Skip to content
Changelog

Report a bug

Honeyhive integration: operations for AI agents

Honeyhive connects to Type.com as an integration. This page lists the 65 operations documented for Claude and Codex in Type.com: 24 read, 22 write, 19 destructive.

About Honeyhive

HoneyHive is a modern AI observability and evaluation platform that enables developers and domain experts to collaboratively build reliable AI applications faster.

Categories: Developer Tools & IT

How to connect Honeyhive to Type.com

Access
Organization connection: one shared account for the workspace.

To add the connection, follow the steps in Space connections.

Documented operations

65 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

65 operations listed.

Sessions

  • Write

    Start a new session

    Start a new session. The request body is a bare session object (no session wrapper). The server creates a session event and returns it. No required properties. Every field has a server-side fallback.

  • Write

    Add a batch of events to a session

    Add a batch of events to an existing session. Each event in the batch is stored with sessionid set from the URL path, overriding any sessionid in the event body. Each event must include eventtype (one of chain, model, tool, session) and inputs.

Events

  • Read

    Get an event by ID

    Retrieve a single event by its unique identifier. The event is fetched directly from S3/MinIO storage.

  • Read

    Retrieve events based on filters

    Search events via POST with filtering and pagination. This is the primary method for retrieving events from HoneyHive.

  • Write

    Create a new event

    Create a new event (span) within a session trace. The request body is a bare event object (no event wrapper). Required properties: - eventtype (string): Must be one of: chain, model, tool, session. - inputs (object): Input data for the event.

  • Write

    Create a batch of events

    Create multiple events in a single request. When singlesession is true, all events share the same session created from sessionproperties. Required properties: - events (array of event objects): Each event must include eventtype (one of chain, model, tool, session) and inputs.

  • Destructive

    Update an event

    Update fields on an existing event. Only the provided fields are modified; omitted fields are left unchanged. Extra fields not listed below are accepted by the server but silently ignored.

Charts

  • Read

    List charts

    Retrieve all charts in a project.

  • Read

    Get a chart

    Retrieve a single chart by id.

  • Write

    Create a new chart

    Create a chart in a project.

  • Write

    Update a chart

    Update a chart's editable fields. Only fields included in the request body are modified.

  • Destructive

    Delete a chart

    Delete a chart from a project, removing it from the project's dashboards.

Data Plane Api Keys

  • Write

    Create a data plane API key

    Create a fine-grained data plane API key rooted at a project. The caller's key must carry project.finegrainedapikeydp.post for the project.

Ingestion Api Keys

  • Write

    Create an ingestion API key

    Create an ingestion API key for a project, the credential an application sends traces with. The caller's key must carry project.ingestionapikey.post for the project.

Metrics

  • Read

    List all metrics

    GET /v1/metrics

  • Write

    Create a new metric

    POST /v1/metrics

  • Write

    Run a metric evaluation

    Execute a metric on a specific event

  • Destructive

    Update an existing metric

    Update a metric's editable fields. Only fields included in the request body are modified.

  • Destructive

    Delete a metric

    DELETE /v1/metrics/{metric_id}

Metric Versions

  • Read

    List versions for a metric

    Retrieve all snapshot versions of the metric's definition, ordered oldest-first. Returns the full version history unpaginated.

  • Write

    Create a new metric version

    Snapshot the supplied metric definition as a new version. By default the version is created as a draft (deployed: false); set deployimmediately: true to also make it the live version in the same transaction.

  • Write

    Deploy a specific metric version

    Mark the named version as the live version for the metric, unmarking any previously deployed version.

Datapoints

  • Read

    Retrieve a list of datapoints

    Retrieve datapoints, optionally filtered by a list of datapoint IDs or dataset name.

  • Read

    Retrieve a specific datapoint

    Get a single datapoint by its unique identifier.

  • Write

    Create a new datapoint

    Create a single datapoint with inputs, history, ground truth, and metadata.

  • Write

    Create multiple datapoints in batch

    Create multiple datapoints from events using field mappings and optional filters.

  • Destructive

    Update a specific datapoint

    Update fields on an existing datapoint. Only the provided fields are modified.

  • Destructive

    Delete a specific datapoint

    Permanently delete a datapoint by its unique identifier.

Datasets

  • Read

    Get datasets

    Retrieve datasets, optionally filtered by dataset ID or name.

  • Write

    Create a dataset

    Create a new dataset with an optional name, description, and initial set of datapoint IDs.

  • Write

    Add datapoints to a dataset

    Add new datapoints to an existing dataset. Provide raw data objects and a field mapping that specifies which fields map to inputs, ground truth, and history.

  • Destructive

    Update a dataset

    Update a dataset's name, description, or list of datapoint IDs.

  • Destructive

    Delete a dataset

    Permanently delete a dataset by its unique identifier.

  • Destructive

    Remove a datapoint from a dataset

    Remove a specific datapoint from a dataset. The datapoint itself is not deleted, only dereferenced from the dataset.

Experiments

  • Read

    Get a list of evaluation runs

    List experiment runs with optional filtering by dataset, status, name, date range, and specific run IDs. Results are paginated and sortable.

  • Read

    Get events schema across all experiment runs in a project

    Retrieve the aggregated events schema (fields, datasets, mappings) across all experiment runs in the project.

  • Read

    Get details of an evaluation run

    Retrieve the full details of a single experiment run by its run ID.

  • Read

    Get events schema for a single experiment run

    Retrieve the events schema (fields, datasets, mappings) for a single experiment run.

  • Read

    Get event metrics for an experiment run

    Retrieve event metrics from ClickHouse for a specific experiment run

  • Read

    Retrieve experiment summary

    Compute evaluation summary for an experiment run: pass/fail results, metric aggregations, per-datapoint results, event details, and the experiment run object.

  • Read

    Retrieve experiment comparison

    Compare metrics and results between two experiment runs

  • Read

    Compare events between two experiment runs

    Retrieve and compare events between two experiment runs for detailed analysis

  • Write

    Create a new evaluation run

    Create a new experiment run to track an evaluation against a dataset.

  • Destructive

    Update an evaluation run

    Update fields on an existing experiment run such as name, status, metadata, or results.

  • Destructive

    Delete an evaluation run

    Permanently delete an experiment run by its run ID.

Queues

  • Read

    List annotation queues

    List annotation queues for the current project scope, optionally filtered by enabled status.

  • Read

    Get an annotation queue

    Retrieve a single annotation queue by its unique identifier.

  • Write

    Create an annotation queue

    Create a new annotation queue with a name, optional description, filters, and an initial set of event IDs to add.

  • Destructive

    Update an annotation queue

    Update fields on an existing annotation queue. Supports updating name, description, filters, enabled status, and adding/removing events.

  • Destructive

    Delete an annotation queue

    Soft-delete an annotation queue by its unique identifier.

Alerts

  • Read

    List alerts

    List the alerts in a project. The project is identified by the projectid path parameter alone; the x-hh-project-id header does not participate. Supports offset pagination, an optional status filter, and sorting (defaults to most recently created first).

  • Read

    Get an alert

    Retrieve a single alert by id, including its thresholds, triggers, and notification configuration. The alert's project is identified by the projectid path parameter alone; the x-hh-project-id header does not participate.

  • Write

    Create an alert

    Create an alert in a project. The project is identified by the projectid path parameter alone; the x-hh-project-id header does not participate.

Workspaces

  • Read

    Get a workspace

    Retrieve a single workspace by id. The workspace is identified by the workspaceid path parameter alone; the x-hh-workspace-id header does not participate. The returned name is the workspace's display name.

  • Write

    Create a workspace

    Create a workspace in a virtual data plane. The parent virtual data plane is identified by the virtualdataplaneid path parameter alone; the x-hh-dataplane-id header does not participate.

  • Destructive

    Update a workspace

    Update a workspace's display name and/or description. The workspace is identified by the workspaceid path parameter alone; the x-hh-workspace-id header does not participate. Only fields included in the request body are modified.

  • Destructive

    Delete a workspace

    Delete a workspace. The workspace is soft-deleted (archived) and no longer appears in reads; the response returns the archived workspace. The workspace is identified by the workspaceid path parameter alone; the x-hh-workspace-id header does not participate.

Projects

  • Read

    Get a project

    Retrieve a single project by id. The project is identified by the projectid path parameter alone; the x-hh-project-id header does not participate.

  • Write

    Create a project

    Create a project in a workspace. The parent workspace is identified by the workspaceid path parameter alone; the x-hh-workspace-id header does not participate. A workspace's id is listed on the API keys page of its workspace settings in the HoneyHive app.

  • Destructive

    Update a project

    Update a project's display name and/or description. The project is identified by the projectid path parameter alone; the x-hh-project-id header does not participate. Only fields included in the request body are modified.

  • Destructive

    Delete a project

    Delete a project. The project is soft-deleted (archived) and no longer appears in reads; the response returns the archived project. The project is identified by the projectid path parameter alone; the x-hh-project-id header does not participate.

Virtual Dataplanes

  • Read

    Get a virtual data plane

    Retrieve a single virtual data plane by id. It is identified by the virtualdataplaneid path parameter alone; the x-hh-dataplane-id header does not participate. The returned name is the display name.

  • Write

    Create a virtual data plane

    Create a virtual data plane in an organization. The parent organization is identified by the orgid path parameter alone; the x-hh-org-id header does not participate. Your organization's id is listed on the API keys page of your organization settings in the HoneyHive app.

  • Destructive

    Update a virtual data plane

    Update a virtual data plane's display name. It is identified by the virtualdataplaneid path parameter alone; the x-hh-dataplane-id header does not participate. name is the only field this endpoint changes.

  • Destructive

    Delete a virtual data plane

    Delete a virtual data plane. It is soft-deleted (archived) and no longer appears in reads; the response returns the archived virtual data plane. It is identified by the virtualdataplaneid path parameter alone; the x-hh-dataplane-id header does not participate.

See How connections work for access and permissions, or browse all integrations.