Showing the first 18000 characters. Load the complete file to read the remainder.
# Labelbox
> Documentation for Recursion Managed Agents and the Labelbox platform.
- [Managed Agents](https://docs.labelbox.com/recursion/index.md): Run agents in managed sandboxes with tools and credentials, follow every step, and collect the files they produce.
- [How it works](https://docs.labelbox.com/recursion/how-it-works.md): The concepts behind Managed Agents and how a session moves from start to finished work, including the lifecycle and how credentials reach the agent.
- [Quickstart](https://docs.labelbox.com/recursion/quickstart.md): Create an API key, an environment, and an agent, start a session with a task, and read the agent's reply, in the console or with cURL.
- [Build in the console](https://docs.labelbox.com/recursion/console.md): Create an agent, prepare its environment, launch a session, and find every screen in the Recursion console.
- [Connect to the Recursion MCP](https://docs.labelbox.com/recursion/ai-coding-agents.md): Connect Claude Code, Codex, Cursor, or another MCP client to the public docs MCP server and to the authenticated Recursion MCP endpoint with an API key.
- [Use the Labelbox MCP server](https://docs.labelbox.com/recursion/labeling-mcp.md): Connect the Labelbox MCP server to the same MCP client as Recursion, so one conversation can read your labeling projects and run your agents.
- [API keys](https://docs.labelbox.com/recursion/api-keys.md): Create, scope, use, rotate, and revoke the personal rma_ keys that authenticate every Managed Agents API request.
- [Organizations and roles](https://docs.labelbox.com/recursion/organizations-and-roles.md): How tenants, organizations, and roles decide what each person and API key can see and do in Managed Agents.
- [Domains](https://docs.labelbox.com/recursion/domains.md): Claim your company's email domain, prove it with DNS, and choose whether people at it can find and join your tenant.
- [Enterprise SSO](https://docs.labelbox.com/recursion/enterprise-sso.md): Connect your SAML 2.0 identity provider, such as Okta, Microsoft Entra ID, or Google Workspace, so people at your verified domains sign in through it.
- [Pricing](https://docs.labelbox.com/recursion/pricing.md): What a session hour costs, what that price covers, and how prepaid credits pay for it.
- [Billing](https://docs.labelbox.com/recursion/billing.md): Buy prepaid credits, manage the cards that pay for them, track purchases and receipts, and see what sessions are charged.
- [Agents](https://docs.labelbox.com/recursion/agents.md): Create an agent, publish immutable versions of it, tag it, and delete it.
- [Tools](https://docs.labelbox.com/recursion/tools.md): See which tools an agent gets in a session, turn off web search, and withhold integration tools.
- [Connect MCP servers](https://docs.labelbox.com/recursion/mcp-servers.md): Add a remote MCP server's tools to an agent, authenticate it with a vault credential, and test the connection before a session depends on it.
- [Skills](https://docs.labelbox.com/recursion/skills.md): Write reusable procedures as SKILL.md, version them, group them, and attach them to agents.
- [Integrations](https://docs.labelbox.com/recursion/integrations.md): Connect your organization to 164+ apps, choose which tools agents may use in each one, and grant apps to agents so sessions can work in them.
- [GitHub access](https://docs.labelbox.com/recursion/github.md): Choose GitHub MCP tools and repositories for each Managed Agent, and use git and gh in the sandbox.
- [Multi-agent](https://docs.labelbox.com/recursion/multi-agent.md): Choose between one agent, delegation, a team, or an advisor, and control exactly what each child agent can use.
- [Teams](https://docs.labelbox.com/recursion/teams.md): Run copies of an agent on a shared task board so independent pieces of work happen in parallel, get reviewed, and end in one decision.
- [Set up an environment](https://docs.labelbox.com/recursion/environments.md): Create an environment, prove its setup script works, control its network access, and keep it current.
- [Environment reference](https://docs.labelbox.com/recursion/environments-reference.md): Look up every environment field, default, compute size, sandbox path, network rule, setup state, and limit.
- [Sessions](https://docs.labelbox.com/recursion/sessions.md): Start a session, watch it work, and continue, stop, or clean it up.
- [Events](https://docs.labelbox.com/recursion/events.md): Send messages to a session, stream and read its events without losing any, and watch many sessions at once.
- [Session operations](https://docs.labelbox.com/recursion/session-operations.md): Search sessions by metadata, see queued messages, measure compute, ask the session analyst, and read the board, tree, and threads.
- [Deliverables and artifacts](https://docs.labelbox.com/recursion/artifacts.md): Ask agents for named deliverables, understand which files are kept and when, show images inline, and get results out of a session.
- [Write outcome rubrics](https://docs.labelbox.com/recursion/outcomes.md): Write a rubric a grader can check, launch a session against it, and read the verdict for each criterion.
- [Reference prior sessions](https://docs.labelbox.com/recursion/referenced-sessions.md): Give a session read-only access to earlier sessions so its agent can search their transcripts, costs, and deliverables.
- [Track usage and cost](https://docs.labelbox.com/recursion/usage-and-cost.md): Read what a session cost, including its helper agents, tools, and sandbox compute, and token usage for many sessions at once.
- [Analytics](https://docs.labelbox.com/recursion/analytics.md): See how many agent session hours your organization's agents used, how their sessions completed, and how their sandboxes started, in the console.
- [Vaults and credentials](https://docs.labelbox.com/recursion/vaults.md): Store secrets once, grant each session exactly the credentials it needs, and know what the agent can and cannot see.
- [Files](https://docs.labelbox.com/recursion/files.md): Upload input files once, attach them read-only to any session, show them to the agent in a message, and download the deliverables sessions save.
- [Agent file history](https://docs.labelbox.com/recursion/agent-file-history.md): Let an agent's sessions search and read the deliverables its earlier sessions saved, by path, metadata, date, and text.
- [Automations](https://docs.labelbox.com/recursion/automations.md): Start agent sessions on a schedule, when a Slack, GitHub, or webhook event arrives, or by hand, with the same agent version, environment, prompt, and credentials every time.
- [Run a research team](https://docs.labelbox.com/recursion/use-cases/research-team.md): Run a team of agents that researches three options in parallel, reviews each finding, and delivers one recommendation.
- [Fix a GitHub issue](https://docs.labelbox.com/recursion/use-cases/fix-a-github-issue.md): Connect GitHub, give an agent write access to one repository, and run a session that fixes an issue and opens a pull request.
- [API conventions](https://docs.labelbox.com/recursion/api.md): Create an API key in the console, then call the Managed Agents REST API or the authenticated MCP endpoint: base URL, authentication, asynchronous starts, idempotency, pagination, errors, rate limits, and request ids.
- [Limits](https://docs.labelbox.com/recursion/limits.md): Every size, count, rate, and time limit you can hit in Managed Agents, with the error you get and where each is explained.
- [Errors](https://docs.labelbox.com/recursion/errors.md): Every error code the Managed Agents API returns, grouped by area, with its cause, the fix, and whether retrying can help.
- [Event types and states](https://docs.labelbox.com/recursion/reference.md): Look up every session status, execution state, stop reason, event type, and setup-run state in Managed Agents.
- [Glossary](https://docs.labelbox.com/recursion/glossary.md): Short definitions of every term used in the Managed Agents docs, with a link to where each is explained.
- [Security](https://docs.labelbox.com/recursion/security.md): How Managed Agents isolates organizations and sandboxes, controls network access, decides which credential values agents can read, and handles your data.
- [Troubleshooting](https://docs.labelbox.com/recursion/troubleshooting.md): Match a Managed Agents symptom or error code to its cause and fix, for sign-in, keys, organizations, billing, environments, integrations, files, automations, MCP servers and credentials, and sessions.
- [List environments](https://docs.labelbox.com/api-reference/environments/list-environments.md): Returns every environment in the calling organization with its full sandbox spec (provider, image, setup, resources, network policy). Soft-deleted environments are omitted, and the response is not paginated.
- [Create environment](https://docs.labelbox.com/api-reference/environments/create-environment.md): Defines the sandbox an agent session runs in and returns the stored environment, including its generated environment_id. The provider must be one this deployment reports from managedAgentsListSandboxProviders. Privileged Docker requires unrestricted internet access (network_policy: {}). Nothing is p…
- [Get environment](https://docs.labelbox.com/api-reference/environments/get-environment.md): Returns one environment and its full sandbox spec. A soft-deleted or unknown id is a 404, and an id belonging to another organization is reported the same way.
