Add prompt optimizers to LiSSA #44

DanielDango · 2025-11-28T11:14:37Z

This PR aims to introduce prompt optimizers developed during my bachelors thesis into the LiSSA framework.
They can be used as a standalone interaction with the framework, as well as chained with regular evaluation pipeline runs.

To-Do:

Re-enable Feedback and Gradient optimizers
add usage to repository documentation

This commit introduces a prompt optimization system that enables automatic tuning of classification prompts to improve trace link recovery performance. Core Components: - PromptOptimizer interface and IterativeOptimizer implementation for iterative naive prompt refinement - Optimization class as the main orchestrator for running optimization workflows - OptimizeCommand CLI integration for executing optimizations from command line Evaluation Framework: - Evaluator base class with strategy pattern for different evaluation approaches - BruteForceEvaluator for exhaustive prompt candidate evaluation - UpperConfidenceBoundBanditEvaluator for efficient exploration-exploitation tradeoff using UCB1 algorithm to reduce computational costs - MockEvaluator for testing purposes Metrics System: - Metric interface with PointwiseMetric and GlobalMetric implementations - FBetaMetric for computing precision, recall, and F-beta scores - Scorer interface with BinaryScorer for trace link classification scoring - Reductor interface with MeanReductor for aggregating pointwise metrics - Factory classes (MetricFactory, ScorerFactory, ReductorFactory) for instantiation Infrastructure Updates: - Extended ModuleConfiguration with prompt management capabilities - Added OptimizerConfiguration for optimizer-specific settings - Enhanced CacheManager with scorer-specific caching via ScorerCacheKey - Added ChatLanguageModelUtils for LLM interaction helpers - Updated Statistics class with methods for computing evaluation metrics Classifier Modifications: - Used setClassificationPrompt() and getClassificationPromptKey() to Classifier abstract class to support dynamic prompt updates - Replaced cache parameters with map Testing: - Added PromptOptimizationUtilsTest with Markdown escaping tests - Extended Requirement2RequirementE2ETest with optimizer test cases - Added test resources with expected outputs and cache files for iterative and simple optimizer configurations - Updated ArchitectureTest to ensure correct usage of dangerous overwrite methods Configuration: - Added example-configs/optimizer-config.json demonstrating optimizer setup

DanielDango · 2025-11-28T11:17:33Z

@dfuchss, your review is not yet required. I intended to request an initial review from @copilot. I will request your review when the ProTeGi (Gradient) and naive optimizer with feedback of misclassified TLs (Feedback) are added.

Copilot · 2025-11-28T11:17:43Z

@DanielDango I've opened a new pull request, #45, to work on those changes. Once the pull request is ready, I'll request review from you.

Copilot

Pull request overview

This PR introduces a comprehensive prompt optimization framework to the LiSSA trace link analysis system. The framework enables iterative improvement of classification prompts through automated optimization strategies, integrating metrics, evaluators, and optimizer implementations.

Key Changes:

Adds prompt optimizer framework with iterative optimization support
Introduces metric system (pointwise and global metrics) for evaluating prompt performance
Implements evaluator strategies (brute-force and Upper Confidence Bound bandit algorithms)
Extends configuration system to support optimization workflows

Reviewed changes

Copilot reviewed 52 out of 54 changed files in this pull request and generated 28 comments.

Show a summary per file

File	Description
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptoptimizer/*	Core optimizer interfaces and implementations (IterativeOptimizer, MockOptimizer, OptimizerFactory, utilities)
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/*	Metric system with scorers (BinaryScorer), reductors (MeanReductor), and metric implementations (PointwiseMetric, GlobalMetric, FBetaMetric)
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/evaluator/*	Evaluator base class with BruteForceEvaluator and UpperConfidenceBoundBanditEvaluator implementations
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/Optimization.java	New optimization pipeline that extends evaluation with prompt optimization step
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/Evaluation.java	Extended to support prompt overwriting for optimization workflow
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/configuration/*	OptimizerConfiguration record and ModuleConfiguration setArgument methods
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/classifier/*	Added getCacheParameters() method and changed copyOf() visibility to public
src/main/java/edu/kit/kastel/sdq/lissa/ratlr/cache/*	New ScorerCacheKey and CacheManager enhancements for optimizer caching
src/main/java/edu/kit/kastel/sdq/lissa/cli/command/OptimizeCommand.java	CLI command for running optimization and optional evaluation pipelines
src/test/java/edu/kit/kastel/sdq/lissa/ratlr/*	Test files including PromptOptimizationUtilsTest and E2E optimizer tests
src/test/resources/warc/*	Test configurations and expected outputs for optimizer validation
example-configs/optimizer-config.json	Example optimizer configuration file

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review for a chance to win a $100 gift card. Take the survey.

Copilot · 2025-11-28T11:22:36Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/evaluator/UpperConfidenceBoundBanditEvaluator.java

+            List<Double> scores;
+            while (true) {
+                try {
+                    // TODO: Pryzant et al. used multiple threads here


The TODO comment "Pryzant et al. used multiple threads here" should be addressed or removed. If multi-threading is planned, create a tracking issue; otherwise, remove the comment if it's not relevant.

Suggested change

// TODO: Pryzant et al. used multiple threads here

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/evaluator/UpperConfidenceBoundBanditEvaluator.java

Copilot · 2025-11-28T11:22:37Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptoptimizer/IterativeOptimizer.java

+     * Custom optimization prompts can also use the placeholders {@value SOURCE_TYPE_PLACEHOLDER},
+     * {@value TARGET_TYPE_PLACEHOLDER} and should use {@value ORIGINAL_PROMPT_PLACEHOLDER}.
+     * The optimized prompt should be enclosed between {@value PROMPT_START} and {@value PROMPT_END}.
+     * TODO: There should probably be spaces around the prompt tags :upsidedown:.


The TODO comment contains an emoji ":upsidedown:" which should be removed or replaced with a proper description. Consider clarifying whether spaces are truly needed or remove the comment if this is acceptable.

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptoptimizer/EvaluationResult.java

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/evaluator/UpperConfidenceBoundBanditEvaluator.java

Copilot · 2025-11-28T11:22:44Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/PointwiseMetric.java

+        return getClassificationKey(task.source().toString(), task.target().toString());
+    }
+
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        return getClassificationKey(result.source().toString(), result.target().toString());


Default toString(): Element inherits toString() from Object, and so is not suitable for printing.

Suggested change

return getClassificationKey(task.source().toString(), task.target().toString());

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

return getClassificationKey(result.source().toString(), result.target().toString());

// Replace toString() with a stable identifier for source and target, e.g., getId()

return getClassificationKey(task.source().getId(), task.target().getId());

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

// Replace toString() with a stable identifier for source and target, e.g., getId()

return getClassificationKey(result.source().getId(), result.target().getId());

Copilot · 2025-11-28T11:22:44Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/PointwiseMetric.java

+        return getClassificationKey(task.source().toString(), task.target().toString());
+    }
+
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        return getClassificationKey(result.source().toString(), result.target().toString());
+    }
+
+    @NotNull


Default toString(): Element inherits toString() from Object, and so is not suitable for printing.

Suggested change

return getClassificationKey(task.source().toString(), task.target().toString());

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

return getClassificationKey(result.source().toString(), result.target().toString());

}

@NotNull

return getClassificationKey(objectKey(task.source()), objectKey(task.target()));

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

return getClassificationKey(objectKey(result.source()), objectKey(result.target()));

}

/**

* Returns a stable string key for the given object, avoiding default Object.toString().

* Modify this method to extract a unique and meaningful identifier from the object.

*/

private static String objectKey(Object obj) {

// If obj is null, return "null"

if (obj == null) {

return "null";

}

// If obj has a getId() method, use it. Otherwise, fallback to toString().

// TODO: Replace this with a more robust implementation if possible.

try {

java.lang.reflect.Method getId = obj.getClass().getMethod("getId");

Object id = getId.invoke(obj);

return id != null ? id.toString() : "null";

} catch (Exception e) {

// Fallback: use toString(), but warn in a comment.

// WARNING: This may use Object.toString() if no getId() is present.

return obj.toString();

}

}

Copilot · 2025-11-28T11:22:45Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/PointwiseMetric.java

+        return getClassificationKey(task.source().toString(), task.target().toString());
+    }
+
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        return getClassificationKey(result.source().toString(), result.target().toString());


Default toString(): Element inherits toString() from Object, and so is not suitable for printing.

Suggested change

return getClassificationKey(task.source().toString(), task.target().toString());

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

return getClassificationKey(result.source().toString(), result.target().toString());

return getClassificationKey(task.source(), task.target());

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

return getClassificationKey(result.source(), result.target());

Copilot · 2025-11-28T11:22:45Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/PointwiseMetric.java

+        return getClassificationKey(task.source().toString(), task.target().toString());
+    }
+
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        return getClassificationKey(result.source().toString(), result.target().toString());


Default toString(): Element inherits toString() from Object, and so is not suitable for printing.

