ci: cut only the Kotlin daemon heap, not Gradle's

Correcting cdb4f1f7, which capped both to 4g and traded one OOM for
another.

The diagnosis was right: test-and-build-android was dying of memory.
gradle.properties asks for -Xmx6g (Gradle) plus -Xmx8g and 2g metaspace
(Kotlin daemon), roughly 16GB of ceiling on a 16GB runner, and that job is
the only one heavy enough to reach it. Capping both did stop the runner
deaths — the job ran 61 minutes and reached R8 and lint, where it used to
die at 11 to 14 minutes during compile.

But it then failed with java.lang.OutOfMemoryError: Java heap space in
minifyPlayBenchmarkWithR8 and lintAnalyzePlayBenchmark. Both draw on the
Gradle daemon's heap, and 4g is not enough for them on this app. 6g always
was — they never OOMed in the five earlier runs; the system did.

So the cut belongs entirely on the Kotlin daemon: 8g + 2g metaspace down
to 4g + 1g, Gradle left at its 6g default. Total ceiling ~11GB instead of
~16GB, which leaves the runner headroom without starving R8.

Confirmation signals stay falsifiable: if the runner dies early again, the
ceiling is still too high; if R8 or lint OOM again, 6g is not enough
either and the job needs splitting rather than tuning.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AXvKXakvup4inNFfAhhr4L

.github/workflows/build.yml

@@ -380,24 +380,25 @@ jobs:
       # variants are compile-equivalent for unit-test purposes; running all six
       # adds ~5× the kotlinc work without catching new defects on PRs. Push to
       # main still gets the full test matrix via the production-build path.
-      # Memory caps, CI-only. gradle.properties asks for -Xmx6g (Gradle) plus
+      # Memory, CI-only. gradle.properties asks for -Xmx6g (Gradle) plus -Xmx8g
-      # -Xmx8g and 2g metaspace (Kotlin daemon), which is ~16GB of ceiling on a
+      # and 2g metaspace (Kotlin daemon) — about 16GB of ceiling on a 16GB
-      # 16GB ubuntu-latest runner before the launcher JVM, Lint's fork and the
+      # ubuntu-latest runner, before the launcher JVM, Lint's fork and the KSP
-      # KSP workers are counted. Every other job stays well under it; this one
+      # workers. This job is the only one heavy enough to reach it, and it died
-      # runs two lint variants, two flavours of unit tests and
+      # five times mid-compile with "the runner has received a shutdown signal",
-      # assembleBenchmark, and it is the only job that has died — five times,
+      # which is the OOM killer taking the runner agent.
-      # each mid-compile or mid-lint, reported as "the runner has received a
+      #
-      # shutdown signal", which is what the Linux OOM killer taking the runner
+      # Only the Kotlin daemon is cut. An earlier attempt capped BOTH to 4g and
-      # agent looks like from the outside.
+      # traded one OOM for another: the runner survived and the job ran to
+      # completion, but R8 and lintAnalyze then failed with
+      # "java.lang.OutOfMemoryError: Java heap space" — they draw on the Gradle
+      # daemon's heap, and 4g is not enough for them on this app. 6g always was,
+      # so it stays; 8g + 2g for kotlinc is the part that did not fit.
       #
       # Overridden here rather than in gradle.properties so local builds on
-      # bigger machines keep the headroom. 4g apiece was verified to complete
+      # bigger machines keep the headroom.
-      # lintFdroidBenchmark and both unit-test tasks; it trades some build time
-      # for a job that finishes.
       - name: Test + Build Android (gradle)
         run: |
           ./gradlew \
-            -Dorg.gradle.jvmargs="-Xmx4g -Dfile.encoding=UTF-8" \
             -Dkotlin.daemon.jvmargs="-Xmx4g -XX:MaxMetaspaceSize=1g" \
             :amethyst:lintFdroidBenchmark \
             :amethyst:lintPlayBenchmark \