llama.cpp b11534, executed-test floor, loader output to stderr, JBang example (PR A)

.github/buildcheck/natives.py

@@ -247,6 +247,37 @@ def check_readme(natives, readme_text):
     return failures + compare("README.md all-backends fat jars", fatjar_targets(natives), fatjar_names(readme_text))
 
 
+JBANG_EXAMPLE = "examples/jbang/Chat.java"
+
+
+def check_jbang_example(natives, script_text, readme_text):
+    """The one-file JBang example runs without a checkout, so it cannot take `llama-platform`: JBang
+    treats a `pom` dependency as a BOM and puts nothing of it on the classpath (measured). It therefore
+    names the classes jar and the platform=yes natives jars itself -- exactly those, at the version of
+    the README's install snippet, which the version bump moves by hand."""
+    deps = [line.split()[1] for line in script_text.splitlines() if line.startswith("//DEPS ")]
+    coords = [d.split(":") for d in deps]
+    good = [c for c in coords if c[:2] == ["net.ladenthin", "llama"] and len(c) in (3, 4)]
+    failures = [f"{JBANG_EXAMPLE}: `{d}` is not net.ladenthin:llama:<version>[:<classifier>]"
+                for d, c in zip(deps, coords) if c not in good]
+    match = re.search(r"<artifactId>llama-platform</artifactId>\s*<version>([^<]+)</version>", readme_text)
+    expected = match.group(1) if match else None
+    versions = {c[2] for c in good}
+    if versions != {expected}:
+        failures.append(f"{JBANG_EXAMPLE}: DEPS version(s) {sorted(versions)} must be the README install "
+                        f"snippet's {expected}")
+    if not any(len(c) == 3 for c in good):
+        failures.append(f"{JBANG_EXAMPLE}: the classes jar net.ladenthin:llama:<version> is missing")
+    named = [c[3] for c in good if len(c) == 4]
+    platform = [r["classifier"] for r in natives if r["platform"] == "yes"]
+    failures += [f"{JBANG_EXAMPLE}: missing the platform natives jar {c}" for c in platform if c not in named]
+    failures += [f"{JBANG_EXAMPLE}: names {c}, which is not a platform=yes row of .github/natives.csv"
+                 for c in named if c not in platform]
+    if len(set(named)) != len(named):
+        failures.append(f"{JBANG_EXAMPLE}: a natives jar is named twice")
+    return failures
+
+
 def check_agent_class_path(natives, agent_pom_text):
     """`java -jar` on the agent jar finds the core through its manifest Class-Path, which names
     every all-backends fat jar."""
@@ -284,5 +315,6 @@ def check(root):
             + check_cmake(natives, read(root, "llama/CMakeLists.txt"))
             + check_dependency_allowlist(natives, nativedeps.ALLOWED)
             + check_readme(natives, read(root, "README.md"))
+            + check_jbang_example(natives, read(root, JBANG_EXAMPLE), read(root, "README.md"))
             + check_agent_class_path(natives, read(root, "llama-atmosphere-agent/pom.xml"))
             + check_agent_version(read(root, "pom.xml"), read(root, "llama-atmosphere-agent/pom.xml")))

.github/buildcheck/tests/test_natives.py

@@ -193,6 +193,27 @@ def test_readme(self):
         failures = natives.check_readme(ROWS, text.replace("`cpu-linux-s390x`", "cpu-linux-s390x"))
         self.assertEqual(failures, ["README.md does not document the natives jar `cpu-linux-s390x`"])
 
