chore: release v3.141.0

* perf: events table io loading

* push

* perf: events table io loading

* perf: events table io loading

* perf: events table io loading

* perf: events table io loading

* perf: events table io loading

.claude/hooks/post-tool-use-tracker.sh

@@ -64,7 +64,8 @@ detect_repo() {
                 echo "$repo"
             fi
             ;;
-        # Examples directory
+        # Default case
+        *)
             # Check if it's a source file in root
             if [[ ! "$relative_path" =~ / ]]; then
                 echo "root"
@@ -166,4 +167,4 @@ if [[ -f "$cache_dir/commands.txt.tmp" ]]; then
 fi
 
 # Exit cleanly
-exit 0
+exit 0

.claude/skills/backend-dev-guidelines/resources/configuration.md

@@ -50,6 +50,7 @@ langfuse/
 Uses **t3-oss/env-nextjs** for Next.js-specific validation with server/client separation.
 
 **Key Features:**
+
 - Separates server-side and client-side environment variables
 - Client variables must be prefixed with `NEXT_PUBLIC_`
 - Validates at build time (unless `DOCKER_BUILD=1`)
@@ -77,7 +78,6 @@ export const env = createEnv({
       .enum(["US", "EU", "STAGING", "DEV", "HIPAA"])
       .optional(),
     NEXT_PUBLIC_SIGN_UP_DISABLED: z.enum(["true", "false"]).default("false"),
-    NEXT_PUBLIC_TURNSTILE_SITE_KEY: z.string().optional(),
     // ... client variables
   },
 
@@ -85,7 +85,8 @@ export const env = createEnv({
   runtimeEnv: {
     DATABASE_URL: process.env.DATABASE_URL,
     NEXTAUTH_SECRET: process.env.NEXTAUTH_SECRET,
-    NEXT_PUBLIC_LANGFUSE_CLOUD_REGION: process.env.NEXT_PUBLIC_LANGFUSE_CLOUD_REGION,
+    NEXT_PUBLIC_LANGFUSE_CLOUD_REGION:
+      process.env.NEXT_PUBLIC_LANGFUSE_CLOUD_REGION,
     // ... must map ALL variables
   },
 
@@ -122,7 +123,9 @@ import { removeEmptyEnvVariables } from "@langfuse/shared";
 
 const EnvSchema = z.object({
   BUILD_ID: z.string().optional(),
-  NODE_ENV: z.enum(["development", "test", "production"]).default("development"),
+  NODE_ENV: z
+    .enum(["development", "test", "production"])
+    .default("development"),
   DATABASE_URL: z.string(),
   PORT: z.coerce.number().positive().max(65536).default(3030),
 
@@ -137,12 +140,22 @@ const EnvSchema = z.object({
   }),
 
   // Queue concurrency settings
-  LANGFUSE_INGESTION_QUEUE_PROCESSING_CONCURRENCY: z.coerce.number().positive().default(20),
-  LANGFUSE_EVAL_EXECUTION_WORKER_CONCURRENCY: z.coerce.number().positive().default(5),
+  LANGFUSE_INGESTION_QUEUE_PROCESSING_CONCURRENCY: z.coerce
+    .number()
+    .positive()
+    .default(20),
+  LANGFUSE_EVAL_EXECUTION_WORKER_CONCURRENCY: z.coerce
+    .number()
+    .positive()
+    .default(5),
 
   // Queue consumer toggles
-  QUEUE_CONSUMER_INGESTION_QUEUE_IS_ENABLED: z.enum(["true", "false"]).default("true"),
-  QUEUE_CONSUMER_BATCH_EXPORT_QUEUE_IS_ENABLED: z.enum(["true", "false"]).default("true"),
+  QUEUE_CONSUMER_INGESTION_QUEUE_IS_ENABLED: z
+    .enum(["true", "false"])
+    .default("true"),
+  QUEUE_CONSUMER_BATCH_EXPORT_QUEUE_IS_ENABLED: z
+    .enum(["true", "false"])
+    .default("true"),
 
   // ... 150+ worker-specific variables
 });
@@ -173,7 +186,9 @@ import { z } from "zod/v4";
 import { removeEmptyEnvVariables } from "./utils/environment";
 
 const EnvSchema = z.object({
-  NODE_ENV: z.enum(["development", "test", "production"]).default("development"),
+  NODE_ENV: z
+    .enum(["development", "test", "production"])
+    .default("development"),
 
   // Redis configuration
   REDIS_HOST: z.string().nullish(),
@@ -193,11 +208,19 @@ const EnvSchema = z.object({
   LANGFUSE_S3_EVENT_UPLOAD_REGION: z.string().optional(),
 
   // Logging
-  LANGFUSE_LOG_LEVEL: z.enum(["trace", "debug", "info", "warn", "error", "fatal"]).optional(),
+  LANGFUSE_LOG_LEVEL: z
+    .enum(["trace", "debug", "info", "warn", "error", "fatal"])
+    .optional(),
   LANGFUSE_LOG_FORMAT: z.enum(["text", "json"]).default("text"),
 
   // Encryption
-  ENCRYPTION_KEY: z.string().length(64, "ENCRYPTION_KEY must be 256 bits, 64 string characters in hex format, generate via: openssl rand -hex 32").optional(),
+  ENCRYPTION_KEY: z
+    .string()
+    .length(
+      64,
+      "ENCRYPTION_KEY must be 256 bits, 64 string characters in hex format, generate via: openssl rand -hex 32",
+    )
+    .optional(),
 
   // ... 80+ shared variables
 });
@@ -254,6 +277,7 @@ const licenseKey = env.LANGFUSE_EE_LICENSE_KEY;
 **Type:** `"US" | "EU" | "STAGING" | "DEV" | "HIPAA" | undefined`
 
 **Where Used:**
+
 - **web/src/env.mjs** - Client-side accessible (prefixed with `NEXT_PUBLIC_`)
 - **ee/src/env.ts** - Enterprise features
 - **packages/shared/src/env.ts** - Shared logic
@@ -261,13 +285,13 @@ const licenseKey = env.LANGFUSE_EE_LICENSE_KEY;
 
 **When Set:**
 
-| Environment | Value | Purpose |
-|-------------|-------|---------|
-| **Developer Laptop** | `"DEV"` or `"STAGING"` | Local development against cloud infrastructure |
-| **Langfuse Cloud US** | `"US"` | Production US region |
-| **Langfuse Cloud EU** | `"EU"` | Production EU region |
-| **Langfuse Cloud HIPAA** | `"HIPAA"` | HIPAA-compliant region |
-| **OSS Self-Hosted** | `undefined` (not set) | Self-hosted deployments don't have region |
+| Environment              | Value                  | Purpose                                        |
+| ------------------------ | ---------------------- | ---------------------------------------------- |
+| **Developer Laptop**     | `"DEV"` or `"STAGING"` | Local development against cloud infrastructure |
+| **Langfuse Cloud US**    | `"US"`                 | Production US region                           |
+| **Langfuse Cloud EU**    | `"EU"`                 | Production EU region                           |
+| **Langfuse Cloud HIPAA** | `"HIPAA"`              | HIPAA-compliant region                         |
+| **OSS Self-Hosted**      | `undefined` (not set)  | Self-hosted deployments don't have region      |
 
 **Use Cases:**
 
@@ -313,20 +337,22 @@ NEXT_PUBLIC_LANGFUSE_CLOUD_REGION=US
 **Type:** `string | undefined`
 
 **Where Used:**
+
 - **web/src/env.mjs** - Web app EE features
 - **ee/src/env.ts** - EE package
 
 **When Set:**
 
-| Deployment | Value | Features Enabled |
-|------------|-------|------------------|
-| **Langfuse Cloud** | Not set | Cloud features controlled by `NEXT_PUBLIC_LANGFUSE_CLOUD_REGION` |
-| **OSS Self-Hosted** | Not set | Core open-source features only |
-| **EE Self-Hosted** | License key string | Enterprise features enabled |
+| Deployment          | Value              | Features Enabled                                                 |
+| ------------------- | ------------------ | ---------------------------------------------------------------- |
+| **Langfuse Cloud**  | Not set            | Cloud features controlled by `NEXT_PUBLIC_LANGFUSE_CLOUD_REGION` |
+| **OSS Self-Hosted** | Not set            | Core open-source features only                                   |
+| **EE Self-Hosted**  | License key string | Enterprise features enabled                                      |
 
 **Enterprise Features Controlled:**
 
 When `LANGFUSE_EE_LICENSE_KEY` is set and valid:
+
 - SSO integrations (custom OIDC, SAML)
 - Advanced RBAC
 - Audit logging
@@ -372,7 +398,7 @@ NEXT_PUBLIC_LANGFUSE_CLOUD_REGION=US
 
 ```typescript
 // Skip validation during Docker builds
-skipValidation: process.env.DOCKER_BUILD === "1"
+skipValidation: process.env.DOCKER_BUILD === "1";
 ```
 
 **Purpose:** Docker builds happen before runtime env vars are available, so validation must be skipped.
@@ -382,7 +408,7 @@ skipValidation: process.env.DOCKER_BUILD === "1"
 ```typescript
 SALT: z.string({
   required_error: "A strong Salt is required to encrypt API keys securely.",
-})
+});
 ```
 
 **Purpose:** Required for encrypting API keys in database. Must be set in production.
@@ -390,7 +416,7 @@ SALT: z.string({
 **ENCRYPTION_KEY**
 
 ```typescript
-ENCRYPTION_KEY: z.string().length(64, "Must be 256 bits, 64 hex characters")
+ENCRYPTION_KEY: z.string().length(64, "Must be 256 bits, 64 hex characters");
 ```
 
 **Purpose:** Optional 256-bit key for encrypting sensitive database fields.
@@ -425,14 +451,14 @@ import { env } from "./env";
 import { env } from "@langfuse/shared/src/env";
 ```
 
-### 3. Client Variables Must Start with NEXT_PUBLIC_
+### 3. Client Variables Must Start with NEXT*PUBLIC*
 
 ```typescript
 // ❌ Won't work in browser
-API_KEY: z.string() // in server config
+API_KEY: z.string(); // in server config
 
 // ✅ Accessible in browser
-NEXT_PUBLIC_API_KEY: z.string() // in client config
+NEXT_PUBLIC_API_KEY: z.string(); // in client config
 ```
 
 ### 4. Provide Sensible Defaults for Development
@@ -447,7 +473,7 @@ REDIS_PORT: z.coerce.number().positive().default(6379),
 
 ```typescript
 // .env files are always strings
-PORT: z.coerce.number() // Converts "3000" to 3000
+PORT: z.coerce.number(); // Converts "3000" to 3000
 ```
 
 ### 6. Transform Complex Values
@@ -523,6 +549,7 @@ langfuse/
 ```
 
 **DO NOT commit:**
+
 - `.env`
 - `.env.local`
 - `.env.production`

.cursor/rules/global.mdc

@@ -1,20 +1,28 @@
 ---
-description: 
-globs: 
+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 Background/Cloud Agent
+
+When running in a background/cloud agent, please adhere to the following rules:
+
+- Before finishing a task, please run prettier via `pnpm format` to format the code of the repository. Otherwise, the CI check will fail on the change.

.env.dev.example

@@ -111,6 +111,11 @@ LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
 REDIS_HOST="127.0.0.1"
 REDIS_PORT=6379
 REDIS_AUTH="myredissecret"
+# REDIS_SENTINEL_ENABLED="false"
+# REDIS_SENTINEL_NODES="sentinel1:26379,sentinel2:26379"
+# REDIS_SENTINEL_MASTER_NAME="mymaster"
+# REDIS_SENTINEL_USERNAME=""
+# REDIS_SENTINEL_PASSWORD=""
 
 # openssl rand -hex 32 used only here
 ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000
@@ -141,3 +146,4 @@ LANGFUSE_AWS_BEDROCK_MODEL="eu.anthropic.claude-3-haiku-20240307-v1:0"
 
 # Events table migration
 LANGFUSE_ENABLE_EVENTS_TABLE_OBSERVATIONS=true
+LANGFUSE_ENABLE_EVENTS_TABLE_FLAGS=true

.env.prod.example

@@ -115,6 +115,7 @@ OTEL_SERVICE_NAME="langfuse"
 # AUTH_KEYCLOAK_ALLOW_ACCOUNT_LINKING=false
 # AUTH_KEYCLOAK_CLIENT_AUTH_METHOD=
 # AUTH_KEYCLOAK_CHECKS=
+# AUTH_KEYCLOAK_NAME=
 # AUTH_WORKOS_CLIENT_ID=
 # AUTH_WORKOS_CLIENT_SECRET=
 # AUTH_WORKOS_ALLOW_ACCOUNT_LINKING=false
@@ -130,6 +131,13 @@ OTEL_SERVICE_NAME="langfuse"
 # AUTH_CUSTOM_ID_TOKEN=false # optional, default is true
 # AUTH_CUSTOM_CLIENT_AUTH_METHOD=
 # AUTH_CUSTOM_CHECKS=
+# AUTH_JUMPCLOUD_CLIENT_ID=
+# AUTH_JUMPCLOUD_CLIENT_SECRET=
+# AUTH_JUMPCLOUD_ISSUER=
+# AUTH_JUMPCLOUD_ALLOW_ACCOUNT_LINKING=
+# AUTH_JUMPCLOUD_CLIENT_AUTH_METHOD=
+# AUTH_JUMPCLOUD_CHECKS=
+# AUTH_JUMPCLOUD_SCOPE=
 
 # Transactional email, optional
 # Defines the email address to use as the from address.
@@ -183,6 +191,13 @@ LANGFUSE_ENABLE_BLOB_STORAGE_FILE_LOG=true
 # REDIS_CLUSTER_ENABLED=false
 # REDIS_CLUSTER_NODES=redis-node1:6379,redis-node2:6379,redis-node3:6379
 
+# Redis Sentinel configuration (optional, cannot be enabled with cluster mode simultaneously)
+# REDIS_SENTINEL_ENABLED=false
+# REDIS_SENTINEL_NODES=sentinel1:26379,sentinel2:26379,sentinel3:26379
+# REDIS_SENTINEL_MASTER_NAME=mymaster
+# REDIS_SENTINEL_USERNAME=
+# REDIS_SENTINEL_PASSWORD=
+
 # Cache configuration
 # LANGFUSE_CACHE_API_KEY_ENABLED=
 # LANGFUSE_CACHE_API_KEY_TTL_SECONDS=
@@ -248,10 +263,6 @@ LANGFUSE_ENABLE_BLOB_STORAGE_FILE_LOG=true
 # SENTRY_CSP_REPORT_URI=
 
 
-# Cloudflare Turnstile
-# NEXT_PUBLIC_TURNSTILE_SITE_KEY=
-# TURNSTILE_SECRET_KEY=
-
 # Demo project that users can use to try the platform
 # NEXT_PUBLIC_DEMO_ORG_ID=
 # NEXT_PUBLIC_DEMO_PROJECT_ID=

.github/DISCUSSION_TEMPLATE/support.yml

@@ -2,20 +2,35 @@ body:
   - type: textarea
     attributes:
       label: Describe your question
-      description: Please describe the question you have as clear and concise as possible.
+      description: Please describe the question you have as clear and concise as possible. Include error messages, unexpected behavior, or steps to reproduce the problem.
     validations:
       required: true
   - type: dropdown
-    id: hosting
     attributes:
-      label: Are you using Langfuse Cloud or self-host Langfuse?
+      label: Langfuse Cloud or Self-Hosted?
       options:
-        - Langfuse Cloud
-        - Self-hosted Langfuse
+        - "Langfuse Cloud"
+        - "Self-Hosted"
     validations:
       required: true
+  - type: input
+    attributes:
+      label: If Self-Hosted
+      description: What version are you running? We may ask you to upgrade to the latest version, as many issues are continuously being fixed.
+  - type: input
+    attributes:
+      label: If Langfuse Cloud
+      description: Please share the link to your Langfuse project or the specific view you have a question about. This helps us resolve requests faster.
+  - type: textarea
+    attributes:
+      label: SDK and integration versions
+      description: If you're experiencing an issue with an integration or SDK, please share all package versions you're using. If you are not on the latest version, try upgrading, as this will often resolve the issue.
   - type: checkboxes
     attributes:
-      label: I checked if there is already an [issue](https://github.com/langfuse/langfuse/issues) or [discussion](https://github.com/orgs/langfuse/discussions) for my question and asked the [Langfuse AI](https://langfuse.com/docs/ask-ai) for help.
+      label: Pre-Submission Checklist
+      description: Please check for existing [issues](https://github.com/langfuse/langfuse/issues) and [discussions](https://github.com/orgs/langfuse/discussions) and ask the [Langfuse AI chatbot](https://langfuse.com/docs/ask-ai).
+      options:
+        - label: I have checked for existing issues/discussions and consulted Langfuse AI.
+          required: true
     validations:
       required: true

.github/workflows/deploy.yml

@@ -12,7 +12,9 @@ on:
           - all
           - web
           - web-ingestion
+          - web-iso
           - worker
+          - worker-cpu
         required: true
       environment:
         description: "Environment to deploy to"
@@ -43,12 +45,12 @@ jobs:
           script: |
             if (context.eventName === "workflow_dispatch") {
               if (context.payload.inputs.service === "all") {
-                return `["web", "web-ingestion", "worker"]`
+                return `["web", "web-ingestion", "web-iso", "worker", "worker-cpu"]`
               }
               return `["${context.payload.inputs.service}"]`
             }
             if (context.eventName === "push") {
-              return `["web", "web-ingestion", "worker"]`
+              return `["web", "web-ingestion", "web-iso", "worker", "worker-cpu"]`
             }
             return "[]"
           result-encoding: string

.github/workflows/pipeline.yml

@@ -59,6 +59,14 @@ jobs:
           node-version: 24
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
+      - name: Setup Turbo cache
+        uses: actions/cache@v4
+        with:
+          path: .turbo
+          key: ${{ runner.os }}-turbo-lint-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-turbo-lint-
+            ${{ runner.os }}-turbo-
       - name: install dependencies
         run: |
           pnpm i
@@ -192,6 +200,23 @@ jobs:
           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: Setup Turbo cache
+        uses: actions/cache@v4
+        with:
+          path: .turbo
+          key: ${{ runner.os }}-turbo-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-turbo-
+      - name: Cache Next.js builds
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ${{ github.workspace }}/web/.next/cache
+          key: ${{ runner.os }}-nextjs-${{ matrix.node-version }}-${{ hashFiles('**/pnpm-lock.yaml') }}-${{ hashFiles('web/**/*.js', 'web/**/*.jsx', 'web/**/*.ts', 'web/**/*.tsx') }}
+          restore-keys: |
+            ${{ runner.os }}-nextjs-${{ matrix.node-version }}-${{ hashFiles('**/pnpm-lock.yaml') }}-
+            ${{ runner.os }}-nextjs-${{ matrix.node-version }}-
       - name: Run dev containers
         run: |
           docker compose -f docker-compose.dev.yml up -d
@@ -221,9 +246,11 @@ jobs:
           LANGFUSE_INIT_USER_NAME: "Demo User"
           LANGFUSE_INIT_USER_PASSWORD: "password"
       - name: run test-sync
-        run: pnpm --filter=web run test-sync
+        working-directory: web
+        run: npx cross-env NODE_OPTIONS='--no-experimental-require-module' npx dotenv -e ../.env.test -e ../.env -- npx jest --verbose --runInBand --detectOpenHandles --selectProjects sync-server
       - name: run test-client
-        run: pnpm --filter=web run test-client
+        working-directory: web
+        run: npx cross-env NODE_OPTIONS='--no-experimental-require-module' npx dotenv -e ../.env.test -e ../.env -- npx jest --verbose --runInBand --detectOpenHandles --selectProjects client
 
   tests-web-async:
     timeout-minutes: 30
@@ -231,12 +258,13 @@ 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${{ matrix.deploy-mode }})
+    name: tests-web-async (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.deploy-mode }}, shard${{ matrix.shard }}/3)
     strategy:
       matrix:
         node-version: [24]
         postgres-version: [12, 15]
         deploy-mode: ["", "-azure", "-redis-cluster"]
+        shard: [1, 2, 3]
     steps:
       - uses: actions/checkout@v4
       - name: Install golang-migrate for Clickhouse migrations
@@ -271,6 +299,23 @@ jobs:
           echo "LANGFUSE_TRACE_DELETE_CONCURRENCY=100" >> .env
           echo "ADMIN_API_KEY=admin-api-key" >> .env
           echo "LANGFUSE_EE_LICENSE_KEY=langfuse_ee_test" >> .env
+      - name: Setup Turbo cache
+        uses: actions/cache@v4
+        with:
+          path: .turbo
+          key: ${{ runner.os }}-turbo-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-turbo-
+      - name: Cache Next.js builds
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ${{ github.workspace }}/web/.next/cache
+          key: ${{ runner.os }}-nextjs-async-${{ matrix.node-version }}-${{ hashFiles('**/pnpm-lock.yaml') }}-${{ hashFiles('web/**/*.js', 'web/**/*.jsx', 'web/**/*.ts', 'web/**/*.tsx') }}
+          restore-keys: |
+            ${{ runner.os }}-nextjs-async-${{ matrix.node-version }}-${{ hashFiles('**/pnpm-lock.yaml') }}-
+            ${{ runner.os }}-nextjs-async-${{ matrix.node-version }}-
       - name: Run dev containers
         run: |
           docker compose -f docker-compose.dev${{ matrix.deploy-mode }}.yml up -d
@@ -314,7 +359,8 @@ jobs:
           LANGFUSE_INIT_USER_NAME: "Demo User"
           LANGFUSE_INIT_USER_PASSWORD: "password"
       - name: run tests
-        run: pnpm --filter=web run test
+        working-directory: web
+        run: npx cross-env NODE_OPTIONS='--no-experimental-require-module' npx dotenv -e ../.env.test -e ../.env -- npx jest --verbose --runInBand --detectOpenHandles --selectProjects async-server --shard=${{ matrix.shard }}/3
 
   tests-worker:
     timeout-minutes: 20
@@ -475,6 +521,24 @@ jobs:
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
           password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
+      - name: Setup Turbo cache
+        uses: actions/cache@v4
+        with:
+          path: .turbo
+          key: ${{ runner.os }}-turbo-e2e-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-turbo-e2e-
+            ${{ runner.os }}-turbo-
+      - name: Cache Next.js builds
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ${{ github.workspace }}/web/.next/cache
+          key: ${{ runner.os }}-nextjs-e2e-${{ hashFiles('**/pnpm-lock.yaml') }}-${{ hashFiles('web/**/*.js', 'web/**/*.jsx', 'web/**/*.ts', 'web/**/*.tsx') }}
+          restore-keys: |
+            ${{ runner.os }}-nextjs-e2e-${{ hashFiles('**/pnpm-lock.yaml') }}-
+            ${{ runner.os }}-nextjs-e2e-
       - name: install dependencies
         run: |
           pnpm install

.gitignore

@@ -56,6 +56,8 @@ yarn-error.log*
 # openapi spec that is copied during build
 /public/openapi*.yml
 
+# claude meta files
+.claude/tsc-cache
 
 # vscode
 node_modules
@@ -70,3 +72,9 @@ web/test-results/*
 
 # local config files
 *.local.*
+
+# claude meta files
+.claude/tsc-cache
+
+# Refactoring planning files (local only)
+**/.refactor/

README.cn.md

@@ -245,7 +245,7 @@ _[Langfuse 中的公共示例追踪](https://cloud.langfuse.com/project/cloramnk
 
 ## ⭐️ 给我们加星
 
-![为 Langfuse 加星](https://langfuse.com/images/docs/github-readme/github-star-howto.gif)
+![star-langfuse-on-github](https://github.com/user-attachments/assets/79a1d816-d229-4526-aecc-097d4a19f1ad)
 
 ## 💭 支持
 

README.ja.md

@@ -248,7 +248,7 @@ _[Langfuseの公開トレース例](https://cloud.langfuse.com/project/cloramnkj
 
 ## ⭐️ Star Langfuse
 
-![Star Langfuse](https://langfuse.com/images/docs/github-readme/github-star-howto.gif)
+![star-langfuse-on-github](https://github.com/user-attachments/assets/79a1d816-d229-4526-aecc-097d4a19f1ad)
 
 ## 💭 サポート
 

README.kr.md

@@ -233,7 +233,7 @@ _[Langfuse의 공개 예제 trace](https://cloud.langfuse.com/project/cloramnkj0
 
 ## ⭐️ 별을 눌러주세요
 
-![Star Langfuse](https://langfuse.com/images/docs/github-readme/github-star-howto.gif)
+![star-langfuse-on-github](https://github.com/user-attachments/assets/79a1d816-d229-4526-aecc-097d4a19f1ad)
 
 ## 💭 지원
 

README.md

@@ -74,7 +74,9 @@
 Langfuse is an **open source LLM engineering** platform. It helps teams collaboratively
 **develop, monitor, evaluate,** and **debug** AI applications. Langfuse can be **self-hosted in minutes** and is **battle-tested**.
 
