@qvac/llm-llamacpp 0.63.0 → 0.64.1

package/README.md

@@ -25,6 +25,7 @@ This native C++ addon, built using the `Bare` Runtime, simplifies running Large
 - [Architecture](#architecture)
 - [Benchmarking](#benchmarking)
 - [Tests](#tests)
+  - [Fuzzing](#fuzzing)
 - [Glossary](#glossary)
 - [License](#license)
 
@@ -340,6 +341,8 @@ const response = await model.run([
 
 `arguments` is an object or the text of a JSON object, and `content` may be empty on the assistant turn. A malformed tool turn is rejected with `InvalidInputFormat`. [`examples/toolCalling.js`](./examples/toolCalling.js) shows a full round trip.
 
+The tool grammar holds the model to the order of `parameters`. Inside an object it accepts the required properties first, in declared order, then the optional ones, also in declared order. When the model writes a property out of that order, the call isn't rejected with an error: the model drops a field, writes a broken value or never finishes the call. Declare `required` properties before optional ones at every level, and declare each group in the order the model is likely to write it. This applies to nested objects, and to every argument in formats that write the arguments as one JSON object (Qwen3). Qwen3.5's top-level `<parameter=...>` arguments are less strict: up to six required arguments in any order, then the optional ones in any order. An optional argument before a required one is still rejected there.
+
 #### Batch inference
 
 Load the model with `parallel >= 2`, then pass an array of prompts. Each chunk arrives tagged with the id of the sequence that produced it; `await()` returns results in input order.
@@ -698,6 +701,28 @@ npm run test:cpp:models:ci   # exactly what .github/workflows/cpp-tests-llm.yml
 
 First-run downloads pull several GB from Hugging Face. Every fixture is SHA256-verified against a digest pinned in `scripts/download-unit-test-models.js`; mismatched or partial files are re-downloaded automatically. Set `HF_TOKEN` if a repo requires authentication. Override paths with env vars such as `SHARDED_MODEL_FIRST_SHARD_PATH` (see `test/unit/test_common.hpp`).
 
+### Fuzzing
+
+`forLogMessage`, `toLowerAscii`, and `matchesAnyStopString` have a
+[Google FuzzTest][fuzztest] target, `llm-string-fuzz`. Fuzzing is Linux-only:
+it needs clang with libFuzzer and AddressSanitizer, CMake 3.25 or newer,
+[vcpkg](https://vcpkg.io/) (set `VCPKG_ROOT`) and `bare-make`. The target does
+not link `@qvac/fabric`, so it runs with full ASan and LeakSanitizer.
+
+```bash
+npm install
+npm run fuzz                     # bounded run of every FUZZ_TEST, as Linux CI does
+npm run fuzz:continuous          # coverage-guided, one FUZZ_TEST at a time
+npm run fuzz:continuous -- LlmStringFuzz.MatchesAnyStopNeverCrashes --fuzz_for=30m
+```
+
+Flags other than `--continuous` and `--build-dir` go to the fuzz binary. See
+[`docs/architecture/ADDON-FUZZING.md`](../../docs/architecture/ADDON-FUZZING.md)
+for the fuzzing design, the vcpkg-supplied FuzzTest stack, and how to add a
+target.
+
+[fuzztest]: https://github.com/google/fuzztest
+
 ## Glossary
 
 • **Bare Runtime** – Small and modular JavaScript runtime for desktop and mobile. [Learn more](https://docs.pears.com/reference/bare-overview).

package/package.json

@@ -1,11 +1,11 @@
 {
   "name": "@qvac/llm-llamacpp",
-  "version": "0.63.0",
+  "version": "0.64.1",
   "description": "llama addon for qvac",
   "addon": true,
   "scripts": {
     "build": "npm run build:ts && npm run build:native",
-    "build:native": "bare-make generate && bare-make build && bare-make install",
+    "build:native": "bare-make generate -D BUILD_FUZZING=OFF && bare-make build && bare-make install",
     "build:ts": "tsc -p tsconfig.build.json",
     "build:pack": "npm run build:ts && mkdir -p dist && npm pack --pack-destination dist",
     "mobile:copy-prebuilds": "cp -r prebuilds/android-arm64 prebuilds/android-ia32 || echo 'Warning: Failed to copy llamacpp prebuilds to android-ia32'; cp -r prebuilds/android-arm64 prebuilds/android-arm || echo 'Warning: Failed to copy llamacpp prebuilds to android-arm'; cp -r prebuilds/android-arm64 prebuilds/android-x64 || echo 'Warning: Failed to copy llamacpp prebuilds to android-x64'; cp -r prebuilds/ios-arm64 prebuilds/ios-arm64-simulator 2>/dev/null || echo 'iOS prebuilds already present'; cp -r prebuilds/ios-arm64 prebuilds/ios-x64-simulator 2>/dev/null || echo 'iOS prebuilds already present'",
@@ -32,13 +32,13 @@
     "test:unit:generate": "brittle -r test/unit/all.js test/unit/*.test.js",
     "test:prestage": "node --test scripts/__tests__/*.test.js ../../.github/actions/cache-models/warm-models.test.mjs",
     "test:unit": "npm run build:ts && npm run test:unit:generate && bare test/unit/all.js --exit && npm run test:prestage && npm run test:mobile:validate",
-    "test:cpp:build": "bare-make generate -D BUILD_TESTING=ON && bare-make build --target addon-test",
+    "test:cpp:build": "bare-make generate -D BUILD_TESTING=ON -D BUILD_FUZZING=OFF && bare-make build --target addon-test",
     "test:cpp:models": "node scripts/download-unit-test-models.js",
     "test:cpp:models:ci": "node scripts/download-unit-test-models.js --ci",
     "test:cpp:run": "node scripts/run-cpp-tests.js",
     "test:cpp:run:ci": "node scripts/run-cpp-tests.js --ci",
     "test:cpp": "npm run test:cpp:build && npm run test:cpp:run",
-    "coverage:cpp:build": "bare-make generate -D BUILD_TESTING=ON -D ENABLE_COVERAGE=ON && bare-make build --target addon-test",
+    "coverage:cpp:build": "bare-make generate -D BUILD_TESTING=ON -D ENABLE_COVERAGE=ON -D BUILD_FUZZING=OFF && bare-make build --target addon-test",
     "coverage:cpp:run": "node scripts/run-cpp-tests.js --coverage",
     "coverage:cpp:run:ci": "node scripts/run-cpp-tests.js --coverage --ci",
     "coverage:cpp:summary": "cd build/test/unit && llvm-cov report ./addon-test --instr-profile=coverage.profdata -ignore-filename-regex='(tests|build|node_modules|gtest|gmock|\\.vcpkg|/usr)/' > coverage-summary.txt",
@@ -46,7 +46,13 @@
     "coverage:cpp": "npm run coverage:cpp:build && npm run coverage:cpp:run && npm run coverage:cpp:report",
     "test:all": "npm run test:unit && npm run test:integration && npm run test:cpp",
     "benchmarks": "./benchmarks/run-benchmarks.sh",
-    "benchmarks:windows": "powershell -ExecutionPolicy Bypass -File ./benchmarks/run-benchmarks.ps1"
+    "benchmarks:windows": "powershell -ExecutionPolicy Bypass -File ./benchmarks/run-benchmarks.ps1",
+    "fuzz:build": "bare-make generate -D BUILD_FUZZING=ON -D BUILD_TESTING=OFF -D FUZZTEST_FUZZING_MODE=OFF && bare-make build --target llm-string-fuzz",
+    "fuzz:build:continuous": "bare-make generate -D BUILD_FUZZING=ON -D BUILD_TESTING=OFF -D FUZZTEST_FUZZING_MODE=ON && bare-make build --target llm-string-fuzz",
+    "fuzz:run": "npm run test:scripts && node scripts/run-cpp-fuzz.js",
+    "test:scripts": "node --test scripts/__tests__/run-cpp-fuzz.test.js",
+    "fuzz": "npm run fuzz:build && npm run fuzz:run",
+    "fuzz:continuous": "npm run fuzz:build:continuous && node scripts/run-cpp-fuzz.js --continuous"
   },
   "files": [
     "binding.js",
@@ -73,8 +79,8 @@
   "bugs": "https://github.com/tetherto/qvac/issues",
   "homepage": "https://qvac.tether.io",
   "devDependencies": {
-    "@qvac/fabric-android-arm64": "0.22.0",
-    "@qvac/fabric-ios": "0.22.0",
+    "@qvac/fabric-android-arm64": "0.23.0",
+    "@qvac/fabric-ios": "0.23.0",
     "@types/node": "^24.2.1",
     "bare-crypto": "^1.15.3",
     "bare-process": "^4.2.2",
@@ -96,22 +102,22 @@
     "typescript-eslint": "^8.63.0"
   },
   "dependencies": {
-    "@qvac/fabric": "^0.22.0",
+    "@qvac/fabric": "^0.23.0",
     "@qvac/infer-base": "^0.8.0",
     "@qvac/logging": "^0.1.0",
     "bare-fs": "^4.5.1",
     "bare-path": "^3.0.0"
   },
   "optionalDependencies": {
-    "@qvac/fabric-linux-x64": "^0.22.0",
-    "@qvac/fabric-linux-arm64": "^0.22.0",
-    "@qvac/fabric-darwin-arm64": "^0.22.0",
-    "@qvac/fabric-darwin-x64": "^0.22.0",
-    "@qvac/fabric-win32-x64": "^0.22.0"
+    "@qvac/fabric-linux-x64": "^0.23.0",
+    "@qvac/fabric-linux-arm64": "^0.23.0",
+    "@qvac/fabric-darwin-arm64": "^0.23.0",
+    "@qvac/fabric-darwin-x64": "^0.23.0",
+    "@qvac/fabric-win32-x64": "^0.23.0"
   },
   "peerDependencies": {
-    "@qvac/fabric-android-arm64": "^0.22.0",
-    "@qvac/fabric-ios": "^0.22.0"
+    "@qvac/fabric-android-arm64": "^0.23.0",
+    "@qvac/fabric-ios": "^0.23.0"
   },
   "peerDependenciesMeta": {
     "@qvac/fabric-android-arm64": {

