Sign in
agent

List agent runs

Retrieve a paginated list of agent runs with optional filtering. Results default to sort_by=updated_at and sort_order=desc.

get/agent/runs

Query parameters

limitinteger

Maximum number of runs to return

cursorstring

Pagination cursor from previous response

sort_by'updated_at' | 'created_at' | 'title' | 'agent'

Sort field for results.

  • updated_at: Sort by last update timestamp (default)
  • created_at: Sort by creation timestamp
  • title: Sort alphabetically by run title
  • agent: Sort alphabetically by skill. Runs without a skill are grouped last.
sort_order'asc' | 'desc'

Sort direction

stateRunState[]

Filter by run state. Can be specified multiple times to match any of the given states.

namestring

Filter by agent config name

model_idstring

Filter by model ID

creatorstring

Filter by creator UID (user or service account)

executorstring

Filter by the user or agent that executed the run. This will often be the same as the creator, but not always: users may delegate tasks to agents.

source'LINEAR' | 'API' | 'SLACK' | 'LOCAL' | 'SCHEDULED_AGENT' | 'WEB_APP' | 'GITHUB_ACTION' | 'CLOUD_MODE' | 'CLI' | 'JIRA' | 'SELF_IMPROVEMENT' | 'GITHUB_WEBHOOK' | 'GITLAB_WEBHOOK' | 'AUTOFIX' | 'RUN_SCORER' | 'ORCHESTRATION'

Source that created the run:

  • LINEAR: Created from Linear integration
  • API: Created via the Warp API
  • SLACK: Created from Slack integration
  • LOCAL: Created from local CLI/app
  • SCHEDULED_AGENT: Created by a scheduled agent
  • WEB_APP: Created from the Warp web app
  • GITHUB_ACTION: Created from a GitHub action
  • CLOUD_MODE: Created from a Cloud Mode
  • CLI: Created from the CLI
  • JIRA: Created from Jira integration
  • SELF_IMPROVEMENT: Created by Warp's self-improvement pipeline
  • GITHUB_WEBHOOK: Created from a GitHub webhook event
  • GITLAB_WEBHOOK: Created from a GitLab webhook event
  • AUTOFIX: Created by Warp's autofix pipeline
  • RUN_SCORER: Created by Warp's run-scoring judge
  • ORCHESTRATION: Created as a child run by the orchestration layer (parent_run_id set)

Filter by run source type

execution_location'LOCAL' | 'REMOTE'

Where the run executed:

  • LOCAL: Executed in the user's local Oz environment
  • REMOTE: Executed by a remote/cloud worker

Filter by where the run executed

created_afterstring date-time

Filter runs created after this timestamp (RFC3339 format)

created_beforestring date-time

Filter runs created before this timestamp (RFC3339 format)

updated_afterstring date-time

Filter runs updated after this timestamp (RFC3339 format)

environment_idstring

Filter runs by environment ID. Passing the literal value empty-environment matches runs with no environment configured, rather than omitting the parameter, which applies no environment filter at all. empty-environment can never collide with a real environment ID: every environment ID is exactly 22 characters drawn from [A-Za-z0-9], while this sentinel contains a hyphen and is a different length.

skillstring

Filter runs by skill spec (e.g., "owner/repo:path/to/SKILL.md"). Alias for skill_spec.

skill_specstring

Filter runs by skill spec (e.g., "owner/repo:path/to/SKILL.md")

schedule_idstring

Filter runs by the scheduled agent ID that created them

ancestor_run_idstring

Filter runs by ancestor run ID. The referenced run must exist and be accessible to the caller.

metadataobject

Filter by exact metadata key/value pairs using object notation (e.g. metadata[ticket_id]=VIS-238). Multiple pairs combine with AND semantics. At most 5 pairs per request. Returns feature_not_available when metadata filtering is not enabled.

artifact_type'PLAN' | 'PULL_REQUEST' | 'SCREENSHOT' | 'FILE' | 'EXTERNAL_REFERENCE'

Filter runs by artifact type

qstring

Fuzzy search query across run title, prompt, and skill_spec

Response

List of runs

Changes