chore(main): release 0.4.2 (#1400 )

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
feat: old sonnet (#1408 )
2026-03-19 11:33:08 +00:00 · 2025-03-28 14:17:21 +00:00 · 2025-03-28 13:51:47 +00:00 · 2025-03-25 07:26:43 +00:00 · 2025-03-21 10:42:48 +00:00 · 2025-03-19 21:05:53 +00:00
21 changed files with 805 additions and 55 deletions
--- a/.github/workflows/build_container.yaml
+++ b/.github/workflows/build_container.yaml
@@ -96,7 +96,7 @@ jobs:
          outputs: type=docker,dest=/tmp/${{ env.IMAGE_NAME }}-image.tar

      - name: Upload image as artifact
-        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
        with:
          name: ${{ env.IMAGE_NAME }}-image.tar
          path: /tmp/${{ env.IMAGE_NAME }}-image.tar
@@ -118,7 +118,7 @@ jobs:
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4

      - name: Login to GitHub Container Registry
-        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567 # v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3
        with:
          registry: "ghcr.io"
          username: ${{ github.actor }}
--- a/.github/workflows/release.yaml
+++ b/.github/workflows/release.yaml
@@ -59,13 +59,13 @@ jobs:
        with:
          fetch-depth: 0
      - name: Set up Go
-        uses: actions/setup-go@3041bf56c941b39c61721a86cd11f3bb1338122a # v5
+        uses: actions/setup-go@0aaccfd150d50ccaeb58ebd88d36e91967a5f35b # v5
        with:
          go-version: '1.22'
      - name: Download Syft
        uses: anchore/sbom-action/download-syft@55dc4ee22412511ee8c3142cbea40418e6cec693 # v0.17.8
      - name: Run GoReleaser
-        uses: goreleaser/goreleaser-action@286f3b13b1b49da4ac219696163fb8c1c93e1200 # v6
+        uses: goreleaser/goreleaser-action@90a3faa9d0182683851fbfa97ca1a2cb983bfca3 # v6
        with:
          # either 'goreleaser' (default) or 'goreleaser-pro'
          distribution: goreleaser
@@ -99,7 +99,7 @@ jobs:
        uses: docker/setup-buildx-action@6524bf65af31da8d45b59e8c27de4bd072b392f5 # v3

      - name: Login to GitHub Container Registry
-        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567 # v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3
        with:
          registry: "ghcr.io"
          username: ${{ github.actor }}
@@ -127,7 +127,7 @@ jobs:
          output-file: ./sbom-${{ env.IMAGE_NAME }}.spdx.json

      - name: Attach SBOM to release
-        uses: softprops/action-gh-release@e7a8f85e1c67a31e6ed99a94b41bd0b71bbee6b8 # v2
+        uses: softprops/action-gh-release@c95fe1489396fe8a9eb87c0abf8aa5b2ef267fda # v2
        with:
          tag_name: ${{ needs.release-please.outputs.tag_name }}
          files: ./sbom-${{ env.IMAGE_NAME }}.spdx.json
--- a/.github/workflows/test.yaml
+++ b/.github/workflows/test.yaml
@@ -18,7 +18,7 @@ jobs:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4

      - name: Set up Go
-        uses: actions/setup-go@3041bf56c941b39c61721a86cd11f3bb1338122a # v5
+        uses: actions/setup-go@0aaccfd150d50ccaeb58ebd88d36e91967a5f35b # v5
        with:
          go-version: ${{ env.GO_VERSION }}

--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1 +1 @@
-{".":"0.4.0"}
+{".":"0.4.2"}
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,46 @@
 # Changelog

+## [0.4.2](https://github.com/k8sgpt-ai/k8sgpt/compare/v0.4.1...v0.4.2) (2025-03-28)
+
+
+### Features
+
+* old sonnet ([#1408](https://github.com/k8sgpt-ai/k8sgpt/issues/1408)) ([e5817f9](https://github.com/k8sgpt-ai/k8sgpt/commit/e5817f9e557f4f97b016a0a7b7674342c3a1773e))
+
+
+### Bug Fixes
+
+* **deps:** update k8s.io/utils digest to 1f6e0b7 ([#1405](https://github.com/k8sgpt-ai/k8sgpt/issues/1405)) ([f5eaf81](https://github.com/k8sgpt-ai/k8sgpt/commit/f5eaf817f0cf2b732013e67e94c758a225c35ba6))
+
+
+### Other
+
+* **deps:** update actions/setup-go digest to 0aaccfd ([#1401](https://github.com/k8sgpt-ai/k8sgpt/issues/1401)) ([81d4aaf](https://github.com/k8sgpt-ai/k8sgpt/commit/81d4aaf402647bf4bcbc618fd82f9518cf3a5b4d))
+* **deps:** update actions/upload-artifact digest to ea165f8 ([#1402](https://github.com/k8sgpt-ai/k8sgpt/issues/1402)) ([eb381b8](https://github.com/k8sgpt-ai/k8sgpt/commit/eb381b8087bbb3216d9bcdcc88a71fbad9e31e41))
+* **deps:** update docker/login-action digest to 74a5d14 ([#1397](https://github.com/k8sgpt-ai/k8sgpt/issues/1397)) ([fdf8e7a](https://github.com/k8sgpt-ai/k8sgpt/commit/fdf8e7a95a6667b782e1e347a3b1d2fb0f2aafde))
+* fix error ([#1403](https://github.com/k8sgpt-ai/k8sgpt/issues/1403)) ([288ca86](https://github.com/k8sgpt-ai/k8sgpt/commit/288ca862b3aaf942e58aa0dad0e15e2fda84780f))
+
+## [0.4.1](https://github.com/k8sgpt-ai/k8sgpt/compare/v0.4.0...v0.4.1) (2025-03-17)
+
+
+### Features
+
+* add amazon bedrock nova pro and nova lite models ([#1383](https://github.com/k8sgpt-ai/k8sgpt/issues/1383)) ([aa1e237](https://github.com/k8sgpt-ai/k8sgpt/commit/aa1e237ebb8c816383561c9b3e6a1ca0ddea8f78))
+* add custom restful backend for complex scenarios (e.g, rag) ([#1228](https://github.com/k8sgpt-ai/k8sgpt/issues/1228)) ([7540e00](https://github.com/k8sgpt-ai/k8sgpt/commit/7540e0084e0c0c44fc52ed9a906b76f9f2e6a981))
+
+
+### Bug Fixes
+
+* **deps:** update default model to gpt-4o for improved performance and cost efficiency ([#1332](https://github.com/k8sgpt-ai/k8sgpt/issues/1332)) ([4e39cb6](https://github.com/k8sgpt-ai/k8sgpt/commit/4e39cb65b3a7fc0d1c057c647794346e072d3fd0))
+* **deps:** update module golang.org/x/net to v0.36.0 [security] ([#1395](https://github.com/k8sgpt-ai/k8sgpt/issues/1395)) ([eb7b36a](https://github.com/k8sgpt-ai/k8sgpt/commit/eb7b36aa2764bc460ffc29a0aee18abe3631c2ed))
+
+
+### Other
+
+* **deps:** update actions/setup-go digest to f111f33 ([#1364](https://github.com/k8sgpt-ai/k8sgpt/issues/1364)) ([f2fdfd8](https://github.com/k8sgpt-ai/k8sgpt/commit/f2fdfd8dcaae6f57378d50396c4746d738d38bf2))
+* **deps:** update goreleaser/goreleaser-action digest to 90a3faa ([#1308](https://github.com/k8sgpt-ai/k8sgpt/issues/1308)) ([d6d2e3b](https://github.com/k8sgpt-ai/k8sgpt/commit/d6d2e3bc4254877c8af61aba7386706e942e3fe9))
+* **deps:** update softprops/action-gh-release digest to c95fe14 ([#1359](https://github.com/k8sgpt-ai/k8sgpt/issues/1359)) ([db5e517](https://github.com/k8sgpt-ai/k8sgpt/commit/db5e517dbb23a4cb0f203427744f4007d6e9faa8))
+
 ## [0.4.0](https://github.com/k8sgpt-ai/k8sgpt/compare/v0.3.50...v0.4.0) (2025-03-06)


--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -2,7 +2,7 @@
 We're happy that you want to contribute to this project. Please read the sections to make the process as smooth as possible.

 ## Requirements
- Golang `1.20`
+- Golang `1.23`
 - An OpenAI API key
  * OpenAI API keys can be obtained from [OpenAI](https://platform.openai.com/account/api-keys)
  * You can set the API key for k8sgpt using `./k8sgpt auth key`
--- a/README.md
+++ b/README.md
@@ -49,7 +49,7 @@ brew install k8sgpt
  <!---x-release-please-start-version-->

  ```
-  sudo rpm -ivh https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.0/k8sgpt_386.rpm
+  sudo rpm -ivh https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.2/k8sgpt_386.rpm
  ```
  <!---x-release-please-end-->

@@ -57,7 +57,7 @@ brew install k8sgpt

  <!---x-release-please-start-version-->
  ```
-  sudo rpm -ivh https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.0/k8sgpt_amd64.rpm
+  sudo rpm -ivh https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.2/k8sgpt_amd64.rpm
  ```
  <!---x-release-please-end-->
 </details>
@@ -70,7 +70,7 @@ brew install k8sgpt
  <!---x-release-please-start-version-->

 ```
-curl -LO https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.0/k8sgpt_386.deb
+curl -LO https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.2/k8sgpt_386.deb
 sudo dpkg -i k8sgpt_386.deb
 ```

@@ -81,7 +81,7 @@ sudo dpkg -i k8sgpt_386.deb
  <!---x-release-please-start-version-->

 ```
-curl -LO https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.0/k8sgpt_amd64.deb
+curl -LO https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.2/k8sgpt_amd64.deb
 sudo dpkg -i k8sgpt_amd64.deb
 ```

@@ -96,7 +96,7 @@ sudo dpkg -i k8sgpt_amd64.deb

  <!---x-release-please-start-version-->
  ```
-  wget https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.0/k8sgpt_386.apk
+  wget https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.2/k8sgpt_386.apk
  apk add --allow-untrusted k8sgpt_386.apk
  ```
  <!---x-release-please-end-->
@@ -105,7 +105,7 @@ sudo dpkg -i k8sgpt_amd64.deb

  <!---x-release-please-start-version-->
  ```
-  wget https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.0/k8sgpt_amd64.apk
+  wget https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.4.2/k8sgpt_amd64.apk
  apk add --allow-untrusted k8sgpt_amd64.apk
  ```
  <!---x-release-please-end-->
@@ -366,6 +366,8 @@ Unused:
 > huggingface
 > noopai
 > googlevertexai
+> watsonxai
+> customrest
 > ibmwatsonxai
 ```

--- a/cmd/auth/add.go
+++ b/cmd/auth/add.go
@@ -28,7 +28,7 @@ import (

 const (
 	defaultBackend = "openai"
-	defaultModel   = "gpt-3.5-turbo"
+	defaultModel   = "gpt-4o"
 )

 var addCmd = &cobra.Command{
--- a/go.mod
+++ b/go.mod
@@ -13,7 +13,7 @@ require (
 	github.com/spf13/cobra v1.8.1
 	github.com/spf13/viper v1.19.0
 	github.com/stretchr/testify v1.10.0
-	golang.org/x/term v0.27.0
+	golang.org/x/term v0.29.0
 	helm.sh/helm/v3 v3.16.3
 	k8s.io/api v0.31.3
 	k8s.io/apimachinery v0.31.3
@@ -242,13 +242,13 @@ require (
 	go.opentelemetry.io/otel/trace v1.31.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0
-	golang.org/x/crypto v0.31.0 // indirect
+	golang.org/x/crypto v0.35.0 // indirect
 	golang.org/x/exp v0.0.0-20240823005443-9b4947da3948 // indirect
-	golang.org/x/net v0.33.0
+	golang.org/x/net v0.36.0
 	golang.org/x/oauth2 v0.24.0 // indirect
-	golang.org/x/sync v0.10.0 // indirect
-	golang.org/x/sys v0.28.0 // indirect
-	golang.org/x/text v0.21.0 // indirect
+	golang.org/x/sync v0.11.0 // indirect
+	golang.org/x/sys v0.30.0 // indirect
+	golang.org/x/text v0.22.0 // indirect
 	golang.org/x/time v0.8.0 // indirect
 	google.golang.org/grpc v1.68.1
 	google.golang.org/protobuf v1.35.2 // indirect
@@ -260,7 +260,7 @@ require (
 	k8s.io/component-base v0.31.3 // indirect
 	k8s.io/klog/v2 v2.130.1 // indirect
 	k8s.io/kube-openapi v0.0.0-20241009091222-67ed5848f094 // indirect
-	k8s.io/utils v0.0.0-20241210054802-24370beab758
+	k8s.io/utils v0.0.0-20250321185631-1f6e0b77f77e
 	oras.land/oras-go v1.2.5 // indirect
 	sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd // indirect
 	sigs.k8s.io/kustomize/api v0.18.0 // indirect
--- a/go.sum
+++ b/go.sum
@@ -1521,8 +1521,8 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
 golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20211108221036-ceb1ce70b4fa/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
-golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
+golang.org/x/crypto v0.35.0 h1:b15kiHdrGCHrP6LvwaQ3c03kgNhhiMgvlhxHQhmg2Xs=
+golang.org/x/crypto v0.35.0/go.mod h1:dy7dXNW32cAb/6/PRuTNsix8T+vJAqvuIy5Bli/x0YQ=
 golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -1642,8 +1642,8 @@ golang.org/x/net v0.5.0/go.mod h1:DivGGAXEgPSlEBzxGzZI+ZLohi+xUj054jfeKui00ws=
 golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.8.0/go.mod h1:QVkue5JL9kW//ek3r6jTKnTFis1tRmNAW2P1shuFdJc=
-golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I=
-golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
+golang.org/x/net v0.36.0 h1:vWF2fRbw4qslQsQzgFqZff+BItCvGFQqKzKIzx1rmoA=
+golang.org/x/net v0.36.0/go.mod h1:bFmbeoIPfrw4sMHNhb4J9f6+tPziuGjq7Jk/38fxi1I=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -1690,8 +1690,8 @@ golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20220819030929-7fc1605a5dde/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220929204114-8fcdb60fdcc0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
-golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.11.0 h1:GGz8+XQP4FvTTrjZPzNKTMFtSXH80RAzG+5ghFPgK9w=
+golang.org/x/sync v0.11.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -1781,8 +1781,8 @@ golang.org/x/sys v0.4.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
-golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.30.0 h1:QjkSwP/36a20jFYWkSue1YwXzLmsV5Gfq7Eiy72C1uc=
+golang.org/x/sys v0.30.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210220032956-6a3ed077a48d/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210615171337-6886f2dfbf5b/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -1791,8 +1791,8 @@ golang.org/x/term v0.2.0/go.mod h1:TVmDHMZPmdnySmBfhjOoOdhjzdE1h4u1VwSiw2l1Nuc=
 golang.org/x/term v0.4.0/go.mod h1:9P2UbLfCdcvo3p/nzKvsmas4TnlujnuoV9hGgYzW1lQ=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
 golang.org/x/term v0.6.0/go.mod h1:m6U89DPEgQRMq3DNkDClhWw02AUbt2daBVO4cn4Hv9U=
-golang.org/x/term v0.27.0 h1:WP60Sv1nlK1T6SupCHbXzSaN0b9wUmsPoRS9b61A23Q=
-golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
+golang.org/x/term v0.29.0 h1:L6pJp37ocefwRRtYPKSWOWzOtWSxVajvz2ldH/xi3iU=
+golang.org/x/term v0.29.0/go.mod h1:6bl4lRlvVuDgSf3179VpIxBF0o10JUpXWOnI7nErv7s=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -1809,8 +1809,8 @@ golang.org/x/text v0.6.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.8.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
-golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
-golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
+golang.org/x/text v0.22.0 h1:bofq7m3/HAFvbF51jz3Q9wLg3jkvSPuiZu/pD1XwgtM=
+golang.org/x/text v0.22.0/go.mod h1:YRoo4H8PVmsu+E3Ou7cqLVH8oXWIHVoX0jqUWALQhfY=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -2231,8 +2231,8 @@ k8s.io/kube-openapi v0.0.0-20241009091222-67ed5848f094 h1:MErs8YA0abvOqJ8gIupA1T
 k8s.io/kube-openapi v0.0.0-20241009091222-67ed5848f094/go.mod h1:7ioBJr1A6igWjsR2fxq2EZ0mlMwYLejazSIc2bzMp2U=
 k8s.io/kubectl v0.31.1 h1:ih4JQJHxsEggFqDJEHSOdJ69ZxZftgeZvYo7M/cpp24=
 k8s.io/kubectl v0.31.1/go.mod h1:aNuQoR43W6MLAtXQ/Bu4GDmoHlbhHKuyD49lmTC8eJM=
-k8s.io/utils v0.0.0-20241210054802-24370beab758 h1:sdbE21q2nlQtFh65saZY+rRM6x6aJJI8IUa1AmH/qa0=
-k8s.io/utils v0.0.0-20241210054802-24370beab758/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
+k8s.io/utils v0.0.0-20250321185631-1f6e0b77f77e h1:KqK5c/ghOm8xkHYhlodbp6i6+r+ChV2vuAuVRdFbLro=
+k8s.io/utils v0.0.0-20250321185631-1f6e0b77f77e/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
 knative.dev/pkg v0.0.0-20241026180704-25f6002b00f3 h1:uUSDGlOIkdPT4svjlhi+JEnP2Ufw7AM/F5QDYiEL02U=
 knative.dev/pkg v0.0.0-20241026180704-25f6002b00f3/go.mod h1:FeMbTLlxQqSASwlRCrYEOsZ0OKUgSj52qxhECwYCJsw=
 lukechampine.com/uint128 v1.1.1/go.mod h1:c4eWIwlEGaxC/+H1VguhU4PHXNWDCDMUlWdIWl2j1gk=
--- a/pkg/ai/amazonbedrock.go
+++ b/pkg/ai/amazonbedrock.go
@@ -3,9 +3,11 @@ package ai
 import (
 	"context"
 	"errors"
-	"github.com/k8sgpt-ai/k8sgpt/pkg/ai/bedrock_support"
+	"github.com/aws/aws-sdk-go/service/bedrockruntime/bedrockruntimeiface"
 	"os"

+	"github.com/k8sgpt-ai/k8sgpt/pkg/ai/bedrock_support"
+
 	"github.com/aws/aws-sdk-go/aws"
 	"github.com/aws/aws-sdk-go/aws/session"
 	"github.com/aws/aws-sdk-go/service/bedrockruntime"
@@ -17,7 +19,7 @@ const amazonbedrockAIClientName = "amazonbedrock"
 type AmazonBedRockClient struct {
 	nopCloser

-	client      *bedrockruntime.BedrockRuntime
+	client      bedrockruntimeiface.BedrockRuntimeAPI
 	model       *bedrock_support.BedrockModel
 	temperature float32
 	topP        float32
@@ -50,24 +52,14 @@ var (
 	models = []bedrock_support.BedrockModel{
 		{
 			Name:       "anthropic.claude-3-5-sonnet-20240620-v1:0",
-			Completion: &bedrock_support.CohereCompletion{},
-			Response:   &bedrock_support.CohereResponse{},
-			Config: bedrock_support.BedrockModelConfig{
-				// sensible defaults
-				MaxTokens:   100,
-				Temperature: 0.5,
-				TopP:        0.9,
-			},
-		},
-		{
-			Name:       "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
-			Completion: &bedrock_support.CohereCompletion{},
-			Response:   &bedrock_support.CohereResponse{},
+			Completion: &bedrock_support.CohereMessagesCompletion{},
+			Response:   &bedrock_support.CohereMessagesResponse{},
 			Config: bedrock_support.BedrockModelConfig{
 				// sensible defaults
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "anthropic.claude-3-5-sonnet-20240620-v1:0",
 			},
 		},
 		{
@@ -79,6 +71,7 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
 			},
 		},
 		{
@@ -90,6 +83,7 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "anthropic.claude-v2",
 			},
 		},
 		{
@@ -101,6 +95,7 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "anthropic.claude-v1",
 			},
 		},
 		{
@@ -112,6 +107,7 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "anthropic.claude-instant-v1",
 			},
 		},
 		{
@@ -123,6 +119,7 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "ai21.j2-ultra-v1",
 			},
 		},
 		{
@@ -134,6 +131,7 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "ai21.j2-jumbo-instruct",
 			},
 		},
 		{
@@ -145,6 +143,82 @@ var (
 				MaxTokens:   100,
 				Temperature: 0.5,
 				TopP:        0.9,
+				ModelName:   "amazon.titan-text-express-v1",
+			},
+		},
+		{
+			Name:       "amazon.nova-pro-v1:0",
+			Completion: &bedrock_support.AmazonCompletion{},
+			Response:   &bedrock_support.NovaResponse{},
+			Config: bedrock_support.BedrockModelConfig{
+				// sensible defaults
+				// https://docs.aws.amazon.com/nova/latest/userguide/getting-started-api.html
+				MaxTokens:   100, // max of 300k tokens
+				Temperature: 0.5,
+				TopP:        0.9,
+				ModelName:   "amazon.nova-pro-v1:0",
+			},
+		},
+		{
+			Name:       "eu.amazon.nova-pro-v1:0",
+			Completion: &bedrock_support.AmazonCompletion{},
+			Response:   &bedrock_support.NovaResponse{},
+			Config: bedrock_support.BedrockModelConfig{
+				// sensible defaults
+				// https://docs.aws.amazon.com/nova/latest/userguide/getting-started-api.html
+				MaxTokens:   100, // max of 300k tokens
+				Temperature: 0.5,
+				TopP:        0.9,
+				ModelName:   "eu.wamazon.nova-pro-v1:0",
+			},
+		},
+		{
+			Name:       "us.amazon.nova-pro-v1:0",
+			Completion: &bedrock_support.AmazonCompletion{},
+			Response:   &bedrock_support.NovaResponse{},
+			Config: bedrock_support.BedrockModelConfig{
+				// sensible defaults
+				// https://docs.aws.amazon.com/nova/latest/userguide/getting-started-api.html
+				MaxTokens:   100, // max of 300k tokens
+				Temperature: 0.5,
+				TopP:        0.9,
+				ModelName:   "us.amazon.nova-pro-v1:0",
+			},
+		},
+		{
+			Name:       "amazon.nova-lite-v1:0",
+			Completion: &bedrock_support.AmazonCompletion{},
+			Response:   &bedrock_support.NovaResponse{},
+			Config: bedrock_support.BedrockModelConfig{
+				// sensible defaults
+				MaxTokens:   100, // max of 300k tokens
+				Temperature: 0.5,
+				TopP:        0.9,
+				ModelName:   "amazon.nova-lite-v1:0",
+			},
+		},
+		{
+			Name:       "eu.amazon.nova-lite-v1:0",
+			Completion: &bedrock_support.AmazonCompletion{},
+			Response:   &bedrock_support.NovaResponse{},
+			Config: bedrock_support.BedrockModelConfig{
+				// sensible defaults
+				MaxTokens:   100, // max of 300k tokens
+				Temperature: 0.5,
+				TopP:        0.9,
+				ModelName:   "eu.amazon.nova-lite-v1:0",
+			},
+		},
+		{
+			Name:       "us.amazon.nova-lite-v1:0",
+			Completion: &bedrock_support.AmazonCompletion{},
+			Response:   &bedrock_support.NovaResponse{},
+			Config: bedrock_support.BedrockModelConfig{
+				// sensible defaults
+				MaxTokens:   100, // max of 300k tokens
+				Temperature: 0.5,
+				TopP:        0.9,
+				ModelName:   "us.amazon.nova-lite-v1:0",
 			},
 		},
 	}
@@ -200,6 +274,7 @@ func (a *AmazonBedRockClient) Configure(config IAIConfig) error {
 	// Create a new BedrockRuntime client
 	a.client = bedrockruntime.New(sess)
 	a.model = foundModel
+	a.model.Config.ModelName = foundModel.Name
 	a.temperature = config.GetTemperature()
 	a.topP = config.GetTopP()
 	a.maxTokens = config.GetMaxTokens()
--- a/pkg/ai/bedrock_support/completions.go
+++ b/pkg/ai/bedrock_support/completions.go
@@ -4,8 +4,22 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 )

+var SUPPPORTED_BEDROCK_MODELS = []string{
+	"anthropic.claude-3-5-sonnet-20240620-v1:0",
+	"us.anthropic.claude-3-5-sonnet-20241022-v2:0",
+	"anthropic.claude-v2",
+	"anthropic.claude-v1",
+	"anthropic.claude-instant-v1",
+	"ai21.j2-ultra-v1",
+	"ai21.j2-jumbo-instruct",
+	"amazon.titan-text-express-v1",
+	"amazon.nova-pro-v1:0",
+	"eu.amazon.nova-lite-v1:0",
+}
+
 type ICompletion interface {
 	GetCompletion(ctx context.Context, prompt string, modelConfig BedrockModelConfig) ([]byte, error)
 }
@@ -28,6 +42,31 @@ func (a *CohereCompletion) GetCompletion(ctx context.Context, prompt string, mod
 	return body, nil
 }

+type CohereMessagesCompletion struct {
+	completion ICompletion
+}
+
+func (a *CohereMessagesCompletion) GetCompletion(ctx context.Context, prompt string, modelConfig BedrockModelConfig) ([]byte, error) {
+	request := map[string]interface{}{
+		"max_tokens":        modelConfig.MaxTokens,
+		"temperature":       modelConfig.Temperature,
+		"top_p":             modelConfig.TopP,
+		"anthropic_version": "bedrock-2023-05-31", // Or another valid version
+		"messages": []map[string]interface{}{
+			{
+				"role":    "user",
+				"content": prompt,
+			},
+		},
+	}
+
+	body, err := json.Marshal(request)
+	if err != nil {
+		return []byte{}, err
+	}
+	return body, nil
+}
+
 type AI21 struct {
 	completion ICompletion
 }
@@ -50,7 +89,27 @@ type AmazonCompletion struct {
 	completion ICompletion
 }

+func isModelSupported(modelName string) bool {
