y} {z_m3} {x_p3} {y_p1} {z_m3} minecraft:oak_fence replace minecraft:air", "fill {x_m3} {y} {z_p3} {x_p3} {y_p1} {z_p3} minecraft:oak_fence replace minecraft:air"], "Got position. Placed fence perimeter around player."),
|
||||
("sudo clear all blocks 10 blocks above me", ["fill {x_m5} {y_p2} {z_m5} {x_p5} {y_p12} {z_p5} minecraft:air"], "Got position. Cleared 10-block column above player."),
|
||||
("sudo spawn a zombie behind me", ["execute at {p} run summon minecraft:zombie ~ ~ ~-3"], "Got player position. Summoned zombie 3 blocks behind using execute at."),
|
||||
("sudo put a chest with supplies at my location", ["setblock {x} {y} {z} minecraft:chest"], "Got position. Placed chest at player location."),
|
||||
("sudo build stairs going up from where I am", ["setblock {x} {y} {z_p1} minecraft:oak_stairs[facing=south]", "setblock {x} {y_p1} {z_p2} minecraft:oak_stairs[facing=south]", "setblock {x} {y_p2} {z_p3} minecraft:oak_stairs[facing=south]"], "Got position. Built ascending stairs going south."),
|
||||
("sudo make me a fishing spot", ["fill {x_m2} {y_m2} {z_p3} {x_p2} {y_m1} {z_p7} minecraft:water", "give {p} minecraft:fishing_rod 1"], "Got position. Dug pool nearby and gave fishing rod."),
|
||||
("sudo set my spawn point here", ["spawnpoint {p} {x} {y} {z}"], "Got position. Set spawn point at current location."),
|
||||
]
|
||||
|
||||
# ── Server State Examples ─────────────────────────────────────────────────
|
||||
|
||||
SERVER_STATE_SCENARIOS = [
|
||||
("sudo give everyone online netherite armor", "Checked online players, giving each full netherite armor."),
|
||||
("sudo announce it's getting dark soon", "Checked time — it's evening. Warning players about night."),
|
||||
("sudo if it's thundering, summon lightning on everyone", "Checked weather. If thundering, striking lightning on all players."),
|
||||
("sudo how many people are online?", "Checked server state. Reporting player count."),
|
||||
("sudo make it night if it's currently day", "Checked time — it was daytime, switching to night."),
|
||||
("sudo give bonus XP to everyone if it's raining", "Checked weather — raining, giving XP bonus."),
|
||||
("sudo tp all players to spawn if it's nighttime", "Checked time — night, teleporting everyone to spawn."),
|
||||
("sudo set weather opposite of current", "Checked weather state and set opposite."),
|
||||
("sudo kill all hostile mobs if there are 3+ players online", "Checked online count. 3+ players → killing hostile mobs."),
|
||||
("sudo announce the time and weather to everyone", "Checked server state. Broadcasting time and weather."),
|
||||
]
|
||||
|
||||
# ── Nearby Entities Examples ──────────────────────────────────────────────
|
||||
|
||||
def sim_nearby_entities(types=None):
|
||||
all_types = [
|
||||
("zombie", random.randint(1, 5), round(random.uniform(3, 25), 1)),
|
||||
("skeleton", random.randint(1, 3), round(random.uniform(5, 30), 1)),
|
||||
("creeper", random.randint(1, 2), round(random.uniform(4, 20), 1)),
|
||||
("cow", random.randint(2, 8), round(random.uniform(2, 15), 1)),
|
||||
("sheep", random.randint(1, 6), round(random.uniform(3, 20), 1)),
|
||||
("pig", random.randint(1, 4), round(random.uniform(5, 18), 1)),
|
||||
("chicken", random.randint(2, 10), round(random.uniform(1, 12), 1)),
|
||||
("spider", random.randint(1, 3), round(random.uniform(6, 25), 1)),
|
||||
("enderman", 1, round(random.uniform(10, 40), 1)),
|
||||
("villager", random.randint(1, 5), round(random.uniform(3, 20), 1)),
|
||||
("iron_golem", 1, round(random.uniform(5, 15), 1)),
|
||||
("wolf", random.randint(1, 3), round(random.uniform(4, 25), 1)),
|
||||
]
|
||||
if types:
|
||||
selected = [e for e in all_types if e[0] in types]
|
||||
else:
|
||||
selected = random.sample(all_types, k=random.randint(2, 5))
|
||||
entities = [{"type": f"minecraft:{t}", "count": c, "nearest_distance": d} for t, c, d in selected]
|
||||
return {"entities": entities, "total": sum(e["count"] for e in entities)}
|
||||
|
||||
NEARBY_SCENARIOS = [
|
||||
("sudo kill all the zombies near me", ["zombie"], ["kill @e[type=minecraft:zombie,distance=..32]"], "Scanned for entities. Found {n} zombies nearby. Killed them all."),
|
||||
("sudo how many mobs are around me?", None, [], "Scanned entities within 32 blocks. Reporting counts."),
|
||||
("sudo clear out the hostile mobs nearby", ["zombie", "skeleton", "creeper", "spider"], ["kill @e[type=minecraft:zombie,distance=..32]", "kill @e[type=minecraft:skeleton,distance=..32]", "kill @e[type=minecraft:creeper,distance=..32]", "kill @e[type=minecraft:spider,distance=..32]"], "Scanned for hostiles. Found and killed all nearby hostile mobs."),
|
||||
("sudo are there any creepers near me?", ["creeper"], [], "Scanned for creepers. Reporting what's nearby."),
|
||||
("sudo kill the closest zombie", ["zombie"], ["kill @e[type=minecraft:zombie,distance=..10,limit=1,sort=nearest]"], "Scanned to confirm zombie presence. Killed the nearest one."),
|
||||
("sudo count the animals around me", ["cow", "sheep", "pig", "chicken"], [], "Scanned for animals. Reporting passive mob counts."),
|
||||
("sudo kill all mobs except villagers in a 50 block radius", None, ["kill @e[type=!minecraft:villager,type=!minecraft:player,distance=..50]"], "Scanned area. Killing everything except villagers and players."),
|
||||
("sudo are there any endermen nearby?", ["enderman"], [], "Scanned for endermen nearby."),
|
||||
("sudo tame any wolves near me", ["wolf"], ["execute as @e[type=minecraft:wolf,distance=..20] run data merge entity @s {Owner:\"{p}\"}"], "Found wolves nearby. Taming them."),
|
||||
("sudo protect me from nearby hostiles", ["zombie", "skeleton", "creeper"], ["kill @e[type=minecraft:zombie,distance=..20]", "kill @e[type=minecraft:skeleton,distance=..20]", "kill @e[type=minecraft:creeper,distance=..20]", "effect give {p} minecraft:resistance 60 2"], "Scanned for hostiles. Killed nearby ones and gave resistance."),
|
||||
("sudo lead me to the nearest villager", ["villager"], [], "Scanned for villagers. Nearest one found — reporting location."),
|
||||
("sudo spawn more of whatever animal is closest", ["cow", "sheep"], ["summon minecraft:cow ~ ~ ~"], "Scanned nearby. Cows closest. Summoned more."),
|
||||
]
|
||||
|
||||
# ── Memory Examples ───────────────────────────────────────────────────────
|
||||
|
||||
MEMORY_WRITE_SCENARIOS = [
|
||||
("sudo remember this location as home", "home", "location", {"x": 100, "y": 64, "z": -200}, "Saved current position as 'home'."),
|
||||
("sudo remember my base is here", "base", "location", {"x": -350, "y": 72, "z": 180}, "Saved current position as 'base'."),
|
||||
("sudo remember that I like diamonds", "favorite_item", "preference", "diamonds", "Noted preference for diamonds."),
|
||||
("sudo save this spot as my nether portal", "nether_portal", "location", {"x": 50, "y": 68, "z": 90}, "Saved nether portal location."),
|
||||
("sudo remember I'm building a castle here", "castle", "location", {"x": 200, "y": 80, "z": -100}, "Saved castle build location."),
|
||||
("sudo my favorite color is red", "favorite_color", "preference", "red", "Remembered color preference."),
|
||||
("sudo remember my farm is at 500 70 -300", "farm", "location", {"x": 500, "y": 70, "z": -300}, "Saved farm location from coordinates."),
|
||||
("sudo remember I don't want to be teleported randomly", "no_random_tp", "preference", "no random teleports", "Noted: player prefers no random teleports."),
|
||||
("sudo save this as my mining spot", "mining_spot", "location", {"x": -100, "y": 12, "z": 400}, "Saved mining location."),
|
||||
("sudo remember that Ace13245 is my friend", "friend_ace", "fact", "Ace13245 is a friend", "Saved social fact."),
|
||||
]
|
||||
|
||||
MEMORY_READ_SCENARIOS = [
|
||||
("sudo tp me home", "home", True, "tp {p} {mx} {my} {mz}", "Read memory for 'home'. Teleporting to saved location."),
|
||||
("sudo take me to my base", "base", True, "tp {p} {mx} {my} {mz}", "Read memory for 'base'. Teleporting."),
|
||||
("sudo what do you know about me?", None, True, None, "Read all memories for this player. Listing what I know."),
|
||||
("sudo where's my nether portal?", "nether_portal", True, None, "Read memory for 'nether portal'. Reporting coordinates."),
|
||||
("sudo tp me to my farm", "farm", True, "tp {p} {mx} {my} {mz}", "Read memory for 'farm'. Teleporting."),
|
||||
("sudo do I have a saved home?", "home", False, None, "Checked memories. No 'home' location saved for this player."),
|
||||
("sudo forget my base location", "base", True, None, "Found 'base' memory. Removing it."),
|
||||
("sudo tp me to my mining spot", "mining_spot", True, "tp {p} {mx} {my} {mz}", "Read memory for 'mining_spot'. Teleporting."),
|
||||
("sudo where did I say my castle was?", "castle", True, None, "Read memory for 'castle'. Reporting saved location."),
|
||||
("sudo take me back to where I was building", "castle", True, "tp {p} {mx} {my} {mz}", "Read 'castle' memory. Teleporting to build site."),
|
||||
]
|
||||
|
||||
# ── Chained Tool Call Examples ────────────────────────────────────────────
|
||||
# These combine multiple tools in one conversation
|
||||
|
||||
CHAINED_SCENARIOS = [
|
||||
# player_info + nearby_entities + rcon
|
||||
("sudo protect me from everything nearby",
|
||||
["player_info", "nearby_entities", "rcon"],
|
||||
"Got position and scanned for hostiles. Killed threats and applied protection."),
|
||||
# memory + player_info + rcon
|
||||
("sudo save this spot and build a marker",
|
||||
["player_info", "memory_write", "rcon"],
|
||||
"Got position, saved to memory, and built a visible marker."),
|
||||
# server_state + rcon (conditional)
|
||||
("sudo if anyone is online, give them all food",
|
||||
["server_state", "rcon"],
|
||||
"Checked who's online. Gave food to all players."),
|
||||
# memory + rcon (tp to saved location)
|
||||
("sudo tp me home and heal me",
|
||||
["memory_read", "rcon", "rcon"],
|
||||
"Read home location from memory. Teleported and healed."),
|
||||
# wiki + rcon (look up then execute)
|
||||
("sudo give me whatever the strongest bow setup is",
|
||||
["wiki", "rcon"],
|
||||
"Looked up bow enchantments. Gave max enchanted bow."),
|
||||
# player_info + server_state + rcon
|
||||
("sudo set up a safe zone around me for the night",
|
||||
["player_info", "server_state", "rcon"],
|
||||
"Checked position and time. Built lit shelter for night."),
|
||||
]
|
||||
|
||||
|
||||
def generate_all():
|
||||
examples = []
|
||||
idx = 0
|
||||
|
||||
# ── Wiki lookups ──
|
||||
for req, query, content, url, cmds, reasoning in WIKI_EXAMPLES:
|
||||
player = random.choice(PLAYERS)
|
||||
mode = "god" if req.startswith("pray ") else "sudo"
|
||||
msgs = [sys_msg(mode), user_msg(f"Player {player}: {req}")]
|
||||
msgs.append(tool_call("minecraft.wiki_lookup", {"query": query}))
|
||||
msgs.append(tool_result({"content": content, "url": url}))
|
||||
for cmd in cmds:
|
||||
resolved = cmd.replace("{p}", player)
|
||||
msgs.append(tool_call("rcon.execute", {"command": resolved}))
|
||||
msgs.append(tool_result({"success": True, "result": rcon_ok(resolved, player)}))
|
||||
resp = {"risk_level": 3, "commands": [c.replace("{p}", player) for c in cmds], "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-wiki-{idx:03d}", "wiki_lookup", msgs))
|
||||
idx += 1
|
||||
|
||||
# ── Player info ──
|
||||
for req, cmds_tmpl, reasoning in PLAYER_INFO_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
pos = rpos()
|
||||
mode = "god" if req.startswith("pray ") else "sudo"
|
||||
msgs = [sys_msg(mode), user_msg(f"Player {player}: {req}")]
|
||||
msgs.append(tool_call("world.player_info", {"player": player}))
|
||||
pinfo = {"health": round(random.uniform(10, 20), 1), "position": pos,
|
||||
"inventory_summary": "Diamond sword, iron armor, 32 steak"}
|
||||
msgs.append(tool_result(pinfo))
|
||||
|
||||
resolved_cmds = []
|
||||
for ct in cmds_tmpl:
|
||||
c = ct.replace("{p}", player)
|
||||
c = c.replace("{x}", str(pos["x"])).replace("{y}", str(pos["y"])).replace("{z}", str(pos["z"]))
|
||||
for delta, tag in [(1, "_p1"), (2, "_p2"), (3, "_p3"), (4, "_p4"), (5, "_p5"), (10, "_p10"), (50, "_p50"),
|
||||
(-1, "_m1"), (-2, "_m2"), (-3, "_m3"), (-5, "_m5"), (-10, "_m10"), (-100, "_minus_100")]:
|
||||
c = c.replace(f"{{x{tag}}}", str(pos["x"] + delta))
|
||||
c = c.replace(f"{{y{tag}}}", str(pos["y"] + delta))
|
||||
c = c.replace(f"{{z{tag}}}", str(pos["z"] + delta))
|
||||
resolved_cmds.append(c)
|
||||
|
||||
for cmd in resolved_cmds:
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": True, "result": rcon_ok(cmd, player)}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": resolved_cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-pinfo-{idx:03d}", "player_info_lookup", msgs))
|
||||
idx += 1
|
||||
|
||||
# ── Server state ──
|
||||
for req, reasoning in SERVER_STATE_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
mode = "god" if req.startswith("pray ") else "sudo"
|
||||
msgs = [sys_msg(mode), user_msg(f"Player {player}: {req}")]
|
||||
msgs.append(tool_call("world.server_state", {}))
|
||||
state = {
|
||||
"time_of_day": random.choice(["morning", "noon", "evening", "night"]),
|
||||
"weather": random.choice(["clear", "rain", "thunder"]),
|
||||
"online_players": random.sample(PLAYERS, k=random.randint(1, 4)),
|
||||
"world_border": 60000000.0,
|
||||
}
|
||||
msgs.append(tool_result(state))
|
||||
|
||||
# Generate contextual commands based on state
|
||||
cmds = []
|
||||
if "everyone" in req.lower() or "all" in req.lower():
|
||||
for p in state["online_players"]:
|
||||
if "netherite" in req: cmds.extend([f"give {p} minecraft:netherite_helmet 1", f"give {p} minecraft:netherite_chestplate 1"])
|
||||
elif "food" in req: cmds.append(f"give {p} minecraft:golden_carrot 32")
|
||||
elif "XP" in req or "xp" in req: cmds.append(f"xp add {p} 500")
|
||||
elif "heal" in req: cmds.append(f"effect give {p} minecraft:instant_health 1 5")
|
||||
elif "tp" in req or "spawn" in req: cmds.append(f"tp {p} 0 64 0")
|
||||
elif "diamond" in req: cmds.append(f"give {p} minecraft:diamond 1")
|
||||
elif "weather" in req.lower():
|
||||
opposite = "clear" if state["weather"] in ("rain", "thunder") else "rain"
|
||||
cmds.append(f"weather {opposite}")
|
||||
elif "night" in req.lower() or "dark" in req.lower():
|
||||
cmds.append("time set night" if state["time_of_day"] in ("morning", "noon") else "time set day")
|
||||
elif "day" in req.lower():
|
||||
cmds.append("time set day" if state["time_of_day"] in ("evening", "night") else "time set night")
|
||||
elif "announce" in req.lower() or "how many" in req.lower():
|
||||
cmds.append(f"say Server: {len(state['online_players'])} players online, time is {state['time_of_day']}, weather is {state['weather']}")
|
||||
elif "hostile" in req.lower() or "kill" in req.lower():
|
||||
cmds.append("kill @e[type=!minecraft:player,type=!minecraft:villager,type=!minecraft:iron_golem]")
|
||||
elif "lightning" in req.lower():
|
||||
for p in state["online_players"]:
|
||||
cmds.append(f"execute at {p} run summon minecraft:lightning_bolt")
|
||||
|
||||
if not cmds:
|
||||
cmds = ["say Check complete"]
|
||||
|
||||
for cmd in cmds:
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": True, "result": rcon_ok(cmd, player)}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-sstate-{idx:03d}", "server_state_check", msgs))
|
||||
idx += 1
|
||||
|
||||
# ── Nearby entities ──
|
||||
for req, entity_filter, cmds_tmpl, reasoning in NEARBY_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {req}")]
|
||||
msgs.append(tool_call("world.nearby_entities", {"player": player, "radius": 32}))
|
||||
ent_data = sim_nearby_entities(entity_filter)
|
||||
