grand-exchange-live: protocol layer, taskset, config, widened reference gate
The stepped engine becomes a runnable taskset. protocol.py is both the render/parse boundary and the security boundary: TurnView carries the live Market, so view.market.items[i].prices is the whole held-out series and a foresight policy reading it earned +9.4% on the oracle. The renderer emits only observed ticks, the trace carries plain scalars, and a sentinel scan of every rendered turn fails if either reopens. House rule 1 had no other enforcement. Replies are a delta sheet and parsing never raises — NaN, Infinity, 1e309 and 20k-deep nesting all resolve to a hold, because the one-shot form has already shown what a real model sends when it gives up. LiveExchangeEnv.run drives the engine host-side with the harness left null. Two things learned the hard way and worth keeping: a terminated Segment mid-window holds the remaining looks instead of raising, and rewards are recorded INSIDE the interaction, before close. Recording after close writes the traces correctly and leaves every eval.log line reading reward=0.000 — the canonical verifiers reference does it after the block; do not copy it there. The reference-family gate is widened from four named rungs to the whole 8x8 (requote_band, idle_share) family: no member may out-earn the shipped reference by more than 1.02x, and any that does must still score >= 0.90. That is the check that caught the first draft's fake 0.152 gap, now shipped rather than remembered. Also guards `clean` on the reference being profitable, here and in the one-shot form. Against a reference that lost money the bar is negative, so doing nothing cleared it and inaction collected a quarter of the reward. Unreachable while viable_market admits only profitable references; one relaxed filter from reachable, and exactly the floor house rule 3 forbids. Probe values unchanged. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Opus 5
@@ -0,0 +1,224 @@
|
||||
"""The taskset and the env: the loop, the seat, and what reaches the trace.
|
||||
|
||||
Everything else in this directory runs with nothing installed. This file needs `verifiers`,
|
||||
so it skips when it is absent — `uv sync --project environments/grand_exchange_live` first,
|
||||
exactly as the README's release gate does.
|
||||
|
||||
The env is driven against a stub agent rather than a model. What is being tested is the
|
||||
control flow that only exists here: a synchronous engine walked through an asynchronous
|
||||
interaction, a prompted task whose first turn must be BARE, a `terminated` segment arriving
|
||||
mid-window, and the rule that `TurnView.market` never reaches the trace.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import sys
|
||||
import types
|
||||
import unittest
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent))
|
||||
import context # noqa: E402 - resolves the package before anything imports it
|
||||
|
||||
try:
|
||||
import verifiers.v1 as vf # noqa: F401
|
||||
except ImportError: # pragma: no cover - the no-dependency path
|
||||
vf = None
|
||||
|
||||
from grand_exchange_live.live import HORIZON, TURNS # noqa: E402
|
||||
from grand_exchange_live.market import build_market # noqa: E402
|
||||
from grand_exchange_live.protocol import opening # noqa: E402
|
||||
|
||||
PRICE_SENTINEL = 9_000_000
|
||||
|
||||
|
||||
@dataclass
|
||||
class StubTrace:
|
||||
rewards: dict = field(default_factory=dict)
|
||||
metrics: dict = field(default_factory=dict)
|
||||
info: dict = field(default_factory=dict)
|
||||
|
||||
def record_reward(self, name, value, weight=1.0):
|
||||
self.rewards[name] = (float(value), float(weight))
|
||||
|
||||
def record_metrics(self, values):
|
||||
self.metrics.update({k: float(v) for k, v in values.items()})
|
||||
|
||||
|
||||
@dataclass
|
||||
class StubSegment:
|
||||
last_reply: str = ""
|
||||
terminated: bool = False
|
||||
|
||||
|
||||
class StubInteraction:
|
||||
"""One rollout, scripted. Records what each turn was asked with."""
|
||||
|
||||
def __init__(self, replies, terminate_at=None):
|
||||
self.replies = replies
|
||||
self.terminate_at = terminate_at
|
||||
self.asked: list = []
|
||||
self.trace = StubTrace()
|
||||
|
||||
async def turn(self, message=None):
|
||||
self.asked.append(message)
|
||||
n = len(self.asked)
|
||||
if self.terminate_at is not None and n >= self.terminate_at:
|
||||
return StubSegment(terminated=True)
|
||||
return StubSegment(last_reply=self.replies[(n - 1) % len(self.replies)])
|
||||
|
||||
async def __aenter__(self):
|
||||
return self
|
||||
|
||||
async def __aexit__(self, *exc):
|
||||
return False
|
||||
|
||||
|
||||
class StubAgent:
|
||||
def __init__(self, interaction):
|
||||
self._interaction = interaction
|
||||
|
||||
def interaction(self, task):
|
||||
return self._interaction
|
||||
|
||||
|
||||
class StubAgents:
|
||||
def __init__(self, interaction):
|
||||
self.agent = StubAgent(interaction)
|
||||
|
||||
|
||||
HOLD = '```json\n{"orders": []}\n```'
|
||||
|
||||
|
||||
@unittest.skipIf(vf is None, "verifiers is not installed")
|
||||
class TasksetTests(unittest.TestCase):
|
||||
def taskset(self, num_tasks=4):
|
||||
from grand_exchange_live.taskset import LiveExchangeConfig, LiveExchangeTaskset
|
||||
|
||||
return LiveExchangeTaskset(
|
||||
LiveExchangeConfig(id="grand-exchange-live", num_tasks=num_tasks)
|
||||
)
|
||||
|
||||
def test_the_seat_is_named_agent(self) -> None:
|
||||
"""A wrong name parses fine and silently leaves the seat empty, so it is asserted
|
||||
rather than read off the file."""
|
||||
from grand_exchange_live.taskset import LiveExchangeEnvConfig
|
||||
|
||||
self.assertIn("agent", LiveExchangeEnvConfig.model_fields)
|
||||
|
||||
def test_tasks_carry_the_seed_and_the_opening_board(self) -> None:
|
||||
tasks = self.taskset().load()
|
||||
self.assertEqual(len(tasks), 4)
|
||||
for task in tasks:
|
||||
market = build_market(task.data.seed, task.data.num_items, task.data.visible,
|
||||
HORIZON)
|
||||
self.assertEqual(task.data.prompt, opening(market, TURNS))
|
||||
self.assertEqual(task.data.turns, TURNS)
|
||||
self.assertIn("Grand Exchange", task.data.system_prompt)
|
||||
|
||||
def test_two_tasks_never_share_a_basket(self) -> None:
|
||||
"""`viable_live_market` skips baskets the reference loses money in; a load that did
|
||||
not advance past the seed it landed on would serve the same basket twice."""
|
||||
seeds = [t.data.seed for t in self.taskset(24).load()]
|
||||
self.assertEqual(len(set(seeds)), len(seeds))
|
||||
|
||||
def test_the_task_stops_at_the_turn_budget(self) -> None:
|
||||
task = self.taskset(1).load()[0]
|
||||
trace = types.SimpleNamespace(num_turns=TURNS - 1)
|
||||
self.assertFalse(asyncio.run(task.budget(trace)))
|
||||
trace.num_turns = TURNS
|
||||
self.assertTrue(asyncio.run(task.budget(trace)))
|
||||
|
||||
|
||||
@unittest.skipIf(vf is None, "verifiers is not installed")
|
||||
class EnvRunTests(unittest.TestCase):
|
||||
def env_and_task(self):
|
||||
from grand_exchange_live.taskset import (
|
||||
LiveExchangeConfig,
|
||||
LiveExchangeEnv,
|
||||
LiveExchangeEnvConfig,
|
||||
LiveExchangeTaskset,
|
||||
)
|
||||
|
||||
config = LiveExchangeEnvConfig(
|
||||
taskset=LiveExchangeConfig(id="grand-exchange-live", num_tasks=1)
|
||||
)
|
||||
# No harness, no model, no runtime: `run()` is the whole subject here, and building
|
||||
# the env through its constructor would stand up an agent to reach it.
|
||||
env = LiveExchangeEnv.__new__(LiveExchangeEnv)
|
||||
env.config = config
|
||||
return env, LiveExchangeTaskset(config.taskset).load()[0]
|
||||
|
||||
def run_env(self, replies, terminate_at=None, task=None, env=None):
|
||||
from grand_exchange_live.taskset import LiveExchangeEnv
|
||||
|
||||
if env is None:
|
||||
env, task = self.env_and_task()
|
||||
interaction = StubInteraction(replies, terminate_at)
|
||||
asyncio.run(LiveExchangeEnv.run(env, task, StubAgents(interaction)))
|
||||
return interaction
|
||||
|
||||
def test_the_first_turn_is_bare_and_every_later_turn_carries_the_view(self) -> None:
|
||||
"""The task is prompted, so the model speaks first. Passing the opening text on turn
|
||||
one raises ValueError inside `verifiers` — the prompt already opened the exchange."""
|
||||
interaction = self.run_env([HOLD])
|
||||
self.assertEqual(len(interaction.asked), TURNS)
|
||||
self.assertIsNone(interaction.asked[0])
|
||||
for message in interaction.asked[1:]:
|
||||
self.assertIsInstance(message, str)
|
||||
self.assertIn("Look ", message)
|
||||
|
||||
def test_a_terminated_segment_mid_window_is_not_an_error(self) -> None:
|
||||
"""The naive loop calls turn() again and gets RuntimeError('the exchange is over'),
|
||||
which fails the episode over a model that stopped talking. The window runs on."""
|
||||
interaction = self.run_env([HOLD], terminate_at=4)
|
||||
self.assertEqual(interaction.trace.metrics["ended_early"], 1.0)
|
||||
self.assertEqual(interaction.trace.metrics["answered_turns"], 3.0)
|
||||
self.assertEqual(set(interaction.trace.rewards), {"profit", "discipline", "gate"})
|
||||
|
||||
def test_a_hold_every_turn_scores_exactly_zero(self) -> None:
|
||||
"""House rule 3's floor, through the whole stack rather than through the engine —
|
||||
including the degenerate reply that 31 of 32 one-shot rollouts produced."""
|
||||
interaction = self.run_env([HOLD])
|
||||
self.assertEqual(interaction.trace.metrics["held_replies"], float(TURNS))
|
||||
self.assertEqual(interaction.trace.metrics["malformed_replies"], 0.0)
|
||||
for name, (score, _) in interaction.trace.rewards.items():
|
||||
self.assertEqual(score, 0.0, name)
|
||||
|
||||
def test_a_malformed_reply_is_a_hold_and_never_fails_the_episode(self) -> None:
|
||||
interaction = self.run_env(["I would rather not."])
|
||||
self.assertEqual(interaction.trace.metrics["malformed_replies"], float(TURNS))
|
||||
self.assertEqual(interaction.trace.rewards["profit"][0], 0.0)
|
||||
|
||||
def test_a_real_sheet_trades(self) -> None:
|
||||
import json
|
||||
|
||||
from grand_exchange_live.book import reference_orders
|
||||
|
||||
env, task = self.env_and_task()
|
||||
market = build_market(task.data.seed, task.data.num_items, task.data.visible,
|
||||
HORIZON)
|
||||
sheet = "```json\n" + json.dumps({"orders": [
|
||||
{"item": o.item, "quantity": o.quantity, "buy": o.buy, "sell": o.sell}
|
||||
for o in reference_orders(market)
|
||||
]}) + "\n```"
|
||||
interaction = self.run_env([sheet, HOLD], env=env, task=task)
|
||||
self.assertGreater(interaction.trace.metrics["bought"], 0.0)
|
||||
self.assertGreater(interaction.trace.rewards["profit"][0], 0.0)
|
||||
|
||||
def test_the_trace_carries_no_held_out_tick_and_no_market(self) -> None:
|
||||
"""House rule 1's other half. The observation is `protocol.render`'s problem; this is
|
||||
the one that would put the whole series in the training data through `trace.info`."""
|
||||
interaction = self.run_env([HOLD])
|
||||
for key, value in interaction.trace.info.items():
|
||||
self.assertIsInstance(value, (int, float, str), key)
|
||||
for key, value in interaction.trace.metrics.items():
|
||||
self.assertIsInstance(value, float, key)
|
||||
self.assertLess(abs(value), PRICE_SENTINEL, key)
|
||||
self.assertEqual(set(interaction.trace.info), {"basket", "freeze"})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user