Replace connection panic integration test with unit test#296
Conversation
Reviewer's guide (collapsed on small PRs)Reviewer's GuideThis PR replaces the heavy TCP-based integration test for connection panics with a concise unit test that directly invokes the inc_connection_panics function and asserts the counter increments. Class diagram for updated connection panic metric testclassDiagram
class TestModule {
+test_connection_panic_metric_increments() [REMOVED]
+test_inc_connection_panics_increments_counter() [ADDED]
}
class DebuggingRecorder {
+new()
+install()
+snapshotter()
}
class WireframeApp {
+on_connection_setup()
}
class TaskTracker {
+new()
+close()
+wait()
}
TestModule --> DebuggingRecorder : used in removed test
TestModule --> WireframeApp : used in removed test
TestModule --> TaskTracker : used in removed test
Flow diagram for simplified connection panic metric testflowchart TD
A[Start unit test] --> B[Call inc_connection_panics]
B --> C[Assert counter incremented]
C --> D[Test complete]
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. Warning Rate limit exceeded@leynos has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 8 minutes and 49 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 (1)
Summary by CodeRabbit
WalkthroughRemove the Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant MetricsRecorder
TestRunner->>MetricsRecorder: Install DebuggingRecorder globally
TestRunner->>MetricsRecorder: Call inc_connection_panics()
TestRunner->>MetricsRecorder: Retrieve and assert CONNECTION_PANICS == 1
TestRunner->>MetricsRecorder: Call inc_connection_panics() twice
TestRunner->>MetricsRecorder: Retrieve and assert CONNECTION_PANICS == 2
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 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 (
|
![codescene-delta-analysis[bot]](https://avatars.githubusercontent.com/in/53921?s=60&v=4){kind=small}
![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> `tests/metrics.rs:77` </location>
<code_context>
- })
- .unwrap_or(0);
- assert_eq!(1, count, "panic metric not recorded");
+ assert!(
+ metrics.iter().any(|(key, _, _, value)| {
+ key.key().name() == wireframe::metrics::CONNECTION_PANICS
+ && matches!(value, DebugValue::Counter(c) if *c == 1)
+ }),
+ "expected CONNECTION_PANICS == 1, got {metrics:#?}"
+ );
}
</code_context>
<issue_to_address>
Consider adding a test for multiple increments.
Adding a test that calls inc_connection_panics multiple times will ensure the counter correctly accumulates values and help detect issues with repeated increments.
</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[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 (2)
src/server/connection.rs(0 hunks)tests/metrics.rs(1 hunks)
💤 Files with no reviewable changes (1)
- src/server/connection.rs
🧰 Additional context used
📓 Path-based instructions (1)
**/*.rs
📄 CodeRabbit Inference Engine (AGENTS.md)
**/*.rs: Function documentation must include clear examples demonstrating the usage and outcome of the function. Test documentation should omit examples where the example serves only to reiterate the test logic.
No single code file may be longer than 400 lines. Long switch statements or dispatch tables should be broken up by feature and constituents colocated with targets. Large blocks of test data should be moved to external data files.
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 using Arc to 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 unnecessary mut bindings.
Handle errors with the Result type instead of panicking where feasible.
Avoid unsafe code unless absolutely necessary and document any usage clearly.
Place function attributes after doc comments.
Do not use return in 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.
Prefer expect over allow.
Prefer .expect() over .unwrap().
Use concat!() to combine long string literals rather than escaping newlines with a backslash.
Prefer semantic error enums. Derive std::error::Error (via the thiserror crate) for any condition the caller might inspect, retry, or map to an HTTP status....
