Method run_observed

crates/libsy/src/core/algorithm.rs:719–830

Process a request to completion while reporting each model call to `observer`.

(
        self: Arc<Self>,
        ctx: Context,
        request: Request,
        observer: Option<RunObserver>,
    )

    /// Process a request to completion while reporting each model call to `observer`.
    async fn run_observed(
        self: Arc<Self>,
        ctx: Context,
        request: Request,
        observer: Option<RunObserver>,
    ) -> Result<(Vec<Arc<dyn Decision>>, Response)> {
        // Serve one offloaded call with its target's default client. A failed *model*
        // call is forwarded to the algorithm via `respond`; this errors only on an
        // infrastructure failure (no default client, or the promise was dropped).
        // `serve` makes the one API call libsy itself performs, so it gets its
        // own `libsy.client_call` span.
        #[tracing::instrument(
            target = "libsy",
            name = "libsy.client_call",
            skip_all,
            fields(
                algorithm = observability::algorithm_label(&call.get_routed().ctx),
                switchyard.algorithm = observability::algorithm_label(&call.get_routed().ctx),
                switchyard.routing.tier = tracing::field::Empty,
                selected_model = call.get_decision().selected_model(),
                otel.kind = "client",
                otel.name = %format_args!("chat {}", call.get_decision().selected_model()),
                openinference.span.kind = "LLM",
                gen_ai.operation.name = "chat",
                gen_ai.request.model = call.get_decision().selected_model(),
                gen_ai.request.stream = tracing::field::Empty,
                gen_ai.request.temperature = tracing::field::Empty,
                gen_ai.request.top_p = tracing::field::Empty,
                gen_ai.request.top_k = tracing::field::Empty,
                gen_ai.request.max_tokens = tracing::field::Empty,
                gen_ai.request.reasoning.level = tracing::field::Empty,
                gen_ai.output.type = tracing::field::Empty,
                gen_ai.conversation.id = tracing::field::Empty,
                server.address = tracing::field::Empty,
                server.port = tracing::field::Empty,
                gen_ai.response.id = tracing::field::Empty,
                gen_ai.response.model = tracing::field::Empty,
                gen_ai.usage.input_tokens = tracing::field::Empty,
                gen_ai.usage.output_tokens = tracing::field::Empty,
                gen_ai.usage.cache_read.input_tokens = tracing::field::Empty,
                gen_ai.usage.cache_creation.input_tokens = tracing::field::Empty,
                gen_ai.usage.reasoning.output_tokens = tracing::field::Empty,
                outcome = tracing::field::Empty,
                otel.status_code = tracing::field::Empty,
                error.type = tracing::field::Empty,
                error = tracing::field::Empty,
            )
        )]
        async fn serve(call: CallLlmRequest) -> Result<()> {
            let span = tracing::Span::current();
            observability::record_gen_ai_request(&span, &call.get_routed().request.llm_request);
            if let Some(tier) = call.get_decision().routing_tier() {
                span.record("switchyard.routing.tier", tier);
            }
            if let Some(session_id) = call
                .get_routed()
                .request
                .metadata