-[![Langfuse Overview Video](https://github.com/user-attachments/assets/3926b288-ff61-4b95-8aa1-45d041c70866)](https://langfuse.com/watch-demo)
+[![Langfuse Overview Video](https://github.com/user-attachments/assets/925d71db-6331-445e-8f3e-727ee95d1c9f)](https://langfuse.com/watch-demo)
+
+
 
 ## ✨ Core Features
 
@@ -142,6 +144,7 @@ See [self-hosting documentation](https://langfuse.com/self-hosting) to learn mor
 | [Haystack](https://langfuse.com/docs/integrations/haystack)                  | Python                     | Automated instrumentation via Haystack content tracing system.                                                                                   |
 | [LiteLLM](https://langfuse.com/docs/integrations/litellm)                    | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |
 | [Vercel AI SDK](https://langfuse.com/docs/integrations/vercel-ai-sdk)        | JS/TS                      | TypeScript toolkit designed to help developers build AI-powered applications with React, Next.js, Vue, Svelte, Node.js.                          |
+| [Mastra](https://langfuse.com/docs/integrations/mastra)                      | JS/TS                      | Open source framework for building AI agents and multi-agent systems.                                                                             |
 | [API](https://langfuse.com/docs/api)                                         |                            | Directly call the public API. OpenAPI spec available.                                                                                            |
 
 ### Packages integrated with Langfuse:

docker-compose.build.yml

@@ -98,7 +98,7 @@ services:
       start_period: 1s
 
   minio:
-    image: docker.io/minio/minio
+    image: cgr.dev/chainguard/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'
@@ -122,6 +122,7 @@ services:
     restart: always
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
+      --maxmemory-policy noeviction
     ports:
       - 6379:6379
     healthcheck:

docker-compose.dev-azure.yml

@@ -23,11 +23,35 @@ services:
     volumes:
       - langfuse_azurite_data:/data
 
+  minio:
+    image: cgr.dev/chainguard/minio
+    container_name: ${MINIO_CONTAINER_NAME:-langfuse-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_ROOT_USER: ${MINIO_ROOT_USER:-minio}
+      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-miniosecret}
+    ports:
+      - ${HOST_IP:-127.0.0.1}:${MINIO_API_PORT:-9090}:9000
+      - ${HOST_IP:-127.0.0.1}:${MINIO_CONSOLE_PORT:-9091}:9001
+    volumes:
+      - langfuse_minio_data:/data
+    healthcheck:
+      test: ["CMD", "mc", "ready", "local"]
+      interval: 1s
+      timeout: 5s
+      retries: 5
+      start_period: 1s
+    networks:
+      - default
+
   redis:
     image: docker.io/redis:7.2.4
     restart: always
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
+      --maxmemory-policy noeviction
     ports:
       - 6379:6379
 
@@ -60,3 +84,6 @@ volumes:
     driver: local
   langfuse_azurite_data:
     driver: local
+  langfuse_minio_data:
+    name: ${MINIO_VOLUME_NAME:-langfuse_minio_data}
+    driver: local

docker-compose.dev-redis-cluster.yml

@@ -16,7 +16,7 @@ services:
       - postgres
 
   minio:
-    image: docker.io/minio/minio
+    image: cgr.dev/chainguard/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'

docker-compose.dev.yml

@@ -21,7 +21,7 @@ services:
       - default
 
   minio:
-    image: docker.io/minio/minio
+    image: cgr.dev/chainguard/minio
     container_name: ${MINIO_CONTAINER_NAME:-langfuse-minio}
     entrypoint: sh
     # create the 'langfuse' bucket before starting the service
@@ -49,6 +49,7 @@ services:
     restart: always
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
+      --maxmemory-policy noeviction
     ports:
       - ${HOST_IP:-127.0.0.1}:${REDIS_HOST_PORT:-6379}:6379
     networks:

docker-compose.yml

@@ -107,7 +107,7 @@ services:
       start_period: 1s
 
   minio:
-    image: docker.io/minio/minio
+    image: cgr.dev/chainguard/minio
     restart: always
     entrypoint: sh
     # create the 'langfuse' bucket before starting the service
@@ -133,6 +133,7 @@ services:
     # CHANGEME: row below to secure redis password
     command: >
       --requirepass ${REDIS_AUTH:-myredissecret}
+      --maxmemory-policy noeviction
     ports:
       - 127.0.0.1:6379:6379
     healthcheck:

ee/package.json

@@ -27,7 +27,7 @@
     "@langfuse/shared": "workspace:*",
     "@opentelemetry/api": ">=1.0.0 <1.10.0",
     "https-proxy-agent": "^7.0.6",
-    "next": "15.5.4",
+    "next": "15.5.9",
     "next-auth": "^4.24.12",
     "zod": "^3.25.62"
   },
@@ -35,7 +35,7 @@
     "@repo/eslint-config": "workspace:*",
     "@repo/typescript-config": "workspace:*",
     "@types/node": "^24.3.0",
-    "@typescript-eslint/parser": "^7.12.0",
+    "@typescript-eslint/parser": "^8.48.1",
     "eslint": "^8.57.0",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",

fern/apis/server/definition/commons.yml

@@ -281,8 +281,8 @@ types:
     extends: BaseScoreV1
     properties:
       value:
-        type: optional<double>
-        docs: Only defined if a config is linked. Represents the numeric category mapping of the stringValue
+        type: double
+        docs: Represents the numeric category mapping of the stringValue. If no config is linked, defaults to 0.
       stringValue:
         type: string
         docs: The string representation of the score value. If no config is linked, can be any string. Otherwise, must map to a config category
@@ -342,8 +342,8 @@ types:
     extends: BaseScore
     properties:
       value:
-        type: optional<double>
-        docs: Only defined if a config is linked. Represents the numeric category mapping of the stringValue
+        type: double
+        docs: Represents the numeric category mapping of the stringValue. If no config is linked, defaults to 0.
       stringValue:
         type: string
         docs: The string representation of the score value. If no config is linked, can be any string. Otherwise, must map to a config category
@@ -384,6 +384,12 @@ types:
       name: string
       description: optional<string>
       metadata: optional<unknown>
+      inputSchema:
+        type: optional<unknown>
+        docs: JSON Schema for validating dataset item inputs
+      expectedOutputSchema:
+        type: optional<unknown>
+        docs: JSON Schema for validating dataset item expected outputs
       projectId: string
       createdAt: datetime
       updatedAt: datetime
@@ -441,7 +447,16 @@ types:
     properties:
       datasetRunItems: list<DatasetRunItem>
   Model:
-    docs: Model definition used for transforming usage into USD cost and/or tokenization.
+    docs: |
+      Model definition used for transforming usage into USD cost and/or tokenization.
+
+      Models can have either simple flat pricing or tiered pricing:
+      - Flat pricing: Single price per usage type (legacy, but still supported)
+      - Tiered pricing: Multiple pricing tiers with conditional matching based on usage patterns
+
+      The pricing tiers approach is recommended for models with usage-based pricing variations.
+      When using tiered pricing, the flat price fields (inputPrice, outputPrice, prices) are populated
+      from the default tier for backward compatibility.
     properties:
       id: string
       modelName:
@@ -473,14 +488,210 @@ types:
         type: optional<unknown>
       isLangfuseManaged:
         type: boolean
+      createdAt:
+        docs: Timestamp when the model was created
+        type: datetime
       prices:
-        docs: Price (USD) by usage type
+        docs: |
+          Deprecated. Use 'pricingTiers' instead for models with usage-based pricing variations.
+
+          This field shows prices by usage type from the default pricing tier. Maintained for backward compatibility.
+          If the model uses tiered pricing, this field will be populated from the default tier's prices.
         type: map<string, ModelPrice>
+      pricingTiers:
+        docs: |
+          Array of pricing tiers with conditional pricing based on usage thresholds.
+
+          Pricing tiers enable accurate cost tracking for models that charge different rates based on usage patterns
+          (e.g., different rates for high-volume usage, large context windows, or cached tokens).
+
+          Each model must have exactly one default tier (isDefault=true, priority=0) that serves as a fallback.
+          Additional conditional tiers can be defined with specific matching criteria.
+
+          If this array is empty, the model uses legacy flat pricing from the inputPrice/outputPrice/totalPrice fields.
+        type: list<PricingTier>
 
   ModelPrice:
     properties:
       price: double
 
+  PricingTierCondition:
+    docs: |
+      Condition for matching a pricing tier based on usage details. Used to implement tiered pricing models where costs vary based on usage thresholds.
+
+      How it works:
+      1. The regex pattern matches against usage detail keys (e.g., "input_tokens", "input_cached")
+      2. Values of all matching keys are summed together
+      3. The sum is compared against the threshold value using the specified operator
+      4. All conditions in a tier must be met (AND logic) for the tier to match
+
+      Common use cases:
+      - Threshold-based pricing: Match when accumulated usage exceeds a certain amount
+      - Usage-type-specific pricing: Different rates for cached vs non-cached tokens, or input vs output
+      - Volume-based pricing: Different rates based on total request or token count
+    properties:
+      usageDetailPattern:
+        docs: |
+          Regex pattern to match against usage detail keys. All matching keys' values are summed for threshold comparison.
+
+          Examples:
+          - "^input" matches "input", "input_tokens", "input_cached", etc.
+          - "^(input|prompt)" matches both "input_tokens" and "prompt_tokens"
+          - "_cache$" matches "input_cache", "output_cache", etc.
+
+          The pattern is case-insensitive by default. If no keys match, the sum is treated as zero.
+        type: string
+      operator:
+        docs: |
+          Comparison operator to apply between the summed value and the threshold.
+
+          - gt: greater than (sum > threshold)
+          - gte: greater than or equal (sum >= threshold)
+          - lt: less than (sum < threshold)
+          - lte: less than or equal (sum <= threshold)
+          - eq: equal (sum == threshold)
+          - neq: not equal (sum != threshold)
+        type: PricingTierOperator
+      value:
+        docs: Threshold value for comparison. For token-based pricing, this is typically the token count threshold (e.g., 200000 for a 200K token threshold).
+        type: double
+      caseSensitive:
+        docs: Whether the regex pattern matching is case-sensitive. Default is false (case-insensitive matching).
+        type: boolean
+
+  PricingTier:
+    docs: |
+      Pricing tier definition with conditional pricing based on usage thresholds.
+
+      Pricing tiers enable accurate cost tracking for LLM providers that charge different rates based on usage patterns.
+      For example, some providers charge higher rates when context size exceeds certain thresholds.
+
+      How tier matching works:
+      1. Tiers are evaluated in ascending priority order (priority 1 before priority 2, etc.)
+      2. The first tier where ALL conditions match is selected
+      3. If no conditional tiers match, the default tier is used as a fallback
+      4. The default tier has priority 0 and no conditions
+
+      Why priorities matter:
+      - Lower priority numbers are evaluated first, allowing you to define specific cases before general ones
+      - Example: Priority 1 for "high usage" (>200K tokens), Priority 2 for "medium usage" (>100K tokens), Priority 0 for default
+      - Without proper ordering, a less specific condition might match before a more specific one
+
+      Every model must have exactly one default tier to ensure cost calculation always succeeds.
+    properties:
+      id:
+        docs: Unique identifier for the pricing tier
+        type: string
+      name:
+        docs: |
+          Name of the pricing tier for display and identification purposes.
+
+          Examples: "Standard", "High Volume Tier", "Large Context", "Extended Context Tier"
+        type: string
+      isDefault:
+        docs: |
+          Whether this is the default tier. Every model must have exactly one default tier with priority 0 and no conditions.
+
+          The default tier serves as a fallback when no conditional tiers match, ensuring cost calculation always succeeds.
+          It typically represents the base pricing for standard usage patterns.
+        type: boolean
+      priority:
+        docs: |
+          Priority for tier matching evaluation. Lower numbers = higher priority (evaluated first).
+
+          The default tier must always have priority 0. Conditional tiers should have priority 1, 2, 3, etc.
+
+          Example ordering:
+          - Priority 0: Default tier (no conditions, always matches as fallback)
+          - Priority 1: High usage tier (e.g., >200K tokens)
+          - Priority 2: Medium usage tier (e.g., >100K tokens)
+
+          This ensures more specific conditions are checked before general ones.
+        type: integer
+      conditions:
+        docs: |
+          Array of conditions that must ALL be met for this tier to match (AND logic).
+
+          The default tier must have an empty conditions array. Conditional tiers should have one or more conditions
+          that define when this tier's pricing applies.
+
+          Multiple conditions enable complex matching scenarios (e.g., "high input tokens AND low output tokens").
+        type: list<PricingTierCondition>
+      prices:
+        docs: |
+          Prices (USD) by usage type for this tier.
+
+          Common usage types: "input", "output", "total", "request", "image"
+          Prices are specified in USD per unit (e.g., per token, per request, per second).
+
+          Example: {"input": 0.000003, "output": 0.000015} means $3 per million input tokens and $15 per million output tokens.
+        type: map<string, double>
+
+  PricingTierInput:
+    docs: |
+      Input schema for creating a pricing tier. The tier ID will be automatically generated server-side.
+
+      When creating a model with pricing tiers:
+      - Exactly one tier must have isDefault=true (the fallback tier)
+      - The default tier must have priority=0 and conditions=[]
+      - All tier names and priorities must be unique within the model
+      - Each tier must define at least one price
+
+      See PricingTier for detailed information about how tiers work and why they're useful.
+    properties:
+      name:
+        docs: |
+          Name of the pricing tier for display and identification purposes.
+
+          Must be unique within the model. Common patterns: "Standard", "High Volume Tier", "Extended Context"
+        type: string
+      isDefault:
+        docs: |
+          Whether this is the default tier. Exactly one tier per model must be marked as default.
+
+          Requirements for default tier:
+          - Must have isDefault=true
+          - Must have priority=0
+          - Must have empty conditions array (conditions=[])
+
+          The default tier acts as a fallback when no conditional tiers match.
+        type: boolean
+      priority:
+        docs: |
+          Priority for tier matching evaluation. Lower numbers = higher priority (evaluated first).
+
+          Must be unique within the model. The default tier must have priority=0.
+          Conditional tiers should use priority 1, 2, 3, etc. based on their specificity.
+        type: integer
+      conditions:
+        docs: |
+          Array of conditions that must ALL be met for this tier to match (AND logic).
+
+          The default tier must have an empty array (conditions=[]).
+          Conditional tiers should define one or more conditions that specify when this tier's pricing applies.
+
+          Each condition specifies a regex pattern, operator, and threshold value for matching against usage details.
+        type: list<PricingTierCondition>
+      prices:
+        docs: |
+          Prices (USD) by usage type for this tier. At least one price must be defined.
+
+          Common usage types: "input", "output", "total", "request", "image"
+          Prices are in USD per unit (e.g., per token).
+
+          Example: {"input": 0.000003, "output": 0.000015} represents $3 per million input tokens and $15 per million output tokens.
+        type: map<string, double>
+
+  PricingTierOperator:
+    docs: Comparison operators for pricing tier conditions
+    enum:
+      - gt
+      - gte
+      - lt
+      - lte
+      - eq
+      - neq
+
   # Utilities
   ModelUsageUnit:
     docs: Unit of usage in Langfuse

fern/apis/server/definition/datasets.yml

@@ -76,6 +76,12 @@ types:
       name: string
       description: optional<string>
       metadata: optional<unknown>
+      inputSchema:
+        type: optional<unknown>
+        docs: JSON Schema for validating dataset item inputs. When set, all new and existing dataset items will be validated against this schema.
+      expectedOutputSchema:
+        type: optional<unknown>
+        docs: JSON Schema for validating dataset item expected outputs. When set, all new and existing dataset items will be validated against this schema.
   PaginatedDatasetRuns:
     properties:
       data: list<commons.DatasetRun>

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

@@ -53,6 +53,9 @@ types:
       extraHeaderKeys:
         type: list<string>
         docs: Keys of extra headers sent with requests (values excluded for security)
+      config:
+        type: optional<map<string, unknown>>
+        docs: Adapter-specific configuration. Required for Bedrock (`{"region":"us-east-1"}`), optional for VertexAI (`{"location":"us-central1"}`), not used by other adapters.
       createdAt: datetime
       updatedAt: datetime
 
@@ -85,6 +88,13 @@ types:
       extraHeaders:
         type: optional<map<string, string>>
         docs: Extra headers to send with requests
+      config:
+        type: optional<map<string, unknown>>
+        docs: >
+          Adapter-specific configuration. Validation rules:
+          - **Bedrock**: Required. Must be `{"region": "<aws-region>"}` (e.g., `{"region":"us-east-1"}`)
+          - **VertexAI**: Optional. If provided, must be `{"location": "<gcp-location>"}` (e.g., `{"location":"us-central1"}`)
+          - **Other adapters**: Not supported. Omit this field or set to null.
 
   LlmAdapter:
     enum:

fern/apis/server/definition/media.yml

@@ -116,6 +116,10 @@ types:
         name: IMAGE_TIFF
       - value: image/bmp
         name: IMAGE_BMP
+      - value: image/avif
+        name: IMAGE_AVIF
+      - value: image/heic
+        name: IMAGE_HEIC
       - value: audio/mpeg
         name: AUDIO_MPEG
       - value: audio/mp3
@@ -132,10 +136,24 @@ types:
         name: AUDIO_MP4
       - value: audio/flac
         name: AUDIO_FLAC
+      - value: audio/opus
+        name: AUDIO_OPUS
+      - value: audio/webm
+        name: AUDIO_WEBM
       - value: video/mp4
         name: VIDEO_MP4
       - value: video/webm
         name: VIDEO_WEBM
+      - value: video/ogg
+        name: VIDEO_OGG
+      - value: video/mpeg
+        name: VIDEO_MPEG
+      - value: video/quicktime
+        name: VIDEO_QUICKTIME
+      - value: video/x-msvideo
+        name: VIDEO_X_MSVIDEO
+      - value: video/x-matroska
+        name: VIDEO_X_MATROSKA
       - value: text/plain
         name: TEXT_PLAIN
       - value: text/html
@@ -144,12 +162,24 @@ types:
         name: TEXT_CSS
       - value: text/csv
         name: TEXT_CSV
+      - value: text/markdown
+        name: TEXT_MARKDOWN
+      - value: text/x-python
+        name: TEXT_X_PYTHON
+      - value: application/javascript
+        name: APPLICATION_JAVASCRIPT
+      - value: text/x-typescript
+        name: TEXT_X_TYPESCRIPT
+      - value: application/x-yaml
+        name: APPLICATION_X_YAML
       - value: application/pdf
         name: APPLICATION_PDF
       - value: application/msword
         name: APPLICATION_MSWORD
       - value: application/vnd.ms-excel
         name: APPLICATION_MS_EXCEL
+      - value: application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
+        name: APPLICATION_OPENXML_SPREADSHEET
       - value: application/zip
         name: APPLICATION_ZIP
       - value: application/json
@@ -158,4 +188,20 @@ types:
         name: APPLICATION_XML
       - value: application/octet-stream
         name: APPLICATION_OCTET_STREAM
+      - value: application/vnd.openxmlformats-officedocument.wordprocessingml.document
+        name: APPLICATION_OPENXML_WORD
+      - value: application/vnd.openxmlformats-officedocument.presentationml.presentation
+        name: APPLICATION_OPENXML_PRESENTATION
+      - value: application/rtf
+        name: APPLICATION_RTF
+      - value: application/x-ndjson
+        name: APPLICATION_X_NDJSON
+      - value: application/vnd.apache.parquet
+        name: APPLICATION_PARQUET
+      - value: application/gzip
+        name: APPLICATION_GZIP
+      - value: application/x-tar
+        name: APPLICATION_X_TAR
+      - value: application/x-7z-compressed
+        name: APPLICATION_X_7Z_COMPRESSED
     docs: The MIME type of the media record

fern/apis/server/definition/metrics-v2.yml

@@ -0,0 +1,178 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  pagination: ./utils/pagination.yml
+  commons: ./commons.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    metrics:
+      docs: |
+        Get metrics from the Langfuse project using a query object. V2 endpoint with optimized performance.
+
+        ## V2 Differences
+        - Supports `observations`, `scores-numeric`, and `scores-categorical` views only (traces view not supported)
+        - Direct access to tags and release fields on observations
+        - Backwards-compatible: traceName, traceRelease, traceVersion dimensions are still available on observations view
+        - High cardinality dimensions are not supported and will return a 400 error (see below)
+
+        For more details, see the [Metrics API documentation](https://langfuse.com/docs/metrics/features/metrics-api).
+
+        ## Available Views
+
+        ### observations
+        Query observation-level data (spans, generations, events).
+
+        **Dimensions:**
+        - `environment` - Deployment environment (e.g., production, staging)
+        - `type` - Type of observation (SPAN, GENERATION, EVENT)
+        - `name` - Name of the observation
+        - `level` - Logging level of the observation
+        - `version` - Version of the observation
+        - `tags` - User-defined tags
+        - `release` - Release version
+        - `traceName` - Name of the parent trace (backwards-compatible)
+        - `traceRelease` - Release version of the parent trace (backwards-compatible, maps to release)
+        - `traceVersion` - Version of the parent trace (backwards-compatible, maps to version)
+        - `providedModelName` - Name of the model used
+        - `promptName` - Name of the prompt used
+        - `promptVersion` - Version of the prompt used
+        - `startTimeMonth` - Month of start_time in YYYY-MM format
+
+        **Measures:**
+        - `count` - Total number of observations
+        - `latency` - Observation latency (milliseconds)
+        - `streamingLatency` - Generation latency from completion start to end (milliseconds)
+        - `inputTokens` - Sum of input tokens consumed
+        - `outputTokens` - Sum of output tokens produced
+        - `totalTokens` - Sum of all tokens consumed
+        - `outputTokensPerSecond` - Output tokens per second
+        - `tokensPerSecond` - Total tokens per second
+        - `inputCost` - Input cost (USD)
+        - `outputCost` - Output cost (USD)
+        - `totalCost` - Total cost (USD)
+        - `timeToFirstToken` - Time to first token (milliseconds)
+        - `countScores` - Number of scores attached to the observation
+
+        ### scores-numeric
+        Query numeric and boolean score data.
+
+        **Dimensions:**
+        - `environment` - Deployment environment
+        - `name` - Name of the score (e.g., accuracy, toxicity)
+        - `source` - Origin of the score (API, ANNOTATION, EVAL)
+        - `dataType` - Data type (NUMERIC, BOOLEAN)
+        - `configId` - Identifier of the score config
+        - `timestampMonth` - Month in YYYY-MM format
+        - `timestampDay` - Day in YYYY-MM-DD format
+        - `value` - Numeric value of the score
+        - `traceName` - Name of the parent trace
+        - `tags` - Tags
+        - `traceRelease` - Release version
+        - `traceVersion` - Version
+        - `observationName` - Name of the associated observation
+        - `observationModelName` - Model name of the associated observation
+        - `observationPromptName` - Prompt name of the associated observation
+        - `observationPromptVersion` - Prompt version of the associated observation
+
+        **Measures:**
+        - `count` - Total number of scores
+        - `value` - Score value (for aggregations)
+
+        ### scores-categorical
+        Query categorical score data. Same dimensions as scores-numeric except uses `stringValue` instead of `value`.
+
+        **Measures:**
+        - `count` - Total number of scores
+
+        ## High Cardinality Dimensions
+        The following dimensions cannot be used as grouping dimensions in v2 metrics API as they can cause performance issues.
+        Use them in filters instead.
+
+        **observations view:**
+        - `id` - Use traceId filter to narrow down results
+        - `traceId` - Use traceId filter instead
+        - `userId` - Use userId filter instead
+        - `sessionId` - Use sessionId filter instead
+        - `parentObservationId` - Use parentObservationId filter instead
+
+        **scores-numeric / scores-categorical views:**
+        - `id` - Use specific filters to narrow down results
+        - `traceId` - Use traceId filter instead
+        - `userId` - Use userId filter instead
+        - `sessionId` - Use sessionId filter instead
+        - `observationId` - Use observationId filter instead
+
+        ## Aggregations
+        Available aggregation functions: `sum`, `avg`, `count`, `max`, `min`, `p50`, `p75`, `p90`, `p95`, `p99`, `histogram`
+
+        ## Time Granularities
+        Available granularities for timeDimension: `auto`, `minute`, `hour`, `day`, `week`, `month`
+        - `auto` bins the data into approximately 50 buckets based on the time range
+      method: GET
+      path: /v2/metrics
+      request:
+        name: GetMetricsV2Request
+        query-parameters:
+          query:
+            type: string
+            docs: |
+              JSON string containing the query parameters with the following structure:
+              ```json
+              {
+                "view": string,           // Required. One of "observations", "scores-numeric", "scores-categorical"
+                "dimensions": [           // Optional. Default: []
+                  {
+                    "field": string       // Field to group by (see available dimensions above)
+                  }
+                ],
+                "metrics": [              // Required. At least one metric must be provided
+                  {
+                    "measure": string,    // What to measure (see available measures above)
+                    "aggregation": string // How to aggregate: "sum", "avg", "count", "max", "min", "p50", "p75", "p90", "p95", "p99", "histogram"
+                  }
+                ],
+                "filters": [              // Optional. Default: []
+                  {
+                    "column": string,     // Column to filter on (any dimension field)
+                    "operator": string,   // Operator based on type:
+                                          // - datetime: ">", "<", ">=", "<="
+                                          // - string: "=", "contains", "does not contain", "starts with", "ends with"
+                                          // - stringOptions: "any of", "none of"
+                                          // - arrayOptions: "any of", "none of", "all of"
+                                          // - number: "=", ">", "<", ">=", "<="
+                                          // - stringObject/numberObject: same as string/number with required "key"
+                                          // - boolean: "=", "<>"
+                                          // - null: "is null", "is not null"
+                    "value": any,         // Value to compare against
+                    "type": string,       // Data type: "datetime", "string", "number", "stringOptions", "categoryOptions", "arrayOptions", "stringObject", "numberObject", "boolean", "null"
+                    "key": string         // Required only for stringObject/numberObject types (e.g., metadata filtering)
+                  }
+                ],
+                "timeDimension": {        // Optional. Default: null. If provided, results will be grouped by time
+                  "granularity": string   // One of "auto", "minute", "hour", "day", "week", "month"
+                },
+                "fromTimestamp": string,  // Required. ISO datetime string for start of time range
+                "toTimestamp": string,    // Required. ISO datetime string for end of time range (must be after fromTimestamp)
+                "orderBy": [              // Optional. Default: null
+                  {
+                    "field": string,      // Field to order by (dimension or metric alias)
+                    "direction": string   // "asc" or "desc"
+                  }
+                ],
+                "config": {               // Optional. Query-specific configuration
+                  "bins": number,         // Optional. Number of bins for histogram aggregation (1-100), default: 10
+                  "row_limit": number     // Optional. Maximum number of rows to return (1-1000), default: 100
+                }
+              }
+              ```
+      response: MetricsV2Response
+types:
+  MetricsV2Response:
+    properties:
+      data:
+        type: list<map<string, unknown>>
+        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/models.yml

@@ -60,14 +60,35 @@ types:
         docs: Unit used by this model.
         type: optional<commons.ModelUsageUnit>
       inputPrice:
-        docs: Price (USD) per input unit
+        docs: Deprecated. Use 'pricingTiers' instead. Price (USD) per input unit. Creates a default tier if pricingTiers not provided.
         type: optional<double>
       outputPrice:
-        docs: Price (USD) per output unit
+        docs: Deprecated. Use 'pricingTiers' instead. Price (USD) per output unit. Creates a default tier if pricingTiers not provided.
         type: optional<double>
       totalPrice:
-        docs: Price (USD) per total units. Cannot be set if input or output price is set.
+        docs: Deprecated. Use 'pricingTiers' instead. Price (USD) per total units. Cannot be set if input or output price is set. Creates a default tier if pricingTiers not provided.
         type: optional<double>
+      pricingTiers:
+        docs: |
+          Optional. Array of pricing tiers for this model.
+
+          Use pricing tiers for all models - both those with threshold-based pricing variations and those with simple flat pricing:
+
+          - For models with standard flat pricing: Create a single default tier with your prices
+            (e.g., one tier with isDefault=true, priority=0, conditions=[], and your standard prices)
+
+          - For models with threshold-based pricing: Create a default tier plus additional conditional tiers
+            (e.g., default tier for standard usage + high-volume tier for usage above certain thresholds)
+
+          Requirements:
+          - Cannot be provided with flat prices (inputPrice/outputPrice/totalPrice) - use one approach or the other
+          - Must include exactly one default tier with isDefault=true, priority=0, and conditions=[]
+          - All tier names and priorities must be unique within the model
+          - Each tier must define at least one price
+
+          If omitted, you must provide flat prices instead (inputPrice/outputPrice/totalPrice),
+          which will automatically create a single default tier named "Standard".
+        type: optional<list<commons.PricingTierInput>>
       tokenizerId:
         docs: Optional. Tokenizer to be applied to observations which match to this model. See docs for more details.
         type: optional<string>

fern/apis/server/definition/observations-v2.yml

@@ -0,0 +1,197 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  commons: ./commons.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    getMany:
+      docs: |
+        Get a list of observations with cursor-based pagination and flexible field selection.
+
+        ## Cursor-based Pagination
+        This endpoint uses cursor-based pagination for efficient traversal of large datasets.
+        The cursor is returned in the response metadata and should be passed in subsequent requests
+        to retrieve the next page of results.
+
+        ## Field Selection
+        Use the `fields` parameter to control which observation fields are returned:
+        - `core` - Always included: id, traceId, startTime, endTime, projectId, parentObservationId, type
+        - `basic` - name, level, statusMessage, version, environment, bookmarked, public, userId, sessionId
+        - `time` - completionStartTime, createdAt, updatedAt
+        - `io` - input, output
+        - `metadata` - metadata
+        - `model` - providedModelName, internalModelId, modelParameters
+        - `usage` - usageDetails, costDetails, totalCost
+        - `prompt` - promptId, promptName, promptVersion
+        - `metrics` - latency, timeToFirstToken
+
+        If not specified, `core` and `basic` field groups are returned.
+
+        ## Filters
+        Multiple filtering options are available via query parameters or the structured `filter` parameter.
+        When using the `filter` parameter, it takes precedence over individual query parameter filters.
+      method: GET
+      path: /v2/observations
+      request:
+        name: GetObservationsV2Request
+        query-parameters:
+          fields:
+            type: optional<string>
+            docs: |
+              Comma-separated list of field groups to include in the response.
+              Available groups: core, basic, time, io, metadata, model, usage, prompt, metrics.
+              If not specified, `core` and `basic` field groups are returned.
+              Example: "basic,usage,model"
+          limit:
+            type: optional<integer>
+            docs: Number of items to return per page. Maximum 1000, default 50.
+          cursor:
+            type: optional<string>
+            docs: Base64-encoded cursor for pagination. Use the cursor from the previous response to get the next page.
+          parseIoAsJson:
+            type: optional<boolean>
+            docs: |
+              Set to `true` to parse input/output fields as JSON, or `false` to return raw strings.
+              Defaults to `false` if not provided.
+          name: optional<string>
+          userId: optional<string>
+          type:
+            type: optional<string>
+            docs: Filter by observation type (e.g., "GENERATION", "SPAN", "EVENT", "AGENT", "TOOL", "CHAIN", "RETRIEVER", "EVALUATOR", "EMBEDDING", "GUARDRAIL")
+          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>
+            allow-multiple: true
+            docs: Optional filter for observations where the environment is one of the provided values.
+          fromStartTime:
+            type: optional<datetime>
+            docs: Retrieve only observations with a start_time on or after this datetime (ISO 8601).
+          toStartTime:
+            type: optional<datetime>
+            docs: Retrieve only observations with a start_time before this datetime (ISO 8601).
+          version:
+            type: optional<string>
+            docs: Optional filter to only include observations with a certain version.
+          filter:
+            type: optional<string>
+            docs: |
+              JSON string containing an array of filter conditions. When provided, this takes precedence over query parameter filters (userId, name, type, level, environment, fromStartTime, ...).
+
+              ## Filter Structure
+              Each filter condition has the following structure:
+              ```json
+              [
+                {
+                  "type": string,           // Required. One of: "datetime", "string", "number", "stringOptions", "categoryOptions", "arrayOptions", "stringObject", "numberObject", "boolean", "null"
+                  "column": string,         // Required. Column to filter on (see available columns below)
+                  "operator": string,       // Required. Operator based on type:
+                                            // - datetime: ">", "<", ">=", "<="
+                                            // - string: "=", "contains", "does not contain", "starts with", "ends with"
+                                            // - stringOptions: "any of", "none of"
+                                            // - categoryOptions: "any of", "none of"
+                                            // - arrayOptions: "any of", "none of", "all of"
+                                            // - number: "=", ">", "<", ">=", "<="
+                                            // - stringObject: "=", "contains", "does not contain", "starts with", "ends with"
+                                            // - numberObject: "=", ">", "<", ">=", "<="
+                                            // - boolean: "=", "<>"
+                                            // - null: "is null", "is not null"
+                  "value": any,             // Required (except for null type). Value to compare against. Type depends on filter type
+                  "key": string             // Required only for stringObject, numberObject, and categoryOptions types when filtering on nested fields like metadata
+                }
+              ]
+              ```
+
+              ## Available Columns
+
+              ### Core Observation Fields
+              - `id` (string) - Observation ID
+              - `type` (string) - Observation type (SPAN, GENERATION, EVENT)
+              - `name` (string) - Observation name
+              - `traceId` (string) - Associated trace ID
+              - `startTime` (datetime) - Observation start time
+              - `endTime` (datetime) - Observation end time
+              - `environment` (string) - Environment tag
+              - `level` (string) - Log level (DEBUG, DEFAULT, WARNING, ERROR)
+              - `statusMessage` (string) - Status message
+              - `version` (string) - Version tag
+              - `userId` (string) - User ID
+              - `sessionId` (string) - Session ID
+
+              ### Trace-Related Fields
+              - `traceName` (string) - Name of the parent trace
+              - `traceTags` (arrayOptions) - Tags from the parent trace
+              - `tags` (arrayOptions) - Alias for traceTags
+
+              ### Performance Metrics
+              - `latency` (number) - Latency in seconds (calculated: end_time - start_time)
+              - `timeToFirstToken` (number) - Time to first token in seconds
+              - `tokensPerSecond` (number) - Output tokens per second
+
+              ### Token Usage
+              - `inputTokens` (number) - Number of input tokens
+              - `outputTokens` (number) - Number of output tokens
+              - `totalTokens` (number) - Total tokens (alias: `tokens`)
+
+              ### Cost Metrics
+              - `inputCost` (number) - Input cost in USD
+              - `outputCost` (number) - Output cost in USD
+              - `totalCost` (number) - Total cost in USD
+
+              ### Model Information
+              - `model` (string) - Provided model name (alias: `providedModelName`)
+              - `promptName` (string) - Associated prompt name
+              - `promptVersion` (number) - Associated prompt version
+
+              ### Structured Data
+              - `metadata` (stringObject/numberObject/categoryOptions) - Metadata key-value pairs. Use `key` parameter to filter on specific metadata keys.
+
+              ## Filter Examples
+              ```json
+              [
+                {
+                  "type": "string",
+                  "column": "type",
+                  "operator": "=",
+                  "value": "GENERATION"
+                },
+                {
+                  "type": "number",
+                  "column": "latency",
+                  "operator": ">=",
+                  "value": 2.5
+                },
+                {
+                  "type": "stringObject",
+                  "column": "metadata",
+                  "key": "environment",
+                  "operator": "=",
+                  "value": "production"
+                }
+              ]
+              ```
+      response: ObservationsV2Response
+
+types:
+  ObservationsV2Response:
+    docs: |
+      Response containing observations with field-group-based filtering and cursor-based pagination.
+
+      The `data` array contains observation objects with only the requested field groups included.
+      Use the `cursor` in `meta` to retrieve the next page of results.
+    properties:
+      data:
+        type: list<map<string, unknown>>
+        docs: Array of observation objects. Fields included depend on the `fields` parameter in the request.
+      meta: ObservationsV2Meta
+
+  ObservationsV2Meta:
+    docs: Metadata for cursor-based pagination
+    properties:
+      cursor:
+        type: optional<string>
+        docs: Base64-encoded cursor to use for retrieving the next page. If not present, there are no more results.

fern/apis/server/definition/observations.yml

@@ -115,10 +115,6 @@ service:
               ### Structured Data
               - `metadata` (stringObject/numberObject/categoryOptions) - Metadata key-value pairs. Use `key` parameter to filter on specific metadata keys.
 
-              ### Scores (requires join with scores table)
-              - `scores_avg` (number) - Average of numeric scores (alias: `scores`)
-              - `score_categories` (categoryOptions) - Categorical score values
-
               ### Associated Trace Fields (requires join with traces table)
               - `userId` (string) - User ID from associated trace
               - `traceName` (string) - Name from associated trace

fern/apis/server/definition/projects.yml

@@ -7,7 +7,7 @@ service:
   base-path: /api/public
   endpoints:
     get:
-      docs: Get Project associated with API key
+      docs: Get Project associated with API key (requires project-scoped API key). You can use GET /api/public/organizations/projects to get all projects with an organization-scoped key.
       method: GET
       path: /projects
       response: Projects

fern/apis/server/definition/prompt-version.yml

@@ -13,7 +13,9 @@ service:
       path-parameters:
         name:
           type: string
-          docs: The name of the prompt
+          docs: |
+            The name of the prompt. If the prompt is in a folder (e.g., "folder/subfolder/prompt-name"), 
+            the folder path must be URL encoded.
         version:
           type: integer
           docs: Version of the prompt to update

fern/apis/server/definition/prompts.yml

@@ -2,6 +2,7 @@
 imports:
   commons: ./commons.yml
   pagination: ./utils/pagination.yml
+  scim: ./scim.yml
 service:
   auth: true
   base-path: /api/public/v2
@@ -13,7 +14,9 @@ service:
       path-parameters:
         promptName:
           type: string
-          docs: The name of the prompt
+          docs: |
+            The name of the prompt. If the prompt is in a folder (e.g., "folder/subfolder/prompt-name"), 
+            the folder path must be URL encoded.
       request:
         name: GetPromptRequest
         query-parameters:
@@ -57,6 +60,24 @@ service:
       request: CreatePromptRequest
       response: Prompt
 
+    delete:
+      docs: Delete prompt versions. If neither version nor label is specified, all versions of the prompt are deleted.
+      method: DELETE
+      path: /prompts/{promptName}
+      path-parameters:
+        promptName:
+          type: string
+          docs: The name of the prompt
+      request:
+        name: DeletePromptRequest
+        query-parameters:
+          label:
+            type: optional<string>
+            docs: Optional label to filter deletion. If specified, deletes all prompt versions that have this label.
+          version:
+            type: optional<integer>
+            docs: Optional version to filter deletion. If specified, deletes only this specific version of the prompt.
+
 types:
   PromptMetaListResponse:
     properties:

fern/apis/server/definition/score-v2.yml

@@ -53,6 +53,12 @@ service:
           sessionId:
             type: optional<string>
             docs: Retrieve only scores with a specific sessionId.
+          datasetRunId:
+            type: optional<string>
+            docs: Retrieve only scores with a specific datasetRunId.
+          traceId:
+            type: optional<string>
+            docs: Retrieve only scores with a specific traceId.
           queueId:
             type: optional<string>
             docs: Retrieve only scores with a specific annotation queueId.

fern/apis/server/definition/score.yml

@@ -33,7 +33,7 @@ types:
         type: commons.CreateScoreValue
         docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores. Boolean score values must equal either 1 or 0 (true or false)
       comment: optional<string>
-      metadata: optional<unknown>
+      metadata: optional<map<string, unknown>>
       environment:
         type: optional<string>
         docs: The environment of the score. Can be any lowercase alphanumeric string with hyphens and underscores that does not start with 'langfuse'.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "langfuse",
-  "version": "3.126.1",
+  "version": "3.141.0",
   "author": "engineering@langfuse.com",
   "license": "MIT",
   "private": true,
@@ -40,7 +40,7 @@
     "husky": "^9.1.7",
     "prettier": "^3.6.2",
     "release-it": "^19.0.4",
-    "turbo": "^2.6.0"
+    "turbo": "^2.6.3"
   },
   "release-it": {
     "git": {
@@ -92,7 +92,11 @@
       "katex": "^0.16.21",
       "tar-fs": "^2.1.2",
       "rollup@^4.0.0": "^4.22.4",
-      "@types/node-fetch": "^2.6.13"
+      "@types/node-fetch": "^2.6.13",
+      "glob": "^10.5.0"
+    },
+    "patchedDependencies": {
+      "next-auth@4.24.12": "patches/next-auth@4.24.12.patch"
     }
   }
 }

packages/config-eslint/next.js

@@ -57,7 +57,18 @@ module.exports = {
         fixStyle: "inline-type-imports",
       },
     ],
-    "@typescript-eslint/no-unused-vars": ["warn", { argsIgnorePattern: "^_" }],
+    "@typescript-eslint/no-unused-vars": [
+      // see: https://typescript-eslint.io/rules/no-unused-vars/#why-does-this-rule-report-variables-used-only-for-types
+      // since v8, vars only used for types are unused at runtime and therefore throw a warning.
+      // we fix those with workarounds (mostly just export the variables, as they are used as part of an API anyways)
+      // see: https://github.com/typescript-eslint/typescript-eslint/issues/10266
+      "warn",
+      {
+        argsIgnorePattern: "^_",
+        varsIgnorePattern: "^_",
+        caughtErrorsIgnorePattern: "^_",
+      },
+    ],
     "react/jsx-key": [
       "error",
       {

packages/config-eslint/package.json

@@ -8,12 +8,12 @@
     "next.js"
   ],
   "devDependencies": {
-    "@typescript-eslint/eslint-plugin": "^7.1.0",
-    "@typescript-eslint/parser": "^7.12.0",
+    "@typescript-eslint/eslint-plugin": "^8.48.1",
+    "@typescript-eslint/parser": "^8.48.1",
     "@vercel/style-guide": "^6.0.0",
-    "eslint-config-next": "^14.2.15",
+    "eslint-config-next": "15.5.9",
     "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^2.6.0",
+    "eslint-config-turbo": "^2.6.3",
     "eslint-plugin-only-warn": "^1.1.0",
     "typescript": "^5.7.2"
   }

packages/shared/clickhouse/migrations/clustered/0031_add_usage_pricing_tier_columns.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE observations ON CLUSTER default DROP COLUMN IF EXISTS usage_pricing_tier_name;
+ALTER TABLE observations ON CLUSTER default DROP COLUMN IF EXISTS usage_pricing_tier_id;

packages/shared/clickhouse/migrations/clustered/0031_add_usage_pricing_tier_columns.up.sql

@@ -0,0 +1,2 @@
+ALTER TABLE observations ON CLUSTER default ADD COLUMN usage_pricing_tier_id Nullable(String);
+ALTER TABLE observations ON CLUSTER default ADD COLUMN usage_pricing_tier_name Nullable(String);

packages/shared/clickhouse/migrations/clustered/0032_add_dataset_version_to_dataset_run_items_rmt.down.sql

@@ -0,0 +1 @@
+ALTER TABLE dataset_run_items_rmt ON CLUSTER default DROP COLUMN IF EXISTS dataset_item_version;

packages/shared/clickhouse/migrations/clustered/0032_add_dataset_version_to_dataset_run_items_rmt.up.sql

@@ -0,0 +1 @@
+ALTER TABLE dataset_run_items_rmt ON CLUSTER default ADD COLUMN IF NOT EXISTS dataset_item_version Nullable(DateTime64(3));

packages/shared/clickhouse/migrations/clustered/0033_add_tool_call_columns.down.sql

@@ -0,0 +1,3 @@
+ALTER TABLE observations ON CLUSTER default DROP COLUMN IF EXISTS tool_definitions SETTINGS alter_sync = 2;
+ALTER TABLE observations ON CLUSTER default DROP COLUMN IF EXISTS tool_calls SETTINGS alter_sync = 2;
+ALTER TABLE observations ON CLUSTER default DROP COLUMN IF EXISTS tool_call_names SETTINGS alter_sync = 2;

packages/shared/clickhouse/migrations/clustered/0033_add_tool_call_columns.up.sql

@@ -0,0 +1,3 @@
+ALTER TABLE observations ON CLUSTER default ADD COLUMN IF NOT EXISTS tool_definitions Map(String, String) DEFAULT map() SETTINGS alter_sync = 2;
+ALTER TABLE observations ON CLUSTER default ADD COLUMN IF NOT EXISTS tool_calls Array(String) DEFAULT [] SETTINGS alter_sync = 2;
+ALTER TABLE observations ON CLUSTER default ADD COLUMN IF NOT EXISTS tool_call_names Array(String) DEFAULT [] SETTINGS alter_sync = 2;

packages/shared/clickhouse/migrations/unclustered/0031_add_usage_pricing_tier_columns.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE observations DROP COLUMN IF EXISTS usage_pricing_tier_name;
+ALTER TABLE observations DROP COLUMN IF EXISTS usage_pricing_tier_id;

packages/shared/clickhouse/migrations/unclustered/0031_add_usage_pricing_tier_columns.up.sql

@@ -0,0 +1,2 @@
+ALTER TABLE observations ADD COLUMN usage_pricing_tier_id Nullable(String);
+ALTER TABLE observations ADD COLUMN usage_pricing_tier_name Nullable(String);

packages/shared/clickhouse/migrations/unclustered/0032_add_dataset_version_to_dataset_run_items_rmt.down.sql

@@ -0,0 +1 @@
+ALTER TABLE dataset_run_items_rmt DROP COLUMN IF EXISTS dataset_item_version;

packages/shared/clickhouse/migrations/unclustered/0032_add_dataset_version_to_dataset_run_items_rmt.up.sql

@@ -0,0 +1 @@
+ALTER TABLE dataset_run_items_rmt ADD COLUMN IF NOT EXISTS dataset_item_version Nullable(DateTime64(3));

packages/shared/clickhouse/migrations/unclustered/0033_add_tool_call_columns.down.sql

@@ -0,0 +1,3 @@
+ALTER TABLE observations DROP COLUMN IF EXISTS tool_definitions SETTINGS alter_sync = 2;
+ALTER TABLE observations DROP COLUMN IF EXISTS tool_calls SETTINGS alter_sync = 2;
+ALTER TABLE observations DROP COLUMN IF EXISTS tool_call_names SETTINGS alter_sync = 2;

packages/shared/clickhouse/migrations/unclustered/0033_add_tool_call_columns.up.sql

@@ -0,0 +1,3 @@
+ALTER TABLE observations ADD COLUMN IF NOT EXISTS tool_definitions Map(String, String) DEFAULT map() SETTINGS alter_sync = 2;
+ALTER TABLE observations ADD COLUMN IF NOT EXISTS tool_calls Array(String) DEFAULT [] SETTINGS alter_sync = 2;
+ALTER TABLE observations ADD COLUMN IF NOT EXISTS tool_call_names Array(String) DEFAULT [] SETTINGS alter_sync = 2;

packages/shared/clickhouse/scripts/dev-tables.sh

@@ -38,26 +38,25 @@ fi
 
 # Ensure CLICKHOUSE_DB is set
 if [ -z "${CLICKHOUSE_DB}" ]; then
-    export CLICKHOUSE_DB="default"
+  export CLICKHOUSE_DB="default"
 fi
 
 # Parse the CLICKHOUSE_MIGRATION_URL to extract host and port
 # Expected format: clickhouse://localhost:9000
 if [[ $CLICKHOUSE_MIGRATION_URL =~ ^clickhouse://([^:]+):([0-9]+)$ ]]; then
-    CLICKHOUSE_HOST="${BASH_REMATCH[1]}"
-    CLICKHOUSE_PORT="${BASH_REMATCH[2]}"
+  CLICKHOUSE_HOST="${BASH_REMATCH[1]}"
+  CLICKHOUSE_PORT="${BASH_REMATCH[2]}"
 elif [[ $CLICKHOUSE_MIGRATION_URL =~ ^clickhouse://([^:]+)$ ]]; then
-    CLICKHOUSE_HOST="${BASH_REMATCH[1]}"
-    CLICKHOUSE_PORT="9000"  # Default native protocol port
+  CLICKHOUSE_HOST="${BASH_REMATCH[1]}"
+  CLICKHOUSE_PORT="9000" # Default native protocol port
 else
-    echo "Error: Could not parse CLICKHOUSE_MIGRATION_URL: ${CLICKHOUSE_MIGRATION_URL}"
-    exit 1
+  echo "Error: Could not parse CLICKHOUSE_MIGRATION_URL: ${CLICKHOUSE_MIGRATION_URL}"
+  exit 1
 fi
 
-if ! command -v clickhouse &> /dev/null
-then
-	echo "Error: clickhouse binary could not be found. Please install ClickHouse client tools."
-	exit 1
+if ! command -v clickhouse &>/dev/null; then
+  echo "Error: clickhouse binary could not be found. Please install ClickHouse client tools."
+  exit 1
 fi
 
 echo "Creating development tables in ClickHouse..."
@@ -101,6 +100,11 @@ CREATE TABLE IF NOT EXISTS observations_batch_staging
     provided_cost_details Map(LowCardinality(String), Decimal64(12)),
     cost_details Map(LowCardinality(String), Decimal64(12)),
     total_cost Nullable(Decimal64(12)),
+    usage_pricing_tier_id Nullable(String),
+    usage_pricing_tier_name Nullable(String),
+    tool_definitions Map(String, String),
+    tool_calls Array(String),
+    tool_call_names Array(String),
     completion_start_time Nullable(DateTime64(3)),
     prompt_id Nullable(String),
     prompt_name Nullable(String),
@@ -113,6 +117,7 @@ CREATE TABLE IF NOT EXISTS observations_batch_staging
     environment LowCardinality(String) DEFAULT 'default',
 ) ENGINE = ReplacingMergeTree(event_ts, is_deleted)
 PARTITION BY toStartOfInterval(s3_first_seen_timestamp, INTERVAL 3 MINUTE)
+PRIMARY KEY (project_id, toDate(s3_first_seen_timestamp))
 ORDER BY (
     project_id,
     toDate(s3_first_seen_timestamp),
@@ -139,74 +144,100 @@ CREATE TABLE IF NOT EXISTS events
       type LowCardinality(String),
       environment LowCardinality(String) DEFAULT 'default',
       version String,
+      release String,
 
+      trace_name String,
       user_id String,
       session_id String,
 
+      tags Array(String),
+      bookmarked Bool DEFAULT false,
+      public Bool DEFAULT false,
+
       level LowCardinality(String),
       status_message String, -- Threat '' and null the same for search
       completion_start_time Nullable(DateTime64(6)),
 
       -- Prompt
-      prompt_id Nullable(String),
-      prompt_name Nullable(String),
-      prompt_version Nullable(String),
+      prompt_id String,
+      prompt_name String,
+      prompt_version Nullable(UInt16),
 
       -- Model
-      model_id Nullable(String),
-      provided_model_name Nullable(String),
-      model_parameters Nullable(String),
+      model_id String,
+      provided_model_name String,
+      model_parameters String,
+      model_parameters_json JSON MATERIALIZED model_parameters::JSON,
 
       -- Usage
-      provided_usage_details JSON(max_dynamic_paths=64, max_dynamic_types=8),
-      usage_details JSON(
+      provided_usage_details Map(LowCardinality(String), UInt64),
+      provided_usage_details_json JSON(max_dynamic_paths=64, max_dynamic_types=8) MATERIALIZED provided_usage_details::JSON,
+      usage_details Map(LowCardinality(String), UInt64),
+      usage_details_json JSON(
         max_dynamic_paths=64,
         max_dynamic_types=8,
         input UInt64,
         output UInt64,
         total UInt64,
-      ),
-      provided_cost_details JSON(max_dynamic_paths=64, max_dynamic_types=8),
-      cost_details JSON(
+      ) MATERIALIZED usage_details::JSON,
+      provided_cost_details Map(LowCardinality(String), Decimal(18,12)),
+      provided_cost_details_json JSON(max_dynamic_paths=64, max_dynamic_types=8) MATERIALIZED provided_cost_details::JSON,
+      cost_details Map(LowCardinality(String), Decimal(18,12)),
+      cost_details_json JSON(
         max_dynamic_paths=64,
         max_dynamic_types=8,
         input Decimal(18,12),
         output Decimal(18,12),
         total Decimal(18,12),
-      ),
-      total_cost Decimal(18,12), -- 0 if not provided
+      ) MATERIALIZED cost_details::JSON,
+
+      calculated_input_cost Decimal(18, 12) MATERIALIZED arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'input') > 0, cost_details))),
+      calculated_output_cost Decimal(18, 12) MATERIALIZED arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'output') > 0, cost_details))),
+      calculated_total_cost Decimal(18, 12) MATERIALIZED arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'input') > 0 OR positionCaseInsensitive(x.1, 'output') > 0, cost_details))),
+      total_cost Decimal(18, 12) ALIAS cost_details_json.total,
+      usage_pricing_tier_id Nullable(String),
+      usage_pricing_tier_name Nullable(String),
+
+      -- Tools
+      tool_definitions Map(String, String),
+      tool_calls Array(String),
+      tool_call_names Array(String),
 
       -- I/O
       input String CODEC(ZSTD(3)),
       input_truncated String MATERIALIZED leftUTF8(input, 1024),
+      input_length UInt64 MATERIALIZED lengthUTF8(input),
       output String CODEC(ZSTD(3)),
       output_truncated String MATERIALIZED leftUTF8(output, 1024),
+      output_length UInt64 MATERIALIZED lengthUTF8(output),
 
-      -- TODO Metadata: Decide for approach
-      -- -- Approach 1: Use plain JSON type with default config
-      metadata JSON(max_dynamic_paths=1024, max_dynamic_types=32),
-      -- -- Approach 2: Uses ideas from https://www.uber.com/en-DE/blog/logging/
-      -- --             but uses Dynamic type to make this a single list
+      -- Metadata
+      -- Keep raw JSON to benefit from future ClickHouse improvements.
+      -- For now, store things as "German Strings" with fast prefix matches based on https://www.uber.com/en-DE/blog/logging/.
+      metadata JSON(max_dynamic_paths=0),
       metadata_names Array(String),
-      metadata_values Array(Dynamic(max_types=32)),
-      -- -- Approach 3: 1:1 copy of https://www.uber.com/en-DE/blog/logging/
-      -- --             May require further high-level types and lots of thought during
-      -- --             write and query-time.
-      -- -- metadata_string_names Array(String),
-      -- -- metadata_string_values Array(String),
-      -- -- metadata_number_names Array(String),
-      -- -- metadata_number_values Array(Float64),
-      -- -- metadata_bool_names Array(String),
-      -- -- metadata_bool_values Array(UInt8),
-      -- -- Approach 4: Apply German strings here, where we store a prefix and for longer values a pointer.
-      metadata_keys Array(String) MATERIALIZED metadata_names,
-      metadata_prefixes Array(String) MATERIALIZED arrayMap(v -> leftUTF8(CAST(v, 'String'), 200), metadata_values),
-      metadata_hashes Array(Nullable(UInt32)) MATERIALIZED arrayMap(v -> if(lengthUTF8(CAST(v, 'String')) > 200, xxHash32(CAST(v, 'String')), NULL), metadata_values),
+      metadata_raw_values Array(String), -- should not be used on retrieval, only for materializing other columns
+      metadata_prefixes Array(String) MATERIALIZED arrayMap(v -> leftUTF8(CAST(v, 'String'), 200), metadata_raw_values),
+      metadata_hashes Array(Nullable(UInt32)) MATERIALIZED arrayMap(v -> if(lengthUTF8(CAST(v, 'String')) > 200, xxHash32(CAST(v, 'String')), NULL), metadata_raw_values),
       metadata_long_values Map(UInt32, String) MATERIALIZED mapFromArrays(
-        arrayMap(v -> xxHash32(CAST(v, 'String')), arrayFilter(v -> lengthUTF8(CAST(v, 'String')) > 200, metadata_values)),
-        arrayMap(v -> CAST(v, 'String'), arrayFilter(v -> lengthUTF8(CAST(v, 'String')) > 200, metadata_values))
+        arrayMap(v -> xxHash32(CAST(v, 'String')), arrayFilter(v -> lengthUTF8(CAST(v, 'String')) > 200, metadata_raw_values)),
+        arrayMap(v -> CAST(v, 'String'), arrayFilter(v -> lengthUTF8(CAST(v, 'String')) > 200, metadata_raw_values))
       ),
 
+      -- Experiment properties
+      experiment_id String,
+      experiment_name String,
+      experiment_metadata_names Array(String),
+      experiment_metadata_values Array(String), -- We will restrict this to 200 characters on the client.
+      experiment_description String,
+      experiment_dataset_id String,
+      experiment_item_id String,
+      experiment_item_version Nullable(DateTime64(6)),
+      experiment_item_expected_output String,
+      experiment_item_metadata_names Array(String),
+      experiment_item_metadata_values Array(String), -- We will restrict this to 200 characters on the client.
+      experiment_item_root_span_id String,
+
       -- Source metadata (Instrumentation)
       source LowCardinality(String),
       service_name String,
@@ -219,7 +250,6 @@ CREATE TABLE IF NOT EXISTS events
 
       -- Generic props
       blob_storage_file_path String,
-      event_raw String,
       event_bytes UInt64,
       created_at DateTime64(6) DEFAULT now(),
       updated_at DateTime64(6) DEFAULT now(),
@@ -248,13 +278,22 @@ CREATE TABLE IF NOT EXISTS events
   ENGINE = ReplacingMergeTree(event_ts, is_deleted)
   -- ENGINE = (Replicated)ReplacingMergeTree(event_ts, is_deleted)
   PARTITION BY toYYYYMM(start_time)
-  ORDER BY (project_id, toUnixTimestamp(start_time), xxHash32(trace_id), span_id)
+  PRIMARY KEY (project_id, start_time, xxHash32(trace_id))
+  ORDER BY (project_id, start_time, xxHash32(trace_id), span_id)
   SAMPLE BY xxHash32(trace_id)
   SETTINGS
     index_granularity = 8192,
     index_granularity_bytes = '64Mi', -- Default 10MiB. Avoid small granules due to large rows.
-    min_rows_for_wide_part = 0,
-    min_bytes_for_wide_part = 0;
+    enable_block_number_column = 1,
+    enable_block_offset_column = 1,
+    dynamic_serialization_version='v3',
+    object_serialization_version='v3',
+    object_shared_data_serialization_version='advanced',
+    object_shared_data_serialization_version_for_zero_level_parts='map_with_buckets'
+    -- Try without, but re-enable if recent row performance is bad
+    -- min_rows_for_wide_part = 0,
+    -- min_bytes_for_wide_part = 0
+  ;
 
 EOF
 
@@ -269,52 +308,55 @@ clickhouse client \
   --multiquery <<EOF
   TRUNCATE events;
   INSERT INTO events (project_id, trace_id, span_id, parent_span_id, start_time, end_time, name, type,
-                      environment, version, user_id, session_id, level, status_message, completion_start_time, prompt_id,
+                      environment, version, release, tags, trace_name, user_id, session_id, public, bookmarked, level, status_message, completion_start_time, prompt_id,
                       prompt_name, prompt_version, model_id, provided_model_name, model_parameters,
-                      provided_usage_details, usage_details, provided_cost_details, cost_details, total_cost, input,
-                      output, metadata, metadata_names, metadata_values,
+                      provided_usage_details, usage_details, provided_cost_details, cost_details, tool_definitions, tool_calls, tool_call_names, input,
+
+                      output, metadata, metadata_names, metadata_raw_values,
                       -- metadata_string_names, metadata_string_values, metadata_number_names, metadata_number_values, metadata_bool_names, metadata_bool_values,
                       source, service_name, service_version, scope_name, scope_version, telemetry_sdk_language,
-                      telemetry_sdk_name, telemetry_sdk_version, blob_storage_file_path, event_raw, event_bytes,
+                      telemetry_sdk_name, telemetry_sdk_version, blob_storage_file_path, event_bytes,
                       created_at, updated_at, event_ts, is_deleted)
-  SELECT project_id,
-         trace_id,
-         id                                                                            AS span_id,
-         parent_observation_id                                                         AS parent_span_id,
-         start_time,
-         end_time,
-         name,
-         type,
-         environment,
-         version,
-         concat('u_', floor(randUniform(1, 100)))                                      AS user_id,
-         concat('s_', floor(randUniform(1, 100)))                                      AS session_id,
-         level,
-         ifNull(status_message, '')                                                    AS status_message,
-         completion_start_time,
-         prompt_id,
-         prompt_name,
-         CAST(prompt_version, 'Nullable(String)'),
-         internal_model_id                                                             AS model_id,
-         provided_model_name,
-         model_parameters,
-         provided_usage_details,
-         usage_details,
-         provided_cost_details,
-         cost_details,
-         ifNull(total_cost, 0)                                                         AS total_cost,
-         ifNull(input, '')                                                             AS input,
-         ifNull(output, '')                                                            AS output,
-         CAST(metadata, 'JSON'),
-         mapKeys(metadata)                                                             AS \`metadata.names\`,
-         mapValues(metadata)                                                           AS \`metadata.values\`,
-         -- mapKeys(metadata)                                                             AS metadata_string_names,
-         -- mapValues(metadata)                                                           AS metadata_string_values,
-         -- []                                                                            AS metadata_number_names,
-         -- []                                                                            AS metadata_number_values,
-         -- []                                                                            AS metadata_bool_names,
-         -- []                                                                            AS metadata_bool_values,
-         multiIf(mapContains(metadata, 'resourceAttributes'), 'otel', 'ingestion-api') AS source,
+  SELECT o.project_id,
+         o.trace_id,
+         o.id                                                                            AS span_id,
+         o.parent_observation_id                                                         AS parent_span_id,
+         o.start_time,
+         o.end_time,
+         o.name,
+         o.type,
+         o.environment,
+         o.version,
+         t.release as release,
+         t.tags as tags,
+         t.name as trace_name,
+         t.user_id                                                                      AS user_id,
+         t.session_id                                                                   AS session_id,
+         t.public                                                                      AS public,
+         t.bookmarked AND (o.parent_observation_id IS NULL OR o.parent_observation_id == '') AS bookmarked,
+         o.level,
+         ifNull(o.status_message, '')                                                   AS status_message,
+         o.completion_start_time,
+         o.prompt_id,
+         o.prompt_name,
+         CAST(o.prompt_version, 'Nullable(String)'),
+         o.internal_model_id                                                             AS model_id,
+         o.provided_model_name,
+         coalesce(o.model_parameters, '{}'),
+         o.provided_usage_details,
+         o.usage_details,
+         o.provided_cost_details,
+         o.cost_details,
+         o.tool_definitions,
+         o.tool_calls,
+         o.tool_call_names,
+
+         ifNull(o.input, '')                                                             AS input,
+         ifNull(o.output, '')                                                            AS output,
+         CAST(o.metadata, 'JSON'),
+         mapKeys(o.metadata)                                                             AS metadata_names,
+         mapValues(o.metadata)                                                           AS metadata_raw_values,
+         multiIf(mapContains(o.metadata, 'resourceAttributes'), 'otel', 'ingestion-api') AS source,
          NULL                                                                          AS service_name,
          NULL                                                                          AS service_version,
          NULL                                                                          AS scope_name,
@@ -323,14 +365,72 @@ clickhouse client \
          NULL                                                                          AS telemetry_sdk_name,
          NULL                                                                          AS telemetry_sdk_version,
          ''                                                                            AS blob_storage_file_path,
-         ''                                                                            AS event_raw,
          0                                                                             AS event_bytes,
-         created_at,
-         updated_at,
-         event_ts,
-         is_deleted
-  FROM observations
-  WHERE (is_deleted = 0);
+         o.created_at,
+         o.updated_at,
+         o.event_ts,
+         o.is_deleted
+  FROM observations o FINAL
+  LEFT JOIN traces t ON o.trace_id = t.id
+  WHERE (o.is_deleted = 0);
+  -- Backfill events from traces table as well
+  INSERT INTO events (project_id, trace_id, span_id, parent_span_id, start_time, name, type,
+                      environment, version, release, tags, trace_name, user_id, session_id, public, bookmarked, level,
+                      model_parameters, provided_usage_details, usage_details, provided_cost_details, cost_details, tool_definitions, tool_calls, tool_call_names,
+
+                      input, output,
+                      metadata, metadata_names, metadata_raw_values,
+                      source, service_name, service_version, scope_name, scope_version, telemetry_sdk_language,
+                      telemetry_sdk_name, telemetry_sdk_version, blob_storage_file_path, event_bytes,
+                      created_at, updated_at, event_ts, is_deleted)
+  SELECT t.project_id,
+         t.id,
+         t.id                                                                            AS span_id,
+         ''                                                                       AS parent_span_id,
+         t.timestamp,
+         t.name,
+         'SPAN',
+         t.environment,
+         t.version,
+         t.release as release,
+         t.tags as tags,
+         t.name as trace_name,
+         t.user_id                                                                      AS user_id,
+         t.session_id                                                                   AS session_id,
+         t.public                                                                       AS public,
+         t.bookmarked                                                                   AS bookmarked,
+         'DEFAULT'                                                                      AS level,
+         map()                                                                           AS model_parameters,
+         map(),
+         map(),
+         map(),
+         map(),
+         map(),
+         [],
+         [],
+
+         ifNull(t.input, '')                                                             AS input,
+         ifNull(t.output, '')                                                            AS output,
+         CAST(t.metadata, 'JSON'),
+         mapKeys(t.metadata)                                                             AS metadata_names,
+         mapValues(t.metadata)                                                           AS metadata_raw_values,
+         multiIf(mapContains(t.metadata, 'resourceAttributes'), 'otel', 'ingestion-api') AS source,
+         NULL                                                                          AS service_name,
+         NULL                                                                          AS service_version,
+         NULL                                                                          AS scope_name,
+         NULL                                                                          AS scope_version,
+         NULL                                                                          AS telemetry_sdk_language,
+         NULL                                                                          AS telemetry_sdk_name,
+         NULL                                                                          AS telemetry_sdk_version,
+         ''                                                                            AS blob_storage_file_path,
+         0                                                                             AS event_bytes,
+         t.created_at,
+         t.updated_at,
+         t.event_ts,
+         t.is_deleted
+  FROM traces t FINAL
+  WHERE (t.is_deleted = 0);
+
 EOF
 
 echo "Development tables created successfully (or already exist)."

packages/shared/clickhouse/scripts/drop.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # Load environment variables
-source ../../.env
+[ -f ../../.env ] && source ../../.env
 
 # Check if golang-migrate is installed
 if ! command -v migrate &> /dev/null

packages/shared/package.json

@@ -62,7 +62,7 @@
     "@aws-sdk/lib-storage": "^3.675.0",
     "@aws-sdk/s3-request-presigner": "^3.679.0",
     "@azure/storage-blob": "^12.26.0",
-    "@clickhouse/client": "^1.12.1",
+    "@clickhouse/client": "^1.13.0",
     "@google-cloud/storage": "^7.17.0",
     "@langchain/anthropic": "^0.3.32",
     "@langchain/aws": "^0.1.15",
@@ -77,6 +77,8 @@
     "@slack/oauth": "^3.0.4",
     "@slack/web-api": "^7.10.0",
     "@types/bcryptjs": "^2.4.6",
+    "ajv": "^8.17.1",
+    "ajv-formats": "^3.0.1",
     "bcryptjs": "^2.4.3",
     "bullmq": "^5.34.10",
     "date-fns": "^3.3.1",
@@ -84,7 +86,7 @@
     "decimal.js": "^10.4.3",
     "exponential-backoff": "^3.1.2",
     "https-proxy-agent": "^7.0.6",
-    "ioredis": "^5.4.1",
+    "ioredis": "^5.8.2",
     "ipaddr.js": "^2.2.0",
     "jsonpath-plus": "10.3.0",
     "kysely": "^0.27.4",
@@ -93,8 +95,9 @@
     "lodash": "^4.17.21",
     "lossless-json": "^4.1.1",
     "next-auth": "^4.24.12",
-    "nodemailer": "^7.0.10",
+    "nodemailer": "^7.0.11",
     "prisma-extension-kysely": "^3.0.0",
+    "safe-regex2": "^5.0.0",
     "uuid": "^9.0.1",
     "winston": "^3.15.0",
     "zod": "^3.25.62",
@@ -105,11 +108,11 @@
     "@repo/typescript-config": "workspace:*",
     "@types/lodash": "^4.17.10",
     "@types/node": "^24.3.0",
-    "@types/nodemailer": "^7.0.3",
+    "@types/nodemailer": "^7.0.4",
     "@types/pg": "^8.11.10",
-    "@types/react": "19.2.2",
+    "@types/react": "19.2.3",
     "@types/uuid": "^9.0.8",
-    "@typescript-eslint/parser": "^7.12.0",
+    "@typescript-eslint/parser": "^8.48.1",
     "eslint": "^8.57.0",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",
@@ -124,7 +127,7 @@
     "typescript": "^5.7.2"
   },
   "peerDependencies": {
-    "@types/react": "~19.2.2",
-    "react": "~19.2.0"
+    "@types/react": "~19.2.3",
+    "react": "~19.2.3"
   }
 }

packages/shared/prisma/generated/types.ts

@@ -158,6 +158,7 @@ export type DashboardWidgetChartType =
 export const ActionType = {
   WEBHOOK: "WEBHOOK",
   SLACK: "SLACK",
+  GITHUB_DISPATCH: "GITHUB_DISPATCH",
 } as const;
 export type ActionType = (typeof ActionType)[keyof typeof ActionType];
 export const ActionExecutionStatus = {
@@ -297,6 +298,23 @@ export type BackgroundMigration = {
   worker_id: string | null;
   locked_at: Timestamp | null;
 };
+export type BatchAction = {
+  id: string;
+  created_at: Generated<Timestamp>;
+  updated_at: Generated<Timestamp>;
+  project_id: string;
+  user_id: string;
+  action_type: string;
+  table_name: string;
+  status: string;
+  finished_at: Timestamp | null;
+  query: unknown;
+  config: unknown | null;
+  total_count: number | null;
+  processed_count: number | null;
+  failed_count: number | null;
+  log: string | null;
+};
 export type BatchExport = {
   id: string;
   created_at: Generated<Timestamp>;
@@ -412,13 +430,15 @@ export type Dataset = {
   metadata: unknown | null;
   remote_experiment_url: string | null;
   remote_experiment_payload: unknown | null;
+  input_schema: unknown | null;
+  expected_output_schema: unknown | null;
   created_at: Generated<Timestamp>;
   updated_at: Generated<Timestamp>;
 };
 export type DatasetItem = {
   id: string;
   project_id: string;
-  status: Generated<DatasetStatus>;
+  status: Generated<DatasetStatus | null>;
   input: unknown | null;
   expected_output: unknown | null;
   metadata: unknown | null;
@@ -427,6 +447,24 @@ export type DatasetItem = {
   dataset_id: string;
   created_at: Generated<Timestamp>;
   updated_at: Generated<Timestamp>;
+  sys_id: Generated<string | null>;
+  valid_from: Generated<Timestamp>;
+  valid_to: Timestamp | null;
+  is_deleted: Generated<boolean>;
+};
+export type DatasetItemEvent = {
+  id: string;
+  item_id: string;
+  project_id: string;
+  dataset_id: string;
+  status: DatasetStatus | null;
+  input: unknown | null;
+  expected_output: unknown | null;
+  metadata: unknown | null;
+  source_trace_id: string | null;
+  source_observation_id: string | null;
+  created_at: Timestamp | null;
+  deleted_at: Timestamp | null;
 };
 export type DatasetRunItems = {
   id: string;
@@ -725,9 +763,20 @@ export type Price = {
   updated_at: Generated<Timestamp>;
   model_id: string;
   project_id: string | null;
+  pricing_tier_id: string;
   usage_type: string;
   price: string;
 };
+export type PricingTier = {
+  id: string;
+  created_at: Generated<Timestamp>;
+  updated_at: Generated<Timestamp>;
+  model_id: string;
+  name: string;
+  is_default: Generated<boolean>;
+  priority: number;
+  conditions: unknown;
+};
 export type Project = {
   id: string;
   org_id: string;
@@ -895,6 +944,7 @@ export type DB = {
   automation_executions: AutomationExecution;
   automations: Automation;
   background_migrations: BackgroundMigration;
+  batch_actions: BatchAction;
   batch_exports: BatchExport;
   billing_meter_backups: BillingMeterBackup;
   blob_storage_integrations: BlobStorageIntegration;
@@ -904,6 +954,7 @@ export type DB = {
   cron_jobs: CronJobs;
   dashboard_widgets: DashboardWidget;
   dashboards: Dashboard;
+  dataset_item_events: DatasetItemEvent;
   dataset_items: DatasetItem;
   dataset_run_items: DatasetRunItems;
   dataset_runs: DatasetRuns;
@@ -927,6 +978,7 @@ export type DB = {
   pending_deletions: PendingDeletion;
   posthog_integrations: PosthogIntegration;
   prices: Price;
+  pricing_tiers: PricingTier;
   project_memberships: ProjectMembership;
   projects: Project;
   prompt_dependencies: PromptDependency;

packages/shared/prisma/migrations/20251104091248_add_dataset_schema_enforcement/migration.sql

@@ -0,0 +1,4 @@
+-- AlterTable
+ALTER TABLE "datasets"
+ADD COLUMN "expected_output_schema" JSON,
+ADD COLUMN "input_schema" JSON;

packages/shared/prisma/migrations/20251118153536_add_dataset_item_event_table/migration.sql

@@ -0,0 +1,20 @@
+-- CreateTable
+CREATE TABLE "dataset_item_events" (
+    "id" TEXT NOT NULL,
+    "item_id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "dataset_id" TEXT NOT NULL,
+    "status" "DatasetStatus",
+    "input" JSONB,
+    "expected_output" JSONB,
+    "metadata" JSONB,
+    "source_trace_id" TEXT,
+    "source_observation_id" TEXT,
+    "created_at" TIMESTAMP(3),
+    "deleted_at" TIMESTAMP(3),
+
+    CONSTRAINT "dataset_item_events_pkey" PRIMARY KEY ("id")
+);
+
+-- AddForeignKey
+ALTER TABLE "dataset_item_events" ADD CONSTRAINT "dataset_item_events_dataset_id_project_id_fkey" FOREIGN KEY ("dataset_id", "project_id") REFERENCES "datasets"("id", "project_id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20251118162943_add_idx_dataset_item_events/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX "dataset_item_events_project_id_dataset_id_item_id_created_at_idx" ON "dataset_item_events"("project_id", "dataset_id", "item_id", "created_at");

packages/shared/prisma/migrations/20251126000000_add_comment_search_indexes/migration.sql

