site: v0.4 release notes

site/src/data/releases/index.json

@@ -2,7 +2,7 @@
   "metadata": {
     "title": "Release Notes",
     "description": "Release Notes for Envoy AI Gateway",
-    "lastUpdated": "2025-08-21"
+    "lastUpdated": "2025-10-30"
   },
   "community": {
     "slack": "https://envoyproxy.slack.com/archives/C07Q4N24VAA",

site/src/data/releases/v0.3.json

@@ -3,7 +3,7 @@
     "version": "v0.3",
     "title": "Envoy AI Gateway v0.3.x",
     "subtitle": "Release version introducing intelligent inference routing with Endpoint Picker Provider,enhanced observability features, Google Vertex AI support, and enhanced provider integrations.",
-    "badge": "Latest",
+    "badge": "Stable",
     "badgeType": "milestone"
   },
   "releases": [

site/src/data/releases/v0.4.json

@@ -0,0 +1,301 @@
+{
+  "series": {
+    "version": "v0.4",
+    "title": "Envoy AI Gateway v0.4.x",
+    "subtitle": "Release introducing Model Context Protocol (MCP) Gateway, OpenAI Image Generation, first-party Anthropic support, guided output decoding for GCP Vertex AI/Gemini, cross-namespace references, enhanced authentication, and comprehensive observability improvements.",
+    "badge": "Latest",
+    "badgeType": "milestone"
+  },
+  "releases": [
+    {
+      "version": "v0.4.0",
+      "date": "October 30, 2025",
+      "type": "minor",
+      "tags": [
+        { "text": "MCP Gateway", "type": "feature" },
+        { "text": "Image Generation", "type": "feature" },
+        { "text": "First-Party Anthropic Support", "type": "feature" },
+        { "text": "Guided Output Decoding", "type": "feature" },
+        { "text": "Cross-Namespace Support", "type": "feature" },
+        { "text": "Enhanced Auth", "type": "feature" },
+        { "text": "Client SDK", "type": "feature" },
+        { "text": "InferencePool v1", "type": "feature" }
+      ],
+      "overview": "Envoy AI Gateway v0.4.0 is a major release introducing Model Context Protocol (MCP) Gateway support with OAuth and API key authentication, OpenAI Image Generation API support, first-party Anthropic provider integration, guided output decoding for GCP Vertex AI/Gemini models, cross-namespace resource references with ReferenceGrant, enhanced AWS and Azure authentication, type-safe Kubernetes client SDK, InferencePool v1 support, and comprehensive observability improvements. This release also includes route-level header mutations, cached token tracking, and standalone CLI auto-configuration for multiple providers.",
+      "features": [
+        {
+          "title": "Model Context Protocol (MCP) Gateway",
+          "items": [
+            {
+              "title": "New <code>MCPRoute</code> CRD",
+              "description": "Introduces <code>MCPRoute</code> custom resource for routing MCP requests to backend MCP servers, enabling unified AI API for multiple MCP backends."
+            },
+            {
+              "title": "Complete MCP spec implementation",
+              "description": "Includes streamable HTTP transport, JSON-RPC 2.0 support, and MCP spec-compliant OAuth 2.0 authorization with JWKS validation and Protected Resource Metadata."
+            },
+            {
+              "title": "Server multiplexing and tool routing",
+              "description": "Aggregates multiple MCP servers behind a single endpoint with intelligent tool routing, tool filtering (exact match and regex patterns), and collision detection."
+            },
+            {
+              "title": "Upstream authentication",
+              "description": "Supports both OAuth-based authentication and API key authentication for secure backend MCP server communication with configurable headers."
+            },
+            {
+              "title": "Session management",
+              "description": "Implements MCP session handling with encryption, rotatable seeds, and graceful session lifecycle management."
+            },
+            {
+              "title": "Full observability integration",
+              "description": "Provides comprehensive monitoring, logging, and tracing for MCP operations with configurable access logs and metrics enrichment."
+            }
+          ]
+        },
+        {
+          "title": "OpenAI Image Generation Support",
+          "items": [
+            {
+              "title": "Complete <code>/v1/images/generations</code> endpoint",
+              "description": "End-to-end support for OpenAI's image generation API including request/response translation, Brotli encoding/decoding, and full protocol compatibility."
+            },
+            {
+              "title": "Image generation tracing",
+              "description": "OpenInference-compliant distributed tracing for image generation requests with detailed request parameters and timing information."
+            },
+            {
+              "title": "Image generation metrics",
+              "description": "Comprehensive metrics instrumentation following OpenTelemetry Gen AI semantic conventions for image generation operations."
+            }
+          ]
+        },
+        {
+          "title": "First-Party Anthropic Provider",
+          "items": [
+            {
+              "title": "Direct api.anthropic.com support",
+              "description": "Native integration with Anthropic's API at <code>api.anthropic.com</code>, complementing existing GCP Vertex AI Anthropic support."
+            },
+            {
+              "title": "Anthropic API key authentication",
+              "description": "Native <code>x-api-key</code> header-based authentication matching Anthropic's API conventions and SDK patterns."
+            },
+            {
+              "title": "Passthrough translator with token usage tracking",
+              "description": "Efficient passthrough translation layer that captures token usage and maintains API compatibility while minimizing overhead."
+            },
+            {
+              "title": "Standalone CLI auto-configuration",
+              "description": "Auto-configuration from ANTHROPIC_API_KEY environment variable in standalone mode, enabling zero-config deployments."
+            }
+          ]
+        },
+        {
+          "title": "Guided Output Support for GCP Vertex AI/Gemini",
+          "items": [
+            {
+              "title": "Guided regex support",
+              "description": "Constrains model outputs to match specific regular expressions for GCP Vertex AI/Gemini models, enabling structured text generation."
+            },
+            {
+              "title": "Guided choice support",
+              "description": "Restricts model outputs to predefined choices for GCP Vertex AI/Gemini models, ensuring responses conform to expected values."
+            },
+            {
+              "title": "Guided JSON support",
+              "description": "Ensures model outputs are valid JSON conforming to specified schemas for GCP Vertex AI/Gemini models, with OpenAI-compatible API translation."
+            }
+          ]
+        },
+        {
+          "title": "Cross-Namespace Resource References",
+          "items": [
+            {
+              "title": "Cross-namespace <code>AIServiceBackend</code> references",
+              "description": "<code>AIGatewayRoute</code> can now reference <code>AIServiceBackend</code> resources in different namespaces, enabling multi-tenant and organizational separation patterns."
+            },
+            {
+              "title": "ReferenceGrant validation",
+              "description": "Comprehensive ReferenceGrant integration following Gateway API patterns, with automatic validation and clear error messages when grants are missing."
+            },
+            {
+              "title": "Event-driven reconciliation",
+              "description": "ReferenceGrant changes automatically trigger reconciliation of affected routes, ensuring security policies are always up-to-date."
+            }
+          ]
+        },
+        {
+          "title": "Enhanced Upstream Authentication",
+          "items": [
+            {
+              "title": "AWS SDK default credential chain",
+              "description": "Support for AWS SDK's default credential chain including IRSA (IAM Roles for Service Accounts), EKS Pod Identity, EC2 Instance Profiles, and environment variables, eliminating need for static credentials."
+            },
+            {
+              "title": "Azure API key authentication",
+              "description": "Native Azure OpenAI API key authentication using the <code>api-key</code> header, matching Azure SDK conventions and console practices."
+            },
+            {
+              "title": "Azure CLI auto-configuration",
+              "description": "Standalone CLI auto-configuration from <code>AZURE_OPENAI_API_KEY</code> and <code>AZURE_OPENAI_ENDPOINT</code> environment variables, compatible with Elastic and other Azure-based deployments."
+            }
+          ]
+        },
+        {
+          "title": "Traffic Management and Configuration",
+          "items": [
+            {
+              "title": "Route-level header mutations",
+              "description": "New <code>headerMutation</code> field in <code>AIGatewayRouteRuleBackendRef</code> enables per-route header manipulation with smart merge logic when combined with backend-level mutations. Essential for GCP provisioned throughput and other advanced routing scenarios."
+            },
+            {
+              "title": "<code>InferencePool</code> v1 support",
+              "description": "Updated to Gateway API Inference Extension v1.0, providing stable intelligent endpoint selection with enhanced performance and reliability."
+            },
+            {
+              "title": "Cached token usage tracking for actual token usage reporting",
+              "description": "Captures and reports cached token statistics from cloud providers (Anthropic, Bedrock, etc.), providing accurate cost attribution for prompt caching features."
+            }
+          ]
+        },
+        {
+          "title": "Standalone Mode and CLI",
+          "items": [
+            {
+              "title": "Docker image support",
+              "description": "Official Docker images for the aigw CLI published to GitHub Container Registry, enabling containerized standalone deployments with proper health checks and lifecycle management."
+            },
+            {
+              "title": "Multi-provider auto-configuration",
+              "description": "Zero-config standalone mode supporting automatic configuration from <code>OPENAI_API_KEY</code>, <code>AZURE_OPENAI_API_KEY</code>, or <code>ANTHROPIC_API_KEY</code> environment variables with intelligent dialect detection and OpenAI SDK compatibility. Generates complete Envoy configuration automatically."
+            },
+            {
+              "title": "MCP server configuration",
+              "description": "Native MCP support in standalone mode via <code>--mcp-config</code> and <code>--mcp-json</code> flags, enabling unified LLM and MCP server configuration in a single aigw run invocation without Kubernetes."
+            },
+            {
+              "title": "XDG Base Directory standards",
+              "description": "Proper separation of configuration, data, state, and runtime files following XDG Base Directory specification, improving organization and enabling better cleanup and management of aigw state."
+            },
+            {
+              "title": "Environment variable substitution",
+              "description": "Support for environment variable substitution in configuration files, enabling dynamic configuration and secrets management in standalone deployments."
+            },
+            {
+              "title": "Enhanced readiness monitoring",
+              "description": "Improved Envoy readiness detection and status reporting in standalone mode, providing clear insights into when the gateway is ready to accept traffic with better error messages."
+            },
+            {
+              "title": "Consolidated admin server",
+              "description": "Unified admin server on a single port serving both <code>/metrics</code> and <code>/health</code> endpoints, simplifying monitoring and health check configuration."
+            },
+            {
+              "title": "Improved error handling",
