chore: release v2.86.0

* style: `New dataset` button as `secondary`

* fix: missing UI-only access check on archive item

* style button consistently

.codespellrc

@@ -1,4 +1,4 @@
 [codespell]
 skip = .git,*.pdf,*.svg,package-lock.json,*.prisma,pnpm-lock.yaml
-ignore-words-list = afterall,vertx
+ignore-words-list = afterall,vertx,notIn
 

.devcontainer/devcontainer.json

@@ -1,14 +0,0 @@
-{
-  "name": "langfuse dev",
-  "image": "mcr.microsoft.com/devcontainers/javascript-node:20-bookworm",
-  "features": {
-    "ghcr.io/devcontainers/features/docker-in-docker:2": {
-      "version": "latest",
-      "moby": true
-    }
-  },
-  "forwardPorts": [3000],
-
-  "onCreateCommand": "npm install -g pnpm@9.5.0",
-  "postCreateCommand": "cp .env.dev.example .env && pnpm run dx-f"
-}

.env.dev.example

@@ -34,11 +34,25 @@ EMAIL_FROM_ADDRESS=""  # Defines the email address to use as the from address.
 SMTP_CONNECTION_URL=""  # Defines the connection url for smtp server.
 
 # S3 storage
-S3_ENDPOINT=
-S3_ACCESS_KEY_ID=
-S3_SECRET_ACCESS_KEY=
-S3_BUCKET_NAME=
-S3_REGION=
+S3_ENDPOINT=http://localhost:9090
+S3_ACCESS_KEY_ID=minio
+S3_SECRET_ACCESS_KEY=miniosecret
+S3_BUCKET_NAME=mybucket
+S3_REGION=us-east-1
+## Necessary for minio compatibility
+S3_FORCE_PATH_STYLE=true
+
+# S3 Event Bucket Upload
+## Set to true to test uploading all events to S3
+LANGFUSE_S3_EVENT_UPLOAD_ENABLED=false
+LANGFUSE_S3_EVENT_UPLOAD_BUCKET=mybucket
+LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID=minio
+LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY=miniosecret
+LANGFUSE_S3_EVENT_UPLOAD_REGION=us-east-1
+LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT=http://localhost:9090
+## Necessary for minio compatibility
+LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE=true
+LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
 
 # Set during docker build of application
 # Used to disable environment verification at build time
@@ -48,7 +62,8 @@ REDIS_HOST="127.0.0.1"
 REDIS_PORT=6379
 REDIS_AUTH="myredissecret"
 
-LANGFUSE_WORKER_PASSWORD=mybasicauthsecret
 # openssl rand -hex 32 used only here
 ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000 
 
+# speeds up local development by not executing init scripts on server startup
+NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT="false"

.env.local.example

@@ -18,7 +18,5 @@ REDIS_HOST="127.0.0.1"
 REDIS_PORT=6379
 REDIS_AUTH="myredissecret"
 
-LANGFUSE_WORKER_PASSWORD=myworkerpassword
-
 # openssl rand -hex 32 used only here
 ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000

.env.prod.example

@@ -28,17 +28,28 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # Use CSP headers to enforce HTTPS, optional
 # LANGFUSE_CSP_ENFORCE_HTTPS="true"
 
+# Configure base path for self-hosting, optional
+# Note: You need to build the docker image with the base path set and cannot use the pre-built docker image if you set this.
+# NEXT_PUBLIC_BASE_PATH="/app"
 
 # Docker only, optional
 # PORT=3000
 # HOSTNAME=localhost
 
+# Opentelemetry, optional
+OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4318"
+OTEL_SERVICE_NAME="langfuse"
+
 # Default role for users who sign up, optional, can be org or org+project
 # LANGFUSE_DEFAULT_ORG_ID=
 # LANGFUSE_DEFAULT_ORG_ROLE=
 # LANGFUSE_DEFAULT_PROJECT_ID=
 # LANGFUSE_DEFAULT_PROJECT_ROLE=
 
+# Logging, optional
+# LANGFUSE_LOG_LEVEL=info
+# LANGFUSE_LOG_FORMAT=text
+
 # Enable experimental features, optional
 # LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES=true
 
@@ -56,6 +67,10 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # AUTH_GITHUB_CLIENT_ID=
 # AUTH_GITHUB_CLIENT_SECRET=
 # AUTH_GITHUB_ALLOW_ACCOUNT_LINKING=false
+# AUTH_GITLAB_CLIENT_ID=
+# AUTH_GITLAB_CLIENT_SECRET=
+# AUTH_GITLAB_ALLOW_ACCOUNT_LINKING=false
+# AUTH_GITLAB_ISSUER=
 # AUTH_AZURE_AD_CLIENT_ID=
 # AUTH_AZURE_AD_CLIENT_SECRET=
 # AUTH_AZURE_AD_TENANT_ID=
@@ -93,12 +108,32 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # S3_REGION=
 # BATCH_EXPORT_DOWNLOAD_LINK_EXPIRATION_HOURS=
 
+# S3 storage for events, optional, used to persist all incoming events
+# LANGFUSE_S3_EVENT_UPLOAD_ENABLED="true"
+# LANGFUSE_S3_EVENT_UPLOAD_BUCKET=
+# Optional prefix to be used within the bucket. Must end with `/` if set
+# LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
+# The following four options are optional and fallback to the normal SDK credential provider chain if omitted
+# See https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/setting-credentials-node.html
+# LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT=
+# LANGFUSE_S3_EVENT_UPLOAD_REGION=
+# LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID=
+# LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY=
+
 # Exports are streamed to S3 in pages to avoid memory issues
 # The page size can be adjusted if needed to optimize performance
 # DB_EXPORT_PAGE_SIZE=1000
 
-# Disable logging to `events` table in db
-# ENABLE_EVENT_LOG=false
+# Automated provisioning of default resources
+# LANGFUSE_INIT_ORG_ID=org-id
+# LANGFUSE_INIT_ORG_NAME=org-name
+# LANGFUSE_INIT_PROJECT_ID=project-id
+# LANGFUSE_INIT_PROJECT_NAME=project-name
+# LANGFUSE_INIT_PROJECT_PUBLIC_KEY=pk-1234567890
+# LANGFUSE_INIT_PROJECT_SECRET_KEY=sk-1234567890
+# LANGFUSE_INIT_USER_EMAIL=user@example.com
+# LANGFUSE_INIT_USER_NAME=User Name
+# LANGFUSE_INIT_USER_PASSWORD=password
 
 
 
@@ -112,6 +147,12 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # LANGFUSE_UI_DOCUMENTATION_HREF=https://docs.example.com
 # LANGFUSE_UI_SUPPORT_HREF=https://support.example.com
 # LANGFUSE_UI_FEEDBACK_HREF=https://feedback.example.com
+# LANGFUSE_UI_LOGO_LIGHT_MODE_HREF=https://static.langfuse.com/langfuse-dev/example-logo-light-mode.png
+# LANGFUSE_UI_LOGO_DARK_MODE_HREF=https://static.langfuse.com/langfuse-dev/example-logo-dark-mode.png
+# LANGFUSE_UI_DEFAULT_MODEL_ADAPTER=Anthropic # OpenAI, Anthropic, Azure
+# LANGFUSE_UI_DEFAULT_BASE_URL_OPENAI=https://api.openai.com/v1
+# LANGFUSE_UI_DEFAULT_BASE_URL_ANTHROPIC=https://api.anthropic.com
+# LANGFUSE_UI_DEFAULT_BASE_URL_AZURE_OPENAI=https://{instanceName}.openai.azure.com/openai/deployments
 
 ### END Enterprise Edition Configuration
 
@@ -142,13 +183,12 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # NEXT_PUBLIC_POSTHOG_KEY=
 
 # Sentry
+# NEXT_PUBLIC_LANGFUSE_TRACING_SAMPLE_RATE
 # NEXT_PUBLIC_SENTRY_DSN=
 # NEXT_SENTRY_ORG=
 # NEXT_SENTRY_PROJECT=
 # SENTRY_AUTH_TOKEN=
-# Used to determine the Sentry sample rate
-# LANGFUSE_TRACING_SAMPLE_RATE=
-# LANGFUSE_WORKER_BETTERSTACK_TOKEN=
+# SENTRY_CSP_REPORT_URI=
 
 
 # Cloudflare Turnstile
@@ -170,6 +210,7 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # REDIS_PORT=
 # REDIS_AUTH=
 # REDIS_CONNECTION_STRING=
+# REDIS_ENABLE_AUTO_PIPELINING=
 
 # Cache configuration
 # LANGFUSE_CACHE_API_KEY_ENABLED=
@@ -177,6 +218,13 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # LANGFUSE_CACHE_PROMPT_ENABLED=
 # LANGFUSE_CACHE_PROMPT_TTL_SECONDS=
 
+# Rate limiting
+# LANGFUSE_RATE_LIMITS_ENABLED=
+
+# Stripe
+# STRIPE_SECRET_KEY=
+# STRIPE_WEBHOOK_SIGNING_SECRET=
+
 ### END Langfuse Cloud Config
 
 
@@ -189,13 +237,12 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # CLICKHOUSE_PASSWORD=
 
 # Ingestion
-# LANGFUSE_INGESTION_BUFFER_TTL_SECONDS=
-# LANGFUSE_INGESTION_FLUSH_DELAY_MS= 
-# LANGFUSE_INGESTION_FLUSH_ATTEMPTS= 
-# LANGFUSE_INGESTION_FLUSH_PROCESSING_CONCURRENCY=
-# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_BATCH_SIZE= 
+# LANGFUSE_INGESTION_QUEUE_DELAY_SECONDS=
+# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_BATCH_SIZE=
 # LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS= 
 # LANGFUSE_INGESTION_CLICKHOUSE_MAX_ATTEMPTS=
-# LANGFUSE_LOG_LEVEL= 
+# LANGFUSE_LEGACY_INGESTION_WORKER_CONCURRENCY=
+# LANGFUSE_ASYNC_INGESTION_PROCESSING="true"
+# QUEUE_CONSUMER_LEGACY_INGESTION_QUEUE_IS_ENABLED="true"
 
 ## END Langfuse V3 Ingestion

.github/dependabot.yml

@@ -8,6 +8,7 @@ updates:
   - package-ecosystem: npm
     directory: "/" # Location of package manifests
     rebase-strategy: "disabled" # use dependabot-rebase-stale
+    open-pull-requests-limit: 10
     schedule:
       interval: "daily"
     versioning-strategy: "increase"
@@ -19,17 +20,29 @@ updates:
       - dependency-name: "@types/node"
       - dependency-name: "@trpc/*"
     groups:
-      sentry:
-        patterns:
-          - "@sentry/*"
       prisma:
         patterns:
           - "prisma"
-          - "@prisma/*"
+          - "@prisma/client"
       next:
         patterns:
           - "eslint-config-next"
           - "next"
-      patches:
-        update-types:
-          - "patch"
+      lodash:
+        patterns:
+          - "lodash"
+          - "@types/lodash"
+      express:
+        patterns:
+          - "express"
+          - "@types/express"
+      observability:
+        patterns:
+          - "dd-trace"
+          - "@opentelemetry/*"
+          - "@appsignal/opentelemetry-instrumentation-bullmq"
+          - "@prisma/instrumentation"
+          - "@sentry/*"
+      radix-ui:
+        patterns:
+          - "@radix-ui/*"

.github/workflows/_deploy_ecs_service.yml

@@ -0,0 +1,75 @@
+name: WorkflowCall - Deploy to ECS Service
+on:
+  workflow_call:
+    inputs:
+      environment:
+        type: string
+        description: Deployment environment
+        required: true
+      service:
+        type: string
+        description: Name of the service to be deployed, e.g. web-ingestion, web, or worker.
+        required: true
+jobs:
+  ecs-deploy:
+    runs-on: ubuntu-latest
+    environment: ${{ inputs.environment }}
+    steps:
+      - name: Get app name
+        uses: winterjung/split@v2
+        id: split
+        with:
+          msg: ${{ inputs.service }}
+          separator: "-"
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Authenticate with AWS
+        # GitHub/AWS recommend to use OIDC here: https://github.com/aws-actions/configure-aws-credentials?tab=readme-ov-file#oidc
+        # Probably more painful to configure, but would remove all long-lived credentials.
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_REGION }}
+      - name: Login to AWS ECR
+        id: login-ecr
+        uses: aws-actions/amazon-ecr-login@v2
+      - name: Build, tag, and push Docker image
+        env:
+          REGISTRY: ${{ steps.login-ecr.outputs.registry }}
+          REPOSITORY: ${{ steps.split.outputs._0 }}
+          IMAGE_TAG: ${{ github.sha }}
+        run: |
+          docker build \
+            -t $REGISTRY/$REPOSITORY:$IMAGE_TAG \
+            -f ./${{ steps.split.outputs._0 }}/Dockerfile \
+            --build-arg NEXT_PUBLIC_LANGFUSE_CLOUD_REGION=${{ vars.NEXT_PUBLIC_LANGFUSE_CLOUD_REGION }} \
+            --build-arg NEXT_LANGFUSE_TRACING_SAMPLE_RATE=${{ vars.NEXT_LANGFUSE_TRACING_SAMPLE_RATE }} \
+            --build-arg NEXT_PUBLIC_SENTRY_ENVIRONMENT=${{ vars.NEXT_PUBLIC_SENTRY_ENVIRONMENT }} \
+            --build-arg NEXT_PUBLIC_DEMO_ORG_ID=${{ vars.NEXT_PUBLIC_DEMO_ORG_ID }} \
+            --build-arg NEXT_PUBLIC_DEMO_PROJECT_ID=${{ vars.NEXT_PUBLIC_DEMO_PROJECT_ID }} \
+            --build-arg NEXT_PUBLIC_SENTRY_DSN=${{ vars.NEXT_PUBLIC_SENTRY_DSN }} \
+            --build-arg NEXT_PUBLIC_BUILD_ID=${{ github.sha }} \
+            --build-arg NEXT_PUBLIC_POSTHOG_KEY=${{ vars.NEXT_PUBLIC_POSTHOG_KEY }} \
+            --build-arg NEXT_PUBLIC_POSTHOG_HOST=${{ vars.NEXT_PUBLIC_POSTHOG_HOST }} \
+            --build-arg NEXT_PUBLIC_CRISP_WEBSITE_ID=${{ vars.NEXT_PUBLIC_CRISP_WEBSITE_ID }} \
+            --build-arg SENTRY_AUTH_TOKEN=${{ secrets.SENTRY_AUTH_TOKEN }} \
+            --build-arg SENTRY_ORG=${{ vars.SENTRY_ORG }} \
+            --build-arg SENTRY_PROJECT=${{ vars.SENTRY_PROJECT }} \
+            .
+          docker push $REGISTRY/$REPOSITORY:$IMAGE_TAG
+
+      - name: Render AWS ECS Task Definition
+        id: render-task-definition
+        uses: aws-actions/amazon-ecs-render-task-definition@v1
+        with:
+          container-name: ${{ inputs.service }}
+          image: ${{ steps.login-ecr.outputs.registry }}/${{ steps.split.outputs._0 }}:${{ github.sha }}
+          task-definition-family: ${{ inputs.environment }}-${{ inputs.service }}
+      - name: Update AWS ECS Service
+        uses: aws-actions/amazon-ecs-deploy-task-definition@v2
+        with:
+          task-definition: ${{ steps.render-task-definition.outputs.task-definition }}
+          service: ${{ inputs.environment }}-${{ inputs.service }}
+          cluster: ${{ inputs.environment }}-cluster
+          wait-for-service-stability: true

.github/workflows/ci.yml.template

@@ -22,7 +22,7 @@ jobs:
 
     steps:
       - name: Checkout repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Start containers
         run: docker compose -f "docker-compose.yml" up -d --build
@@ -31,7 +31,7 @@ jobs:
         uses: pnpm/action-setup@v2.2.4
 
       - name: Setup Node 18
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18
 

.github/workflows/codeql.yml

@@ -0,0 +1,92 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: ["main", "production", "v*"]
+  pull_request:
+    branches: ["main", "production", "v*"]
+  schedule:
+    - cron: "31 13 * * 0"
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - language: javascript-typescript
+            build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v3
+        with:
+          languages: ${{ matrix.language }}
+          build-mode: ${{ matrix.build-mode }}
+          # If you wish to specify custom queries, you can do so here or in a config file.
+          # By default, queries listed here will override any specified in a config file.
+          # Prefix the list here with "+" to use these queries and those in the config file.
+
+          # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+          # queries: security-extended,security-and-quality
+
+      # If the analyze step fails for one of the languages you are analyzing with
+      # "We were unable to automatically build your code", modify the matrix above
+      # to set the build mode to "manual" for that language. Then modify this step
+      # to build your code.
+      # ℹ️ Command-line programs to run using the OS shell.
+      # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+      - if: matrix.build-mode == 'manual'
+        shell: bash
+        run: |
+          echo 'If you are using a "manual" build mode for one or more of the' \
+            'languages you are analyzing, replace this with the commands to build' \
+            'your code, for example:'
+          echo '  make bootstrap'
+          echo '  make release'
+          exit 1
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v3
+        with:
+          category: "/language:${{matrix.language}}"

.github/workflows/deploy.yml

@@ -0,0 +1,106 @@
+on:
+  push:
+    branches:
+      - main
+      - production
+  workflow_dispatch:
+    inputs:
+      service:
+        description: 'Service to be deployed'
+        type: choice
+        options:
+          - all
+          - web
+          - web-ingestion
+          - worker
+        required: true
+      environment:
+        description: 'Environment to deploy to'
+        type: choice
+        options:
+          - staging
+          - prod-eu-temp
+          - prod-eu
+          - prod-us
+        required: true
+
+concurrency:
+  # Support concurrent `push` and `workflow_dispatch`` actions
+  group: deploy-${{ github.event_name }}-${{ github.ref }}
+  cancel-in-progress: true
+
+name: Deploy to ECS
+jobs:
+  affected-services:
+    runs-on: ubuntu-latest
+    outputs:
+      services: ${{ steps.affected-services.outputs.result }}
+    steps:
+      - name: Get affected services
+        id: affected-services
+        uses: actions/github-script@v7
+        with:
+          script: |
+            if (context.eventName === "workflow_dispatch") {
+              if (context.payload.inputs.service === "all") {
+                return `["web", "web-ingestion", "worker"]`
+              }
+              return `["${context.payload.inputs.service}"]`
+            }
+            if (context.eventName === "push") {
+              return `["web", "web-ingestion", "worker"]`
+            }
+            return "[]"
+          result-encoding: string
+      - name: Print services to build
+        uses: actions/github-script@v7
+        env:
+          services: ${{ steps.affected-services.outputs.result }}
+        with:
+          result-encoding: string
+          script: |
+            console.log('Services', `${process.env.services}` ?? 'n/a');
+
+  affected-environments:
+    runs-on: ubuntu-latest
+    outputs:
+      environments: ${{ steps.affected-environments.outputs.result }}
+    steps:
+      - name: Get affected environments
+        id: affected-environments
+        uses: actions/github-script@v7
+        with:
+          script: |
+            if (context.eventName === "workflow_dispatch") {
+              return `["${context.payload.inputs.environment}"]`
+            }
+            if (context.eventName === "push") {
+              if (context.ref === "refs/heads/main") {
+                return `["staging"]`
+              }
+              if (context.ref === "refs/heads/production") {
+                return `["prod-eu-temp", "prod-eu", "prod-us"]`
+              }
+            }
+            return "[]"
+          result-encoding: string
+      - name: Print environments to build
+        uses: actions/github-script@v7
+        env:
+          environments: ${{ steps.affected-environments.outputs.result }}
+        with:
+          result-encoding: string
+          script: |
+            console.log('Environments', `${process.env.environments}` ?? 'n/a');
+
+  ecs-deploy:
+    uses: ./.github/workflows/_deploy_ecs_service.yml
+    needs: [affected-services, affected-environments]
+    secrets: inherit
+    strategy:
+      matrix:
+        service: ${{ fromJson(needs.affected-services.outputs.services) }}
+        environment: ${{ fromJson(needs.affected-environments.outputs.environments) }}
+    with:
+      service: ${{ matrix.service }}
+      environment: ${{ matrix.environment }}

.github/workflows/licencecheck.yml

@@ -14,10 +14,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Setup node
-        uses: actions/setup-node@v2
+        uses: actions/setup-node@v4
         with:
           node-version: 18
 

.github/workflows/pipeline.yml

@@ -16,11 +16,11 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
           version: 9.5.0
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: "pnpm"
@@ -35,24 +35,22 @@ jobs:
         run: pnpm run lint
 
   test-docker-build:
+    timeout-minutes: 20
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
-
+        uses: actions/checkout@v4
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
+      - name: Set NEXT_PUBLIC_BUILD_ID
+        run: echo "NEXT_PUBLIC_BUILD_ID=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
       - name: Build and run both images from compose
         run: |
           docker compose -f docker-compose.build.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
-
-      - name: Check server health
-        run: |
-          timeout 10 bash -c 'until curl -f http://localhost:3000/api/public/health; do sleep 2; done'
-
-      - name: Check worker health
-        run: |
-          timeout 10 bash -c 'until curl -f http://localhost:3030/api/health; do sleep 2; done'
-
       - name: Ensure no unhealthy status
         run: |
           if docker-compose ps | grep "(unhealthy)"; then
@@ -61,6 +59,12 @@ jobs:
           else
             echo "All services are healthy"
           fi
+      - name: Check worker health
+        run: |
+          timeout 10 bash -c 'until curl -f http://localhost:3030/api/health; do sleep 2; done'
+      - name: Check server health
+        run: |
+          timeout 10 bash -c 'until curl -f http://localhost:3000/api/public/health; do sleep 2; done'
 
   tests-web:
     timeout-minutes: 20
@@ -75,27 +79,28 @@ jobs:
         uses: pierotofy/set-swap-space@master
         with:
           swap-size-gb: 10
-
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
           version: 9.5.0
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
       - name: Use Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node-version }}
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: install dependencies
         run: |
           pnpm install
-
       - name: Load default env
         run: |
           cp .env.dev.example .env
-          grep -v '^REDIS_HOST=' .env.dev.example > web/.env
-
+          grep -v -e '^S3_BUCKET_NAME=' -e '^REDIS_HOST=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev.example > .env
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
@@ -103,18 +108,23 @@ jobs:
           docker compose ps
         env:
           POSTGRES_VERSION: ${{ matrix.postgres-version }}
-
       - name: Seed DB
         run: |
           pnpm run db:migrate
-          pnpm run db:seed
-
       - name: Build
         run: pnpm run build
-
       - name: Start Langfuse
         run: (pnpm run start&)
-
+        env:
+          LANGFUSE_INIT_ORG_ID: "seed-org-id"
+          LANGFUSE_INIT_ORG_NAME: "Seed Org"
+          LANGFUSE_INIT_PROJECT_ID: "7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"
+          LANGFUSE_INIT_PROJECT_NAME: "Seed Project"
+          LANGFUSE_INIT_PROJECT_PUBLIC_KEY: "pk-lf-1234567890"
+          LANGFUSE_INIT_PROJECT_SECRET_KEY: "sk-lf-1234567890"
+          LANGFUSE_INIT_USER_EMAIL: "demo@langfuse.com"
+          LANGFUSE_INIT_USER_NAME: "Demo User"
+          LANGFUSE_INIT_USER_PASSWORD: "password"
       - name: run tests
         run: pnpm --filter=web run test
 
