# Labelbox: Recursion API reference > Documentation for Recursion Managed Agents and the Labelbox platform. ## API reference ### API reference - [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. ### Endpoints #### Environments - [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). Recognized secret formats are redacted before the log is stor… - [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 environments](https://docs.labelbox.com/api-reference/environments/list-environments-1.md): Returns a page of environments in the calling organization, newest first. Soft-deleted environments are omitted. Follow nextCursor with the cursor query parameter until it is null to retrieve every environment. - [Create environment](https://docs.labelbox.com/api-reference/environments/create-environment-1.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 (networkPolicy: {}). Nothing is pr… - [Get environment](https://docs.labelbox.com/api-reference/environments/get-environment-1.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-1.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-1.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 networkPolicy: {"version":"v1","rules":[]} for deny-a… - [List setup runs](https://docs.labelbox.com/api-reference/environments/list-setup-runs-1.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 setupVerification verdict; a session run records legacy in-session setup and can be read here by its sess… - [Run and verify the environment's setup script](https://docs.labelbox.com/api-reference/environments/run-and-verify-the-environments-setup-script-1.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-1.md): Returns one setup run. With waitSeconds the call blocks until the run reaches a terminal status or the wait elapses, so a poll loop needs no client-side timer. nextAction 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-1.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). Recognized secret formats are redacted before the log is stor… - [Cancel a setup run](https://docs.labelbox.com/api-reference/environments/cancel-a-setup-run-1.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 portable environment templates](https://docs.labelbox.com/api-reference/environments/list-portable-environment-templates-1.md): Returns reviewed, versioned environment starting points. Copy a definition into managedAgentsCreateEnvironmentV2, 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 supported sandbox providers](https://docs.labelbox.com/api-reference/environments/list-supported-sandbox-providers-1.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. #### Agents - [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, 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.md): Soft deletes the agent so it no longer appears in reads and cannot start new sessions. Its version history and the sessions that used it are retained, and the delete cannot be undone through this API. A platform-managed outcome evaluator cannot be deleted (409 managed_agent_immutable). An agent refe… - [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, namePrefix to match the start of the name case-insensitively, and agentId (at most 100 distinct IDs) to list only those agents; filters combine with AND. Fo… - [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 and cannot start new sessions. Its version history and the sessions that used it are retained, and the delete cannot be undone through this API. A platform-managed outcome evaluator cannot be deleted (409 managed_agent_immutable). An agent refe… - [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 if they have one; send a question to start one (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 re… - [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. Copy one definition into managedAgentsCreateAgent to create an ordinary managed agent; listing templates has no side effects and performs no live model validation. - [List static agent templates](https://docs.labelbox.com/api-reference/agents/list-static-agent-templates-1.md): Returns the startup-validated static catalog of agent definitions. Copy one definition into managedAgentsCreateAgentV2 to create an ordinary managed agent; listing templates has no side effects and performs no live model validation. The startup-validated embedded catalog has a fixed, bounded number… - [Search an agent's file history](https://docs.labelbox.com/api-reference/agents/search-an-agents-file-history.md): Searches the session outputs this agent's sessions saved, including outputs its subagents and teammates saved, which are what its sessions read with search_agent_files when the agent has fileHistoryEnabled. Structured and metadata conditions are exact and apply before paging; text searches the conte… - [Get one file of an agent's file history](https://docs.labelbox.com/api-reference/agents/get-one-file-of-an-agents-file-history.md): Returns one session output from this agent's file history. A file of another agent, of another organization, or outside the history answers 404. - [Get what an agent's skills cost the prompt](https://docs.labelbox.com/api-reference/agents/get-what-an-agents-skills-cost-the-prompt.md): Reports how the agent's saved skills will appear in the prompt of its next session: the skills in the order the model reads them, which of them the model's budget leaves room to describe, and how many characters of that budget they use. It answers for the agent's latest version, with the model and b… - [Preview importing an agent export file](https://docs.labelbox.com/api-reference/agents/preview-importing-an-agent-export-file.md): Resolves an agent export file against the calling organization exactly as managedAgentsImportAgentV2 would, and writes nothing. Each vault, integration connection, team member and skill the file names is matched by name; items lists every one with a choice to make, with its candidates here. A vault… - [Import an agent export file](https://docs.labelbox.com/api-reference/agents/import-an-agent-export-file.md): Creates the agent an export file describes in the calling