+              "description": "<code>aigw</code> CLI now fails fast and exits cleanly if external processor fails to start, preventing silent failures and improving debugging experience."
+            }
+          ]
+        },
+        {
+          "title": "Developer Experience",
+          "items": [
+            {
+              "title": "Type-safe Kubernetes client SDK",
+              "description": "Generated client libraries for all AI Gateway CRDs following standard Kubernetes client-go patterns, enabling developers to build controllers, operators, CLI tools, and custom integrations with type safety."
+            }
+          ]
+        },
+        {
+          "title": "Observability Enhancements",
+          "items": [
+            {
+              "title": "OpenTelemetry native metrics export",
+              "description": "Support for OTEL-native metrics export (in addition to Prometheus), enabling integration with Elastic Stack, OTEL-TUI, and other OTEL-native observability systems. Includes console exporter for ad-hoc debugging without external dependencies."
+            },
+            {
+              "title": "Embeddings tracing implementation",
+              "description": "Complete OpenInference-compliant tracing for embeddings operations, complementing existing chat completion tracing."
+            },
+            {
+              "title": "Azure OpenAI embeddings translator",
+              "description": "Native support for Azure OpenAI embeddings API with proper protocol translation and token usage tracking."
+            },
+            {
+              "title": "Enhanced <code>/messages</code> endpoint metrics",
+              "description": "Distinct metrics for Anthropic's <code>/messages</code> endpoint, providing accurate attribution separate from <code>/chat/completions</code> endpoints."
+            },
+            {
+              "title": "Legacy <code>/v1/completions</code> endpoint",
+              "description": "Full pass-through support for OpenAI's legacy <code>/v1/completions</code> endpoint with complete tracing and metrics implementation, ensuring backward compatibility and comprehensive observability."
+            },
+            {
+              "title": "Original model tracking",
+              "description": "Metrics now track both the original requested model and any overridden model names, providing accurate attribution in multi-provider and model virtualization scenarios."
+            }
+          ]
+        },
+        {
+          "title": "Provider-Specific Enhancements",
+          "items": [
+            {
+              "title": "AWS Bedrock reasoning support",
+              "description": "Full support for reasoning/thinking tokens in AWS Bedrock responses for both streaming and non-streaming modes, properly exposing extended thinking processes in Claude and other reasoning-capable models."
+            },
+            {
+              "title": "GCP Vertex AI safety settings",
+              "description": "Support for GCP-specific safety settings configuration, allowing fine-grained control over content filtering and safety thresholds for Gemini models."
+            },
+            {
+              "title": "Gemini usage chunk improvements",
+              "description": "Accurate completion_tokens reporting in streaming usage chunks for Gemini models, ensuring proper token accounting during streaming responses."
+            }
+          ]
+        }
+      ],
+      "apiChanges": [
+        {
+          "title": "New <code>MCPRoute</code> CRD",
+          "description": "Introduces <code>MCPRoute</code> custom resource with comprehensive fields for MCP server configuration, tool filtering, authentication policies (OAuth and API key), and Protected Resource Metadata."
+        },
+        {
+          "title": "Cross-namespace references in <code>AIGatewayRoute</code>",
+          "description": "Added namespace field to <code>AIGatewayRouteRuleBackendRef</code>, enabling cross-namespace backend references with ReferenceGrant validation."
+        },
+        {
+          "title": "Route-level header mutations",
+          "description": "Added headerMutation field to <code>AIGatewayRouteRuleBackendRef</code> for per-route header manipulation with smart merge logic."
+        },
+        {
+          "title": "Anthropic API key authentication",
+          "description": "Added <code>AnthropicAPIKey</code> to <code>BackendSecurityPolicy</code> for <code>x-api-key</code> header authentication."
+        },
+        {
+          "title": "Azure API key authentication",
+          "description": "Added AzureAPIKey to <code>BackendSecurityPolicy</code> for api-key header authentication."
+        },
+        {
+          "title": "AWS credential chain support",
+          "description": "<code>BackendSecurityPolicy</code> AWS auth now supports SDK default credential chain when credentials are not explicitly provided."
+        },
+        {
+          "title": "<code>InferencePool</code> v1",
+          "description": "Updated to support Gateway API Inference Extension v1.0 (inference.networking.k8s.io/v1) instead of v1alpha1."
+        },
+        {
+          "title": "Enforced <code>Backend</code> resource requirement",
+          "description": "Added CRD validation to <code>AIServiceBackend</code> explicitly requiring Envoy Gateway <code>Backend</code> resources (Kubernetes Service is not supported)."
+        }
+      ],
+      "dependencies": [
+        { "title": "Go 1.25.3", "description": "Updated to Go 1.25.3 for improved performance and security." },
+        { "title": "Envoy Gateway v1.6", "description": "Built on Envoy Gateway v1.6 for proven data plane capabilities and enhanced features." },
+        { "title": "Envoy v1.36", "description": "Leveraging Envoy Proxy v1.36's battle-tested networking capabilities." },
+        { "title": "Gateway API v1.4.0", "description": "Support for Gateway API v1.4.0 specifications." },
+        { "title": "Gateway API Inference Extension v1.0.2", "description": "Integration with Gateway API Inference Extension v1.0.2 for stable intelligent endpoint selection." }
+      ]
+    }
+  ],
+  "navigation": {
+    "previous": { "version": "v0.3.x Series", "path": "/release-notes/v0.3" },
+    "next": null
+  }
+}

