AWS Bedrock support was not compiled into this build…

Error message

AWS Bedrock support was not compiled into this build (enable the `bedrock` feature)

What it means

BAML compiles AWS Bedrock support behind the optional `bedrock` cargo feature. When a config declares an aws-bedrock client but the runtime binary was built without that feature, dynamic client construction bails with this message. The configuration itself may be fine; the build simply lacks the provider.

Solutions

Use a BAML build/distribution compiled with the `bedrock` feature enabled.
Build BAML from source with `--features bedrock`.
Switch the prompt's client provider to one available in your build (e.g. openai, anthropic, google-ai).
Check your installed binding's feature set / docs to confirm Bedrock support before configuring it.

Example fix

// before
cargo build -p baml-runtime --no-default-features
// after
cargo build -p baml-runtime --features bedrock

Defensive patterns

Strategy: fallback

Validate before calling

// Detect support before configuring
const supportsBedrock = /* runtime feature check or docs */ true;
if (clientProvider === 'aws-bedrock' && !supportsBedrock) throw new Error('This BAML build lacks the `bedrock` feature; use another provider or a Bedrock-enabled build.');

Try / catch

try { await b.MyPrompt(...) } catch (e) { if (String(e).includes('not compiled into this build')) { /* switch to openai/anthropic client or reinstall a bedrock-enabled build */ } else throw e; }

Prevention

Confirm your BAML distribution includes the `bedrock` feature before using aws-bedrock providers.
Build from source with --features bedrock if needed.
Keep a non-Bedrock fallback client in your generator config.

When it happens

Trigger: Using a BAML runtime build compiled without the `bedrock` feature (e.g. a language client distribution that excludes Bedrock) while a prompt's client block specifies provider "aws-bedrock".

Common situations: Installing a prebuilt baml language-client package that ships without Bedrock support, or building BAML from source with default features and then pointing a project at Bedrock; also happens in some Python/Node bindings built for size.

Related errors

AI-assisted analysis of BoundaryML/baml@bd85ce9dee (2026-09-12). Data as JSON: /api/errors/ca313322e7da1c87. Report an issue: GitHub.

Appendix: source

Thrown at engine/baml-runtime/src/internal/llm_client/primitive/mod.rs:150

                    OpenAIClientProviderVariant::Generic => {
                        OpenAIClient::dynamic_new_generic(value, ctx).map(Into::into)
                    }
                    OpenAIClientProviderVariant::Responses => {
                        OpenAIClient::dynamic_new_responses(value, ctx).map(Into::into)
                    }
                    OpenAIClientProviderVariant::Transcriptions => {
                        OpenAIClient::dynamic_new_transcriptions(value, ctx).map(Into::into)
                    }
                    OpenAIClientProviderVariant::OpenRouter => {
                        OpenAIClient::dynamic_new_openrouter(value, ctx).map(Into::into)
                    }
                }
            }
            ClientProvider::Anthropic => AnthropicClient::dynamic_new(value, ctx).map(Into::into),
            #[cfg(feature = "bedrock")]
            ClientProvider::AwsBedrock => AwsClient::dynamic_new(value, ctx).map(Into::into),
            #[cfg(not(feature = "bedrock"))]
            ClientProvider::AwsBedrock => anyhow::bail!(
                "AWS Bedrock support was not compiled into this build (enable the `bedrock` feature)"
            ),
            ClientProvider::GoogleAi => GoogleAIClient::dynamic_new(value, ctx).map(Into::into),
            ClientProvider::Vertex => VertexClient::dynamic_new(value, ctx).map(Into::into),
            ClientProvider::Strategy(strategy_client_provider) => {
                unimplemented!(
                    "Strategy client providers are not supported yet in LLMPrimitiveProvider"
                )
            } // "openai" => OpenAIClient::dynamic_new(value, ctx).map(Into::into),
              // "openai-generic" => OpenAIClient::dynamic_new_generic(value, ctx).map(Into::into),
              // "azure-openai" => OpenAIClient::dynamic_new_azure(value, ctx).map(Into::into),
              // "ollama" => OpenAIClient::dynamic_new_ollama(value, ctx).map(Into::into),
              // "anthropic" => AnthropicClient::dynamic_new(value, ctx).map(Into::into),
              // "google-ai" => GoogleAIClient::dynamic_new(value, ctx).map(Into::into),
              // "vertex-ai" => VertexClient::dynamic_new(value, ctx).map(Into::into),
              // // dynamic_new is not implemented for aws::AwsClient
              // other => {
              //     let options = [

View on GitHub (pinned to bd85ce9dee)