Skip to content

[model]

Required at the top level of seal.toml.

Typestringrequired
Typestringrequired
Typeenum (string), optional

User-supplied effort level. None ⇒ resolved at backend-build time via seal_runtime::llm::default_effort_for_model(&model.name) so Opus 4.7 sessions get xhigh automatically while older / non-supporting models fall back to high. Explicit values in seal.toml always win over the auto-default.

Stored as Option (not as a resolved string) so grant hashes stay stable across seal-version bumps of the default table — a user who didn’t set an explicit effort doesn’t face re-approval when the default changes. Mirrors the max_tokens Option-through-grant pattern (see grant.rs Grant::Llm).

ValueMeaning
"low"
"medium"
"high"
"xhigh"Between High and Max. Anthropic’s recommended starting point for coding / agentic workloads on Opus 4.7.
"max"Anthropic’s highest effort level. Opus-4.6+ only; other models return a 400 when this value is sent.
TypeobjectDefault

Extra HTTP headers merged into every LLM request.

Typeinteger | null

Output-token cap to send to the provider as max_tokens. None ⇒ auto-detect: the daemon queries the provider’s models API at startup and uses the model’s advertised ceiling. Some(n) is a user-supplied override that the daemon clamps to the provider’s reported limit if it’s higher (silent clamp; an API 400 would be the alternative).

Typeenum (string)

Extended thinking mode for LLM requests.

ValueMeaning
"adaptive"Model decides how much to think (default).
"manual"Explicit token budget for thinking (requires thinking_budget).
"disabled"No thinking.
Typeinteger | null