@databricks/appkit 0.71.0 → 0.73.0

package/CLAUDE.md

@@ -48,6 +48,7 @@ npx @databricks/appkit docs <query>
 - [Analytics plugin](./docs/plugins/analytics.md): Enables SQL query execution against Databricks SQL Warehouses.
 - [Caching](./docs/plugins/caching.md): AppKit provides both global and plugin-level caching capabilities.
 - [Creating custom plugins](./docs/plugins/custom-plugins.md): If you need custom API routes or background logic, implement an AppKit plugin. The fastest way is to use the CLI:
+- [Database plugin](./docs/plugins/database.md): This plugin is currently beta. APIs may change between minor releases. Import from @databricks/appkit/beta. See Plugin Stability Tiers.
 - [Execution context](./docs/plugins/execution-context.md): AppKit manages Databricks authentication via two contexts:
 - [Files plugin](./docs/plugins/files.md): File operations against Databricks Unity Catalog Volumes. Supports listing, reading, downloading, uploading, deleting, and previewing files with built-in caching, retry, and timeout handling via the execution interceptor pipeline.
 - [Genie plugin](./docs/plugins/genie.md): Integrates Databricks AI/BI Genie spaces into your AppKit application, enabling natural language data queries via a conversational interface.
@@ -68,9 +69,11 @@ npx @databricks/appkit docs <query>
 - [Class: AuthenticationError](./docs/api/appkit/Class.AuthenticationError.md): Error thrown when authentication fails.
 - [Class: ConfigurationError](./docs/api/appkit/Class.ConfigurationError.md): Error thrown when configuration is missing or invalid.
 - [Class: ConnectionError](./docs/api/appkit/Class.ConnectionError.md): Error thrown when a connection or network operation fails.
+- [Class: DatabaseValidationError](./docs/api/appkit/Class.DatabaseValidationError.md): Deliberate validation failure raised by a database mutation hook. Generated
 - [Class: DatabricksAdapter](./docs/api/appkit/Class.DatabricksAdapter.md): Adapter that talks directly to Databricks Model Serving /invocations endpoint.
 - [Class: ExecutionError](./docs/api/appkit/Class.ExecutionError.md): Error thrown when an operation execution fails.
 - [Class: InitializationError](./docs/api/appkit/Class.InitializationError.md): Error thrown when a service or component is not properly initialized.
+- [Class: MlflowClient](./docs/api/appkit/Class.MlflowClient.md): A thin client over the Databricks workspace REST API, owning the host + bearer
 - [Abstract Class: Plugin<TConfig>](./docs/api/appkit/Class.Plugin.md): Base abstract class for creating AppKit plugins.
 - [Class: PolicyDeniedError](./docs/api/appkit/Class.PolicyDeniedError.md): Thrown when a policy denies an action.
 - [Class: ResourceRegistry](./docs/api/appkit/Class.ResourceRegistry.md): Central registry for tracking plugin resource requirements.
@@ -86,20 +89,31 @@ npx @databricks/appkit docs <query>
 - [Function: bigid()](./docs/api/appkit/Function.bigid.md): Returns
 - [Function: bigint()](./docs/api/appkit/Function.bigint.md): Returns
 - [Function: boolean()](./docs/api/appkit/Function.boolean.md): Returns
+- [Function: buildAssessments()](./docs/api/appkit/Function.buildAssessments.md): Parameters
+- [Function: configureJudge()](./docs/api/appkit/Function.configureJudge.md): Configure the judge once. Sets the OpenAI-compatible client env autoevals
 - [Function: createAgent()](./docs/api/appkit/Function.createAgent.md): Pure factory for agent definitions: cycle-detects the sub-agent graph and
 - [Function: createApp()](./docs/api/appkit/Function.createApp.md): Bootstraps AppKit with the provided configuration.
+- [Function: createHttpDriver()](./docs/api/appkit/Function.createHttpDriver.md): Drives an agent by POSTing to a running app's chat endpoint and parsing the
 - [Function: createLakebasePool()](./docs/api/appkit/Function.createLakebasePool.md): Create a Lakebase pool with appkit's logger integration.
 - [Function: createLakebasePoolManager()](./docs/api/appkit/Function.createLakebasePoolManager.md): Create a pool manager that maintains per-key Lakebase connection pools.
 - [Function: createWorkspaceClient()](./docs/api/appkit/Function.createWorkspaceClient.md): Construct an AppKit workspace client.
 - [Function: database()](./docs/api/appkit/Function.database.md): Create a typed database plugin registration for a finalized schema.
+- [Function: defineEval()](./docs/api/appkit/Function.defineEval.md): Define an agent eval. Default-export the result from a
 - [Function: defineManifest()](./docs/api/appkit/Function.defineManifest.md): Validates a raw manifest (typically a manifest.json import) against the
 - [Function: defineSchema()](./docs/api/appkit/Function.defineSchema.md): Compile one declared schema. The returned type keeps the table names the
 - [Function: defineTool()](./docs/api/appkit/Function.defineTool.md): Defines a single tool entry for a plugin's internal registry.
+- [Function: discoverEvalFiles()](./docs/api/appkit/Function.discoverEvalFiles.md): Discover evals under /server/agents//evals/ — co-located
 - [Function: enumColumn()](./docs/api/appkit/Function.enumColumn.md): Parameters
+- [Function: equals()](./docs/api/appkit/Function.equals.md): Passes when the value equals expected exactly.
+- [Function: evalGlyph()](./docs/api/appkit/Function.evalGlyph.md): Status glyph for a single eval result.
 - [Function: executeFromRegistry()](./docs/api/appkit/Function.executeFromRegistry.md): Validates tool-call arguments against the entry's schema and invokes its
 - [Function: extractServingEndpoints()](./docs/api/appkit/Function.extractServingEndpoints.md): Extract serving endpoint config from a server file by AST-parsing it.
 - [Function: findServerFile()](./docs/api/appkit/Function.findServerFile.md): Find the server entry file by checking candidate paths in order.
 - [Function: fk()](./docs/api/appkit/Function.fk.md): Declare foreign-key to another column.
+- [Function: formatEvalDetail()](./docs/api/appkit/Function.formatEvalDetail.md): Indented detail lines for a failing eval (error + failing assertions).
+- [Function: formatEvalHeadline()](./docs/api/appkit/Function.formatEvalHeadline.md): The one-line header for a single eval result (no failure detail).
+- [Function: formatEvalResults()](./docs/api/appkit/Function.formatEvalResults.md): Render all results as a human-readable console report (non-streaming).
+- [Function: formatSummaryLine()](./docs/api/appkit/Function.formatSummaryLine.md): The final PASS/FAIL summary line.
 - [Function: fromSupervisorApi()](./docs/api/appkit/Function.fromSupervisorApi.md): Creates an AgentAdapter backed by the Databricks AI Gateway
 - [Function: functionToolToDefinition()](./docs/api/appkit/Function.functionToolToDefinition.md): Parameters
 - [Function: generateDatabaseCredential()](./docs/api/appkit/Function.generateDatabaseCredential.md): Generate OAuth credentials for Postgres database connection using the proper Postgres API.
@@ -111,19 +125,30 @@ npx @databricks/appkit docs <query>
 - [Function: getUsernameWithApiLookup()](./docs/api/appkit/Function.getUsernameWithApiLookup.md): Resolves the PostgreSQL username for a Lakebase connection.
 - [Function: getWorkspaceClient()](./docs/api/appkit/Function.getWorkspaceClient.md): Get workspace client from config or SDK default auth chain
 - [Function: id()](./docs/api/appkit/Function.id.md): Returns
+- [Function: includes()](./docs/api/appkit/Function.includes.md): Passes when the value contains substring.
 - [Function: integer()](./docs/api/appkit/Function.integer.md): Returns
 - [Function: isFunctionTool()](./docs/api/appkit/Function.isFunctionTool.md): Parameters
 - [Function: isHostedTool()](./docs/api/appkit/Function.isHostedTool.md): Parameters
+- [Function: isJudgeConfigured()](./docs/api/appkit/Function.isJudgeConfigured.md): Returns
 - [Function: isSQLTypeMarker()](./docs/api/appkit/Function.isSQLTypeMarker.md): Type guard to check if a value is a SQL type marker
 - [Function: isSupervisorTool()](./docs/api/appkit/Function.isSupervisorTool.md): Type guard for HostedSupervisorTool. Used by the agents plugin
 - [Function: isToolkitEntry()](./docs/api/appkit/Function.isToolkitEntry.md): Type guard for ToolkitEntry — used by the agents plugin to differentiate
 - [Function: jsonb()](./docs/api/appkit/Function.jsonb.md): Returns
 - [Function: loadAgentFromFile()](./docs/api/appkit/Function.loadAgentFromFile.md): Loads a single markdown agent file and resolves its frontmatter against
 - [Function: loadAgentsFromDir()](./docs/api/appkit/Function.loadAgentsFromDir.md): Scans a directory for one subdirectory per agent, each containing
+- [Function: matches()](./docs/api/appkit/Function.matches.md): Passes when the value matches pattern.
 - [Function: mcpServer()](./docs/api/appkit/Function.mcpServer.md): Factory for declaring a custom MCP server tool.
+- [Function: normalizeHost()](./docs/api/appkit/Function.normalizeHost.md): Ensure the host has a scheme (Databricks env often lacks https://).
 - [Function: parseTextToolCalls()](./docs/api/appkit/Function.parseTextToolCalls.md): Parses text-based tool calls from model output.
+- [Function: readEvalDataset()](./docs/api/appkit/Function.readEvalDataset.md): Read a Databricks managed evaluation dataset (a Unity Catalog table with
+- [Function: reportToMlflow()](./docs/api/appkit/Function.reportToMlflow.md): Write one pass/fail assessment per eval result to the Databricks MLflow REST
+- [Function: resolveDatabricksAuth()](./docs/api/appkit/Function.resolveDatabricksAuth.md): Parameters
 - [Function: resolveHostedTools()](./docs/api/appkit/Function.resolveHostedTools.md): Parameters
+- [Function: resolveWorkspaceClient()](./docs/api/appkit/Function.resolveWorkspaceClient.md): Construct a Databricks WorkspaceClient for the eval runner — the object the
 - [Function: runAgent()](./docs/api/appkit/Function.runAgent.md): Standalone agent execution without createApp. Resolves the adapter, binds
+- [Function: runEval()](./docs/api/appkit/Function.runEval.md): Run a single eval against a driver. Never throws for assertion or agent
+- [Function: runEvalsInDir()](./docs/api/appkit/Function.runEvalsInDir.md): Discover, load, and run every eval under each agent's evals/ dir, driving
+- [Function: summarize()](./docs/api/appkit/Function.summarize.md): Parameters
 - [Function: text()](./docs/api/appkit/Function.text.md): Returns
 - [Function: timestamp()](./docs/api/appkit/Function.timestamp.md): Parameters
 - [Function: tool()](./docs/api/appkit/Function.tool.md): Factory for defining function tools with Zod schemas.
@@ -136,18 +161,36 @@ npx @databricks/appkit docs <query>
 - [Interface: AgentRunContext](./docs/api/appkit/Interface.AgentRunContext.md): Properties
 - [Interface: AgentsPluginConfig](./docs/api/appkit/Interface.AgentsPluginConfig.md): Base configuration interface for AppKit plugins
 - [Interface: AgentToolDefinition](./docs/api/appkit/Interface.AgentToolDefinition.md): Properties
+- [Interface: AssertionHandle](./docs/api/appkit/Interface.AssertionHandle.md): Chainable handle returned by every assertion to control its severity.
+- [Interface: AssertionResult](./docs/api/appkit/Interface.AssertionResult.md): A single recorded assertion outcome.
+- [Interface: Assessment](./docs/api/appkit/Interface.Assessment.md): A Feedback assessment in the MLflow REST proto-JSON shape.
 - [Interface: AutoInheritToolsConfig](./docs/api/appkit/Interface.AutoInheritToolsConfig.md): Auto-inherit configuration. When enabled for a given agent origin, agents
 - [Interface: BasePluginConfig](./docs/api/appkit/Interface.BasePluginConfig.md): Base configuration interface for AppKit plugins
 - [Interface: CacheConfig](./docs/api/appkit/Interface.CacheConfig.md): Configuration for the CacheInterceptor. Controls TTL, size limits, storage backend, and probabilistic cleanup.
+- [Interface: CustomJudgeSpec](./docs/api/appkit/Interface.CustomJudgeSpec.md): A custom LLM-judge definition: a prompt template and choice→score mapping.
 - [Interface: DatabaseCredential](./docs/api/appkit/Interface.DatabaseCredential.md): Database credentials with OAuth token for Postgres connection