+	for _, supportedModel := range SUPPPORTED_BEDROCK_MODELS {
+		if modelName == supportedModel {
+			return true
+		}
+	}
+	return false
+}
+
 func (a *AmazonCompletion) GetCompletion(ctx context.Context, prompt string, modelConfig BedrockModelConfig) ([]byte, error) {
+	if !isModelSupported(modelConfig.ModelName) {
+		return nil, fmt.Errorf("model %s is not supported", modelConfig.ModelName)
+	}
+	if strings.Contains(modelConfig.ModelName, "nova") {
+		return a.GetNovaCompletion(ctx, prompt, modelConfig)
+	} else {
+		return a.GetDefaultCompletion(ctx, prompt, modelConfig)
+	}
+}
+
+func (a *AmazonCompletion) GetDefaultCompletion(ctx context.Context, prompt string, modelConfig BedrockModelConfig) ([]byte, error) {
 	request := map[string]interface{}{
 		"inputText": fmt.Sprintf("\n\nUser: %s", prompt),
 		"textGenerationConfig": map[string]interface{}{
@@ -64,4 +123,30 @@ func (a *AmazonCompletion) GetCompletion(ctx context.Context, prompt string, mod
 		return []byte{}, err
 	}
 	return body, nil
+
+}
+
+func (a *AmazonCompletion) GetNovaCompletion(ctx context.Context, prompt string, modelConfig BedrockModelConfig) ([]byte, error) {
+	request := map[string]interface{}{
+		"inferenceConfig": map[string]interface{}{
+			"max_new_tokens": modelConfig.MaxTokens,
+			"temperature":    modelConfig.Temperature,
+			"topP":           modelConfig.TopP,
+		},
+		"messages": []map[string]interface{}{
+			{
+				"role": "user",
+				"content": []map[string]interface{}{
+					{
+						"text": prompt,
+					},
+				},
+			},
+		},
+	}
+	body, err := json.Marshal(request)
+	if err != nil {
+		return []byte{}, err
+	}
+	return body, nil
 }
--- a/pkg/ai/bedrock_support/completions_test.go
+++ b/pkg/ai/bedrock_support/completions_test.go
@@ -0,0 +1,179 @@
+package bedrock_support
+
+import (
+	"context"
+	"encoding/json"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCohereCompletion_GetCompletion(t *testing.T) {
+	completion := &CohereCompletion{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   100,
+		Temperature: 0.7,
+		TopP:        0.9,
+	}
+	prompt := "Test prompt"
+
+	body, err := completion.GetCompletion(context.Background(), prompt, modelConfig)
+	assert.NoError(t, err)
+
+	var request map[string]interface{}
+	err = json.Unmarshal(body, &request)
+	assert.NoError(t, err)
+
+	assert.Equal(t, "\n\nHuman: Test prompt  \n\nAssistant:", request["prompt"])
+	assert.Equal(t, 100, int(request["max_tokens_to_sample"].(float64)))
+	assert.Equal(t, 0.7, request["temperature"])
+	assert.Equal(t, 0.9, request["top_p"])
+}
+
+func TestAI21_GetCompletion(t *testing.T) {
+	completion := &AI21{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   150,
+		Temperature: 0.6,
+		TopP:        0.8,
+	}
+	prompt := "Another test prompt"
+
+	body, err := completion.GetCompletion(context.Background(), prompt, modelConfig)
+	assert.NoError(t, err)
+
+	var request map[string]interface{}
+	err = json.Unmarshal(body, &request)
+	assert.NoError(t, err)
+
+	assert.Equal(t, "Another test prompt", request["prompt"])
+	assert.Equal(t, 150, int(request["maxTokens"].(float64)))
+	assert.Equal(t, 0.6, request["temperature"])
+	assert.Equal(t, 0.8, request["topP"])
+}
+
+func TestAmazonCompletion_GetDefaultCompletion(t *testing.T) {
+	completion := &AmazonCompletion{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   200,
+		Temperature: 0.5,
+		TopP:        0.7,
+		ModelName:   "amazon.titan-text-express-v1",
+	}
+	prompt := "Default test prompt"
+
+	body, err := completion.GetDefaultCompletion(context.Background(), prompt, modelConfig)
+	assert.NoError(t, err)
+
+	var request map[string]interface{}
+	err = json.Unmarshal(body, &request)
+	assert.NoError(t, err)
+
+	assert.Equal(t, "\n\nUser: Default test prompt", request["inputText"])
+	textConfig := request["textGenerationConfig"].(map[string]interface{})
+	assert.Equal(t, 200, int(textConfig["maxTokenCount"].(float64)))
+	assert.Equal(t, 0.5, textConfig["temperature"])
+	assert.Equal(t, 0.7, textConfig["topP"])
+}
+
+func TestAmazonCompletion_GetNovaCompletion(t *testing.T) {
+	completion := &AmazonCompletion{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   250,
+		Temperature: 0.4,
+		TopP:        0.6,
+		ModelName:   "amazon.nova-pro-v1:0",
+	}
+	prompt := "Nova test prompt"
+
+	body, err := completion.GetNovaCompletion(context.Background(), prompt, modelConfig)
+	assert.NoError(t, err)
+
+	var request map[string]interface{}
+	err = json.Unmarshal(body, &request)
+	assert.NoError(t, err)
+
+	inferenceConfig := request["inferenceConfig"].(map[string]interface{})
+	assert.Equal(t, 250, int(inferenceConfig["max_new_tokens"].(float64)))
+	assert.Equal(t, 0.4, inferenceConfig["temperature"])
+	assert.Equal(t, 0.6, inferenceConfig["topP"])
+
+	messages := request["messages"].([]interface{})
+	message := messages[0].(map[string]interface{})
+	content := message["content"].([]interface{})
+	contentMap := content[0].(map[string]interface{})
+	assert.Equal(t, "Nova test prompt", contentMap["text"])
+}
+
+func TestAmazonCompletion_GetCompletion_Nova(t *testing.T) {
+	completion := &AmazonCompletion{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   250,
+		Temperature: 0.4,
+		TopP:        0.6,
+		ModelName:   "amazon.nova-pro-v1:0",
+	}
+	prompt := "Nova test prompt"
+
+	body, err := completion.GetCompletion(context.Background(), prompt, modelConfig)
+	assert.NoError(t, err)
+
+	var request map[string]interface{}
+	err = json.Unmarshal(body, &request)
+	assert.NoError(t, err)
+
+	inferenceConfig := request["inferenceConfig"].(map[string]interface{})
+	assert.Equal(t, 250, int(inferenceConfig["max_new_tokens"].(float64)))
+	assert.Equal(t, 0.4, inferenceConfig["temperature"])
+	assert.Equal(t, 0.6, inferenceConfig["topP"])
+
+	messages := request["messages"].([]interface{})
+	message := messages[0].(map[string]interface{})
+	content := message["content"].([]interface{})
+	contentMap := content[0].(map[string]interface{})
+	assert.Equal(t, "Nova test prompt", contentMap["text"])
+}
+
+func TestAmazonCompletion_GetCompletion_Default(t *testing.T) {
+	completion := &AmazonCompletion{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   200,
+		Temperature: 0.5,
+		TopP:        0.7,
+		ModelName:   "amazon.titan-text-express-v1",
+	}
+	prompt := "Default test prompt"
+
+	body, err := completion.GetCompletion(context.Background(), prompt, modelConfig)
+	assert.NoError(t, err)
+
+	var request map[string]interface{}
+	err = json.Unmarshal(body, &request)
+	assert.NoError(t, err)
+
+	assert.Equal(t, "\n\nUser: Default test prompt", request["inputText"])