@@ -0,0 +1,5 @@
+-- Full-text search index for comment content filtering
+-- This enables efficient text search queries on comment content
+-- Uses PostgreSQL's built-in full-text search with GIN index
+CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_comments_content_gin
+ON comments USING gin(to_tsvector('english', content));

packages/shared/prisma/migrations/20251127105316_add_pricing_tiers/migration.sql

@@ -0,0 +1,63 @@
+BEGIN;
+
+-- CreateTable
+CREATE TABLE "pricing_tiers" (
+    "id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "model_id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "is_default" BOOLEAN NOT NULL DEFAULT false,
+    "priority" INTEGER NOT NULL,
+    "conditions" JSONB NOT NULL,
+
+    CONSTRAINT "pricing_tiers_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "pricing_tiers_model_id_priority_key" ON "pricing_tiers"("model_id", "priority");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "pricing_tiers_model_id_name_key" ON "pricing_tiers"("model_id", "name");
+
+-- AddForeignKey
+ALTER TABLE "pricing_tiers" ADD CONSTRAINT "pricing_tiers_model_id_fkey" FOREIGN KEY ("model_id") REFERENCES "models"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AlterTable
+ALTER TABLE "prices" ADD COLUMN "pricing_tier_id" TEXT;
+
+-- Data Migration: Create default pricing tiers with DETERMINISTIC IDs
+-- Pattern: {model_id}_tier_default
+INSERT INTO "pricing_tiers" (id, model_id, name, is_default, priority, conditions)
+SELECT
+  model_id || '_tier_default',
+  model_id,
+  'Standard',
+  TRUE,
+  0,
+  '[]'::jsonb
+FROM (
+  SELECT DISTINCT model_id
+  FROM prices
+  WHERE pricing_tier_id IS NULL
+) AS distinct_models
+ON CONFLICT (id) DO NOTHING;
+
+-- Data Migration: Link existing prices to their default tiers using deterministic IDs
+UPDATE prices
+SET pricing_tier_id = model_id || '_tier_default'
+WHERE pricing_tier_id IS NULL;
+
+-- AlterTable: Make pricing_tier_id NOT NULL
+ALTER TABLE "prices" ALTER COLUMN "pricing_tier_id" SET NOT NULL;
+
+-- AddForeignKey
+ALTER TABLE "prices" ADD CONSTRAINT "prices_pricing_tier_id_fkey" FOREIGN KEY ("pricing_tier_id") REFERENCES "pricing_tiers"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- DropIndex
+DROP INDEX IF EXISTS "prices_model_id_usage_type_key";
+
+-- CreateIndex
+CREATE UNIQUE INDEX "prices_model_id_usage_type_pricing_tier_id_key" ON "prices"("model_id", "usage_type", "pricing_tier_id");
+
+COMMIT;

packages/shared/prisma/migrations/20251127181728_add_prices_index_on_pricing_tier_id/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX CONCURRENTLY "prices_pricing_tier_id_idx" ON "prices"("pricing_tier_id");

packages/shared/prisma/migrations/20251201095227_dataset_items_add_version_cols/migration.sql

@@ -0,0 +1,14 @@
+BEGIN;
+
+-- 1. Add columns 
+ALTER TABLE "dataset_items" 
+    ADD COLUMN "is_deleted" BOOLEAN NOT NULL DEFAULT false,
+    ADD COLUMN "sys_id" TEXT, 
+    ADD COLUMN "valid_from" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    ALTER COLUMN "status" DROP NOT NULL;
+
+-- 2. Set default for NEW rows
+ALTER TABLE "dataset_items" 
+    ALTER COLUMN "sys_id" SET DEFAULT md5(random()::text || clock_timestamp()::text)::uuid::text;
+
+COMMIT;

packages/shared/prisma/migrations/20251204213345_add_github_dispatch_action_type/migration.sql

@@ -0,0 +1,6 @@
+-- Migration: Add GitHub Dispatch Action Type
+-- This migration adds support for GitHub repository dispatch actions by:
+-- 1. Adding GITHUB_DISPATCH to the ActionType enum
+
+-- AlterEnum
+ALTER TYPE "ActionType" ADD VALUE 'GITHUB_DISPATCH';

packages/shared/prisma/migrations/20251208121203_dataset_run_items_drop_fk_dataset_items/migration.sql

@@ -0,0 +1,2 @@
+-- DropForeignKey
+ALTER TABLE "dataset_run_items" DROP CONSTRAINT "dataset_run_items_dataset_item_id_project_id_fkey";

packages/shared/prisma/migrations/20251210130559_add_batch_action_table/migration.sql

@@ -0,0 +1,32 @@
+-- CreateTable
+CREATE TABLE "batch_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,
+    "user_id" TEXT NOT NULL,
+    "action_type" TEXT NOT NULL,
+    "table_name" TEXT NOT NULL,
+    "status" TEXT NOT NULL,
+    "finished_at" TIMESTAMP(3),
+    "query" JSONB NOT NULL,
+    "config" JSONB,
+    "total_count" INTEGER,
+    "processed_count" INTEGER,
+    "failed_count" INTEGER,
+    "log" TEXT,
+
+    CONSTRAINT "batch_actions_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "batch_actions_project_id_user_id_idx" ON "batch_actions"("project_id", "user_id");
+
+-- CreateIndex
+CREATE INDEX "batch_actions_status_idx" ON "batch_actions"("status");
+
+-- CreateIndex
+CREATE INDEX "batch_actions_project_id_action_type_idx" ON "batch_actions"("project_id", "action_type");
+
+-- AddForeignKey
+ALTER TABLE "batch_actions" ADD CONSTRAINT "batch_actions_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20251210133946_dataset_items_create_idx_id_project_id_valid_from/migration.sql

@@ -0,0 +1,9 @@
+/*
+  Warnings:
+
+  - A unique constraint covering the columns `[id,project_id,valid_from]` on the table `dataset_items` will be added. If there are existing duplicate values, this will fail.
+
+*/
+-- CreateIndex
+CREATE UNIQUE INDEX CONCURRENTLY IF NOT EXISTS "dataset_items_id_project_id_valid_from_key" ON "dataset_items"("id", "project_id", "valid_from");
+

packages/shared/prisma/migrations/20251211204006_dataset_items_switch_pk/migration.sql

@@ -0,0 +1,9 @@
+/*
+  Warnings:
+
+  - The primary key for the `dataset_items` table will be changed. If it partially fails, the table could be left without primary key constraint.
+
+*/
+-- AlterTable
+ALTER TABLE "dataset_items" DROP CONSTRAINT "dataset_items_pkey",
+ADD CONSTRAINT "dataset_items_pkey" PRIMARY KEY USING INDEX "dataset_items_id_project_id_valid_from_key";

packages/shared/prisma/migrations/20251215230232_dataset_items_add_idx_project_id_id_valid_from/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX CONCURRENTLY IF NOT EXISTS "dataset_items_project_id_id_valid_from_idx" ON "dataset_items"("project_id", "id", "valid_from");

packages/shared/prisma/migrations/20251215233730_dataset_items_add_valid_to/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "dataset_items" ADD COLUMN "valid_to" TIMESTAMP(3);

packages/shared/prisma/migrations/20251215233903_dataset_items_add_idx_project_id_valid_to/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX "dataset_items_project_id_valid_to_idx" ON "dataset_items"("project_id", "valid_to");

packages/shared/prisma/migrations/20251215233905_backfill_dataset_items_valid_to/migration.sql

@@ -0,0 +1,2 @@
+INSERT INTO background_migrations (id, name, script, args)
+VALUES ('d4f5a6b7-c8d9-4e1f-a2b3-c4d5e6f7a8b8', '20251216_1001_backfill_dataset_items_valid_to', 'backfillValidToForDatasetItems', '{}');

packages/shared/prisma/schema.prisma

@@ -153,6 +153,7 @@ model Project {
   BlobStorageIntegration    BlobStorageIntegration[]
   scoreConfig               ScoreConfig[]
   BatchExport               BatchExport[]
+  BatchAction               BatchAction[]
   comment                   Comment[]
   commentReactions          CommentReaction[]
   annotationQueue           AnnotationQueue[]
@@ -591,18 +592,21 @@ model CronJobs {
 }
 
 model Dataset {
-  id                      String        @default(cuid())
-  projectId               String        @map("project_id")
+  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")
+  remoteExperimentUrl     String?            @map("remote_experiment_url")
+  remoteExperimentPayload Json?              @map("remote_experiment_payload")
+  inputSchema             Json?              @map("input_schema") @db.Json
+  expectedOutputSchema    Json?              @map("expected_output_schema") @db.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[]
+  datasetItemEvents       DatasetItemEvent[]
 
   @@id([id, projectId])
   @@unique([projectId, name])
@@ -612,21 +616,27 @@ model Dataset {
 }
 
 model DatasetItem {
-  id                  String            @default(cuid())
-  projectId           String            @map("project_id")
-  status              DatasetStatus     @default(ACTIVE)
+  id                  String         @default(cuid())
+  projectId           String         @map("project_id")
+  status              DatasetStatus? @default(ACTIVE)
   input               Json?
-  expectedOutput      Json?             @map("expected_output")
+  expectedOutput      Json?          @map("expected_output")
   metadata            Json?
-  sourceTraceId       String?           @map("source_trace_id")
-  sourceObservationId String?           @map("source_observation_id")
-  datasetId           String            @map("dataset_id")
-  dataset             Dataset           @relation(fields: [datasetId, projectId], references: [id, projectId], onDelete: Cascade)
-  createdAt           DateTime          @default(now()) @map("created_at")
-  updatedAt           DateTime          @default(now()) @updatedAt @map("updated_at")
-  datasetRunItems     DatasetRunItems[]
+  sourceTraceId       String?        @map("source_trace_id")
+  sourceObservationId String?        @map("source_observation_id")
+  datasetId           String         @map("dataset_id")
+  dataset             Dataset        @relation(fields: [datasetId, projectId], references: [id, projectId], onDelete: Cascade)
+  createdAt           DateTime       @default(now()) @map("created_at")
+  updatedAt           DateTime       @default(now()) @updatedAt @map("updated_at")
+  // dataset version cols
+  sysId               String?        @default(dbgenerated()) @map("sys_id")
+  validFrom           DateTime       @default(now()) @map("valid_from")
+  validTo             DateTime?      @map("valid_to")
+  isDeleted           Boolean        @default(false) @map("is_deleted")
 
-  @@id([id, projectId])
+  @@id([id, projectId, validFrom])
+  @@index([projectId, validTo])
+  @@index([projectId, id, validFrom])
   @@index([sourceTraceId], type: Hash)
   @@index([sourceObservationId], type: Hash)
   @@index([datasetId], type: Hash)
@@ -635,6 +645,25 @@ model DatasetItem {
   @@map("dataset_items")
 }
 
+model DatasetItemEvent {
+  id                  String         @id @default(cuid())
+  itemId              String         @map("item_id")
+  projectId           String         @map("project_id")
+  datasetId           String         @map("dataset_id")
+  dataset             Dataset        @relation(fields: [datasetId, projectId], references: [id, projectId], onDelete: Cascade)
+  status              DatasetStatus?
+  input               Json?
+  expectedOutput      Json?          @map("expected_output")
+  metadata            Json?
+  sourceTraceId       String?        @map("source_trace_id")
+  sourceObservationId String?        @map("source_observation_id")
+  createdAt           DateTime?      @map("created_at")
+  deletedAt           DateTime?      @map("deleted_at")
+
+  @@index([projectId, datasetId, itemId, createdAt])
+  @@map("dataset_item_events")
+}
+
 enum DatasetStatus {
   ACTIVE
   ARCHIVED
@@ -666,7 +695,6 @@ model DatasetRunItems {
   datasetRunId  String      @map("dataset_run_id")
   datasetRun    DatasetRuns @relation(fields: [datasetRunId, projectId], references: [id, projectId], onDelete: Cascade)
   datasetItemId String      @map("dataset_item_id")
-  datasetItem   DatasetItem @relation(fields: [datasetItemId, projectId], references: [id, projectId], onDelete: Cascade)
   traceId       String      @map("trace_id")
   observationId String?     @map("observation_id")
   createdAt     DateTime    @default(now()) @map("created_at")
@@ -818,16 +846,17 @@ model Model {
   projectId String?  @map("project_id")
   project   Project? @relation(fields: [projectId], references: [id], onDelete: Cascade)
 
-  modelName       String    @map("model_name")
-  matchPattern    String    @map("match_pattern")
-  startDate       DateTime? @map("start_date")
-  inputPrice      Decimal?  @map("input_price")
-  outputPrice     Decimal?  @map("output_price")
-  totalPrice      Decimal?  @map("total_price")
+  modelName       String        @map("model_name")
+  matchPattern    String        @map("match_pattern")
+  startDate       DateTime?     @map("start_date")
+  inputPrice      Decimal?      @map("input_price")
+  outputPrice     Decimal?      @map("output_price")
+  totalPrice      Decimal?      @map("total_price")
   unit            String? // TOKENS, CHARACTERS, MILLISECONDS, SECONDS, REQUESTS, or IMAGES
-  tokenizerId     String?   @map("tokenizer_id")
-  tokenizerConfig Json?     @map("tokenizer_config")
+  tokenizerId     String?       @map("tokenizer_id")
+  tokenizerConfig Json?         @map("tokenizer_config")
   Price           Price[]
+  pricingTiers    PricingTier[]
 
   @@unique([projectId, modelName, startDate, unit])
   @@index(modelName)
@@ -835,18 +864,41 @@ model Model {
 }
 
 model Price {
+  id            String      @id @default(cuid())
+  createdAt     DateTime    @default(now()) @map("created_at")
+  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)
+  pricingTierId String      @map("pricing_tier_id")
+  pricingTier   PricingTier @relation(fields: [pricingTierId], references: [id], onDelete: Cascade)
+  usageType     String      @map("usage_type")
+  price         Decimal
+
+  @@unique([modelId, usageType, pricingTierId])
+  @@index(pricingTierId)
+  @@map("prices")
+}
+
+model PricingTier {
   id        String   @id @default(cuid())
   createdAt DateTime @default(now()) @map("created_at")
   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
 
-  @@unique([modelId, usageType])
-  @@map("prices")
+  modelId String @map("model_id")
+  model   Model  @relation(fields: [modelId], references: [id], onDelete: Cascade)
+
+  name       String  @map("name")
+  isDefault  Boolean @default(false) @map("is_default")
+  priority   Int     @map("priority")
+  conditions Json    @map("conditions") @db.JsonB
+
+  prices Price[]
+
+  @@unique([modelId, priority])
+  @@unique([modelId, name])
+  @@map("pricing_tiers")
 }
 
 enum AuditLogRecordType {
@@ -1127,6 +1179,35 @@ model BatchExport {
   @@map("batch_exports")
 }
 
+model BatchAction {
+  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)
+  userId    String  @map("user_id")
+
+  actionType String @map("action_type")
+  tableName  String @map("table_name")
+
+  status     String
+  finishedAt DateTime? @map("finished_at")
+
+  query  Json
+  config Json?
+
+  totalCount     Int?    @map("total_count")
+  processedCount Int?    @map("processed_count")
+  failedCount    Int?    @map("failed_count")
+  log            String?
+
+  @@index([projectId, userId])
+  @@index([status])
+  @@index([projectId, actionType])
+  @@map("batch_actions")
+}
+
 model Media {
   id               String
   sha256Hash       String             @map("sha_256_hash") @db.Char(44)
@@ -1399,6 +1480,7 @@ model Automation {
 enum ActionType {
   WEBHOOK
   SLACK
+  GITHUB_DISPATCH
   // More action types can be added as needed
 }
 

packages/shared/scripts/seeder/seed-dataset-versions.ts

@@ -0,0 +1,210 @@
+import { PrismaClient } from "../../src/index";
+import { logger } from "../../src/server";
+
+// Config
+const ITEM_COUNT = 500;
+const BULK_VERSIONS = 5;
+const ITEMS_PER_BULK_VERSION = 100;
+const ADDITIONAL_VERSIONS = 5;
+const TOTAL_VERSIONS = 10;
+
+const TEST_DATASET_NAME = "version-perf-test";
+
+interface VersionData {
+  timestamp: Date;
+  operations: Array<{
+    itemId: string;
+    operation: "create" | "update" | "delete";
+    status: "ACTIVE" | null;
+    input?: any;
+    expectedOutput?: any;
+    metadata?: any;
+    validFrom?: Date;
+  }>;
+}
+
+export async function seedDatasetVersions(
+  prismaClient: PrismaClient,
+  projectIds: string[],
+) {
+  logger.info("Starting dataset version test data generation");
+
+  for (const projectId of projectIds) {
+    // Create test dataset
+    const dataset = await prismaClient.dataset.upsert({
+      where: {
+        projectId_name: {
+          projectId,
+          name: TEST_DATASET_NAME,
+        },
+      },
+      create: {
+        name: TEST_DATASET_NAME,
+        projectId,
+        description: "Performance test dataset for versioning",
+      },
+      update: {},
+    });
+
+    logger.info(`Dataset created/found: ${dataset.id}`);
+
+    // Generate version timeline
+    const versions: VersionData[] = [];
+    const baseTime = new Date("2024-01-01T00:00:00Z");
+
+    // Create 5 bulk insert versions (10k items each)
+    for (let v = 0; v < BULK_VERSIONS; v++) {
+      const timestamp = new Date(baseTime.getTime() + v * 60 * 60 * 1000); // 1 hour apart
+      const operations = [];
+
+      for (let i = 0; i < ITEMS_PER_BULK_VERSION; i++) {
+        const itemId = `item-${v * ITEMS_PER_BULK_VERSION + i}`;
+        operations.push({
+          itemId,
+          operation: "create" as const,
+          input: { prompt: `Initial prompt for ${itemId}` },
+          expectedOutput: { response: `Initial response for ${itemId}` },
+          metadata: { version: v, batch: true },
+          status: "ACTIVE" as const,
+        });
+      }
+
+      versions.push({ timestamp, operations });
+    }
+
+    logger.info(
+      `Created ${BULK_VERSIONS} bulk versions with ${ITEMS_PER_BULK_VERSION} items each`,
+    );
+
+    // Create additional versions with mixed operations
+    const existingItemIds = Array.from(
+      { length: BULK_VERSIONS * ITEMS_PER_BULK_VERSION },
+      (_, i) => `item-${i}`,
+    );
+
+    for (let v = 0; v < ADDITIONAL_VERSIONS; v++) {
+      const timestamp = new Date(
+        baseTime.getTime() + (BULK_VERSIONS + v) * 60 * 60 * 1000,
+      );
+      const operations = [];
+      const operationCount = Math.floor(Math.random() * 100) + 50; // 50-150 operations per version
+
+      for (let i = 0; i < operationCount; i++) {
+        const rand = Math.random();
+        const itemId =
+          existingItemIds[Math.floor(Math.random() * existingItemIds.length)];
+
+        if (rand < 0.7) {
+          // 70% updates
+          operations.push({
+            itemId,
+            operation: "update" as const,
+            input: { prompt: `Updated prompt v${v} for ${itemId}` },
+            expectedOutput: {
+              response: `Updated response v${v} for ${itemId}`,
+            },
+            status: "ACTIVE" as const,
+            metadata: { version: v + BULK_VERSIONS, updated: true },
+          });
+        } else if (rand < 0.85) {
+          // 15% deletes
+          operations.push({
+            itemId,
+            operation: "delete" as const,
+            input: null,
+            expectedOutput: null,
+            metadata: null,
+            status: null,
+            validFrom: timestamp,
+          });
+        } else {
+          // 15% creates (new items)
+          const newItemId = `item-${BULK_VERSIONS * ITEMS_PER_BULK_VERSION + v * 100 + i}`;
+          existingItemIds.push(newItemId);
+          operations.push({
+            itemId: newItemId,
+            operation: "create" as const,
+            input: { prompt: `New prompt v${v} for ${newItemId}` },
+            expectedOutput: { response: `New response v${v} for ${newItemId}` },
+            status: "ACTIVE" as const,
+            metadata: { version: v + BULK_VERSIONS, new: true },
+          });
+        }
+      }
+      versions.push({ timestamp, operations });
+    }
+
+    logger.info(
+      `Created ${ADDITIONAL_VERSIONS} additional versions with mixed operations`,
+    );
+
+    // Insert all data
+    logger.info("Starting bulk insert...");
+    let totalInserts = 0;
+    const BATCH_SIZE = 1000;
+
+    for (const version of versions) {
+      const items = version.operations.map((op) => {
+        const baseRow = {
+          id: op.itemId, // The logical item ID (stays same across versions)
+          projectId,
+          datasetId: dataset.id,
+          input: op.input,
+          expectedOutput: op.expectedOutput,
+          metadata: op.metadata,
+          status: op.status,
+          sourceTraceId: null,
+          sourceObservationId: null,
+        };
+        if (op.operation === "delete") {
+          return {
+            ...baseRow,
+            validFrom: op.validFrom, // When this version became valid
+            isDeleted: true, // Soft delete flag
+          };
+        } else {
+          return {
+            ...baseRow,
+            validFrom: version.timestamp, // When this version became valid
+          };
+        }
+      });
+
+      // Insert in batches directly into dataset_items (versioned table)
+      for (let i = 0; i < items.length; i += BATCH_SIZE) {
+        const batch = items.slice(i, i + BATCH_SIZE);
+        await prismaClient.datasetItem.createMany({
+          data: batch,
+          skipDuplicates: true, // Skip if already exists (handles re-runs)
+        });
+        totalInserts += batch.length;
+      }
+
+      // After inserting the new version, update valid_to on previous versions
+      // This marks old versions as superseded by the new version
+      const itemIds = items.map((item) => item.id);
+      const validFrom = version.timestamp;
+
+      await prismaClient.$executeRaw`
+        UPDATE dataset_items
+        SET valid_to = ${validFrom}
+        WHERE project_id = ${projectId}
+          AND dataset_id = ${dataset.id}
+          AND id = ANY(${itemIds}::text[])
+          AND valid_from < ${validFrom}
+          AND valid_to IS NULL
+      `;
+
+      if (totalInserts % 10000 === 0) {
+        logger.info(`Inserted ${totalInserts} rows...`);
+      }
+    }
+
+    logger.info(
+      `✅ Complete! Inserted ${totalInserts} total version rows into dataset_items`,
+    );
+    logger.info(`   Dataset: ${TEST_DATASET_NAME}`);
+    logger.info(`   Versions: ${TOTAL_VERSIONS}`);
+    logger.info(`   Unique items: ~${ITEM_COUNT}`);
+  }
+}

packages/shared/scripts/seeder/seed-postgres.ts

@@ -29,6 +29,7 @@ import {
   generateEvalScoreId,
   generateEvalTraceId,
 } from "./utils/seed-helpers";
+import { seedDatasetVersions } from "./seed-dataset-versions";
 
 const options = {
   environment: { type: "string" },
@@ -346,6 +347,7 @@ async function main() {
     );
 
     await createDashboardsAndWidgets([project1, project2]);
+    await seedDatasetVersions(prisma, [project1.id, project2.id]);
 
     await prisma.llmSchema.createMany({
       data: [
@@ -521,6 +523,8 @@ export async function createDatasets(
         }));
 
       const datasetItemIds: string[] = [];
+      const itemsToCreate = [];
+
       for (let index = 0; index < data.items.length; index++) {
         const item = data.items[index];
         const sourceTraceId =
@@ -528,27 +532,31 @@ export async function createDatasets(
             ? `${Math.floor(Math.random() * 100)}`
             : undefined;
 
-        // Use upsert to prevent duplicates
-        const datasetItem = await prisma.datasetItem.upsert({
-          where: {
-            id_projectId: {
-              id: generateDatasetItemId(datasetName, index, projectId),
-              projectId,
-            },
-          },
-          create: {
-            projectId,
-            id: generateDatasetItemId(datasetName, index, projectId),
-            datasetId: dataset.id,
-            sourceTraceId: sourceTraceId ?? null,
-            sourceObservationId: null,
-            input: item.input,
-            expectedOutput: item.output,
-            metadata: Math.random() > 0.5 ? { key: "value" } : undefined,
-          },
-          update: {}, // Don't update if it exists
+        const itemId = generateDatasetItemId(datasetName, index, projectId);
+        datasetItemIds.push(itemId);
+
+        // Create dataset items in versioned format with all required fields
+        itemsToCreate.push({
+          id: itemId,
+          projectId,
+          datasetId: dataset.id,
+          sourceTraceId: sourceTraceId ?? null,
+          sourceObservationId: null,
+          input: item.input,
+          expectedOutput: item.output,
+          metadata: Math.random() > 0.5 ? { key: "value" } : undefined,
+          status: "ACTIVE" as const,
+          validFrom: new Date(),
+          isDeleted: false,
+        });
+      }
+
+      // Bulk insert all items (use createMany for better performance)
+      if (itemsToCreate.length > 0) {
+        await prisma.datasetItem.createMany({
+          data: itemsToCreate,
+          skipDuplicates: true, // Skip if already exists (handles re-runs)
         });
-        datasetItemIds.push(datasetItem.id);
       }
 
       for (let datasetRunNumber = 0; datasetRunNumber < 3; datasetRunNumber++) {

packages/shared/scripts/seeder/utils/clickhouse-builder.ts

@@ -193,7 +193,9 @@ export class ClickHouseQueryBuilder {
         start_time AS created_at,
         start_time AS updated_at,
         start_time AS event_ts,
-        0 AS is_deleted
+        0 AS is_deleted,
+        '' AS usage_pricing_tier_id,
+        '' AS usage_pricing_tier_name
       FROM numbers(${totalObservations});
     `;
   }

packages/shared/scripts/seeder/utils/framework-traces/pydantic-ai-trace-2025-06-06.json

@@ -1,312 +0,0 @@
-{
-  "trace": {
-    "id": "25f4bdeebaab60e6e1bee7e8469554bc",
-    "projectId": "cloramnkj0002jz088vzn1ja4",
-    "name": "pydantic-ai-qa-trace",
-    "timestamp": "2025-06-06T14:40:28.562Z",
-    "environment": "default",
-    "tags": ["dev", "pydantic-ai"],
-    "bookmarked": false,
-    "release": null,
-    "version": "1.0.0",
-    "userId": "user_123",
-    "sessionId": "session_abc",
-    "public": true,
-    "input": "\"What is Langfuse?\"",
-    "output": "\"Langfuse is a tool designed for observability and monitoring of applications that utilize large language models (LLMs). It provides features to trace, log, and visualize requests, helping developers understand the behavior of their LLM-powered applications more effectively. This can be particularly useful for debugging, performance optimization, and ensuring reliable operation of systems that depend on LLMs. Langfuse is designed to integrate easily with existing infrastructure, supporting both self-hosted implementations and cloud-based solutions.\"",
-    "metadata": "{\"email\":\"user@langfuse.com\",\"resourceAttributes\":{\"telemetry.sdk.language\":\"python\",\"telemetry.sdk.name\":\"opentelemetry\",\"telemetry.sdk.version\":\"1.33.1\",\"service.name\":\"unknown_service\"},\"scope\":{\"name\":\"langfuse-sdk\",\"version\":\"3.0.0\",\"attributes\":{\"public_key\":\"pk-lf-5855d85e-3943-497e-bd10-f50ad414bcba\"}}}",
-    "createdAt": "2025-06-06T14:40:34.000Z",
-    "updatedAt": "2025-06-06T14:40:33.635Z",
-    "latency": 4.795
-  },
-  "observations": [
-    {
-      "id": "538fed87d11686d3",
-      "traceId": "25f4bdeebaab60e6e1bee7e8469554bc",
-      "projectId": "cloramnkj0002jz088vzn1ja4",
-      "type": "SPAN",
-      "environment": "default",
-      "parentObservationId": null,
-      "startTime": "2025-06-06T14:40:28.562Z",
-      "endTime": "2025-06-06T14:40:33.357Z",
-      "name": "pydantic-ai-qa-trace",
-      "level": "DEFAULT",
-      "statusMessage": null,
-      "version": "1.0.0",
-      "modelParameters": null,
-      "completionStartTime": null,
-      "promptId": null,
-      "createdAt": "2025-06-06T14:40:33.595Z",
-      "updatedAt": "2025-06-06T14:40:33.630Z",
-      "usageDetails": {},
-      "costDetails": {},
-      "providedCostDetails": {},
-      "model": null,
-      "internalModelId": null,
-      "promptName": null,
-      "promptVersion": null,
-      "latency": 4795,
-      "timeToFirstToken": null,
-      "inputCost": null,
-      "outputCost": null,
-      "totalCost": 0,
-      "inputUsage": 0,
-      "outputUsage": 0,
-      "totalUsage": 0,
-      "input": null,
-      "output": null,
-      "metadata": {
-        "resourceAttributes": {
-          "telemetry.sdk.language": "python",
-          "telemetry.sdk.name": "opentelemetry",
-          "telemetry.sdk.version": "1.33.1",
-          "service.name": "unknown_service"
-        },
-        "scope": {
-          "name": "langfuse-sdk",
-          "version": "3.0.0",
-          "attributes": {
-            "public_key": "pk-lf-5855d85e-3943-497e-bd10-f50ad414bcba"
-          }
-        }
-      }
-    },
-    {
-      "id": "0a4fac2553f22f2e",
-      "traceId": "25f4bdeebaab60e6e1bee7e8469554bc",
-      "projectId": "cloramnkj0002jz088vzn1ja4",
-      "type": "SPAN",
-      "environment": "default",
-      "parentObservationId": "538fed87d11686d3",
-      "startTime": "2025-06-06T14:40:28.562Z",
-      "endTime": "2025-06-06T14:40:33.357Z",
-      "name": "qa_agent run",
-      "level": "DEFAULT",
-      "statusMessage": null,
-      "version": null,
-      "modelParameters": null,
-      "completionStartTime": null,
-      "promptId": null,
-      "createdAt": "2025-06-06T14:40:33.596Z",
-      "updatedAt": "2025-06-06T14:40:33.641Z",
-      "usageDetails": {},
-      "costDetails": {},
-      "providedCostDetails": {},
-      "model": null,
-      "internalModelId": null,
-      "promptName": null,
-      "promptVersion": null,
-      "latency": 4795,
-      "timeToFirstToken": null,
-      "inputCost": null,
-      "outputCost": null,
-      "totalCost": 0,
-      "inputUsage": 0,
-      "outputUsage": 0,
-      "totalUsage": 0,
-      "input": null,
-      "output": [
-        {
-          "content": "You are a helpful assistant that answers questions clearly and concisely.",
-          "role": "system",
-          "gen_ai.message.index": 0,
-          "event.name": "gen_ai.system.message"
-        },
-        {
-          "content": "What is Langfuse?",
-          "role": "user",
-          "gen_ai.message.index": 0,
-          "event.name": "gen_ai.user.message"
-        },
-        {
-          "role": "assistant",
-          "content": "Langfuse is a tool designed for observability and monitoring of applications that utilize large language models (LLMs). It provides features to trace, log, and visualize requests, helping developers understand the behavior of their LLM-powered applications more effectively. This can be particularly useful for debugging, performance optimization, and ensuring reliable operation of systems that depend on LLMs. Langfuse is designed to integrate easily with existing infrastructure, supporting both self-hosted implementations and cloud-based solutions.",
-          "gen_ai.message.index": 1,
-          "event.name": "gen_ai.assistant.message"
-        }
-      ],
-      "metadata": {
-        "attributes": {
-          "model_name": "gpt-4o",
-          "agent_name": "qa_agent",
-          "logfire.msg": "qa_agent run",
-          "final_result": "Langfuse is a tool designed for observability and monitoring of applications that utilize large language models (LLMs). It provides features to trace, log, and visualize requests, helping developers understand the behavior of their LLM-powered applications more effectively. This can be particularly useful for debugging, performance optimization, and ensuring reliable operation of systems that depend on LLMs. Langfuse is designed to integrate easily with existing infrastructure, supporting both self-hosted implementations and cloud-based solutions.",
-          "gen_ai.usage.input_tokens": "31",
-          "gen_ai.usage.output_tokens": "96",
-          "all_messages_events": [
-            {
-              "content": "You are a helpful assistant that answers questions clearly and concisely.",
-              "role": "system",
-              "gen_ai.message.index": 0,
-              "event.name": "gen_ai.system.message"
-            },
-            {
-              "content": "What is Langfuse?",
-              "role": "user",
-              "gen_ai.message.index": 0,
-              "event.name": "gen_ai.user.message"
-            },
-            {
-              "role": "assistant",
-              "content": "Langfuse is a tool designed for observability and monitoring of applications that utilize large language models (LLMs). It provides features to trace, log, and visualize requests, helping developers understand the behavior of their LLM-powered applications more effectively. This can be particularly useful for debugging, performance optimization, and ensuring reliable operation of systems that depend on LLMs. Langfuse is designed to integrate easily with existing infrastructure, supporting both self-hosted implementations and cloud-based solutions.",
-              "gen_ai.message.index": 1,
-              "event.name": "gen_ai.assistant.message"
-            }
-          ],
-          "logfire.json_schema": {
-            "type": "object",
-            "properties": {
-              "all_messages_events": {
-                "type": "array"
-              },
-              "final_result": {
-                "type": "object"
-              }
-            }
-          }
-        },
-        "resourceAttributes": {
-          "telemetry.sdk.language": "python",
-          "telemetry.sdk.name": "opentelemetry",
-          "telemetry.sdk.version": "1.33.1",
-          "service.name": "unknown_service"
-        },
-        "scope": {
-          "name": "pydantic-ai",
-          "version": "0.2.15",
-          "attributes": {}
-        }
-      }
-    },
-    {
-      "id": "5cb389a3bdd21a6e",
-      "traceId": "25f4bdeebaab60e6e1bee7e8469554bc",
-      "projectId": "cloramnkj0002jz088vzn1ja4",
-      "type": "GENERATION",
-      "environment": "default",
-      "parentObservationId": "0a4fac2553f22f2e",
-      "startTime": "2025-06-06T14:40:28.562Z",
-      "endTime": "2025-06-06T14:40:33.356Z",
-      "name": "chat gpt-4o",
-      "level": "DEFAULT",
-      "statusMessage": null,
-      "version": null,
-      "modelParameters": {},
-      "completionStartTime": null,
-      "promptId": null,
-      "createdAt": "2025-06-06T14:40:33.440Z",
-      "updatedAt": "2025-06-06T14:40:33.478Z",
-      "usageDetails": {
-        "input": 31,
-        "output": 96,
-        "total": 127
-      },
-      "costDetails": {
-        "input": 0.0000775,
-        "output": 0.00096,
-        "total": 0.0010375
-      },
-      "providedCostDetails": {},
-      "model": "gpt-4o",
-      "internalModelId": "b9854a5c92dc496b997d99d20",
-      "promptName": null,
-      "promptVersion": null,
-      "latency": 4794,
-      "timeToFirstToken": null,
-      "inputCost": 0.0000775,
-      "outputCost": 0.00096,
-      "totalCost": 0.0010375,
-      "inputUsage": 31,
-      "outputUsage": 96,
-      "totalUsage": 127,
-      "input": [
-        {
-          "content": "You are a helpful assistant that answers questions clearly and concisely.",
-          "role": "system",
-          "gen_ai.system": "openai",
-          "gen_ai.message.index": 0,
-          "event.name": "gen_ai.system.message"
-        },
-        {
-          "content": "What is Langfuse?",
-          "role": "user",
-          "gen_ai.system": "openai",
-          "gen_ai.message.index": 0,
-          "event.name": "gen_ai.user.message"
-        }
-      ],
-      "output": {
-        "index": 0,
-        "message": {
-          "role": "assistant",
-          "content": "Langfuse is a tool designed for observability and monitoring of applications that utilize large language models (LLMs). It provides features to trace, log, and visualize requests, helping developers understand the behavior of their LLM-powered applications more effectively. This can be particularly useful for debugging, performance optimization, and ensuring reliable operation of systems that depend on LLMs. Langfuse is designed to integrate easily with existing infrastructure, supporting both self-hosted implementations and cloud-based solutions."
-        },
-        "gen_ai.system": "openai",
-        "event.name": "gen_ai.choice"
-      },
-      "metadata": {
-        "attributes": {
-          "gen_ai.operation.name": "chat",
-          "gen_ai.system": "openai",
-          "gen_ai.request.model": "gpt-4o",
-          "server.address": "api.openai.com",
-          "model_request_parameters": {
-            "function_tools": [],
-            "allow_text_output": true,
-            "output_tools": []
-          },
-          "gen_ai.usage.input_tokens": "31",
-          "gen_ai.usage.output_tokens": "96",
-          "gen_ai.response.model": "gpt-4o-2024-08-06",
-          "events": [
-            {
-              "content": "You are a helpful assistant that answers questions clearly and concisely.",
-              "role": "system",
-              "gen_ai.system": "openai",
-              "gen_ai.message.index": 0,
-              "event.name": "gen_ai.system.message"
-            },
-            {
-              "content": "What is Langfuse?",
-              "role": "user",
-              "gen_ai.system": "openai",
-              "gen_ai.message.index": 0,
-              "event.name": "gen_ai.user.message"
-            },
-            {
-              "index": 0,
-              "message": {
-                "role": "assistant",
-                "content": "Langfuse is a tool designed for observability and monitoring of applications that utilize large language models (LLMs). It provides features to trace, log, and visualize requests, helping developers understand the behavior of their LLM-powered applications more effectively. This can be particularly useful for debugging, performance optimization, and ensuring reliable operation of systems that depend on LLMs. Langfuse is designed to integrate easily with existing infrastructure, supporting both self-hosted implementations and cloud-based solutions."
-              },
-              "gen_ai.system": "openai",
-              "event.name": "gen_ai.choice"
-            }
-          ],
-          "logfire.json_schema": {
-            "type": "object",
-            "properties": {
-              "events": {
-                "type": "array"
-              },
-              "model_request_parameters": {
-                "type": "object"
-              }
-            }
-          }
-        },
-        "resourceAttributes": {
-          "telemetry.sdk.language": "python",
-          "telemetry.sdk.name": "opentelemetry",
-          "telemetry.sdk.version": "1.33.1",
-          "service.name": "unknown_service"
-        },
-        "scope": {
-          "name": "pydantic-ai",
-          "version": "0.2.15",
-          "attributes": {}
-        }
-      }
-    }
-  ]
-}

packages/shared/src/domain/automations.ts

@@ -37,7 +37,7 @@ export type ActionDomainWithSecrets = Omit<Action, "config"> & {
   config: ActionConfigWithSecrets;
 };
 
-export const ActionTypeSchema = z.enum(["WEBHOOK", "SLACK"]);
+export const ActionTypeSchema = z.enum(["WEBHOOK", "SLACK", "GITHUB_DISPATCH"]);
 
 export const AvailableWebhookApiSchema = z.record(
   z.enum(["prompt"]),
@@ -87,19 +87,54 @@ export const SlackActionConfigSchema = z.object({
 
 export type SlackActionConfig = z.infer<typeof SlackActionConfigSchema>;
 
+export const GitHubDispatchActionConfigSchema = z.object({
+  type: z.literal("GITHUB_DISPATCH"),
+  url: z.url(),
+  eventType: z.string().min(1).max(100),
+  githubToken: z.string(),
+  displayGitHubToken: z.string(),
+  lastFailingExecutionId: z.string().nullish(),
+});
+
+export const SafeGitHubDispatchActionConfigSchema =
+  GitHubDispatchActionConfigSchema.omit({
+    githubToken: true,
+  });
+
+export type SafeGitHubDispatchActionConfig = z.infer<
+  typeof SafeGitHubDispatchActionConfigSchema
+>;
+
+export const GitHubDispatchActionCreateSchema = z.object({
+  type: z.literal("GITHUB_DISPATCH"),
+  url: z.string().url().optional(), // Optional for updates, validated in helper
+  eventType: z.string().min(1).max(100).optional(), // Optional for updates, validated in helper
+  githubToken: z.string().optional(), // Optional for updates, validated in helper
+});
+
+export type GitHubDispatchActionCreate = z.infer<
+  typeof GitHubDispatchActionCreateSchema
+>;
+export type GitHubDispatchActionConfigWithSecrets = z.infer<
+  typeof GitHubDispatchActionConfigSchema
+>;
+
 export const ActionConfigSchema = z.discriminatedUnion("type", [
   WebhookActionConfigSchema,
   SlackActionConfigSchema,
+  GitHubDispatchActionConfigSchema,
 ]);
 
 export const ActionCreateSchema = z.discriminatedUnion("type", [
   WebhookActionCreateSchema,
   SlackActionConfigSchema,
+  GitHubDispatchActionCreateSchema,
 ]);
 
 export const SafeActionConfigSchema = z.discriminatedUnion("type", [
   SafeWebhookActionConfigSchema,
   SlackActionConfigSchema,
+  SafeGitHubDispatchActionConfigSchema,
 ]);
 
 export type ActionTypes = z.infer<typeof ActionTypeSchema>;
@@ -169,3 +204,52 @@ export function convertToSafeWebhookConfig(
     lastFailingExecutionId: webhookConfig.lastFailingExecutionId,
   };
 }
+
+/**
+ * Type guard to check if a config is a valid GitHub dispatch configuration with secrets
+ */
+export function isGitHubDispatchActionConfig(
+  config: unknown,
+): config is GitHubDispatchActionConfigWithSecrets {
+  return GitHubDispatchActionConfigSchema.safeParse(config).success;
+}
+
+/**
+ * Type guard to check if an entire action has valid GitHub dispatch configuration
+ */
+export function isGitHubDispatchAction(action: {
+  type: string;
+  config: unknown;
+}): action is {
+  type: "GITHUB_DISPATCH";
+  config: GitHubDispatchActionConfigWithSecrets;
+} {
+  return (
+    action.type === "GITHUB_DISPATCH" &&
+    isGitHubDispatchActionConfig(action.config)
+  );
+}
+
+/**
+ * Type guard for safe GitHub dispatch config (without secrets)
+ */
+export function isSafeGitHubDispatchActionConfig(
+  config: unknown,
+): config is SafeGitHubDispatchActionConfig {
+  return SafeGitHubDispatchActionConfigSchema.safeParse(config).success;
+}
+
+/**
+ * Converts GitHub dispatch config with secrets to safe config by only including allowed fields
+ */
+export function convertToSafeGitHubDispatchConfig(
+  config: GitHubDispatchActionConfigWithSecrets,
+): SafeGitHubDispatchActionConfig {
+  return {
+    type: config.type,
+    url: config.url,
+    eventType: config.eventType,
+    displayGitHubToken: config.displayGitHubToken,
+    lastFailingExecutionId: config.lastFailingExecutionId,
+  };
+}

packages/shared/src/domain/dataset-items.ts

@@ -0,0 +1,27 @@
+import { DatasetItem, DatasetStatus } from "../db";
+
+export type DatasetItemDomain = Pick<
+  DatasetItem,
+  | "id"
+  | "projectId"
+  | "datasetId"
+  | "input"
+  | "expectedOutput"
+  | "metadata"
+  | "sourceTraceId"
+  | "sourceObservationId"
+  | "createdAt"
+  | "updatedAt"
+  | "validFrom"
+> & {
+  status: DatasetStatus;
+};
+
+/**
+ * DatasetItemDomain without IO fields (input, expectedOutput, metadata)
+ * Used for listing items without fetching large payloads
+ */
+export type DatasetItemDomainWithoutIO = Omit<
+  DatasetItemDomain,
+  "input" | "expectedOutput" | "metadata"
+>;

packages/shared/src/domain/index.ts

@@ -5,3 +5,4 @@ export * from "./table-view-presets";
 export * from "./automations";
 export * from "./webhooks";
 export * from "./prompts";
+export * from "./dataset-items";

packages/shared/src/domain/observations.ts

@@ -90,15 +90,35 @@ export const ObservationSchema = z.object({
   inputUsage: z.number(),
   outputUsage: z.number(),
   totalUsage: z.number(),
+  // pricing tier information
+  usagePricingTierId: z.string().nullable(),
+  usagePricingTierName: z.string().nullable(),
 });
 
 export type Observation = z.infer<typeof ObservationSchema>;
 
+export type ObservationCoreFields = Pick<
+  Observation,
+  "id" | "traceId" | "startTime" | "projectId" | "parentObservationId"
+>;
+
+export const EventsObservationSchema = ObservationSchema.extend({
+  userId: z.string().nullable(),
+  sessionId: z.string().nullable(),
+});
+
+export type EventsObservation = z.infer<typeof EventsObservationSchema>;
+
+export type PartialObservation = Partial<Observation> & ObservationCoreFields;
+
+export type PartialEventsObservation = Partial<EventsObservation> &
+  ObservationCoreFields;
+
 /**
  * Returns true if an observation type is generation-like, meaning it could include LLM calls
  * and potentially has similar input/output fields.
  */
-export const GenerationLikeObservationTypes = [
+const GenerationLikeObservationTypes = [
   ObservationType.GENERATION,
   ObservationType.AGENT,
   ObservationType.TOOL,

packages/shared/src/domain/scores.ts

@@ -1,38 +1,80 @@
 import z from "zod/v4";
 import { MetadataDomain } from "./traces";
-import { ScoreDataType } from "@prisma/client";
 
-export const ScoreSource = {
-  ANNOTATION: "ANNOTATION",
+export const ScoreSourceArray = ["API", "EVAL", "ANNOTATION"] as const;
+export const ScoreSourceEnum = {
   API: "API",
   EVAL: "EVAL",
+  ANNOTATION: "ANNOTATION",
 } as const;
-
-export const ScoreSourceDomain = z.enum(["ANNOTATION", "API", "EVAL"]);
+export const ScoreSourceDomain = z.enum(ScoreSourceArray);
 export type ScoreSourceType = z.infer<typeof ScoreSourceDomain>;
 
-export const ScoreSchema = z.object({
+export const ScoreDataTypeArray = [
+  "NUMERIC",
+  "CATEGORICAL",
+  "BOOLEAN",
+] as const;
+export const ScoreDataTypeEnum = {
+  NUMERIC: "NUMERIC",
+  CATEGORICAL: "CATEGORICAL",
+  BOOLEAN: "BOOLEAN",
+} as const;
+export const ScoreDataTypeDomain = z.enum(ScoreDataTypeArray);
+export type ScoreDataTypeType = z.infer<typeof ScoreDataTypeDomain>;
+
+export const NumericData = z.object({
+  stringValue: z.union([z.null(), z.undefined()]),
+  dataType: z.literal("NUMERIC"),
+});
+
+export const CategoricalData = z.object({
+  stringValue: z.string(),
+  dataType: z.literal("CATEGORICAL"),
+});
+
+export const BooleanData = z.object({
+  stringValue: z.string(),
+  dataType: z.literal("BOOLEAN"),
+});
+
+// Only used for backwards compatibility with old score API schemas
+export const ScoreSchemaExclReferencesAndDates = z.object({
+  // Core identifiers
   id: z.string(),
-  timestamp: z.date(),
   projectId: z.string(),
+  // Metadata
   environment: z.string(),
+  // Score data
   name: z.string(),
-  value: z.number().nullable(),
+  value: z.number(),
   source: ScoreSourceDomain,
   authorUserId: z.string().nullable(),
   comment: z.string().nullable(),
-  traceId: z.string().nullable(),
-  sessionId: z.string().nullable(),
-  datasetRunId: z.string().nullable(),
   metadata: MetadataDomain,
-  observationId: z.string().nullable(),
+  // Score associations
   configId: z.string().nullable(),
-  stringValue: z.string().nullable(),
   queueId: z.string().nullable(),
+  // Score execution
   executionTraceId: z.string().nullable(),
-  createdAt: z.date(),
-  updatedAt: z.date(),
-  dataType: z.enum(ScoreDataType),
 });
 
+const ScoreFoundationSchema = ScoreSchemaExclReferencesAndDates.and(
+  z.object({
+    // Timestamps
+    createdAt: z.date(),
+    updatedAt: z.date(),
+    timestamp: z.date(),
+    // Score references; one of the following must be provided
+    traceId: z.string().nullable(),
+    sessionId: z.string().nullable(),
+    datasetRunId: z.string().nullable(),
+    observationId: z.string().nullable(),
+  }),
+);
+
+export const ScoreSchema = ScoreFoundationSchema.and(
+  z.discriminatedUnion("dataType", [NumericData, CategoricalData, BooleanData]),
+);
+
 export type ScoreDomain = z.infer<typeof ScoreSchema>;

packages/shared/src/domain/webhooks.ts

@@ -35,3 +35,12 @@ export const PromptWebhookOutboundSchema = z
   .and(WebhookOutboundBaseSchema);
 
 export type PromptWebhookOutput = z.infer<typeof PromptWebhookOutboundSchema>;
+
+export const GitHubDispatchWebhookOutboundSchema = z.object({
+  event_type: z.string(),
+  client_payload: PromptWebhookOutboundSchema,
+});
+
+export type GitHubDispatchWebhookOutput = z.infer<
+  typeof GitHubDispatchWebhookOutboundSchema
+>;

packages/shared/src/env.ts

@@ -22,10 +22,22 @@ const EnvSchema = z.object({
   REDIS_TLS_CA_PATH: z.string().optional(),
   REDIS_TLS_CERT_PATH: z.string().optional(),
   REDIS_TLS_KEY_PATH: z.string().optional(),
+  REDIS_TLS_SERVERNAME: z.string().optional(),
+  REDIS_TLS_REJECT_UNAUTHORIZED: z.enum(["true", "false"]).optional(),
+  REDIS_TLS_CHECK_SERVER_IDENTITY: z.enum(["true", "false"]).optional(),
+  REDIS_TLS_SECURE_PROTOCOL: z.string().optional(),
+  REDIS_TLS_CIPHERS: z.string().optional(),
+  REDIS_TLS_HONOR_CIPHER_ORDER: z.enum(["true", "false"]).optional(),
+  REDIS_TLS_KEY_PASSPHRASE: z.string().optional(),
   REDIS_ENABLE_AUTO_PIPELINING: z.enum(["true", "false"]).default("true"),
   // Redis Cluster Configuration
   REDIS_CLUSTER_ENABLED: z.enum(["true", "false"]).default("false"),
   REDIS_CLUSTER_NODES: z.string().optional(),
+  REDIS_SENTINEL_ENABLED: z.enum(["true", "false"]).default("false"),
+  REDIS_SENTINEL_NODES: z.string().optional(),
+  REDIS_SENTINEL_MASTER_NAME: z.string().optional(),
+  REDIS_SENTINEL_USERNAME: z.string().optional(),
+  REDIS_SENTINEL_PASSWORD: z.string().optional(),
   ENCRYPTION_KEY: z
     .string()
     .length(
@@ -45,6 +57,15 @@ const EnvSchema = z.object({
   CLICKHOUSE_PASSWORD: z.string(),
   CLICKHOUSE_KEEP_ALIVE_IDLE_SOCKET_TTL: z.coerce.number().int().default(9000),
   CLICKHOUSE_MAX_OPEN_CONNECTIONS: z.coerce.number().int().default(25),
+  // Optional to allow for server-setting fallbacks
+  CLICKHOUSE_ASYNC_INSERT_MAX_DATA_SIZE: z.string().optional(),
+  CLICKHOUSE_ASYNC_INSERT_BUSY_TIMEOUT_MS: z.coerce.number().int().optional(),
+  CLICKHOUSE_LIGHTWEIGHT_DELETE_MODE: z
+    .enum(["alter_update", "lightweight_update", "lightweight_update_force"])
+    .default("alter_update"),
+  CLICKHOUSE_UPDATE_PARALLEL_MODE: z
+    .enum(["sync", "async", "auto"])
+    .default("auto"),
 
