Enum ModelPurpose 

#[non_exhaustive]
pub enum ModelPurpose {
    OfflineEvaluate,
    Segment,
    Coverage,
    Route,
    Locate,
    Extract,
    Verify,
    QuestionFrame,
    CrossCheck,
    Respects,
    Investigate,
    Acknowledge,
    Answer,
    Review,
    Progress,
}

Why the runtime is calling a model (spec §20.2).

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

OfflineEvaluate

Offline evaluation of a corpus (spec §27.6); never on the request path.

Segment

Split a message into units: requests, questions, constraints and the rest.

Coverage

Find a request or question the units do not cover.

Route

Choose the operation a unit asks for.

Locate

Choose the record an act aims at.

Extract

Fill an act’s arguments.

Verify

Check an act against the words it came from.

QuestionFrame

Choose the record and subjects a question is about.

CrossCheck

Check the whole understanding of a message against the message.

Respects

Judge whether an act changes what a keep-unchanged constraint keeps.

Investigate

Ask for read-only context before a unit is understood.

Acknowledge

Write what a turn did and what it needs next.

Answer

Answer one question.

Review

Check a written block against its facts.

Progress

Say, as it happens, what the assistant is doing to understand a message.

Implementations

impl ModelPurpose

pub const ALL: [Self; 15]

Every purpose, for exhaustive registration and tests.

pub const fn is_understanding(self) -> bool

The tasks that understand a message, before any effect.

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

Stable snake-case label, used in replay records and metrics.

pub const fn is_critical(self) -> bool

Returns true for the purposes whose output can lead to commands or reads being executed (spec §20.4 “critical stage”).

pub fn requirements(self) -> CapabilityRequirements

Capability requirements under SafetyMode::Default (spec §20.4).

pub fn requirements_in(self, mode: SafetyMode) -> CapabilityRequirements

Capability requirements under an explicit safety mode.

• The understanding tasks: one of MUTATION_SAFE_STRUCTURED_OUTPUT, except Investigate, whose output can only trigger reads.
• Investigate and the narration tasks: one of READ_ONLY_STRUCTURED_OUTPUT; their documents only become text.
• OfflineEvaluate: none; evaluation deliberately measures every transport.
• SafetyMode::UnsafeExperimental removes the structured-output requirement for every purpose, and nothing else.

pub const fn logging_policy(self) -> LoggingPolicy

Logging policy of the purpose.

Request-path purposes never log prompts beyond metadata because prompts carry user text and case state; outputs are logged redacted where they are useful for debugging the understanding. OfflineEvaluate may log in full because evaluation corpora are curated. No purpose retains raw provider bodies (spec §25.2).

Trait Implementations

impl Clone for ModelPurpose

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for ModelPurpose

impl Debug for ModelPurpose

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelPurpose

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for ModelPurpose

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

Formats the value using the given formatter.

impl Eq for ModelPurpose

impl Hash for ModelPurpose

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

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 ModelPurpose

fn cmp(&self, other: &Self) -> 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 ModelPurpose

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

Equality operator ==.

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

Inequality operator !=.

impl PartialOrd for ModelPurpose

fn partial_cmp(&self, other: &Self) -> 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 Serialize for ModelPurpose

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelPurpose