Enum ApiSpecificResponse 

pub enum ApiSpecificResponse {
    OpenAIChat {
        logprobs: Option<Json>,
        system_fingerprint: Option<String>,
        service_tier: Option<String>,
    },
    OpenAIResponses {
        output_items: Option<Vec<Json>>,
        status: Option<String>,
        incomplete_details: Option<Json>,
        previous_response_id: Option<String>,
        store: Option<bool>,
        service_tier: Option<String>,
        truncation: Option<Json>,
        reasoning: Option<Json>,
        input_tokens_details: Option<Json>,
        output_tokens_details: Option<Json>,
    },
    AnthropicMessages {
        object_type: Option<String>,
        role: Option<String>,
        stop_reason: Option<String>,
        stop_sequence: Option<String>,
        service_tier: Option<String>,
        container: Option<Json>,
        content_blocks: Option<Vec<Json>>,
    },
    Custom {
        api_name: String,
        data: Json,
    },
}

API-specific response data that cannot be normalized across providers.

Each variant captures fields unique to a particular LLM API, stored via internal tagging on the "api" key.

Variants

OpenAIChat

OpenAI Chat Completions-specific fields.

Fields

logprobs: Option<Json>

Token-level log probabilities (raw JSON, too complex to normalize).

system_fingerprint: Option<String>

System fingerprint for reproducibility.

service_tier: Option<String>

Processing tier used (e.g., “default”).

OpenAIResponses

OpenAI Responses API-specific fields.

Fields

output_items: Option<Vec<Json>>

Full output items array for direct access.

status: Option<String>

Response status (e.g., “completed”, “incomplete”).

incomplete_details: Option<Json>

Details about why the response is incomplete.

previous_response_id: Option<String>

Echoed previous response ID for conversation continuation.

store: Option<bool>

Whether this response is marked for server-side storage.

service_tier: Option<String>

Service tier used for the response.

truncation: Option<Json>

Truncation behavior metadata.

reasoning: Option<Json>

Reasoning configuration/result metadata.

input_tokens_details: Option<Json>

Raw input token details payload.

output_tokens_details: Option<Json>

Raw output token details payload.

AnthropicMessages

Anthropic Messages API-specific fields.

Fields

object_type: Option<String>

Anthropic object type (typically "message").

role: Option<String>

Anthropic response role (typically "assistant").

stop_reason: Option<String>

Raw Anthropic stop_reason.

stop_sequence: Option<String>

Which stop sequence was matched (if any).

service_tier: Option<String>

Anthropic response service tier when present.

container: Option<Json>

Anthropic container payload when present.

content_blocks: Option<Vec<Json>>

Full content blocks array for direct access.

Custom

Custom/unknown API – catch-all for user-implemented codecs.

Fields

api_name: String

API identifier.

data: Json

Opaque API-specific data.

Trait Implementations

impl Clone for ApiSpecificResponse

fn clone(&self) -> ApiSpecificResponse

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ApiSpecificResponse

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ApiSpecificResponse

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ApiSpecificResponse

fn eq(&self, other: &ApiSpecificResponse) -> 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 ApiSpecificResponse

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 ApiSpecificResponse