+    def test_jbang_example(self):
+        readme = "<artifactId>llama-platform</artifactId>\n    <version>5.2.0</version>\n</dependency>"
+        platform = [r["classifier"] for r in ROWS if r["platform"] == "yes"]
+        lines = ["//DEPS net.ladenthin:llama:5.2.0"] + [f"//DEPS net.ladenthin:llama:5.2.0:{c}" for c in platform]
+        script = "///usr/bin/env jbang\n" + "\n".join(lines) + "\n// a comment naming net.ladenthin:llama:5.2.0:cuda13-linux-x86-64 is not a dependency\n"
+        self.assertEqual(natives.check_jbang_example(ROWS, script, readme), [])
+        # a platform jar missing, a GPU jar named instead
+        broken = script.replace(":cpu-linux-s390x", ":cuda13-linux-x86-64")
+        self.assertEqual(natives.check_jbang_example(ROWS, broken, readme),
+                         ["examples/jbang/Chat.java: missing the platform natives jar cpu-linux-s390x",
+                          "examples/jbang/Chat.java: names cuda13-linux-x86-64, which is not a platform=yes row of .github/natives.csv"])
+        # the classes jar missing
+        failures = natives.check_jbang_example(ROWS, script.replace("//DEPS net.ladenthin:llama:5.2.0\n", ""), readme)
+        self.assertEqual(failures, ["examples/jbang/Chat.java: the classes jar net.ladenthin:llama:<version> is missing"])
+        # a version the README has moved past (the bump edits both by hand)
+        failures = natives.check_jbang_example(ROWS, script, readme.replace("5.2.0", "5.3.0"))
+        self.assertEqual(failures, ["examples/jbang/Chat.java: DEPS version(s) ['5.2.0'] must be the README install snippet's 5.3.0"])
+        # another artifact, or JBang's BOM-only pom form
+        failures = natives.check_jbang_example(ROWS, script + "//DEPS net.ladenthin:llama-platform:5.2.0@pom\n", readme)
+        self.assertEqual(failures, ["examples/jbang/Chat.java: `net.ladenthin:llama-platform:5.2.0@pom` is not net.ladenthin:llama:<version>[:<classifier>]"])
+
     def test_agent_class_path(self):
         good = "<Class-Path>llama-${v}-all-linux-x86-64-jar-with-dependencies.jar llama-${v}-jar-with-dependencies.jar</Class-Path>"
         self.assertEqual(natives.check_agent_class_path(ROWS, good), [])

.github/verify-test-counts.sh

@@ -14,33 +14,39 @@
 # The shape is what defeats the obvious guard: a CLASS-LEVEL assumption failure makes Surefire
 # record tests="0" errors="0" failures="0" skipped="0" for that class. It contributes NO test
 # entries at all, so "did this run skip anything?" is structurally blind to it — a skipped test is
-# still a reported test. Two checks catch it:
+# still a reported test. Three checks catch it:
 #
 #   1. Any testsuite reporting tests="0". This is the exact signature above, it is precise, and it
 #      is platform-independent: a class that runs nowhere is a bug on every OS.
-#   2. A floor on the total number of tests executed. The backstop for a whole class file going
-#      missing from the run rather than reporting zero.
+#   2. A floor on the number of tests EXECUTED (run minus skipped). This is the other shape of the
+#      same failure: a METHOD-LEVEL assumption (Assume.assumeTrue inside a test) does report the
+#      test, as skipped. Measured on a green run at b11529, every test-java-* job runs 1869 tests
+#      and skips 4 (Linux), 11 (macOS, all three jobs) or 13 (Windows, Ninja and MSVC), i.e. it
+#      executes 1856 to 1865; the same tree in a checkout WITHOUT the models runs 1869 and skips
+#      280, i.e. executes 1589. The jobs pass --min-executed 1800: that catches the model set going
+#      missing (or a resolver regression) with a margin of ~200 either way, and tolerates ordinary
+#      test removals of up to ~56 tests before someone has to lower it, deliberately.
+#   3. A floor on the total (--min-total), the backstop for a whole class file going missing from
+#      the run rather than reporting zero. Implied by check 2 when both are given.
 #
-# Check 1 is the sensitive one; check 2 is deliberately slack so it never fails spuriously on a
-# platform that legitimately runs fewer tests. Tighten --min-total once real per-platform numbers
-# are known from a green run.
-#
-# Usage: .github/verify-test-counts.sh <surefire-reports-dir> [--min-total N]
+# Usage: .github/verify-test-counts.sh <surefire-reports-dir> [--min-total N] [--min-executed N]
 # Exit codes: 0 all good, 1 a check failed, 2 nothing to scan.
 
 set -euo pipefail
 
 REPORT_DIR="${1:-}"
 MIN_TOTAL=0
+MIN_EXECUTED=0
 shift || true
 while [ $# -gt 0 ]; do
     case "$1" in
         --min-total) MIN_TOTAL="$2"; shift 2 ;;
+        --min-executed) MIN_EXECUTED="$2"; shift 2 ;;
         *) echo "unknown argument: $1" >&2; exit 1 ;;
     esac
 done
 
