chore: release v3.97.2

* fix: fail silently when /api/latest-releases returns invalid schema

* push

.claude/settings.json

@@ -0,0 +1,14 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(find:*)",
+      "Bash(rg:*)",
+      "Bash(grep:*)",
+      "Bash(ls:*)",
+      "Bash(cat:*)",
+      "Bash(head:*)",
+      "Bash(tail:*)"
+    ],
+    "deny": []
+  }
+}

.codespellrc

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

.cursor/Dockerfile

@@ -0,0 +1,54 @@
+FROM node:20
+
+# ---------- System packages --------------------------------------------------
+# The buildpack-deps base already ships git, build-essential, python, etc.
+# Add a few extra tools handy during Langfuse development.
+RUN apt-get update && \
+    DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+      openssl \
+      wget \
+      curl \
+      ca-certificates \
+      postgresql-client \
+      redis-tools \
+      less nano \
+      sudo \
+    && rm -rf /var/lib/apt/lists/*
+
+# ---------- Docker -----------------------------------------------------------
+# Install Docker for background agents that need container capabilities
+RUN curl -fsSL https://get.docker.com -o get-docker.sh && \
+    sh get-docker.sh && \
+    rm get-docker.sh
+
+# ---------- pnpm -------------------------------------------------------------
+# Langfuse monorepo relies on pnpm 9.5.0 (see CONTRIBUTING.md)
+ENV PNPM_HOME="/pnpm"
+ENV PATH="$PNPM_HOME:$PATH"
+RUN corepack enable && \
+    corepack prepare pnpm@9.5.0 --activate
+
+# ---------- golang-migrate ----------------------------------------------------
+# CLI used for database migrations during development.
+ENV MIGRATE_VERSION=4.18.3
+RUN wget -qO- "https://github.com/golang-migrate/migrate/releases/download/v${MIGRATE_VERSION}/migrate.linux-amd64.tar.gz" \
+    | tar -xz -C /usr/local/bin && \
+    chmod +x /usr/local/bin/migrate
+
+# ---------- Non-root user -----------------------------------------------------
+# Create non-root user with sudo privileges and docker group access
+RUN useradd -ms /bin/bash ubuntu && \
+    usermod -aG sudo ubuntu && \
+    usermod -aG docker ubuntu && \
+    echo "ubuntu ALL=(ALL) NOPASSWD:ALL" >> /etc/sudoers
+
+# Pre-create pnpm store and set correct ownership to avoid first-run cost & permission issues
+RUN pnpm store path > /dev/null && \
+    chown -R ubuntu:ubuntu /pnpm
+
+USER ubuntu
+WORKDIR /home/ubuntu
+ENV HOME=/home/ubuntu
+
+# Container starts with a bash shell ready for hacking.
+CMD ["bash"]

.cursor/environment.json

@@ -0,0 +1,14 @@
+{
+  "install": "cp .env.dev.example .env && pnpm i",
+  "build": {
+    "context": ".",
+    "dockerfile": "Dockerfile"
+  },
+  "start": "sudo service docker start",
+  "terminals": [
+    {
+      "name": "dev server",
+      "command": "pnpm run dx-f"
+    }
+  ]
+}

.cursor/rules/frontend-features.mdc

@@ -11,7 +11,7 @@ alwaysApply: true
 ## File Structure
 
 - We generally put all code related to a net-new feature into a folder within web/src/features.
-- Checkout other features to learn about the common structure.
+- Check out other features to learn about the common structure.
 
 ## API for frontend features
 

.cursor/rules/general-info.mdc

@@ -0,0 +1,9 @@
+---
+description: 
+globs: 
+alwaysApply: true
+---
+# General rules
+
+- Linting in this repo only works if the development server is running
+- Always run the full mono-repo via `pnpm run dx` (use `pnpm dx-f` when you run this in a background agent). Thereby the database will also be seeded.

.cursor/rules/global.mdc

@@ -0,0 +1,20 @@
+---
+description: 
+globs: 
+alwaysApply: true
+---
+## Project setup
+- This project is a Turborepo monorepo
+- We build two containers, web (./web) and worker (./worker)
+- We have shared code between these two in the shared package (./packages/shared). For that package, we have different entry points [package.json](mdc:packages/shared/package.json).
+
+
+## Domain layer
+The most important domain objects are in [observations.ts](mdc:packages/shared/src/domain/observations.ts), [traces.ts](mdc:packages/shared/src/domain/traces.ts), [scores.ts](mdc:packages/shared/src/domain/scores.ts).
+
+
+## Database schema
+We use Postgres and Clickhouse.
+- The postgres schema is in [schema.prisma](mdc:packages/shared/prisma/schema.prisma)
+- The clickhouse schema is in [0001_traces.up.sql](mdc:packages/shared/clickhouse/migrations/clustered/0001_traces.up.sql), [0002_observations.up.sql](mdc:packages/shared/clickhouse/migrations/clustered/0002_observations.up.sql), [0003_scores.up.sql](mdc:packages/shared/clickhouse/migrations/clustered/0003_scores.up.sql)
+

.cursor/rules/public-api.mdc

@@ -1,6 +1,6 @@
 ---
 description: How to create new public api routes for Langfuse
-globs: 
+globs:
 alwaysApply: false
 ---
 
@@ -13,4 +13,5 @@ alwaysApply: false
   - Add end-to-end test, similar to [datasets-api.servertest.ts](mdc:web/src/__tests__/async/datasets-api.servertest.ts)
   - Add fern configuration in /fern, learn more about structure here: https://buildwithfern.com/learn/api-definition/fern/overview
   - Prompt user to regenerate the OpenAPI spec via the fern CLI
-  - Pagination starts at 1, query typing defined in publicApiPaginationZod, return meta in paginationMetaResponseZod
+  - Pagination starts at 1, query typing defined in publicApiPaginationZod, return meta in paginationMetaResponseZod
+- For tests, please look at [this directory](mdc:web/src/__tests__/async/) for examples

.cursor/rules/tests.mdc

@@ -0,0 +1,9 @@
+---
+description: 
+globs: 
+alwaysApply: true
+---
+# Writing tests
+
+- When writing tests, focus on decoupling each `it` or `test` block to ensure that they can run independently and concurrently. Tests must never depend on the action or outcome of previous or subsequent tests.
+- When writing tests, especially in the __tests__/async directory, ensure that you avoid `pruneDatabase` calls.

.devcontainer/Dockerfile

@@ -0,0 +1,13 @@
+# Dev container Dockerfile
+FROM mcr.microsoft.com/vscode/devcontainers/typescript-node:20-bookworm
+
+# Install golang-migrate for database migrations
+RUN curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.3/migrate.linux-amd64.tar.gz | tar xvz && \
+    chmod +x migrate && \
+    mv migrate /usr/local/bin/migrate
+
+# Install pnpm globally
+RUN npm install -g pnpm@9.5.0
+
+# Install Claude Code CLI
+RUN npm install -g @anthropic-ai/claude-code

.devcontainer/devcontainer.json

@@ -0,0 +1,8 @@
+{
+  "name": "langfuse-development",
+  "build": {
+    "dockerfile": "Dockerfile"
+  },
+  "forwardPorts": [3000, 5432, 6379, 8123, 9000],
+  "postCreateCommand": "cp .env.dev.example .env && pnpm i"
+}

.env.dev-azure.example

@@ -68,6 +68,7 @@ LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE=true
 LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
 
 LANGFUSE_USE_AZURE_BLOB=true
+LANGFUSE_AZURE_SKIP_CONTAINER_CHECK=false
 
 # Set during docker build of application
 # Used to disable environment verification at build time

.env.dev-redis-cluster.example

@@ -0,0 +1,93 @@
+# When adding additional environment variables, the schema in "/src/env.mjs"
+# should be updated accordingly.
+
+# Prisma
+# https://www.prisma.io/docs/reference/database-reference/connection-urls#env
+DIRECT_URL="postgresql://postgres:postgres@localhost:5432/postgres"
+DATABASE_URL="postgresql://postgres:postgres@localhost:5432/postgres"
+
+# Clickhouse
+CLICKHOUSE_MIGRATION_URL="clickhouse://localhost:9000"
+CLICKHOUSE_URL="http://localhost:8123"
+CLICKHOUSE_USER="clickhouse"
+CLICKHOUSE_PASSWORD="clickhouse"
+CLICKHOUSE_CLUSTER_ENABLED="false"
+
+# Next Auth
+# You can generate a new secret on the command line with:
+# openssl rand -base64 32
+# https://next-auth.js.org/configuration/options#secret
+# NEXTAUTH_SECRET=""
+NEXTAUTH_URL="http://localhost:3000"
+NEXTAUTH_SECRET="secret"
+
+# Langfuse Cloud Environment
+NEXT_PUBLIC_LANGFUSE_CLOUD_REGION="DEV"
+
+# Langfuse experimental features
+LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES="true"
+
+# Salt for API key hashing
+SALT="salt"
+
+# Email
+EMAIL_FROM_ADDRESS=""  # Defines the email address to use as the from address.
+SMTP_CONNECTION_URL=""  # Defines the connection url for smtp server.
+
+# S3 Batch Exports
+LANGFUSE_S3_BATCH_EXPORT_ENABLED=true
+LANGFUSE_S3_BATCH_EXPORT_BUCKET=langfuse
+LANGFUSE_S3_BATCH_EXPORT_ACCESS_KEY_ID=minio
+LANGFUSE_S3_BATCH_EXPORT_SECRET_ACCESS_KEY=miniosecret
+LANGFUSE_S3_BATCH_EXPORT_REGION=us-east-1
+LANGFUSE_S3_BATCH_EXPORT_ENDPOINT=http://localhost:9090
+## Necessary for minio compatibility
+LANGFUSE_S3_BATCH_EXPORT_FORCE_PATH_STYLE=true
+LANGFUSE_S3_BATCH_EXPORT_PREFIX=exports/
+
+# S3 Media Upload LOCAL
+LANGFUSE_S3_MEDIA_UPLOAD_BUCKET=langfuse
+LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID=minio
+LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY=miniosecret
+LANGFUSE_S3_MEDIA_UPLOAD_REGION=us-east-1
+LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT=http://localhost:9090
+## Necessary for minio compatibility
+LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE=true
+LANGFUSE_S3_MEDIA_UPLOAD_PREFIX=media/
+
+# S3 Event Bucket Upload
+## Set to true to test uploading all events to S3
+LANGFUSE_S3_EVENT_UPLOAD_BUCKET=langfuse
+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
+# DOCKER_BUILD=1
+
+REDIS_HOST="127.0.0.1"
+REDIS_PORT=6379
+REDIS_AUTH="bitnami"
+REDIS_CLUSTER_ENABLED="true"
+REDIS_CLUSTER_NODES="127.0.0.1:6370,127.0.0.1:6371,127.0.0.1:6372,127.0.0.1:6373,127.0.0.1:6374,127.0.0.1:6375"
+LANGFUSE_INGESTION_QUEUE_SHARD_COUNT=8
+LANGFUSE_TRACE_UPSERT_QUEUE_SHARD_COUNT=4
+
+# 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"
+
+# Use the following settings to enforce running the new AMTs during the tests
+LANGFUSE_EXPERIMENT_INSERT_INTO_AGGREGATING_MERGE_TREES="true"
+LANGFUSE_EXPERIMENT_COMPARE_READ_FROM_AGGREGATING_MERGE_TREES="true"
+LANGFUSE_EXPERIMENT_WHITELISTED_PROJECT_IDS="7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"
+LANGFUSE_EXPERIMENT_ADD_QUERY_RESULT_TO_SPAN_PROJECT_IDS="7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"
+LANGFUSE_EXPERIMENT_RETURN_NEW_RESULT="true"
+LANGFUSE_EXPERIMENT_SAMPLING_RATE=1

.env.dev.example

@@ -75,7 +75,16 @@ REDIS_PORT=6379
 REDIS_AUTH="myredissecret"
 
 # openssl rand -hex 32 used only here
-ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000 
+ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000
 
 # speeds up local development by not executing init scripts on server startup
 NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT="false"
+
+# For SDK integration tests to pass, decrease the ingestion queue delay by uncommenting the env vars:
+# LANGFUSE_INGESTION_QUEUE_DELAY_MS=10
+# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS=10
+
+# Slack credentials for development
+SLACK_CLIENT_ID=your_slack_client_id
+SLACK_CLIENT_SECRET=your_slack_client_secret
+SLACK_STATE_SECRET=your_slack_state_secret

.env.prod.example

@@ -172,9 +172,14 @@ OTEL_SERVICE_NAME="langfuse"
 # REDIS_HOST=
 # REDIS_PORT=
 # REDIS_AUTH=
+# REDIS_USERNAME=default
 # REDIS_CONNECTION_STRING=
 # REDIS_ENABLE_AUTO_PIPELINING=
 
+# Redis Cluster configuration (optional)
+# REDIS_CLUSTER_ENABLED=false
+# REDIS_CLUSTER_NODES=redis-node1:6379,redis-node2:6379,redis-node3:6379
+
 # Cache configuration
 # LANGFUSE_CACHE_API_KEY_ENABLED=
 # LANGFUSE_CACHE_API_KEY_TTL_SECONDS=

.env.test.example

@@ -0,0 +1,12 @@
+# Test Environment Configuration
+# Copy this file to .env.test for test database isolation
+# Only overrides specific test variables - other values inherited from .env
+
+# PostgreSQL - Test Database
+DIRECT_URL="postgresql://postgres:postgres@localhost:5432/langfuse_test"
+DATABASE_URL="postgresql://postgres:postgres@localhost:5432/langfuse_test"
+
+# ClickHouse - Use Default Database for now, nothing set
+
+# Redis - Test Database (database 1 for isolation)
+REDIS_CONNECTION_STRING="redis://:myredissecret@127.0.0.1:6379/1"

.github/PULL_REQUEST_TEMPLATE.md

@@ -28,7 +28,7 @@ Fixes # (issue)
 <!-- Remove bullet points below that don't apply to you -->
 
 - I haven't read the [contributing guide](https://github.com/langfuse/langfuse/blob/main/CONTRIBUTING.md)
-- My code doesn't follow the style guidelines of this project (`npm run prettier`)
+- My code doesn't follow the style guidelines of this project (`pnpm run format`)
 - I haven't commented my code, particularly in hard-to-understand areas
 - I haven't checked if my PR needs changes to the documentation
 - I haven't checked if my changes generate no new warnings (`npm run lint`)

.github/dependabot.yml

@@ -36,6 +36,7 @@ updates:
         patterns:
           - "express"
           - "@types/express"
+          - "@types/express-serve-static-core"
       observability:
         patterns:
           - "dd-trace"

.github/workflows/_deploy_ecs_service.yml

@@ -15,10 +15,6 @@ jobs:
     runs-on: ubuntu-latest
     environment: ${{ inputs.environment }}
     steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@master
-        with:
-          swap-size-gb: 10
       - name: Get app name
         uses: winterjung/split@v2
         id: split

.github/workflows/pipeline.yml

@@ -52,6 +52,49 @@ jobs:
       - name: lint web
         run: pnpm run lint
 
+  prettier-check:
+    runs-on: ubuntu-latest
+    needs:
+      - pre-job
+    if: needs.pre-job.outputs.should_skip != 'true'
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - 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 i
+      - name: Load default env
+        run: |
+          cp .env.dev.example .env
+      - name: Check formatting on changed files
+        run: |
+          if [ "${{ github.event_name }}" = "pull_request" ]; then
+            BASE_SHA=${{ github.event.pull_request.base.sha }}
+          else
+            BASE_SHA=$(git merge-base origin/main HEAD)
+          fi
+          
+          echo "Checking files changed from $BASE_SHA to HEAD"
+          
+          # Get changed files
+          CHANGED_FILES=$(git diff --name-only $BASE_SHA HEAD -- '*.js' '*.jsx' '*.ts' '*.tsx' '*.css' | tr '\n' ' ')
+          
+          if [ -n "$CHANGED_FILES" ] && [ "$CHANGED_FILES" != " " ]; then
+            echo "Files to check: $CHANGED_FILES"
+            pnpm prettier --check --experimental-cli $CHANGED_FILES
+          else
+            echo "No JS/TS/CSS files changed - skipping prettier check"
+          fi
+
   test-docker-build:
     timeout-minutes: 20
     runs-on: ubuntu-latest
@@ -71,7 +114,9 @@ jobs:
         run: echo "NEXT_PUBLIC_BUILD_ID=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
       - name: Build and run both images from compose
         run: |
-          docker compose -f docker-compose.build.yml up -d
+          docker compose --progress plain --verbose -f docker-compose.build.yml build --print > /tmp/bake.json
+          docker buildx bake -f /tmp/bake.json
+          docker compose --progress plain -f docker-compose.build.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
       - name: Ensure no unhealthy status
         run: |
@@ -100,14 +145,10 @@ jobs:
         node-version: [20]
         postgres-version: [12, 15]
     steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@master
-        with:
-          swap-size-gb: 10
       - uses: actions/checkout@v4
       - name: Install golang-migrate for Clickhouse migrations
         run: |
-          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.3/migrate.linux-amd64.tar.gz | tar xvz
           sudo mv migrate /usr/bin/migrate
           which migrate
       - uses: pnpm/action-setup@v3
@@ -133,6 +174,7 @@ jobs:
           cp .env.dev.example .env
           grep -v -e '^LANGFUSE_S3_BATCH_EXPORT_ENABLED=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev.example > .env
           echo "LANGFUSE_INGESTION_QUEUE_DELAY_MS=1" >> .env
+          echo "LANGFUSE_CACHE_PROMPT_ENABLED=false" >> .env
           echo "LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS=1" >> .env
       - name: Run dev containers
         run: |
@@ -171,21 +213,17 @@ jobs:
     needs:
       - pre-job
     if: needs.pre-job.outputs.should_skip != 'true'
-    name: tests-web-async (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.blob-provider }})
+    name: tests-web-async (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.deploy-mode }})
     strategy:
       matrix:
         node-version: [20]
         postgres-version: [12, 15]
-        blob-provider: ["", "-azure"]
+        deploy-mode: ["", "-azure", "-redis-cluster"]
     steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@master
-        with:
-          swap-size-gb: 10
       - uses: actions/checkout@v4
       - name: Install golang-migrate for Clickhouse migrations
         run: |
-          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.3/migrate.linux-amd64.tar.gz | tar xvz
           sudo mv migrate /usr/bin/migrate
           which migrate
       - uses: pnpm/action-setup@v3
@@ -208,8 +246,8 @@ jobs:
           pnpm install
       - name: Load default env
         run: |
-          cp .env.dev${{ matrix.blob-provider }}.example .env
-          grep -v -e '^LANGFUSE_S3_BATCH_EXPORT_ENABLED=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev${{ matrix.blob-provider }}.example > .env
+          cp .env.dev${{ matrix.deploy-mode }}.example .env
+          grep -v -e '^LANGFUSE_S3_BATCH_EXPORT_ENABLED=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev${{ matrix.deploy-mode }}.example > .env
           echo "LANGFUSE_INGESTION_QUEUE_DELAY_MS=1" >> .env
           echo "LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS=1" >> .env
           echo "LANGFUSE_TRACE_DELETE_CONCURRENCY=100" >> .env
@@ -217,7 +255,7 @@ jobs:
           echo "LANGFUSE_EE_LICENSE_KEY=langfuse_ee_test" >> .env
       - name: Run dev containers
         run: |
-          docker compose -f docker-compose.dev${{ matrix.blob-provider }}.yml up -d
+          docker compose -f docker-compose.dev${{ matrix.deploy-mode }}.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
           docker compose ps
         env:
@@ -250,17 +288,13 @@ jobs:
     needs:
       - pre-job
     if: needs.pre-job.outputs.should_skip != 'true'
-    name: tests-worker (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.blob-provider }})
+    name: tests-worker (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.deploy-mode }})
     strategy:
       matrix:
         node-version: [20]
         postgres-version: [12, 15]
-        blob-provider: ["", "-azure"]
+        deploy-mode: ["", "-azure", "-redis-cluster"]
     steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@master
-        with:
-          swap-size-gb: 10
       - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
@@ -282,17 +316,17 @@ jobs:
           pnpm install
       - name: Install golang-migrate for Clickhouse migrations
         run: |
-          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.3/migrate.linux-amd64.tar.gz | tar xvz
           sudo mv migrate /usr/bin/migrate
           which migrate
       - name: Load default env
         run: |
-          cp .env.dev${{ matrix.blob-provider }}.example .env
-          cp .env.dev${{ matrix.blob-provider }}.example web/.env
-          cp .env.dev${{ matrix.blob-provider }}.example worker/.env
+          cp .env.dev${{ matrix.deploy-mode }}.example .env
+          cp .env.dev${{ matrix.deploy-mode }}.example web/.env
+          cp .env.dev${{ matrix.deploy-mode }}.example worker/.env
       - name: Run + migrate
         run: |
-          docker compose -f docker-compose.dev${{ matrix.blob-provider }}.yml up -d
+          docker compose -f docker-compose.dev${{ matrix.deploy-mode }}.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
           docker compose ps
       - name: Ensure no unhealthy status
@@ -343,7 +377,7 @@ jobs:
           cp .env.dev.example web/.env
       - name: Install golang-migrate for Clickhouse migrations
         run: |
-          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.3/migrate.linux-amd64.tar.gz | tar xvz
           sudo mv migrate /usr/bin/migrate
           which migrate
       - name: Run + migrate
@@ -397,14 +431,12 @@ jobs:
           pnpm install
       - name: Install golang-migrate for Clickhouse migrations
         run: |
-          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.3/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
-          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
@@ -442,6 +474,7 @@ jobs:
     needs:
       [
         lint,
+        prettier-check,
         tests-web-sync,
         tests-worker,
         e2e-tests,
@@ -452,13 +485,21 @@ jobs:
     if: always()
     steps:
       - name: Successful deploy
-        if: ${{ !(contains(needs.*.result, 'failure')) }}
+        if: ${{ !(contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled')) }}
         run: exit 0
         working-directory: .
       - name: Failing deploy
-        if: ${{ contains(needs.*.result, 'failure') }}
+        if: ${{ contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') }}
         run: exit 1
         working-directory: .
+      - name: Notify Slack
+        uses: ravsamhq/notify-slack-action@v2
+        if: always() && github.event_name == 'push' && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/'))
+        with:
+          status: ${{ job.status }}
+          notify_when: "failure"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
 
   push-docker-image:
     needs: all-ci-passed

.github/workflows/snyk.yml

@@ -1,65 +1,28 @@
 name: Snyk Container
 on:
-  pull_request:
-    branches:
-      - "**"
   push:
-    branches:
-      - main
-  # Snyk cannot upload results in merge group. Hence, we only run on PRs and when pushingon the main branch https://github.com/github/codeql-action/issues/1572
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+    branches: ["main"]
 
 jobs:
   snyk:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - name: Build a Docker image
-        run: docker compose -f docker-compose.build.yml up -d
+      - uses: actions/checkout@v3
 
-      - name: Run Snyk to check Docker image for vulnerabilities (langfuse-web)
-        continue-on-error: true
+      - name: Scan web image with Snyk
         uses: snyk/actions/docker@master
+        continue-on-error: true # let upload step always run
         env:
           SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
         with:
-          image: langfuse-langfuse-web
-          args: --file=web/Dockerfile
+          image: langfuse/langfuse # pulled from Docker Hub
+          args: --severity-threshold=high # (any extra CLI flags, but NO --file)
 
-      # Workaround for https://github.com/github/codeql-action/issues/2187
-      - name: Replace security-severity undefined for license-related findings
-        run: "sed -i 's/\"security-severity\": \"undefined\"/\"security-severity\": \"0\"/g' snyk.sarif"
-
-      - name: Replace security-severity null for license-related findings
-        run: "sed -i 's/\"security-severity\": \"null\"/\"security-severity\": \"0\"/g' snyk.sarif"
-
-      - name: Upload result to GitHub Code Scanning
-        uses: github/codeql-action/upload-sarif@v3
-        with:
-          sarif_file: snyk.sarif
-          category: web
-
-      - name: Run Snyk to check Docker image for vulnerabilities (langfuse-worker)
-        continue-on-error: true
+      - name: Scan worker image with Snyk
         uses: snyk/actions/docker@master
+        continue-on-error: true # let upload step always run
         env:
           SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
         with:
-          image: langfuse-langfuse-worker
-          args: --file=worker/Dockerfile
-
-      # Workaround for https://github.com/github/codeql-action/issues/2187
-      - name: Replace security-severity undefined for license-related findings
-        run: "sed -i 's/\"security-severity\": \"undefined\"/\"security-severity\": \"0\"/g' snyk.sarif"
-
-      - name: Replace security-severity null for license-related findings
-        run: "sed -i 's/\"security-severity\": \"null\"/\"security-severity\": \"0\"/g' snyk.sarif"
-
-      - name: Upload result to GitHub Code Scanning
-        uses: github/codeql-action/upload-sarif@v3
-        with:
-          sarif_file: snyk.sarif
-          category: worker
+          image: langfuse/langfuse-worker # pulled from Docker Hub
+          args: --severity-threshold=high # (any extra CLI flags, but NO --file)

.gitignore

@@ -4,6 +4,7 @@
 /node_modules
 /.pnp
 .pnp.js
+migrate
 
 # testing
 /coverage
@@ -39,7 +40,9 @@ yarn-error.log*
 .env*
 !.env.dev.example
 !.env.dev-azure.example
+!.env.dev-redis-cluster.example
 !.env.prod.example
+!.env.test.example
 
 # vercel
 .vercel
@@ -47,15 +50,13 @@ yarn-error.log*
 # typescript
 *.tsbuildinfo
 
-/generated/typescript-server
+/generated
 
 # openapi spec that is copied during build
 /public/openapi*.yml
 
 
 # vscode
-.devcontainer
-
 node_modules
 **/node_modules
 **/dist
@@ -64,4 +65,7 @@ node_modules
 .yarn
 .turbo
 
-web/test-results/*
+web/test-results/*
+
+# local config files
+*.local.*

.husky/pre-commit

@@ -11,12 +11,13 @@ if [ "$current_branch" = "$protected_branch" ]; then
     echo "🚨 You are about to commit to the $protected_branch branch. Are you sure? (y/n)"
     read -r answer < /dev/tty
     if [ "$answer" != "${answer#[Yy]}" ]; then
-        exit 0 # Commit will proceed
+        # Commit approved, check formatting. On files changed, block commit
+        pnpm run format:check
     else
         echo "Commit to $protected_branch branch has been canceled."
         exit 1 # Commit will be blocked
     fi
 fi
 
-# If not the protected branch, proceed with the commit
-exit 0
+# If not the protected branch, check formatting (on changed files, block)
+pnpm run format:check

.nvmrc

@@ -1 +1 @@
-v20
+v20.19.2

.prettierignore

@@ -0,0 +1,2 @@
+# Generated code
+packages/shared/prisma/generated

AGENTS.md

@@ -8,6 +8,8 @@ Langfuse is an **open source LLM engineering** platform for developing, monitori
 
 ## Tests
 - Codex cannot run the test suite because it depends on Docker-based infrastructure that is unavailable in this environment.
+- When writing tests, focus on decoupling each `it` or `test` block to ensure that they can run independently and concurrently. Tests must never depend on the action or outcome of previous or subsequent tests.
+- When writing tests, especially in the __tests__/async directory, ensure that you avoid `pruneDatabase` calls.
 
 ## Cursor Rules
 - Additional folder-specific rules live in `.cursor/rules/`.

CLAUDE.md

@@ -0,0 +1,197 @@
+# CLAUDE.md
+
+## Project Overview
+
+Langfuse is an open-source LLM engineering platform that helps teams collaboratively develop, monitor, evaluate, and debug AI applications.
+The main feature areas are tracing, evals and prompt management. Langfuse consists of the web application (this repo), documentation, python SDK and javascript/typescript SDK.
+This repo contains the web application, worker, and supporting packages but notably not the JS nor Python client SDKs.
+
+## Repository Structure
+High level structure. There are more folders (eg for hooks etc).
+```
+langfuse/
+├── web/                     # Next.js 14 frontend/backend application
+│   ├── src/
+│   │   ├── components/     # Reusable UI components (shadcn/ui)
+│   │   ├── features/       # Feature-specific code organized by domain
+│   │   ├── pages/          # Next.js pages (Pages Router)
+│   │   └── server/         # tRPC API routes and server logic
+│   └── public/             # Static assets
+├── worker/                  # Express.js background job processor
+│   └── src/
+│       ├── queues/         # BullMQ job queues
+│       └── services/       # Background processing services
+├── packages/
+│   ├── shared/             # Shared types, schemas, and utilities
+│   │   ├── prisma/         # Database schema and migrations
+│   │   └── src/            # Shared TypeScript code
+│   ├── config-eslint/      # ESLint configuration
+│   └── config-typescript/  # TypeScript configuration
+├── ee/                     # Enterprise Edition features
+├── fern/                   # API documentation and OpenAPI specs
+├── generated/              # Auto-generated client code
+└── scripts/                # Development and deployment scripts
+```
+
+## Repository Architecture
+This is a **pnpm + Turbo monorepo** with the following key packages:
+
+### Core Applications
+- **`/web/`** - Next.js 14 application (Pages Router) providing both frontend UI and backend APIs
+- **`/worker/`** - Express.js background job processing server
+- **`/packages/shared/`** - Shared database schema, types, and utilities
+
+### Supporting Packages
+- **`/ee/`** - Enterprise Edition features (separate licensing)
+- **`/packages/config-eslint/`** - Shared ESLint configuration
+- **`/packages/config-typescript/`** - Shared TypeScript configuration
+
+## Development Commands
+
+### Development
+```sh
+pnpm i               # Install dependencies
+pnpm run dev         # Start all services (web + worker)
+pnpm run dev:web     # Web app only (localhost:3000) - **used in most cases!**
+pnpm run dev:worker  # Worker only
+pnpm run dx          # Full initial setup: install deps, reset DBs, resets node modules, seed data, start dev. USE SPARINGLY AS IT WIPES THE DATABASE & node_modules
+```
+
+### Database Management
+database commands are to be run in the `packages/shared/` folder.
+```sh
+pnpm run db:generate       # Build prisma models
+pnpm run db:migrate        # Run Prisma migrations
+pnpm run db:reset          # Reset and reseed databases
+pnpm run db:seed           # Seed with example data
+```
+
+### Infrastructure
+```sh
+pnpm run infra:dev:up      # Start Docker services (PostgreSQL, ClickHouse, Redis, MinIO)
+pnpm run infra:dev:down    # Stop Docker services
+```
+
+### Building
+```sh
+pnpm --filter=PACKAGE_NAME run build  # Runs the build command, will show real typescript errors etc.
+```
+
+### Testing in Web Package
+The web package uses JEST for unit tests.
+Depending on the file location (sync, async)
+`web` related tests must go into the `web/src/__tests__/` folder.
+```sh
+pnpm test-sync --testPathPattern="$FILE_LOCATION_PATTERN" --testNamePattern="$TEST_NAME_PATTERN"
+pnpm test-async --testPathPattern="$FILE_LOCATION_PATTERN" --testNamePattern="$TEST_NAME_PATTERN"
+```
+
+### Testing in the Worker Package
+The worker uses `vitest` for unit tests.
+```sh
+pnpm run test --filter=worker -- $TEST_FILE_NAME -t "$TEST_NAME"
+```
+
+### Utilities
+```bash
+pnpm run format            # Format code across entire project
+pnpm run nuke              # Remove all node_modules, build files, wipe database, docker containers. **USE WITH CAUTION**
+```
+
+## Technology Stack
+
+### Web Application (`/web/`)
+- **Framework**: Next.js 14 (Pages Router)
+- **APIs**: tRPC (type-safe client-server communication) + REST APIs for public access
+- **Authentication**: NextAuth.js/Auth.js
+- **Database**: Prisma ORM with PostgreSQL
+- **Analytics Database**: ClickHouse (high-volume trace data)
+- **Validation**: Zod schemas, we use zodv4 (always import from `zod/v4`)
+- **Styling**: Tailwind CSS with CSS variables for theming
+- **Components**: shadcn/ui (Radix UI primitives)
+- **State Management**: TanStack Query (React Query) + tRPC
+- **Charts**: Tremor, Recharts
+
+### Worker Application (`/worker/`)
+- **Framework**: Express.js
+- **Queue System**: BullMQ with Redis
+- **Purpose**: Async processing (data ingestion, evaluations, exports, integrations)
+
+### Infrastructure
+- **Primary Database**: PostgreSQL (via Prisma ORM)
+- **Analytics Database**: ClickHouse
+- **Cache/Queues**: Redis
+- **Blob Storage**: MinIO/S3
+
+## Development Guidelines
+
+### Frontend Features
+- All new features go in `/web/src/features/[feature-name]/`
+- Use tRPC for full-stack features (entry point: `web/src/server/api/root.ts`)
+- Follow existing feature structure for consistency
+- Use shadcn/ui components from `@/src/components/ui`
+- Custom reusable components go in `@/src/components`
+
+### Public API Development
+- All public API routes in `/web/src/pages/api/public`
+- Use `withMiddlewares.ts` wrapper
+- Define types in `/web/src/features/public-api/types` with strict Zod v4 objects
+- Add end-to-end tests (see `datasets-api.servertest.ts`)
+- Manually update Fern API specs in `/fern/`, then regenerate OpenAPI spec via Fern CLI
+
+### Authorization & RBAC
+- Check `/web/src/features/rbac/README.md` for authorization patterns
+- Implement proper entitlements checking (see `/web/src/features/entitlements/README.md`)
+
+### Database
+- **Dual database system**: PostgreSQL (primary) + ClickHouse (analytics)
+- Use `golang-migrate` CLI for database migrations
+- All database operations go through Prisma ORM for PostgreSQL
+- Foreign key relationships may not be enforced in schema to allow unordered ingestion
+
+### Testing
+- Jest for API tests, Playwright for E2E tests
+- For backend/API changes, tests must pass before pushes
+- Add tests for new API endpoints and features
+- When writing tests, focus on decoupling each `it` or `test` block to ensure that they can run independently and concurrently. Tests must never depend on the action or outcome of previous or subsequent tests.
+- When writing tests, especially in the __tests__/async directory, ensure that you avoid `pruneDatabase` calls.
+
+### Code Conventions
+- **Pages Router** (not App Router)
+- Follow conventional commits on main branch
+- Use CSS variables for theming (supports auto dark/light mode)
+- TypeScript throughout
+- Zod v4 for all input validation
+
+## Environment Setup
+
+- **Node.js**: Version 20 (specified in `.nvmrc`)
+- **Package Manager**: pnpm v9.5.0
+- **Database Dependencies**: Docker for local PostgreSQL, ClickHouse, Redis, MinIO
+- **Environment**: Copy `.env.dev.example` to `.env`
+
+## Login for Development
+
+When running locally with seed data:
+- Username: `demo@langfuse.com`
+- Password: `password`
+- Demo project URL: `http://localhost:3000/project/7a88fb47-b4e2-43b8-a06c-a5ce950dc53a`
+
+## Linear MCP
+To get a project, use the `get_project` capability with the full project name as it is in the title.
+- bad: message-placeholder-in-chat-messages-2beb6f02ec48
+- good: Message placeholder in chat messages
+
+## Front-end Tips
+
+### Window Location Handling
+- Whenever you want to use or do use window.location..., ensure that you also add proper handling for a custom basePath
+
+## TypeScript Best Practices
+- In TypeScript, if possible, don't use the `any` type
+
+## General Coding Guidelines
+- For easier code reviews, prefer not to move functions etc around within a file unless necessary or instructed to do so
+
+## Development Tips
+- Before trying to build the package, try running the linter once first

CONTRIBUTING.md

@@ -42,7 +42,7 @@ A good first step is to search for open [issues](https://github.com/langfuse/lan
   - NextAuth.js / Auth.js
   - tRPC: Frontend APIs
   - Prisma ORM
-  - Zod
+  - Zod v4
   - Tailwind CSS
   - shadcn/ui tailwind components (using Radix and tanstack)
   - Fern: generate OpenAPI spec and Pydantic models
@@ -58,16 +58,30 @@ See this [diagram](https://langfuse.com/self-hosting#architecture) for an overvi
 ### Network Overview
 
 ```mermaid
-flowchart LR
-   Browser ---|Web UI & TRPC API| App
-   Integrations/SDKs ---|Public HTTP API| App
-   subgraph i1["Application Network"]
-      App["Langfuse Application"]
-   end
-   subgraph i2["Database Network"]
-      DB["Postgres Database"]
-   end
-   App --- DB
+flowchart TB
+    User["UI, API, SDKs"]
+    subgraph vpc["VPC"]
+        Web["Web Server<br/>(langfuse/langfuse)"]
+        Worker["Async Worker<br/>(langfuse/worker)"]
+        Postgres["Postgres - OLTP<br/>(Transactional Data)"]
+        Cache["Redis/Valkey<br/>(Cache, Queue)"]
+        Clickhouse["Clickhouse - OLAP<br/>(Observability Data)"]
+        S3["S3 / Blob Storage<br/>(Raw events, multi-modal attachments)"]
+    end
+    LLM["LLM API/Gateway<br/>(optional)"]
+
+    User --> Web
+    Web --> S3
+    Web --> Postgres
+    Web --> Cache
+    Web --> Clickhouse
+    Web -.->|"optional for playground"| LLM
+
+    Cache --> Worker
+    Worker --> Clickhouse
+    Worker --> Postgres
+    Worker --> S3
+    Worker -.->|"optional for evals"| LLM
 ```
 
 ### Database Overview
@@ -110,16 +124,24 @@ Requirements
    cd langfuse
    ```
 
-3. Create an env file
+3. Install dependencies and set up pre-commit hooks
+
+   ```bash
+   pnpm install
+   pnpm run prepare  # Sets up Husky pre-commit hooks for code formatting
+   ```
+
+4. Create an env file
 
    ```bash
     cp .env.dev.example .env
    ```
 
-4. Run the entire infrastructure in dev mode
+4. Run the entire infrastructure in dev mode. **Note**: if you have an existing database, this command wipes it. Also, this will fail on the very first run. Please run it again.
 
    ```bash
-   pnpm run dx
+   pnpm run dx # first run only (resets db, docker containers, etc...)
+   pnpm run dev # any subsequent runs
    ```
 
    You will be asked whether you want to reset Postgres and ClickHouse. Confirm both with 'Y' and press enter.
@@ -134,6 +156,12 @@ Requirements
    - Username: `demo@langfuse.com`
    - Password: `password`
 
+To get comprehensive example data, you can use the `seed` command:
+
+```sh
+pnpm run db:seed:examples
+```
+
 ## Monorepo quickstart
 
 - Available packages and their dependencies
@@ -183,23 +211,65 @@ Requirements
 
 On the main branch, we adhere to the best practices of [conventional commits](https://www.conventionalcommits.org/en/v1.0.0/). All pull requests and branches are squash-merged to maintain a clean and readable history. This approach ensures the addition of a conventional commit message when merging contributions.
 
-## Test the public API
+## Running Unit Tests
 
-The API is tested using Jest. With the development server running, you can run the tests with:
+All tests run in the CI and must pass before merging.
+All tests run against a running langfuse instance and **write/delete real data from the database**.
 
-Run all
+### Test Database Setup
+
+Per default, the tests use the local development database. Therefore, wiping your data in the process.
+For proper test isolation, create a `.env.test` file in the root directory:
 
 ```bash
-npm run test
+cp .env.test.example .env.test
 ```
 
-Run interactively in watch mode
+Then, a different PostgreSQL and Redis are used for the tests.
+The `.env.test` file only overrides the set values and falls back on `.env` for all undefined values.
 
-```bash
-npm run test:watch
+- **PostgreSQL**: Uses separate `langfuse_test` database for isolation
+- **ClickHouse**: Uses shared `default` database for now
+- **Redis**: Uses database 1 instead of 0 for isolation (Redis data is not cleaned between tests)
+
+Tests automatically create the PostgreSQL test database if it doesn't exist and clean up data between runs.
+
+### Tests in the `web` package (public API)
+
+We're using Jest with in the `web` package. Therefore, if you want to provide an argument to the test runner, do it directly without an intermittent `--`.
+
+There are three types of unit tests:
+
+- `test-sync`
+- `test-async`
+- `test-client`
+
+To run a specific test, for example the test: `"should handle special characters in prompt names"` in `prompts.v2.servertest.ts`, run:
+
+```sh
+cd web  # or with --filter=web
+pnpm test-sync --testPathPattern="prompts\.v2\.servertest" --testNamePattern="should handle special characters in prompt names"
 ```
 
-These tests are also run in CI.
+To run all tests:
+
+```sh
+pnpm run test
+```
+
+Run interactively in watch mode (not recommended!)
+
+```sh
+pnpm run test:watch
+```
+
+### Tests in the `worker` package
+
+For the `worker` package, we're using `vitest` to run unit tests.
+
+```sh
+pnpm run test --filter=worker -- FILE_YOU_WANT_TO_TEST.ts -t "test name"
+```
 
 ## CI/CD
 
@@ -327,6 +397,20 @@ Please note that
 
 Until the V3 release, both the JSON record must be updated **and** a migration must be created to continue supporting self-hosted users. Note that the migration must updated both the `models` as well as the `prices` table accordingly.
 
+## Updating the OpenAPI Specs & fern SDKs
+
+We maintain the API specifications manually to guarantee a high degree of understandability. If you made changes to the API, please update the respective `.yml` files in `fern/apis/...`.
+
+To generate the respective `openapi.yml` files which power the online API reference & SDKs, run:
+
+```sh
+npx fern-api generate --api server  # for the server API
+npx fern-api generate --api client  # for the client API
+npx fern-api generate --api organizations  # for the organizations API
+```
+
+**Note:** You need a signed in fern account to run those commands.
+
 ## License
 
 Langfuse is MIT licensed, except for `ee/` folder. See [LICENSE](LICENSE) and [docs](https://langfuse.com/docs/open-source) for more details.

README.cn.md

@@ -26,7 +26,7 @@
     <a href="https://langfuse.com/roadmap"><strong>路线图</strong></a> ·
   </div>
   <br/>
-  <span>Langfuse 使用 <a href="https://github.com/orgs/langfuse/discussions"><strong>Github Discussions</strong></a> 作为支持和功能请求的平台。</span>
+  <span>Langfuse 使用 <a href="https://github.com/orgs/langfuse/discussions"><strong>GitHub Discussions</strong></a> 作为支持和功能请求的平台。</span>
   <br/>
   <span><b>我们正在招聘。</b> <a href="https://langfuse.com/careers"><strong>加入我们</strong></a>，从事产品工程和技术市场职位。</span>
   <br/>
@@ -94,7 +94,7 @@ Langfuse 是一个 **开源 LLM 工程** 平台。它帮助团队协作 **开发
   
 - [提示管理](https://langfuse.com/docs/prompts/get-started) 帮助你集中管理、版本控制并协作迭代提示。得益于服务器和客户端的高效缓存，你可以在不增加延迟的情况下反复迭代提示。
 
-- [评估](https://langfuse.com/docs/scores/overview) 是 LLM 应用开发流程的关键组成部分，Langfuse 能够满足你的多样需求。它支持 LLM 作为“裁判”、用户反馈收集、手动标注以及通过 API/SDK 实现自定义评估流程。
+- [评估](https://langfuse.com/docs/scores/overview) 是 LLM 应用开发流程的关键组成部分，Langfuse 能够满足你的多样需求。它支持 LLM 作为"裁判"、用户反馈收集、手动标注以及通过 API/SDK 实现自定义评估流程。
 
 - [数据集](https://langfuse.com/docs/datasets/overview) 为评估你的 LLM 应用提供测试集和基准。它们支持持续改进、部署前测试、结构化实验、灵活评估，并能与 LangChain、LlamaIndex 等框架无缝整合。
 
@@ -135,7 +135,7 @@ Langfuse 是一个 **开源 LLM 工程** 平台。它帮助团队协作 **开发
 
 - [虚拟机](https://langfuse.com/self-hosting/docker-compose)：使用 Docker Compose 在单台虚拟机上部署 Langfuse。
 
-- 【计划中】：针对各云平台的部署指南，欢迎在以下讨论中投票和评论：[AWS](https://github.com/orgs/langfuse/discussions/4645)、[Google Cloud](https://github.com/langfuse/discussions/4646)、[Azure](https://github.com/orgs/langfuse/discussions/4647)。
+- Terraform 模板: [AWS](https://langfuse.com/self-hosting/aws)、[Azure](https://langfuse.com/self-hosting/azure)、[GCP](https://langfuse.com/self-hosting/gcp)
 
 请参阅 [自托管文档](https://langfuse.com/self-hosting) 了解更多关于架构和配置选项的信息。
 
@@ -155,6 +155,7 @@ Langfuse 是一个 **开源 LLM 工程** 平台。它帮助团队协作 **开发
 | [LiteLLM](https://langfuse.com/docs/integrations/litellm)               | Python, JS/TS (仅代理)     | 允许使用任何 LLM 替代 GPT。支持 Azure、OpenAI、Cohere、Anthropic、Ollama、VLLM、Sagemaker、HuggingFace、Replicate（100+ LLMs）。         |
 | [Vercel AI SDK](https://langfuse.com/docs/integrations/vercel-ai-sdk)     | JS/TS                    | 基于 TypeScript 的工具包，帮助开发者使用 React、Next.js、Vue、Svelte 和 Node.js 构建 AI 驱动的应用。                                           |
 | [API](https://langfuse.com/docs/api)                                    |                          | 直接调用公共 API。提供 OpenAPI 规格。                                                                                                       |
+| [Google VertexAI 和 Gemini](https://langfuse.com/docs/integrations/google-vertex-ai) | 模型                | 在 Google 上运行基础模型和微调模型。                                                                         |
 
 ### 与 Langfuse 集成的软件包：
 
@@ -162,9 +163,9 @@ Langfuse 是一个 **开源 LLM 工程** 平台。它帮助团队协作 **开发
 | ---------------------------------------------------------------------- | ------------------- | -------------------------------------------------------------------------------------------------------- |
 | [Instructor](https://langfuse.com/docs/integrations/instructor)         | 库                  | 用于获取结构化 LLM 输出（JSON、Pydantic）的库。                                                         |
 | [DSPy](https://langfuse.com/docs/integrations/dspy)                     | 库                  | 一个系统性优化语言模型提示和权重的框架。                                                                 |
+| [Amazon Bedrock](https://langfuse.com/docs/integrations/amazon-bedrock) | 模型                | 在 AWS 上运行基础模型和微调模型。                                                                         |
 | [Mirascope](https://langfuse.com/docs/integrations/mirascope)           | 库                  | 构建 LLM 应用的 Python 工具包。                                                                           |
 | [Ollama](https://langfuse.com/docs/integrations/ollama)                 | 模型（本地）         | 在你的机器上轻松运行开源 LLM。                                                                            |
-| [Amazon Bedrock](https://langfuse.com/docs/integrations/amazon-bedrock) | 模型                | 在 AWS 上运行基础模型和微调模型。                                                                         |
 | [AutoGen](https://langfuse.com/docs/integrations/autogen)               | 代理框架             | 用于构建分布式代理的开源 LLM 平台。                                                                       |
 | [Flowise](https://langfuse.com/docs/integrations/flowise)               | 聊天/代理界面         | 基于 JS/TS 的无代码构建器，用于定制化 LLM 流程。                                                          |
 | [Langflow](https://langfuse.com/docs/integrations/langflow)             | 聊天/代理界面         | 基于 Python 的 LangChain 用户界面，采用 react-flow 设计，提供便捷的实验与原型构建体验。                   |
@@ -213,8 +214,8 @@ LANGFUSE_HOST="https://cloud.langfuse.com" # 🇪🇺 欧盟区域
 
 创建示例代码（文件名：**main.py**）：
 
-````python:main.py
-from langfuse.decorators import observe
+```python:main.py
+from langfuse import observe
 from langfuse.openai import openai  # OpenAI 集成
 
 @observe()
@@ -253,7 +254,7 @@ _[Langfuse 中的公共示例追踪](https://cloud.langfuse.com/project/cloramnk
 
 - 我们的 [文档](https://langfuse.com/docs) 是查找答案的最佳起点。内容全面，我们投入大量时间进行维护。你也可以通过 GitHub 提出文档修改建议。
 - [Langfuse 常见问题](https://langfuse.com/faq) 解答了最常见的问题。
-- 使用 “[Ask AI](https://langfuse.com/docs/ask-ai)” 立即获取问题答案。
+- 使用 "Ask AI" 立即获取问题答案。
 
 支持渠道：
 
@@ -351,4 +352,4 @@ _[Langfuse 中的公共示例追踪](https://cloud.langfuse.com/project/cloramnk
 所有数据均不会与第三方共享，也不包含任何敏感信息。我们对这一过程保持高度透明，你可以在 [此处](/web/src/features/telemetry/index.ts) 查看我们收集的具体数据。
 
 你可以通过设置 `TELEMETRY_ENABLED=false` 来选择退出。
-````
+```

README.ja.md

@@ -26,7 +26,7 @@
       <a href="https://langfuse.com/roadmap"><strong>ロードマップ</strong></a> ·
    </div>
    <br/>
-   <span>Langfuseは、サポートと機能リクエストのために <a href="https://github.com/orgs/langfuse/discussions"><strong>Github Discussions</strong></a> を利用しています。</span>
+   <span>Langfuseは、サポートと機能リクエストのために <a href="https://github.com/orgs/langfuse/discussions"><strong>GitHub Discussions</strong></a> を利用しています。</span>
    <br/>
    <span><b>We're hiring.</b> <a href="https://langfuse.com/careers"><strong>チームに加わる</strong></a> （製品エンジニアリングおよびテクニカルGTMのポジション）への応募をお待ちしています。</span>
    <br/>
@@ -141,9 +141,7 @@ Langfuseチームによるマネージドデプロイメント。充実した無
 - **[VM](https://langfuse.com/self-hosting/docker-compose):**  
   Docker Composeを使用して、単一の仮想マシン上でLangfuseを実行します。
 
-- **Planned:**  
-  クラウド固有のデプロイガイドは計画中です。以下のスレッドに対して投票やコメントをお願いします:  
-  [AWS](https://github.com/orgs/langfuse/discussions/4645), [Google Cloud](https://github.com/orgs/langfuse/discussions/4646), [Azure](https://github.com/orgs/langfuse/discussions/4647).
+- Terraform テンプレート: [AWS](https://langfuse.com/self-hosting/aws), [Azure](https://langfuse.com/self-hosting/azure), [GCP](https://langfuse.com/self-hosting/gcp)
 
 [セルフホスティングのドキュメント](https://langfuse.com/self-hosting)を参照し、アーキテクチャや設定オプションの詳細をご確認ください。
 
@@ -219,7 +217,7 @@ LANGFUSE_HOST="https://cloud.langfuse.com" # 🇪🇺 EUリージョン
 ```
 
 ```python:/@observe()/ /from langfuse.openai import openai/ filename="main.py"
-from langfuse.decorators import observe
+from langfuse import observe
 from langfuse.openai import openai  # OpenAI統合
 
 @observe()

README.kr.md

@@ -128,7 +128,7 @@ Langfuse 팀이 관리하는 배포 방식으로, 후한 무료 플랜(취미
 
 - [Kubernetes (Helm)](https://langfuse.com/self-hosting/kubernetes-helm): Helm을 사용해 Kubernetes 클러스터에서 Langfuse를 실행합니다. 이는 권장되는 프로덕션 배포 방식입니다.
 - [VM](https://langfuse.com/self-hosting/docker-compose): Docker Compose를 사용해 단일 가상 머신에서 Langfuse를 실행합니다.
-- 예정: 클라우드별 배포 가이드 – 아래 스레드에서 투표 및 댓글을 남겨주세요: [AWS](https://github.com/orgs/langfuse/discussions/4645), [Google Cloud](https://github.com/orgs/langfuse/discussions/4646), [Azure](https://github.com/orgs/langfuse/discussions/4647).
+- Terraform 템플릿: [AWS](https://langfuse.com/self-hosting/aws), [Azure](https://langfuse.com/self-hosting/azure), [GCP](https://langfuse.com/self-hosting/gcp)
 
 자세한 내용은 [자체 호스팅 문서](https://langfuse.com/self-hosting)를 참조하세요.
 
@@ -158,6 +158,7 @@ Langfuse 팀이 관리하는 배포 방식으로, 후한 무료 플랜(취미
 | [Mirascope](https://langfuse.com/docs/integrations/mirascope)           | 라이브러리         | LLM 애플리케이션 구축을 위한 Python 툴킷입니다.                                                                    |
 | [Ollama](https://langfuse.com/docs/integrations/ollama)                 | 모델 (로컬)        | 자신의 컴퓨터에서 오픈 소스 LLM을 손쉽게 실행할 수 있습니다.                                                      |
 | [Amazon Bedrock](https://langfuse.com/docs/integrations/amazon-bedrock) | 모델               | AWS에서 기본 및 파인튜닝된 모델을 실행합니다.                                                                      |
+| [Google VertexAI and Gemini](https://langfuse.com/docs/integrations/google-vertex-ai) | 모델               | Google에서 기본 및 파인튜닝된 모델을 실행합니다.                                                                      |
 | [AutoGen](https://langfuse.com/docs/integrations/autogen)               | 에이전트 프레임워크 | 분산 에이전트 구축을 위한 오픈 소스 LLM 플랫폼입니다.                                                              |
 | [Flowise](https://langfuse.com/docs/integrations/flowise)               | 채팅/에이전트 UI    | 맞춤형 LLM 플로우를 위한 JS/TS 코드 없는(no-code) 빌더입니다.                                                       |
 | [Langflow](https://langfuse.com/docs/integrations/langflow)             | 채팅/에이전트 UI    | react-flow를 활용하여 실험 및 프로토타이핑을 손쉽게 할 수 있도록 디자인된 LangChain용 Python 기반 UI입니다.          |
@@ -201,7 +202,7 @@ LANGFUSE_HOST="https://cloud.langfuse.com" # 🇪🇺 EU region
 ```
 
 ```python:main.py
-from langfuse.decorators import observe
+from langfuse import observe
 from langfuse.openai import openai # OpenAI integration
 
 @observe()

README.md

@@ -3,6 +3,9 @@
 <div align="center">
    <div>
       <h3>
+        <a href="https://langfuse.com/blog/2025-06-04-open-sourcing-langfuse-product">
+            <strong>Langfuse Is Doubling Down On Open Source</strong>
+         </a> <br> <br>
          <a href="https://cloud.langfuse.com">
             <strong>Langfuse Cloud</strong>
          </a> · 
@@ -23,7 +26,7 @@
       <a href="https://langfuse.com/roadmap"><strong>Roadmap</strong></a> ·
    </div>
    <br/>
-   <span>Langfuse uses <a href="https://github.com/orgs/langfuse/discussions"><strong>Github Discussions</strong></a>  for Support and Feature Requests.</span>
+   <span>Langfuse uses <a href="https://github.com/orgs/langfuse/discussions"><strong>GitHub Discussions</strong></a>  for Support and Feature Requests.</span>
    <br/>
    <span><b>We're hiring.</b> <a href="https://langfuse.com/careers"><strong>Join us</strong></a> in product engineering and technical go-to-market roles.</span>
    <br/>
@@ -93,7 +96,7 @@ Langfuse is an **open source LLM engineering** platform. It helps teams collabor
 
 ### Langfuse Cloud
 
-Managed deployment by the Langfuse team, generous free-tier (hobby plan), no credit card required.
+Managed deployment by the Langfuse team, generous free-tier, no credit card required.
 
 <div align="center">
     <a href="https://cloud.langfuse.com" target="_blank">
@@ -115,12 +118,11 @@ Run Langfuse on your own infrastructure:
   # Run the langfuse docker compose
   docker compose up
   ```
-
-- [Kubernetes (Helm)](https://langfuse.com/self-hosting/kubernetes-helm): Run Langfuse on a Kubernetes cluster using Helm. This is the preferred production deployment.
 - [VM](https://langfuse.com/self-hosting/docker-compose): Run Langfuse on a single Virtual Machine using Docker Compose.
-- Planned: Cloud-specific deployment guides, please upvote and comment on the following threads: [AWS](https://github.com/orgs/langfuse/discussions/4645), [Google Cloud](https://github.com/orgs/langfuse/discussions/4646), [Azure](https://github.com/orgs/langfuse/discussions/4647).
+- [Kubernetes (Helm)](https://langfuse.com/self-hosting/kubernetes-helm): Run Langfuse on a Kubernetes cluster using Helm. This is the preferred production deployment.
+- Terraform Templates: [AWS](https://langfuse.com/self-hosting/aws), [Azure](https://langfuse.com/self-hosting/azure), [GCP](https://langfuse.com/self-hosting/gcp)
 
-See [self-hosting documentation](https://langfuse.com/self-hosting) to learn more about the architecture and configuration options.
+See [self-hosting documentation](https://langfuse.com/self-hosting) to learn more about architecture and configuration options.
 
 ## 🔌 Integrations
 
@@ -191,7 +193,7 @@ LANGFUSE_HOST="https://cloud.langfuse.com" # 🇪🇺 EU region
 ```
 
 ```python /@observe()/ /from langfuse.openai import openai/ filename="main.py"
-from langfuse.decorators import observe
+from langfuse import observe
 from langfuse.openai import openai # OpenAI integration
 
 @observe()

docker-compose.build.yml

@@ -78,7 +78,7 @@ services:
       retries: 3
 
   clickhouse:
-    image: clickhouse/clickhouse-server
+    image: docker.io/clickhouse/clickhouse-server
     user: "101:101"
     environment:
       CLICKHOUSE_DB: default
@@ -98,7 +98,7 @@ services:
       start_period: 1s
 
   minio:
-    image: minio/minio
+    image: docker.io/minio/minio
     entrypoint: sh
     # create the 'langfuse' bucket before starting the service
     command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
@@ -118,7 +118,7 @@ services:
       start_period: 1s
 
   redis:
-    image: redis:7
+    image: docker.io/redis:7
     restart: always
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
@@ -131,7 +131,7 @@ services:
       retries: 10
 
   postgres:
-    image: postgres:${POSTGRES_VERSION:-latest}
+    image: docker.io/postgres:${POSTGRES_VERSION:-latest}
     restart: always
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -U postgres"]

docker-compose.dev-azure.yml

@@ -1,6 +1,6 @@
 services:
   clickhouse:
-    image: clickhouse/clickhouse-server:24.3
+    image: docker.io/clickhouse/clickhouse-server:24.3
     user: "101:101"
     environment:
       CLICKHOUSE_DB: default
@@ -24,7 +24,7 @@ services:
       - langfuse_azurite_data:/data
 
   redis:
-    image: redis:7.2.4
+    image: docker.io/redis:7.2.4
     restart: always
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
@@ -32,7 +32,7 @@ services:
       - 6379:6379
 
   postgres:
-    image: postgres:${POSTGRES_VERSION:-latest}
+    image: docker.io/postgres:${POSTGRES_VERSION:-latest}
     restart: always
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -U postgres"]

docker-compose.dev-redis-cluster.yml

@@ -0,0 +1,146 @@
+services:
+  clickhouse:
+    image: docker.io/clickhouse/clickhouse-server:24.3
+    user: "101:101"
+    environment:
+      CLICKHOUSE_DB: default
+      CLICKHOUSE_USER: clickhouse
+      CLICKHOUSE_PASSWORD: clickhouse
+    volumes:
+      - langfuse_clickhouse_data:/var/lib/clickhouse
+      - langfuse_clickhouse_logs:/var/log/clickhouse-server
+    ports:
+      - 127.0.0.1:8123:8123
+      - 127.0.0.1:9000:9000
+    depends_on:
+      - postgres
+
+  minio:
+    image: docker.io/minio/minio
+    entrypoint: sh
+    # create the 'langfuse' bucket before starting the service
+    command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
+    environment:
+      MINIO_ACCESS_KEY: minio
+      MINIO_SECRET_KEY: miniosecret
+    ports:
+      - 127.0.0.1:9090:9000
+      - 127.0.0.1:9091:9001
+    volumes:
+      - langfuse_minio_data:/data
+    healthcheck:
+      test: ["CMD", "mc", "ready", "local"]
+      interval: 1s
+      timeout: 5s
+      retries: 5
+      start_period: 1s
+
+  postgres:
+    image: docker.io/postgres:${POSTGRES_VERSION:-latest}
+    restart: always
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U postgres"]
+      interval: 3s
+      timeout: 3s
+      retries: 10
+    command: ["postgres", "-c", "log_statement=all"]
+    environment:
+      - POSTGRES_USER=postgres
+      - POSTGRES_PASSWORD=postgres
+      - POSTGRES_DB=postgres
+    ports:
+      - 127.0.0.1:5432:5432
+    volumes:
+      - langfuse_postgres_data:/var/lib/postgresql/data
+
+  # Redis Cluster. Requires a Unix host to work for network_mode: host. I.e. tests will fail on windows and mac with this setup.
+  redis-node-0:
+    image: docker.io/bitnami/redis-cluster:8.0
+    network_mode: host
+    volumes:
+      - redis-cluster_data-0:/bitnami/redis/data
+    environment:
+      REDIS_PASSWORD: bitnami
+      REDIS_PORT_NUMBER: 6370
+      REDIS_NODES: 127.0.0.1:6370 127.0.0.1:6371 127.0.0.1:6372 127.0.0.1:6373 127.0.0.1:6374 127.0.0.1:6375
+
+  redis-node-1:
+    image: docker.io/bitnami/redis-cluster:8.0
+    network_mode: host
+    volumes:
+      - redis-cluster_data-1:/bitnami/redis/data
+    environment:
+      REDIS_PASSWORD: bitnami
+      REDIS_PORT_NUMBER: 6371
+      REDIS_NODES: 127.0.0.1:6370 127.0.0.1:6371 127.0.0.1:6372 127.0.0.1:6373 127.0.0.1:6374 127.0.0.1:6375
+
+  redis-node-2:
+    image: docker.io/bitnami/redis-cluster:8.0
+    network_mode: host
+    volumes:
+      - redis-cluster_data-2:/bitnami/redis/data
+    environment:
+      REDIS_PASSWORD: bitnami
+      REDIS_PORT_NUMBER: 6372
+      REDIS_NODES: 127.0.0.1:6370 127.0.0.1:6371 127.0.0.1:6372 127.0.0.1:6373 127.0.0.1:6374 127.0.0.1:6375
+
+  redis-node-3:
+    image: docker.io/bitnami/redis-cluster:8.0
+    network_mode: host
+    volumes:
+      - redis-cluster_data-3:/bitnami/redis/data
+    environment:
+      REDIS_PASSWORD: bitnami
+      REDIS_PORT_NUMBER: 6373
+      REDIS_NODES: 127.0.0.1:6370 127.0.0.1:6371 127.0.0.1:6372 127.0.0.1:6373 127.0.0.1:6374 127.0.0.1:6375
+
+  redis-node-4:
+    image: docker.io/bitnami/redis-cluster:8.0
+    network_mode: host
+    volumes:
+      - redis-cluster_data-4:/bitnami/redis/data
+    environment:
+      REDIS_PASSWORD: bitnami
+      REDIS_PORT_NUMBER: 6374
+      REDIS_NODES: 127.0.0.1:6370 127.0.0.1:6371 127.0.0.1:6372 127.0.0.1:6373 127.0.0.1:6374 127.0.0.1:6375
+
+  redis-node-5:
+    image: docker.io/bitnami/redis-cluster:8.0
+    network_mode: host
+    volumes:
+      - redis-cluster_data-5:/bitnami/redis/data
+    depends_on:
+      - redis-node-0
+      - redis-node-1
+      - redis-node-2
+      - redis-node-3
+      - redis-node-4
+    environment:
+      REDISCLI_AUTH: bitnami
+      REDIS_CLUSTER_REPLICAS: 1
+      REDIS_PASSWORD: bitnami
+      REDIS_PORT_NUMBER: 6375
+      REDIS_NODES: 127.0.0.1:6370 127.0.0.1:6371 127.0.0.1:6372 127.0.0.1:6373 127.0.0.1:6374 127.0.0.1:6375
+      REDIS_CLUSTER_CREATOR: yes
+
+volumes:
+  langfuse_postgres_data:
+    driver: local
+  langfuse_clickhouse_data:
+    driver: local
+  langfuse_clickhouse_logs:
+    driver: local
+  langfuse_minio_data:
+    driver: local
+  redis-cluster_data-0:
+    driver: local
+  redis-cluster_data-1:
+    driver: local
+  redis-cluster_data-2:
+    driver: local
+  redis-cluster_data-3:
+    driver: local
+  redis-cluster_data-4:
+    driver: local
+  redis-cluster_data-5:
+    driver: local

docker-compose.dev.yml

@@ -1,6 +1,6 @@
 services:
   clickhouse:
-    image: clickhouse/clickhouse-server:24.3
+    image: docker.io/clickhouse/clickhouse-server:24.3
     user: "101:101"
     environment:
       CLICKHOUSE_DB: default
@@ -16,7 +16,7 @@ services:
       - postgres
 
   minio:
-    image: minio/minio
+    image: docker.io/minio/minio
     entrypoint: sh
     # create the 'langfuse' bucket before starting the service
     command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
@@ -36,7 +36,7 @@ services:
       start_period: 1s
 
   redis:
-    image: redis:7.2.4
+    image: docker.io/redis:7.2.4
     restart: always
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
@@ -44,7 +44,7 @@ services:
       - 127.0.0.1:6379:6379
 
   postgres:
-    image: postgres:${POSTGRES_VERSION:-latest}
+    image: docker.io/postgres:${POSTGRES_VERSION:-latest}
     restart: always
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -U postgres"]

docker-compose.yml

@@ -5,7 +5,7 @@
 # External connections from other machines will not be able to reach these services directly.
 services:
   langfuse-worker:
-    image: langfuse/langfuse-worker:3
+    image: docker.io/langfuse/langfuse-worker:3
     restart: always
     depends_on: &langfuse-depends-on
       postgres:
@@ -19,6 +19,7 @@ services:
     ports:
       - 127.0.0.1:3030:3030
     environment: &langfuse-worker-env
+      NEXTAUTH_URL: http://localhost:3000
       DATABASE_URL: postgresql://postgres:postgres@postgres:5432/postgres # CHANGEME
       SALT: "mysalt" # CHANGEME
       ENCRYPTION_KEY: "0000000000000000000000000000000000000000000000000000000000000000" # CHANGEME: generate via `openssl rand -hex 32`
@@ -29,6 +30,7 @@ services:
       CLICKHOUSE_USER: ${CLICKHOUSE_USER:-clickhouse}
       CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-clickhouse} # CHANGEME
       CLICKHOUSE_CLUSTER_ENABLED: ${CLICKHOUSE_CLUSTER_ENABLED:-false}
+      LANGFUSE_USE_AZURE_BLOB: ${LANGFUSE_USE_AZURE_BLOB:-false}
       LANGFUSE_S3_EVENT_UPLOAD_BUCKET: ${LANGFUSE_S3_EVENT_UPLOAD_BUCKET:-langfuse}
       LANGFUSE_S3_EVENT_UPLOAD_REGION: ${LANGFUSE_S3_EVENT_UPLOAD_REGION:-auto}
       LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID:-minio}
@@ -61,16 +63,17 @@ services:
       REDIS_TLS_CA: ${REDIS_TLS_CA:-/certs/ca.crt}
       REDIS_TLS_CERT: ${REDIS_TLS_CERT:-/certs/redis.crt}
       REDIS_TLS_KEY: ${REDIS_TLS_KEY:-/certs/redis.key}
+      EMAIL_FROM_ADDRESS: ${EMAIL_FROM_ADDRESS:-}
+      SMTP_CONNECTION_URL: ${SMTP_CONNECTION_URL:-}
 
   langfuse-web:
-    image: langfuse/langfuse:3
+    image: docker.io/langfuse/langfuse:3
     restart: always
     depends_on: *langfuse-depends-on
     ports:
       - 3000:3000
     environment:
       <<: *langfuse-worker-env
-      NEXTAUTH_URL: http://localhost:3000
       NEXTAUTH_SECRET: mysecret # CHANGEME
       LANGFUSE_INIT_ORG_ID: ${LANGFUSE_INIT_ORG_ID:-}
       LANGFUSE_INIT_ORG_NAME: ${LANGFUSE_INIT_ORG_NAME:-}
@@ -83,7 +86,7 @@ services:
       LANGFUSE_INIT_USER_PASSWORD: ${LANGFUSE_INIT_USER_PASSWORD:-}
 
   clickhouse:
-    image: clickhouse/clickhouse-server
+    image: docker.io/clickhouse/clickhouse-server
     restart: always
     user: "101:101"
     environment:
@@ -104,7 +107,7 @@ services:
       start_period: 1s
 
   minio:
-    image: minio/minio
+    image: docker.io/minio/minio
     restart: always
     entrypoint: sh
     # create the 'langfuse' bucket before starting the service
@@ -125,7 +128,7 @@ services:
       start_period: 1s
 
   redis:
-    image: redis:7
+    image: docker.io/redis:7
     restart: always
     # CHANGEME: row below to secure redis password
     command: >
@@ -139,7 +142,7 @@ services:
       retries: 10
 
   postgres:
-    image: postgres:${POSTGRES_VERSION:-latest}
+    image: docker.io/postgres:${POSTGRES_VERSION:-latest}
     restart: always
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -U postgres"]

ee/package.json

@@ -26,11 +26,10 @@
   "dependencies": {
     "@langfuse/shared": "workspace:*",
     "@opentelemetry/api": ">=1.0.0 <1.10.0",
-    "axios": "^1.8.2",
     "https-proxy-agent": "^7.0.6",
-    "next": "^14.2.26",
+    "next": "^14.2.30",
     "next-auth": "^4.24.11",
-    "zod": "^3.24.4"
+    "zod": "^3.25.62"
   },
   "devDependencies": {
     "@repo/eslint-config": "workspace:*",
@@ -41,14 +40,9 @@
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",
     "eslint-plugin-prettier": "^5.1.3",
-    "prettier": "^3.3.3",
+    "prettier": "^3.6.2",
     "ts-node": "^10.9.2",
     "tsc-watch": "^6.2.0",
     "typescript": "^5.4.5"
-  },
-  "pnpm": {
-    "overrides": {
-      "nanoid": "^3.3.8"
-    }
   }
 }

ee/src/env.ts

@@ -1,4 +1,4 @@
-import { z } from "zod";
+import { z } from "zod/v4";
 import { removeEmptyEnvVariables } from "@langfuse/shared";
 
 const EnvSchema = z.object({

fern/apis/server/definition/annotation-queues.yml

@@ -105,6 +105,28 @@ service:
           docs: The unique identifier of the annotation queue item
       response: DeleteAnnotationQueueItemResponse
 
+    createQueueAssignment:
+      docs: Create an assignment for a user to an annotation queue
+      method: POST
+      path: /annotation-queues/{queueId}/assignments
+      path-parameters:
+        queueId:
+          type: string
+          docs: The unique identifier of the annotation queue
+      request: AnnotationQueueAssignmentRequest
+      response: CreateAnnotationQueueAssignmentResponse
+
+    deleteQueueAssignment:
+      docs: Delete an assignment for a user to an annotation queue
+      method: DELETE
+      path: /annotation-queues/{queueId}/assignments
+      path-parameters:
+        queueId:
+          type: string
+          docs: The unique identifier of the annotation queue
+      request: AnnotationQueueAssignmentRequest
+      response: DeleteAnnotationQueueAssignmentResponse
+
 types:
   AnnotationQueueStatus:
     enum:
@@ -163,3 +185,17 @@ types:
     properties:
       success: boolean
       message: string
+
+  AnnotationQueueAssignmentRequest:
+    properties:
+      userId: string
+
+  DeleteAnnotationQueueAssignmentResponse:
+    properties:
+      success: boolean
+
+  CreateAnnotationQueueAssignmentResponse:
+    properties:
+      userId: string
+      queueId: string
+      projectId: string

fern/apis/server/definition/commons.yml

@@ -457,13 +457,13 @@ types:
         docs: Unit used by this model.
         type: optional<ModelUsageUnit>
       inputPrice:
-        docs: Price (USD) per input unit
+        docs: Deprecated. See 'prices' instead. Price (USD) per input unit
         type: optional<double>
       outputPrice:
-        docs: Price (USD) per output unit
+        docs: Deprecated. See 'prices' instead. Price (USD) per output unit
         type: optional<double>
       totalPrice:
-        docs: Price (USD) per total unit. Cannot be set if input or output price is set.
+        docs: Deprecated. See 'prices' instead. Price (USD) per total unit. Cannot be set if input or output price is set.
         type: optional<double>
       tokenizerId:
         docs: Optional. Tokenizer to be applied to observations which match to this model. See docs for more details.
@@ -473,6 +473,13 @@ types:
         type: optional<unknown>
       isLangfuseManaged:
         type: boolean
+      prices:
+        docs: Price (USD) by usage type
+        type: map<string, ModelPrice>
+
+  ModelPrice:
+    properties:
+      price: double
 
   # Utilities
   ModelUsageUnit:

fern/apis/server/definition/dataset-run-items.yml

@@ -27,7 +27,7 @@ service:
           limit:
             type: optional<integer>
             docs: limit of items per page
-          response: PaginatedDatasetRunItems
+      response: PaginatedDatasetRunItems
 
 types:
   CreateDatasetRunItemRequest:

fern/apis/server/definition/llm-connections.yml

@@ -0,0 +1,102 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  commons: ./commons.yml
+  pagination: ./utils/pagination.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    list:
+      method: GET
+      docs: Get all LLM connections in a project
+      path: /llm-connections
+      request:
+        name: GetLlmConnectionsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: limit of items per page
+      response: PaginatedLlmConnections
+    upsert:
+      method: PUT
+      docs: Create or update an LLM connection. The connection is upserted on provider.
+      path: /llm-connections
+      request: UpsertLlmConnectionRequest
+      response: LlmConnection
+
+types:
+  LlmConnection:
+    docs: LLM API connection configuration (secrets excluded)
+    properties:
+      id: string
+      provider:
+        type: string
+        docs: Provider name (e.g., 'openai', 'my-gateway'). Must be unique in project, used for upserting.
+      adapter:
+        type: string
+        docs: The adapter used to interface with the LLM
+      displaySecretKey:
+        type: string
+        docs: Masked version of the secret key for display purposes
+      baseURL:
+        type: optional<string>
+        docs: Custom base URL for the LLM API
+      customModels:
+        type: list<string>
+        docs: List of custom model names available for this connection
+      withDefaultModels:
+        type: boolean
+        docs: Whether to include default models for this adapter
+      extraHeaderKeys:
+        type: list<string>
+        docs: Keys of extra headers sent with requests (values excluded for security)
+      createdAt: datetime
+      updatedAt: datetime
+
+  PaginatedLlmConnections:
+    properties:
+      data: list<LlmConnection>
+      meta: pagination.MetaResponse
+
+  UpsertLlmConnectionRequest:
+    docs: Request to create or update an LLM connection (upsert)
+    properties:
+      provider:
+        type: string
+        docs: Provider name (e.g., 'openai', 'my-gateway'). Must be unique in project, used for upserting.
+      adapter:
+        type: LlmAdapter
+        docs: The adapter used to interface with the LLM
+      secretKey:
+        type: string
+        docs: Secret key for the LLM API.
+      baseURL:
+        type: optional<string>
+        docs: Custom base URL for the LLM API
+      customModels:
+        type: optional<list<string>>
+        docs: List of custom model names
+      withDefaultModels:
+        type: optional<boolean>
+        docs: Whether to include default models. Default is true.
+      extraHeaders:
+        type: optional<map<string, string>>
+        docs: Extra headers to send with requests
+
+  LlmAdapter:
+    enum:
+      - value: anthropic
+        name: Anthropic
+      - value: openai
+        name: OpenAI
+      - value: azure
+        name: Azure
+      - value: bedrock
+        name: Bedrock
+      - value: google-vertex-ai
+        name: GoogleVertexAI
+      - value: google-ai-studio
+        name: GoogleAIStudio

fern/apis/server/definition/metrics.yml

@@ -28,7 +28,7 @@ service:
                 "metrics": [              // Required. At least one metric must be provided
                   {
                     "measure": string,    // What to measure, e.g. "count", "latency", "value"
-                    "aggregation": string // How to aggregate, e.g. "count", "sum", "avg", "p95"
+                    "aggregation": string // How to aggregate, e.g. "count", "sum", "avg", "p95", "histogram"
                   }
                 ],
                 "filters": [              // Optional. Default: []
@@ -50,7 +50,11 @@ service:
                     "field": string,      // Field to order by
                     "direction": string   // "asc" or "desc"
                   }
-                ]
+                ],
+                "config": {               // Optional. Query-specific configuration
+                  "bins": number,         // Optional. Number of bins for histogram (1-100), default: 10
+                  "row_limit": number     // Optional. Row limit for results (1-1000)
+                }
               }
               ```
       response: MetricsResponse
@@ -62,3 +66,4 @@ types:
         docs: |
           The metrics data. Each item in the list contains the metric values and dimensions requested in the query.
           Format varies based on the query parameters.
+          Histograms will return an array with [lower, upper, height] tuples.

fern/apis/server/definition/observations.yml

@@ -32,6 +32,9 @@ service:
           userId: optional<string>
           type: optional<string>
           traceId: optional<string>
+          level:
+            type: optional<commons.ObservationLevel>
+            docs: Optional filter for observations with a specific level (e.g. "DEBUG", "DEFAULT", "WARNING", "ERROR").
           parentObservationId: optional<string>
           environment:
             type: optional<string>

fern/apis/server/definition/projects.yml

@@ -11,7 +11,7 @@ service:
       method: GET
       path: /projects
       response: Projects
-    
+
     create:
       docs: Create a new project (requires organization-scoped API key)
       method: POST
@@ -28,7 +28,7 @@ service:
               type: integer
               docs: Number of days to retain data. Must be 0 or at least 3 days. Requires data-retention entitlement for non-zero values. Optional.
       response: Project
-    
+
     update:
       docs: Update a project by ID (requires organization-scoped API key).
       method: PUT
@@ -47,7 +47,7 @@ service:
               type: integer
               docs: Number of days to retain data. Must be 0 or at least 3 days. Requires data-retention entitlement for non-zero values. Optional.
       response: Project
-    
+
     delete:
       docs: Delete a project by ID (requires organization-scoped API key). Project deletion is processed asynchronously.
       method: DELETE
@@ -57,7 +57,7 @@ service:
       response:
         status-code: 202
         type: ProjectDeletionResponse
-        
+
     # API Key endpoints
     getApiKeys:
       docs: Get all API keys for a project (requires organization-scoped API key)
@@ -104,14 +104,14 @@ types:
         type: map<string, unknown>
         docs: Metadata for the project
       retentionDays:
-        type: integer
+        type: optional<integer>
         docs: Number of days to retain data. Null or 0 means no retention. Omitted if no retention is configured.
 
   ProjectDeletionResponse:
     properties:
       success: boolean
       message: string
-      
+
   ApiKeyList:
     docs: List of API keys for a project
     properties:
@@ -137,7 +137,7 @@ types:
       secretKey: string
       displaySecretKey: string
       note: optional<string>
-      
+
   ApiKeyDeletionResponse:
     docs: Response for API key deletion
     properties:

fern/apis/server/definition/prompts.yml

@@ -82,7 +82,7 @@ types:
   CreateChatPromptRequest:
     properties:
       name: string
-      prompt: list<ChatMessage>
+      prompt: list<ChatMessageWithPlaceholders>
       config: optional<unknown>
       labels:
         type: optional<list<string>>
@@ -132,6 +132,11 @@ types:
         type: optional<map<string, unknown>>
         docs: The dependency resolution graph for the current prompt. Null if prompt has no dependencies.
 
+  ChatMessageWithPlaceholders:
+    union:
+      chatmessage: ChatMessage
+      placeholder: PlaceholderMessage
+
   ChatMessage:
     properties:
       role:
@@ -139,6 +144,11 @@ types:
       content:
         type: string
 
+  PlaceholderMessage:
+    properties:
+      name:
+        type: string
+
   TextPrompt:
     extends: BasePrompt
     properties:
@@ -147,4 +157,4 @@ types:
   ChatPrompt:
     extends: BasePrompt
     properties:
-      prompt: list<ChatMessage>
+      prompt: list<ChatMessageWithPlaceholders>

fern/apis/server/definition/trace.yml

@@ -63,6 +63,9 @@ service:
             type: optional<string>
             allow-multiple: true
             docs: Optional filter for traces where the environment is one of the provided values.
+          fields:
+            type: optional<string>
+            docs: "Comma-separated list of fields to include in the response. Available field groups are 'core' (always included), 'io' (input, output, metadata), 'scores', 'observations', 'metrics'. If not provided, all fields are included. Example: 'core,scores,metrics'"
       response: Traces
     deleteMultiple:
       docs: Delete multiple traces

fern/apis/server/generators.yml

@@ -1,3 +1,4 @@
+# yaml-language-server: $schema=https://schema.buildwithfern.dev/generators-yml.json
 default-group: local
 groups:
   local:
@@ -7,6 +8,7 @@ groups:
         output:
           location: local-file-system
           path: ../../../web/public/generated/api
+
       - name: fernapi/fern-python-sdk
         version: 2.16.0
         output:
@@ -19,35 +21,32 @@ groups:
           pydantic_config:
             require_optional_fields: false
             use_str_enums: false
-#      - name: fernapi/fern-java-sdk
-#        version: 2.20.1
-#        output:
-#          location: local-file-system
-#          path: ../../../../langfuse-java/src/main/java/com/langfuse/client/
-#        config:
-#          client-class-name: LangfuseClient
+
+      # - name: fernapi/fern-java-sdk
+      #   version: 2.20.1
+      #   output:
+      #     location: local-file-system
+      #     path: ../../../../langfuse-java/src/main/java/com/langfuse/client/
+      #   config:
+      #     client-class-name: LangfuseClient
+
+      - name: fernapi/fern-typescript-node-sdk
+        version: 2.6.1
+        output:
+          location: local-file-system
+          path: ../../../generated/typescript
+        config:
+          namespaceExport: LangfuseAPI
+          outputSourceFiles: true
+          skipResponseValidation: true
+          fetchSupport: native
+          formDataSupport: Node18
+          fileResponseType: binary-response
+          streamType: web
+          omitFernHeaders: true
+
       - name: fernapi/fern-postman
         version: 0.0.45
         output:
           location: local-file-system
           path: ../../../web/public/generated/postman
-  # published:
-  #   generators:
-  #     - name: fernapi/fern-python-sdk
-  #       version: 0.3.7
-  #       output:
-  #         location: pypi
-  #         url: pypi.buildwithfern.com
-  #         package-name: finto-fern-langfuse
-  #       config:
-  #         namespaceExport: Langfuse
-  #         allowCustomFetcher: true
-  #     - name: fernapi/fern-typescript-node-sdk
-  #       version: 0.7.1
-  #       output:
-  #         location: npm
-  #         url: npm.buildwithfern.com
-  #         package-name: "@finto-fern/langfuse-node"
-  #       config:
-  #         namespaceExport: Langfuse
-  #         allowCustomFetcher: true

generated/.gitignore

@@ -1 +0,0 @@
-python/

package.json

@@ -1,6 +1,6 @@
 {
   "name": "langfuse",
-  "version": "3.63.0",
+  "version": "3.97.2",
   "author": "engineering@langfuse.com",
   "license": "MIT",
   "private": true,
@@ -17,27 +17,30 @@
     "db:seed": "turbo run db:seed",
     "db:seed:examples": "turbo run db:seed:examples",
     "nuke": "bash ./scripts/nuke.sh",
-    "dx": "pnpm i && pnpm run infra:dev:prune && pnpm run infra:dev:up --pull always && 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:prune && pnpm run infra:dev:up --pull always && 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",
+    "dx": "pnpm i && pnpm run infra:dev:prune && pnpm run infra:dev:up --pull always && pnpm --filter=shared run db:reset:test && 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:prune && pnpm run infra:dev:up --pull always && pnpm --filter=shared run db:reset:test && pnpm --filter=shared run db:reset -f && SKIP_CONFIRM=1 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:test && 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",
     "dev:worker": "turbo run dev --filter=worker",
     "dev:web": "turbo run dev --filter=web",
+    "dev:web-turbo": "turbo run dev --filter=web -- --turbo",
     "lint": "turbo run lint",
+    "format": "prettier --write \"**/*.{js,jsx,ts,tsx,css}\" --experimental-cli",
+    "format:check": "prettier --check \"**/*.{js,jsx,ts,tsx,css}\" --experimental-cli",
     "test": "turbo run test",
     "release": "dotenv -e ../.env -- release-it",
     "prepare": "husky"
   },
   "devDependencies": {
-    "@release-it/bumper": "^7.0.1",
+    "@release-it/bumper": "^7.0.5",
     "braces": "3.0.3",
     "dotenv-cli": "^7.4.2",
     "husky": "^9.0.11",
-    "prettier": "^3.3.3",
-    "release-it": "^18.1.2",
-    "turbo": "^1.13.4"
+    "prettier": "^3.6.2",
+    "release-it": "^19.0.3",
+    "turbo": "^2.5.5"
   },
   "release-it": {
     "git": {
@@ -86,7 +89,10 @@
   "pnpm": {
     "overrides": {
       "nanoid": "^3.3.8",
-      "katex": "^0.16.21"
+      "katex": "^0.16.21",
+      "tar-fs": "^2.1.2",
+      "rollup@^4.0.0": "^4.22.4",
+      "@types/node-fetch": "^2.6.13"
     },
     "patchedDependencies": {
       "next-auth@4.24.11": "patches/next-auth@4.24.11.patch"

packages/config-eslint/library.js

@@ -35,5 +35,13 @@ module.exports = {
     {
       files: ["*.js?(x)", "*.ts?(x)"],
     },
+    {
+      files: ["*.ts", "*.mts", "*.cts", "*.tsx"],
+      // no-undef doesn't make sense in TS, see:
+      // https://typescript-eslint.io/troubleshooting/faqs/eslint/#i-get-errors-from-the-no-undef-rule-about-global-variables-not-being-defined-even-though-there-are-no-typescript-errors
+      rules: {
+        "no-undef": "off",
+      },
+    },
   ],
 };

packages/config-eslint/package.json

@@ -13,7 +13,7 @@
     "@vercel/style-guide": "^6.0.0",
     "eslint-config-next": "^14.2.15",
     "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^1.13.4",
+    "eslint-config-turbo": "^2.5.5",
     "eslint-plugin-only-warn": "^1.1.0",
     "typescript": "^5.4.5"
   }

packages/shared/clickhouse/migrations/clustered/0019_analytics_traces.down.sql

@@ -0,0 +1 @@
+DROP VIEW IF EXISTS analytics_traces ON CLUSTER default;

packages/shared/clickhouse/migrations/clustered/0019_analytics_traces.up.sql

@@ -0,0 +1,15 @@
+CREATE VIEW analytics_traces ON CLUSTER default AS
+SELECT
+    project_id,
+    toStartOfHour(timestamp) AS hour,
+    uniq(id) AS countTraces,
+    max(user_id IS NOT NULL) AS hasUsers,
+    max(session_id IS NOT NULL) AS hasSessions,
+    max(if(environment != 'default', 1, 0)) AS hasEnvironments,
+    max(length(tags) > 0) AS hasTags
+FROM
+    traces
+WHERE toStartOfHour(timestamp) <= toStartOfHour(subtractHours(now(), 1))
+GROUP BY
+    project_id,
+    hour;

packages/shared/clickhouse/migrations/clustered/0020_analytics_observations.down.sql

@@ -0,0 +1 @@
+DROP VIEW IF EXISTS analytics_observations ON CLUSTER default;

packages/shared/clickhouse/migrations/clustered/0020_analytics_observations.up.sql

@@ -0,0 +1,18 @@
+CREATE VIEW analytics_observations ON CLUSTER default AS
+SELECT
+    project_id,
+    type,
+    toStartOfHour(start_time) AS hour,
+    uniq(id) AS countObservations,
+    max(level != 'DEFAULT') AS hasLevel,
+    max(provided_model_name IS NOT NULL) AS hasProvidedModelName,
+    max(length(provided_usage_details) > 0) AS hasProvidedUsageDetails,
+    max(length(provided_cost_details) > 0) AS hasProvidedCostDetails,
+    max(prompt_name IS NOT NULL) AS hasPromptName
+FROM
+    observations
+WHERE toStartOfHour(start_time) <= toStartOfHour(subtractHours(now(), 1))
+GROUP BY
+    project_id,
+    type,
+    hour;

packages/shared/clickhouse/migrations/clustered/0021_analytics_scores.down.sql

@@ -0,0 +1 @@
+DROP VIEW IF EXISTS analytics_scores ON CLUSTER default;

packages/shared/clickhouse/migrations/clustered/0021_analytics_scores.up.sql

@@ -0,0 +1,21 @@
+CREATE VIEW analytics_scores ON CLUSTER default AS
+SELECT
+    project_id,
+    toStartOfHour(timestamp) AS hour,
+    uniq(id) AS countScores,
+    max(source = 'ANNOTATION') AS hasAnnotation,
+    max(source = 'API') AS hasApi,
+    max(source = 'EVAL') AS hasEval,
+    max(observation_id IS NOT NULL) AS hasObservationScore,
+    max(session_id IS NOT NULL) AS hasSessionScore,
+    max(dataset_run_id IS NOT NULL) AS hasDatasetRunScore,
+    max(data_type = 'BOOLEAN') AS hasBoolScore,
+    max(data_type = 'NUMERIC') AS hasNumericScore,
+    max(data_type = 'CATEGORICAL') AS hasCategoricalScore,
+    max(comment IS NOT NULL) AS hasComment
+FROM
+    scores
+WHERE toStartOfHour(timestamp) <= toStartOfHour(subtractHours(now(), 1))
+GROUP BY
+    project_id,
+    hour;

packages/shared/clickhouse/migrations/clustered/0022_dataset_run_items.down.sql

@@ -0,0 +1 @@
+DROP TABLE dataset_run_items ON CLUSTER default;

packages/shared/clickhouse/migrations/clustered/0022_dataset_run_items.up.sql

@@ -0,0 +1,36 @@
+CREATE TABLE dataset_run_items ON CLUSTER default (
+    -- primary identifiers
+    `id` String,
+    `project_id` String,
+    `dataset_run_id` String,
+    `dataset_item_id` String,
+    `dataset_id` String,
+    `trace_id` String,
+    `observation_id` Nullable(String),
+
+    -- error field
+    `error` Nullable(String),
+
+     -- timestamps
+    `created_at` DateTime64(3) DEFAULT now(),
+    `updated_at` DateTime64(3) DEFAULT now(),
+
+    -- denormalized immutable dataset run fields
+    `dataset_run_name` String,
+    `dataset_run_description` Nullable(String),
+    `dataset_run_metadata` Map(LowCardinality(String), String),
+    `dataset_run_created_at` DateTime64(3),
+
+    -- denormalized dataset item fields (mutable, but snapshots are relevant)
+    `dataset_item_input` Nullable(String) CODEC(ZSTD(3)), -- json
+    `dataset_item_expected_output` Nullable(String) CODEC(ZSTD(3)), -- json
+    `dataset_item_metadata` Map(LowCardinality(String), String),
+
+    -- clickhouse engine fields
+    `event_ts` DateTime64(3),
+    `is_deleted` UInt8,
+
+    -- For dataset item lookups
+    INDEX idx_dataset_item dataset_item_id TYPE bloom_filter(0.001) GRANULARITY 1,
+) ENGINE = ReplacingMergeTree(event_ts, is_deleted)
+ORDER BY (project_id, dataset_id, dataset_run_id, id);

packages/shared/clickhouse/migrations/clustered/0023_traces_aggregating_merge_trees.down.sql

@@ -0,0 +1,12 @@
+-- Drop materialized views first
+DROP VIEW IF EXISTS traces_30d_amt_mv ON CLUSTER default;
+DROP VIEW IF EXISTS traces_7d_amt_mv ON CLUSTER default;
+DROP VIEW IF EXISTS traces_all_amt_mv ON CLUSTER default;
+
+-- Drop AMT tables
+DROP TABLE IF EXISTS traces_30d_amt ON CLUSTER default;
+DROP TABLE IF EXISTS traces_7d_amt ON CLUSTER default;
+DROP TABLE IF EXISTS traces_all_amt ON CLUSTER default;
+
+-- Drop the Null table
+DROP TABLE IF EXISTS traces_null ON CLUSTER default;

packages/shared/clickhouse/migrations/clustered/0023_traces_aggregating_merge_trees.up.sql

@@ -0,0 +1,300 @@
+-- Create a Null table that serves as a trigger for all materialized views.
+-- We use a Null engine here to avoid storing intermediate results and save on storage.
+CREATE TABLE traces_null ON CLUSTER default
+(
+    -- Identifiers
+    `project_id`      String,
+    `id`              String,
+    `start_time`      DateTime64(3),
+    `end_time`        Nullable(DateTime64(3)),
+    `name`            Nullable(String),
+
+    -- Metadata properties
+    `metadata`        Map(LowCardinality(String), String),
+    `user_id`         Nullable(String),
+    `session_id`      Nullable(String),
+    `environment`     String,
+    `tags`            Array(String),
+    `version`         Nullable(String),
+    `release`         Nullable(String),
+
+    -- UI properties - We make them nullable to prevent absent values being interpreted as overwrites.
+    `bookmarked`      Nullable(Bool),
+    `public`          Nullable(Bool),
+
+    -- Aggregations -- DO NOT USE
+    `observation_ids` Array(String),
+    `score_ids`       Array(String),
+    `cost_details`    Map(String, Decimal64(12)),
+    `usage_details`   Map(String, UInt64),
+    -- TODO: Do we want to aggregate/collect `levels` seen within the trace?
+
+    -- Input/Output
+    `input`           String,
+    `output`          String,
+
+    `created_at`      DateTime64(3),
+    `updated_at`      DateTime64(3),
+    `event_ts`        DateTime64(3)
+) Engine = Null();
+
+-- Create the all AMT
+CREATE TABLE traces_all_amt ON CLUSTER default
+(    
+    -- Identifiers
+    `project_id`         String,
+    `id`                 String,
+    `timestamp`          SimpleAggregateFunction(min, DateTime64(3)),  -- Backward compatibility: redundant with start_time
+    `start_time`         SimpleAggregateFunction(min, DateTime64(3)),
+    `end_time`           SimpleAggregateFunction(max, Nullable(DateTime64(3))),
+    `name`               SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- Metadata properties
+    `metadata`           SimpleAggregateFunction(maxMap, Map(String, String)),
+    `user_id`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `session_id`         SimpleAggregateFunction(anyLast, Nullable(String)),
+    `environment`        SimpleAggregateFunction(anyLast, String),
+    `tags`               SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `version`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `release`            SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- UI properties
+    `bookmarked`         AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+    `public`             AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+
+    -- Aggregations -- DO NOT USE
+    `observation_ids`    SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `score_ids`          SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `cost_details`       SimpleAggregateFunction(sumMap, Map(String, Decimal(38, 12))),
+    `usage_details`      SimpleAggregateFunction(sumMap, Map(String, UInt64)),
+
+    -- Input/Output -> prefer correctness via argMax
+    `input`       AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+    `output`      AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+
+    `created_at`         SimpleAggregateFunction(min, DateTime64(3)),
+    `updated_at`         SimpleAggregateFunction(max, DateTime64(3)),
+
+    -- Indexes
+    INDEX idx_trace_id id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_user_id user_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_session_id session_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_name name TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_version version TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_release release TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_tags tags TYPE bloom_filter(0.001) GRANULARITY 1
+) Engine = AggregatingMergeTree()
+      ORDER BY (project_id, id);
+
+-- Create materialized view for all_amt
+CREATE MATERIALIZED VIEW IF NOT EXISTS traces_all_amt_mv ON CLUSTER default TO traces_all_amt AS
+SELECT
+    -- Identifiers
+    tn.project_id                                                                              as project_id,
+    tn.id                                                                                      as id,
+    min(tn.start_time)                                                                         as timestamp,  -- Backward compatibility: redundant with start_time
+    min(tn.start_time)                                                                         as start_time,
+    max(coalesce(tn.end_time, tn.start_time))                                                  as end_time,
+    anyLast(tn.name)                                                                           as name,
+
+    -- Metadata properties
+    maxMap(tn.metadata)                                                                        as metadata,
+    anyLast(tn.user_id)                                                                        as user_id,
+    anyLast(tn.session_id)                                                                     as session_id,
+    anyLast(tn.environment)                                                                    as environment,
+    groupUniqArrayArray(tn.tags)                                                               as tags,
+    anyLast(tn.version)                                                                        as version,
+    anyLast(tn.release)                                                                        as release,
+
+    -- UI properties
+    argMaxState(tn.bookmarked, if(tn.bookmarked is not null, tn.event_ts, toDateTime64(0, 3))) as bookmarked,
+    argMaxState(tn.public, if(tn.public is not null, tn.event_ts, toDateTime64(0, 3)))         as public,
+
+    -- Aggregations -- DO NOT USE
+    groupUniqArrayArray(tn.observation_ids)                                                    as observation_ids,
+    groupUniqArrayArray(tn.score_ids)                                                          as score_ids,
+    sumMap(tn.cost_details)                                                                    as cost_details,
+    sumMap(tn.usage_details)                                                                   as usage_details,
+
+    -- Input/Output
+    argMaxState(tn.input, if(tn.input <> '', tn.event_ts, toDateTime64(0, 3)))                 as input,
+    argMaxState(tn.output, if(tn.output <> '', tn.event_ts, toDateTime64(0, 3)))               as output,
+
+    min(tn.created_at)                                                                         as created_at,
+    max(tn.updated_at)                                                                         as updated_at
+FROM traces_null tn
+GROUP BY project_id, id;
+
+-- Create the 7-day TTL AMT
+CREATE TABLE traces_7d_amt ON CLUSTER default
+(
+    -- Identifiers
+    `project_id`         String,
+    `id`                 String,
+    `timestamp`          SimpleAggregateFunction(min, DateTime64(3)),  -- Backward compatibility: redundant with start_time
+    `start_time`         SimpleAggregateFunction(min, DateTime64(3)),
+    `end_time`           SimpleAggregateFunction(max, Nullable(DateTime64(3))),
+    `name`               SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- Metadata properties
+    `metadata`           SimpleAggregateFunction(maxMap, Map(String, String)),
+    `user_id`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `session_id`         SimpleAggregateFunction(anyLast, Nullable(String)),
+    `environment`        SimpleAggregateFunction(anyLast, String),
+    `tags`               SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `version`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `release`            SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- UI properties
+    `bookmarked`         AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+    `public`             AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+
+    -- Aggregations -- DO NOT USE
+    `observation_ids`    SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `score_ids`          SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `cost_details`       SimpleAggregateFunction(sumMap, Map(String, Decimal(38, 12))),
+    `usage_details`      SimpleAggregateFunction(sumMap, Map(String, UInt64)),
+
+    -- Input/Output -> prefer correctness via argMax
+    `input`       AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+    `output`      AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+
+    `created_at`         SimpleAggregateFunction(min, DateTime64(3)),
+    `updated_at`         SimpleAggregateFunction(max, DateTime64(3)),
+
+    -- Indexes
+    INDEX idx_user_id user_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_session_id session_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_name name TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_version version TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_release release TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_tags tags TYPE bloom_filter(0.001) GRANULARITY 1
+) Engine = AggregatingMergeTree()
+    ORDER BY (project_id, id)
+    TTL toDate(start_time) + INTERVAL 7 DAY;
+
+-- Create materialized view for 7d_amt
+CREATE MATERIALIZED VIEW IF NOT EXISTS traces_7d_amt_mv ON CLUSTER default TO traces_7d_amt AS
+SELECT
+    -- Identifiers
+    tn.project_id                                                                              as project_id,
+    tn.id                                                                                      as id,
+    min(tn.start_time)                                                                         as timestamp,  -- Backward compatibility: redundant with start_time
+    min(tn.start_time)                                                                         as start_time,
+    max(coalesce(tn.end_time, tn.start_time))                                                  as end_time,
+    anyLast(tn.name)                                                                           as name,
+
+    -- Metadata properties
+    maxMap(tn.metadata)                                                                        as metadata,
+    anyLast(tn.user_id)                                                                        as user_id,
+    anyLast(tn.session_id)                                                                     as session_id,
+    anyLast(tn.environment)                                                                    as environment,
+    groupUniqArrayArray(tn.tags)                                                               as tags,
+    anyLast(tn.version)                                                                        as version,
+    anyLast(tn.release)                                                                        as release,
+
+    -- UI properties
+    argMaxState(tn.bookmarked, if(tn.bookmarked is not null, tn.event_ts, toDateTime64(0, 3))) as bookmarked,
+    argMaxState(tn.public, if(tn.public is not null, tn.event_ts, toDateTime64(0, 3)))         as public,
+
+    -- Aggregations -- DO NOT USE
+    groupUniqArrayArray(tn.observation_ids)                                                    as observation_ids,
+    groupUniqArrayArray(tn.score_ids)                                                          as score_ids,
+    sumMap(tn.cost_details)                                                                    as cost_details,
+    sumMap(tn.usage_details)                                                                   as usage_details,
+
+    -- Input/Output
+    argMaxState(tn.input, if(tn.input <> '', tn.event_ts, toDateTime64(0, 3)))                 as input,
+    argMaxState(tn.output, if(tn.output <> '', tn.event_ts, toDateTime64(0, 3)))               as output,
+
+    min(tn.created_at)                                                                         as created_at,
+    max(tn.updated_at)                                                                         as updated_at
+FROM traces_null tn
+GROUP BY project_id, id;
+
+-- Create the 30-day TTL AMT
+CREATE TABLE traces_30d_amt ON CLUSTER default
+(
+    -- Identifiers
+    `project_id`         String,
+    `id`                 String,
+    `timestamp`          SimpleAggregateFunction(min, DateTime64(3)),  -- Backward compatibility: redundant with start_time
+    `start_time`         SimpleAggregateFunction(min, DateTime64(3)),
+    `end_time`           SimpleAggregateFunction(max, Nullable(DateTime64(3))),
+    `name`               SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- Metadata properties
+    `metadata`           SimpleAggregateFunction(maxMap, Map(String, String)),
+    `user_id`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `session_id`         SimpleAggregateFunction(anyLast, Nullable(String)),
+    `environment`        SimpleAggregateFunction(anyLast, String),
+    `tags`               SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `version`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `release`            SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- UI properties
+    `bookmarked`         AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+    `public`             AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+
+    -- Aggregations -- DO NOT USE
+    `observation_ids`    SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `score_ids`          SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `cost_details`       SimpleAggregateFunction(sumMap, Map(String, Decimal(38, 12))),
+    `usage_details`      SimpleAggregateFunction(sumMap, Map(String, UInt64)),
+
+    -- Input/Output -> prefer correctness via argMax
+    `input`       AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+    `output`      AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+
+    `created_at`         SimpleAggregateFunction(min, DateTime64(3)),
+    `updated_at`         SimpleAggregateFunction(max, DateTime64(3)),
+
+    -- Indexes
+    INDEX idx_user_id user_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_session_id session_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_name name TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_version version TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_release release TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_tags tags TYPE bloom_filter(0.001) GRANULARITY 1
+) Engine = AggregatingMergeTree()
+    ORDER BY (project_id, id)
+    TTL toDate(start_time) + INTERVAL 30 DAY;
+
+-- Create materialized view for 30d_amt
+CREATE MATERIALIZED VIEW IF NOT EXISTS traces_30d_amt_mv ON CLUSTER default TO traces_30d_amt AS
+SELECT
+    -- Identifiers
+    tn.project_id                                                                              as project_id,
+    tn.id                                                                                      as id,
+    min(tn.start_time)                                                                         as timestamp,  -- Backward compatibility: redundant with start_time
+    min(tn.start_time)                                                                         as start_time,
+    max(coalesce(tn.end_time, tn.start_time))                                                  as end_time,
+    anyLast(tn.name)                                                                           as name,
+
+    -- Metadata properties
+    maxMap(tn.metadata)                                                                        as metadata,
+    anyLast(tn.user_id)                                                                        as user_id,
+    anyLast(tn.session_id)                                                                     as session_id,
+    anyLast(tn.environment)                                                                    as environment,
+    groupUniqArrayArray(tn.tags)                                                               as tags,
+    anyLast(tn.version)                                                                        as version,
+    anyLast(tn.release)                                                                        as release,
+
+    -- UI properties
+    argMaxState(tn.bookmarked, if(tn.bookmarked is not null, tn.event_ts, toDateTime64(0, 3))) as bookmarked,
+    argMaxState(tn.public, if(tn.public is not null, tn.event_ts, toDateTime64(0, 3)))         as public,
+
+    -- Aggregations -- DO NOT USE
+    groupUniqArrayArray(tn.observation_ids)                                                    as observation_ids,
+    groupUniqArrayArray(tn.score_ids)                                                          as score_ids,
+    sumMap(tn.cost_details)                                                                    as cost_details,
+    sumMap(tn.usage_details)                                                                   as usage_details,
+
+    -- Input/Output
+    argMaxState(tn.input, if(tn.input <> '', tn.event_ts, toDateTime64(0, 3)))                 as input,
+    argMaxState(tn.output, if(tn.output <> '', tn.event_ts, toDateTime64(0, 3)))               as output,
+
+    min(tn.created_at)                                                                         as created_at,
+    max(tn.updated_at)                                                                         as updated_at
+FROM traces_null tn
+GROUP BY project_id, id;

packages/shared/clickhouse/migrations/unclustered/0006_add_user_id_index.down.sql

@@ -1 +1 @@
-ALTER TABLE traces ON CLUSTER default DROP INDEX IF EXISTS idx_user_id;
+ALTER TABLE traces DROP INDEX IF EXISTS idx_user_id;

packages/shared/clickhouse/migrations/unclustered/0019_analytics_traces.down.sql

@@ -0,0 +1 @@
+DROP VIEW IF EXISTS analytics_traces;

packages/shared/clickhouse/migrations/unclustered/0019_analytics_traces.up.sql

@@ -0,0 +1,15 @@
+CREATE VIEW analytics_traces AS
+SELECT
+    project_id,
+    toStartOfHour(timestamp) AS hour,
+    uniq(id) AS countTraces,
+    max(user_id IS NOT NULL) AS hasUsers,
+    max(session_id IS NOT NULL) AS hasSessions,
+    max(if(environment != 'default', 1, 0)) AS hasEnvironments,
+    max(length(tags) > 0) AS hasTags
+FROM
+    traces
+WHERE toStartOfHour(timestamp) <= toStartOfHour(subtractHours(now(), 1))
+GROUP BY
+    project_id,
+    hour;

packages/shared/clickhouse/migrations/unclustered/0020_analytics_observations.down.sql

@@ -0,0 +1 @@
+DROP VIEW IF EXISTS analytics_observations;

packages/shared/clickhouse/migrations/unclustered/0020_analytics_observations.up.sql

@@ -0,0 +1,18 @@
+CREATE VIEW analytics_observations AS
+SELECT
+    project_id,
+    type,
+    toStartOfHour(start_time) AS hour,
+    uniq(id) AS countObservations,
+    max(level != 'DEFAULT') AS hasLevel,
+    max(provided_model_name IS NOT NULL) AS hasProvidedModelName,
+    max(length(provided_usage_details) > 0) AS hasProvidedUsageDetails,
+    max(length(provided_cost_details) > 0) AS hasProvidedCostDetails,
+    max(prompt_name IS NOT NULL) AS hasPromptName
+FROM
+    observations
+WHERE toStartOfHour(start_time) <= toStartOfHour(subtractHours(now(), 1))
+GROUP BY
+    project_id,
+    type,
+    hour;

packages/shared/clickhouse/migrations/unclustered/0021_analytics_scores.down.sql

@@ -0,0 +1 @@
+DROP VIEW IF EXISTS analytics_scores;

packages/shared/clickhouse/migrations/unclustered/0021_analytics_scores.up.sql

@@ -0,0 +1,21 @@
+CREATE VIEW analytics_scores AS
+SELECT
+    project_id,
+    toStartOfHour(timestamp) AS hour,
+    uniq(id) AS countScores,
+    max(source = 'ANNOTATION') AS hasAnnotation,
+    max(source = 'API') AS hasApi,
+    max(source = 'EVAL') AS hasEval,
+    max(observation_id IS NOT NULL) AS hasObservationScore,
+    max(session_id IS NOT NULL) AS hasSessionScore,
+    max(dataset_run_id IS NOT NULL) AS hasDatasetRunScore,
+    max(data_type = 'BOOLEAN') AS hasBoolScore,
+    max(data_type = 'NUMERIC') AS hasNumericScore,
+    max(data_type = 'CATEGORICAL') AS hasCategoricalScore,
+    max(comment IS NOT NULL) AS hasComment
+FROM
+    scores
+WHERE toStartOfHour(timestamp) <= toStartOfHour(subtractHours(now(), 1))
+GROUP BY
+    project_id,
+    hour;

packages/shared/clickhouse/migrations/unclustered/0022_dataset_run_items.down.sql

@@ -0,0 +1 @@
+DROP TABLE dataset_run_items;

packages/shared/clickhouse/migrations/unclustered/0022_dataset_run_items.up.sql

@@ -0,0 +1,36 @@
+CREATE TABLE dataset_run_items (
+    -- primary identifiers
+    `id` String,
+    `project_id` String,
+    `dataset_run_id` String,
+    `dataset_item_id` String,
+    `dataset_id` String,
+    `trace_id` String,
+    `observation_id` Nullable(String),
+
+    -- error field
+    `error` Nullable(String),
+
+     -- timestamps
+    `created_at` DateTime64(3) DEFAULT now(),
+    `updated_at` DateTime64(3) DEFAULT now(),
+
+    -- denormalized immutable dataset run fields
+    `dataset_run_name` String,
+    `dataset_run_description` Nullable(String),
+    `dataset_run_metadata` Map(LowCardinality(String), String),
+    `dataset_run_created_at` DateTime64(3),
+
+    -- denormalized dataset item fields (mutable, but snapshots are relevant)
+    `dataset_item_input` Nullable(String) CODEC(ZSTD(3)), -- json
+    `dataset_item_expected_output` Nullable(String) CODEC(ZSTD(3)), -- json
+    `dataset_item_metadata` Map(LowCardinality(String), String),
+
+    -- clickhouse engine fields
+    `event_ts` DateTime64(3),
+    `is_deleted` UInt8,
+
+    -- For dataset item lookups
+    INDEX idx_dataset_item dataset_item_id TYPE bloom_filter(0.001) GRANULARITY 1,
+) ENGINE = ReplacingMergeTree(event_ts, is_deleted)
+ORDER BY (project_id, dataset_id, dataset_run_id, id);

packages/shared/clickhouse/migrations/unclustered/0023_traces_aggregating_merge_trees.down.sql

@@ -0,0 +1,12 @@
+-- Drop materialized views first
+DROP VIEW IF EXISTS traces_30d_amt_mv;
+DROP VIEW IF EXISTS traces_7d_amt_mv;
+DROP VIEW IF EXISTS traces_all_amt_mv;
+
+-- Drop AMT tables
+DROP TABLE IF EXISTS traces_30d_amt;
+DROP TABLE IF EXISTS traces_7d_amt;
+DROP TABLE IF EXISTS traces_all_amt;
+
+-- Drop the Null table
+DROP TABLE IF EXISTS traces_null;

packages/shared/clickhouse/migrations/unclustered/0023_traces_aggregating_merge_trees.up.sql

@@ -0,0 +1,300 @@
+-- Create a Null table that serves as a trigger for all materialized views.
+-- We use a Null engine here to avoid storing intermediate results and save on storage.
+CREATE TABLE traces_null
+(
+    -- Identifiers
+    `project_id`      String,
+    `id`              String,
+    `start_time`      DateTime64(3),
+    `end_time`        Nullable(DateTime64(3)),
+    `name`            Nullable(String),
+
+    -- Metadata properties
+    `metadata`        Map(LowCardinality(String), String),
+    `user_id`         Nullable(String),
+    `session_id`      Nullable(String),
+    `environment`     String,
+    `tags`            Array(String),
+    `version`         Nullable(String),
+    `release`         Nullable(String),
+
+    -- UI properties - We make them nullable to prevent absent values being interpreted as overwrites.
+    `bookmarked`      Nullable(Bool),
+    `public`          Nullable(Bool),
+
+    -- Aggregations
+    `observation_ids` Array(String),
+    `score_ids`       Array(String),
+    `cost_details`    Map(String, Decimal64(12)),
+    `usage_details`   Map(String, UInt64),
+    -- TODO: Do we want to aggregate/collect `levels` seen within the trace?
+
+    -- Input/Output
+    `input`           String,
+    `output`          String,
+
+    `created_at`      DateTime64(3),
+    `updated_at`      DateTime64(3),
+    `event_ts`        DateTime64(3)
+) Engine = Null();
+
+-- Create the all AMT
+CREATE TABLE traces_all_amt
+(    
+    -- Identifiers
+    `project_id`         String,
+    `id`                 String,
+    `timestamp`          SimpleAggregateFunction(min, DateTime64(3)),  -- Backward compatibility: redundant with start_time
+    `start_time`         SimpleAggregateFunction(min, DateTime64(3)),
+    `end_time`           SimpleAggregateFunction(max, Nullable(DateTime64(3))),
+    `name`               SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- Metadata properties
+    `metadata`           SimpleAggregateFunction(maxMap, Map(String, String)),
+    `user_id`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `session_id`         SimpleAggregateFunction(anyLast, Nullable(String)),
+    `environment`        SimpleAggregateFunction(anyLast, String),
+    `tags`               SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `version`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `release`            SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- UI properties
+    `bookmarked`         AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+    `public`             AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+
+    -- Aggregations
+    `observation_ids`    SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `score_ids`          SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `cost_details`       SimpleAggregateFunction(sumMap, Map(String, Decimal(38, 12))),
+    `usage_details`      SimpleAggregateFunction(sumMap, Map(String, UInt64)),
+
+    -- Input/Output -> prefer correctness via argMax
+    `input`       AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+    `output`      AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+
+    `created_at`         SimpleAggregateFunction(min, DateTime64(3)),
+    `updated_at`         SimpleAggregateFunction(max, DateTime64(3)),
+
+    -- Indexes
+    INDEX idx_trace_id id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_user_id user_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_session_id session_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_name name TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_version version TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_release release TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_tags tags TYPE bloom_filter(0.001) GRANULARITY 1
+) Engine = AggregatingMergeTree()
+      ORDER BY (project_id, id);
+
+-- Create materialized view for all_amt
+CREATE MATERIALIZED VIEW IF NOT EXISTS traces_all_amt_mv TO traces_all_amt AS
+SELECT
+    -- Identifiers
+    tn.project_id                                                                              as project_id,
+    tn.id                                                                                      as id,
+    min(tn.start_time)                                                                         as timestamp,  -- Backward compatibility: redundant with start_time
+    min(tn.start_time)                                                                         as start_time,
+    max(coalesce(tn.end_time, tn.start_time))                                                  as end_time,
+    anyLast(tn.name)                                                                           as name,
+
+    -- Metadata properties
+    maxMap(tn.metadata)                                                                        as metadata,
+    anyLast(tn.user_id)                                                                        as user_id,
+    anyLast(tn.session_id)                                                                     as session_id,
+    anyLast(tn.environment)                                                                    as environment,
+    groupUniqArrayArray(tn.tags)                                                               as tags,
+    anyLast(tn.version)                                                                        as version,
+    anyLast(tn.release)                                                                        as release,
+
+    -- UI properties
+    argMaxState(tn.bookmarked, if(tn.bookmarked is not null, tn.event_ts, toDateTime64(0, 3))) as bookmarked,
+    argMaxState(tn.public, if(tn.public is not null, tn.event_ts, toDateTime64(0, 3)))         as public,
+
+    -- Aggregations
+    groupUniqArrayArray(tn.observation_ids)                                                    as observation_ids,
+    groupUniqArrayArray(tn.score_ids)                                                          as score_ids,
+    sumMap(tn.cost_details)                                                                    as cost_details,
+    sumMap(tn.usage_details)                                                                   as usage_details,
+
+    -- Input/Output
+    argMaxState(tn.input, if(tn.input <> '', tn.event_ts, toDateTime64(0, 3)))                 as input,
+    argMaxState(tn.output, if(tn.output <> '', tn.event_ts, toDateTime64(0, 3)))               as output,
+
+    min(tn.created_at)                                                                         as created_at,
+    max(tn.updated_at)                                                                         as updated_at
+FROM traces_null tn
+GROUP BY project_id, id;
+
+-- Create the 7-day TTL AMT
+CREATE TABLE traces_7d_amt
+(
+    -- Identifiers
+    `project_id`         String,
+    `id`                 String,
+    `timestamp`          SimpleAggregateFunction(min, DateTime64(3)),  -- Backward compatibility: redundant with start_time
+    `start_time`         SimpleAggregateFunction(min, DateTime64(3)),
+    `end_time`           SimpleAggregateFunction(max, Nullable(DateTime64(3))),
+    `name`               SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- Metadata properties
+    `metadata`           SimpleAggregateFunction(maxMap, Map(String, String)),
+    `user_id`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `session_id`         SimpleAggregateFunction(anyLast, Nullable(String)),
+    `environment`        SimpleAggregateFunction(anyLast, String),
+    `tags`               SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `version`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `release`            SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- UI properties
+    `bookmarked`         AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+    `public`             AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+
+    -- Aggregations
+    `observation_ids`    SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `score_ids`          SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `cost_details`       SimpleAggregateFunction(sumMap, Map(String, Decimal(38, 12))),
+    `usage_details`      SimpleAggregateFunction(sumMap, Map(String, UInt64)),
+
+    -- Input/Output -> prefer correctness via argMax
+    `input`       AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+    `output`      AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+
+    `created_at`         SimpleAggregateFunction(min, DateTime64(3)),
+    `updated_at`         SimpleAggregateFunction(max, DateTime64(3)),
+
+    -- Indexes
+    INDEX idx_user_id user_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_session_id session_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_name name TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_version version TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_release release TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_tags tags TYPE bloom_filter(0.001) GRANULARITY 1
+) Engine = AggregatingMergeTree()
+    ORDER BY (project_id, id)
+    TTL toDate(start_time) + INTERVAL 7 DAY;
+
+-- Create materialized view for 7d_amt
+CREATE MATERIALIZED VIEW IF NOT EXISTS traces_7d_amt_mv TO traces_7d_amt AS
+SELECT
+    -- Identifiers
+    tn.project_id                                                                              as project_id,
+    tn.id                                                                                      as id,
+    min(tn.start_time)                                                                         as timestamp,  -- Backward compatibility: redundant with start_time
+    min(tn.start_time)                                                                         as start_time,
+    max(coalesce(tn.end_time, tn.start_time))                                                  as end_time,
+    anyLast(tn.name)                                                                           as name,
+
+    -- Metadata properties
+    maxMap(tn.metadata)                                                                        as metadata,
+    anyLast(tn.user_id)                                                                        as user_id,
+    anyLast(tn.session_id)                                                                     as session_id,
+    anyLast(tn.environment)                                                                    as environment,
+    groupUniqArrayArray(tn.tags)                                                               as tags,
+    anyLast(tn.version)                                                                        as version,
+    anyLast(tn.release)                                                                        as release,
+
+    -- UI properties
+    argMaxState(tn.bookmarked, if(tn.bookmarked is not null, tn.event_ts, toDateTime64(0, 3))) as bookmarked,
+    argMaxState(tn.public, if(tn.public is not null, tn.event_ts, toDateTime64(0, 3)))         as public,
+
+    -- Aggregations
+    groupUniqArrayArray(tn.observation_ids)                                                    as observation_ids,
+    groupUniqArrayArray(tn.score_ids)                                                          as score_ids,
+    sumMap(tn.cost_details)                                                                    as cost_details,
+    sumMap(tn.usage_details)                                                                   as usage_details,
+
+    -- Input/Output
+    argMaxState(tn.input, if(tn.input <> '', tn.event_ts, toDateTime64(0, 3)))                 as input,
+    argMaxState(tn.output, if(tn.output <> '', tn.event_ts, toDateTime64(0, 3)))               as output,
+
+    min(tn.created_at)                                                                         as created_at,
+    max(tn.updated_at)                                                                         as updated_at
+FROM traces_null tn
+GROUP BY project_id, id;
+
+-- Create the 30-day TTL AMT
+CREATE TABLE traces_30d_amt
+(
+    -- Identifiers
+    `project_id`         String,
+    `id`                 String,
+    `timestamp`          SimpleAggregateFunction(min, DateTime64(3)),  -- Backward compatibility: redundant with start_time
+    `start_time`         SimpleAggregateFunction(min, DateTime64(3)),
+    `end_time`           SimpleAggregateFunction(max, Nullable(DateTime64(3))),
+    `name`               SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- Metadata properties
+    `metadata`           SimpleAggregateFunction(maxMap, Map(String, String)),
+    `user_id`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `session_id`         SimpleAggregateFunction(anyLast, Nullable(String)),
+    `environment`        SimpleAggregateFunction(anyLast, String),
+    `tags`               SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `version`            SimpleAggregateFunction(anyLast, Nullable(String)),
+    `release`            SimpleAggregateFunction(anyLast, Nullable(String)),
+
+    -- UI properties
+    `bookmarked`         AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+    `public`             AggregateFunction(argMax, Nullable(Bool), DateTime64(3)),
+
+    -- Aggregations
+    `observation_ids`    SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `score_ids`          SimpleAggregateFunction(groupUniqArrayArray, Array(String)),
+    `cost_details`       SimpleAggregateFunction(sumMap, Map(String, Decimal(38, 12))),
+    `usage_details`      SimpleAggregateFunction(sumMap, Map(String, UInt64)),
+
+    -- Input/Output -> prefer correctness via argMax
+    `input`       AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+    `output`      AggregateFunction(argMax, String, DateTime64(3)) CODEC (ZSTD(3)),
+
+    `created_at`         SimpleAggregateFunction(min, DateTime64(3)),
+    `updated_at`         SimpleAggregateFunction(max, DateTime64(3)),
+
+    -- Indexes
+    INDEX idx_user_id user_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_session_id session_id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_name name TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_version version TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_release release TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_tags tags TYPE bloom_filter(0.001) GRANULARITY 1
+) Engine = AggregatingMergeTree()
+    ORDER BY (project_id, id)
+    TTL toDate(start_time) + INTERVAL 30 DAY;
+
+-- Create materialized view for 30d_amt
+CREATE MATERIALIZED VIEW IF NOT EXISTS traces_30d_amt_mv TO traces_30d_amt AS
+SELECT
+    -- Identifiers
+    tn.project_id                                                                              as project_id,
+    tn.id                                                                                      as id,
+    min(tn.start_time)                                                                         as timestamp,  -- Backward compatibility: redundant with start_time
+    min(tn.start_time)                                                                         as start_time,
+    max(coalesce(tn.end_time, tn.start_time))                                                  as end_time,
+    anyLast(tn.name)                                                                           as name,
+
+    -- Metadata properties
+    maxMap(tn.metadata)                                                                        as metadata,
+    anyLast(tn.user_id)                                                                        as user_id,
+    anyLast(tn.session_id)                                                                     as session_id,
+    anyLast(tn.environment)                                                                    as environment,
+    groupUniqArrayArray(tn.tags)                                                               as tags,
+    anyLast(tn.version)                                                                        as version,
+    anyLast(tn.release)                                                                        as release,
+
+    -- UI properties
+    argMaxState(tn.bookmarked, if(tn.bookmarked is not null, tn.event_ts, toDateTime64(0, 3))) as bookmarked,
+    argMaxState(tn.public, if(tn.public is not null, tn.event_ts, toDateTime64(0, 3)))         as public,
+
+    -- Aggregations
+    groupUniqArrayArray(tn.observation_ids)                                                    as observation_ids,
+    groupUniqArrayArray(tn.score_ids)                                                          as score_ids,
+    sumMap(tn.cost_details)                                                                    as cost_details,
+    sumMap(tn.usage_details)                                                                   as usage_details,
+
+    -- Input/Output
+    argMaxState(tn.input, if(tn.input <> '', tn.event_ts, toDateTime64(0, 3)))                 as input,
+    argMaxState(tn.output, if(tn.output <> '', tn.event_ts, toDateTime64(0, 3)))               as output,
+
+    min(tn.created_at)                                                                         as created_at,
+    max(tn.updated_at)                                                                         as updated_at
+FROM traces_null tn
+GROUP BY project_id, id;

packages/shared/clickhouse/scripts/down.sh

@@ -36,8 +36,12 @@ if [ "$CLICKHOUSE_CLUSTER_ENABLED" == "false" ] ; then
       DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=${CLICKHOUSE_DB}&x-multi-statement=true&x-migrations-table-engine=MergeTree"
   fi
 