organization, resolved as managedAgentsPreviewAgentImportV2 resolves it with the same choices. The catalog skills the file carries, bundled files included, the agent with its first version, and its memory settings are created in one transacti… #### Tags - [Replace an agent's complete tag set](https://docs.labelbox.com/api-reference/tags/replace-an-agents-complete-tag-set.md): Atomically replaces the agent's classifications with tag_ids and returns the resulting full definitions. Every id must be live in the calling organization; [] clears the set. This never changes agent.updated_at or mints an AgentVersion. - [Apply one tag to an agent](https://docs.labelbox.com/api-reference/tags/apply-one-tag-to-an-agent.md): Idempotently applies one live organization tag and returns the agent's resulting full tag definitions. The classification write does not update the agent or mint a version. - [Remove one tag from an agent](https://docs.labelbox.com/api-reference/tags/remove-one-tag-from-an-agent.md): Removes the application and returns 204. Retrying after the relationship is already absent also returns 204; the agent and tag must still exist in the calling organization. - [List organization tags](https://docs.labelbox.com/api-reference/tags/list-organization-tags.md): Returns every live tag definition in the calling organization. The list is bounded by the 200-tag organization quota and is not paginated. - [Create an organization tag](https://docs.labelbox.com/api-reference/tags/create-an-organization-tag.md): Creates a mutable classification definition in the calling organization. Labels are trimmed and case-insensitively unique among live tags; deleting a tag releases its label. The 201 response includes the created tag and its Location. An optional Idempotency-Key makes an ambiguous retry replay that o… - [Get one organization tag](https://docs.labelbox.com/api-reference/tags/get-one-organization-tag.md): Returns one live tag definition. Unknown, deleted, and cross-organization ids all return the same 404. - [Soft delete a tag](https://docs.labelbox.com/api-reference/tags/soft-delete-a-tag.md): Soft deletes the bounded definition row. Live-definition joins immediately hide every application without rewriting them; agents and immutable versions are untouched, and the label may be reused. A repeated delete of an existing tombstone in the same organization returns 204 again; unknown and cross… - [Update a tag definition](https://docs.labelbox.com/api-reference/tags/update-a-tag-definition.md): Atomically merges one or more supplied fields into a live tag definition and returns the stored tag. Omitted fields keep their values; null and an empty object are rejected. This does not change an application, update an agent, mint an AgentVersion, or affect a running session. Concurrent updates se… #### Skills - [List skills](https://docs.labelbox.com/api-reference/skills/list-skills.md): Returns one page of the calling organization's skills, newest first, following next_page_token until it is absent to read the whole catalog. Soft-deleted skills are omitted. Instructions are not included: attach a skill to an agent and the model receives its name in every turn, its description while… - [Create a skill from a document](https://docs.labelbox.com/api-reference/skills/create-a-skill-from-a-document.md): Creates a skill from a SKILL.md document and returns it. The document's frontmatter supplies the skill's name and description, which are validated against the Agent Skills standard: the name must be lowercase letters, digits, and single hyphens, and a description is required because it is the only s… - [Publish a skill from a bundle upload](https://docs.labelbox.com/api-reference/skills/publish-a-skill-from-a-bundle-upload.md): Creates a skill from a zipped skill directory and returns it. Send the archive as the bundle part of a multipart/form-data body. Its SKILL.md supplies the skill's document, name, and description; its scripts/ and references/ are mounted into the sandbox for sessions that attach it. To create a docum… - [Preview what a skill set costs the prompt](https://docs.labelbox.com/api-reference/skills/preview-what-a-skill-set-costs-the-prompt.md): Reports how a proposed skills list would appear in an agent's prompt, without saving anything. The list is resolved the way a session start resolves it: group attachments expand to their skills, catalog references are read, and skills that share a name collapse to one. The response lists the resulti… - [Get one skill](https://docs.labelbox.com/api-reference/skills/get-one-skill.md): Returns one skill's catalog entry, including the id of its latest version. A soft-deleted or unknown id is a 404. - [Soft delete skill](https://docs.labelbox.com/api-reference/skills/soft-delete-skill.md): Soft deletes the skill so it no longer appears in reads and cannot be resolved into new sessions. Agents that reference it keep their configuration; their next session reports the skill as unavailable and runs without it rather than failing to start. - [Refile a skill into a catalog group](https://docs.labelbox.com/api-reference/skills/refile-a-skill-into-a-catalog-group.md): Moves a skill between catalog groups, or out of one, and returns the skill. Filing is not authoring: this mints no version and leaves the skill's document, title, metadata and bundled files exactly as they are, because advancing latest_skill_version_id for a move would make every agent following thi… - [List a skill's immutable version history](https://docs.labelbox.com/api-reference/skills/list-a-skills-immutable-version-history.md): Returns the skill's full immutable version history, newest first, so a caller can see exactly which instructions a past session ran under. The response is not paginated and omits instructions; read one version to get them. - [Publish a skill version from a document](https://docs.labelbox.com/api-reference/skills/publish-a-skill-version-from-a-document.md): Mints a new immutable version from a SKILL.md document and returns it, because an author who just published needs the version id to pin an agent to it. Sessions