-[ -n "$REPORT_DIR" ] || { echo "usage: $0 <surefire-reports-dir> [--min-total N]" >&2; exit 1; }
+[ -n "$REPORT_DIR" ] || { echo "usage: $0 <surefire-reports-dir> [--min-total N] [--min-executed N]" >&2; exit 1; }
 [ -d "$REPORT_DIR" ] || { echo "ERROR: no such directory: $REPORT_DIR" >&2; exit 2; }
 
 shopt -s nullglob
@@ -54,18 +60,26 @@ if [ "${#reports[@]}" -eq 0 ]; then
     exit 2
 fi
 
+# An attribute of the <testsuite> element; the first match, so a nested element carrying the same
+# attribute name cannot shift the number (<testcase> has neither, a skipped test is a child element).
+suite_attr() {
+    local n
+    n="$(grep -o "$2=\"[0-9]*\"" "$1" | head -1 | grep -o '[0-9]*' || true)"
+    echo "${n:-0}"
+}
+
 total=0
+skipped=0
 empty_suites=()
 for f in "${reports[@]}"; do
-    # The count lives on the <testsuite> element; take the first match so a nested element
-    # carrying the same attribute name cannot shift the number.
-    n="$(grep -o 'tests="[0-9]*"' "$f" | head -1 | grep -o '[0-9]*' || true)"
-    [ -n "$n" ] || n=0
+    n="$(suite_attr "$f" tests)"
     total=$((total + n))
+    skipped=$((skipped + $(suite_attr "$f" skipped)))
     if [ "$n" -eq 0 ]; then
         empty_suites+=("$(basename "$f")")
     fi
 done
+executed=$((total - skipped))
 
 status=0
 
@@ -79,11 +93,20 @@ if [ "${#empty_suites[@]}" -gt 0 ]; then
 fi
 
 if [ "$total" -lt "$MIN_TOTAL" ]; then
-    echo "ERROR: only $total test(s) executed, below the floor of $MIN_TOTAL" >&2
+    echo "ERROR: only $total test(s) run, below the floor of $MIN_TOTAL" >&2
+    status=1
+fi
+
+if [ "$executed" -lt "$MIN_EXECUTED" ]; then
+    echo "ERROR: only $executed test(s) executed ($total run, $skipped skipped), below the floor of $MIN_EXECUTED" >&2
+    echo "  Method-level assumptions skipping in bulk look like this: a model file the tests expect is" >&2
+    echo "  missing or resolves to the wrong directory (TestConstants.resolveModelPath), or a native" >&2
+    echo "  library failed to load. If the suite legitimately shrank, lower --min-executed in the" >&2
+    echo "  workflow deliberately." >&2
     status=1
 fi
 
 if [ "$status" -eq 0 ]; then
-    echo "test counts verified: $total test(s) across ${#reports[@]} class(es), none empty (floor $MIN_TOTAL)"
+    echo "test counts verified: $total test(s) run, $skipped skipped, $executed executed across ${#reports[@]} class(es), none empty (floors: total $MIN_TOTAL, executed $MIN_EXECUTED)"
 fi
 exit "$status"

.github/workflows/java-tests.yml

@@ -93,7 +93,7 @@ jobs:
       # zero check is the sensitive half.
       - name: Verify tests actually ran
         shell: bash
-        run: .github/verify-test-counts.sh llama/target/surefire-reports --min-total 1500
+        run: .github/verify-test-counts.sh llama/target/surefire-reports --min-executed 1800
       - name: Memory after tests
         if: always() && runner.os == 'macOS'
         run: vm_stat && sysctl hw.memsize hw.physmem

.github/workflows/publish.yml

@@ -2329,7 +2329,7 @@ jobs:
       # muted on every test-java-* job for months. The floor is deliberately slack; the per-class
       # zero check is the sensitive half.
       - name: Verify tests actually ran
-        run: .github/verify-test-counts.sh llama/target/surefire-reports --min-total 1500
+        run: .github/verify-test-counts.sh llama/target/surefire-reports --min-executed 1800
       - uses: actions/upload-artifact@v7
         if: success()
         with:

CHANGELOG.md

@@ -10,6 +10,12 @@ from version 5.0.0 onward. Pre-fork releases (`1.x`–`4.2.0`) were authored by
 ## [Unreleased]
 