   LANGFUSE_INGESTION_QUEUE_DELAY_MS: z.coerce
     .number()
@@ -59,10 +80,15 @@ const EnvSchema = z.object({
     .number()
     .positive()
     .default(1),
+  LANGFUSE_TRACE_UPSERT_QUEUE_ATTEMPTS: z.coerce.number().positive().default(2),
   LANGFUSE_TRACE_DELETE_DELAY_MS: z.coerce
     .number()
     .nonnegative()
     .default(5_000),
+  LANGFUSE_TRACE_DELETE_SKIP_PROJECT_IDS: z
+    .string()
+    .optional()
+    .transform((s) => (s ? s.split(",").map((id) => id.trim()) : [])),
   SALT: z.string().optional(), // used by components imported by web package
   LANGFUSE_LOG_LEVEL: z
     .enum(["trace", "debug", "info", "warn", "error", "fatal"])
@@ -113,6 +139,13 @@ const EnvSchema = z.object({
     .default("true"),
 
   LANGFUSE_S3_LIST_MAX_KEYS: z.coerce.number().positive().default(200),
+  LANGFUSE_S3_RATE_ERROR_SLOWDOWN_ENABLED: z
+    .enum(["true", "false"])
+    .default("false"),
+  LANGFUSE_S3_RATE_ERROR_SLOWDOWN_TTL_SECONDS: z.coerce
+    .number()
+    .positive()
+    .default(3600), // 1 hour
   LANGFUSE_S3_CORE_DATA_EXPORT_IS_ENABLED: z
     .enum(["true", "false"])
     .default("false"),
@@ -219,11 +252,31 @@ const EnvSchema = z.object({
 
   LANGFUSE_AWS_BEDROCK_REGION: z.string().optional(),
 
+  // API Performance Flags
+  // Whether to add a `FINAL` modifier to the observations CTE in GET /api/public/traces.
+  // Can be used to improve performance for self-hosters that are fully on the new OTel SDKs.
+  LANGFUSE_API_CLICKHOUSE_DISABLE_OBSERVATIONS_FINAL: z
+    .enum(["true", "false"])
+    .default("false"),
+  // Enable Redis-based tracking of projects using OTEL API to optimize ClickHouse queries.
+  // When enabled, projects ingesting via OTEL API skip the FINAL modifier on some observations queries for better performance.
+  LANGFUSE_SKIP_FINAL_FOR_OTEL_PROJECTS: z
+    .enum(["true", "false"])
+    .default("false"),
+
   // Langfuse AI Features
   LANGFUSE_AI_FEATURES_PUBLIC_KEY: z.string().optional(),
   LANGFUSE_AI_FEATURES_SECRET_KEY: z.string().optional(),
   LANGFUSE_AI_FEATURES_HOST: z.string().optional(),
   LANGFUSE_AI_FEATURES_PROJECT_ID: z.string().optional(),
+
+  // Dataset Service
+  LANGFUSE_DATASET_SERVICE_WRITE_TO_VERSIONED_IMPLEMENTATION: z
+    .enum(["true", "false"])
+    .default("true"),
+  LANGFUSE_DATASET_SERVICE_READ_FROM_VERSIONED_IMPLEMENTATION: z
+    .enum(["true", "false"])
+    .default("true"),
 });
 
 export const env: z.infer<typeof EnvSchema> =

packages/shared/src/eventsTable.ts

@@ -0,0 +1,238 @@
+import { type ColumnDefinition } from "./tableDefinitions";
+
+// Column definitions for the ClickHouse events table
+// Used for filtering, sorting, and mapping UI columns to ClickHouse columns
+export const eventsTableCols: ColumnDefinition[] = [
+  {
+    name: "ID",
+    id: "id",
+    type: "stringOptions",
+    internal: "e.span_id",
+    options: [], // to be added at runtime
+  },
+  {
+    name: "Trace ID",
+    id: "traceId",
+    type: "string",
+    internal: "e.trace_id",
+  },
+  {
+    name: "Start Time",
+    id: "startTime",
+    type: "datetime",
+    internal: "e.start_time",
+  },
+  {
+    name: "End Time",
+    id: "endTime",
+    type: "datetime",
+    internal: "e.end_time",
+    nullable: true,
+  },
+  {
+    name: "Name",
+    id: "name",
+    type: "stringOptions",
+    internal: "e.name",
+    options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "Type",
+    id: "type",
+    type: "stringOptions",
+    internal: "e.type",
+    options: [],
+  },
+  {
+    name: "Environment",
+    id: "environment",
+    type: "stringOptions",
+    internal: "e.environment",
+    options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "Version",
+    id: "version",
+    type: "string",
+    internal: "e.version",
+    nullable: true,
+  },
+  {
+    name: "User ID",
+    id: "userId",
+    type: "string",
+    internal: "e.user_id",
+    nullable: true,
+  },
+  {
+    name: "Session ID",
+    id: "sessionId",
+    type: "string",
+    internal: "e.session_id",
+    nullable: true,
+  },
+  {
+    name: "Level",
+    id: "level",
+    type: "stringOptions",
+    internal: "e.level",
+    options: [],
+  },
+  {
+    name: "Status Message",
+    id: "statusMessage",
+    type: "string",
+    internal: "e.status_message",
+    nullable: true,
+  },
+  {
+    name: "Prompt Name",
+    id: "promptName",
+    type: "stringOptions",
+    internal: "e.prompt_name",
+    options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "Model ID",
+    id: "modelId",
+    type: "stringOptions",
+    internal: "e.model_id",
+    options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "Provided Model Name",
+    id: "providedModelName",
+    type: "stringOptions",
+    internal: "e.provided_model_name",
+    options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "Total Cost ($)",
+    id: "totalCost",
+    type: "number",
+    internal:
+      "if(mapExists((k, v) -> (k = 'total'), cost_details), cost_details['total'], NULL)",
+    nullable: true,
+  },
+  {
+    name: "Input Tokens",
+    id: "inputTokens",
+    type: "number",
+    internal:
+      "arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'input') > 0, usage_details)))",
+    nullable: true,
+  },
+  {
+    name: "Output Tokens",
+    id: "outputTokens",
+    type: "number",
+    internal:
+      "arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'output') > 0, usage_details)))",
+    nullable: true,
+  },
+  {
+    name: "Total Tokens",
+    id: "totalTokens",
+    type: "number",
+    internal:
+      "if(mapExists((k, v) -> (k = 'total'), usage_details), usage_details['total'], NULL)",
+    nullable: true,
+  },
+  {
+    name: "Input Cost ($)",
+    id: "inputCost",
+    type: "number",
+    internal:
+      "arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'input') > 0, cost_details)))",
+    nullable: true,
+  },
+  {
+    name: "Output Cost ($)",
+    id: "outputCost",
+    type: "number",
+    internal:
+      "arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'output') > 0, cost_details)))",
+    nullable: true,
+  },
+  {
+    name: "Latency (s)",
+    id: "latency",
+    type: "number",
+    internal: "date_diff('millisecond', e.start_time, e.end_time) / 1000.0",
+    nullable: true,
+  },
+  {
+    name: "Time To First Token (s)",
+    id: "timeToFirstToken",
+    type: "number",
+    internal:
+      "date_diff('millisecond', e.start_time, e.completion_start_time) / 1000.0",
+    nullable: true,
+  },
+  {
+    name: "Tokens per second",
+    id: "tokensPerSecond",
+    type: "number",
+    internal:
+      "(arraySum(mapValues(mapFilter(x -> positionCaseInsensitive(x.1, 'output') > 0, usage_details))) / (date_diff('millisecond', start_time, end_time) / 1000))",
+    nullable: true,
+  },
+  {
+    name: "Input",
+    id: "input",
+    type: "string",
+    internal: "e.input",
+    nullable: true,
+  },
+  {
+    name: "Output",
+    id: "output",
+    type: "string",
+    internal: "e.output",
+    nullable: true,
+  },
+  {
+    name: "Metadata",
+    id: "metadata",
+    type: "stringObject",
+    internal: "e.metadata",
+  },
+  {
+    name: "Trace Tags",
+    id: "traceTags",
+    type: "arrayOptions",
+    internal: "t.tags",
+    options: [], // to be added at runtime
+  },
+  {
+    name: "Scores (numeric)",
+    id: "scores_avg",
+    type: "numberObject",
+    internal: "scores_avg",
+  },
+  {
+    name: "Scores (categorical)",
+    id: "score_categories",
+    type: "categoryOptions",
+    internal: "score_categories",
+    options: [], // to be added at runtime
+    nullable: true,
+  },
+  {
+    name: "Comment Count",
+    id: "commentCount",
+    type: "number",
+    internal: "", // handled by comment filter helpers
+  },
+  {
+    name: "Comment Content",
+    id: "commentContent",
+    type: "string",
+    internal: "", // handled by comment filter helpers
+  },
+];

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

@@ -1,30 +1,6 @@
 import z from "zod/v4";
-import { type ScoreDataType } from "../../db";
 import { StringNoHTML, StringNoHTMLNonEmpty } from "../../utils/zod";
-
-const NUMERIC: ScoreDataType = "NUMERIC";
-const CATEGORICAL: ScoreDataType = "CATEGORICAL";
-const BOOLEAN: ScoreDataType = "BOOLEAN";
-
-export const availableDataTypes = [NUMERIC, CATEGORICAL, BOOLEAN] as const;
-
-const NumericData = z.object({
-  value: z.number(),
-  stringValue: z.undefined().nullish(),
-  dataType: z.literal("NUMERIC"),
-});
-
-const CategoricalData = z.object({
-  value: z.number().nullish(),
-  stringValue: z.string(),
-  dataType: z.literal("CATEGORICAL"),
-});
-
-const BooleanData = z.object({
-  value: z.number(),
-  stringValue: z.string(),
-  dataType: z.literal("BOOLEAN"),
-});
+import { BooleanData, CategoricalData, NumericData } from "../../domain";
 
 const ScoreTargetTrace = z.object({
   type: z.literal("trace"),
@@ -50,13 +26,14 @@ export type ScoreTarget = z.infer<typeof ScoreTarget>;
 const CreateAnnotationScoreBase = z.object({
   id: z.string().optional(),
   name: StringNoHTMLNonEmpty,
+  value: z.number(),
   projectId: z.string(),
   environment: z.string().default("default"),
   scoreTarget: ScoreTarget,
   configId: z.string(),
   comment: StringNoHTML.nullish(),
   queueId: z.string().nullish(),
-  timestamp: z.date().optional(), // Required for ClickHouse deduplication
+  timestamp: z.coerce.date().optional(), // Required for ClickHouse deduplication - coerce handles string/number inputs
 });
 
 const UpdateAnnotationScoreBase = CreateAnnotationScoreBase.extend({
@@ -67,11 +44,9 @@ const UpdateAnnotationScoreBase = CreateAnnotationScoreBase.extend({
  * CreateAnnotationScoreData is only used for annotation scores created via the UI.
  * For langfuse score types please refer to `web/src/features/public-api/types/scores.ts`
  */
-export const CreateAnnotationScoreData = z.discriminatedUnion("dataType", [
-  CreateAnnotationScoreBase.merge(NumericData),
-  CreateAnnotationScoreBase.merge(CategoricalData),
-  CreateAnnotationScoreBase.merge(BooleanData),
-]);
+export const CreateAnnotationScoreData = CreateAnnotationScoreBase.and(
+  z.discriminatedUnion("dataType", [NumericData, CategoricalData, BooleanData]),
+);
 
 export type CreateAnnotationScoreData = z.infer<
   typeof CreateAnnotationScoreData
@@ -81,11 +56,9 @@ export type CreateAnnotationScoreData = z.infer<
  * UpdateAnnotationScoreData is only used for annotation scores updated via the UI
  * For langfuse score types please refer to `web/src/features/public-api/types/scores.ts`
  */
-export const UpdateAnnotationScoreData = z.discriminatedUnion("dataType", [
-  UpdateAnnotationScoreBase.merge(NumericData),
-  UpdateAnnotationScoreBase.merge(CategoricalData),
-  UpdateAnnotationScoreBase.merge(BooleanData),
-]);
+export const UpdateAnnotationScoreData = UpdateAnnotationScoreBase.and(
+  z.discriminatedUnion("dataType", [NumericData, CategoricalData, BooleanData]),
+);
 
 export type UpdateAnnotationScoreData = z.infer<
   typeof UpdateAnnotationScoreData

packages/shared/src/features/batchAction/addToDatasetTypes.ts

@@ -0,0 +1,70 @@
+import z from "zod/v4";
+
+// Source field type
+export const SourceFieldSchema = z.enum(["input", "output", "metadata"]);
+
+// Mapping mode for each field
+export const MappingModeSchema = z.enum(["full", "custom", "none"]);
+
+// Mapping target type: "root" extracts single value, "keyValueMap" builds an object
+export const MappingTargetSchema = z.enum(["root", "keyValueMap"]);
+
+// Root mapping config - single JSON path extraction
+export const RootMappingConfigSchema = z.object({
+  sourceField: SourceFieldSchema,
+  jsonPath: z.string(),
+});
+
+// Key-value mapping entry - key-value pair for building objects
+export const KeyValueMappingEntrySchema = z.object({
+  id: z.string(),
+  key: z.string().min(1, "Key is required"),
+  sourceField: SourceFieldSchema,
+  value: z.string(), // JSON path if starts with $, else literal string
+});
+
+// Custom mapping config - either root or key-value map type
+export const CustomMappingConfigSchema = z.object({
+  type: MappingTargetSchema,
+  rootConfig: RootMappingConfigSchema.optional(),
+  keyValueMapConfig: z
+    .object({
+      entries: z
+        .array(KeyValueMappingEntrySchema)
+        .min(1, "At least one entry is required"),
+    })
+    .optional(),
+});
+
+// Per-field mapping config
+export const FieldMappingConfigSchema = z.object({
+  mode: MappingModeSchema,
+  custom: CustomMappingConfigSchema.optional(),
+});
+
+// Complete mapping config for all three fields
+export const AddToDatasetMappingSchema = z.object({
+  input: FieldMappingConfigSchema,
+  expectedOutput: FieldMappingConfigSchema,
+  metadata: FieldMappingConfigSchema,
+});
+
+// Config for the batch action
+export const ObservationAddToDatasetConfigSchema = z.object({
+  datasetId: z.string(),
+  datasetName: z.string(),
+  mapping: AddToDatasetMappingSchema,
+});
+
+// Type exports
+export type SourceField = z.infer<typeof SourceFieldSchema>;
+export type MappingMode = z.infer<typeof MappingModeSchema>;
+export type MappingTarget = z.infer<typeof MappingTargetSchema>;
+export type RootMappingConfig = z.infer<typeof RootMappingConfigSchema>;
+export type KeyValueMappingEntry = z.infer<typeof KeyValueMappingEntrySchema>;
+export type CustomMappingConfig = z.infer<typeof CustomMappingConfigSchema>;
+export type FieldMappingConfig = z.infer<typeof FieldMappingConfigSchema>;
+export type AddToDatasetMapping = z.infer<typeof AddToDatasetMappingSchema>;
+export type ObservationAddToDatasetConfig = z.infer<
+  typeof ObservationAddToDatasetConfigSchema
+>;

packages/shared/src/features/batchAction/applyFieldMapping.ts

@@ -0,0 +1,219 @@
+import { JSONPath } from "jsonpath-plus";
+import { set } from "lodash";
+import type {
+  FieldMappingConfig,
+  SourceField,
+  AddToDatasetMapping,
+} from "./addToDatasetTypes";
+
+type ObservationData = {
+  input: unknown;
+  output: unknown;
+  metadata: unknown;
+};
+
+/**
+ * Test if a JSON path is valid against the given data
+ */
+export function testJsonPath(props: { jsonPath: string; data: unknown }): {
+  success: boolean;
+  error?: string;
+} {
+  try {
+    const parsed =
+      typeof props.data === "string" ? JSON.parse(props.data) : props.data;
+    JSONPath({ path: props.jsonPath, json: parsed });
+    return { success: true };
+  } catch (error) {
+    return {
+      success: false,
+      error: error instanceof Error ? error.message : "Unknown error",
+    };
+  }
+}
+
+/**
+ * Evaluate a JSON path against the given data and return the result
+ */
+export function evaluateJsonPath(data: unknown, jsonPath: string): unknown {
+  try {
+    const parsed = typeof data === "string" ? JSON.parse(data) : data;
+    const results = JSONPath({ path: jsonPath, json: parsed });
+    return results?.[0];
+  } catch {
+    return undefined;
+  }
+}
+
+/**
+ * Check if a value is a JSON path (starts with $)
+ */
+export function isJsonPath(value: string): boolean {
+  return value.startsWith("$");
+}
+
+/**
+ * Set a value at a nested path using dot notation.
+ * Creates intermediate objects as needed.
+ * Uses lodash's set which has built-in prototype pollution protection.
+ *
+ * @example
+ * setNestedValue({}, "context.user_id", "123")
+ * // Returns: { context: { user_id: "123" } }
+ */
+function setNestedValue(
+  obj: Record<string, unknown>,
+  path: string,
+  value: unknown,
+): void {
+  set(obj, path, value);
+}
+
+/**
+ * Apply field mapping config to get the result for a single field
+ */
+export function applyFieldMappingConfig(props: {
+  observation: ObservationData;
+  config: FieldMappingConfig;
+  defaultSourceField: SourceField;
+}): unknown {
+  const { observation, config, defaultSourceField } = props;
+
+  switch (config.mode) {
+    case "full":
+      // Return the full source field
+      return observation[defaultSourceField];
+
+    case "none":
+      // Return null (will be written as Prisma.DbNull)
+      return null;
+
+    case "custom":
+      if (!config.custom) {
+        return observation[defaultSourceField];
+      }
+
+      if (config.custom.type === "root") {
+        // Root mode: extract single value using JSON path
+        const rootConfig = config.custom.rootConfig;
+        if (!rootConfig) {
+          return observation[defaultSourceField];
+        }
+
+        const sourceData = observation[rootConfig.sourceField];
+        return evaluateJsonPath(sourceData, rootConfig.jsonPath);
+      }
+
+      if (config.custom.type === "keyValueMap") {
+        // Key-value map mode: build object from entries
+        // Supports dot notation for nested objects (e.g., "context.user_id")
+        const keyValueMapConfig = config.custom.keyValueMapConfig;
+        if (!keyValueMapConfig || keyValueMapConfig.entries.length === 0) {
+          return observation[defaultSourceField];
+        }
+
+        const result: Record<string, unknown> = {};
+        for (const entry of keyValueMapConfig.entries) {
+          // Skip entries with empty values
+          if (!entry.value && entry.value !== "") {
+            continue;
+          }
+
+          let resolvedValue: unknown;
+          if (isJsonPath(entry.value)) {
+            // It's a JSON path - evaluate it
+            const sourceData = observation[entry.sourceField];
+            resolvedValue = evaluateJsonPath(sourceData, entry.value);
+          } else {
+            // It's a literal string (including empty string)
+            resolvedValue = entry.value;
+          }
+
+          // Use dot notation path setter for nested objects
+          if (entry.key.includes(".")) {
+            setNestedValue(result, entry.key, resolvedValue);
+          } else {
+            result[entry.key] = resolvedValue;
+          }
+        }
+        return result;
+      }
+
+      return observation[defaultSourceField];
+
+    default:
+      return observation[defaultSourceField];
+  }
+}
+
+/**
+ * Apply the full mapping config to an observation and return the dataset item fields
+ */
+export function applyFullMapping(props: {
+  observation: ObservationData;
+  mapping: AddToDatasetMapping;
+}): {
+  input: unknown;
+  expectedOutput: unknown;
+  metadata: unknown;
+} {
+  const { observation, mapping } = props;
+
+  return {
+    input: applyFieldMappingConfig({
+      observation,
+      config: mapping.input,
+      defaultSourceField: "input",
+    }),
+    expectedOutput: applyFieldMappingConfig({
+      observation,
+      config: mapping.expectedOutput,
+      defaultSourceField: "output",
+    }),
+    metadata: applyFieldMappingConfig({
+      observation,
+      config: mapping.metadata,
+      defaultSourceField: "metadata",
+    }),
+  };
+}
+
+/**
+ * Generate autocomplete suggestions for JSON paths based on the data structure
+ */
+export function generateJsonPathSuggestions(
+  data: unknown,
+  prefix: string = "$",
+): string[] {
+  const suggestions: string[] = [];
+
+  if (data === null || data === undefined) {
+    return suggestions;
+  }
+
+  if (typeof data === "object") {
+    if (Array.isArray(data)) {
+      // For arrays, suggest index access and wildcard
+      suggestions.push(`${prefix}[0]`);
+      suggestions.push(`${prefix}[*]`);
+      // Also recurse into first element
+      if (data.length > 0) {
+        suggestions.push(
+          ...generateJsonPathSuggestions(data[0], `${prefix}[0]`),
+        );
+      }
+    } else {
+      // For objects, suggest each key
+      for (const [key, value] of Object.entries(
+        data as Record<string, unknown>,
+      )) {
+        const childPath = `${prefix}.${key}`;
+        suggestions.push(childPath);
+        // Recurse into nested objects/arrays
+        suggestions.push(...generateJsonPathSuggestions(value, childPath));
+      }
+    }
+  }
+
+  return suggestions;
+}

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

@@ -10,15 +10,24 @@ export enum BatchActionType {
   Delete = "delete",
 }
 
-const ActionIdSchema = z.enum([
-  "score-delete",
-  "trace-delete",
-  "trace-add-to-annotation-queue",
-  "session-add-to-annotation-queue",
-  "observation-add-to-annotation-queue",
-]);
+export enum BatchActionStatus {
+  Queued = "QUEUED",
+  Processing = "PROCESSING",
+  Completed = "COMPLETED",
+  Failed = "FAILED",
+  Partial = "PARTIAL",
+}
 
-export type ActionId = z.infer<typeof ActionIdSchema>;
+export enum ActionId {
+  ScoreDelete = "score-delete",
+  TraceDelete = "trace-delete",
+  TraceAddToAnnotationQueue = "trace-add-to-annotation-queue",
+  SessionAddToAnnotationQueue = "session-add-to-annotation-queue",
+  ObservationAddToAnnotationQueue = "observation-add-to-annotation-queue",
+  ObservationAddToDataset = "observation-add-to-dataset",
+}
+
+const ActionIdSchema = z.nativeEnum(ActionId);
 
 export const BatchActionQuerySchema = z.object({
   filter: z.array(singleFilter).nullable(),