already running keep the version they froze. base_skill_version_id must be the skill's current latest_skill_version_id or the request is re… - [Publish a skill version from a bundle upload](https://docs.labelbox.com/api-reference/skills/publish-a-skill-version-from-a-bundle-upload.md): Mints a new immutable version from a zipped skill directory and returns it. Send the archive as the bundle part of a multipart/form-data body. Sessions already running keep the version they froze. base_skill_version_id must be the skill's current latest_skill_version_id or the request is rejected wi… - [Get one immutable skill version](https://docs.labelbox.com/api-reference/skills/get-one-immutable-skill-version.md): Returns one immutable skill version by id, including its full instructions. The version must belong to the skill in the path; a mismatch is a 404 rather than a cross-skill read. - [Download a skill version's bundle](https://docs.labelbox.com/api-reference/skills/download-a-skill-versions-bundle.md): Returns the version's canonical archive as a gzipped tarball: exactly the bytes a session mounts, with executable bits already assigned by this platform. Repacking is deterministic, so re-downloading a version always yields the same digest. A version with no bundled files answers 404; read the versi… - [List skill groups](https://docs.labelbox.com/api-reference/skills/list-skill-groups.md): Returns one page of the caller organization's skill groups, newest first, each with how many live skills are filed under it. Follow next_page_token to read the rest. Groups are a catalog-side folder: they are never disclosed to the model, and they do not scope skill names. - [Create a skill group](https://docs.labelbox.com/api-reference/skills/create-a-skill-group.md): Creates a group you can file skills under and attach to an agent as one entry. An agent attached to a group picks up skills added to it later, without an agent update. - [Get one skill group](https://docs.labelbox.com/api-reference/skills/get-one-skill-group.md): Returns one group and how many live skills it holds. - [Delete a skill group](https://docs.labelbox.com/api-reference/skills/delete-a-skill-group.md): Deletes the group and leaves every skill in it in the catalog with its historical group id. Agents attached to the group report it as unavailable at session start and run without its skills, rather than failing to start. - [Update a skill group](https://docs.labelbox.com/api-reference/skills/update-a-skill-group.md): Renames a group or changes its title, description, or metadata. An omitted field is left unchanged. Renaming is safe at any time: no agent prompt mentions the group. - [List the skills in a group](https://docs.labelbox.com/api-reference/skills/list-the-skills-in-a-group.md): Returns one page of the live skills filed under the group, in the order a group attachment expands them at session start. That order matters: it decides which skill's description is dropped first if the disclosure budget is exceeded. Follow next_page_token to read the whole group, which is what an a… #### Sessions - [List sessions](https://docs.labelbox.com/api-reference/sessions/list-sessions.md): Returns unclassified public sessions in the calling organization, most recently updated first unless sortBy and sortDirection select another order, filtered by any combination of status, kind, agent_id, current agent tag_ids, and external source. kind accepts a comma-separated list, while tag_ids us… - [Start a managed session](https://docs.labelbox.com/api-reference/sessions/start-a-managed-session.md): Starts a managed agent session and returns 202 with its session_id and status_path; the agent runs asynchronously, so poll managedAgentsGetSession or subscribe with managedAgentsStreamSessionEvents to follow it. Sandbox compute is provisioned here, which is where a session begins costing money. Requ… - [Snapshot every root session created in a window](https://docs.labelbox.com/api-reference/sessions/snapshot-every-root-session-created-in-a-window.md): Returns a compact point-in-time projection of live unclassified public root sessions created at or after since (at most 30 days ago), newest first. Draw the snapshot whole, then keep it current with managedAgentsStreamSessionGestalt from as_of. Classified roots are omitted. Windows with more than 50… - [Stream changes to the sessions gestalt as Server-Sent Events](https://docs.labelbox.com/api-reference/sessions/stream-changes-to-the-sessions-gestalt-as-server-sent-events.md): Streams changes to unclassified public root sessions in the requested window as gestalt.change events whose data is a SessionGestaltChange and whose id is the frame's read timestamp. Resume from a snapshot's as_of via after, or from the last frame via after or Last-Event-ID. A gestalt.reset event me… - [Roll up token and cost totals for a batch of sessions](https://docs.labelbox.com/api-reference/sessions/roll-up-token-and-cost-totals-for-a-batch-of-sessions.md): Rolls up token counts and cost for the sessions named in session_ids and returns one row per session. Ids that do not exist in this organization are omitted rather than erroring, so compare the row count against what you asked for. The request is rejected if it names more ids than the per-request ma… - [List the caller-defined metadata keys sessions carry](https://docs.labelbox.com/api-reference/sessions/list-the-caller-defined-metadata-keys-sessions-carry.md): Returns the distinct caller-defined metadata keys across every session the caller may list, sorted, so a client can offer them as filter choices without knowing them in advance. Sessions the caller's access policy hides contribute nothing. Capped at 200 keys; truncated reports when the cap was hit.… - [List the values one caller-defined metadata key takes](https://docs.labelbox.com/api-reference/sessions/list-the-values-one-caller-defined-metadata-key-takes.md): Returns the distinct values of one caller-defined metadata key across every session the caller may list, sorted and optionally narrowed to a case-sensitive prefix with q, for a typeahead over managedAgentsListSessions metadata filters. Sessions the caller's access policy hides contribute nothing. A… - [Get session](https://docs.labelbox.com/api-reference/sessions/get-session.md): Returns one session with its status, agent and environment binding, and timing. A poller should stop on completed, failed, or cancelled, and also when the session needs you: awaiting_human, or execution_state idle with a stop_reason such as requires_action or budget_reached. A later message can resu… - [Soft delete a session subtree (events retained)](https://docs.labelbox.com/api-reference/sessions/soft-delete-a-session-subtree-events-retained.md): Soft deletes the session subtree: it is stopped if still running, sandbox teardown is requested, and its rows disappear from reads. An active Evaluation or one with unfinished clone cleanup returns retryable 409 evaluation_deletion_pending and remains visible; retry when cleanup finishes. A pending… - [Open the session analyst for a session](https://docs.labelbox.com/api-reference/sessions/open-the-session-analyst-for-a-session.md): Returns the caller's session analyst for the tree containing this session if they have one; send a question to start one (201 when this call started it, 200 otherwise): a read-only assistant session that answers questions about the target -- what the agents were asked to do, what they did, which too… - [Open the organization assistant](https://docs.labelbox.com/api-reference/sessions/open-the-organization-assistant.md): Returns the caller's organization assistant if they have one; send a question or a template to start one (created is true when this call started it): an assistant session that knows the platform's capabilities and the organization's agents, environments, skills and connections, and helps design, set… - [Decide on an assistant interaction](https://docs.labelbox.com/api-reference/sessions/decide-on-an-assistant-interaction.md): Records the caller's decision on the pending interaction an assistant put in front of them -- answers to its questions, acceptance of a blueprint, approval of a plan, a revision request, or dismissal -- and delivers it to the assistant as the caller's next message. Only the person who opened the ass… - [Get the team board](https://docs.labelbox.com/api-reference/sessions/get-the-team-board.md): Returns the shared task board of a session whose roster runs as a team: every task with its status, owner, notes, and outcome; the notices and the decision; and the members named the way the board names them. Any session id in the tree is accepted; the read resolves to its root. A session whose tree… - [Read sandbox CPU, memory, and GPU usage for a session tree](https://docs.labelbox.com/api-reference/sessions/read-sandbox-cpu-memory-and-gpu-usage-for-a-session-tree.md): Returns the tree's sandbox attachments and one page of per-minute resource usage buckets for them, ordered by attachment then time. Each bucket carries the minute's average and peak; resolution=raw adds the individual samples as parallel arrays indexed by offsets_ms. A tree whose compute was release… - [Get root timeline events](https://docs.labelbox.com/api-reference/sessions/get-root-timeline-events.md): Returns one page of the root timeline's events in chronological order, plus next_page_token to continue from. A page can come back shorter than limit because an aggregate serialized-byte budget applies as well as the count, so treat an empty page with no token as the end rather than inferring the en… - [Append user/system events to a session](https://docs.labelbox.com/api-reference/sessions/append-usersystem-events-to-a-session.md): The canonical session message operation for Send and Interrupt & send. Set interrupt=true to stop the current operation and read the replacement immediately while delegated work continues; the session handles coordination. Omit or use false for ordinary Send. Interrupting also requires update capabi… - [Get root session tree and timeline](https://docs.labelbox.com/api-reference/sessions/get-root-session-tree-and-timeline.md): Returns every session in the root session's tree, its threads, and the first bounded page of the merged chronological event log. When next_event_id is set, more events remain and should be fetched with managedAgentsListSessionEvents rather than by re-reading the tree. Any session id in the tree is a… - [List session threads](https://docs.labelbox.com/api-reference/sessions/list-session-threads.md): Returns every thread in the session's tree, including one synthesized thread per session that has no explicit thread rows, sorted by thread path. Any session id in the tree is accepted; the read resolves to its root. - [Get session thread](https://docs.labelbox.com/api-reference/sessions/get-session-thread.md): Returns one thread from the session's tree. The thread must belong to the tree rooted at the session in the path; anything else is a 404 rather than a cross-tree read. - [Stream session events as Server-Sent Events](https://docs.labelbox.com/api-reference/sessions/stream-session-events-as-server-sent-events.md): Streams the session's events as Server-Sent Events, resuming from after_event_id or the Last-Event-ID header when either is present. The query cursor takes precedence. Clients that set after_event_id must replace it with their latest event id, or remove it to use Last-Event-ID, on every reconnect; r… - [Stream one authenticated complete event content document](https://docs.labelbox.com/api-reference/sessions/stream-one-authenticated-complete-event-content-document.md): Returns the complete stored content document for one event as application/json when its payload was externalized instead of inlined in the timeline. The event must belong to the session in the path. - [Get one private session image](https://docs.labelbox.com/api-reference/sessions/get-one-private-session-image.md) - [Hard stop a session immediately](https://docs.labelbox.com/api-reference/sessions/hard-stop-a-session-immediately.md): Stops the session immediately and schedules durable sandbox teardown. The response confirms the session stopped; sandbox cleanup may