Add -w/--webui switch for llama-cpp webui integration (#15)

* Add -w switch for llama-cpp webui integration

- Add -w/--webui CLI flag to enable webui and open browser
- Add llama.cpp as git submodule (sparse checkout for webui only)
- Add /props endpoint for llama.cpp webui compatibility
- Add webui serving with gzip decompression and CSS injection
- Make 'model' field optional in chat completion requests
- Add Makefile targets: submodules, webui, build-with-webui
- Update build-portable.sh to include webui resources
- Update .gitignore for webui build artifacts

The webui uses OpenAI-compatible endpoints (/v1/chat/completions,
/v1/models, /health) which are already implemented. CSS injection
hides the attachment button since AFM doesn't support file uploads.

Note: Most webui settings (penalties, top-k, etc.) have no effect
as Apple Foundation Model only supports temperature parameter.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add Homebrew distribution support for webui

- Add Homebrew-style paths to webui discovery (/usr/local/share/afm/webui/,
  /opt/homebrew/share/afm/webui/)
- Update create-distribution.sh to include webui in tarball
- Update portable install script to install webui to share directory

This ensures the webui works when installed via Homebrew tap or
portable distribution package.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add AFM branding and pin llama.cpp submodule version

- Inject JavaScript to rebrand webui ("Apple Foundation Models" instead of "llama.cpp")
- Change subtitle to "Type a message to get started" (removes upload reference)
- Update Makefile to document pinned llama.cpp commit
- Add submodule-status target to show pinned versions
- Remove --recursive flag (not needed for webui-only sparse checkout)

The llama.cpp submodule is pinned to commit 0e4ebeb05 for reproducible builds.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

Author: scouzi1966

.gitignore

@@ -62,4 +62,9 @@ test.pdf
 
 # LoRA adapter files for testing
 *.fmadapter
-test_lora.fmadapter
+test_lora.fmadapter
+
+# WebUI build artifacts
+Resources/webui/
+vendor/llama.cpp/tools/server/webui/node_modules/
+vendor/llama.cpp/tools/server/public/

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "vendor/llama.cpp"]
+	path = vendor/llama.cpp
+	url = https://github.com/ggml-org/llama.cpp.git

Makefile

@@ -1,7 +1,7 @@
 # AFM - Apple Foundation Models API
 # Makefile for building and distributing the portable CLI
 
-.PHONY: build clean install uninstall portable dist test help
+.PHONY: build clean install uninstall portable dist test help submodules submodule-status webui build-with-webui
 
 # Default target
 all: build
@@ -22,6 +22,34 @@ build:
 portable:
 	@./build-portable.sh
 
+# Initialize git submodules (pinned to specific commit for reproducibility)
+# NOTE: llama.cpp is pinned to a specific commit - do not use --remote flag
+submodules:
+	@echo "📦 Initializing git submodules (pinned version)..."
+	@git submodule update --init
+	@echo "✅ Submodules initialized (llama.cpp @ $$(cd vendor/llama.cpp && git rev-parse --short HEAD))"
+
+# Show pinned submodule versions
+submodule-status:
+	@echo "📌 Pinned submodule versions:"
+	@git submodule status
+
+# Build the webui from llama.cpp
+webui: submodules
+	@echo "🌐 Building webui..."
+	@if [ ! -d "vendor/llama.cpp/tools/server/webui" ]; then \
+		echo "❌ Error: webui source not found. Run 'make submodules' first."; \
+		exit 1; \
+	fi
+	@cd vendor/llama.cpp/tools/server/webui && npm install && npm run build
+	@mkdir -p Resources/webui
+	@cp vendor/llama.cpp/tools/server/public/index.html.gz Resources/webui/
+	@echo "✅ WebUI built: Resources/webui/index.html.gz"
+
+# Build with webui included
+build-with-webui: webui build
+	@echo "✅ Build with webui complete"
+
 # Clean build artifacts
 clean:
 	@echo "🧹 Cleaning build artifacts..."
@@ -73,19 +101,23 @@ help:
 	@echo "=================================="
 	@echo ""
 	@echo "Available targets:"
-	@echo "  build     - Build release binary (default, portable)"
-	@echo "  portable  - Build with enhanced portability"
-	@echo "  clean     - Clean build artifacts"
-	@echo "  install   - Install to /usr/local/bin (requires sudo)"
-	@echo "  uninstall - Remove from /usr/local/bin"
-	@echo "  dist      - Create distribution package"
-	@echo "  test      - Test the binary and portability"
-	@echo "  debug     - Build debug version"
-	@echo "  run       - Build and run debug server"
-	@echo "  help      - Show this help"
+	@echo "  build           - Build release binary (default, portable)"
+	@echo "  portable        - Build with enhanced portability"
+	@echo "  clean           - Clean build artifacts"
+	@echo "  install         - Install to /usr/local/bin (requires sudo)"
+	@echo "  uninstall       - Remove from /usr/local/bin"
+	@echo "  dist            - Create distribution package"
+	@echo "  test            - Test the binary and portability"
+	@echo "  debug           - Build debug version"
+	@echo "  run             - Build and run debug server"
+	@echo "  submodules      - Initialize git submodules"
+	@echo "  webui           - Build webui from llama.cpp (requires Node.js)"
+	@echo "  build-with-webui - Build with webui included"
+	@echo "  help            - Show this help"
 	@echo ""
 	@echo "Examples:"
 	@echo "  make build              # Build portable executable"
+	@echo "  make build-with-webui   # Build with webui support"
 	@echo "  make install            # Build and install to system"
 	@echo "  make dist               # Create distribution package"
 	@echo "  make test               # Test binary works"

Sources/MacLocalAPI/Controllers/ChatCompletionsController.swift

@@ -62,7 +62,7 @@ struct ChatCompletionsController: RouteCollection {
             let completionTokens = estimateTokens(for: content)
 
             let response = ChatCompletionResponse(
-                model: chatRequest.model,
+                model: chatRequest.model ?? "foundation",
                 content: content,
                 promptTokens: promptTokens,
                 completionTokens: completionTokens
@@ -155,7 +155,7 @@ struct ChatCompletionsController: RouteCollection {
                 try await streamContentSmoothly(
                     content: content,
                     streamId: streamId,
-                    model: chatRequest.model,
+                    model: chatRequest.model ?? "foundation",
                     encoder: encoder,
                     writer: writer,
                     isFirst: &isFirst,
@@ -176,7 +176,7 @@ struct ChatCompletionsController: RouteCollection {
                 // Send final chunk with metrics
                 let finalChunk = ChatCompletionStreamResponse(
                     id: streamId,
-                    model: chatRequest.model,
+                    model: chatRequest.model ?? "foundation",
                     content: "",
                     isFinished: true,
                     usage: usage

Sources/MacLocalAPI/Models/OpenAIRequest.swift

@@ -2,7 +2,7 @@ import Vapor
 import Foundation
 
 struct ChatCompletionRequest: Content {
-    let model: String
+    let model: String?
     let messages: [Message]
     let temperature: Double?
     let maxTokens: Int?