Merge branch 'main' into langchain_llamastack

.github/dependabot.yml

@@ -9,6 +9,7 @@ updates:
       day: "saturday"
     commit-message:
       prefix: chore(github-deps)
+
   - package-ecosystem: "uv"
     directory: "/"
     schedule:
@@ -19,3 +20,14 @@ updates:
       - python
     commit-message:
       prefix: chore(python-deps)
+
+  - package-ecosystem: npm
+    directory: "/llama_stack/ui"
+    schedule:
+      interval: "weekly"
+      day: "saturday"
+    labels:
+      - type/dependencies
+      - javascript
+    commit-message:
+      prefix: chore(ui-deps)

.github/workflows/changelog.yml

@@ -17,7 +17,7 @@ jobs:
       pull-requests: write  # for peter-evans/create-pull-request to create a PR
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           ref: main
           fetch-depth: 0

.github/workflows/install-script-ci.yml

@@ -16,14 +16,14 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # 4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # 5.0.0
       - name: Run ShellCheck on install.sh
         run: shellcheck scripts/install.sh
   smoke-test-on-dev:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/integration-auth-tests.yml

@@ -18,7 +18,7 @@ on:
       - '.github/workflows/integration-auth-tests.yml' # This workflow
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -31,7 +31,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/integration-sql-store-tests.yml

@@ -16,7 +16,7 @@ on:
       - '.github/workflows/integration-sql-store-tests.yml' # This workflow
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -44,7 +44,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/integration-tests.yml

@@ -65,7 +65,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Setup test environment
         uses: ./.github/actions/setup-test-environment

.github/workflows/integration-vector-io-tests.yml

@@ -33,7 +33,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/pre-commit.yml

@@ -8,7 +8,7 @@ on:
     branches: [main]
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -20,7 +20,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           # For dependabot PRs, we need to checkout with a token that can push changes
           token: ${{ github.actor == 'dependabot[bot]' && secrets.GITHUB_TOKEN || github.token }}
@@ -36,20 +36,16 @@ jobs:
             **/requirements*.txt
             .pre-commit-config.yaml
 
-      # npm ci may fail -
+      - name: Set up Node.js
-      #   npm error `npm ci` can only install packages when your package.json and package-lock.json or npm-shrinkwrap.json are in sync. Please update your lock file with `npm install` before continuing.
+        uses: actions/setup-node@39370e3970a6d050c480ffad4ff0ed4d3fdee5af # v4.1.0
-      #   npm error Invalid: lock file's llama-stack-client@0.2.17 does not satisfy llama-stack-client@0.2.18
+        with:
+          node-version: '20'
+          cache: 'npm'
+          cache-dependency-path: 'llama_stack/ui/'
 
-      # - name: Set up Node.js
+      - name: Install npm dependencies
-      #   uses: actions/setup-node@39370e3970a6d050c480ffad4ff0ed4d3fdee5af # v4.1.0
+        run: npm ci
-      #   with:
+        working-directory: llama_stack/ui
-      #     node-version: '20'
-      #     cache: 'npm'
-      #     cache-dependency-path: 'llama_stack/ui/'
-
-      # - name: Install npm dependencies
-      #   run: npm ci
-      #   working-directory: llama_stack/ui
 
       - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
         continue-on-error: true

.github/workflows/providers-build.yml

@@ -26,7 +26,7 @@ on:
       - 'pyproject.toml'
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -36,7 +36,7 @@ jobs:
       distros: ${{ steps.set-matrix.outputs.distros }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Generate Distribution List
         id: set-matrix
@@ -55,7 +55,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner
@@ -79,7 +79,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner
@@ -92,7 +92,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner
@@ -106,6 +106,10 @@ jobs:
       - name: Inspect the container image entrypoint
         run: |
           IMAGE_ID=$(docker images --format "{{.Repository}}:{{.Tag}}" | head -n 1)
+          if [ -z "$IMAGE_ID" ]; then
+            echo "No image found"
+            exit 1
+          fi
           entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
           echo "Entrypoint: $entrypoint"
           if [ "$entrypoint" != "[python -m llama_stack.core.server.server /app/run.yaml]" ]; then
@@ -117,7 +121,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner
@@ -140,6 +144,10 @@ jobs:
       - name: Inspect UBI9 image
         run: |
           IMAGE_ID=$(docker images --format "{{.Repository}}:{{.Tag}}" | head -n 1)
+          if [ -z "$IMAGE_ID" ]; then
+            echo "No image found"
+            exit 1
+          fi
           entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
           echo "Entrypoint: $entrypoint"
           if [ "$entrypoint" != "[python -m llama_stack.core.server.server /app/run.yaml]" ]; then

.github/workflows/python-build-test.yml

@@ -21,10 +21,10 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
     - name: Install uv
-      uses: astral-sh/setup-uv@e92bafb6253dcd438e0484186d7669ea7a8ca1cc # v6.4.3
+      uses: astral-sh/setup-uv@d9e0f98d3fc6adb07d1e3d37f3043649ddad06a1 # v6.5.0
       with:
         python-version: ${{ matrix.python-version }}
         activate-environment: true

.github/workflows/record-integration-tests.yml

@@ -46,7 +46,7 @@ jobs:
           echo "::endgroup::"
 
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-depth: 0
 

.github/workflows/semantic-pr.yml

@@ -22,6 +22,6 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check PR Title's semantic conformance
-        uses: amannn/action-semantic-pull-request@0723387faaf9b38adef4775cd42cfd5155ed6017 # v5.5.3
+        uses: amannn/action-semantic-pull-request@7f33ba792281b034f64e96f4c0b5496782dd3b37 # v6.1.0
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-external-provider-module.yml

@@ -27,7 +27,7 @@ jobs:
         # container and point 'uv pip install' to the correct path...
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/test-external.yml

@@ -27,7 +27,7 @@ jobs:
         # container and point 'uv pip install' to the correct path...
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/ui-unit-tests.yml

@@ -13,7 +13,7 @@ on:
   workflow_dispatch:
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -26,10 +26,10 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Setup Node.js
-        uses: actions/setup-node@39370e3970a6d050c480ffad4ff0ed4d3fdee5af # v4.1.0
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
         with:
           node-version: ${{ matrix.node-version }}
           cache: 'npm'

.github/workflows/unit-tests.yml

@@ -18,7 +18,7 @@ on:
   workflow_dispatch:
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -32,7 +32,7 @@ jobs:
           - "3.13"
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.github/workflows/update-readthedocs.yml

@@ -27,7 +27,7 @@ on:
       - '.github/workflows/update-readthedocs.yml'
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
+  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -37,7 +37,7 @@ jobs:
       TOKEN: ${{ secrets.READTHEDOCS_TOKEN }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install dependencies
         uses: ./.github/actions/setup-runner

.pre-commit-config.yaml

@@ -146,31 +146,13 @@ repos:
         pass_filenames: false
         require_serial: true
         files: ^.github/workflows/.*$
-      # ui-prettier and ui-eslint are disabled until we can avoid `npm ci`, which is slow and may fail -
+      - id: ui-linter
-      #   npm error `npm ci` can only install packages when your package.json and package-lock.json or npm-shrinkwrap.json are in sync. Please update your lock file with `npm install` before continuing.
+        name: Format & Lint UI
-      #   npm error Invalid: lock file's llama-stack-client@0.2.17 does not satisfy llama-stack-client@0.2.18
+        entry: bash ./scripts/run-ui-linter.sh
-      # and until we have infra for installing prettier and next via npm -
+        language: system
-      #   Lint UI code with ESLint.....................................................Failed
+        files: ^llama_stack/ui/.*\.(ts|tsx)$
-      #   - hook id: ui-eslint
+        pass_filenames: false
-      #   - exit code: 127
+        require_serial: true
-      #   > ui@0.1.0 lint
-      #   > next lint --fix --quiet
-      #   sh: line 1: next: command not found
-      #
-      # - id: ui-prettier
-      #   name: Format UI code with Prettier
-      #   entry: bash -c 'cd llama_stack/ui && npm ci && npm run format'
-      #   language: system
-      #   files: ^llama_stack/ui/.*\.(ts|tsx)$
-      #   pass_filenames: false
-      #   require_serial: true
-      # - id: ui-eslint
-      #   name: Lint UI code with ESLint
-      #   entry: bash -c 'cd llama_stack/ui && npm run lint -- --fix --quiet'
-      #   language: system
-      #   files: ^llama_stack/ui/.*\.(ts|tsx)$
-      #   pass_filenames: false
-      #   require_serial: true
 
       - id: check-log-usage
         name: Ensure 'llama_stack.log' usage for logging

docs/_static/llama-stack-spec.html

@@ -4605,6 +4605,49 @@
                 }
             }
         },
+        "/v1/inference/rerank": {
+            "post": {
+                "responses": {
+                    "200": {
+                        "description": "RerankResponse with indices sorted by relevance score (descending).",
+                        "content": {
+                            "application/json": {
+                                "schema": {
+                                    "$ref": "#/components/schemas/RerankResponse"
+                                }
+                            }
+                        }
+                    },
+                    "400": {
+                        "$ref": "#/components/responses/BadRequest400"
+                    },
+                    "429": {
+                        "$ref": "#/components/responses/TooManyRequests429"
+                    },
+                    "500": {
+                        "$ref": "#/components/responses/InternalServerError500"
+                    },
+                    "default": {
+                        "$ref": "#/components/responses/DefaultError"
+                    }
+                },
+                "tags": [
+                    "Inference"
+                ],
+                "description": "Rerank a list of documents based on their relevance to a query.",
+                "parameters": [],
+                "requestBody": {
+                    "content": {
+                        "application/json": {
+                            "schema": {
+                                "$ref": "#/components/schemas/RerankRequest"
+                            }
+                        }
+                    },
+                    "required": true
+                }
+            }
+        },
         "/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume": {
             "post": {
                 "responses": {
@@ -16587,6 +16630,95 @@
                 ],
                 "title": "RegisterVectorDbRequest"
             },
+            "RerankRequest": {
+                "type": "object",
+                "properties": {
+                    "model": {
+                        "type": "string",
+                        "description": "The identifier of the reranking model to use."
+                    },
+                    "query": {
+                        "oneOf": [
+                            {
+                                "type": "string"
+                            },
+                            {
+                                "$ref": "#/components/schemas/OpenAIChatCompletionContentPartTextParam"
+                            },
+                            {
+                                "$ref": "#/components/schemas/OpenAIChatCompletionContentPartImageParam"
+                            }
+                        ],
+                        "description": "The search query to rank items against. Can be a string, text content part, or image content part. The input must not exceed the model's max input token length."
+                    },
+                    "items": {
+                        "type": "array",
+                        "items": {
+                            "oneOf": [
+                                {
+                                    "type": "string"
+                                },
+                                {
+                                    "$ref": "#/components/schemas/OpenAIChatCompletionContentPartTextParam"
+                                },
+                                {
+                                    "$ref": "#/components/schemas/OpenAIChatCompletionContentPartImageParam"
+                                }
+                            ]
+                        },
+                        "description": "List of items to rerank. Each item can be a string, text content part, or image content part. Each input must not exceed the model's max input token length."
+                    },
+                    "max_num_results": {
+                        "type": "integer",
+                        "description": "(Optional) Maximum number of results to return. Default: returns all."
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "model",
+                    "query",
+                    "items"
+                ],
+                "title": "RerankRequest"
+            },
+            "RerankData": {
+                "type": "object",
+                "properties": {
+                    "index": {
+                        "type": "integer",
+                        "description": "The original index of the document in the input list"
+                    },
+                    "relevance_score": {
+                        "type": "number",
+                        "description": "The relevance score from the model output. Values are inverted when applicable so that higher scores indicate greater relevance."
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "index",
+                    "relevance_score"
+                ],
+                "title": "RerankData",
+                "description": "A single rerank result from a reranking response."
+            },
+            "RerankResponse": {
+                "type": "object",
+                "properties": {
+                    "data": {
+                        "type": "array",
+                        "items": {
+                            "$ref": "#/components/schemas/RerankData"
+                        },
+                        "description": "List of rerank result objects, sorted by relevance score (descending)"
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "data"
+                ],
+                "title": "RerankResponse",
+                "description": "Response from a reranking request."
+            },
             "ResumeAgentTurnRequest": {
                 "type": "object",
                 "properties": {

docs/_static/llama-stack-spec.yaml

@@ -3264,6 +3264,37 @@ paths:
             schema:
               $ref: '#/components/schemas/QueryTracesRequest'
         required: true
+  /v1/inference/rerank:
+    post:
+      responses:
+        '200':
+          description: >-
+            RerankResponse with indices sorted by relevance score (descending).
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/RerankResponse'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Inference
+      description: >-
+        Rerank a list of documents based on their relevance to a query.
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/RerankRequest'
+        required: true
   /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume:
     post:
       responses:
@@ -12337,6 +12368,76 @@ components:
         - vector_db_id
         - embedding_model
       title: RegisterVectorDbRequest
+    RerankRequest:
+      type: object
+      properties:
+        model:
+          type: string
+          description: >-
+            The identifier of the reranking model to use.
+        query:
+          oneOf:
+            - type: string
+            - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
+            - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
+          description: >-
+            The search query to rank items against. Can be a string, text content
+            part, or image content part. The input must not exceed the model's max
+            input token length.
+        items:
+          type: array
+          items:
+            oneOf:
+              - type: string
+              - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
+              - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
+          description: >-
+            List of items to rerank. Each item can be a string, text content part,
+            or image content part. Each input must not exceed the model's max input
+            token length.
+        max_num_results:
+          type: integer
+          description: >-
+            (Optional) Maximum number of results to return. Default: returns all.
+      additionalProperties: false
+      required:
+        - model
+        - query
+        - items
+      title: RerankRequest
+    RerankData:
+      type: object
+      properties:
+        index:
+          type: integer
+          description: >-
+            The original index of the document in the input list
+        relevance_score:
+          type: number
+          description: >-
+            The relevance score from the model output. Values are inverted when applicable
+            so that higher scores indicate greater relevance.
+      additionalProperties: false
+      required:
+        - index
+        - relevance_score
+      title: RerankData
+      description: >-
+        A single rerank result from a reranking response.
+    RerankResponse:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/RerankData'
+          description: >-
+            List of rerank result objects, sorted by relevance score (descending)
+      additionalProperties: false
+      required:
+        - data
+      title: RerankResponse
+      description: Response from a reranking request.
     ResumeAgentTurnRequest:
       type: object
       properties:

docs/source/distributions/configuration.md

@@ -225,8 +225,32 @@ server:
   port: 8321  # Port to listen on (default: 8321)
   tls_certfile: "/path/to/cert.pem"  # Optional: Path to TLS certificate for HTTPS
   tls_keyfile: "/path/to/key.pem"    # Optional: Path to TLS key for HTTPS
+  cors: true  # Optional: Enable CORS (dev mode) or full config object
 ```
 
+### CORS Configuration
+
+CORS (Cross-Origin Resource Sharing) can be configured in two ways:
+
+**Local development** (allows localhost origins only):
+```yaml
+server:
+  cors: true
+```
+
+**Explicit configuration** (custom origins and settings):
+```yaml
+server:
+  cors:
+    allow_origins: ["https://myapp.com", "https://app.example.com"]
+    allow_methods: ["GET", "POST", "PUT", "DELETE"]
+    allow_headers: ["Content-Type", "Authorization"]
+    allow_credentials: true
+    max_age: 3600
+```
+
+When `cors: true`, the server enables secure localhost-only access for local development. For production, specify exact origins to maintain security.
+
 ### Authentication Configuration
 
 > **Breaking Change (v0.2.14)**: The authentication configuration structure has changed. The previous format with `provider_type` and `config` fields has been replaced with a unified `provider_config` field that includes the `type` field. Update your configuration files accordingly.
@@ -618,6 +642,54 @@ Content-Type: application/json
 }
 ```
 
+### CORS Configuration
+
+Configure CORS to allow web browsers to make requests from different domains. Disabled by default.
+
+#### Quick Setup
+
+For development, use the simple boolean flag:
+
+```yaml
+server:
+  cors: true  # Auto-enables localhost with any port
+```
+
+This automatically allows `http://localhost:*` and `https://localhost:*` with secure defaults.
+
+#### Custom Configuration
+
+For specific origins and full control:
+
+```yaml
+server:
+  cors:
+    allow_origins: ["https://myapp.com", "https://staging.myapp.com"]
+    allow_credentials: true
+    allow_methods: ["GET", "POST", "PUT", "DELETE"]
+    allow_headers: ["Content-Type", "Authorization"]
+    allow_origin_regex: "https://.*\\.example\\.com"  # Optional regex pattern
+    expose_headers: ["X-Total-Count"]
+    max_age: 86400
+```
+
+#### Configuration Options
+
+| Field                | Description                                    | Default |
+| -------------------- | ---------------------------------------------- | ------- |
+| `allow_origins`      | List of allowed origins. Use `["*"]` for any. | `["*"]` |
+| `allow_origin_regex` | Regex pattern for allowed origins (optional). | `None`  |
+| `allow_methods`      | Allowed HTTP methods.                          | `["*"]` |
+| `allow_headers`      | Allowed headers.                               | `["*"]` |
+| `allow_credentials`  | Allow credentials (cookies, auth headers).    | `false` |
+| `expose_headers`     | Headers exposed to browser.                   | `[]`    |
+| `max_age`            | Preflight cache time (seconds).               | `600`   |
+
+**Security Notes**:
+- `allow_credentials: true` requires explicit origins (no wildcards)
+- `cors: true` enables localhost access only (secure for development)
+- For public APIs, always specify exact allowed origins
+
 ## Extending to handle Safety
 
 Configuring Safety can be a little involved so it is instructive to go through an example.

docs/source/distributions/importing_as_library.md

@@ -17,7 +17,6 @@ client = LlamaStackAsLibraryClient(
     # provider_data is optional, but if you need to pass in any provider specific data, you can do so here.
     provider_data={"tavily_search_api_key": os.environ["TAVILY_SEARCH_API_KEY"]},
 )
-client.initialize()
 ```
 
 This will parse your config and set up any inline implementations and remote clients needed for your implementation.
@@ -32,5 +31,4 @@ If you've created a [custom distribution](https://llama-stack.readthedocs.io/en/
 
 ```python
 client = LlamaStackAsLibraryClient(config_path)
-client.initialize()
 ```

docs/source/providers/files/index.md

@@ -10,4 +10,5 @@ This section contains documentation for all available providers for the **files*
 :maxdepth: 1
 
 inline_localfs
+remote_s3
 ```

docs/source/providers/files/remote_s3.md

@@ -0,0 +1,33 @@
+# remote::s3
+
+## Description
+
+AWS S3-based file storage provider for scalable cloud file management with metadata persistence.
+
+## Configuration
+
+| Field | Type | Required | Default | Description |
+|-------|------|----------|---------|-------------|
+| `bucket_name` | `<class 'str'>` | No |  | S3 bucket name to store files |
+| `region` | `<class 'str'>` | No | us-east-1 | AWS region where the bucket is located |
+| `aws_access_key_id` | `str \| None` | No |  | AWS access key ID (optional if using IAM roles) |
+| `aws_secret_access_key` | `str \| None` | No |  | AWS secret access key (optional if using IAM roles) |
+| `endpoint_url` | `str \| None` | No |  | Custom S3 endpoint URL (for MinIO, LocalStack, etc.) |
+| `auto_create_bucket` | `<class 'bool'>` | No | False | Automatically create the S3 bucket if it doesn't exist |
+| `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
+
+## Sample Configuration
+
+```yaml
+bucket_name: ${env.S3_BUCKET_NAME}
+region: ${env.AWS_REGION:=us-east-1}
+aws_access_key_id: ${env.AWS_ACCESS_KEY_ID:=}
+aws_secret_access_key: ${env.AWS_SECRET_ACCESS_KEY:=}
+endpoint_url: ${env.S3_ENDPOINT_URL:=}
+auto_create_bucket: ${env.S3_AUTO_CREATE_BUCKET:=false}
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/s3_files_metadata.db
+
+```
+

llama_stack/apis/inference/inference.py

@@ -473,6 +473,28 @@ class EmbeddingsResponse(BaseModel):
     embeddings: list[list[float]]
 
 
+@json_schema_type
+class RerankData(BaseModel):
+    """A single rerank result from a reranking response.
+
+    :param index: The original index of the document in the input list
+    :param relevance_score: The relevance score from the model output. Values are inverted when applicable so that higher scores indicate greater relevance.
+    """
+
+    index: int
+    relevance_score: float
+
+
+@json_schema_type
+class RerankResponse(BaseModel):
+    """Response from a reranking request.
+
+    :param data: List of rerank result objects, sorted by relevance score (descending)
+    """
+
+    data: list[RerankData]
+
+
 @json_schema_type
 class OpenAIChatCompletionContentPartTextParam(BaseModel):
     """Text content part for OpenAI-compatible chat completion messages.
@@ -1131,6 +1153,24 @@ class InferenceProvider(Protocol):
         """
         ...
 
+    @webmethod(route="/inference/rerank", method="POST", experimental=True)
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        """Rerank a list of documents based on their relevance to a query.
+
+        :param model: The identifier of the reranking model to use.
+        :param query: The search query to rank items against. Can be a string, text content part, or image content part. The input must not exceed the model's max input token length.
+        :param items: List of items to rerank. Each item can be a string, text content part, or image content part. Each input must not exceed the model's max input token length.
+        :param max_num_results: (Optional) Maximum number of results to return. Default: returns all.
+        :returns: RerankResponse with indices sorted by relevance score (descending).
+        """
+        raise NotImplementedError("Reranking is not implemented")
+
     @webmethod(route="/openai/v1/completions", method="POST")
     async def openai_completion(
         self,

llama_stack/cli/stack/run.py

@@ -15,7 +15,7 @@ from llama_stack.log import get_logger
 
 REPO_ROOT = Path(__file__).parent.parent.parent.parent
 
-logger = get_logger(name=__name__, category="server")
+logger = get_logger(name=__name__, category="cli")
 
 
 class StackRun(Subcommand):

llama_stack/core/datatypes.py

@@ -318,6 +318,41 @@ class QuotaConfig(BaseModel):
     period: QuotaPeriod = Field(default=QuotaPeriod.DAY, description="Quota period to set")
 
 
+class CORSConfig(BaseModel):
+    allow_origins: list[str] = Field(default_factory=list)
+    allow_origin_regex: str | None = Field(default=None)
+    allow_methods: list[str] = Field(default=["OPTIONS"])
+    allow_headers: list[str] = Field(default_factory=list)
+    allow_credentials: bool = Field(default=False)
+    expose_headers: list[str] = Field(default_factory=list)
+    max_age: int = Field(default=600, ge=0)
+
+    @model_validator(mode="after")
+    def validate_credentials_config(self) -> Self:
+        if self.allow_credentials and (self.allow_origins == ["*"] or "*" in self.allow_origins):
+            raise ValueError("Cannot use wildcard origins with credentials enabled")
+        return self
+
+
+def process_cors_config(cors_config: bool | CORSConfig | None) -> CORSConfig | None:
+    if cors_config is False or cors_config is None:
+        return None
+
+    if cors_config is True:
+        # dev mode: allow localhost on any port
+        return CORSConfig(
+            allow_origins=[],
+            allow_origin_regex=r"https?://localhost:\d+",
+            allow_methods=["GET", "POST", "PUT", "DELETE", "OPTIONS"],
+            allow_headers=["Content-Type", "Authorization", "X-Requested-With"],
+        )
+
+    if isinstance(cors_config, CORSConfig):
+        return cors_config
+
+    raise ValueError(f"Expected bool or CORSConfig, got {type(cors_config).__name__}")
+
+
 class ServerConfig(BaseModel):
     port: int = Field(
         default=8321,
@@ -349,6 +384,12 @@ class ServerConfig(BaseModel):
         default=None,
         description="Per client quota request configuration",
     )
+    cors: bool | CORSConfig | None = Field(
+        default=None,
+        description="CORS configuration for cross-origin requests. Can be:\n"
+        "- true: Enable localhost CORS for development\n"
+        "- {allow_origins: [...], allow_methods: [...], ...}: Full configuration",
+    )
 
 
 class StackRunConfig(BaseModel):

llama_stack/core/library_client.py

@@ -146,39 +146,26 @@ class LlamaStackAsLibraryClient(LlamaStackClient):
     ):
         super().__init__()
         self.async_client = AsyncLlamaStackAsLibraryClient(
-            config_path_or_distro_name, custom_provider_registry, provider_data
+            config_path_or_distro_name, custom_provider_registry, provider_data, skip_logger_removal
         )
         self.pool_executor = ThreadPoolExecutor(max_workers=4)
-        self.skip_logger_removal = skip_logger_removal
         self.provider_data = provider_data
 
         self.loop = asyncio.new_event_loop()
 
-    def initialize(self):
-        if in_notebook():
-            import nest_asyncio
-
-            nest_asyncio.apply()
-            if not self.skip_logger_removal:
-                self._remove_root_logger_handlers()
-
         # use a new event loop to avoid interfering with the main event loop
         loop = asyncio.new_event_loop()
         asyncio.set_event_loop(loop)
         try:
-            return loop.run_until_complete(self.async_client.initialize())
+            loop.run_until_complete(self.async_client.initialize())
         finally:
             asyncio.set_event_loop(None)
 
-    def _remove_root_logger_handlers(self):
+    def initialize(self):
         """
-        Remove all handlers from the root logger. Needed to avoid polluting the console with logs.
+        Deprecated method for backward compatibility.
         """
-        root_logger = logging.getLogger()
+        pass
-
-        for handler in root_logger.handlers[:]:
-            root_logger.removeHandler(handler)
-            logger.info(f"Removed handler {handler.__class__.__name__} from root logger")
 
     def request(self, *args, **kwargs):
         loop = self.loop
@@ -216,6 +203,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
         config_path_or_distro_name: str,
         custom_provider_registry: ProviderRegistry | None = None,
         provider_data: dict[str, Any] | None = None,
+        skip_logger_removal: bool = False,
     ):
         super().__init__()
         # when using the library client, we should not log to console since many
@@ -223,6 +211,13 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
         current_sinks = os.environ.get("TELEMETRY_SINKS", "sqlite").split(",")
         os.environ["TELEMETRY_SINKS"] = ",".join(sink for sink in current_sinks if sink != "console")
 
+        if in_notebook():
+            import nest_asyncio
+
+            nest_asyncio.apply()
+            if not skip_logger_removal:
+                self._remove_root_logger_handlers()
+
         if config_path_or_distro_name.endswith(".yaml"):
             config_path = Path(config_path_or_distro_name)
             if not config_path.exists():
@@ -239,7 +234,24 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
         self.provider_data = provider_data
         self.route_impls: RouteImpls | None = None  # Initialize to None to prevent AttributeError
 
+    def _remove_root_logger_handlers(self):
+        """
+        Remove all handlers from the root logger. Needed to avoid polluting the console with logs.
+        """
+        root_logger = logging.getLogger()
+
+        for handler in root_logger.handlers[:]:
+            root_logger.removeHandler(handler)
+            logger.info(f"Removed handler {handler.__class__.__name__} from root logger")
+
     async def initialize(self) -> bool:
+        """
+        Initialize the async client.
+
+        Returns:
+            bool: True if initialization was successful
+        """
+
         try:
             self.route_impls = None
             self.impls = await construct_stack(self.config, self.custom_provider_registry)

llama_stack/core/routers/datasets.py

@@ -12,7 +12,7 @@ from llama_stack.apis.datasets import DatasetPurpose, DataSource
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import RoutingTable
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routers")
 
 
 class DatasetIORouter(DatasetIO):

llama_stack/core/routers/eval_scoring.py

@@ -16,7 +16,7 @@ from llama_stack.apis.scoring import (
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import RoutingTable
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routers")
 
 
 class ScoringRouter(Scoring):

llama_stack/core/routers/inference.py

@@ -65,7 +65,7 @@ from llama_stack.providers.datatypes import HealthResponse, HealthStatus, Routin
 from llama_stack.providers.utils.inference.inference_store import InferenceStore
 from llama_stack.providers.utils.telemetry.tracing import get_current_span
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="core::routers")
 
 
 class InferenceRouter(Inference):

llama_stack/core/routers/safety.py

@@ -13,7 +13,7 @@ from llama_stack.apis.shields import Shield
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import RoutingTable
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routers")
 
 
 class SafetyRouter(Safety):

llama_stack/core/routers/tool_runtime.py

@@ -22,7 +22,7 @@ from llama_stack.log import get_logger
 
 from ..routing_tables.toolgroups import ToolGroupsRoutingTable
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routers")
 
 
 class ToolRuntimeRouter(ToolRuntime):

llama_stack/core/routers/vector_io.py

@@ -30,7 +30,7 @@ from llama_stack.apis.vector_io import (
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import HealthResponse, HealthStatus, RoutingTable
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routers")
 
 
 class VectorIORouter(VectorIO):

llama_stack/core/routing_tables/benchmarks.py

@@ -14,7 +14,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 class BenchmarksRoutingTable(CommonRoutingTableImpl, Benchmarks):

llama_stack/core/routing_tables/common.py

@@ -23,7 +23,7 @@ from llama_stack.core.store import DistributionRegistry
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, RoutingTable
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 def get_impl_api(p: Any) -> Api:

llama_stack/core/routing_tables/datasets.py

@@ -26,7 +26,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):

llama_stack/core/routing_tables/models.py

@@ -17,7 +17,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl, lookup_model
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 class ModelsRoutingTable(CommonRoutingTableImpl, Models):

llama_stack/core/routing_tables/scoring_functions.py

@@ -19,7 +19,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 class ScoringFunctionsRoutingTable(CommonRoutingTableImpl, ScoringFunctions):

llama_stack/core/routing_tables/shields.py

@@ -15,7 +15,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 class ShieldsRoutingTable(CommonRoutingTableImpl, Shields):

llama_stack/core/routing_tables/toolgroups.py

@@ -14,7 +14,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 def parse_toolgroup_from_toolgroup_name_pair(toolgroup_name_with_maybe_tool_name: str) -> str | None:

llama_stack/core/routing_tables/vector_dbs.py

@@ -30,7 +30,7 @@ from llama_stack.log import get_logger
 
 from .common import CommonRoutingTableImpl, lookup_model
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="core::routing_tables")
 
 
 class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):

llama_stack/core/server/auth.py

@@ -15,7 +15,7 @@ from llama_stack.core.server.auth_providers import create_auth_provider
 from llama_stack.core.server.routes import find_matching_route, initialize_route_impls
 from llama_stack.log import get_logger
 
-logger = get_logger(name=__name__, category="auth")
+logger = get_logger(name=__name__, category="core::auth")
 
 
 class AuthenticationMiddleware:

llama_stack/core/server/auth_providers.py

@@ -23,7 +23,7 @@ from llama_stack.core.datatypes import (
 )
 from llama_stack.log import get_logger
 
-logger = get_logger(name=__name__, category="auth")
+logger = get_logger(name=__name__, category="core::auth")
 
 
 class AuthResponse(BaseModel):

llama_stack/core/server/quota.py

@@ -15,7 +15,7 @@ from llama_stack.providers.utils.kvstore.api import KVStore
 from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
 from llama_stack.providers.utils.kvstore.kvstore import kvstore_impl
 
-logger = get_logger(name=__name__, category="quota")
+logger = get_logger(name=__name__, category="core::server")
 
 
 class QuotaMiddleware:

llama_stack/core/server/server.py

@@ -28,6 +28,7 @@ from aiohttp import hdrs
 from fastapi import Body, FastAPI, HTTPException, Request, Response
 from fastapi import Path as FastapiPath
 from fastapi.exceptions import RequestValidationError
+from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse, StreamingResponse
 from openai import BadRequestError
 from pydantic import BaseModel, ValidationError
@@ -40,6 +41,7 @@ from llama_stack.core.datatypes import (
     AuthenticationRequiredError,
     LoggingConfig,
     StackRunConfig,
+    process_cors_config,
 )
 from llama_stack.core.distribution import builtin_automatically_routed_apis
 from llama_stack.core.external import ExternalApiSpec, load_external_apis
@@ -82,7 +84,7 @@ from .quota import QuotaMiddleware
 
 REPO_ROOT = Path(__file__).parent.parent.parent.parent
 
-logger = get_logger(name=__name__, category="server")
+logger = get_logger(name=__name__, category="core::server")
 
 
 def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
@@ -413,7 +415,7 @@ def main(args: argparse.Namespace | None = None):
         config_contents = yaml.safe_load(fp)
         if isinstance(config_contents, dict) and (cfg := config_contents.get("logging_config")):
             logger_config = LoggingConfig(**cfg)
-        logger = get_logger(name=__name__, category="server", config=logger_config)
+        logger = get_logger(name=__name__, category="core::server", config=logger_config)
         if args.env:
             for env_pair in args.env:
                 try:
@@ -483,6 +485,12 @@ def main(args: argparse.Namespace | None = None):
             window_seconds=window_seconds,
         )
 
+    if config.server.cors:
+        logger.info("Enabling CORS")
+        cors_config = process_cors_config(config.server.cors)
+        if cors_config:
+            app.add_middleware(CORSMiddleware, **cors_config.model_dump())
+
     if Api.telemetry in impls:
         setup_logger(impls[Api.telemetry])
     else:

llama_stack/core/store/registry.py

@@ -16,7 +16,7 @@ from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
 from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
 
-logger = get_logger(__name__, category="core")
+logger = get_logger(__name__, category="core::registry")
 
 
 class DistributionRegistry(Protocol):

llama_stack/core/utils/config_resolution.py

@@ -10,7 +10,7 @@ from pathlib import Path
 from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR
 from llama_stack.log import get_logger
 
-logger = get_logger(name=__name__, category="config_resolution")
+logger = get_logger(name=__name__, category="core")
 
 
 DISTRO_DIR = Path(__file__).parent.parent.parent.parent / "llama_stack" / "distributions"

llama_stack/models/llama/llama3/multimodal/model.py

@@ -36,7 +36,7 @@ from .utils import get_negative_inf_value, to_2tuple
 
 MP_SCALE = 8
 
-logger = get_logger(name=__name__, category="models")
+logger = get_logger(name=__name__, category="models::llama")
 
 
 def reduce_from_tensor_model_parallel_region(input_):

llama_stack/models/llama/llama3/tool_utils.py

@@ -11,7 +11,7 @@ from llama_stack.log import get_logger
 
 from ..datatypes import BuiltinTool, RecursiveType, ToolCall, ToolPromptFormat
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="models::llama")
 
 BUILTIN_TOOL_PATTERN = r'\b(?P<tool_name>\w+)\.call\(query="(?P<query>[^"]*)"\)'
 CUSTOM_TOOL_CALL_PATTERN = re.compile(r"<function=(?P<function_name>[^}]+)>(?P<args>{.*?})")

llama_stack/models/llama/llama4/quantization/loader.py

@@ -18,7 +18,7 @@ from ...datatypes import QuantizationMode
 from ..model import Transformer, TransformerBlock
 from ..moe import MoE
 