 - [Interface: DatabaseRegistry](./docs/api/appkit/Interface.DatabaseRegistry.md): CANONICAL augmentation target. Empty by default; the generated database.d.ts
+- [Interface: DatabaseValidationIssue](./docs/api/appkit/Interface.DatabaseValidationIssue.md): One rejected field; path names public columns, never their values.
+- [Interface: DatabricksAuth](./docs/api/appkit/Interface.DatabricksAuth.md): Resolved Databricks host + bearer token for the eval runner's REST calls.
+- [Interface: DatasetRow](./docs/api/appkit/Interface.DatasetRow.md): One row of a managed evaluation dataset. inputs are the kwargs passed to the
+- [Interface: DiscoveredEval](./docs/api/appkit/Interface.DiscoveredEval.md): An eval file found under server/agents//evals/.
+- [Interface: DriveResult](./docs/api/appkit/Interface.DriveResult.md): What a driver returns for a single t.send.
 - [Interface: EndpointConfig](./docs/api/appkit/Interface.EndpointConfig.md): Properties
+- [Interface: EntityMutationHooks<TTable>](./docs/api/appkit/Interface.EntityMutationHooks.md): Mutation lifecycle for one entity. A before hook may return a replacement
+- [Interface: EvalDefinition](./docs/api/appkit/Interface.EvalDefinition.md): A single eval, default-exported from a *.eval.ts file.
+- [Interface: EvalDriver](./docs/api/appkit/Interface.EvalDriver.md): Abstraction over how the agent is driven. The HTTP driver posts to a running
+- [Interface: EvalResult](./docs/api/appkit/Interface.EvalResult.md): The outcome of running one eval.
+- [Interface: EvalRunSummary](./docs/api/appkit/Interface.EvalRunSummary.md): Properties
+- [Interface: EvalSummary](./docs/api/appkit/Interface.EvalSummary.md): Properties
 - [Interface: FilePolicyUser](./docs/api/appkit/Interface.FilePolicyUser.md): Minimal user identity passed to the policy function.
 - [Interface: FileResource](./docs/api/appkit/Interface.FileResource.md): Describes the file or directory being acted upon.
 - [Interface: FunctionTool](./docs/api/appkit/Interface.FunctionTool.md): Properties
 - [Interface: GenerateDatabaseCredentialRequest](./docs/api/appkit/Interface.GenerateDatabaseCredentialRequest.md): Request parameters for generating database OAuth credentials
 - [Interface: GenerationParams](./docs/api/appkit/Interface.GenerationParams.md): Optional generation parameters forwarded to the OpenAI-compatible serving
+- [Interface: HookApp](./docs/api/appkit/Interface.HookApp.md): The only capability a hook receives: entities bound to its transaction.
+- [Interface: HookContext](./docs/api/appkit/Interface.HookContext.md): Which entity is being mutated, and the surface a hook may write through.
 - [Interface: HostedSupervisorTool](./docs/api/appkit/Interface.HostedSupervisorTool.md): Tagged record returned by every supervisorTools factory. The
+- [Interface: HttpDriverOptions](./docs/api/appkit/Interface.HttpDriverOptions.md): Properties
 - [Interface: IAiSearchConfig](./docs/api/appkit/Interface.IAiSearchConfig.md): Base configuration interface for AppKit plugins
 - [Interface: IJobsConfig](./docs/api/appkit/Interface.IJobsConfig.md): Configuration for the Jobs plugin.
 - [Interface: IndexConfig](./docs/api/appkit/Interface.IndexConfig.md): Properties
@@ -155,22 +198,32 @@ npx @databricks/appkit docs <query>
 - [Interface: JobAPI](./docs/api/appkit/Interface.JobAPI.md): User-facing API for a single configured job.
 - [Interface: JobConfig](./docs/api/appkit/Interface.JobConfig.md): Per-job configuration options.
 - [Interface: JobsConnectorConfig](./docs/api/appkit/Interface.JobsConnectorConfig.md): Properties
+- [Interface: JudgeConfig](./docs/api/appkit/Interface.JudgeConfig.md): Properties
+- [Interface: JudgeScore](./docs/api/appkit/Interface.JudgeScore.md): A normalized judge result. score is 0..1.
 - [Interface: LakebasePool](./docs/api/appkit/Interface.LakebasePool.md): Subset of pg.Pool exposed by the Lakebase plugin.
 - [Interface: LakebasePoolConfig](./docs/api/appkit/Interface.LakebasePoolConfig.md): Configuration for creating a Lakebase connection pool
 - [Interface: LakebasePoolManager](./docs/api/appkit/Interface.LakebasePoolManager.md): Manages multiple Lakebase connection pools keyed by an identifier (e.g. userId).
+- [Interface: MatchResult](./docs/api/appkit/Interface.MatchResult.md): Result of a deterministic matcher run against a value.
 - [Interface: McpConnectAllResult](./docs/api/appkit/Interface.McpConnectAllResult.md): Per-endpoint outcome of AppKitMcpClient.connectAll. Callers (the
 - [Interface: Message](./docs/api/appkit/Interface.Message.md): Properties
 - [Interface: PluginManifest<TName>](./docs/api/appkit/Interface.PluginManifest.md): Plugin manifest that declares metadata and resource requirements.
 - [Interface: PluginToolkitProvider](./docs/api/appkit/Interface.PluginToolkitProvider.md): Minimum shape every entry in the Plugins map must expose. Core
+- [Interface: PostResult](./docs/api/appkit/Interface.PostResult.md): Structured result for a best-effort POST that must not throw.
 - [Interface: PromptContext](./docs/api/appkit/Interface.PromptContext.md): Context passed to baseSystemPrompt callbacks.
+- [Interface: ReadEvalDatasetOptions](./docs/api/appkit/Interface.ReadEvalDatasetOptions.md): Properties
+- [Interface: ReadSerializerContext](./docs/api/appkit/Interface.ReadSerializerContext.md): Which entity and generated operation produced the row being shaped.
 - [Interface: RegisteredAgent](./docs/api/appkit/Interface.RegisteredAgent.md): Properties
+- [Interface: ReportOutcome](./docs/api/appkit/Interface.ReportOutcome.md): Properties
 - [Interface: RequestedClaims](./docs/api/appkit/Interface.RequestedClaims.md): Optional claims for fine-grained Unity Catalog table permissions
 - [Interface: RequestedResource](./docs/api/appkit/Interface.RequestedResource.md): Resource to request permissions for in Unity Catalog
 - [Interface: RerankerConfig](./docs/api/appkit/Interface.RerankerConfig.md): Properties
+- [Interface: ResolveDatabricksAuthOptions](./docs/api/appkit/Interface.ResolveDatabricksAuthOptions.md): Properties
 - [Interface: ResourceEntry](./docs/api/appkit/Interface.ResourceEntry.md): Internal representation of a resource in the registry.
 - [Interface: ResourceRequirement](./docs/api/appkit/Interface.ResourceRequirement.md): Declares a resource requirement for a plugin.
 - [Interface: RunAgentInput](./docs/api/appkit/Interface.RunAgentInput.md): Properties
 - [Interface: RunAgentResult](./docs/api/appkit/Interface.RunAgentResult.md): Properties
+- [Interface: RunEvalOptions](./docs/api/appkit/Interface.RunEvalOptions.md): Properties
+- [Interface: RunEvalsOptions](./docs/api/appkit/Interface.RunEvalsOptions.md): Properties
 - [Interface: Schema<TTableName>](./docs/api/appkit/Interface.Schema.md): One finalized schema. TTableName keeps the declared names in the type, so
 - [Interface: SearchRequest](./docs/api/appkit/Interface.SearchRequest.md): Properties
 - [Interface: SearchResponse<T>](./docs/api/appkit/Interface.SearchResponse.md): Type Parameters
@@ -181,6 +234,7 @@ npx @databricks/appkit docs <query>
 - [Interface: SupervisorApiAdapterOptions](./docs/api/appkit/Interface.SupervisorApiAdapterOptions.md): Properties
 - [Interface: SupervisorExtension](./docs/api/appkit/Interface.SupervisorExtension.md): Shape of the value at AgentInput.extensions[SUPERVISOREXTENSIONKEY].
 - [Interface: TelemetryConfig](./docs/api/appkit/Interface.TelemetryConfig.md): OpenTelemetry configuration for AppKit applications
+- [Interface: TestContext](./docs/api/appkit/Interface.TestContext.md): The t context passed to an eval's test function.
 - [Interface: Thread](./docs/api/appkit/Interface.Thread.md): Properties
 - [Interface: ThreadStore](./docs/api/appkit/Interface.ThreadStore.md): Methods
 - [Interface: ToolAnnotations](./docs/api/appkit/Interface.ToolAnnotations.md): Properties
@@ -199,7 +253,12 @@ npx @databricks/appkit docs <query>
 - [Type Alias: AgentToolsFn()](./docs/api/appkit/TypeAlias.AgentToolsFn.md): Function form of AgentDefinition.tools. Receives the typed
 - [Type Alias: BaseSystemPromptOption](./docs/api/appkit/TypeAlias.BaseSystemPromptOption.md)
 - [Type Alias: ConfigSchema](./docs/api/appkit/TypeAlias.ConfigSchema.md): Configuration schema definition for plugin config.
+- [Type Alias: DatabaseApiConfig<TSchema>](./docs/api/appkit/TypeAlias.DatabaseApiConfig.md): Full generated CRUD for every declared table by default. Set false to disable
+- [Type Alias: DatabaseApiWriteOperation](./docs/api/appkit/TypeAlias.DatabaseApiWriteOperation.md): Generated HTTP write operations.
+- [Type Alias: DatabaseApiWritesConfig<TSchema>](./docs/api/appkit/TypeAlias.DatabaseApiWritesConfig.md): All writes by default; false keeps reads only, and an object narrows writes.
 - [Type Alias: DatabaseExports](./docs/api/appkit/TypeAlias.DatabaseExports.md): Typed database API published by the plugin.
+- [Type Alias: EntityHooks<TTable>](./docs/api/appkit/TypeAlias.EntityHooks.md): Response shaping and mutation lifecycle declared for one table.
+- [Type Alias: EvalProgress](./docs/api/appkit/TypeAlias.EvalProgress.md)
 - [Type Alias: ExecutionResult<T>](./docs/api/appkit/TypeAlias.ExecutionResult.md): Discriminated union for plugin execution results.
 - [Type Alias: FileAction](./docs/api/appkit/TypeAlias.FileAction.md): Every action the files plugin can perform.
 - [Type Alias: FilePolicy()](./docs/api/appkit/TypeAlias.FilePolicy.md): A policy function that decides whether user may perform action on
@@ -207,16 +266,20 @@ npx @databricks/appkit docs <query>
 - [Type Alias: IAppRouter](./docs/api/appkit/TypeAlias.IAppRouter.md): Express router type for plugin route registration
 - [Type Alias: IDatabaseConfig<TSchema>](./docs/api/appkit/TypeAlias.IDatabaseConfig.md): Configuration for one schema-bound DatabasePlugin instance.
 - [Type Alias: JobsExport()](./docs/api/appkit/TypeAlias.JobsExport.md): Public API shape of the jobs plugin.
+- [Type Alias: Matcher()](./docs/api/appkit/TypeAlias.Matcher.md): A deterministic matcher: inspects a string value and returns a result.
 - [Type Alias: PluginData<T, U, N>](./docs/api/appkit/TypeAlias.PluginData.md): Tuple of plugin class, config, and name. Created by toPlugin() and passed to createApp().
 - [Type Alias: Plugins](./docs/api/appkit/TypeAlias.Plugins.md): Plugin map passed to the function form of AgentDefinition.tools.
+- [Type Alias: ReadSerializer()](./docs/api/appkit/TypeAlias.ReadSerializer.md): Shape one already private-safe row before it reaches the wire. A Promise
 - [Type Alias: ResolvedToolEntry](./docs/api/appkit/TypeAlias.ResolvedToolEntry.md): Internal tool-index entry after a tool record has been resolved to a dispatchable form.
 - [Type Alias: ResourceFieldEntry](./docs/api/appkit/TypeAlias.ResourceFieldEntry.md)
 - [Type Alias: ResourcePermission](./docs/api/appkit/TypeAlias.ResourcePermission.md): Union of all possible permission levels across all resource types.
 - [Type Alias: SearchFilters](./docs/api/appkit/TypeAlias.SearchFilters.md)
 - [Type Alias: ServingFactory](./docs/api/appkit/TypeAlias.ServingFactory.md): Factory function returned by AppKit.serving.
+- [Type Alias: Severity](./docs/api/appkit/TypeAlias.Severity.md): Whether an assertion fails the eval (gate) or is tracked only (soft).
 - [Type Alias: SupervisorTool](./docs/api/appkit/TypeAlias.SupervisorTool.md): Tools supported by the Databricks AI Gateway Responses API. The shapes match
 - [Type Alias: ToolRegistry](./docs/api/appkit/TypeAlias.ToolRegistry.md)
 - [Type Alias: ToPlugin()<T, U, N>](./docs/api/appkit/TypeAlias.ToPlugin.md): Factory function type returned by toPlugin(). Accepts optional config and returns a PluginData tuple.
+- [Type Alias: TransactionClient](./docs/api/appkit/TypeAlias.TransactionClient.md): Entity and SQL capabilities bound to one transaction.
 - [Variable: agents](./docs/api/appkit/Variable.agents.md): Plugin factory for the agents plugin. Discovers agents from
 - [Variable: aiSearch](./docs/api/appkit/Variable.aiSearch.md)
 - [Variable: READ_ACTIONS](./docs/api/appkit/Variable.READ_ACTIONS.md): Actions that only read data.

