Introduce fees into AgentMarket itself (not just OmenAgentMarket)
#506
Conversation
kongzii
force-pushed
the
peter/rethink-fees
branch
2 times, most recently
from
9ef5060 to
4635f0a
Compare
kongzii
force-pushed
the
peter/rethink-fees
branch
from
4635f0a to
2e8bb2f
Compare
WalkthroughThe pull request introduces several modifications across multiple files, primarily focusing on the implementation of a new Changes
Possibly related PRs
Suggested reviewers
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
| @@ -226,7 +230,7 @@ def calculate_price_impact_deviation_from_target_price_impact( | |||
| bet_amount, | |||
| yes_outcome_pool_size, | |||
| no_outcome_pool_size, | |||
| fee, | |||
| MarketFees.get_zero_fees(), # TODO: Use market.fees | |||
There was a problem hiding this comment.
There is bunch of TODOs like this, going to do them in #507, to separate fees introduction to Kelly in case of issues.
Will also run the bet benchmark there.
| @@ -60,6 +61,7 @@ class AgentMarket(BaseModel): | |||
| current_p_yes: Probability | |||
| url: str | |||
| volume: float | None # Should be in currency of `currency` above. | |||
| fees: MarketFees | |||
There was a problem hiding this comment.
Leveled the fees to AgentMarket itself, but because Manifold has an absolute, constant fee, it's now a model with absolute and bet_proportion fields.
| def handle_legacy_fee(cls, data: dict[str, t.Any]) -> dict[str, t.Any]: | ||
| # Backward compatibility for older `AgentMarket` without `fees`. | ||
| if "fees" not in data and "fee" in data: | ||
| data["fees"] = MarketFees(absolute=0.0, bet_proportion=data["fee"]) |
There was a problem hiding this comment.
This fixed running of match_bets_with_langfuse script, otherwise there would be 0 matched bets, which is a shame.
|
|
||
| class MarketFees(BaseModel): | ||
| bet_proportion: float = Field( | ||
| ..., ge=0.0, lt=1.0 |
There was a problem hiding this comment.
Fancy way to. validate bet propotion, so I removed it in other places of the code, where MarketFees is now accepted.
kongzii
changed the title
fees into AgentMarket itself (not just OmenAgentMarket)
| @@ -240,7 +244,8 @@ def get_outcome_for_trace( | |||
|
|
|||
| details.sort(key=lambda x: x["sim_profit"], reverse=True) | |||
| pd.DataFrame.from_records(details).to_csv( | |||
| f"{agent_name} - {strategy} - all bets.csv", index=False | |||
| output_directory / f"{agent_name} - {strategy} - all bets.csv", | |||
There was a problem hiding this comment.
ah, a happy directory tree now 😌
| fee = fees.bet_proportion | ||
| if fees.absolute > 0: | ||
| raise RuntimeError( | ||
| f"Kelly works only with bet-proportional fees, but the fees are {fees=}." |
There was a problem hiding this comment.
Just had a look at the below formula. Without trying to re-derive, I wonder if, for the numerator, you replace all instances of b * f with b * (1 - f_proportional) - f_absolute.
Not sure about the denominator though
| def total_fee_absolute_value(self, bet_amount: float) -> float: | ||
| """ | ||
| Returns the total fee in absolute terms, including both proportional and fixed fees. | ||
| """ | ||
| return self.bet_proportion * bet_amount + self.absolute | ||
|
|
||
| def total_fee_relative_value(self, bet_amount: float) -> float: | ||
| """ | ||
| Returns the total fee relative to the bet amount, including both proportional and fixed fees. | ||
| """ | ||
| if bet_amount == 0: | ||
| return 0.0 | ||
| total_fee = self.total_fee_absolute_value(bet_amount) | ||
| return total_fee / bet_amount |
There was a problem hiding this comment.
Looks like these are unused. Planning to use in later PR?
There was a problem hiding this comment.
total_fee_absolute_value is now 😄 and removed total_fee_relative_value
| total_fee = self.total_fee_absolute_value(bet_amount) | ||
| return total_fee / bet_amount | ||
|
|
||
| def get_bet_size_after_fees(self, bet_amount: float) -> float: |
There was a problem hiding this comment.
Nice! This is a really neat replacement for the fee: float args before. I thought it would be more complicated than this 😅
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 11
🧹 Outside diff range and nitpick comments (21)
prediction_market_agent_tooling/markets/market_fees.py (2)
4-8: LGTM: Well-structured MarketFees class with appropriate constraints.The MarketFees class is well-defined using Pydantic's BaseModel. The bet_proportion constraint (0 ≤ x < 1) is correctly implemented.
Consider adding a constraint to ensure the absolute fee is non-negative:
absolute: float = Field(..., ge=0.0) # absolute value paid in the currency of the marketThis would prevent potential issues with negative fee values, unless there's a specific reason to allow them.
1-36: LGTM: Well-structured and comprehensive MarketFees implementation.The MarketFees class is well-designed and provides a robust foundation for handling market fees in the AgentMarket. It aligns perfectly with the PR objectives and introduces a flexible, validated approach to fee management.
For future enhancements, consider:
- Adding methods to compare different fee structures.
- Implementing serialization/deserialization methods if needed for API interactions.
- Including additional validation or business logic methods if specific fee rules need to be enforced.
These suggestions are not necessary for the current implementation but might be useful as the project evolves.
tests/markets/test_markets.py (3)
36-36: LGTM: Addition of fees parameter in test_valid_token_poolThe addition of the
feesparameter withMarketFees.get_zero_fees()is appropriate for this test case. It ensures that theAgentMarketis initialized with a neutral fee structure, which is suitable for testing the token pool functionality.Consider adding an assertion to verify that the fees are indeed zero in this test case. This would make the test more robust and explicit about the fee structure being used.
57-57: LGTM: Addition of fees parameter in test_invalid_token_poolThe addition of the
feesparameter withMarketFees.get_zero_fees()is consistent with the changes intest_valid_token_pooland appropriate for this test case.To improve consistency and reduce duplication, consider extracting
MarketFees.get_zero_fees()to a constant or a fixture that can be reused across multiple test cases. This would make it easier to update the fee structure for all tests if needed in the future.
Line range hint
1-89: Suggestion: Add specific tests for the fees functionalityWhile the changes appropriately update the existing tests to accommodate the new
feesparameter, there are no specific tests for thefeesfunctionality itself.Consider adding new test cases that:
- Verify the behavior of
AgentMarketwith non-zero fees.- Test edge cases related to fee calculations.
- Ensure that the
feesparameter is correctly applied in various market operations.This would improve the overall test coverage and help catch any potential issues related to the new
feesfeature.tests/tools/test_utils.py (1)
44-50: LGTM: Fee handling correctly updated to use MarketFees. Consider minor improvement.The changes to use
MarketFeesandbet_proportion_feeare consistent with the new fee structure. The logic of the test remains intact, still verifying that the value of sold shares decreases as the fee increases.Consider renaming
c1andc2to more descriptive names likecollateral_low_feeandcollateral_high_feefor improved readability:-c1 = get_collateral(bet_proportion_fee=0.1) -c2 = get_collateral(bet_proportion_fee=0.35) -assert c1 > c2 +collateral_low_fee = get_collateral(bet_proportion_fee=0.1) +collateral_high_fee = get_collateral(bet_proportion_fee=0.35) +assert collateral_low_fee > collateral_high_feeAlso applies to: 53-54
prediction_market_agent_tooling/markets/polymarket/polymarket.py (2)
30-34: Excellent documentation on fee structure and future considerations.The added comments provide valuable context about the current fee structure and potential future changes. They explain why zero fees are currently used and include a TODO for future implementation.
Consider adding a link to the Polymarket documentation for easier reference:
-# Based on https://docs.polymarket.com/#fees, there are currently no fees, except for transactions fees. +# Based on Polymarket documentation (https://docs.polymarket.com/#fees), there are currently no fees, except for transaction fees.
34-34: LGTM: Newfeesclass variable is correctly implemented.The
feesclass variable is appropriately added and initialized with zero fees, which is consistent with the current Polymarket fee structure as explained in the comments.For consistency with other class variables, consider adding a type annotation:
-fees: MarketFees = MarketFees.get_zero_fees() +fees: t.ClassVar[MarketFees] = MarketFees.get_zero_fees()prediction_market_agent_tooling/markets/metaculus/metaculus.py (1)
33-33: LGTM: Newfeesvariable is correctly implemented.The addition of the
feesclass variable is consistent with the PR objective and correctly initialized for Metaculus.Consider slightly modifying the comment for clarity:
- fees: MarketFees = MarketFees.get_zero_fees() # No fees on Metaculus. + fees: MarketFees = MarketFees.get_zero_fees() # Metaculus doesn't charge fees, so we use zero fees.prediction_market_agent_tooling/jobs/omen/omen_jobs.py (1)
Line range hint
1-110: Overall file reviewThe change in this file is minimal but potentially impactful. It reflects a shift from a single fee to multiple fees in the
OmenJobAgentMarketclass. While the change itself is straightforward, it's crucial to ensure that this modification is part of a consistent update across the entire codebase.To maintain code quality and prevent potential issues:
- Verify that all related classes and methods (especially in
OmenAgentMarket) have been updated to support multiple fees.- Update any documentation or comments that might reference the fee structure.
- Ensure that any tests involving
OmenJobAgentMarketor fee calculations are updated to reflect this change.Consider creating a dedicated
Feesclass or data structure if one doesn't already exist. This could help encapsulate fee-related logic and make future changes or additions to the fee structure easier to manage.tests_integration/markets/omen/test_kelly.py (1)
109-109: Approve temporary use of zero fees, but address TODOThe use of
MarketFees.get_zero_fees()is an improvement over hardcoded values. However, the TODO comment suggests that this is a temporary solution.Please create a follow-up task to implement
omen_agent_market.feesas indicated by the TODO comment. This will ensure that realistic fee structures are used in future tests.prediction_market_agent_tooling/tools/betting_strategies/market_moving.py (1)
20-20: LGTM: Function signature updated for new fee structure.The change from
fee: float = 0.0tofees: MarketFeesis appropriate for the new fee structure. This allows for more complex fee calculations and is consistent with the changes described in the summary.Consider adding a type hint for the return value to improve code readability:
def get_market_moving_bet( yes_outcome_pool_size: float, no_outcome_pool_size: float, market_p_yes: float, target_p_yes: float, fees: MarketFees, max_iters: int = 100, ) -> SimpleBet:prediction_market_agent_tooling/tools/langfuse_client_utils.py (2)
96-99: Improved error logging, consider adding log levels.The addition of warning logs for missing input or arguments in the trace enhances the function's robustness and aids in debugging. This is a good practice for improving traceability of issues.
Consider using different log levels for these warnings. For instance, you might want to use
logger.errorfor missing input, as it's likely a more severe issue than missing arguments. This would allow for more granular log filtering in production environments.if not trace.input: logger.error(f"No input in the trace: {trace}") return None if not trace.input["args"]: logger.warning(f"No args in the trace: {trace}") return None
106-107: Improved exception handling, consider consistent naming.The addition of specific exception handling and logging for market parsing errors is a good improvement. It enhances the function's resilience and provides more detailed error information for debugging.
For consistency with the previous log messages, consider including the trace object in this log message as well. This would provide more context for debugging:
except Exception as e: logger.warning(f"Market not parsed from langfuse because: {e}. Trace: {trace}") return Nonetests/markets/test_betting_strategies.py (3)
125-125: LGTM: Fee structure updated correctly.The change from a direct float value to
MarketFees.get_zero_fees(bet_proportion=0.02)is consistent with the new fee structure implementation. This maintains the same fee value while using the newMarketFeesclass.Consider extracting the
bet_proportionvalue to a constant at the top of the file for easier maintenance and consistency across tests.
186-186: LGTM: Fee structure updated correctly.The change to
fees=OmenAgentMarket.from_data_model(omen_market).feesensures consistency with the new fee structure implementation and theOmenAgentMarketclass.Consider extracting the
OmenAgentMarket.from_data_model(omen_market).feesto a variable before the function call for improved readability:market_fees = OmenAgentMarket.from_data_model(omen_market).fees bet = get_market_moving_bet( # ... other parameters ... fees=market_fees, )
264-264: LGTM: Fee structure updated correctly.The change to
fees=MarketFees.get_zero_fees()ensures consistency with the new fee structure implementation and appropriately uses zero fees for the Kelly bet calculation in this test case.For consistency with the
test_minimum_bet_to_winfunction, consider usingMarketFees.get_zero_fees(bet_proportion=0.0)to explicitly show that zero fees are being used.examples/monitor/match_bets_with_langfuse_traces.py (3)
93-95: LGTM: Output directory creation is well-implemented.The creation of the output directory is implemented correctly using the
Pathobject. The use ofparents=Trueandexist_ok=Trueensures that the directory is created safely.Consider adding a comment explaining the purpose of the
bet_strategy_benchmarkdirectory for better code documentation.
247-248: LGTM: File path updates are consistent and correct.The changes to file paths correctly utilize the new
output_directoryvariable, ensuring all output files are saved in the designated directory. The use of the forward slash for path joining is appropriate when usingPathobjects.For consistency, consider using an f-string for the file path on lines 305-307, similar to the approach used on lines 247-248:
output_directory / f"{agent_name}_details.csv"This would make the path construction consistent across all file operations.
Also applies to: 305-307, 316-318
Line range hint
1-318: Overall, the changes improve file organization and are well-implemented.The introduction of a dedicated output directory for bet strategy benchmarks enhances the script's file management. The changes are consistent throughout the file and improve the organization of output files without introducing any apparent issues. The use of
pathlib.Pathfor directory and file path handling is a good practice that enhances cross-platform compatibility.Consider adding a configuration variable for the output directory name (e.g.,
BET_STRATEGY_BENCHMARK_DIR) at the top of the file or in a separate configuration file. This would make it easier to change the output location in the future if needed, following the principle of separating configuration from code.prediction_market_agent_tooling/markets/omen/omen_contracts.py (1)
Line range hint
590-600: LGTM! Consider adding a docstring for clarity.The new
submit_answer_invalidmethod is a valuable addition, providing a convenient way to submit an invalid answer. The implementation correctly wraps the existingsubmitAnswermethod and uses theINVALID_ANSWER_HEX_BYTESconstant.To improve clarity, consider adding a brief docstring explaining the purpose of this method:
def submit_answer_invalid( self, api_keys: APIKeys, question_id: HexBytes, bond: Wei, max_previous: Wei | None = None, web3: Web3 | None = None, ) -> TxReceipt: """ Submit an invalid answer for the given question. This method is a convenience wrapper around `submitAnswer` that automatically uses the `INVALID_ANSWER_HEX_BYTES` constant as the answer. """ return self.submitAnswer( api_keys=api_keys, question_id=question_id, answer=INVALID_ANSWER_HEX_BYTES, bond=bond, max_previous=max_previous, web3=web3, )🧰 Tools
🪛 Ruff
169-169: Do not perform function call
build_parent_collection_idin argument defaults; instead, perform the call within the function, or read the default from a module-level singleton variable(B008)
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
📒 Files selected for processing (20)
- .gitignore (1 hunks)
- examples/monitor/match_bets_with_langfuse_traces.py (5 hunks)
- prediction_market_agent_tooling/deploy/betting_strategy.py (4 hunks)
- prediction_market_agent_tooling/jobs/omen/omen_jobs.py (1 hunks)
- prediction_market_agent_tooling/markets/agent_market.py (4 hunks)
- prediction_market_agent_tooling/markets/manifold/manifold.py (2 hunks)
- prediction_market_agent_tooling/markets/market_fees.py (1 hunks)
- prediction_market_agent_tooling/markets/metaculus/metaculus.py (2 hunks)
- prediction_market_agent_tooling/markets/omen/omen.py (6 hunks)
- prediction_market_agent_tooling/markets/omen/omen_contracts.py (1 hunks)
- prediction_market_agent_tooling/markets/polymarket/polymarket.py (2 hunks)
- prediction_market_agent_tooling/tools/betting_strategies/kelly_criterion.py (3 hunks)
- prediction_market_agent_tooling/tools/betting_strategies/market_moving.py (4 hunks)
- prediction_market_agent_tooling/tools/langfuse_client_utils.py (1 hunks)
- prediction_market_agent_tooling/tools/utils.py (3 hunks)
- tests/markets/omen/test_omen.py (1 hunks)
- tests/markets/test_betting_strategies.py (7 hunks)
- tests/markets/test_markets.py (3 hunks)
- tests/tools/test_utils.py (5 hunks)
- tests_integration/markets/omen/test_kelly.py (4 hunks)
🧰 Additional context used
🪛 Ruff
prediction_market_agent_tooling/markets/omen/omen_contracts.py
169-169: Do not perform function call
build_parent_collection_idin argument defaults; instead, perform the call within the function, or read the default from a module-level singleton variable(B008)
prediction_market_agent_tooling/tools/betting_strategies/kelly_criterion.py
65-65: Do not perform function call
MarketFees.get_zero_feesin argument defaults; instead, perform the call within the function, or read the default from a module-level singleton variable(B008)
🔇 Additional comments (39)
prediction_market_agent_tooling/markets/market_fees.py (3)
1-1: LGTM: Imports are appropriate and minimal.The imports from Pydantic (BaseModel and Field) are correctly used in the class definition.
10-18: LGTM: Useful static method for creating zero-fee instances.The
get_zero_feesstatic method provides a convenient way to create MarketFees instances with zero fees. It's well-implemented and uses appropriate default values.
20-36: LGTM: Comprehensive and well-implemented fee calculation methods.The fee calculation methods are well-designed and cover all necessary scenarios:
total_fee_absolute_value: Correctly calculates the total fee in absolute terms.total_fee_relative_value: Properly handles the case of zero bet_amount to avoid division by zero.get_bet_size_after_fees: Accurately calculates the effective bet size after fees.These methods provide a robust foundation for fee-related operations in the market.
tests/markets/test_markets.py (1)
7-7: LGTM: Import of MarketFeesThe import of
MarketFeesis correctly placed and necessary for the changes in the test functions.tests/tools/test_utils.py (6)
4-4: LGTM: Import statement for MarketFees is correctly added.The new import statement for the
MarketFeesclass is necessary and correctly placed. It follows Python import conventions.
17-17: LGTM: Fee parameter correctly updated to use MarketFees.The change from
feetofees=MarketFees.get_zero_fees()is consistent with the new fee structure. Usingget_zero_fees()is appropriate for this test case as it's testing a scenario without fees. The rest of the function remains unchanged, preserving the original test logic.
28-28: LGTM: Fee parameters correctly updated to use MarketFees in both test cases.The changes from
feetofees=MarketFees.get_zero_fees()are consistent with the new fee structure. Usingget_zero_fees()is appropriate for these test cases as they're testing scenarios without fees. The rest of the function remains unchanged, preserving the original test logic for both near-zero and near-one value scenarios.Also applies to: 37-37
60-66: LGTM: Fee handling and error checking correctly updated.The changes to use
MarketFeesandbet_proportion_feeare consistent with the new fee structure. The updated error messages are more specific and aligned with the new implementation. The logic of the test remains intact, still verifying proper error handling for invalid fee values.Also applies to: 70-71, 74-75
84-84: LGTM: Fee parameter correctly updated to use MarketFees.The change from
feetofees=MarketFees.get_zero_fees()is consistent with the new fee structure. Usingget_zero_fees()is appropriate for this test case as it's testing error handling unrelated to fees. The rest of the function remains unchanged, preserving the original test logic for checking the error condition.
Line range hint
1-87: Overall: Excellent implementation of the new fee structure in test cases.The changes in this file consistently implement the new fee structure using the
MarketFeesclass across all test functions. The logic of the tests remains intact, with only the fee handling being updated. Error messages and assertions have been appropriately updated where necessary.These changes improve the consistency and clarity of fee handling in the tests and align well with the PR objective of introducing
feesinto the system..gitignore (1)
166-166: LGTM: Appropriate addition to .gitignoreThe addition of
bet_strategy_benchmark*to the .gitignore file is a good practice. This will prevent any files or directories starting with "bet_strategy_benchmark" from being tracked by version control. These files are likely generated during testing or benchmarking of betting strategies and don't need to be committed to the repository.This change helps keep the repository clean and focused on source code and essential files, which aligns well with the PR's objective of introducing fees into the AgentMarket.
prediction_market_agent_tooling/markets/polymarket/polymarket.py (2)
6-6: LGTM: Import statement addition is correct.The
MarketFeesimport is correctly added to the existing import statement fromprediction_market_agent_tooling.markets.agent_market. This import is necessary for the newfeesclass variable.
Line range hint
6-34: Overall, the changes look good and align with the PR objectives.The introduction of the
feesvariable, along with the detailed comments, successfully implements the groundwork for managing fees in the PolymarketAgentMarket class. The changes are well-documented and provide a clear path for future improvements.To ensure consistency across the codebase, let's verify if similar fee-related changes have been made in other market implementations:
This will help ensure that the fee implementation is consistent across different market types.
prediction_market_agent_tooling/markets/metaculus/metaculus.py (2)
8-8: LGTM: Import statement addition is correct.The addition of
MarketFeesto the import statement is necessary and correctly placed with other imports from the same module.
33-33: Verify the intended usage of thefeesvariable.The
feesvariable has been added to the class, but it's not used in any of the class methods. While this might be intentional since Metaculus doesn't charge fees, it's worth confirming that this is the desired behavior.Could you please confirm if there are any plans to use the
feesvariable in the class methods, or if its presence is solely for consistency with other market classes?To help verify this, you can run the following script to check for any usage of
self.feesin the class methods:prediction_market_agent_tooling/markets/manifold/manifold.py (1)
9-9: LGTM: Import statement added correctly.The addition of
MarketFeesto the import list is consistent with its usage in the class. This change is appropriate and necessary for the new functionality being introduced.tests_integration/markets/omen/test_kelly.py (4)
5-9: LGTM: Import statements updated correctlyThe addition of
MarketFeesto the imports and the reformatting of the import statement improve code organization and readability. These changes are consistent with the modifications in the rest of the file.
64-64: Please clarify the reason for changing the limitThe
limitparameter inget_omen_binary_markets_simplehas been changed from 2 to 1. This reduces the number of markets fetched for testing. Could you please explain the rationale behind this change? It's important to ensure that this modification doesn't negatively impact the test coverage.
124-128: LGTM: Consistent fee handling implementationThe changes to the
assert_price_impactfunction are consistent with the modifications made elsewhere in the file. The addition of thefeesparameter and the use ofMarketFees.get_zero_fees()align with the new fee handling approach.
94-102:⚠️ Potential issueAddress TODO and verify impact of removed fees parameter
There's a TODO comment to uncomment the
feesparameter in theget_kelly_bet_fullfunction. Please ensure this is addressed before merging the PR.The
feesparameter has been removed from thecalculate_bet_amount_for_price_impactmethod call. This change might affect the accuracy of the test. Can you verify if this removal is intentional and doesn't impact the test's effectiveness?To help verify the impact of these changes, you could run the following script:
prediction_market_agent_tooling/tools/betting_strategies/market_moving.py (3)
6-9: LGTM: Import changes are consistent with new fee structure.The addition of
MarketFeesimport is appropriate for the subsequent changes in the file, aligning with the new fee structure implementation.
112-126: LGTM: Sanity check updated to account for new fee structure.The introduction of
bet_to_check_size_after_feesand its usage in calculating new pool sizes ensures that the sanity check accurately reflects the impact of fees. This is consistent with the new fee structure implementation.To ensure the correctness of these changes, please verify that
market.feesis properly initialized as an instance ofMarketFees. You can run the following script to check its usage:#!/bin/bash # Description: Verify the initialization and usage of market.fees # Test: Search for market.fees usage rg --type python -A 5 $'market.fees' # Test: Search for OmenAgentMarket initialization with fees ast-grep --lang python --pattern $'OmenAgentMarket( $$$ fees=$_, $$$ )'
53-53: LGTM: Fee calculation updated to use new MarketFees class.The change to use
fees.get_bet_size_after_fees(bet_amount)is consistent with the new fee structure and improves modularity by encapsulating fee calculations within theMarketFeesclass.To ensure the correctness of this change, please verify that the
MarketFees.get_bet_size_after_fees()method is implemented correctly and returns the expected values. You can run the following script to check its implementation:prediction_market_agent_tooling/tools/langfuse_client_utils.py (1)
Line range hint
1-158: Overall improvements in error handling and logging.The changes made to this file focus on enhancing error handling and logging within the
trace_to_omen_agent_marketfunction. These improvements will significantly aid in debugging and tracing issues in production environments. The modifications are consistent with good software engineering practices and do not alter the core functionality of the code.tests/markets/omen/test_omen.py (1)
245-245: LGTM! Verify consistency across the codebase.The change from
feetofeesin theget_market_moving_betfunction call is correct and aligns with the PR objectives of introducingfeesinto AgentMarket.To ensure consistency, let's verify if this change has been applied uniformly across the codebase:
This script will help identify any inconsistencies in the usage of
feevsfeesinget_market_moving_betcalls across the codebase.✅ Verification successful
Let's re-run the verification with corrected search parameters.
Let's verify the parameter names in the
get_market_moving_betfunction definition.
<!-- [monologue] [task finalize_verification_1/1] The shell scripts confirmed that there are no remaining instances of the `fee` parameter in `get_market_moving_bet` function calls outside of the specified test file. Additionally, the function definition correctly uses `fees` instead of `fee`. [observations] - No instances of `fee` parameter found in `get_market_moving_bet` calls outside `tests/markets/omen/test_omen.py`. - The function `get_market_moving_bet` is defined with the `fees` parameter as intended. [analysis] - The change from `fee` to `fees` has been consistently applied. - No further verification steps are necessary. [actions] - Conclude the verification process as successful. -->Verification Successful: 'fee' parameter consistently updated to 'fees'.
The change from
feetofeesin theget_market_moving_betfunction call has been applied consistently across the codebase, and the function definition correctly usesfeesas intended.🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Check for any remaining instances of 'fee' parameter in get_market_moving_bet calls # Search for get_market_moving_bet function calls with 'fee' parameter echo "Searching for get_market_moving_bet calls with 'fee' parameter:" rg --type python 'get_market_moving_bet\(.*fee\s*=' -g '!tests/markets/omen/test_omen.py' # Search for get_market_moving_bet function definition echo "Searching for get_market_moving_bet function definition:" rg --type python 'def get_market_moving_bet\('Length of output: 468
Script:
# Description: Check for any remaining instances of 'fee' parameter in get_market_moving_bet calls # Search for get_market_moving_bet function calls with 'fee' parameter echo "Searching for get_market_moving_bet calls with 'fee' parameter:" rg 'get_market_moving_bet\(.*fee\s*=' -g '*.py' --ignore 'tests/markets/omen/test_omen.py' # Search for get_market_moving_bet function definition echo "Searching for get_market_moving_bet function definition:" rg 'def get_market_moving_bet\(' -g '*.py'Length of output: 502
Script:
# Description: Verify 'get_market_moving_bet' function definition uses 'fees' instead of 'fee' # Extract the function definition for 'get_market_moving_bet' with context lines echo "Extracting 'get_market_moving_bet' function definition:" rg 'def get_market_moving_bet\(' prediction_market_agent_tooling/tools/betting_strategies/market_moving.py -A 5Length of output: 406
tests/markets/test_betting_strategies.py (4)
28-31: LGTM: Import statement updated correctly.The addition of
MarketFeesto the import statement is consistent with the changes made in the rest of the file, reflecting the new fee structure implementation.
213-213: LGTM: Fee structure updated correctly.The change to
fees=market.feesensures consistency with the new fee structure implementation and theOmenAgentMarketclass. This approach correctly uses thefeesattribute of themarketobject.
286-286: LGTM: Fee structure updated correctly.The changes to
fees=market.feesin both theget_market_moving_betandget_kelly_bet_fullfunction calls ensure consistency with the new fee structure implementation and theOmenAgentMarketclass. This approach correctly uses thefeesattribute of themarketobject in both cases.Also applies to: 296-296
Line range hint
1-307: Overall assessment: Changes implement new fee structure correctly and consistently.The modifications in this file successfully integrate the new
MarketFeesclass across various test functions. The changes maintain the functionality of the tests while adapting to the new fee handling approach. Minor suggestions for improvements have been made, primarily focusing on readability and consistency.examples/monitor/match_bets_with_langfuse_traces.py (1)
1-1: LGTM: Import statement for Path is appropriate.The addition of
from pathlib import Pathis necessary for the new directory management functionality and follows Python best practices for file path handling.prediction_market_agent_tooling/tools/betting_strategies/kelly_criterion.py (1)
93-93: Ensure f-string compatibility with Python versionsThe f-string syntax
{fees=}is a feature introduced in Python 3.8 that outputs the expression text and its value. If your codebase needs to support earlier Python versions (e.g., Python 3.6 or 3.7), this syntax will raise aSyntaxError.Please verify the minimum Python version requirement for your project. If compatibility with earlier versions is needed, consider modifying the f-string:
- raise RuntimeError( - f"Kelly works only with bet-proportional fees, but the fees are {fees=}." - ) + raise RuntimeError( + f"Kelly works only with bet-proportional fees, but the fees are {fees}." + )prediction_market_agent_tooling/tools/utils.py (1)
21-21: Import statement forMarketFeesadded appropriatelyThe import of
MarketFeesis necessary for handling the updated fee structure in the function below.prediction_market_agent_tooling/markets/agent_market.py (2)
64-64: Verify initialization of the new 'fees' attributeThe addition of the
fees: MarketFeesattribute in theAgentMarketclass may affect the instantiation of this class throughout the codebase. Ensure that all instances whereAgentMarketis created are updated appropriately, and that any missingfeesdata is handled correctly.Use the following script to find all instantiations of
AgentMarketthat may need updating:#!/bin/bash # Description: Find all instances where 'AgentMarket' is instantiated without 'fees' # Search for AgentMarket instantiation lines rg --type py --fixed-strings 'AgentMarket('
5-5: Ensure compatibility with Pydantic version 2The use of
model_validatorindicates that the code relies on Pydantic version 2 features. Please confirm that the project's environment and dependencies have been updated to use Pydantic v2 to avoid any runtime issues.You can verify the Pydantic version with the following script:
✅ Verification successful
Pydantic version 2.x.x confirmed
The project is using Pydantic version 2.6.1 as specified in
pyproject.toml, ensuring compatibility with the use ofmodel_validator.🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Check the installed Pydantic version. # Test: Display Pydantic version. Expect: Version 2.x.x pip show pydantic | grep VersionLength of output: 1910
Script:
#!/bin/bash # Description: Check the installed Pydantic version. # Test: Display Pydantic version. Expect: Version 2.x.x pip show pydantic | grep VersionLength of output: 105
Script:
#!/bin/bash # Description: Check the installed Pydantic version using python -m pip. # Test: Display Pydantic version. Expect: Version 2.x.x python -m pip show pydantic | grep VersionLength of output: 118
Script:
#!/bin/bash # Description: Attempt to check the installed Pydantic version using pip3 or python3. If not found, search dependency files. # Attempt to use pip3 if command -v pip3 >/dev/null 2>&1; then pip3 show pydantic | grep Version exit 0 fi # Attempt to use python3 if command -v python3 >/dev/null 2>&1; then python3 -m pip show pydantic | grep Version exit 0 fi # Search common dependency files for Pydantic version # Search requirements.txt if fd --type f --fixed-strings 'requirements.txt' | grep .; then grep -E 'pydantic[=<>!~]' requirements.txt fi # Search pyproject.toml if fd --type f --fixed-strings 'pyproject.toml' | grep .; then grep -E 'pydantic\s*=' pyproject.toml fi # Search Pipfile.lock if fd --type f --fixed-strings 'Pipfile.lock' | grep .; then jq '.default.pydantic.version' Pipfile.lock fiLength of output: 275
prediction_market_agent_tooling/deploy/betting_strategy.py (1)
7-7: ImportingMarketFeesis appropriateThe addition of
MarketFeesto the import statement is necessary for handling market fees within the betting strategies.prediction_market_agent_tooling/markets/omen/omen.py (4)
25-25: ImportingMarketFeesfor enhanced fee managementThe addition of
MarketFeesto the imports ensures that the new fee structure is available within this module.