@@ -131,98 +141,151 @@ jobs:
         uses: pierotofy/set-swap-space@master
         with:
           swap-size-gb: 10
-
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
           version: 9.5.0
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
       - name: Use Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node-version }}
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: install dependencies
         run: |
           pnpm install
-
       - name: Install golang-migrate for Clickhouse migrations
         run: |
           curl -L https://github.com/golang-migrate/migrate/releases/download/v4.16.2/migrate.linux-amd64.tar.gz | tar xvz
           sudo mv migrate /usr/bin/migrate
           which migrate
-
       - name: Load default env
         run: |
           cp .env.dev.example .env
           cp .env.dev.example web/.env
           cp .env.dev.example worker/.env
-
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
           docker compose ps
-
+      - name: Ensure no unhealthy status
+        run: |
+          if docker compose ps | grep "(unhealthy)"; then
+            echo "One or more services are unhealthy"
+            exit 1
+          else
+            echo "All services are healthy"
+          fi
       - name: Seed DB
         run: |
-          pnpm run --filter=shared ch:up
           pnpm run db:migrate
           pnpm run db:seed
-
+          pnpm run --filter=shared ch:up
       - name: Build
         run: pnpm --filter=worker... run build
-
       - name: run tests
         run: pnpm --filter=worker run test
 
   e2e-tests:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
           version: 9.5.0
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
       - name: install dependencies
         run: |
           pnpm install
-
       - name: Load default env
         run: |
           cp .env.dev.example .env
           cp .env.dev.example web/.env
-
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
           docker compose ps
           sleep 5 # Wait for PostgreSQL to accept connections
-
       - name: Seed DB
         run: |
           pnpm run db:migrate
           pnpm run db:seed
-
       - name: Build
         run: pnpm run build
-
       - name: Install playwright
         run: pnpm --filter=web exec playwright install --with-deps
-
       - name: Run e2e tests
         run: pnpm --filter=web run test:e2e
 
+  e2e-server-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
+      - uses: pnpm/action-setup@v3
+        with:
+          version: 9.5.0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: "pnpm"
+          cache-dependency-path: "pnpm-lock.yaml"
+      - name: install dependencies
+        run: |
+          pnpm install
+      - name: Load default env
+        run: |
+          cp .env.dev.example .env
+          echo "LANGFUSE_ASYNC_INGESTION_PROCESSING=true" >> .env
+          echo "LANGFUSE_CACHE_API_KEY_ENABLED=true" >> .env
+          echo "LANGFUSE_CACHE_PROMPT_ENABLED=true" >> .env
+      - name: Run + migrate
+        run: |
+          docker compose -f docker-compose.dev.yml up -d
+          docker compose ps
+          sleep 5 # Wait for PostgreSQL to accept connections
+      - name: Seed DB
+        run: |
+          pnpm run db:migrate
+          pnpm run db:seed:examples
+      - name: Build
+        run: pnpm run build
+      - name: Run server
+        run: (pnpm run start&)
+      - name: Run e2e tests
+        run: pnpm --filter=web run test:e2e:server
+
   all-ci-passed:
     # This allows us to have a branch protection rule for tests and deploys with matrix
     runs-on: ubuntu-latest
-    needs: [lint, tests-web, tests-worker, e2e-tests, test-docker-build]
+    needs:
+      [
+        lint,
+        tests-web,
+        tests-worker,
+        e2e-tests,
+        test-docker-build,
+        e2e-server-tests,
+      ]
     if: always()
     steps:
       - name: Successful deploy
@@ -248,35 +311,31 @@ jobs:
         with:
           version: 9.5.0
       - name: Setup node
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 20
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: Checkout
-        uses: actions/checkout@v3
-
+        uses: actions/checkout@v4
+      - name: Set NEXT_PUBLIC_BUILD_ID
+        run: echo "NEXT_PUBLIC_BUILD_ID=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
       - name: Log in to the GitHub Container registry
         uses: docker/login-action@v2
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Log in to Docker Hub
         uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
-
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
         with:
           driver-opts: network=host
-
       - name: Extract metadata (tags, labels) for Docker
         id: meta-web
         uses: docker/metadata-action@v4
@@ -291,7 +350,6 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
-
       - name: Build and push Docker image (web)
         uses: docker/build-push-action@v4
         with:
@@ -303,7 +361,6 @@ jobs:
           platforms: |
             linux/amd64
             ${{ startsWith(github.ref, 'refs/tags/') && 'linux/arm64' || '' }}
-
       - name: Extract metadata (tags, labels) for Docker
         id: meta-worker
         uses: docker/metadata-action@v4
@@ -318,7 +375,6 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
-
       - name: Build and push Docker image (worker)
         uses: docker/build-push-action@v4
         with:

.github/workflows/porter_stack_web_eu_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to web
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-      - name: Set Github tag
-        id: vars
-        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-      - name: Setup porter
-        uses: porter-dev/setup-porter@v0.1.0
-      - name: Deploy stack
-        timeout-minutes: 30
-        run: exec porter apply
-        env:
-          PORTER_CLUSTER: "4060"
-          PORTER_DEPLOYMENT_TARGET_ID: 3be075c0-b121-4123-aec1-5dc571626b0c
-          PORTER_HOST: https://dashboard.porter.run
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: web
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4060 }}

.github/workflows/porter_stack_web_staging.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - main
-name: Deploy to web (Staging)
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-      - name: Set Github tag
-        id: vars
-        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-      - name: Setup porter
-        uses: porter-dev/setup-porter@v0.1.0
-      - name: Deploy stack
-        timeout-minutes: 30
-        run: exec porter apply
-        env:
-          PORTER_CLUSTER: "4037"
-          PORTER_DEPLOYMENT_TARGET_ID: c22d8fa2-f97c-4e1f-9cae-83cc6bfbad35
-          PORTER_HOST: https://dashboard.getporter.dev
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: web
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4037 }}

.github/workflows/porter_stack_web_us_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to web (US temp)
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-      - name: Set Github tag
-        id: vars
-        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-      - name: Setup porter
-        uses: porter-dev/setup-porter@v0.1.0
-      - name: Deploy stack
-        timeout-minutes: 30
-        run: exec porter apply
-        env:
-          PORTER_CLUSTER: "4054"
-          PORTER_DEPLOYMENT_TARGET_ID: cddc0f2a-bb19-401a-9819-29f59f76b101
-          PORTER_HOST: https://dashboard.porter.run
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: web
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4054 }}

.github/workflows/porter_stack_worker_eu_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to worker (EU temp)
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-      - name: Set Github tag
-        id: vars
-        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-      - name: Setup porter
-        uses: porter-dev/setup-porter@v0.1.0
-      - name: Deploy stack
-        timeout-minutes: 30
-        run: exec porter apply
-        env:
-          PORTER_CLUSTER: "4060"
-          PORTER_DEPLOYMENT_TARGET_ID: 3be075c0-b121-4123-aec1-5dc571626b0c
-          PORTER_HOST: https://dashboard.porter.run
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: worker
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4060 }}

.github/workflows/porter_stack_worker_staging.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - main
-name: Deploy to worker (staging)
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-      - name: Set Github tag
-        id: vars
-        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-      - name: Setup porter
-        uses: porter-dev/setup-porter@v0.1.0
-      - name: Deploy stack
-        timeout-minutes: 30
-        run: exec porter apply
-        env:
-          PORTER_CLUSTER: "4037"
-          PORTER_DEPLOYMENT_TARGET_ID: c22d8fa2-f97c-4e1f-9cae-83cc6bfbad35
-          PORTER_HOST: https://dashboard.getporter.dev
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: worker
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4037 }}

.github/workflows/porter_stack_worker_us_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to worker (US temp)
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-      - name: Set Github tag
-        id: vars
-        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-      - name: Setup porter
-        uses: porter-dev/setup-porter@v0.1.0
-      - name: Deploy stack
-        timeout-minutes: 30
-        run: exec porter apply
-        env:
-          PORTER_CLUSTER: "4054"
-          PORTER_DEPLOYMENT_TARGET_ID: cddc0f2a-bb19-401a-9819-29f59f76b101
-          PORTER_HOST: https://dashboard.porter.run
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: worker
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4054 }}

.github/workflows/snyk.yml

@@ -1,11 +1,11 @@
 name: Snyk Container
 on:
-  push:
-    branches-ignore:
-      - "dependabot/**"
   pull_request:
     branches:
       - "**"
+  push:
+    branches:
+      - main
 
 jobs:
   snyk:

.vscode/launch.json

@@ -2,10 +2,10 @@
   "version": "0.2.0",
   "configurations": [
     {
-      "name": "Next.js: debug server-side",
+      "name": "Web and Worker: server side",
       "type": "node-terminal",
       "request": "launch",
-      "command": "npm run dev"
+      "command": "pnpm run dev"
     },
     {
       "name": "Next.js: debug client-side",

README.md

@@ -1,8 +1,7 @@
-![langfuse_logo_1024](https://github.com/user-attachments/assets/f17d8fc1-8206-4afa-a5ec-774826be88a8)
+![Langfuse GitHub Banner](https://github.com/langfuse/langfuse/assets/121163007/6035f0f3-d691-4963-b5d0-10cf506e9d42)
 
-<div align="center"><h1> Langfuse: Open Source LLM Engineering Platform</h4></div>
-<div align="center"><h2> Debug and improve your LLM app</h4></div>
-<div align="center"><h3> LLM Observability, Prompt Management, LLM Evaluations, Datasets, LLM Metrics and Prompt Playground</h4></div>
+<div align="center"><h1>Langfuse: Open Source LLM Engineering Platform</h1></div>
+<div align="center"><h4>LLM Observability, Prompt Management, LLM Evaluations,<br/>Datasets, LLM Metrics, and Prompt Playground</h4></div>
 
 <div align="center">
    <div>
@@ -28,15 +27,15 @@
    </div>
    <span>Langfuse uses <a href="https://github.com/orgs/langfuse/discussions"><strong>Github Discussions</strong></a>  for Support and Feature Requests.</span>
    <br/>
-   <span>We're hiring. <a href="https://langfuse.com/careers"><strong>Join us</strong></a> in Backend Engineering, Product Engineering, and Developer Relations.</span>
+   <span>We're hiring. <a href="https://langfuse.com/careers"><strong>Join us</strong></a> in Product Engineering and Developer Relations.</span>
    <br/>
    <br/>
    <div>
       <a href="https://github.com/langfuse/langfuse/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-red.svg?style=flat-square" alt="MIT License"></a>
       <a href="https://www.ycombinator.com/companies/langfuse"><img src="https://img.shields.io/badge/Y%20Combinator-W23-orange?style=flat-square" alt="Y Combinator W23"></a>
       <a href="https://github.com/langfuse/langfuse/pkgs/container/langfuse"><img alt="Docker Image" src="https://img.shields.io/badge/docker-langfuse-blue?logo=Docker&logoColor=white&style=flat-square"></a>
-      <a href="https://www.npmjs.com/package/langfuse"><img src="https://img.shields.io/npm/v/langfuse?style=flat-square&label=npm+langfuse" alt="langfuse npm package"></a>
-      <a href="https://pypi.python.org/pypi/langfuse"><img src="https://img.shields.io/pypi/v/langfuse.svg?style=flat-square&label=pypi+langfuse" alt="langfuse Python package on PyPi"></a>
+      <a href="https://pypi.python.org/pypi/langfuse"><img src="https://img.shields.io/pypi/dm/langfuse?style=flat-square&logo=python&logoColor=white&label=pypi%20langfuse&color=blue" alt="langfuse Python package on PyPi"></a>
+      <a href="https://www.npmjs.com/package/langfuse"><img src="https://img.shields.io/npm/dm/langfuse?style=flat-square&logo=npm&logoColor=white&label=npm%20langfuse&color=blue" alt="langfuse npm package"></a>
    </div>
 </div>
 </br>
@@ -93,10 +92,10 @@ docker compose up -d
 
 ### Self-host (docker)
 
-Langfuse is simple to self-host and keep updated. It currently requires only a single docker container.
+Langfuse is simple to self-host and keep updated. It currently requires only a single docker container and a postgres database.
 [→ Self Hosting Instructions](https://langfuse.com/docs/deployment/self-host)
 
-Templated deployments: [Railway, GCP Cloud Run, AWS Fargate, Kubernetes and others](https://langfuse.com/docs/deployment/self-host#platform-specific-information)
+Templated deployments: [Railway, GCP, AWS, Azure, Kubernetes and others](https://langfuse.com/docs/deployment/self-host#platform-specific-information)
 
 ## Get Started
 
@@ -108,31 +107,31 @@ You need a Langfuse public and secret key to get started. Sign up [here](https:/
 
 Note: We recommend using our fully async, typed [SDKs](https://langfuse.com/docs/sdk) that allow you to instrument any LLM application with any underlying model. They are available in [Python (Decorators)](https://langfuse.com/docs/sdk/python) & [JS/TS](https://langfuse.com/docs/sdk/typescript). The SDKs will always be the most fully featured and stable way to ingest data into Langfuse.
 
-You may want to use another integration to get started quickly or implement a use case that we do not yet support. However, we recommend to migrate to the Langfuse SDKs over time to ensure performance and stability.
-
 See the [→ Quickstart](https://langfuse.com/docs/get-started) to integrate Langfuse.
 
 ### LLM Observability Integrations
 
-| Integration                                              | Supports                   | Description                                                                                                                                      |
-| -------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
-| [SDK](/docs/sdk)                                         | Python, JS/TS              | Manual instrumentation using the SDKs for full flexibility.                                                                                      |
-| [OpenAI](/docs/integrations/openai)                      | Python, JS/TS              | Automated instrumentation using drop-in replacement of OpenAI SDK.                                                                               |
-| [Langchain](/docs/integrations/langchain)                | Python, JS/TS              | Automated instrumentation by passing callback handler to Langchain application.                                                                  |
-| [LlamaIndex](/docs/integrations/llama-index/get-started) | Python                     | Automated instrumentation via LlamaIndex callback system.                                                                                        |
-| [Haystack](/docs/integrations/haystack)                  | Python                     | Automated instrumentation via Haystack content tracing system.                                                                                   |
-| [LiteLLM](/docs/integrations/litellm)                    | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |
-| [API](/docs/api)                                         |                            | Directly call the public API. OpenAPI spec available.                                                                                            |
+| Integration                                                                  | Supports                   | Description                                                                                                                                      |
+| ---------------------------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
+| [SDK](https://langfuse.com/docs/sdk)                                         | Python, JS/TS              | Manual instrumentation using the SDKs for full flexibility.                                                                                      |
+| [OpenAI](https://langfuse.com/docs/integrations/openai)                      | Python, JS/TS              | Automated instrumentation using drop-in replacement of OpenAI SDK.                                                                               |
+| [Langchain](https://langfuse.com/docs/integrations/langchain)                | Python, JS/TS              | Automated instrumentation by passing callback handler to Langchain application.                                                                  |
+| [LlamaIndex](https://langfuse.com/docs/integrations/llama-index/get-started) | Python                     | Automated instrumentation via LlamaIndex callback system.                                                                                        |
+| [Haystack](https://langfuse.com/docs/integrations/haystack)                  | Python                     | Automated instrumentation via Haystack content tracing system.                                                                                   |
+| [LiteLLM](https://langfuse.com/docs/integrations/litellm)                    | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |
+| [Vercel AI SDK](https://langfuse.com/docs/integrations/vercel-ai-sdk)        | JS/TS                      | TypeScript toolkit designed to help developers build AI-powered applications with React, Next.js, Vue, Svelte, Node.js.                          |
+| [API](https://langfuse.com/docs/api)                                         |                            | Directly call the public API. OpenAPI spec available.                                                                                            |
 
-Packages that integrate with Langfuse:
+Packages integrated with Langfuse:
 
-| Name                                                       | Description                                                                                                             |
-| ---------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
-| [Instructor](/docs/integrations/instructor)                | Library to get structured LLM outputs (JSON, Pydantic)                                                                  |
-| [Mirascope](/docs/integrations/mirascope)                  | Python toolkit for building LLM applications.                                                                           |
-| [AI SDK by Vercel](/docs/sdk/typescript/example-vercel-ai) | Typescript SDK that makes streaming LLM outputs super easy.                                                             |
-| [Flowise](/docs/integrations/flowise)                      | JS/TS no-code builder for customized LLM flows.                                                                         |
-| [Langflow](/docs/integrations/langflow)                    | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
+| Name                                                            | Description                                                                                                             |
+| --------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+| [Instructor](https://langfuse.com/docs/integrations/instructor) | Library to get structured LLM outputs (JSON, Pydantic)                                                                  |
+| [Dify](https://langfuse.com/docs/integrations/dify)             | Open source LLM app development platform with no-code builder.                                                          |
+| [Ollama](https://langfuse.com/docs/integrations/ollama)         | Easily run open source LLMs on your own machine.                                                                        |
+| [Mirascope](https://langfuse.com/docs/integrations/mirascope)   | Python toolkit for building LLM applications.                                                                           |
+| [Flowise](https://langfuse.com/docs/integrations/flowise)       | JS/TS no-code builder for customized LLM flows.                                                                         |
+| [Langflow](https://langfuse.com/docs/integrations/langflow)     | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
 
 ## Questions and feedback
 
@@ -140,13 +139,13 @@ Packages that integrate with Langfuse:
 
 - [Roadmap](https://langfuse.com/roadmap)
 - [GitHub Discussions](https://github.com/orgs/langfuse/discussions)
-- [Feature Requests](https://langfuse.com/idea
+- [Feature Requests](https://langfuse.com/ideas)
 
 ### Support and feedback
 
 In order of preference the best way to communicate with us:
 
-- [GitHub Discussions](https://github.com/orgs/langfuse/discussions): Contribute [ideas](https://langfuse.com/idea) [support requests](https://github.com/orgs/langfuse/discussions/categories/support) and [report bugs](https://github.com/langfuse/langfuse/issues/new?labels=%F0%9F%90%9E%E2%9D%94+unconfirmed+bug&projects=&template=bug_report.yml&title=bug%3A+) (preferred as we create a permanent, indexed artifact for other community members)
+- [GitHub Discussions](https://github.com/orgs/langfuse/discussions) (preferred): Contribute [ideas](https://langfuse.com/ideas), [support requests](https://langfuse.com/gh-support) and [report bugs](https://langfuse.com/issues)
 - [Discord](https://langfuse.com/discord): community support
 - Privately: contact at langfuse dot com
 

careers

@@ -3,7 +3,6 @@ Join us in scaling Langfuse in Berlin, Germany. We are an open source company, w
 