continue asynchronously and is retried. An active Evaluation or one with unfinished clone cleanup returns retryable 409 evaluation_cancellation_pending before the sess… - [Interrupt a running session](https://docs.labelbox.com/api-reference/sessions/interrupt-a-running-session.md): Pauses ongoing work and delegated agents without supplying a replacement instruction. Queued messages stay durable and do not restart the session. Idle sessions are paused as well. Only an explicit Send or managedAgentsResumeSession continues work; helper reports, board updates and timers do not. Th… - [Resume a paused session](https://docs.labelbox.com/api-reference/sessions/resume-a-paused-session.md): Continues a paused or naturally finished session without requiring message text. Accepted queued inputs are read in order. The continuation is subject to the same credit, budget and start authorization as Send. An optional Idempotency-Key replays the first response instead of accepting another conti… - [List input a session has accepted but not read](https://docs.labelbox.com/api-reference/sessions/list-input-a-session-has-accepted-but-not-read.md): Returns the messages waiting for a busy session, in acceptance order. A message sent while the agent is mid-turn is durable immediately but is not part of the transcript until the next turn boundary reads it, so it appears here and not in the events listing. Each entry's input_id becomes the event i… - [List a session's outcomes and grading history](https://docs.labelbox.com/api-reference/sessions/list-a-sessions-outcomes-and-grading-history.md): Returns the session's outcomes and their grading history, so a caller can see what "done" was defined as and how each attempt was scored. - [Define what done looks like for a session](https://docs.labelbox.com/api-reference/sessions/define-what-done-looks-like-for-a-session.md): Defines what done looks like for an existing session and returns the stored outcome. Outcomes chain rather than run concurrently: the request is rejected while the session still has a non-terminal outcome, so define the next one only after the previous is graded. - [Get the agent version a session runs](https://docs.labelbox.com/api-reference/sessions/get-the-agent-version-a-session-runs.md): Returns the version of its agent a root session runs now, the version it is set to run, whether a move is pending or was refused, the agent's latest version, and how far each open thread of the session tree has followed. The state changes as the session works, so read it again rather than keeping a… - [Move a session to another version of its agent](https://docs.labelbox.com/api-reference/sessions/move-a-session-to-another-version-of-its-agent.md): Sets the version of its agent a root session runs. A move brings the session's instructions, model and inference settings, tools, MCP servers, skills, integrations, credentials and roster to the new version, tells the agent what changed, and moves an outcome the session inherited from the agent's de… - [Move an agent's live sessions to its latest version](https://docs.labelbox.com/api-reference/sessions/move-an-agents-live-sessions-to-its-latest-version.md): Starts a background upgrade that asks every live root session of the agent the caller may change -- active, queued, idle or awaiting a person -- to move to the agent's latest version, pinned when the request is accepted. It returns 202 at once with the upgrade; follow it with managedAgentsGetAgentSe… - [Get an agent's session upgrade](https://docs.labelbox.com/api-reference/sessions/get-an-agents-session-upgrade.md): Returns the agent's newest session upgrade: its state, the counts of sessions it asked to move, found current, skipped or could not ask, and a sample of the sessions it skipped. Read it again rather than keeping a copy while state is running. 404 when the agent is not one of the caller's organizatio… - [Stop an agent's running session upgrade](https://docs.labelbox.com/api-reference/sessions/stop-an-agents-running-session-upgrade.md): Stops the agent's running session upgrade before it asks any further session. Sessions it already asked keep their pending move; move any of them back with managedAgentsReplaceSessionAgentVersion. The response is the upgrade as managedAgentsGetAgentSessionUpgrade returns it; state becomes cancelled… - [Set a session's budget](https://docs.labelbox.com/api-reference/sessions/set-a-sessions-budget.md): Sets a root session tree's budget and returns it. The budget must be more than the tree has already spent and no more than the agent's multiagent.limits.max_tree_cost_usd; a budget that reached that cap cannot be raised, and a thread or grader returns 400 naming its root. Work paused at the old budg… - [Remove a session's budget](https://docs.labelbox.com/api-reference/sessions/remove-a-sessions-budget.md): Removes a root session tree's budget, and continues work paused at it the same way as managedAgentsReplaceSessionBudget. A session whose agent declares multiagent.limits.max_tree_cost_usd keeps a budget and returns 400. Removing a budget the session no longer has succeeds. Returns 400 where session… #### Memory - [List memory status for every agent](https://docs.labelbox.com/api-reference/memory/list-memory-status-for-every-agent.md): Returns each customer agent's current memory summary, including agents that have not learned yet. Each status is derived from that agent's latest run. - [Get an agent's memory summary](https://docs.labelbox.com/api-reference/memory/get-an-agents-memory-summary.md): Returns the current permanent collection, its effective model, and automatic learning progress without starting work. - [Search an agent's current memories](https://docs.labelbox.com/api-reference/memory/search-an-agents-current-memories.md): Lists current memories as a flat, searchable keyset page, with topics from the entire collection. Retired memories are available through detail and history reads. - [Search an agent's current memories](https://docs.labelbox.com/api-reference/memory/search-an-agents-current-memories-1.md): Lists current memories as a flat, searchable keyset page, with topics from the entire collection. Retired memories are available through detail and history reads. - [Get an agent's memory settings](https://docs.labelbox.com/api-reference/memory/get-an-agents-memory-settings.md): Returns whether memory is enabled, its model and standing instructions with a strong revision ETag. New agents start with memory enabled. If-None-Match may answer 304. - [Update an agent's memory settings](https://docs.labelbox.com/api-reference/memory/update-an-agents-memory-settings.md): Changes subsequent memory jobs and session attachments. Disabling stops new digests and detaches the learned store from new sessions. Omitted fields remain unchanged. Send the latest settings ETag in If-Match; a stale editor receives 412. - [List an agent's memory runs](https://docs.labelbox.com/api-reference/memory/list-an-agents-memory-runs.md): Returns automatic memory updates and checks, newest first, including unchanged checks and failed attempts. - [Get one memory job run](https://docs.labelbox.com/api-reference/memory/get-one-memory-job-run.md): Returns one run: its trigger, status, the sessions whose reports it read, the collection it updated, and the id of the session that ran it. Read what the run spent from that session's costs, which settle after the session ends. - [Read one memory](https://docs.labelbox.com/api-reference/memory/read-one-memory.md): Returns one learned memory, including its full content and content hash. - [Delete a memory](https://docs.labelbox.com/api-reference/memory/delete-a-memory.md): Removes one learned memory from future recall and records the deletion as a version. The path becomes available for reuse. - [List memory versions](https://docs.labelbox.com/api-reference/memory/list-memory-versions.md): Returns a store's change history, newest first, optionally filtered to one memory. Versions belong to the store rather than the memory, so the trail survives the memory being deleted. Retained 30 days, except that the recent versions of a live memory are kept regardless of age. - [Get one memory version](https://docs.labelbox.com/api-reference/memory/get-one-memory-version.md): Returns one version including the content as it stood, unless the version has been redacted. - [List memory store revisions](https://docs.labelbox.com/api-reference/memory/list-memory-store-revisions.md): Returns the revisions a store committed, newest first, each with when it committed, who wrote it and the memory versions it committed. createdAtGte and createdAtLt bound the commit time. Changes made before revisions were recorded are not listed. #### Evaluations - [List immutable evaluation verdicts](https://docs.labelbox.com/api-reference/evaluations/list-immutable-evaluation-verdicts.md): Returns an organization-scoped page of immutable evaluator verdicts ordered by created_at descending, then evaluation_id ascending. Optional filters are combined with AND; createdAtGte and createdAtLt select the half-open interval [createdAtGte, createdAtLt). Retained same-organization evaluation hi… - [Start one evaluation session per target](https://docs.labelbox.com/api-reference/evaluations/start-one-evaluation-session-per-target.md): Resolves a bounded target set, then starts one public evaluation root session per target. All items share an evaluation_batch_id. Each item reports its own session id or start error because a later target can fail after earlier sessions commit. A stopped target workspace is cloned and bound to an un… - [List evaluation runs](https://docs.labelbox.com/api-reference/evaluations/list-evaluation-runs.md): Returns evaluation runs newest first unless sortBy and sortDirection select another order, including active runs and failed runs with no verdicts. Each run's target and verdict counts are read at one consistent point in time. #### Vaults - [List credential vaults](https://docs.labelbox.com/api-reference/vaults/list-credential-vaults.md): Returns every credential vault in the calling organization. A vault is a grantable bundle of credential references; it holds no secret values, so this read is safe for any caller with API access. - [Create a credential vault](https://docs.labelbox.com/api-reference/vaults/create-a-credential-vault.md): Creates an empty credential vault and returns it with its generated vault_id. Vaults are the unit a session or agent is granted, so create one per trust boundary and add credential references to it afterwards. An optional Idempotency-Key makes ambiguous retries safe: the durable receipt key determin… - [List credential vaults](https://docs.labelbox.com/api-reference/vaults/list-credential-vaults-1.md): Returns every credential vault in the calling organization. A vault is a grantable bundle of credential references; it holds no secret values, so this read is safe for any caller with API access. - [Get a credential vault](https://docs.labelbox.com/api-reference/vaults/get-a-credential-vault.md): Returns one vault with its display name and metadata. Its credential references are listed separately by managedAgentsListVaultCredentials. - [Soft delete a vault and hide its credentials](https://docs.labelbox.com/api-reference/vaults/soft-delete-a-vault-and-hide-its-credentials.md): Soft deletes the vault and hides the credential references inside it, so neither can be granted to a new session. Running sessions are not stopped, but from their next turn the vault's MCP tokens no longer reach them; a sandbox that is already running keeps the environment variables it started with.… - [Rename a vault or replace its metadata](https://docs.labelbox.com/api-reference/vaults/rename-a-vault-or-replace-its-metadata.md): Renames a vault or replaces its metadata and returns the stored vault; omitted fields keep their current values. This never changes which credentials the vault contains. Do not automatically retry an ambiguous transport failure: re-read the vault first, because this operation does not replay a prior… - [Get a credential vault](https://docs.labelbox.com/api-reference/vaults/get-a-credential-vault-1.md): Returns one vault with its display name and metadata. Its credential references are listed separately by managedAgentsListVaultCredentials. - [List a vault's credential references](https://docs.labelbox.com/api-reference/vaults/list-a-vaults-credential-references.md): Returns the credential references in one vault, each with its type. Only references are returned; the secret values themselves are never exposed by this API. - [Register a credential reference in a vault](https://docs.labelbox.com/api-reference/vaults/register-a-credential-reference-in-a-vault.md): Registers one credential in a vault and returns the stored reference. Supply exactly one of secret_value (encrypted under the organization's key and stored as ciphertext) or secret_ref (material you already stored yourself) for secret-backed kinds. Integration grants carry neither; they reference a… - [List a vault's credential references](https://docs.labelbox.com/api-reference/vaults/list-a-vaults-credential-references-1.md): Returns the credential references in one vault, each with its type. Only references are returned; the secret values themselves are never exposed by this API. The result is paginated with an opaque cursor and is not cached. - [Get one credential reference](https://docs.labelbox.com/api-reference/vaults/get-one-credential-reference.md): Returns one credential reference with its type. The credential must belong to the vault in the path, and the secret value is never included. - [Soft delete a credential reference](https://docs.labelbox.com/api-reference/vaults/soft-delete-a-credential-reference.md): Soft deletes one credential reference so it can no longer be granted to a new session. Running sessions are not stopped, but from their next turn an MCP token it held no longer reaches them; a sandbox that is already running keeps the environment variables it started with. The delete cannot be undon… - [Rename a credential or rotate its reference](https://docs.labelbox.com/api-reference/vaults/rename-a-credential-or-rotate-its-reference.md): Renames a credential or rotates the secret it points at, and returns the stored reference; omitted fields keep their current values. An integration credential's connection cannot be repointed, because that would silently change which account the agent acts as. - [Get one credential reference](https://docs.labelbox.com/api-reference/vaults/get-one-credential-reference-1.md): Returns one credential reference with its type. The credential must belong to the vault in the path, and the secret value is never included. - [Test an MCP server connection and list its tools](https://docs.labelbox.com/api-reference/vaults/test-an-mcp-server-connection-and-list-its-tools.md): Opens a live connection to an MCP server using exactly the credential resolution a session would use, and returns the tools it advertises. A server that cannot be reached or authenticated is still HTTP 200 with ok=false, so inspect that field rather than relying on the status code. Pass vault_ids to… #### Event Sources - [Check IMAP OAuth website sign-in availability](https://docs.labelbox.com/api-reference/event-sources/check-imap-oauth-website-sign-in-availability.md): Reports whether this deployment can seal reusable IMAP OAuth tokens. A staged API edge withholds this operation until it can also serve sign-in. - [Start website sign-in for an IMAP OAuth credential](https://docs.labelbox.com/api-reference/event-sources/start-website-sign-in-for-an-imap-oauth-credential.md): Creates a short-lived, single-use authorization state bound to this user, organization, credential, and confirmed IMAP hostname and OAuth endpoints. The user must confirm the exact authorization endpoint and token endpoint before the authorization code can be sent there. Follow the returned provider… - [Complete website sign-in for an IMAP OAuth credential](https://docs.labelbox.com/api-reference/event-sources/complete-website-sign-in-for-an-imap-oauth-credential.md): Consumes the authorization state and exchanges the provider code with PKCE. A 409 conflict means the credential changed during sign-in; start sign-in again. Client secrets and tokens stay encrypted on the organization credential and are never returned. - [List event sources](https://docs.labelbox.com/api-reference/event-sources/list-event-sources.md): Returns a bounded page of non-secret source summaries, newest first. Protocol configuration is available only on member reads. - [Create a paused event source](https://docs.labelbox.com/api-reference/event-sources/create-a-paused-event-source.md): Creates a webhook or managed IMAP source in the paused state. delivery.kind must be webhook or imap; integration sources are connection-managed. Verification or IMAP authentication credentials reference Vault and secret material is never returned. IMAP uses verified implicit TLS; after resume, its f… - [Get an event source](https://docs.labelbox.com/api-reference/event-sources/get-an-event-source.md): Returns non-secret source configuration with a strong revision ETag. If-None-Match may answer 304. - [Replace an event source configuration](https://docs.labelbox.com/api-reference/event-sources/replace-an-event-source-configuration.md): Replaces writable webhook or managed IMAP configuration while preserving lifecycle state. An IMAP server, account and mailbox cannot change under an existing checkpoint; create a new source to change mailbox identity. Its display name and authentication credential may change. Connection-managed sour… - [Delete an unused event source](https://docs.labelbox.com/api-reference/event-sources/delete-an-unused-event-source.md): Soft-deletes a webhook or managed IMAP source only when no live trigger depends on it. IMAP deletion also removes its encrypted checkpoint and pending mail; a replacement source establishes a fresh baseline. Mail in the provider inbox and the referenced Vault credential are unchanged. Connection-man… - [Get volatile event-source status](https://docs.labelbox.com/api-reference/event-sources/get-volatile-event-source-status.md): Returns live trigger count and bounded last-delivery diagnostics separately from revisioned configuration. - [Pause