# Bulk Workspace Resources ## Apply a workspace resource bundle `$ cadenya bulk-workspace-resources apply` **post** `/v1/workspaces/{workspaceId}/bulk_workspace_applies` Asynchronously applies a declarative bundle of workspace resources. Returns the operation immediately in PENDING; clients poll Get to track progress. ### Parameters - `--workspace-id: string` Workspace ID. - `--data: object { bundleKey, agents, automaticallyPublishAgents, 3 more }` ### Returns - `bulk_workspace_apply: object { data, metadata, status, info }` The operation resource produced by a call to BulkWorkspaceResources.Apply. It carries the input bundle in `data`, the lifecycle state in `status`, and aggregate counts in `info`. - `data: object { bundleKey, agents, automaticallyPublishAgents, 3 more }` - `bundleKey: string` Required. Bundle ownership key. Resources created or updated by an Apply have their `metadata.bundle_key` set to this value. On subsequent applies with the same bundle_key, resources currently bearing this bundle_key but absent from the spec are soft-deleted. - `agents: optional map[AgentEntry]` Agents to upsert, keyed by external_id. - `name: string` - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `labels: optional map[string]` - `schedules: optional map[AgentScheduleEntry]` Schedules under this agent, keyed by external_id. - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` - `variations: optional map[AgentVariationEntry]` Variations under this agent, keyed by external_id. - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` - `automaticallyPublishAgents: optional boolean` When true, every agent created or updated by this Apply has its status forced to AGENT_STATUS_PUBLISHED, regardless of the status declared in the agent's AgentSpec. Useful when the bundle represents a production configuration and you want all of its agents live without setting status: AGENT_STATUS_PUBLISHED on each entry. Default false: each agent's AgentSpec.status controls (which is AGENT_STATUS_DRAFT on create when unspecified). - `memoryLayers: optional map[MemoryLayerEntry]` Memory layers to upsert, keyed by external_id. - `name: string` - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `entries: optional map[MemoryEntryItem]` Memory entries in this layer, keyed by external_id. - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` - `labels: optional map[string]` - `sourceUrl: optional string` Optional URL pointing to the source of this apply (GitHub PR, Jenkins build, GitLab pipeline, etc.). Surfaced in the dashboard so users can jump from an apply back to the change that produced it. Free-form HTTPS URI; not interpreted by the server. - `toolSets: optional map[ToolSetEntry]` Tool sets to upsert, keyed by external_id. - `name: string` - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `labels: optional map[string]` - `tools: optional map[ToolEntry]` Tools in this tool set, keyed by external_id. - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` - `metadata: object { id, accountId, createdAt, 4 more }` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `id: string` Unique identifier for the operation (prefixed ULID, e.g., "obj_01HXK...") - `accountId: string` Account this operation belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying - `profileId: string` ID of the actor (user or service account) that created this operation - `workspaceId: string` Workspace this operation belongs to for organizational grouping (prefixed ULID) - `externalId: optional string` External ID for the operation (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: object { state, message, preflightError }` - `state: "STATE_UNSPECIFIED" or "STATE_PENDING" or "STATE_VALIDATING" or 5 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_VALIDATING"` - `"STATE_RUNNING"` - `"STATE_SUCCEEDED"` - `"STATE_PARTIALLY_APPLIED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message: optional string` - `preflightError: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `info: optional object { completedAt, createdBy, createdCount, 6 more }` - `completedAt: optional string` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `createdCount: optional number` - `deletedCount: optional number` - `failedCount: optional number` - `startedAt: optional string` - `totalCount: optional number` - `unchangedCount: optional number` - `updatedCount: optional number` ### Example ```cli cadenya bulk-workspace-resources apply \ --api-key 'My API Key' \ --workspace-id workspaceId \ --data '{bundleKey: bundleKey}' ``` #### Response ```json { "data": { "bundleKey": "bundleKey", "agents": { "foo": { "name": "name", "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "inputDataSchema": { "foo": "bar" }, "outputDefinition": { "foo": "bar" }, "webhookEventsUrl": "webhookEventsUrl" }, "labels": { "foo": "string" }, "schedules": { "foo": { "name": "name", "spec": { "initialMessage": "initialMessage", "schedule": { "calendars": [ { "comment": "comment", "dayOfMonth": [ { "end": 0, "start": 0, "step": 0 } ], "dayOfWeek": [ { "end": 0, "start": 0, "step": 0 } ], "hour": [ { "end": 0, "start": 0, "step": 0 } ], "minute": [ { "end": 0, "start": 0, "step": 0 } ], "month": [ { "end": 0, "start": 0, "step": 0 } ], "second": [ { "end": 0, "start": 0, "step": 0 } ] } ], "intervals": [ { "every": "-160513s", "offset": "-160513s" } ], "timezone": "timezone" }, "data": {}, "overlapPolicy": "OVERLAP_POLICY_UNSPECIFIED", "status": "AGENT_SCHEDULE_STATUS_UNSPECIFIED", "variationId": "variationId" }, "labels": { "foo": "string" } } }, "variations": { "foo": { "name": "name", "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "progressiveDiscovery": { "hints": [ "string" ], "maxTools": 0, "rerankThreshold": 0 }, "prompt": "prompt", "weight": 0 }, "assignments": [ { "subAgentId": "subAgentId", "toolId": "toolId", "toolSetId": "toolSetId" } ], "labels": { "foo": "string" }, "memoryLayers": [ { "memoryLayerId": "memoryLayerId", "position": 0 } ] } } } }, "automaticallyPublishAgents": true, "memoryLayers": { "foo": { "name": "name", "spec": { "type": "MEMORY_LAYER_TYPE_UNSPECIFIED", "description": "description", "expiresAt": "2019-12-27T18:11:19.117Z", "systemManaged": true }, "entries": { "foo": { "key": "key", "content": "content", "description": "description", "uploadId": "uploadId" } }, "labels": { "foo": "string" } } }, "sourceUrl": "sourceUrl", "toolSets": { "foo": { "name": "name", "spec": { "adapter": { "http": { "baseUrl": "baseUrl", "headers": { "foo": "string" } }, "mcp": { "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "url": "url" }, "openapi": { "baseUrl": "baseUrl", "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "serverName": "serverName", "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "uploadId": "uploadId", "url": "url" } }, "description": "description" }, "labels": { "foo": "string" }, "tools": { "foo": { "name": "name", "spec": { "config": { "http": { "requestMethod": "HTTP_METHOD_UNSPECIFIED", "headers": { "foo": "string" }, "path": "path", "query": "query", "requestBodyContentType": "requestBodyContentType", "requestBodyTemplate": "requestBodyTemplate", "toolName": "toolName" }, "mcp": { "toolDescription": "toolDescription", "toolName": "toolName", "toolTitle": "toolTitle" }, "openapi": { "method": "method", "operationId": "operationId", "path": "path" } }, "description": "description", "parameters": { "foo": "bar" }, "status": "TOOL_STATUS_UNSPECIFIED", "requiresApproval": true }, "labels": { "foo": "string" } } } } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message", "preflightError": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" } }, "info": { "completedAt": "2019-12-27T18:11:19.117Z", "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "createdCount": 0, "deletedCount": 0, "failedCount": 0, "startedAt": "2019-12-27T18:11:19.117Z", "totalCount": 0, "unchangedCount": 0, "updatedCount": 0 } } ``` ## Get a bulk workspace apply operation `$ cadenya bulk-workspace-resources retrieve` **get** `/v1/workspaces/{workspaceId}/bulk_workspace_applies/{id}` Retrieves a bulk workspace apply operation by ID. ### Parameters - `--workspace-id: string` Workspace ID. - `--id: string` Apply ID in canonical apply_… form. Bulk applies do not support external_id lookup. ### Returns - `bulk_workspace_apply: object { data, metadata, status, info }` The operation resource produced by a call to BulkWorkspaceResources.Apply. It carries the input bundle in `data`, the lifecycle state in `status`, and aggregate counts in `info`. - `data: object { bundleKey, agents, automaticallyPublishAgents, 3 more }` - `bundleKey: string` Required. Bundle ownership key. Resources created or updated by an Apply have their `metadata.bundle_key` set to this value. On subsequent applies with the same bundle_key, resources currently bearing this bundle_key but absent from the spec are soft-deleted. - `agents: optional map[AgentEntry]` Agents to upsert, keyed by external_id. - `name: string` - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `labels: optional map[string]` - `schedules: optional map[AgentScheduleEntry]` Schedules under this agent, keyed by external_id. - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` - `variations: optional map[AgentVariationEntry]` Variations under this agent, keyed by external_id. - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` - `automaticallyPublishAgents: optional boolean` When true, every agent created or updated by this Apply has its status forced to AGENT_STATUS_PUBLISHED, regardless of the status declared in the agent's AgentSpec. Useful when the bundle represents a production configuration and you want all of its agents live without setting status: AGENT_STATUS_PUBLISHED on each entry. Default false: each agent's AgentSpec.status controls (which is AGENT_STATUS_DRAFT on create when unspecified). - `memoryLayers: optional map[MemoryLayerEntry]` Memory layers to upsert, keyed by external_id. - `name: string` - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `entries: optional map[MemoryEntryItem]` Memory entries in this layer, keyed by external_id. - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` - `labels: optional map[string]` - `sourceUrl: optional string` Optional URL pointing to the source of this apply (GitHub PR, Jenkins build, GitLab pipeline, etc.). Surfaced in the dashboard so users can jump from an apply back to the change that produced it. Free-form HTTPS URI; not interpreted by the server. - `toolSets: optional map[ToolSetEntry]` Tool sets to upsert, keyed by external_id. - `name: string` - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `labels: optional map[string]` - `tools: optional map[ToolEntry]` Tools in this tool set, keyed by external_id. - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` - `metadata: object { id, accountId, createdAt, 4 more }` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `id: string` Unique identifier for the operation (prefixed ULID, e.g., "obj_01HXK...") - `accountId: string` Account this operation belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying - `profileId: string` ID of the actor (user or service account) that created this operation - `workspaceId: string` Workspace this operation belongs to for organizational grouping (prefixed ULID) - `externalId: optional string` External ID for the operation (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: object { state, message, preflightError }` - `state: "STATE_UNSPECIFIED" or "STATE_PENDING" or "STATE_VALIDATING" or 5 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_VALIDATING"` - `"STATE_RUNNING"` - `"STATE_SUCCEEDED"` - `"STATE_PARTIALLY_APPLIED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message: optional string` - `preflightError: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `info: optional object { completedAt, createdBy, createdCount, 6 more }` - `completedAt: optional string` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `createdCount: optional number` - `deletedCount: optional number` - `failedCount: optional number` - `startedAt: optional string` - `totalCount: optional number` - `unchangedCount: optional number` - `updatedCount: optional number` ### Example ```cli cadenya bulk-workspace-resources retrieve \ --api-key 'My API Key' \ --workspace-id workspaceId \ --id id ``` #### Response ```json { "data": { "bundleKey": "bundleKey", "agents": { "foo": { "name": "name", "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "inputDataSchema": { "foo": "bar" }, "outputDefinition": { "foo": "bar" }, "webhookEventsUrl": "webhookEventsUrl" }, "labels": { "foo": "string" }, "schedules": { "foo": { "name": "name", "spec": { "initialMessage": "initialMessage", "schedule": { "calendars": [ { "comment": "comment", "dayOfMonth": [ { "end": 0, "start": 0, "step": 0 } ], "dayOfWeek": [ { "end": 0, "start": 0, "step": 0 } ], "hour": [ { "end": 0, "start": 0, "step": 0 } ], "minute": [ { "end": 0, "start": 0, "step": 0 } ], "month": [ { "end": 0, "start": 0, "step": 0 } ], "second": [ { "end": 0, "start": 0, "step": 0 } ] } ], "intervals": [ { "every": "-160513s", "offset": "-160513s" } ], "timezone": "timezone" }, "data": {}, "overlapPolicy": "OVERLAP_POLICY_UNSPECIFIED", "status": "AGENT_SCHEDULE_STATUS_UNSPECIFIED", "variationId": "variationId" }, "labels": { "foo": "string" } } }, "variations": { "foo": { "name": "name", "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "progressiveDiscovery": { "hints": [ "string" ], "maxTools": 0, "rerankThreshold": 0 }, "prompt": "prompt", "weight": 0 }, "assignments": [ { "subAgentId": "subAgentId", "toolId": "toolId", "toolSetId": "toolSetId" } ], "labels": { "foo": "string" }, "memoryLayers": [ { "memoryLayerId": "memoryLayerId", "position": 0 } ] } } } }, "automaticallyPublishAgents": true, "memoryLayers": { "foo": { "name": "name", "spec": { "type": "MEMORY_LAYER_TYPE_UNSPECIFIED", "description": "description", "expiresAt": "2019-12-27T18:11:19.117Z", "systemManaged": true }, "entries": { "foo": { "key": "key", "content": "content", "description": "description", "uploadId": "uploadId" } }, "labels": { "foo": "string" } } }, "sourceUrl": "sourceUrl", "toolSets": { "foo": { "name": "name", "spec": { "adapter": { "http": { "baseUrl": "baseUrl", "headers": { "foo": "string" } }, "mcp": { "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "url": "url" }, "openapi": { "baseUrl": "baseUrl", "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "serverName": "serverName", "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "uploadId": "uploadId", "url": "url" } }, "description": "description" }, "labels": { "foo": "string" }, "tools": { "foo": { "name": "name", "spec": { "config": { "http": { "requestMethod": "HTTP_METHOD_UNSPECIFIED", "headers": { "foo": "string" }, "path": "path", "query": "query", "requestBodyContentType": "requestBodyContentType", "requestBodyTemplate": "requestBodyTemplate", "toolName": "toolName" }, "mcp": { "toolDescription": "toolDescription", "toolName": "toolName", "toolTitle": "toolTitle" }, "openapi": { "method": "method", "operationId": "operationId", "path": "path" } }, "description": "description", "parameters": { "foo": "bar" }, "status": "TOOL_STATUS_UNSPECIFIED", "requiresApproval": true }, "labels": { "foo": "string" } } } } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message", "preflightError": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" } }, "info": { "completedAt": "2019-12-27T18:11:19.117Z", "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "createdCount": 0, "deletedCount": 0, "failedCount": 0, "startedAt": "2019-12-27T18:11:19.117Z", "totalCount": 0, "unchangedCount": 0, "updatedCount": 0 } } ``` ## List bulk workspace apply operations `$ cadenya bulk-workspace-resources list` **get** `/v1/workspaces/{workspaceId}/bulk_workspace_applies` Lists past and in-flight bulk workspace apply operations in the workspace. ### Parameters - `--workspace-id: string` Workspace ID. - `--bundle-key: optional string` Filter by bundle_key — list every apply for a given bundle. - `--cursor: optional string` Pagination cursor from previous response - `--limit: optional number` Maximum number of results to return - `--sort-order: optional string` Sort order for results (asc or desc by creation time) - `--state: optional "STATE_UNSPECIFIED" or "STATE_PENDING" or "STATE_VALIDATING" or 5 more` Filter by lifecycle state. ### Returns - `ListBulkWorkspaceAppliesResponse: object { items, pagination }` - `items: optional array of BulkWorkspaceApply` - `data: object { bundleKey, agents, automaticallyPublishAgents, 3 more }` - `bundleKey: string` Required. Bundle ownership key. Resources created or updated by an Apply have their `metadata.bundle_key` set to this value. On subsequent applies with the same bundle_key, resources currently bearing this bundle_key but absent from the spec are soft-deleted. - `agents: optional map[AgentEntry]` Agents to upsert, keyed by external_id. - `name: string` - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `labels: optional map[string]` - `schedules: optional map[AgentScheduleEntry]` Schedules under this agent, keyed by external_id. - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` - `variations: optional map[AgentVariationEntry]` Variations under this agent, keyed by external_id. - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` - `automaticallyPublishAgents: optional boolean` When true, every agent created or updated by this Apply has its status forced to AGENT_STATUS_PUBLISHED, regardless of the status declared in the agent's AgentSpec. Useful when the bundle represents a production configuration and you want all of its agents live without setting status: AGENT_STATUS_PUBLISHED on each entry. Default false: each agent's AgentSpec.status controls (which is AGENT_STATUS_DRAFT on create when unspecified). - `memoryLayers: optional map[MemoryLayerEntry]` Memory layers to upsert, keyed by external_id. - `name: string` - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `entries: optional map[MemoryEntryItem]` Memory entries in this layer, keyed by external_id. - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` - `labels: optional map[string]` - `sourceUrl: optional string` Optional URL pointing to the source of this apply (GitHub PR, Jenkins build, GitLab pipeline, etc.). Surfaced in the dashboard so users can jump from an apply back to the change that produced it. Free-form HTTPS URI; not interpreted by the server. - `toolSets: optional map[ToolSetEntry]` Tool sets to upsert, keyed by external_id. - `name: string` - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `labels: optional map[string]` - `tools: optional map[ToolEntry]` Tools in this tool set, keyed by external_id. - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` - `metadata: object { id, accountId, createdAt, 4 more }` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `id: string` Unique identifier for the operation (prefixed ULID, e.g., "obj_01HXK...") - `accountId: string` Account this operation belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying - `profileId: string` ID of the actor (user or service account) that created this operation - `workspaceId: string` Workspace this operation belongs to for organizational grouping (prefixed ULID) - `externalId: optional string` External ID for the operation (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: object { state, message, preflightError }` - `state: "STATE_UNSPECIFIED" or "STATE_PENDING" or "STATE_VALIDATING" or 5 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_VALIDATING"` - `"STATE_RUNNING"` - `"STATE_SUCCEEDED"` - `"STATE_PARTIALLY_APPLIED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message: optional string` - `preflightError: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `info: optional object { completedAt, createdBy, createdCount, 6 more }` - `completedAt: optional string` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `createdCount: optional number` - `deletedCount: optional number` - `failedCount: optional number` - `startedAt: optional string` - `totalCount: optional number` - `unchangedCount: optional number` - `updatedCount: optional number` - `pagination: optional object { nextCursor, total }` - `nextCursor: optional string` - `total: optional number` ### Example ```cli cadenya bulk-workspace-resources list \ --api-key 'My API Key' \ --workspace-id workspaceId ``` #### Response ```json { "items": [ { "data": { "bundleKey": "bundleKey", "agents": { "foo": { "name": "name", "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "inputDataSchema": { "foo": "bar" }, "outputDefinition": { "foo": "bar" }, "webhookEventsUrl": "webhookEventsUrl" }, "labels": { "foo": "string" }, "schedules": { "foo": { "name": "name", "spec": { "initialMessage": "initialMessage", "schedule": { "calendars": [ { "comment": "comment", "dayOfMonth": [ { "end": 0, "start": 0, "step": 0 } ], "dayOfWeek": [ { "end": 0, "start": 0, "step": 0 } ], "hour": [ { "end": 0, "start": 0, "step": 0 } ], "minute": [ { "end": 0, "start": 0, "step": 0 } ], "month": [ { "end": 0, "start": 0, "step": 0 } ], "second": [ { "end": 0, "start": 0, "step": 0 } ] } ], "intervals": [ { "every": "-160513s", "offset": "-160513s" } ], "timezone": "timezone" }, "data": {}, "overlapPolicy": "OVERLAP_POLICY_UNSPECIFIED", "status": "AGENT_SCHEDULE_STATUS_UNSPECIFIED", "variationId": "variationId" }, "labels": { "foo": "string" } } }, "variations": { "foo": { "name": "name", "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "progressiveDiscovery": { "hints": [ "string" ], "maxTools": 0, "rerankThreshold": 0 }, "prompt": "prompt", "weight": 0 }, "assignments": [ { "subAgentId": "subAgentId", "toolId": "toolId", "toolSetId": "toolSetId" } ], "labels": { "foo": "string" }, "memoryLayers": [ { "memoryLayerId": "memoryLayerId", "position": 0 } ] } } } }, "automaticallyPublishAgents": true, "memoryLayers": { "foo": { "name": "name", "spec": { "type": "MEMORY_LAYER_TYPE_UNSPECIFIED", "description": "description", "expiresAt": "2019-12-27T18:11:19.117Z", "systemManaged": true }, "entries": { "foo": { "key": "key", "content": "content", "description": "description", "uploadId": "uploadId" } }, "labels": { "foo": "string" } } }, "sourceUrl": "sourceUrl", "toolSets": { "foo": { "name": "name", "spec": { "adapter": { "http": { "baseUrl": "baseUrl", "headers": { "foo": "string" } }, "mcp": { "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "url": "url" }, "openapi": { "baseUrl": "baseUrl", "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "serverName": "serverName", "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "uploadId": "uploadId", "url": "url" } }, "description": "description" }, "labels": { "foo": "string" }, "tools": { "foo": { "name": "name", "spec": { "config": { "http": { "requestMethod": "HTTP_METHOD_UNSPECIFIED", "headers": { "foo": "string" }, "path": "path", "query": "query", "requestBodyContentType": "requestBodyContentType", "requestBodyTemplate": "requestBodyTemplate", "toolName": "toolName" }, "mcp": { "toolDescription": "toolDescription", "toolName": "toolName", "toolTitle": "toolTitle" }, "openapi": { "method": "method", "operationId": "operationId", "path": "path" } }, "description": "description", "parameters": { "foo": "bar" }, "status": "TOOL_STATUS_UNSPECIFIED", "requiresApproval": true }, "labels": { "foo": "string" } } } } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message", "preflightError": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" } }, "info": { "completedAt": "2019-12-27T18:11:19.117Z", "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "createdCount": 0, "deletedCount": 0, "failedCount": 0, "startedAt": "2019-12-27T18:11:19.117Z", "totalCount": 0, "unchangedCount": 0, "updatedCount": 0 } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Domain Types ### Agent Entry - `agent_entry: object { name, spec, labels, 2 more }` - `name: string` - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `labels: optional map[string]` - `schedules: optional map[AgentScheduleEntry]` Schedules under this agent, keyed by external_id. - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` - `variations: optional map[AgentVariationEntry]` Variations under this agent, keyed by external_id. - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` ### Agent Schedule Entry - `agent_schedule_entry: object { name, spec, labels }` - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` ### Agent Variation Entry - `agent_variation_entry: object { name, spec, assignments, 2 more }` - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` ### Bulk Workspace Apply - `bulk_workspace_apply: object { data, metadata, status, info }` The operation resource produced by a call to BulkWorkspaceResources.Apply. It carries the input bundle in `data`, the lifecycle state in `status`, and aggregate counts in `info`. - `data: object { bundleKey, agents, automaticallyPublishAgents, 3 more }` - `bundleKey: string` Required. Bundle ownership key. Resources created or updated by an Apply have their `metadata.bundle_key` set to this value. On subsequent applies with the same bundle_key, resources currently bearing this bundle_key but absent from the spec are soft-deleted. - `agents: optional map[AgentEntry]` Agents to upsert, keyed by external_id. - `name: string` - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `labels: optional map[string]` - `schedules: optional map[AgentScheduleEntry]` Schedules under this agent, keyed by external_id. - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` - `variations: optional map[AgentVariationEntry]` Variations under this agent, keyed by external_id. - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` - `automaticallyPublishAgents: optional boolean` When true, every agent created or updated by this Apply has its status forced to AGENT_STATUS_PUBLISHED, regardless of the status declared in the agent's AgentSpec. Useful when the bundle represents a production configuration and you want all of its agents live without setting status: AGENT_STATUS_PUBLISHED on each entry. Default false: each agent's AgentSpec.status controls (which is AGENT_STATUS_DRAFT on create when unspecified). - `memoryLayers: optional map[MemoryLayerEntry]` Memory layers to upsert, keyed by external_id. - `name: string` - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `entries: optional map[MemoryEntryItem]` Memory entries in this layer, keyed by external_id. - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` - `labels: optional map[string]` - `sourceUrl: optional string` Optional URL pointing to the source of this apply (GitHub PR, Jenkins build, GitLab pipeline, etc.). Surfaced in the dashboard so users can jump from an apply back to the change that produced it. Free-form HTTPS URI; not interpreted by the server. - `toolSets: optional map[ToolSetEntry]` Tool sets to upsert, keyed by external_id. - `name: string` - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `labels: optional map[string]` - `tools: optional map[ToolEntry]` Tools in this tool set, keyed by external_id. - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` - `metadata: object { id, accountId, createdAt, 4 more }` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `id: string` Unique identifier for the operation (prefixed ULID, e.g., "obj_01HXK...") - `accountId: string` Account this operation belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying - `profileId: string` ID of the actor (user or service account) that created this operation - `workspaceId: string` Workspace this operation belongs to for organizational grouping (prefixed ULID) - `externalId: optional string` External ID for the operation (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: object { state, message, preflightError }` - `state: "STATE_UNSPECIFIED" or "STATE_PENDING" or "STATE_VALIDATING" or 5 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_VALIDATING"` - `"STATE_RUNNING"` - `"STATE_SUCCEEDED"` - `"STATE_PARTIALLY_APPLIED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message: optional string` - `preflightError: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `info: optional object { completedAt, createdBy, createdCount, 6 more }` - `completedAt: optional string` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `createdCount: optional number` - `deletedCount: optional number` - `failedCount: optional number` - `startedAt: optional string` - `totalCount: optional number` - `unchangedCount: optional number` - `updatedCount: optional number` ### Bulk Workspace Apply Data - `bulk_workspace_apply_data: object { bundleKey, agents, automaticallyPublishAgents, 3 more }` - `bundleKey: string` Required. Bundle ownership key. Resources created or updated by an Apply have their `metadata.bundle_key` set to this value. On subsequent applies with the same bundle_key, resources currently bearing this bundle_key but absent from the spec are soft-deleted. - `agents: optional map[AgentEntry]` Agents to upsert, keyed by external_id. - `name: string` - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `labels: optional map[string]` - `schedules: optional map[AgentScheduleEntry]` Schedules under this agent, keyed by external_id. - `name: string` - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `labels: optional map[string]` - `variations: optional map[AgentVariationEntry]` Variations under this agent, keyed by external_id. - `name: string` - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `assignments: optional array of VariationAssignmentEntry` Reconciled list — server adjusts the variation's assignments to exactly this set when the variation is bundle-owned. - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` - `labels: optional map[string]` - `memoryLayers: optional array of VariationMemoryLayerEntry` Reconciled list of memory layer assignments. Up to 10 entries. - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` - `automaticallyPublishAgents: optional boolean` When true, every agent created or updated by this Apply has its status forced to AGENT_STATUS_PUBLISHED, regardless of the status declared in the agent's AgentSpec. Useful when the bundle represents a production configuration and you want all of its agents live without setting status: AGENT_STATUS_PUBLISHED on each entry. Default false: each agent's AgentSpec.status controls (which is AGENT_STATUS_DRAFT on create when unspecified). - `memoryLayers: optional map[MemoryLayerEntry]` Memory layers to upsert, keyed by external_id. - `name: string` - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `entries: optional map[MemoryEntryItem]` Memory entries in this layer, keyed by external_id. - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` - `labels: optional map[string]` - `sourceUrl: optional string` Optional URL pointing to the source of this apply (GitHub PR, Jenkins build, GitLab pipeline, etc.). Surfaced in the dashboard so users can jump from an apply back to the change that produced it. Free-form HTTPS URI; not interpreted by the server. - `toolSets: optional map[ToolSetEntry]` Tool sets to upsert, keyed by external_id. - `name: string` - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `labels: optional map[string]` - `tools: optional map[ToolEntry]` Tools in this tool set, keyed by external_id. - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` ### Bulk Workspace Apply Info - `bulk_workspace_apply_info: object { completedAt, createdBy, createdCount, 6 more }` - `completedAt: optional string` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `createdCount: optional number` - `deletedCount: optional number` - `failedCount: optional number` - `startedAt: optional string` - `totalCount: optional number` - `unchangedCount: optional number` - `updatedCount: optional number` ### Bulk Workspace Apply Status - `bulk_workspace_apply_status: object { state, message, preflightError }` - `state: "STATE_UNSPECIFIED" or "STATE_PENDING" or "STATE_VALIDATING" or 5 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_VALIDATING"` - `"STATE_RUNNING"` - `"STATE_SUCCEEDED"` - `"STATE_PARTIALLY_APPLIED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message: optional string` - `preflightError: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. ### Memory Entry Item - `memory_entry_item: object { key, content, description, uploadId }` - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` ### Memory Layer Entry - `memory_layer_entry: object { name, spec, entries, labels }` - `name: string` - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `entries: optional map[MemoryEntryItem]` Memory entries in this layer, keyed by external_id. - `key: string` - `content: optional string` - `description: optional string` - `uploadId: optional string` - `labels: optional map[string]` ### Tool Entry - `tool_entry: object { name, spec, labels }` - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` ### Tool Set Entry - `tool_set_entry: object { name, spec, labels, tools }` - `name: string` - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `labels: optional map[string]` - `tools: optional map[ToolEntry]` Tools in this tool set, keyed by external_id. - `name: string` - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `labels: optional map[string]` ### Variation Assignment Entry - `variation_assignment_entry: object { subAgentId, toolId, toolSetId }` - `subAgentId: optional string` - `toolId: optional string` - `toolSetId: optional string` ### Variation Memory Layer Entry - `variation_memory_layer_entry: object { memoryLayerId, position }` - `memoryLayerId: optional string` external_id: form. Canonical IDs are rejected. - `position: optional number` # Results ## List per-resource results for a bulk workspace apply `$ cadenya bulk-workspace-resources:results list` **get** `/v1/workspaces/{workspaceId}/bulk_workspace_applies/{bulkWorkspaceApplyId}/results` Lists each resource action recorded by a bulk workspace apply operation. ### Parameters - `--workspace-id: string` Workspace ID. - `--bulk-workspace-apply-id: string` Apply ID in canonical apply_… form. - `--action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` Filter by action. - `--cursor: optional string` Pagination cursor from previous response - `--limit: optional number` Maximum number of results to return - `--sort-order: optional string` Sort order for results (asc or desc by creation time) - `--type: optional string` Filter by data.type discriminator (e.g., "toolSet", "memoryEntry"). ### Returns - `ListBulkWorkspaceApplyResultsResponse: object { items, pagination }` - `items: optional array of BulkWorkspaceApplyResult` - `data: object { agent, agentSchedule, agentVariation, 7 more }` Outcome for a single resource within a bulk apply. The `type` field is the discriminator string naming the populated `outcome` oneof variant (e.g., "toolSet", "memoryEntry"). Every outcome shell carries an `action` enum and either a resulting resource snapshot (for ACTION_CREATED, ACTION_UPDATED, ACTION_UNCHANGED, ACTION_DELETED) or a google.rpc.Status (for ACTION_FAILED). - `agent: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` Agent resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `info: optional object { createdBy, variationCount }` AgentInfo contains simple information about an agent for display or quick reference - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `variationCount: optional number` - `agentSchedule: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentSchedule resource — a recurring trigger attached to an agent that creates objectives on its cadence. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `info: optional object { createdBy, lastFireAt, lastObjectiveId, 4 more }` AgentScheduleInfo provides read-only runtime data about a schedule. - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `lastFireAt: optional string` When the schedule last fired (regardless of objective outcome). - `lastObjectiveId: optional string` ID of the most recent objective the schedule created. - `lastSkippedAt: optional string` When the schedule most recently skipped a fire (SKIP policy + prior in flight). - `lastSkipReason: optional string` Reason for the most recent skip (e.g. "previous objective still running"). - `nextFireAt: optional string` When the schedule will next fire. Computed from the spec; absent when the schedule is PAUSED/ARCHIVED or has no future fire times. - `totalFires: optional number` Lifetime count of objectives created by this schedule. - `agentVariation: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentVariation resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `info: optional object { assignments, createdBy, feedbackCount, 7 more }` AgentVariationInfo provides read-only summary information about a variation - `assignments: optional array of VariationAssignment` All tools, tool sets, and sub-agents assigned to this variation. Populated on reads so clients can render a variation's full assignment list without calling the add/remove endpoints just to enumerate. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `feedbackCount: optional number` Total number of objective feedbacks received for this variation - `memoryLayerAssignments: optional array of VariationMemoryLayerAssignment` Read-only list of memory layer assignments for this variation, returned in ascending `position` (bottom → top). Capped at 10 entries. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. - `memoryLayerCount: optional number` Count of memory layer assignments. - `model: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `score: optional number` Thompson Sampling score: posterior mean of Beta(ts_alpha, ts_beta). Range [0, 1] where 0.5 = neutral, >0.5 = positive, <0.5 = negative. - `subAgentCount: optional number` Number of sub-agents assigned to this variation - `toolCount: optional number` Number of individual tools assigned to this variation - `toolSetCount: optional number` Number of tool sets assigned to this variation - `memoryEntry: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryEntry is a single keyed value within a MemoryLayer. Entries are addressed by their key, which follows the S3 object key safe-character convention (see MemoryEntrySpec.key for the full rule). Keys are unique within a single layer; the same key may appear in multiple layers, in which case the LIFO stack-walk determines which one wins for a given objective. MemoryEntry is the summary shape, returned by ListMemoryEntries. It does not carry the entry body — callers that need the body must fetch the entry individually via GetMemoryEntry, which returns a MemoryEntryDetail. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { key, description }` MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views. - `key: string` The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path. Additional rules enforced by the service: - May not begin or end with / - May not contain consecutive slashes (//) - May not begin with reserved prefixes (cadenya/, system/) - Case-sensitive - Unique within the parent layer For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content. - `description: optional string` One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter. - `info: optional object { createdBy, memoryLayer }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `memoryLayer: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `memoryLayer: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryLayer is a named container of memory entries that can be composed into an objective's memory stack. Layers are workspace-scoped resources. The layer type controls how its entries participate in the agent loop — see MemoryLayerType for details. See "Memory stack composition" above for how layers compose at lookup time. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `info: optional object { createdBy, entryCount, lastUsedAt }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `entryCount: optional number` Number of entries currently in this layer. - `lastUsedAt: optional string` Timestamp of the most recent objective that resolved against this layer. Useful for surfacing unused layers in the dashboard. - `tool: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `info: optional object { createdBy, toolSet }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `toolSet: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `toolSet: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `info: optional object { agentCount, createdBy, lastSync, toolCount }` Tool set information - `agentCount: optional number` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `lastSync: optional string` - `toolCount: optional number` - `type: optional string` - `variationAssignment: optional object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, agent, tool, toolSet }` A read-only reference to a single tool, tool set, or sub-agent attached to a variation. Read the full set of assignments via `AgentVariationInfo.assignments`; mutations go through the dedicated add/remove assignment endpoints. The `id` identifies the assignment itself (not the referenced resource) and is the handle used to remove the assignment. It is returned by the add endpoint and present on every entry in `AgentVariationInfo.assignments`. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `variationMemoryLayer: optional object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, memoryLayer, position }` VariationMemoryLayerAssignment attaches a single MemoryLayer to a variation at a given position in the variation's baseline memory stack. A variation has at most one assignment per memory_layer_id. Variations only support whole-layer attachments — entry pinning is an objective-level capability. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. - `metadata: object { id, accountId, createdAt, 4 more }` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `id: string` Unique identifier for the operation (prefixed ULID, e.g., "obj_01HXK...") - `accountId: string` Account this operation belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying - `profileId: string` ID of the actor (user or service account) that created this operation - `workspaceId: string` Workspace this operation belongs to for organizational grouping (prefixed ULID) - `externalId: optional string` External ID for the operation (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `pagination: optional object { nextCursor, total }` - `nextCursor: optional string` - `total: optional number` ### Example ```cli cadenya bulk-workspace-resources:results list \ --api-key 'My API Key' \ --workspace-id workspaceId \ --bulk-workspace-apply-id bulkWorkspaceApplyId ``` #### Response ```json { "items": [ { "data": { "agent": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "inputDataSchema": { "foo": "bar" }, "outputDefinition": { "foo": "bar" }, "webhookEventsUrl": "webhookEventsUrl" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "variationCount": 0 } } }, "agentSchedule": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "initialMessage": "initialMessage", "schedule": { "calendars": [ { "comment": "comment", "dayOfMonth": [ { "end": 0, "start": 0, "step": 0 } ], "dayOfWeek": [ { "end": 0, "start": 0, "step": 0 } ], "hour": [ { "end": 0, "start": 0, "step": 0 } ], "minute": [ { "end": 0, "start": 0, "step": 0 } ], "month": [ { "end": 0, "start": 0, "step": 0 } ], "second": [ { "end": 0, "start": 0, "step": 0 } ] } ], "intervals": [ { "every": "-160513s", "offset": "-160513s" } ], "timezone": "timezone" }, "data": {}, "overlapPolicy": "OVERLAP_POLICY_UNSPECIFIED", "status": "AGENT_SCHEDULE_STATUS_UNSPECIFIED", "variationId": "variationId" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "lastFireAt": "2019-12-27T18:11:19.117Z", "lastObjectiveId": "lastObjectiveId", "lastSkippedAt": "2019-12-27T18:11:19.117Z", "lastSkipReason": "lastSkipReason", "nextFireAt": "2019-12-27T18:11:19.117Z", "totalFires": 0 } } }, "agentVariation": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "progressiveDiscovery": { "hints": [ "string" ], "maxTools": 0, "rerankThreshold": 0 }, "prompt": "prompt", "weight": 0 }, "info": { "assignments": [ { "id": "id", "agent": { "id": "id", "name": "name" }, "tool": { "id": "id", "name": "name" }, "toolSet": { "id": "id", "name": "name" } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "feedbackCount": 0, "memoryLayerAssignments": [ { "id": "id", "memoryLayer": { "id": "id", "name": "name" }, "position": 0 } ], "memoryLayerCount": 0, "model": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "score": 0, "subAgentCount": 0, "toolCount": 0, "toolSetCount": 0 } } }, "memoryEntry": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "key": "key", "description": "description" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "memoryLayer": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } } } } }, "memoryLayer": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "MEMORY_LAYER_TYPE_UNSPECIFIED", "description": "description", "expiresAt": "2019-12-27T18:11:19.117Z", "systemManaged": true }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "entryCount": 0, "lastUsedAt": "2019-12-27T18:11:19.117Z" } } }, "tool": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "config": { "http": { "requestMethod": "HTTP_METHOD_UNSPECIFIED", "headers": { "foo": "string" }, "path": "path", "query": "query", "requestBodyContentType": "requestBodyContentType", "requestBodyTemplate": "requestBodyTemplate", "toolName": "toolName" }, "mcp": { "toolDescription": "toolDescription", "toolName": "toolName", "toolTitle": "toolTitle" }, "openapi": { "method": "method", "operationId": "operationId", "path": "path" } }, "description": "description", "parameters": { "foo": "bar" }, "status": "TOOL_STATUS_UNSPECIFIED", "requiresApproval": true }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "toolSet": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } } } } }, "toolSet": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "externalId": "externalId", "resource": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "bundleKey": "bundleKey", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "adapter": { "http": { "baseUrl": "baseUrl", "headers": { "foo": "string" } }, "mcp": { "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "url": "url" }, "openapi": { "baseUrl": "baseUrl", "excludeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "headers": { "foo": "string" }, "includeTools": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] }, "serverName": "serverName", "toolApprovals": { "always": true, "only": { "operator": "OPERATOR_UNSPECIFIED", "filters": [ { "attribute": "ATTRIBUTE_UNSPECIFIED", "matcher": { "caseSensitive": true, "contains": "contains", "endsWith": "endsWith", "exact": "exact", "regex": "regex", "startsWith": "startsWith" } } ] } }, "uploadId": "uploadId", "url": "url" } }, "description": "description" }, "info": { "agentCount": 0, "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_UNSPECIFIED", "email": "email", "name": "name" } }, "lastSync": "2019-12-27T18:11:19.117Z", "toolCount": 0 } } }, "type": "type", "variationAssignment": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "resource": { "id": "id", "agent": { "id": "id", "name": "name" }, "tool": { "id": "id", "name": "name" }, "toolSet": { "id": "id", "name": "name" } } }, "variationMemoryLayer": { "action": "ACTION_UNSPECIFIED", "error": { "code": 0, "details": [ { "@type": "@type" } ], "message": "message" }, "resource": { "id": "id", "memoryLayer": { "id": "id", "name": "name" }, "position": 0 } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Domain Types ### Bulk Workspace Apply Result - `bulk_workspace_apply_result: object { data, metadata }` One row of the per-resource result list for a BulkWorkspaceApply. Each row is itself an operation that can be paginated, sorted by created_at, and addressed individually. - `data: object { agent, agentSchedule, agentVariation, 7 more }` Outcome for a single resource within a bulk apply. The `type` field is the discriminator string naming the populated `outcome` oneof variant (e.g., "toolSet", "memoryEntry"). Every outcome shell carries an `action` enum and either a resulting resource snapshot (for ACTION_CREATED, ACTION_UPDATED, ACTION_UNCHANGED, ACTION_DELETED) or a google.rpc.Status (for ACTION_FAILED). - `agent: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` Agent resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `info: optional object { createdBy, variationCount }` AgentInfo contains simple information about an agent for display or quick reference - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `variationCount: optional number` - `agentSchedule: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentSchedule resource — a recurring trigger attached to an agent that creates objectives on its cadence. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `info: optional object { createdBy, lastFireAt, lastObjectiveId, 4 more }` AgentScheduleInfo provides read-only runtime data about a schedule. - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `lastFireAt: optional string` When the schedule last fired (regardless of objective outcome). - `lastObjectiveId: optional string` ID of the most recent objective the schedule created. - `lastSkippedAt: optional string` When the schedule most recently skipped a fire (SKIP policy + prior in flight). - `lastSkipReason: optional string` Reason for the most recent skip (e.g. "previous objective still running"). - `nextFireAt: optional string` When the schedule will next fire. Computed from the spec; absent when the schedule is PAUSED/ARCHIVED or has no future fire times. - `totalFires: optional number` Lifetime count of objectives created by this schedule. - `agentVariation: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentVariation resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `info: optional object { assignments, createdBy, feedbackCount, 7 more }` AgentVariationInfo provides read-only summary information about a variation - `assignments: optional array of VariationAssignment` All tools, tool sets, and sub-agents assigned to this variation. Populated on reads so clients can render a variation's full assignment list without calling the add/remove endpoints just to enumerate. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `feedbackCount: optional number` Total number of objective feedbacks received for this variation - `memoryLayerAssignments: optional array of VariationMemoryLayerAssignment` Read-only list of memory layer assignments for this variation, returned in ascending `position` (bottom → top). Capped at 10 entries. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. - `memoryLayerCount: optional number` Count of memory layer assignments. - `model: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `score: optional number` Thompson Sampling score: posterior mean of Beta(ts_alpha, ts_beta). Range [0, 1] where 0.5 = neutral, >0.5 = positive, <0.5 = negative. - `subAgentCount: optional number` Number of sub-agents assigned to this variation - `toolCount: optional number` Number of individual tools assigned to this variation - `toolSetCount: optional number` Number of tool sets assigned to this variation - `memoryEntry: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryEntry is a single keyed value within a MemoryLayer. Entries are addressed by their key, which follows the S3 object key safe-character convention (see MemoryEntrySpec.key for the full rule). Keys are unique within a single layer; the same key may appear in multiple layers, in which case the LIFO stack-walk determines which one wins for a given objective. MemoryEntry is the summary shape, returned by ListMemoryEntries. It does not carry the entry body — callers that need the body must fetch the entry individually via GetMemoryEntry, which returns a MemoryEntryDetail. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { key, description }` MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views. - `key: string` The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path. Additional rules enforced by the service: - May not begin or end with / - May not contain consecutive slashes (//) - May not begin with reserved prefixes (cadenya/, system/) - Case-sensitive - Unique within the parent layer For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content. - `description: optional string` One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter. - `info: optional object { createdBy, memoryLayer }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `memoryLayer: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `memoryLayer: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryLayer is a named container of memory entries that can be composed into an objective's memory stack. Layers are workspace-scoped resources. The layer type controls how its entries participate in the agent loop — see MemoryLayerType for details. See "Memory stack composition" above for how layers compose at lookup time. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `info: optional object { createdBy, entryCount, lastUsedAt }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `entryCount: optional number` Number of entries currently in this layer. - `lastUsedAt: optional string` Timestamp of the most recent objective that resolved against this layer. Useful for surfacing unused layers in the dashboard. - `tool: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `info: optional object { createdBy, toolSet }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `toolSet: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `toolSet: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `info: optional object { agentCount, createdBy, lastSync, toolCount }` Tool set information - `agentCount: optional number` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `lastSync: optional string` - `toolCount: optional number` - `type: optional string` - `variationAssignment: optional object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, agent, tool, toolSet }` A read-only reference to a single tool, tool set, or sub-agent attached to a variation. Read the full set of assignments via `AgentVariationInfo.assignments`; mutations go through the dedicated add/remove assignment endpoints. The `id` identifies the assignment itself (not the referenced resource) and is the handle used to remove the assignment. It is returned by the add endpoint and present on every entry in `AgentVariationInfo.assignments`. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `variationMemoryLayer: optional object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, memoryLayer, position }` VariationMemoryLayerAssignment attaches a single MemoryLayer to a variation at a given position in the variation's baseline memory stack. A variation has at most one assignment per memory_layer_id. Variations only support whole-layer attachments — entry pinning is an objective-level capability. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. - `metadata: object { id, accountId, createdAt, 4 more }` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `id: string` Unique identifier for the operation (prefixed ULID, e.g., "obj_01HXK...") - `accountId: string` Account this operation belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying - `profileId: string` ID of the actor (user or service account) that created this operation - `workspaceId: string` Workspace this operation belongs to for organizational grouping (prefixed ULID) - `externalId: optional string` External ID for the operation (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} ### Bulk Workspace Apply Result Data - `bulk_workspace_apply_result_data: object { agent, agentSchedule, agentVariation, 7 more }` Outcome for a single resource within a bulk apply. The `type` field is the discriminator string naming the populated `outcome` oneof variant (e.g., "toolSet", "memoryEntry"). Every outcome shell carries an `action` enum and either a resulting resource snapshot (for ACTION_CREATED, ACTION_UPDATED, ACTION_UNCHANGED, ACTION_DELETED) or a google.rpc.Status (for ACTION_FAILED). - `agent: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` Agent resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `info: optional object { createdBy, variationCount }` AgentInfo contains simple information about an agent for display or quick reference - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `variationCount: optional number` - `agentSchedule: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentSchedule resource — a recurring trigger attached to an agent that creates objectives on its cadence. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `info: optional object { createdBy, lastFireAt, lastObjectiveId, 4 more }` AgentScheduleInfo provides read-only runtime data about a schedule. - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `lastFireAt: optional string` When the schedule last fired (regardless of objective outcome). - `lastObjectiveId: optional string` ID of the most recent objective the schedule created. - `lastSkippedAt: optional string` When the schedule most recently skipped a fire (SKIP policy + prior in flight). - `lastSkipReason: optional string` Reason for the most recent skip (e.g. "previous objective still running"). - `nextFireAt: optional string` When the schedule will next fire. Computed from the spec; absent when the schedule is PAUSED/ARCHIVED or has no future fire times. - `totalFires: optional number` Lifetime count of objectives created by this schedule. - `agentVariation: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentVariation resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `info: optional object { assignments, createdBy, feedbackCount, 7 more }` AgentVariationInfo provides read-only summary information about a variation - `assignments: optional array of VariationAssignment` All tools, tool sets, and sub-agents assigned to this variation. Populated on reads so clients can render a variation's full assignment list without calling the add/remove endpoints just to enumerate. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `feedbackCount: optional number` Total number of objective feedbacks received for this variation - `memoryLayerAssignments: optional array of VariationMemoryLayerAssignment` Read-only list of memory layer assignments for this variation, returned in ascending `position` (bottom → top). Capped at 10 entries. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. - `memoryLayerCount: optional number` Count of memory layer assignments. - `model: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `score: optional number` Thompson Sampling score: posterior mean of Beta(ts_alpha, ts_beta). Range [0, 1] where 0.5 = neutral, >0.5 = positive, <0.5 = negative. - `subAgentCount: optional number` Number of sub-agents assigned to this variation - `toolCount: optional number` Number of individual tools assigned to this variation - `toolSetCount: optional number` Number of tool sets assigned to this variation - `memoryEntry: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryEntry is a single keyed value within a MemoryLayer. Entries are addressed by their key, which follows the S3 object key safe-character convention (see MemoryEntrySpec.key for the full rule). Keys are unique within a single layer; the same key may appear in multiple layers, in which case the LIFO stack-walk determines which one wins for a given objective. MemoryEntry is the summary shape, returned by ListMemoryEntries. It does not carry the entry body — callers that need the body must fetch the entry individually via GetMemoryEntry, which returns a MemoryEntryDetail. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { key, description }` MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views. - `key: string` The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path. Additional rules enforced by the service: - May not begin or end with / - May not contain consecutive slashes (//) - May not begin with reserved prefixes (cadenya/, system/) - Case-sensitive - Unique within the parent layer For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content. - `description: optional string` One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter. - `info: optional object { createdBy, memoryLayer }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `memoryLayer: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `memoryLayer: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryLayer is a named container of memory entries that can be composed into an objective's memory stack. Layers are workspace-scoped resources. The layer type controls how its entries participate in the agent loop — see MemoryLayerType for details. See "Memory stack composition" above for how layers compose at lookup time. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `info: optional object { createdBy, entryCount, lastUsedAt }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `entryCount: optional number` Number of entries currently in this layer. - `lastUsedAt: optional string` Timestamp of the most recent objective that resolved against this layer. Useful for surfacing unused layers in the dashboard. - `tool: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `info: optional object { createdBy, toolSet }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `toolSet: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `toolSet: optional object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `info: optional object { agentCount, createdBy, lastSync, toolCount }` Tool set information - `agentCount: optional number` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `spec: object { type, email, name }` Configuration for a profile. - `lastSync: optional string` - `toolCount: optional number` - `type: optional string` - `variationAssignment: optional object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, agent, tool, toolSet }` A read-only reference to a single tool, tool set, or sub-agent attached to a variation. Read the full set of assignments via `AgentVariationInfo.assignments`; mutations go through the dedicated add/remove assignment endpoints. The `id` identifies the assignment itself (not the referenced resource) and is the handle used to remove the assignment. It is returned by the add endpoint and present on every entry in `AgentVariationInfo.assignments`. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `variationMemoryLayer: optional object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, memoryLayer, position }` VariationMemoryLayerAssignment attaches a single MemoryLayer to a variation at a given position in the variation's baseline memory stack. A variation has at most one assignment per memory_layer_id. Variations only support whole-layer attachments — entry pinning is an objective-level capability. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. ### Bulk Workspace Apply Result Data Agent Outcome - `bulk_workspace_apply_result_data_agent_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` Agent resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { status, variationSelectionMode, description, 3 more }` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" or "AGENT_STATUS_DRAFT" or "AGENT_STATUS_PUBLISHED" or "AGENT_STATUS_ARCHIVED"` Status of the agent - `"AGENT_STATUS_UNSPECIFIED"` - `"AGENT_STATUS_DRAFT"` - `"AGENT_STATUS_PUBLISHED"` - `"AGENT_STATUS_ARCHIVED"` - `variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" or "VARIATION_SELECTION_MODE_RANDOM" or "VARIATION_SELECTION_MODE_WEIGHTED"` Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description: optional string` Description of the agent's purpose - `inputDataSchema: optional map[unknown]` InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. - `outputDefinition: optional map[unknown]` Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. - `webhookEventsUrl: optional string` The URL that Cadenya will send events for any objective assigned to the agent. - `info: optional object { createdBy, variationCount }` AgentInfo contains simple information about an agent for display or quick reference - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `variationCount: optional number` ### Bulk Workspace Apply Result Data Agent Schedule Outcome - `bulk_workspace_apply_result_data_agent_schedule_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentSchedule resource — a recurring trigger attached to an agent that creates objectives on its cadence. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { initialMessage, schedule, data, 3 more }` AgentScheduleSpec is the user-provided configuration for a schedule. - `initialMessage: string` The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective's chat history. - `schedule: object { calendars, intervals, timezone }` Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR'd together. At least one rule is required. - `calendars: optional array of ScheduleCalendar` Wall-clock rules. May be empty if `intervals` is non-empty. - `comment: optional string` - `dayOfMonth: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `dayOfWeek: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `hour: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `minute: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `month: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `second: optional array of ScheduleRange` - `end: optional number` - `start: optional number` - `step: optional number` - `intervals: optional array of ScheduleInterval` Duration-based rules. May be empty if `calendars` is non-empty. - `every: optional string` - `offset: optional string` Phase shift within `every`. Must be < `every` (enforced at runtime). - `timezone: optional string` IANA tz name (e.g. "America/New_York"). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone. - `data: optional unknown` Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it. - `overlapPolicy: optional "OVERLAP_POLICY_UNSPECIFIED" or "OVERLAP_POLICY_ALLOW" or "OVERLAP_POLICY_SKIP"` What to do when the previous run is still in flight. Defaults to SKIP. - `"OVERLAP_POLICY_UNSPECIFIED"` - `"OVERLAP_POLICY_ALLOW"` - `"OVERLAP_POLICY_SKIP"` - `status: optional "AGENT_SCHEDULE_STATUS_UNSPECIFIED" or "AGENT_SCHEDULE_STATUS_ACTIVE" or "AGENT_SCHEDULE_STATUS_PAUSED" or "AGENT_SCHEDULE_STATUS_ARCHIVED"` Lifecycle. Defaults to ACTIVE on create when unspecified. - `"AGENT_SCHEDULE_STATUS_UNSPECIFIED"` - `"AGENT_SCHEDULE_STATUS_ACTIVE"` - `"AGENT_SCHEDULE_STATUS_PAUSED"` - `"AGENT_SCHEDULE_STATUS_ARCHIVED"` - `variationId: optional string` Optional explicit variation. When unset, the agent's variation_selection_mode chooses per fire. - `info: optional object { createdBy, lastFireAt, lastObjectiveId, 4 more }` AgentScheduleInfo provides read-only runtime data about a schedule. - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `lastFireAt: optional string` When the schedule last fired (regardless of objective outcome). - `lastObjectiveId: optional string` ID of the most recent objective the schedule created. - `lastSkippedAt: optional string` When the schedule most recently skipped a fire (SKIP policy + prior in flight). - `lastSkipReason: optional string` Reason for the most recent skip (e.g. "previous objective still running"). - `nextFireAt: optional string` When the schedule will next fire. Computed from the spec; absent when the schedule is PAUSED/ARCHIVED or has no future fire times. - `totalFires: optional number` Lifetime count of objectives created by this schedule. ### Bulk Workspace Apply Result Data Agent Variation Outcome - `bulk_workspace_apply_result_data_agent_variation_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` AgentVariation resource - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { compactionConfig, constraints, description, 6 more }` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization: optional object { instructions }` SummarizationStrategy configures LLM-powered summarization of older conversation turns. - `instructions: optional string` Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." - `toolResultClearing: optional object { preserveRecentResults }` ToolResultClearingStrategy configures clearing of older tool result content. - `preserveRecentResults: optional number` Number of most recent tool call results to keep intact. Older tool results have their content replaced with "[result cleared]" while preserving the assistant tool call message (function name, arguments). Default: 2 - `triggerThreshold: optional number` Trigger threshold as a percentage of the model's context window (0.0 to 1.0). When input tokens reach this percentage of the model's limit, compaction triggers. Default: 0.75 (75%) - `constraints: optional object { maxSubObjectives, maxToolCalls }` Execution constraints - `maxSubObjectives: optional number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls: optional number` The maximum number of tool calls that can be made. 0 means no limit. - `description: optional string` Human-readable description of what this variation does or when it should be used - `enableEpisodicMemory: optional boolean` Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective's episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode. - `episodicMemoryTtl: optional number` How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely. - `modelConfig: optional object { modelId, temperature }` ModelConfig defines the model configuration for a variation - `modelId: optional string` The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") - `temperature: optional number` Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness - `progressiveDiscovery: optional object { hints, maxTools, rerankThreshold }` ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. - `hints: optional array of string` - `maxTools: optional number` - `rerankThreshold: optional number` Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed. - `prompt: optional string` The system prompt for this variation - `weight: optional number` Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent's variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest. - `info: optional object { assignments, createdBy, feedbackCount, 7 more }` AgentVariationInfo provides read-only summary information about a variation - `assignments: optional array of VariationAssignment` All tools, tool sets, and sub-agents assigned to this variation. Populated on reads so clients can render a variation's full assignment list without calling the add/remove endpoints just to enumerate. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `feedbackCount: optional number` Total number of objective feedbacks received for this variation - `memoryLayerAssignments: optional array of VariationMemoryLayerAssignment` Read-only list of memory layer assignments for this variation, returned in ascending `position` (bottom → top). Capped at 10 entries. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument. - `memoryLayerCount: optional number` Count of memory layer assignments. - `model: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `score: optional number` Thompson Sampling score: posterior mean of Beta(ts_alpha, ts_beta). Range [0, 1] where 0.5 = neutral, >0.5 = positive, <0.5 = negative. - `subAgentCount: optional number` Number of sub-agents assigned to this variation - `toolCount: optional number` Number of individual tools assigned to this variation - `toolSetCount: optional number` Number of tool sets assigned to this variation ### Bulk Workspace Apply Result Data Memory Entry Outcome - `bulk_workspace_apply_result_data_memory_entry_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryEntry is a single keyed value within a MemoryLayer. Entries are addressed by their key, which follows the S3 object key safe-character convention (see MemoryEntrySpec.key for the full rule). Keys are unique within a single layer; the same key may appear in multiple layers, in which case the LIFO stack-walk determines which one wins for a given objective. MemoryEntry is the summary shape, returned by ListMemoryEntries. It does not carry the entry body — callers that need the body must fetch the entry individually via GetMemoryEntry, which returns a MemoryEntryDetail. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { key, description }` MemoryEntrySpec is the metadata portion of an entry — the fields that identify and describe it, without the body. It appears on both the summary (MemoryEntry) and detail (MemoryEntryDetail) views. - `key: string` The lookup key for this entry within its layer. Must conform to the S3 object key safe-characters spec: ASCII alphanumerics and the special characters !, -, _, ., *, ', (, ), and /. Forward slashes may be used to suggest hierarchy (e.g., "skills/postmortem/write"), but lookups are flat — the key is a single opaque string, not a path. Additional rules enforced by the service: - May not begin or end with / - May not contain consecutive slashes (//) - May not begin with reserved prefixes (cadenya/, system/) - Case-sensitive - Unique within the parent layer For skills entries, this key is also the id the model passes to memory_load_skill when it decides to load the entry's content. - `description: optional string` One-line "when to use this" hint shown in the frontmatter manifest for skills entries. The model uses this to decide whether to load the body, so it should be written for the model as the audience. Ignored for layer types that do not advertise frontmatter. - `info: optional object { createdBy, memoryLayer }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `memoryLayer: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} ### Bulk Workspace Apply Result Data Memory Layer Outcome - `bulk_workspace_apply_result_data_memory_layer_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` MemoryLayer is a named container of memory entries that can be composed into an objective's memory stack. Layers are workspace-scoped resources. The layer type controls how its entries participate in the agent loop — see MemoryLayerType for details. See "Memory stack composition" above for how layers compose at lookup time. - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, description, expiresAt, systemManaged }` - `type: "MEMORY_LAYER_TYPE_UNSPECIFIED" or "MEMORY_LAYER_TYPE_EPISODIC" or "MEMORY_LAYER_TYPE_SKILLS"` - `"MEMORY_LAYER_TYPE_UNSPECIFIED"` - `"MEMORY_LAYER_TYPE_EPISODIC"` - `"MEMORY_LAYER_TYPE_SKILLS"` - `description: optional string` Human-readable description of the layer's purpose. Encouraged for user-created layers; system-managed layers may have a generated description. - `expiresAt: optional string` For layers with a finite lifetime (e.g., episodic), the time at which the layer becomes eligible for cleanup. Set by the system; unset for persistent layers. - `systemManaged: optional boolean` Server-set. True for layers managed by the system (e.g., episodic layers created automatically when an objective uses an episodic_key). System-managed layers cannot be assigned to objective stacks via the API and cannot be mutated by clients — their lifecycle is controlled entirely by the runtime. - `info: optional object { createdBy, entryCount, lastUsedAt }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `entryCount: optional number` Number of entries currently in this layer. - `lastUsedAt: optional string` Timestamp of the most recent objective that resolved against this layer. Useful for surfacing unused layers in the dashboard. ### Bulk Workspace Apply Result Data Tool Outcome - `bulk_workspace_apply_result_data_tool_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { config, description, parameters, 2 more }` - `config: object { http, mcp, openapi }` Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline. - `http: optional object { requestMethod, headers, path, 4 more }` - `requestMethod: "HTTP_METHOD_UNSPECIFIED" or "GET" or "POST" or 3 more` - `"HTTP_METHOD_UNSPECIFIED"` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers: optional map[string]` - `path: optional string` - `query: optional string` - `requestBodyContentType: optional string` - `requestBodyTemplate: optional string` These are only used when the request method is a POST, PUT, or PATCH - `toolName: optional string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp: optional object { toolDescription, toolName, toolTitle }` - `toolDescription: optional string` - `toolName: optional string` - `toolTitle: optional string` - `openapi: optional object { method, operationId, path }` - `method: optional string` - `operationId: optional string` - `path: optional string` - `description: string` - `parameters: map[unknown]` - `status: "TOOL_STATUS_UNSPECIFIED" or "TOOL_STATUS_AVAILABLE" or "TOOL_STATUS_OMITTED" or "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_OMITTED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval: optional boolean` - `info: optional object { createdBy, toolSet }` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `toolSet: optional object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} ### Bulk Workspace Apply Result Data Tool Set Outcome - `bulk_workspace_apply_result_data_tool_set_outcome: object { action, error, externalId, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `externalId: optional string` - `resource: optional object { metadata, spec, info }` - `metadata: object { id, accountId, createdAt, 6 more }` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `createdAt: string` Timestamp when this resource was created - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` ID of the actor (user or service account) that created this resource - `workspaceId: string` Workspace this resource belongs to for organizational grouping (prefixed ULID) - `bundleKey: optional string` Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply. - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { adapter, description }` - `adapter: optional object { http, mcp, openapi }` - `http: optional object { baseUrl, headers }` - `baseUrl: optional string` - `headers: optional map[string]` - `mcp: optional object { excludeTools, headers, includeTools, 2 more }` - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `"OPERATOR_UNSPECIFIED"` - `"OPERATOR_AND"` - `"OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `attribute: "ATTRIBUTE_UNSPECIFIED" or "ATTRIBUTE_NAME" or "ATTRIBUTE_TITLE" or "ATTRIBUTE_DESCRIPTION"` - `"ATTRIBUTE_UNSPECIFIED"` - `"ATTRIBUTE_NAME"` - `"ATTRIBUTE_TITLE"` - `"ATTRIBUTE_DESCRIPTION"` - `matcher: optional object { caseSensitive, contains, endsWith, 3 more }` String matching operations - `caseSensitive: optional boolean` - `contains: optional string` - `endsWith: optional string` - `exact: optional string` - `regex: optional string` - `startsWith: optional string` - `headers: optional map[string]` - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `url: optional string` - `openapi: optional object { baseUrl, excludeTools, headers, 5 more }` - `baseUrl: optional string` Base URL for dispatching tool calls. If set, overrides the server resolved from the spec's servers array. - `excludeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `headers: optional map[string]` Headers sent when fetching the spec from a URL and when dispatching tool calls. - `includeTools: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `operator: "OPERATOR_UNSPECIFIED" or "OPERATOR_AND" or "OPERATOR_OR"` - `filters: optional array of AttributeFilter` - `serverName: optional string` Name of the server entry in the spec's servers array (OpenAPI 3.2 server.name field). Used to select which server URL to dispatch to when base_url is not set. If unset, the first server is used. Ignored when base_url is set. - `toolApprovals: optional object { always, only }` Approval filters that will automatically set the approval requirement on tools synced from an external source - `always: optional boolean` - `only: optional object { operator, filters }` Top-level filter with simple boolean logic (no nesting) - `uploadId: optional string` ID of a COMPLETE Upload containing the OpenAPI spec document. - `url: optional string` URL to fetch the OpenAPI spec from. Synced automatically every hour. - `description: optional string` - `info: optional object { agentCount, createdBy, lastSync, toolCount }` Tool set information - `agentCount: optional number` - `createdBy: optional object { metadata, spec }` A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. - `metadata: object { id, accountId, name, 3 more }` AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. - `id: string` Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") - `accountId: string` Account this resource belongs to for multi-tenant isolation (prefixed ULID) - `name: string` Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly - `profileId: string` - `externalId: optional string` External ID for the resource (e.g., a workflow ID from an external system) - `labels: optional map[string]` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: object { type, email, name }` Configuration for a profile. - `type: "PROFILE_TYPE_UNSPECIFIED" or "PROFILE_TYPE_USER" or "PROFILE_TYPE_API_KEY" or "PROFILE_TYPE_SYSTEM"` Whether this profile represents a human user, an API key, or a system principal. - `"PROFILE_TYPE_UNSPECIFIED"` - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email: optional string` Email address of the profile. Required and unique within an account for user profiles. - `name: optional string` Display name (e.g., "Bobby Tables"). - `lastSync: optional string` - `toolCount: optional number` ### Bulk Workspace Apply Result Data Variation Assignment Outcome - `bulk_workspace_apply_result_data_variation_assignment_outcome: object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, agent, tool, toolSet }` A read-only reference to a single tool, tool set, or sub-agent attached to a variation. Read the full set of assignments via `AgentVariationInfo.assignments`; mutations go through the dedicated add/remove assignment endpoints. The `id` identifies the assignment itself (not the referenced resource) and is the handle used to remove the assignment. It is returned by the add endpoint and present on every entry in `AgentVariationInfo.assignments`. - `id: optional string` - `agent: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `tool: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `toolSet: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). ### Bulk Workspace Apply Result Data Variation Memory Layer Outcome - `bulk_workspace_apply_result_data_variation_memory_layer_outcome: object { action, error, resource }` - `action: optional "ACTION_UNSPECIFIED" or "ACTION_CREATED" or "ACTION_UPDATED" or 3 more` - `"ACTION_UNSPECIFIED"` - `"ACTION_CREATED"` - `"ACTION_UPDATED"` - `"ACTION_UNCHANGED"` - `"ACTION_DELETED"` - `"ACTION_FAILED"` - `error: optional object { code, details, message }` The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). - `code: optional number` The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. - `details: optional array of object { "@type" }` A list of messages that carry the error details. There is a common set of message types for APIs to use. - `@type: optional string` The type of the serialized message. - `message: optional string` A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. - `resource: optional object { id, memoryLayer, position }` VariationMemoryLayerAssignment attaches a single MemoryLayer to a variation at a given position in the variation's baseline memory stack. A variation has at most one assignment per memory_layer_id. Variations only support whole-layer attachments — entry pinning is an objective-level capability. - `id: optional string` Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer's id. - `memoryLayer: optional object { id, name }` BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves. - `id: optional string` - `name: optional string` Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks). - `position: optional number` Position in the variation's baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation's baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment's position is rejected with InvalidArgument.