The Clawdius configuration file is a TOML document with the following schema.
Clawdius looks for configuration in this order (later overrides earlier):
.clawdius/config.toml (default)
clawdius.toml (in current directory)
Path specified by --config / -C flag
[project]
name = "my-project"
rigor_level = "high" # low | medium | high
lifecycle_phase = "context_discovery"
[workspace]
name = "default"
storage = "sqlite" # sqlite | postgres | mariadb
database_path = ".clawdius/workspace.db"
postgres_url = "" # For postgres backend
mariadb_url = "" # For mariadb backend
per_project_tokens = 2000
max_total_tokens = 8000
[storage]
database_path = ".clawdius/graph/index.db"
vector_path = ".clawdius/graph/vectors.lance"
sessions_path = ".clawdius/sessions.db"
[llm]
default_provider = "anthropic" # anthropic | openai | ollama | zai | deepseek | google
max_tokens = 4096
[llm.anthropic]
model = "claude-sonnet-4-20250514"
api_key_env = "ANTHROPIC_API_KEY"
api_key = "" # Not recommended
base_url = "" # Custom endpoint
[llm.openai]
model = "gpt-4o"
api_key_env = "OPENAI_API_KEY"
[llm.ollama]
model = "llama3.2"
base_url = "http://localhost:11434"
[llm.retry]
max_retries = 3
initial_delay_ms = 1000
max_delay_ms = 30000
exponential_base = 2.0
retry_on = ["rate_limit", "timeout", "server_error", "network_error"]
[session]
compact_threshold = 0.85
keep_recent = 4
min_messages = 10
auto_save = true
[output]
show_progress = true
format = "text" # text | json | stream-json
[shell_sandbox]
blocked_commands = [
"rm -rf /",
"mkfs",
"dd if=/dev/zero",
]
timeout_secs = 120
max_output_bytes = 1048576
restrict_to_cwd = true
Key Type Default Description
namestring "clawdius"Project name
rigor_levelstring "high"Rigor level: low, medium, high
lifecycle_phasestring "context_discovery"Current Nexus FSM phase
Key Type Default Description
database_pathpath .clawdius/graph/index.dbSQLite database path
vector_pathpath .clawdius/graph/vectors.lanceLanceDB vector store path
sessions_pathpath .clawdius/sessions.dbSessions database path
Key Type Default Description
default_providerstring (none) Default LLM provider
max_tokensinteger 4096Maximum response tokens
Key Type Default Description
compact_thresholdfloat 0.85Auto-compact at this context fraction
keep_recentinteger 4Messages to keep when compacting
min_messagesinteger 10Minimum messages before compacting
auto_saveboolean trueAuto-save sessions
Key Type Default Description
blocked_commandsarray of strings (see defaults) Blocked command patterns
timeout_secsinteger 120Command timeout in seconds
max_output_bytesinteger 1048576Maximum output size in bytes
restrict_to_cwdboolean trueRestrict to project directory
Key Type Default Description
max_retriesinteger 3Maximum retry attempts
initial_delay_msinteger 1000Initial delay in ms
max_delay_msinteger 30000Maximum delay cap in ms
exponential_basefloat 2.0Backoff multiplier
retry_onarray of strings (all) Conditions: rate_limit, timeout, server_error, network_error
clawdius config show # Show current config (API keys masked)
clawdius config path # Show config file path
clawdius config list # List available keys
clawdius config get llm.default_provider
clawdius config set llm.default_provider openai
API keys can be set via environment variables (highest priority):
Variable Provider
ANTHROPIC_API_KEYAnthropic
OPENAI_API_KEYOpenAI
DEEPSEEK_API_KEYDeepSeek
ZAI_API_KEYZ.AI
OLLAMA_BASE_URLOllama server URL