5b2b94fd71
Review feedback: shared experiment-loop-base.md and pre-submit-review.md contained Java/Kotlin-specific content that all languages inherit. This broke step numbering for non-Java agents and polluted cross-language files. Changes: - Revert experiment-loop-base.md to language-neutral (18-step original) - Revert pre-submit-review.md to language-neutral (remove Java section) - Create plugin/languages/java/references/pre-submit-review.md following the same pattern as the existing Python pre-submit-review.md - Reduce duplication in all 4 domain agents (cpu, memory, async, deep): replace inlined benchmark-validity and correctness-verification content with concise references, keeping only domain-specific additions - Add pre-submit-review.md to Deep References in all agents No content was removed — all JMH validation, correctness verification, mechanism explanation, milestone sanity check, and JDK compatibility requirements remain in the Java language overlay. They are now referenced from the single-source-of-truth files instead of being duplicated inline. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2.9 KiB
Pre-Submit Self-Review — Java/Kotlin
Java/Kotlin-specific checks for the pre-submit review. Read ${CLAUDE_PLUGIN_ROOT}/references/shared/pre-submit-review.md first for the language-agnostic checklist.
JMH Benchmark Validity
For every KEEP, confirm the benchmark was validated per benchmark-validity.md:
- Results consumed (anti-DCE): every
@Benchmarkmethod returns or usesBlackhole.consume() - Inputs dynamic (anti-constant-folding): all inputs from
@Stateor@Param, not literals - Warmup meets floors: >=5 iterations for fast ops, >=3 for slow
- Fork count:
@Fork(2)minimum,@Fork(3)for GC-sensitive or marginal improvements - Error bars do NOT overlap between baseline and optimized
If any KEEP lacks valid JMH evidence, re-run the benchmark now.
Mechanism Explanation
Every KEEP commit message must contain a one-paragraph explanation of WHY the optimization is faster at the JVM level — the specific mechanism (e.g., "eliminates autoboxing allocations" or "replaces O(n^2) nested loop with HashMap index"). If you wrote "improved performance" without explaining the mechanism, fix the commit message.
JDK Version Compatibility
Verify every optimization uses only APIs available on the project's minimum JDK version (from .codeflash/setup.md). Common traps:
| API / Feature | Minimum JDK |
|---|---|
List.of(), Map.of(), Set.of() |
9 |
String.isBlank(), String.strip(), String.repeat() |
11 |
String.formatted() |
15 |
Stream.toList() |
16 |
record types |
16 |
sealed classes |
17 |
Virtual threads (Thread.ofVirtual()) |
21 |
SequencedCollection, SequencedMap |
21 |
An optimization using unavailable APIs does not compile in production.
Correctness Verification
For every KEEP, confirm output equivalence was verified per correctness-verification.md:
- Return value deep equality (
.equals(), not==) - Floating-point tolerance (relative epsilon)
- Collection ordering semantics (ordered vs unordered comparison)
- Mutable parameter state preservation
- Exception contract preservation
- Side effect preservation
- Serialization compatibility (if the object is serialized)
Milestone Sanity Check
If milestones were reached, confirm the cumulative JMH improvement was at least 70% of the sum of individual improvements. If not, at least one KEEP is a false positive — re-measure each individual KEEP and revert the non-contributing one(s).
GC Impact Verification
If you claimed GC improvement, verify with JFR GC events (jdk.G1GarbageCollection, jdk.GCPhasePause) or -Xlog:gc*, not just CPU timing. Compare pause distributions (p50, p99, max), not just averages.
Serialization Safety
If you changed collection types (e.g., ArrayList to EnumSet, HashMap to Map.of()), check if the object is serialized anywhere (Java serialization, Jackson, protobuf). See correctness-verification.md section 7.