--- title: "Get Agent Overview" method: GET path: "/api/v1/agents/{agent_id}/overview" tags: ["agents"] --- # Get Agent Overview `GET /api/v1/agents/{agent_id}/overview` ## Path parameters - `agent_id` string, required ## Query parameters - `limit` integer - `cursor` string, nullable ## Response `200` Successful Response - AgentOverviewResponse - `agent` AgentResponse, required - `agent_id` string, required — Stable identifier for the agent. - `organization_id` string, required — Organization that owns the agent. - `name` string, required — Human-readable agent name. - `description` string, nullable — Optional description of the agent's purpose. - `created_at` string, date-time, required — Time the agent was created. - `updated_at` string, date-time, required — Time the agent was last updated. - `benchmark_ids` string[], required — Benchmarks owned by the agent. - `model_slug` string, nullable, required — The agent's stable serving model slug. - `items` AgentOverviewSpec[], required - `benchmark` BenchmarkListItem, required - `bench_id` string, required - `agent_id` string, nullable - `organization_id` string, required - `name` string, required - `description` string - `visibility` string - `family` string, nullable - `created_at` string, date-time, required - `updated_at` string, date-time, required - `eval_run_count` integer - `completed_evaluations` EvalRun[], required - `agent_id` string, nullable, required — Persisted owner; null for unassigned legacy runs. - `eval_run_id` string, required — Unique evaluation run identifier. - `bench_id` string, required — Benchmark evaluated by this run. - `rollout_xid` string, nullable — XID containing this run's evaluation trajectories. - `display_name` string, nullable, required — User-facing name for the evaluation run; null for legacy rows. - `model_slug` string, nullable — Model evaluated by this run. - `status` 'pending' | 'registered' | 'running' | 'completed' | 'failed' | 'cancelled', required - `checkpoint_id` string, nullable — Checkpoint evaluated by this run, when applicable. - `training_run_id` string, nullable — Training run that produced the evaluated checkpoint. - `step` integer, nullable — Evaluated checkpoint training step. - `reward_mean` number, nullable — Completed evaluation mean reward. - `created_at` string, date-time, required — Time when the evaluation run was created. - `updated_at` string, date-time, required — Time when the evaluation run was last updated. - `completed_at` string, date-time, nullable — Time when the evaluation reached a terminal status. - `failure` AsyncFailure - `type` string, required — Stable category used for exception mapping. - `code` string, required — Stable programmatic reason for the asynchronous failure. - `message` string, required — Human-readable explanation for this failure occurrence. - `context` object — Machine-readable values specific to this failure code. - `completed_model_count` integer, required - `active_evaluations` EvalRun[], required - `agent_id` string, nullable, required — Persisted owner; null for unassigned legacy runs. - `eval_run_id` string, required — Unique evaluation run identifier. - `bench_id` string, required — Benchmark evaluated by this run. - `rollout_xid` string, nullable — XID containing this run's evaluation trajectories. - `display_name` string, nullable, required — User-facing name for the evaluation run; null for legacy rows. - `model_slug` string, nullable — Model evaluated by this run. - `status` 'pending' | 'registered' | 'running' | 'completed' | 'failed' | 'cancelled', required - `checkpoint_id` string, nullable — Checkpoint evaluated by this run, when applicable. - `training_run_id` string, nullable — Training run that produced the evaluated checkpoint. - `step` integer, nullable — Evaluated checkpoint training step. - `reward_mean` number, nullable — Completed evaluation mean reward. - `created_at` string, date-time, required — Time when the evaluation run was created. - `updated_at` string, date-time, required — Time when the evaluation run was last updated. - `completed_at` string, date-time, nullable — Time when the evaluation reached a terminal status. - `failure` AsyncFailure - `type` string, required — Stable category used for exception mapping. - `code` string, required — Stable programmatic reason for the asynchronous failure. - `message` string, required — Human-readable explanation for this failure occurrence. - `context` object — Machine-readable values specific to this failure code. - `active_evaluation_count` integer, required - `latest_unsuccessful_evaluation` EvalRun, required - `agent_id` string, nullable, required — Persisted owner; null for unassigned legacy runs. - `eval_run_id` string, required — Unique evaluation run identifier. - `bench_id` string, required — Benchmark evaluated by this run. - `rollout_xid` string, nullable — XID containing this run's evaluation trajectories. - `display_name` string, nullable, required — User-facing name for the evaluation run; null for legacy rows. - `model_slug` string, nullable — Model evaluated by this run. - `status` 'pending' | 'registered' | 'running' | 'completed' | 'failed' | 'cancelled', required - `checkpoint_id` string, nullable — Checkpoint evaluated by this run, when applicable. - `training_run_id` string, nullable — Training run that produced the evaluated checkpoint. - `step` integer, nullable — Evaluated checkpoint training step. - `reward_mean` number, nullable — Completed evaluation mean reward. - `created_at` string, date-time, required — Time when the evaluation run was created. - `updated_at` string, date-time, required — Time when the evaluation run was last updated. - `completed_at` string, date-time, nullable — Time when the evaluation reached a terminal status. - `failure` AsyncFailure - `type` string, required — Stable category used for exception