Files:
tests/metrics.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/metrics.rs
🧬 Code Graph Analysis (1)
tests/metrics.rs (1)
src/metrics.rs (2)
inc_connection_panics(108-108)inc_connection_panics(111-111)
🔍 MCP Research (1 server)
Deepwiki:
-
The connection panic resilience test (
connection_panic_is_caught) is implemented as a behavioral test using the Cucumber BDD framework. It uses aPanicWorldtest context that starts aWireframeServerconfigured to panic during connection setup. The test establishes two TCP connections, both triggering panics, and verifies that both connections succeed without crashing the server. It asserts that the logs contain an error entry indicating the connection task panicked with the specific panic message. (Source: Behavioral Testing page) -
The connection actor model uses an actor-per-connection pattern where each TCP connection is managed by a dedicated async task. Connection tasks are wrapped with panic recovery using
std::panic::AssertUnwindSafe(...).catch_unwind()to catch panics and log them without crashing the server or worker tasks. This design ensures that panics in connection handlers increment the panic metric and do not affect other connections. (Source: ConnectionActor page, WireframeServer page) -
The
wireframe_testingcrate provides utilities for testingWireframeAppinstances with in-memory streams, enabling unit and integration tests without real network I/O. The metrics test intests/metrics.rsuses this infrastructure to verify metric increments. (Source: Testing Utilities page)
⏰ Context from checks skipped due to timeout of 120000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: build-test
🔇 Additional comments (1)
tests/metrics.rs (1)
66-84: Retain behavioural tests for connection panic resilience
Keep the PanicWorld scenario and related BDD tests alongside the new unit test to verify the recovery path and ensure panics don’t crash the server.Locations to preserve:
- src/server/connection.rs – async fn connection_panic_is_caught
- tests/world.rs – PanicWorld context
- tests/features/connection_panic.feature
- tests/steps/panic_steps.rs – Given/When/Then steps for PanicWorld
|
@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 (1)
tests/metrics.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:
tests/metrics.rs
🧬 Code Graph Analysis (1)
tests/metrics.rs (1)
src/metrics.rs (2)
inc_connection_panics(108-108)inc_connection_panics(111-111)
🔍 MCP Research (2 servers)
Deepwiki:
-
The server’s panic recovery code in
src/server.rsspawns connection tasks wrapped withcatch_unwindto catch panics, log the panic message and peer address, and prevent server crashes, ensuring resilience to panics in connection handlers (ENG-2040). -
The behavioral test
connection_panic.featureverifies that connection panics do not crash the server, allowing subsequent connections to succeed, using aPanicWorldtest context that starts a server configured to panic during connection setup and verifies multiple connection attempts succeed (ENG-2040). -
The metrics system uses the
metricscrate to track operational metrics including connection panics; the functioninc_connection_panicsincrements theCONNECTION_PANICScounter metric, and tests intests/metrics.rsverify that callinginc_connection_panicsincrements the counter exactly once and accumulates over multiple calls (ENG-2040). -
The removal of the integration test in
src/server/connection.rsand replacement with unit tests intests/metrics.rsaligns with the architecture where connection panics are caught and logged in the worker task spawning code insrc/server.rs, and the metric increment function is tested in isolation (ENG-2040).
Context7:
-
Document /metrics-rs/metrics: The
metrics::with_local_recorderfunction is used to temporarily override the global metrics recorder within a closure, enabling thread-safe and deterministic testing or localized metric collection without affecting global state. This is demonstrated by creating aDebuggingRecorder, usingmetrics::with_local_recorderto run code that increments a counter metric, and then asserting the snapshot contains the expected metric increment. This pattern aligns with the new unit test approach intests/metrics.rswhere the panic counter increment is tested using a local debugging recorder and snapshotter. (Source: /metrics-rs/metrics RELEASES.md snippet "Using Scoped Metrics Recorder in Rust") -
Document /metrics-rs/metrics: The
increment_counter!macro is the standard way to increment a counter metric by one, which is the underlying operation tested by the new unit tests that callinc_connection_panicsto increment theCONNECTION_PANICScounter. (Source: /metrics-rs/metrics RELEASES.md snippet "Incrementing Counter in Rust")
🔇 Additional comments (2)
tests/metrics.rs (2)
66-74: Use a local recorder; eliminate global-state flakiness.Adopt
metrics::with_local_recorderand drop global installation. This aligns with our guidance and avoids single-recorder panics in parallel test runs. LGTM.
86-105: Add accumulation test; improve coverage.Validate that multiple invocations accumulate correctly. This closes the gap flagged earlier and hardens the metric’s contract. LGTM.
1 participant
Summary
inc_connection_panicsincrements the panic counterTesting
make fmtmake lintmake testhttps://chatgpt.com/codex/tasks/task_e_689686c68b6c8322834b0fa5f6723cb3
Summary by Sourcery
Tests: