Configuration — Fuze AI Docs

Fuze is configured via fuze.toml in your project root. All settings have sensible defaults — you don't need a config file to get started.

Full reference

[defaults]
max_retries = 3           # Max retries per guarded function
timeout = "30s"           # Per-call timeout
max_cost_per_step = 1.00  # USD ceiling per individual call
max_cost_per_run = 10.00  # USD ceiling for the entire run
max_iterations = 25       # Hard iteration cap
on_loop = "kill"          # "kill", "warn", or "skip"
trace_output = "./fuze-traces.jsonl"  # Path for trace output

[loop_detection]
window_size = 5           # Number of recent outputs to compare
repeat_threshold = 3      # Consecutive identical outputs before triggering
max_flat_steps = 4        # Max steps with no cost change before flagging
cost_velocity_window = 60 # Window in seconds for cost velocity check
cost_velocity_threshold = 1.0  # USD/min threshold that triggers an alert

[daemon]
socket_path = "/tmp/fuze.sock"       # Unix: /tmp/fuze.sock
# socket_path = "\\\\.\\pipe\\fuze.sock"  # Windows: \\.\pipe\fuze.sock
api_port = 7700            # HTTP API port for the daemon
storage = "sqlite"         # "sqlite" or "postgres"
storage_path = "~/.fuze/traces.db"
retention_days = 180       # Minimum 180 for EU AI Act Art. 19

[daemon.budget]
org_daily_budget = 100.00       # Org-wide daily spend ceiling (USD)
per_agent_daily_budget = 10.00  # Per-agent daily spend ceiling (USD)
alert_threshold = 0.80          # Alert at this fraction of ceiling

[daemon.alerts]
dedup_window_ms = 60000   # Suppress duplicate alerts within this window (ms)
webhook_urls = []         # List of webhook URLs for alert delivery

[providers]
# Override default pricing for enterprise discounts
# "openai/gpt-4o" = { input = 0.0020, output = 0.008 }

[alerts]
budget_threshold = 0.80   # Alert at 80% of ceiling
webhook_url = ""          # Optional webhook for alerts

[compliance]
enabled = false
risk_level = "minimal"    # "minimal", "limited", or "high"
log_pii = false           # Anonymize personal data in traces

Configuration priority

Settings are merged in this order (last wins):

Built-in defaults — sensible values for all options
fuze.toml — project-level configuration
Per-function options — guard(fn, { maxCost: 0.50 }) overrides everything

Sections

`[defaults]`

Key	Type	Default	Description
`max_retries`	number	`3`	Maximum retry attempts
`timeout`	string	`"30s"`	Per-call timeout
`max_cost_per_step`	number	`1.00`	USD ceiling per call
`max_cost_per_run`	number	`10.00`	USD ceiling per run
`max_iterations`	number	`25`	Hard iteration cap
`on_loop`	string	`"kill"`	Behavior on loop detection: `"kill"`, `"warn"`, or `"skip"`
`trace_output`	string	`"./fuze-traces.jsonl"`	File path for trace output

`[loop_detection]`

Controls how Fuze detects repetitive agent behavior.

Key	Type	Default	Description
`window_size`	number	`5`	Number of recent outputs to compare
`repeat_threshold`	number	`3`	Consecutive identical outputs before triggering
`max_flat_steps`	number	`4`	Max steps with no cost change before flagging
`cost_velocity_window`	number	`60`	Window in seconds for cost velocity check
`cost_velocity_threshold`	number	`1.0`	USD/min threshold that triggers an alert

`[daemon]`

Key	Type	Default	Description
`socket_path`	string	`"/tmp/fuze.sock"`	Socket path. On Windows use `\\.\pipe\fuze.sock`
`api_port`	number	`7700`	HTTP API port for the daemon
`storage`	string	`"sqlite"`	Storage backend
`storage_path`	string	`"~/.fuze/traces.db"`	Database file path
`retention_days`	number	`180`	Log retention (min 180 for Art. 19)

`[daemon.budget]`

Key	Type	Default	Description
`org_daily_budget`	number	`100.00`	Organization-wide daily spend ceiling (USD)
`per_agent_daily_budget`	number	`10.00`	Per-agent daily spend ceiling (USD)
`alert_threshold`	number	`0.80`	Alert at this fraction of the ceiling

`[daemon.alerts]`

Key	Type	Default	Description
`dedup_window_ms`	number	`60000`	Suppress duplicate alerts within this window (ms)
`webhook_urls`	array	`[]`	List of webhook URLs for alert delivery

`[compliance]`

Key	Type	Default	Description
`enabled`	boolean	`false`	Enable compliance features
`risk_level`	string	`"minimal"`	AI system risk classification
`log_pii`	boolean	`false`	Store raw args/results (GDPR warning)