msgs.append(tool_result(ent_data))
|
||||
|
||||
cmds = [c.replace("{p}", player) for c in cmds_tmpl]
|
||||
n_found = ent_data["total"]
|
||||
real_reasoning = reasoning.replace("{n}", str(n_found))
|
||||
|
||||
if cmds:
|
||||
for cmd in cmds:
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": True, "result": rcon_ok(cmd, player)}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": cmds, "reasoning": real_reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-nearby-{idx:03d}", "nearby_entities", msgs))
|
||||
idx += 1
|
||||
|
||||
# ── Memory write ──
|
||||
for req, key, mtype, value, reasoning in MEMORY_WRITE_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
if mtype == "location" and isinstance(value, dict):
|
||||
pos = rpos()
|
||||
value = pos
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {req}")]
|
||||
msgs.append(tool_call("memory.write", {"player": player, "type": mtype, "key": key, "value": value}))
|
||||
msgs.append(tool_result({"ok": True, "key": key}))
|
||||
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-memw-{idx:03d}", "memory_write", msgs))
|
||||
idx += 1
|
||||
|
||||
# ── Memory read ──
|
||||
for req, key, found, cmd_tmpl, reasoning in MEMORY_READ_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
if key:
|
||||
msgs.append(tool_call("memory.read", {"player": player, "key": key}))
|
||||
else:
|
||||
msgs.append(tool_call("memory.read", {"player": player}))
|
||||
|
||||
if found:
|
||||
pos = rpos()
|
||||
if key:
|
||||
mem = [{"key": key, "type": "location", "value": {"x": pos["x"], "y": pos["y"], "z": pos["z"]}}]
|
||||
else:
|
||||
mem = [
|
||||
{"key": "home", "type": "location", "value": rpos()},
|
||||
{"key": "favorite_item", "type": "preference", "value": "diamonds"},
|
||||
]
|
||||
msgs.append(tool_result({"memories": mem}))
|
||||
|
||||
if cmd_tmpl:
|
||||
cmd = cmd_tmpl.replace("{p}", player).replace("{mx}", str(pos["x"])).replace("{my}", str(pos["y"])).replace("{mz}", str(pos["z"]))
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": True, "result": rcon_ok(cmd, player)}))
|
||||
resp = {"risk_level": 3, "commands": [cmd], "reasoning": reasoning}
|
||||
else:
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": reasoning}
|
||||
else:
|
||||
msgs.append(tool_result({"memories": []}))
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": reasoning}
|
||||
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-memr-{idx:03d}", "memory_read", msgs))
|
||||
idx += 1
|
||||
|
||||
# ── Chained tool calls ──
|
||||
for req, tools, reasoning in CHAINED_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
pos = rpos()
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
for t in tools:
|
||||
if t == "player_info":
|
||||
msgs.append(tool_call("world.player_info", {"player": player}))
|
||||
msgs.append(tool_result({"health": 18.5, "position": pos, "inventory_summary": "Diamond gear"}))
|
||||
elif t == "nearby_entities":
|
||||
msgs.append(tool_call("world.nearby_entities", {"player": player, "radius": 32}))
|
||||
msgs.append(tool_result(sim_nearby_entities(["zombie", "skeleton"])))
|
||||
elif t == "server_state":
|
||||
msgs.append(tool_call("world.server_state", {}))
|
||||
msgs.append(tool_result({"time_of_day": "night", "weather": "clear", "online_players": [player, "Ace13245"], "world_border": 60000000.0}))
|
||||
elif t == "memory_write":
|
||||
msgs.append(tool_call("memory.write", {"player": player, "type": "location", "key": "marker", "value": pos}))
|
||||
msgs.append(tool_result({"ok": True, "key": "marker"}))
|
||||
elif t == "memory_read":
|
||||
msgs.append(tool_call("memory.read", {"player": player, "key": "home"}))
|
||||
home = rpos()
|
||||
msgs.append(tool_result({"memories": [{"key": "home", "type": "location", "value": home}]}))
|
||||
pos = home # use home coords for subsequent commands
|
||||
elif t == "wiki":
|
||||
msgs.append(tool_call("minecraft.wiki_lookup", {"query": "best bow enchantments 1.21"}))
|
||||
msgs.append(tool_result({"content": "Bow: Power V, Infinity or Mending, Unbreaking III, Flame I, Punch II. Infinity and Mending are mutually exclusive.", "url": "https://minecraft.wiki/w/Bow"}))
|
||||
elif t == "rcon":
|
||||
cmd = f"give {player} minecraft:diamond 1"
|
||||
if "heal" in req: cmd = f"effect give {player} minecraft:instant_health 1 5"
|
||||
elif "protect" in req: cmd = f"kill @e[type=minecraft:zombie,distance=..32]"
|
||||
elif "marker" in req or "build" in req: cmd = f"setblock {pos['x']} {pos['y']+1} {pos['z']} minecraft:glowstone"
|
||||
elif "food" in req:
|
||||
pass # handled per player below
|
||||
elif "bow" in req: cmd = f"give {player} minecraft:bow[enchantments={{power:5,infinity:1,unbreaking:3,flame:1,punch:2}}] 1"
|
||||
elif "home" in req or "tp" in req: cmd = f"tp {player} {pos['x']} {pos['y']} {pos['z']}"
|
||||
elif "safe" in req or "shelter" in req: cmd = f"fill {pos['x']-3} {pos['y']} {pos['z']-3} {pos['x']+3} {pos['y']+4} {pos['z']+3} minecraft:oak_planks hollow"
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": True, "result": rcon_ok(cmd, player)}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": [], "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append(make_example(f"exp-chain-{idx:03d}", "chained", msgs))
|
||||
idx += 1
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def main():
|
||||
print("Generating expanded tool training data...")
|
||||
examples = generate_all()
|
||||
|
||||
# Count by type
|
||||
counts = {}
|
||||
for ex in examples:
|
||||
t = ex["type"]
|
||||
counts[t] = counts.get(t, 0) + 1
|
||||
|
||||
print(f"\nGenerated {len(examples)} examples:")
|
||||
for t, c in sorted(counts.items()):
|
||||
print(f" {t}: {c}")
|
||||
|
||||
# Write
|
||||
OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(OUTPUT_PATH, "w") as f:
|
||||
for ex in examples:
|
||||
f.write(json.dumps(ex, ensure_ascii=False) + "\n")
|
||||
|
||||
print(f"\nWritten to {OUTPUT_PATH}")
|
||||
print(f"Next: merge into tool_training.jsonl or add to training pipeline")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,663 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate RCON-validated training data for server plugins.
|
||||
|
||||
Plugins: WorldGuard, CoreProtect, EssentialsX, Vault, LuckPerms, FAWE
|
||||
Each command is executed against the live server to capture real responses.
|
||||
|
||||
Target: 120+ high-quality examples.
|
||||
"""
|
||||
|
||||
import json
|
||||
import random
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from agent.tools.persistent_rcon import get_rcon
|
||||
from agent.tools.tool_schemas import qwen3_tools_block
|
||||
from agent.prompts.system_prompts import SYNTAX_RULES, RISK_GRADIENT
|
||||
|
||||
OUTPUT_PATH = PROJECT_ROOT / "data" / "raw" / "plugin_training.jsonl"
|
||||
|
||||
TOOLS_BLOCK = qwen3_tools_block()
|
||||
SYSTEM = (
|
||||
"You are a Minecraft 1.21 command translator for a Paper server with plugins: "
|
||||
"FastAsyncWorldEdit, WorldGuard, CoreProtect, EssentialsX, Vault, LuckPerms.\n\n"
|
||||
"You know plugin command syntax. Use the correct plugin prefix when needed.\n"
|
||||
"PERMISSION LEVEL: 4 (generous).\n\n"
|
||||
"Return JSON: {\"risk_level\": <0-5>, \"commands\": [...], \"reasoning\": \"...\"}\n\n"
|
||||
+ SYNTAX_RULES + RISK_GRADIENT + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
PLAYERS = ["slingshooter08", "Ace13245", "TheBigBoss", "xXDragonSlayerXx"]
|
||||
|
||||
def sys_msg():
|
||||
return {"role": "system", "content": SYSTEM}
|
||||
|
||||
def user_msg(text):
|
||||
return {"role": "user", "content": text}
|
||||
|
||||
def tool_call(name, args):
|
||||
return {"role": "assistant", "content": f"<tool_call>\n{json.dumps({'name': name, 'arguments': args})}\n</tool_call>"}
|
||||
|
||||
def tool_result(data):
|
||||
return {"role": "tool", "content": json.dumps(data)}
|
||||
|
||||
def final_response(resp):
|
||||
return {"role": "assistant", "content": json.dumps(resp)}
|
||||
|
||||
def is_error(result):
|
||||
return any(e in result for e in ("<--[HERE]", "Unknown command", "Incorrect argument", "An internal error"))
|
||||
|
||||
|
||||
def run_cmd(rcon, cmd):
|
||||
"""Execute and return (result_str, is_ok)."""
|
||||
try:
|
||||
result = rcon.command(cmd)
|
||||
clean = re.sub(r'§.', '', result)
|
||||
ok = not is_error(result)
|
||||
return clean[:400], ok
|
||||
except Exception as e:
|
||||
return str(e)[:200], False
|
||||
|
||||
|
||||
def make_example(eid, etype, msgs):
|
||||
return {"id": eid, "source": "plugin_training", "type": etype, "messages": msgs}
|
||||
|
||||
|
||||
def build_rcon_example(rcon, eid, etype, prompt, commands, reasoning, player=None, mode="sudo"):
|
||||
"""Build a full multi-turn tool-calling example with real RCON responses."""
|
||||
player = player or random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
resolved_cmds = []
|
||||
all_ok = True
|
||||
for cmd in commands:
|
||||
cmd = cmd.replace("{p}", player)
|
||||
result, ok = run_cmd(rcon, cmd)
|
||||
if not ok:
|
||||
all_ok = False
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": ok, "result": result}))
|
||||
resolved_cmds.append(cmd)
|
||||
time.sleep(0.05)
|
||||
|
||||
resp = {"risk_level": 3, "commands": resolved_cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
return {
|
||||
"id": eid, "source": "plugin_training", "type": etype,
|
||||
"messages": msgs, "all_success": all_ok,
|
||||
}
|
||||
|
||||
|
||||
def gen_worldguard(rcon):
|
||||
"""WorldGuard region management examples."""
|
||||
print(" WorldGuard...")
|
||||
examples = []
|
||||
|
||||
WG = [
|
||||
# Region creation and management
|
||||
("sudo protect this area as my-base", [
|
||||
"//pos1 0,64,0",
|
||||
"//pos2 50,128,50",
|
||||
"rg define my-base {p}",
|
||||
], "Selected area and created 'my-base' region owned by the player."),
|
||||
("sudo protect a 20 block radius around spawn", [
|
||||
"rg define spawn-protection -w world",
|
||||
"rg flag spawn-protection pvp deny",
|
||||
"rg flag spawn-protection mob-spawning deny",
|
||||
], "Created spawn protection region with PvP and mob spawning denied."),
|
||||
("sudo make my region pvp-free", [
|
||||
"rg flag my-base pvp deny",
|
||||
], "Disabled PvP in the player's region."),
|
||||
("sudo allow TNT in the arena", [
|
||||
"rg flag arena tnt allow",
|
||||
], "Enabled TNT in the arena region."),
|
||||
("sudo prevent mobs from spawning in town", [
|
||||
"rg flag town mob-spawning deny",
|
||||
], "Disabled mob spawning in the town region."),
|
||||
("sudo add Ace13245 as a member of my base", [
|
||||
"rg addmember my-base Ace13245",
|
||||
], "Added Ace13245 as a member of my-base region."),
|
||||
("sudo remove TheBigBoss from my region", [
|
||||
"rg removemember my-base TheBigBoss",
|
||||
], "Removed TheBigBoss from my-base region."),
|
||||
("sudo show info about the spawn region", [
|
||||
"rg info spawn-protection",
|
||||
], "Displayed info about the spawn-protection region."),
|
||||
("sudo list all regions", [
|
||||
"rg list",
|
||||
], "Listed all defined regions."),
|
||||
("sudo prevent building in spawn", [
|
||||
"rg flag spawn-protection build deny",
|
||||
], "Denied building in spawn protection zone."),
|
||||
("sudo make the arena a free-for-all", [
|
||||
"rg flag arena pvp allow",
|
||||
"rg flag arena invincibility deny",
|
||||
"rg flag arena blocked-cmds /home,/spawn,/tpa",
|
||||
], "Made arena PvP-enabled, disabled invincibility, blocked escape commands."),
|
||||
("sudo set entry message for my base", [
|
||||
"rg flag my-base greeting Welcome to my base!",
|
||||
], "Set greeting message when entering the region."),
|
||||
("sudo deny entry to non-members in my vault", [
|
||||
"rg flag vault entry -g nonmembers deny",
|
||||
], "Denied entry for non-members to the vault region."),
|
||||
("sudo prevent creeper explosions everywhere", [
|
||||
"rg flag __global__ creeper-explosion deny",
|
||||
], "Disabled creeper explosions globally."),
|
||||
("sudo make a healing zone at spawn", [
|
||||
"rg flag spawn-protection heal-amount 2",
|
||||
"rg flag spawn-protection heal-delay 3",
|
||||
], "Players in spawn zone heal 1 heart every 3 seconds."),
|
||||
("sudo delete the old-arena region", [
|
||||
"rg remove old-arena",
|
||||
], "Removed the old-arena region."),
|
||||
("sudo set region priority for spawn over global", [
|
||||
"rg setpriority spawn-protection 10",
|
||||
], "Set spawn-protection priority to 10 (higher overrides lower)."),
|
||||
("sudo prevent fire spread in the village", [
|
||||
"rg flag village fire-spread deny",
|
||||
"rg flag village lava-fire deny",
|
||||
], "Disabled fire spread and lava fire in the village region."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, reasoning) in enumerate(WG):
|
||||
ex = build_rcon_example(rcon, f"plugin-wg-{i:03d}", "worldguard", prompt, cmds, reasoning)
|
||||
examples.append(ex)
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_coreprotect(rcon):
|
||||
"""CoreProtect inspection and rollback examples."""
|
||||
print(" CoreProtect...")
|
||||
examples = []
|
||||
|
||||
CP = [
|
||||
("sudo check who broke blocks near me", [
|
||||
"co inspect",
|
||||
], "Enabled CoreProtect inspector mode. Player can now click blocks to see history."),
|
||||
("sudo rollback griefing from the last hour", [
|
||||
"co rollback t:1h",
|
||||
], "Rolled back all block changes from the last hour."),
|
||||
("sudo rollback what TheBigBoss did in the last 30 minutes", [
|
||||
"co rollback u:TheBigBoss t:30m",
|
||||
], "Rolled back TheBigBoss's actions from the last 30 minutes."),
|
||||
("sudo restore blocks that were rolled back", [
|
||||
"co restore t:1h",
|
||||
], "Restored previously rolled-back changes from the last hour."),
|
||||
("sudo check what happened here in the last day", [
|
||||
"co lookup t:24h r:10",
|
||||
], "Looked up all changes within 10 blocks in the last 24 hours."),
|
||||
("sudo rollback only TNT damage", [
|
||||
"co rollback t:1h a:tnt",
|
||||
], "Rolled back only TNT explosion damage from the last hour."),
|
||||
("sudo rollback fire damage from the last 2 hours", [
|
||||
"co rollback t:2h a:fire",
|
||||
], "Rolled back fire damage from the last 2 hours."),
|
||||
("sudo who placed blocks around 100 64 200?", [
|
||||
"co lookup t:7d r:5 l:100,64,200",
|
||||
], "Looked up 7 days of block placement history near those coordinates."),
|
||||
("sudo undo what happened to the diamond blocks", [
|
||||
"co rollback t:12h b:diamond_block",
|
||||
], "Rolled back changes to diamond blocks in the last 12 hours."),
|
||||
("sudo rollback Ace's actions but only block breaks", [
|
||||
"co rollback u:Ace13245 t:1h a:block",
|
||||
], "Rolled back only block break/place actions by Ace in the last hour."),
|
||||
("sudo check the status of CoreProtect", [
|
||||
"co status",
|
||||
], "Displayed CoreProtect status including database size and version."),
|
||||
("sudo stop inspecting", [
|
||||
"co inspect",
|
||||
], "Toggled off CoreProtect inspector mode."),
|
||||
("sudo rollback all container theft in the last 6 hours", [
|
||||
"co rollback t:6h a:container",
|
||||
], "Rolled back container (chest/barrel/etc.) access in the last 6 hours."),
|
||||
("sudo lookup what Ace13245 did today", [
|
||||
"co lookup u:Ace13245 t:24h",
|
||||
], "Looked up all of Ace13245's actions in the last 24 hours."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, reasoning) in enumerate(CP):
|
||||
ex = build_rcon_example(rcon, f"plugin-cp-{i:03d}", "coreprotect", prompt, cmds, reasoning)
|
||||
examples.append(ex)
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_essentialsx(rcon):
|
||||
"""EssentialsX home/warp/kit/economy examples."""
|
||||
print(" EssentialsX...")
|
||||
examples = []
|
||||
|
||||
ESS = [
|
||||
# Homes
|
||||
("sudo set my home here", [
|
||||
"sethome {p} home",
|
||||
], "Set player's home location."),
|
||||
("sudo set a home called mine", [
|
||||
"sethome {p} mine",
|
||||
], "Set named home 'mine' for the player."),
|
||||
("sudo tp me to my home", [
|
||||
"home {p}",
|
||||
], "Teleported player to their default home."),
|
||||
("sudo delete my mine home", [
|
||||
"delhome {p} mine",
|
||||
], "Deleted the 'mine' home."),
|
||||
|
||||
# Warps
|
||||
("sudo create a warp called arena", [
|
||||
"setwarp arena",
|
||||
], "Created warp point 'arena' at current location."),
|
||||
("sudo tp me to the arena warp", [
|
||||
"warp arena {p}",
|
||||
], "Warped player to the arena."),
|
||||
("sudo list all warps", [
|
||||
"warps",
|
||||
], "Listed all available warp points."),
|
||||
("sudo delete the old warp", [
|
||||
"delwarp old",
|
||||
], "Deleted the 'old' warp point."),
|
||||
("sudo create a warp at spawn", [
|
||||
"setwarp spawn",
|
||||
], "Created spawn warp at current location."),
|
||||
|
||||
# Kits
|
||||
("sudo give me the starter kit", [
|
||||
"kit starter {p}",
|
||||
], "Gave the starter kit to the player."),
|
||||
|
||||
# Economy
|
||||
("sudo give Ace 1000 coins", [
|
||||
"eco give Ace13245 1000",
|
||||
], "Added $1000 to Ace13245's balance."),
|
||||
("sudo check my balance", [
|
||||
"balance {p}",
|
||||
], "Checked player's economy balance."),
|
||||
("sudo set everyone's balance to 500", [
|
||||
"eco set * 500",
|
||||
], "Set all players' balance to $500."),
|
||||
("sudo take 200 from TheBigBoss", [
|
||||
"eco take TheBigBoss 200",
|
||||
], "Removed $200 from TheBigBoss's balance."),
|
||||
|
||||
# Teleport
|
||||
("sudo tp Ace to me", [
|
||||
"tp Ace13245 {p}",
|
||||
], "Teleported Ace13245 to the requesting player."),
|
||||
("sudo tp everyone to spawn", [
|
||||
"tpall spawn",
|
||||
], "Teleported all players to spawn."),
|
||||
|
||||
# Player management
|
||||
("sudo set my nickname to StoneKing", [
|
||||
"nick {p} StoneKing",
|
||||
], "Changed player's display name to StoneKing."),
|
||||
("sudo heal me", [
|
||||
"heal {p}",
|
||||
], "Fully healed the player."),
|
||||
("sudo feed me", [
|
||||
"feed {p}",
|
||||
], "Restored player's hunger bar."),
|
||||
("sudo repair what I'm holding", [
|
||||
"repair {p}",
|
||||
], "Repaired the player's held item."),
|
||||
("sudo check how long Ace has played", [
|
||||
"seen Ace13245",
|
||||
], "Checked when Ace13245 was last online and playtime."),
|
||||
("sudo set spawn point here", [
|
||||
"setspawn",
|
||||
], "Set the server spawn point to current location."),
|
||||
("sudo broadcast a message to everyone", [
|
||||
"broadcast Welcome to the new world!",
|
||||
], "Broadcast server-wide message."),
|
||||
("sudo give me god mode", [
|
||||
"god {p}",
|
||||
], "Toggled god mode (invulnerability) for the player."),
|
||||
("sudo fly mode on", [
|
||||
"fly {p}",
|
||||
], "Toggled flight for the player."),
|
||||
("sudo set player speed to fast", [
|
||||
"speed fly 5 {p}",
|
||||
], "Set flying speed to maximum for the player."),
|
||||
("sudo check who's online and their info", [
|
||||
"list",
|
||||
"whois {p}",
|
||||
], "Listed online players and checked requesting player's info."),
|
||||
("sudo make it sunny", [
|
||||
"sun",
|
||||
], "Set weather to clear using Essentials shorthand."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, reasoning) in enumerate(ESS):
|
||||
ex = build_rcon_example(rcon, f"plugin-ess-{i:03d}", "essentialsx", prompt, cmds, reasoning)
|
||||
examples.append(ex)
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_luckperms(rcon):
|
||||
"""LuckPerms permission management examples."""
|
||||
print(" LuckPerms...")
|
||||
examples = []
|
||||
|
||||
LP = [
|
||||
("sudo give Ace13245 permission to fly", [
|
||||
"lp user Ace13245 permission set essentials.fly true",
|
||||
], "Granted flight permission to Ace13245."),
|
||||
("sudo create a VIP group", [
|
||||
"lp creategroup vip",
|
||||
], "Created the VIP permission group."),
|
||||
("sudo add Ace to VIP group", [
|
||||
"lp user Ace13245 parent add vip",
|
||||
], "Added Ace13245 to the VIP group."),
|
||||
("sudo give VIP group access to /fly and /heal", [
|
||||
"lp group vip permission set essentials.fly true",
|
||||
"lp group vip permission set essentials.heal true",
|
||||
], "Gave VIP group fly and heal permissions."),
|
||||
("sudo remove TheBigBoss from VIP", [
|
||||
"lp user TheBigBoss parent remove vip",
|
||||
], "Removed TheBigBoss from VIP group."),
|
||||
("sudo check what permissions Ace has", [
|
||||
"lp user Ace13245 permission info",
|
||||
], "Displayed Ace13245's permission info."),
|
||||
("sudo give temporary VIP for 1 day to slingshooter08", [
|
||||
"lp user slingshooter08 parent addtemp vip 1d",
|
||||
], "Gave slingshooter08 temporary VIP status for 24 hours."),
|
||||
("sudo set VIP prefix to gold [VIP]", [
|
||||
"lp group vip meta setprefix 100 \"&6[VIP] \"",
|
||||
], "Set gold-colored VIP chat prefix."),
|
||||
("sudo create a builder group with WorldEdit access", [
|
||||
"lp creategroup builder",
|
||||
"lp group builder permission set worldedit.* true",
|
||||
], "Created builder group with full WorldEdit permissions."),
|
||||
("sudo deny TNT placement for default group", [
|
||||
"lp group default permission set minecraft.command.setblock false",
|
||||
], "Denied setblock command for default group."),
|
||||
("sudo list all groups", [
|
||||
"lp listgroups",
|
||||
], "Listed all permission groups."),
|
||||
("sudo check VIP group permissions", [
|
||||
"lp group vip permission info",
|
||||
], "Displayed VIP group permission details."),
|
||||
("sudo give me all permissions", [
|
||||
"lp user {p} permission set * true",
|
||||
], "Granted wildcard (all) permissions to the player."),
|
||||
("sudo set default group to have basic essentials", [
|
||||
"lp group default permission set essentials.home true",
|
||||
"lp group default permission set essentials.spawn true",
|
||||
"lp group default permission set essentials.tpa true",
|
||||
"lp group default permission set essentials.msg true",
|
||||
], "Gave default group basic Essentials permissions: home, spawn, tpa, msg."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, reasoning) in enumerate(LP):
|
||||
ex = build_rcon_example(rcon, f"plugin-lp-{i:03d}", "luckperms", prompt, cmds, reasoning)
|
||||
examples.append(ex)
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_fawe_advanced(rcon):
|
||||
"""Advanced FAWE/WorldEdit examples beyond basic commands."""
|
||||
print(" FAWE advanced...")
|
||||
examples = []
|
||||
|
||||
FAWE = [
|
||||
("sudo make a sphere of glass 10 blocks wide", [
|
||||
"//sphere minecraft:glass 10",
|
||||
], "Created a glass sphere with radius 10."),
|
||||
("sudo hollow sphere of stone", [
|
||||
"//hsphere minecraft:stone 8",
|
||||
], "Created hollow stone sphere radius 8."),
|
||||
("sudo cylinder of quartz 5 wide 10 tall", [
|
||||
"//cyl minecraft:quartz_block 5 10",
|
||||
], "Created quartz cylinder radius 5, height 10."),
|
||||
("sudo replace all stone with deepslate in selection", [
|
||||
"//replace minecraft:stone minecraft:deepslate",
|
||||
], "Replaced stone with deepslate in the selected region."),
|
||||
("sudo copy and paste this structure 20 blocks east", [
|
||||
"//copy",
|
||||
"//paste",
|
||||
], "Copied selection and pasted it."),
|
||||
("sudo undo my last WorldEdit action", [
|
||||
"//undo",
|
||||
], "Undid the last WorldEdit operation."),
|
||||
("sudo redo what I just undid", [
|
||||
"//redo",
|
||||
], "Redid the last undone WorldEdit operation."),
|
||||
("sudo smooth the terrain in my selection", [
|
||||
"//smooth 5",
|
||||
], "Smoothed terrain in selection with 5 iterations."),
|
||||
("sudo drain all water within 20 blocks", [
|
||||
"//drain 20",
|
||||
], "Drained water within 20 block radius."),
|
||||
("sudo set a pyramid of sandstone 10 tall", [
|
||||
"//pyramid minecraft:sandstone 10",
|
||||
], "Created sandstone pyramid 10 blocks tall."),
|
||||
("sudo hollow out the selected area", [
|
||||
"//hollow",
|
||||
], "Hollowed out the selected region leaving only the shell."),
|
||||
("sudo make walls around my selection", [
|
||||
"//walls minecraft:stone_bricks",
|
||||
], "Built stone brick walls around the selection (no floor/ceiling)."),
|
||||
("sudo fill the selection with a checkerboard pattern", [
|
||||
"//set 50%minecraft:white_concrete,50%minecraft:black_concrete",
|
||||
], "Filled with alternating black and white concrete."),
|
||||
("sudo stack my selection 5 times going north", [
|
||||
"//stack 5 north",
|
||||
], "Stacked the selection 5 times northward."),
|
||||
("sudo generate a forest in my selection", [
|
||||
"//forest oak 10",
|
||||
], "Generated oak trees with 10% density in the selection."),
|
||||
("sudo remove all snow in a 50 block radius", [
|
||||
"//removenear minecraft:snow 50",
|
||||
], "Removed snow layers within 50 blocks."),
|
||||
("sudo count blocks in my selection", [
|
||||
"//count minecraft:diamond_ore",
|
||||
], "Counted diamond ore blocks in the selection."),
|
||||
("sudo make a natural-looking cave", [
|
||||
"//cyl minecraft:air 4 8",
|
||||
], "Carved cylindrical tunnel (air cylinder) radius 4, depth 8."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, reasoning) in enumerate(FAWE):
|
||||
ex = build_rcon_example(rcon, f"plugin-fawe-{i:03d}", "fawe", prompt, cmds, reasoning)
|
||||
examples.append(ex)
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_combined_plugin_examples(rcon):
|
||||
"""Examples that combine multiple plugins in one request."""
|
||||
print(" Combined plugin examples...")
|
||||
examples = []
|
||||
|
||||
COMBINED = [
|
||||
("sudo create a protected arena with WorldEdit and WorldGuard", [
|
||||
"//pos1 -50,60,-50",
|
||||
"//pos2 50,100,50",
|
||||
"//set minecraft:air",
|
||||
"//walls minecraft:stone_bricks",
|
||||
"//floor minecraft:smooth_stone",
|
||||
"rg define arena {p}",
|
||||
"rg flag arena pvp allow",
|
||||
"rg flag arena heal-amount 1",
|
||||
"rg flag arena heal-delay 5",
|
||||
], "Built arena with WorldEdit, then protected with WorldGuard. PvP enabled, slow healing."),
|
||||
("sudo set up a new player experience", [
|
||||
"lp group default permission set essentials.home true",
|
||||
"lp group default permission set essentials.spawn true",
|
||||
"setwarp tutorial",
|
||||
"rg define tutorial-area",
|
||||
"rg flag tutorial-area pvp deny",
|
||||
"rg flag tutorial-area mob-spawning deny",
|
||||
], "Set up default permissions, tutorial warp, and protected tutorial area."),
|
||||
("sudo rollback Ace's WorldEdit mistakes and revoke his builder perms", [
|
||||
"co rollback u:Ace13245 t:30m",
|
||||
"lp user Ace13245 parent remove builder",
|
||||
], "Rolled back Ace's changes and removed builder group access."),
|
||||
("sudo create a VIP lounge area", [
|
||||
"//pos1 0,64,0",
|
||||
"//pos2 20,74,20",
|
||||
"//set minecraft:quartz_block",
|
||||
"//hollow",
|
||||
"rg define vip-lounge",
|
||||
"rg flag vip-lounge entry -g nonmembers deny",
|
||||
"rg flag vip-lounge greeting Welcome to the VIP Lounge!",
|
||||
"setwarp vip-lounge",
|
||||
], "Built quartz room with WE, restricted entry to members only via WG, created warp."),
|
||||
("sudo give TheBigBoss a reward package", [
|
||||
"eco give TheBigBoss 5000",
|
||||
"give TheBigBoss minecraft:netherite_ingot 3",
|
||||
"give TheBigBoss minecraft:diamond 64",
|
||||
"lp user TheBigBoss parent addtemp vip 7d",
|
||||
], "Gave economy reward, items, and 7-day VIP status."),
|
||||
("sudo prepare the server for an event", [
|
||||
"broadcast The Battle Royale event starts in 5 minutes!",
|
||||
"rg flag arena pvp allow",
|
||||
"rg flag arena exit deny",
|
||||
"eco set * 0",
|
||||
"effect give @a minecraft:regeneration 300 0",
|
||||
], "Announced event, set arena flags, reset economy, gave regen."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, reasoning) in enumerate(COMBINED):
|
||||
ex = build_rcon_example(rcon, f"plugin-combo-{i:03d}", "combined", prompt, cmds, reasoning)
|
||||
examples.append(ex)
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_god_mode_plugin_examples(rcon):
|
||||
"""God persona using plugins for divine judgment."""
|
||||
print(" God mode plugin examples...")
|
||||
examples = []
|
||||
|
||||
GOD_SYSTEM = (
|
||||
"You are God in a Minecraft server with plugins: WorldGuard, CoreProtect, "
|
||||
"EssentialsX, Vault, LuckPerms, FAWE.\n"
|
||||
"Return JSON: {\"risk_level\": <0-5>, \"message\": \"...\", \"commands\": [...], \"reasoning\": \"...\"}\n\n"
|
||||
+ SYNTAX_RULES + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
GOD = [
|
||||
("pray lord, someone destroyed my house!", [
|
||||
"co rollback t:2h r:30",
|
||||
], "A mortal's home was desecrated. I have turned back time to restore it.",
|
||||
"Used CoreProtect to rollback damage near the player."),
|
||||
("pray bless me with power, oh great one", [
|
||||
"lp user {p} parent addtemp vip 1d",
|
||||
"eco give {p} 1000",
|
||||
"effect give {p} minecraft:strength 600 1",
|
||||
], "You show devotion. I grant you temporary divine favor — VIP status, wealth, and strength.",
|
||||
"Gave 24h VIP, economy bonus, and strength effect."),
|
||||
("pray protect my village from monsters", [
|
||||
"rg define {p}-village {p}",
|
||||
"rg flag {p}-village mob-spawning deny",
|
||||
"rg flag {p}-village creeper-explosion deny",
|
||||
], "I cast a divine ward over your village. No creature of darkness shall spawn within its borders.",
|
||||
"Created region with mob spawning and creeper explosion protection."),
|
||||
("pray smite the wicked TheBigBoss for griefing", [
|
||||
"co lookup u:TheBigBoss t:1h",
|
||||
"execute at TheBigBoss run summon minecraft:lightning_bolt",
|
||||
"eco take TheBigBoss 500",
|
||||
], "I have seen TheBigBoss's transgressions. Lightning falls upon the wicked, and their coffers are lightened.",
|
||||
"Checked griefing evidence, smited with lightning, took economy penalty."),
|
||||
("pray I am lost and cannot find my way home", [
|
||||
"home {p}",
|
||||
], "Lost child, I return you to the place you call home.",
|
||||
"Used Essentials home teleport."),
|
||||
("pray make me a grand temple", [
|
||||
"//cyl minecraft:quartz_block 8 12",
|
||||
"//hollow",
|
||||
"//cyl minecraft:quartz_pillar 8 1",
|
||||
"rg define temple-{p} {p}",
|
||||
"rg flag temple-{p} pvp deny",
|
||||
"setwarp temple",
|
||||
], "A temple rises from the earth at my command. It is sanctified — no blood shall be spilled within.",
|
||||
"Built quartz temple with WE, protected with WG, created warp."),
|
||||
]
|
||||
|
||||
for i, (prompt, cmds, god_msg, reasoning) in enumerate(GOD):
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [{"role": "system", "content": GOD_SYSTEM}, user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
resolved_cmds = []
|
||||
for cmd in cmds:
|
||||
cmd = cmd.replace("{p}", player)
|
||||
result, ok = run_cmd(rcon, cmd)
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": ok, "result": result}))
|
||||
resolved_cmds.append(cmd)
|
||||
time.sleep(0.05)
|
||||
|
||||
resp = {"risk_level": 3, "message": god_msg, "commands": resolved_cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
examples.append({
|
||||
"id": f"plugin-god-{i:03d}", "source": "plugin_training",
|
||||
"type": "god_plugin", "messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--rcon-host", default="192.168.0.244")
|
||||
parser.add_argument("--rcon-port", type=int, default=25577)
|
||||
parser.add_argument("--rcon-pass", default="REDACTED_RCON")
|
||||
args = parser.parse_args()
|
||||
|
||||
print(f"Connecting to {args.rcon_host}:{args.rcon_port}...")
|
||||
rcon = get_rcon(args.rcon_host, args.rcon_port, args.rcon_pass)
|
||||
print("Connected.\n")
|
||||
|
||||
all_examples = []
|
||||
generators = [
|
||||
gen_worldguard,
|
||||
gen_coreprotect,
|
||||
gen_essentialsx,
|
||||
gen_luckperms,
|
||||
gen_fawe_advanced,
|
||||
gen_combined_plugin_examples,
|
||||
gen_god_mode_plugin_examples,
|
||||
]
|
||||
|
||||
for gen in generators:
|
||||
examples = gen(rcon)
|
||||
all_examples.extend(examples)
|
||||
ok = sum(1 for e in examples if e.get("all_success", True))
|
||||
print(f" → {len(examples)} examples ({ok} all-success)")
|
||||
|
||||
# Summary
|
||||
by_type = {}
|
||||
for e in all_examples:
|
||||
t = e["type"]
|
||||
by_type[t] = by_type.get(t, 0) + 1
|
||||
|
||||
print(f"\nTotal: {len(all_examples)} examples")
|
||||
for t, c in sorted(by_type.items()):
|
||||
print(f" {t}: {c}")
|
||||
|
||||
success_total = sum(1 for e in all_examples if e.get("all_success", True))
|
||||
print(f" All-success: {success_total}/{len(all_examples)}")
|
||||
|
||||
OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(OUTPUT_PATH, "w") as f:
|
||||
for ex in all_examples:
|
||||
f.write(json.dumps(ex, ensure_ascii=False) + "\n")
|
||||
|
||||
print(f"\nWritten to {OUTPUT_PATH}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,661 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate high-quality tool-calling training data with REAL RCON responses.
|
||||
|
||||
No AI involved — we craft the prompts, commands, and tool sequences by hand,
|
||||
then execute each command through RCON to get actual server responses.
|
||||
This produces gold-standard training data with real validation.
|
||||
|
||||
Generates examples across all 14 tools with proper multi-turn conversations:
|
||||
- script.validate → script.write → script.execute (with real RCON validation)
|
||||
- memory.read → rcon.execute (tp to saved location)
|
||||
- world.nearby_entities → rcon.execute (kill scanned mobs)
|
||||
- wiki_lookup → rcon.execute (apply looked-up knowledge)
|
||||
- chained multi-tool sequences
|
||||
|
||||
Usage:
|
||||
python3 generate_rcon_validated_training.py --rcon-host 192.168.0.244 --rcon-port 25577
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import random
|
||||
import re
|
||||
import socket
|
||||
import struct
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from agent.tools.tool_schemas import qwen3_tools_block
|
||||
from agent.prompts.system_prompts import SYNTAX_RULES, RISK_GRADIENT
|
||||
|
||||
OUTPUT_PATH = PROJECT_ROOT / "data" / "raw" / "rcon_validated_tool_training.jsonl"
|
||||
|
||||
TOOLS_BLOCK = qwen3_tools_block()
|
||||
SYSTEM_SUDO = (
|
||||
"You are a Minecraft 1.21 command translator with full tool access.\n"
|
||||
"Tools: rcon.execute, minecraft.wiki_lookup, world.player_info, world.server_state, "
|
||||
"world.nearby_entities, memory.read, memory.write, script.write, script.validate, "
|
||||
"script.execute, script.read, script.list, script.delete, script.schedule.\n\n"
|
||||
"For complex builds (4+ commands), write mcfunction scripts. Validate before writing.\n"
|
||||
"PERMISSION LEVEL: 4 (generous).\n\n"
|
||||
"Return JSON: {\"risk_level\": <0-5>, \"commands\": [...], \"reasoning\": \"...\"}\n\n"
|
||||
+ SYNTAX_RULES + RISK_GRADIENT + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
SYSTEM_GOD = (
|
||||
"You are God in a Minecraft server. You have full tool access.\n"
|
||||
"Return JSON: {\"risk_level\": <0-5>, \"message\": \"...\", \"commands\": [...], \"reasoning\": \"...\"}\n\n"
|
||||
+ SYNTAX_RULES + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
PLAYERS = ["slingshooter08", "Ace13245", "TheBigBoss", "xXDragonSlayerXx"]
|
||||
|
||||
|
||||
from agent.tools.persistent_rcon import get_rcon as _get_rcon
|
||||
|
||||
class SimpleRCON:
|
||||
"""Wrapper around persistent_rcon."""
|
||||
def __init__(self, host, port, password):
|
||||
self._rcon = _get_rcon(host, port, password)
|
||||
|
||||
def command(self, cmd):
|
||||
return self._rcon.command(cmd)
|
||||
|
||||
|
||||
def sys_msg(mode="sudo"):
|
||||
return {"role": "system", "content": SYSTEM_GOD if mode == "god" else SYSTEM_SUDO}
|
||||
|
||||
def user_msg(text):
|
||||
return {"role": "user", "content": text}
|
||||
|
||||
def tool_call(name, args):
|
||||
return {"role": "assistant", "content": f"<tool_call>\n{json.dumps({'name': name, 'arguments': args})}\n</tool_call>"}
|
||||
|
||||
def tool_result(data):
|
||||
return {"role": "tool", "content": json.dumps(data)}
|
||||
|
||||
def final_response(resp):
|
||||
return {"role": "assistant", "content": json.dumps(resp)}
|
||||
|
||||
def is_error(result):
|
||||
return any(e in result for e in ("<--[HERE]", "Unknown", "Incorrect", "Expected", "Invalid"))
|
||||
|
||||
|
||||
def validate_commands_rcon(rcon, commands):
|
||||
"""Execute commands through RCON and return results."""
|
||||
results = []
|
||||
for cmd in commands:
|
||||
cmd = cmd.strip()
|
||||
if not cmd or cmd.startswith("#"):
|
||||
results.append({"cmd": cmd, "result": "comment", "ok": True})
|
||||
continue
|
||||
try:
|
||||
result = rcon.command(cmd)
|
||||
ok = not is_error(result)
|
||||
results.append({"cmd": cmd, "result": result[:300], "ok": ok})
|
||||
except Exception as e:
|
||||
results.append({"cmd": cmd, "result": str(e), "ok": False})
|
||||
return results
|
||||
|
||||
|
||||
def gen_script_examples(rcon):
|
||||
"""Script write/validate/execute examples with real RCON validation."""
|
||||
examples = []
|
||||
|
||||
SCRIPTS = [
|
||||
("build me a small oak cabin", "oak_cabin", "Small oak cabin with door, windows, and lantern", [
|
||||
"fill ~-3 ~ ~-3 ~3 ~3 ~3 minecraft:oak_planks hollow",
|
||||
"fill ~-3 ~ ~-3 ~3 ~ ~3 minecraft:oak_planks",
|
||||
"fill ~-2 ~1 ~-3 ~2 ~2 ~-3 minecraft:air",
|
||||
"setblock ~0 ~1 ~-3 minecraft:oak_door[facing=north,half=lower]",
|
||||
"setblock ~0 ~2 ~-3 minecraft:oak_door[facing=north,half=upper]",
|
||||
"setblock ~2 ~1 ~3 minecraft:glass_pane",
|
||||
"setblock ~-2 ~1 ~3 minecraft:glass_pane",
|
||||
"setblock ~0 ~2 ~0 minecraft:lantern[hanging=true]",
|
||||
]),
|
||||
("create a pvp arena with wool corners", "pvp_arena", "PvP arena with colored corners", [
|
||||
"fill ~-12 ~-1 ~-12 ~12 ~-1 ~12 minecraft:smooth_stone",
|
||||
"fill ~-12 ~ ~-12 ~12 ~4 ~-12 minecraft:iron_bars",
|
||||
"fill ~-12 ~ ~12 ~12 ~4 ~12 minecraft:iron_bars",
|
||||
"fill ~-12 ~ ~-12 ~-12 ~4 ~12 minecraft:iron_bars",
|
||||
"fill ~12 ~ ~-12 ~12 ~4 ~12 minecraft:iron_bars",
|
||||
"fill ~-12 ~-1 ~-12 ~-10 ~-1 ~-10 minecraft:red_wool",
|
||||
"fill ~10 ~-1 ~10 ~12 ~-1 ~12 minecraft:blue_wool",
|
||||
]),
|
||||
("make an enchanting room", "enchant_room", "Enchanting table surrounded by bookshelves", [
|
||||
"fill ~-3 ~ ~-3 ~3 ~3 ~3 minecraft:deepslate_bricks hollow",
|
||||
"fill ~-2 ~ ~-2 ~2 ~2 ~2 minecraft:air",
|
||||
"setblock ~0 ~ ~0 minecraft:enchanting_table",
|
||||
"fill ~-2 ~1 ~-2 ~2 ~1 ~2 minecraft:bookshelf",
|
||||
"fill ~-1 ~1 ~-1 ~1 ~1 ~1 minecraft:air",
|
||||
"setblock ~0 ~1 ~0 minecraft:enchanting_table",
|
||||
"setblock ~0 ~2 ~0 minecraft:lantern[hanging=true]",
|
||||
]),
|
||||
("build a nether portal frame", "nether_portal", "Obsidian nether portal frame", [
|
||||
"fill ~0 ~ ~0 ~3 ~4 ~0 minecraft:obsidian",
|
||||
"fill ~1 ~1 ~0 ~2 ~3 ~0 minecraft:air",
|
||||
]),
|
||||
("create a mob farm collection area", "mob_farm", "Mob farm with hoppers and chest", [
|
||||
"fill ~-4 ~-1 ~-4 ~4 ~-1 ~4 minecraft:cobblestone",
|
||||
"setblock ~0 ~-2 ~0 minecraft:chest",
|
||||
"setblock ~0 ~-1 ~0 minecraft:hopper",
|
||||
"fill ~-4 ~ ~0 ~-1 ~ ~0 minecraft:water",
|
||||
"fill ~1 ~ ~0 ~4 ~ ~0 minecraft:water",
|
||||
]),
|
||||
("build a lookout tower", "lookout_tower", "Tall stone tower with viewing platform", [
|
||||
"fill ~-1 ~ ~-1 ~1 ~8 ~1 minecraft:stone_bricks hollow",
|
||||
"fill ~0 ~ ~0 ~0 ~7 ~0 minecraft:air",
|
||||
"fill ~1 ~1 ~0 ~1 ~7 ~0 minecraft:ladder[facing=west]",
|
||||
"fill ~-2 ~8 ~-2 ~2 ~8 ~2 minecraft:stone_brick_slab",
|
||||
"fill ~-2 ~9 ~-2 ~2 ~9 ~2 minecraft:stone_brick_wall",
|
||||
"fill ~-1 ~9 ~-1 ~1 ~9 ~1 minecraft:air",
|
||||
"setblock ~0 ~10 ~0 minecraft:lantern",
|
||||
]),
|
||||
("make a fishing dock", "fishing_dock", "Wooden dock extending over water", [
|
||||
"fill ~0 ~-1 ~0 ~1 ~-1 ~8 minecraft:oak_planks",
|
||||
"fill ~-1 ~-2 ~0 ~-1 ~-1 ~8 minecraft:oak_fence",
|
||||
"fill ~2 ~-2 ~0 ~2 ~-1 ~8 minecraft:oak_fence",
|
||||
"setblock ~0 ~0 ~8 minecraft:oak_fence",
|
||||
"setblock ~1 ~0 ~8 minecraft:oak_fence",
|
||||
"setblock ~0 ~0 ~0 minecraft:lantern",
|
||||
]),
|
||||
("create a garden with flower beds", "garden", "Flower garden with paths", [
|
||||
"fill ~-5 ~-1 ~-5 ~5 ~-1 ~5 minecraft:grass_block",
|
||||
"fill ~-5 ~-1 ~0 ~5 ~-1 ~0 minecraft:gravel",
|
||||
"fill ~0 ~-1 ~-5 ~0 ~-1 ~5 minecraft:gravel",
|
||||
"setblock ~-3 ~ ~-3 minecraft:rose_bush[half=lower]",
|
||||
"setblock ~3 ~ ~-3 minecraft:peony[half=lower]",
|
||||
"setblock ~-3 ~ ~3 minecraft:lilac[half=lower]",
|
||||
"setblock ~3 ~ ~3 minecraft:sunflower[half=lower]",
|
||||
"setblock ~0 ~ ~0 minecraft:water",
|
||||
]),
|
||||
("build a redstone clock", "redstone_clock", "Simple repeater clock", [
|
||||
"setblock ~0 ~ ~0 minecraft:redstone_wire",
|
||||
"setblock ~1 ~ ~0 minecraft:repeater[facing=west,delay=4]",
|
||||
"setblock ~2 ~ ~0 minecraft:redstone_wire",
|
||||
"setblock ~2 ~ ~1 minecraft:repeater[facing=north,delay=4]",
|
||||
"setblock ~2 ~ ~2 minecraft:redstone_wire",
|
||||
"setblock ~1 ~ ~2 minecraft:repeater[facing=east,delay=4]",
|
||||
"setblock ~0 ~ ~2 minecraft:redstone_wire",
|
||||
"setblock ~0 ~ ~1 minecraft:repeater[facing=south,delay=4]",
|
||||
]),
|
||||
("make a treasure vault", "treasure_vault", "Secure room with chests and iron door", [
|
||||
"fill ~-3 ~ ~-3 ~3 ~3 ~3 minecraft:deepslate_brick_wall hollow",
|
||||
"fill ~-2 ~ ~-2 ~2 ~2 ~2 minecraft:air",
|
||||
"setblock ~0 ~0 ~-3 minecraft:iron_door[facing=north,half=lower]",
|
||||
"setblock ~0 ~1 ~-3 minecraft:iron_door[facing=north,half=upper]",
|
||||
"setblock ~-1 ~0 ~-2 minecraft:chest",
|
||||
"setblock ~1 ~0 ~-2 minecraft:chest",
|
||||
"setblock ~-1 ~0 ~2 minecraft:chest",
|
||||
"setblock ~1 ~0 ~2 minecraft:chest",
|
||||
"setblock ~0 ~2 ~0 minecraft:lantern[hanging=true]",
|
||||
]),
|
||||
]
|
||||
|
||||
for prompt, name, desc, commands in SCRIPTS:
|
||||
player = random.choice(PLAYERS)
|
||||
mode = "sudo"
|
||||
msgs = [sys_msg(mode), user_msg(f"Player {player}: sudo {prompt}")]
|
||||
|
||||
# Step 1: Validate
|
||||
rcon_results = validate_commands_rcon(rcon, commands)
|
||||
valid = all(r["ok"] for r in rcon_results)
|
||||
errors = [{"line": i+1, "command": r["cmd"], "error": r["result"]}
|
||||
for i, r in enumerate(rcon_results) if not r["ok"]]
|
||||
|
||||
msgs.append(tool_call("script.validate", {"commands": commands}))
|
||||
msgs.append(tool_result({
|
||||
"valid": valid,
|
||||
"total": len(commands),
|
||||
"passed": sum(1 for r in rcon_results if r["ok"]),
|
||||
"errors": errors,
|
||||
}))
|
||||
|
||||
# Step 2: Write (if valid or partially valid)
|
||||
write_cmds = [r["cmd"] for r in rcon_results if r["ok"]] if not valid else commands
|
||||
msgs.append(tool_call("script.write", {"name": name, "commands": write_cmds, "description": desc}))
|
||||
msgs.append(tool_result({"ok": True, "path": f"mortdecai:{name}", "lines": len(write_cmds)}))
|
||||
|
||||
# Step 3: Execute
|
||||
msgs.append(tool_call("script.execute", {"name": name, "as_player": player}))
|
||||
msgs.append(tool_result({"ok": True, "result": f"Executed {len(write_cmds)} commands from function mortdecai:{name}"}))
|
||||
|
||||
# Final
|
||||
fix_note = f" Fixed {len(errors)} validation errors." if errors else ""
|
||||
resp = {
|
||||
"risk_level": 3,
|
||||
"commands": [f"function mortdecai:{name}"],
|
||||
"reasoning": f"Validated {len(commands)} commands ({sum(1 for r in rcon_results if r['ok'])} passed).{fix_note} Wrote and executed '{name}' script at player position.",
|
||||
}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
examples.append({
|
||||
"id": f"rcon-script-{name}",
|
||||
"source": "rcon_validated",
|
||||
"type": "script_write_execute",
|
||||
"messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_direct_command_examples(rcon):
|
||||
"""Direct rcon.execute examples with real server responses."""
|
||||
examples = []
|
||||
|
||||
COMMANDS = [
|
||||
("sudo give me a diamond sword with sharpness 5", [
|
||||
"give {p} minecraft:diamond_sword[enchantments={sharpness:5,unbreaking:3,mending:1}] 1",
|
||||
], "Gave max enchanted diamond sword."),
|
||||
("sudo full netherite armor please", [
|
||||
"give {p} minecraft:netherite_helmet[enchantments={protection:4,unbreaking:3,mending:1}] 1",
|
||||
"give {p} minecraft:netherite_chestplate[enchantments={protection:4,unbreaking:3,mending:1}] 1",
|
||||
"give {p} minecraft:netherite_leggings[enchantments={protection:4,unbreaking:3,mending:1}] 1",
|
||||
"give {p} minecraft:netherite_boots[enchantments={protection:4,unbreaking:3,mending:1}] 1",
|
||||
], "Full netherite armor set with protection 4 and mending."),
|
||||
("sudo make it night", ["time set night"], "Set time to night."),
|
||||
("sudo give me 64 golden apples", [
|
||||
"give {p} minecraft:golden_apple 64",
|
||||
], "Gave 64 golden apples."),
|
||||
("sudo smite me with lightning", [
|
||||
"execute at {p} run summon minecraft:lightning_bolt",
|
||||
], "Summoned lightning at player position."),
|
||||
("sudo give me speed 3 for 10 minutes", [
|
||||
"effect give {p} minecraft:speed 600 2",
|
||||
], "Applied speed 3 (amplifier 2) for 600 seconds."),
|
||||
("sudo clear weather", ["weather clear 999999"], "Cleared weather."),
|
||||
("sudo make me invincible", [
|
||||
"effect give {p} minecraft:resistance 6000 4",
|
||||
"effect give {p} minecraft:regeneration 6000 2",
|
||||
"effect give {p} minecraft:fire_resistance 6000 0",
|
||||
], "Applied resistance 5, regeneration 3, and fire resistance for 100 minutes."),
|
||||
("sudo give me a god bow", [
|
||||
"give {p} minecraft:bow[enchantments={power:5,infinity:1,flame:1,punch:2,unbreaking:3}] 1",
|
||||
], "Bow with power 5, infinity, flame, punch 2."),
|
||||
("sudo stack of each wood type", [
|
||||
"give {p} minecraft:oak_log 64",
|
||||
"give {p} minecraft:spruce_log 64",
|
||||
"give {p} minecraft:birch_log 64",
|
||||
"give {p} minecraft:jungle_log 64",
|
||||
"give {p} minecraft:acacia_log 64",
|
||||
"give {p} minecraft:dark_oak_log 64",
|
||||
"give {p} minecraft:cherry_log 64",
|
||||
"give {p} minecraft:mangrove_log 64",
|
||||
], "All 8 wood types, one stack each."),
|
||||
("sudo clear my inventory", ["clear {p}"], "Cleared all items."),
|
||||
("sudo tp me to 0 100 0", ["tp {p} 0 100 0"], "Teleported to coordinates."),
|
||||
("sudo gamemode creative", ["gamemode creative {p}"], "Set creative mode."),
|
||||
("sudo gamemode survival", ["gamemode survival {p}"], "Set survival mode."),
|
||||
("sudo kill all zombies", ["kill @e[type=minecraft:zombie]"], "Killed all zombies."),
|
||||
("sudo summon 5 cows", [
|
||||
"summon minecraft:cow ~ ~ ~1",
|
||||
"summon minecraft:cow ~ ~ ~2",
|
||||
"summon minecraft:cow ~ ~ ~3",
|
||||
"summon minecraft:cow ~1 ~ ~1",
|
||||
"summon minecraft:cow ~1 ~ ~2",
|
||||
], "Summoned 5 cows nearby."),
|
||||
("sudo give everyone a diamond", [
|
||||
"give @a minecraft:diamond 1",
|
||||
], "Gave all players a diamond."),
|
||||
("sudo set time to sunrise", ["time set 23000"], "Set to dawn (tick 23000)."),
|
||||
("sudo fill a 5x5 area with gold blocks under me", [
|
||||
"fill ~-2 ~-1 ~-2 ~2 ~-1 ~2 minecraft:gold_block",
|
||||
], "Filled 5x5 gold platform under player."),
|
||||
("sudo give me a trident with loyalty and channeling", [
|
||||
"give {p} minecraft:trident[enchantments={loyalty:3,channeling:1,impaling:5,unbreaking:3,mending:1}] 1",
|
||||
], "Trident with loyalty 3, channeling, impaling 5. Loyalty and riptide are mutually exclusive — used loyalty."),
|
||||
("sudo night vision forever", [
|
||||
"effect give {p} minecraft:night_vision 999999 0",
|
||||
], "Permanent night vision."),
|
||||
("sudo repair what I'm holding", [
|
||||
"give {p} minecraft:experience_bottle 64",
|
||||
], "Gave XP bottles — use with mending items to repair. Cannot directly repair via commands."),
|
||||
("sudo give me a mace", [
|
||||
"give {p} minecraft:mace[enchantments={density:5,wind_burst:3,unbreaking:3,mending:1}] 1",
|
||||
], "Mace with density 5 and wind burst 3. New 1.21 weapon."),
|
||||
("sudo spawn a warden", [
|
||||
"summon minecraft:warden ~ ~ ~5",
|
||||
], "Summoned warden 5 blocks away. Be careful — 500 HP, 2-hit kill."),
|
||||
("sudo give me all the music discs", [
|
||||
"give {p} minecraft:music_disc_13 1",
|
||||
"give {p} minecraft:music_disc_cat 1",
|
||||
"give {p} minecraft:music_disc_blocks 1",
|
||||
"give {p} minecraft:music_disc_chirp 1",
|
||||
"give {p} minecraft:music_disc_far 1",
|
||||
"give {p} minecraft:music_disc_mall 1",
|
||||
"give {p} minecraft:music_disc_mellohi 1",
|
||||
"give {p} minecraft:music_disc_stal 1",
|
||||
"give {p} minecraft:music_disc_strad 1",
|
||||
"give {p} minecraft:music_disc_ward 1",
|
||||
"give {p} minecraft:music_disc_pigstep 1",
|
||||
"give {p} minecraft:music_disc_otherside 1",
|
||||
], "All music discs."),
|
||||
("sudo potion of the turtle master", [
|
||||
"give {p} minecraft:potion[potion_contents={potion:\"minecraft:turtle_master\"}] 1",
|
||||
], "Turtle master potion — slowness 4 + resistance 3."),
|
||||
("sudo banner with a skull pattern", [
|
||||
"give {p} minecraft:white_banner[banner_patterns=[{pattern:\"minecraft:skull\",color:\"black\"}]] 1",
|
||||
], "White banner with black skull pattern using 1.21 syntax."),
|
||||
]
|
||||
|
||||
for prompt, cmds_tmpl, reasoning in COMMANDS:
|
||||
player = random.choice(PLAYERS)
|
||||
cmds = [c.replace("{p}", player) for c in cmds_tmpl]
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
all_ok = True
|
||||
for cmd in cmds:
|
||||
rcon_result = rcon.command(cmd)
|
||||
ok = not is_error(rcon_result)
|
||||
if not ok:
|
||||
all_ok = False
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": ok, "result": rcon_result[:300]}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
examples.append({
|
||||
"id": f"rcon-direct-{len(examples):03d}",
|
||||
"source": "rcon_validated",
|
||||
"type": "direct_command",
|
||||
"rcon_validated": True,
|
||||
"all_success": all_ok,
|
||||
"messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_memory_examples(rcon):
|
||||
"""Memory read/write examples."""
|
||||
examples = []
|
||||
|
||||
MEMORY_OPS = [
|
||||
("sudo remember this as home", "write", "home", "location", {"x": 100, "y": 64, "z": -200}, None,
|
||||
"Saved current location as 'home'."),
|
||||
("sudo save this spot as my base", "write", "base", "location", {"x": -500, "y": 72, "z": 300}, None,
|
||||
"Saved base location."),
|
||||
("sudo tp me home", "read", "home", None, None, "tp {p} 100 64 -200",
|
||||
"Read 'home' from memory. Teleporting."),
|
||||
("sudo take me to my base", "read", "base", None, None, "tp {p} -500 72 300",
|
||||
"Read 'base' from memory. Teleporting."),
|
||||
("sudo what do you remember about me?", "read", None, None, None, None,
|
||||
"Listed all memories for this player."),
|
||||
("sudo remember my favorite tool is a pickaxe", "write", "favorite_tool", "preference", "diamond pickaxe", None,
|
||||
"Saved tool preference."),
|
||||
("sudo remember Ace is my enemy", "write", "enemy_ace", "fact", "Ace13245 is an enemy", None,
|
||||
"Noted player relationship."),
|
||||
("sudo forget my base", "delete", "base", None, None, None,
|
||||
"Deleted 'base' memory."),
|
||||
("sudo save this as my mine", "write", "mine", "location", {"x": 30, "y": 11, "z": -80}, None,
|
||||
"Saved mining location."),
|
||||
("sudo tp me to my mine", "read", "mine", None, None, "tp {p} 30 11 -80",
|
||||
"Read 'mine' from memory. Teleporting to Y=11."),
|
||||
]
|
||||
|
||||
for prompt, action, key, mtype, value, cmd_tmpl, reasoning in MEMORY_OPS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
if action == "write":
|
||||
msgs.append(tool_call("memory.write", {"player": player, "type": mtype, "key": key, "value": value}))
|
||||
msgs.append(tool_result({"ok": True, "key": key}))
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": reasoning}
|
||||
elif action == "read":
|
||||
args = {"player": player}
|
||||
if key:
|
||||
args["key"] = key
|
||||
msgs.append(tool_call("memory.read", args))
|
||||
if key:
|
||||
mem_val = value or {"x": random.randint(-500,500), "y": random.randint(60,120), "z": random.randint(-500,500)}
|
||||
msgs.append(tool_result({"memories": [{"key": key, "type": mtype or "location", "value": mem_val}]}))
|
||||
else:
|
||||
msgs.append(tool_result({"memories": [
|
||||
{"key": "home", "type": "location", "value": {"x": 100, "y": 64, "z": -200}},
|
||||
{"key": "favorite_tool", "type": "preference", "value": "diamond pickaxe"},
|
||||
]}))
|
||||
|
||||
if cmd_tmpl:
|
||||
cmd = cmd_tmpl.replace("{p}", player)
|
||||
result = rcon.command(cmd)
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": not is_error(result), "result": result[:200]}))
|
||||
resp = {"risk_level": 3, "commands": [cmd], "reasoning": reasoning}
|
||||
else:
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": reasoning}
|
||||
elif action == "delete":
|
||||
msgs.append(tool_call("memory.read", {"player": player, "key": key}))
|
||||
msgs.append(tool_result({"memories": [{"key": key, "type": "location", "value": {"x": -500, "y": 72, "z": 300}}]}))
|
||||
resp = {"risk_level": 3, "commands": [], "reasoning": reasoning}
|
||||
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({
|
||||
"id": f"rcon-memory-{len(examples):03d}",
|
||||
"source": "rcon_validated",
|
||||
"type": f"memory_{action}",
|
||||
"messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_wiki_examples(rcon):
|
||||
"""Wiki lookup → command execution with real RCON results."""
|
||||
examples = []
|
||||
|
||||
WIKI = [
|
||||
("sudo best pickaxe enchantments", "pickaxe enchantments 1.21",
|
||||
"Pickaxe enchantments:\n- Efficiency V: faster mining\n- Fortune III: more drops from ores\n- Silk Touch: mine blocks directly\n- Unbreaking III: durability\n- Mending: XP repair\nFortune and Silk Touch are mutually exclusive.",
|
||||
["give {p} minecraft:netherite_pickaxe[enchantments={efficiency:5,fortune:3,unbreaking:3,mending:1}] 1"],
|
||||
"Max pickaxe with fortune. Fortune and silk touch are exclusive — chose fortune for ore farming."),
|
||||
("sudo what enchants for boots?", "boot enchantments 1.21",
|
||||
"Boot enchantments:\n- Protection IV or Blast/Fire/Projectile Protection IV\n- Feather Falling IV: reduces fall damage\n- Depth Strider III or Frost Walker II (exclusive)\n- Soul Speed III: faster on soul sand\n- Swift Sneak III: faster sneaking\n- Unbreaking III, Mending I",
|
||||
["give {p} minecraft:netherite_boots[enchantments={protection:4,feather_falling:4,depth_strider:3,soul_speed:3,unbreaking:3,mending:1}] 1"],
|
||||
"All compatible boot enchants. Depth strider over frost walker for general use."),
|
||||
("sudo how do I use the /place command?", "place command 1.21",
|
||||
"/place feature <feature> [pos]\n/place jigsaw <pool> <target> <max_depth> [pos]\n/place structure <structure> [pos]\n/place template <template> [pos] [rotation] [mirror]\n\nUseful for placing structures, trees, etc.",
|
||||
["place feature minecraft:oak ~ ~ ~5"],
|
||||
"Placed an oak tree feature 5 blocks away using /place."),
|
||||
("sudo what's the command for teams?", "team command minecraft",
|
||||
"Team commands:\n/team add <name> [display_name]\n/team join <team> [members]\n/team leave [members]\n/team modify <team> <option> <value>\nOptions: color, friendlyFire, seeFriendlyInvisibles, nametagVisibility, collisionRule, prefix, suffix",
|
||||
["team add red Red Team", "team modify red color red"],
|
||||
"Created 'Red Team' with red name color."),
|
||||
("sudo how to make colored text in chat?", "tellraw color formatting minecraft",
|
||||
"tellraw @a {\"text\":\"Hello\",\"color\":\"gold\",\"bold\":true}\nColors: black, dark_blue, dark_green, dark_aqua, dark_red, dark_purple, gold, gray, dark_gray, blue, green, aqua, red, light_purple, yellow, white\nFormatting: bold, italic, underlined, strikethrough, obfuscated",
|
||||
['tellraw @a {"text":"Welcome to the server!","color":"gold","bold":true}'],
|
||||
"Used tellraw with gold color and bold formatting."),
|
||||
]
|
||||
|
||||
for prompt, query, content, cmds_tmpl, reasoning in WIKI:
|
||||
player = random.choice(PLAYERS)
|
||||
cmds = [c.replace("{p}", player) for c in cmds_tmpl]
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
msgs.append(tool_call("minecraft.wiki_lookup", {"query": query}))
|
||||
msgs.append(tool_result({"content": content, "url": f"https://minecraft.wiki/w/{query.split()[0]}"}))
|
||||
|
||||
for cmd in cmds:
|
||||
result = rcon.command(cmd)
|
||||
msgs.append(tool_call("rcon.execute", {"command": cmd}))
|
||||
msgs.append(tool_result({"success": not is_error(result), "result": result[:300]}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
examples.append({
|
||||
"id": f"rcon-wiki-{len(examples):03d}",
|
||||
"source": "rcon_validated",
|
||||
"type": "wiki_lookup",
|
||||
"messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_error_correction_examples(rcon):
|
||||
"""Commands that fail, get corrected, and succeed — with real RCON errors."""
|
||||
examples = []
|
||||
|
||||
ERRORS = [
|
||||
("sudo give me a bed", "give {p} minecraft:bed 1", "give {p} minecraft:white_bed 1",
|
||||
"No item 'bed' — correct ID is 'white_bed' in 1.21."),
|
||||
("sudo give me cooked beef", "give {p} minecraft:steak 1", "give {p} minecraft:cooked_beef 1",
|
||||
"Item is 'cooked_beef', not 'steak'."),
|
||||
("sudo give me speed", "effect give {p} minecraft:speed", "effect give {p} minecraft:speed 300 1",
|
||||
"Effect needs duration and amplifier arguments."),
|
||||
("sudo give me a log", "give {p} minecraft:log 64", "give {p} minecraft:oak_log 64",
|
||||
"No item 'log' — must specify wood type: oak_log, spruce_log, etc."),
|
||||
("sudo fill with stone 10", "fill ~ ~ ~ ~10 ~10 ~10 minecraft:stone 10", "fill ~ ~ ~ ~10 ~10 ~10 minecraft:stone",
|
||||
"Fill doesn't take a trailing count number."),
|
||||
]
|
||||
|
||||
for prompt, wrong_cmd_tmpl, right_cmd_tmpl, reasoning in ERRORS:
|
||||
player = random.choice(PLAYERS)
|
||||
wrong_cmd = wrong_cmd_tmpl.replace("{p}", player)
|
||||
right_cmd = right_cmd_tmpl.replace("{p}", player)
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
# Wrong attempt
|
||||
wrong_result = rcon.command(wrong_cmd)
|
||||
msgs.append(tool_call("rcon.execute", {"command": wrong_cmd}))
|
||||
msgs.append(tool_result({"success": False, "result": wrong_result[:300]}))
|
||||
|
||||
# Corrected attempt
|
||||
right_result = rcon.command(right_cmd)
|
||||
msgs.append(tool_call("rcon.execute", {"command": right_cmd}))
|
||||
msgs.append(tool_result({"success": not is_error(right_result), "result": right_result[:300]}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": [right_cmd], "reasoning": f"First attempt failed: {wrong_result[:100]}. {reasoning}"}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
examples.append({
|
||||
"id": f"rcon-errfix-{len(examples):03d}",
|
||||
"source": "rcon_validated",
|
||||
"type": "error_correction",
|
||||
"messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def gen_chained_examples(rcon):
|
||||
"""Multi-tool chained examples with real RCON."""
