Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WARMUP | No | Pre-warm the index by opening key files | |
| PROJECT | Yes | Path to C++ project root (required) | |
| TIMEOUT | No | LSP request timeout | 5.0 |
| LOG_LEVEL | No | Logging verbosity: debug, info, warning, error | |
| AI_ENABLED | No | Enable AI features | |
| INDEX_PATH | No | Custom clangd index location | |
| AI_PROVIDER | No | AI provider: gemini-2.5-flash or gemini-2.5-flash-lite | |
| WARMUP_LIMIT | No | Number of files to warm up | 10 |
| AI_CACHE_DAYS | No | Cache AI summaries for N days | 7 |
| AI_COST_LIMIT | No | Monthly cost limit in USD | 10.0 |
| INDEX_TIMEOUT | No | Timeout for index wait | 300 |
| WAIT_FOR_INDEX | No | Wait for clangd indexing to complete | |
| AI_CONTEXT_LEVEL | No | Code context depth: minimal, local, or full | minimal |
| AI_ANALYSIS_LEVEL | No | Default analysis depth: summary or detailed | summary |
| CALL_HIERARCHY_DEPTH | No | Maximum depth (1-10) | 3 |
| CLANGAROO_AI_API_KEY | No | Google AI API key (can also be set via --ai-api-key) | |
| CALL_HIERARCHY_MAX_CALLS | No | Total call limit | 100 |
| CALL_HIERARCHY_PER_LEVEL | No | Calls per depth level | 25 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |