BoundaryML/baml · error

{e}

Error message

{e}

What it means

During orchestration, BAML renders each strategy node's prompt before calling the LLM. If render_prompt fails, the node returns an InternalFailure LLMResponse plus this error whose message is the stringified prompt-rendering error ({e}). It means no HTTP request was made for this node — the failure happened entirely inside BAML's prompt pipeline.

Source

Thrown at engine/baml-runtime/src/internal/llm_client/orchestrator/call.rs:100

                results.push((
                    cancel_scope,
                    LLMResponse::Cancelled("Operation cancelled".to_string()),
                    Some(Err(anyhow::anyhow!(
                        crate::errors::ExposedError::AbortError {
                            detailed_message: String::new()
                        }
                    ))),
                ));
                break;
            }
            result = async {
                let prompt = match node.render_prompt(ir, prompt, ctx, params).await {
                    Ok(p) => p,
                    Err(e) => {
                        return Some((
                            node.scope,
                            LLMResponse::InternalFailure(e.to_string()),
                            Some(Err(anyhow::anyhow!(e.to_string()))),
                        ));
                    }
                };

                let ctx = CtxWithHttpRequestId::from(ctx);
                let response = node.single_call(&ctx, &prompt).await;
                let parsed_response = match &response {
                    LLMResponse::Success(s) => {
                        if !node
                            .finish_reason_filter()
                            .is_allowed(s.metadata.finish_reason.as_ref())
                        {
                            let message = "Finish reason not allowed".to_string();
                            Some(Err(anyhow::anyhow!(
                                crate::errors::ExposedError::FinishReasonError {
                                    prompt: prompt.to_string(),
                                    raw_output: s.content.clone(),
                                    detailed_message: message.clone(),

View on GitHub (pinned to bd85ce9dee)

Solutions

1. Read the embedded message {e}; it names the exact rendering problem.
2. Fix the prompt template: correct variable names and Jinja syntax; ensure all ctx/params values are provided and correctly typed.
3. Re-run `baml-cli dev` / regenerate the client so IR and generated code are in sync.
4. Add an orchestration fallback strategy so other nodes can still serve the request if one fails to render.

Example fix

// before
b.baml_value("name", None)?; // render fails: missing param
// after
let ctx = runtime.ctx.create(Some(maplit::btreemap! {
    "name" => "Alice".into(),
}))?;

// Ensure all template variables the prompt needs are present before invoking
fn ensure_vars(prompt_vars: &[&str], params: &HashMap<String, String>) -> Result<(), String> {
    prompt_vars.iter().find(|v| !params.contains_key(**v))
        .map(|v| format!("prompt variable '{v}' not supplied"))
        .map_or(Ok(()), Err)
}

match node_result {
    Err(e) if e.to_string().contains("render") || e.to_string().contains("Missing") => {
        log::error!("prompt render failed: {e}");
        fallback_client_call()
    }
    other => other,
}

When it happens

Trigger: orchestrate() -> node.render_prompt(ir, prompt, ctx, params) returns Err: bad Jinja/template syntax in the .baml prompt, missing or wrongly-typed parameters, or IR resolution failure for the referenced prompt/client.

Common situations: Renaming a function/parameter in .baml without updating callers; passing None for a required param; template referencing an undefined variable; BAML CLI version mismatch between generated client and runtime.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

• Failed before LLM call: {message}
• args must be a map
• {self}\n\nDetailed message: {detailed_message}
• Strategy provider is empty: {}
• Operation cancelled: {message}

AI-assisted analysis of BoundaryML/baml@bd85ce9dee (2026-09-12). Data as JSON: /api/errors/ae7ca7e86da90dc2. Report an issue: GitHub.