Suggested change

return getClassificationKey(task.source().toString(), task.target().toString());

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

return getClassificationKey(result.source().toString(), result.target().toString());

// Ensure that source() and target() return meaningful string representations.

Object source = task.source();

Object target = task.target();

String sourceStr = (source instanceof String) ? (String) source : String.valueOf(source);

String targetStr = (target instanceof String) ? (String) target : String.valueOf(target);

return getClassificationKey(sourceStr, targetStr);

}

@NotNull

private static String getClassificationKey(ClassificationResult result) {

// Ensure that source() and target() return meaningful string representations.

Object source = result.source();

Object target = result.target();

String sourceStr = (source instanceof String) ? (String) source : String.valueOf(source);

String targetStr = (target instanceof String) ? (String) target : String.valueOf(target);

return getClassificationKey(sourceStr, targetStr);

Copilot

Pull request overview

Copilot reviewed 52 out of 54 changed files in this pull request and generated 10 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review for a chance to win a $100 gift card. Take the survey.

Copilot · 2025-11-28T11:30:30Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/evaluator/UpperConfidenceBoundBanditEvaluator.java

+            List<Double> scores;
+            while (true) {
+                try {
+                    // TODO: Pryzant et al. used multiple threads here


The TODO comment about Pryzant et al. using multiple threads should be addressed. If multi-threading is intended to be added, this should be tracked properly. Otherwise, the comment should be removed or clarified.

Suggested change

// TODO: Pryzant et al. used multiple threads here

// Note: Pryzant et al. used multiple threads here. This implementation is currently single-threaded.

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/classifier/ChatLanguageModelProvider.java

Copilot · 2025-11-28T11:30:31Z

src/test/java/edu/kit/kastel/sdq/lissa/ratlr/ArchitectureTest.java

            });

+    /**
+     * Prompts for classifiers should only be modified by optimizers or smetricscorers. Otherwise, there will be


Typo or grammatical issue: "smetricscorers" should likely be "metrics scorers" or "metric scorers" with proper spacing.

Copilot · 2025-11-28T11:30:31Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/GlobalMetric.java

+     * TODO: consider extracting into a aggregator implementation ???
+     *


The TODO comment about extracting this into an aggregator implementation should be addressed or clarified. If this is a design decision that needs to be made, consider opening an issue to track it rather than leaving it as a TODO in the code.

Suggested change

* TODO: consider extracting into a aggregator implementation ???

*

*

*

Copilot · 2025-11-28T11:30:31Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/Evaluation.java

+     */
+    public Evaluation(Configuration config) throws IOException {
+        this.configuration = config;
+        // TODO maybe dont?


The TODO comment "maybe dont?" on line 151 should be resolved. It's unclear what the concern is about setting configFile to null. This should either be addressed or the comment should be clarified.

Suggested change

// TODO maybe dont?

// No config file path available when constructed from Configuration object

Copilot · 2025-11-28T11:30:32Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/evaluator/UpperConfidenceBoundBanditEvaluator.java

+            return Arrays.stream(ucbScores)
+                    .boxed()
+                    // sort in descending order
+                    .sorted((a, b) -> Double.compare(b, a))
+                    .limit(n)
+                    .map(score -> {
+                        for (int i = 0; i < ucbScores.length; i++) {
+                            if (ucbScores[i] == score) {
+                                return i;
+                            }
+                        }
+                        // should never happen
+                        return -1;
+                    })
+                    .toList();


The choose method has a bug in finding the indices of top-scoring prompts. After sorting scores in descending order (line 182), the code attempts to find the original index by comparing values (lines 185-188). However, if multiple prompts have the same score, this will always return the first matching index, potentially selecting the same prompt multiple times. Consider using a proper sorting with index tracking, such as creating a list of index-score pairs before sorting.

Suggested change

return Arrays.stream(ucbScores)

.boxed()

// sort in descending order

.sorted((a, b) -> Double.compare(b, a))

.limit(n)

.map(score -> {

for (int i = 0; i < ucbScores.length; i++) {

if (ucbScores[i] == score) {

return i;

}

}

// should never happen

return -1;

})

.toList();

// Pair each score with its index

List<int[]> indexScorePairs = new ArrayList<>();

for (int i = 0; i < ucbScores.length; i++) {

indexScorePairs.add(new int[] {i, Double.isNaN(ucbScores[i]) ? Integer.MIN_VALUE : (int) Math.round(ucbScores[i])});

