fix(torii): ensure correct serde of args in config file #2704
Conversation
WalkthroughOhayo, sensei! This pull request introduces several enhancements to the Torii project, primarily focusing on the command-line interface (CLI) and dependency management. A new dependency, Changes
Possibly related PRs
Suggested reviewers
🪧 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
Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Outside diff range and nitpick comments (4)
bin/torii/src/cli.rs (1)
9-14: Clean and efficient CLI structure implementation!The
Clistruct implementation demonstrates good practices:
- Uses
clap::Parserderive macro for automatic CLI argument parsing- Properly configured command attributes for name, author, version, and description
- Smart use of
#[command(flatten)]to incorporateToriiArgsfields directlyThis aligns with the PR objective of removing version from
ToriiArgswhile maintaining clean configuration handling.Consider adding examples in the command's long help text using
long_aboutfor better user experience. For instance:-#[command(name = "torii", author, version, about, long_about = None)] +#[command( + name = "torii", + author, + version, + about, + long_about = "Torii server for Dojo engine\n\nExample:\n torii --world-address 0x123..." +)]crates/torii/core/src/types.rs (1)
159-163: Consider adding documentation for the Display implementationWhile the implementation is clear, it would be helpful to add documentation explaining the format and its intended use in configuration files.
+/// Formats a Contract as "{type}:{address}" where address is in lowercase hex. +/// This format is used for serialization in configuration files. impl std::fmt::Display for Contract {bin/torii/src/main.rs (1)
Line range hint
52-248: Consider breaking down the main function, sensei!The main function handles multiple responsibilities including:
- Configuration initialization
- Database setup
- Server initialization
- Component orchestration
This could be split into smaller, focused functions for better maintainability.
Consider extracting these into separate functions:
async fn initialize_database(args: &Args) -> Result<SqlitePool> { // Database initialization logic } async fn initialize_servers( pool: Arc<SqlitePool>, args: &Args, shutdown_tx: Sender<()> ) -> Result<(Engine, Executor, Vec<JoinHandle<()>>)> { // Server initialization logic } async fn main() -> anyhow::Result<()> { let args = Cli::parse().args.with_config_file()?; let pool = initialize_database(&args).await?; let (engine, executor, handles) = initialize_servers(pool, &args, shutdown_tx).await?; // Main orchestration logic }crates/torii/cli/src/options.rs (1)
332-343: Ohayo! Implementation looks solid, but let's add tests!The serialization logic is well-implemented with proper error handling. However, it would be beneficial to add unit tests to verify the serialization format matches the expected output, especially since this is a critical part of the config file handling.
Would you like me to help generate unit tests for the
serialize_contractsfunction? We should test various scenarios including:
- Empty vector
- Single contract
- Multiple contracts
- Different contract types
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
⛔ Files ignored due to path filters (1)
Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (6)
bin/torii/Cargo.toml(1 hunks)bin/torii/src/cli.rs(1 hunks)bin/torii/src/main.rs(2 hunks)crates/torii/cli/src/args.rs(1 hunks)crates/torii/cli/src/options.rs(3 hunks)crates/torii/core/src/types.rs(1 hunks)
🔇 Additional comments (11)
bin/torii/src/cli.rs (1)
1-5: Ohayo! Well-documented module purpose and design decisions, sensei!
The documentation clearly explains the module's purpose and future extensibility considerations. This forward-thinking approach aligns well with the PR's objectives of improving configuration handling.
bin/torii/Cargo.toml (1)
15-15: Ohayo! The new dependency looks good, sensei!
The addition of clap_complete with workspace version is well-placed and follows the project's dependency management pattern.
crates/torii/core/src/types.rs (2)
159-163: Ohayo sensei! The Display implementation looks good!
The implementation provides a clean string representation of Contract instances, formatting them as {type}:{address}. This aligns well with the PR's objective of ensuring correct serialization in config files.
159-163: Verify the string format usage in CLI serialization
Let's ensure this format is consistently used in the CLI serialization code.
✅ Verification successful
Display implementation is correctly used in CLI serialization, sensei!
The Contract's Display implementation (type:address) format is perfectly aligned with:
- CLI parsing in
parse_erc_contractwhich expectstype:addressformat - CLI serialization which uses
contract.to_string()to serialize back to the same format - CLI deserialization which parses the string using the same format
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Search for usage of Contract serialization in CLI code
rg -t rust "serialize.*Contract" crates/torii/cli/
Length of output: 296
Script:
#!/bin/bash
# Let's check the implementation of these serialize/deserialize functions
rg -A 10 -B 2 "serialize_contracts|deserialize_contracts" crates/torii/cli/src/options.rs
Length of output: 1261
Script:
#!/bin/bash
# Let's check how the contract is parsed to understand the format
rg -A 10 "parse_erc_contract" crates/torii/cli/src/options.rs
Length of output: 1309
crates/torii/cli/src/args.rs (2)
Line range hint 1-256: Ohayo sensei! Excellent implementation of args handling!
The implementation demonstrates robust handling of CLI arguments and configuration files with:
- Clear precedence rules (CLI over config file)
- Proper serialization/deserialization
- Comprehensive test coverage
- Clean separation of concerns
This aligns perfectly with the PR objective of ensuring correct serde of args in the config file.
17-17: Ohayo sensei! Version removal looks good!
Removing the version from ToriiArgs is a positive change that aligns with the PR objectives. This modification will allow the torii/cli crates to be reused without version conflicts when imported as a dependency.
Let's verify there are no remaining version dependencies:
✅ Verification successful
Ohayo sensei! The version removal is indeed verified!
The removal of the version attribute from ToriiArgs is safe and aligns with the codebase. The search results confirm that:
- The version attribute is correctly removed from the command in
crates/torii/cli/src/args.rs - Other binaries in the codebase (
sozo,katana, etc.) maintain their own version attributes independently - No other parts of the codebase depend on the version from
ToriiArgs
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Check for any remaining version-related code
# Test: Search for version-related attributes or methods
rg -i 'version|vers' --type rust
Length of output: 44196
bin/torii/src/main.rs (2)
21-21: Ohayo sensei! Clean modularization of CLI concerns!
The separation of CLI logic into a dedicated module improves code organization and maintainability.
Also applies to: 49-49
53-53: Verify CLI backward compatibility, sensei!
While the new Cli structure improves reusability, let's ensure existing command-line usage patterns are preserved.
✅ Verification successful
Ohayo sensei! CLI backward compatibility is preserved
The change from ToriiArgs::parse() to Cli::parse().args maintains backward compatibility because:
- The
Clistruct wrapsToriiArgsand delegates to its parsing functionality - The
with_config_file()method continues to work as before - Test cases in
crates/torii/cli/src/args.rsverify the expected behavior:- Command-line arguments take precedence over config file
- All existing ToriiArgs fields are preserved and parsed correctly
- Config file parsing remains unchanged
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Check for any changes in command-line argument patterns
# Search for ToriiArgs usage patterns in tests and documentation
rg -t rust "ToriiArgs::" -A 3
rg -t md "torii.*--" -A 3
# Look for any command-line examples in documentation
fd -t f "README" -X cat {} 2>/dev/null | rg "torii.*--" -A 3
Length of output: 843
Script:
#!/bin/bash
# Let's check the implementation and usage of both Cli and ToriiArgs
# Check Cli implementation
ast-grep --pattern 'struct Cli {
$$$
}'
# Check ToriiArgs implementation and its fields
ast-grep --pattern 'struct ToriiArgs {
$$$
}'
# Check for any CLI argument parsing tests
rg -t rust "test.*cli|test.*args" -B 2 -A 5
# Check for command-line argument handling
ast-grep --pattern 'fn parse($$$) {
$$$
}'
# Look for any integration tests that might use CLI
fd -e rs -t f integration_test -X cat {}
Length of output: 4717
Script:
#!/bin/bash
# Let's look more specifically at the CLI argument handling changes
# Check the implementation of with_config_file
ast-grep --pattern 'fn with_config_file($$$) {
$$$
}'
# Look for CLI argument parsing in main.rs files
fd -t f "main.rs" -X cat {}
# Check for any argument parsing tests
rg -t rust "parse.*args|args.*parse" -B 2 -A 5
# Look for any CLI usage examples in tests
rg -t rust "Cli::parse|ToriiArgs::parse" -B 2 -A 5
Length of output: 48938
crates/torii/cli/src/options.rs (3)
6-6: Ohayo sensei! LGTM on the SerializeSeq import!
The import is correctly placed and necessary for the sequence serialization implementation.
145-147: Symmetrical serde implementation looks good!
The addition of serialize_with complements the existing deserialize_with, ensuring consistent contract handling in both directions.
338-340: Verify Contract's Display implementation
The serialization relies on contract.to_string(). Let's verify the Display implementation matches the expected format for the config file.
✅ Verification successful
Display implementation is correct and consistent
The Contract's Display implementation in crates/torii/core/src/types.rs matches the format expected by parse_erc_contract:
- Display outputs
{type}:{address}format (e.g. "ERC20:0x123") - This matches the parsing logic in
parse_erc_contractwhich splits on ':' - ContractType's Display implementation correctly outputs the type strings that ContractType::from_str accepts
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Find and verify Contract's Display implementation
# Expected: Implementation that matches the format used in parse_erc_contract
# Look for Display implementation for Contract
ast-grep --pattern 'impl Display for Contract {
$$$
fn fmt($_, $_, $_) {
$$$
}
}'
# Look for any tests of the Display implementation
rg -l "impl.*Display.*for.*Contract" | xargs rg "mod.*test.*Display"
Length of output: 164
Script:
#!/bin/bash
# Let's try a different approach to find the Contract type and its Display implementation
# First, find the Contract type definition
ast-grep --pattern 'struct Contract {
$$$
}'
# Look for Display implementation with a more flexible pattern
ast-grep --pattern 'impl Display for Contract'
# Search for Contract type and Display implementation using ripgrep
rg "struct Contract" -A 10
rg "impl.*Display.*Contract" -A 10
# Look for contract parsing code that might show expected format
rg "parse.*contract" -A 10
Length of output: 53367
| @@ -12,6 +12,7 @@ base64.workspace = true | |||
| camino.workspace = true | |||
| chrono.workspace = true | |||
| clap.workspace = true | |||
| clap_complete.workspace = true | |||
There was a problem hiding this comment.
💡 Codebase verification
Ohayo sensei! The clap_complete dependency in torii seems unused!
The dependency is added to torii's Cargo.toml but there's no actual usage of it in the crate. While clap_complete is properly used in katana and sozo for shell completion generation, it appears to be an unnecessary dependency for torii at this time.
- Consider removing
clap_completefrombin/torii/Cargo.tomlif there are no immediate plans to implement shell completions for torii
🔗 Analysis chain
Let's verify the usage of clap_complete, sensei!
We should ensure this new dependency is being utilized in the codebase.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Check if clap_complete is being used in the codebase
# Search for clap_complete usage in Rust files
rg -t rust "use.*clap_complete"
# Search for shell completion generation code
ast-grep --pattern 'clap_complete::generate'
Length of output: 323
Script:
#!/bin/bash
# Let's check if clap_complete is also used in the torii crate
rg -t rust "use.*clap_complete" bin/torii/
# Check for any shell completion generation in torii
ast-grep --pattern 'clap_complete::generate' bin/torii/
# Let's see if there's a completions command or similar functionality
rg -t rust "completions" bin/torii/
Length of output: 136
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Outside diff range and nitpick comments (1)
crates/katana/cli/src/options.rs (1)
Line range hint
58-373: Ohayo sensei! Consider enhancing the documentationWhile the implementations are solid, it would be helpful to document the actual default values in the struct field documentation. For example:
/// The metrics will be served at the given port. /// Default: 8081 #[arg(requires = "metrics")] #[arg(long = "metrics.port", value_name = "PORT")] #[arg(default_value_t = DEFAULT_METRICS_PORT)] #[serde(default = "default_metrics_port")] pub metrics_port: u16,
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
📒 Files selected for processing (1)
crates/katana/cli/src/options.rs(2 hunks)
🔇 Additional comments (3)
crates/katana/cli/src/options.rs (3)
Line range hint 58-66: Ohayo sensei! LGTM - Default implementation for MetricsOptions looks good!
The implementation correctly uses the predefined constants and aligns with the struct's field documentation.
Line range hint 111-121: Ohayo sensei! The ServerOptions default implementation is well-structured!
The implementation provides secure defaults and correctly uses the predefined constants. Setting http_cors_origins to None by default is a good security practice.
370-373: Ohayo sensei! The default_page_size function is properly implemented!
The function follows the established pattern for default value functions and is correctly feature-gated.
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #2704 +/- ##
==========================================
- Coverage 56.17% 56.15% -0.02%
==========================================
Files 411 411
Lines 52947 52958 +11
==========================================
- Hits 29742 29738 -4
- Misses 23205 23220 +15 ☔ View full report in Codecov by Sentry. 🚨 Try these New Features:
|
Description
This PR ensures that the serialized contracts in a config files are actually compliant with the expected format.
Also, the version of Torii is now removed from the
ToriiArgsto be used at the binary level. This helps re-using thetorii/clicrates without havingversionconflicting with the binary importing the crate.Summary by CodeRabbit
Release Notes
New Features
Improvements
IndexingOptionsstruct for better handling during serialization processes.Contractinstances, improving usability.Bug Fixes
ToriiArgsto streamline command-line interactions.