Merge pull request #91 from valory-xyz/fix/circular-import

Fix circular import

packages/packages.json

@@ -1,17 +1,18 @@
 {
     "dev": {
-        "skill/valory/market_manager_abci/0.1.0": "bafybeicjqkzen2gvpnc3syojcf6ibr4kjaorcwktikqp2zzxec6vs64oky",
-        "skill/valory/decision_maker_abci/0.1.0": "bafybeic77zhxf5a53ngfzacklmm3nag4t4jeufdhoeg3ykrmvknojtwipi",
-        "skill/valory/trader_abci/0.1.0": "bafybeibi3rt3rdk4bvng3tlmwdxal3mk3bflq4cgq3fxyjwzpmhj3y6pmy",
+        "skill/valory/market_manager_abci/0.1.0": "bafybeigvw5tqei5xb272jb7retxiryhuhxxzupddmbdixgsmxzco3n2dde",
+        "skill/valory/decision_maker_abci/0.1.0": "bafybeihm77vt53vu3xt6x7istsvaw75juptlynpriebgeltbil5evvhtue",
+        "skill/valory/trader_abci/0.1.0": "bafybeiea2r67bzi5gkymu2pu2m3sg3lflke5m2finonak4uprqpbdcp2ru",
         "contract/valory/market_maker/0.1.0": "bafybeif6hivvhxqv4a3uqo2v3yszluzrmngsp624utdi466xwo5qbz5bsi",
-        "agent/valory/trader/0.1.0": "bafybeigoojaxpc7sz7vuswkxvpa5lp37lipuwc4qycztqk4hxdesmxqcda",
-        "service/valory/trader/0.1.0": "bafybeidyuzdmwrt66w32oppopviesvhinmwd76q73zv3dex2th7nldpbyi",
+        "agent/valory/trader/0.1.0": "bafybeiba5eqawktwkpziiazxm5u6ftm7o3zytcbafqsjwt7zrr63o2yis4",
+        "service/valory/trader/0.1.0": "bafybeifqi4yprf6ajureyqn45aa3mo7vezwsx63skc4n56grlormdzoz5i",
         "contract/valory/erc20/0.1.0": "bafybeiggo4u56drxusvcdruqrr7mlfzqbieg4hajalh4tkctxhh3c5lpdi",
-        "skill/valory/tx_settlement_multiplexer_abci/0.1.0": "bafybeidtrigrfjikl7tkbtowbp6mrdzxulayxnxcmviwy3gag557vnymlq",
-        "contract/valory/mech/0.1.0": "bafybeibfikekaruskx6ui7u4qnls57i2namfxi45zhqslziqyxg4npjzxu",
+        "skill/valory/tx_settlement_multiplexer_abci/0.1.0": "bafybeiey57caacd6d3ow25i6a2zuiinkx6kjtckdktannk7kijpd3p2zb4",
+        "contract/valory/mech/0.1.0": "bafybeidtezc4ubsyqdltiojvqe5eeh77ejte7vqbojspiej5quivgap3ae",
         "contract/valory/realitio/0.1.0": "bafybeigb722aznqhc5lsbt3dn4bpyaqe5hnl5onmnestqmzliwtvl3eaom",
         "contract/valory/realitio_proxy/0.1.0": "bafybeibvndq6756qck7forgeavhdbn6ykgqs2ufyg7n5g6qdfpveatxuwy",
-        "contract/valory/conditional_tokens/0.1.0": "bafybeicxwjdbmjajgr5rsmadtkxxwmcm42r2htef3tvng73uzib4hmb6qa"
+        "contract/valory/conditional_tokens/0.1.0": "bafybeicxwjdbmjajgr5rsmadtkxxwmcm42r2htef3tvng73uzib4hmb6qa",
+        "contract/valory/agent_registry/0.1.0": "bafybeib6odummk6qqietjekpljkmhqfxk7kv56kv6pyfsnnanews625ncy"
     },
     "third_party": {
         "protocol/open_aea/signing/1.0.0": "bafybeifuxs7gdg2okbn7uofymenjlmnih2wxwkym44lsgwmklgwuckxm2m",

packages/valory/agents/trader/aea-config.yaml

@@ -21,7 +21,7 @@ contracts:
 - valory/market_maker:0.1.0:bafybeif6hivvhxqv4a3uqo2v3yszluzrmngsp624utdi466xwo5qbz5bsi
 - valory/erc20:0.1.0:bafybeiggo4u56drxusvcdruqrr7mlfzqbieg4hajalh4tkctxhh3c5lpdi
 - valory/multisend:0.1.0:bafybeidfktuprydtmi4umolfles5qaf7s3t26puvvs44hvkq6uwwr3ia3a
-- valory/mech:0.1.0:bafybeibfikekaruskx6ui7u4qnls57i2namfxi45zhqslziqyxg4npjzxu
+- valory/mech:0.1.0:bafybeidtezc4ubsyqdltiojvqe5eeh77ejte7vqbojspiej5quivgap3ae
 - valory/conditional_tokens:0.1.0:bafybeicxwjdbmjajgr5rsmadtkxxwmcm42r2htef3tvng73uzib4hmb6qa
 - valory/realitio:0.1.0:bafybeigb722aznqhc5lsbt3dn4bpyaqe5hnl5onmnestqmzliwtvl3eaom
 - valory/realitio_proxy:0.1.0:bafybeibvndq6756qck7forgeavhdbn6ykgqs2ufyg7n5g6qdfpveatxuwy
@@ -41,10 +41,10 @@ skills:
 - valory/reset_pause_abci:0.1.0:bafybeiblayblhp5wuirfomwcpgydg35ve5tfq3xxetlosjn47wva5ucmzy
 - valory/termination_abci:0.1.0:bafybeieqfhvk6klnvxak3vo2ibslkrnnk2bfsn5l3gbaelcprd6cjngxki
 - valory/transaction_settlement_abci:0.1.0:bafybeicisazpyvnnzlqso3txiucxr5qhsa4ac7ius6b4mhouxr2wkadwfy
-- valory/tx_settlement_multiplexer_abci:0.1.0:bafybeidtrigrfjikl7tkbtowbp6mrdzxulayxnxcmviwy3gag557vnymlq
-- valory/market_manager_abci:0.1.0:bafybeicjqkzen2gvpnc3syojcf6ibr4kjaorcwktikqp2zzxec6vs64oky
-- valory/decision_maker_abci:0.1.0:bafybeic77zhxf5a53ngfzacklmm3nag4t4jeufdhoeg3ykrmvknojtwipi
-- valory/trader_abci:0.1.0:bafybeibi3rt3rdk4bvng3tlmwdxal3mk3bflq4cgq3fxyjwzpmhj3y6pmy
+- valory/tx_settlement_multiplexer_abci:0.1.0:bafybeiey57caacd6d3ow25i6a2zuiinkx6kjtckdktannk7kijpd3p2zb4
+- valory/market_manager_abci:0.1.0:bafybeigvw5tqei5xb272jb7retxiryhuhxxzupddmbdixgsmxzco3n2dde
+- valory/decision_maker_abci:0.1.0:bafybeihm77vt53vu3xt6x7istsvaw75juptlynpriebgeltbil5evvhtue
+- valory/trader_abci:0.1.0:bafybeiea2r67bzi5gkymu2pu2m3sg3lflke5m2finonak4uprqpbdcp2ru
 default_ledger: ethereum
 required_ledgers:
 - ethereum
@@ -188,9 +188,10 @@ models:
       slippage: ${float:0.01}
       redeem_margin_days: ${int:15}
       epsilon: ${float:0.1}
-      irrelevant_tools: ${set:{"openai-text-davinci-002", "openai-text-davinci-003", "openai-gpt-3.5-turbo", 
-        "openai-gpt-4", "stabilityai-stable-diffusion-v1-5", "stabilityai-stable-diffusion-xl-beta-v2-2-2", 
-        "stabilityai-stable-diffusion-512-v2-1", "stabilityai-stable-diffusion-768-v2-1"}}
+      irrelevant_tools: ${list:["openai-text-davinci-002", "openai-text-davinci-003",
+        "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5",
+        "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1",
+        "stabilityai-stable-diffusion-768-v2-1"]}
 ---
 public_id: valory/p2p_libp2p_client:0.1.0
 type: connection

