Playbooks Configuration System

Playbooks uses playbooks.toml file for configuration.

Default Configuration

The default configuration is in the playbooks package here.

playbooks.toml

debug = false
timeout_s = 60
artifact_result_threshold = 500  # Auto-create artifact for playbook results longer than this (# of chars)
max_llm_calls = 50
meeting_message_batch_timeout = 2.0  # Rolling timeout in seconds for batching meeting messages to minimize thrashing
meeting_message_batch_max_wait = 10.0  # Absolute maximum wait time in seconds (prevents starvation under heavy load)
timestamp_granularity = 0  # Timestamp precision: 0=seconds, 1=0.1s, 2=0.01s, 3=milliseconds, -1=10s, -2=100s

[model]
provider = "anthropic"
# name = "claude-sonnet-4-5-20250929"
name = "claude-haiku-4-5-20251001"
temperature = 0.2
max_completion_tokens=15000

[model.execution]
# provider = "xai"
# name = "xai/grok-4-1-fast-non-reasoning"
provider = "gemini"
name = "gemini/gemini-3-flash-preview"

[model.compilation]
provider = "anthropic"
name = "claude-sonnet-4-5-20250929"
temperature = 0.2
max_completion_tokens=15000

[llm_cache]
enabled = true
type = "disk"
path = ".llm_cache"

[langfuse]
enabled = false

See config.py for how to override the default configuration.

$TODO: Add friendly documentation here.