 _Open Roles_
 
-- Backend Engineer, 70-130k EUR, 0.25-0.75% Equity, https://www.ycombinator.com/companies/langfuse/jobs/mnrdwla-backend-engineer
 - Product Engineer, 70-130k EUR, 0.25-0.75% Equity, https://www.ycombinator.com/companies/langfuse/jobs/aAvmoFB-product-engineer
 - Developer Advocate, 60-110k EUR, 0.25-0.5% Equity, https://www.ycombinator.com/companies/langfuse/jobs/uHysbKH-developer-advocate-devrel
 

docker-compose.build.yml

@@ -20,8 +20,15 @@ services:
       - NEXTAUTH_URL=http://localhost:3000
       - TELEMETRY_ENABLED=${TELEMETRY_ENABLED:-true}
       - LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES=${LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES:-false}
-      - LANGFUSE_WORKER_HOST=${LANGFUSE_WORKER_HOST:-worker}
-      - LANGFUSE_WORKER_PASSWORD=${LANGFUSE_WORKER_PASSWORD:-mybasicauthsecret}
+      - LANGFUSE_INIT_ORG_ID=${LANGFUSE_INIT_ORG_ID:-}
+      - LANGFUSE_INIT_ORG_NAME=${LANGFUSE_INIT_ORG_NAME:-}
+      - LANGFUSE_INIT_PROJECT_ID=${LANGFUSE_INIT_PROJECT_ID:-}
+      - LANGFUSE_INIT_PROJECT_NAME=${LANGFUSE_INIT_PROJECT_NAME:-}
+      - LANGFUSE_INIT_PROJECT_PUBLIC_KEY=${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
+      - LANGFUSE_INIT_PROJECT_SECRET_KEY=${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
+      - LANGFUSE_INIT_USER_EMAIL=${LANGFUSE_INIT_USER_EMAIL:-}
+      - LANGFUSE_INIT_USER_NAME=${LANGFUSE_INIT_USER_NAME:-}
+      - LANGFUSE_INIT_USER_PASSWORD=${LANGFUSE_INIT_USER_PASSWORD:-}
     restart: always
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:3000/api/public/health"]
@@ -49,7 +56,6 @@ services:
       - REDIS_HOST=${REDIS_HOST:-redis}
       - REDIS_PORT=${REDIS_PORT:-6379}
       - REDIS_AUTH=${REDIS_AUTH:-myredissecret}
-      - LANGFUSE_WORKER_PASSWORD=${LANGFUSE_WORKER_PASSWORD:-mybasicauthsecret}
     restart: always
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:3030/api/health"]

docker-compose.dev.yml

@@ -17,6 +17,38 @@ services:
     depends_on:
       - postgres
 
+  minio:
+    image: minio/minio
+    container_name: minio
+    command: server /data --console-address ":9001"
+    environment:
+      MINIO_ACCESS_KEY: minio
+      MINIO_SECRET_KEY: miniosecret
+    ports:
+      - "9090:9000"
+      - "9091:9001"
+    volumes:
+      - langfuse_minio_data:/data
+    healthcheck:
+      test: ["CMD", "mc", "ready", "local"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 5s
+
+  miniocreatebucket:
+    image: minio/mc
+    container_name: miniocreatebucket
+    entrypoint: ["/bin/sh", "-c"]
+    command: >
+      "mc alias set minio http://minio:9000 minio miniosecret && 
+       mc rm -r --force minio/mybucket || true &&
+       mc mb minio/mybucket && 
+       mc policy set download minio/mybucket"
+    depends_on:
+      minio:
+        condition: service_healthy
+
   redis:
     image: redis:7.2.4
     restart: always
@@ -45,3 +77,5 @@ volumes:
     driver: local
   langfuse_clickhouse_logs:
     driver: local
+  langfuse_minio_data:
+    driver: local

docker-compose.yml

@@ -14,6 +14,15 @@ services:
       - NEXTAUTH_URL=http://localhost:3000
       - TELEMETRY_ENABLED=${TELEMETRY_ENABLED:-true}
       - LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES=${LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES:-false}
+      - LANGFUSE_INIT_ORG_ID=${LANGFUSE_INIT_ORG_ID:-}
+      - LANGFUSE_INIT_ORG_NAME=${LANGFUSE_INIT_ORG_NAME:-}
+      - LANGFUSE_INIT_PROJECT_ID=${LANGFUSE_INIT_PROJECT_ID:-}
+      - LANGFUSE_INIT_PROJECT_NAME=${LANGFUSE_INIT_PROJECT_NAME:-}
+      - LANGFUSE_INIT_PROJECT_PUBLIC_KEY=${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
+      - LANGFUSE_INIT_PROJECT_SECRET_KEY=${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
+      - LANGFUSE_INIT_USER_EMAIL=${LANGFUSE_INIT_USER_EMAIL:-}
+      - LANGFUSE_INIT_USER_NAME=${LANGFUSE_INIT_USER_NAME:-}
+      - LANGFUSE_INIT_USER_PASSWORD=${LANGFUSE_INIT_USER_PASSWORD:-}
 
   db:
     image: postgres

ee/package.json

@@ -25,7 +25,9 @@
   },
   "dependencies": {
     "@langfuse/shared": "workspace:*",
-    "next": "^14.2.3",
+    "@opentelemetry/api": ">=1.0.0 <1.10.0",
+    "axios": "^1.7.7",
+    "next": "^14.2.15",
     "next-auth": "^4.24.7",
     "zod": "^3.23.8"
   },
@@ -38,9 +40,14 @@
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",
     "eslint-plugin-prettier": "^5.1.3",
-    "prettier": "^3.2.5",
+    "prettier": "^3.3.3",
     "ts-node": "^10.9.2",
     "tsc-watch": "^6.2.0",
     "typescript": "^5.4.5"
+  },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.0"
+    }
   }
 }

ee/prettierrc.json

@@ -1,4 +0,0 @@
-{
-  "trailingComma": "es5",
-  "printWidth": 120
-}

ee/src/env.ts

@@ -1,9 +1,12 @@
 import { z } from "zod";
-import { env as sharedEnv } from "@langfuse/shared";
+import { env as sharedEnv, removeEmptyEnvVariables } from "@langfuse/shared";
 
 const EnvSchema = z.object({
   NEXT_PUBLIC_LANGFUSE_CLOUD_REGION: z.string().optional(),
   LANGFUSE_EE_LICENSE_KEY: z.string().optional(),
 });
 
-export const env = { ...sharedEnv, ...EnvSchema.parse(process.env) };
+export const env = {
+  ...sharedEnv,
+  ...EnvSchema.parse(removeEmptyEnvVariables(process.env)),
+};

fern/apis/server/definition/comments.yml

@@ -0,0 +1,73 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  pagination: ./utils/pagination.yml
+  commons: ./commons.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    create:
+      docs: Create a comment. Comments may be attached to different object types (trace, observation, session, prompt).
+      method: POST
+      path: /comments
+      request: CreateCommentRequest
+      response: CreateCommentResponse
+    get:
+      docs: Get all comments
+      method: GET
+      path: /comments
+      request:
+        name: GetCommentsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: Page number, starts at 1.
+          limit:
+            type: optional<integer>
+            docs: Limit of items per page. If you encounter api issues due to too large page sizes, try to reduce the limit
+          objectType:
+            type: optional<string>
+            docs: Filter comments by object type (trace, observation, session, prompt).
+          objectId:
+            type: optional<string>
+            docs: Filter comments by object id. If objectType is not provided, an error will be thrown.
+          authorUserId:
+            type: optional<string>
+            docs: Filter comments by author user id.
+      response: GetCommentsResponse
+    get-by-id:
+      docs: Get a comment by id
+      method: GET
+      path: /comments/{commentId}
+      path-parameters:
+        commentId:
+          type: string
+          docs: The unique langfuse identifier of a comment
+      response: commons.Comment
+types:
+  CreateCommentRequest:
+    properties:
+      projectId:
+        type: string
+        docs: The id of the project to attach the comment to.
+      objectType:
+        type: string
+        docs: The type of the object to attach the comment to (trace, observation, session, prompt).
+      objectId:
+        type: string
+        docs: The id of the object to attach the comment to. If this does not reference a valid existing object, an error will be thrown.
+      content:
+        type: string
+        docs: The content of the comment. May include markdown. Currently limited to 500 characters.
+      authorUserId:
+        type: optional<string>
+        docs: The id of the user who created the comment.
+  CreateCommentResponse:
+    properties:
+      id:
+        type: string
+        docs: The id of the created object in Langfuse
+  GetCommentsResponse:
+    properties:
+      data: list<commons.Comment>
+      meta: pagination.MetaResponse

fern/apis/server/definition/commons.yml

@@ -240,6 +240,9 @@ types:
       configId:
         type: optional<string>
         docs: Reference a score config on a score. When set, config and score name must be equal and value must comply to optionally defined numerical range
+      queueId:
+        type: optional<string>
+        docs: Reference an annotation queue on a score. Populated if the score was initially created in an annotation queue.
   NumericScore:
     extends: BaseScore
     properties:
@@ -283,6 +286,18 @@ types:
       - double
       - string
     docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores
+
+  Comment:
+    properties:
+      id: string
+      projectId: string
+      createdAt: datetime
+      updatedAt: datetime
+      objectType: CommentObjectType
+      objectId: string
+      content: string
+      authorUserId: optional<string>
+
   Dataset:
     properties:
       id: string
@@ -402,6 +417,12 @@ types:
       - optional<integer>
       - optional<boolean>
       - optional<list<string>>
+  CommentObjectType:
+    enum:
+      - TRACE
+      - OBSERVATION
+      - SESSION
+      - PROMPT
   DatasetStatus:
     enum:
       - ACTIVE

fern/apis/server/definition/metrics.yml

@@ -31,10 +31,10 @@ service:
             docs: Optional filter for metrics where traces include all of these tags
           fromTimestamp:
             type: optional<datetime>
-            docs: Optional filter to only include traces on or after a certain datetime (ISO 8601)
+            docs: Optional filter to only include traces and observations on or after a certain datetime (ISO 8601)
           toTimestamp:
             type: optional<datetime>
-            docs: Optional filter to only include traces before a certain datetime (ISO 8601)
+            docs: Optional filter to only include traces and observations before a certain datetime (ISO 8601)
       response: DailyMetrics
 types:
   DailyMetrics:

fern/apis/server/definition/models.yml

@@ -55,7 +55,7 @@ types:
         type: string
       startDate:
         docs: Apply only to generations which are newer than this ISO date.
-        type: optional<date>
+        type: optional<datetime>
       unit:
         docs: Unit used by this model.
         type: commons.ModelUsageUnit

fern/apis/server/definition/score.yml

@@ -52,10 +52,17 @@ service:
           configId:
             type: optional<string>
             docs: Retrieve only scores with a specific configId.
+          queueId:
+            type: optional<string>
+            docs: Retrieve only scores with a specific annotation queueId.
           dataType:
             type: optional<commons.ScoreDataType>
             docs: Retrieve only scores with a specific dataType.
-      response: Scores
+          traceTags:
+            type: optional<list<string>>
+            allow-multiple: true
+            docs: Only scores linked to traces that include all of these tags will be returned.
+      response: GetScoresResponse
     get-by-id:
       docs: Get a score
       method: GET
@@ -132,7 +139,19 @@ types:
       id:
         type: string
         docs: The id of the created object in Langfuse
-  Scores:
+  GetScoresResponseTraceData:
     properties:
-      data: list<commons.Score>
+      userId:
+        type: optional<string>
+        docs: The user ID associated with the trace referenced by score
+      tags:
+        type: optional<list<string>>
+        docs: A list of tags associated with the trace referenced by score
+  GetScoresResponseData:
+    properties:
+      <<: commons.Score
+      trace: GetScoresResponseTraceData
+  GetScoresResponse:
+    properties:
+      data: list<GetScoresResponseData>
       meta: pagination.MetaResponse

fern/apis/server/generators.yml

@@ -3,32 +3,22 @@ groups:
   local:
     generators:
       - name: fernapi/fern-openapi
-        version: 0.0.28
+        version: 0.0.31
         output:
           location: local-file-system
           path: ../../../web/public/generated/api
-        config:
-          namespaceExport: Langfuse
-          allowCustomFetcher: true
       - name: fernapi/fern-python-sdk
-        version: 1.1.0-rc2
+        version: 2.16.0
         output:
           location: local-file-system
           path: ../../../generated/python
         config:
           client_class_name: FernLangfuse
           improved_imports: false
+          inline_request_params: false
           pydantic_config:
             require_optional_fields: false
             use_str_enums: false
-      - name: fernapi/fern-typescript-node-sdk
-        version: 0.7.1
-        output:
-          location: local-file-system
-          path: ../../../generated/typescript-server
-        config:
-          namespaceExport: Langfuse
-          allowCustomFetcher: true
       - name: fernapi/fern-postman
         version: 0.0.45
         output:

fern/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization": "finto",
-  "version": "0.30.3"
+  "version": "0.43.7"
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "langfuse",
-  "version": "2.70.1",
+  "version": "2.86.0",
   "author": "engineering@langfuse.com",
   "license": "MIT",
   "private": true,
@@ -18,6 +18,7 @@
     "nuke": "bash ./scripts/nuke.sh",
     "dx": "pnpm i && pnpm run infra:dev:up && pnpm --filter=shared run db:reset && pnpm --filter=shared run ch:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
     "dx-f": "pnpm i && pnpm run infra:dev:up && pnpm --filter=shared run db:reset -f && pnpm --filter=shared run ch:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
+    "dx:skip-infra": "pnpm i && pnpm --filter=shared run db:reset && pnpm --filter=shared run ch:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
     "build": "turbo run build",
     "start": "turbo run start",
     "dev": "turbo run dev",
@@ -32,7 +33,7 @@
     "braces": "3.0.3",
     "dotenv-cli": "^7.4.2",
     "husky": "^9.0.11",
-    "prettier": "^3.2.5",
+    "prettier": "^3.3.3",
     "release-it": "^17.3.0",
     "turbo": "^1.13.4"
   },
@@ -79,5 +80,10 @@
       }
     }
   },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.0"
+    }
+  },
   "packageManager": "pnpm@9.5.0"
 }

packages/config-eslint/package.json

@@ -11,7 +11,7 @@
     "@typescript-eslint/eslint-plugin": "^7.1.0",
     "@typescript-eslint/parser": "^7.12.0",
     "@vercel/style-guide": "^6.0.0",
-    "eslint-config-next": "^14.2.3",
+    "eslint-config-next": "^14.2.15",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-turbo": "^1.13.4",
     "eslint-plugin-only-warn": "^1.1.0",

packages/shared/clickhouse/migrations/0001_traces.up.sql

@@ -15,12 +15,13 @@ CREATE TABLE traces (
     `session_id` Nullable(String),
     `created_at` DateTime64(3) DEFAULT now(),
     `updated_at` DateTime64(3) DEFAULT now(),
+    event_ts DateTime64(3),
     INDEX idx_id id TYPE bloom_filter(0.001) GRANULARITY 1,
     INDEX idx_res_metadata_key mapKeys(metadata) TYPE bloom_filter(0.01) GRANULARITY 1,
     INDEX idx_res_metadata_value mapValues(metadata) TYPE bloom_filter(0.01) GRANULARITY 1
 ) ENGINE = ReplacingMergeTree Partition by toYYYYMM(timestamp)
 ORDER BY (
         project_id,
-        toUnixTimestamp(timestamp),
+        toDate(timestamp),
         id
-    );
+    );

packages/shared/clickhouse/migrations/0002_observations.up.sql

@@ -35,6 +35,7 @@ CREATE TABLE observations (
     `prompt_version` Nullable(UInt16),
     `created_at` DateTime64(3) DEFAULT now(),
     `updated_at` DateTime64(3) DEFAULT now(),
+    event_ts DateTime64(3),
     INDEX idx_id id TYPE bloom_filter() GRANULARITY 1,
     INDEX idx_trace_id trace_id TYPE bloom_filter() GRANULARITY 1,
     INDEX idx_project_id project_id TYPE bloom_filter() GRANULARITY 1,
@@ -44,7 +45,7 @@ CREATE TABLE observations (
 ORDER BY (
         project_id,
         `type`,
-        trace_id,
-        toUnixTimestamp(start_time),
+        toDate(start_time),
         id
-    );
+    );
+

packages/shared/clickhouse/migrations/0003_scores.up.sql

@@ -14,12 +14,13 @@ CREATE TABLE scores (
     `string_value` Nullable(String),
     `created_at` DateTime64(3) DEFAULT now(),
     `updated_at` DateTime64(3) DEFAULT now(),
+    event_ts DateTime64(3),
     INDEX idx_id id TYPE bloom_filter(0.001) GRANULARITY 1,
-    INDEX idx_project_id trace_id TYPE bloom_filter(0.001) GRANULARITY 1
+    INDEX idx_project_trace_observation (project_id, trace_id, observation_id) TYPE bloom_filter(0.001) GRANULARITY 1
 ) ENGINE = ReplacingMergeTree Partition by toYYYYMM(timestamp)
 ORDER BY (
         project_id,
-        trace_id,
-        toUnixTimestamp(timestamp),
+        toDate(timestamp),
+        name,
         id
-    );
+    )

packages/shared/clickhouse/migrations/0004_observations_wide.down.sql

@@ -0,0 +1,3 @@
+DROP TABLE IF EXISTS mv_observations_to_observations_wide;
+DROP TABLE IF EXISTS mv_traces_to_observations_wide;
+DROP TABLE IF EXISTS observations_wide;

packages/shared/clickhouse/migrations/0004_observations_wide.up.sql

@@ -0,0 +1,175 @@
+CREATE TABLE observations_wide
+(
+    `id` String,
+    trace_id Nullable(String),
+    `name` Nullable(String),
+    `project_id` String,
+    `user_id` Nullable(String),
+    `metadata` Map(String, String),
+    `release` Nullable(String),
+    `version` Nullable(String),
+    `public` Bool,
+    `bookmarked` Bool,
+    `tags` Array(String),
+    `input` Nullable(String),
+    `output` Nullable(String),
+    `session_id` Nullable(String),
+    `created_at` DateTime64(3),
+    `updated_at` DateTime64(3),
+    event_ts DateTime64(3),
+    `type` LowCardinality(String),
+    `parent_observation_id` Nullable(String),
+    `start_time` DateTime64(3),
+    `end_time` Nullable(DateTime64(3)),
+    `level` LowCardinality(String),
+    `status_message` Nullable(String),
+    `provided_model_name` Nullable(String),
+    `internal_model_id` Nullable(String),
+    `model_parameters` Nullable(String),
+    `provided_input_usage_units` Nullable(Decimal64(12)),
+    `provided_output_usage_units` Nullable(Decimal64(12)),
+    `provided_total_usage_units` Nullable(Decimal64(12)),
+    `input_usage_units` Nullable(Decimal64(12)),
+    `output_usage_units` Nullable(Decimal64(12)),
+    `total_usage_units` Nullable(Decimal64(12)),
+    `unit` Nullable(String),
+    `provided_input_cost` Nullable(Decimal64(12)),
+    `provided_output_cost` Nullable(Decimal64(12)),
+    `provided_total_cost` Nullable(Decimal64(12)),
+    `input_cost` Nullable(Decimal64(12)),
+    `output_cost` Nullable(Decimal64(12)),
+    `total_cost` Nullable(Decimal64(12)),
+    `completion_start_time` Nullable(DateTime64(3)),
+    `prompt_id` Nullable(String),
+    `prompt_name` Nullable(String),
+    `prompt_version` Nullable(UInt16),
+    trace_timestamp DateTime64(3),
+    trace_name String,
+    trace_user_id Nullable(String),
+    trace_metadata Map(String, String),
+    trace_release Nullable(String),
+    trace_version Nullable(String),
+    trace_public Bool,
+    trace_bookmarked Bool,
+    trace_tags Array(String),
+    trace_input Nullable(String),
+    trace_output Nullable(String),
+    trace_session_id Nullable(String),
+    trace_event_ts DateTime64(3)
+) ENGINE = ReplacingMergeTree Partition by toYYYYMM(start_time)
+ORDER BY (
+        project_id,
+        `type`,
+        toDate(start_time),
+        id
+    );
+
+CREATE MATERIALIZED VIEW mv_traces_to_observations_wide TO observations_wide AS
+SELECT 
+    argMax(t.`name`, o.event_ts) as trace_name,
+    argMax(t.timestamp, o.event_ts) as trace_timestamp,
+    argMax(t.user_id, o.event_ts) as trace_user_id,
+    argMax(t.metadata, o.event_ts) as trace_metadata,
+    argMax(t.release, o.event_ts) as trace_release,
+    argMax(t.version, o.event_ts) as trace_version,
+    argMax(t.project_id, o.event_ts) as trace_project_id,
+    argMax(t.public, o.event_ts) as trace_public,
+    argMax(t.bookmarked, o.event_ts) as trace_bookmarked,
+    argMax(t.tags, o.event_ts) as trace_tags,
+    argMax(t.input, o.event_ts) as trace_input,
+    argMax(t.output, o.event_ts) as trace_output,
+    argMax(t.session_id, o.event_ts) as trace_session_id,
+    argMax(t.event_ts, o.event_ts) as trace_event_ts,
+    o.id as id,
+    argMax(o.trace_id, o.event_ts) as trace_id,
+    argMax(o.name, o.event_ts) as `name`,
+    o.project_id as project_id,
+    argMax(o.metadata, o.event_ts) as metadata,
+    argMax(o.type, o.event_ts) as type,
+    argMax(o.parent_observation_id, o.event_ts) as parent_observation_id,
+    argMax(o.start_time, o.event_ts) as start_time,
+    argMax(o.end_time, o.event_ts) as end_time,
+    argMax(o.level, o.event_ts) as level,
+    argMax(o.status_message, o.event_ts) as status_message,
+    argMax(o.provided_model_name, o.event_ts) as provided_model_name,
+    argMax(o.internal_model_id, o.event_ts) as internal_model_id,
+    argMax(o.model_parameters, o.event_ts) as model_parameters,
+    argMax(o.provided_input_usage_units, o.event_ts) as provided_input_usage_units,
+    argMax(o.provided_output_usage_units, o.event_ts) as provided_output_usage_units,
+    argMax(o.provided_total_usage_units, o.event_ts) as provided_total_usage_units,
+    argMax(o.input_usage_units, o.event_ts) as input_usage_units,
+    argMax(o.output_usage_units, o.event_ts) as output_usage_units,
+    argMax(o.total_usage_units, o.event_ts) as total_usage_units,
+    argMax(o.unit, o.event_ts) as unit,
+    argMax(o.provided_input_cost, o.event_ts) as provided_input_cost,
+    argMax(o.provided_output_cost, o.event_ts) as provided_output_cost,
+    argMax(o.provided_total_cost, o.event_ts) as provided_total_cost,
+    argMax(o.input_cost, o.event_ts) as input_cost,
+    argMax(o.output_cost, o.event_ts) as output_cost,
+    argMax(o.total_cost, o.event_ts) as total_cost,
+    argMax(o.completion_start_time, o.event_ts) as completion_start_time,
+    argMax(o.prompt_id, o.event_ts) as prompt_id,
+    argMax(o.prompt_name, o.event_ts) as prompt_name,
+    argMax(o.prompt_version, o.event_ts) as prompt_version,
+    argMax(o.created_at, o.event_ts) as created_at,
+    argMax(o.updated_at, o.event_ts) as updated_at,
+    argMax(o.event_ts, o.event_ts) as event_ts
+FROM traces t
+INNER JOIN observations o ON t.id = o.trace_id
+GROUP BY o.id, o.project_id;
+
+CREATE MATERIALIZED VIEW mv_observations_to_observations_wide TO observations_wide AS
+SELECT 
+  argMax(t.timestamp, o.event_ts) as trace_timestamp,
+    argMax(t.name, o.event_ts) as trace_name,
+    argMax(t.user_id, o.event_ts) as trace_user_id,
+    argMax(t.metadata, o.event_ts) as trace_metadata,
+    argMax(t.release, o.event_ts) as trace_release,
+    argMax(t.version, o.event_ts) as trace_version,
+    argMax(t.project_id, o.event_ts) as trace_project_id,
+    argMax(t.public, o.event_ts) as trace_public,
+    argMax(t.bookmarked, o.event_ts) as trace_bookmarked,
+    argMax(t.tags, o.event_ts) as trace_tags,
+    argMax(t.input, o.event_ts) as trace_input,
+    argMax(t.output, o.event_ts) as trace_output,
+    argMax(t.session_id, o.event_ts) as trace_session_id,
+    argMax(t.event_ts, o.event_ts) as trace_event_ts,
+    o.id as id,
+    argMax(o.trace_id, o.event_ts) as trace_id,
+    argMax(o.name, o.event_ts) as name,
+    o.project_id as project_id,
+    argMax(o.metadata, o.event_ts) as metadata,
+    argMax(o.type, o.event_ts) as type,
+    argMax(o.parent_observation_id, o.event_ts) as parent_observation_id,
+    argMax(o.start_time, o.event_ts) as start_time,
+    argMax(o.end_time, o.event_ts) as end_time,
+    argMax(o.level, o.event_ts) as level,
+    argMax(o.status_message, o.event_ts) as status_message,
+    argMax(o.provided_model_name, o.event_ts) as provided_model_name,
+    argMax(o.internal_model_id, o.event_ts) as internal_model_id,
+    argMax(o.model_parameters, o.event_ts) as model_parameters,
+    argMax(o.provided_input_usage_units, o.event_ts) as provided_input_usage_units,
+    argMax(o.provided_output_usage_units, o.event_ts) as provided_output_usage_units,
+    argMax(o.provided_total_usage_units, o.event_ts) as provided_total_usage_units,
+    argMax(o.input_usage_units, o.event_ts) as input_usage_units,
+    argMax(o.output_usage_units, o.event_ts) as output_usage_units,
+    argMax(o.total_usage_units, o.event_ts) as total_usage_units,
+    argMax(o.unit, o.event_ts) as unit,
+    argMax(o.provided_input_cost, o.event_ts) as provided_input_cost,
+    argMax(o.provided_output_cost, o.event_ts) as provided_output_cost,
+    argMax(o.provided_total_cost, o.event_ts) as provided_total_cost,
+    argMax(o.input_cost, o.event_ts) as input_cost,
+    argMax(o.output_cost, o.event_ts) as output_cost,
+    argMax(o.total_cost, o.event_ts) as total_cost,
+    argMax(o.completion_start_time, o.event_ts) as completion_start_time,
+    argMax(o.prompt_id, o.event_ts) as prompt_id,
+    argMax(o.prompt_name, o.event_ts) as prompt_name,
+    argMax(o.prompt_version, o.event_ts) as prompt_version,
+    argMax(o.created_at, o.event_ts) as created_at,
+    argMax(o.updated_at, o.event_ts) as updated_at,
+    argMax(o.event_ts, o.event_ts) as event_ts
+FROM observations o
+LEFT OUTER JOIN traces t ON t.id = o.trace_id
+GROUP BY o.id, o.project_id;
+
+

