> ## Documentation Index > Fetch the complete documentation index at: https://docs.guidinghand.ai/llms.txt > Use this file to discover all available pages before exploring further. # Duplicate an agent > Makes a new agent from this one’s current config (its draft, when it has unpublished changes), with copies of its files and procedures. The copy is named “ (copy)” at the next free agent id (`billing-copy`, `billing-copy-2`…) and published as its version 1. Its versions and its cloud browser’s saved logins stay with the original. Returns the new agent. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/agents/{agent_id}/duplicate openapi: 3.1.0 info: title: Eager API version: 1.0.0 description: >- Train AI agents like new hires: hand an agent your files and coach it, and it writes its own procedures and works in any software, even without an API. Talk to your agents one message at a time (POST /v1/agents/{agent_id}/responses): they answer from their files, procedures and your HTTP tools, and run tasks on their own cloud browser or your linked computers when an answer needs a website or a desktop app. Manage agents (versioned: save a draft, publish it), their procedures, browser and computers; follow conversations and tasks, answer approvals, and fetch history and recordings. Run tasks yourself on a session: a customer’s computer through an invite link, or a cloud browser. Test agents with evals: chat, browser and desktop test cases, run several times against your agents and judged on the answer. Every change is in the org’s audit log. servers: - url: https://guidinghand.ai description: Production - url: https://dev.guidinghand.ai description: Development (Stripe test mode) security: - bearerAuth: [] tags: - name: Agents - name: Agent files - name: Agent tools - name: Agent folders - name: Computers description: >- Computers your org links with the Eager app, and pools of them, for agents’ desktop tasks. Attach them to an agent in its `resources.computers`. - name: Phone numbers description: >- Bring your own Twilio numbers: connect the account, add its numbers, and pick the agent that answers each. Calls are answered by the agent's published version. - name: Sessions - name: Tasks - name: Webhooks - name: Audit log - name: Test cases - name: Test sets - name: Test runs - name: Start states - name: Runners - name: Responses description: >- Talk to an agent: each call is one turn of a conversation. The agent answers with its files, procedures and tools (and, with Run code, its own sandbox), asks for details with forms, and runs browser and desktop tasks when an answer needs a website or a desktop app. - name: Conversations description: >- The history of each conversation: messages, tool calls and the tasks the agent started, in order. - name: Uploads description: >- Files for conversations: attach them to a message, and download what the agent’s code made. Kept as long as their conversation. - name: Procedures description: >- An agent’s playbooks: when to use each and its steps. The agent finds and follows them; ones it writes from a first run are marked written_by: agent. - name: Categories description: The kinds of request an org’s procedures and test cases are sorted into. - name: Escalations description: >- What needs your team: an approval only the team can give or a question only it can answer, in a real conversation; a procedure run that failed; and one that worked another way, with the procedure rewritten to match (a proposed change). Test chats never escalate; evals do, without webhooks. - name: Schedules description: >- Run an agent’s procedure on a cron expression, in a time zone, with the inputs it needs. Each run is a conversation of its own with nobody in it (`channel` `schedule` in its variables): the procedure’s steps without AI run outright when it has them, else the model follows it to its end. Its record says how it ended, what the agent said last and what it cost; the team hears by webhook (`schedule.run_completed`, `schedule.run_failed`), email and Slack or Teams, as the schedule says. paths: /v1/agents/{agent_id}/duplicate: parameters: - name: agent_id in: path required: true description: The agent’s id, e.g. `billing`. schema: type: string post: tags: - Agents summary: Duplicate an agent description: >- Makes a new agent from this one’s current config (its draft, when it has unpublished changes), with copies of its files and procedures. The copy is named “ (copy)” at the next free agent id (`billing-copy`, `billing-copy-2`…) and published as its version 1. Its versions and its cloud browser’s saved logins stay with the original. Returns the new agent. operationId: duplicateAgent responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/Agent' '401': $ref: '#/components/responses/E401' '403': $ref: '#/components/responses/E403' '404': $ref: '#/components/responses/E404' '409': $ref: '#/components/responses/E409' components: schemas: Agent: type: object properties: object: const: agent agent_id: type: string example: billing name: type: string example: Billing help instructions: type: string description: Added under Eager’s own rules, which always win. model: $ref: '#/components/schemas/Model' effort: $ref: '#/components/schemas/Effort' greeting: type: string description: >- The agent’s first message: it opens every new conversation (the first item, before the person’s message) and is shown on the invite page. display_name: type: string description: >- What the Eager app calls the agent on the person’s screen while it works (“Acme Support is typing”). Empty means “Eager”. example: Acme Support narration: type: boolean description: >- The app shows the agent’s thoughts and steps on the person’s screen as it works, and its summary when it finishes. These are the agent’s own words, so they can repeat what your team answered. Off: no thoughts, steps or summary; they see the banner with the Stop button (and the agent’s questions and approval requests, if `customer_answers` and `customer_approvals` are on). customer_answers: type: boolean description: >- The person at the computer can answer the agent’s questions in the Eager app (your team still can too; the first answer is used). Off: only your team answers, and the question isn’t shown on the person’s screen. customer_approvals: type: boolean description: >- The person at the computer can approve or deny the agent’s approval requests in the Eager app (your team still can too; the first decision is used). Off: only your team decides, and the request isn’t shown on the person’s screen. guardrails: $ref: '#/components/schemas/Guardrails' tools: $ref: '#/components/schemas/AgentTools' resources: $ref: '#/components/schemas/AgentResources' escalations: $ref: '#/components/schemas/EscalationRules' voice: type: - string - 'null' enum: - marin - gleam - meridian - vesper - willow - stone - quartz - ripple - delta - cinder - beacon - bossa - tempo - nuri - juni - flitz - brise - sillage - nira - harema - shida - noeul - null description: >- The voice it speaks with on GPT-Live: in Coach by voice and on phone calls to its numbers. null means the default, marin. Voices are listed by language at https://developers.openai.com/api/docs/guides/live-conversations#voice-options. example: meridian folder_id: type: - string - 'null' description: >- The folder it’s in (`client.agentFolders`); null at the top. Moving an agent makes no new version. invite_url_template: type: string example: https://guidinghand.ai/acme/billing/{code} version: type: integer minimum: 0 example: 3 description: >- The published version: what sessions and tasks run. 1 when the agent is made; each publish adds one. has_draft: type: boolean description: It has unpublished changes (`GET /v1/agents/{agent_id}/draft`). created_by: $ref: '#/components/schemas/Actor' description: Who made it. updated_by: $ref: '#/components/schemas/Actor' description: >- Who last changed it: saved its draft, published it or restored a version. created_at: type: - string - 'null' format: date-time updated_at: type: - string - 'null' format: date-time Model: type: - string - 'null' enum: - claude-haiku-5-5 - claude-sonnet-5-5 - claude-opus-5-5 - claude-fable-5-1 - gpt-6-luna - gpt-6.1-sol - gpt-6-astra - gemini-3.8-flash - gemini-4-argon - null description: >- The AI model the agent runs on: `claude-haiku-5-5`, `claude-sonnet-5-5`, `claude-opus-5-5` or `claude-fable-5-1` (Anthropic), `gpt-6-luna`, `gpt-6.1-sol` or `gpt-6-astra` (OpenAI), `gemini-3.8-flash` or `gemini-4-argon` (Google). Null for Eager’s default, GPT-6 Astra (`gpt-6-astra`). It sets the price of the agent’s tokens (US$ per million: see /pricing). Starting a task with a model this server can’t run returns 503 with `code: "model_unavailable"`. Effort: type: - string - 'null' enum: - low - medium - high - null description: >- How much the model thinks per step. Null for Eager’s default (Low). It has no price of its own: more thinking uses more tokens. Guardrails: type: object required: - mode - confirm - block - apps - sites - safety_checks - scope - screen_check - max_steps - max_minutes - approval_timeout_minutes description: >- Rules Eager enforces on each action the agent asks for, before it runs. They add to Eager’s own rules and can’t loosen them. In order, the first that applies decides: text that looks like a secret, or typing into a password field, is not typed (the person is asked to type it); a match in `apps.block` or `sites.block` is blocked; with a non-empty `apps.allow` or `sites.allow`, anything not on it is blocked; a step in a `block` category is blocked; a step in a `confirm` category waits for an approval; anything else runs. On a Mac (Eager 1.0.20 or later) a step’s category comes from what it would do: what’s under a click; what Space, Return or Enter presses (the focused button, or a dialog’s default button); Cmd/Ctrl+Enter, and Enter in a message box, count as sending; Delete or Backspace outside a text field counts as deleting; both ends of a drag (dropping on the Trash counts as deleting); and typed text a line at a time (text holding a secret is refused whole). A click or acting key Eager can’t see waits for an approval when the agent has any `confirm` or `block` categories. A Mac where Eager isn’t allowed Accessibility can’t check guardrails, so a task with rules to check fails at start. On Windows, and before 1.0.20, categories rest on the agent’s own approval requests. Always returned whole, with defaults filled in. properties: mode: type: string enum: - supervised - auto - unattended default: supervised description: >- `supervised`: someone can approve (your team, and the person at the computer when `customer_approvals` is on). `auto`: nobody is asked; anything that would need an approval (a step, a safety check, a screen check, a tool call) is approved automatically and recorded as an `approved` event with `answered_by: "auto"`, so the task only waits on a person for questions. Blocked categories, app and site rules and secrets still apply, and `safety_checks: stop` still stops. `unattended`: nobody is there to approve, so anything that would need an approval is refused instead and the agent plans around it, and a safety check stops the task. Questions still go to your team (and the person at the computer, when `customer_answers` is on) as usual. confirm: type: array items: $ref: '#/components/schemas/GuardrailCategory' uniqueItems: true default: - purchase - send - delete - install - security - terms description: >- Always ask for an approval before these, described by Eager rather than by the model. In `auto` mode they are approved automatically, and in `unattended` mode refused. block: type: array items: $ref: '#/components/schemas/GuardrailCategory' uniqueItems: true default: [] description: >- Never do these. A category in both `confirm` and `block` is blocked; take it out of `block` later and, if it’s still in `confirm`, the agent asks first again. Both lists come back as you set them. apps: type: object required: - allow - block properties: allow: type: array maxItems: 50 items: type: string maxLength: 100 default: [] description: Only these apps (when not empty). block: type: array maxItems: 50 items: type: string maxLength: 100 default: [] description: Never these apps. description: >- App names or ids (`Google Chrome`, `com.google.Chrome`, `chrome.exe`), matched without regard to case. Names differ by system, so for Macs and Windows PCs list both. A non-empty `allow` means only those apps; on a Mac the Dock, menu bar, Control Center and Spotlight stay usable, and on Windows nothing is exempt (the taskbar, File Explorer and the Run box are `explorer.exe`). `block` always wins. With any app rule, a step Eager can’t place in an app is refused. sites: type: object required: - allow - block properties: allow: type: array maxItems: 50 items: type: string maxLength: 100 default: [] description: Only these sites in a browser (when not empty). block: type: array maxItems: 50 items: type: string maxLength: 100 default: [] description: Never these sites. description: >- Hosts, stored in lowercase without a scheme, path or port (`https://Shop.example.com/cart` is kept as `shop.example.com`). `example.com` also covers its subdomains. Site rules cover anything showing a web page: browsers, and apps with web content such as Slack’s desktop app, which counts as the site it shows; an app’s local files (`file://`) aren’t a site. A non-empty `allow` means only those sites. `block` wins over `allow`. With any site rule, a step on a page whose address can’t be read is refused, and what’s typed into the address bar since it was last clicked is judged together, by where it goes. Site rules need a computer that reports page addresses (macOS with Eager 1.0.20 or later, for now): on one that can’t, tasks with this agent fail at start. safety_checks: type: string enum: - ask - stop default: ask description: >- When the model raises a safety check on a step: `ask` for an approval with `risk: high` (denying it stops the task), or `stop` the task. In `auto` mode an `ask` is approved automatically; in `unattended` mode a safety check always stops the task. scope: type: string maxLength: 2000 default: '' description: >- What this agent is for, in plain language. When set, each task is checked against it before it starts: a task that is clearly something else, or one the check can’t give a clear yes or no on, fails with the reason in `error`. Empty: no check. screen_check: type: boolean default: false description: >- Check each new app, window or site the agent sees for text that tries to give the agent instructions (prompt injection). What happens when it finds some, or can’t check, follows `safety_checks`. max_steps: type: integer minimum: 1 maximum: 500 default: 150 description: >- Model turns per task. A task that reaches it without finishing fails. max_minutes: type: - integer - 'null' minimum: 1 maximum: 240 default: null description: >- Running minutes per task, not counting time waiting for answers or approvals. A task that reaches it fails. `null`: no limit. approval_timeout_minutes: type: - integer - 'null' minimum: 1 maximum: 1440 default: null description: >- An approval nobody decides within this many minutes is denied, with `answered_by: "timeout"`. `null`: wait until someone decides. AgentTools: type: object required: - files - http description: >- The agent’s tools beyond the computer: its own file system (on by default) your HTTP tools, and its cloud browser’s sign-ins, and Run code. Part of its config, so versioned with it. Always returned whole, with defaults filled in. properties: files: type: object required: - enabled - access properties: enabled: type: boolean default: true description: >- The agent has its own file system: text files Eager keeps for this agent, separate from the computer it works on. It can list, read and search them during tasks (read only, for now). access: type: string enum: - read_only default: read_only description: >- For now agents only read their files: `read_only` (it lists, reads and searches them; your team adds and changes them). `read_write` isn’t available and is refused. http: type: array maxItems: 20 items: $ref: '#/components/schemas/HttpTool' default: [] description: Your own functions the agent can call, up to 20. mcp: type: array maxItems: 10 items: $ref: '#/components/schemas/McpServer' default: [] description: Remote MCP servers the agent can call, up to 10. browser: type: object properties: keep_logins: type: boolean description: >- Its cloud browser keeps the sites your team signed in to (its cookies, encrypted) from one browser to the next. Off: every browser starts signed out, and turning it off forgets what was kept. default: false required: - keep_logins code: type: object description: >- Run code: in the chat, the agent has its model provider’s own sandbox, with no internet. On Claude models, Anthropic’s code execution (Bash and Python), kept between turns; on GPT models, OpenAI’s Code Interpreter (Python), reset after 20 minutes unused, with the conversation’s files put back. Either works on files people attach (they’re in the sandbox too), does exact calculations, and can hand back files it makes; one sandbox per conversation. On Gemini models, Gemini’s code execution (Python, 30 seconds a run, nothing kept between runs): exact calculations and charts, but no other files in or out, so files only a sandbox opens are refused. properties: enabled: type: boolean default: false visual: type: object description: >- Visual answers: in the chat, a long answer (a status, options to compare, a table, steps) is also laid out as UI, which the console and the website widget show (`view` on the message). The text stays the answer. On unless turned off. properties: enabled: type: boolean default: true blocks: type: array items: type: string enum: - facts - table - options - list - callout - badges - bars description: >- The cards a view may use; all of them by default. `text` is always there, and `buttons` come with `choices`. choices: type: boolean default: true description: >- Whether a view has anything to press: a `pick` on options and `buttons` for next steps, which send a reply for the person. Off: nothing to press. instructions: type: - string - 'null' maxLength: 2000 description: >- How answers should be laid out, in your words, like "Lead with the warranty status. Put part numbers in a table." It steers the layout only: a view still has only what the answer says. null: none. AgentResources: type: object description: >- Where the agent’s tasks may run. `browser`: its own cloud browser in each conversation (`enabled`, off by default; `start_url`, an absolute http(s) address where it opens; `keep_logins`, the same setting as `tools.browser.keep_logins`). `computers`: up to 50 linked computers and pools for its desktop tasks, used in order, whichever is free first. Send part of it to change only those keys; `computers`, when sent, is the whole list; `browser: null` turns the browser off and `resources: null` resets both. properties: browser: type: object properties: enabled: type: boolean default: false start_url: type: - string - 'null' format: uri maxLength: 2000 keep_logins: type: boolean default: false computers: type: array maxItems: 50 items: type: object required: - type - id properties: type: type: string enum: - computer - pool id: type: string maxLength: 60 description: >- A linked computer’s id (its code, like `K7QM-24XP`) or a pool’s (`pool_…`). example: browser: enabled: true start_url: https://portal.example.com/orders keep_logins: false computers: - type: pool id: pool_8fK2mQ0aLp4x EscalationRules: type: object description: >- What needs the team, and whether the agent's procedure runs are checked. Every key is on by default. Returned whole; in a change, send only the keys that change (null turns them all back on). properties: qa: type: boolean default: true description: >- AI Review: check each run of one of the agent's procedures against its steps, on the cheapest model of the agent's provider. Charged by its tokens at that model's price. Off: runs aren't checked, and no `procedure_failed` or `procedure_change` is raised. approval: type: boolean default: true description: >- Escalate approvals only the team can decide (list, email, webhook). Off: they still wait in their conversation. question: type: boolean default: true description: >- Escalate questions only the team can answer. Off: they still wait in their conversation. procedure_failed: type: boolean default: true description: Escalate runs the check found failed (needs `qa`). procedure_change: type: boolean default: true description: >- Escalate runs the check found worked another way, with the procedure rewritten to match (needs `qa`). handoff: type: boolean default: true description: >- Let the agent hand a request to the team from a chat (its `escalate` tool), raising a `handoff` escalation (list, email, webhook). Off: it isn’t offered the tool. Actor: oneOf: - title: Person type: object description: A person in the org (in the console). properties: type: const: user email: type: - string - 'null' example: jane@acme.com - title: API key type: object description: One of the org’s API keys. properties: type: const: api_key key_id: type: string name: type: - string - 'null' example: Zendesk prefix: type: - string - 'null' description: The key’s first characters. example: gh_live_AbC1 - type: 'null' description: >- Who did it: a person (in the console) or an API key. Null when nobody was recorded: it was made with a session token, by Eager itself, or before this was kept. Error: type: object required: - error properties: error: type: object required: - type - message properties: type: type: string enum: - invalid_request - authentication - payment_required - permission - not_found - conflict - rate_limit - server_error message: type: string code: type: string description: >- Why it was refused, when there’s more to say than the status. Starting a task or a chat reply: `insufficient_balance`, `auto_topup_limit_reached` or `card_needs_attention` (402: the balance is empty and auto top-up can’t add funds; add funds, raise the auto top-up limit, or update the card), `concurrency_limit` (429), `model_unavailable` (503: the agent’s `model` can’t run on this server; choose another). Deciding a conversation’s request: `already_decided` (409: someone decided or answered it first; see `decided_by`) or `not_pending` (409: its task has ended, so nothing would act on it). POST /v1/tasks/{task_id}/respond: `decide_in_conversation` (409: decide it in the task’s conversation; see `conversation_id`, `agent_id`, and `approval_id` or `question_id`). Deleting a start state that test cases use: `in_use` (409, with `test_case_ids`). test_case_ids: type: array items: type: string description: 'With `in_use`: the test cases that use the start state.' decided_by: description: 'With `already_decided`: who decided first.' allOf: - $ref: '#/components/schemas/Decider' conversation_id: type: string description: >- With `decide_in_conversation`: the conversation to decide it in (POST /v1/conversations/{conversation_id}/decisions). agent_id: type: - string - 'null' description: >- With `decide_in_conversation`: the task’s agent (null for a task run without one). approval_id: type: string description: 'With `decide_in_conversation`: the approval to decide.' question_id: type: string description: 'With `decide_in_conversation`: the question to answer.' GuardrailCategory: type: string enum: - purchase - send - delete - install - security - terms description: >- `purchase`: buying or paying. `send`: sending, posting or submitting. `delete`: deleting or removing. `install`: installing software. `security`: security and account settings. `terms`: accepting terms or agreements. HttpTool: type: object required: - name - description - url description: >- An API the agent can call. When the model calls the tool, Eager makes the call as the tool says (unsigned) and gives the model the response body (64 KB, within `timeout_seconds`). A set call (`method`, `parameters`): `{name}` placeholders in `url`’s path take those arguments, and the others are the query of a `GET` or `DELETE`, else the JSON body. An open call (`methods`): `url` is a base, and the agent gives each call’s `method`, `path` (with any query) and JSON `body`; a call that would leave the base (another host, or a path outside it) is refused. Redirects are followed only to an address the tool could call itself. Tools made before 2026-10-21 were signed POSTs of an envelope; they are now set calls, a POST of their arguments to the same `url`. properties: name: type: string pattern: ^[a-zA-Z][a-zA-Z0-9_-]{0,63}$ example: lookup_order description: >- What the model calls it: a letter, then letters, numbers, `_` or `-`, up to 64. Unique for the agent (in any case), and not one of Eager’s own (`ask_user`, `request_approval`, `computer`, or the file system’s). description: type: string maxLength: 1000 example: 'Look up an order by its number: status, items and delivery date.' description: What it does and when to use it, for the model. url: type: string format: uri example: https://api.acme.com/v1/orders/{order} description: >- The API’s address: public https, without a user name or password, and no keys or tokens in its query. For a set call, the endpoint, with `{name}` placeholders in its path for arguments. For an open call, the base (its host and path prefix, without a query), like `https://api.example.com/v1/`: the agent calls only paths under it. method: type: string enum: - GET - POST - PUT - PATCH - DELETE default: POST description: >- A set call’s method. Arguments not in `url` go in the query of a `GET` or `DELETE`, else in the JSON body. parameters: type: object default: type: object properties: {} description: >- A set call’s arguments, as a JSON Schema object (`{ "type": "object", "properties": { … } }`), under 