Changelog¶

AI Gateway Helm chart v0.2.0¶

May 29, 2025

🆕 Features

• Updates AI Gateway Core image to v1.1.0.

• Updates AI Gateway Processors image to v1.1.0.

• Adds AI Gateway processor labs Data Security and Prompt Guard v0.0.1 images.

• Adds Azure Blob Storage support to the audit exporter.

• Adds clusterIP, loadbalancerIP, externalTrafficPolicy and imagePullSecrets configuration for all services.

• Moves AI Gateway chart to private-registry.f5.com/aigw/charts/aigw.

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Helm registry:

• oci://private-registry.f5.com/aigw/charts/aigw:0.2.0

AI Gateway Core v1.1.0¶

May 29, 2025

✨ Highlights:

• Major enhancements to transaction export, including a new format (this is a breaking change to an experimental feature), Azure Blob Storage support, and OpenTelemetry tracing for exports. Note: this feature remains experimental and may change in future releases.

• Service reliability improvements: fallback and retry support for HTTP requests to services.

• Expanded observability: new OpenTelemetry metrics for services and processors.

• Expanded troubleshooting: stacktrace debug logging on panics, and detailed raw HTTP logging.

🆕 Features:

• Improve the format of exported transactions to capture more data and request/response attributes. Note: This is breaking change. The feature remains experimental and may change in future releases.

• Support service fallback: if the core fails to send an HTTP request to a service, it can now send the request to a fallback service.

• Support service retries: the core can now retry failed HTTP requests to services.

• Support exporting transactions to Azure Blob Storage.

• Add OpenTelemetry tracing for transaction exports: each time the core exports a transaction, it creates a trace.

• Support logging stacktraces when the core panics while processing a request (requires debug logging to be enabled).

• Add OpenTelemetry metrics to count tokens, extracted from LLM provider response metadata.

• Add OpenTelemetry metrics to count rejections performed by processors.

• Support logging raw HTTP request/response attributes and payloads for communications with services, processors, and blob storages, to aid debugging and troubleshooting.

• Change timeout related response status code: the core now returns a 502 Gateway Timeout status code (instead of 500 Internal Server Error) when request processing is aborted due to a route timeout.

🐛 Bug fixes:

• Fix debug logging level: previously, the core logged debug-level entries at the info level.

• Fix the default Anthropic version: previously, if the version was not set in the config, the core would use an empty version instead of the default, resulting in failed requests.

• Fix OpenTelemetry span for services: previously, the core created a span for the service API call with the wrong parent (the service phase span instead of the selected service span).

• Ensure F5 FCP licenses are supported.

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

• F5 processors 1.1.0 or higher

• Processors developed with SDK 1.0 or higher

📦 Container images:

• private-registry.f5.com/aigw/aigw:v1.1.0

AI Gateway Processors v1.1.0¶

May 29, 2025

✨ Highlights:

• Minor optimizations for the language-id and prompt-injection processors

• API updates to support new features in Core v1.1.0

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Container images:

• private-registry.f5.com/aigw/aigw-processors-f5:v1.1.0

AI Gateway Prompt Guard Labs processor v0.0.1¶

May 29, 2025

✨ Highlights:

• Initial release

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Container images:

• private-registry.f5.com/aigw/processor-labs/prompt-guard:v0.0.1

AI Gateway Helm chart v0.1.1¶

March 31, 2025

🆕 Features

• Adds readiness configuration and endpoint for AI Gateway Core image.

• Updates AI Gateway Core image to v1.0.2.

• Updates AI Gateway Processors image to v1.0.1.

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Helm registry:

• oci://private-registry.f5.com/aigw/aigw:0.1.1

AI Gateway Core v1.0.2¶

March 31, 2025

🐛 Bug fixes:

• Fix the core not rejecting request/response for parallel stages: if a stage was parallel, the core would not reject request/response, even if a processor rejected it.

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Container images:

• private-registry.f5.com/aigw/aigw:v1.0.2

AI Gateway Core v1.0.1¶

March 28, 2025

✨ Highlights:

• The release includes a number of bug fixes.

🐛 Bug fixes:

• Improve error messages in logs: make the messages more descriptive and user-friendly.

• Fix the readiness probe health check: previously, the probe could have succeeded even if the core wasn’t ready to receive the traffic.

• Return 502 Bad Gateway status when the core doesn’t select any service for a request. Previously, the core would return 404.

• Ensure the core adds an error to an OTel trace for a span that corresponds to the profile sequential stage.

• Ensure the core validates the processor parameters (the params field of the processor configuration).

• Ensure the core returns a 500 Internal Server Error when a processor executed in a parallel stage modifies the client request or LLM response. Such modifications are not allowed. Previously, the core would disregard any modifications, but incorrectly proceed further with any processing.

• Ensure the core fails to start if aigw start is invoked without the config file path.

• Do not print usage if the core terminates with an error.

• Ensure the core returns JSON errors when it cannot match a request against any route. Previously, it would return plain text errors.

• When a service returns an error, ensure the core propagates the HTTP status code to the client. Previously, the core would always return the 500 status code.

• Ensure the core returns errors to clients in JSON using the OpenAI-like error format. Previously, for some cases, the core would return errors in different format.

• Ensure when the core is being shutdown, it exports any pending unexpected transaction. Note: if transactions are not exported in 30s (default terminationGracePeriodSeconds pod parameter), Kubernetes will kill the pod, and, as a result, the unexported transactions will get lost.

• Improve validation of the path field in routes.

• Change the minimal acceptable TLS version for connections to processors and services from v1.3 to v1.2.

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Container images:

• private-registry.f5.com/aigw/aigw:v1.0.1

AI Gateway Processors v1.0.1¶

March 28, 2025

✨ Highlights:

• Minor optimizations for the language-id and prompt-injection processors

• Improved validation of model pipeline parameters

🐛 Bug fixes:

• Fixed an issue with processors server not utilizing worker processors when WEB_CONCURRENCY is set

✅ Compatibility:

• Kubernetes version 1.25.0-0 or higher

📦 Container images:

• private-registry.f5.com/aigw/aigw-processors-f5:v1.0.1

AI Gateway v1.0.0¶

February 25, 2025

AI Gateway Core v0.2.0¶

January 23, 2025

v0.1.0¶

November 13, 2024

✨ Highlights:

F5 AI Gateway routes generative AI traffic to an appropriate Large Language Model (LLM) backend and protects the traffic against common threats, which includes:

• Inspecting and filtering client requests and LLM responses

• Preventing malicious inputs from reaching an LLM backend

• Ensuring that LLM responses are safe to send to clients

• Protecting against leaking sensitive information

AI Gateway is a standalone product that runs on Kubernetes.