 ### Added
+- **`examples/jbang/Chat.java`**, a one-file console chat that [JBang](https://www.jbang.dev) runs without a
+  checkout or a build (`jbang https://github.com/bernardladenthin/java-llama.cpp/blob/main/examples/jbang/Chat.java
+  model.gguf`). Its `//DEPS` lines name the classes jar and the CPU natives jar of every desktop platform
+  themselves -- JBang treats a `pom` dependency such as `llama-platform` as a BOM and puts nothing of it on the
+  classpath -- and `check-natives.py` holds them to the `platform=yes` rows of `natives.csv` and to the README's
+  release version.
 - **`ModelParameters.setMoeCacheMib(int)`** (`--moe-cache-mib`, llama.cpp b11480, EXPERIMENTAL upstream): a
   GPU cache for the MoE expert weights a `setCpuMoeLayers` / `--cpu-moe` setup keeps in host memory,
   split among several GPUs like the layers; `0` (the default) disables it.
@@ -57,6 +63,20 @@ from version 5.0.0 onward. Pre-fork releases (`1.x`–`4.2.0`) were authored by
   in `build.sh` opts back in). With CUDA 13.4 and sccache 0.18.0 the nvcc launcher failed on the first `.cu`
   files in two confirmed runs (`Missing "cubin" file output`, `Compiler killed by signal 126`), and the
   uncached retry that followed made those jobs slower than a cold build; the C/C++ objects stay cached.
+- **Upgraded the pinned llama.cpp from b11529 to b11534**, in 3 reviewed steps, each ending at a tag. No
+  carried patch needed a refresh, and every drop-check still finds its defect. The one step with project
+  code is b11531, **#30210 "chat : refactor API"**: the prompt and the parser state of a chat generation now
+  live in a `common_chat_session` that `oaicompat_chat_params_parse` fills and the server task applies,
+  replacing the `chat_format` / `chat_parser` / `generation_prompt` / `parse_tool_calls` request fields
+  (none was a `RequestField`, so the Java wire surface is unchanged); `jllama.cpp` threads a session through
+  its four chat entry points and the C++ tests follow the new signatures. Also in the range: OpenCL kernels
+  that compile on Adreno A6x (#30176, the `opencl-android-aarch64` jar and the `llama-android-opencl` AAR on
+  that family), exact GELU for ModernBERT encoders (#30108), and no redundant CUDA copies after `SSM_SCAN`
+  (#29807). Per-step record: `docs/history/llama-cpp-breaking-changes.md`.
+- **CI: every `test-java-*` job now requires at least 1800 tests *executed*** (`verify-test-counts.sh
+  --min-executed`, run minus skipped), where it required 1500 *run* before. The run count cannot see the
+  other shape of the muted-suite failure -- method-level assumptions skipping in bulk -- while the executed
+  count does: the jobs execute 1856 (Windows) to 1865 (Linux) tests, a checkout without the models 1589.
 - **Upgraded the pinned llama.cpp from b11512 to b11529**, in 5 reviewed steps, each ending at a tag. No
   carried patch needed a refresh, and every drop-check still finds its defect. In the range: the server's
   default port moves from 8080 to 9931 (#30159, the `NativeServer` entry above); CUDA top-k selection is
@@ -255,6 +275,11 @@ from version 5.0.0 onward. Pre-fork releases (`1.x`–`4.2.0`) were authored by
   4.4.7 (none of the files the agent's carried JLine fixes touch changed between 4.4.6 and 4.4.7).
 
 ### Fixed
+- **`LlamaLoader` prints its two diagnostic lines to stderr**, `[jllama] using native backend '…'` and
+  `[jllama] extracted '…'`, where they went to stdout before. A router worker JVM
+  (`NativeServer.setWorkerCommand`) printed them onto the router's command pipe, which since llama.cpp b11401
+  the router reports as `unexpected output on the command pipe` (harmless, misleading); and the stdout of a
+  `java -jar` server is otherwise the upstream server's. The CI smokes read both streams already.
 - **`llama/patches/0017`** fixes two defects in the four `_mm_prefetch` calls of ggml's x86
   `quants.c` (the SSSE3-without-AVX branch of `ggml_vec_dot_q4_0_q8_0`, and the only
   `_mm_prefetch` calls in the whole ggml tree), both by routing the address through one new