package/NOTICE.md

@@ -8,6 +8,7 @@ This Software contains code from the following open source projects:
 | :--------------- | :---------------- | :----------- | :--------------------------------------------------- |
 | [@ast-grep/napi](https://www.npmjs.com/package/@ast-grep/napi) | 0.37.0 | MIT | https://ast-grep.github.io |
 | [@clack/prompts](https://www.npmjs.com/package/@clack/prompts) | 1.0.1 | MIT | https://github.com/bombshell-dev/clack/tree/main/packages/prompts#readme |
+| [@mlflow/core](https://www.npmjs.com/package/@mlflow/core) | 0.4.0 | Apache-2.0 | https://mlflow.org/ |
 | [@opentelemetry/api](https://www.npmjs.com/package/@opentelemetry/api) | 1.9.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/api |
 | [@opentelemetry/api-logs](https://www.npmjs.com/package/@opentelemetry/api-logs) | 0.205.0, 0.219.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/experimental/packages/api-logs |
 | [@opentelemetry/auto-instrumentations-node](https://www.npmjs.com/package/@opentelemetry/auto-instrumentations-node) | 0.77.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js-contrib/tree/main/packages/auto-instrumentations-node#readme |
@@ -20,8 +21,8 @@ This Software contains code from the following open source projects:
 | [@opentelemetry/resources](https://www.npmjs.com/package/@opentelemetry/resources) | 2.1.0, 2.8.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/packages/opentelemetry-resources |
 | [@opentelemetry/sdk-logs](https://www.npmjs.com/package/@opentelemetry/sdk-logs) | 0.205.0, 0.219.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/experimental/packages/sdk-logs |
 | [@opentelemetry/sdk-metrics](https://www.npmjs.com/package/@opentelemetry/sdk-metrics) | 2.1.0, 2.8.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/packages/sdk-metrics |
-| [@opentelemetry/sdk-node](https://www.npmjs.com/package/@opentelemetry/sdk-node) | 0.205.0, 0.219.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/experimental/packages/opentelemetry-sdk-node |
 | [@opentelemetry/sdk-trace-base](https://www.npmjs.com/package/@opentelemetry/sdk-trace-base) | 2.1.0, 2.8.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/packages/opentelemetry-sdk-trace-base |
+| [@opentelemetry/sdk-trace-node](https://www.npmjs.com/package/@opentelemetry/sdk-trace-node) | 2.1.0, 2.8.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/packages/opentelemetry-sdk-trace-node |
 | [@opentelemetry/semantic-conventions](https://www.npmjs.com/package/@opentelemetry/semantic-conventions) | 1.38.0 | Apache-2.0 | https://github.com/open-telemetry/opentelemetry-js/tree/main/semantic-conventions |
 | [@radix-ui/react-accordion](https://www.npmjs.com/package/@radix-ui/react-accordion) | 1.2.12 | MIT | https://radix-ui.com/primitives |
 | [@radix-ui/react-alert-dialog](https://www.npmjs.com/package/@radix-ui/react-alert-dialog) | 1.1.15 | MIT | https://radix-ui.com/primitives |
@@ -53,6 +54,7 @@ This Software contains code from the following open source projects:
 | [@tanstack/react-table](https://www.npmjs.com/package/@tanstack/react-table) | 8.21.3 | MIT | https://tanstack.com/table |
 | [@types/semver](https://www.npmjs.com/package/@types/semver) | 7.7.1 | MIT | https://github.com/DefinitelyTyped/DefinitelyTyped/tree/master/types/semver |
 | [apache-arrow](https://www.npmjs.com/package/apache-arrow) | 21.1.0 | Apache-2.0 | https://arrow.apache.org/js/ |
+| [autoevals](https://www.npmjs.com/package/autoevals) | 0.3.0 | MIT | https://www.braintrust.dev/docs |
 | [class-variance-authority](https://www.npmjs.com/package/class-variance-authority) | 0.7.1 | Apache-2.0 | https://github.com/joe-bell/cva#readme |
 | [clsx](https://www.npmjs.com/package/clsx) | 2.1.1 | MIT | https://github.com/lukeed/clsx#readme |
 | [cmdk](https://www.npmjs.com/package/cmdk) | 1.1.1 | MIT | https://github.com/pacocoursey/cmdk#readme |
@@ -71,7 +73,6 @@ This Software contains code from the following open source projects:
 | [lucide-react](https://www.npmjs.com/package/lucide-react) | 0.554.0 | ISC | https://lucide.dev |
 | [magic-string](https://www.npmjs.com/package/magic-string) | 0.30.21 | MIT | https://github.com/Rich-Harris/magic-string#readme |
 | [marked](https://www.npmjs.com/package/marked) | 16.4.2, 17.0.3 | MIT | https://marked.js.org |
-| [mlflow-tracing](https://www.npmjs.com/package/mlflow-tracing) | 0.1.3 | Apache-2.0 | https://mlflow.org/ |
 | [next-themes](https://www.npmjs.com/package/next-themes) | 0.4.6 | MIT | https://github.com/pacocoursey/next-themes#readme |
 | [obug](https://www.npmjs.com/package/obug) | 2.1.1 | MIT | https://github.com/sxzz/obug#readme |
 | [pg](https://www.npmjs.com/package/pg) | 8.18.0 | MIT | https://github.com/brianc/node-postgres |

package/dist/appkit/package.js

@@ -1,6 +1,6 @@
 //#region package.json
 var name = "@databricks/appkit";
-var version = "0.71.0";
+var version = "0.73.0";
 
 //#endregion
 export { name, version };

package/dist/beta.d.ts

@@ -15,14 +15,29 @@ import { Schema } from "./database/schema-builder/types.js";
 import { bigid, bigint, boolean, enumColumn, id, integer, jsonb, text, timestamp, uuid, varchar } from "./database/schema-builder/columns.js";
 import { defineSchema } from "./database/schema-builder/define-schema.js";
 import { fk } from "./database/schema-builder/fk.js";
+import { DatabricksAuth, ResolveDatabricksAuthOptions, resolveDatabricksAuth, resolveWorkspaceClient } from "./connectors/mlflow/auth.js";
+import { MlflowClient, PostResult, normalizeHost } from "./connectors/mlflow/client.js";
+import { DatasetRow, ReadEvalDatasetOptions, readEvalDataset } from "./evals/dataset.js";
+import { AssertionHandle, AssertionResult, CustomJudgeSpec, DriveResult, EvalDefinition, EvalDriver, EvalResult, MatchResult, Matcher, Severity, TestContext } from "./evals/types.js";
+import { defineEval } from "./evals/define-eval.js";
+import { DiscoveredEval, discoverEvalFiles } from "./evals/discover.js";
+import { HttpDriverOptions, createHttpDriver } from "./evals/http-driver.js";
+import { JudgeConfig, JudgeScore, configureJudge, isJudgeConfigured } from "./evals/judge.js";
+import { equals, includes, matches } from "./evals/matchers.js";
+import { Assessment, ReportOutcome, buildAssessments, reportToMlflow } from "./evals/mlflow-report.js";
+import { EvalSummary, evalGlyph, formatEvalDetail, formatEvalHeadline, formatEvalResults, formatSummaryLine, summarize } from "./evals/report.js";
+import { RunEvalOptions, runEval } from "./evals/run-eval.js";
+import { EvalProgress, EvalRunSummary, RunEvalsOptions, runEvalsInDir } from "./evals/run-evals.js";
+import "./evals/index.js";
 import { agentIdFromMarkdownPath, loadAgentFromFile, loadAgentsFromDir } from "./core/agent/load-agents.js";
 import { agents } from "./plugins/agents/agents.js";
 import "./plugins/agents/index.js";
 import { IAiSearchConfig, IndexConfig, RerankerConfig, SearchFilters, SearchRequest, SearchResponse, SearchResult } from "./plugins/ai-search/types.js";
 import { aiSearch } from "./plugins/ai-search/ai-search.js";
-import { DatabaseExports } from "./plugins/database/entity-types.js";
-import { IDatabaseConfig } from "./plugins/database/types.js";
+import { DatabaseExports, TransactionClient } from "./plugins/database/entity-types.js";
+import { EntityMutationHooks, HookApp, HookContext } from "./plugins/database/hooks.js";
+import { DatabaseApiConfig, DatabaseApiWriteOperation, DatabaseApiWritesConfig, EntityHooks, IDatabaseConfig, ReadSerializer, ReadSerializerContext } from "./plugins/database/types.js";
 import { database } from "./plugins/database/database.js";
 import "./plugins/database/index.js";
 import "./plugins/beta-exports.generated.js";
-export { type AgentAdapter, type AgentDefinition, type AgentEvent, type AgentInput, type AgentRunContext, type AgentTool, type AgentToolDefinition, type AgentTools, type AgentToolsFn, type AgentsPluginConfig, AppKitMcpClient, type AutoInheritToolsConfig, type BaseSystemPromptOption, type DatabaseExports, DatabricksAdapter, type FunctionTool, type GenerationParams, type HostedSupervisorTool, type HostedTool, type IAiSearchConfig, type IDatabaseConfig, type IndexConfig, type McpConnectAllResult, type Message, type PluginToolkitProvider, type Plugins, type PromptContext, type RegisteredAgent, type RerankerConfig, type ResolvedToolEntry, type RunAgentInput, type RunAgentResult, SUPERVISOR_EXTENSION_KEY, type Schema, type SearchFilters, type SearchRequest, type SearchResponse, type SearchResult, SupervisorApiAdapter, type SupervisorApiAdapterOptions, type SupervisorExtension, type SupervisorTool, type Thread, type ThreadStore, type ToolAnnotations, type ToolConfig, type ToolEntry, type ToolProvider, type ToolRegistry, type ToolkitEntry, type ToolkitOptions, type WorkspaceClientLike, agentIdFromMarkdownPath, agents, aiSearch, bigid, bigint, boolean, createAgent, database, defineSchema, defineTool, enumColumn, executeFromRegistry, fk, fromSupervisorApi, functionToolToDefinition, id, integer, isFunctionTool, isHostedTool, isSupervisorTool, isToolkitEntry, jsonb, loadAgentFromFile, loadAgentsFromDir, mcpServer, parseTextToolCalls, resolveHostedTools, runAgent, supervisorTools, text, timestamp, tool, toolsFromRegistry, uuid, varchar };
+export { type AgentAdapter, type AgentDefinition, type AgentEvent, type AgentInput, type AgentRunContext, type AgentTool, type AgentToolDefinition, type AgentTools, type AgentToolsFn, type AgentsPluginConfig, AppKitMcpClient, AssertionHandle, AssertionResult, Assessment, type AutoInheritToolsConfig, type BaseSystemPromptOption, CustomJudgeSpec, type DatabaseApiConfig, type DatabaseApiWriteOperation, type DatabaseApiWritesConfig, type DatabaseExports, DatabricksAdapter, DatabricksAuth, DatasetRow, DiscoveredEval, DriveResult, type EntityHooks, type EntityMutationHooks, EvalDefinition, EvalDriver, EvalProgress, EvalResult, EvalRunSummary, EvalSummary, type FunctionTool, type GenerationParams, type HookApp, type HookContext, type HostedSupervisorTool, type HostedTool, HttpDriverOptions, type IAiSearchConfig, type IDatabaseConfig, type IndexConfig, JudgeConfig, JudgeScore, MatchResult, Matcher, type McpConnectAllResult, type Message, MlflowClient, type PluginToolkitProvider, type Plugins, PostResult, type PromptContext, ReadEvalDatasetOptions, type ReadSerializer, type ReadSerializerContext, type RegisteredAgent, ReportOutcome, type RerankerConfig, ResolveDatabricksAuthOptions, type ResolvedToolEntry, type RunAgentInput, type RunAgentResult, RunEvalOptions, RunEvalsOptions, SUPERVISOR_EXTENSION_KEY, type Schema, type SearchFilters, type SearchRequest, type SearchResponse, type SearchResult, Severity, SupervisorApiAdapter, type SupervisorApiAdapterOptions, type SupervisorExtension, type SupervisorTool, TestContext, type Thread, type ThreadStore, type ToolAnnotations, type ToolConfig, type ToolEntry, type ToolProvider, type ToolRegistry, type ToolkitEntry, type ToolkitOptions, type TransactionClient, type WorkspaceClientLike, agentIdFromMarkdownPath, agents, aiSearch, bigid, bigint, boolean, buildAssessments, configureJudge, createAgent, createHttpDriver, database, defineEval, defineSchema, defineTool, discoverEvalFiles, enumColumn, equals, evalGlyph, executeFromRegistry, fk, formatEvalDetail, formatEvalHeadline, formatEvalResults, formatSummaryLine, fromSupervisorApi, functionToolToDefinition, id, includes, integer, isFunctionTool, isHostedTool, isJudgeConfigured, isSupervisorTool, isToolkitEntry, jsonb, loadAgentFromFile, loadAgentsFromDir, matches, mcpServer, normalizeHost, parseTextToolCalls, readEvalDataset, reportToMlflow, resolveDatabricksAuth, resolveHostedTools, resolveWorkspaceClient, runAgent, runEval, runEvalsInDir, summarize, supervisorTools, text, timestamp, tool, toolsFromRegistry, uuid, varchar };

package/dist/beta.js

@@ -1,4 +1,6 @@
 import { AppKitMcpClient } from "./connectors/mcp/client.js";
+import { resolveDatabricksAuth, resolveWorkspaceClient } from "./connectors/mlflow/auth.js";
+import { MlflowClient, normalizeHost } from "./connectors/mlflow/client.js";
 import { tool } from "./core/agent/tools/tool.js";
 import { defineTool, executeFromRegistry, toolsFromRegistry } from "./core/agent/tools/define-tool.js";
 import { bigid, bigint, boolean, enumColumn, id, integer, jsonb, text, timestamp, uuid, varchar } from "./database/schema-builder/columns.js";
@@ -13,6 +15,17 @@ import { isToolkitEntry } from "./core/agent/types.js";
 import { runAgent } from "./core/agent/run-agent.js";
 import "./core/agent/tools/index.js";
 import "./database/schema-builder/index.js";
+import { readEvalDataset } from "./evals/dataset.js";
+import { defineEval } from "./evals/define-eval.js";
+import { discoverEvalFiles } from "./evals/discover.js";
+import { createHttpDriver } from "./evals/http-driver.js";
+import { configureJudge, isJudgeConfigured } from "./evals/judge.js";
+import { equals, includes, matches } from "./evals/matchers.js";
+import { buildAssessments, reportToMlflow } from "./evals/mlflow-report.js";
+import { evalGlyph, formatEvalDetail, formatEvalHeadline, formatEvalResults, formatSummaryLine, summarize } from "./evals/report.js";
+import { runEval } from "./evals/run-eval.js";
+import { runEvalsInDir } from "./evals/run-evals.js";
+import "./evals/index.js";
 import { agentIdFromMarkdownPath, loadAgentFromFile, loadAgentsFromDir } from "./core/agent/load-agents.js";
 import { agents } from "./plugins/agents/agents.js";
 import "./plugins/agents/index.js";
@@ -20,4 +33,4 @@ import { aiSearch } from "./plugins/ai-search/ai-search.js";
 import { database } from "./plugins/database/database.js";
 import "./plugins/beta-exports.generated.js";
 