10 KB. Left out: no arguments. methods: type: array items: type: string enum: - GET - POST - PUT - PATCH - DELETE default: - GET - POST description: >- Makes it an open call: the methods the agent may use. It then has no `method` or `parameters`: each call takes `method`, `path` and `body`. headers: type: object additionalProperties: type: string maxProperties: 20 example: User-Agent: Mozilla/5.0 description: >- Fixed headers sent with every call. No keys, tokens or sign-ins (a header named like `Authorization`, `Cookie` or `X-Api-Key` is refused: it would be kept in every version of the agent). Tools can’t hold keys yet. timeout_seconds: type: integer minimum: 5 maximum: 120 description: >- How long a call waits for an answer, in seconds. Left out: 45. A `GET` that times out is tried once more. approval: type: string enum: - never - always default: never description: >- `always`: each call waits for your team’s approval first, asked in the conversation (a task is `paused` until it’s decided). In `auto` mode such a call is approved automatically, and in `unattended` mode refused. McpServer: type: object required: - name - url - tools - approval description: >- A remote MCP server the agent can call. Eager lists its tools (`tools/list`) when it's saved and keeps them with the agent's version, so a version always offers the same tools; at run time each call is a `tools/call` from Eager's servers, signed in with the server's saved headers or OAuth sign-in (its access token renewed before it expires). The tool's text result is what the model gets (images and audio are described, not shown). properties: name: type: string pattern: ^[a-zA-Z][a-zA-Z0-9-]{0,29}$ example: crm description: >- The server's name: a letter, then letters, numbers or `-`, up to 30. The model sees each of its tools as `__` (characters other than letters, numbers, `_` and `-` in a tool's name become `_`). url: type: string format: uri example: https://mcp.example.com/mcp description: >- Its Streamable HTTP address (MCP 2025-03-26 or later): public https only. Servers that only speak the older SSE transport aren't supported. description: type: string maxLength: 1000 description: >- When the agent should use it. Added to each of its tools' descriptions. auth: type: object description: >- The sign-in it was saved with: the header names and the id of the secret holding them, or (`type: "oauth"`) an OAuth sign-in connected in the console. The values and tokens are kept encrypted for your organization, never returned and never kept in the agent's versions. properties: headers: type: array items: type: string example: - Authorization secret_id: type: string example: tsec_8Zp2kQ7wLm4x type: type: string enum: - oauth description: >- `oauth`: an OAuth sign-in (see `GET /v1/mcp_oauth/{secret_id}` for whether it's connected). Left out: headers. tools: type: array items: type: object properties: name: type: string example: lookup_order description: type: string parameters: type: object description: Its arguments' JSON Schema, as the server gave it. description: Its tools, as listed when it was last saved (or refreshed). allowed_tools: type: array items: type: string description: >- The names of its tools the agent may use. Left out (or `null`): all of them. Up to 100 tools across an agent's servers. approval: type: string enum: - never - always default: never description: >- `always`: your team allows each call first (unattended agents can't use its tools). timeout_seconds: type: integer minimum: 5 maximum: 120 description: 'How long a call waits for an answer, in seconds. Left out: 30.' Decider: type: object description: Who decided a request, or answered a question. required: - type properties: type: type: string enum: - person - team - auto - refused - timeout - operator - moved_on description: >- `person`: the person in the chat (in the Eager app, or a visitor to your website’s widget), when the agent lets them (`customer_approvals`, `customer_answers`) and the request isn’t for your team only. `team`: a member in the console (`email`) or an API key (`key_id`). `auto`: the agent’s guardrails approve without asking (`mode: auto`). `refused`: its guardrails refuse (`mode: unattended`). `timeout`: nobody decided within its `approval_timeout_minutes`. `operator`: an eval case’s operator. `moved_on`: the person sent a new message instead, so it was declined. email: type: string description: '`team`: the member who decided.' key_id: type: string description: '`team`: the API key that decided.' responses: E401: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' E403: description: Your role can’t do this. content: application/json: schema: $ref: '#/components/schemas/Error' E404: description: Not found in this org. content: application/json: schema: $ref: '#/components/schemas/Error' E409: description: >- Conflicts with the current state (e.g. no computer connected, a task already running, nothing pending, no draft to publish, an agent’s file limits). content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer description: An org API key (`gh_live_…`) from Settings → API keys in the console. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.