Enum StreamPart 

pub enum StreamPart {
    TextStart {
        id: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    TextDelta {
        id: String,
        delta: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    TextEnd {
        id: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    StreamStart {
        warnings: Vec<Warning>,
    },
    Finish {
        finish_reason: FinishReason,
        usage: Usage,
        provider_metadata: Option<ProviderMetadata>,
    },
    Error {
        error: AiMuxError,
    },
    ToolInputStart {
        id: String,
        tool_name: String,
        provider_executed: Option<bool>,
        dynamic: Option<bool>,
        title: Option<String>,
        provider_metadata: Option<ProviderMetadata>,
    },
    ToolInputDelta {
        id: String,
        delta: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    ToolInputEnd {
        id: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    ToolCall {
        tool_call_id: String,
        tool_name: String,
        input: Value,
        provider_executed: Option<bool>,
        dynamic: Option<bool>,
        thought_signature: Option<String>,
        invalid: Option<bool>,
        error: Option<AiMuxError>,
        provider_metadata: Option<ProviderMetadata>,
    },
    ToolResult {
        tool_call_id: String,
        tool_name: String,
        result: Value,
        is_error: Option<bool>,
        preliminary: Option<bool>,
        dynamic: Option<bool>,
        provider_metadata: Option<ProviderMetadata>,
    },
    File {
        data: FileData,
        media_type: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    ReasoningStart {
        id: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    ReasoningDelta {
        id: String,
        delta: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    ReasoningEnd {
        id: String,
        provider_metadata: Option<ProviderMetadata>,
    },
    ResponseMetadata {
        id: Option<String>,
        timestamp: Option<String>,
        model_id: Option<String>,
    },
    Source {
        id: String,
        source_type: String,
        url: Option<String>,
        title: Option<String>,
        provider_metadata: Option<ProviderMetadata>,
    },
    Raw {
        raw_value: Value,
    },
}

A single chunk in the stream returned by do_stream.

Variants

TextStart

Start of a text segment.

Fields

id: String

provider_metadata: Option<ProviderMetadata>

TextDelta

A delta of generated text.

Fields

id: String

delta: String

provider_metadata: Option<ProviderMetadata>

TextEnd

End of a text segment.

Fields

id: String

provider_metadata: Option<ProviderMetadata>

StreamStart

First chunk — carries warnings from the provider.

Fields

warnings: Vec<Warning>

Finish

Final chunk — carries usage, finish reason, and metadata.

Fields

finish_reason: FinishReason

usage: Usage

provider_metadata: Option<ProviderMetadata>

Error

An error occurred mid-stream.

Fields

error: AiMuxError

ToolInputStart

Start of a tool call’s input streaming.

Fields

id: String

tool_name: String

provider_executed: Option<bool>

Whether the tool call will be executed by the provider.

dynamic: Option<bool>

Whether the tool is dynamic (defined at runtime, e.g. MCP tools).

title: Option<String>

Optional title for the tool call.

provider_metadata: Option<ProviderMetadata>

ToolInputDelta

A delta of tool call input (partial JSON).

Fields

id: String

delta: String

provider_metadata: Option<ProviderMetadata>

ToolInputEnd

End of a tool call’s input streaming.

Fields

id: String

provider_metadata: Option<ProviderMetadata>

ToolCall

A complete tool call (alternative to the start/delta/end flow).

Fields

tool_call_id: String

tool_name: String

input: Value

Serialized argument text in a Value::String from do_stream; parsed input after stream_text.

provider_executed: Option<bool>

Whether the tool call will be executed by the provider.

dynamic: Option<bool>

Whether the tool is dynamic (defined at runtime, e.g. MCP tools).

thought_signature: Option<String>

Provider-assigned thought signature (e.g. Google Gemini thoughtSignature). Must be echoed back verbatim on the follow-up turn when the tool result is sent.

invalid: Option<bool>

Set by Core when the call remains invalid after optional repair.

error: Option<AiMuxError>

Typed lookup, parsing, schema, or repair failure.

provider_metadata: Option<ProviderMetadata>

ToolResult

A tool result (provider-executed tools).

Fields

tool_call_id: String

tool_name: String

result: Value

is_error: Option<bool>

Whether the result is an error or error message.

preliminary: Option<bool>

Whether the result is preliminary (replaces prior, e.g. image previews).

dynamic: Option<bool>

Whether the tool is dynamic (defined at runtime, e.g. MCP tools).

provider_metadata: Option<ProviderMetadata>

Additional provider-specific metadata for the tool result.

File

A file generated by the model (e.g. an image or document).

Mirrors the Vercel AI SDK file stream part. data is a tagged union covering base64 data, URL, or provider reference.

Fields

data: FileData

media_type: String

provider_metadata: Option<ProviderMetadata>

ReasoningStart

Fields

id: String

provider_metadata: Option<ProviderMetadata>

Provider-specific metadata (e.g. xAI itemId).

ReasoningDelta

Fields

id: String

delta: String

provider_metadata: Option<ProviderMetadata>

Provider-specific metadata (e.g. xAI itemId).

ReasoningEnd

Fields

id: String

provider_metadata: Option<ProviderMetadata>

Provider-specific metadata (e.g. xAI itemId, reasoningEncryptedContent).

ResponseMetadata

Response metadata (id, timestamp, model_id).

Fields

id: Option<String>

timestamp: Option<String>

model_id: Option<String>

Source

A source / citation (e.g. URL citation from search-preview models).

Fields

id: String

source_type: String

url: Option<String>

title: Option<String>

provider_metadata: Option<ProviderMetadata>

Raw

A raw chunk from the provider (for debugging, when include_raw_chunks is set).

Fields

raw_value: Value

Trait Implementations

impl Clone for StreamPart

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for StreamPart

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for StreamPart

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for StreamPart

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl TS for StreamPart

type WithoutGenerics = StreamPart

If this type does not have generic parameters, then WithoutGenerics should just be Self. If the type does have generic parameters, then all generic parameters must be replaced with a dummy type, e.g ts_rs::Dummy or ().
The only requirement for these dummy types is that EXPORT_TO must be None.

type OptionInnerType = StreamPart

If the implementing type is std::option::Option<T>, then this associated type is set to T. All other implementations of TS should set this type to Self instead.

fn ident(cfg: &Config) -> String

Identifier of this type, excluding generic parameters.

fn docs() -> Option<String>

JSDoc comment to describe this type in TypeScript - when TS is derived, docs are automatically read from your doc comments or #[doc = ".."] attributes

fn name(cfg: &Config) -> String

Name of this type in TypeScript, including generic parameters

fn decl_concrete(cfg: &Config) -> String

Declaration of this type using the supplied generic arguments. The resulting TypeScript definition will not be generic. For that, see TS::decl(). If this type is not generic, then this function is equivalent to TS::decl().

fn decl(cfg: &Config) -> String

Declaration of this type, e.g. type User = { user_id: number, ... }. This function will panic if the type has no declaration.

fn inline(cfg: &Config) -> String

Formats this types definition in TypeScript, e.g { user_id: number }. This function will panic if the type cannot be inlined.

fn inline_flattened(cfg: &Config) -> String

Flatten a type declaration. This function will panic if the type cannot be flattened.

fn visit_generics(v: &mut impl TypeVisitor)

where Self: 'static,

Iterates over all type parameters of this type.

fn output_path() -> Option<PathBuf>

Returns the output path to where T should be exported, relative to the output directory. The returned path does not include any base directory.

fn visit_dependencies(v: &mut impl TypeVisitor)

where Self: 'static,

Iterates over all dependency of this type.

fn dependencies(cfg: &Config) -> Vec<Dependency>

where Self: 'static,

Resolves all dependencies of this type recursively.

fn export(cfg: &Config) -> Result<(), ExportError>

where Self: 'static,

Manually export this type to the filesystem. To export this type together with all of its dependencies, use TS::export_all.

fn export_all(cfg: &Config) -> Result<(), ExportError>

where Self: 'static,

Manually export this type to the filesystem, together with all of its dependencies. To export only this type, without its dependencies, use TS::export.

fn export_to_string(cfg: &Config) -> Result<String, ExportError>

where Self: 'static,

Manually generate bindings for this type, returning a String. This function does not format the output, even if the format feature is enabled.