package/prebuilds/darwin-arm64/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.63"
+        "version": "0.64.1"
       }
     ],
     "exported_symbols": [
@@ -233,6 +233,7 @@
             "__ZNK30qvac_lib_inference_addon_llama8batching20RuntimeStatsSnapshot22prefillTokensPerSecondEv",
             "__ZN14TextLlmContext15checkAntipromptEmi",
             "__ZN10LlamaModel13setInitLoaderENSt3__18optionalIN10InitLoader11LOADER_TYPEEEENS1_I23FinetuneConfigOverridesEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils21renderWithoutUserTurnEPK21common_chat_templatesRK28common_chat_templates_inputsRKNSt3__18functionIFNS7_6vectorIiNS7_9allocatorIiEEEERKNS7_12basic_stringIcNS7_11char_traitsIcEENSA_IcEEEEEEE",
             "__ZThn48_N14TextLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request13tokenToFeedAtEi",
             "__ZNK14MtmdLlmContext19residentStateTokensEv",
@@ -675,8 +676,9 @@
             "__ZThn40_N10LlamaModelD0Ev",
             "__ZNK14TextLlmContext9saveCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZThn48_NK14MtmdLlmContext28appendCheckpointsToCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
-            "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher6cancelEjRKNSt3__18functionIFvjEEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils11hasUserTurnERKNSt3__16vectorI15common_chat_msgNS1_9allocatorIS3_EEEE",
             "__ZN30qvac_lib_inference_addon_llama7parsers26parseReasoningBudgetConfigENSt3__117basic_string_viewIcNS1_11char_traitsIcEEEE",
+            "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher6cancelEjRKNSt3__18functionIFvjEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching22aggregateObservedStatsERKNSt3__16vectorINS0_20ObservedRequestStatsENS1_9allocatorIS3_EEEE",
             "__ZN14MtmdLlmContext11evalMessageERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEEbb",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23cancelKeyDeferredLockedEv",