- [Soft delete environment](https://docs.labelbox.com/api-reference/environments/soft-delete-environment.md): Soft deletes the environment: it disappears from reads and can no longer be referenced by a new session, but nothing is erased. Sessions that already ran against it keep their history. There is no undelete on this API.
- [Update environment](https://docs.labelbox.com/api-reference/environments/update-environment.md): Applies a partial update and returns the stored environment; omitted fields keep their current values; a name, when sent, must not be blank or null. Changing from a non-Runs provider to Runs with an absent or {} stored policy requires an explicit network_policy: {"version":"v1","rules":[]} for deny-…
- [List setup runs](https://docs.labelbox.com/api-reference/environments/list-setup-runs.md): Returns the environment's recent setup runs, newest first: manual, automatic runner_refresh, and legacy session-triggered runs. The newest manual or runner_refresh run supplies the environment's setup_verification verdict; a session run records legacy in-session setup and can be read here by its ses…
- [Run and verify the environment's setup script](https://docs.labelbox.com/api-reference/environments/run-and-verify-the-environments-setup-script.md): Requires Idempotency-Key because this operation provisions billable compute. Provisions fresh compute for the environment, runs its setup script exactly as a session would (same image, resources, and variables; no session credentials), records every line of output, profiles the compute, releases it,…
- [Get a setup run, optionally waiting for it to finish](https://docs.labelbox.com/api-reference/environments/get-a-setup-run-optionally-waiting-for-it-to-finish.md): Returns one setup run. With wait_seconds the call blocks until the run reaches a terminal status or the wait elapses, so a poll loop needs no client-side timer. next_action names the call to make on the result: poll again, read the log, or start a session.
- [Read or tail a setup run's log](https://docs.labelbox.com/api-reference/environments/read-or-tail-a-setup-runs-log.md): Returns the run's output after a cursor: stdout and stderr as the script produced them, marker lines naming each script line before it runs, and system lines for the setup phases around the script (provision, gpu_check, profile, cleanup). Secrets are redacted before storage. To tail a live run, loop…
- [Cancel a setup run](https://docs.labelbox.com/api-reference/environments/cancel-a-setup-run.md): Stops a queued or in-flight manual or automatic runner_refresh setup run and releases its compute. Sessions waiting on a cancelled runner_refresh fail with that run as their cause. The cancelled run is returned with status cancelled and active_setup_run_id is cleared. A cancelled run proves nothing:…
- [List portable environment templates](https://docs.labelbox.com/api-reference/environments/list-portable-environment-templates.md): Returns reviewed, versioned environment starting points. Copy a definition into managedAgentsCreateEnvironment, bind any organization-specific fields in the form, and verify its setup before starting a session.
- [List supported sandbox providers](https://docs.labelbox.com/api-reference/environments/list-supported-sandbox-providers.md): Returns the sandbox runtimes this deployment can run environments on, with the display name, description, whether the provider is the default, and its required credential name if any. This is static service capability, not organization data, so every caller sees the same list.
- [List agents](https://docs.labelbox.com/api-reference/agents/list-agents.md): Returns every agent in the calling organization, each resolved to its latest immutable version and hydrated with current tag definitions in one batch. tag_ids is a comma-separated AND filter: every returned agent carries every requested tag. Soft-deleted agents are omitted, and the response is not p…
- [Create an agent and immutable version](https://docs.labelbox.com/api-reference/agents/create-an-agent-and-immutable-version.md)
- [Get one agent](https://docs.labelbox.com/api-reference/agents/get-one-agent.md): Returns one agent resolved to its latest immutable version, including its system prompt and default credential grants. A soft-deleted or unknown id is a 404.
- [Soft delete agent](https://docs.labelbox.com/api-reference/agents/soft-delete-agent.md): Soft deletes the agent so it no longer appears in reads or starts new sessions. Its version history and existing sessions are retained. A repeated delete returns 404 because the deleted agent is no longer readable. The delete cannot be undone through this API.
- [List agents](https://docs.labelbox.com/api-reference/agents/list-agents-1.md): Returns a page of live agents in the calling organization, newest first. Repeat tagIdsAll (at most 32 distinct IDs) to require every named tag. Follow nextCursor until null; pages may change as agents or tags are edited.
