Models and Runtimes

Warden selects one runtime backend for a config layer and can use separate model lanes for different kinds of model work.

Runtime

The runtime selects the backend used for model-backed execution. Configure it under [defaults]:

warden.toml

[defaults]
runtime = "pi"

Runtime	Purpose
pi	Default. Runs through Pi. Model values must use provider/model selectors.
claude	Runs through Claude Code. Requires Anthropic API key or Claude Code OAuth auth.

Runtime selection is global within a config layer. runtime is not currently a skill-level or trigger-level field.

Pi Model Selectors

When runtime = "pi", configured model values must include a provider prefix:

warden.toml

[defaults.agent]
model = "anthropic/claude-sonnet-4-6"

Examples:

Selector	Credential
openai/gpt-5.5	WARDEN_OPENAI_API_KEY
anthropic/claude-sonnet-4-6	WARDEN_ANTHROPIC_API_KEY

Claude Runtime Models

When runtime = "claude", use the model IDs accepted by Claude Code:

warden.toml

[defaults]
runtime = "claude"

[defaults.agent]
model = "claude-sonnet-4-6"

In GitHub Actions, set WARDEN_ANTHROPIC_API_KEY or provide Claude Code OAuth auth. Locally, Claude runtime can also use existing Claude Code auth.

Model Lanes

Warden can use different models for different stages:

defaults.agent.modelstring

Main repo-aware skill analysis. Preferred default model field.

defaults.auxiliary.modelstring

Structured helper calls such as extraction, repair, merging, dedupe, and fix evaluation.

defaults.synthesis.modelstring

Post-analysis synthesis and consolidation. Falls back to defaults.auxiliary.model when unset.

warden.toml

[defaults]
runtime = "pi"

[defaults.agent]
model = "anthropic/claude-sonnet-4-6"
maxTurns = 30

[defaults.auxiliary]
model = "anthropic/claude-haiku-4-5"
maxRetries = 3

[defaults.synthesis]
model = "anthropic/claude-opus-4-5"

defaults.model and defaults.maxTurns are legacy shorthand for the agent lane. Prefer defaults.agent.model and defaults.agent.maxTurns in new config.

Overrides

Skills and triggers can override the main agent model:

warden.toml

[[skills]]
name = "security-review"
model = "anthropic/claude-opus-4-5"

[[skills.triggers]]
type = "pull_request"
actions = ["opened", "synchronize"]
model = "anthropic/claude-sonnet-4-6"

The CLI --model flag and WARDEN_MODEL environment variable are fallbacks. They only apply when the resolved skill or trigger path does not set a model.

Main agent model precedence, from highest to lowest:

Source	Notes
skills.triggers.model	Most specific. Applies to one trigger.
skills.model	Applies to one skill.
defaults.agent.model	Preferred global default.
defaults.model	Legacy global default.
--model	CLI fallback.
WARDEN_MODEL	Environment fallback.
SDK/runtime default	Used when no explicit model is set.

Auxiliary and synthesis models only come from [defaults.auxiliary] and [defaults.synthesis]. They do not inherit skill or trigger model overrides.

Generated Skill Commands

warden build and warden improve use the synthesis lane because they generate or revise skill artifacts. Their model fallback order is:

Source	Notes
defaults.synthesis.model	Preferred generated-skill model.
defaults.auxiliary.model	Fallback when synthesis is unset.
--model	CLI fallback for this command.
WARDEN_MODEL	Environment fallback.
SDK/runtime default	Used when no explicit model is set.