package/prebuilds/darwin-x64/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.63"
+        "version": "0.64.1"
       }
     ],
     "exported_symbols": [
@@ -896,6 +896,7 @@
             "__ZNK10LlamaModel23batchRuntimeStatsLockedEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15failGroupLockedERKNSt3__110shared_ptrINS1_10BatchGroupEEESt13exception_ptrNS1_15SaveCachePolicyE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchSchedulerC1E15LlmModelContextjjmiRK13common_paramsNSt3__18functionIFNS6_10unique_ptrI14SequenceDriverNS6_14default_deleteIS9_EEEES5_jiEEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils21renderWithoutUserTurnEPK21common_chat_templatesRK28common_chat_templates_inputsRKNSt3__18functionIFNS7_6vectorIiNS7_9allocatorIiEEEERKNS7_12basic_stringIcNS7_11char_traitsIcEENSA_IcEEEEEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request21chunkConsumesAllUnfedEj",
             "__ZN10LlamaModel7processERKNSt3__13anyE",
             "__ZThn48_N14MtmdLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
@@ -1127,6 +1128,7 @@
             "__ZN14TextLlmContext29clearCacheReconciliationStateEv",
             "__ZN14MtmdLlmContext18adoptResidentStateERKNSt3__16vectorIiNS0_9allocatorIiEEEE",
             "__ZThn40_N10LlamaModelD0Ev",
+            "__ZN30qvac_lib_inference_addon_llama5utils11hasUserTurnERKNSt3__16vectorI15common_chat_msgNS1_9allocatorIS3_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching22aggregateObservedStatsERKNSt3__16vectorINS0_20ObservedRequestStatsENS1_9allocatorIS3_EEEE",
             "__ZN14MtmdLlmContext11evalMessageERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEEbb",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23cancelKeyDeferredLockedEv",

package/prebuilds/ios-arm64/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.63"
+        "version": "0.64.1"
       }
     ],
     "exported_symbols": [
@@ -233,6 +233,7 @@
             "__ZNK30qvac_lib_inference_addon_llama8batching20RuntimeStatsSnapshot22prefillTokensPerSecondEv",
             "__ZN14TextLlmContext15checkAntipromptEmi",
             "__ZN10LlamaModel13setInitLoaderENSt3__18optionalIN10InitLoader11LOADER_TYPEEEENS1_I23FinetuneConfigOverridesEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils21renderWithoutUserTurnEPK21common_chat_templatesRK28common_chat_templates_inputsRKNSt3__18functionIFNS7_6vectorIiNS7_9allocatorIiEEEERKNS7_12basic_stringIcNS7_11char_traitsIcEENSA_IcEEEEEEE",
             "__ZThn48_N14TextLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request13tokenToFeedAtEi",
             "__ZNK14MtmdLlmContext19residentStateTokensEv",
@@ -675,8 +676,9 @@
             "__ZThn40_N10LlamaModelD0Ev",
             "__ZNK14TextLlmContext9saveCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZThn48_NK14MtmdLlmContext28appendCheckpointsToCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
-            "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher6cancelEjRKNSt3__18functionIFvjEEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils11hasUserTurnERKNSt3__16vectorI15common_chat_msgNS1_9allocatorIS3_EEEE",
             "__ZN30qvac_lib_inference_addon_llama7parsers26parseReasoningBudgetConfigENSt3__117basic_string_viewIcNS1_11char_traitsIcEEEE",
+            "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher6cancelEjRKNSt3__18functionIFvjEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching22aggregateObservedStatsERKNSt3__16vectorINS0_20ObservedRequestStatsENS1_9allocatorIS3_EEEE",
             "__ZN14MtmdLlmContext11evalMessageERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEEbb",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23cancelKeyDeferredLockedEv",