-export { AppKitMcpClient, DatabricksAdapter, SUPERVISOR_EXTENSION_KEY, SupervisorApiAdapter, agentIdFromMarkdownPath, agents, aiSearch, bigid, bigint, boolean, createAgent, database, defineSchema, defineTool, enumColumn, executeFromRegistry, fk, fromSupervisorApi, functionToolToDefinition, id, integer, isFunctionTool, isHostedTool, isSupervisorTool, isToolkitEntry, jsonb, loadAgentFromFile, loadAgentsFromDir, mcpServer, parseTextToolCalls, resolveHostedTools, runAgent, supervisorTools, text, timestamp, tool, toolsFromRegistry, uuid, varchar };
+export { AppKitMcpClient, DatabricksAdapter, MlflowClient, SUPERVISOR_EXTENSION_KEY, SupervisorApiAdapter, agentIdFromMarkdownPath, agents, aiSearch, bigid, bigint, boolean, buildAssessments, configureJudge, createAgent, createHttpDriver, database, defineEval, defineSchema, defineTool, discoverEvalFiles, enumColumn, equals, evalGlyph, executeFromRegistry, fk, formatEvalDetail, formatEvalHeadline, formatEvalResults, formatSummaryLine, fromSupervisorApi, functionToolToDefinition, id, includes, integer, isFunctionTool, isHostedTool, isJudgeConfigured, isSupervisorTool, isToolkitEntry, jsonb, loadAgentFromFile, loadAgentsFromDir, matches, mcpServer, normalizeHost, parseTextToolCalls, readEvalDataset, reportToMlflow, resolveDatabricksAuth, resolveHostedTools, resolveWorkspaceClient, runAgent, runEval, runEvalsInDir, summarize, supervisorTools, text, timestamp, tool, toolsFromRegistry, uuid, varchar };

package/dist/cli/commands/agent/eval.js

@@ -0,0 +1,120 @@
+import { Command } from "commander";
+
+//#region src/cli/commands/agent/eval.ts
+/**
+* Loaded at runtime from the consuming project so this command (which ships in
+* `@databricks/shared`) doesn't take a build-time dependency on appkit. The
+* specifier is a variable so the type checker treats it as `any`.
+*/
+async function loadRunner() {
+	const spec = "@databricks/appkit/beta";
+	try {
+		return await import(spec);
+	} catch (err) {
+		throw new Error(`Could not load @databricks/appkit. Run \`appkit agent eval\` from a project with @databricks/appkit installed. Cause: ${err instanceof Error ? err.message : String(err)}`);
+	}
+}
+function parseHeaders(values) {
+	const headers = {};
+	for (const v of values) {
+		const i = v.indexOf(":");
+		if (i === -1) continue;
+		headers[v.slice(0, i).trim()] = v.slice(i + 1).trim();
+	}
+	return headers;
+}
+/**
+* Native MLflow "Evaluation run" config — only when creds + an experiment are
+* all present (traces live in the app; the run + scores are driven from here).
+*/
+function resolveMlflow(opts, auth) {
+	const experimentId = opts.experiment ?? process.env.MLFLOW_EXPERIMENT_ID;
+	if (!(auth.host && auth.token && experimentId)) return void 0;
+	const sqlWarehouseId = opts.warehouseId ?? process.env.MLFLOW_TRACING_SQL_WAREHOUSE_ID ?? process.env.DATABRICKS_WAREHOUSE_ID;
+	return {
+		host: auth.host,
+		token: auth.token,
+		experimentId,
+		...sqlWarehouseId ? { sqlWarehouseId } : {}
+	};
+}
+/** LLM-as-judge config — reuses the Databricks creds + a judge serving endpoint. */
+function resolveJudge(opts, auth) {
+	const model = opts.judgeModel ?? process.env.APPKIT_JUDGE_MODEL;
+	return model && auth.host && auth.token ? {
+		host: auth.host,
+		token: auth.token,
+		model
+	} : void 0;
+}
+/** Progress reporter: stream each eval as it runs instead of going silent. */
+function makeProgressReporter(runner, url) {
+	return (event) => {
+		switch (event.type) {
+			case "discovered":
+				console.log(`Running ${event.total} eval${event.total === 1 ? "" : "s"} against ${url}\n`);
+				break;
+			case "run-created":
+				console.log(`MLflow evaluation run: ${event.runId}\n`);
+				break;
+			case "result":
+				console.log(`[${event.index + 1}/${event.total}] ${runner.formatEvalHeadline(event.result)}`);
+				for (const line of runner.formatEvalDetail(event.result)) console.log(line);
+				break;
+		}
+	};
+}
+function formatFailureLine(f) {
+	return `  ✗ trace ${f.traceId}: ${f.status ?? ""} ${f.error ?? ""}`.trim();
+}
+/** Print the MLflow assessment/finish outcome after a run that created one. */
+function printMlflowOutcome(mlflow) {
+	const { report, finish } = mlflow;
+	console.log(`MLflow: ${report.written} assessment(s) written` + (report.skipped ? `, ${report.skipped} skipped` : "") + (report.failures.length ? `, ${report.failures.length} failed` : ""));
+	for (const f of report.failures) console.error(formatFailureLine(f));
+	if (finish.metricsError) console.error(`  ⚠ metrics not logged: ${finish.metricsError}`);
+	if (!finish.finished) console.error(`  ✗ run left RUNNING — failed to finish: ${finish.finishError ?? "unknown"}`);
+}
+async function runAgentEval(filter, opts) {
+	const runner = await loadRunner();
+	const auth = await runner.resolveDatabricksAuth({
+		profile: opts.profile ?? process.env.DATABRICKS_CONFIG_PROFILE,
+		host: opts.databricksHost ?? process.env.DATABRICKS_HOST,
+		token: opts.databricksToken ?? process.env.DATABRICKS_TOKEN
+	}) ?? {};
+	const warehouseId = opts.warehouseId ?? process.env.DATABRICKS_WAREHOUSE_ID;
+	const workspaceClient = runner.resolveWorkspaceClient({
+		profile: opts.profile ?? process.env.DATABRICKS_CONFIG_PROFILE,
+		host: opts.databricksHost ?? process.env.DATABRICKS_HOST,
+		token: opts.databricksToken ?? process.env.DATABRICKS_TOKEN
+	});
+	let summary;
+	try {
+		summary = await runner.runEvalsInDir({
+			rootDir: opts.root,
+			baseUrl: opts.url,
+			filter,
+			strict: opts.strict,
+			headers: opts.header ? parseHeaders(opts.header) : void 0,
+			concurrency: opts.concurrency,
+			mlflow: resolveMlflow(opts, auth),
+			judge: resolveJudge(opts, auth),
+			workspaceClient,
+			warehouseId,
+			onEvent: makeProgressReporter(runner, opts.url)
+		});
+	} catch (err) {
+		console.error(`\nEval run failed: ${err instanceof Error ? err.message : String(err)}`);
+		process.exitCode = 1;
+		return;
+	}
+	console.log(`\n${runner.formatSummaryLine(summary.results)}`);
+	if (summary.mlflow) printMlflowOutcome(summary.mlflow);
+	else console.log("\nMLflow evaluation run skipped — pass --experiment (or set MLFLOW_EXPERIMENT_ID) plus --profile/--databricks-host to create one.");
+	if (!runner.summarize(summary.results).allPassed) process.exitCode = 1;
+}
+const agentEvalCommand = new Command("eval").description("Run agent evals (server/agents/<id>/evals/*.eval.ts) against a running app").argument("[filter]", "Only run evals whose <agent>/<id> contains this substring (or an exact agent id)").option("--url <url>", "Base URL of the running app", "http://localhost:3000").option("--strict", "Fail on soft-assertion misses too", false).option("--concurrency <n>", "Max evals to run concurrently (default 4; keep at or below the app's max concurrent streams per user)", (v) => Number.parseInt(v, 10)).option("--root <dir>", "Project root containing server/agents/ (default: cwd)").option("--header <header...>", "Extra request header as 'Key: value' (repeatable)").option("--profile <name>", "Databricks CLI profile to authenticate with via OAuth (default: DATABRICKS_CONFIG_PROFILE)").option("--databricks-host <host>", "Databricks host for writing MLflow assessments (default: DATABRICKS_HOST)").option("--databricks-token <token>", "Databricks token for writing MLflow assessments (default: DATABRICKS_TOKEN)").option("--experiment <id>", "MLflow experiment id for the evaluation run (default: MLFLOW_EXPERIMENT_ID)").option("--warehouse-id <id>", "SQL warehouse id for reading managed eval datasets and writing assessments to UC-backed experiments (default: DATABRICKS_WAREHOUSE_ID, or MLFLOW_TRACING_SQL_WAREHOUSE_ID for assessments)").option("--judge-model <endpoint>", "Databricks serving endpoint to use as the LLM judge for t.judge.* (default: APPKIT_JUDGE_MODEL)").action(runAgentEval);
+
+//#endregion
+export { agentEvalCommand };
+//# sourceMappingURL=eval.js.map

package/dist/cli/commands/agent/eval.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"eval.js","names":[],"sources":["../../../../src/cli/commands/agent/eval.ts"],"sourcesContent":["import { Command } from \"commander\";\n\ninterface EvalRunSummary {\n  results: unknown[];\n  mlflow?: {\n    runId: string;\n    report: {\n      written: number;\n      skipped: number;\n      failures: Array<{ traceId: string; status?: number; error?: string }>;\n    };\n    finish: { finished: boolean; metricsError?: string; finishError?: string };\n  };\n}\n\ntype EvalProgress =\n  | { type: \"discovered\"; total: number }\n  | { type: \"run-created\"; runId: string }\n  | { type: \"start\"; id: string; index: number; total: number }\n  | { type: \"result\"; result: unknown; index: number; total: number };\n\n/** Subset of `@databricks/appkit/beta`'s eval runner used by this command. */\ninterface EvalRunner {\n  runEvalsInDir(opts: {\n    rootDir?: string;\n    baseUrl: string;\n    filter?: string;\n    strict?: boolean;\n    headers?: Record<string, string>;\n    concurrency?: number;\n    mlflow?: {\n      host: string;\n      token: string;\n      experimentId: string;\n      sqlWarehouseId?: string;\n    };\n    judge?: { host: string; token: string; model: string };\n    workspaceClient?: unknown;\n    warehouseId?: string;\n    onEvent?: (event: EvalProgress) => void;\n  }): Promise<EvalRunSummary>;\n  resolveDatabricksAuth(opts: {\n    profile?: string;\n    host?: string;\n    token?: string;\n  }): Promise<{ host: string; token: string } | undefined>;\n  resolveWorkspaceClient(opts: {\n    profile?: string;\n    host?: string;\n    token?: string;\n  }): unknown;\n  formatEvalHeadline(result: unknown): string;\n  evalGlyph(result: unknown): string;\n  formatEvalDetail(result: unknown): string[];\n  formatSummaryLine(results: unknown[]): string;\n  summarize(results: unknown[]): { allPassed: boolean };\n}\n\n/**\n * Loaded at runtime from the consuming project so this command (which ships in\n * `@databricks/shared`) doesn't take a build-time dependency on appkit. The\n * specifier is a variable so the type checker treats it as `any`.\n */\nasync function loadRunner(): Promise<EvalRunner> {\n  const spec = \"@databricks/appkit/beta\";\n  try {\n    return (await import(spec)) as unknown as EvalRunner;\n  } catch (err) {\n    throw new Error(\n      \"Could not load @databricks/appkit. Run `appkit agent eval` from a \" +\n        \"project with @databricks/appkit installed. \" +\n        `Cause: ${err instanceof Error ? err.message : String(err)}`,\n    );\n  }\n}\n\nfunction parseHeaders(values: string[]): Record<string, string> {\n  const headers: Record<string, string> = {};\n  for (const v of values) {\n    const i = v.indexOf(\":\");\n    if (i === -1) continue;\n    headers[v.slice(0, i).trim()] = v.slice(i + 1).trim();\n  }\n  return headers;\n}\n\ninterface EvalOptions {\n  url: string;\n  strict?: boolean;\n  root?: string;\n  header?: string[];\n  profile?: string;\n  databricksHost?: string;\n  databricksToken?: string;\n  experiment?: string;\n  judgeModel?: string;\n  concurrency?: number;\n  warehouseId?: string;\n}\n\n/** Resolved Databricks host + bearer (either field may be absent). */\ntype Auth = { host?: string; token?: string };\n\n/**\n * Native MLflow \"Evaluation run\" config — only when creds + an experiment are\n * all present (traces live in the app; the run + scores are driven from here).\n */\nfunction resolveMlflow(opts: EvalOptions, auth: Auth) {\n  const experimentId = opts.experiment ?? process.env.MLFLOW_EXPERIMENT_ID;\n  if (!(auth.host && auth.token && experimentId)) return undefined;\n  // UC-backed experiments need a SQL warehouse to write assessments to their\n  // V4 traces. Mirror mlflow's env var, and accept the common DATABRICKS one.\n  const sqlWarehouseId =\n    opts.warehouseId ??\n    process.env.MLFLOW_TRACING_SQL_WAREHOUSE_ID ??\n    process.env.DATABRICKS_WAREHOUSE_ID;\n  return {\n    host: auth.host,\n    token: auth.token,\n    experimentId,\n    ...(sqlWarehouseId ? { sqlWarehouseId } : {}),\n  };\n}\n\n/** LLM-as-judge config — reuses the Databricks creds + a judge serving endpoint. */\nfunction resolveJudge(opts: EvalOptions, auth: Auth) {\n  const model = opts.judgeModel ?? process.env.APPKIT_JUDGE_MODEL;\n  return model && auth.host && auth.token\n    ? { host: auth.host, token: auth.token, model }\n    : undefined;\n}\n\n/** Progress reporter: stream each eval as it runs instead of going silent. */\nfunction makeProgressReporter(\n  runner: EvalRunner,\n  url: string,\n): (event: EvalProgress) => void {\n  return (event) => {\n    switch (event.type) {\n      case \"discovered\":\n        console.log(\n          `Running ${event.total} eval${event.total === 1 ? \"\" : \"s\"} against ${url}\\n`,\n        );\n        break;\n      case \"run-created\":\n        console.log(`MLflow evaluation run: ${event.runId}\\n`);\n        break;\n      case \"result\": {\n        // One full line per completion — evals run concurrently, so a split\n        // \"start … glyph\" prefix would interleave into garbage.\n        console.log(\n          `[${event.index + 1}/${event.total}] ${runner.formatEvalHeadline(event.result)}`,\n        );\n        for (const line of runner.formatEvalDetail(event.result)) {\n          console.log(line);\n        }\n        break;\n      }\n    }\n  };\n}\n\nfunction formatFailureLine(f: {\n  traceId: string;\n  status?: number;\n  error?: string;\n}): string {\n  return `  ✗ trace ${f.traceId}: ${f.status ?? \"\"} ${f.error ?? \"\"}`.trim();\n}\n\n/** Print the MLflow assessment/finish outcome after a run that created one. */\nfunction printMlflowOutcome(\n  mlflow: NonNullable<EvalRunSummary[\"mlflow\"]>,\n): void {\n  const { report, finish } = mlflow;\n  console.log(\n    `MLflow: ${report.written} assessment(s) written` +\n      (report.skipped ? `, ${report.skipped} skipped` : \"\") +\n      (report.failures.length ? `, ${report.failures.length} failed` : \"\"),\n  );\n  for (const f of report.failures) {\n    console.error(formatFailureLine(f));\n  }\n  if (finish.metricsError) {\n    console.error(`  ⚠ metrics not logged: ${finish.metricsError}`);\n  }\n  if (!finish.finished) {\n    console.error(\n      `  ✗ run left RUNNING — failed to finish: ${finish.finishError ?? \"unknown\"}`,\n    );\n  }\n}\n\nasync function runAgentEval(\n  filter: string | undefined,\n  opts: EvalOptions,\n): Promise<void> {\n  const runner = await loadRunner();\n\n  // Resolve Databricks host + bearer the AppKit-native way: an explicit\n  // host/token (or DATABRICKS_* env) wins; otherwise the SDK mints an OAuth\n  // token from the CLI profile — so no hand-set PAT is required.\n  const auth: Auth =\n    (await runner.resolveDatabricksAuth({\n      profile: opts.profile ?? process.env.DATABRICKS_CONFIG_PROFILE,\n      host: opts.databricksHost ?? process.env.DATABRICKS_HOST,\n      token: opts.databricksToken ?? process.env.DATABRICKS_TOKEN,\n    })) ?? {};\n\n  // Managed-dataset reads: a workspace client (same profile/host/token) + a SQL\n  // warehouse. Only needed by evals that declare `dataset`.\n  const warehouseId = opts.warehouseId ?? process.env.DATABRICKS_WAREHOUSE_ID;\n  const workspaceClient = runner.resolveWorkspaceClient({\n    profile: opts.profile ?? process.env.DATABRICKS_CONFIG_PROFILE,\n    host: opts.databricksHost ?? process.env.DATABRICKS_HOST,\n    token: opts.databricksToken ?? process.env.DATABRICKS_TOKEN,\n  });\n\n  let summary: EvalRunSummary;\n  try {\n    summary = await runner.runEvalsInDir({\n      rootDir: opts.root,\n      baseUrl: opts.url,\n      filter,\n      strict: opts.strict,\n      headers: opts.header ? parseHeaders(opts.header) : undefined,\n      concurrency: opts.concurrency,\n      mlflow: resolveMlflow(opts, auth),\n      judge: resolveJudge(opts, auth),\n      workspaceClient,\n      warehouseId,\n      onEvent: makeProgressReporter(runner, opts.url),\n    });\n  } catch (err) {\n    // Setup failures (e.g. a bad --experiment for the MLflow run) reject before\n    // any eval runs; surface a clean message + non-zero exit rather than an\n    // unhandled promise rejection with a raw stack.\n    console.error(\n      `\\nEval run failed: ${err instanceof Error ? err.message : String(err)}`,\n    );\n    process.exitCode = 1;\n    return;\n  }\n  console.log(`\\n${runner.formatSummaryLine(summary.results)}`);\n\n  if (summary.mlflow) {\n    printMlflowOutcome(summary.mlflow);\n  } else {\n    console.log(\n      \"\\nMLflow evaluation run skipped — pass --experiment (or set\" +\n        \" MLFLOW_EXPERIMENT_ID) plus --profile/--databricks-host to create one.\",\n    );\n  }\n\n  if (!runner.summarize(summary.results).allPassed) {\n    process.exitCode = 1;\n  }\n}\n\nexport const agentEvalCommand = new Command(\"eval\")\n  .description(\n    \"Run agent evals (server/agents/<id>/evals/*.eval.ts) against a running app\",\n  )\n  .argument(\n    \"[filter]\",\n    \"Only run evals whose <agent>/<id> contains this substring (or an exact agent id)\",\n  )\n  .option(\"--url <url>\", \"Base URL of the running app\", \"http://localhost:3000\")\n  .option(\"--strict\", \"Fail on soft-assertion misses too\", false)\n  .option(\n    \"--concurrency <n>\",\n    \"Max evals to run concurrently (default 4; keep at or below the app's max concurrent streams per user)\",\n    (v) => Number.parseInt(v, 10),\n  )\n  .option(\n    \"--root <dir>\",\n    \"Project root containing server/agents/ (default: cwd)\",\n  )\n  .option(\n    \"--header <header...>\",\n    \"Extra request header as 'Key: value' (repeatable)\",\n  )\n  .option(\n    \"--profile <name>\",\n    \"Databricks CLI profile to authenticate with via OAuth (default: DATABRICKS_CONFIG_PROFILE)\",\n  )\n  .option(\n    \"--databricks-host <host>\",\n    \"Databricks host for writing MLflow assessments (default: DATABRICKS_HOST)\",\n  )\n  .option(\n    \"--databricks-token <token>\",\n    \"Databricks token for writing MLflow assessments (default: DATABRICKS_TOKEN)\",\n  )\n  .option(\n    \"--experiment <id>\",\n    \"MLflow experiment id for the evaluation run (default: MLFLOW_EXPERIMENT_ID)\",\n  )\n  .option(\n    \"--warehouse-id <id>\",\n    \"SQL warehouse id for reading managed eval datasets and writing assessments to UC-backed experiments (default: DATABRICKS_WAREHOUSE_ID, or MLFLOW_TRACING_SQL_WAREHOUSE_ID for assessments)\",\n  )\n  .option(\n    \"--judge-model <endpoint>\",\n    \"Databricks serving endpoint to use as the LLM judge for t.judge.* (default: APPKIT_JUDGE_MODEL)\",\n  )\n  .action(runAgentEval);\n"],"mappings":";;;;;;;;AA+DA,eAAe,aAAkC;CAC/C,MAAM,OAAO;AACb,KAAI;AACF,SAAQ,MAAM,OAAO;UACd,KAAK;AACZ,QAAM,IAAI,MACR,yHAEY,eAAe,QAAQ,IAAI,UAAU,OAAO,IAAI,GAC7D;;;AAIL,SAAS,aAAa,QAA0C;CAC9D,MAAM,UAAkC,EAAE;AAC1C,MAAK,MAAM,KAAK,QAAQ;EACtB,MAAM,IAAI,EAAE,QAAQ,IAAI;AACxB,MAAI,MAAM,GAAI;AACd,UAAQ,EAAE,MAAM,GAAG,EAAE,CAAC,MAAM,IAAI,EAAE,MAAM,IAAI,EAAE,CAAC,MAAM;;AAEvD,QAAO;;;;;;AAwBT,SAAS,cAAc,MAAmB,MAAY;CACpD,MAAM,eAAe,KAAK,cAAc,QAAQ,IAAI;AACpD,KAAI,EAAE,KAAK,QAAQ,KAAK,SAAS,cAAe,QAAO;CAGvD,MAAM,iBACJ,KAAK,eACL,QAAQ,IAAI,mCACZ,QAAQ,IAAI;AACd,QAAO;EACL,MAAM,KAAK;EACX,OAAO,KAAK;EACZ;EACA,GAAI,iBAAiB,EAAE,gBAAgB,GAAG,EAAE;EAC7C;;;AAIH,SAAS,aAAa,MAAmB,MAAY;CACnD,MAAM,QAAQ,KAAK,cAAc,QAAQ,IAAI;AAC7C,QAAO,SAAS,KAAK,QAAQ,KAAK,QAC9B;EAAE,MAAM,KAAK;EAAM,OAAO,KAAK;EAAO;EAAO,GAC7C;;;AAIN,SAAS,qBACP,QACA,KAC+B;AAC/B,SAAQ,UAAU;AAChB,UAAQ,MAAM,MAAd;GACE,KAAK;AACH,YAAQ,IACN,WAAW,MAAM,MAAM,OAAO,MAAM,UAAU,IAAI,KAAK,IAAI,WAAW,IAAI,IAC3E;AACD;GACF,KAAK;AACH,YAAQ,IAAI,0BAA0B,MAAM,MAAM,IAAI;AACtD;GACF,KAAK;AAGH,YAAQ,IACN,IAAI,MAAM,QAAQ,EAAE,GAAG,MAAM,MAAM,IAAI,OAAO,mBAAmB,MAAM,OAAO,GAC/E;AACD,SAAK,MAAM,QAAQ,OAAO,iBAAiB,MAAM,OAAO,CACtD,SAAQ,IAAI,KAAK;AAEnB;;;;AAMR,SAAS,kBAAkB,GAIhB;AACT,QAAO,aAAa,EAAE,QAAQ,IAAI,EAAE,UAAU,GAAG,GAAG,EAAE,SAAS,KAAK,MAAM;;;AAI5E,SAAS,mBACP,QACM;CACN,MAAM,EAAE,QAAQ,WAAW;AAC3B,SAAQ,IACN,WAAW,OAAO,QAAQ,2BACvB,OAAO,UAAU,KAAK,OAAO,QAAQ,YAAY,OACjD,OAAO,SAAS,SAAS,KAAK,OAAO,SAAS,OAAO,WAAW,IACpE;AACD,MAAK,MAAM,KAAK,OAAO,SACrB,SAAQ,MAAM,kBAAkB,EAAE,CAAC;AAErC,KAAI,OAAO,aACT,SAAQ,MAAM,2BAA2B,OAAO,eAAe;AAEjE,KAAI,CAAC,OAAO,SACV,SAAQ,MACN,4CAA4C,OAAO,eAAe,YACnE;;AAIL,eAAe,aACb,QACA,MACe;CACf,MAAM,SAAS,MAAM,YAAY;CAKjC,MAAM,OACH,MAAM,OAAO,sBAAsB;EAClC,SAAS,KAAK,WAAW,QAAQ,IAAI;EACrC,MAAM,KAAK,kBAAkB,QAAQ,IAAI;EACzC,OAAO,KAAK,mBAAmB,QAAQ,IAAI;EAC5C,CAAC,IAAK,EAAE;CAIX,MAAM,cAAc,KAAK,eAAe,QAAQ,IAAI;CACpD,MAAM,kBAAkB,OAAO,uBAAuB;EACpD,SAAS,KAAK,WAAW,QAAQ,IAAI;EACrC,MAAM,KAAK,kBAAkB,QAAQ,IAAI;EACzC,OAAO,KAAK,mBAAmB,QAAQ,IAAI;EAC5C,CAAC;CAEF,IAAI;AACJ,KAAI;AACF,YAAU,MAAM,OAAO,cAAc;GACnC,SAAS,KAAK;GACd,SAAS,KAAK;GACd;GACA,QAAQ,KAAK;GACb,SAAS,KAAK,SAAS,aAAa,KAAK,OAAO,GAAG;GACnD,aAAa,KAAK;GAClB,QAAQ,cAAc,MAAM,KAAK;GACjC,OAAO,aAAa,MAAM,KAAK;GAC/B;GACA;GACA,SAAS,qBAAqB,QAAQ,KAAK,IAAI;GAChD,CAAC;UACK,KAAK;AAIZ,UAAQ,MACN,sBAAsB,eAAe,QAAQ,IAAI,UAAU,OAAO,IAAI,GACvE;AACD,UAAQ,WAAW;AACnB;;AAEF,SAAQ,IAAI,KAAK,OAAO,kBAAkB,QAAQ,QAAQ,GAAG;AAE7D,KAAI,QAAQ,OACV,oBAAmB,QAAQ,OAAO;KAElC,SAAQ,IACN,oIAED;AAGH,KAAI,CAAC,OAAO,UAAU,QAAQ,QAAQ,CAAC,UACrC,SAAQ,WAAW;;AAIvB,MAAa,mBAAmB,IAAI,QAAQ,OAAO,CAChD,YACC,6EACD,CACA,SACC,YACA,mFACD,CACA,OAAO,eAAe,+BAA+B,wBAAwB,CAC7E,OAAO,YAAY,qCAAqC,MAAM,CAC9D,OACC,qBACA,0GACC,MAAM,OAAO,SAAS,GAAG,GAAG,CAC9B,CACA,OACC,gBACA,wDACD,CACA,OACC,wBACA,oDACD,CACA,OACC,oBACA,6FACD,CACA,OACC,4BACA,4EACD,CACA,OACC,8BACA,8EACD,CACA,OACC,qBACA,8EACD,CACA,OACC,uBACA,6LACD,CACA,OACC,4BACA,kGACD,CACA,OAAO,aAAa"}