- [Create an agent and immutable version](https://docs.labelbox.com/api-reference/agents/create-an-agent-and-immutable-version-1.md)
- [Get one agent](https://docs.labelbox.com/api-reference/agents/get-one-agent-1.md): Returns one agent resolved to its latest immutable version, including its system prompt, toolsets, and default credential grants. A soft-deleted or unknown id is a 404.
- [Soft delete agent](https://docs.labelbox.com/api-reference/agents/soft-delete-agent-1.md): Soft deletes the agent so it no longer appears in reads or starts new sessions. Its version history and existing sessions are retained. A repeated delete returns 404 because the deleted agent is no longer readable. The delete cannot be undone through this API.
- [Open the analyst for an agent's sessions](https://docs.labelbox.com/api-reference/agents/open-the-analyst-for-an-agents-sessions.md): Returns the caller's agent analyst, starting one if they have none (created is true when this call started it): a read-only assistant session that answers questions across every session the agent ran -- volume, outcomes, failures, spend, which session produced which file -- and can read any one of t…
- [List an agent's immutable version history](https://docs.labelbox.com/api-reference/agents/list-an-agents-immutable-version-history.md): Returns all immutable agent versions, newest to oldest, projected through the current public contract. Prompt, model, and supported capabilities remain visible; inert legacy tool declarations remain stored but are omitted from these responses. The response is not paginated.
- [Create a new immutable agent version](https://docs.labelbox.com/api-reference/agents/create-a-new-immutable-agent-version.md): Creates a new immutable agent version from a full definition and moves the agent's latest pointer to it, in one atomic operation. base_agent_version_id must be the agent's current latest_agent_version_id or the request is rejected with 409 revision_conflict, so the caller can re-read and retry rathe…
- [Get one immutable agent version](https://docs.labelbox.com/api-reference/agents/get-one-immutable-agent-version.md): Returns one immutable agent version by id. The version must belong to the agent in the path; a mismatch is a 404 rather than a cross-agent read.
- [List an agent's immutable version history](https://docs.labelbox.com/api-reference/agents/list-an-agents-immutable-version-history-1.md): Returns a page of an agent's immutable versions, newest first. Follow nextCursor until null. A newly published version can appear ahead of a cursor and will be included on a fresh listing.
- [Create a new immutable agent version](https://docs.labelbox.com/api-reference/agents/create-a-new-immutable-agent-version-1.md): Creates an immutable agent version from a full definition and atomically advances the agent's latest pointer. baseAgentVersionId must equal the current latestAgentVersionId; otherwise the request returns 409 revision_conflict without creating a version. Omitted definition fields are cleared, not inh…
- [Get one immutable agent version](https://docs.labelbox.com/api-reference/agents/get-one-immutable-agent-version-1.md): Returns one immutable agent version by id. The version must belong to the agent in the path; a mismatch is a 404 rather than a cross-agent read.
- [List static agent templates](https://docs.labelbox.com/api-reference/agents/list-static-agent-templates.md): Returns the startup-validated static catalog of agent definitions.
Measured from the saved file
Linked document
UTF-8 text size
91.5 KB93650 bytes
Token count
19930o200k_base encoding
Markdown links
379379 distinct URLs
Fenced code blocks
0388 lines in the file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Project H1
Labelbox
Opening blockquote
Documentation for Recursion Managed Agents and the Labelbox platform.
Context architecture
How the content is divided
2 H2 sections organize 379 parsed Markdown links. 376 links point to .md or .markdown paths; 1 link occurrences use another hostname. Linked destinations have not been recursively validated.
H2 section
Links
UTF-8 bytes
Tokens
OpenAPI SpecsLine 382
1
39
13
OptionalLine 386 · Optional
1
70
19
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Code, installation and API examples
Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
5 links have authentication-related labels
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
The Optional section
1 H2 section named “Optional” contain 1 parsed links. 378 links sit outside those sections. That puts 0.3% of the file’s parsed links under Optional.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP references and configuration text
MCP-related text was detected in the captured file. 5 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
Whole-file size not established by the bounded response
Token count
Not measured for the whole file
Retrieval scope
Bounded prefix inspected; the whole body was not downloaded
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
What can be said about freshness
This capture establishes a baseline. Update frequency cannot be determined from one observation.
Linked release and migration material
3 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.