-log = get_logger(name=__name__, category="models")
+log = get_logger(name=__name__, category="models::llama")
 
 
 def swiglu_wrapper_no_reduce(

llama_stack/models/llama/quantize_impls.py

@@ -9,7 +9,7 @@ import collections
 
 from llama_stack.log import get_logger
 
-log = get_logger(name=__name__, category="llama")
+log = get_logger(name=__name__, category="models::llama")
 
 try:
     import fbgemm_gpu.experimental.gen_ai  # noqa: F401

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -84,7 +84,7 @@ MEMORY_QUERY_TOOL = "knowledge_search"
 WEB_SEARCH_TOOL = "web_search"
 RAG_TOOL_GROUP = "builtin::rag"
 
-logger = get_logger(name=__name__, category="agents")
+logger = get_logger(name=__name__, category="agents::meta_reference")
 
 
 class ChatAgent(ShieldRunnerMixin):

llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -51,7 +51,7 @@ from .config import MetaReferenceAgentsImplConfig
 from .persistence import AgentInfo
 from .responses.openai_responses import OpenAIResponsesImpl
 
-logger = get_logger(name=__name__, category="agents")
+logger = get_logger(name=__name__, category="agents::meta_reference")
 
 
 class MetaReferenceAgentsImpl(Agents):

llama_stack/providers/inline/agents/meta_reference/persistence.py

@@ -17,7 +17,7 @@ from llama_stack.core.request_headers import get_authenticated_user
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import KVStore
 
-log = get_logger(name=__name__, category="agents")
+log = get_logger(name=__name__, category="agents::meta_reference")
 
 
 class AgentSessionInfo(Session):

llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py

@@ -41,7 +41,7 @@ from .utils import (
     convert_response_text_to_chat_response_format,
 )
 
-logger = get_logger(name=__name__, category="responses")
+logger = get_logger(name=__name__, category="openai::responses")
 
 
 class OpenAIResponsePreviousResponseWithInputItems(BaseModel):

llama_stack/providers/inline/agents/meta_reference/responses/streaming.py

@@ -47,7 +47,7 @@ from llama_stack.log import get_logger
 from .types import ChatCompletionContext, ChatCompletionResult
 from .utils import convert_chat_choice_to_response_message, is_function_tool_call
 
-logger = get_logger(name=__name__, category="responses")
+logger = get_logger(name=__name__, category="agents::meta_reference")
 
 
 class StreamingResponseOrchestrator:

llama_stack/providers/inline/agents/meta_reference/responses/tool_executor.py

@@ -38,7 +38,7 @@ from llama_stack.log import get_logger
 
 from .types import ChatCompletionContext, ToolExecutionResult
 
-logger = get_logger(name=__name__, category="responses")
+logger = get_logger(name=__name__, category="agents::meta_reference")
 
 
 class ToolExecutor:

llama_stack/providers/inline/agents/meta_reference/responses/utils.py

@@ -17,6 +17,8 @@ from llama_stack.apis.agents.openai_responses import (
     OpenAIResponseOutputMessageContent,
     OpenAIResponseOutputMessageContentOutputText,
     OpenAIResponseOutputMessageFunctionToolCall,
+    OpenAIResponseOutputMessageMCPCall,
+    OpenAIResponseOutputMessageMCPListTools,
     OpenAIResponseText,
 )
 from llama_stack.apis.inference import (
@@ -99,14 +101,22 @@ async def convert_response_input_to_chat_messages(
     """
     messages: list[OpenAIMessageParam] = []
     if isinstance(input, list):
+        # extract all OpenAIResponseInputFunctionToolCallOutput items
+        # so their corresponding OpenAIToolMessageParam instances can
+        # be added immediately following the corresponding
+        # OpenAIAssistantMessageParam
+        tool_call_results = {}
         for input_item in input:
             if isinstance(input_item, OpenAIResponseInputFunctionToolCallOutput):
-                messages.append(
+                tool_call_results[input_item.call_id] = OpenAIToolMessageParam(
-                    OpenAIToolMessageParam(
+                    content=input_item.output,
-                        content=input_item.output,
+                    tool_call_id=input_item.call_id,
-                        tool_call_id=input_item.call_id,
-                    )
                 )
+
+        for input_item in input:
+            if isinstance(input_item, OpenAIResponseInputFunctionToolCallOutput):
+                # skip as these have been extracted and inserted in order
+                pass
             elif isinstance(input_item, OpenAIResponseOutputMessageFunctionToolCall):
                 tool_call = OpenAIChatCompletionToolCall(
                     index=0,
@@ -117,6 +127,28 @@ async def convert_response_input_to_chat_messages(
                     ),
                 )
                 messages.append(OpenAIAssistantMessageParam(tool_calls=[tool_call]))
+                if input_item.call_id in tool_call_results:
+                    messages.append(tool_call_results[input_item.call_id])
+                    del tool_call_results[input_item.call_id]
+            elif isinstance(input_item, OpenAIResponseOutputMessageMCPCall):
+                tool_call = OpenAIChatCompletionToolCall(
+                    index=0,
+                    id=input_item.id,
+                    function=OpenAIChatCompletionToolCallFunction(
+                        name=input_item.name,
+                        arguments=input_item.arguments,
+                    ),
+                )
+                messages.append(OpenAIAssistantMessageParam(tool_calls=[tool_call]))
+                messages.append(
+                    OpenAIToolMessageParam(
+                        content=input_item.output,
+                        tool_call_id=input_item.id,
+                    )
+                )
+            elif isinstance(input_item, OpenAIResponseOutputMessageMCPListTools):
+                # the tool list will be handled separately
+                pass
             else:
                 content = await convert_response_content_to_chat_content(input_item.content)
                 message_type = await get_message_type_by_role(input_item.role)
@@ -125,6 +157,10 @@ async def convert_response_input_to_chat_messages(
                         f"Llama Stack OpenAI Responses does not yet support message role '{input_item.role}' in this context"
                     )
                 messages.append(message_type(content=content))
+        if len(tool_call_results):
+            raise ValueError(
+                f"Received function_call_output(s) with call_id(s) {tool_call_results.keys()}, but no corresponding function_call"
+            )
     else:
         messages.append(OpenAIUserMessageParam(content=input))
     return messages

llama_stack/providers/inline/agents/meta_reference/safety.py

@@ -11,7 +11,7 @@ from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.telemetry import tracing
 
-log = get_logger(name=__name__, category="agents")
+log = get_logger(name=__name__, category="agents::meta_reference")
 
 
 class SafetyException(Exception):  # noqa: N818

llama_stack/providers/inline/inference/meta_reference/inference.py

@@ -33,6 +33,9 @@ from llama_stack.apis.inference import (
     InterleavedContent,
     LogProbConfig,
     Message,
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
+    RerankResponse,
     ResponseFormat,
     SamplingParams,
     StopReason,
@@ -442,6 +445,15 @@ class MetaReferenceInferenceImpl(
         results = await self._nonstream_chat_completion(request_batch)
         return BatchChatCompletionResponse(batch=results)
 
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Meta Reference")
+
     async def _nonstream_chat_completion(
         self, request_batch: list[ChatCompletionRequest]
     ) -> list[ChatCompletionResponse]:

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -12,6 +12,9 @@ from llama_stack.apis.inference import (
     InterleavedContent,
     LogProbConfig,
     Message,
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
+    RerankResponse,
     ResponseFormat,
     SamplingParams,
     ToolChoice,
@@ -122,3 +125,12 @@ class SentenceTransformersInferenceImpl(
         logprobs: LogProbConfig | None = None,
     ):
         raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")
+
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Sentence Transformers")

llama_stack/providers/registry/files.py

@@ -5,9 +5,11 @@
 # the root directory of this source tree.
 
 from llama_stack.providers.datatypes import (
+    AdapterSpec,
     Api,
     InlineProviderSpec,
     ProviderSpec,
+    remote_provider_spec,
 )
 from llama_stack.providers.utils.sqlstore.sqlstore import sql_store_pip_packages
 
@@ -23,4 +25,14 @@ def available_providers() -> list[ProviderSpec]:
             config_class="llama_stack.providers.inline.files.localfs.config.LocalfsFilesImplConfig",
             description="Local filesystem-based file storage provider for managing files and documents locally.",
         ),
+        remote_provider_spec(
+            api=Api.files,
+            adapter=AdapterSpec(
+                adapter_type="s3",
+                pip_packages=["boto3"] + sql_store_pip_packages,
+                module="llama_stack.providers.remote.files.s3",
+                config_class="llama_stack.providers.remote.files.s3.config.S3FilesImplConfig",
+                description="AWS S3-based file storage provider for scalable cloud file management with metadata persistence.",
+            ),
+        ),
     ]

llama_stack/providers/remote/files/s3/README.md

@@ -0,0 +1,237 @@
+# S3 Files Provider
+
+A remote S3-based implementation of the Llama Stack Files API that provides scalable cloud file storage with metadata persistence.
+
+## Features
+
+- **AWS S3 Storage**: Store files in AWS S3 buckets for scalable, durable storage
+- **Metadata Management**: Uses SQL database for efficient file metadata queries
+- **OpenAI API Compatibility**: Full compatibility with OpenAI Files API endpoints
+- **Flexible Authentication**: Support for IAM roles and access keys
+- **Custom S3 Endpoints**: Support for MinIO and other S3-compatible services
+
+## Configuration
+
+### Basic Configuration
+
+```yaml
+api: files
+provider_type: remote::s3
+config:
+  bucket_name: my-llama-stack-files
+  region: us-east-1
+  metadata_store:
+    type: sqlite
+    db_path: ./s3_files_metadata.db
+```
+
+### Advanced Configuration
+
+```yaml
+api: files
+provider_type: remote::s3
+config:
+  bucket_name: my-llama-stack-files
+  region: us-east-1
+  aws_access_key_id: YOUR_ACCESS_KEY
+  aws_secret_access_key: YOUR_SECRET_KEY
+  endpoint_url: https://s3.amazonaws.com  # Optional for custom endpoints
+  metadata_store:
+    type: sqlite
+    db_path: ./s3_files_metadata.db
+```
+
+### Environment Variables
+
+The configuration supports environment variable substitution:
+
+```yaml
+config:
+  bucket_name: "${env.S3_BUCKET_NAME}"
+  region: "${env.AWS_REGION:=us-east-1}"
+  aws_access_key_id: "${env.AWS_ACCESS_KEY_ID:=}"
+  aws_secret_access_key: "${env.AWS_SECRET_ACCESS_KEY:=}"
+  endpoint_url: "${env.S3_ENDPOINT_URL:=}"
+```
+
+Note: `S3_BUCKET_NAME` has no default value since S3 bucket names must be globally unique.
+
+## Authentication
+
+### IAM Roles (Recommended)
+
+For production deployments, use IAM roles:
+
+```yaml
+config:
+  bucket_name: my-bucket
+  region: us-east-1
+  # No credentials needed - will use IAM role
+```
+
+### Access Keys
+
+For development or specific use cases:
+
+```yaml
+config:
+  bucket_name: my-bucket
+  region: us-east-1
+  aws_access_key_id: AKIAIOSFODNN7EXAMPLE
+  aws_secret_access_key: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
+```
+
+## S3 Bucket Setup
+
+### Required Permissions
+
+The S3 provider requires the following permissions:
+
+```json
+{
+  "Version": "2012-10-17",
+  "Statement": [
+    {
+      "Effect": "Allow",
+      "Action": [
+        "s3:GetObject",
+        "s3:PutObject",
+        "s3:DeleteObject",
+        "s3:ListBucket"
+      ],
+      "Resource": [
+        "arn:aws:s3:::your-bucket-name",
+        "arn:aws:s3:::your-bucket-name/*"
+      ]
+    }
+  ]
+}
+```
+
+### Automatic Bucket Creation
+
+By default, the S3 provider expects the bucket to already exist. If you want the provider to automatically create the bucket when it doesn't exist, set `auto_create_bucket: true` in your configuration:
+
+```yaml
+config:
+  bucket_name: my-bucket
+  auto_create_bucket: true  # Will create bucket if it doesn't exist
+  region: us-east-1
+```
+
+**Note**: When `auto_create_bucket` is enabled, the provider will need additional permissions:
+
+```json
+{
+  "Version": "2012-10-17",
+  "Statement": [
+    {
+      "Effect": "Allow",
+      "Action": [
+        "s3:GetObject",
+        "s3:PutObject",
+        "s3:DeleteObject",
+        "s3:ListBucket",
+        "s3:CreateBucket"
+      ],
+      "Resource": [
+        "arn:aws:s3:::your-bucket-name",
+        "arn:aws:s3:::your-bucket-name/*"
+      ]
+    }
+  ]
+}
+```
+
+### Bucket Policy (Optional)
+
+For additional security, you can add a bucket policy:
+
+```json
+{
+  "Version": "2012-10-17",
+  "Statement": [
+    {
+      "Sid": "LlamaStackAccess",
+      "Effect": "Allow",
+      "Principal": {
+        "AWS": "arn:aws:iam::YOUR-ACCOUNT:role/LlamaStackRole"
+      },
+      "Action": [
+        "s3:GetObject",
+        "s3:PutObject",
+        "s3:DeleteObject"
+      ],
+      "Resource": "arn:aws:s3:::your-bucket-name/*"
+    },
+    {
+      "Sid": "LlamaStackBucketAccess",
+      "Effect": "Allow",
+      "Principal": {
+        "AWS": "arn:aws:iam::YOUR-ACCOUNT:role/LlamaStackRole"
+      },
+      "Action": [
+        "s3:ListBucket"
+      ],
+      "Resource": "arn:aws:s3:::your-bucket-name"
+    }
+  ]
+}
+```
+
+## Features
+
+### Metadata Persistence
+
+File metadata is stored in a SQL database for fast queries and OpenAI API compatibility. The metadata includes:
+
+- File ID
+- Original filename
+- Purpose (assistants, batch, etc.)
+- File size in bytes
+- Created and expiration timestamps
+
+### TTL and Cleanup
+
+Files currently have a fixed long expiration time (100 years).
+
+## Development and Testing
+
+### Using MinIO
+
+For self-hosted S3-compatible storage:
+
+```yaml
+config:
+  bucket_name: test-bucket
+  region: us-east-1
+  endpoint_url: http://localhost:9000
+  aws_access_key_id: minioadmin
+  aws_secret_access_key: minioadmin
+```
+
+## Monitoring and Logging
+
+The provider logs important operations and errors. For production deployments, consider:
+
+- CloudWatch monitoring for S3 operations
+- Custom metrics for file upload/download rates
+- Error rate monitoring
+- Performance metrics tracking
+
+## Error Handling
+
+The provider handles various error scenarios:
+
+- S3 connectivity issues
+- Bucket access permissions
+- File not found errors
+- Metadata consistency checks
+
+## Known Limitations
+
+- Fixed long TTL (100 years) instead of configurable expiration
+- No server-side encryption enabled by default
+- No support for AWS session tokens
+- No S3 key prefix organization support
+- No multipart upload support (all files uploaded as single objects)

llama_stack/providers/remote/files/s3/__init__.py

@@ -0,0 +1,20 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Any
+
+from llama_stack.core.datatypes import Api
+
+from .config import S3FilesImplConfig
+
+
+async def get_adapter_impl(config: S3FilesImplConfig, deps: dict[Api, Any]):
+    from .files import S3FilesImpl
+
+    # TODO: authorization policies and user separation
+    impl = S3FilesImpl(config)
+    await impl.initialize()
+    return impl

llama_stack/providers/remote/files/s3/config.py

@@ -0,0 +1,42 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig, SqlStoreConfig
+
+
+class S3FilesImplConfig(BaseModel):
+    """Configuration for S3-based files provider."""
+
+    bucket_name: str = Field(description="S3 bucket name to store files")
+    region: str = Field(default="us-east-1", description="AWS region where the bucket is located")
+    aws_access_key_id: str | None = Field(default=None, description="AWS access key ID (optional if using IAM roles)")
+    aws_secret_access_key: str | None = Field(
+        default=None, description="AWS secret access key (optional if using IAM roles)"
+    )
+    endpoint_url: str | None = Field(default=None, description="Custom S3 endpoint URL (for MinIO, LocalStack, etc.)")
+    auto_create_bucket: bool = Field(
+        default=False, description="Automatically create the S3 bucket if it doesn't exist"
+    )
+    metadata_store: SqlStoreConfig = Field(description="SQL store configuration for file metadata")
+
+    @classmethod
+    def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
+        return {
+            "bucket_name": "${env.S3_BUCKET_NAME}",  # no default, buckets must be globally unique
+            "region": "${env.AWS_REGION:=us-east-1}",
+            "aws_access_key_id": "${env.AWS_ACCESS_KEY_ID:=}",
+            "aws_secret_access_key": "${env.AWS_SECRET_ACCESS_KEY:=}",
+            "endpoint_url": "${env.S3_ENDPOINT_URL:=}",
+            "auto_create_bucket": "${env.S3_AUTO_CREATE_BUCKET:=false}",
+            "metadata_store": SqliteSqlStoreConfig.sample_run_config(
+                __distro_dir__=__distro_dir__,
+                db_name="s3_files_metadata.db",
+            ),
+        }

llama_stack/providers/remote/files/s3/files.py

@@ -0,0 +1,272 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import time
+import uuid
+from typing import Annotated
+
+import boto3
+from botocore.exceptions import BotoCoreError, ClientError, NoCredentialsError
+from fastapi import File, Form, Response, UploadFile
+
+from llama_stack.apis.common.errors import ResourceNotFoundError
+from llama_stack.apis.common.responses import Order
+from llama_stack.apis.files import (
+    Files,
+    ListOpenAIFileResponse,
+    OpenAIFileDeleteResponse,
+    OpenAIFileObject,
+    OpenAIFilePurpose,
+)
+from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
+from llama_stack.providers.utils.sqlstore.sqlstore import SqlStore, sqlstore_impl
+
+from .config import S3FilesImplConfig
+
+# TODO: provider data for S3 credentials
+
+
+def _create_s3_client(config: S3FilesImplConfig) -> boto3.client:
+    try:
+        s3_config = {
+            "region_name": config.region,
+        }
+
+        # endpoint URL if specified (for MinIO, LocalStack, etc.)
+        if config.endpoint_url:
+            s3_config["endpoint_url"] = config.endpoint_url
+
+        if config.aws_access_key_id and config.aws_secret_access_key:
+            s3_config.update(
+                {
+                    "aws_access_key_id": config.aws_access_key_id,
+                    "aws_secret_access_key": config.aws_secret_access_key,
+                }
+            )
+
+        return boto3.client("s3", **s3_config)
+
+    except (BotoCoreError, NoCredentialsError) as e:
+        raise RuntimeError(f"Failed to initialize S3 client: {e}") from e
+
+
+async def _create_bucket_if_not_exists(client: boto3.client, config: S3FilesImplConfig) -> None:
+    try:
+        client.head_bucket(Bucket=config.bucket_name)
+    except ClientError as e:
+        error_code = e.response["Error"]["Code"]
+        if error_code == "404":
+            if not config.auto_create_bucket:
+                raise RuntimeError(
+                    f"S3 bucket '{config.bucket_name}' does not exist. "
+                    f"Either create the bucket manually or set 'auto_create_bucket: true' in your configuration."
+                ) from e
+            try:
+                # For us-east-1, we can't specify LocationConstraint
+                if config.region == "us-east-1":
+                    client.create_bucket(Bucket=config.bucket_name)
+                else:
+                    client.create_bucket(
+                        Bucket=config.bucket_name,
+                        CreateBucketConfiguration={"LocationConstraint": config.region},
+                    )
+            except ClientError as create_error:
+                raise RuntimeError(
+                    f"Failed to create S3 bucket '{config.bucket_name}': {create_error}"
+                ) from create_error
+        elif error_code == "403":
+            raise RuntimeError(f"Access denied to S3 bucket '{config.bucket_name}'") from e
+        else:
+            raise RuntimeError(f"Failed to access S3 bucket '{config.bucket_name}': {e}") from e
+
+
+class S3FilesImpl(Files):
+    """S3-based implementation of the Files API."""
+
+    # TODO: implement expiration, for now a silly offset
+    _SILLY_EXPIRATION_OFFSET = 100 * 365 * 24 * 60 * 60
+
+    def __init__(self, config: S3FilesImplConfig) -> None:
+        self._config = config
+        self._client: boto3.client | None = None
+        self._sql_store: SqlStore | None = None
+
+    async def initialize(self) -> None:
+        self._client = _create_s3_client(self._config)
+        await _create_bucket_if_not_exists(self._client, self._config)
+
+        self._sql_store = sqlstore_impl(self._config.metadata_store)
+        await self._sql_store.create_table(
+            "openai_files",
+            {
+                "id": ColumnDefinition(type=ColumnType.STRING, primary_key=True),
+                "filename": ColumnType.STRING,
+                "purpose": ColumnType.STRING,
+                "bytes": ColumnType.INTEGER,
+                "created_at": ColumnType.INTEGER,
+                "expires_at": ColumnType.INTEGER,
+                # TODO: add s3_etag field for integrity checking
+            },
+        )
+
+    async def shutdown(self) -> None:
+        pass
+
+    @property
+    def client(self) -> boto3.client:
+        assert self._client is not None, "Provider not initialized"
+        return self._client
+
+    @property
+    def sql_store(self) -> SqlStore:
+        assert self._sql_store is not None, "Provider not initialized"
+        return self._sql_store
+
+    async def openai_upload_file(
+        self,
+        file: Annotated[UploadFile, File()],
+        purpose: Annotated[OpenAIFilePurpose, Form()],
+    ) -> OpenAIFileObject:
+        file_id = f"file-{uuid.uuid4().hex}"
+
+        filename = getattr(file, "filename", None) or "uploaded_file"
+
+        created_at = int(time.time())
+        expires_at = created_at + self._SILLY_EXPIRATION_OFFSET
+        content = await file.read()
+        file_size = len(content)
+
+        await self.sql_store.insert(
+            "openai_files",
+            {
+                "id": file_id,
+                "filename": filename,
+                "purpose": purpose.value,
+                "bytes": file_size,
+                "created_at": created_at,
+                "expires_at": expires_at,
+            },
+        )
+
+        try:
+            self.client.put_object(
+                Bucket=self._config.bucket_name,
+                Key=file_id,
+                Body=content,
+                # TODO: enable server-side encryption
+            )
+        except ClientError as e:
+            await self.sql_store.delete("openai_files", where={"id": file_id})
+
+            raise RuntimeError(f"Failed to upload file to S3: {e}") from e
+
+        return OpenAIFileObject(
+            id=file_id,
+            filename=filename,
+            purpose=purpose,
+            bytes=file_size,
+            created_at=created_at,
+            expires_at=expires_at,
+        )
+
+    async def openai_list_files(
+        self,
+        after: str | None = None,
+        limit: int | None = 10000,
+        order: Order | None = Order.desc,
+        purpose: OpenAIFilePurpose | None = None,
+    ) -> ListOpenAIFileResponse:
+        # this purely defensive. it should not happen because the router also default to Order.desc.
+        if not order:
+            order = Order.desc
+
+        where_conditions = {}
+        if purpose:
+            where_conditions["purpose"] = purpose.value
+
+        paginated_result = await self.sql_store.fetch_all(
+            table="openai_files",
+            where=where_conditions if where_conditions else None,
+            order_by=[("created_at", order.value)],
+            cursor=("id", after) if after else None,
+            limit=limit,
+        )
+
+        files = [
+            OpenAIFileObject(
+                id=row["id"],
+                filename=row["filename"],
+                purpose=OpenAIFilePurpose(row["purpose"]),
+                bytes=row["bytes"],
+                created_at=row["created_at"],
+                expires_at=row["expires_at"],
+            )
+            for row in paginated_result.data
+        ]
+
+        return ListOpenAIFileResponse(
+            data=files,
+            has_more=paginated_result.has_more,
+            # empty string or None? spec says str, ref impl returns str | None, we go with spec
+            first_id=files[0].id if files else "",
+            last_id=files[-1].id if files else "",
+        )
+
+    async def openai_retrieve_file(self, file_id: str) -> OpenAIFileObject:
+        row = await self.sql_store.fetch_one("openai_files", where={"id": file_id})
+        if not row:
+            raise ResourceNotFoundError(file_id, "File", "files.list()")
+
+        return OpenAIFileObject(
+            id=row["id"],
+            filename=row["filename"],
+            purpose=OpenAIFilePurpose(row["purpose"]),
+            bytes=row["bytes"],
+            created_at=row["created_at"],
+            expires_at=row["expires_at"],
+        )
+
+    async def openai_delete_file(self, file_id: str) -> OpenAIFileDeleteResponse:
+        row = await self.sql_store.fetch_one("openai_files", where={"id": file_id})
+        if not row:
+            raise ResourceNotFoundError(file_id, "File", "files.list()")
+
+        try:
+            self.client.delete_object(
+                Bucket=self._config.bucket_name,
+                Key=row["id"],
+            )
+        except ClientError as e:
+            if e.response["Error"]["Code"] != "NoSuchKey":
+                raise RuntimeError(f"Failed to delete file from S3: {e}") from e
+
+        await self.sql_store.delete("openai_files", where={"id": file_id})
+
+        return OpenAIFileDeleteResponse(id=file_id, deleted=True)
+
+    async def openai_retrieve_file_content(self, file_id: str) -> Response:
+        row = await self.sql_store.fetch_one("openai_files", where={"id": file_id})
+        if not row:
+            raise ResourceNotFoundError(file_id, "File", "files.list()")
+
+        try:
+            response = self.client.get_object(
+                Bucket=self._config.bucket_name,
+                Key=row["id"],
+            )
+            # TODO: can we stream this instead of loading it into memory
+            content = response["Body"].read()
+        except ClientError as e:
+            if e.response["Error"]["Code"] == "NoSuchKey":
+                await self.sql_store.delete("openai_files", where={"id": file_id})
+                raise ResourceNotFoundError(file_id, "File", "files.list()") from e
+            raise RuntimeError(f"Failed to download file from S3: {e}") from e
+
+        return Response(
+            content=content,
+            media_type="application/octet-stream",
+            headers={"Content-Disposition": f'attachment; filename="{row["filename"]}"'},
+        )

llama_stack/providers/remote/inference/fireworks/fireworks.py

@@ -65,7 +65,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 from .config import FireworksImplConfig
 from .models import MODEL_ENTRIES
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::fireworks")
 
 
 class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):

llama_stack/providers/remote/inference/llama_openai_compat/llama.py

@@ -3,6 +3,11 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+from llama_stack.apis.inference import (
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
+    RerankResponse,
+)
 from llama_stack.log import get_logger
 from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
 from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
@@ -10,7 +15,7 @@ from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .models import MODEL_ENTRIES
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::llama_openai_compat")
 
 
 class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
@@ -54,3 +59,12 @@ class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
 
     async def shutdown(self):
         await super().shutdown()
+
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Llama OpenAI Compat")

llama_stack/providers/remote/inference/nvidia/NVIDIA.md

@@ -41,6 +41,11 @@ client.initialize()
 
 ### Create Completion
 
+> Note on Completion API
+>
+> The hosted NVIDIA Llama NIMs (e.g., `meta-llama/Llama-3.1-8B-Instruct`) with ```NVIDIA_BASE_URL="https://integrate.api.nvidia.com"``` does not support the ```completion``` method, while the locally deployed NIM does.
+
+
 ```python
 response = client.inference.completion(
     model_id="meta-llama/Llama-3.1-8B-Instruct",
@@ -76,6 +81,73 @@ response = client.inference.chat_completion(
 print(f"Response: {response.completion_message.content}")
 ```
 
+### Tool Calling Example ###
+```python
+from llama_stack.models.llama.datatypes import ToolDefinition, ToolParamDefinition
+
+tool_definition = ToolDefinition(
+    tool_name="get_weather",
+    description="Get current weather information for a location",
+    parameters={
+        "location": ToolParamDefinition(
+            param_type="string",
+            description="The city and state, e.g. San Francisco, CA",
+            required=True,
+        ),
+        "unit": ToolParamDefinition(
+            param_type="string",
+            description="Temperature unit (celsius or fahrenheit)",
+            required=False,
+            default="celsius",
+        ),
+    },
+)
+
+tool_response = client.inference.chat_completion(
+    model_id="meta-llama/Llama-3.1-8B-Instruct",
+    messages=[{"role": "user", "content": "What's the weather like in San Francisco?"}],
+    tools=[tool_definition],
+)
+
+print(f"Tool Response: {tool_response.completion_message.content}")
+if tool_response.completion_message.tool_calls:
+    for tool_call in tool_response.completion_message.tool_calls:
+        print(f"Tool Called: {tool_call.tool_name}")
+        print(f"Arguments: {tool_call.arguments}")
+```
+
+### Structured Output Example
+```python
+from llama_stack.apis.inference import JsonSchemaResponseFormat, ResponseFormatType
+
+person_schema = {
+    "type": "object",
+    "properties": {
+        "name": {"type": "string"},
+        "age": {"type": "integer"},
+        "occupation": {"type": "string"},
+    },
+    "required": ["name", "age", "occupation"],
+}
+
+response_format = JsonSchemaResponseFormat(
+    type=ResponseFormatType.json_schema, json_schema=person_schema
+)
+
+structured_response = client.inference.chat_completion(
+    model_id="meta-llama/Llama-3.1-8B-Instruct",
+    messages=[
+        {
+            "role": "user",
+            "content": "Create a profile for a fictional person named Alice who is 30 years old and is a software engineer. ",
+        }
+    ],
+    response_format=response_format,
+)
+
+print(f"Structured Response: {structured_response.completion_message.content}")
+```
+
 ### Create Embeddings
 > Note on OpenAI embeddings compatibility
 >

llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -7,7 +7,7 @@
 import warnings
 from collections.abc import AsyncIterator
 
-from openai import NOT_GIVEN, APIConnectionError, BadRequestError
+from openai import NOT_GIVEN, APIConnectionError
 
 from llama_stack.apis.common.content_types import (
     InterleavedContent,
@@ -57,7 +57,7 @@ from .openai_utils import (
 )
 from .utils import _is_nvidia_hosted
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::nvidia")
 
 
 class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
@@ -197,15 +197,11 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
             }
             extra_body["input_type"] = task_type_options[task_type]
 
-        try:
+        response = await self.client.embeddings.create(
-            response = await self.client.embeddings.create(
+            model=provider_model_id,
-                model=provider_model_id,
+            input=input,
-                input=input,
+            extra_body=extra_body,
-                extra_body=extra_body,
+        )
-            )
-        except BadRequestError as e:
-            raise ValueError(f"Failed to get embeddings: {e}") from e
-
         #
         # OpenAI: CreateEmbeddingResponse(data=[Embedding(embedding=list[float], ...)], ...)
         #  ->

llama_stack/providers/remote/inference/nvidia/utils.py

@@ -10,7 +10,7 @@ from llama_stack.log import get_logger
 
 from . import NVIDIAConfig
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::nvidia")
 
 
 def _is_nvidia_hosted(config: NVIDIAConfig) -> bool:

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -37,11 +37,14 @@ from llama_stack.apis.inference import (
     Message,
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
     OpenAICompletion,
     OpenAIEmbeddingsResponse,
     OpenAIEmbeddingUsage,
     OpenAIMessageParam,
     OpenAIResponseFormatParam,
+    RerankResponse,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
@@ -85,7 +88,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .models import MODEL_ENTRIES
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::ollama")
 
 
 class OllamaInferenceAdapter(
@@ -641,6 +644,15 @@ class OllamaInferenceAdapter(
     ):
         raise NotImplementedError("Batch chat completion is not supported for Ollama")
 
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Ollama")
+
 
 async def convert_message_to_openai_dict_for_ollama(message: Message) -> list[dict]:
     async def _convert_content(content) -> dict:

llama_stack/providers/remote/inference/openai/openai.py

@@ -11,7 +11,7 @@ from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 from .config import OpenAIConfig
 from .models import MODEL_ENTRIES
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::openai")
 
 
 #

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -58,7 +58,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
 
-log = get_logger(name=__name__, category="inference")
+log = get_logger(name=__name__, category="inference::tgi")
 
 
 def build_hf_repo_model_entries():

llama_stack/providers/remote/inference/together/together.py

@@ -61,7 +61,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 from .config import TogetherImplConfig
 from .models import MODEL_ENTRIES
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="inference::together")
 
 
 class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -39,12 +39,15 @@ from llama_stack.apis.inference import (
     Message,
     ModelStore,
     OpenAIChatCompletion,
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
     OpenAICompletion,
     OpenAIEmbeddingData,
     OpenAIEmbeddingsResponse,
     OpenAIEmbeddingUsage,
     OpenAIMessageParam,
     OpenAIResponseFormatParam,
+    RerankResponse,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
@@ -85,7 +88,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import VLLMInferenceAdapterConfig
 
-log = get_logger(name=__name__, category="inference")
+log = get_logger(name=__name__, category="inference::vllm")
 
 
 def build_hf_repo_model_entries():
@@ -732,4 +735,13 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
         response_format: ResponseFormat | None = None,
         logprobs: LogProbConfig | None = None,
     ):
-        raise NotImplementedError("Batch chat completion is not supported for Ollama")
+        raise NotImplementedError("Batch chat completion is not supported for vLLM")
+
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for vLLM")

llama_stack/providers/remote/post_training/nvidia/utils.py

@@ -15,7 +15,7 @@ from llama_stack.providers.remote.post_training.nvidia.config import SFTLoRADefa
 
 from .config import NvidiaPostTrainingConfig
 
-logger = get_logger(name=__name__, category="integration")
+logger = get_logger(name=__name__, category="post_training::nvidia")
 
 
 def warn_unsupported_params(config_dict: Any, supported_keys: set[str], config_name: str) -> None:

llama_stack/providers/remote/safety/bedrock/bedrock.py

@@ -21,7 +21,7 @@ from llama_stack.providers.utils.bedrock.client import create_bedrock_client
 
 from .config import BedrockSafetyConfig
 
-logger = get_logger(name=__name__, category="safety")
+logger = get_logger(name=__name__, category="safety::bedrock")
 
 
 class BedrockSafetyAdapter(Safety, ShieldsProtocolPrivate):

llama_stack/providers/remote/safety/nvidia/nvidia.py

@@ -9,7 +9,7 @@ from typing import Any
 import requests
 
 from llama_stack.apis.inference import Message
-from llama_stack.apis.safety import RunShieldResponse, Safety, SafetyViolation, ViolationLevel
+from llama_stack.apis.safety import ModerationObject, RunShieldResponse, Safety, SafetyViolation, ViolationLevel
 from llama_stack.apis.shields import Shield
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
@@ -17,7 +17,7 @@ from llama_stack.providers.utils.inference.openai_compat import convert_message_
 
 from .config import NVIDIASafetyConfig
 
-logger = get_logger(name=__name__, category="safety")
+logger = get_logger(name=__name__, category="safety::nvidia")
 
 
 class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
@@ -67,6 +67,9 @@ class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
         self.shield = NeMoGuardrails(self.config, shield.shield_id)
         return await self.shield.run(messages)
 
+    async def run_moderation(self, input: str | list[str], model: str) -> ModerationObject:
+        raise NotImplementedError("NVIDIA safety provider currently does not implement run_moderation")
+
 
 class NeMoGuardrails:
     """

llama_stack/providers/remote/safety/sambanova/sambanova.py

@@ -25,7 +25,7 @@ from llama_stack.providers.utils.inference.openai_compat import convert_message_
 
 from .config import SambaNovaSafetyConfig
 
-logger = get_logger(name=__name__, category="safety")
+logger = get_logger(name=__name__, category="safety::sambanova")
 
 CANNED_RESPONSE_TEXT = "I can't answer that. Can I help with something else?"
 

llama_stack/providers/remote/vector_io/chroma/chroma.py

@@ -33,7 +33,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import ChromaVectorIOConfig as RemoteChromaVectorIOConfig
 
-log = get_logger(name=__name__, category="vector_io")
+log = get_logger(name=__name__, category="vector_io::chroma")
 
 ChromaClientType = chromadb.api.AsyncClientAPI | chromadb.api.ClientAPI
 

llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -36,7 +36,7 @@ from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collecti
 
 from .config import MilvusVectorIOConfig as RemoteMilvusVectorIOConfig
 
-logger = get_logger(name=__name__, category="vector_io")
+logger = get_logger(name=__name__, category="vector_io::milvus")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:milvus:{VERSION}::"

llama_stack/providers/remote/vector_io/pgvector/pgvector.py

@@ -34,7 +34,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import PGVectorVectorIOConfig
 
-log = get_logger(name=__name__, category="vector_io")
+log = get_logger(name=__name__, category="vector_io::pgvector")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:pgvector:{VERSION}::"

llama_stack/providers/remote/vector_io/qdrant/qdrant.py

@@ -36,7 +36,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig
 
-log = get_logger(name=__name__, category="vector_io")
+log = get_logger(name=__name__, category="vector_io::qdrant")
 CHUNK_ID_KEY = "_chunk_id"
 
 # KV store prefixes for vector databases

llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -34,7 +34,7 @@ from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collecti
 
 from .config import WeaviateVectorIOConfig
 
-log = get_logger(name=__name__, category="vector_io")
+log = get_logger(name=__name__, category="vector_io::weaviate")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:weaviate:{VERSION}::"

llama_stack/providers/utils/inference/embedding_mixin.py

@@ -28,7 +28,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import interleaved_con
 EMBEDDING_MODELS = {}
 
 
-log = get_logger(name=__name__, category="inference")
+log = get_logger(name=__name__, category="providers::utils")
 
 
 class SentenceTransformerEmbeddingMixin:

llama_stack/providers/utils/inference/litellm_openai_mixin.py

@@ -54,7 +54,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="providers::utils")
 
 
 class LiteLLMOpenAIMixin(

llama_stack/providers/utils/inference/model_registry.py

@@ -17,7 +17,7 @@ from llama_stack.providers.utils.inference import (
     ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR,
 )
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="providers::utils")
 
 
 class RemoteInferenceProviderConfig(BaseModel):

llama_stack/providers/utils/inference/openai_compat.py

@@ -134,7 +134,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     decode_assistant_message,
 )
 
-logger = get_logger(name=__name__, category="inference")
+logger = get_logger(name=__name__, category="providers::utils")
 
 
 class OpenAICompatCompletionChoiceDelta(BaseModel):

llama_stack/providers/utils/inference/openai_mixin.py

@@ -25,7 +25,7 @@ from llama_stack.apis.inference import (
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
 
-logger = get_logger(name=__name__, category="core")
+logger = get_logger(name=__name__, category="providers::utils")
 
 
 class OpenAIMixin(ABC):

llama_stack/providers/utils/inference/prompt_adapter.py

@@ -58,7 +58,7 @@ from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.models.llama.sku_types import ModelFamily, is_multimodal
 from llama_stack.providers.utils.inference import supported_inference_models
 
-log = get_logger(name=__name__, category="inference")
+log = get_logger(name=__name__, category="providers::utils")
 
 
 class ChatCompletionRequestWithRawContent(ChatCompletionRequest):

llama_stack/providers/utils/kvstore/mongodb/mongodb.py

@@ -13,7 +13,7 @@ from llama_stack.providers.utils.kvstore import KVStore
 
 from ..config import MongoDBKVStoreConfig
 
-log = get_logger(name=__name__, category="kvstore")
+log = get_logger(name=__name__, category="providers::utils")
 
 
 class MongoDBKVStoreImpl(KVStore):

llama_stack/providers/utils/kvstore/postgres/postgres.py

@@ -14,7 +14,7 @@ from llama_stack.log import get_logger
 from ..api import KVStore
 from ..config import PostgresKVStoreConfig
 
-log = get_logger(name=__name__, category="kvstore")
+log = get_logger(name=__name__, category="providers::utils")
 
 
 class PostgresKVStoreImpl(KVStore):

llama_stack/providers/utils/memory/openai_vector_store_mixin.py

@@ -44,7 +44,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     make_overlapped_chunks,
 )
 
-logger = get_logger(name=__name__, category="memory")
+logger = get_logger(name=__name__, category="providers::utils")
 
 # Constants for OpenAI vector stores
 CHUNK_MULTIPLIER = 5

llama_stack/providers/utils/memory/vector_store.py

@@ -33,7 +33,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 )
 from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id
 
-log = get_logger(name=__name__, category="memory")
+log = get_logger(name=__name__, category="providers::utils")
 
 
 class ChunkForDeletion(BaseModel):

llama_stack/providers/utils/scheduler.py

@@ -17,7 +17,7 @@ from pydantic import BaseModel
 
 from llama_stack.log import get_logger
 
-logger = get_logger(name=__name__, category="scheduler")
+logger = get_logger(name=__name__, category="providers::utils")
 
 
 # TODO: revisit the list of possible statuses when defining a more coherent

llama_stack/providers/utils/sqlstore/authorized_sqlstore.py

@@ -17,7 +17,7 @@ from llama_stack.log import get_logger
 from .api import ColumnDefinition, ColumnType, PaginatedResponse, SqlStore
 from .sqlstore import SqlStoreType
 
-logger = get_logger(name=__name__, category="authorized_sqlstore")
+logger = get_logger(name=__name__, category="providers::utils")
 
 # Hardcoded copy of the default policy that our SQL filtering implements
 # WARNING: If default_policy() changes, this constant must be updated accordingly

llama_stack/providers/utils/sqlstore/sqlalchemy_sqlstore.py

@@ -22,6 +22,7 @@ from sqlalchemy import (
     text,
 )
 from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+from sqlalchemy.ext.asyncio.engine import AsyncEngine
 
 from llama_stack.apis.common.responses import PaginatedResponse
 from llama_stack.log import get_logger
@@ -29,7 +30,7 @@ from llama_stack.log import get_logger
 from .api import ColumnDefinition, ColumnType, SqlStore
 from .sqlstore import SqlAlchemySqlStoreConfig
 
-logger = get_logger(name=__name__, category="sqlstore")
+logger = get_logger(name=__name__, category="providers::utils")
 
 TYPE_MAPPING: dict[ColumnType, Any] = {
     ColumnType.INTEGER: Integer,
@@ -45,9 +46,12 @@ TYPE_MAPPING: dict[ColumnType, Any] = {
 class SqlAlchemySqlStoreImpl(SqlStore):
     def __init__(self, config: SqlAlchemySqlStoreConfig):
         self.config = config
-        self.async_session = async_sessionmaker(create_async_engine(config.engine_str))
+        self.async_session = async_sessionmaker(self.create_engine())
         self.metadata = MetaData()
 
+    def create_engine(self) -> AsyncEngine:
+        return create_async_engine(self.config.engine_str, pool_pre_ping=True)
+
     async def create_table(
         self,
         table: str,
@@ -83,7 +87,7 @@ class SqlAlchemySqlStoreImpl(SqlStore):
         else:
             sqlalchemy_table = self.metadata.tables[table]
 
-        engine = create_async_engine(self.config.engine_str)
+        engine = self.create_engine()
         async with engine.begin() as conn:
             await conn.run_sync(self.metadata.create_all, tables=[sqlalchemy_table], checkfirst=True)
 
@@ -241,7 +245,7 @@ class SqlAlchemySqlStoreImpl(SqlStore):
         nullable: bool = True,
     ) -> None:
         """Add a column to an existing table if the column doesn't already exist."""
-        engine = create_async_engine(self.config.engine_str)
+        engine = self.create_engine()
 
         try:
             async with engine.begin() as conn:

llama_stack/ui/app/chat-playground/page.test.tsx

@@ -0,0 +1,587 @@
+import React from "react";
+import {
+  render,
+  screen,
+  fireEvent,
+  waitFor,
+  act,
+} from "@testing-library/react";
+import "@testing-library/jest-dom";
+import ChatPlaygroundPage from "./page";
+
+const mockClient = {
+  agents: {
+    list: jest.fn(),
+    create: jest.fn(),
+    retrieve: jest.fn(),
+    delete: jest.fn(),
+    session: {
+      list: jest.fn(),
+      create: jest.fn(),
+      delete: jest.fn(),
+      retrieve: jest.fn(),
+    },
+    turn: {
+      create: jest.fn(),
+    },
+  },
+  models: {
+    list: jest.fn(),
+  },
+  toolgroups: {
+    list: jest.fn(),
+  },
+};
+
+jest.mock("@/hooks/use-auth-client", () => ({
+  useAuthClient: jest.fn(() => mockClient),
+}));
+
+jest.mock("@/components/chat-playground/chat", () => ({
+  Chat: jest.fn(
+    ({
+      className,
+      messages,
+      handleSubmit,
+      input,
+      handleInputChange,
+      isGenerating,
+      append,
+      suggestions,
+    }) => (
+      <div data-testid="chat-component" className={className}>
+        <div data-testid="messages-count">{messages.length}</div>
+        <input
+          data-testid="chat-input"
+          value={input}
+          onChange={handleInputChange}
+          disabled={isGenerating}
+        />
+        <button data-testid="submit-button" onClick={handleSubmit}>
+          Submit
+        </button>
+        {suggestions?.map((suggestion: string, index: number) => (
+          <button
+            key={index}
+            data-testid={`suggestion-${index}`}
+            onClick={() => append({ role: "user", content: suggestion })}
+          >
+            {suggestion}
+          </button>
+        ))}
+      </div>
+    )
+  ),
+}));
+
+jest.mock("@/components/chat-playground/conversations", () => ({
+  SessionManager: jest.fn(({ selectedAgentId, onNewSession }) => (
+    <div data-testid="session-manager">
+      {selectedAgentId && (
+        <>
+          <div data-testid="selected-agent">{selectedAgentId}</div>
+          <button data-testid="new-session-button" onClick={onNewSession}>
+            New Session
+          </button>
+        </>
+      )}
+    </div>
+  )),
+  SessionUtils: {
+    saveCurrentSessionId: jest.fn(),
+    loadCurrentSessionId: jest.fn(),
+    loadCurrentAgentId: jest.fn(),
+    saveCurrentAgentId: jest.fn(),
+    clearCurrentSession: jest.fn(),
+    saveSessionData: jest.fn(),
+    loadSessionData: jest.fn(),
+    saveAgentConfig: jest.fn(),
+    loadAgentConfig: jest.fn(),
+    clearAgentCache: jest.fn(),
+    createDefaultSession: jest.fn(() => ({
+      id: "test-session-123",
+      name: "Default Session",
+      messages: [],
+      selectedModel: "",
+      systemMessage: "You are a helpful assistant.",
+      agentId: "test-agent-123",
+      createdAt: Date.now(),
+      updatedAt: Date.now(),
+    })),
+  },
+}));
+
+const mockAgents = [
+  {
+    agent_id: "agent_123",
+    agent_config: {
+      name: "Test Agent",
+      instructions: "You are a test assistant.",
+    },
+  },
+  {
+    agent_id: "agent_456",
+    agent_config: {
+      agent_name: "Another Agent",
+      instructions: "You are another assistant.",
+    },
+  },
+];
+
+const mockModels = [
+  {
+    identifier: "test-model-1",
+    model_type: "llm",
+  },
+  {
+    identifier: "test-model-2",
+    model_type: "llm",
+  },
+];
+
+const mockToolgroups = [
+  {
+    identifier: "builtin::rag",
+    provider_id: "test-provider",
+    type: "tool_group",
+    provider_resource_id: "test-resource",
+  },
+];
+
+describe("ChatPlaygroundPage", () => {
+  beforeEach(() => {
+    jest.clearAllMocks();
+    Element.prototype.scrollIntoView = jest.fn();
+    mockClient.agents.list.mockResolvedValue({ data: mockAgents });
+    mockClient.models.list.mockResolvedValue(mockModels);
+    mockClient.toolgroups.list.mockResolvedValue(mockToolgroups);
+    mockClient.agents.session.create.mockResolvedValue({
+      session_id: "new-session-123",
+    });
+    mockClient.agents.session.list.mockResolvedValue({ data: [] });
+    mockClient.agents.session.retrieve.mockResolvedValue({
+      session_id: "test-session",
+      session_name: "Test Session",
+      started_at: new Date().toISOString(),
+      turns: [],
+    }); // No turns by default
+    mockClient.agents.retrieve.mockResolvedValue({
+      agent_id: "test-agent",
+      agent_config: {
+        toolgroups: ["builtin::rag"],
+        instructions: "Test instructions",
+        model: "test-model",
+      },
+    });
+    mockClient.agents.delete.mockResolvedValue(undefined);
+  });
+
+  describe("Agent Selector Rendering", () => {
+    test("shows agent selector when agents are available", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(screen.getByText("Agent Session:")).toBeInTheDocument();
+        expect(screen.getAllByRole("combobox")).toHaveLength(2);
+        expect(screen.getByText("+ New Agent")).toBeInTheDocument();
+        expect(screen.getByText("Clear Chat")).toBeInTheDocument();
+      });
+    });
+
+    test("does not show agent selector when no agents are available", async () => {
+      mockClient.agents.list.mockResolvedValue({ data: [] });
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(screen.queryByText("Agent Session:")).not.toBeInTheDocument();
+        expect(screen.getAllByRole("combobox")).toHaveLength(1);
+        expect(screen.getByText("+ New Agent")).toBeInTheDocument();
+        expect(screen.queryByText("Clear Chat")).not.toBeInTheDocument();
+      });
+    });
+
+    test("does not show agent selector while loading", async () => {
+      mockClient.agents.list.mockImplementation(() => new Promise(() => {}));
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      expect(screen.queryByText("Agent Session:")).not.toBeInTheDocument();
+      expect(screen.getAllByRole("combobox")).toHaveLength(1);
+      expect(screen.getByText("+ New Agent")).toBeInTheDocument();
+      expect(screen.queryByText("Clear Chat")).not.toBeInTheDocument();
+    });
+
+    test("shows agent options in selector", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        const agentCombobox = screen.getAllByRole("combobox").find(element => {
+          return (
+            element.textContent?.includes("Test Agent") ||
+            element.textContent?.includes("Select Agent")
+          );
+        });
+        expect(agentCombobox).toBeDefined();
+        fireEvent.click(agentCombobox!);
+      });
+
+      await waitFor(() => {
+        expect(screen.getAllByText("Test Agent")).toHaveLength(2);
+        expect(screen.getByText("Another Agent")).toBeInTheDocument();
+      });
+    });
+
+    test("displays agent ID when no name is available", async () => {
+      const agentWithoutName = {
+        agent_id: "agent_789",
+        agent_config: {
+          instructions: "You are an agent without a name.",
+        },
+      };
+
+      mockClient.agents.list.mockResolvedValue({ data: [agentWithoutName] });
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        const agentCombobox = screen.getAllByRole("combobox").find(element => {
+          return (
+            element.textContent?.includes("Agent agent_78") ||
+            element.textContent?.includes("Select Agent")
+          );
+        });
+        expect(agentCombobox).toBeDefined();
+        fireEvent.click(agentCombobox!);
+      });
+
+      await waitFor(() => {
+        expect(screen.getAllByText("Agent agent_78...")).toHaveLength(2);
+      });
+    });
+  });
+
+  describe("Agent Creation Modal", () => {
+    test("opens agent creation modal when + New Agent is clicked", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      const newAgentButton = screen.getByText("+ New Agent");
+      fireEvent.click(newAgentButton);
+
+      expect(screen.getByText("Create New Agent")).toBeInTheDocument();
+      expect(screen.getByText("Agent Name (optional)")).toBeInTheDocument();
+      expect(screen.getAllByText("Model")).toHaveLength(2);
+      expect(screen.getByText("System Instructions")).toBeInTheDocument();
+      expect(screen.getByText("Tools (optional)")).toBeInTheDocument();
+    });
+
+    test("closes modal when Cancel is clicked", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      const newAgentButton = screen.getByText("+ New Agent");
+      fireEvent.click(newAgentButton);
+
+      const cancelButton = screen.getByText("Cancel");
+      fireEvent.click(cancelButton);
+
+      expect(screen.queryByText("Create New Agent")).not.toBeInTheDocument();
+    });
+
+    test("creates agent when Create Agent is clicked", async () => {
+      mockClient.agents.create.mockResolvedValue({ agent_id: "new-agent-123" });
+      mockClient.agents.list
+        .mockResolvedValueOnce({ data: mockAgents })
+        .mockResolvedValueOnce({
+          data: [
+            ...mockAgents,
+            { agent_id: "new-agent-123", agent_config: { name: "New Agent" } },
+          ],
+        });
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      const newAgentButton = screen.getByText("+ New Agent");
+      await act(async () => {
+        fireEvent.click(newAgentButton);
+      });
+
+      await waitFor(() => {
+        expect(screen.getByText("Create New Agent")).toBeInTheDocument();
+      });
+
+      const nameInput = screen.getByPlaceholderText("My Custom Agent");
+      await act(async () => {
+        fireEvent.change(nameInput, { target: { value: "Test Agent Name" } });
+      });
+
+      const instructionsTextarea = screen.getByDisplayValue(
+        "You are a helpful assistant."
+      );
+      await act(async () => {
+        fireEvent.change(instructionsTextarea, {
+          target: { value: "Custom instructions" },
+        });
+      });
+
+      await waitFor(() => {
+        const modalModelSelectors = screen
+          .getAllByRole("combobox")
+          .filter(el => {
+            return (
+              el.textContent?.includes("Select Model") ||
+              el.closest('[class*="modal"]') ||
+              el.closest('[class*="card"]')
+            );
+          });
+        expect(modalModelSelectors.length).toBeGreaterThan(0);
+      });
+
+      const modalModelSelectors = screen.getAllByRole("combobox").filter(el => {
+        return (
+          el.textContent?.includes("Select Model") ||
+          el.closest('[class*="modal"]') ||
+          el.closest('[class*="card"]')
+        );
+      });
+
+      await act(async () => {
+        fireEvent.click(modalModelSelectors[0]);
+      });
+
+      await waitFor(() => {
+        const modelOptions = screen.getAllByText("test-model-1");
+        expect(modelOptions.length).toBeGreaterThan(0);
+      });
+
+      const modelOptions = screen.getAllByText("test-model-1");
+      const dropdownOption = modelOptions.find(
+        option =>
+          option.closest('[role="option"]') ||
+          option.id?.includes("radix") ||
+          option.getAttribute("aria-selected") !== null
+      );
+
+      await act(async () => {
+        fireEvent.click(
+          dropdownOption || modelOptions[modelOptions.length - 1]
+        );
+      });
+
+      await waitFor(() => {
+        const createButton = screen.getByText("Create Agent");
+        expect(createButton).not.toBeDisabled();
+      });
+
+      const createButton = screen.getByText("Create Agent");
+      await act(async () => {
+        fireEvent.click(createButton);
+      });
+
+      await waitFor(() => {
+        expect(mockClient.agents.create).toHaveBeenCalledWith({
+          agent_config: {
+            model: expect.any(String),
+            instructions: "Custom instructions",
+            name: "Test Agent Name",
+            enable_session_persistence: true,
+          },
+        });
+      });
+
+      await waitFor(() => {
+        expect(screen.queryByText("Create New Agent")).not.toBeInTheDocument();
+      });
+    });
+  });
+
+  describe("Agent Selection", () => {
+    test("creates default session when agent is selected", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        // first agent should be auto-selected
+        expect(mockClient.agents.session.create).toHaveBeenCalledWith(
+          "agent_123",
+          { session_name: "Default Session" }
+        );
+      });
+    });
+
+    test("switches agent when different agent is selected", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        const agentCombobox = screen.getAllByRole("combobox").find(element => {
+          return (
+            element.textContent?.includes("Test Agent") ||
+            element.textContent?.includes("Select Agent")
+          );
+        });
+        expect(agentCombobox).toBeDefined();
+        fireEvent.click(agentCombobox!);
+      });
+
+      await waitFor(() => {
+        const anotherAgentOption = screen.getByText("Another Agent");
+        fireEvent.click(anotherAgentOption);
+      });
+
+      expect(mockClient.agents.session.create).toHaveBeenCalledWith(
+        "agent_456",
+        { session_name: "Default Session" }
+      );
+    });
+  });
+
+  describe("Agent Deletion", () => {
+    test("shows delete button when multiple agents exist", async () => {
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(screen.getByTitle("Delete current agent")).toBeInTheDocument();
+      });
+    });
+
+    test("hides delete button when only one agent exists", async () => {
+      mockClient.agents.list.mockResolvedValue({
+        data: [mockAgents[0]],
+      });
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(
+          screen.queryByTitle("Delete current agent")
+        ).not.toBeInTheDocument();
+      });
+    });
+
+    test("deletes agent and switches to another when confirmed", async () => {
+      global.confirm = jest.fn(() => true);
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(screen.getByTitle("Delete current agent")).toBeInTheDocument();
+      });
+
+      mockClient.agents.delete.mockResolvedValue(undefined);
+      mockClient.agents.list.mockResolvedValueOnce({ data: mockAgents });
+      mockClient.agents.list.mockResolvedValueOnce({
+        data: [mockAgents[1]],
+      });
+
+      const deleteButton = screen.getByTitle("Delete current agent");
+      await act(async () => {
+        deleteButton.click();
+      });
+
+      await waitFor(() => {
+        expect(mockClient.agents.delete).toHaveBeenCalledWith("agent_123");
+        expect(global.confirm).toHaveBeenCalledWith(
+          "Are you sure you want to delete this agent? This action cannot be undone and will delete all associated sessions."
+        );
+      });
+
+      (global.confirm as jest.Mock).mockRestore();
+    });
+
+    test("does not delete agent when cancelled", async () => {
+      global.confirm = jest.fn(() => false);
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(screen.getByTitle("Delete current agent")).toBeInTheDocument();
+      });
+
+      const deleteButton = screen.getByTitle("Delete current agent");
+      await act(async () => {
+        deleteButton.click();
+      });
+
+      await waitFor(() => {
+        expect(global.confirm).toHaveBeenCalled();
+        expect(mockClient.agents.delete).not.toHaveBeenCalled();
+      });
+
+      (global.confirm as jest.Mock).mockRestore();
+    });
+  });
+
+  describe("Error Handling", () => {
+    test("handles agent loading errors gracefully", async () => {
+      mockClient.agents.list.mockRejectedValue(
+        new Error("Failed to load agents")
+      );
+      const consoleSpy = jest
+        .spyOn(console, "error")
+        .mockImplementation(() => {});
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(consoleSpy).toHaveBeenCalledWith(
+          "Error fetching agents:",
+          expect.any(Error)
+        );
+      });
+
+      expect(screen.getByText("+ New Agent")).toBeInTheDocument();
+
+      consoleSpy.mockRestore();
+    });
+
+    test("handles model loading errors gracefully", async () => {
+      mockClient.models.list.mockRejectedValue(
+        new Error("Failed to load models")
+      );
+      const consoleSpy = jest
+        .spyOn(console, "error")
+        .mockImplementation(() => {});
+
+      await act(async () => {
+        render(<ChatPlaygroundPage />);
+      });
+
+      await waitFor(() => {
+        expect(consoleSpy).toHaveBeenCalledWith(
+          "Error fetching models:",
+          expect.any(Error)
+        );
+      });
+
+      consoleSpy.mockRestore();
+    });
+  });
+});