Configuration
Configure backends, privacy boundaries, and runtime limits.
Vaner reads configuration from .vaner/config.toml.
Example
[backend]
base_url = "http://127.0.0.1:11434/v1"
model = "qwen2.5-coder:32b"
api_key_env = "OLLAMA_API_KEY"
[proxy]
allow_repo_override = false
max_requests_per_minute = 120
[privacy]
allowed_paths = ["src/**", "docs/**"]
excluded_patterns = ["*.env", "*.key", "*.pem", "credentials*", "secrets*"]
redact_patterns = ["sk-[a-zA-Z0-9_-]{20,}"]
[limits]
max_age_seconds = 3600
max_context_tokens = 4096
Key sections
backend: default upstream endpoint and model.backends.<name>: optional named backend profiles.proxy: HTTP behavior, auth, and rate limits.privacy: include/exclude/redaction rules.limits: freshness and token budgets.
Use vaner init --profile minimal|advanced|multi to scaffold configs with different detail levels.