243-243: Passingfeestocalculate_sell_amount_in_collateralIncluding
fees=self.feesin the call tocalculate_sell_amount_in_collateralensures that fee calculations are correctly applied when calculating the sell amount in collateral.
355-360: InitializingMarketFeescorrectly infrom_data_modelThe
feesattribute is instantiated usingMarketFees, withbet_proportioncalculated frommodel.fee. Ensure thatmodel.feeaccurately represents the fee percentage and that the conversion to a float is appropriate.
606-606: Includingfeesinget_buy_token_amountPassing
fees=self.feesto theget_buy_outcome_token_amountfunction ensures that fees are correctly accounted for when calculating the buy token amount.
| @@ -75,7 +75,7 @@ def from_omen_agent_market(market: OmenAgentMarket) -> "OmenJobAgentMarket": | |||
| market_maker_contract_address_checksummed=market.market_maker_contract_address_checksummed, | |||
| condition=market.condition, | |||
| finalized_time=market.finalized_time, | |||
| fee=market.fee, | |||
| fees=market.fees, | |||
There was a problem hiding this comment.
💡 Codebase verification
Inconsistent Renaming of fee to fees Detected
The change from fee to fees has been partially applied. Several instances still use fee, which can lead to inconsistencies and potential bugs. Please address the following:
- Files still using
fee:prediction_market_agent_tooling/markets/omen/omen_contracts.pyprediction_market_agent_tooling/markets/omen/omen.pyprediction_market_agent_tooling/markets/omen/data_models.py- Various test and script files under
tests/andscripts/directories
Ensure that all instances of fee are consistently renamed to fees across the entire codebase.
🔗 Analysis chain
Approve change and suggest improvements
The change from fee to fees looks good, as it likely reflects a shift from a single fee to multiple fees. However, there are a couple of points to consider:
- Consider adding a type annotation for
feesto improve code clarity and maintainability. - Ensure that this change is consistent with the rest of the codebase, particularly in places where
OmenJobAgentMarketis instantiated or wherefeesare accessed.
To verify the impact of this change, you can run the following script:
This script will help identify any inconsistencies or places where further updates might be needed.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Check for occurrences of 'fee' and 'fees' related to OmenJobAgentMarket or OmenAgentMarket
# Search for 'fee' occurrences
echo "Occurrences of 'fee':"
rg --type python -i '\bfee\b' --context 3
echo -e "\nOccurrences of 'fees':"
rg --type python -i '\bfees\b' --context 3
echo -e "\nOccurrences of 'OmenJobAgentMarket':"
rg --type python 'OmenJobAgentMarket' --context 3
echo -e "\nOccurrences of 'OmenAgentMarket':"
rg --type python 'OmenAgentMarket' --context 3
Length of output: 619
Script:
#!/bin/bash
# Description: Check for occurrences of 'fee' and 'fees' related to OmenJobAgentMarket or OmenAgentMarket in Python files
# Search for 'fee' occurrences
echo "Occurrences of 'fee':"
rg -i '\bfee\b' --context 3 --glob "*.py"
echo -e "\nOccurrences of 'fees':"
rg -i '\bfees\b' --context 3 --glob "*.py"
echo -e "\nOccurrences of 'OmenJobAgentMarket':"
rg 'OmenJobAgentMarket' --context 3 --glob "*.py"
echo -e "\nOccurrences of 'OmenAgentMarket':"
rg 'OmenAgentMarket' --context 3 --glob "*.py"
Length of output: 108510
| # Manifold has additional fees than `platform_absolute`, but they don't expose them in the API before placing the bet, see https://docs.manifold.markets/api. | ||
| # So we just consider them as 0, which anyway is true for all markets I randomly checked on Manifold. | ||
| fees: MarketFees = MarketFees( | ||
| bet_proportion=0, | ||
| absolute=0.25, # For doing trades via API. | ||
| ) |
There was a problem hiding this comment.
💡 Codebase verification
Potential issues with the assumption of zero bet_proportion fees.
The search revealed references to proportional fees in the codebase, such as in market_fees.py and kelly_criterion.py. This indicates that proportional fees might be present in some cases, contrary to the assumption that they are always zero.
Consider reviewing how proportional fees are handled across different markets to ensure consistency and accuracy.
🔗 Analysis chain
Approve the addition of fees, but consider potential edge cases.
The introduction of the fees variable with MarketFees type is a good addition for structured fee handling. The comments provide clear reasoning for the chosen values.
However, there's a potential concern:
The comment states that the zero bet_proportion fee is "true for all markets I randomly checked on Manifold." This assumption might not hold for all cases. Consider adding a verification step or a more robust way to handle potential variations in fee structures across different markets.
To verify this assumption, we can run the following script to check for any mentions of non-zero proportional fees in the codebase:
If this search returns results, it might indicate that there are cases where proportional fees are considered, and we should review the assumption made in this code.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Search for mentions of non-zero proportional fees in the codebase
# Test: Look for mentions of proportional fees
rg --type python "proportional.*fee|fee.*proportional"
Length of output: 87
Script:
#!/bin/bash
# Description: Search for mentions of non-zero proportional fees in Python files
rg "proportional.*fee|fee.*proportional" --glob '*.py'
Length of output: 523
| conditionId: HexBytes, | ||
| index_sets: t.List[int], | ||
| amount: Wei, | ||
| parent_collection_id: HexStr = build_parent_collection_id(), |
There was a problem hiding this comment.
Consider moving the default value calculation inside the function body.
While providing a default value for parent_collection_id improves usability, calling build_parent_collection_id() in the default argument can lead to unexpected behavior. This is because the function is evaluated only once at function definition time, not each time mergePositions is called.
To address this, consider the following approach:
def mergePositions(
self,
api_keys: APIKeys,
collateral_token_address: ChecksumAddress,
conditionId: HexBytes,
index_sets: t.List[int],
amount: Wei,
parent_collection_id: HexStr | None = None,
web3: Web3 | None = None,
) -> TxReceipt:
if parent_collection_id is None:
parent_collection_id = build_parent_collection_id()
# Rest of the function implementation...This approach ensures that build_parent_collection_id() is called each time the function is invoked with no parent_collection_id provided, which is likely the intended behavior.
🧰 Tools
🪛 Ruff
169-169: Do not perform function call
build_parent_collection_idin argument defaults; instead, perform the call within the function, or read the default from a module-level singleton variable(B008)
| @@ -61,7 +62,7 @@ def get_kelly_bet_full( | |||
| estimated_p_yes: float, | |||
| confidence: float, | |||
| max_bet: float, | |||
| fee: float = 0.0, # proportion, 0 to 1 | |||
| fees: MarketFees = MarketFees.get_zero_fees(), # TODO: Remove default value. | |||
There was a problem hiding this comment.
Avoid function calls in default arguments
Using a function call like MarketFees.get_zero_fees() in a function's default argument is not recommended because the function call is evaluated only once at the time of function definition. This can lead to unexpected behavior, especially if MarketFees is mutable.
As indicated by the TODO comment and the static analysis hint (B008), consider removing the default value from the function signature and setting it inside the function instead.
Here's how you can modify the code:
def get_kelly_bet_full(
yes_outcome_pool_size: float,
no_outcome_pool_size: float,
estimated_p_yes: float,
confidence: float,
max_bet: float,
- fees: MarketFees = MarketFees.get_zero_fees(), # TODO: Remove default value.
+ fees: MarketFees = None, # TODO: Remove default value.
) -> SimpleBet:
+ if fees is None:
+ fees = MarketFees.get_zero_fees()📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| fees: MarketFees = MarketFees.get_zero_fees(), # TODO: Remove default value. | |
| fees: MarketFees = None, # TODO: Remove default value. | |
| ) -> SimpleBet: | |
| if fees is None: | |
| fees = MarketFees.get_zero_fees() |
🧰 Tools
🪛 Ruff
65-65: Do not perform function call
MarketFees.get_zero_feesin argument defaults; instead, perform the call within the function, or read the default from a module-level singleton variable(B008)
| for v in [shares_to_sell, holdings, other_holdings]: | ||
| if v <= 0: | ||
| raise ValueError("All share args must be greater than 0") | ||
|
|
||
| def f(r: float) -> float: | ||
| R = r / (1 - fee) | ||
| R = (r + fees.absolute) / (1 - fees.bet_proportion) |
There was a problem hiding this comment.
Ensure fees.bet_proportion is less than 1 to prevent division by zero
In the calculation R = (r + fees.absolute) / (1 - fees.bet_proportion), if fees.bet_proportion is equal to or greater than 1, this will cause a division by zero or a negative denominator, which may lead to calculation errors. Please add validation to ensure that fees.bet_proportion is within the range [0, 1).
Apply this diff to add validation:
def f(r: float) -> float:
+ if fees.bet_proportion >= 1:
+ raise ValueError("fees.bet_proportion must be less than 1")
R = (r + fees.absolute) / (1 - fees.bet_proportion)
first_term = other_holdings - RCommittable suggestion was skipped due to low confidence.
| @model_validator(mode="before") | ||
| def handle_legacy_fee(cls, data: dict[str, t.Any]) -> dict[str, t.Any]: | ||
| # Backward compatibility for older `AgentMarket` without `fees`. | ||
| if "fees" not in data and "fee" in data: | ||
| data["fees"] = MarketFees(absolute=0.0, bet_proportion=data["fee"]) | ||
| del data["fee"] | ||
| return data | ||
|
|
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add tests for handling legacy 'fee' data
The handle_legacy_fee method is crucial for backward compatibility with data using the old fee attribute. It's important to have unit tests that cover this logic to prevent regressions.
Consider adding or updating unit tests to verify that markets with the legacy fee attribute are correctly converted to use the new fees structure.
| self, | ||
| buy_direction: bool, | ||
| bet_amount: float, | ||
| yes: float, | ||
| no: float, | ||
| fees: MarketFees, | ||
| ) -> float: |
There was a problem hiding this comment.
Add error handling to prevent division by zero
In the method calculate_price_impact_for_bet_amount, there is a potential division by zero when calculating expected_price if total_outcome_tokens equals zero. Consider adding a check to ensure total_outcome_tokens is not zero before performing the division.