packages/shared/clickhouse/migrations/0005_traces_wide.down.sql

@@ -0,0 +1,3 @@
+DROP TABLE IF EXISTS mv_observations_to_traces_wide;
+DROP TABLE IF EXISTS mv_traces_to_traces_wide;
+DROP TABLE IF EXISTS traces_wide;

packages/shared/clickhouse/migrations/0005_traces_wide.up.sql

@@ -0,0 +1,172 @@
+CREATE TABLE traces_wide
+(
+    `id` String,
+    trace_id Nullable(String),
+    `name` Nullable(String),
+    `project_id` String,
+    `user_id` Nullable(String),
+    `metadata` Map(String, String),
+    `release` Nullable(String),
+    `version` Nullable(String),
+    `public` Bool,
+    `bookmarked` Bool,
+    `tags` Array(String),
+    `input` Nullable(String),
+    `output` Nullable(String),
+    `session_id` Nullable(String),
+    `created_at` DateTime64(3),
+    `updated_at` DateTime64(3),
+    event_ts DateTime64(3),
+    `type` LowCardinality(String),
+    `parent_observation_id` Nullable(String),
+    `start_time` DateTime64(3),
+    `end_time` Nullable(DateTime64(3)),
+    `level` LowCardinality(String),
+    `status_message` Nullable(String),
+    `provided_model_name` Nullable(String),
+    `internal_model_id` Nullable(String),
+    `model_parameters` Nullable(String),
+    `provided_input_usage_units` Nullable(Decimal64(12)),
+    `provided_output_usage_units` Nullable(Decimal64(12)),
+    `provided_total_usage_units` Nullable(Decimal64(12)),
+    `input_usage_units` Nullable(Decimal64(12)),
+    `output_usage_units` Nullable(Decimal64(12)),
+    `total_usage_units` Nullable(Decimal64(12)),
+    `unit` Nullable(String),
+    `provided_input_cost` Nullable(Decimal64(12)),
+    `provided_output_cost` Nullable(Decimal64(12)),
+    `provided_total_cost` Nullable(Decimal64(12)),
+    `input_cost` Nullable(Decimal64(12)),
+    `output_cost` Nullable(Decimal64(12)),
+    `total_cost` Nullable(Decimal64(12)),
+    `completion_start_time` Nullable(DateTime64(3)),
+    `prompt_id` Nullable(String),
+    `prompt_name` Nullable(String),
+    `prompt_version` Nullable(UInt16),
+    trace_timestamp DateTime64(3),
+    trace_name String,
+    trace_user_id Nullable(String),
+    trace_metadata Map(String, String),
+    trace_release Nullable(String),
+    trace_version Nullable(String),
+    trace_public Bool,
+    trace_bookmarked Bool,
+    trace_tags Array(String),
+    trace_input Nullable(String),
+    trace_output Nullable(String),
+    trace_session_id Nullable(String),
+    trace_event_ts DateTime64(3)
+) ENGINE = ReplacingMergeTree Partition by toYYYYMM(start_time)
+ORDER BY (
+        project_id,
+        `type`,
+        toDate(start_time),
+        id
+    );
+
+CREATE MATERIALIZED VIEW mv_traces_to_traces_wide TO traces_wide AS
+SELECT 
+    argMax(t.`name`, t.event_ts) as trace_name,
+    argMax(t.timestamp, t.event_ts) as trace_timestamp,
+    argMax(t.user_id, t.event_ts) as trace_user_id,
+    argMax(t.metadata, t.event_ts) as trace_metadata,
+    argMax(t.release, t.event_ts) as trace_release,
+    argMax(t.version, t.event_ts) as trace_version,
+    argMax(t.public, t.event_ts) as trace_public,
+    argMax(t.bookmarked, t.event_ts) as trace_bookmarked,
+    argMax(t.tags, t.event_ts) as trace_tags,
+    argMax(t.input, t.event_ts) as trace_input,
+    argMax(t.output, t.event_ts) as trace_output,
+    argMax(t.session_id, t.event_ts) as trace_session_id,
+    argMax(t.event_ts, t.event_ts) as trace_event_ts,
+    o.id as id,
+    argMax(o.trace_id, t.event_ts) as trace_id,
+    argMax(o.name, t.event_ts) as `name`,
+    o.project_id as project_id,
+    argMax(o.metadata, t.event_ts) as metadata,
+    argMax(o.type, t.event_ts) as type,
+    argMax(o.parent_observation_id, t.event_ts) as parent_observation_id,
+    argMax(o.start_time, t.event_ts) as start_time,
+    argMax(o.end_time, t.event_ts) as end_time,
+    argMax(o.level, t.event_ts) as level,
+    argMax(o.status_message, t.event_ts) as status_message,
+    argMax(o.provided_model_name, t.event_ts) as provided_model_name,
+    argMax(o.internal_model_id, t.event_ts) as internal_model_id,
+    argMax(o.model_parameters, t.event_ts) as model_parameters,
+    argMax(o.provided_input_usage_units, t.event_ts) as provided_input_usage_units,
+    argMax(o.provided_output_usage_units, t.event_ts) as provided_output_usage_units,
+    argMax(o.provided_total_usage_units, t.event_ts) as provided_total_usage_units,
+    argMax(o.input_usage_units, t.event_ts) as input_usage_units,
+    argMax(o.output_usage_units, t.event_ts) as output_usage_units,
+    argMax(o.total_usage_units, t.event_ts) as total_usage_units,
+    argMax(o.unit, t.event_ts) as unit,
+    argMax(o.provided_input_cost, t.event_ts) as provided_input_cost,
+    argMax(o.provided_output_cost, t.event_ts) as provided_output_cost,
+    argMax(o.provided_total_cost, t.event_ts) as provided_total_cost,
+    argMax(o.input_cost, t.event_ts) as input_cost,
+    argMax(o.output_cost, t.event_ts) as output_cost,
+    argMax(o.total_cost, t.event_ts) as total_cost,
+    argMax(o.completion_start_time, t.event_ts) as completion_start_time,
+    argMax(o.prompt_id, t.event_ts) as prompt_id,
+    argMax(o.prompt_name, t.event_ts) as prompt_name,
+    argMax(o.prompt_version, t.event_ts) as prompt_version,
+    argMax(o.created_at, t.event_ts) as created_at,
+    argMax(o.updated_at, t.event_ts) as updated_at,
+    argMax(o.event_ts, t.event_ts) as event_ts
+FROM traces t
+LEFT JOIN observations o ON t.id = o.trace_id
+GROUP BY o.id, o.project_id;
+
+CREATE MATERIALIZED VIEW mv_observations_to_traces_wide TO traces_wide AS
+SELECT 
+    argMax(t.timestamp, o.event_ts) as trace_timestamp,
+    argMax(t.name, o.event_ts) as trace_name,
+    argMax(t.user_id, o.event_ts) as trace_user_id,
+    argMax(t.metadata, o.event_ts) as trace_metadata,
+    argMax(t.release, o.event_ts) as trace_release,
+    argMax(t.version, o.event_ts) as trace_version,
+    argMax(t.public, o.event_ts) as trace_public,
+    argMax(t.bookmarked, o.event_ts) as trace_bookmarked,
+    argMax(t.tags, o.event_ts) as trace_tags,
+    argMax(t.input, o.event_ts) as trace_input,
+    argMax(t.output, o.event_ts) as trace_output,
+    argMax(t.session_id, o.event_ts) as trace_session_id,
+    argMax(t.event_ts, o.event_ts) as trace_event_ts,
+    o.id as id,
+    argMax(o.trace_id, o.event_ts) as trace_id,
+    argMax(o.name, o.event_ts) as name,
+    o.project_id as project_id,
+    argMax(o.metadata, o.event_ts) as metadata,
+    argMax(o.type, o.event_ts) as type,
+    argMax(o.parent_observation_id, o.event_ts) as parent_observation_id,
+    argMax(o.start_time, o.event_ts) as start_time,
+    argMax(o.end_time, o.event_ts) as end_time,
+    argMax(o.level, o.event_ts) as level,
+    argMax(o.status_message, o.event_ts) as status_message,
+    argMax(o.provided_model_name, o.event_ts) as provided_model_name,
+    argMax(o.internal_model_id, o.event_ts) as internal_model_id,
+    argMax(o.model_parameters, o.event_ts) as model_parameters,
+    argMax(o.provided_input_usage_units, o.event_ts) as provided_input_usage_units,
+    argMax(o.provided_output_usage_units, o.event_ts) as provided_output_usage_units,
+    argMax(o.provided_total_usage_units, o.event_ts) as provided_total_usage_units,
+    argMax(o.input_usage_units, o.event_ts) as input_usage_units,
+    argMax(o.output_usage_units, o.event_ts) as output_usage_units,
+    argMax(o.total_usage_units, o.event_ts) as total_usage_units,
+    argMax(o.unit, o.event_ts) as unit,
+    argMax(o.provided_input_cost, o.event_ts) as provided_input_cost,
+    argMax(o.provided_output_cost, o.event_ts) as provided_output_cost,
+    argMax(o.provided_total_cost, o.event_ts) as provided_total_cost,
+    argMax(o.input_cost, o.event_ts) as input_cost,
+    argMax(o.output_cost, o.event_ts) as output_cost,
+    argMax(o.total_cost, o.event_ts) as total_cost,
+    argMax(o.completion_start_time, o.event_ts) as completion_start_time,
+    argMax(o.prompt_id, o.event_ts) as prompt_id,
+    argMax(o.prompt_name, o.event_ts) as prompt_name,
+    argMax(o.prompt_version, o.event_ts) as prompt_version,
+    argMax(o.created_at, o.event_ts) as created_at,
+    argMax(o.updated_at, o.event_ts) as updated_at,
+    argMax(o.event_ts, o.event_ts) as event_ts
+FROM observations o
+INNER JOIN traces t ON t.id = o.trace_id
+WHERE t.id IS NOT NULL
+GROUP BY o.id, o.project_id;

packages/shared/clickhouse/scripts/seed.ts

@@ -0,0 +1,28 @@
+import { clickhouseClient } from "@langfuse/shared/src/server";
+import { prisma } from "../../src/db";
+import { redis } from "@langfuse/shared/src/server";
+import { prepareClickhouse } from "../../scripts/prepareClickhouse";
+
+async function main() {
+  try {
+    const projectIds = [
+      "7a88fb47-b4e2-43b8-a06c-a5ce950dc53a",
+      "239ad00f-562f-411d-af14-831c75ddd875",
+    ]; // Example project IDs
+    await prepareClickhouse(projectIds, {
+      numberOfDays: 3,
+      totalObservations: 1000,
+    });
+
+    console.log("Clickhouse preparation completed successfully.");
+  } catch (error) {
+    console.error("Error during Clickhouse preparation:", error);
+  } finally {
+    await clickhouseClient.close();
+    await prisma.$disconnect();
+    redis?.disconnect();
+    console.log("Disconnected from Clickhouse.");
+  }
+}
+
+main();

packages/shared/clickhouse/scripts/up.sh

@@ -18,5 +18,6 @@ if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
 else
     DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-migrations-table-engine=MergeTree"
 fi
+
 # Execute the up command
 migrate -source file://clickhouse/migrations -database "$DATABASE_URL" up

packages/shared/package.json

@@ -21,6 +21,10 @@
       "import": "./dist/src/server/index.js",
       "require": "./dist/src/server/index.js"
     },
+    "./src/server/auth/apiKeys": {
+      "import": "./dist/src/server/auth/apiKeys.js",
+      "require": "./dist/src/server/auth/apiKeys.js"
+    },
     "./encryption": {
       "import": "./dist/src/encryption/index.js",
       "require": "./dist/src/encryption/index.js"
@@ -43,64 +47,79 @@
     "ch:up": "bash clickhouse/scripts/up.sh",
     "ch:down": "bash clickhouse/scripts/down.sh",
     "ch:drop": "bash clickhouse/scripts/drop.sh",
-    "ch:reset": "pnpm run ch:down && pnpm run ch:up"
+    "ch:reset": "pnpm run ch:down && pnpm run ch:up && pnpm run ch:seed",
+    "ch:seed": "dotenv -e ../../.env -- tsx clickhouse/scripts/seed.ts",
+    "load:setup": "dotenv -e ../../.env -- tsx scripts/load-seed.ts"
   },
   "prisma": {
     "seed": "ts-node -r tsconfig-paths/register -r dotenv/config --compiler-options {\"module\":\"CommonJS\"} prisma/seed.ts"
   },
   "dependencies": {
     "@anthropic-ai/tokenizer": "^0.0.4",
-    "@aws-sdk/client-s3": "^3.627.0",
-    "@aws-sdk/lib-storage": "^3.568.0",
-    "@aws-sdk/s3-request-presigner": "^3.554.0",
+    "@aws-sdk/client-cloudwatch": "^3.675.0",
+    "@aws-sdk/client-s3": "^3.675.0",
+    "@aws-sdk/lib-storage": "^3.675.0",
+    "@aws-sdk/s3-request-presigner": "^3.675.0",
     "@clickhouse/client": "^1.4.0",
-    "@langchain/anthropic": "^0.1.21",
-    "@langchain/core": "^0.1.61",
-    "@langchain/openai": "^0.0.33",
-    "@prisma/client": "^5.13.0",
+    "@langchain/anthropic": "^0.3.1",
+    "@langchain/aws": "^0.1.0",
+    "@langchain/core": "^0.3.9",
+    "@langchain/openai": "^0.3.0",
+    "@opentelemetry/api": ">=1.0.0 <1.10.0",
+    "@prisma/client": "^5.20.0",
     "@react-email/components": "^0.0.19",
     "@react-email/render": "^0.0.15",
     "@types/bcryptjs": "^2.4.6",
+    "axios": "^1.7.7",
     "bcryptjs": "^2.4.3",
-    "bullmq": "^5.4.2",
+    "bullmq": "^5.12.10",
+    "dd-trace": "^5.23.1",
+    "decimal.js": "^10.4.3",
+    "exponential-backoff": "^3.1.1",
     "ioredis": "^5.4.1",
-    "js-tiktoken": "^1.0.12",
-    "kysely": "^0.27.3",
-    "langchain": "^0.2.6",
+    "kysely": "^0.27.4",
+    "langchain": "^0.3.2",
     "lodash": "^4.17.21",
     "next-auth": "^4.24.7",
-    "nodemailer": "^6.9.13",
+    "nodemailer": "^6.9.15",
     "prisma-extension-kysely": "^2.1.0",
     "uuid": "^9.0.1",
+    "winston": "^3.14.2",
     "zod": "^3.23.8",
-    "zod-to-json-schema": "^3.22.5"
+    "zod-to-json-schema": "^3.23.2"
   },
   "devDependencies": {
     "@repo/eslint-config": "workspace:*",
     "@repo/typescript-config": "workspace:*",
-    "@types/lodash": "^4.17.5",
+    "@types/lodash": "^4.17.10",
     "@types/node": "^20.11.29",
-    "@types/nodemailer": "^6.4.15",
-    "@types/pg": "^8.11.6",
+    "@types/nodemailer": "^6.4.16",
+    "@types/pg": "^8.11.10",
     "@types/uuid": "^9.0.8",
     "@typescript-eslint/parser": "^7.12.0",
     "eslint": "^8.57.0",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",
     "eslint-plugin-prettier": "^5.1.3",
-    "kysely-codegen": "^0.11.0",
-    "nodemon": "^3.1.3",
-    "prettier": "^3.2.5",
-    "prisma": "^5.13.0",
+    "kysely-codegen": "^0.16.8",
+    "nodemon": "^3.1.7",
+    "prettier": "^3.3.3",
+    "prisma": "^5.20.0",
     "prisma-erd-generator": "^1.11.2",
     "prisma-kysely": "^1.8.0",
     "ts-node": "^10.9.2",
     "tsc-watch": "^6.2.0",
+    "tsx": "^4.19.1",
     "typescript": "^5.4.5",
-    "vitest": "^1.5.3"
+    "vitest": "^2.1.2"
   },
   "peerDependencies": {
-    "@types/react": "^18.2.79",
-    "react": "^18.0.0"
+    "@types/react": "~18.2.79",
+    "react": "~18.2.0"
+  },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.0"
+    }
   }
 }

packages/shared/prettierrc.json

@@ -1,4 +0,0 @@
-{
-  "trailingComma": "es5",
-  "printWidth": 120
-}

packages/shared/prisma/generated/types.ts

@@ -37,11 +37,28 @@ export const ScoreDataType = {
     BOOLEAN: "BOOLEAN"
 } as const;
 export type ScoreDataType = (typeof ScoreDataType)[keyof typeof ScoreDataType];
+export const AnnotationQueueStatus = {
+    PENDING: "PENDING",
+    COMPLETED: "COMPLETED"
+} as const;
+export type AnnotationQueueStatus = (typeof AnnotationQueueStatus)[keyof typeof AnnotationQueueStatus];
+export const AnnotationQueueObjectType = {
+    TRACE: "TRACE",
+    OBSERVATION: "OBSERVATION"
+} as const;
+export type AnnotationQueueObjectType = (typeof AnnotationQueueObjectType)[keyof typeof AnnotationQueueObjectType];
 export const DatasetStatus = {
     ACTIVE: "ACTIVE",
     ARCHIVED: "ARCHIVED"
 } as const;
 export type DatasetStatus = (typeof DatasetStatus)[keyof typeof DatasetStatus];
+export const CommentObjectType = {
+    TRACE: "TRACE",
+    OBSERVATION: "OBSERVATION",
+    SESSION: "SESSION",
+    PROMPT: "PROMPT"
+} as const;
+export type CommentObjectType = (typeof CommentObjectType)[keyof typeof CommentObjectType];
 export const JobType = {
     EVAL: "EVAL"
 } as const;
@@ -73,6 +90,31 @@ export type Account = {
     scope: string | null;
     id_token: string | null;
     session_state: string | null;
+    refresh_token_expires_in: number | null;
+    created_at: number | null;
+};
+export type AnnotationQueue = {
+    id: string;
+    name: string;
+    description: string | null;
+    score_config_ids: Generated<string[]>;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+};
+export type AnnotationQueueItem = {
+    id: string;
+    queue_id: string;
+    object_id: string;
+    object_type: AnnotationQueueObjectType;
+    status: Generated<AnnotationQueueStatus>;
+    locked_at: Timestamp | null;
+    locked_by_user_id: string | null;
+    annotator_user_id: string | null;
+    completed_at: Timestamp | null;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
 };
 export type ApiKey = {
     id: string;
@@ -116,6 +158,16 @@ export type BatchExport = {
     url: string | null;
     log: string | null;
 };
+export type Comment = {
+    id: string;
+    project_id: string;
+    object_type: CommentObjectType;
+    object_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    content: string;
+    author_user_id: string | null;
+};
 export type CronJobs = {
     name: string;
     last_run: Timestamp | null;
@@ -227,6 +279,7 @@ export type LlmApiKeys = {
     base_url: string | null;
     custom_models: Generated<string[]>;
     with_default_models: Generated<boolean>;
+    config: unknown | null;
     project_id: string;
 };
 export type MembershipInvitation = {
@@ -392,6 +445,7 @@ export type Score = {
     observation_id: string | null;
     config_id: string | null;
     string_value: string | null;
+    queue_id: string | null;
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
     data_type: Generated<ScoreDataType>;
@@ -488,9 +542,12 @@ export type VerificationToken = {
 };
 export type DB = {
     Account: Account;
+    annotation_queue_items: AnnotationQueueItem;
+    annotation_queues: AnnotationQueue;
     api_keys: ApiKey;
     audit_logs: AuditLog;
     batch_exports: BatchExport;
+    comments: Comment;
     cron_jobs: CronJobs;
     dataset_items: DatasetItem;
     dataset_run_items: DatasetRunItems;

packages/shared/prisma/migrations/20240814223824_model_fix_text_embedding_3_large/migration.sql

@@ -0,0 +1,7 @@
+
+-- Fix model name
+-- https://github.com/langfuse/langfuse/issues/2688
+
+UPDATE models
+SET model_name = 'text-embedding-3-large'
+WHERE id = 'clruwn76700020al7gp8e4g4l'

packages/shared/prisma/migrations/20240814233029_dataset_items_drop_fkey_on_traces_and_observations/migration.sql

@@ -0,0 +1,5 @@
+-- DropForeignKey
+ALTER TABLE "dataset_items" DROP CONSTRAINT "dataset_items_source_observation_id_fkey";
+
+-- DropForeignKey
+ALTER TABLE "dataset_items" DROP CONSTRAINT "dataset_items_source_trace_id_fkey";

packages/shared/prisma/migrations/20240815171916_add_comments/migration.sql

@@ -0,0 +1,22 @@
+-- CreateEnum
+CREATE TYPE "CommentObjectType" AS ENUM ('TRACE', 'OBSERVATION', 'SESSION', 'PROMPT');
+
+-- CreateTable
+CREATE TABLE "comments" (
+    "id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "object_type" "CommentObjectType" NOT NULL,
+    "object_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "content" TEXT NOT NULL,
+    "author_user_id" TEXT,
+
+    CONSTRAINT "comments_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "comments_project_id_object_type_object_id_idx" ON "comments"("project_id", "object_type", "object_id");
+
+-- AddForeignKey
+ALTER TABLE "comments" ADD CONSTRAINT "comments_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20240913095558_models_add_openai_o1_2024-09-12/migration.sql

@@ -0,0 +1,30 @@
+-- For OpenAI reasoning models, manually tokenizing output string does not account for reasoning tokens, thus would lead to incorrect cost
+-- So no manual tokenizer config is provided
+-- Reference: https://platform.openai.com/docs/guides/reasoning/how-reasoning-works
+
+INSERT INTO models (
+  id,
+  project_id,
+  model_name,
+  match_pattern,
+  start_date,
+  input_price,
+  output_price,
+  total_price,
+  unit,
+  tokenizer_id,
+  tokenizer_config
+)
+VALUES
+  -- o1-preview
+  ('cm10ivcdp0000gix7lelmbw80', NULL, 'o1-preview', '(?i)^(o1-preview)$', NULL, 0.000015, 0.00006, NULL, 'TOKENS', NULL, NULL), 
+
+  -- o1-preview-2024-09-12
+  ('cm10ivo130000n8x7qopcjjcg', NULL, 'o1-preview-2024-09-12', '(?i)^(o1-preview-2024-09-12)$', NULL, 0.000015, 0.00006, NULL, 'TOKENS', NULL, NULL), 
+
+  -- o1-mini
+  ('cm10ivwo40000r1x7gg3syjq0', NULL, 'o1-mini', '(?i)^(o1-mini)$', NULL, 0.000003, 0.000012, NULL, 'TOKENS', NULL, NULL), 
+
+  -- o1-mini-2024-09-12
+  ('cm10iw6p20000wgx7it1hlb22', NULL, 'o1-mini-2024-09-12', '(?i)^(o1-mini-2024-09-12)$', NULL, 0.000003, 0.000012, NULL, 'TOKENS', NULL, NULL) 
+

packages/shared/prisma/migrations/20240913185822_account_add_refresh_token_expires_in/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "Account" ADD COLUMN     "refresh_token_expires_in" INTEGER;

packages/shared/prisma/migrations/20240917183001_remove_covered_indexes_01/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "traces_project_id_idx"; -- covered by traces_project_id_timestamp_idx

packages/shared/prisma/migrations/20240917183002_remove_covered_indexes_02/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "datasets_project_id_idx"; -- covered by datasets_project_id_name_key (unique)

packages/shared/prisma/migrations/20240917183003_remove_covered_indexes_03/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "eval_templates_project_id_idx"; -- covered by eval_templates_project_id_id_idx

packages/shared/prisma/migrations/20240917183004_remove_covered_indexes_04/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "job_configurations_project_id_idx"; -- covered by job_configurations_project_id_id_idx

packages/shared/prisma/migrations/20240917183005_remove_covered_indexes_05/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "job_executions_project_id_idx"; -- covered by job_executions_project_id_id_idx

packages/shared/prisma/migrations/20240917183006_remove_covered_indexes_06/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "llm_api_keys_project_id_provider_idx"; -- covered by llm_api_keys_project_id_provider_key (unique)

packages/shared/prisma/migrations/20240917183007_remove_covered_indexes_07/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "models_project_id_model_name_idx"; -- covered by models_project_id_model_name_start_date_unit_key (unique)

packages/shared/prisma/migrations/20240917183008_remove_covered_indexes_08/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "models_project_id_model_name_start_date_unit_idx"; -- covered by models_project_id_model_name_start_date_unit_key (unique)

packages/shared/prisma/migrations/20240917183009_remove_covered_indexes_09/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "observations_project_id_idx"; -- covered by observations_project_id_start_time_type_idx

packages/shared/prisma/migrations/20240917183010_remove_covered_indexes_10/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "observations_trace_id_idx"; -- covered by observations_trace_id_project_id_start_time_idx

packages/shared/prisma/migrations/20240917183011_remove_covered_indexes_11/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "observations_trace_id_project_id_idx"; -- covered by observations_trace_id_project_id_start_time_idx

packages/shared/prisma/migrations/20240917183012_remove_covered_indexes_12/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "organization_memberships_org_id_idx"; -- covered by organization_memberships_org_id_user_id_key (unique)

packages/shared/prisma/migrations/20240917183013_remove_covered_indexes_13/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "posthog_integrations_project_id_idx"; -- covered by posthog_integrations_pkey (unique)

packages/shared/prisma/migrations/20240917183014_remove_covered_indexes_14/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "prompts_project_id_idx"; -- covered by prompts_project_id_name_version_key (unique)

packages/shared/prisma/migrations/20240917183015_remove_covered_indexes_15/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "prompts_project_id_name_version_idx"; -- covered by prompts_project_id_name_version_key (unique)

packages/shared/prisma/migrations/20240917183016_remove_covered_indexes_16/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "scores_project_id_idx"; -- covered by scores_project_id_name_idx

packages/shared/prisma/migrations/20241009042557_auth_add_created_at_for_gitlab/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "Account" ADD COLUMN     "created_at" INTEGER;

packages/shared/prisma/migrations/20241009110720_scores_add_nullable_queue_id_column/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "scores" ADD COLUMN     "queue_id" TEXT;

packages/shared/prisma/migrations/20241009113245_add_annotation_queue/migration.sql

@@ -0,0 +1,75 @@
+-- CreateEnum
+CREATE TYPE "AnnotationQueueStatus" AS ENUM ('PENDING', 'COMPLETED');
+
+-- CreateEnum
+CREATE TYPE "AnnotationQueueObjectType" AS ENUM ('TRACE', 'OBSERVATION');
+
+-- CreateTable
+CREATE TABLE "annotation_queues" (
+    "id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "description" TEXT,
+    "score_config_ids" TEXT[] DEFAULT ARRAY[]::TEXT[],
+    "project_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "annotation_queues_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "annotation_queue_items" (
+    "id" TEXT NOT NULL,
+    "queue_id" TEXT NOT NULL,
+    "object_id" TEXT NOT NULL,
+    "object_type" "AnnotationQueueObjectType" NOT NULL,
+    "status" "AnnotationQueueStatus" NOT NULL DEFAULT 'PENDING',
+    "locked_at" TIMESTAMP(3),
+    "locked_by_user_id" TEXT,
+    "annotator_user_id" TEXT,
+    "completed_at" TIMESTAMP(3),
+    "project_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "annotation_queue_items_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "annotation_queues_id_project_id_idx" ON "annotation_queues"("id", "project_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queues_project_id_created_at_idx" ON "annotation_queues"("project_id", "created_at");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "annotation_queues_project_id_name_key" ON "annotation_queues"("project_id", "name");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_id_project_id_idx" ON "annotation_queue_items"("id", "project_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_project_id_queue_id_status_idx" ON "annotation_queue_items"("project_id", "queue_id", "status");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_object_id_object_type_project_id_que_idx" ON "annotation_queue_items"("object_id", "object_type", "project_id", "queue_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_annotator_user_id_idx" ON "annotation_queue_items"("annotator_user_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_created_at_idx" ON "annotation_queue_items"("created_at");
+
+-- AddForeignKey
+ALTER TABLE "annotation_queues" ADD CONSTRAINT "annotation_queues_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_queue_id_fkey" FOREIGN KEY ("queue_id") REFERENCES "annotation_queues"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_locked_by_user_id_fkey" FOREIGN KEY ("locked_by_user_id") REFERENCES "users"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_annotator_user_id_fkey" FOREIGN KEY ("annotator_user_id") REFERENCES "users"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20241010120245_llm_keys_add_config/migration.sql

@@ -0,0 +1 @@
+ALTER TABLE "llm_api_keys" ADD COLUMN "config" JSONB;

packages/shared/prisma/migrations/20241015110145_prompts_config_to_JSON/migration.sql

@@ -0,0 +1,107 @@
+-- Temporarily drop observations_view as prompts.config is a calculated column in the view and we need to update it to a JSON type
+DROP VIEW IF EXISTS "observations_view"; -- Drop view as column was added in 20240705154048_observation_view_add_created_at_updated_at and update view must have same columns
+
+-- Update prompts.config to JSON type. Use JSON as JSONB is reordering keys for optimization, which is undesired
+ALTER TABLE prompts ALTER COLUMN config TYPE JSON USING config::JSON;
+ALTER TABLE prompts ALTER COLUMN config SET DEFAULT '{}'::JSON;
+
+-- Recreate the view with the updated prompts.config column
+CREATE VIEW "observations_view" AS -- Specify the columns that should be returned in the view, as calculated columns are added but exist in the observations table already
+SELECT
+    o.id,
+    o.name,
+    o.start_time,
+    o.end_time,
+    o.parent_observation_id,
+    o.type,
+    o.trace_id,
+    o.metadata,
+    o.model,
+    o."modelParameters",
+    o.input,
+    o.output,
+    o.level,
+    o.status_message,
+    o.completion_start_time,
+    o.completion_tokens,
+    o.prompt_tokens,
+    o.total_tokens,
+    o.version,
+    o.project_id,
+    o.created_at,
+    o.updated_at,
+    o.unit,
+    o.prompt_id,
+    p.name as prompt_name,         -- added in this change
+    p.version as prompt_version,   -- added in this change
+    o.input_cost,
+    o.output_cost,
+    o.total_cost,
+    o.internal_model,
+    m.id AS "model_id",
+    m.start_date AS "model_start_date",
+    m.input_price,
+    m.output_price,
+    m.total_price,
+    m.tokenizer_config AS "tokenizer_config",
+    CASE 
+        WHEN o.calculated_input_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.prompt_tokens::decimal * m.input_price
+        ELSE
+            COALESCE(o.calculated_input_cost, o.input_cost)
+    END AS "calculated_input_cost",
+    CASE 
+        WHEN o.calculated_output_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.completion_tokens::decimal * m.output_price
+        ELSE
+            COALESCE(o.calculated_output_cost, o.output_cost)
+    END AS "calculated_output_cost",
+    CASE 
+        WHEN o.calculated_total_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            CASE 
+                WHEN m.total_price IS NOT NULL AND o.total_tokens IS NOT NULL THEN
+                    m.total_price * o.total_tokens
+                ELSE
+                    o.prompt_tokens::decimal * m.input_price + 
+                    o.completion_tokens::decimal * m.output_price
+            END
+        ELSE
+            COALESCE(o.calculated_total_cost, o.total_cost)
+    END AS "calculated_total_cost",
+    CASE WHEN o.end_time IS NULL THEN NULL ELSE (EXTRACT(EPOCH FROM o."end_time") - EXTRACT(EPOCH FROM o."start_time"))::double precision END AS "latency",
+    CASE WHEN o.completion_start_time IS NOT NULL AND o.start_time IS NOT NULL THEN EXTRACT(EPOCH FROM (completion_start_time - start_time))::double precision ELSE NULL END as "time_to_first_token"
+    
+FROM
+    observations o
+LEFT JOIN LATERAL (
+    SELECT
+        models.*
+    FROM
+        models
+    WHERE (models.project_id = o.project_id OR models.project_id IS NULL)
+    AND models.model_name = o.internal_model
+    AND (models.start_date < o.start_time OR models.start_date IS NULL)
+    AND o.unit::TEXT = models.unit
+    ORDER BY
+        models.project_id ASC, -- in postgres, NULLs are sorted last when ordering ASC
+        models.start_date DESC NULLS LAST -- now, NULLs are sorted last when ordering DESC as well
+    LIMIT 1
+) m ON TRUE
+LEFT JOIN LATERAL (
+    SELECT
+        prompts.*
+    FROM
+        prompts
+    WHERE prompts.id = o.prompt_id
+    AND prompts.project_id = o.project_id
+    LIMIT 1
+) p ON TRUE
+
+
+-- requirements:
+-- 1. The view should return all columns from the observations table
+-- 2. The view should match with only one model for each observation if:
+--     a. The model has the same project_id as the observation, otherwise the model without project_id. 
+--     b. The model has the same model_name as the observation
+--     c. The model has a start_date that is less than the observation start_time, otherwise the model without start_date
+--     d. The model has the same unit as the observation

packages/shared/prisma/migrations/20241022110145_add_claude_sonnet_35/migration.sql

@@ -0,0 +1,18 @@
+INSERT INTO models (
+  id,
+  project_id,
+  model_name,
+  match_pattern,
+  start_date,
+  input_price,
+  output_price,
+  total_price,
+  unit,
+  tokenizer_id,
+  tokenizer_config
+)
+VALUES
+  -- https://docs.anthropic.com/en/docs/about-claude/models#model-comparison-table
+  ('cm2krz1uf000208jjg5653iud', NULL, 'claude-3.5-haiku-20241022', '(?i)^(claude-3-5-sonnet-20241022|anthropic\.claude-3-5-sonnet-20241022-v2:0|claude-3-5-sonnet-V2@20241022)$', NULL, 0.000003, 0.000015, NULL, 'TOKENS', 'claude', NULL),
+  ('cm2ks2vzn000308jjh4ze1w7q', NULL, 'claude-3.5-haiku-latest', '(?i)^(claude-3-5-sonnet-latest)$', NULL, 0.000003, 0.000015, NULL, 'TOKENS', 'claude', NULL)
+

packages/shared/prisma/schema.prisma

@@ -34,21 +34,23 @@ generator kysely {
 
 // Necessary for Next auth
 model Account {
-    id                String  @id @default(cuid())
-    userId            String  @map("user_id")
-    type              String
-    provider          String
-    providerAccountId String
-    refresh_token     String? // @db.Text
-    access_token      String? // @db.Text
-    expires_at        Int?
-    expires_in        Int?
-    ext_expires_in    Int?
-    token_type        String?
-    scope             String?
-    id_token          String? // @db.Text
-    session_state     String?
-    user              User    @relation(fields: [userId], references: [id], onDelete: Cascade)
+    id                       String  @id @default(cuid())
+    userId                   String  @map("user_id")
+    type                     String
+    provider                 String
+    providerAccountId        String
+    refresh_token            String? // @db.Text
+    access_token             String? // @db.Text
+    expires_at               Int?
+    expires_in               Int?
+    ext_expires_in           Int?
+    token_type               String?
+    scope                    String?
+    id_token                 String? // @db.Text
+    session_state            String?
+    refresh_token_expires_in Int?
+    created_at               Int? // GitLab
+    user                     User    @relation(fields: [userId], references: [id], onDelete: Cascade)
 
     @@unique([provider, providerAccountId])
     @@index([userId])
@@ -78,6 +80,8 @@ model User {
     createdAt               DateTime                 @default(now()) @map("created_at")
     updatedAt               DateTime                 @default(now()) @updatedAt @map("updated_at")
     featureFlags            String[]                 @default([]) @map("feature_flags")
+    annotatedLockedItem     AnnotationQueueItem[]    @relation("LockedByUser")
+    annotatedCompletedItem  AnnotationQueueItem[]    @relation("AnnotatorUser")
 
     @@map("users")
 }
@@ -105,30 +109,33 @@ model Organization {
 }
 
 model Project {
-    id                 String                 @id @default(cuid())
-    orgId              String                 @map("org_id")
-    createdAt          DateTime               @default(now()) @map("created_at")
-    updatedAt          DateTime               @default(now()) @updatedAt @map("updated_at")
-    name               String
-    projectMembers     ProjectMembership[]
-    organization       Organization           @relation(fields: [orgId], references: [id], onUpdate: Cascade, onDelete: Cascade)
-    traces             Trace[]
-    observations       Observation[]
-    apiKeys            ApiKey[]
-    dataset            Dataset[]
-    RawEvents          Events[]
-    invitations        MembershipInvitation[]
-    sessions           TraceSession[]
-    Prompt             Prompt[]
-    Model              Model[]
-    EvalTemplate       EvalTemplate[]
-    JobConfiguration   JobConfiguration[]
-    JobExecution       JobExecution[]
-    LlmApiKeys         LlmApiKeys[]
-    PosthogIntegration PosthogIntegration[]
-    Score              Score[]
-    scoreConfig        ScoreConfig[]
-    BatchExport        BatchExport[]
+    id                  String                 @id @default(cuid())
+    orgId               String                 @map("org_id")
+    createdAt           DateTime               @default(now()) @map("created_at")
+    updatedAt           DateTime               @default(now()) @updatedAt @map("updated_at")
+    name                String
+    projectMembers      ProjectMembership[]
+    organization        Organization           @relation(fields: [orgId], references: [id], onUpdate: Cascade, onDelete: Cascade)
+    traces              Trace[]
+    observations        Observation[]
+    apiKeys             ApiKey[]
+    dataset             Dataset[]
+    RawEvents           Events[]
+    invitations         MembershipInvitation[]
+    sessions            TraceSession[]
+    Prompt              Prompt[]
+    Model               Model[]
+    EvalTemplate        EvalTemplate[]
+    JobConfiguration    JobConfiguration[]
+    JobExecution        JobExecution[]
+    LlmApiKeys          LlmApiKeys[]
+    PosthogIntegration  PosthogIntegration[]
+    Score               Score[]
+    scoreConfig         ScoreConfig[]
+    BatchExport         BatchExport[]
+    comment             Comment[]
+    annotationQueue     AnnotationQueue[]
+    annotationQueueItem AnnotationQueueItem[]
 
     @@index([orgId])
     @@map("projects")
@@ -166,12 +173,12 @@ model LlmApiKeys {
     baseURL           String?  @map("base_url")
     customModels      String[] @default([]) @map("custom_models")
     withDefaultModels Boolean  @default(true) @map("with_default_models")
+    config            Json?
 
     projectId String  @map("project_id")
     project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
 
     @@unique([projectId, provider])
-    @@index([projectId, provider])
     @@map("llm_api_keys")
 }
 
@@ -188,7 +195,6 @@ model OrganizationMembership {
 
     @@unique([orgId, userId])
     @@index([userId])
-    @@index([orgId])
     @@map("organization_memberships")
 }
 
@@ -279,10 +285,8 @@ model Trace {
     createdAt  DateTime      @default(now()) @map("created_at")
     updatedAt  DateTime      @default(now()) @updatedAt @map("updated_at")
 
-    DatasetItem  DatasetItem[]
     JobExecution JobExecution[]
 
-    @@index([projectId])
     @@index([projectId, timestamp])
     @@index([sessionId])
     @@index([name])
@@ -364,9 +368,8 @@ model Observation {
     calculatedOutputCost Decimal? @map("calculated_output_cost")
     calculatedTotalCost  Decimal? @map("calculated_total_cost")
 
-    completionStartTime DateTime?     @map("completion_start_time")
-    project             Project       @relation(fields: [projectId], references: [id], onDelete: Cascade)
-    derivedDatasetItems DatasetItem[]
+    completionStartTime DateTime? @map("completion_start_time")
+    project             Project   @relation(fields: [projectId], references: [id], onDelete: Cascade)
 
     promptId String? @map("prompt_id") // no fk constraint, prompt can be deleted
 
@@ -374,12 +377,9 @@ model Observation {
     @@index([projectId, internalModel, startTime, unit])
     @@index([traceId, projectId, type, startTime])
     @@index([traceId, projectId, startTime])
-    @@index([traceId, projectId])
-    @@index([traceId])
     @@index([type])
     @@index(startTime)
     @@index(createdAt)
-    @@index(projectId)
     @@index(model)
     @@index(internalModel)
     @@index([projectId, promptId])
@@ -465,6 +465,7 @@ model Score {
     observationId String?        @map("observation_id")
     configId      String?        @map("config_id")
     stringValue   String?        @map("string_value") // always defined if data type is CATEGORICAL or BOOLEAN, null for NUMERIC
+    queueId       String?        @map("queue_id")
     createdAt     DateTime       @default(now()) @map("created_at")
     updatedAt     DateTime       @default(now()) @updatedAt @map("updated_at")
     dataType      ScoreDataType  @default(NUMERIC) @map("data_type")
@@ -474,7 +475,6 @@ model Score {
     @@unique([id, projectId]) // used for upserts via prisma
     @@index(timestamp)
     @@index([value])
-    @@index([projectId])
     @@index([projectId, name])
     @@index([authorUserId])
     @@index([configId])
@@ -522,6 +522,59 @@ enum ScoreDataType {
     BOOLEAN
 }
 
