Merge branch 'main' into dependabot/cargo/notify-8.2.0

Author: Jakedismo

.codegraph.toml.example

@@ -0,0 +1,100 @@
+# CodeGraph Configuration File
+# Copy this to .codegraph.toml or ~/.codegraph/config.toml and customize
+
+# ============================================================================
+# Embedding Configuration
+# ============================================================================
+[embedding]
+# Provider: "auto", "onnx", "ollama", "openai", or "lmstudio"
+# "auto" will detect available models automatically
+# "lmstudio" recommended for MLX + Flash Attention 2 (macOS)
+provider = "lmstudio"
+
+# Model path or identifier
+# For ONNX: Absolute path to model directory (auto-detected from HuggingFace cache)
+# For Ollama: Model name (e.g., "all-minilm:latest")
+# For LM Studio: Model name (e.g., "jinaai/jina-embeddings-v3")
+# For OpenAI: Model name (e.g., "text-embedding-3-small")
+# Recommended: jinaai/jina-embeddings-v3 (1536-dim, optimized for code)
+model = "jinaai/jina-embeddings-v3"
+
+# LM Studio URL (default port 1234)
+lmstudio_url = "http://localhost:1234"
+
+# Ollama URL (only used if provider is "ollama")
+ollama_url = "http://localhost:11434"
+
+# OpenAI API key (only used if provider is "openai")
+# Can also be set via OPENAI_API_KEY environment variable
+# openai_api_key = "sk-..."
+
+# Embedding dimension (1536 for jina-code-embeddings-1.5b, 384 for all-MiniLM)
+dimension = 1536
+
+# Batch size for embedding generation (GPU optimization)
+batch_size = 64
+
+# ============================================================================
+# LLM Configuration (for insights generation)
+# ============================================================================
+[llm]
+# Enable LLM insights (false = context-only mode for agents like Claude/GPT-4)
+# Set to false for maximum speed if using an external agent
+enabled = false
+
+# LLM provider: "ollama" or "lmstudio"
+# "lmstudio" recommended for MLX + Flash Attention 2 (macOS)
+provider = "lmstudio"
+
+# LLM model identifier
+# For LM Studio: lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
+# For Ollama: Model name (e.g., "qwen2.5-coder:14b", "codellama:13b")
+# Recommended: DeepSeek Coder v2 Lite Instruct Q4_K_M (superior performance)
+model = "lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF"
+
+# LM Studio URL (default port 1234)
+lmstudio_url = "http://localhost:1234"
+
+# Ollama URL
+ollama_url = "http://localhost:11434"
+
+# Context window size (tokens)
+# DeepSeek Coder v2 Lite: 32768 tokens
+context_window = 32000
+
+# Temperature for generation (0.0 = deterministic, 1.0 = creative)
+temperature = 0.1
+
+# Insights mode: "context-only", "balanced", or "deep"
+# - context-only: Return context only (fastest, for agents)
+# - balanced: Process top 10 files with LLM (good speed/quality)
+# - deep: Process all reranked files (comprehensive)
+insights_mode = "context-only"
+
+# ============================================================================
+# Performance Configuration
+# ============================================================================
+[performance]
+# Number of worker threads (defaults to CPU count)
+num_threads = 0  # 0 = auto-detect
+
+# Cache size in MB
+cache_size_mb = 512
+
+# Enable GPU acceleration (requires CUDA/Metal support)
+enable_gpu = false
+
+# Maximum concurrent requests for embedding/LLM
+max_concurrent_requests = 4
+
+# ============================================================================
+# Logging Configuration
+# ============================================================================
+[logging]
+# Log level: "trace", "debug", "info", "warn", "error"
+# Use "warn" during indexing for clean TUI output (recommended)
+# Use "info" for development/debugging
+level = "warn"
+
+# Log format: "pretty", "json", "compact"
+format = "pretty"

.env.example

@@ -1,6 +1,73 @@
-# CodeGraph Security Configuration
+# CodeGraph Configuration Example
 # Copy this file to .env and update the values for your environment
 
