Refactor main module into smaller components#59
Conversation
Reviewer's GuideThis PR refactors the monolithic main.rs by extracting distinct functionalities—review thread fetching, summary generation, issue retrieval, configuration loading, and test utilities—into dedicated modules, reducing code duplication and improving maintainability. Class diagram for extracted review thread types and functionsclassDiagram
class ReviewThread {
+String id
+bool is_resolved
+CommentConnection comments
}
class CommentConnection {
+Vec~ReviewComment~ nodes
+PageInfo page_info
}
class ReviewComment {
+String body
+String diff_hunk
+Option<i32> original_position
+Option<i32> position
+String path
+String url
+Option<User> author
}
class PageInfo {
+bool has_next_page
+Option<String> end_cursor
}
class User {
+String login
}
ReviewThread --> CommentConnection : comments
CommentConnection --> ReviewComment : nodes
ReviewComment --> User : author
ReviewThread --> PageInfo : page_info
CommentConnection --> PageInfo : page_info
class review_threads {
+fetch_review_threads(client, repo, number)
}
Class diagram for summary module utilitiesclassDiagram
class summary {
+summarize_files(threads: &[ReviewThread]) Vec<(String, usize)>
+write_summary<W: Write>(out: W, summary: &[(String, usize)])
+print_summary(summary: &[(String, usize)])
+print_end_banner()
}
Class diagram for issues moduleclassDiagram
class Issue {
+String title
+String body
}
class issues {
+fetch_issue(client, repo, number) Issue
}
Class diagram for configuration loading helperclassDiagram
class config {
+load_with_reference_fallback<T>(cli_args: T) Result<T, OrthoError>
}
Class diagram for test utilities moduleclassDiagram
class test_utils {
+set_var(key, value)
+remove_var(key)
}
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
|
Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. Summary by CodeRabbit
WalkthroughModularise the codebase by extracting configuration loading, GitHub issue fetching, review thread retrieval, summary generation, and test utilities into dedicated modules. Remove local definitions from Changes
Sequence Diagram(s)sequenceDiagram
participant CLI
participant Config
participant Issues
participant ReviewThreads
participant Summary
CLI->>Config: load_with_reference_fallback(args)
Config-->>CLI: Result<Config>
CLI->>Issues: fetch_issue(client, repo, number)
Issues-->>CLI: Issue
CLI->>ReviewThreads: fetch_review_threads(client, repo, pr_number)
ReviewThreads-->>CLI: Vec<ReviewThread>
CLI->>Summary: summarize_files(threads)
Summary-->>CLI: Vec<(file, count)>
CLI->>Summary: print_summary(summary)
Summary-->>CLI: (prints to stdout)
CLI->>Summary: print_end_banner()
Summary-->>CLI: (prints to stdout)
Estimated code review effort🎯 4 (Complex) | ⏱️ ~40 minutes Possibly related PRs
Poem
✨ Finishing Touches
🧪 Generate unit tests
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey @leynos - I've reviewed your changes and they look great!
Prompt for AI Agents
Please address the comments from this code review:
## Individual Comments
### Comment 1
<location> `src/review_threads.rs:151` </location>
<code_context>
- repo: &RepoInfo,
- number: u64,
-) -> Result<Vec<ReviewThread>, VkError> {
- let mut threads = paginate(|cursor| fetch_thread_page(client, repo, number, cursor)).await?;
- threads.retain(|t| !t.is_resolved);
-
</code_context>
<issue_to_address>
Potential performance issue: all threads are fetched before filtering unresolved ones.
If possible, apply the unresolved filter in the GraphQL query to minimize data transfer and improve efficiency.
Suggested implementation:
```rust
let mut threads = paginate(|cursor| fetch_thread_page(client, repo, number, cursor, Some(false))).await?;
```
section.
Here are the code changes:
<file_operations>
<file_operation operation="edit" file_path="src/review_threads.rs">
<<<<<<< SEARCH
let mut threads = paginate(|cursor| fetch_thread_page(client, repo, number, cursor)).await?;
threads.retain(|t| !t.is_resolved);
=======
let mut threads = paginate(|cursor| fetch_thread_page(client, repo, number, cursor, Some(false))).await?;
>>>>>>> REPLACE
</file_operation>
</file_operations>
<additional_changes>
1. Update the signature of `fetch_thread_page` to accept an additional parameter, e.g., `only_unresolved: Option<bool>`.
2. Update the GraphQL query in `fetch_thread_page` (and possibly in `THREADS_QUERY`) to include a filter for unresolved threads, if supported by the GitHub API. For example, add a `isResolved: false` argument if available.
3. Pass the `only_unresolved` parameter through to the query construction.
4. Remove the `.retain(|t| !t.is_resolved);` line entirely, as shown above.
5. If the GitHub API does not support server-side filtering, document this and revert to client-side filtering.
</issue_to_address>
### Comment 2
<location> `src/review_threads.rs:13` </location>
<code_context>
- body: String,
-}
-
-#[derive(Debug, Deserialize, Default)]
-struct ReviewThreadConnection {
- nodes: Vec<ReviewThread>,
</code_context>
<issue_to_address>
Consider replacing the multiple connection and wrapper structs with a single generic Connection<T> and NodeWrapper<T> to reduce boilerplate.
Here’s one way to collapse much of that boilerplate without losing any functionality:
1. Introduce a single, generic `Connection<T>` and a tiny `NodeWrapper<T>`:
```rust
#[derive(Debug, Deserialize)]
struct Connection<T> {
nodes: Vec<T>,
#[serde(rename = "pageInfo")]
page_info: PageInfo,
}
#[derive(Debug, Deserialize)]
struct NodeWrapper<T> {
node: Option<T>,
}
```
2. Alias your two current connection types to that:
```rust
type ReviewThreadConnection = Connection<ReviewThread>;
type CommentConnection = Connection<ReviewComment>;
```
3. Kill `CommentNode`/`CommentNodeWrapper` entirely and simplify your two fetch functions:
```rust
async fn fetch_comment_page(
client: &GraphQLClient,
id: &str,
cursor: Option<String>,
) -> Result<(Vec<ReviewComment>, PageInfo), VkError> {
// Use our generic NodeWrapper + Connection
let NodeWrapper { node } = client
.run_query(COMMENT_QUERY, json!({ "id": id, "cursor": cursor }))
.await?;
let Connection { nodes, page_info } = node
.ok_or_else(|| VkError::BadResponse(format!("Missing comment node id={id}")))?;
Ok((nodes, page_info))
}
async fn fetch_thread_page(
client: &GraphQLClient,
repo: &RepoInfo,
number: u64,
cursor: Option<String>,
) -> Result<(Vec<ReviewThread>, PageInfo), VkError> {
#[derive(Deserialize)]
struct PullRequestData {
#[serde(rename = "reviewThreads")]
review_threads: ReviewThreadConnection,
}
#[derive(Deserialize)]
struct RepoData {
#[serde(rename = "pullRequest")]
pull_request: PullRequestData,
}
#[derive(Deserialize)]
struct ThreadData {
repository: RepoData,
}
let ThreadData { repository } = client
.run_query(
THREADS_QUERY,
json!({
"owner": repo.owner,
"name": repo.name,
"number": number,
"cursor": cursor,
}),
)
.await?;
let Connection { nodes, page_info } = repository
.pull_request
.review_threads;
Ok((nodes, page_info))
}
```
4. Your `ReviewThread` stays the same but now reuses `CommentConnection`:
```rust
#[derive(Debug, Deserialize)]
pub struct ReviewThread {
pub id: String,
#[serde(rename = "isResolved")]
pub is_resolved: bool,
pub comments: CommentConnection,
}
```
By doing this you:
- Remove 4–5 tiny wrapper structs.
- Collapse two connection types into one generic.
- Keep pagination/merge logic exactly as-is.
- Retain full serde support (and error paths).
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
♻️ Duplicate comments (2)
src/review_threads.rs (2)
151-152: Performance: Apply unresolved filter in GraphQL queryFetching all threads before filtering wastes bandwidth and processing time.
13-38: Reduce boilerplate with generic Connection patternThe multiple wrapper structs create unnecessary complexity.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (6)
src/config.rs(1 hunks)src/issues.rs(1 hunks)src/main.rs(3 hunks)src/review_threads.rs(1 hunks)src/summary.rs(1 hunks)src/test_utils.rs(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
⚙️ CodeRabbit Configuration File
**/*.rs: * Seek to keep the cyclomatic complexity of functions no more than 12.
Adhere to single responsibility and CQRS
Place function attributes after doc comments.
Do not use
returnin single-line functions.Move conditionals with >2 branches into a predicate function.
Avoid
unsafeunless absolutely necessary.Every module must begin with a
//!doc comment that explains the module's purpose and utility.Comments and docs must follow en-GB-oxendict (-ize / -our) spelling and grammar
Lints must not be silenced except as a last resort.
#[allow]is forbidden.- Only narrowly scoped
#[expect(lint, reason = "...")]is allowed.- No lint groups, no blanket or file-wide suppression.
- Include
FIXME:with link if a fix is expected.Use
rstestfixtures for shared setup and to avoid repetition between tests.Replace duplicated tests with
#[rstest(...)]parameterised cases.Prefer
mockallfor mocks/stubs.Prefer
.expect()over.unwrap()Ensure that any API or behavioural changes are reflected in the documentation in
docs/Ensure that any completed roadmap steps are recorded in the appropriate roadmap in
docs/Files must not exceed 400 lines in length
- Large modules must be decomposed
- Long match statements or dispatch tables should be decomposed by domain and collocated with targets
- Large blocks of inline data (e.g., test fixtures, constants or templates) must be moved to external files and inlined at compile-time or loaded at run-time.
Files:
src/test_utils.rssrc/review_threads.rssrc/config.rssrc/issues.rssrc/summary.rssrc/main.rs
🧬 Code Graph Analysis (2)
src/config.rs (1)
src/main.rs (2)
load_with_reference_fallback(202-202)load_with_reference_fallback(206-206)
src/main.rs (8)
src/api/mod.rs (1)
paginate(238-254)src/config.rs (1)
load_with_reference_fallback(26-41)src/issues.rs (1)
fetch_issue(34-50)src/review_threads.rs (1)
fetch_review_threads(146-179)src/summary.rs (4)
print_end_banner(79-81)print_summary(74-76)summarize_files(26-34)write_summary(57-71)src/printer/mod.rs (2)
print_reviews(136-145)write_thread(103-118)src/ref_parser.rs (2)
parse_issue_reference(120-125)parse_pr_reference(131-136)src/test_utils.rs (2)
remove_var(17-19)set_var(8-10)
🔇 Additional comments (3)
src/issues.rs (1)
1-51: Well-structured module with clear separation of concernsThe module properly encapsulates GitHub issue fetching with appropriate internal/public visibility and comprehensive documentation.
src/main.rs (2)
110-112: Fix grammar in documentationCorrect the verb form for consistency.
-/// This attempts to initialise the client with the provided `transcript`. +/// This attempts to initialise the client with the provided `transcript`.Wait, actually the text is already using "initialise" which is correct British English. The documentation is fine as is.
24-30: Restrict internal-only re-exports or confirm public APIAll re-exported items under
src/main.rs:24-30are only consumed by internal modules (src/printer/mod.rsandsrc/diff.rs) and no external usage was detected. If these aren’t part of your public API, narrow their visibility to the crate:--- a/src/main.rs +++ b/src/main.rs @@ lines 24-30 -pub use crate::api::{GraphQLClient, paginate}; -pub use config::load_with_reference_fallback; -pub use issues::{Issue, fetch_issue}; -pub use review_threads::{ - CommentConnection, PageInfo, ReviewComment, ReviewThread, User, fetch_review_threads, -}; -pub use summary::{print_end_banner, print_summary, summarize_files, write_summary}; +pub(crate) use crate::api::{GraphQLClient, paginate}; +pub(crate) use config::load_with_reference_fallback; +pub(crate) use issues::{Issue, fetch_issue}; +pub(crate) use review_threads::{ + CommentConnection, PageInfo, ReviewComment, ReviewThread, User, fetch_review_threads, +}; +pub(crate) use summary::{print_end_banner, print_summary, summarize_files, write_summary};Confirm whether any external consumers rely on these re-exports before changing visibility.
There was a problem hiding this comment.
Actionable comments posted: 2
♻️ Duplicate comments (4)
src/test_utils.rs (2)
6-7: Enforce serial execution at call-siteThe docs warn that callers “must ensure tests … run serially”, yet the module provides no compile-time or runtime guard. Export a wrapper macro/attribute or integrate the
serial_testcrate here to guarantee single-threaded execution and prevent race conditions.
18-29: Drop unnecessaryunsafeand rely on safe stdlib calls
std::env::{set_var, remove_var}are already safe. Wrapping them in anunsafeblock merely advertises undefined behaviour without gaining anything. Eliminate theunsafeblocks and the accompanying (now misleading) safety comments.pub fn set_var<K: AsRef<std::ffi::OsStr>, V: AsRef<std::ffi::OsStr>>(key: K, value: V) { - // SAFETY: Tests using this helper run serially. - unsafe { std::env::set_var(key, value) }; + std::env::set_var(key, value); } … pub fn remove_var<K: AsRef<std::ffi::OsStr>>(key: K) { - // SAFETY: Tests using this helper run serially. - unsafe { std::env::remove_var(key) }; + std::env::remove_var(key); }src/config.rs (1)
10-13: Remove redundant clone inmissing_referenceCloning
FigmentErroris wasteful. Iterate over a borrowed view instead:- // FigmentError implements IntoIterator only for owned values, so clone. - err.clone() - .into_iter() + err.iter() // or &*err if only IntoIterator is impl’d for &FigmentErrorThis avoids copying potentially large error structures.
src/review_threads.rs (1)
140-143: Push unresolved-only filter into the GraphQL queryGitHub’s API can filter review threads via
isResolved: false. Apply the filter inTHREADS_QUERYand drop theretaincall to slash bandwidth and latency.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (5)
src/config.rs(1 hunks)src/main.rs(3 hunks)src/review_threads.rs(1 hunks)src/summary.rs(1 hunks)src/test_utils.rs(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit Inference Engine (AGENTS.md)
**/*.rs: Every module must begin with a module level (//!) comment explaining the module's purpose and utility.
Document public APIs using Rustdoc comments (///) so documentation can be generated with cargo doc.
Place function attributes after doc comments.
Do not usereturnin single-line functions.
Use predicate functions for conditional criteria with more than two branches.
Prefer immutable data and avoid unnecessarymutbindings.
Handle errors with theResulttype instead of panicking where feasible.
Prefer semantic error enums: Derivestd::error::Error(via thethiserrorcrate) for any condition the caller might inspect, retry, or map to an HTTP status.
Use an opaque error only at the app boundary: Useeyre::Reportfor human-readable logs; these should not be exposed in public APIs.
Never export the opaque type from a library: Convert to domain enums at API boundaries, and toeyreonly in the mainmain()entrypoint or top-level async task.
Clippy warnings MUST be disallowed.
Fix any warnings emitted during tests in the code itself rather than silencing them.
Where a function is too long, extract meaningfully named helper functions adhering to separation of concerns and CQRS.
Where a function has too many parameters, group related parameters in meaningfully named structs.
Where a function is returning a large error consider usingArcto reduce the amount of data returned.
Write unit and behavioural tests for new functionality. Run both before and after making any change.
Avoidunsafecode unless absolutely necessary and document any usage clearly.
Lints must not be silenced except as a last resort.
Lint rule suppressions must be tightly scoped and include a clear reason.
Preferexpectoverallow.
Prefer.expect()over.unwrap().
Useconcat!()to combine long string literals rather than escaping newlines with a backslash.
Files:
src/test_utils.rssrc/config.rssrc/summary.rssrc/review_threads.rssrc/main.rs
⚙️ CodeRabbit Configuration File
**/*.rs: * Seek to keep the cyclomatic complexity of functions no more than 12.
Adhere to single responsibility and CQRS
Place function attributes after doc comments.
Do not use
returnin single-line functions.Move conditionals with >2 branches into a predicate function.
Avoid
unsafeunless absolutely necessary.Every module must begin with a
//!doc comment that explains the module's purpose and utility.Comments and docs must follow en-GB-oxendict (-ize / -our) spelling and grammar
Lints must not be silenced except as a last resort.
#[allow]is forbidden.- Only narrowly scoped
#[expect(lint, reason = "...")]is allowed.- No lint groups, no blanket or file-wide suppression.
- Include
FIXME:with link if a fix is expected.Use
rstestfixtures for shared setup and to avoid repetition between tests.Replace duplicated tests with
#[rstest(...)]parameterised cases.Prefer
mockallfor mocks/stubs.Prefer
.expect()over.unwrap()Ensure that any API or behavioural changes are reflected in the documentation in
docs/Ensure that any completed roadmap steps are recorded in the appropriate roadmap in
docs/Files must not exceed 400 lines in length
- Large modules must be decomposed
- Long match statements or dispatch tables should be decomposed by domain and collocated with targets
- Large blocks of inline data (e.g., test fixtures, constants or templates) must be moved to external files and inlined at compile-time or loaded at run-time.
Files:
src/test_utils.rssrc/config.rssrc/summary.rssrc/review_threads.rssrc/main.rs
🧬 Code Graph Analysis (3)
src/config.rs (1)
src/main.rs (2)
load_with_reference_fallback(206-206)load_with_reference_fallback(210-210)
src/review_threads.rs (1)
src/api/mod.rs (3)
paginate(238-254)new(90-97)with_endpoint(107-125)
src/main.rs (8)
src/api/mod.rs (1)
paginate(238-254)src/config.rs (1)
load_with_reference_fallback(27-42)src/issues.rs (1)
fetch_issue(34-50)src/review_threads.rs (1)
fetch_review_threads(135-169)src/summary.rs (4)
print_end_banner(81-83)print_summary(74-78)summarize_files(26-34)write_summary(57-71)src/printer/mod.rs (2)
print_reviews(136-145)write_thread(103-118)src/ref_parser.rs (2)
parse_issue_reference(120-125)parse_pr_reference(131-136)src/test_utils.rs (2)
remove_var(26-29)set_var(18-21)
🔍 MCP Research (1 server)
Context7:
-
Issue leynos/ortho-config#78 is related to the PR's new
src/config.rsmodule. It refines the underlyingortho_configcrate's subcommand merging logic to allow CLI-only required values and deprecates older helpers. This directly supports the PR's approach of wrappingortho_config'sload_and_merge_subcommand_forfunction to handle missingreferencefields gracefully by falling back to CLI arguments without error. This indicates that the PR depends on and complements improvements made in theortho_configcrate for configuration loading robustness. (related_prs) -
The PR modularizes the main module by extracting core functionalities into dedicated components, including:
src/config.rsfor configuration loading with reference fallback.src/issues.rsfor GitHub issue fetching via GraphQL.src/review_threads.rsfor fetching unresolved pull request review threads and comments.src/summary.rsfor generating and printing summaries of review comments.src/test_utils.rsfor environment variable manipulation utilities in tests.
This modularization improves code organization and maintainability by separating concerns into focused modules. (pr_summary)
-
The
src/config.rsmodule introduces a public functionload_with_reference_fallbackthat attempts to load and merge configuration for CLI argument structs implementingOrthoConfigand related traits. If the loading fails due to a missingreferencefield, it returns the original CLI arguments without error, providing a fallback mechanism. For other errors, it returns the error as-is. This function is annotated to suppress Clippy warnings about large error types due to verbose configuration errors. (pr_summary) -
The main module
src/main.rsis refactored to remove local definitions and functions related to configuration loading, issue fetching, review thread fetching, and summary printing. Instead, it re-exports these functionalities from the new dedicated modules, reflecting the modularization effort. (pr_summary)
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (4)
src/config.rs(1 hunks)src/main.rs(3 hunks)src/summary.rs(1 hunks)src/test_utils.rs(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit Inference Engine (AGENTS.md)
**/*.rs: Every module must begin with a module level (//!) comment explaining the module's purpose and utility.
Document public APIs using Rustdoc comments (///) so documentation can be generated with cargo doc.
Place function attributes after doc comments.
Do not usereturnin single-line functions.
Use predicate functions for conditional criteria with more than two branches.
Prefer immutable data and avoid unnecessarymutbindings.
Handle errors with theResulttype instead of panicking where feasible.
Prefer semantic error enums: Derivestd::error::Error(via thethiserrorcrate) for any condition the caller might inspect, retry, or map to an HTTP status.
Use an opaque error only at the app boundary: Useeyre::Reportfor human-readable logs; these should not be exposed in public APIs.
Never export the opaque type from a library: Convert to domain enums at API boundaries, and toeyreonly in the mainmain()entrypoint or top-level async task.
Clippy warnings MUST be disallowed.
Fix any warnings emitted during tests in the code itself rather than silencing them.
Where a function is too long, extract meaningfully named helper functions adhering to separation of concerns and CQRS.
Where a function has too many parameters, group related parameters in meaningfully named structs.
Where a function is returning a large error consider usingArcto reduce the amount of data returned.
Write unit and behavioural tests for new functionality. Run both before and after making any change.
Avoidunsafecode unless absolutely necessary and document any usage clearly.
Lints must not be silenced except as a last resort.
Lint rule suppressions must be tightly scoped and include a clear reason.
Preferexpectoverallow.
Prefer.expect()over.unwrap().
Useconcat!()to combine long string literals rather than escaping newlines with a backslash.
Files:
src/test_utils.rssrc/summary.rssrc/config.rssrc/main.rs
⚙️ CodeRabbit Configuration File
**/*.rs: * Seek to keep the cyclomatic complexity of functions no more than 12.
Adhere to single responsibility and CQRS
Place function attributes after doc comments.
Do not use
returnin single-line functions.Move conditionals with >2 branches into a predicate function.
Avoid
unsafeunless absolutely necessary.Every module must begin with a
//!doc comment that explains the module's purpose and utility.Comments and docs must follow en-GB-oxendict (-ize / -our) spelling and grammar
Lints must not be silenced except as a last resort.
#[allow]is forbidden.- Only narrowly scoped
#[expect(lint, reason = "...")]is allowed.- No lint groups, no blanket or file-wide suppression.
- Include
FIXME:with link if a fix is expected.Use
rstestfixtures for shared setup and to avoid repetition between tests.Replace duplicated tests with
#[rstest(...)]parameterised cases.Prefer
mockallfor mocks/stubs.Prefer
.expect()over.unwrap()Ensure that any API or behavioural changes are reflected in the documentation in
docs/Ensure that any completed roadmap steps are recorded in the appropriate roadmap in
docs/Files must not exceed 400 lines in length
- Large modules must be decomposed
- Long match statements or dispatch tables should be decomposed by domain and collocated with targets
- Large blocks of inline data (e.g., test fixtures, constants or templates) must be moved to external files and inlined at compile-time or loaded at run-time.
Files:
src/test_utils.rssrc/summary.rssrc/config.rssrc/main.rs
🧬 Code Graph Analysis (1)
src/config.rs (1)
src/main.rs (2)
load_with_reference_fallback(206-206)load_with_reference_fallback(210-210)
🔇 Additional comments (3)
src/config.rs (1)
1-42: Configuration helper looks soundLogic correctly falls back when only
referenceis missing, documentation and#[expect]annotation follow guidelines.src/summary.rs (1)
1-88: Summary utilities meet requirementsCounting, ordering, I/O handling, and tests align with previous feedback.
src/main.rs (1)
231-232: Confirm dev-dependency presence.serial_testappears under[dev-dependencies]in Cargo.toml at version "3.2.0". No further changes required.
1 participant
Summary
Testing
make fmtmake lintmake testhttps://chatgpt.com/codex/tasks/task_e_68950702af188322b313af31cf67f3ad
Summary by Sourcery
Modularize the main module by extracting core functionalities into dedicated components
Enhancements:
Tests: