Struct ObservableChatClient 

pub struct ObservableChatClient<C: ChatClient> { /* private fields */ }

A ChatClient decorator that emits a chat span per request following the OpenTelemetry GenAI semantic conventions.

Message-content capture (gen_ai.input.messages / gen_ai.output.messages, plus gen_ai.system_instructions / gen_ai.tool.definitions) is off by default; enable it with ObservableChatClient::with_content_capture, mirroring Python’s enable_sensitive_data flag — or construct via ObservableChatClient::from_env to read that flag from ENABLE_SENSITIVE_DATA.

Implementations

impl<C: ChatClient> ObservableChatClient<C>

pub fn new(inner: C, system: impl Into<String>) -> Self

Wrap inner, tagging spans with the given provider/system name (the gen_ai.system / gen_ai.provider.name attributes), e.g. "openai" or "anthropic".

pub fn from_env(inner: C, system: impl Into<String>) -> Self

Wrap inner using ObservabilityConfig::from_env to decide whether content capture is enabled (ENABLE_SENSITIVE_DATA). Equivalent to:

ObservableChatClient::new(inner, system)
    .with_content_capture(ObservabilityConfig::from_env().enable_sensitive_data)

pub fn with_content_capture(self, capture: bool) -> Self

Enable or disable capturing message content on spans (default: off).

pub fn with_observability_config(self, config: ObservabilityConfig) -> Self

Replace the whole ObservabilityConfig — content capture and the GenAI semantic-convention version this client emits for.

pub fn inner(&self) -> &C

A reference to the wrapped client.

Trait Implementations

impl<C: ChatClient> ChatClient for ObservableChatClient<C>

fn get_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Get a complete (non-streaming) response.

fn get_streaming_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatStream>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Get a streaming response as a sequence of updates.

fn model(&self) -> Option<&str>

The default model id for this client, if any.