packages/valory/contracts/agent_registry/contract.yaml

@@ -6,12 +6,9 @@ description: Agent Registry contract
 license: Apache-2.0
 aea_version: '>=1.0.0, <2.0.0'
 fingerprint:
-  __init__.py: bafybeidey4syohls5hxmso6qsp5p4uhtzle5txv2mlbym6ktjzknich6oa
-  build/AgentRegistry.json: bafybeia4qi2vstrutejzrxfpbb6eift7va5cjs7bparaal2fafiiczuiyy
-  build/AgentRegistryL2.json: bafybeic2jylwfod4nmdtbs4izyxyi246pd3f35aoqyahnmyrvzn7j3sv4e
-  contract.py: bafybeibqwl52cnz64cysjd2jnjijuakdvyrffapxq65cdzx6g65gu42deq
-  tests/__init__.py: bafybeicl2oklx774jomlt6wwwegfdzrxh6iazjxwcyc7h4gepjljkpl4ji
-  tests/test_contract.py: bafybeicj535veqf35zb3ycu5iqjvqgj4a2kdmogmx5ba7fiolt5chah42a
+  __init__.py: bafybeid3wfzglolebuo6jrrsopswzu4lk77bm76mvw3euizlsjtnt3wmgu
+  build/AgentRegistry.json: bafybeicoe5elvvsv2neiirsdn4uddrilizmyib3x4mvpklr7olhj2kh4ue
+  contract.py: bafybeihrv6blme3v6diwci6zxxn72qbg5sanzmfq5tobhs4375ebcuyday
 fingerprint_ignore_patterns: []
 contracts: []
 class_name: AgentRegistryContract

packages/valory/contracts/mech/contract.yaml

@@ -9,7 +9,7 @@ fingerprint:
   README.md: bafybeibl4uw7rs6mwh7zuvdnqmj2o2xyr7nx5qk3w7torwx3jg6farn6ca
   __init__.py: bafybeicx5pxh3cxnml2biuuoebvafvu5tvy6mgkzyjzuubuoeebb5yzjsm
   build/mech.json: bafybeihsfz7rdnf6cpa3c4eagvs4pw6jhr6pcsikstakejrlkuwvwzhw7m
-  contract.py: bafybeigypn3frcjr7mcmdoe5ubgoy57owm4bfcgtrcytiu76u7khthlvei
+  contract.py: bafybeifbfa6p3jcwn6j7s5aiiqxb3ne4vbmvoggr5zpptmd727gpsjqjpe
 fingerprint_ignore_patterns: []
 contracts: []
 class_name: Mech

packages/valory/services/trader/service.yaml

@@ -7,7 +7,7 @@ license: Apache-2.0
 fingerprint:
   README.md: bafybeigtuothskwyvrhfosps2bu6suauycolj67dpuxqvnicdrdu7yhtvq
 fingerprint_ignore_patterns: []
-agent: valory/trader:0.1.0:bafybeigoojaxpc7sz7vuswkxvpa5lp37lipuwc4qycztqk4hxdesmxqcda
+agent: valory/trader:0.1.0:bafybeiba5eqawktwkpziiazxm5u6ftm7o3zytcbafqsjwt7zrr63o2yis4
 number_of_agents: 4
 deployment: {}
 ---
@@ -105,10 +105,10 @@ type: skill
         slippage: ${SLIPPAGE:float:0.01}
         redeem_margin_days: ${REDEEM_MARGIN_DAYS:int:15}
         epsilon: ${EPSILON:float:0.1}
-        irrelevant_tools: ${IRRELEVANT_TOOLS:set:{"openai-text-davinci-002", "openai-text-davinci-003", 
-          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5", 
-          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1", 
-          "stabilityai-stable-diffusion-768-v2-1"}}
+        irrelevant_tools: ${IRRELEVANT_TOOLS:list:["openai-text-davinci-002", "openai-text-davinci-003",
+          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5",
+          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1",
+          "stabilityai-stable-diffusion-768-v2-1"]}
     benchmark_tool: &id005
       args:
         log_dir: ${LOG_DIR:str:/benchmarks}
@@ -174,10 +174,10 @@ type: skill
         slippage: ${SLIPPAGE:float:0.01}
         redeem_margin_days: ${REDEEM_MARGIN_DAYS:int:15}
         epsilon: ${EPSILON:float:0.1}
-        irrelevant_tools: ${IRRELEVANT_TOOLS:set:{"openai-text-davinci-002", "openai-text-davinci-003", 
-          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5", 
-          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1", 
-          "stabilityai-stable-diffusion-768-v2-1"}}
+        irrelevant_tools: ${IRRELEVANT_TOOLS:list:["openai-text-davinci-002", "openai-text-davinci-003",
+          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5",
+          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1",
+          "stabilityai-stable-diffusion-768-v2-1"]}
     benchmark_tool: *id005
 2:
   models:
@@ -241,10 +241,10 @@ type: skill
         slippage: ${SLIPPAGE:float:0.01}
         redeem_margin_days: ${REDEEM_MARGIN_DAYS:int:15}
         epsilon: ${EPSILON:float:0.1}
-        irrelevant_tools: ${IRRELEVANT_TOOLS:set:{"openai-text-davinci-002", "openai-text-davinci-003", 
-          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5", 
-          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1", 
-          "stabilityai-stable-diffusion-768-v2-1"}}
+        irrelevant_tools: ${IRRELEVANT_TOOLS:list:["openai-text-davinci-002", "openai-text-davinci-003",
+          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5",
+          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1",
+          "stabilityai-stable-diffusion-768-v2-1"]}
     benchmark_tool: *id005
 3:
   models:
@@ -308,10 +308,10 @@ type: skill
         slippage: ${SLIPPAGE:float:0.01}
         redeem_margin_days: ${REDEEM_MARGIN_DAYS:int:15}
         epsilon: ${EPSILON:float:0.1}
-        irrelevant_tools: ${IRRELEVANT_TOOLS:set:{"openai-text-davinci-002", "openai-text-davinci-003", 
-          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5", 
-          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1", 
-          "stabilityai-stable-diffusion-768-v2-1"}}
+        irrelevant_tools: ${IRRELEVANT_TOOLS:list:["openai-text-davinci-002", "openai-text-davinci-003",
+          "openai-gpt-3.5-turbo", "openai-gpt-4", "stabilityai-stable-diffusion-v1-5",
+          "stabilityai-stable-diffusion-xl-beta-v2-2-2", "stabilityai-stable-diffusion-512-v2-1",
+          "stabilityai-stable-diffusion-768-v2-1"]}
     benchmark_tool: *id005
 ---
 public_id: valory/ledger:0.19.0

packages/valory/skills/decision_maker_abci/behaviours/base.py

@@ -40,9 +40,9 @@
 )
 from packages.valory.skills.decision_maker_abci.models import (
     DecisionMakerParams,
-    EGreedyPolicy,
     MultisendBatch,
 )
+from packages.valory.skills.decision_maker_abci.policy import EGreedyPolicy
 from packages.valory.skills.decision_maker_abci.states.base import SynchronizedData
 from packages.valory.skills.transaction_settlement_abci.payload_tools import (
     hash_payload_to_hex,

packages/valory/skills/decision_maker_abci/behaviours/tool_selection.py

@@ -30,11 +30,9 @@
     DecisionMakerBaseBehaviour,
     WaitableConditionType,
 )
-from packages.valory.skills.decision_maker_abci.models import (
-    AgentToolsSpecs,
-    EGreedyPolicy,
-)
+from packages.valory.skills.decision_maker_abci.models import AgentToolsSpecs
 from packages.valory.skills.decision_maker_abci.payloads import ToolSelectionPayload
+from packages.valory.skills.decision_maker_abci.policy import EGreedyPolicy
 from packages.valory.skills.decision_maker_abci.states.tool_selection import (
     ToolSelectionRound,
 )

packages/valory/skills/decision_maker_abci/fsm_specification.yaml

@@ -38,6 +38,7 @@ states:
 - RedeemRound
 - RefillRequiredRound
 - SamplingRound
+- ToolSelectionRound
 transition_func:
     (BetPlacementRound, DONE): FinishedDecisionMakerRound
     (BetPlacementRound, INSUFFICIENT_BALANCE): RefillRequiredRound
@@ -68,7 +69,11 @@ transition_func:
     (RedeemRound, NO_MAJORITY): RedeemRound
     (RedeemRound, NO_REDEEMING): FinishedWithoutRedeemingRound
     (RedeemRound, ROUND_TIMEOUT): RedeemRound
-    (SamplingRound, DONE): DecisionRequestRound
+    (SamplingRound, DONE): ToolSelectionRound
     (SamplingRound, NONE): FinishedWithoutDecisionRound
     (SamplingRound, NO_MAJORITY): SamplingRound
     (SamplingRound, ROUND_TIMEOUT): SamplingRound
+    (ToolSelectionRound, DONE): DecisionRequestRound
+    (ToolSelectionRound, NONE): ToolSelectionRound
+    (ToolSelectionRound, NO_MAJORITY): ToolSelectionRound
+    (ToolSelectionRound, ROUND_TIMEOUT): ToolSelectionRound

packages/valory/skills/decision_maker_abci/models.py

@@ -20,11 +20,10 @@
 """This module contains the models for the skill."""
 