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

@@ -12,6 +12,7 @@ export enum BatchExportStatus {
   PROCESSING = "PROCESSING", // eslint-disable-line no-unused-vars
   COMPLETED = "COMPLETED", // eslint-disable-line no-unused-vars
   FAILED = "FAILED", // eslint-disable-line no-unused-vars
+  CANCELLED = "CANCELLED", // eslint-disable-line no-unused-vars
 }
 
 export enum BatchExportFileFormat {
@@ -32,12 +33,16 @@ export const exportOptions: Record<
     fileType: string;
   }
 > = {
-  CSV: { label: "CSV", extension: "csv", fileType: "text/csv" },
-  JSON: { label: "JSON", extension: "json", fileType: "application/json" },
+  CSV: { label: "CSV", extension: "csv", fileType: "text/csv; charset=utf-8" },
+  JSON: {
+    label: "JSON",
+    extension: "json",
+    fileType: "application/json; charset=utf-8",
+  },
   JSONL: {
     label: "JSONL",
     extension: "jsonl",
-    fileType: "application/x-ndjson",
+    fileType: "application/x-ndjson; charset=utf-8",
   },
 } as const;
 

packages/shared/src/features/datasets/validation.ts

@@ -5,3 +5,17 @@ import { withFolderPathValidation } from "../folders/validation";
  * Dataset name validation schema for API, tRPC and client
  */
 export const DatasetNameSchema = withFolderPathValidation(StringNoHTMLNonEmpty);
+
+/**
+ * Type for bulk dataset item validation errors
+ * Used when validating multiple items before creation (e.g., CSV upload)
+ */
+export type BulkDatasetItemValidationError = {
+  itemIndex: number;
+  field: "input" | "expectedOutput";
+  errors: Array<{
+    path: string;
+    message: string;
+    keyword?: string;
+  }>;
+};

packages/shared/src/features/model-pricing/index.ts

@@ -0,0 +1 @@
+export * from "./validation";

packages/shared/src/features/model-pricing/validation.ts

@@ -0,0 +1,251 @@
+import safeRegex from "safe-regex2";
+import { z } from "zod/v4";
+
+/**
+ * Shared validation for pricing tier regex patterns and conditions
+ * Used by both Public API and tRPC routes
+ */
+
+/**
+ * Validates a regex pattern for safety and correctness
+ * @throws Error with descriptive message if pattern is invalid
+ */
+export function validateRegexPattern(pattern: string): void {
+  // Length check
+  if (pattern.length > 200) {
+    throw new Error("Pattern exceeds maximum length of 200 characters");
+  }
+
+  // Check for empty pattern
+  if (pattern.length === 0) {
+    throw new Error("Pattern cannot be empty");
+  }
+
+  // Syntax check
+  try {
+    new RegExp(pattern);
+  } catch (e) {
+    throw new Error(
+      `Invalid regex syntax: ${e instanceof Error ? e.message : String(e)}`,
+    );
+  }
+
+  // Safety check (catastrophic backtracking)
+  if (!safeRegex(pattern)) {
+    throw new Error(
+      "Pattern may cause catastrophic backtracking. Please simplify your regex.",
+    );
+  }
+}
+
+/**
+ * Pricing tier condition schema (shared across API and tRPC)
+ */
+export const PricingTierConditionSchema = z.object({
+  usageDetailPattern: z
+    .string()
+    .min(1, "Pattern cannot be empty")
+    .max(200, "Pattern exceeds maximum length of 200 characters")
+    .refine(
+      (pattern) => {
+        try {
+          validateRegexPattern(pattern);
+          return true;
+        } catch {
+          return false;
+        }
+      },
+      {
+        message:
+          "Invalid regex pattern: must be valid regex and not cause catastrophic backtracking",
+      },
+    ),
+  operator: z.enum(["gt", "gte", "lt", "lte", "eq", "neq"]),
+  value: z.number().nonnegative(),
+  caseSensitive: z.boolean().default(false),
+});
+
+export type PricingTierCondition = z.infer<typeof PricingTierConditionSchema>;
+
+/**
+ * Pricing tier input schema (for creation - no ID)
+ * Used when creating new tiers via API or tRPC
+ */
+export const PricingTierInputSchema = z.object({
+  name: z
+    .string()
+    .min(1, "Name cannot be empty")
+    .max(100, "Name exceeds maximum length of 100 characters"),
+  isDefault: z.boolean().default(false),
+  priority: z
+    .number()
+    .int("Priority must be an integer")
+    .min(0, "Priority must be non-negative")
+    .max(999, "Priority cannot exceed 999"),
+  conditions: z.array(PricingTierConditionSchema),
+  prices: z.record(
+    z.string(),
+    z.number().nonnegative("Price must be non-negative"),
+  ),
+});
+
+export type PricingTierInput = z.infer<typeof PricingTierInputSchema>;
+
+/**
+ * Validates an array of pricing tiers
+ * Ensures:
+ * - Exactly one default tier
+ * - Unique priorities
+ * - Unique names
+ * - Default tier has priority 0 and empty conditions
+ */
+export function validatePricingTiers(
+  tiers: PricingTierInput[],
+): { valid: true } | { valid: false; error: string } {
+  if (tiers.length === 0) {
+    return { valid: false, error: "At least one pricing tier is required" };
+  }
+
+  // Check for exactly one default tier
+  const defaultTiers = tiers.filter((t) => t.isDefault);
+  if (defaultTiers.length === 0) {
+    return {
+      valid: false,
+      error: "Exactly one pricing tier must have isDefault: true",
+    };
+  }
+  if (defaultTiers.length > 1) {
+    return {
+      valid: false,
+      error:
+        "Only one pricing tier can have isDefault: true, found " +
+        defaultTiers.length,
+    };
+  }
+
+  // Validate default tier has priority 0 and empty conditions
+  const defaultTier = defaultTiers[0];
+  if (defaultTier.priority !== 0) {
+    return {
+      valid: false,
+      error: "Default pricing tier must have priority: 0",
+    };
+  }
+  if (defaultTier.conditions.length > 0) {
+    return {
+      valid: false,
+      error: "Default pricing tier must have empty conditions array",
+    };
+  }
+
+  // Validate non-default tiers have at least 1 condition
+  for (const tier of tiers) {
+    if (!tier.isDefault && tier.conditions.length === 0) {
+      return {
+        valid: false,
+        error: `Non-default pricing tier "${tier.name}" must have at least one condition`,
+      };
+    }
+  }
+
+  // Check for unique priorities
+  const priorities = tiers.map((t) => t.priority);
+  const uniquePriorities = new Set(priorities);
+  if (priorities.length !== uniquePriorities.size) {
+    return {
+      valid: false,
+      error: "Pricing tier priorities must be unique within a model",
+    };
+  }
+
+  // Check for unique names
+  const names = tiers.map((t) => t.name);
+  const uniqueNames = new Set(names);
+  if (names.length !== uniqueNames.size) {
+    return { valid: false, error: "Pricing tier names must be unique" };
+  }
+
+  // Validate all conditions have valid regex patterns
+  for (const tier of tiers) {
+    for (const condition of tier.conditions) {
+      try {
+        validateRegexPattern(condition.usageDetailPattern);
+      } catch (error) {
+        return {
+          valid: false,
+          error: `Invalid regex pattern in tier "${tier.name}": ${
+            error instanceof Error ? error.message : String(error)
+          }`,
+        };
+      }
+    }
+  }
+
+  // Validate all tiers have at least one price
+  for (const tier of tiers) {
+    if (Object.keys(tier.prices).length === 0) {
+      return {
+        valid: false,
+        error: `Pricing tier "${tier.name}" must have at least one price defined`,
+      };
+    }
+  }
+
+  // Validate all tiers have the same usage keys
+  if (tiers.length > 1) {
+    const defaultTierForKeys = tiers.find((t) => t.isDefault);
+    if (!defaultTierForKeys) {
+      return { valid: false, error: "No default tier found" };
+    }
+
+    const defaultKeys = Object.keys(defaultTierForKeys.prices).sort();
+
+    for (const tier of tiers) {
+      if (tier.isDefault) continue;
+
+      const tierKeys = Object.keys(tier.prices).sort();
+
+      // Check if keys match
+      if (
+        defaultKeys.length !== tierKeys.length ||
+        !defaultKeys.every((key, index) => key === tierKeys[index])
+      ) {
+        return {
+          valid: false,
+          error: `Pricing tier "${tier.name}" must have the same usage keys as the default tier. Expected: [${defaultKeys.join(", ")}], Got: [${tierKeys.join(", ")}]`,
+        };
+      }
+    }
+  }
+
+  return { valid: true };
+}
+
+/**
+ * Validates that pricing tiers can be used with flat prices
+ * Returns error if both are provided
+ */
+export function validatePricingMethod(params: {
+  hasFlatPrices: boolean;
+  hasPricingTiers: boolean;
+}): { valid: true } | { valid: false; error: string } {
+  const { hasFlatPrices, hasPricingTiers } = params;
+
+  if (hasFlatPrices && hasPricingTiers) {
+    return {
+      valid: false,
+      error:
+        "Cannot provide both flat prices (inputPrice/outputPrice/totalPrice) and pricingTiers",
+    };
+  }
+
+  if (!hasFlatPrices && !hasPricingTiers) {
+    return {
+      valid: false,
+      error:
+        "Must provide either flat prices (inputPrice/outputPrice/totalPrice) OR pricingTiers",
+    };
+  }
+
+  return { valid: true };
+}

packages/shared/src/features/prompts/constants.ts

@@ -1,3 +1,16 @@
 export const PRODUCTION_LABEL = "production";
 export const LATEST_PROMPT_LABEL = "latest";
 export const COMMIT_MESSAGE_MAX_LENGTH = 500;
+
+// Prompt name validation
+export const PROMPT_NAME_MAX_LENGTH = 255;
+export const RESERVED_PROMPT_NAME_NEW = "new";
+export const PROMPT_NAME_PIPE_RESTRICTION_REGEX = /^[^|]*$/;
+export const PROMPT_NAME_PIPE_RESTRICTION_ERROR =
+  "Prompt name cannot contain '|' character";
+
+// Prompt label validation
+export const PROMPT_LABEL_MAX_LENGTH = 36;
+export const PROMPT_LABEL_REGEX = /^[a-z0-9_\-.]+$/;
+export const PROMPT_LABEL_REGEX_ERROR =
+  "Label must be lowercase alphanumeric with optional underscores, hyphens, or periods";

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

@@ -1,7 +1,12 @@
 import { z } from "zod/v4";
 import type { Prompt } from "../../../prisma/generated/types";
 import { jsonSchema } from "../../utils/zod";
-import { COMMIT_MESSAGE_MAX_LENGTH } from "./constants";
+import {
+  COMMIT_MESSAGE_MAX_LENGTH,
+  PROMPT_LABEL_MAX_LENGTH,
+  PROMPT_LABEL_REGEX,
+  PROMPT_LABEL_REGEX_ERROR,
+} from "./constants";
 import { PromptChatMessageSchema } from "../../server/llm/types";
 import { PromptNameSchema } from "./validation";
 
@@ -18,11 +23,8 @@ export enum PromptType {
 export const PromptLabelSchema = z
   .string()
   .min(1)
-  .max(36)
-  .regex(
-    /^[a-z0-9_\-.]+$/,
-    "Label must be lowercase alphanumeric with optional underscores, hyphens, or periods",
-  );
+  .max(PROMPT_LABEL_MAX_LENGTH)
+  .regex(PROMPT_LABEL_REGEX, PROMPT_LABEL_REGEX_ERROR);
 
 const BaseCreateTextPromptSchema = z.object({
   name: PromptNameSchema,
@@ -91,12 +93,22 @@ export type GetPromptsMetaType = z.infer<typeof GetPromptsMetaSchema>;
 export const GetPromptSchema = z.object({
   name: z.string().transform((v) => decodeURIComponent(v)),
   version: z.coerce.number().int().nullish(),
+  resolve: z
+    .enum(["true", "false"])
+    .nullish()
+    .default("true")
+    .transform((v) => v === "true"), // Optional, defaults to true for backward compatibility
 });
 
 export const GetPromptByNameSchema = z.object({
   promptName: z.string(),
   version: z.coerce.number().int().nullish(),
   label: z.string().optional(),
+  resolve: z
+    .enum(["true", "false"])
+    .nullish()
+    .default("true")
+    .transform((v) => v === "true"), // Optional, defaults to true for backward compatibility
 });
 
 const BaseTextPromptSchema = z.object({

packages/shared/src/features/prompts/validation.ts

@@ -1,14 +1,22 @@
 import { StringNoHTMLNonEmpty } from "../../utils/zod";
 import { withFolderPathValidation } from "../folders/validation";
+import {
+  PROMPT_NAME_PIPE_RESTRICTION_REGEX,
+  PROMPT_NAME_PIPE_RESTRICTION_ERROR,
+  RESERVED_PROMPT_NAME_NEW,
+} from "./constants";
 
 /**
  * Prompt name validation schema for API, tRPC and client
  */
 export const PromptNameSchema = withFolderPathValidation(
   StringNoHTMLNonEmpty.regex(
-    /^[^|]*$/,
+    PROMPT_NAME_PIPE_RESTRICTION_REGEX,
     // Note: pipe character is used for prompt composition
-    "Prompt name cannot contain '|' character",
+    PROMPT_NAME_PIPE_RESTRICTION_ERROR,
   ),
   // Note: we use "new" as a special name for the new prompt form
-).refine((name) => name !== "new", "Prompt name cannot be 'new'");
+).refine(
+  (name) => name !== RESERVED_PROMPT_NAME_NEW,
+  `Prompt name cannot be '${RESERVED_PROMPT_NAME_NEW}'`,
+);

packages/shared/src/features/scores/interfaces/api/index.ts

@@ -1,6 +1,5 @@
 export * from "./v1/schemas";
 export * from "./v1/validation";
 export * from "./v1/endpoints";
-export * from "./v2/schemas";
 export * from "./v2/validation";
 export * from "./v2/endpoints";

packages/shared/src/features/scores/interfaces/api/shared.ts

@@ -1,57 +1,14 @@
 import { z } from "zod/v4";
-import { jsonSchema, publicApiPaginationZod } from "../../../../utils/zod";
+import { publicApiPaginationZod } from "../../../../utils/zod";
 import { stringDateTime } from "../../../../utils/typeChecks";
 import { applyScoreValidation } from "../../../../utils/scores";
 import { PostScoreBodyFoundationSchema } from "../shared";
+import {
+  ScoreDataTypeDomain,
+  ScoreSourceDomain,
+} from "../../../../domain/scores";
 
 const operators = ["<", ">", "<=", ">=", "!=", "="] as const;
-const ScoreDataType = ["NUMERIC", "CATEGORICAL", "BOOLEAN"] as const;
-const ScoreSource = ["API", "EVAL", "ANNOTATION"] as const;
-
-/**
- * Objects
- */
-export const NumericData = z.object({
-  value: z.number(),
-  stringValue: z.undefined().nullish(),
-  dataType: z.literal("NUMERIC"),
-});
-
-export const CategoricalData = z.object({
-  value: z.number().nullish(),
-  stringValue: z.string(),
-  dataType: z.literal("CATEGORICAL"),
-});
-
-export const BooleanData = z.object({
-  value: z.number(),
-  stringValue: z.string(),
-  dataType: z.literal("BOOLEAN"),
-});
-
-/**
- * Foundation schema for all score types, needs to be extended with entity score may be associated with. Note there are two API versions, where v1 allows only trace and observation scores, while v2 additionally allows session and dataset run scores
- * @see {@link ScoreFoundationSchemaV1}, {@link ScoreFoundationSchemaV2}
- *
- * Must also be extended with score data specific schema (numeric, categorical, boolean)
- * @see {@link NumericData}, {@link CategoricalData}, {@link BooleanData}
- */
-export const ScoreFoundationSchema = z.object({
-  id: z.string(),
-  timestamp: z.coerce.date(),
-  projectId: z.string(),
-  environment: z.string().default("default"),
-  name: z.string(),
-  source: z.enum(ScoreSource),
-  authorUserId: z.string().nullish(),
-  comment: z.string().nullish(),
-  metadata: jsonSchema.nullish(),
-  configId: z.string().nullish(),
-  createdAt: z.coerce.date(),
-  updatedAt: z.coerce.date(),
-  queueId: z.string().nullish(),
-  executionTraceId: z.string().nullish(),
-});
 
 /**
  * Endpoints
@@ -66,7 +23,7 @@ export const GetScoreQuery = z.object({
 export const GetScoresQuery = z.object({
   ...publicApiPaginationZod,
   userId: z.string().nullish(),
-  dataType: z.enum(ScoreDataType).nullish(),
+  dataType: ScoreDataTypeDomain.nullish(),
   configId: z.string().nullish(),
   queueId: z.string().nullish(),
   traceTags: z.union([z.array(z.string()), z.string()]).nullish(),
@@ -74,7 +31,7 @@ export const GetScoresQuery = z.object({
   name: z.string().nullish(),
   fromTimestamp: stringDateTime,
   toTimestamp: stringDateTime,
-  source: z.enum(ScoreSource).nullish(),
+  source: ScoreSourceDomain.nullish(),
   value: z.coerce.number().nullish(),
   operator: z.enum(operators).nullish(),
   scoreIds: z
@@ -92,22 +49,18 @@ export const GetScoresQuery = z.object({
  * PostScoresBody is copied for the ingestion API as `ScoreBody`. Please copy any changes here in `packages/shared/src/features/ingestion/types.ts`
  */
 export const PostScoresBody = applyScoreValidation(
-  z.discriminatedUnion("dataType", [
-    PostScoreBodyFoundationSchema.merge(
+  PostScoreBodyFoundationSchema.and(
+    z.discriminatedUnion("dataType", [
       z.object({
         value: z.number(),
         dataType: z.literal("NUMERIC"),
         configId: z.string().nullish(),
       }),
-    ),
-    PostScoreBodyFoundationSchema.merge(
       z.object({
         value: z.string(),
         dataType: z.literal("CATEGORICAL"),
         configId: z.string().nullish(),
       }),
-    ),
-    PostScoreBodyFoundationSchema.merge(
       z.object({
         value: z.number().refine((value) => value === 0 || value === 1, {
           message:
@@ -116,15 +69,13 @@ export const PostScoresBody = applyScoreValidation(
         dataType: z.literal("BOOLEAN"),
         configId: z.string().nullish(),
       }),
-    ),
-    PostScoreBodyFoundationSchema.merge(
       z.object({
         value: z.union([z.string(), z.number()]),
         dataType: z.undefined(),
         configId: z.string().nullish(),
       }),
-    ),
-  ]),
+    ]),
+  ),
 );
 
 export const PostScoresResponse = z.object({ id: z.string() });

packages/shared/src/features/scores/interfaces/api/v1/schemas.ts

@@ -1,10 +1,10 @@
 import { z } from "zod/v4";
 import {
+  ScoreSchemaExclReferencesAndDates,
   CategoricalData,
   NumericData,
   BooleanData,
-  ScoreFoundationSchema,
-} from "../shared";
+} from "../../../../../domain/scores";
 
 /**
  * Foundation schema for scores API v1 i.e. trace and observation scores ONLY
@@ -12,15 +12,18 @@ import {
  * Must be extended with score data specific schema (numeric, categorical, boolean)
  * @see {@link NumericData}, {@link CategoricalData}, {@link BooleanData}
  */
-const ScoreFoundationSchemaV1 = ScoreFoundationSchema.extend({
+const ScoreFoundationSchemaV1 = ScoreSchemaExclReferencesAndDates.extend({
+  // Timestamps
+  createdAt: z.coerce.date(),
+  updatedAt: z.coerce.date(),
+  timestamp: z.coerce.date(),
+  // Score references
   traceId: z.string(),
   observationId: z.string().nullish(),
 });
 
-export const APIScoreSchemaV1 = z.discriminatedUnion("dataType", [
-  ScoreFoundationSchemaV1.merge(NumericData),
-  ScoreFoundationSchemaV1.merge(CategoricalData),
-  ScoreFoundationSchemaV1.merge(BooleanData),
-]);
+export const APIScoreSchemaV1 = ScoreFoundationSchemaV1.and(
+  z.discriminatedUnion("dataType", [NumericData, CategoricalData, BooleanData]),
+);
 
 export type APIScoreV1 = z.infer<typeof APIScoreSchemaV1>;

packages/shared/src/features/scores/interfaces/api/v2/endpoints.ts

@@ -10,6 +10,8 @@ export const GetScoreResponseV2 = APIScoreSchemaV2;
 // GET /scores v2
 export const GetScoresQueryV2 = GetScoresQuery.extend({
   sessionId: z.string().nullish(),
+  traceId: z.string().nullish(),
+  datasetRunId: z.string().nullish(),
 });
 export const GetScoreResponseDataV2 = z.intersection(
   APIScoreSchemaV2,

packages/shared/src/features/scores/interfaces/api/v2/schemas.ts

@@ -1,10 +1,10 @@
-import { z } from "zod/v4";
 import {
+  BooleanData,
   CategoricalData,
   NumericData,
-  BooleanData,
-  ScoreFoundationSchema,
-} from "../shared";
+  ScoreSchemaExclReferencesAndDates,
+} from "../../../../../domain";
+import z from "zod/v4";
 
 /**
  * Foundation schema for scores API v2 i.e. trace, observation AND session scores
@@ -12,17 +12,20 @@ import {
  * Must be extended with score data specific schema (numeric, categorical, boolean)
  * @see {@link NumericData}, {@link CategoricalData}, {@link BooleanData}
  */
-const ScoreFoundationSchemaV2 = ScoreFoundationSchema.extend({
+const ScoreFoundationSchemaV2 = ScoreSchemaExclReferencesAndDates.extend({
+  // Timestamps
+  createdAt: z.coerce.date(),
+  updatedAt: z.coerce.date(),
+  timestamp: z.coerce.date(),
+  // Score references; one of the following must be provided
   traceId: z.string().nullish(),
   observationId: z.string().nullish(),
   sessionId: z.string().nullish(),
   datasetRunId: z.string().nullish(),
 });
 
-export const APIScoreSchemaV2 = z.discriminatedUnion("dataType", [
-  ScoreFoundationSchemaV2.merge(NumericData),
-  ScoreFoundationSchemaV2.merge(CategoricalData),
-  ScoreFoundationSchemaV2.merge(BooleanData),
-]);
+export const APIScoreSchemaV2 = ScoreFoundationSchemaV2.and(
+  z.discriminatedUnion("dataType", [NumericData, CategoricalData, BooleanData]),
+);
 
 export type APIScoreV2 = z.infer<typeof APIScoreSchemaV2>;

packages/shared/src/features/scores/interfaces/application/validation.ts

@@ -1,9 +1,8 @@
 import z from "zod/v4";
-import { APIScoreSchemaV2, APIScoreV2 } from "../api/v2/schemas";
 import { APIScoreSchemaV1, APIScoreV1 } from "../api/v1/schemas";
-import { ScoreDomain } from "../../../../domain";
+import { ScoreDomain, ScoreSchema } from "../../../../domain";
 
-type ValidatedAPIScore<IncludeHasMetadata extends boolean> = APIScoreV2 & {
+type ValidatedScore<IncludeHasMetadata extends boolean> = ScoreDomain & {
   hasMetadata: IncludeHasMetadata extends true ? boolean : never;
 };
 
@@ -16,8 +15,8 @@ type InputScore = ScoreDomain & { hasMetadata?: boolean };
  * @returns validated score
  * @throws error if score fails validation
  */
-export const validateDbScore = (score: ScoreDomain): APIScoreV2 =>
-  APIScoreSchemaV2.parse(score);
+export const validateDbScore = (score: unknown): ScoreDomain =>
+  ScoreSchema.parse(score);
 
 /**
  * Use this function when pulling a list of scores from the database before using in the application to ensure type safety.
@@ -36,21 +35,21 @@ export const filterAndValidateDbScoreList = <
   includeHasMetadata?: IncludeHasMetadata;
   // eslint-disable-next-line no-unused-vars
   onParseError?: (error: z.ZodError) => void;
-}): ValidatedAPIScore<IncludeHasMetadata>[] => {
+}): ValidatedScore<IncludeHasMetadata>[] => {
   return scores.reduce((acc, ts) => {
-    const result = APIScoreSchemaV2.safeParse(ts);
+    const result = ScoreSchema.safeParse(ts);
     if (result.success) {
       const score = { ...result.data };
       if (includeHasMetadata) {
         Object.assign(score, { hasMetadata: ts.hasMetadata ?? false });
       }
-      acc.push(score as ValidatedAPIScore<IncludeHasMetadata>);
+      acc.push(score as ValidatedScore<IncludeHasMetadata>);
     } else {
       console.error("Score parsing error: ", result.error);
       onParseError?.(result.error);
     }
     return acc;
-  }, [] as ValidatedAPIScore<IncludeHasMetadata>[]);
+  }, [] as ValidatedScore<IncludeHasMetadata>[]);
 };
 
 type ValidatedAPITraceScore<IncludeHasMetadata extends boolean> = APIScoreV1 & {

packages/shared/src/index.ts

@@ -8,17 +8,20 @@ export * from "./tableDefinitions";
 export * from "./types";
 export * from "./tableDefinitions/tracesTable";
 export * from "./observationsTable";
+export * from "./eventsTable";
 export * from "./utils/zod";
 export * from "./utils/json";
 export * from "./utils/stringChecks";
 export * from "./utils/objects";
 export * from "./utils/typeChecks";
 export * from "./utils/prompts";
+export * from "./utils/jsonSchemaValidation";
 export * from "./features/entitlements/plans";
 export * from "./interfaces/rate-limits";
 export * from "./tableDefinitions/typeHelpers";
 export * from "./domain/webhooks";
 export * from "./domain/dataset-run-items";
+export * from "./domain/dataset-items";
 export * from "./domain/score-configs";
 
 // llm api
@@ -30,6 +33,8 @@ export * from "./features/evals/utilities";
 // table actions
 export * from "./features/batchExport/types";
 export * from "./features/batchAction/types";
+export * from "./features/batchAction/addToDatasetTypes";
+export * from "./features/batchAction/applyFieldMapping";
 export { BatchTableNames } from "./interfaces/tableNames";
 
 // annotation
@@ -50,6 +55,9 @@ export * from "./features/experiments/utils";
 // datasets
 export * from "./features/datasets/validation";
 
+// model pricing
+export * from "./features/model-pricing/";
+
 // prompts
 export * from "./features/prompts/parsePromptDependencyTags";
 export * from "./features/prompts/validation";
@@ -79,3 +87,6 @@ export * from "./interfaces/search";
 
 // domain
 export * from "./domain";
+
+// io representation
+export * from "./utils/IORepresentation";