}

// Sort pairs by score descending

indexScorePairs.sort((a, b) -> Double.compare(ucbScores[b[0]], ucbScores[a[0]]));

// Select the indices of the top n pairs

List<Integer> chosen = new ArrayList<>();

for (int i = 0; i < Math.min(n, indexScorePairs.size()); i++) {

chosen.add(indexScorePairs.get(i)[0]);

}

return chosen;

Copilot · 2025-11-28T11:30:32Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/GlobalMetric.java

+        classifier.setClassificationPrompt(prompt);
+        List<ClassificationResult> acceptedTraceLinks = new ArrayList<>();
+        List<ClassificationResult> rejectedTraceLinks = new ArrayList<>();
+        new Pair<>(new ArrayList<>(), new ArrayList<>());


Line 107 creates a new Pair object that is immediately discarded and never used. This appears to be dead code that should be removed.

Suggested change

new Pair<>(new ArrayList<>(), new ArrayList<>());

Copilot · 2025-11-28T11:30:32Z

src/test/java/edu/kit/kastel/sdq/lissa/ratlr/e2e/Requirement2RequirementE2ETest.java

+                expectedPrompt.lines().map(String::strip).toList(),
+                escapedOptimizedPrompt.lines().map(String::strip).toList(),
+                "The optimized prompt does not match every line (regardless of line terminators or leading/trailing "
+                        + "spaces) of of the expected prompt.");


Typo: "of of the expected prompt" should be "of the expected prompt" - remove the duplicate "of".

Copilot · 2025-11-28T11:30:32Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/PointwiseMetric.java

+
+    @NotNull
+    private static String getClassificationKey(ClassificationTask task) {
+        return getClassificationKey(task.source().toString(), task.target().toString());


Default toString(): Element inherits toString() from Object, and so is not suitable for printing.

Copilot · 2025-11-28T11:30:33Z

src/main/java/edu/kit/kastel/sdq/lissa/ratlr/promptmetric/PointwiseMetric.java

+
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        return getClassificationKey(result.source().toString(), result.target().toString());


Default toString(): Element inherits toString() from Object, and so is not suitable for printing.

…ented by @copilot on #44

- refines iterative optimizer with feedback on misclassified trace links (false positive or false negative) - add sample strategy to configure which TLs will be used as feedback

- add SLF4J Simple Logger configuration for improved logging in tests

…g and Simple Classifiers

… correctly.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

… optimization

… feature/add-prompt-optimization-module # Conflicts: # src/main/java/edu/kit/kastel/sdq/lissa/ratlr/classifier/ChatLanguageModelProvider.java

…timization with "Gradient Descent" and Beam Search" of Pryzant et al. 2023

- this changed expected outputs

sonarqubecloud · 2025-12-23T13:59:40Z

Quality Gate passed

Issues
25 New issues
1 Accepted issue

Measures
0 Security Hotspots
No data about Coverage
0.0% Duplication on New Code

See analysis details on SonarQube Cloud

Copilot · 2025-12-23T14:12:50Z

@DanielDango I've opened a new pull request, #49, to work on those changes. Once the pull request is ready, I'll request review from you.

DanielDango marked this pull request as ready for review November 28, 2025 11:15

DanielDango requested a review from dfuchss as a code owner November 28, 2025 11:15

Copilot AI review requested due to automatic review settings November 28, 2025 11:15

Copilot started reviewing on behalf of DanielDango November 28, 2025 11:15 View session

Copilot AI mentioned this pull request Nov 28, 2025

[WIP] Add prompt optimizers to LiSSA #45

Closed

Copilot finished reviewing on behalf of DanielDango November 28, 2025 11:19

Copilot AI reviewed Nov 28, 2025

View reviewed changes

DanielDango marked this pull request as draft November 28, 2025 11:23

DanielDango requested a review from Copilot November 28, 2025 11:23

Copilot started reviewing on behalf of DanielDango November 28, 2025 11:23 View session

Copilot finished reviewing on behalf of DanielDango November 28, 2025 11:27

Copilot AI reviewed Nov 28, 2025

View reviewed changes

DanielDango and others added 15 commits November 28, 2025 13:16

fix: correct typos and improve documentation in various files as comm…

7887f8d

…ented by @copilot on #44

add feedback optimizer implementation

4a7744a

- refines iterative optimizer with feedback on misclassified trace links (false positive or false negative) - add sample strategy to configure which TLs will be used as feedback

wip: add more logging

75dddd1

- add SLF4J Simple Logger configuration for improved logging in tests

feat: enhance cache parameters to include classifier type in Reasonin…

565a80e

…g and Simple Classifiers

feat: Enhance logging for cache operations and misclassification checks

883ede1

Rework caching. Now it shall be ensured that Cacheparameters are used…

cb89983

… correctly.

