Conversation
Reviewer's GuideAdds Cucumber-based BDD scenarios for IR generation, including a new feature file and updated step definitions to validate build graph creation and error conditions. File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
|
Warning Rate limit exceeded@leynos has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 13 minutes and 21 seconds before requesting another review. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (3)
Summary by CodeRabbit
WalkthroughAdd a feature test suite for IR (Intermediate Representation) Generation, covering successful and error scenarios for compiling manifests into build graphs. Extend Cucumber step definitions and assertions to support new test cases and verification steps. Integrate new step handlers and assertion functions to validate build graph creation and IR generation attempts. Changes
Sequence Diagram(s)sequenceDiagram
participant Tester
participant TestWorld
participant IRCompiler
Tester->>TestWorld: Create new BuildGraph
Tester->>TestWorld: Compile manifest file to IR
TestWorld->>IRCompiler: Compile manifest
IRCompiler-->>TestWorld: BuildGraph or Error
Tester->>TestWorld: Check graph contents or generation result
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 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. 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 (
|
![codescene-delta-analysis[bot]](https://avatars.githubusercontent.com/in/53921?s=60&v=4){kind=small}
![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
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (3)
tests/features/ir_generation.feature(1 hunks)tests/steps/ir_steps.rs(3 hunks)tests/steps/manifest_steps.rs(2 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit Inference Engine (AGENTS.md)
**/*.rs: 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.
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.
Prefer immutable data and avoid unnecessarymutbindings.
Handle errors with theResulttype instead of panicking where feasible.
Avoidunsafecode unless absolutely necessary and document any usage clearly.
Place function attributes after doc comments.
Do not usereturnin single-line functions.
Use predicate functions for conditional criteria with more than two branches.
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.
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.
Files:
tests/steps/manifest_steps.rstests/steps/ir_steps.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:
tests/steps/manifest_steps.rstests/steps/ir_steps.rs
🔇 Additional comments (7)
tests/features/ir_generation.feature (1)
1-44: Comprehensive BDD scenarios with proper Gherkin structure.The feature file provides excellent test coverage for IR generation, including both success and failure scenarios. The scenarios are well-structured and cover critical edge cases like rule deduplication, circular dependencies, and various validation failures.
The test cases appropriately validate the core functionality whilst ensuring robust error handling.
tests/steps/manifest_steps.rs (3)
38-43: Clear and focused assertion function.The
assert_graphfunction follows the established pattern and provides a clear assertion with an appropriate error message.
45-50: Appropriate assertion logic for IR generation attempts.The
assert_generationfunction correctly validates that IR generation was attempted by checking for either a successful build graph or a manifest error. This covers both success and failure paths appropriately.
66-67: Proper integration of new assertion functions.The extension to
when_item_checkedcorrectly maps the new step phrases to their corresponding assertion functions, maintaining consistency with the existing pattern.tests/steps/ir_steps.rs (3)
4-4: Appropriate import addition for Given step support.Adding the
givenimport enables the extended step annotations and follows the existing import pattern.
7-7: Good reuse of existing function as Given step.The additional
#[given]annotation appropriately allows thecreate_graphfunction to be used in both Given and When contexts without code duplication.
35-35: Proper extension for manifest compilation as Given step.The additional
#[given]annotation enables reuse of the compilation logic in precondition contexts, maintaining DRY principles.
![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 - here's some feedback:
- assert_graph and assert_generation currently live in manifest_steps.rs despite only being used for IR scenarios—consider moving them into ir_steps.rs to keep IR logic encapsulated.
- assert_generation’s check (build_graph.is_some() || manifest_error.is_some()) can mask unexpected states; consider splitting success/failure assertions or adding a dedicated IR error field for clearer pass/fail reporting.
- The create_graph step is annotated with both #[given] and #[when] using the same text—if you don’t need both entry points, you can remove one to reduce redundant annotations.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- assert_graph and assert_generation currently live in manifest_steps.rs despite only being used for IR scenarios—consider moving them into ir_steps.rs to keep IR logic encapsulated.
- assert_generation’s check (build_graph.is_some() || manifest_error.is_some()) can mask unexpected states; consider splitting success/failure assertions or adding a dedicated IR error field for clearer pass/fail reporting.
- The create_graph step is annotated with both #[given] and #[when] using the same text—if you don’t need both entry points, you can remove one to reduce redundant annotations.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
|
@coderabbitai Have the following now been resolved?
|
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed: Length of output: 7544 @leynos Based on my examination of the current code, here's the status of the three issues: ✅ RESOLVED: Function locationThe ✅ RESOLVED: Redundant annotationsThe
|
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
|
@coderabbitai Have the following now been resolved? Still an issue: The underlying logic world.build_graph.is_some() || world.manifest_error.is_some() can still mask unexpected states where both fields are NoneThe core concern remains: if both build_graph and manifest_error are None, the assertion would fail, but it's unclear whether this represents a bug in the test setup or legitimate state. Consider adding explicit checks for this scenario or ensuring one of these fields is always populated after IR generation attempts. Two out of three issues have been fully resolved, with the third showing significant improvement but retaining the original logic concern. |
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain@leynos Based on my examination of the current code, this issue has NOT been resolved. The fn assert_generation_attempted(world: &CliWorld) {
assert!(world.build_graph.is_some() || world.manifest_error.is_some());
}The core problem remains unchanged:
Recommendations to properly resolve this:
fn assert_generation_attempted(world: &CliWorld) {
match (world.build_graph.is_some(), world.manifest_error.is_some()) {
(true, false) => {}, // Success case
(false, true) => {}, // Error case
(false, false) => panic!("BUG: IR generation was attempted but neither build_graph nor manifest_error was populated"),
(true, true) => panic!("BUG: Both build_graph and manifest_error are populated - this should not happen"),
}
}
fn assert_generation_succeeded(world: &CliWorld) {
assert!(world.build_graph.is_some(), "Expected build_graph to be populated after successful IR generation");
assert!(world.manifest_error.is_none(), "Expected no manifest_error after successful IR generation");
}
fn assert_generation_failed(world: &CliWorld) {
assert!(world.manifest_error.is_some(), "Expected manifest_error to be populated after failed IR generation");
assert!(world.build_graph.is_none(), "Expected no build_graph after failed IR generation");
}The underlying logic concern has not been addressed - the assertion can still mask unexpected states and provide unclear failure messages. 🏁 Script executed: Length of output: 3159 @leynos YES, this issue has been FULLY RESOLVED! ✅ The fn assert_generation_attempted(world: &CliWorld) {
match (world.build_graph.is_some(), world.manifest_error.is_some()) {
(true, false) | (false, true) => (),
(true, true) => panic!("unexpected: graph and error present"),
(false, false) => panic!("IR generation not attempted"),
}
}What's been fixed:
This implementation perfectly addresses your original concerns:
All three issues from your original feedback have now been fully resolved! |
leynos
deleted the
codex/implement-gherkin-scenarios-as-cucumber-rs-tests
branch
1 participant
Summary
ir_generation.featureto describe IR generation behaviourGivenTesting
make fmtmake lintmake testhttps://chatgpt.com/codex/tasks/task_e_688ca0d2a0688322a1d8d2b2010fdc3a
Summary by Sourcery
Add BDD tests for IR generation by creating a new feature file and enhancing step definitions to compile manifests and verify build graph or error outcomes.
New Features:
Enhancements:
Tests: