Enum AiEndpoint 

pub enum AiEndpoint {
    Chat,
    Embeddings,
    Images,
    Audio,
    Moderation,
    Batch,
}

AI-02: which AI endpoint a route serves. The chat endpoint (the default) uses the full adapter translation pipeline (DW-075). The other endpoints are proxied as a passthrough: the request body is forwarded to the provider’s upstream as-is, and the response is returned as-is. Model governance (allowlist check) still applies using the model field from the request body.

Variants

Chat

OpenAI chat-completions (POST /v1/chat/completions). The full adapter translation pipeline applies (DW-075). This is the default.

Embeddings

OpenAI embeddings (POST /v1/embeddings). Proxied as a passthrough; the request body {model, input} is forwarded as-is. Token usage from the response is recorded for budget accounting.

Images

OpenAI images (POST /v1/images/generations). Proxied as a passthrough; no token usage (image generation is priced per image, not per token).

Audio

OpenAI audio (TTS POST /v1/audio/speech, transcription POST /v1/audio/transcriptions). Proxied as a passthrough.

Moderation

OpenAI moderation (POST /v1/moderations). Proxied as a passthrough.

Batch

AI-04 (#194): OpenAI Batch API (POST /v1/batches). Proxied as a passthrough for batch creation/status/cancel. When batch results are retrieved (GET /v1/batches/{id}/output), the JSONL result file is parsed and each line’s usage is metered at the batch (50% discount) rate.

Trait Implementations

impl Clone for AiEndpoint

fn clone(&self) -> AiEndpoint

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AiEndpoint

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

Formats the value using the given formatter.

impl Default for AiEndpoint

fn default() -> AiEndpoint

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AiEndpoint

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for AiEndpoint

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for AiEndpoint

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for AiEndpoint

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for AiEndpoint

impl Eq for AiEndpoint

impl StructuralPartialEq for AiEndpoint