Merge branch 'main' into alexagriffith/add-agent-e2e-test

Signed-off-by: Alexa Griffith  <agriffith96@gmail.com>

Makefile

@@ -89,13 +89,12 @@ apigen: controller-gen
 .PHONY: apidoc
 apidoc: crd-ref-docs
 	@$(CRD_REF_DOCS) \
-    	--source-path=api/v1alpha1 \
-    	--config=site/crd-ref-docs/config.yaml \
-    	--templates-dir=site/crd-ref-docs/templates \
-    	--output-path=API.md \
-    	--max-depth 20 \
-    	--output-path site/docs/api.md \
-    	--renderer=markdown
+		--source-path=api/v1alpha1 \
+		--config=site/crd-ref-docs/config-core.yaml \
+		--templates-dir=site/crd-ref-docs/templates \
+		--max-depth 20 \
+		--output-path site/docs/api/api.mdx \
+		--renderer=markdown
 
 # This runs all necessary steps to prepare for a commit.
 .PHONY: precommit

Makefile.tools.mk

@@ -16,15 +16,25 @@ CRD_REF_DOCS = $(LOCALBIN)/crd-ref-docs
 GO_TEST_COVERAGE ?= $(LOCALBIN)/go-test-coverage
 
 ## Tool versions.
-CONTROLLER_TOOLS_VERSION ?= v0.17.1 # https://github.com/kubernetes-sigs/controller-tools/releases
-ENVTEST_VERSION ?= release-0.20 # https://github.com/kubernetes-sigs/controller-runtime/releases Note: this needs to point to a release branch.
-GOLANGCI_LINT_VERSION ?= v1.63.4 # https://github.com/golangci/golangci-lint/releases
-GO_FUMPT_VERSION ?= v0.7.0 # https://github.com/mvdan/gofumpt/releases
-GCI_VERSION ?= v0.13.5 # https://github.com/daixiang0/gci/releases
-EDITORCONFIG_CHECKER_VERSION ?= v3.2.0 # https://github.com/editorconfig-checker/editorconfig-checker/releases
-KIND_VERSION ?= v0.26.0 # https://github.com/kubernetes-sigs/kind/releases
-CRD_REF_DOCS_VERSION ?= v0.1.0 # https://github.com/elastic/crd-ref-docs/releases
-GO_TEST_COVERAGE_VERSION ?= v2.11.4 # https://github.com/vladopajic/go-test-coverage/releases
+# Note: Ensure no blank after version and no comments, or the version value would have a blank as suffix.
+# https://github.com/kubernetes-sigs/controller-tools/releases
+CONTROLLER_TOOLS_VERSION ?= v0.17.1
+# https://github.com/kubernetes-sigs/controller-runtime/releases Note: this needs to point to a release branch.
+ENVTEST_VERSION ?= release-0.20
+# https://github.com/golangci/golangci-lint/releases
+GOLANGCI_LINT_VERSION ?= v1.63.4
+# https://github.com/mvdan/gofumpt/releases
+GO_FUMPT_VERSION ?= v0.7.0
+# https://github.com/daixiang0/gci/releases
+GCI_VERSION ?= v0.13.5
+# https://github.com/editorconfig-checker/editorconfig-checker/releases
+EDITORCONFIG_CHECKER_VERSION ?= v3.2.0
+# https://github.com/kubernetes-sigs/kind/releases
+KIND_VERSION ?= v0.26.0
+# https://github.com/elastic/crd-ref-docs/releases
+CRD_REF_DOCS_VERSION ?= v0.1.0
+# https://github.com/vladopajic/go-test-coverage/releases
+GO_TEST_COVERAGE_VERSION ?= v2.11.4
 