mapping. - `code` string, required — Stable programmatic reason for the asynchronous failure. - `message` string, required — Human-readable explanation for this failure occurrence. - `context` object — Machine-readable values specific to this failure code. - `next_cursor` string, nullable, required - `has_more` boolean, required - `recent_training_runs` TrainingRunResponse[], required - `agent_id` string, nullable, required — Persisted owner; null for unassigned legacy runs. - `parent_checkpoint_id` string, nullable - `training_run_id` string, required - `pipeline_run_id` string, nullable, required - `display_name` string, nullable, required — User-facing training run name; null for legacy rows. - `xid` string, nullable - `status` 'pending' | 'running' | 'cancel_signaled' | 'cancelling' | 'succeeded' | 'failed' | 'cancelled', required - `bench_id` string, nullable, required - `base_model_id` string, required - `training_options` object, required - `created_by` string, required - `created_at` string, date-time, required - `failure` AsyncFailure - `type` string, required — Stable category used for exception mapping. - `code` string, required — Stable programmatic reason for the asynchronous failure. - `message` string, required — Human-readable explanation for this failure occurrence. - `context` object — Machine-readable values specific to this failure code. - `has_training_execution` boolean, required — Whether a training execution has been assigned. - `recent_training_specs` BenchmarkListItem[], required - `bench_id` string, required - `agent_id` string, nullable - `organization_id` string, required - `name` string, required - `description` string - `visibility` string - `family` string, nullable - `created_at` string, date-time, required - `updated_at` string, date-time, required - `eval_run_count` integer - `evaluation_training_runs` TrainingRunResponse[], required - `agent_id` string, nullable, required — Persisted owner; null for unassigned legacy runs. - `parent_checkpoint_id` string, nullable - `training_run_id` string, required - `pipeline_run_id` string, nullable, required - `display_name` string, nullable, required — User-facing training run name; null for legacy rows. - `xid` string, nullable - `status` 'pending' | 'running' | 'cancel_signaled' | 'cancelling' | 'succeeded' | 'failed' | 'cancelled', required - `bench_id` string, nullable, required - `base_model_id` string, required - `training_options` object, required - `created_by` string, required - `created_at` string, date-time, required - `failure` AsyncFailure - `type` string, required — Stable category used for exception mapping. - `code` string, required — Stable programmatic reason for the asynchronous failure. - `message` string, required — Human-readable explanation for this failure occurrence. - `context` object — Machine-readable values specific to this failure code. - `has_training_execution` boolean, required — Whether a training execution has been assigned. - `serving_deployment` Deployment, required — Spanner-backed deployment lifecycle row for the platform UI. - `deployment_id` string, required — Deployment row id. - `agent_id` string, nullable — Owning agent; null for unassigned legacy deployments. - `model_slug` string, required — Human-readable slug this deployment serves under. - `model_slug_id` string, required — Id of the slug this deployment serves under. - `status` 'PENDING' | 'MERGING' | 'DEPLOYING' | 'DEPLOYED' | 'FAILED', required — Spanner deployment row status. - `role` 'production' | 'test', required - `is_active` boolean, required — True when this deployment currently answers for the slug. - `provider` 'baseten' | 'tinker' - `checkpoint_id` string, required — Trajectory checkpoint selected when the deployment was created. - `model_endpoint_id` string, nullable — Model Endpoint serving this deployment. - `model_id` string, nullable — Merged model backing this deployment; null until the merge lands. - `playground_endpoint_url` string, nullable — Per-deployment URL a test checkpoint is reachable at. - `base_model_slug` string, required — Base model of the source checkpoint. - `checkpoint_step` integer, required — Training step of the source checkpoint. - `output_speed` 'normal' | 'turbo' — Which GPU tier a deployment runs on: H100 (normal) or B200 (turbo). - `expected_concurrency` 'low' | 'medium' | 'high' — Traffic level a deployment is sized for; picks its replica count. - `merge_xid` string, nullable — XID of the krun job that is merging the checkpoint weights. - `deploy_xid` string, nullable — XID of the krun job that is deploying the merged model. - `created_by` string, nullable — Email of the user who requested this deployment. - `completed_at` string, date-time, nullable — When the deployment first became DEPLOYED; unlike updated_at, later promote/demote transitions never overwrite this. - `created_at` string, date-time, required — When the deployment was requested. - `updated_at` string, date-time, nullable — Last lifecycle transition; null until the row first moves. - `failure` AsyncFailure - `type` string, required — Stable category used for exception mapping. - `code` string, required — Stable programmatic reason for the asynchronous failure. - `message` string, required — Human-readable explanation for this failure occurrence. - `context` object — Machine-readable values specific to this failure code. - `production_in_flight` boolean, required ## Changes - **2026-09-28** `8331f8435ce8` — 1 info - endpoint added [Change history](https://skmtc.dev/trajectory/apis/trajectory-api/changes/api/v1/agents/:agent_id/overview/get.md) --- [API](https://skmtc.dev/trajectory/apis/trajectory-api.md) · [All operations](https://skmtc.dev/trajectory/apis/trajectory-api/llms.txt) · [OpenAPI document](https://skmtc.dev/trajectory/apis/trajectory-api/revisions/8331f8435ce8?raw)