Update ArchitectureTest.java

fb1de00

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

feat: Remove caching from GlobalMetric and PointwiseMetric for prompt…

3e7facf

… optimization

Merge remote-tracking branch 'upstream/feature/simplify-caching' into…

e31c6c1

… feature/add-prompt-optimization-module # Conflicts: # src/main/java/edu/kit/kastel/sdq/lissa/ratlr/classifier/ChatLanguageModelProvider.java

chore: update formatting

c5fff3f

chore: update cache parameter usage

abd5a4f

feat: add additional logging

317d3cc

fix: revert reduced target store deduplication

63df5fb

fix: re-enable other e2e optimizer tests

a8d1d47

feat: Add gradient optimizer based on ProTeGi by "Automatic Prompt Op…

aa5772f

…timization with "Gradient Descent" and Beam Search" of Pryzant et al. 2023

DanielDango added 2 commits December 23, 2025 14:50

chore: apply spotless and use SecureRandom instead of Random

3739508

revert: use Random instead of SecureRandom

629ac80

- this changed expected outputs

Copilot AI mentioned this pull request Dec 23, 2025

Remove TODO comment from MockClassifier.setClassificationPrompt #49

Draft

-        return getClassificationKey(task.source().toString(), task.target().toString());
-    }
-    @NotNull
-    private static String getClassificationKey(ClassificationResult result) {
-        return getClassificationKey(result.source().toString(), result.target().toString());
-    }
-    @NotNull
+        return getClassificationKey(objectKey(task.source()), objectKey(task.target()));
+    }
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        return getClassificationKey(objectKey(result.source()), objectKey(result.target()));
+    }
+    /**
+     * Returns a stable string key for the given object, avoiding default Object.toString().
+     * Modify this method to extract a unique and meaningful identifier from the object.
+     */
+    private static String objectKey(Object obj) {
+        // If obj is null, return "null"
+        if (obj == null) {
+            return "null";
+        }
+        // If obj has a getId() method, use it. Otherwise, fallback to toString().
+        // TODO: Replace this with a more robust implementation if possible.
+        try {
+            java.lang.reflect.Method getId = obj.getClass().getMethod("getId");
+            Object id = getId.invoke(obj);
+            return id != null ? id.toString() : "null";
+        } catch (Exception e) {
+            // Fallback: use toString(), but warn in a comment.
+            // WARNING: This may use Object.toString() if no getId() is present.
+            return obj.toString();
+        }
+    }

-        return getClassificationKey(task.source().toString(), task.target().toString());
-    }
-    @NotNull
-    private static String getClassificationKey(ClassificationResult result) {
-        return getClassificationKey(result.source().toString(), result.target().toString());
+        // Ensure that source() and target() return meaningful string representations.
+        Object source = task.source();
+        Object target = task.target();
+        String sourceStr = (source instanceof String) ? (String) source : String.valueOf(source);
+        String targetStr = (target instanceof String) ? (String) target : String.valueOf(target);
+        return getClassificationKey(sourceStr, targetStr);
+    }
+    @NotNull
+    private static String getClassificationKey(ClassificationResult result) {
+        // Ensure that source() and target() return meaningful string representations.
+        Object source = result.source();
+        Object target = result.target();
+        String sourceStr = (source instanceof String) ? (String) source : String.valueOf(source);
+        String targetStr = (target instanceof String) ? (String) target : String.valueOf(target);
+        return getClassificationKey(sourceStr, targetStr);

	// TODO: Pryzant et al. used multiple threads here
	// Note: Pryzant et al. used multiple threads here. This implementation is currently single-threaded.

		* TODO: consider extracting into a aggregator implementation ???
		*

	// TODO maybe dont?
	// No config file path available when constructed from Configuration object

Add prompt optimizers to LiSSA #44

Are you sure you want to change the base?

Add prompt optimizers to LiSSA #44

Uh oh!

Conversation

DanielDango commented Nov 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

DanielDango commented Nov 28, 2025

Uh oh!

Copilot AI commented Nov 28, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

sonarqubecloud bot commented Dec 23, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Quality Gate passed

Uh oh!

Copilot AI commented Dec 23, 2025

Uh oh!

Reviewers

Assignees

Labels

DanielDango commented Nov 28, 2025 •

edited

Loading

sonarqubecloud bot commented Dec 23, 2025 •

edited

Loading