site/src/pages/release-notes/index.mdx

@@ -8,10 +8,12 @@ import { ReleaseCard } from '../../components/ReleaseNotes';
 import v01Data from '../../data/releases/v0.1.json';
 import v02Data from '../../data/releases/v0.2.json';
 import v03Data from '../../data/releases/v0.3.json';
+import v04Data from '../../data/releases/v0.4.json';
 import indexData from '../../data/releases/index.json';
 import styles from '../../components/ReleaseNotes/ReleaseNotes.module.css';
 
 export const allReleases = [
+  ...v04Data.releases,
   ...v03Data.releases,
   ...v02Data.releases,
   ...v01Data.releases
@@ -33,15 +35,27 @@ export const getMarkerStyle = (type) => {
 Stay up-to-date with the latest improvements, features, and fixes in Envoy AI Gateway.
 
 <div className={styles.releaseNotesGrid}>
+  <ReleaseCard
+    version="v0.4.x"
+    date="October 30, 2025 - Current"
+    summary={v04Data.series.subtitle}
+    tags={v04Data.releases[0].tags.slice(0, 10)}
+    linkTo="/release-notes/v0.4"
+    linkText="View Release Notes →"
+    badge={v04Data.series.badge}
+    featured={true}
+    versions={v04Data.releases.map(release => release.version).join(', ')}
+  />
+
   <ReleaseCard
     version="v0.3.x"
-    date="August 21, 2025 - Current"
+    date="August 21, 2025 - October 30, 2025"
     summary={v03Data.series.subtitle}
     tags={v03Data.releases[0].tags.slice(0, 10)}
     linkTo="/release-notes/v0.3"
     linkText="View Release Notes →"
     badge={v03Data.series.badge}
-    featured={true}
+    featured={false}
     versions={v03Data.releases.map(release => release.version).join(', ')}
   />