> ## Documentation Index > Fetch the complete documentation index at: https://docs.duvo.ai/llms.txt > Use this file to discover all available pages before exploring further. # List Runs > List runs for the current team. Supports filtering by agent, user, queue, status, etc. Messages, evaluation data, and queue metadata are included where available. Set count_only=true to skip Run row selection and enrichment. The normal response shape is returned with data: [] and the matching total. To sweep a whole team, follow `next_cursor` rather than raising `offset`. ## OpenAPI ````yaml https://api.duvo.ai/v2/documentation/mintlify.json get /v2/teams/{teamId}/runs openapi: 3.0.3 info: title: Duvo Public API description: >- Public API for programmatic access to Duvo. Authenticate with API keys created in the Duvo dashboard. ## Rate limits Requests are counted per API key. Every response advertises the quota with the IETF RateLimit fields, so a client can self-throttle without waiting for a rejection: - `RateLimit-Policy: "default";q=;w=` — the policy in force: `q` requests per `w` seconds. - `RateLimit: "default";r=;t=` — the live state: `r` requests left, quota resetting in `t` seconds. - Read the quota from the headers rather than hard-coding it; it differs per environment. - The same numbers are also sent as `ratelimit-limit`, `ratelimit-remaining` and `ratelimit-reset`. Once the quota is exhausted the API answers `429 Too Many Requests` with `Retry-After` set to the seconds to wait; honor it instead of retrying immediately. version: 1.0.0 servers: - url: https://api.duvo.ai description: Production server security: [] tags: - name: Runs description: Start, monitor, and manage agent runs (Runs in the Duvo UI) - name: Sandboxes description: Create sandboxes and upload files for agent runs - name: Queues description: Manage queues and their agent bindings - name: Cases description: Create, list, and manage cases and their labels within queues - name: Case Approvals description: Submit decisions on pending case approval requests issued by an agent run - name: Case Attachments description: Upload, list, download, and remove the files attached to a case - name: Automations description: >- List and manage automations — the workspace container that groups the agents and queues making up one end-to-end process - name: Agents description: Create and manage agents for automation workloads - name: Revisions description: Create and manage agent revisions — the underlying Setup for an Agent - name: Agent Folders description: Organize agents into folders - name: Agent Memory description: Read an agent's memory files (the Memory feature in the Duvo UI) - name: Suggestions description: >- List, apply, and dismiss an Agent's improvement suggestions (the suggestions inbox in the Duvo UI) - name: Notifications description: >- List, read, dismiss, and clear the authenticated user's team notifications (the Notification Center in the Duvo UI) - name: Schedules description: List schedules configured for an agent - name: Duvo Pulse description: >- Create, list, iterate on, and delete Duvo Pulse dashboards — live, agent-generated visualizations of your Duvo data - name: Case Triggers description: >- Configure case triggers that automatically dispatch agent runs (Runs in the Duvo UI) for cases added to a queue - name: Triggers description: >- Configure event triggers that start a Run automatically when an external event fires (e.g. an email arrives, a Linear issue is created, or a file changes in Google Drive) - name: Skills description: Manage team and system skills (reusable knowledge packs). - name: Files description: Manage team files. - name: Plugins description: Discover plugins that can be referenced from a revision. - name: Organizations description: Inspect organizations you belong to and the teams within them - name: Team description: Inspect the team and members associated with the API key - name: Invites description: >- Invite people to a team — one at a time or in bulk, scoped to a Clarity process or the whole team — and manage the team's shareable invite link - name: Integrations description: Browse the team's catalog of available integration types - name: Connections description: Manage your connected integrations - name: Credentials description: >- Manage logins (domain + username + password + TOTP) used by agents to sign in to websites and desktop applications, and attach them to assignment revisions - name: Secrets description: >- Manage env-var secrets injected into runs, and attach them to assignment revisions. Only metadata is exposed; values are never returned - name: Revision Integrations description: >- Attach integrations to assignment revisions, pin specific connections, and link queues - name: ClarityV2 description: >- Manage Clarity v2 process snapshots, automation proposals, and the extra-capture-request follow-up loop paths: /v2/teams/{teamId}/runs: get: tags: - Runs summary: List Runs description: >- List runs for the current team. Supports filtering by agent, user, queue, status, etc. Messages, evaluation data, and queue metadata are included where available. Set count_only=true to skip Run row selection and enrichment. The normal response shape is returned with data: [] and the matching total. To sweep a whole team, follow `next_cursor` rather than raising `offset`. operationId: listRuns parameters: - schema: default: 20 type: number minimum: 1 maximum: 100 in: query name: limit required: false description: Number of runs per page (1-100, default 20) - schema: type: number minimum: 0 in: query name: offset required: false description: >- Number of runs to skip. Every skipped run is still read by the database, so deep offsets get slower page by page; to walk a whole team's history, page with `cursor` instead. - schema: type: string minLength: 1 in: query name: cursor required: false description: >- Resume after the run a previous page ended on: pass the `next_cursor` that page returned, with the same filters and sort_order. Unlike offset, a cursor page does not re-read the runs before it, so a sweep does not slow down as it goes deeper; send `include_total=false` on the first page to skip the full count too. Runs created in between cannot shift a boundary already passed, so pages do not repeat or skip runs the way offset pages do. A run created or completed while a sweep is in progress can still be missed by that sweep, so to export runs continuously, poll with `since` and a short overlap and deduplicate on run id. Cannot be combined with `offset`. 