package/dist/cli/commands/agent/index.js

@@ -0,0 +1,18 @@
+import { agentEvalCommand } from "./eval.js";
+import { Command } from "commander";
+
+//#region src/cli/commands/agent/index.ts
+/**
+* Parent command for agent development operations.
+* Subcommands:
+*   - eval: Run agent evals against a running app
+*/
+const agentCommand = new Command("agent").description("Agent development commands").addCommand(agentEvalCommand).addHelpText("after", `
+Examples:
+  $ appkit agent eval
+  $ appkit agent eval support --strict
+  $ appkit agent eval --url https://my-app.databricksapps.com`);
+
+//#endregion
+export { agentCommand };
+//# sourceMappingURL=index.js.map

package/dist/cli/commands/agent/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":[],"sources":["../../../../src/cli/commands/agent/index.ts"],"sourcesContent":["import { Command } from \"commander\";\n\nimport { agentEvalCommand } from \"./eval\";\n\n/**\n * Parent command for agent development operations.\n * Subcommands:\n *   - eval: Run agent evals against a running app\n */\nexport const agentCommand = new Command(\"agent\")\n  .description(\"Agent development commands\")\n  .addCommand(agentEvalCommand)\n  .addHelpText(\n    \"after\",\n    `\nExamples:\n  $ appkit agent eval\n  $ appkit agent eval support --strict\n  $ appkit agent eval --url https://my-app.databricksapps.com`,\n  );\n"],"mappings":";;;;;;;;;AASA,MAAa,eAAe,IAAI,QAAQ,QAAQ,CAC7C,YAAY,6BAA6B,CACzC,WAAW,iBAAiB,CAC5B,YACC,SACA;;;;+DAKD"}

package/dist/cli/index.js

@@ -1,4 +1,5 @@
 #!/usr/bin/env node
+import { agentCommand } from "./commands/agent/index.js";
 import { codemodCommand } from "./commands/codemod/index.js";
 import { docsCommand } from "./commands/docs.js";
 import { doctorCommand } from "./commands/doctor/index.js";
@@ -28,6 +29,7 @@ cmd.addCommand(codemodCommand);
 cmd.addCommand(doctorCommand);
 cmd.addCommand(registryCommand, { hidden: true });
 cmd.addCommand(addCommand, { hidden: true });
+cmd.addCommand(agentCommand);
 await cmd.parseAsync();
 
 //#endregion

package/dist/cli/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","names":[],"sources":["../../src/cli/index.ts"],"sourcesContent":["#!/usr/bin/env node\nimport \"dotenv/config\";\nimport { readFileSync } from \"node:fs\";\nimport { dirname, join } from \"node:path\";\nimport { fileURLToPath } from \"node:url\";\n\nimport { Command } from \"commander\";\n\nimport { codemodCommand } from \"./commands/codemod/index.js\";\nimport { docsCommand } from \"./commands/docs.js\";\nimport { doctorCommand } from \"./commands/doctor/index.js\";\nimport { generateTypesCommand } from \"./commands/generate-types.js\";\nimport { lintCommand } from \"./commands/lint.js\";\nimport { pluginCommand } from \"./commands/plugin/index.js\";\nimport { addCommand } from \"./commands/registry/add.js\";\nimport { registryCommand } from \"./commands/registry/index.js\";\nimport { setupCommand } from \"./commands/setup.js\";\n\nconst __dirname = dirname(fileURLToPath(import.meta.url));\nconst pkgPath = join(__dirname, \"../../package.json\");\nconst pkg = JSON.parse(readFileSync(pkgPath, \"utf-8\"));\n\nconst cmd = new Command();\n\ncmd\n  .name(\"appkit\")\n  .description(\"CLI tools for Databricks AppKit\")\n  .version(pkg.version);\n\ncmd.addCommand(setupCommand);\ncmd.addCommand(generateTypesCommand);\ncmd.addCommand(lintCommand);\ncmd.addCommand(docsCommand);\ncmd.addCommand(pluginCommand);\ncmd.addCommand(codemodCommand);\ncmd.addCommand(doctorCommand);\n// Registry commands are executable but hidden from --help while the feature\n// is still in development (registry + add work end-to-end but aren't announced).\ncmd.addCommand(registryCommand, { hidden: true });\ncmd.addCommand(addCommand, { hidden: true });\n\nawait cmd.parseAsync();\n"],"mappings":";;;;;;;;;;;;;;;;;AAmBA,MAAM,UAAU,KADE,QAAQ,cAAc,OAAO,KAAK,IAAI,CAAC,EACzB,qBAAqB;AACrD,MAAM,MAAM,KAAK,MAAM,aAAa,SAAS,QAAQ,CAAC;AAEtD,MAAM,MAAM,IAAI,SAAS;AAEzB,IACG,KAAK,SAAS,CACd,YAAY,kCAAkC,CAC9C,QAAQ,IAAI,QAAQ;AAEvB,IAAI,WAAW,aAAa;AAC5B,IAAI,WAAW,qBAAqB;AACpC,IAAI,WAAW,YAAY;AAC3B,IAAI,WAAW,YAAY;AAC3B,IAAI,WAAW,cAAc;AAC7B,IAAI,WAAW,eAAe;AAC9B,IAAI,WAAW,cAAc;AAG7B,IAAI,WAAW,iBAAiB,EAAE,QAAQ,MAAM,CAAC;AACjD,IAAI,WAAW,YAAY,EAAE,QAAQ,MAAM,CAAC;AAE5C,MAAM,IAAI,YAAY"}
+{"version":3,"file":"index.js","names":[],"sources":["../../src/cli/index.ts"],"sourcesContent":["#!/usr/bin/env node\nimport \"dotenv/config\";\nimport { readFileSync } from \"node:fs\";\nimport { dirname, join } from \"node:path\";\nimport { fileURLToPath } from \"node:url\";\n\nimport { Command } from \"commander\";\n\nimport { agentCommand } from \"./commands/agent/index.js\";\nimport { codemodCommand } from \"./commands/codemod/index.js\";\nimport { docsCommand } from \"./commands/docs.js\";\nimport { doctorCommand } from \"./commands/doctor/index.js\";\nimport { generateTypesCommand } from \"./commands/generate-types.js\";\nimport { lintCommand } from \"./commands/lint.js\";\nimport { pluginCommand } from \"./commands/plugin/index.js\";\nimport { addCommand } from \"./commands/registry/add.js\";\nimport { registryCommand } from \"./commands/registry/index.js\";\nimport { setupCommand } from \"./commands/setup.js\";\n\nconst __dirname = dirname(fileURLToPath(import.meta.url));\nconst pkgPath = join(__dirname, \"../../package.json\");\nconst pkg = JSON.parse(readFileSync(pkgPath, \"utf-8\"));\n\nconst cmd = new Command();\n\ncmd\n  .name(\"appkit\")\n  .description(\"CLI tools for Databricks AppKit\")\n  .version(pkg.version);\n\ncmd.addCommand(setupCommand);\ncmd.addCommand(generateTypesCommand);\ncmd.addCommand(lintCommand);\ncmd.addCommand(docsCommand);\ncmd.addCommand(pluginCommand);\ncmd.addCommand(codemodCommand);\ncmd.addCommand(doctorCommand);\n// Registry commands are executable but hidden from --help while the feature\n// is still in development (registry + add work end-to-end but aren't announced).\ncmd.addCommand(registryCommand, { hidden: true });\ncmd.addCommand(addCommand, { hidden: true });\ncmd.addCommand(agentCommand);\n\nawait cmd.parseAsync();\n"],"mappings":";;;;;;;;;;;;;;;;;;AAoBA,MAAM,UAAU,KADE,QAAQ,cAAc,OAAO,KAAK,IAAI,CAAC,EACzB,qBAAqB;AACrD,MAAM,MAAM,KAAK,MAAM,aAAa,SAAS,QAAQ,CAAC;AAEtD,MAAM,MAAM,IAAI,SAAS;AAEzB,IACG,KAAK,SAAS,CACd,YAAY,kCAAkC,CAC9C,QAAQ,IAAI,QAAQ;AAEvB,IAAI,WAAW,aAAa;AAC5B,IAAI,WAAW,qBAAqB;AACpC,IAAI,WAAW,YAAY;AAC3B,IAAI,WAAW,YAAY;AAC3B,IAAI,WAAW,cAAc;AAC7B,IAAI,WAAW,eAAe;AAC9B,IAAI,WAAW,cAAc;AAG7B,IAAI,WAAW,iBAAiB,EAAE,QAAQ,MAAM,CAAC;AACjD,IAAI,WAAW,YAAY,EAAE,QAAQ,MAAM,CAAC;AAC5C,IAAI,WAAW,aAAa;AAE5B,MAAM,IAAI,YAAY"}

package/dist/connectors/index.js

@@ -13,6 +13,8 @@ import "./jobs/index.js";
 import { buildMcpHostPolicy } from "./mcp/host-policy.js";
 import { AppKitMcpClient } from "./mcp/client.js";
 import "./mcp/index.js";
+import { resolveDatabricksAuth, resolveWorkspaceClient } from "./mlflow/auth.js";
+import { MlflowClient, normalizeHost } from "./mlflow/client.js";
 import { DEFAULT_WAREHOUSE_STARTUP_TIMEOUT_MS, SQLWarehouseConnector } from "./sql-warehouse/client.js";
 import "./sql-warehouse/index.js";
 

package/dist/connectors/mlflow/auth.d.ts

@@ -0,0 +1,28 @@
+import { WorkspaceClient } from "../../workspace-client/index.js";
+
+//#region src/connectors/mlflow/auth.d.ts
+/** Resolved Databricks host + bearer token for the eval runner's REST calls. */
+interface DatabricksAuth {
+  host: string;
+  token: string;
+}
+interface ResolveDatabricksAuthOptions {
+  /** `~/.databrickscfg` profile to authenticate with (e.g. `dogfood`). */
+  profile?: string;
+  /** Explicit host; wins over the profile/SDK-resolved host when set. */
+  host?: string;
+  /** Explicit bearer token; when set, no OAuth is minted (PAT/CI path). */
+  token?: string;
+}
+declare function resolveDatabricksAuth(options?: ResolveDatabricksAuthOptions): Promise<DatabricksAuth | undefined>;
+/**
+ * Construct a Databricks `WorkspaceClient` for the eval runner — the object the
+ * SDK-backed connectors (e.g. `SQLWarehouseConnector`) take. An explicit
+ * host+token builds a PAT client; otherwise the profile (or ambient config) is
+ * used and the SDK resolves credentials, minting OAuth as needed. Returns
+ * `undefined` if construction throws (missing/invalid config).
+ */
+declare function resolveWorkspaceClient(options?: ResolveDatabricksAuthOptions): WorkspaceClient | undefined;
+//#endregion
+export { DatabricksAuth, ResolveDatabricksAuthOptions, resolveDatabricksAuth, resolveWorkspaceClient };
+//# sourceMappingURL=auth.d.ts.map

package/dist/connectors/mlflow/auth.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"auth.d.ts","names":[],"sources":["../../../src/connectors/mlflow/auth.ts"],"mappings":";;;;UAMiB,cAAA;EACf,IAAA;EACA,KAAA;AAAA;AAAA,UAGe,4BAAA;EAHV;EAKL,OAAA;EAF2C;EAI3C,IAAA;EAJ2C;EAM3C,KAAA;AAAA;AAAA,iBA8CoB,qBAAA,CACpB,OAAA,GAAS,4BAAA,GACR,OAAA,CAAQ,cAAA;;;AAFX;;;;;iBAiBgB,sBAAA,CACd,OAAA,GAAS,4BAAA,GACR,eAAA"}