 .PHONY: golangci-lint
 golangci-lint: $(GOLANGCI_LINT)

api/v1alpha1/api.go

@@ -99,20 +99,21 @@ type AIGatewayRouteSpec struct {
 	// metadata per HTTP request. The namespaced key is "io.envoy.ai_gateway",
 	//
 	// For example, let's say we have the following LLMRequestCosts configuration:
-	//
+	// ```yaml
 	//	llmRequestCosts:
 	//	- metadataKey: llm_input_token
 	//	  type: InputToken
 	//	- metadataKey: llm_output_token
 	//	  type: OutputToken
 	//	- metadataKey: llm_total_token
 	//	  type: TotalToken
-	//
+	// ```
 	// Then, with the following BackendTrafficPolicy of Envoy Gateway, you can have three
 	// rate limit buckets for each unique x-user-id header value. One bucket is for the input token,
 	// the other is for the output token, and the last one is for the total token.
 	// Each bucket will be reduced by the corresponding token usage captured by the AI Gateway filter.
 	//
+	// ```yaml
 	//	apiVersion: gateway.envoyproxy.io/v1alpha1
 	//	kind: BackendTrafficPolicy
 	//	metadata:
@@ -182,7 +183,7 @@ type AIGatewayRouteSpec struct {
 	//	              metadata:
 	//	                namespace: io.envoy.ai_gateway
 	//	                key: llm_total_token
-	//
+	// ```
 	// +optional
 	// +kubebuilder:validation:MaxItems=36
 	LLMRequestCosts []LLMRequestCost `json:"llmRequestCosts,omitempty"`

go.mod

@@ -1,23 +1,23 @@
 module github.com/envoyproxy/ai-gateway
 
-go 1.23.5
+go 1.23.6
 
 require (
-	github.com/aws/aws-sdk-go-v2 v1.36.0
+	github.com/aws/aws-sdk-go-v2 v1.36.1
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.8
-	github.com/aws/aws-sdk-go-v2/config v1.29.4
+	github.com/aws/aws-sdk-go-v2/config v1.29.6
 	github.com/envoyproxy/gateway v1.3.0
 	github.com/envoyproxy/go-control-plane/envoy v1.32.4
 	github.com/go-logr/logr v1.4.2
 	github.com/google/cel-go v0.23.2
 	github.com/google/go-cmp v0.6.0
-	github.com/openai/openai-go v0.1.0-alpha.51
+	github.com/openai/openai-go v0.1.0-alpha.56
 	github.com/stretchr/testify v1.10.0
 	go.uber.org/goleak v1.3.0
 	go.uber.org/zap v1.27.0
-	golang.org/x/exp v0.0.0-20250128182459-e0ece0dbea4c
+	golang.org/x/exp v0.0.0-20250207012021-f9890c6ad9f3
 	google.golang.org/grpc v1.70.0
-	google.golang.org/protobuf v1.36.4
+	google.golang.org/protobuf v1.36.5
 	k8s.io/api v0.32.1
 	k8s.io/apiextensions-apiserver v0.32.1
 	k8s.io/apimachinery v0.32.1
@@ -32,16 +32,16 @@ require (
 require (
 	cel.dev/expr v0.19.2 // indirect
 	github.com/antlr4-go/antlr/v4 v4.13.1 // indirect
-	github.com/aws/aws-sdk-go-v2/credentials v1.17.57 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.27 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.31 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.31 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.17.59 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.28 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.32 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.32 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.2 // indirect
 	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.2 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.12 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.24.14 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.13 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sts v1.33.12 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.24.15 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.14 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.33.14 // indirect
 	github.com/aws/smithy-go v1.22.2 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect

go.sum

@@ -2,32 +2,32 @@ cel.dev/expr v0.19.2 h1:V354PbqIXr9IQdwy4SYA4xa0HXaWq1BUPAGzugBY5V4=
 cel.dev/expr v0.19.2/go.mod h1:MrpN08Q+lEBs+bGYdLxxHkZoUSsCp0nSKTs0nTymJgw=
 github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYWrPrQ=
 github.com/antlr4-go/antlr/v4 v4.13.1/go.mod h1:GKmUxMtwp6ZgGwZSva4eWPC5mS6vUAmOABFgjdkM7Nw=
-github.com/aws/aws-sdk-go-v2 v1.36.0 h1:b1wM5CcE65Ujwn565qcwgtOTT1aT4ADOHHgglKjG7fk=
-github.com/aws/aws-sdk-go-v2 v1.36.0/go.mod h1:5PMILGVKiW32oDzjj6RU52yrNrDPUHcbZQYr1sM7qmM=
+github.com/aws/aws-sdk-go-v2 v1.36.1 h1:iTDl5U6oAhkNPba0e1t1hrwAo02ZMqbrGq4k5JBWM5E=
+github.com/aws/aws-sdk-go-v2 v1.36.1/go.mod h1:5PMILGVKiW32oDzjj6RU52yrNrDPUHcbZQYr1sM7qmM=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.8 h1:zAxi9p3wsZMIaVCdoiQp2uZ9k1LsZvmAnoTBeZPXom0=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.8/go.mod h1:3XkePX5dSaxveLAYY7nsbsZZrKxCyEuE5pM4ziFxyGg=
-github.com/aws/aws-sdk-go-v2/config v1.29.4 h1:ObNqKsDYFGr2WxnoXKOhCvTlf3HhwtoGgc+KmZ4H5yg=
-github.com/aws/aws-sdk-go-v2/config v1.29.4/go.mod h1:j2/AF7j/qxVmsNIChw1tWfsVKOayJoGRDjg1Tgq7NPk=
-github.com/aws/aws-sdk-go-v2/credentials v1.17.57 h1:kFQDsbdBAR3GZsB8xA+51ptEnq9TIj3tS4MuP5b+TcQ=
-github.com/aws/aws-sdk-go-v2/credentials v1.17.57/go.mod h1:2kerxPUUbTagAr/kkaHiqvj/bcYHzi2qiJS/ZinllU0=
-github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.27 h1:7lOW8NUwE9UZekS1DYoiPdVAqZ6A+LheHWb+mHbNOq8=
-github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.27/go.mod h1:w1BASFIPOPUae7AgaH4SbjNbfdkxuggLyGfNFTn8ITY=
-github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.31 h1:lWm9ucLSRFiI4dQQafLrEOmEDGry3Swrz0BIRdiHJqQ=
-github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.31/go.mod h1:Huu6GG0YTfbPphQkDSo4dEGmQRTKb9k9G7RdtyQWxuI=
-github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.31 h1:ACxDklUKKXb48+eg5ROZXi1vDgfMyfIA/WyvqHcHI0o=
-github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.31/go.mod h1:yadnfsDwqXeVaohbGc/RaD287PuyRw2wugkh5ZL2J6k=
+github.com/aws/aws-sdk-go-v2/config v1.29.6 h1:fqgqEKK5HaZVWLQoLiC9Q+xDlSp+1LYidp6ybGE2OGg=
+github.com/aws/aws-sdk-go-v2/config v1.29.6/go.mod h1:Ft+WLODzDQmCTHDvqAH1JfC2xxbZ0MxpZAcJqmE1LTQ=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.59 h1:9btwmrt//Q6JcSdgJOLI98sdr5p7tssS9yAsGe8aKP4=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.59/go.mod h1:NM8fM6ovI3zak23UISdWidyZuI1ghNe2xjzUZAyT+08=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.28 h1:KwsodFKVQTlI5EyhRSugALzsV6mG/SGrdjlMXSZSdso=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.28/go.mod h1:EY3APf9MzygVhKuPXAc5H+MkGb8k/DOSQjWS0LgkKqI=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.32 h1:BjUcr3X3K0wZPGFg2bxOWW3VPN8rkE3/61zhP+IHviA=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.32/go.mod h1:80+OGC/bgzzFFTUmcuwD0lb4YutwQeKLFpmt6hoWapU=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.32 h1:m1GeXHVMJsRsUAqG6HjZWx9dj7F5TR+cF1bjyfYyBd4=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.32/go.mod h1:IitoQxGfaKdVLNg0hD8/DXmAqNy0H4K2H2Sf91ti8sI=
 github.com/aws/aws-sdk-go-v2/internal/ini v1.8.2 h1:Pg9URiobXy85kgFev3og2CuOZ8JZUBENF+dcgWBaYNk=
 github.com/aws/aws-sdk-go-v2/internal/ini v1.8.2/go.mod h1:FbtygfRFze9usAadmnGJNc8KsP346kEe+y2/oyhGAGc=
 github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.2 h1:D4oz8/CzT9bAEYtVhSBmFj2dNOtaHOtMKc2vHBwYizA=
 github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.2/go.mod h1:Za3IHqTQ+yNcRHxu1OFucBh0ACZT4j4VQFF0BqpZcLY=
-github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.12 h1:O+8vD2rGjfihBewr5bT+QUfYUHIxCVgG61LHoT59shM=
-github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.12/go.mod h1:usVdWJaosa66NMvmCrr08NcWDBRv4E6+YFG2pUdw1Lk=
-github.com/aws/aws-sdk-go-v2/service/sso v1.24.14 h1:c5WJ3iHz7rLIgArznb3JCSQT3uUMiz9DLZhIX+1G8ok=
-github.com/aws/aws-sdk-go-v2/service/sso v1.24.14/go.mod h1:+JJQTxB6N4niArC14YNtxcQtwEqzS3o9Z32n7q33Rfs=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.13 h1:f1L/JtUkVODD+k1+IiSJUUv8A++2qVr+Xvb3xWXETMU=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.13/go.mod h1:tvqlFoja8/s0o+UruA1Nrezo/df0PzdunMDDurUfg6U=
-github.com/aws/aws-sdk-go-v2/service/sts v1.33.12 h1:fqg6c1KVrc3SYWma/egWue5rKI4G2+M4wMQN2JosNAA=
-github.com/aws/aws-sdk-go-v2/service/sts v1.33.12/go.mod h1:7Yn+p66q/jt38qMoVfNvjbm3D89mGBnkwDcijgtih8w=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.13 h1:SYVGSFQHlchIcy6e7x12bsrxClCXSP5et8cqVhL8cuw=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.13/go.mod h1:kizuDaLX37bG5WZaoxGPQR/LNFXpxp0vsUnqfkWXfNE=
+github.com/aws/aws-sdk-go-v2/service/sso v1.24.15 h1:/eE3DogBjYlvlbhd2ssWyeuovWunHLxfgw3s/OJa4GQ=
+github.com/aws/aws-sdk-go-v2/service/sso v1.24.15/go.mod h1:2PCJYpi7EKeA5SkStAmZlF6fi0uUABuhtF8ILHjGc3Y=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.14 h1:M/zwXiL2iXUrHputuXgmO94TVNmcenPHxgLXLutodKE=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.14/go.mod h1:RVwIw3y/IqxC2YEXSIkAzRDdEU1iRabDPaYjpGCbCGQ=
+github.com/aws/aws-sdk-go-v2/service/sts v1.33.14 h1:TzeR06UCMUq+KA3bDkujxK1GVGy+G8qQN/QVYzGLkQE=
+github.com/aws/aws-sdk-go-v2/service/sts v1.33.14/go.mod h1:dspXf/oYWGWo6DEvj98wpaTeqt5+DMidZD0A9BYTizc=
 github.com/aws/smithy-go v1.22.2 h1:6D9hW43xKFrRx/tXXfAlIZc4JI+yQe6snnWcQyxSyLQ=
 github.com/aws/smithy-go v1.22.2/go.mod h1:irrKGvNn1InZwb2d7fkIRNucdfwR8R+Ts3wxYa/cJHg=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
@@ -117,8 +117,8 @@ github.com/onsi/ginkgo/v2 v2.21.0 h1:7rg/4f3rB88pb5obDgNZrNHrQ4e6WpjonchcpuBRnZM
 github.com/onsi/ginkgo/v2 v2.21.0/go.mod h1:7Du3c42kxCUegi0IImZ1wUQzMBVecgIHjR1C+NkhLQo=
 github.com/onsi/gomega v1.35.1 h1:Cwbd75ZBPxFSuZ6T+rN/WCb/gOc6YgFBXLlZLhC7Ds4=
 github.com/onsi/gomega v1.35.1/go.mod h1:PvZbdDc8J6XJEpDK4HCuRBm8a6Fzp9/DmhC9C7yFlog=
-github.com/openai/openai-go v0.1.0-alpha.51 h1:/iuF8QoWt4x9yoEr6AdMsSBc2SglamxA/a7wClrDrqw=
-github.com/openai/openai-go v0.1.0-alpha.51/go.mod h1:3SdE6BffOX9HPEQv8IL/fi3LYZ5TUpRYaqGQZbyk11A=
+github.com/openai/openai-go v0.1.0-alpha.56 h1:wKKsyVUi6ppZ8WRL+PC+tOB67alvJjfEWkC3Lc9YnqU=
+github.com/openai/openai-go v0.1.0-alpha.56/go.mod h1:3SdE6BffOX9HPEQv8IL/fi3LYZ5TUpRYaqGQZbyk11A=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgmp0tecUJ0sJuv4pzYCqS9+RGSn52M3FUwPs+uo=
@@ -184,8 +184,8 @@ go.uber.org/zap v1.27.0/go.mod h1:GB2qFLM7cTU87MWRP2mPIjqfIDnGu+VIO4V/SdhGo2E=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/exp v0.0.0-20250128182459-e0ece0dbea4c h1:KL/ZBHXgKGVmuZBZ01Lt57yE5ws8ZPSkkihmEyq7FXc=
-golang.org/x/exp v0.0.0-20250128182459-e0ece0dbea4c/go.mod h1:tujkw807nyEEAamNbDrEGzRav+ilXA7PCRAd6xsmwiU=
+golang.org/x/exp v0.0.0-20250207012021-f9890c6ad9f3 h1:qNgPs5exUA+G0C96DrPwNrvLSj7GT/9D+3WMWUcUg34=
+golang.org/x/exp v0.0.0-20250207012021-f9890c6ad9f3/go.mod h1:tujkw807nyEEAamNbDrEGzRav+ilXA7PCRAd6xsmwiU=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
@@ -232,8 +232,8 @@ google.golang.org/genproto/googleapis/rpc v0.0.0-20250127172529-29210b9bc287 h1:
 google.golang.org/genproto/googleapis/rpc v0.0.0-20250127172529-29210b9bc287/go.mod h1:8BS3B93F/U1juMFq9+EDk+qOT5CO1R9IzXxG3PTqiRk=
 google.golang.org/grpc v1.70.0 h1:pWFv03aZoHzlRKHWicjsZytKAiYCtNS0dHbXnIdq7jQ=
 google.golang.org/grpc v1.70.0/go.mod h1:ofIJqVKDXx/JiXrwr2IG4/zwdH9txy3IlF40RmcJSQw=
-google.golang.org/protobuf v1.36.4 h1:6A3ZDJHn/eNqc1i+IdefRzy/9PokBTPvcqMySR7NNIM=
-google.golang.org/protobuf v1.36.4/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+google.golang.org/protobuf v1.36.5 h1:tPhr+woSbjfYvY6/GPufUoYizxw1cF/yFoxJ2fmpwlM=
+google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=

internal/extproc/backendauth/aws_test.go

@@ -3,6 +3,7 @@ package backendauth
 import (
 	"context"
 	"os"
+	"sync"
 	"testing"
 
 	corev3 "github.com/envoyproxy/go-control-plane/envoy/config/core/v3"
@@ -40,17 +41,14 @@ func TestAWSHandler_Do(t *testing.T) {
 		CredentialFileName: awsCredentialFile,
 		Region:             "us-east-1",
 	})
+	require.NoError(t, err)
 
-	for _, tc := range []struct {
-		name    string
-		handler Handler
-	}{
-		{
-			name:    "Using AWS Credential File",
-			handler: credentialFileHandler,
-		},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
+	// Handler.Do is called concurrently, so we test it with 100 goroutines to ensure it is thread-safe.
+	var wg sync.WaitGroup
+	wg.Add(100)
+	for range 100 {
+		go func() {
+			defer wg.Done()
 			requestHeaders := map[string]string{":method": "POST"}
 			headerMut := &extprocv3.HeaderMutation{
 				SetHeaders: []*corev3.HeaderValueOption{
@@ -65,8 +63,18 @@ func TestAWSHandler_Do(t *testing.T) {
 					Body: []byte(`{"messages": [{"role": "user", "content": [{"text": "Say this is a test!"}]}]}`),
 				},
 			}
-			err = tc.handler.Do(context.Background(), requestHeaders, headerMut, bodyMut)
+			err := credentialFileHandler.Do(context.Background(), requestHeaders, headerMut, bodyMut)
 			require.NoError(t, err)
-		})
+
+			// Ensures that the headers are set.
+			headers := map[string]string{}
+			for _, h := range headerMut.SetHeaders {
+				headers[h.Header.Key] = h.Header.Value
+			}
+			require.Contains(t, headers, "X-Amz-Date")
+			require.Contains(t, headers, "Authorization")
+		}()
 	}
+
+	wg.Wait()
 }

internal/extproc/translator/openai_awsbedrock.go

@@ -21,7 +21,7 @@ import (
 	"github.com/envoyproxy/ai-gateway/internal/extproc/router"
 )
 
-// newOpenAIToAWSBedrockTranslator implements [TranslatorFactory] for OpenAI to AWS Bedrock translation.
+// newOpenAIToAWSBedrockTranslator implements [Factory] for OpenAI to AWS Bedrock translation.
 func newOpenAIToAWSBedrockTranslator(path string) (Translator, error) {
 	if path == "/v1/chat/completions" {
 		return &openAIToAWSBedrockTranslatorV1ChatCompletion{}, nil
@@ -52,6 +52,8 @@ func (o *openAIToAWSBedrockTranslatorV1ChatCompletion) RequestBody(body router.R
 	if openAIReq.Stream {
 		o.stream = true
 		// We need to change the processing mode for streaming requests.
+		// TODO: We can delete this explicit setting of ResponseHeaderMode below as it is the default value we use
+		// 	after https://github.com/envoyproxy/envoy/pull/38254 this is released.
 		override = &extprocv3http.ProcessingMode{
 			ResponseHeaderMode: extprocv3http.ProcessingMode_SEND,
 			ResponseBodyMode:   extprocv3http.ProcessingMode_STREAMED,

internal/extproc/translator/openai_openai.go

@@ -14,7 +14,7 @@ import (
 	"github.com/envoyproxy/ai-gateway/internal/extproc/router"
 )
 
-// newOpenAIToOpenAITranslator implements [TranslatorFactory] for OpenAI to OpenAI translation.
+// newOpenAIToOpenAITranslator implements [Factory] for OpenAI to OpenAI translation.
 func newOpenAIToOpenAITranslator(path string) (Translator, error) {
 	if path == "/v1/chat/completions" {
 		return &openAIToOpenAITranslatorV1ChatCompletion{}, nil
@@ -29,7 +29,7 @@ type openAIToOpenAITranslatorV1ChatCompletion struct {
 	bufferingDone bool
 }
 
-// RequestBody implements [RequestBody].
+// RequestBody implements [Translator.RequestBody].
 func (o *openAIToOpenAITranslatorV1ChatCompletion) RequestBody(body router.RequestBody) (
 	headerMutation *extprocv3.HeaderMutation, bodyMutation *extprocv3.BodyMutation, override *extprocv3http.ProcessingMode, err error,
 ) {
@@ -40,6 +40,8 @@ func (o *openAIToOpenAITranslatorV1ChatCompletion) RequestBody(body router.Reque
 	if req.Stream {
 		o.stream = true
 		override = &extprocv3http.ProcessingMode{
+			// TODO: We can delete this explicit setting of ResponseHeaderMode below as it is the default value we use
+			// 	after https://github.com/envoyproxy/envoy/pull/38254 this is released.
 			ResponseHeaderMode: extprocv3http.ProcessingMode_SEND,
 			ResponseBodyMode:   extprocv3http.ProcessingMode_STREAMED,
 		}