400 when the value is not a valid runs cursor. - schema: type: string enum: - 'true' - 'false' in: query name: include_total required: false description: >- Whether to return `total`, the count of every matching run. Counting walks every match, so it costs far more than the page itself on a large team. Defaults to true on a first page and false on a `cursor` page, where `total` is null unless this is true. Implied by `count_only`. - schema: default: created_at type: string enum: - created_at in: query name: sort_by required: false description: Field to sort by (default created_at) - schema: default: desc type: string enum: - asc - desc in: query name: sort_order required: false description: Sort direction (default desc) - schema: type: string enum: - not_started - pending - starting - running - waiting - completed - failed - interrupted - stopped - needs_attention in: query name: status required: false description: Filter to runs with this status - schema: type: string format: uuid in: query name: agent_id required: false description: Filter to runs for this agent - schema: type: string format: uuid in: query name: automation_id required: false description: >- Filter to runs that ran under this automation. A run keeps the automation it was created under, even after its agent moves to another automation - schema: type: string format: uuid in: query name: user_id required: false description: >- Filter to runs owned by this user; non-superadmin callers are scoped to themselves regardless of this value - schema: type: string format: uuid in: query name: case_queue_id required: false description: Filter to runs associated with this queue - schema: type: string in: query name: source required: false description: Filter to runs created from this source (e.g. api, schedule) - schema: type: string in: query name: search required: false description: Full-text search across run titles and case titles - schema: type: string enum: - 'true' - 'false' in: query name: has_issues required: false description: >- Filter on the run's latest successful evaluation: true returns only runs it flagged, false only runs it did not. Only the latest evaluation counts — an older flag does not match — and a run whose latest evaluation errored, or that has none, counts as unflagged. Omit to return both. - schema: type: string enum: - critical - medium - low in: query name: issue_severity required: false description: >- If set, only return runs whose latest successful evaluation has at least one failing rubric with this severity (critical | medium | low). Implies has_issues; legacy evaluations without severity companion fields do not match this filter. - schema: type: string format: date-time in: query name: since required: false description: >- Return runs completed at or after this ISO-8601 timestamp. Runs that have not completed are excluded. - schema: type: string format: date-time in: query name: until required: false description: >- Return runs completed before this ISO-8601 timestamp. The upper bound is exclusive. Runs that have not completed are excluded. - schema: type: string format: uuid in: query name: digest_id required: false - schema: default: 'false' type: string enum: - 'true' - 'false' in: query name: count_only required: false description: >- Skip row selection and enrichment. The normal list response shape is returned with an empty row array and the matching total. - name: teamId in: path required: true schema: type: string responses: '200': description: Default Response content: application/json: schema: type: object properties: data: type: array items: type: object properties: id: type: string format: uuid created_at: type: string format: date-time updated_at: type: string format: date-time started_at: nullable: true type: string format: date-time completed_at: nullable: true type: string format: date-time status: type: string enum: - not_started - pending - starting - running - waiting - completed - failed - interrupted source: type: string nullable: true title: type: string run_number: type: number agent_id: type: string format: uuid agent_name: type: string build_id: type: string format: uuid automation_id: nullable: true type: string format: uuid automation_name: type: string nullable: true user_id: nullable: true type: string format: uuid case_queue_item_id: nullable: true type: string format: uuid case_queue_id: nullable: true type: string format: uuid case_queue_name: type: string nullable: true case_title: type: string nullable: true postponed_to: nullable: true type: string format: date-time submitted_prompt_count: type: integer minimum: 0 maximum: 9007199254740991 eval_summaries: nullable: true type: object properties: evaluationId: type: string format: uuid passed: type: number total: type: number final_comment: type: string status: type: string enum: - ready - unavailable - in_progress severityCounts: type: object properties: critical: type: integer minimum: 0 maximum: 9007199254740991 medium: type: integer minimum: 0 maximum: 9007199254740991 low: type: integer minimum: 0 maximum: 9007199254740991 required: - critical - medium - low additionalProperties: false required: - passed - total - status additionalProperties: false required: - id - created_at - updated_at - started_at - completed_at - status - source - title - run_number - agent_id - agent_name - build_id - automation_id - automation_name - user_id - case_queue_item_id - case_queue_id - case_queue_name - case_title - postponed_to - submitted_prompt_count additionalProperties: false total: nullable: true description: >- Total runs matching the filters, ignoring pagination. Null when no count was requested (a `cursor` page without `include_total=true`, or `include_total=false`) — distinct from a count of 0. type: number has_more: default: false description: >- Whether another page exists past this one, determined by looking one row ahead. False on a count_only response. type: boolean next_cursor: default: null description: >- Pass as `cursor` (same filters, same sort_order) to fetch the next page. Null when `has_more` is false. Continues right after the last run on this page. nullable: true type: string required: - data - total - has_more - next_cursor additionalProperties: false '400': description: Default Response content: application/json: schema: type: object properties: error: type: string message: type: string required: - error additionalProperties: false '401': description: Default Response content: application/json: schema: type: object properties: error: type: string message: type: string required: - error additionalProperties: false '500': description: Default Response content: application/json: schema: type: object properties: error: type: string message: type: string required: - error additionalProperties: false security: - bearerAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer description: API key authentication. Get your API key from the Duvo dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.