|
||||
examples = []
|
||||
|
||||
CHAINS = [
|
||||
("sudo gear me up for the nether", [
|
||||
("rcon.execute", {"command": "give {p} minecraft:netherite_sword[enchantments={sharpness:5,fire_aspect:2,unbreaking:3,mending:1}] 1"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:netherite_pickaxe[enchantments={efficiency:5,fortune:3,unbreaking:3,mending:1}] 1"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:netherite_chestplate[enchantments={protection:4,unbreaking:3,mending:1}] 1"}),
|
||||
("rcon.execute", {"command": "effect give {p} minecraft:fire_resistance 6000 0"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:golden_apple 16"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:ender_pearl 16"}),
|
||||
], "Full nether loadout: netherite sword+pick, protection armor, fire resistance, golden apples, pearls."),
|
||||
("sudo prepare me for an end fight", [
|
||||
("rcon.execute", {"command": "give {p} minecraft:netherite_sword[enchantments={sharpness:5,unbreaking:3,mending:1}] 1"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:bow[enchantments={power:5,infinity:1,unbreaking:3}] 1"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:arrow 64"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:golden_apple 32"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:ender_pearl 16"}),
|
||||
("rcon.execute", {"command": "effect give {p} minecraft:slow_falling 600 0"}),
|
||||
("rcon.execute", {"command": "give {p} minecraft:cobblestone 128"}),
|
||||
], "End fight kit: weapons, slow falling for void safety, blocks for pillaring, pearls for dodging."),
|
||||
]
|
||||
|
||||
for prompt, tool_calls, reasoning in CHAINS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg("sudo"), user_msg(f"Player {player}: {prompt}")]
|
||||
|
||||
all_cmds = []
|
||||
for tool_name, args_tmpl in tool_calls:
|
||||
args = {}
|
||||
for k, v in args_tmpl.items():
|
||||
args[k] = v.replace("{p}", player) if isinstance(v, str) else v
|
||||
|
||||
if tool_name == "rcon.execute":
|
||||
cmd = args["command"]
|
||||
result = rcon.command(cmd)
|
||||
msgs.append(tool_call(tool_name, args))
|
||||
msgs.append(tool_result({"success": not is_error(result), "result": result[:300]}))
|
||||
all_cmds.append(cmd)
|
||||
else:
|
||||
msgs.append(tool_call(tool_name, args))
|
||||
msgs.append(tool_result({"ok": True}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": all_cmds, "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
|
||||
examples.append({
|
||||
"id": f"rcon-chain-{len(examples):03d}",
|
||||
"source": "rcon_validated",
|
||||
"type": "chained",
|
||||
"messages": msgs,
|
||||
})
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--rcon-host", default="192.168.0.244")
|
||||
parser.add_argument("--rcon-port", type=int, default=25577)
|
||||
parser.add_argument("--rcon-pass", default="REDACTED_RCON")
|
||||
args = parser.parse_args()
|
||||
|
||||
print(f"Connecting to RCON at {args.rcon_host}:{args.rcon_port}...")
|
||||
rcon = SimpleRCON(args.rcon_host, args.rcon_port, args.rcon_pass)
|
||||
print("Connected.\n")
|
||||
|
||||
all_examples = []
|
||||
|
||||
print("Generating script examples...")
|
||||
scripts = gen_script_examples(rcon)
|
||||
all_examples.extend(scripts)
|
||||
print(f" {len(scripts)} script examples")
|
||||
|
||||
print("Generating direct command examples...")
|
||||
direct = gen_direct_command_examples(rcon)
|
||||
all_examples.extend(direct)
|
||||
print(f" {len(direct)} direct command examples")
|
||||
|
||||
print("Generating memory examples...")
|
||||
memory = gen_memory_examples(rcon)
|
||||
all_examples.extend(memory)
|
||||
print(f" {len(memory)} memory examples")
|
||||
|
||||
print("Generating wiki examples...")
|
||||
wiki = gen_wiki_examples(rcon)
|
||||
all_examples.extend(wiki)
|
||||
print(f" {len(wiki)} wiki examples")
|
||||
|
||||
print("Generating error correction examples...")
|
||||
errors = gen_error_correction_examples(rcon)
|
||||
all_examples.extend(errors)
|
||||
print(f" {len(errors)} error correction examples")
|
||||
|
||||
print("Generating chained multi-tool examples...")
|
||||
chained = gen_chained_examples(rcon)
|
||||
all_examples.extend(chained)
|
||||
print(f" {len(chained)} chained examples")
|
||||
|
||||
# Stats
|
||||
success_count = sum(1 for e in all_examples if e.get("all_success", True))
|
||||
print(f"\nTotal: {len(all_examples)} examples")
|
||||
print(f" RCON validated: {sum(1 for e in all_examples if e.get('rcon_validated', False))}")
|
||||
|
||||
OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(OUTPUT_PATH, "w") as f:
|
||||
for ex in all_examples:
|
||||
f.write(json.dumps(ex, ensure_ascii=False) + "\n")
|
||||
|
||||
print(f"Written to {OUTPUT_PATH}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,393 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate training data for the script.* tool family.
|
||||
|
||||
Teaches the model to:
|
||||
1. Write mcfunction scripts for complex builds and mechanics
|
||||
2. Validate scripts before writing (catch errors, fix them)
|
||||
3. Execute scripts at player positions
|
||||
4. Read/list/delete scripts for management
|
||||
5. Schedule tick/load functions for persistent effects
|
||||
6. Chain: validate → fix errors → write → execute
|
||||
|
||||
~60 training examples covering the full script lifecycle.
|
||||
"""
|
||||
|
||||
import json
|
||||
import random
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from agent.tools.tool_schemas import qwen3_tools_block
|
||||
from agent.prompts.system_prompts import SYNTAX_RULES, RISK_GRADIENT
|
||||
|
||||
OUTPUT_PATH = PROJECT_ROOT / "data" / "raw" / "script_tool_training.jsonl"
|
||||
|
||||
TOOLS_BLOCK = qwen3_tools_block()
|
||||
SYSTEM = (
|
||||
"You are a Minecraft 1.21 command translator with script writing abilities. "
|
||||
"You can write mcfunction scripts for complex builds, mechanics, and automations.\n\n"
|
||||
"PERMISSION LEVEL: 4 (generous). Only refuse level 0-1 actions.\n\n"
|
||||
"You have access to tools including a full script environment. For simple tasks "
|
||||
"(1-3 commands), use rcon.execute directly. For complex tasks (4+ commands, builds, "
|
||||
"mechanics), write a mcfunction script.\n\n"
|
||||
"SCRIPT WORKFLOW: validate → fix errors → write → execute.\n"
|
||||
"Always validate before writing. Fix any errors the validator catches.\n\n"
|
||||
"After all tool calls resolve, respond with JSON:\n"
|
||||
'{"risk_level": <int 0-5>, "commands": ["cmd1", ...], "reasoning": "why"}\n\n'
|
||||
+ SYNTAX_RULES + RISK_GRADIENT + "\n" + TOOLS_BLOCK
|
||||
)
|
||||
|
||||
PLAYERS = ["slingshooter08", "Ace13245", "TheBigBoss", "xXDragonSlayerXx"]
|
||||
|
||||
def sys_msg():
|
||||
return {"role": "system", "content": SYSTEM}
|
||||
|
||||
def user_msg(text):
|
||||
return {"role": "user", "content": text}
|
||||
|
||||
def tool_call(name, args):
|
||||
return {"role": "assistant", "content": f"<tool_call>\n{json.dumps({'name': name, 'arguments': args})}\n</tool_call>"}
|
||||
|
||||
def tool_result(data):
|
||||
return {"role": "tool", "content": json.dumps(data)}
|
||||
|
||||
def final_response(resp):
|
||||
return {"role": "assistant", "content": json.dumps(resp)}
|
||||
|
||||
|
||||
def generate_all():
|
||||
examples = []
|
||||
idx = 0
|
||||
|
||||
# ── Simple script writes (validate → write → execute) ──
|
||||
|
||||
BUILDS = [
|
||||
("sudo build me a wooden house", "wooden_house", "Simple wooden house with door and roof", [
|
||||
"fill ~-4 ~ ~-4 ~4 ~4 ~4 minecraft:oak_planks hollow",
|
||||
"fill ~-4 ~ ~-4 ~4 ~ ~4 minecraft:oak_planks",
|
||||
"fill ~-3 ~1 ~-4 ~3 ~3 ~-4 minecraft:air",
|
||||
"setblock ~0 ~1 ~-4 minecraft:oak_door[facing=north,half=lower]",
|
||||
"setblock ~0 ~2 ~-4 minecraft:oak_door[facing=north,half=upper]",
|
||||
"fill ~-3 ~1 ~4 ~-3 ~2 ~4 minecraft:glass_pane",
|
||||
"fill ~3 ~1 ~4 ~3 ~2 ~4 minecraft:glass_pane",
|
||||
"setblock ~0 ~3 ~0 minecraft:lantern[hanging=true]",
|
||||
]),
|
||||
("sudo create a pvp arena", "pvp_arena", "PvP arena with walls and starting positions", [
|
||||
"fill ~-15 ~-1 ~-15 ~15 ~-1 ~15 minecraft:smooth_stone",
|
||||
"fill ~-15 ~ ~-15 ~15 ~5 ~-15 minecraft:stone_bricks",
|
||||
"fill ~-15 ~ ~15 ~15 ~5 ~15 minecraft:stone_bricks",
|
||||
"fill ~-15 ~ ~-15 ~-15 ~5 ~15 minecraft:stone_bricks",
|
||||
"fill ~15 ~ ~-15 ~15 ~5 ~15 minecraft:stone_bricks",
|
||||
"fill ~-14 ~ ~-14 ~14 ~4 ~14 minecraft:air",
|
||||
"setblock ~-10 ~ ~0 minecraft:red_concrete",
|
||||
"setblock ~10 ~ ~0 minecraft:blue_concrete",
|
||||
"fill ~-1 ~-1 ~-1 ~1 ~-1 ~1 minecraft:glowstone",
|
||||
]),
|
||||
("sudo make a nether portal room", "portal_room", "Decorated nether portal room", [
|
||||
"fill ~-5 ~ ~-5 ~5 ~6 ~5 minecraft:blackstone hollow",
|
||||
"fill ~-4 ~ ~-4 ~4 ~5 ~4 minecraft:air",
|
||||
"fill ~-1 ~1 ~0 ~1 ~5 ~0 minecraft:obsidian",
|
||||
"fill ~0 ~1 ~0 ~0 ~4 ~0 minecraft:air",
|
||||
"setblock ~0 ~1 ~0 minecraft:nether_portal[axis=x]",
|
||||
"setblock ~0 ~2 ~0 minecraft:nether_portal[axis=x]",
|
||||
"setblock ~0 ~3 ~0 minecraft:nether_portal[axis=x]",
|
||||
"fill ~-4 ~-1 ~-4 ~4 ~-1 ~4 minecraft:polished_blackstone_bricks",
|
||||
"setblock ~-3 ~1 ~-3 minecraft:soul_lantern",
|
||||
"setblock ~3 ~1 ~-3 minecraft:soul_lantern",
|
||||
"setblock ~-3 ~1 ~3 minecraft:soul_lantern",
|
||||
"setblock ~3 ~1 ~3 minecraft:soul_lantern",
|
||||
]),
|
||||
("sudo build a watchtower", "watchtower", "Tall watchtower with ladder access", [
|
||||
"fill ~-2 ~ ~-2 ~2 ~10 ~2 minecraft:cobblestone hollow",
|
||||
"fill ~-1 ~ ~-1 ~1 ~9 ~1 minecraft:air",
|
||||
"fill ~-2 ~10 ~-2 ~2 ~10 ~2 minecraft:oak_planks",
|
||||
"fill ~-2 ~11 ~-2 ~2 ~11 ~2 minecraft:oak_fence",
|
||||
"fill ~-1 ~11 ~-1 ~1 ~11 ~1 minecraft:air",
|
||||
"fill ~2 ~1 ~0 ~2 ~9 ~0 minecraft:ladder[facing=west]",
|
||||
"setblock ~0 ~12 ~0 minecraft:lantern",
|
||||
]),
|
||||
("sudo build a farm plot with water", "farm_plot", "9x9 farm with central water and tilled soil", [
|
||||
"fill ~-4 ~-1 ~-4 ~4 ~-1 ~4 minecraft:farmland",
|
||||
"setblock ~0 ~-1 ~0 minecraft:water",
|
||||
"fill ~-4 ~ ~-4 ~4 ~ ~4 minecraft:air",
|
||||
"fill ~-5 ~-1 ~-5 ~5 ~-1 ~-5 minecraft:oak_fence",
|
||||
"fill ~-5 ~-1 ~5 ~5 ~-1 ~5 minecraft:oak_fence",
|
||||
"fill ~-5 ~-1 ~-5 ~-5 ~-1 ~5 minecraft:oak_fence",
|
||||
"fill ~5 ~-1 ~-5 ~5 ~-1 ~5 minecraft:oak_fence",
|
||||
"setblock ~-5 ~-1 ~0 minecraft:oak_fence_gate[facing=east]",
|
||||
]),
|
||||
("sudo make a mob grinder platform", "mob_grinder", "Mob spawning platform with water channels", [
|
||||
"fill ~-8 ~ ~-8 ~8 ~ ~8 minecraft:cobblestone",
|
||||
"fill ~-7 ~1 ~-7 ~7 ~3 ~7 minecraft:air",
|
||||
"fill ~-8 ~1 ~-8 ~8 ~1 ~-8 minecraft:cobblestone",
|
||||
"fill ~-8 ~1 ~8 ~8 ~1 ~8 minecraft:cobblestone",
|
||||
"fill ~-8 ~1 ~-8 ~-8 ~1 ~8 minecraft:cobblestone",
|
||||
"fill ~8 ~1 ~-8 ~8 ~1 ~8 minecraft:cobblestone",
|
||||
"setblock ~0 ~-1 ~0 minecraft:air",
|
||||
"setblock ~0 ~-2 ~0 minecraft:hopper",
|
||||
"fill ~-8 ~ ~0 ~-1 ~ ~0 minecraft:water",
|
||||
"fill ~1 ~ ~0 ~8 ~ ~0 minecraft:water",
|
||||
]),
|
||||
("sudo create a trophy room", "trophy_room", "Display room with item frames and lighting", [
|
||||
"fill ~-6 ~ ~-6 ~6 ~4 ~6 minecraft:smooth_quartz hollow",
|
||||
"fill ~-5 ~ ~-5 ~5 ~3 ~5 minecraft:air",
|
||||
"fill ~-6 ~-1 ~-6 ~6 ~-1 ~6 minecraft:polished_deepslate",
|
||||
"fill ~-5 ~2 ~-6 ~5 ~2 ~-6 minecraft:item_frame[facing=south]",
|
||||
"fill ~-5 ~2 ~6 ~5 ~2 ~6 minecraft:item_frame[facing=north]",
|
||||
"setblock ~-4 ~3 ~0 minecraft:lantern[hanging=true]",
|
||||
"setblock ~0 ~3 ~0 minecraft:lantern[hanging=true]",
|
||||
"setblock ~4 ~3 ~0 minecraft:lantern[hanging=true]",
|
||||
]),
|
||||
]
|
||||
|
||||
for req, name, desc, cmds in BUILDS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
# Validate first
|
||||
msgs.append(tool_call("script.validate", {"commands": cmds}))
|
||||
msgs.append(tool_result({"valid": True, "total": len(cmds), "passed": len(cmds), "errors": []}))
|
||||
|
||||
# Write
|
||||
msgs.append(tool_call("script.write", {"name": name, "commands": cmds, "description": desc}))
|
||||
msgs.append(tool_result({"ok": True, "path": f"mortdecai:{name}", "lines": len(cmds)}))
|
||||
|
||||
# Execute at player
|
||||
msgs.append(tool_call("script.execute", {"name": name, "as_player": player}))
|
||||
msgs.append(tool_result({"ok": True, "result": f"Executed {len(cmds)} commands from function mortdecai:{name}"}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": [f"function mortdecai:{name}"], "reasoning": f"Wrote and executed '{name}' script ({len(cmds)} commands) at {player}'s position."}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({"id": f"script-build-{idx:03d}", "source": "script_training", "type": "script_write_execute", "messages": msgs})
|
||||
idx += 1
|
||||
|
||||
# ── Validate-fix-write cycle (model catches and fixes errors) ──
|
||||
|
||||
ERROR_SCENARIOS = [
|
||||
("sudo build a glass bridge", "glass_bridge", [
|
||||
"fill ~0 ~-1 ~0 ~0 ~-1 ~20 minecraft:glass",
|
||||
"fill ~-1 ~ ~0 ~-1 ~ ~20 minecraft:glass_pane",
|
||||
"fill ~1 ~ ~0 ~1 ~ ~20 minecraft:glass_paine", # typo
|
||||
], 2, "glass_paine", "Unknown block type: minecraft:glass_paine", [
|
||||
"fill ~0 ~-1 ~0 ~0 ~-1 ~20 minecraft:glass",
|
||||
"fill ~-1 ~ ~0 ~-1 ~ ~20 minecraft:glass_pane",
|
||||
"fill ~1 ~ ~0 ~1 ~ ~20 minecraft:glass_pane",
|
||||
]),
|
||||
("sudo create an enchanting setup", "enchanting_room", [
|
||||
"setblock ~0 ~ ~0 minecraft:enchanting_table",
|
||||
"fill ~-2 ~ ~-2 ~2 ~1 ~2 minecraft:bookshelf",
|
||||
"fill ~-1 ~ ~-1 ~1 ~1 ~1 minecraft:air",
|
||||
"setblock ~0 ~2 ~0 minecraft:lantern",
|
||||
"effect give @s minecraft:luck 600", # missing amplifier — not an error but let's say
|
||||
], 4, "minecraft:luck", "Unknown effect: minecraft:luck", [
|
||||
"setblock ~0 ~ ~0 minecraft:enchanting_table",
|
||||
"fill ~-2 ~ ~-2 ~2 ~1 ~2 minecraft:bookshelf",
|
||||
"fill ~-1 ~ ~-1 ~1 ~1 ~1 minecraft:air",
|
||||
"setblock ~0 ~2 ~0 minecraft:lantern",
|
||||
]),
|
||||
("sudo make a redstone door", "redstone_door", [
|
||||
"setblock ~2 ~1 ~0 minecraft:sticky_pistons[facing=west]", # wrong ID
|
||||
"setblock ~2 ~ ~0 minecraft:redstone_block",
|
||||
], 0, "minecraft:sticky_pistons", "Unknown block: minecraft:sticky_pistons", [
|
||||
"setblock ~2 ~1 ~0 minecraft:sticky_piston[facing=west]",
|
||||
"setblock ~2 ~ ~0 minecraft:redstone_block",
|
||||
]),
|
||||
]
|
||||
|
||||
for req, name, bad_cmds, err_line, err_cmd_fragment, err_msg, fixed_cmds in ERROR_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
# First validation fails
|
||||
msgs.append(tool_call("script.validate", {"commands": bad_cmds}))
|
||||
msgs.append(tool_result({
|
||||
"valid": False, "total": len(bad_cmds), "passed": len(bad_cmds) - 1,
|
||||
"errors": [{"line": err_line + 1, "command": bad_cmds[err_line], "error": err_msg}]
|
||||
}))
|
||||
|
||||
# Fix and re-validate
|
||||
msgs.append(tool_call("script.validate", {"commands": fixed_cmds}))
|
||||
msgs.append(tool_result({"valid": True, "total": len(fixed_cmds), "passed": len(fixed_cmds), "errors": []}))
|
||||
|
||||
# Write fixed version
|
||||
msgs.append(tool_call("script.write", {"name": name, "commands": fixed_cmds}))
|
||||
msgs.append(tool_result({"ok": True, "path": f"mortdecai:{name}", "lines": len(fixed_cmds)}))
|
||||
|
||||
# Execute
|
||||
msgs.append(tool_call("script.execute", {"name": name, "as_player": player}))
|
||||
msgs.append(tool_result({"ok": True, "result": "Executed commands"}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": [f"function mortdecai:{name}"], "reasoning": f"Validation caught an error. Fixed and wrote '{name}' script."}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({"id": f"script-fix-{idx:03d}", "source": "script_training", "type": "script_validate_fix", "messages": msgs})
|
||||
idx += 1
|
||||
|
||||
# ── Script management (list, read, delete) ──
|
||||
|
||||
MGMT_SCENARIOS = [
|
||||
("sudo show me all my scripts", "list", None),
|
||||
("sudo what's in the pvp_arena script?", "read", "pvp_arena"),
|
||||
("sudo delete the old test script", "delete", "test_script"),
|
||||
("sudo what scripts do I have?", "list", None),
|
||||
("sudo show me the watchtower script", "read", "watchtower"),
|
||||
("sudo remove the mob_grinder script", "delete", "mob_grinder"),
|
||||
]
|
||||
|
||||
for req, action, target in MGMT_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
if action == "list":
|
||||
msgs.append(tool_call("script.list", {}))
|
||||
msgs.append(tool_result({"scripts": [
|
||||
{"name": "wooden_house", "lines": 8, "scheduled": "none"},
|
||||
{"name": "pvp_arena", "lines": 9, "scheduled": "none"},
|
||||
{"name": "portal_room", "lines": 12, "scheduled": "none"},
|
||||
{"name": "ambient_particles", "lines": 3, "scheduled": "tick"},
|
||||
]}))
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": "Listed all scripts in the datapack."}
|
||||
elif action == "read":
|
||||
msgs.append(tool_call("script.read", {"name": target}))
|
||||
msgs.append(tool_result({"ok": True, "commands": ["fill ~-15 ~-1 ~-15 ~15 ~-1 ~15 minecraft:smooth_stone", "# ... more commands"], "lines": 9}))
|
||||
resp = {"risk_level": 4, "commands": [], "reasoning": f"Read the '{target}' script contents."}
|
||||
elif action == "delete":
|
||||
msgs.append(tool_call("script.delete", {"name": target}))
|
||||
msgs.append(tool_result({"ok": True}))
|
||||
resp = {"risk_level": 3, "commands": [], "reasoning": f"Deleted the '{target}' script."}
|
||||
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({"id": f"script-mgmt-{idx:03d}", "source": "script_training", "type": "script_management", "messages": msgs})
|
||||
idx += 1
|
||||
|
||||
# ── Tick/load scheduling ──
|
||||
|
||||
SCHEDULE_SCENARIOS = [
|
||||
("sudo make ambient particles around spawn forever", "ambient_particles", "tick", [
|
||||
"execute at @a run particle minecraft:cherry_leaves ~ ~2 ~ 3 1 3 0.02 5",
|
||||
]),
|
||||
("sudo set up scoreboards when the server starts", "init_scoreboards", "load", [
|
||||
"scoreboard objectives add deaths deathCount Deaths",
|
||||
"scoreboard objectives add kills playerKillCount Kills",
|
||||
"scoreboard objectives setdisplay sidebar kills",
|
||||
]),
|
||||
("sudo make it rain XP orbs on everyone every tick", "xp_rain", "tick", [
|
||||
"execute at @a run summon minecraft:experience_orb ~ ~3 ~ {Value:1}",
|
||||
]),
|
||||
("sudo initialize gamerules on server load", "init_gamerules", "load", [
|
||||
"gamerule keepInventory true",
|
||||
"gamerule doDaylightCycle true",
|
||||
"gamerule announceAdvancements true",
|
||||
"gamerule playersSleepingPercentage 50",
|
||||
]),
|
||||
]
|
||||
|
||||
for req, name, sched_type, cmds in SCHEDULE_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
# Validate
|
||||
msgs.append(tool_call("script.validate", {"commands": cmds}))
|
||||
msgs.append(tool_result({"valid": True, "total": len(cmds), "passed": len(cmds), "errors": []}))
|
||||
|
||||
# Write
|
||||
msgs.append(tool_call("script.write", {"name": name, "commands": cmds, "description": req}))
|
||||
msgs.append(tool_result({"ok": True, "path": f"mortdecai:{name}", "lines": len(cmds)}))
|
||||
|
||||
# Schedule
|
||||
msgs.append(tool_call("script.schedule", {"name": name, "type": sched_type}))
|
||||
msgs.append(tool_result({"ok": True}))
|
||||
|
||||
resp = {"risk_level": 3 if sched_type == "load" else 2, "commands": [f"function mortdecai:{name}"], "reasoning": f"Wrote '{name}' and scheduled it to run on {sched_type}."}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({"id": f"script-sched-{idx:03d}", "source": "script_training", "type": "script_schedule", "messages": msgs})
|
||||
idx += 1
|
||||
|
||||
# ── Direct rcon for simple tasks (model should NOT use scripts for 1-2 commands) ──
|
||||
|
||||
SIMPLE = [
|
||||
("sudo give me a diamond", ["give {p} minecraft:diamond 1"], "Simple give — no script needed."),
|
||||
("sudo set time to day", ["time set day"], "Single command, no script needed."),
|
||||
("sudo kill nearby zombies", ["kill @e[type=minecraft:zombie,distance=..30]"], "One command, direct execution is better."),
|
||||
]
|
||||
|
||||
for req, cmds, reasoning in SIMPLE:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {req}")]
|
||||
for cmd in cmds:
|
||||
resolved = cmd.replace("{p}", player)
|
||||
msgs.append(tool_call("rcon.execute", {"command": resolved}))
|
||||
msgs.append(tool_result({"success": True, "result": "Command executed successfully"}))
|
||||
resp = {"risk_level": 3, "commands": [c.replace("{p}", player) for c in cmds], "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({"id": f"script-simple-{idx:03d}", "source": "script_training", "type": "direct_rcon", "messages": msgs})
|
||||
idx += 1
|
||||
|
||||
# ── Edit cycle: read → modify → validate → write ──
|
||||
|
||||
EDIT_SCENARIOS = [
|
||||
("sudo add lighting to the pvp arena", "pvp_arena",
|
||||
["fill ~-15 ~-1 ~-15 ~15 ~-1 ~15 minecraft:smooth_stone", "fill ~-15 ~ ~-15 ~15 ~5 ~-15 minecraft:stone_bricks"],
|
||||
["fill ~-15 ~-1 ~-15 ~15 ~-1 ~15 minecraft:smooth_stone", "fill ~-15 ~ ~-15 ~15 ~5 ~-15 minecraft:stone_bricks",
|
||||
"setblock ~-10 ~4 ~0 minecraft:lantern[hanging=true]", "setblock ~0 ~4 ~0 minecraft:lantern[hanging=true]", "setblock ~10 ~4 ~0 minecraft:lantern[hanging=true]"],
|
||||
"Read existing arena script, added hanging lanterns for lighting."),
|
||||
("sudo add a roof to the wooden house", "wooden_house",
|
||||
["fill ~-4 ~ ~-4 ~4 ~4 ~4 minecraft:oak_planks hollow"],
|
||||
["fill ~-4 ~ ~-4 ~4 ~4 ~4 minecraft:oak_planks hollow",
|
||||
"fill ~-5 ~4 ~-5 ~5 ~4 ~5 minecraft:oak_slab", "fill ~-4 ~5 ~-4 ~4 ~5 ~4 minecraft:oak_slab"],
|
||||
"Read existing house script, added oak slab roof."),
|
||||
]
|
||||
|
||||
for req, name, old_cmds, new_cmds, reasoning in EDIT_SCENARIOS:
|
||||
player = random.choice(PLAYERS)
|
||||
msgs = [sys_msg(), user_msg(f"Player {player}: {req}")]
|
||||
|
||||
# Read existing
|
||||
msgs.append(tool_call("script.read", {"name": name}))
|
||||
msgs.append(tool_result({"ok": True, "commands": old_cmds, "lines": len(old_cmds)}))
|
||||
|
||||
# Validate new version
|
||||
msgs.append(tool_call("script.validate", {"commands": new_cmds}))
|
||||
msgs.append(tool_result({"valid": True, "total": len(new_cmds), "passed": len(new_cmds), "errors": []}))
|
||||
|
||||
# Overwrite
|
||||
msgs.append(tool_call("script.write", {"name": name, "commands": new_cmds}))
|
||||
msgs.append(tool_result({"ok": True, "path": f"mortdecai:{name}", "lines": len(new_cmds)}))
|
||||
|
||||
# Execute
|
||||
msgs.append(tool_call("script.execute", {"name": name, "as_player": player}))
|
||||
msgs.append(tool_result({"ok": True, "result": "Executed commands"}))
|
||||
|
||||
resp = {"risk_level": 3, "commands": [f"function mortdecai:{name}"], "reasoning": reasoning}
|
||||
msgs.append(final_response(resp))
|
||||
examples.append({"id": f"script-edit-{idx:03d}", "source": "script_training", "type": "script_edit", "messages": msgs})
|
||||
idx += 1
|
||||
|
||||
return examples
|
||||
|
||||
|
||||
def main():
|
||||
print("Generating script tool training data...")
|
||||
examples = generate_all()
|
||||
|
||||
counts = {}
|
||||
for ex in examples:
|
||||
t = ex["type"]
|
||||
counts[t] = counts.get(t, 0) + 1
|
||||
|
||||
print(f"\nGenerated {len(examples)} examples:")
|
||||
for t, c in sorted(counts.items()):
|
||||
print(f" {t}: {c}")
|
||||
|
||||
with open(OUTPUT_PATH, "w") as f:
|
||||
for ex in examples:
|
||||
f.write(json.dumps(ex, ensure_ascii=False) + "\n")
|
||||
|
||||
print(f"\nWritten to {OUTPUT_PATH}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Executable
+80
@@ -0,0 +1,80 @@
|
||||
#!/bin/bash
|
||||
# Training launcher — stops competing Ollama, trains, restarts Ollama.
|
||||
# Usage: ./run_training.sh [--resume]
|
||||
#
|
||||
# Prevents the OOM crash caused by ollama.service holding 6GB on the 3090 Ti.
|
||||
|
||||
set -e
|
||||
|
||||
VERSION="0.5.0"
|
||||
MODEL="Qwen/Qwen3.5-9B"
|
||||
OUTPUT="training/checkpoints/mortdecai-${VERSION}"
|
||||
LOG="training/train_run_${VERSION}.log"
|
||||
RESUME_FLAG=""
|
||||
|
||||
if [[ "$1" == "--resume" ]]; then
|
||||
RESUME_FLAG="--resume"
|
||||
echo ">> Resume mode: will pick up from latest checkpoint"
|
||||
fi
|
||||
|
||||
# Disable torch compile (causes "Argument list too long" on this system)
|
||||
export TORCH_COMPILE_DISABLE=1
|
||||
export TORCHDYNAMO_DISABLE=1
|
||||
|
||||
# Use the 3090 Ti (CUDA device ordering: GPU 1 in nvidia-smi = device 0 in CUDA when isolated)
|
||||
export CUDA_VISIBLE_DEVICES=0
|
||||
|
||||
echo "============================================"
|
||||
echo " Mortdecai ${VERSION} Training"
|
||||
echo "============================================"
|
||||
echo "Model: ${MODEL}"
|
||||
echo "Output: ${OUTPUT}"
|
||||
echo "Log: ${LOG}"
|
||||
echo ""
|
||||
|
||||
# Stop Ollama on 3090 Ti to free VRAM
|
||||
echo ">> Stopping ollama.service (3090 Ti)..."
|
||||
sudo systemctl stop ollama.service 2>/dev/null && echo " Stopped." || echo " Already stopped or not found."
|
||||
sleep 2
|
||||
|
||||
# Verify VRAM is free
|
||||
echo ">> GPU status:"
|
||||
nvidia-smi --id=1 --query-gpu=name,memory.used,memory.free --format=csv,noheader
|
||||
echo ""
|
||||
|
||||
# Run training
|
||||
echo ">> Starting training at $(date)"
|
||||
cd "$(dirname "$0")/../.."
|
||||
|
||||
python3 training/scripts/train_lora.py \
|
||||
--model "${MODEL}" \
|
||||
--output "${OUTPUT}" \
|
||||
--lr 1e-4 \
|
||||
--epochs 1 \
|
||||
--batch-size 2 \
|
||||
--grad-accum 4 \
|
||||
--max-seq-len 2048 \
|
||||
--save-steps 50 \
|
||||
${RESUME_FLAG} \
|
||||
2>&1 | tee "${LOG}"
|
||||
|
||||
TRAIN_EXIT=$?
|
||||
|
||||
echo ""
|
||||
echo ">> Training finished at $(date) (exit code: ${TRAIN_EXIT})"
|
||||
|
||||
# Restart Ollama
|
||||
echo ">> Restarting ollama.service..."
|
||||
sudo systemctl start ollama.service 2>/dev/null && echo " Started." || echo " Failed to start."
|
||||
|
||||
if [ $TRAIN_EXIT -eq 0 ]; then
|
||||
echo ""
|
||||
echo "============================================"
|
||||
echo " Training complete! Next steps:"
|
||||
echo " 1. Export GGUF: python3 -m unsloth.save --model ${OUTPUT} --output_type gguf"
|
||||
echo " 2. Create Ollama model: ollama create mortdecai:${VERSION} -f Modelfile"
|
||||
echo " 3. Run bake-off: python3 training/scripts/bakeoff.py"
|
||||
echo "============================================"
|
||||
fi
|
||||
|
||||
exit $TRAIN_EXIT
|
||||
@@ -0,0 +1,414 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Tool-focused self-play — exercises all 14 tools on a live dev server.
|
||||
|
||||
Unlike regular self-play (which tests command generation), this script
|
||||
specifically generates prompts that require tool use: script writing,
|
||||
memory operations, entity scanning, wiki lookups, and chained multi-tool
|
||||
flows. Runs on the dev server via RCON.
|
||||
|
||||
The model responds, its tool calls get executed for real, and the full
|
||||
interaction (prompt + tool calls + results + final response) gets logged
|
||||
as training data.