+# ============================================================================
+# CodeGraph Core Configuration (Simplified Setup)
+# ============================================================================
+
+# Minimal Setup - Auto-detect embedding provider (ONNX, Ollama, or OpenAI)
+CODEGRAPH_EMBEDDING_PROVIDER=auto
+
+# That's it for basic usage! CodeGraph will auto-detect everything else.
+# Uncomment and customize the settings below if you need more control.
+
+# Embedding Provider Configuration
+# ----------------------------------
+# Provider options: "auto", "onnx", "ollama", "openai", or "lmstudio"
+# CODEGRAPH_EMBEDDING_PROVIDER=auto
+
+# ONNX: Specify model path (or leave empty for auto-detection from HuggingFace cache)
+# CODEGRAPH_LOCAL_MODEL=/path/to/your/onnx/model
+
+# Ollama: Specify embedding model name
+# CODEGRAPH_EMBEDDING_MODEL=all-minilm:latest
+# CODEGRAPH_OLLAMA_URL=http://localhost:11434
+
+# LM Studio: Best for MLX + Flash Attention 2 (recommended on macOS)
+# Default: jina-code-embeddings-1.5b (1536 dimensions)
+# CODEGRAPH_EMBEDDING_PROVIDER=lmstudio
+# CODEGRAPH_EMBEDDING_MODEL=jinaai/jina-embeddings-v3
+# CODEGRAPH_LMSTUDIO_URL=http://localhost:1234
+# CODEGRAPH_EMBEDDING_DIMENSION=1536
+
+# OpenAI: Model name (API key configured below in Security section)
+# CODEGRAPH_EMBEDDING_MODEL=text-embedding-3-small
+
+# LLM Configuration (for local insights generation)
+# --------------------------------------------------
+# Leave empty to use context-only mode (fastest, recommended for agents like Claude/GPT-4)
+# Set to enable local LLM insights generation
+
+# LM Studio with DeepSeek Coder v2 Lite Instruct (recommended)
+# Superior MLX support and Flash Attention 2 on macOS
+# CODEGRAPH_LLM_PROVIDER=lmstudio
+# CODEGRAPH_MODEL=lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
+# CODEGRAPH_LMSTUDIO_URL=http://localhost:1234
+# CODEGRAPH_CONTEXT_WINDOW=32000
+# CODEGRAPH_TEMPERATURE=0.1
+
+# Ollama (alternative)
+# LLM model (e.g., "qwen2.5-coder:14b", "codellama:13b")
+# CODEGRAPH_MODEL=qwen2.5-coder:14b
+# CODEGRAPH_OLLAMA_URL=http://localhost:11434
+
+# LLM context window size (tokens)
+# CODEGRAPH_CONTEXT_WINDOW=32000
+
+# LLM temperature (0.0 = deterministic, 1.0 = creative)
+# CODEGRAPH_TEMPERATURE=0.1
+
+# Logging
+# -------
+# Log level: trace, debug, info, warn, error
+# Use "warn" during indexing for clean TUI output (recommended)
+# Use "info" for development/debugging
+RUST_LOG=warn
+
+# ============================================================================
+# Security Configuration (for production deployments)
+# ============================================================================
+
 # JWT Authentication
 JWT_SECRET=replace_with_secure_random_secret_minimum_32_characters_long
 JWT_EXPIRY_HOURS=24
@@ -33,8 +100,8 @@ MAX_REQUEST_SIZE=10485760  # 10MB
 SESSION_TIMEOUT_HOURS=24
 PASSWORD_MIN_LENGTH=12
 
-# Logging
-LOG_LEVEL=info
+# Logging (see RUST_LOG above for CodeGraph core logging)
+# LOG_LEVEL=info  # For application-level logging
 SECURITY_LOG_LEVEL=warn
 LOG_FORMAT=json
 

.github/workflows/docs.yml

@@ -436,7 +436,7 @@ jobs:
         path: docs-site
 
     - name: Setup Node.js
-      uses: actions/setup-node@v4
+      uses: actions/setup-node@v6
       with:
         node-version: '18'
 

.gitignore

@@ -168,4 +168,5 @@ CLAUDE.md
 AGENTS.md
 CRUSH.md
 OUROBOROS.md
-.codegraph/
+.codegraph/
+SESSION-MEMORY.md

.gitignore.codegraph

@@ -0,0 +1,5 @@
+# CodeGraph generated files
+.codegraph/db/
+.codegraph/cache/
+.codegraph/vectors/
+.codegraph/logs/