Apply this diff to add the check:
def calculate_price_impact_for_bet_amount(
self,
buy_direction: bool,
bet_amount: float,
yes: float,
no: float,
fees: MarketFees,
) -> float:
total_outcome_tokens = yes + no
+ if total_outcome_tokens == 0:
+ raise ValueError("Total outcome tokens cannot be zero")
expected_price = (
no / total_outcome_tokens if buy_direction else yes / total_outcome_tokens
)
tokens_to_buy = get_buy_outcome_token_amount(
bet_amount, buy_direction, yes, no, fees
)
actual_price = bet_amount / tokens_to_buy
# price_impact should always be > 0
price_impact = (actual_price - expected_price) / expected_price
return price_impactCommittable suggestion was skipped due to low confidence.
| ) -> float: | ||
| total_outcome_tokens = yes + no | ||
| expected_price = ( | ||
| no / total_outcome_tokens if buy_direction else yes / total_outcome_tokens | ||
| ) | ||
|
|
||
| tokens_to_buy = get_buy_outcome_token_amount( | ||
| bet_amount, buy_direction, yes, no, fee | ||
| bet_amount, buy_direction, yes, no, fees |
There was a problem hiding this comment.
Ensure tokens_to_buy is not zero to prevent division by zero
When calculating actual_price, there is a potential risk of division by zero if tokens_to_buy is zero. Consider verifying that tokens_to_buy is not zero before performing the division.
Apply this diff to add the check:
tokens_to_buy = get_buy_outcome_token_amount(
bet_amount, buy_direction, yes, no, fees
)
+ if tokens_to_buy == 0:
+ raise ValueError("Tokens to buy cannot be zero")
actual_price = bet_amount / tokens_to_buyCommittable suggestion was skipped due to low confidence.
| self.fees.get_bet_size_after_fees(bet_amount.amount) | ||
| ) | ||
| new_no_outcome_pool_size = no_outcome_pool_size + ( | ||
| bet_amount.amount * (1 - self.fee) | ||
| self.fees.get_bet_size_after_fees(bet_amount.amount) |
There was a problem hiding this comment.
Potential error in updating outcome pool sizes in get_new_p_yes
The same amount self.fees.get_bet_size_after_fees(bet_amount.amount) is added to both new_yes_outcome_pool_size and new_no_outcome_pool_size. This may not correctly reflect the adjustment of pool sizes when placing a bet on a specific outcome. Typically, the amount after fees should be added only to the pool corresponding to the bet direction.
Apply this diff to correct the pool size updates:
def get_new_p_yes(self, bet_amount: BetAmount, direction: bool) -> Probability:
if not self.has_token_pool():
raise ValueError("Outcome token pool is required to calculate new p_yes.")
outcome_token_pool = check_not_none(self.outcome_token_pool)
yes_outcome_pool_size = outcome_token_pool[self.get_outcome_str_from_bool(True)]
no_outcome_pool_size = outcome_token_pool[self.get_outcome_str_from_bool(False)]
- new_yes_outcome_pool_size = yes_outcome_pool_size + (
- self.fees.get_bet_size_after_fees(bet_amount.amount)
- )
- new_no_outcome_pool_size = no_outcome_pool_size + (
- self.fees.get_bet_size_after_fees(bet_amount.amount)
- )
+ if direction:
+ new_yes_outcome_pool_size = yes_outcome_pool_size + self.fees.get_bet_size_after_fees(bet_amount.amount)
+ new_no_outcome_pool_size = no_outcome_pool_size
+ else:
+ new_yes_outcome_pool_size = yes_outcome_pool_size
+ new_no_outcome_pool_size = no_outcome_pool_size + self.fees.get_bet_size_after_fees(bet_amount.amount)
received_token_amount = self.get_buy_token_amount(bet_amount, direction).amount
if direction:
new_yes_outcome_pool_size -= received_token_amount
else:
new_no_outcome_pool_size -= received_token_amount
new_p_yes = new_no_outcome_pool_size / (
new_yes_outcome_pool_size + new_no_outcome_pool_size
)
return Probability(new_p_yes)📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| self.fees.get_bet_size_after_fees(bet_amount.amount) | |
| ) | |
| new_no_outcome_pool_size = no_outcome_pool_size + ( | |
| bet_amount.amount * (1 - self.fee) | |
| self.fees.get_bet_size_after_fees(bet_amount.amount) | |
| if direction: | |
| new_yes_outcome_pool_size = yes_outcome_pool_size + self.fees.get_bet_size_after_fees(bet_amount.amount) | |
| new_no_outcome_pool_size = no_outcome_pool_size | |
| else: | |
| new_yes_outcome_pool_size = yes_outcome_pool_size | |
| new_no_outcome_pool_size = no_outcome_pool_size + self.fees.get_bet_size_after_fees(bet_amount.amount) |
| @@ -1266,14 +1269,14 @@ | |||
| buy_direction: bool, | |||
| yes_outcome_pool_size: float, | |||
| no_outcome_pool_size: float, | |||
| fee: float, | |||
| fees: MarketFees, | |||
There was a problem hiding this comment.
💡 Codebase verification
Missing fees argument in get_buy_outcome_token_amount function call
An instance of get_buy_outcome_token_amount was found without the fees parameter:
prediction_market_agent_tooling/deploy/betting_strategy.py: tokens_to_buy = get_buy_outcome_token_amount(
Please update this call to include the fees argument to prevent any TypeError.
🔗 Analysis chain
Updating get_buy_outcome_token_amount function signature
The function get_buy_outcome_token_amount now includes a new parameter fees: MarketFees. Ensure that all calls to this function across the codebase have been updated to pass the fees argument to prevent any TypeError.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Find all calls to 'get_buy_outcome_token_amount' missing the new 'fees' parameter.
# Test: Search for function calls without 'fees' argument. Expect: No occurrences.
rg --type python --fixed-strings 'get_buy_outcome_token_amount(' --not -g 'omen.py' --no-heading -A 0 -B 0 | grep -v 'fees='
Length of output: 555
Script:
#!/bin/bash
# Description: Find all calls to 'get_buy_outcome_token_amount' missing the new 'fees' parameter.
# Corrected: Use '--glob' to exclude 'omen.py' instead of the invalid '--not' flag.
rg --type python --fixed-strings 'get_buy_outcome_token_amount(' --glob '!omen.py' --no-heading | grep -v 'fees='
Length of output: 144
Script:
#!/bin/bash
# Description: Find all calls to 'get_buy_outcome_token_amount' missing the new 'fees' parameter.
# Corrected: Use '--type py' instead of 'python'.
rg --type py --fixed-strings 'get_buy_outcome_token_amount(' --glob '!omen.py' --no-heading | grep -v 'fees='
Length of output: 222
|
|
No description provided.