+	textConfig := request["textGenerationConfig"].(map[string]interface{})
+	assert.Equal(t, 200, int(textConfig["maxTokenCount"].(float64)))
+	assert.Equal(t, 0.5, textConfig["temperature"])
+	assert.Equal(t, 0.7, textConfig["topP"])
+}
+
+func TestAmazonCompletion_GetCompletion_UnsupportedModel(t *testing.T) {
+	completion := &AmazonCompletion{}
+	modelConfig := BedrockModelConfig{
+		MaxTokens:   200,
+		Temperature: 0.5,
+		TopP:        0.7,
+		ModelName:   "unsupported-model",
+	}
+	prompt := "Test prompt"
+
+	_, err := completion.GetCompletion(context.Background(), prompt, modelConfig)
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "model unsupported-model is not supported")
+}
+
+func Test_isModelSupported(t *testing.T) {
+	assert.True(t, isModelSupported("anthropic.claude-v2"))
+	assert.False(t, isModelSupported("unsupported-model"))
+}
--- a/pkg/ai/bedrock_support/model.go
+++ b/pkg/ai/bedrock_support/model.go
@@ -4,6 +4,7 @@ type BedrockModelConfig struct {
 	MaxTokens   int
 	Temperature float32
 	TopP        float32
+	ModelName   string
 }
 type BedrockModel struct {
 	Name       string
--- a/pkg/ai/bedrock_support/model_test.go
+++ b/pkg/ai/bedrock_support/model_test.go
@@ -0,0 +1,59 @@
+package bedrock_support
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestBedrockModelConfig(t *testing.T) {
+	config := BedrockModelConfig{
+		MaxTokens:   100,
+		Temperature: 0.7,
+		TopP:        0.9,
+		ModelName:   "test-model",
+	}
+
+	assert.Equal(t, 100, config.MaxTokens)
+	assert.Equal(t, float32(0.7), config.Temperature)
+	assert.Equal(t, float32(0.9), config.TopP)
+	assert.Equal(t, "test-model", config.ModelName)
+}
+
+func TestBedrockModel(t *testing.T) {
+	completion := &MockCompletion{}
+	response := &MockResponse{}
+	config := BedrockModelConfig{
+		MaxTokens:   100,
+		Temperature: 0.7,
+		TopP:        0.9,
+		ModelName:   "test-model",
+	}
+
+	model := BedrockModel{
+		Name:       "Test Model",
+		Completion: completion,
+		Response:   response,
+		Config:     config,
+	}
+
+	assert.Equal(t, "Test Model", model.Name)
+	assert.Equal(t, completion, model.Completion)
+	assert.Equal(t, response, model.Response)
+	assert.Equal(t, config, model.Config)
+}
+
+// MockCompletion is a mock implementation of the ICompletion interface
+type MockCompletion struct{}
+
+func (m *MockCompletion) GetCompletion(ctx context.Context, prompt string, config BedrockModelConfig) ([]byte, error) {
+	return []byte(`{"prompt": "mock prompt"}`), nil
+}
+
+// MockResponse is a mock implementation of the IResponse interface
+type MockResponse struct{}
+
+func (m *MockResponse) ParseResponse(body []byte) (string, error) {
+	return "mock response", nil
+}
--- a/pkg/ai/bedrock_support/responses.go
+++ b/pkg/ai/bedrock_support/responses.go
@@ -1,11 +1,52 @@
 package bedrock_support

-import "encoding/json"
+import (
+	"encoding/json"
+)

 type IResponse interface {
 	ParseResponse(rawResponse []byte) (string, error)
 }

+type CohereMessagesResponse struct {
+	response IResponse
+}
+
+func (a *CohereMessagesResponse) ParseResponse(rawResponse []byte) (string, error) {
+	type InvokeModelResponseBody struct {
+		ID      string `json:"id"`
+		Type    string `json:"type"`
+		Role    string `json:"role"`
+		Model   string `json:"model"`
+		Content []struct {
+			Type string `json:"type"`
+			Text string `json:"text"`
+		} `json:"content"`
+		StopReason   string      `json:"stop_reason"`
+		StopSequence interface{} `json:"stop_sequence"` // Could be null
+		Usage        struct {
+			InputTokens  int `json:"input_tokens"`
+			OutputTokens int `json:"output_tokens"`
+		} `json:"usage"`
+	}
+
+	output := &InvokeModelResponseBody{}
+	err := json.Unmarshal(rawResponse, output)
+	if err != nil {
+		return "", err
+	}
+
+	// Extract the text content from the Content array
+	var resultText string
+	for _, content := range output.Content {
+		if content.Type == "text" {
+			resultText += content.Text
+		}
+	}
+
+	return resultText, nil
+}
+
 type CohereResponse struct {
 	response IResponse
 }
@@ -49,6 +90,13 @@ type AmazonResponse struct {
 	response IResponse
 }

+type NovaResponse struct {
+	response NResponse
+}
+type NResponse interface {
+	ParseResponse(rawResponse []byte) (string, error)
+}
+
 func (a *AmazonResponse) ParseResponse(rawResponse []byte) (string, error) {
 	type Result struct {
 		TokenCount       int    `json:"tokenCount"`
@@ -66,3 +114,42 @@ func (a *AmazonResponse) ParseResponse(rawResponse []byte) (string, error) {
 	}
 	return output.Results[0].OutputText, nil
 }
+
+func (a *NovaResponse) ParseResponse(rawResponse []byte) (string, error) {
+	type Content struct {
+		Text string `json:"text"`
+	}
+
+	type Message struct {
+		Role    string    `json:"role"`
+		Content []Content `json:"content"`
+	}
+
+	type UsageDetails struct {
+		InputTokens               int `json:"inputTokens"`
+		OutputTokens              int `json:"outputTokens"`
+		TotalTokens               int `json:"totalTokens"`
+		CacheReadInputTokenCount  int `json:"cacheReadInputTokenCount"`
+		CacheWriteInputTokenCount int `json:"cacheWriteInputTokenCount,omitempty"`
+	}
+
+	type AmazonNovaResponse struct {
+		Output struct {
+			Message Message `json:"message"`
+		} `json:"output"`
+		StopReason string       `json:"stopReason"`
+		Usage      UsageDetails `json:"usage"`
+	}
+
+	response := &AmazonNovaResponse{}
+	err := json.Unmarshal(rawResponse, response)
+	if err != nil {
+		return "", err
+	}
+
+	if len(response.Output.Message.Content) > 0 {
+		return response.Output.Message.Content[0].Text, nil
+	}
+
+	return "", nil
+}
--- a/pkg/ai/bedrock_support/responses_test.go
+++ b/pkg/ai/bedrock_support/responses_test.go
@@ -0,0 +1,65 @@
+package bedrock_support
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCohereResponse_ParseResponse(t *testing.T) {
+	response := &CohereResponse{}
+	rawResponse := []byte(`{"completion": "Test completion", "stop_reason": "max_tokens"}`)
+
+	result, err := response.ParseResponse(rawResponse)
+	assert.NoError(t, err)
+	assert.Equal(t, "Test completion", result)
+
+	invalidResponse := []byte(`{"completion": "Test completion", "invalid_json":]`)
+	_, err = response.ParseResponse(invalidResponse)
+	assert.Error(t, err)
+}
+
+func TestAI21Response_ParseResponse(t *testing.T) {
+	response := &AI21Response{}
+	rawResponse := []byte(`{"completions": [{"data": {"text": "AI21 test"}}], "id": "123"}`)
+
+	result, err := response.ParseResponse(rawResponse)
+	assert.NoError(t, err)
+	assert.Equal(t, "AI21 test", result)
+
+	invalidResponse := []byte(`{"completions": [{"data": {"text": "AI21 test"}}, "invalid_json":]`)
+	_, err = response.ParseResponse(invalidResponse)
+	assert.Error(t, err)
+}
+
+func TestAmazonResponse_ParseResponse(t *testing.T) {
+	response := &AmazonResponse{}
+	rawResponse := []byte(`{"inputTextTokenCount": 10, "results": [{"tokenCount": 20, "outputText": "Amazon test", "completionReason": "stop"}]}`)
+
+	result, err := response.ParseResponse(rawResponse)
+	assert.NoError(t, err)
+	assert.Equal(t, "Amazon test", result)
+
+	invalidResponse := []byte(`{"inputTextTokenCount": 10, "results": [{"tokenCount": 20, "outputText": "Amazon test", "invalid_json":]`)
+	_, err = response.ParseResponse(invalidResponse)
+	assert.Error(t, err)
+}
+
+func TestNovaResponse_ParseResponse(t *testing.T) {
+	response := &NovaResponse{}
+	rawResponse := []byte(`{"output": {"message": {"content": [{"text": "Nova test"}]}}, "stopReason": "stop", "usage": {"inputTokens": 10, "outputTokens": 20, "totalTokens": 30, "cacheReadInputTokenCount": 5}}`)
+
+	result, err := response.ParseResponse(rawResponse)
+	assert.NoError(t, err)
+	assert.Equal(t, "Nova test", result)
+
+	rawResponseEmptyContent := []byte(`{"output": {"message": {"content": []}}, "stopReason": "stop", "usage": {"inputTokens": 10, "outputTokens": 20, "totalTokens": 30, "cacheReadInputTokenCount": 5}}`)
+
+	resultEmptyContent, errEmptyContent := response.ParseResponse(rawResponseEmptyContent)
+	assert.NoError(t, errEmptyContent)
+	assert.Equal(t, "", resultEmptyContent)
+
+	invalidResponse := []byte(`{"output": {"message": {"content": [{"text": "Nova test"}}, "invalid_json":]`)
+	_, err = response.ParseResponse(invalidResponse)
+	assert.Error(t, err)
+}
--- a/pkg/ai/customrest.go
+++ b/pkg/ai/customrest.go
@@ -0,0 +1,147 @@
+package ai
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"strings"
+	"time"
+)
+
+const CustomRestClientName = "customrest"
+
+type CustomRestClient struct {
+	nopCloser
+	client      *http.Client
+	base        *url.URL
+	token       string
+	model       string
+	temperature float32
+	topP        float32
+	topK        int32
+}
+
+type CustomRestRequest struct {
+	Model string `json:"model"`
+
+	// Prompt is the textual prompt to send to the model.
+	Prompt string `json:"prompt"`
+
+	// Options lists model-specific options. For example, temperature can be
+	// set through this field, if the model supports it.
+	Options map[string]interface{} `json:"options"`
+}
+
+type CustomRestResponse struct {
+	// Model is the model name that generated the response.
+	Model string `json:"model"`
+
+	// CreatedAt is the timestamp of the response.
+	CreatedAt time.Time `json:"created_at"`
+
+	// Response is the textual response itself.
+	Response string `json:"response"`
+}
+
+func (c *CustomRestClient) Configure(config IAIConfig) error {
+	baseURL := config.GetBaseURL()
+	if baseURL == "" {
+		baseURL = defaultBaseURL
+	}
+	c.token = config.GetPassword()
+	baseClientURL, err := url.Parse(baseURL)
+	if err != nil {
+		return err
+	}
+	c.base = baseClientURL
+
+	proxyEndpoint := config.GetProxyEndpoint()
+	c.client = http.DefaultClient
+	if proxyEndpoint != "" {
+		proxyUrl, err := url.Parse(proxyEndpoint)
+		if err != nil {
+			return err
+		}
+		transport := &http.Transport{
+			Proxy: http.ProxyURL(proxyUrl),
+		}
+
+		c.client = &http.Client{
+			Transport: transport,
+		}
+	}
+
+	c.model = config.GetModel()
+	if c.model == "" {
+		c.model = defaultModel
+	}
+	c.temperature = config.GetTemperature()
+	c.topP = config.GetTopP()
+	c.topK = config.GetTopK()
+	return nil
+}
+
+func (c *CustomRestClient) GetCompletion(ctx context.Context, prompt string) (string, error) {
+	var promptDetail struct {
+		Language string `json:"language,omitempty"`
+		Message  string `json:"message"`
+		Prompt   string `json:"prompt,omitempty"`
+	}
+	prompt = strings.NewReplacer("\n", "\\n", "\t", "\\t").Replace(prompt)
+	if err := json.Unmarshal([]byte(prompt), &promptDetail); err != nil {
+		return "", err
+	}
+	generateRequest := &CustomRestRequest{
+		Model:  c.model,
+		Prompt: promptDetail.Prompt,
+		Options: map[string]interface{}{
+			"temperature": c.temperature,
+			"top_p":       c.topP,
+			"top_k":       c.topK,
+			"message":     promptDetail.Message,
+			"language":    promptDetail.Language,
+		},
+	}
+	requestBody, err := json.Marshal(generateRequest)
+	if err != nil {
+		return "", err
+	}
+	request, err := http.NewRequestWithContext(ctx, http.MethodPost, c.base.String(), bytes.NewBuffer(requestBody))
+	if err != nil {
+		return "", err
+	}
+	if c.token != "" {
+		request.Header.Set("Authorization", "Bearer "+c.token)
+	}
+	request.Header.Set("Content-Type", "application/json")
+	request.Header.Set("Accept", "application/x-ndjson")
+
+	response, err := c.client.Do(request)
+	if err != nil {
+		return "", err
+	}
+	defer response.Body.Close()
+
+	responseBody, err := io.ReadAll(response.Body)
+	if err != nil {
+		return "", fmt.Errorf("could not read response body: %w", err)
+	}
+
+	if response.StatusCode >= http.StatusBadRequest {
+		return "", fmt.Errorf("Request Error, StatusCode: %d, ErrorMessage: %s", response.StatusCode, responseBody)
+	}
+
+	var result CustomRestResponse
+	if err := json.Unmarshal(responseBody, &result); err != nil {
+		return "", err
+	}
+	return result.Response, nil
+}
+
+func (c *CustomRestClient) GetName() string {
+	return CustomRestClientName
+}
--- a/pkg/ai/iai.go
+++ b/pkg/ai/iai.go
@@ -32,6 +32,7 @@ var (
 		&HuggingfaceClient{},
 		&GoogleVertexAIClient{},
 		&OCIGenAIClient{},
+		&CustomRestClient{},
 		&IBMWatsonxAIClient{},
 	}
 	Backends = []string{
@@ -47,6 +48,7 @@ var (
 		huggingfaceAIClientName,
 		googleVertexAIClientName,
 		ociClientName,
+		CustomRestClientName,
 		ibmWatsonxAIClientName,
 	}
 )
@@ -181,7 +183,7 @@ func (p *AIProvider) GetCustomHeaders() []http.Header {
 	return p.CustomHeaders
 }

-var passwordlessProviders = []string{"localai", "ollama", "amazonsagemaker", "amazonbedrock", "googlevertexai", "oci"}
+var passwordlessProviders = []string{"localai", "ollama", "amazonsagemaker", "amazonbedrock", "googlevertexai", "oci", "customrest"}

 func NeedPassword(backend string) bool {
 	for _, b := range passwordlessProviders {
--- a/pkg/ai/prompts.go
+++ b/pkg/ai/prompts.go
@@ -56,9 +56,11 @@ const (

 	Solution: {kubectl command}
 	`
+	raw_promt = `{"language": "%s","message": "%s","prompt": "%s"}`
 )

 var PromptMap = map[string]string{
+	"raw":                           raw_promt,
 	"default":                       default_prompt,
 	"PrometheusConfigValidate":      prom_conf_prompt,
 	"PrometheusConfigRelabelReport": prom_relabel_prompt,
--- a/pkg/analysis/analysis.go
+++ b/pkg/analysis/analysis.go
@@ -295,7 +295,9 @@ func (a *Analysis) executeAnalyzer(analyzer common.IAnalyzer, filter string, ana

 	// Run the analyzer
 	results, err := analyzer.Analyze(analyzerConfig)
-
+	if err != nil {
+		fmt.Println(err)
+	}
 	// Measure the time taken
 	if a.WithStats {
 		elapsedTime = time.Since(startTime)
@@ -405,6 +407,9 @@ func (a *Analysis) getAIResultForSanitizedFailures(texts []string, promptTmpl st

 	// Process template.
 	prompt := fmt.Sprintf(strings.TrimSpace(promptTmpl), a.Language, inputKey)
+	if a.AIClient.GetName() == ai.CustomRestClientName {
+		prompt = fmt.Sprintf(ai.PromptMap["raw"], a.Language, inputKey, prompt)
+	}
 	response, err := a.AIClient.GetCompletion(a.Context, prompt)
 	if err != nil {
 		return "", err
Author	SHA1	Message	Date
github-actions[bot]	a75ec50789	chore(main): release 0.4.2 (#1400 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2025-03-28 14:17:21 +00:00
Alex Jones	e5817f9e55	feat: old sonnet (#1408 ) * chore: rebased chore: removed trivy Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * chore: updated deps Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * fix: missing error Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * fix: missing error Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * feat: switching old sonnet to message API Signed-off-by: AlexsJones <alexsimonjones@gmail.com> --------- Signed-off-by: AlexsJones <alexsimonjones@gmail.com>	2025-03-28 13:51:47 +00:00
renovate[bot]	f5eaf817f0	fix(deps): update k8s.io/utils digest to 1f6e0b7 (#1405 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-25 07:26:43 +00:00
renovate[bot]	eb381b8087	chore(deps): update actions/upload-artifact digest to ea165f8 (#1402 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-21 10:42:48 +00:00
Alex Jones	288ca862b3	chore: fix error (#1403 ) * chore: rebased chore: removed trivy Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * chore: updated deps Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * fix: missing error Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * fix: missing error Signed-off-by: AlexsJones <alexsimonjones@gmail.com> --------- Signed-off-by: AlexsJones <alexsimonjones@gmail.com>	2025-03-19 21:05:53 +00:00
renovate[bot]	81d4aaf402	chore(deps): update actions/setup-go digest to 0aaccfd (#1401 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-19 15:39:46 +00:00
renovate[bot]	fdf8e7a95a	chore(deps): update docker/login-action digest to 74a5d14 (#1397 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-17 19:17:47 +00:00
github-actions[bot]	5a48bae667	chore(main): release 0.4.1 (#1389 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2025-03-17 12:23:11 +00:00
popsiclexu	7540e0084e	feat: add custom restful backend for complex scenarios (e.g, rag) (#1228 ) * feat: add custom restful backend for complex scenarios (e.g, rag) Signed-off-by: popsiclexu <zhenxuexu@gmail.com> * chore: rebased chore: removed trivy Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * chore: updated deps Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * chore: resolved issues Signed-off-by: AlexsJones <alexsimonjones@gmail.com> --------- Signed-off-by: popsiclexu <zhenxuexu@gmail.com> Signed-off-by: popsiclexu <ZhenxueXu@gmail.com> Signed-off-by: AlexsJones <alexsimonjones@gmail.com> Co-authored-by: popsiclexu <zhenxue.xu@mthreads.com> Co-authored-by: Alex Jones <alexsimonjones@gmail.com>	2025-03-17 12:21:38 +00:00
renovate[bot]	eb7b36aa27	fix(deps): update module golang.org/x/net to v0.36.0 [security] (#1395 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-17 12:06:10 +00:00
renovate[bot]	d6d2e3bc42	chore(deps): update goreleaser/goreleaser-action digest to 90a3faa (#1308 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-11 21:20:04 +00:00
100daysofdevops	4e39cb65b3	fix(deps): update default model to gpt-4o for improved performance and cost efficiency (#1332 ) * fix: update OpenAI API key generation URL to reflect new platform link Updated the outdated URL 'https://beta.openai.com/account/api-keys' to the current OpenAI API key generation page 'https://platform.openai.com/account/api-keys'. This resolves the issue where users were directed to an incorrect URL when generating an OpenAI API key. Signed-off-by: 100daysofdevops <47483190+100daysofdevops@users.noreply.github.com> * fix(deps):Add transition plan for GPT-3.5 Turbo to GPT-4o - A comprehensive comparison of GPT-3.5 Turbo and GPT-4o models, focusing on performance and cost improvements. - Documentation updates highlighting the planned deprecation of gpt-3.5-turbo-0301 on February 13, 2025. - Clear migration guidelines for transitioning to GPT-4o or GPT-4o mini to ensure service continuity. Signed-off-by: 100daysofdevops <47483190+100daysofdevops@users.noreply.github.com> --------- Signed-off-by: 100daysofdevops <47483190+100daysofdevops@users.noreply.github.com> Co-authored-by: Alex Jones <alexsimonjones@gmail.com>	2025-03-11 20:58:21 +00:00
renovate[bot]	db5e517dbb	chore(deps): update softprops/action-gh-release digest to c95fe14 (#1359 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-11 20:52:28 +00:00
Cindy Tong	aa1e237ebb	feat: add amazon bedrock nova pro and nova lite models (#1383 ) * feat: add amazon bedrock nova pro and nova lite models Signed-off-by: Cindy Tong <tongcindyy@gmail.com> * fix nova responses Signed-off-by: Cindy Tong <tongcindyy@gmail.com> * remove printing of Nova Response Signed-off-by: Cindy Tong <tongcindyy@gmail.com> * remove comments Signed-off-by: Cindy Tong <tongcindyy@gmail.com> * chore: rebased chore: removed trivy Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * chore: updated deps Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * chore: adding inference profile labels as model names Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * feat: added some tests around completions and responses Signed-off-by: AlexsJones <alexsimonjones@gmail.com> * feat: added model test Signed-off-by: AlexsJones <alexsimonjones@gmail.com> --------- Signed-off-by: Cindy Tong <tongcindyy@gmail.com> Signed-off-by: AlexsJones <alexsimonjones@gmail.com> Co-authored-by: AlexsJones <alexsimonjones@gmail.com>	2025-03-11 12:55:21 +00:00
renovate[bot]	f2fdfd8dca	chore(deps): update actions/setup-go digest to f111f33 (#1364 ) Signed-off-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-07 12:07:47 +00:00