+model AnnotationQueue {
+    id                  String                @id @default(cuid())
+    name                String
+    description         String?
+    scoreConfigIds      String[]              @default([]) @map("score_config_ids")
+    projectId           String                @map("project_id")
+    project             Project               @relation(fields: [projectId], references: [id], onDelete: Cascade)
+    createdAt           DateTime              @default(now()) @map("created_at")
+    updatedAt           DateTime              @default(now()) @updatedAt @map("updated_at")
+    annotationQueueItem AnnotationQueueItem[]
+
+    @@unique([projectId, name])
+    @@index([id, projectId])
+    @@index([projectId, createdAt])
+    @@map("annotation_queues")
+}
+
+model AnnotationQueueItem {
+    id              String                    @id @default(cuid())
+    queueId         String                    @map("queue_id")
+    queue           AnnotationQueue           @relation(fields: [queueId], references: [id], onDelete: Cascade)
+    objectId        String                    @map("object_id")
+    objectType      AnnotationQueueObjectType @map("object_type")
+    status          AnnotationQueueStatus     @default(PENDING)
+    lockedAt        DateTime?                 @map("locked_at")
+    lockedByUserId  String?                   @map("locked_by_user_id")
+    lockedByUser    User?                     @relation("LockedByUser", fields: [lockedByUserId], references: [id], onDelete: SetNull)
+    annotatorUserId String?                   @map("annotator_user_id")
+    annotatorUser   User?                     @relation("AnnotatorUser", fields: [annotatorUserId], references: [id], onDelete: SetNull)
+    completedAt     DateTime?                 @map("completed_at")
+    projectId       String                    @map("project_id")
+    project         Project                   @relation(fields: [projectId], references: [id], onDelete: Cascade)
+    createdAt       DateTime                  @default(now()) @map("created_at")
+    updatedAt       DateTime                  @default(now()) @updatedAt @map("updated_at")
+
+    @@index([id, projectId])
+    @@index([projectId, queueId, status])
+    @@index([objectId, objectType, projectId, queueId])
+    @@index([annotatorUserId])
+    @@index([createdAt])
+    @@map("annotation_queue_items")
+}
+
+enum AnnotationQueueStatus {
+    PENDING
+    COMPLETED
+}
+
+enum AnnotationQueueObjectType {
+    TRACE
+    OBSERVATION
+}
+
 model CronJobs {
     name         String    @id
     lastRun      DateTime? @map("last_run")
@@ -545,7 +598,6 @@ model Dataset {
 
     @@id([id, projectId])
     @@unique([projectId, name])
-    @@index([projectId], type: Hash)
     @@index([createdAt])
     @@index([updatedAt])
     @@map("datasets")
@@ -559,9 +611,7 @@ model DatasetItem {
     expectedOutput      Json?             @map("expected_output")
     metadata            Json?
     sourceTraceId       String?           @map("source_trace_id")
-    sourceTrace         Trace?            @relation(fields: [sourceTraceId], references: [id], onDelete: SetNull)
     sourceObservationId String?           @map("source_observation_id")
-    sourceObservation   Observation?      @relation(fields: [sourceObservationId], references: [id], onDelete: SetNull)
     datasetId           String            @map("dataset_id")
     dataset             Dataset           @relation(fields: [datasetId, projectId], references: [id, projectId], onDelete: Cascade)
     createdAt           DateTime          @default(now()) @map("created_at")
@@ -639,6 +689,28 @@ model Events {
     @@map("events")
 }
 
+model Comment {
+    id           String            @id @default(cuid())
+    projectId    String            @map("project_id")
+    project      Project           @relation(fields: [projectId], references: [id], onDelete: Cascade)
+    objectType   CommentObjectType @map("object_type")
+    objectId     String            @map("object_id")
+    createdAt    DateTime          @default(now()) @map("created_at")
+    updatedAt    DateTime          @default(now()) @updatedAt @map("updated_at")
+    content      String
+    authorUserId String?           @map("author_user_id") // no fk constraint, user can be deleted
+
+    @@index([projectId, objectType, objectId])
+    @@map("comments")
+}
+
+enum CommentObjectType {
+    TRACE
+    OBSERVATION
+    SESSION
+    PROMPT
+}
+
 model Prompt {
     id        String   @id @default(cuid())
     createdAt DateTime @default(now()) @map("created_at")
@@ -654,14 +726,12 @@ model Prompt {
     version  Int
     type     String   @default("text")
     isActive Boolean? @map("is_active") // Deprecated. To be removed once 'production' labels work as expected.
-    config   Json     @default("{}")
+    config   Json     @default("{}") @db.Json
     tags     String[] @default([])
     labels   String[] @default([])
 
     @@unique([projectId, name, version])
-    @@index([projectId, name, version])
     @@index([projectId, id])
-    @@index([projectId])
     @@index([createdAt])
     @@index([updatedAt])
     @@index([tags(ops: ArrayOps)], type: Gin)
@@ -688,8 +758,6 @@ model Model {
     tokenizerConfig Json?     @map("tokenizer_config")
 
     @@unique([projectId, modelName, startDate, unit])
-    @@index([projectId, modelName, startDate, unit])
-    @@index([projectId, modelName])
     @@index(modelName)
     @@map("models")
 }
@@ -738,7 +806,6 @@ model EvalTemplate {
 
     @@unique([projectId, name, version])
     @@index([projectId, id])
-    @@index([projectId])
     @@map("eval_templates")
 }
 
@@ -773,7 +840,6 @@ model JobConfiguration {
     JobExecution    JobExecution[]
 
     @@index([projectId, id])
-    @@index([projectId])
     @@map("job_configurations")
 }
 
@@ -808,7 +874,6 @@ model JobExecution {
 
     @@index([projectId, status])
     @@index([projectId, id])
-    @@index([projectId])
     @@index([jobConfigurationId])
     @@index([jobOutputScoreId])
     @@index([jobInputTraceId])
@@ -841,7 +906,6 @@ model PosthogIntegration {
     enabled                Boolean
     createdAt              DateTime  @default(now()) @map("created_at")
 
-    @@index([projectId])
     @@map("posthog_integrations")
 }
 

packages/shared/prisma/seed.ts

@@ -5,6 +5,7 @@ import {
   ObservationType,
   ScoreSource,
   ScoreDataType,
+  AnnotationQueueObjectType,
 } from "../src/index";
 import { hash } from "bcryptjs";
 import { parseArgs } from "node:util";
@@ -12,7 +13,7 @@ import { parseArgs } from "node:util";
 import { chunk } from "lodash";
 import { v4 } from "uuid";
 import { ModelUsageUnit } from "../src";
-import { getDisplaySecretKey, hashSecretKey } from "../src/server";
+import { getDisplaySecretKey, hashSecretKey, logger } from "../src/server";
 import { encrypt } from "../src/encryption";
 import { redis } from "../src/server/redis/redis";
 
@@ -77,6 +78,9 @@ async function main() {
     create: {
       id: seedOrgId,
       name: "Seed Org",
+      cloudConfig: {
+        plan: "Team",
+      },
     },
   });
 
@@ -250,6 +254,11 @@ async function main() {
       project2,
     ]);
 
+    const queueIds = await generateQueuesForProject(
+      [project1, project2],
+      configIdsAndNames
+    );
+
     const promptIds = await generatePromptsForProject([project1, project2]);
 
     const envTags = [null, "development", "staging", "production"];
@@ -257,21 +266,38 @@ async function main() {
 
     const traceVolume = environment === "load" ? LOAD_TRACE_VOLUME : 100;
 
-    const { traces, observations, scores, sessions, events } = createObjects(
+    const {
+      traces,
+      observations,
+      scores,
+      sessions,
+      events,
+      comments,
+      queueItems,
+    } = createObjects(
       traceVolume,
       envTags,
       colorTags,
       project1,
       project2,
       promptIds,
+      queueIds,
       configIdsAndNames
     );
 
-    console.log(
+    logger.info(
       `Seeding ${traces.length} traces, ${observations.length} observations, and ${scores.length} scores`
     );
 
-    await uploadObjects(traces, observations, scores, sessions, events);
+    await uploadObjects(
+      traces,
+      observations,
+      scores,
+      sessions,
+      events,
+      comments,
+      queueItems
+    );
 
     // If openai key is in environment, add it to the projects LLM API keys
     const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
@@ -287,7 +313,7 @@ async function main() {
         },
       });
     } else {
-      console.warn(
+      logger.warn(
         "No OPENAI_API_KEY found in environment. Skipping seeding LLM API key."
       );
     }
@@ -449,13 +475,13 @@ main()
   .then(async () => {
     await prisma.$disconnect();
     redis?.disconnect();
-    console.log("Disconnected from postgres and redis");
+    logger.info("Disconnected from postgres and redis");
   })
   .catch(async (e) => {
-    console.error(e);
+    logger.error(e);
     await prisma.$disconnect();
     redis?.disconnect();
-    console.log("Disconnected from postgres and redis");
+    logger.info("Disconnected from postgres and redis");
     process.exit(1);
   });
 
@@ -464,7 +490,9 @@ async function uploadObjects(
   observations: Prisma.ObservationCreateManyInput[],
   scores: Prisma.ScoreCreateManyInput[],
   sessions: Prisma.TraceSessionCreateManyInput[],
-  events: Prisma.ObservationCreateManyInput[]
+  events: Prisma.ObservationCreateManyInput[],
+  comments: Prisma.CommentCreateManyInput[],
+  queueItems: Prisma.AnnotationQueueItemCreateManyInput[]
 ) {
   let promises: Prisma.PrismaPromise<unknown>[] = [];
 
@@ -484,7 +512,7 @@ async function uploadObjects(
 
   for (let i = 0; i < promises.length; i++) {
     if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
-      console.log(
+      logger.info(
         `Seeding of Sessions ${((i + 1) / promises.length) * 100}% complete`
       );
     await promises[i];
@@ -501,7 +529,7 @@ async function uploadObjects(
   });
   for (let i = 0; i < promises.length; i++) {
     if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
-      console.log(
+      logger.info(
         `Seeding of Traces ${((i + 1) / promises.length) * 100}% complete`
       );
     await promises[i];
@@ -518,7 +546,7 @@ async function uploadObjects(
 
   for (let i = 0; i < promises.length; i++) {
     if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
-      console.log(
+      logger.info(
         `Seeding of Observations ${((i + 1) / promises.length) * 100}% complete`
       );
     await promises[i];
@@ -535,7 +563,7 @@ async function uploadObjects(
 
   for (let i = 0; i < promises.length; i++) {
     if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
-      console.log(
+      logger.info(
         `Seeding of Events ${((i + 1) / promises.length) * 100}% complete`
       );
     await promises[i];
@@ -551,11 +579,43 @@ async function uploadObjects(
   });
   for (let i = 0; i < promises.length; i++) {
     if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
-      console.log(
+      logger.info(
         `Seeding of Scores ${((i + 1) / promises.length) * 100}% complete`
       );
     await promises[i];
   }
+
+  promises = [];
+  chunk(comments, chunkSize).forEach((chunk) => {
+    promises.push(
+      prisma.comment.createMany({
+        data: chunk,
+      })
+    );
+  });
+  for (let i = 0; i < promises.length; i++) {
+    if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
+      logger.info(
+        `Seeding of Comments ${((i + 1) / promises.length) * 100}% complete`
+      );
+    await promises[i];
+  }
+
+  promises = [];
+  chunk(queueItems, chunkSize).forEach((chunk) => {
+    promises.push(
+      prisma.annotationQueueItem.createMany({
+        data: chunk,
+      })
+    );
+  });
+  for (let i = 0; i < promises.length; i++) {
+    if (i + 1 >= promises.length || i % Math.ceil(promises.length / 10) === 0)
+      logger.info(
+        `Seeding of Annotation Queue Items ${((i + 1) / promises.length) * 100}% complete`
+      );
+    await promises[i];
+  }
 }
 
 function createObjects(
@@ -565,6 +625,7 @@ function createObjects(
   project1: Project,
   project2: Project,
   promptIds: Map<string, string[]>,
+  queueIds: Map<string, string[]>,
   configParams: Map<
     string,
     {
@@ -581,6 +642,8 @@ function createObjects(
   const sessions: Prisma.TraceSessionCreateManyInput[] = [];
   const events: Prisma.ObservationCreateManyInput[] = [];
   const configs: Prisma.ScoreConfigCreateManyInput[] = [];
+  const comments: Prisma.CommentCreateManyInput[] = [];
+  const queueItems: Prisma.AnnotationQueueItemCreateManyInput[] = [];
 
   for (let i = 0; i < traceVolume; i++) {
     // print progress to console with a progress bar that refreshes every 10 iterations
@@ -611,6 +674,7 @@ function createObjects(
     const trace = {
       id: `trace-${v4()}`,
       timestamp: traceTs,
+      createdAt: traceTs,
       projectId: projectId,
       name: ["generate-outreach", "label-inbound", "draft-response"][
         i % 3
@@ -662,6 +726,21 @@ function createObjects(
       }),
     };
 
+    const queueItem = [
+      ...(Math.random() > 0.9 && queueIds.get(projectId)?.[0]
+        ? [
+            {
+              queueId: queueIds.get(projectId)?.[0] as string,
+              objectId: trace.id,
+              objectType: AnnotationQueueObjectType.TRACE,
+              projectId,
+            },
+          ]
+        : []),
+    ];
+
+    queueItems.push(...queueItem);
+
     const traceScores = [
       ...(Math.random() > 0.5
         ? [
@@ -669,6 +748,7 @@ function createObjects(
               traceId: trace.id,
               name: annotationScoreName,
               timestamp: traceTs,
+              createdAt: traceTs,
               source: ScoreSource.ANNOTATION,
               projectId,
               authorUserId: `user-${i}`,
@@ -685,6 +765,7 @@ function createObjects(
               name: "sentiment",
               value: Math.floor(Math.random() * 10) - 5,
               timestamp: traceTs,
+              createdAt: traceTs,
               source: ScoreSource.API,
               projectId,
               dataType: ScoreDataType.NUMERIC,
@@ -697,6 +778,7 @@ function createObjects(
               traceId: trace.id,
               name: "Completeness",
               timestamp: traceTs,
+              createdAt: traceTs,
               source: ScoreSource.API,
               projectId,
               dataType: ScoreDataType.CATEGORICAL,
@@ -707,6 +789,15 @@ function createObjects(
         : []),
     ];
 
+    if (Math.random() > 0.9)
+      comments.push({
+        projectId: trace.projectId,
+        objectId: trace.id,
+        objectType: "TRACE",
+        content: "Trace comment content",
+        ...(Math.random() > 0.5 ? { authorUserId: `user-${i}` } : {}),
+      });
+
     scores.push(...traceScores);
 
     const existingSpanIds: string[] = [];
@@ -725,6 +816,7 @@ function createObjects(
         type: ObservationType.SPAN,
         id: `span-${v4()}`,
         startTime: spanTsStart,
+        createdAt: spanTsStart,
         endTime: spanTsEnd,
         name: `span-${i}-${j}`,
         metadata: {
@@ -792,45 +884,21 @@ function createObjects(
             )
           ];
 
+        const { input, output } = getGenerationInputOutput();
+
         const generation = {
           type: ObservationType.GENERATION,
           id: `generation-${v4()}`,
           startTime: generationTsStart,
+          createdAt: generationTsStart,
           endTime: generationTsEnd,
           completionStartTime:
             Math.random() > 0.5 ? generationTsCompletionStart : undefined,
           name: `generation-${i}-${j}-${k}`,
           projectId: trace.projectId,
           promptId: promptId,
-          input:
-            Math.random() > 0.5
-              ? [
-                  {
-                    role: "system",
-                    content: "Be a helpful assistant",
-                  },
-                  {
-                    role: "user",
-                    content: "How can i create a *React* component?",
-                  },
-                ]
-              : {
-                  input: "How can i create a React component?",
-                  retrievedDocuments: [
-                    {
-                      title: "How to create a React component",
-                      url: "https://www.google.com",
-                      description: "A guide to creating React components",
-                    },
-                    {
-                      title: "React component creation",
-                      url: "https://www.google.com",
-                      description: "A guide to creating React components",
-                    },
-                  ],
-                },
-          output:
-            "Creating a React component can be done in two ways: as a functional component or as a class component. Let's start with a basic example of both.\n\n**Image**\n\n![Languse Example Image](https://static.langfuse.com/langfuse-dev/langfuse-example-image.jpeg)\n\n1.  **Functional Component**:\n\nA functional component is just a plain JavaScript function that accepts props as an argument, and returns a React element. Here's how you can create one:\n\n```javascript\nimport React from 'react';\nfunction Greeting(props) {\n  return <h1>Hello, {props.name}</h1>;\n}\nexport default Greeting;\n```\n\nTo use this component in another file, you can do:\n\n```javascript\nimport Greeting from './Greeting';\nfunction App() {\n  return (\n    <div>\n      <Greeting name=\"John\" />\n    </div>\n  );\n}\nexport default App;\n```\n\n2.  **Class Component**:\n\nYou can also define components as classes in React. These have some additional features compared to functional components:\n\n```javascript\nimport React, { Component } from 'react';\nclass Greeting extends Component {\n  render() {\n    return <h1>Hello, {this.props.name}</h1>;\n  }\n}\nexport default Greeting;\n```\n\nAnd here's how to use this component:\n\n```javascript\nimport Greeting from './Greeting';\nclass App extends Component {\n  render() {\n    return (\n      <div>\n        <Greeting name=\"John\" />\n      </div>\n    );\n  }\n}\nexport default App;\n```\n\nWith the advent of hooks in React, functional components can do everything that class components can do and hence, the community has been favoring functional components over class components.\n\nRemember to import React at the top of your file whenever you're creating a component, because JSX transpiles to `React.createElement` calls under the hood.",
+          input,
+          output,
           model: model,
           internalModel: model,
           modelParameters: {
@@ -866,6 +934,8 @@ function createObjects(
             traceId: trace.id,
             source: ScoreSource.API,
             projectId: trace.projectId,
+            timestamp: generationTsEnd,
+            createdAt: traceTs,
           });
         if (Math.random() > 0.6)
           scores.push({
@@ -875,6 +945,16 @@ function createObjects(
             traceId: trace.id,
             source: ScoreSource.API,
             projectId: trace.projectId,
+            timestamp: generationTsEnd,
+            createdAt: traceTs,
+          });
+
+        if (Math.random() > 0.8)
+          comments.push({
+            projectId: trace.projectId,
+            objectId: generation.id,
+            objectType: "OBSERVATION",
+            content: "Observation comment content",
           });
 
         for (let l = 0; l < Math.floor(Math.random() * 2); l++) {
@@ -890,6 +970,7 @@ function createObjects(
             type: ObservationType.EVENT,
             id: `event-${v4()}`,
             startTime: eventTs,
+            createdAt: eventTs,
             name: `event-${i}-${j}-${k}-${l}`,
             metadata: {
               user: `user-${i}@langfuse.com`,
@@ -912,8 +993,10 @@ function createObjects(
     observations,
     scores,
     configs,
+    queueItems,
     sessions: uniqueSessions,
     events,
+    comments,
   };
 }
 
