Merge branch 'concedo_experimental' into esocrok

Author: Nexesenex

.clang-format

@@ -22,6 +22,13 @@ AllowShortIfStatementsOnASingleLine: Never
 AllowShortLambdasOnASingleLine: Inline
 AllowShortLoopsOnASingleLine: false
 AlwaysBreakBeforeMultilineStrings: true
+# Treat CUDA keywords/attributes as "attribute macros" and avoid breaking lines inside them
+AttributeMacros:
+  - __host__
+  - __device__
+  - __global__
+  - __forceinline__
+  - __launch_bounds__
 BinPackArguments: true
 BinPackParameters: false # OnePerLine
 BitFieldColonSpacing: Both

.editorconfig

@@ -52,3 +52,11 @@ insert_final_newline = unset
 [vendor/miniaudio/miniaudio.h]
 trim_trailing_whitespace = unset
 insert_final_newline = unset
+
+[tools/server/webui/**]
+indent_style = unset
+indent_size = unset
+end_of_line = unset
+charset = unset
+trim_trailing_whitespace = unset
+insert_final_newline = unset

.windsurf/rules/css-architecture.md

@@ -0,0 +1,7 @@
+---
+trigger: manual
+---
+
+#### Tailwind & CSS
+
+-   We are using Tailwind v4 which uses oklch colors so we now want to refer to the CSS vars directly, without wrapping it with any color function like `hsla/hsl`, `rgba` etc.

.windsurf/rules/sveltekit-architecture.md

@@ -0,0 +1,48 @@
+---
+trigger: manual
+---
+
+# Coding rules
+
+## Svelte & SvelteKit
+
+### Services vs Stores Separation Pattern
+
+#### `lib/services/` - Pure Business Logic
+
+-   **Purpose**: Stateless business logic and external communication
+-   **Contains**:
+    -   API calls to external services (ApiService)
+    -   Pure business logic functions (ChatService, etc.)
+-   **Rules**:
+    -   NO Svelte runes ($state, $derived, $effect)
+    -   NO reactive state management
+    -   Pure functions and classes only
+    -   Can import types but not stores
+    -   Focus on "how" - implementation details
+
+#### `lib/stores/` - Reactive State Management
+
+-   **Purpose**: Svelte-specific reactive state with runes
+-   **Contains**:
+    -   Reactive state classes with $state, $derived, $effect
+    -   Database operations (DatabaseStore)
+    -   UI-focused state management
+    -   Store orchestration logic
+-   **Rules**:
+    -   USE Svelte runes for reactivity
+    -   Import and use services for business logic
+    -   NO direct database operations
+    -   NO direct API calls (use services)
+    -   Focus on "what" - reactive state for UI
+
+#### Enforcement
+
+-   Services should be testable without Svelte
+-   Stores should leverage Svelte's reactivity system
+-   Clear separation: services handle data, stores handle state
+-   Services can be reused across multiple stores
+
+#### Misc
+
+-   Always use `let` for $derived state variables

.windsurf/rules/tests.md

@@ -0,0 +1,9 @@
+---
+trigger: manual
+---
+
+# Automated Tests
+
+## General rules
+
+-   NEVER include any test code in the production code - we should always have it in a separate dedicated files

.windsurf/rules/typescript-architecture.md

@@ -0,0 +1,7 @@
+---
+trigger: manual
+---
+
+## TypeScript
+
+-   Add JSDocs for functions

Makefile

@@ -81,7 +81,9 @@ CFLAGS += -DLLAMA_USE_LLGUIDANCE
 CXXFLAGS += -DLLAMA_USE_LLGUIDANCE
 LDFLAGS  += -Lllguidance/target/release -lllguidance
 OBJS_FULL += llguidance.o
-llguidance.o: common/llguidance.cpp
+llguidance:
+	git clone --depth=1 --branch v1.2.0 https://github.com/guidance-ai/llguidance.git
+llguidance.o: common/llguidance.cpp llguidance
 	cd llguidance && cargo build --release
 	$(CXX) $(CXXFLAGS) -Illguidance/target/release -c $< -o $@
 endif
@@ -316,17 +318,29 @@ ifdef LLAMA_METAL
 CFLAGS   += -DGGML_USE_METAL -DGGML_METAL_NDEBUG -DSD_USE_METAL
 CXXFLAGS += -DGGML_USE_METAL -DSD_USE_METAL
 LDFLAGS  += -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
-OBJS     += ggml-metal.o ggml-metal-common.o
+OBJS     += ggml-metal.o ggml-metal-device.o ggml-metal-device-m.o ggml-metal-context-m.o ggml-metal-common.o ggml-metal-ops.o
 
 ggml-metal-common.o: ggml/src/ggml-metal/ggml-metal-common.cpp ggml/src/ggml-metal/ggml-metal-common.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
-ggml-metal.o: ggml/src/ggml-metal/ggml-metal.m ggml/src/ggml-metal/ggml-metal-impl.h ggml/include/ggml-metal.h
+ggml-metal-ops.o: ggml/src/ggml-metal/ggml-metal-ops.cpp ggml/src/ggml-metal/ggml-metal-ops.h
+	$(CXX) $(CXXFLAGS) -c $< -o $@
+
+ggml-metal.o: ggml/src/ggml-metal/ggml-metal.cpp
+	$(CXX) $(CXXFLAGS) -c $< -o $@
+
+ggml-metal-device.o: ggml/src/ggml-metal/ggml-metal-device.cpp
+	$(CXX) $(CXXFLAGS) -c $< -o $@
+
+ggml-metal-device-m.o: ggml/src/ggml-metal/ggml-metal-device.m ggml/src/ggml-metal/ggml-metal-impl.h ggml/include/ggml-metal.h
 	@echo "== Preparing merged Metal file =="
 	@sed -e '/#include "ggml-common.h"/r ggml/src/ggml-common.h' -e '/#include "ggml-common.h"/d' < ggml/src/ggml-metal/ggml-metal.metal > ggml/src/ggml-metal/ggml-metal-embed.metal.tmp
 	@sed -e '/#include "ggml-metal-impl.h"/r ggml/src/ggml-metal/ggml-metal-impl.h' -e '/#include "ggml-metal-impl.h"/d' < ggml/src/ggml-metal/ggml-metal-embed.metal.tmp > ggml/src/ggml-metal/ggml-metal-merged.metal
 	@cp ggml/src/ggml-metal/ggml-metal-merged.metal ./ggml-metal-merged.metal
 	$(CC) $(CFLAGS) -c $< -o $@
+
+ggml-metal-context-m.o: ggml/src/ggml-metal/ggml-metal-context.m ggml/src/ggml-metal/ggml-metal-impl.h ggml/include/ggml-metal.h
+	$(CC) $(CFLAGS) -c $< -o $@
 endif # LLAMA_METAL
 
 ifneq ($(filter aarch64%,$(UNAME_M)),)
@@ -729,6 +743,7 @@ clean:
 	rm -vf *.o main ttsmain sdmain whispermain quantize_gguf quantize_clip quantize_gpt2 quantize_gptj quantize_neox quantize_mpt vulkan-shaders-gen vulkan-shaders-gen-noext gguf-split mtmd-cli mainvk mainvk.exe mtmd-cli.exe gguf-split.exe vulkan-shaders-gen.exe vulkan-shaders-gen-noext.exe main.exe ttsmain.exe sdmain.exe whispermain.exe quantize_clip.exe quantize_gguf.exe quantize_gptj.exe quantize_gpt2.exe quantize_neox.exe quantize_mpt.exe koboldcpp_default.dll koboldcpp_failsafe.dll koboldcpp_noavx2.dll koboldcpp_clblast.dll koboldcpp_clblast_noavx2.dll koboldcpp_clblast_failsafe.dll koboldcpp_cublas.dll koboldcpp_hipblas.dll koboldcpp_vulkan.dll koboldcpp_vulkan_noavx2.dll koboldcpp_default.so koboldcpp_failsafe.so koboldcpp_noavx2.so koboldcpp_clblast.so koboldcpp_clblast_noavx2.so koboldcpp_clblast_failsafe.so koboldcpp_cublas.so koboldcpp_hipblas.so koboldcpp_vulkan.so koboldcpp_vulkan_noavx2.so ggml/src/ggml-vulkan-shaders.cpp ggml/src/ggml-vulkan-shaders.hpp ggml/src/ggml-vulkan-shaders-noext.cpp ggml/src/ggml-vulkan-shaders-noext.hpp
 	rm -vrf ggml/src/ggml-cuda/*.o
 	rm -vrf ggml/src/ggml-cuda/template-instances/*.o
+	rm -vrf llguidance
 
 # useful tools
 main: tools/main/main.cpp common/arg.cpp build-info.h ggml.o ggml-cpu.o ggml-ops.o ggml-vec.o ggml-binops.o ggml-unops.o llama.o console.o llavaclip_default.o llava.o ggml-backend_default.o ggml-backend-reg_default.o ggml-repack.o $(OBJS_FULL) $(OBJS)