|
||||
|
||||
Usage:
|
||||
python3 tool_self_play.py --ollama-url http://192.168.0.179:11434 \\
|
||||
--rcon-host 192.168.0.112 --rcon-port 25578 --rounds 30
|
||||
|
||||
# Or via the scheduler preset
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
import requests
|
||||
from agent.tools.persistent_rcon import get_rcon
|
||||
|
||||
OUTPUT_DIR = PROJECT_ROOT / "data" / "raw" / "tool_selfplay"
|
||||
|
||||
# ── Prompt categories that exercise specific tools ─────────────────────────
|
||||
|
||||
PROMPTS = {
|
||||
"script_build": [
|
||||
"sudo build me a small cobblestone house with a door and windows",
|
||||
"sudo create a fighting arena with red and blue corners",
|
||||
"sudo make a nether portal room with soul lanterns",
|
||||
"sudo build a watchtower 15 blocks tall with a ladder",
|
||||
"sudo create a 9x9 wheat farm with water in the center",
|
||||
"sudo build an enchanting setup with bookshelves",
|
||||
"sudo make a mob grinder platform with water channels",
|
||||
"sudo create a trophy room with item frames",
|
||||
"sudo build a bridge 30 blocks long over this ravine",
|
||||
"sudo make a lighthouse with a glowstone top",
|
||||
"sudo create a hedge maze using oak leaves",
|
||||
"sudo build a dock with oak wood extending into the water",
|
||||
"sudo make an underground bunker with iron doors",
|
||||
"sudo create a garden with flowers and paths",
|
||||
"sudo build a market stall with a counter and signs",
|
||||
],
|
||||
"script_schedule": [
|
||||
"sudo make cherry leaf particles fall around spawn forever",
|
||||
"sudo set up a scoreboard that tracks deaths on server load",
|
||||
"sudo make ambient campfire smoke particles at spawn every tick",
|
||||
"sudo create a function that heals everyone every 5 minutes",
|
||||
"sudo make it always rain XP orbs at spawn",
|
||||
],
|
||||
"script_manage": [
|
||||
"sudo show me all scripts",
|
||||
"sudo what scripts are running on tick?",
|
||||
"sudo delete the test script",
|
||||
"sudo read me the arena script",
|
||||
"sudo what did I build last?",
|
||||
],
|
||||
"memory_write": [
|
||||
"sudo remember this as my home",
|
||||
"sudo save this location as my base",
|
||||
"sudo remember my nether portal is here",
|
||||
"sudo my favorite item is a diamond pickaxe, remember that",
|
||||
"sudo save this as my farm",
|
||||
"sudo remember that Ace13245 is my friend",
|
||||
"sudo mark this spot as the village center",
|
||||
"sudo save this as my fishing spot",
|
||||
],
|
||||
"memory_read": [
|
||||
"sudo tp me home",
|
||||
"sudo take me to my base",
|
||||
"sudo where's my nether portal?",
|
||||
"sudo what do you know about me?",
|
||||
"sudo tp me to my farm",
|
||||
"sudo where was I building?",
|
||||
"sudo do I have any saved locations?",
|
||||
],
|
||||
"nearby_entities": [
|
||||
"sudo what mobs are near me?",
|
||||
"sudo kill all the zombies around me",
|
||||
"sudo how many animals are nearby?",
|
||||
"sudo clear hostile mobs in a 50 block radius",
|
||||
"sudo are there any creepers close to me?",
|
||||
"sudo kill the nearest skeleton",
|
||||
"sudo count everything within 30 blocks",
|
||||
"sudo protect me from nearby hostiles",
|
||||
],
|
||||
"wiki_lookup": [
|
||||
"sudo what enchantments can go on a mace?",
|
||||
"sudo how do I craft a lodestone?",
|
||||
"sudo what food gives the best saturation?",
|
||||
"sudo what are the new 1.21 armor trim patterns?",
|
||||
"sudo what's the difference between smite and sharpness?",
|
||||
"sudo how does fortune work on ores?",
|
||||
"sudo what are all the copper variants?",
|
||||
"sudo how do trial spawners work?",
|
||||
],
|
||||
"player_info": [
|
||||
"sudo build a wall around me",
|
||||
"sudo teleport me 50 blocks up",
|
||||
"sudo place torches around me",
|
||||
"sudo create a beacon at my location",
|
||||
"sudo surround me with glass",
|
||||
"sudo set my spawn here",
|
||||
"sudo light up this cave around me",
|
||||
],
|
||||
"server_state": [
|
||||
"sudo if it's night, make it day",
|
||||
"sudo give everyone online a golden apple",
|
||||
"sudo how many people are playing right now?",
|
||||
"sudo announce the current time and weather",
|
||||
"sudo clear the weather if it's raining",
|
||||
],
|
||||
"chained": [
|
||||
"sudo save this location as home, then build a marker here",
|
||||
"sudo check what's near me and kill all hostiles, then give me resistance",
|
||||
"sudo look up the best sword enchantments and give me one",
|
||||
"sudo tp me home and heal me",
|
||||
"sudo build an arena and save it as a script I can rerun",
|
||||
"sudo check my health, if low heal me and give me food",
|
||||
"sudo what scripts do I have? run the arena one at my position",
|
||||
"sudo remember this spot, scan for mobs, kill hostiles, build a fort",
|
||||
],
|
||||
# ── Plugin categories ──
|
||||
"worldguard": [
|
||||
"sudo protect this area as my base",
|
||||
"sudo make a no-pvp zone around spawn",
|
||||
"sudo prevent mob spawning in the village",
|
||||
"sudo add Ace13245 as a member of my region",
|
||||
"sudo block entry for non-members in the vault",
|
||||
"sudo allow TNT in the arena region",
|
||||
"sudo set a greeting message for my base region",
|
||||
"sudo list all protected regions",
|
||||
"sudo prevent creeper explosions globally",
|
||||
"sudo create a healing zone at spawn",
|
||||
"sudo remove the old-test region",
|
||||
"sudo make a safe zone with no fire spread",
|
||||
],
|
||||
"coreprotect": [
|
||||
"sudo check who broke blocks near me",
|
||||
"sudo rollback griefing from the last hour",
|
||||
"sudo rollback what TheBigBoss did recently",
|
||||
"sudo who placed blocks around here today?",
|
||||
"sudo undo TNT damage from the last 2 hours",
|
||||
"sudo rollback all container theft recently",
|
||||
"sudo restore what was rolled back",
|
||||
"sudo check CoreProtect status",
|
||||
"sudo rollback fire damage near spawn",
|
||||
"sudo lookup what Ace13245 did in the last day",
|
||||
],
|
||||
"essentialsx": [
|
||||
"sudo set my home here",
|
||||
"sudo tp me to my home",
|
||||
"sudo create a warp called arena",
|
||||
"sudo tp me to the arena warp",
|
||||
"sudo give Ace 1000 coins",
|
||||
"sudo check my balance",
|
||||
"sudo heal me",
|
||||
"sudo feed me",
|
||||
"sudo repair what I'm holding",
|
||||
"sudo set my nickname to DragonLord",
|
||||
"sudo give me god mode",
|
||||
"sudo toggle fly for me",
|
||||
"sudo broadcast a server message",
|
||||
"sudo set spawn point here",
|
||||
"sudo check when Ace was last online",
|
||||
],
|
||||
"luckperms": [
|
||||
"sudo give me permission to fly",
|
||||
"sudo create a VIP group",
|
||||
"sudo add Ace to the VIP group",
|
||||
"sudo give VIP access to fly and heal",
|
||||
"sudo give me temporary VIP for 1 day",
|
||||
"sudo set VIP chat prefix to gold",
|
||||
"sudo create a builder group with WorldEdit",
|
||||
"sudo list all permission groups",
|
||||
"sudo check what permissions I have",
|
||||
"sudo remove TheBigBoss from VIP",
|
||||
],
|
||||
"fawe": [
|
||||
"sudo make a glass sphere 10 blocks wide",
|
||||
"sudo hollow sphere of stone",
|
||||
"sudo cylinder of quartz 5 wide 10 tall",
|
||||
"sudo replace all stone with deepslate in my selection",
|
||||
"sudo smooth the terrain around here",
|
||||
"sudo drain all water within 20 blocks",
|
||||
"sudo build a sandstone pyramid 10 tall",
|
||||
"sudo hollow out the selected area",
|
||||
"sudo make walls around my selection with stone bricks",
|
||||
"sudo fill with a checkerboard pattern",
|
||||
"sudo stack my selection 5 times north",
|
||||
"sudo undo my last WorldEdit action",
|
||||
],
|
||||
"plugin_combined": [
|
||||
"sudo create a protected pvp arena with WorldEdit and WorldGuard",
|
||||
"sudo rollback Ace's griefing and revoke his builder perms",
|
||||
"sudo set up a VIP lounge — build it, protect it, make a warp",
|
||||
"sudo give TheBigBoss a reward: money, items, and temp VIP",
|
||||
"sudo prepare the server for an event: announce, set arena flags, heal everyone",
|
||||
"pray someone destroyed my house, please restore it",
|
||||
"pray protect my village from monsters",
|
||||
"pray smite TheBigBoss for griefing",
|
||||
"pray make me a temple worthy of your glory",
|
||||
],
|
||||
}
|
||||
|
||||
PLAYERS = ["slingshooter08", "Ace13245", "TheBigBoss", "xXDragonSlayerXx"]
|
||||
|
||||
|
||||
def query_model(prompt, player, ollama_url, model, rcon):
|
||||
"""Send a prompt to the model and capture the full interaction."""
|
||||
system = (
|
||||
"You are a Minecraft 1.21 command translator for a Paper server.\n"
|
||||
"Plugins: FastAsyncWorldEdit, WorldGuard, CoreProtect, EssentialsX, Vault, LuckPerms.\n"
|
||||
"Tools: rcon.execute, minecraft.wiki_lookup, world.player_info, "
|
||||
"world.server_state, world.nearby_entities, memory.read, memory.write, "
|
||||
"script.write, script.validate, script.execute, script.read, script.list, "
|
||||
"script.delete, script.schedule.\n\n"
|
||||
"Plugin commands: //set, //sphere, //cyl (FAWE), /rg define/flag (WorldGuard), "
|
||||
"/co rollback/inspect (CoreProtect), /home, /warp, /eco (EssentialsX), "
|
||||
"/lp user/group (LuckPerms).\n\n"
|
||||
"For complex builds (4+ commands), write a mcfunction script. "
|
||||
"For simple tasks, use rcon.execute directly.\n\n"
|
||||
"Return JSON: {\"commands\": [...], \"reasoning\": \"...\", \"message\": \"...\"}\n"
|
||||
"Use /no_think mode."
|
||||
)
|
||||
|
||||
try:
|
||||
r = requests.post(f"{ollama_url}/api/chat", json={
|
||||
"model": model,
|
||||
"messages": [
|
||||
{"role": "system", "content": "/no_think\n" + system},
|
||||
{"role": "user", "content": f"Player {player}: {prompt}"},
|
||||
],
|
||||
"stream": False, "format": "json",
|
||||
"options": {"temperature": 0.4, "num_predict": 800},
|
||||
}, timeout=120)
|
||||
|
||||
content = r.json()["message"]["content"]
|
||||
content = re.sub(r'<think>[\s\S]*?</think>\s*', '', content)
|
||||
parsed = json.loads(content)
|
||||
return parsed
|
||||
except Exception as e:
|
||||
return {"error": str(e), "raw": content if 'content' in dir() else ""}
|
||||
|
||||
|
||||
def validate_commands(commands, rcon):
|
||||
"""Run commands through RCON and capture results."""
|
||||
results = []
|
||||
for cmd in commands[:12]:
|
||||
if not isinstance(cmd, str) or not cmd.strip():
|
||||
continue
|
||||
try:
|
||||
result = rcon.command(cmd)
|
||||
is_error = any(e in result for e in ("<--[HERE]", "Unknown", "Incorrect", "Expected"))
|
||||
results.append({"cmd": cmd, "result": result[:200], "ok": not is_error})
|
||||
except Exception as e:
|
||||
results.append({"cmd": cmd, "result": str(e), "ok": False})
|
||||
return results
|
||||
|
||||
|
||||
def run_round(category, ollama_url, model, rcon, player):
|
||||
"""Run one self-play round for a specific tool category."""
|
||||
prompt = random.choice(PROMPTS[category])
|
||||
|
||||
print(f" [{category:18s}] {prompt[:60]}")
|
||||
start = time.time()
|
||||
|
||||
response = query_model(prompt, player, ollama_url, model, rcon)
|
||||
elapsed = time.time() - start
|
||||
|
||||
if "error" in response:
|
||||
print(f" ERROR: {response['error'][:80]}")
|
||||
return None
|
||||
|
||||
commands = response.get("commands", [])
|
||||
message = response.get("message", "")
|
||||
reasoning = response.get("reasoning", "")
|
||||
|
||||
# Validate commands via RCON
|
||||
rcon_results = []
|
||||
if commands and all(isinstance(c, str) for c in commands):
|
||||
rcon_results = validate_commands(commands, rcon)
|
||||
success = all(r["ok"] for r in rcon_results)
|
||||
else:
|
||||
success = False
|
||||
|
||||
ok_count = sum(1 for r in rcon_results if r["ok"])
|
||||
fail_count = sum(1 for r in rcon_results if not r["ok"])
|
||||
status = "OK" if success else f"PARTIAL ({ok_count}/{ok_count+fail_count})" if ok_count > 0 else "FAIL"
|
||||
print(f" → {len(commands)} cmds, {status}, {elapsed:.1f}s")
|
||||
|
||||
# Build training example
|
||||
example = {
|
||||
"id": f"tool-selfplay-{int(time.time())}-{random.randint(0,9999):04d}",
|
||||
"source": "tool_self_play",
|
||||
"category": category,
|
||||
"input": {
|
||||
"user_message": prompt,
|
||||
"server_context": {
|
||||
"server_type": "paper",
|
||||
"version": "1.21.x",
|
||||
"online_players": [player],
|
||||
},
|
||||
},
|
||||
"output": {
|
||||
"commands": commands,
|
||||
"message": message,
|
||||
"reasoning": reasoning,
|
||||
},
|
||||
"metadata": {
|
||||
"rcon_results": rcon_results,
|
||||
"all_success": success,
|
||||
"elapsed_seconds": round(elapsed, 2),
|
||||
"model": model,
|
||||
"tool_category": category,
|
||||
},
|
||||
}
|
||||
|
||||
return example
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Tool-focused self-play")
|
||||
parser.add_argument("--ollama-url", default="http://192.168.0.179:11434")
|
||||
parser.add_argument("--model", default="mortdecai:0.4.0")
|
||||
parser.add_argument("--rcon-host", default="192.168.0.112")
|
||||
parser.add_argument("--rcon-port", type=int, default=25578)
|
||||
parser.add_argument("--rcon-pass", default="REDACTED_RCON")
|
||||
parser.add_argument("--rounds", type=int, default=30, help="Rounds per category")
|
||||
parser.add_argument("--categories", default="all", help="Comma-separated categories or 'all'")
|
||||
parser.add_argument("--output", default="")
|
||||
args = parser.parse_args()
|
||||
|
||||
OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
|
||||
output_path = args.output or str(OUTPUT_DIR / f"tool_selfplay_{int(time.time())}.jsonl")
|
||||
|
||||
rcon = get_rcon(args.rcon_host, args.rcon_port, args.rcon_pass)
|
||||
|
||||
if args.categories == "all":
|
||||
categories = list(PROMPTS.keys())
|
||||
else:
|
||||
categories = [c.strip() for c in args.categories.split(",")]
|
||||
|
||||
print(f"Tool Self-Play")
|
||||
print(f" Model: {args.model} on {args.ollama_url}")
|
||||
print(f" RCON: {args.rcon_host}:{args.rcon_port}")
|
||||
print(f" Categories: {', '.join(categories)}")
|
||||
print(f" Rounds per category: {args.rounds}")
|
||||
print(f" Output: {output_path}")
|
||||
print()
|
||||
|
||||
stats = {"total": 0, "success": 0, "partial": 0, "fail": 0, "error": 0}
|
||||
examples = []
|
||||
|
||||
for round_num in range(args.rounds):
|
||||
print(f"\n── Round {round_num + 1}/{args.rounds} ──")
|
||||
random.shuffle(categories)
|
||||
|
||||
for cat in categories:
|
||||
player = random.choice(PLAYERS)
|
||||
example = run_round(cat, args.ollama_url, args.model, rcon, player)
|
||||
|
||||
stats["total"] += 1
|
||||
if example is None:
|
||||
stats["error"] += 1
|
||||
continue
|
||||
|
||||
if example["metadata"]["all_success"]:
|
||||
stats["success"] += 1
|
||||
elif any(r["ok"] for r in example["metadata"].get("rcon_results", [])):
|
||||
stats["partial"] += 1
|
||||
else:
|
||||
stats["fail"] += 1
|
||||
|
||||
examples.append(example)
|
||||
|
||||
# Write incrementally
|
||||
with open(output_path, "a") as f:
|
||||
f.write(json.dumps(example, ensure_ascii=False) + "\n")
|
||||
|
||||
time.sleep(0.3)
|
||||
|
||||
# Progress report
|
||||
if (round_num + 1) % 5 == 0:
|
||||
rate = stats["success"] / max(stats["total"], 1) * 100
|
||||
print(f"\n Progress: {stats['total']} total, {rate:.0f}% success, "
|
||||
f"{stats['partial']} partial, {stats['fail']} fail, {stats['error']} error")
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"Tool Self-Play Complete")
|
||||
print(f" Total: {stats['total']}")
|
||||
print(f" Success: {stats['success']} ({stats['success']/max(stats['total'],1)*100:.0f}%)")
|
||||
print(f" Partial: {stats['partial']}")
|
||||
print(f" Fail: {stats['fail']}")
|
||||
print(f" Error: {stats['error']}")
|
||||
print(f" Output: {output_path} ({len(examples)} examples)")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -157,6 +157,8 @@ def main():
|
||||
parser.add_argument("--grad-accum", type=int, default=4, help="Gradient accumulation steps")
|
||||
parser.add_argument("--max-seq-len", type=int, default=2048, help="Max sequence length")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Load model and dataset but don't train")
|
||||
parser.add_argument("--save-steps", type=int, default=50, help="Save checkpoint every N steps")
|
||||
parser.add_argument("--resume", action="store_true", help="Resume from latest checkpoint if available")
|
||||
args = parser.parse_args()
|
||||
|
||||
# Auto-detect paths
|
||||
@@ -258,13 +260,25 @@ def main():
|
||||
weight_decay=0.01,
|
||||
bf16=True,
|
||||
logging_steps=1,
|
||||
save_strategy="epoch",
|
||||
save_strategy="steps",
|
||||
save_steps=args.save_steps,
|
||||
save_total_limit=3,
|
||||
seed=42,
|
||||
max_seq_length=args.max_seq_len,
|
||||
dataset_text_field="text",
|
||||
packing=True,
|
||||
)
|
||||
|
||||
# Check for resume checkpoint
|
||||
resume_ckpt = None
|
||||
if args.resume:
|
||||
ckpt_dir = Path(args.output)
|
||||
if ckpt_dir.exists():
|
||||
checkpoints = sorted(ckpt_dir.glob("checkpoint-*"), key=lambda p: int(p.name.split("-")[-1]))
|
||||
if checkpoints:
|
||||
resume_ckpt = str(checkpoints[-1])
|
||||
print(f" Resuming from: {resume_ckpt}")
|
||||
|
||||
# Train
|
||||
print(f"\nStarting training ({args.epochs} epochs, {len(train_data)} examples)...")
|
||||
trainer = SFTTrainer(
|
||||
@@ -274,7 +288,7 @@ def main():
|
||||
args=training_args,
|
||||
)
|
||||
|
||||
trainer.train()
|
||||
trainer.train(resume_from_checkpoint=resume_ckpt)
|
||||
|
||||
# Save adapter
|
||||
print(f"\nSaving LoRA adapter to {args.output}...")
|
||||
|
||||
Reference in New Issue
Block a user