@@ -1188,3 +1271,125 @@ async function generateConfigs(project: Project) {
 
   return configNameAndId;
 }
+
+function getGenerationInputOutput(): {
+  input: Prisma.InputJsonValue;
+  output: Prisma.InputJsonValue;
+} {
+  if (Math.random() > 0.9) {
+    const input = [
+      {
+        role: "user",
+        content: [
+          { text: "What’s depicted in this image?", type: "text" },
+          {
+            type: "image_url",
+            image_url: {
+              url: "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+            },
+          },
+          { text: "Describe the scene in detail.", type: "text" },
+        ],
+      },
+    ];
+
+    const output =
+      "The image depicts a serene landscape featuring a wooden pathway or boardwalk that winds through a lush green field. The field is filled with tall grass and surrounded by trees and shrubs. Above, the sky is bright with scattered clouds, suggesting a clear and pleasant day. The scene conveys a sense of tranquility and natural beauty.";
+
+    return { input, output };
+  }
+
+  const input =
+    Math.random() > 0.5
+      ? [
+          {
+            role: "system",
+            content: "Be a helpful assistant",
+          },
+          {
+            role: "user",
+            content: "How can i create a *React* component?",
+          },
+        ]
+      : {
+          input: "How can i create a React component?",
+          retrievedDocuments: [
+            {
+              title: "How to create a React component",
+              url: "https://www.google.com",
+              description: "A guide to creating React components",
+            },
+            {
+              title: "React component creation",
+              url: "https://www.google.com",
+              description: "A guide to creating React components",
+            },
+          ],
+        };
+
+  const output =
+    "Creating a React component can be done in two ways: as a functional component or as a class component. Let's start with a basic example of both.\n\n**Image**\n\n![Languse Example Image](https://static.langfuse.com/langfuse-dev/langfuse-example-image.jpeg)\n\n1.  **Functional Component**:\n\nA functional component is just a plain JavaScript function that accepts props as an argument, and returns a React element. Here's how you can create one:\n\n```javascript\nimport React from 'react';\nfunction Greeting(props) {\n  return <h1>Hello, {props.name}</h1>;\n}\nexport default Greeting;\n```\n\nTo use this component in another file, you can do:\n\n```javascript\nimport Greeting from './Greeting';\nfunction App() {\n  return (\n    <div>\n      <Greeting name=\"John\" />\n    </div>\n  );\n}\nexport default App;\n```\n\n2.  **Class Component**:\n\nYou can also define components as classes in React. These have some additional features compared to functional components:\n\n```javascript\nimport React, { Component } from 'react';\nclass Greeting extends Component {\n  render() {\n    return <h1>Hello, {this.props.name}</h1>;\n  }\n}\nexport default Greeting;\n```\n\nAnd here's how to use this component:\n\n```javascript\nimport Greeting from './Greeting';\nclass App extends Component {\n  render() {\n    return (\n      <div>\n        <Greeting name=\"John\" />\n      </div>\n    );\n  }\n}\nexport default App;\n```\n\nWith the advent of hooks in React, functional components can do everything that class components can do and hence, the community has been favoring functional components over class components.\n\nRemember to import React at the top of your file whenever you're creating a component, because JSX transpiles to `React.createElement` calls under the hood.";
+
+  return { input, output };
+}
+
+async function generateQueuesForProject(
+  projects: Project[],
+  configIdsAndNames: Map<
+    string,
+    {
+      name: string;
+      id: string;
+      dataType: ScoreDataType;
+      categories: ConfigCategory[] | null;
+    }[]
+  >
+) {
+  const projectIdsToQueues: Map<string, string[]> = new Map();
+
+  await Promise.all(
+    projects.map(async (project) => {
+      const queueIds = await generateQueues(
+        project,
+        configIdsAndNames.get(project.id) ?? []
+      );
+      projectIdsToQueues.set(project.id, queueIds);
+    })
+  );
+  return projectIdsToQueues;
+}
+
+async function generateQueues(
+  project: Project,
+  configIdsAndNames: {
+    name: string;
+    id: string;
+    dataType: ScoreDataType;
+    categories: ConfigCategory[] | null;
+  }[]
+) {
+  const queue = {
+    id: `queue-${v4()}`,
+    name: "Default",
+    description: "Default queue",
+    scoreConfigIds: configIdsAndNames.map((config) => config.id),
+    projectId: project.id,
+  };
+
+  await prisma.annotationQueue.upsert({
+    where: {
+      projectId_name: {
+        projectId: queue.projectId,
+        name: queue.name,
+      },
+    },
+    create: {
+      ...queue,
+    },
+    update: {
+      id: queue.id,
+    },
+  });
+
+  return [queue.id];
+}

packages/shared/scripts/load-seed.ts

@@ -0,0 +1,133 @@
+import { randomUUID } from "crypto";
+import { prisma } from "../src/db";
+import {
+  clickhouseClient,
+  getDisplaySecretKey,
+  hashSecretKey,
+  logger,
+} from "../src/server";
+import { prepareClickhouse } from "./prepareClickhouse";
+import { redis } from "@langfuse/shared/src/server";
+
+const createRandomProjectId = () => randomUUID().toString();
+
+const prepareProjectsAndApiKeys = async (
+  numOfProjects: number,
+  opts: { requiredProjectIds: string[] }
+) => {
+  const { requiredProjectIds } = opts;
+  const projectsToCreate = numOfProjects - requiredProjectIds.length;
+  const projectIds = [...requiredProjectIds];
+
+  for (let i = 0; i < projectsToCreate; i++) {
+    projectIds.push(createRandomProjectId());
+  }
+
+  const operations = projectIds.map(async (projectId) => {
+    const orgId = `org-${projectId}`;
+
+    await prisma.organization.upsert({
+      where: { id: orgId },
+      update: {},
+      create: {
+        id: orgId,
+        name: `Organization for ${projectId}`,
+      },
+    });
+
+    await prisma.project.upsert({
+      where: { id: projectId },
+      update: {},
+      create: {
+        id: projectId,
+        name: `Project ${projectId}`,
+        orgId: orgId,
+      },
+    });
+
+    const apiKeyId = `api-key-${projectId}`;
+    const apiKeyExists = await prisma.apiKey.findUnique({
+      where: { id: apiKeyId },
+    });
+    if (!apiKeyExists) {
+      const sk = await hashSecretKey(
+        `sk-${Math.random().toString(36).substr(2, 9)}`
+      );
+      await prisma.apiKey.create({
+        data: {
+          id: apiKeyId,
+          note: `API Key for ${projectId}`,
+          publicKey: `pk-${Math.random().toString(36).substr(2, 9)}`,
+          hashedSecretKey: sk,
+          displaySecretKey: getDisplaySecretKey(sk),
+          project: {
+            connect: {
+              id: projectId,
+            },
+          },
+        },
+      });
+    }
+  });
+
+  await Promise.all(operations);
+  return projectIds;
+};
+
+async function main() {
+  let numOfProjects = parseInt(process.argv[3], 10);
+  let numberOfDays = parseInt(process.argv[4], 10);
+  let totalObservations = parseInt(process.argv[5], 10);
+
+  if (isNaN(totalObservations)) {
+    logger.warn(
+      "Total observations not provided or invalid. Defaulting to 1000 observations."
+    );
+    totalObservations = 1000;
+  }
+
+  if (isNaN(numOfProjects)) {
+    logger.warn(
+      "Number of projects not provided or invalid. Defaulting to 10 projects."
+    );
+    numOfProjects = 10;
+  }
+
+  if (isNaN(numberOfDays)) {
+    logger.warn(
+      "Number of days not provided or invalid. Defaulting to 3 days."
+    );
+    numberOfDays = 3;
+  }
+
+  logger.info(
+    `Preparing Clickhouse for ${numOfProjects} projects and ${numberOfDays} days with max Observations ${totalObservations}.`
+  );
+
+  try {
+    const projectIds = [
+      "7a88fb47-b4e2-43b8-a06c-a5ce950dc53a",
+      "239ad00f-562f-411d-af14-831c75ddd875",
+    ];
+
+    const createdProjectIds = await prepareProjectsAndApiKeys(numOfProjects, {
+      requiredProjectIds: projectIds,
+    });
+
+    await prepareClickhouse(createdProjectIds, {
+      numberOfDays,
+      totalObservations: totalObservations ?? 1000,
+    });
+
+    logger.info("Clickhouse preparation completed successfully.");
+  } catch (error) {
+    logger.error("Error during Clickhouse preparation:", error);
+  } finally {
+    await clickhouseClient.close();
+    await prisma.$disconnect();
+    redis?.disconnect();
+    logger.info("Disconnected from Clickhouse.");
+  }
+}
+
+main();

packages/shared/scripts/prepareClickhouse.ts

@@ -0,0 +1,222 @@
+import { clickhouseClient, logger } from "../src/server";
+
+function randn_bm(min: number, max: number, skew: number) {
+  let u = 0,
+    v = 0;
+  while (u === 0) u = Math.random(); //Converting [0,1) to (0,1)
+  while (v === 0) v = Math.random();
+  let num = Math.sqrt(-2.0 * Math.log(u)) * Math.cos(2.0 * Math.PI * v);
+
+  num = num / 10.0 + 0.5; // Translate to 0 -> 1
+  if (num > 1 || num < 0)
+    num = randn_bm(min, max, skew); // resample between 0 and 1 if out of range
+  else {
+    num = Math.pow(num, skew); // Skew
+    num *= max - min; // Stretch to fill range
+    num += min; // offset to min
+  }
+  return num;
+}
+
+export const prepareClickhouse = async (
+  projectIds: string[],
+  opts: {
+    numberOfDays: number;
+    totalObservations: number;
+  }
+) => {
+  logger.info(
+    `Preparing Clickhouse for ${projectIds.length} projects and ${opts.numberOfDays} days.`
+  );
+
+  const projectData = projectIds.map((projectId) => {
+    const observationsPerProject = Math.ceil(
+      randn_bm(0, opts.totalObservations, 2)
+    ); // Skew the number of observations
+
+    const tracesPerProject = Math.floor(observationsPerProject / 6); // On average, one trace should have 6 observations
+    const scoresPerProject = tracesPerProject * 10; // On average, one trace should have 10 scores
+    return {
+      projectId,
+      observationsPerProject,
+      tracesPerProject,
+      scoresPerProject,
+    };
+  });
+
+  for (const data of projectData) {
+    const {
+      projectId,
+      tracesPerProject,
+      observationsPerProject,
+      scoresPerProject,
+    } = data;
+    logger.info(
+      `Preparing Clickhouse for ${projectId}: Traces: ${tracesPerProject}, Scores: ${scoresPerProject}, Observations: ${observationsPerProject}`
+    );
+
+    const tracesQuery = `
+    INSERT INTO traces
+    SELECT toString(number) AS id,
+      toDateTime(now() - randUniform(0, ${opts.numberOfDays} * 24 * 60 * 60)) AS timestamp,
+      concat('name_', toString(rand() % 100)) AS name,
+      concat('user_id_', toString(randUniform(0, 100))) AS user_id,
+      map('key', 'value') AS metadata,
+      concat('release_', toString(randUniform(0, 100))) AS release,
+      concat('version_', toString(randUniform(0, 100))) AS version,
+      '${projectId}' AS project_id,
+      if(rand() < 0.8, true, false) as public,
+      if(rand() < 0.8, true, false) as bookmarked,
+      array('tag1', 'tag2') as tags,
+      repeat('input', toInt64(randExponential(1 / 100))) AS input,
+      repeat('output', toInt64(randExponential(1 / 100))) AS output,
+      concat('session_', toString(rand() % 100)) AS session_id,
+      timestamp AS created_at,
+      timestamp AS updated_at,
+      timestamp AS event_ts
+    FROM numbers(${tracesPerProject});
+  `;
+
+    const observationsQuery = `
+    INSERT INTO observations
+    SELECT toString(number) AS id,
+      toString(floor(randUniform(0, ${tracesPerProject}))) AS trace_id,
+      '${projectId}' AS project_id,
+      if(rand() < 0.47, 'GENERATION', if(rand() < 0.94, 'SPAN', 'EVENT')) AS type,
+      toString(rand()) AS parent_observation_id,
+      toDateTime(now() - randUniform(0, ${opts.numberOfDays} * 24 * 60 * 60)) AS start_time,
+      addSeconds(start_time, if(rand() < 0.6, floor(randUniform(0, 20)), floor(randUniform(0, 3600)))) AS end_time,
+      concat('name', toString(rand() % 100)) AS name,
+      map('key', 'value') AS metadata,
+      if(rand() < 0.9, 'DEFAULT', if(rand() < 0.5, 'ERROR', if(rand() < 0.5, 'DEBUG', 'WANING'))) AS level,
+      'status_message' AS status_message,
+      'version' AS version,
+      repeat('input', toInt64(randExponential(1 / 100))) AS input,
+      repeat('output', toInt64(randExponential(1 / 100))) AS output,
+      case
+        when number % 2 = 0 then 'claude-3-haiku-20240307'
+        else 'gpt-4'
+      end as provided_model_name,
+      case
+        when number % 2 = 0 then 'cltr0w45b000008k1407o9qv1'
+        else 'clrntkjgy000f08jx79v9g1xj'
+      end as internal_model_id,
+      'model_parameters' AS model_parameters,
+      toInt32(randUniform(0, 1000)) AS provided_input_usage_units,
+      toInt32(randUniform(0, 1000)) AS provided_output_usage_units,
+      toInt32(randUniform(0, 1000)) AS provided_total_usage_units,
+      toInt32(randUniform(0, 1000)) AS input_usage_units,
+      toInt32(randUniform(0, 1000)) AS output_usage_units,
+      toInt32(randUniform(0, 1000)) AS total_usage_units,
+      toInt32(randUniform(0, 1000)) AS provided_input_cost,
+      toInt32(randUniform(0, 1000)) AS provided_output_cost,
+      toInt32(randUniform(0, 1000)) AS provided_total_cost,
+      'TOKENS' AS unit,
+      toInt32(randUniform(0, 1000)) AS input_cost,
+      toInt32(randUniform(0, 1000)) AS output_cost,
+      toInt32(randUniform(0, 1000)) AS total_cost,
+      start_time AS completion_start_time,
+      toString(rand()) AS prompt_id,
+      toString(rand()) AS prompt_name,
+      1000 AS prompt_version,
+      start_time AS created_at,
+      start_time AS updated_at,
+      start_time AS event_ts
+    FROM numbers(${observationsPerProject});
+  `;
+
+    const scoresQuery = `
+    INSERT INTO scores
+    SELECT toString(floor(randUniform(0, 100))) AS id,
+      toDateTime(now() - randUniform(0, ${opts.numberOfDays} * 24 * 60 * 60)) AS timestamp,
+      '${projectId}' AS project_id,
+      toString(floor(randUniform(0, ${tracesPerProject}))) AS trace_id,
+      if(
+        rand() > 0.9,
+        toString(floor(randUniform(0, ${observationsPerProject}))),
+        NULL
+      ) AS observation_id,
+      concat('name_', toString(rand() % 100)) AS name,
+      randUniform(0, 100) as value,
+      'API' as source,
+      'comment' as comment,
+      toString(rand() % 100) as author_user_id,
+      toString(rand() % 100) as config_id,
+      toString(rand() % 100) as data_type,
+      toString(rand() % 100) as string_value,
+      timestamp AS created_at,
+      timestamp AS updated_at,
+      timestamp AS event_ts
+    FROM numbers(${scoresPerProject});
+  `;
+
+    const queries = [tracesQuery, scoresQuery, observationsQuery];
+
+    for (const query of queries) {
+      logger.info(`Executing query: ${query}`);
+      await clickhouseClient.command({
+        query,
+        clickhouse_settings: {
+          wait_end_of_query: 1,
+        },
+      });
+    }
+  }
+
+  const tables = ["traces", "scores", "observations"];
+  for (const table of tables) {
+    const query = `
+            SELECT
+            project_id,
+            count() AS per_project_count,
+            bar(per_project_count, 0, (
+                SELECT count(*)
+                FROM ${table}
+            ), 50) AS bar_representation
+          FROM ${table}
+          GROUP BY project_id
+          ORDER BY count() desc
+          `;
+
+    const result = await clickhouseClient.query({
+      query,
+      format: "TabSeparated",
+    });
+
+    logger.info(
+      `${table.charAt(0).toUpperCase() + table.slice(1)} per Project: \n` +
+        (await result.text())
+    );
+  }
+
+  const tablesWithDateColumns = [
+    { name: "traces", dateColumn: "timestamp" },
+    { name: "scores", dateColumn: "timestamp" },
+    { name: "observations", dateColumn: "start_time" },
+  ];
+
+  for (const { name: table, dateColumn } of tablesWithDateColumns) {
+    const query = `
+            SELECT
+            toDate(${dateColumn}) AS event_date,
+            count() AS per_date_count,
+            bar(per_date_count, 0, (
+                SELECT count(*)
+                FROM ${table}
+            ), 50) AS bar_representation
+          FROM ${table}
+          GROUP BY event_date
+          ORDER BY event_date desc
+          `;
+
+    const result = await clickhouseClient.query({
+      query,
+      format: "TabSeparated",
+    });
+
+    logger.info(
+      `${table.charAt(0).toUpperCase() + table.slice(1)} per Date: \n` +
+        (await result.text())
+    );
+  }
+};

packages/shared/src/db.ts

@@ -1,7 +1,7 @@
 // This file exports the prisma db connection, the Prisma Object, and the Typescript types.
 // This is not imported in the index.ts file of this package, as we must not import this into FE code.
 
-import { PrismaClient } from "@prisma/client";
+import { Prisma, PrismaClient } from "@prisma/client";
 import { env } from "process";
 import kyselyExtension from "prisma-extension-kysely";
 import {
@@ -11,21 +11,86 @@ import {
   PostgresQueryCompiler,
 } from "kysely";
 import { DB } from ".";
+import { logger } from "./server";
 
-// Instantiated according to the Prisma documentation
-// https://www.prisma.io/docs/orm/more/help-and-troubleshooting/help-articles/nextjs-prisma-client-dev-practices
+export class PrismaClientSingleton {
+  private static instance: PrismaClient;
 
-const prismaClientSingleton = () => {
-  return new PrismaClient({
-    log:
-      env.NODE_ENV === "development"
-        ? ["query", "error", "warn"]
-        : ["error", "warn"],
+  public static getInstance(): PrismaClient {
+    if (PrismaClientSingleton.instance) {
+      return PrismaClientSingleton.instance;
+    }
+
+    PrismaClientSingleton.instance = createPrismaInstance();
+
+    return PrismaClientSingleton.instance;
+  }
+}
+
+const createPrismaInstance = () => {
+  const client = new PrismaClient<
+    Prisma.PrismaClientOptions,
+    "warn" | "error" | "query"
+  >({
+    log: [
+      { emit: "event", level: "query" },
+      { emit: "event", level: "error" },
+      { emit: "event", level: "warn" },
+    ],
   });
+
+  if (env.NODE_ENV === "development") {
+    client.$on("query", (event) => {
+      logger.info(`prisma:query ${event.query}, ${event.duration}ms`);
+    });
+  }
+
+  client.$on("warn", (event) => {
+    logger.warn(`prisma:warn ${event.message}`);
+  });
+
+  client.$on("error", (event) => {
+    logger.error(`prisma:error ${event.message}`);
+  });
+  return client;
 };
 
-const kyselySingleton = (prismaClient: PrismaClient) => {
-  return prismaClient.$extends(
+export class KyselySingleton {
+  private static instance: { $kysely: Kysely<DB> };
+
+  public static getInstance() {
+    if (KyselySingleton.instance) {
+      return KyselySingleton.instance;
+    }
+
+    KyselySingleton.instance = PrismaClientSingleton.getInstance().$extends(
+      kyselyExtension({
+        kysely: (driver) =>
+          new Kysely<DB>({
+            dialect: {
+              // This is where the magic happens!
+              createDriver: () => driver,
+              // Don't forget to customize these to match your database!
+              createAdapter: () => new PostgresAdapter(),
+              createIntrospector: (db) => new PostgresIntrospector(db),
+              createQueryCompiler: () => new PostgresQueryCompiler(),
+            },
+          }),
+      })
+    );
+
+    return KyselySingleton.instance;
+  }
+}
+
+declare const globalThis: {
+  prismaGlobal: PrismaClient | undefined;
+  kyselyPrismaGlobal: { $kysely: Kysely<DB> } | undefined;
+} & typeof global;
+
+if (process.env.NODE_ENV === "development") {
+  globalThis.prismaGlobal ??= createPrismaInstance(); // regular instantiation
+  globalThis.kyselyPrismaGlobal ??= globalThis.prismaGlobal.$extends(
     kyselyExtension({
       kysely: (driver) =>
         new Kysely<DB>({
@@ -40,16 +105,11 @@ const kyselySingleton = (prismaClient: PrismaClient) => {
         }),
     })
   );
-};
-declare global {
-  // eslint-disable-next-line no-var
-  var prisma: undefined | ReturnType<typeof prismaClientSingleton>;
-  var kyselyPrisma: undefined | ReturnType<typeof kyselySingleton>;
 }
 
-export const prisma = globalThis.prisma ?? prismaClientSingleton();
-export const kyselyPrisma = globalThis.kyselyPrisma ?? kyselySingleton(prisma);
+export const prisma =
+  globalThis.prismaGlobal ?? PrismaClientSingleton.getInstance();
+export const kyselyPrisma =
+  globalThis.kyselyPrismaGlobal ?? KyselySingleton.getInstance();
 
 export * from "@prisma/client";
-
-if (process.env.NODE_ENV !== "production") globalThis.prisma = prisma;

packages/shared/src/env.ts

@@ -1,4 +1,5 @@
 import { z } from "zod";
+import { removeEmptyEnvVariables } from "./utils/environment";
 
 const EnvSchema = z.object({
   NODE_ENV: z
@@ -16,11 +17,12 @@ const EnvSchema = z.object({
     .nullable(),
   REDIS_AUTH: z.string().nullish(),
   REDIS_CONNECTION_STRING: z.string().nullish(),
+  REDIS_ENABLE_AUTO_PIPELINING: z.enum(["true", "false"]).default("true"),
   ENCRYPTION_KEY: z
     .string()
     .length(
       64,
-      "ENCRYPTION_KEY must be 256 bits, 64 string characters in hex format, generate via: openssl rand -hex 32"
+      "ENCRYPTION_KEY must be 256 bits, 64 string characters in hex format, generate via: openssl rand -hex 32",
     )
     .optional(),
   LANGFUSE_CACHE_PROMPT_ENABLED: z.enum(["true", "false"]).default("false"),
@@ -28,6 +30,14 @@ const EnvSchema = z.object({
   CLICKHOUSE_URL: z.string().url().optional(),
   CLICKHOUSE_USER: z.string().optional(),
   CLICKHOUSE_PASSWORD: z.string().optional(),
+  SALT: z.string().optional(), // used by components imported by web package
+  LANGFUSE_LOG_LEVEL: z
+    .enum(["trace", "debug", "info", "warn", "error", "fatal"])
+    .optional(),
+  LANGFUSE_LOG_FORMAT: z.enum(["text", "json"]).default("text"),
+  ENABLE_AWS_CLOUDWATCH_METRIC_PUBLISHING: z
+    .enum(["true", "false"])
+    .default("false"),
 });
 
-export const env = EnvSchema.parse(process.env);
+export const env = EnvSchema.parse(removeEmptyEnvVariables(process.env));

packages/shared/src/features/annotation/types.ts

@@ -32,6 +32,7 @@ const CreateAnnotationScoreBase = z.object({
   configId: z.string().optional(),
   observationId: z.string().optional(),
   comment: z.string().nullish(),
+  queueId: z.string().nullish(),
 });
 
 const UpdateAnnotationScoreBase = CreateAnnotationScoreBase.extend({
@@ -57,3 +58,15 @@ export const UpdateAnnotationScoreData = z.discriminatedUnion("dataType", [
   UpdateAnnotationScoreBase.merge(CategoricalData),
   UpdateAnnotationScoreBase.merge(BooleanData),
 ]);
+
+// annotation queues
+
+export const CreateQueueData = z.object({
+  name: z.string().min(1).max(35),
+  description: z.string().max(1000).optional(),
+  scoreConfigIds: z.array(z.string()).min(1, {
+    message: "At least 1 score config must be selected",
+  }),
+});
+
+export type CreateQueue = z.infer<typeof CreateQueueData>;

packages/shared/src/features/batchExport/types.ts

@@ -19,6 +19,8 @@ export enum BatchExportFileFormat {
 
 export enum BatchExportTableName {
   Sessions = "sessions",
+  Traces = "traces",
+  Generations = "generations",
 }
 
 export const exportOptions: Record<

packages/shared/src/features/comments/types.ts

@@ -0,0 +1,22 @@
+import { z } from "zod";
+
+const COMMENT_OBJECT_TYPES = [
+  "TRACE",
+  "OBSERVATION",
+  "SESSION",
+  "PROMPT",
+] as const;
+
+export const CreateCommentData = z.object({
+  projectId: z.string(),
+  content: z.string().trim().min(1).max(500),
+  objectId: z.string(),
+  objectType: z.enum(COMMENT_OBJECT_TYPES),
+});
+
+export const DeleteCommentData = z.object({
+  projectId: z.string(),
+  commentId: z.string(),
+  objectId: z.string(),
+  objectType: z.enum(COMMENT_OBJECT_TYPES),
+});

packages/shared/src/features/entitlements/plans.ts

@@ -0,0 +1,17 @@
+export const planLabels = {
+  oss: "OSS",
+  "cloud:hobby": "Hobby",
+  "cloud:pro": "Pro",
+  "cloud:team": "Team",
+  "self-hosted:enterprise": "Enterprise",
+} as const;
+
+export type Plan = keyof typeof planLabels;
+
+export const plans = Object.keys(planLabels) as Plan[];
+
+// This function is kept here to ensure consistency when updating plan names in the future.
+export const isCloudPlan = (plan: Plan) => plan.startsWith("cloud");
+
+export const isPlan = (value: string): value is Plan =>
+  plans.includes(value as Plan);

packages/shared/src/features/evals/types.ts

@@ -1,5 +1,4 @@
 import z from "zod";
-import { LLMAdapter } from "../..";
 
 export const langfuseObjects = [
   "trace",
@@ -77,18 +76,6 @@ export const availableEvalVariables = [
   },
 ];
 
-export const evalModelsByAdapter: Record<LLMAdapter, string[]> = {
-  [LLMAdapter.OpenAI]: [
-    "gpt-4o",
-    "gpt-4o-mini",
-    "gpt-4o-2024-08-06", // cheaper than gpt-4o
-    "gpt-4-turbo-preview",
-    "gpt-3.5-turbo",
-  ] as const,
-  [LLMAdapter.Anthropic]: [] as const,
-  [LLMAdapter.Azure]: [] as const,
-};
-
 export const OutputSchema = z.object({
   reasoning: z.string(),
   score: z.string(),

packages/shared/src/features/scores/scoreConfigTypes.ts

@@ -144,7 +144,7 @@ const ValidatedScoreConfigSchema = z
 
 /**
  * Use this function when pulling a list of score configs from the database before using in the application to ensure type safety.
- * All score configs are expected to pass the validation. If a score fails validation, it will be logged to Sentry.
+ * All score configs are expected to pass the validation. If a score fails validation, it will be logged to Otel.
  * @param scoreConfigs
  * @returns list of validated score configs
  */

packages/shared/src/features/scores/scoreTypes.ts

@@ -55,6 +55,7 @@ const ScoreBase = z.object({
   configId: z.string().nullish(),
   createdAt: z.coerce.date(),
   updatedAt: z.coerce.date(),
+  queueId: z.string().nullish(),
 });
 
 const BaseScoreBody = z.object({
@@ -155,7 +156,7 @@ export const ScorePropsAgainstConfig = z.union([
 
 /**
  * Use this function when pulling a list of scores from the database before using in the application to ensure type safety.
- * All scores are expected to pass the validation. If a score fails validation, it will be logged to Sentry.
+ * All scores are expected to pass the validation. If a score fails validation, it will be logged to Otel.
  * @param scores
  * @returns list of validated scores
  */
@@ -234,6 +235,8 @@ export const GetScoresQuery = z.object({
   userId: z.string().nullish(),
   dataType: z.enum(ScoreDataType).nullish(),
   configId: z.string().nullish(),
+  queueId: z.string().nullish(),
+  traceTags: z.union([z.array(z.string()), z.string()]).nullish(),
   name: z.string().nullish(),
   fromTimestamp: stringDateTime,
   toTimestamp: stringDateTime,
@@ -255,6 +258,7 @@ const LegacyGetScoreResponseDataV1 = z.intersection(
   z.object({
     trace: z.object({
       userId: z.string().nullish(),
+      tags: z.array(z.string()).nullish(),
     }),
   })
 );

packages/shared/src/index.ts

@@ -1,24 +1,24 @@
 export * from "./constants";
-export * from "./queries";
-export * from "./queues";
 export * from "./interfaces/filters";
 export * from "./interfaces/orderBy";
+export * from "./interfaces/cloudConfigSchema";
+export * from "./interfaces/parseDbOrg";
+export * from "./interfaces/customLLMProviderConfigSchemas";
 export * from "./tableDefinitions";
 export * from "./types";
-export * from "./filterToPrisma";
-export * from "./orderByToPrisma";
 export * from "./tracesTable";
-export * from "./server/auth";
+export * from "./server/auth/apiKeys";
 export * from "./observationsTable";
 export * from "./utils/zod";
 export * from "./utils/json";
 export * from "./utils/objects";
 export * from "./utils/typeChecks";
+export * from "./features/entitlements/plans";
+export * from "./interfaces/rate-limits";
 export { env } from "./env";
 
 // llm api
 export * from "./server/llm/types";
-export * from "./server/llm/fetchLLMCompletion";
 
 // evals
 export * from "./features/evals/types";
@@ -31,9 +31,14 @@ export * from "./features/annotation/types";
 export * from "./features/scores/scoreConfigTypes";
 export * from "./features/scores/scoreTypes";
 
+// comments
+export * from "./features/comments/types";
+
 // export db types only
 export * from "@prisma/client";
 export { type DB } from "../prisma/generated/types";
 
 // errors
 export * from "./errors/index";
+
+export * from "./utils/environment";

packages/shared/src/interfaces/cloudConfigSchema.ts

@@ -0,0 +1,22 @@
+import { z } from "zod";
+import { CloudConfigRateLimit } from "./rate-limits";
+
+export const CloudConfigSchema = z.object({
+  plan: z.enum(["Hobby", "Pro", "Team", "Enterprise"]).optional(),
+  monthlyObservationLimit: z.number().int().positive().optional(),
+  // used for table and dashboard queries
+  defaultLookBackDays: z.number().int().positive().optional(),
+  // need to update stripe webhook if you change this, it fetches from db via these fields
+  stripe: z
+    .object({
+      customerId: z.string().optional(),
+      activeSubscriptionId: z.string().optional(),
+      activeProductId: z.string().optional(),
+    })
+    .optional(),
+
+  // custom rate limits for an organization
+  rateLimitOverrides: CloudConfigRateLimit.optional(),
+});
+
+export type CloudConfigSchema = z.infer<typeof CloudConfigSchema>;

packages/shared/src/interfaces/customLLMProviderConfigSchemas.ts

@@ -0,0 +1,12 @@
+import { z } from "zod";
+
+export const BedrockConfigSchema = z.object({ region: z.string() });
+export type BedrockConfig = z.infer<typeof BedrockConfigSchema>;
+
+export const BedrockCredentialSchema = z
+  .object({
+    accessKeyId: z.string(),
+    secretAccessKey: z.string(),
+  })
+  .optional();
+export type BedrockCredential = z.infer<typeof BedrockCredentialSchema>;

packages/shared/src/interfaces/parseDbOrg.ts

@@ -1,5 +1,5 @@
-import { CloudConfigSchema } from "@/src/features/organizations/utils/cloudConfigSchema";
-import { type Organization } from "@langfuse/shared";
+import { type Organization } from "@prisma/client";
+import { CloudConfigSchema } from "./cloudConfigSchema";
 
 type parsedOrg = Omit<Organization, "cloudConfig"> & {
   cloudConfig: CloudConfigSchema | null;

packages/shared/src/interfaces/rate-limits.ts

@@ -0,0 +1,31 @@
+import z from "zod";
+import { ApiAccessScope } from "../server";
+
+export const RateLimitResource = z.enum([
+  "ingestion",
+  "public-api",
+  "public-api-metrics",
+  "prompts",
+  "legacy-ingestion",
+]);
+
+// result of the rate limit check.
+export type RateLimitResult = {
+  resource: z.infer<typeof RateLimitResource>;
+  points: number;
+  scope: ApiAccessScope;
+
+  // from rate-limiter-flexible
+  remainingPoints: number;
+  msBeforeNext: number;
+  consumedPoints: number;
+  isFirstInDuration: boolean;
+};
+
+export const RateLimitConfig = z.object({
+  points: z.number().nullish(),
+  durationInSec: z.number().nullish(),
+  resource: RateLimitResource,
+});
+
+export const CloudConfigRateLimit = z.array(RateLimitConfig);

packages/shared/src/observationsTable.ts

@@ -18,6 +18,7 @@ export const observationsTableCols: ColumnDefinition[] = [
     type: "stringOptions",
     internal: 'o."name"',
     options: [], // to be added at runtime
+    nullable: true,
   },
   { name: "Trace ID", id: "traceId", type: "string", internal: 't."id"' },
   {
@@ -26,8 +27,15 @@ export const observationsTableCols: ColumnDefinition[] = [
     type: "stringOptions",
     internal: 't."name"',
     options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "User ID",
+    id: "userId",
+    type: "string",
+    internal: 't."user_id"',
+    nullable: true,
   },
-  { name: "User ID", id: "userId", type: "string", internal: 't."user_id"' },
   {
     name: "Start Time",
     id: "startTime",
@@ -44,7 +52,9 @@ export const observationsTableCols: ColumnDefinition[] = [
     name: "Time To First Token (s)",
     id: "timeToFirstToken",
     type: "number",
-    internal: 'o."completion_start_time" - o."start_time"',
+    internal:
+      'EXTRACT(EPOCH FROM (o."completion_start_time" - o."start_time"))',
+    nullable: true,
   },
   {
     name: "Latency (s)",
@@ -53,28 +63,32 @@ export const observationsTableCols: ColumnDefinition[] = [
     internal: '"latency"',
   },
   {
-    name: "Time Per Output Token (s)",
-    id: "timePerOutputToken",
+    name: "Tokens per second",
+    id: "tokensPerSecond",
     type: "number",
-    internal: '"latency" / o."completion_tokens"',
+    internal: 'o."completion_tokens" / "latency"',
+    nullable: true,
   },
   {
     name: "Input Cost ($)",
     id: "inputCost",
     type: "number",
     internal: 'o."calculated_input_cost"',
+    nullable: true,
   },
   {
     name: "Output Cost ($)",
     id: "outputCost",
     type: "number",
     internal: 'o."calculated_output_cost"',
+    nullable: true,
   },
   {
     name: "Total Cost ($)",
     id: "totalCost",
     type: "number",
     internal: 'o."calculated_total_cost"',
+    nullable: true,
   },
   {
     name: "Level",
@@ -88,6 +102,7 @@ export const observationsTableCols: ColumnDefinition[] = [
     id: "statusMessage",
     type: "string",
     internal: 'o."status_message"',
+    nullable: true,
   },
   {
     name: "Model",
@@ -95,24 +110,28 @@ export const observationsTableCols: ColumnDefinition[] = [
     type: "stringOptions",
     internal: 'o."model"',
     options: [], // to be added at runtime
+    nullable: true,
   },
   {
     name: "Input Tokens",
     id: "inputTokens",
     type: "number",
     internal: 'o."prompt_tokens"',
+    nullable: true,
   },
   {
     name: "Output Tokens",
     id: "outputTokens",
     type: "number",
     internal: 'o."completion_tokens"',
+    nullable: true,
   },
   {
     name: "Total Tokens",
     id: "totalTokens",
     type: "number",
     internal: 'o."total_tokens"',
+    nullable: true,
   },
   {
     name: "Usage",
@@ -137,6 +156,7 @@ export const observationsTableCols: ColumnDefinition[] = [
     id: "version",
     type: "string",
     internal: 'o."version"',
+    nullable: true,
   },
   {
     name: "Prompt Name",
@@ -144,12 +164,21 @@ export const observationsTableCols: ColumnDefinition[] = [
     type: "stringOptions",
     internal: "p.name",
     options: [], // to be added at runtime
+    nullable: true,
   },
   {
     name: "Prompt Version",
     id: "promptVersion",
     type: "number",
     internal: "p.version",
+    nullable: true,
+  },
+  {
+    name: "Trace Tags",
+    id: "tags",
+    type: "arrayOptions",
+    internal: "t.tags",
+    options: [], // to be added at runtime
   },
 ];
 
@@ -161,6 +190,7 @@ export type ObservationOptions = {
   traceName: Array<OptionsDefinition>;
   scores_avg: Array<string>;
   promptName: Array<OptionsDefinition>;
+  tags: Array<OptionsDefinition>;
 };
 
 export function observationsTableColsWithOptions(
@@ -182,6 +212,9 @@ export function observationsTableColsWithOptions(
     if (col.id === "promptName") {
       return { ...col, options: options?.promptName ?? [] };
     }
+    if (col.id === "tags") {
+      return { ...col, options: options?.tags ?? [] };
+    }
     return col;
   });
 }

packages/shared/src/queries/index.ts

@@ -1 +0,0 @@
-export { getSessionTableSQL } from "./getSessionTableSQL";

packages/shared/src/queues.ts

@@ -1,77 +0,0 @@
-import { z } from "zod";
-
-export enum EventName {
-  TraceUpsert = "TraceUpsert",
-  BatchExport = "BatchExport",
-  EvaluationExecution = "EvaluationExecution",
-}
-
-export const BatchExportJobSchema = z.object({
-  projectId: z.string(),
-  batchExportId: z.string(),
-});
-export const TraceUpsertEventSchema = z.object({
-  projectId: z.string(),
-  traceId: z.string(),
-});
-export const EvalExecutionEvent = z.object({
-  projectId: z.string(),
-  jobExecutionId: z.string(),
-});
-
-export type BatchExportJobType = z.infer<typeof BatchExportJobSchema>;
-export type TraceUpsertEventType = z.infer<typeof TraceUpsertEventSchema>;
-export type EvalExecutionEventType = z.infer<typeof EvalExecutionEvent>;
-
-export const EventBodySchema = z.union([
-  z.object({
-    name: z.literal(EventName.TraceUpsert),
-    payload: z.array(TraceUpsertEventSchema),
-  }),
-  z.object({
-    name: z.literal(EventName.EvaluationExecution),
-    payload: EvalExecutionEvent,
-  }),
-  z.object({
-    name: z.literal(EventName.BatchExport),
-    payload: BatchExportJobSchema,
-  }),
-]);
-export type EventBodyType = z.infer<typeof EventBodySchema>;
-
-export enum QueueName {
-  TraceUpsert = "trace-upsert", // Ingestion pipeline adds events on each Trace upsert
-  EvaluationExecution = "evaluation-execution-queue", // Worker executes Evals
-  BatchExport = "batch-export-queue",
-  RepeatQueue = "repeat-queue",
-  IngestionFlushQueue = "ingestion-flush-queue",
-}
-
-export enum QueueJobs {
-  TraceUpsert = "trace-upsert",
-  EvaluationExecution = "evaluation-execution-job",
-  BatchExportJob = "batch-export-job",
-  EnqueueBatchExportJobs = "enqueue-batch-export-jobs",
-  FlushIngestionEntity = "flush-ingestion-entity",
-}
-
-export type TQueueJobTypes = {
-  [QueueName.TraceUpsert]: {
-    timestamp: Date;
-    id: string;
-    payload: TraceUpsertEventType;
-    name: QueueJobs.TraceUpsert;
-  };
-  [QueueName.EvaluationExecution]: {
-    timestamp: Date;
-    id: string;
-    payload: EvalExecutionEventType;
-    name: QueueJobs.EvaluationExecution;
-  };
-  [QueueName.BatchExport]: {
-    timestamp: Date;
-    id: string;
-    payload: BatchExportJobType;
-    name: QueueJobs.BatchExportJob;
-  };
-};

packages/shared/src/server/auth.ts

@@ -1,81 +0,0 @@
-import { compare, hash } from "bcryptjs";
-import { randomUUID } from "crypto";
-import * as crypto from "crypto";
-import type { OAuthConfig, OAuthUserConfig } from "next-auth/providers/oauth";
-
-export function generateSecretKey() {
-  return `sk-lf-${randomUUID()}`;
-}
-
-export function generatePublicKey() {
-  return `pk-lf-${randomUUID()}`;
-}
-
-export function getDisplaySecretKey(secretKey: string) {
-  return secretKey.slice(0, 6) + "..." + secretKey.slice(-4);
-}
-
-export async function hashSecretKey(key: string) {
-  // legacy, uses bcrypt, transformed into hashed key upon first use
-  const hashedKey = await hash(key, 11);
-  return hashedKey;
-}
-
-export async function generateKeySet() {
-  const pk = generatePublicKey();
-  const sk = generateSecretKey();
-  const hashedSk = await hashSecretKey(sk);
-  const displaySk = getDisplaySecretKey(sk);
-
-  return {
-    pk,
-    sk,
-    hashedSk,
-    displaySk,
-  };
-}
-
-export async function verifySecretKey(key: string, hashedKey: string) {
-  const isValid = await compare(key, hashedKey);
-  return isValid;
-}
-
-export function createShaHash(privateKey: string, salt: string): string {
-  const hash = crypto
-    .createHash("sha256")
-    .update(privateKey)
-    .update(crypto.createHash("sha256").update(salt, "utf8").digest("hex"))
-    .digest("hex");
-
-  return hash;
-}
-
-export interface CustomSSOUser extends Record<string, any> {
-  email: string;
-  id: string;
-  name: string;
-  verified: boolean;
-}
-
-export function CustomSSOProvider<P extends CustomSSOUser>(
-  options: OAuthUserConfig<P>
-): OAuthConfig<P> {
-  return {
-    id: "custom",
-    name: "CustomSSOProvider",
-    type: "oauth",
-    wellKnown: `${options.issuer}/.well-known/openid-configuration`,
-    authorization: { params: { scope: "openid email profile" } }, // overridden by options.authorization to be able to set custom scopes, deep merged with this default
-    checks: ["pkce", "state"],
-    idToken: true,
-    profile(profile) {
-      return {
-        id: profile.sub,
-        name: profile.name,
-        email: profile.email,
-        image: null,
-      };
-    },
-    options,
-  };
-}

packages/shared/src/server/auth/apiKeys.ts

@@ -0,0 +1,81 @@
+import { PrismaClient } from "@prisma/client";
+import { compare, hash } from "bcryptjs";
+import { randomUUID } from "crypto";
+import * as crypto from "crypto";
+import { env } from "../../env";
+
+export function getDisplaySecretKey(secretKey: string) {
+  return secretKey.slice(0, 6) + "..." + secretKey.slice(-4);
+}
+
+export async function hashSecretKey(key: string) {
+  // legacy, uses bcrypt, transformed into hashed key upon first use
+  const hashedKey = await hash(key, 11);
+  return hashedKey;
+}
+
+async function generateKeySet() {
+  return {
+    pk: `pk-lf-${randomUUID()}`,
+    sk: `sk-lf-${randomUUID()}`,
+  };
+}
+
+export async function verifySecretKey(key: string, hashedKey: string) {
+  const isValid = await compare(key, hashedKey);
+  return isValid;
+}
+
+export function createShaHash(privateKey: string, salt: string): string {
+  const hash = crypto
+    .createHash("sha256")
+    .update(privateKey)
+    .update(crypto.createHash("sha256").update(salt, "utf8").digest("hex"))
+    .digest("hex");
+
+  return hash;
+}
+
+export async function createAndAddApiKeysToDb(p: {
+  prisma: PrismaClient;
+  projectId: string;
+  note?: string;
+  predefinedKeys?: {
+    secretKey: string;
+    publicKey: string;
+  };
+}) {
+  const salt = env.SALT;
+  if (!salt) {
+    throw new Error("SALT is not set");
+  }
+
+  const { pk, sk } = p.predefinedKeys
+    ? { pk: p.predefinedKeys.publicKey, sk: p.predefinedKeys.secretKey }
+    : await generateKeySet();
+
+  const hashedSk = await hashSecretKey(sk);
+  const displaySk = getDisplaySecretKey(sk);
+
+  const hashFromProvidedKey = createShaHash(sk, salt);
+
+  const apiKey = await p.prisma.apiKey.create({
+    data: {
+      projectId: p.projectId,
+      publicKey: pk,
+      hashedSecretKey: hashedSk,
+      displaySecretKey: displaySk,
+      fastHashedSecretKey: hashFromProvidedKey,
+      note: p.note,
+    },
+  });
+
+  return {
+    id: apiKey.id,
+    createdAt: apiKey.createdAt,
+    note: apiKey.note,
+    publicKey: apiKey.publicKey,
+    secretKey: sk,
+    displaySecretKey: displaySk,
+  };
+}

packages/shared/src/server/auth/customSsoProvider.ts

@@ -0,0 +1,31 @@
+import type { OAuthConfig, OAuthUserConfig } from "next-auth/providers/oauth";
+
+interface CustomSSOUser extends Record<string, any> {
+  email: string;
+  id: string;
+  name: string;
+  verified: boolean;
+}
+
+export function CustomSSOProvider<P extends CustomSSOUser>(
+  options: OAuthUserConfig<P>
+): OAuthConfig<P> {
+  return {
+    id: "custom",
+    name: "CustomSSOProvider",
+    type: "oauth",
+    wellKnown: `${options.issuer}/.well-known/openid-configuration`,
+    authorization: { params: { scope: "openid email profile" } }, // overridden by options.authorization to be able to set custom scopes, deep merged with this default
+    checks: ["pkce", "state"],
+    idToken: true,
+    profile(profile) {
+      return {
+        id: profile.sub,
+        name: profile.name,
+        email: profile.email,
+        image: null,
+      };
+    },
+    options,
+  };
+}