fix(llama-cpp): guard score task for fork backends

TurboQuant and Bonsai reuse the primary gRPC server against llama.cpp forks that do not carry LocalAI's slot-based Score patches. Compile the Score integration only for the patched primary backend and return UNIMPLEMENTED from fork builds instead of referencing absent task types and common_params fields.

Assisted-by: Codex:gpt-5 [gh]
Signed-off-by: Richard Palethorpe <io@richiejp.com>

Author: richiejp

backend/cpp/bonsai/Makefile

@@ -41,6 +41,7 @@ define bonsai-build
 	# and are applied by apply-patches.sh below.
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build purge
+	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:$(1)$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build llama.cpp
@@ -77,6 +78,7 @@ bonsai-cpu-all:
 	# and are applied by apply-patches.sh below.
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build purge
+	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:cpu-all-variants$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build llama.cpp

backend/cpp/llama-cpp/disable-score-task.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+# Mark a copied gRPC server as targeting a llama.cpp fork that does not carry
+# LocalAI's slot-based Score patches. The RPC remains present in the shared
+# protobuf service, but responds with UNIMPLEMENTED instead of referencing
+# server task types and common_params fields absent from those forks.
+
+set -euo pipefail
+
+if [[ $# -ne 1 ]]; then
+    echo "usage: $0 <grpc-server.cpp>" >&2
+    exit 2
+fi
+
+SRC=$1
+
+if [[ ! -f "$SRC" ]]; then
+    echo "grpc-server.cpp not found at $SRC" >&2
+    exit 2
+fi
+
+if grep -q '^#define LOCALAI_LLAMA_CPP_NO_SCORE_TASK' "$SRC"; then
+    echo "==> $SRC already disables the LocalAI score task, skipping"
+    exit 0
+fi
+
+awk '
+    !done && /^#include/ {
+        print "#define LOCALAI_LLAMA_CPP_NO_SCORE_TASK 1"
+        print "// ^ injected by disable-score-task.sh for an unpatched llama.cpp fork"
+        print ""
+        done = 1
+    }
+    { print }
+    END {
+        if (!done) {
+            print "disable-score-task.sh: no #include anchor found" > "/dev/stderr"
+            exit 1
+        }
+    }
+' "$SRC" > "$SRC.tmp"
+mv "$SRC.tmp" "$SRC"
+
+echo "==> LocalAI score task disabled in $SRC"

backend/cpp/llama-cpp/grpc-server.cpp

@@ -690,6 +690,7 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                     // If conversion fails, keep default value (0)
                 }
             }
+#ifndef LOCALAI_LLAMA_CPP_NO_SCORE_TASK
         } else if (!strcmp(optname, "n_rs_seq") || !strcmp(optname, "rs_seq")) {
             // Recurrent-state rollback snapshots per sequence. Hybrid models
             // (deltanet/conv layers) cannot rewind their state, so without
@@ -704,6 +705,7 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                     // If conversion fails, keep default value (0)
                 }
             }
+#endif
         } else if (!strcmp(optname, "slot_prompt_similarity") || !strcmp(optname, "sps")) {
             if (optval != NULL) {
                 try {
@@ -1344,6 +1346,7 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
         }
     }
 
+#ifndef LOCALAI_LLAMA_CPP_NO_SCORE_TASK
     // Score-task suffix forking: reserve seq ids (and recurrent-state cells)
     // beyond the slots so one scoring call decodes all candidate tails in a
     // single batch (SERVER_TASK_TYPE_SCORE, patches/). Requires the unified
@@ -1352,6 +1355,7 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
     // passes so an explicit kv_unified:false wins and disables forking.
     params.score_enabled = request->enablescore();
     params.n_seq_score_forks = params.score_enabled && params.kv_unified ? SERVER_SCORE_FORK_SEQS : 0;
+#endif
 
     // Terminate/pad the override vectors only after BOTH the named-option loop
     // and the generic passthrough (common_params_parse above) have pushed their
@@ -1409,13 +1413,15 @@ class BackendServiceImpl final : public backend::Backend::Service {
         common_params params;
         params_parse(ctx_server, request, params);
 
+#ifndef LOCALAI_LLAMA_CPP_NO_SCORE_TASK
         if (params.score_enabled && !params.kv_unified) {
             const std::string error_msg =
                 "Score requires the unified KV cache; remove kv_unified:false or remove score from known_usecases";
             result->set_message(error_msg);
             result->set_success(false);
             return grpc::Status(grpc::StatusCode::INVALID_ARGUMENT, error_msg);
         }
+#endif
 
         common_init();
         // Ensure debug logs are enabled after common_init() sets up logging
@@ -2912,6 +2918,12 @@ class BackendServiceImpl final : public backend::Backend::Service {
         if (params_base.model.path.empty()) {
             return grpc::Status(grpc::StatusCode::FAILED_PRECONDITION, "Model not loaded");
         }
+#ifdef LOCALAI_LLAMA_CPP_NO_SCORE_TASK
+        (void) request;
+        (void) response;
+        return grpc::Status(grpc::StatusCode::UNIMPLEMENTED,
+            "Score is unavailable in this llama.cpp fork backend");
+#else
         if (!params_base.score_enabled) {
             return grpc::Status(grpc::StatusCode::FAILED_PRECONDITION,
                 "Score was not enabled when the model was loaded; add score to known_usecases");
@@ -3140,6 +3152,7 @@ class BackendServiceImpl final : public backend::Backend::Service {
         }
 
         return grpc::Status::OK;
+#endif
     }
 
     grpc::Status TokenizeString(ServerContext* context, const backend::PredictOptions* request, backend::TokenizationResponse* response) override {

backend/cpp/turboquant/Makefile

@@ -47,6 +47,7 @@ define turboquant-build
 	# original under backend/cpp/llama-cpp/, so the stock llama-cpp build
 	# stays compiling against vanilla upstream.
 	bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build/grpc-server.cpp
+	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build/grpc-server.cpp
 	$(info $(GREEN)I turboquant build info:$(1)$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(TURBOQUANT_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build llama.cpp
@@ -84,6 +85,7 @@ turboquant-cpu-all:
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build purge
 	bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server.cpp
+	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server.cpp
 	$(info $(GREEN)I turboquant build info:cpu-all-variants$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(TURBOQUANT_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build llama.cpp