@qvac/llm-llamacpp 0.64.0 → 0.64.1

package/README.md

@@ -341,6 +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.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qvac/llm-llamacpp",
-  "version": "0.64.0",
+  "version": "0.64.1",
   "description": "llama addon for qvac",
   "addon": true,
   "scripts": {

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

@@ -7,7 +7,7 @@
     ],
     "current_versions": [
       {
-        "version": "0.64"
+        "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": "0.64"
+        "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": "0.64"
+        "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": "0.64"
+        "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": "0.64"
+        "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",