Enum ContentPart 

pub enum ContentPart {
    Text {
        text: String,
        provider_options: Option<Value>,
    },
    Image {
        image: Vec<u8>,
        media_type: String,
        provider_options: Option<Value>,
    },
    File {
        data: Vec<u8>,
        media_type: String,
        filename: Option<String>,
        provider_options: Option<Value>,
    },
    FileBase64 {
        data: String,
        media_type: String,
        filename: Option<String>,
        provider_options: Option<Value>,
    },
    FileUrl {
        url: String,
        media_type: String,
        provider_options: Option<Value>,
    },
    FileReference {
        media_type: String,
        reference: Value,
        filename: Option<String>,
        provider_options: Option<Value>,
    },
    Reasoning {
        text: String,
        signature: Option<String>,
        provider_options: Option<Value>,
    },
    ToolCall {
        tool_call_id: String,
        tool_name: String,
        input: Value,
        provider_executed: Option<bool>,
        thought_signature: Option<String>,
        provider_options: Option<Value>,
    },
    ToolResult {
        tool_call_id: String,
        result: Value,
        tool_name: Option<String>,
        is_error: Option<bool>,
        preliminary: Option<bool>,
        dynamic: Option<bool>,
        provider_options: Option<Value>,
    },
}

A part of a multi-part message.

Shared between ModelMessage (user-facing) and LanguageModelPrompt (provider-facing).

Variants

Text

A text segment.

Fields

text: String

provider_options: Option<Value>

Provider-specific options for this part (e.g. openai.promptCacheBreakpoint).

Image

An image (raw bytes + MIME type).

Fields

image: Vec<u8>

media_type: String

provider_options: Option<Value>

File

A file (raw bytes + MIME type).

Fields

data: Vec<u8>

media_type: String

filename: Option<String>

provider_options: Option<Value>

FileBase64

A file whose inline data is an already-base64-encoded string.

Mirrors the Vercel AI SDK file part with data: { type: 'data', data: '<base64>' }: the data field holds the raw base64 string verbatim (it is NOT decoded into bytes), so it round-trips through providers that emit a base64 source unchanged.

Fields

data: String

media_type: String

filename: Option<String>

provider_options: Option<Value>

FileUrl

A file referenced by URL.

Mirrors the Vercel AI SDK file part with data: { type: 'url', url }.

Fields

url: String

media_type: String

provider_options: Option<Value>

FileReference

A file referenced by a provider-specific reference (e.g. an OpenAI file ID).

Mirrors the Vercel AI SDK file part with data: { type: 'reference', reference: { openai: 'file-xxx' } }. The reference field is a JSON object keyed by provider name.

Fields

media_type: String

reference: Value

filename: Option<String>

provider_options: Option<Value>

Reasoning

A reasoning / thinking segment produced by the model.

Mirrors the Vercel AI SDK reasoning part. signature is the Anthropic thinking-block signature (from providerOptions.anthropic.signature); when absent the part is treated as having unsupported metadata (unless providerOptions.anthropic.redactedData is present, in which case a redacted_thinking block is emitted).

Fields

text: String

signature: Option<String>

provider_options: Option<Value>

Provider-specific options for this part (e.g. anthropic.signature, anthropic.redactedData, anthropic.cacheControl).

ToolCall

A tool call requested by the model.

Fields

tool_call_id: String

tool_name: String

input: Value

Arguments as a JSON value (usually an object).

provider_executed: Option<bool>

Whether the tool call is executed by the provider rather than by the client. This is part of the prompt contract because providers need it to replay server tool calls on a later turn.

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.

provider_options: Option<Value>

Provider-specific options for this part (e.g. anthropic.cacheControl).

ToolResult

The result of executing a tool call.

Fields

tool_call_id: String

result: Value

The tool’s output (usually a JSON value or plain text).

Accepts the legacy output field name (used by the Vercel AI SDK and the 0.1.0 TypeScript bindings) as an alias during deserialization, so multi-part tool messages constructed either way round-trip correctly. Serialization always emits result.

tool_name: Option<String>

The name of the tool that produced this result (optional on the user-input side; providers that need it can look it up from the preceding tool call).

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_options: Option<Value>

Provider-specific options for this part (e.g. anthropic.cacheControl).

Implementations

impl ContentPart

pub fn text(text: impl Into<String>) -> Self

Convenience constructor for a text part (no provider options).

pub fn tool_call( tool_call_id: impl Into<String>, tool_name: impl Into<String>, input: Value, ) -> Self

Convenience constructor for a tool-call part (no provider options).

pub fn tool_result(tool_call_id: impl Into<String>, result: Value) -> Self

Convenience constructor for a tool-result part (no provider options).

pub fn reasoning(text: impl Into<String>) -> Self

Convenience constructor for a reasoning/thinking part (no provider options, no signature).

pub fn image(image: Vec<u8>, media_type: impl Into<String>) -> Self

Convenience constructor for an image part (no provider options).

pub fn file(data: Vec<u8>, media_type: impl Into<String>) -> Self

Convenience constructor for a file part (no provider options, no filename).

pub fn file_base64( data: impl Into<String>, media_type: impl Into<String>, ) -> Self

Convenience constructor for a base64-encoded file part (no provider options, no filename).

pub fn file_url(url: impl Into<String>, media_type: impl Into<String>) -> Self

Convenience constructor for a URL-referenced file part (no provider options).

pub fn file_reference(media_type: impl Into<String>, reference: Value) -> Self

Convenience constructor for a provider-referenced file part (no provider options, no filename).

Trait Implementations

impl Clone for ContentPart

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 ContentPart

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ContentPart

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ContentPart

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ContentPart

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 ContentPart

impl TS for ContentPart

type WithoutGenerics = ContentPart

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 = ContentPart

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.