-  # Execute the up command
-  migrate -source file://clickhouse/migrations/unclustered -database "$DATABASE_URL" down
+  # If SKIP_CONFIRM is set, automatically answer the confirmation prompt. Otherwise run interactively.
+  if [ "$SKIP_CONFIRM" = "1" ] || [ "$SKIP_CONFIRM" = "true" ]; then
+    printf 'y\n' | migrate -source file://clickhouse/migrations/unclustered -database "$DATABASE_URL" down
+  else
+    migrate -source file://clickhouse/migrations/unclustered -database "$DATABASE_URL" down
+  fi
 else
   if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
       DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=${CLICKHOUSE_DB}&x-multi-statement=true&secure=true&skip_verify=true&x-cluster-name=${CLICKHOUSE_CLUSTER_NAME}&x-migrations-table-engine=ReplicatedMergeTree"
@@ -45,6 +49,10 @@ else
       DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=${CLICKHOUSE_DB}&x-multi-statement=true&x-cluster-name=${CLICKHOUSE_CLUSTER_NAME}&x-migrations-table-engine=ReplicatedMergeTree"
   fi
 
-  # Execute the up command
-  migrate -source file://clickhouse/migrations/clustered -database "$DATABASE_URL" down
+  # If SKIP_CONFIRM is set, automatically answer the confirmation prompt. Otherwise run interactively.
+  if [ "$SKIP_CONFIRM" = "1" ] || [ "$SKIP_CONFIRM" = "true" ]; then
+    printf 'y\n' | migrate -source file://clickhouse/migrations/clustered -database "$DATABASE_URL" down
+  else
+    migrate -source file://clickhouse/migrations/clustered -database "$DATABASE_URL" down
+  fi
 fi

packages/shared/clickhouse/scripts/seed.ts

@@ -1,70 +0,0 @@
-import { prisma } from "../../src/db";
-import { ObservationRecordReadType, redis } from "../../src/server";
-import { prepareClickhouse } from "../../scripts/prepareClickhouse";
-import { createDatasets } from "../../prisma/seed";
-import { queryClickhouse } from "../../src/server/repositories/clickhouse";
-import { convertObservation } from "../../src/server/repositories/observations_converters";
-
-async function main() {
-  try {
-    const projectIds = ["7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"]; // Example project IDs
-    if (
-      await prisma.project.findFirst({
-        where: { id: "239ad00f-562f-411d-af14-831c75ddd875" },
-      })
-    ) {
-      projectIds.push("239ad00f-562f-411d-af14-831c75ddd875");
-    }
-    await prepareClickhouse(projectIds, {
-      numberOfDays: 3,
-      totalObservations: 10000,
-    });
-
-    const project1 = await prisma.project.findFirst({
-      where: { id: "7a88fb47-b4e2-43b8-a06c-a5ce950dc53a" },
-    });
-
-    const project2 =
-      projectIds.length > 1
-        ? await prisma.project.findFirst({
-            where: { id: "239ad00f-562f-411d-af14-831c75ddd875" },
-          })
-        : await prisma.project.findFirst();
-
-    const query = `
-        SELECT *
-        FROM observations o
-        WHERE o.project_id IN ({projectIds: Array(String)})
-        LIMIT 2000;
-      `;
-
-    const res = await queryClickhouse<ObservationRecordReadType>({
-      query,
-      params: {
-        projectIds,
-      },
-    });
-
-    await createDatasets(
-      project1!,
-      project2!,
-      (await Promise.all(res.map(convertObservation))).map((o) => ({
-        ...o,
-        metadata: {},
-        modelParameters: {},
-        input: {},
-        output: {},
-      })),
-    );
-
-    console.log("Clickhouse preparation completed successfully.");
-  } catch (error) {
-    console.error("Error during Clickhouse preparation:", error);
-  } finally {
-    await prisma.$disconnect();
-    redis?.disconnect();
-    console.log("Disconnected from Clickhouse.");
-  }
-}
-
-main();

packages/shared/clickhouse/scripts/up.sh

@@ -5,8 +5,30 @@
 
 # Check if CLICKHOUSE_URL is configured
 if [ -z "${CLICKHOUSE_URL}" ]; then
-  echo "Info: CLICKHOUSE_URL not configured, skipping migration."
-  exit 0
+  echo "Error: CLICKHOUSE_URL is not configured."
+  echo "Please set CLICKHOUSE_URL in your environment variables."
+  exit 1
+fi
+
+# Check if CLICKHOUSE_MIGRATION_URL is configured
+if [ -z "${CLICKHOUSE_MIGRATION_URL}" ]; then
+  echo "Error: CLICKHOUSE_MIGRATION_URL is not configured."
+  echo "Please set CLICKHOUSE_MIGRATION_URL in your environment variables."
+  exit 1
+fi
+
+# Check if CLICKHOUSE_USER is set
+if [ -z "${CLICKHOUSE_USER}" ]; then
+  echo "Error: CLICKHOUSE_USER is not set."
+  echo "Please set CLICKHOUSE_USER in your environment variables."
+  exit 1
+fi
+
+# Check if CLICKHOUSE_PASSWORD is set
+if [ -z "${CLICKHOUSE_PASSWORD}" ]; then
+  echo "Error: CLICKHOUSE_PASSWORD is not set."
+  echo "Please set CLICKHOUSE_PASSWORD in your environment variables."
+  exit 1
 fi
 
 # Check if golang-migrate is installed

packages/shared/package.json

@@ -33,11 +33,12 @@
   "scripts": {
     "build": "tsc",
     "dev": "tsc --watch",
-    "lint": "eslint . --ext .js,.jsx,.ts,.tsx --max-warnings 70",
+    "lint": "eslint . --ext .js,.jsx,.ts,.tsx --max-warnings 0",
     "lint:fix": "eslint . --ext .js,.jsx,.ts,.tsx --fix",
     "db:migrate": "DISABLE_ERD=false dotenv -e ../../.env -- npx prisma migrate dev",
     "db:push": "DISABLE_ERD=false dotenv -e ../../.env -- npx prisma db push",
     "db:reset": "dotenv -e ../../.env npx -- prisma migrate reset",
+    "db:reset:test": "if [ -f ../../.env.test ]; then dotenv -e ../../.env.test -e ../../.env -- npx prisma migrate reset --force; fi",
     "db:deploy": "dotenv -e ../../.env npx -- prisma migrate deploy",
     "db:seed": "dotenv -e ../../.env -- npx prisma db seed",
     "db:generate": "dotenv -e ../../.env -- npx prisma generate",
@@ -47,11 +48,11 @@
     "ch:down": "bash clickhouse/scripts/down.sh",
     "ch:drop": "bash clickhouse/scripts/drop.sh",
     "ch:reset": "pnpm run ch:down && pnpm run ch:up && pnpm run ch:seed",
-    "ch:seed": "dotenv -e ../../.env -- ts-node -r tsconfig-paths/register -r dotenv/config --compiler-options '{\"module\":\"CommonJS\"}' clickhouse/scripts/seed.ts",
-    "load:setup": "dotenv -e ../../.env -- tsx scripts/load-seed.ts"
+    "ch:seed": "dotenv -e ../../.env -- ts-node -r tsconfig-paths/register -r dotenv/config --compiler-options '{\"module\":\"CommonJS\"}' scripts/seeder/seed-clickhouse.ts",
+    "load:setup": "dotenv -e ../../.env -- tsx scripts/seeder/load-seed-clickhouse.ts"
   },
   "prisma": {
-    "seed": "ts-node -r tsconfig-paths/register -r dotenv/config --compiler-options {\"module\":\"CommonJS\"} prisma/seed.ts"
+    "seed": "ts-node -r tsconfig-paths/register -r dotenv/config --compiler-options {\"module\":\"CommonJS\"} scripts/seeder/seed-postgres.ts"
   },
   "dependencies": {
     "@anthropic-ai/tokenizer": "^0.0.4",
@@ -60,38 +61,40 @@
     "@aws-sdk/lib-storage": "^3.675.0",
     "@aws-sdk/s3-request-presigner": "^3.679.0",
     "@azure/storage-blob": "^12.26.0",
-    "@clickhouse/client": "^1.4.0",
+    "@clickhouse/client": "^1.12.0",
     "@google-cloud/storage": "^7.15.2",
-    "@langchain/anthropic": "^0.3.12",
-    "@langchain/aws": "^0.1.3",
-    "@langchain/core": "^0.3.37",
-    "@langchain/google-genai": "^0.1.9",
-    "@langchain/google-vertexai": "^0.1.8",
-    "@langchain/openai": "^0.3.17",
+    "@langchain/anthropic": "^0.3.22",
+    "@langchain/aws": "^0.1.11",
+    "@langchain/core": "^0.3.58",
+    "@langchain/google-genai": "^0.2.12",
+    "@langchain/google-vertexai": "^0.2.12",
+    "@langchain/openai": "^0.5.13",
     "@opentelemetry/api": ">=1.0.0 <1.10.0",
-    "@prisma/client": "^6.3.0",
-    "@react-email/components": "^0.0.19",
-    "@react-email/render": "^0.0.15",
+    "@prisma/client": "^6.10.1",
+    "@react-email/components": "^0.1.0",
+    "@react-email/render": "^1.1.2",
+    "@slack/oauth": "^3.0.3",
+    "@slack/web-api": "^7.9.3",
     "@types/bcryptjs": "^2.4.6",
-    "axios": "^1.8.2",
     "bcryptjs": "^2.4.3",
     "bullmq": "^5.34.10",
     "dd-trace": "^5.36.0",
     "decimal.js": "^10.4.3",
-    "exponential-backoff": "^3.1.1",
+    "exponential-backoff": "^3.1.2",
     "https-proxy-agent": "^7.0.6",
     "ioredis": "^5.4.1",
+    "jsonpath-plus": "10.3.0",
     "kysely": "^0.27.4",
-    "langchain": "^0.3.15",
-    "langfuse-langchain": "3.30.3",
+    "langchain": "^0.3.28",
+    "langfuse-langchain": "3.38.4",
     "lodash": "^4.17.21",
-    "lossless-json": "^4.0.2",
+    "lossless-json": "^4.1.1",
     "next-auth": "^4.24.11",
     "nodemailer": "^6.9.15",
     "prisma-extension-kysely": "^2.1.0",
     "uuid": "^9.0.1",
     "winston": "^3.15.0",
-    "zod": "^3.24.4",
+    "zod": "^3.25.62",
     "zod-to-json-schema": "^3.23.5"
   },
   "devDependencies": {
@@ -101,6 +104,7 @@
     "@types/node": "^20.11.29",
     "@types/nodemailer": "^6.4.16",
     "@types/pg": "^8.11.10",
+    "@types/react": "18.2.79",
     "@types/uuid": "^9.0.8",
     "@typescript-eslint/parser": "^7.12.0",
     "eslint": "^8.57.0",
@@ -109,23 +113,16 @@
     "eslint-plugin-prettier": "^5.1.3",
     "kysely-codegen": "^0.16.8",
     "nodemon": "^3.1.7",
-    "prettier": "^3.3.3",
-    "prisma": "^6.3.0",
+    "prettier": "^3.6.2",
+    "prisma": "^6.10.1",
     "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": "^2.1.2"
+    "typescript": "^5.4.5"
   },
   "peerDependencies": {
     "@types/react": "~18.2.79",
     "react": "~18.2.0"
-  },
-  "pnpm": {
-    "overrides": {
-      "nanoid": "^3.3.8"
-    }
   }
 }

packages/shared/prisma/migrations/20250529071241_make_blobstorage_integration_credentials_optional/migration.sql

@@ -0,0 +1,3 @@
+-- AlterTable
+ALTER TABLE "blob_storage_integrations" ALTER COLUMN "access_key_id" DROP NOT NULL,
+ALTER COLUMN "secret_access_key" DROP NOT NULL;

packages/shared/prisma/migrations/20250604085536_add_histogram_chart_type/migration.sql

@@ -0,0 +1,2 @@
+-- AlterEnum
+ALTER TYPE "DashboardWidgetChartType" ADD VALUE 'HISTOGRAM';

packages/shared/prisma/migrations/20250625_add_pivot_table_charttype/migration.sql

@@ -0,0 +1,9 @@
+-- Database migration to add PIVOT_TABLE chart type to DashboardWidgetChartType enum
+-- This enables the creation of pivot table widgets in the dashboard system
+-- 
+-- This migration adds support for tabular data visualization with configurable
+-- row dimensions and metrics, extending the existing widget types (line charts,
+-- bar charts, pie charts, etc.) to include pivot table functionality.
+
+-- AlterEnum
+ALTER TYPE "DashboardWidgetChartType" ADD VALUE 'PIVOT_TABLE'; 

packages/shared/prisma/migrations/20250704170658_add_automations/migration.sql

@@ -0,0 +1,111 @@
+-- CreateEnum
+CREATE TYPE "ActionType" AS ENUM ('WEBHOOK');
+
+-- CreateEnum
+CREATE TYPE "ActionExecutionStatus" AS ENUM ('COMPLETED', 'ERROR', 'PENDING', 'CANCELLED');
+
+-- CreateTable
+CREATE TABLE "actions" (
+    "id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "project_id" TEXT NOT NULL,
+    "type" "ActionType" NOT NULL,
+    "config" JSONB NOT NULL,
+
+    CONSTRAINT "actions_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "triggers" (
+    "id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "project_id" TEXT NOT NULL,
+    "eventSource" TEXT NOT NULL,
+    "eventActions" TEXT[],
+    "filter" JSONB,
+    "status" "JobConfigState" NOT NULL DEFAULT 'ACTIVE',
+
+    CONSTRAINT "triggers_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "automations" (
+    "id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "trigger_id" TEXT NOT NULL,
+    "action_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "project_id" TEXT NOT NULL,
+
+    CONSTRAINT "automations_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "automation_executions" (
+    "id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "source_id" TEXT NOT NULL,
+    "automation_id" TEXT NOT NULL,
+    "trigger_id" TEXT NOT NULL,
+    "action_id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "status" "ActionExecutionStatus" NOT NULL DEFAULT 'PENDING',
+    "input" JSONB NOT NULL,
+    "output" JSONB,
+    "started_at" TIMESTAMP(3),
+    "finished_at" TIMESTAMP(3),
+    "error" TEXT,
+
+    CONSTRAINT "automation_executions_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "actions_project_id_idx" ON "actions"("project_id");
+
+-- CreateIndex
+CREATE INDEX "triggers_project_id_idx" ON "triggers"("project_id");
+
+-- CreateIndex
+CREATE INDEX "automations_project_id_action_id_trigger_id_idx" ON "automations"("project_id", "action_id", "trigger_id");
+
+-- CreateIndex
+CREATE INDEX "automations_project_id_name_idx" ON "automations"("project_id", "name");
+
+-- CreateIndex
+CREATE INDEX "automation_executions_trigger_id_idx" ON "automation_executions"("trigger_id");
+
+-- CreateIndex
+CREATE INDEX "automation_executions_action_id_idx" ON "automation_executions"("action_id");
+
+-- CreateIndex
+CREATE INDEX "automation_executions_project_id_idx" ON "automation_executions"("project_id");
+
+-- AddForeignKey
+ALTER TABLE "actions" ADD CONSTRAINT "actions_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "triggers" ADD CONSTRAINT "triggers_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automations" ADD CONSTRAINT "automations_trigger_id_fkey" FOREIGN KEY ("trigger_id") REFERENCES "triggers"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automations" ADD CONSTRAINT "automations_action_id_fkey" FOREIGN KEY ("action_id") REFERENCES "actions"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automations" ADD CONSTRAINT "automations_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automation_executions" ADD CONSTRAINT "automation_executions_automation_id_fkey" FOREIGN KEY ("automation_id") REFERENCES "automations"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automation_executions" ADD CONSTRAINT "automation_executions_trigger_id_fkey" FOREIGN KEY ("trigger_id") REFERENCES "triggers"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automation_executions" ADD CONSTRAINT "automation_executions_action_id_fkey" FOREIGN KEY ("action_id") REFERENCES "actions"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "automation_executions" ADD CONSTRAINT "automation_executions_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20250709113103_add_blob_export_schedule_type/migration.sql

@@ -0,0 +1,6 @@
+-- CreateEnum
+CREATE TYPE "BlobStorageExportMode" AS ENUM ('FULL_HISTORY', 'FROM_TODAY', 'FROM_CUSTOM_DATE');
+
+-- AlterTable
+ALTER TABLE "blob_storage_integrations" ADD COLUMN     "export_mode" "BlobStorageExportMode" NOT NULL DEFAULT 'FULL_HISTORY',
+ADD COLUMN     "export_start_date" TIMESTAMP(3);

packages/shared/prisma/migrations/20250711105322_prices_add_project_id/migration.sql

@@ -0,0 +1,13 @@
+-- AlterTable
+ALTER TABLE "prices"
+    ADD COLUMN "project_id" TEXT;
+
+-- AddForeignKey
+ALTER TABLE "prices"
+    ADD CONSTRAINT "prices_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects" ("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- BackfillData
+UPDATE "prices"
+SET "project_id" = (SELECT "models"."project_id"
+                    FROM "models"
+                    WHERE "models"."id" = "prices"."model_id");

packages/shared/prisma/migrations/20250711134738_add_patch_llm_tool_schema_audit_logs_background_migration/migration.sql

@@ -0,0 +1,2 @@
+INSERT INTO background_migrations (id, name, script, args)
+VALUES ('3445cac4-d9d5-4750-8b65-351135c1b85e', '20250711_1347_patch_llm_tool_schema_audit_logs', 'patchLLMToolAndLLLMSchemaAuditLogs', '{}');

packages/shared/prisma/migrations/20250714151410_add_trace_session_combined_index/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX CONCURRENTLY IF NOT EXISTS "trace_sessions_project_id_created_at_idx" ON "trace_sessions"("project_id", "created_at" DESC);

packages/shared/prisma/migrations/20250714151410_remove_trace_session_created_at_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "trace_sessions_created_at_idx";

packages/shared/prisma/migrations/20250714151410_remove_trace_session_project_id_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "trace_sessions_project_id_idx";

packages/shared/prisma/migrations/20250714151410_remove_trace_session_updated_at_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "trace_sessions_updated_at_idx";

packages/shared/prisma/migrations/20250724114251_add_webhooks_datasets/migration.sql

@@ -0,0 +1,3 @@
+-- AlterTable
+ALTER TABLE "datasets" ADD COLUMN     "remote_experiment_payload" JSONB,
+ADD COLUMN     "remote_experiment_url" TEXT;

packages/shared/prisma/migrations/20250724160133_add_session_object_type_annoation_queue_items/migration.sql

@@ -0,0 +1,2 @@
+-- AlterEnum
+ALTER TYPE "AnnotationQueueObjectType" ADD VALUE 'SESSION';

packages/shared/prisma/migrations/20250730100100_add_slack_integration/migration.sql

@@ -0,0 +1,30 @@
+-- Migration: Add Slack Integration Support
+-- This migration adds support for Slack automation actions by:
+-- 1. Adding SLACK to the ActionType enum
+-- 2. Creating slack_integrations table for centralized token storage
+
+-- AlterEnum
+ALTER TYPE "ActionType" ADD VALUE 'SLACK';
+
+-- CreateTable
+CREATE TABLE "slack_integrations" (
+    "id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "team_id" TEXT NOT NULL,
+    "team_name" TEXT NOT NULL,
+    "bot_token" TEXT NOT NULL,
+    "bot_user_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "slack_integrations_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "slack_integrations_project_id_key" ON "slack_integrations"("project_id");
+
+-- CreateIndex
+CREATE INDEX "slack_integrations_team_id_idx" ON "slack_integrations"("team_id");
+
+-- AddForeignKey
+ALTER TABLE "slack_integrations" ADD CONSTRAINT "slack_integrations_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE; 

packages/shared/prisma/migrations/20250731100100_add_dataset_run_items_pg_to_ch_background_migration/migration.sql

@@ -0,0 +1,2 @@
+INSERT INTO background_migrations (id, name, script, args)
+VALUES ('8d47f91b-3e5c-4a26-9f85-c12d6e4b9a3d', '20250731_1001_migrate_dataset_run_items_pg_to_ch', 'migrateDatasetRunItemsFromPostgresToClickhouse', '{}');

packages/shared/prisma/migrations/20250731202005_add_trace_deletion_table/migration.sql

@@ -0,0 +1,21 @@
+-- CreateTable
+CREATE TABLE "pending_deletions" (
+    "id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "object" TEXT NOT NULL,
+    "object_id" TEXT NOT NULL,
+    "is_deleted" BOOLEAN NOT NULL DEFAULT false,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "pending_deletions_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "pending_deletions_project_id_object_is_deleted_idx" ON "pending_deletions"("project_id", "object", "is_deleted");
+
+-- CreateIndex
+CREATE INDEX "pending_deletions_object_id_object_idx" ON "pending_deletions"("object_id", "object");
+
+-- AddForeignKey
+ALTER TABLE "pending_deletions" ADD CONSTRAINT "pending_deletions_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20250806100613_add_annotation_queue_assignment_table/migration.sql

@@ -0,0 +1,23 @@
+-- CreateTable
+CREATE TABLE "annotation_queue_assignments" (
+    "id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "user_id" TEXT NOT NULL,
+    "queue_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_assignments_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "annotation_queue_assignments_project_id_queue_id_key" ON "annotation_queue_assignments"("project_id", "queue_id", "user_id");
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_assignments" ADD CONSTRAINT "annotation_queue_assignments_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_assignments" ADD CONSTRAINT "annotation_queue_assignments_user_id_fkey" FOREIGN KEY ("user_id") REFERENCES "users"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_assignments" ADD CONSTRAINT "annotation_queue_assignments_queue_id_fkey" FOREIGN KEY ("queue_id") REFERENCES "annotation_queues"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20250808081624_add_surveys_table/migration.sql

@@ -0,0 +1,24 @@
+-- CreateEnum
+CREATE TYPE "SurveyName" AS ENUM ('org_onboarding', 'user_onboarding');
+
+-- CreateTable
+CREATE TABLE "surveys" (
+    "id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "survey_name" "SurveyName" NOT NULL,
+    "response" JSONB NOT NULL,
+    "user_id" TEXT,
+    "user_email" TEXT,
+    "org_id" TEXT,
+
+    CONSTRAINT "surveys_pkey" PRIMARY KEY ("id")
+);
+
+-- AddForeignKey
+ALTER TABLE "surveys" ADD CONSTRAINT "surveys_org_id_fkey" FOREIGN KEY ("org_id") REFERENCES "organizations"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "surveys" ADD CONSTRAINT "surveys_user_id_fkey" FOREIGN KEY ("user_id") REFERENCES "users"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- RenameIndex
+ALTER INDEX "annotation_queue_assignments_project_id_queue_id_key" RENAME TO "annotation_queue_assignments_project_id_queue_id_user_id_key";

packages/shared/prisma/migrations/migration_lock.toml

@@ -1,3 +1,3 @@
 # Please do not edit this file manually
 # It should be added in your version-control system (e.g., Git)
-provider = "postgresql"
+provider = "postgresql"

packages/shared/prisma/schema.prisma

@@ -65,29 +65,31 @@ model Session {
 }
 
 model User {
-  id                      String                   @id @default(cuid())
-  name                    String?
-  email                   String?                  @unique
-  emailVerified           DateTime?                @map("email_verified")
-  password                String?
-  image                   String?
-  admin                   Boolean                  @default(false)
-  accounts                Account[]
-  sessions                Session[]
-  organizationMemberships OrganizationMembership[]
-  projectMemberships      ProjectMembership[]
-  invitations             MembershipInvitation[]
-  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")
-  dashboardWidgetsCreated DashboardWidget[]        @relation("CreatedByUser")
-  dashboardWidgetsUpdated DashboardWidget[]        @relation("UpdatedByUser")
-  dashboardCreated        Dashboard[]              @relation("CreatedByUser")
-  dashboardUpdated        Dashboard[]              @relation("UpdatedByUser")
-  tableViewPresetCreated  TableViewPreset[]        @relation("CreatedByUser")
-  tableViewPresetUpdated  TableViewPreset[]        @relation("UpdatedByUser")
+  id                        String                      @id @default(cuid())
+  name                      String?
+  email                     String?                     @unique
+  emailVerified             DateTime?                   @map("email_verified")
+  password                  String?
+  image                     String?
+  admin                     Boolean                     @default(false)
+  accounts                  Account[]
+  sessions                  Session[]
+  organizationMemberships   OrganizationMembership[]
+  projectMemberships        ProjectMembership[]
+  invitations               MembershipInvitation[]
+  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")
+  dashboardWidgetsCreated   DashboardWidget[]           @relation("CreatedByUser")
+  dashboardWidgetsUpdated   DashboardWidget[]           @relation("UpdatedByUser")
+  dashboardCreated          Dashboard[]                 @relation("CreatedByUser")
+  dashboardUpdated          Dashboard[]                 @relation("UpdatedByUser")
+  tableViewPresetCreated    TableViewPreset[]           @relation("CreatedByUser")
+  tableViewPresetUpdated    TableViewPreset[]           @relation("UpdatedByUser")
+  annotationQueueAssignment AnnotationQueueAssignment[]
+  surveys                   Survey[]
 
   @@map("users")
 }
@@ -112,52 +114,61 @@ model Organization {
   projects                Project[]
   MembershipInvitation    MembershipInvitation[]
   ApiKey                  ApiKey[]
+  surveys                 Survey[]
 
   @@map("organizations")
 }
 
 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")
-  deletedAt              DateTime?                 @map("deleted_at")
-  name                   String
-  retentionDays          Int?                      @map("retention_days")
-  metadata               Json?
-  projectMembers         ProjectMembership[]
-  organization           Organization              @relation(fields: [orgId], references: [id], onUpdate: Cascade, onDelete: Cascade)
-  apiKeys                ApiKey[]
-  dataset                Dataset[]
-  invitations            MembershipInvitation[]
-  sessions               TraceSession[]
-  Prompt                 Prompt[]
-  Model                  Model[]
-  EvalTemplate           EvalTemplate[]
-  JobConfiguration       JobConfiguration[]
-  JobExecution           JobExecution[]
-  LlmApiKeys             LlmApiKeys[]
-  PosthogIntegration     PosthogIntegration[]
-  BlobStorageIntegration BlobStorageIntegration[]
-  scoreConfig            ScoreConfig[]
-  BatchExport            BatchExport[]
-  comment                Comment[]
-  annotationQueue        AnnotationQueue[]
-  annotationQueueItem    AnnotationQueueItem[]
-  TraceMedia             TraceMedia[]
-  Media                  Media[]
-  ObservationMedia       ObservationMedia[]
-  LegacyTrace            LegacyPrismaTrace[]
-  LegacyObservation      LegacyPrismaObservation[]
-  LegacyScore            LegacyPrismaScore[]
-  PromptDependency       PromptDependency[]
-  LlmSchema              LlmSchema[]
-  LlmTool                LlmTool[]
-  PromptProtectedLabels  PromptProtectedLabels[]
-  Dashboard              Dashboard[]
-  DashboardWidget        DashboardWidget[]
-  TableViewPreset        TableViewPreset[]
-  DefaultLlmModel        DefaultLlmModel[]
+  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")
+  deletedAt                 DateTime?                   @map("deleted_at")
+  name                      String
+  retentionDays             Int?                        @map("retention_days")
+  metadata                  Json?
+  projectMembers            ProjectMembership[]
+  organization              Organization                @relation(fields: [orgId], references: [id], onUpdate: Cascade, onDelete: Cascade)
+  apiKeys                   ApiKey[]
+  dataset                   Dataset[]
+  invitations               MembershipInvitation[]
+  sessions                  TraceSession[]
+  Prompt                    Prompt[]
+  Model                     Model[]
+  EvalTemplate              EvalTemplate[]
+  JobConfiguration          JobConfiguration[]
+  JobExecution              JobExecution[]
+  LlmApiKeys                LlmApiKeys[]
+  PosthogIntegration        PosthogIntegration[]
+  BlobStorageIntegration    BlobStorageIntegration[]
+  scoreConfig               ScoreConfig[]
+  BatchExport               BatchExport[]
+  comment                   Comment[]
+  annotationQueue           AnnotationQueue[]
+  annotationQueueItem       AnnotationQueueItem[]
+  TraceMedia                TraceMedia[]
+  Media                     Media[]
+  ObservationMedia          ObservationMedia[]
+  LegacyTrace               LegacyPrismaTrace[]
+  LegacyObservation         LegacyPrismaObservation[]
+  LegacyScore               LegacyPrismaScore[]
+  PromptDependency          PromptDependency[]
+  LlmSchema                 LlmSchema[]
+  LlmTool                   LlmTool[]
+  PromptProtectedLabels     PromptProtectedLabels[]
+  Dashboard                 Dashboard[]
+  DashboardWidget           DashboardWidget[]
+  TableViewPreset           TableViewPreset[]
+  actions                   Action[]
+  triggers                  Trigger[]
+  automationExecutions      AutomationExecution[]
+  Automation                Automation[]
+  DefaultLlmModel           DefaultLlmModel[]
+  Price                     Price[]
+  SlackIntegration          SlackIntegration?
+  PendingDeletion           PendingDeletion[]
+  AnnotationQueueAssignment AnnotationQueueAssignment[]
 
   @@index([orgId])
   @@map("projects")
@@ -306,9 +317,7 @@ model TraceSession {
   environment String   @default("default")
 
   @@id([id, projectId])
-  @@index([projectId])
-  @@index([createdAt])
-  @@index([updatedAt])
+  @@index([projectId, createdAt(sort: Desc)])
   @@map("trace_sessions")
 }
 
@@ -486,15 +495,16 @@ enum ScoreDataType {
 }
 
 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[]
+  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[]
+  annotationQueueAssignment AnnotationQueueAssignment[]
 
   @@unique([projectId, name])
   @@index([id, projectId])
@@ -536,6 +546,22 @@ enum AnnotationQueueStatus {
 enum AnnotationQueueObjectType {
   TRACE
   OBSERVATION
+  SESSION
+}
+
+model AnnotationQueueAssignment {
+  id        String          @id @default(cuid())
+  projectId String          @map("project_id")
+  project   Project         @relation(fields: [projectId], references: [id], onDelete: Cascade)
+  userId    String          @map("user_id")
+  user      User            @relation(fields: [userId], references: [id], onDelete: Cascade)
+  queueId   String          @map("queue_id")
+  queue     AnnotationQueue @relation(fields: [queueId], references: [id], onDelete: Cascade)
+  createdAt DateTime        @default(now()) @map("created_at")
+  updatedAt DateTime        @default(now()) @updatedAt @map("updated_at")
+
+  @@unique([projectId, queueId, userId])
+  @@map("annotation_queue_assignments")
 }
 
 model CronJobs {
@@ -548,16 +574,18 @@ model CronJobs {
 }
 
 model Dataset {
-  id           String        @default(cuid())
-  projectId    String        @map("project_id")
-  name         String
-  description  String?
-  metadata     Json?
-  project      Project       @relation(fields: [projectId], references: [id], onDelete: Cascade)
-  createdAt    DateTime      @default(now()) @map("created_at")
-  updatedAt    DateTime      @default(now()) @updatedAt @map("updated_at")
-  datasetItems DatasetItem[]
-  datasetRuns  DatasetRuns[]
+  id                      String        @default(cuid())
+  projectId               String        @map("project_id")
+  name                    String
+  description             String?
+  metadata                Json?
+  remoteExperimentUrl     String?       @map("remote_experiment_url")
+  remoteExperimentPayload Json?         @map("remote_experiment_payload")
+  project                 Project       @relation(fields: [projectId], references: [id], onDelete: Cascade)
+  createdAt               DateTime      @default(now()) @map("created_at")
+  updatedAt               DateTime      @default(now()) @updatedAt @map("updated_at")
+  datasetItems            DatasetItem[]
+  datasetRuns             DatasetRuns[]
 
   @@id([id, projectId])
   @@unique([projectId, name])
@@ -751,6 +779,8 @@ model Price {
   updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
   modelId   String   @map("model_id") // Model is already linked to project (or default), so we don't need projectId here
   Model     Model    @relation(fields: [modelId], references: [id], onDelete: Cascade)
+  projectId String?  @map("project_id")
+  project   Project? @relation(fields: [projectId], references: [id], onDelete: Cascade)
   usageType String   @map("usage_type")
   price     Decimal
 
@@ -871,7 +901,7 @@ model JobExecution {
   jobConfiguration   JobConfiguration @relation(fields: [jobConfigurationId], references: [id], onDelete: Cascade)
 
   jobTemplateId String?       @map("job_template_id")
-  jobTemplate   EvalTemplate? @relation(fields: [jobTemplateId], references: [id], onDelete: SetNull)
+  jobTemplate   EvalTemplate? @relation(fields: [jobTemplateId], references: [id], onDelete: SetNull, onUpdate: NoAction)
 
   status    JobExecutionStatus
   startTime DateTime?          @map("start_time")
@@ -902,7 +932,7 @@ model DefaultLlmModel {
   updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
 
   projectId String  @map("project_id")
-  Project   Project @relation(fields: [projectId], references: [id])
+  Project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
 
   llmApiKeyId String     @map("llm_api_key_id")
   LlmApiKey   LlmApiKeys @relation("LlmApiKeyId", fields: [llmApiKeyId], references: [id], onDelete: Cascade)
@@ -951,8 +981,8 @@ model BlobStorageIntegration {
   type            BlobStorageIntegrationType @map("type")
   bucketName      String                     @map("bucket_name")
   prefix          String                     @map("prefix")
-  accessKeyId     String                     @map("access_key_id")
-  secretAccessKey String                     @map("secret_access_key")
+  accessKeyId     String?                    @map("access_key_id")
+  secretAccessKey String?                    @map("secret_access_key")
   region          String                     @map("region")
   endpoint        String?                    @map("endpoint")
   forcePathStyle  Boolean                    @map("force_path_style")
@@ -963,6 +993,8 @@ model BlobStorageIntegration {
   enabled         Boolean
   exportFrequency String                         @map("export_frequency")
   fileType        BlobStorageIntegrationFileType @default(CSV) @map("file_type")
+  exportMode      BlobStorageExportMode          @default(FULL_HISTORY) @map("export_mode")
+  exportStartDate DateTime?                      @map("export_start_date")
 
   createdAt DateTime @default(now()) @map("created_at")
   updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
@@ -986,6 +1018,14 @@ enum BlobStorageIntegrationType {
   @@map("BlobStorageIntegrationType")
 }
 
+enum BlobStorageExportMode {
+  FULL_HISTORY
+  FROM_TODAY
+  FROM_CUSTOM_DATE
+
+  @@map("BlobStorageExportMode")
+}
+
 model BatchExport {
   id        String   @id @default(cuid())
   createdAt DateTime @default(now()) @map("created_at")
@@ -1156,6 +1196,8 @@ enum DashboardWidgetChartType {
   VERTICAL_BAR
   PIE
   NUMBER
+  HISTOGRAM
+  PIVOT_TABLE
 }
 
 model DashboardWidget {
@@ -1212,3 +1254,169 @@ model TableViewPreset {
   @@unique([projectId, tableName, name])
   @@map("table_view_presets")
 }
+
+model Action {
+  id        String   @id @default(cuid())
+  createdAt DateTime @default(now()) @map("created_at")
+  updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
+
+  projectId String  @map("project_id")
+  project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
+
+  type ActionType
+
+  // Configuration specific to each action type
+  config Json // Structured JSON for different action types
+  // For WEBHOOK: { version: "1.0", url: "...", method: "POST", headers: {...}, secretId: "..." }
+  // For ANNOTATION_QUEUE: { version: "1.0", queueId: "..." }
+
+  automations          Automation[]
+  automationExecutions AutomationExecution[]
+
+  @@index([projectId])
+  @@map("actions")
+}
+
+model Trigger {
+  id        String   @id @default(cuid())
+  createdAt DateTime @default(now()) @map("created_at")
+  updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
+
+  projectId String  @map("project_id")
+  project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
+
+  // When should this trigger fire
+  eventSource  String // trace, prompt, etc.
+  eventActions String[] // created, updated, deleted
+  filter       Json? // Filter conditions (format: { field: "name", operator: "equals", value: "my_trace" })
+
+  // Additional attributes
+  status JobConfigState @default(ACTIVE) @map("status")
+
+  // Link to executions
+  automationExecutions AutomationExecution[]
+  automations          Automation[]
+
+  @@index([projectId])
+  @@map("triggers")
+}
+
+model Automation {
+  id                  String                @id @default(cuid())
+  name                String                @map("name")
+  trigger             Trigger               @relation(fields: [triggerId], references: [id], onDelete: Cascade)
+  triggerId           String                @map("trigger_id")
+  action              Action                @relation(fields: [actionId], references: [id], onDelete: Cascade)
+  actionId            String                @map("action_id")
+  createdAt           DateTime              @default(now()) @map("created_at")
+  projectId           String                @map("project_id")
+  project             Project               @relation(fields: [projectId], references: [id], onDelete: Cascade)
+  AutomationExecution AutomationExecution[]
+
+  @@index([projectId, actionId, triggerId])
+  @@index([projectId, name])
+  @@map("automations")
+}
+
+enum ActionType {
+  WEBHOOK
+  SLACK
+  // More action types can be added as needed
+}
+
+enum ActionExecutionStatus {
+  COMPLETED
+  ERROR
+  PENDING
+  CANCELLED
+}
+
+model AutomationExecution {
+  id        String   @id @default(cuid())
+  createdAt DateTime @default(now()) @map("created_at")
+  updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
+  sourceId  String   @map("source_id")
+
+  automationId String     @map("automation_id")
+  automation   Automation @relation(fields: [automationId], references: [id], onDelete: Cascade)
+
+  triggerId String  @map("trigger_id")
+  trigger   Trigger @relation(fields: [triggerId], references: [id], onDelete: Cascade)
+
+  actionId String @map("action_id")
+  action   Action @relation(fields: [actionId], references: [id], onDelete: Cascade)
+
+  projectId String  @map("project_id")
+  project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
+
+  status     ActionExecutionStatus @default(PENDING) @map("status")
+  input      Json                  @map("input")
+  output     Json?                 @map("output")
+  startedAt  DateTime?             @map("started_at")
+  finishedAt DateTime?             @map("finished_at")
+  error      String?               @map("error")
+
+  @@index([triggerId])
+  @@index([actionId])
+  @@index([projectId])
+  @@map("automation_executions")
+}
+
+// Slack Integration: Stores centralized Slack workspace connection for each project
+// One project can connect to one Slack workspace, supporting multiple channel automations
+model SlackIntegration {
+  id        String  @id @default(cuid())
+  projectId String  @unique @map("project_id")
+  project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
+
+  // Installation details (encrypted using shared encryption utilities)
+  teamId    String @map("team_id") // Slack workspace ID
+  teamName  String @map("team_name") // Human-readable workspace name
+  botToken  String @map("bot_token") // Encrypted bot token for API calls
+  botUserId String @map("bot_user_id") // Bot user ID for workspace
+
+  createdAt DateTime @default(now()) @map("created_at")
+  updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
+
+  @@index([teamId])
+  @@map("slack_integrations")
+}
+
+// Pending Deletions: Tracks objects (like traces) that are scheduled for batch deletion
+model PendingDeletion {
+  id        String  @id @default(cuid())
+  projectId String  @map("project_id")
+  project   Project @relation(fields: [projectId], references: [id], onDelete: Cascade)
+
+  object    String  @map("object") // e.g., "trace", "observation", etc.
+  objectId  String  @map("object_id") // The ID of the object to be deleted
+  isDeleted Boolean @default(false) @map("is_deleted")
+
+  createdAt DateTime @default(now()) @map("created_at")
+  updatedAt DateTime @default(now()) @updatedAt @map("updated_at")
+
+  @@index([projectId, object, isDeleted])
+  @@index([objectId, object])
+  @@map("pending_deletions")
+}
+
+model Survey {
+  id         String        @id @default(cuid())
+  createdAt  DateTime      @default(now()) @map("created_at")
+  surveyName SurveyName    @map("survey_name")
+  response   Json
+  userId     String?       @map("user_id")
+  userEmail  String?       @map("user_email")
+  orgId      String?       @map("org_id")
+  org        Organization? @relation(fields: [orgId], references: [id], onDelete: Cascade)
+  user       User?         @relation(fields: [userId], references: [id], onDelete: Cascade)
+
+  @@map("surveys")
+}
+
+enum SurveyName {
+  ORG_ONBOARDING  @map("org_onboarding")
+  USER_ONBOARDING @map("user_onboarding")
+
+  @@map("SurveyName")
+}