feat: end-to-end OpenAI Image Generation support (#1280)

**Description**
This PR adds complete support for OpenAI’s image generation endpoint
(/v1/images/generations) across the Envoy AI Gateway. It introduces a
processor, translation layer, tracing and metrics instrumentation,
Brotli decoding, example client/service updates, and repo hygiene
improvements.

---------

Signed-off-by: Hrushikesh Patil <[email protected]>

Author: nutanix-Hrushikesh

.gitignore

@@ -49,3 +49,4 @@ inference-extension-conformance-test-report.yaml
 .mcp.json
 
 .goose
+/aigw

cmd/extproc/mainlib/main.go

@@ -234,6 +234,7 @@ func Main(ctx context.Context, args []string, stderr io.Writer) (err error) {
 	messagesMetrics := metrics.NewMessagesFactory(meter, metricsRequestHeaderAttributes)
 	completionMetrics := metrics.NewCompletionFactory(meter, metricsRequestHeaderAttributes)
 	embeddingsMetrics := metrics.NewEmbeddingsFactory(meter, metricsRequestHeaderAttributes)
+	imageGenerationMetrics := metrics.NewImageGenerationFactory(meter, metricsRequestHeaderAttributes)()
 	mcpMetrics := metrics.NewMCP(meter, metricsRequestHeaderAttributes)
 
 	tracing, err := tracing.NewTracingFromEnv(ctx, os.Stdout, spanRequestHeaderAttributes)
@@ -248,6 +249,7 @@ func Main(ctx context.Context, args []string, stderr io.Writer) (err error) {
 	server.Register(path.Join(flags.rootPrefix, "/v1/chat/completions"), extproc.ChatCompletionProcessorFactory(chatCompletionMetrics))
 	server.Register(path.Join(flags.rootPrefix, "/v1/completions"), extproc.CompletionsProcessorFactory(completionMetrics))
 	server.Register(path.Join(flags.rootPrefix, "/v1/embeddings"), extproc.EmbeddingsProcessorFactory(embeddingsMetrics))
+	server.Register(path.Join(flags.rootPrefix, "/v1/images/generations"), extproc.ImageGenerationProcessorFactory(imageGenerationMetrics))
 	server.Register(path.Join(flags.rootPrefix, "/v1/models"), extproc.NewModelsProcessor)
 	server.Register(path.Join(flags.rootPrefix, "/anthropic/v1/messages"), extproc.MessagesProcessorFactory(messagesMetrics))
 

go.mod

@@ -8,6 +8,7 @@ require (
 	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.0
 	github.com/a8m/envsubst v1.4.3
 	github.com/alecthomas/kong v1.12.1
+	github.com/andybalholm/brotli v1.2.0
 	github.com/anthropics/anthropic-sdk-go v1.14.0
 	github.com/aws/aws-sdk-go-v2 v1.39.3
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.2

go.sum

@@ -41,6 +41,8 @@ github.com/alecthomas/kong v1.12.1 h1:iq6aMJDcFYP9uFrLdsiZQ2ZMmcshduyGv4Pek0MQPW
 github.com/alecthomas/kong v1.12.1/go.mod h1:p2vqieVMeTAnaC83txKtXe8FLke2X07aruPWXyMPQrU=
 github.com/alecthomas/repr v0.4.0 h1:GhI2A8MACjfegCPVq9f1FLvIBS+DrQ2KQBFZP1iFzXc=
 github.com/alecthomas/repr v0.4.0/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
+github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
+github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
 github.com/anthropics/anthropic-sdk-go v1.14.0 h1:EzNQvnZlaDHe2UPkoUySDz3ixRgNbwKdH8KtFpv7pi4=
 github.com/anthropics/anthropic-sdk-go v1.14.0/go.mod h1:WTz31rIUHUHqai2UslPpw5CwXrQP3geYBioRV4WOLvE=
 github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYWrPrQ=
@@ -448,6 +450,8 @@ github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
 github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
 github.com/xiang90/probing v0.0.0-20221125231312-a49e3df8f510 h1:S2dVYn90KE98chqDkyE9Z4N61UnQd+KOfgp5Iu53llk=
 github.com/xiang90/probing v0.0.0-20221125231312-a49e3df8f510/go.mod h1:UETIi67q53MR2AWcXfiuqkDkRtnGDLqkBTpCHuJHxtU=
+github.com/xyproto/randomstring v1.0.5 h1:YtlWPoRdgMu3NZtP45drfy1GKoojuR7hmRcnhZqKjWU=
+github.com/xyproto/randomstring v1.0.5/go.mod h1:rgmS5DeNXLivK7YprL0pY+lTuhNQW3iGxZ18UQApw/E=
 github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
 github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=

internal/apischema/openai/openai.go

@@ -57,6 +57,10 @@ const (
 
 	// ModelTextEmbedding3Small is the cheapest model usable with /embeddings.
 	ModelTextEmbedding3Small = "text-embedding-3-small"
+
+	// ModelGPTImage1Mini is the smallest/cheapest Images model usable with
+	// /v1/images/generations. Use with size "1024x1024" and quality "low".
+	ModelGPTImage1Mini = "gpt-image-1-mini"
 )
 
 // ChatCompletionContentPartRefusalType The type of the content part.