package/prebuilds/ios-arm64-simulator/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.63"
+        "version": "0.64.1"
       }
     ],
     "exported_symbols": [
@@ -233,6 +233,7 @@
             "__ZNK30qvac_lib_inference_addon_llama8batching20RuntimeStatsSnapshot22prefillTokensPerSecondEv",
             "__ZN14TextLlmContext15checkAntipromptEmi",
             "__ZN10LlamaModel13setInitLoaderENSt3__18optionalIN10InitLoader11LOADER_TYPEEEENS1_I23FinetuneConfigOverridesEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils21renderWithoutUserTurnEPK21common_chat_templatesRK28common_chat_templates_inputsRKNSt3__18functionIFNS7_6vectorIiNS7_9allocatorIiEEEERKNS7_12basic_stringIcNS7_11char_traitsIcEENSA_IcEEEEEEE",
             "__ZThn48_N14TextLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request13tokenToFeedAtEi",
             "__ZNK14MtmdLlmContext19residentStateTokensEv",
@@ -675,8 +676,9 @@
             "__ZThn40_N10LlamaModelD0Ev",
             "__ZNK14TextLlmContext9saveCacheERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
             "__ZThn48_NK14MtmdLlmContext28appendCheckpointsToCacheFileERKNSt3__112basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEE",
-            "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher6cancelEjRKNSt3__18functionIFvjEEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils11hasUserTurnERKNSt3__16vectorI15common_chat_msgNS1_9allocatorIS3_EEEE",
             "__ZN30qvac_lib_inference_addon_llama7parsers26parseReasoningBudgetConfigENSt3__117basic_string_viewIcNS1_11char_traitsIcEEEE",
+            "__ZN30qvac_lib_inference_addon_llama8batching19MultiRequestBatcher6cancelEjRKNSt3__18functionIFvjEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching22aggregateObservedStatsERKNSt3__16vectorINS0_20ObservedRequestStatsENS1_9allocatorIS3_EEEE",
             "__ZN14MtmdLlmContext11evalMessageERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEEbb",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23cancelKeyDeferredLockedEv",

package/prebuilds/ios-x64-simulator/qvac__llm-llamacpp.bare.exports

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.63"
+        "version": "0.64.1"
       }
     ],
     "exported_symbols": [
@@ -909,6 +909,7 @@
             "__ZNK10LlamaModel23batchRuntimeStatsLockedEv",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler15failGroupLockedERKNSt3__110shared_ptrINS1_10BatchGroupEEESt13exception_ptrNS1_15SaveCachePolicyE",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchSchedulerC1E15LlmModelContextjjmiRK13common_paramsNSt3__18functionIFNS6_10unique_ptrI14SequenceDriverNS6_14default_deleteIS9_EEEES5_jiEEE",
+            "__ZN30qvac_lib_inference_addon_llama5utils21renderWithoutUserTurnEPK21common_chat_templatesRK28common_chat_templates_inputsRKNSt3__18functionIFNS7_6vectorIiNS7_9allocatorIiEEEERKNS7_12basic_stringIcNS7_11char_traitsIcEENSA_IcEEEEEEE",
             "__ZNK30qvac_lib_inference_addon_llama8batching7Request21chunkConsumesAllUnfedEj",
             "__ZN10LlamaModel7processERKNSt3__13anyE",
             "__ZThn48_N14MtmdLlmContext18onDraftLogitsReadyEiijRKNSt3__18functionIFvRKNS0_12basic_stringIcNS0_11char_traitsIcEENS0_9allocatorIcEEEEEEE",
@@ -1140,6 +1141,7 @@
             "__ZN14TextLlmContext29clearCacheReconciliationStateEv",
             "__ZN14MtmdLlmContext18adoptResidentStateERKNSt3__16vectorIiNS0_9allocatorIiEEEE",
             "__ZThn40_N10LlamaModelD0Ev",
+            "__ZN30qvac_lib_inference_addon_llama5utils11hasUserTurnERKNSt3__16vectorI15common_chat_msgNS1_9allocatorIS3_EEEE",
             "__ZN30qvac_lib_inference_addon_llama8batching22aggregateObservedStatsERKNSt3__16vectorINS0_20ObservedRequestStatsENS1_9allocatorIS3_EEEE",
             "__ZN14MtmdLlmContext11evalMessageERKNSt3__16vectorI15common_chat_msgNS0_9allocatorIS2_EEEEbb",
             "__ZN30qvac_lib_inference_addon_llama8batching24ContinuousBatchScheduler23cancelKeyDeferredLockedEv",