Enum ReasoningLevel 

pub enum ReasoningLevel {
    Off,
    Adaptive,
    Low,
    Medium,
    High,
    XHigh,
    Max,
    Ultra,
    UltraCode,
}

A named reasoning / thinking depth level.

Ordering is from least to most intensive; Off < Adaptive < Low < … < Ultra.

Variants

Off

No reasoning / thinking output.

Adaptive

Model decides reasoning depth automatically (Anthropic adaptive path).

Low

Low reasoning budget.

Medium

Medium reasoning budget.

High

High reasoning budget.

XHigh

Extra-high reasoning budget (above high, below max).

Max

Maximum named level (below ultra).

Ultra

Ultra — highest intensity, only a subset of Codex models supports this.

UltraCode

Anthropic-only logical xhigh plus standing workflow mode.

Implementations

impl ReasoningLevel

pub fn parse(s: &str) -> Option<ReasoningLevel>

Parse a level from its canonical logical/config string.

Returns None for unknown strings; callers must not silently fallback.

pub fn as_str(self) -> &'static str

The canonical logical/config representation.

Provider request planners own wire conversion. In particular, Codex logical Ultra uses the exact catalog’s multi-agent wire effort (e.g. Astra xhigh, Sol max) plus foreground proactive mode.

pub fn to_legacy_budget(self) -> Option<u32>

Convert to the legacy Anthropic token budget used by the enabled+budget_tokens request shape. Returns None for levels that have no meaningful numeric mapping (Max and Ultra are Codex execution modes, not numeric budgets).

pub fn from_legacy_budget(budget: u32) -> ReasoningLevel

Build from a legacy token budget value (Anthropic path).

0 → Adaptive, positive values → their tier. Does not produce Max or Ultra — those are provider-named levels, never inferred from a budget.

pub fn requires_codex_support(self) -> bool

All levels that are strictly above XHigh (require Codex-specific support).

pub fn requires_anthropic_support(self) -> bool

Whether this level requires exact Anthropic mode capability evidence.

Trait Implementations

impl Clone for ReasoningLevel

fn clone(&self) -> ReasoningLevel

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for ReasoningLevel

impl Debug for ReasoningLevel

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Default for ReasoningLevel

fn default() -> ReasoningLevel

Returns the “default value” for a type.

impl Display for ReasoningLevel

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Eq for ReasoningLevel

impl Hash for ReasoningLevel

fn hash<__H>(&self, state: &mut __H)

where __H: Hasher,

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl Ord for ReasoningLevel

fn cmp(&self, other: &ReasoningLevel) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

fn clamp_to<R>(self, range: R) -> Self

where Self: Sized, R: ClampBounds<Self>,

🔬This is a nightly-only experimental API. (clamp_to)

Restrict a value to a certain range.

impl PartialEq for ReasoningLevel

fn eq(&self, other: &ReasoningLevel) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl PartialOrd for ReasoningLevel

fn partial_cmp(&self, other: &ReasoningLevel) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Rhs) -> bool

Tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Rhs) -> bool

Tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Rhs) -> bool

Tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Rhs) -> bool

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl StructuralPartialEq for ReasoningLevel