 import json
-import random
 import re
-from dataclasses import asdict, dataclass, is_dataclass
+from dataclasses import dataclass
 from string import Template
-from typing import Any, Dict, List, Optional, Set
+from typing import Any, Dict, Optional, Set
 
 from aea.exceptions import enforce
 from hexbytes import HexBytes
@@ -127,7 +126,7 @@ def __init__(self, *args: Any, **kwargs: Any) -> None:
         self.agent_registry_address: str = self._ensure(
             "agent_registry_address", kwargs, str
         )
-        self.irrelevant_tools: set = self._ensure("irrelevant_tools", kwargs, set)
+        self.irrelevant_tools: set = set(self._ensure("irrelevant_tools", kwargs, list))
         super().__init__(*args, **kwargs)
 
     @property
@@ -226,88 +225,3 @@ def incorrect_format(cls, res: Any) -> "MechInteractionResponse":
         response = cls()
         response.error = f"The response's format was unexpected: {res}"
         return response
-
-
-class DataclassEncoder(json.JSONEncoder):
-    """A custom JSON encoder for dataclasses."""
-
-    def default(self, o: Any) -> Any:
-        """The default JSON encoder."""
-        if is_dataclass(o):
-            return asdict(o)
-        return super().default(o)
-
-
-def argmax(li: List) -> int:
-    """Get the index of the max value within the provided list."""
-    return li.index((max(li)))
-
-
-@dataclass
-class EGreedyPolicy:
-    """An e-Greedy policy for the tool selection."""
-
-    eps: float
-    n_tools: int
-    counts: List[int]
-    rewards: List[float]
-
-    @classmethod
-    def initial_state(cls, eps: float, n_tools: int) -> "EGreedyPolicy":
-        """Return an instance on its initial state."""
-        if n_tools == 0:
-            error = f"Cannot initialize an e Greedy Policy with {n_tools=}"
-            raise ValueError(error)
-
-        return EGreedyPolicy(eps, n_tools, [0] * n_tools, [0.0] * n_tools)
-
-    @classmethod
-    def deserialize(cls, policy: str) -> "EGreedyPolicy":
-        """Deserialize a string to an `EGreedyPolicy` object."""
-        return EGreedyPolicy(**json.loads(policy))
-
-    @property
-    def random_tool(self) -> int:
-        """Get the index of a tool randomly."""
-        return random.randrange(self.n_tools)
-
-    @property
-    def reward_rates(self) -> List[float]:
-        """Get the reward rates."""
-        return [reward / count for reward, count in zip(self.rewards, self.counts)]
-
-    def add_new_tools(self, n_new: int) -> None:
-        """Add new tools to the current policy."""
-        self.n_tools += n_new
-        self.counts.extend([0] * n_new)
-        self.rewards.extend([0.0] * n_new)
-
-    def remove_tools(self, indexes: List[int]) -> None:
-        """Remove the knowledge for the tools corresponding to the given indexes."""
-        self.n_tools -= len(indexes)
-        for i in indexes:
-            try:
-                del self.counts[i]
-                del self.rewards[i]
-            except IndexError as exc:
-                error = "Attempted to remove tools using incorrect indexes!"
-                raise ValueError(error) from exc
-
-    def select_tool(self) -> Optional[int]:
-        """Select a Mech tool and return its index."""
-        if self.n_tools == 0:
-            return None
-
-        if sum(self.counts) == 0 or random.random() < self.eps:
-            return self.random_tool
-
-        return argmax(self.reward_rates)
-
-    def add_reward(self, index: int, reward: float) -> None:
-        """Add a reward for the tool corresponding to the given index."""
-        self.counts[index] += 1
-        self.rewards[index] += reward
-
-    def serialize(self) -> str:
-        """Return the policy serialized."""
-        return json.dumps(self, cls=DataclassEncoder, sort_keys=True)