event admission from a source](https://docs.labelbox.com/api-reference/event-sources/pause-event-admission-from-a-source.md): Stops new admissions from this source without changing dependent triggers. Requires the latest strong ETag in If-Match. - [Resume event admission from a source](https://docs.labelbox.com/api-reference/event-sources/resume-event-admission-from-a-source.md): Allows verified deliveries to reach dependent triggers again. Requires the latest strong ETag in If-Match. #### Integrations - [List the native integrations this deployment supports](https://docs.labelbox.com/api-reference/integrations/list-the-native-integrations-this-deployment-supports.md): Returns the third-party integrations this deployment supports. Providers that the deployment has not configured are listed too, with their configured state, so a caller can tell "not set up here" apart from "not offered". - [Begin authorizing a third-party account connection](https://docs.labelbox.com/api-reference/integrations/begin-authorizing-a-third-party-account-connection.md): Begins authorizing a third-party account connection and returns the provider URL to send the operator to, together with a single-use, short-lived state nonce. A caller may also continue one of the opaque provider options returned by managedAgentsCompleteIntegrationInstall. Nothing is connected until… - [Finish connecting provider accounts after the authorization redirect](https://docs.labelbox.com/api-reference/integrations/finish-connecting-provider-accounts-after-the-authorization-redirect.md): Finishes an authorization begun by managedAgentsStartIntegrationInstall. It returns either connected accounts or provider-neutral account/action options that continue through managedAgentsStartIntegrationInstall. The provider and organization come from the authenticated caller and single-use state n… - [List connected third-party accounts](https://docs.labelbox.com/api-reference/integrations/list-connected-third-party-accounts.md): Returns the organization's connected third-party accounts, each with its provider, account login, resource selection, and state. A connection holds no secret material, so nothing here needs to be redacted. - [Get one connected account](https://docs.labelbox.com/api-reference/integrations/get-one-connected-account.md): Returns one connected account. An unknown id, or one belonging to another organization, is reported as a 404. - [Disconnect an account and retire the grants that used it](https://docs.labelbox.com/api-reference/integrations/disconnect-an-account-and-retire-the-grants-that-used-it.md): Disconnects the account and retires every credential grant that referenced it, returning how many grants were revoked. Agents holding those grants lose access to the provider on their next session; existing sessions are not torn down. - [Check a connection against the provider and try minting a token](https://docs.labelbox.com/api-reference/integrations/check-a-connection-against-the-provider-and-try-minting-a-token.md): Checks a connection against the provider and tries to mint a short-lived access token, returning what the provider reported. The completed outcome and check time are retained on that connection as lastCheck, including failed checks. A suspended or revoked installation is still HTTP 200 with ok=false… - [List the repositories a connection can reach, for the grant picker](https://docs.labelbox.com/api-reference/integrations/list-the-repositories-a-connection-can-reach-for-the-grant-picker.md): Returns the repositories this connection can reach, for building a grant picker. Results are paged by the 1-based page query parameter at up to 100 repositories per page; the list comes from the provider live, so it reflects the installation's current access. - [List pull requests for a connected repository](https://docs.labelbox.com/api-reference/integrations/list-pull-requests-for-a-connected-repository.md) - [Get the connected Slack bot's bounded channel-selection catalog](https://docs.labelbox.com/api-reference/integrations/get-the-connected-slack-bots-bounded-channel-selection-catalog.md): Returns a channel-selection snapshot of at most 1,000 memberships from the connected Slack workspace, using that installation's credential, so an automation trigger can be configured by picking a channel instead of pasting its id. Only a Slack connection has channels; the list is scoped to the conne… - [Get the connected Slack workspace's bounded member catalog](https://docs.labelbox.com/api-reference/integrations/get-the-connected-slack-workspaces-bounded-member-catalog.md): Returns the people and apps of the connected Slack workspace, at most 2,000, read with that installation's own credential, so a Slack trigger's fromUserIds filter can be configured by picking authors instead of pasting their ids. Apps are listed with isBot=true; deleted accounts and the connection's… - [Get enabled Slack user groups for a trigger sender filter](https://docs.labelbox.com/api-reference/integrations/get-enabled-slack-user-groups-for-a-trigger-sender-filter.md): Lists enabled user groups from the selected Slack connection's workspace with that installation's credential. Use an S-prefixed group ID from this catalog in fromUserGroupIds or notFromUserGroupIds. The catalog is bounded at 1,000 groups; enter an ID directly when it is truncated or unavailable. The… #### Models - [List the models agents can run on](https://docs.labelbox.com/api-reference/models/list-the-models-agents-can-run-on.md): Returns the models agents can currently run on. The list is not stored per organization; it reflects service configuration, so it can change without any write from this API. #### Automations - [List canonical automations](https://docs.labelbox.com/api-reference/automations/list-canonical-automations.md): Returns a bounded page of canonical automation summaries, newest first. Prompt, run defaults, and trigger configuration are available only on member reads. - [Create a paused canonical automation](https://docs.labelbox.com/api-reference/automations/create-a-paused-canonical-automation.md): Creates a complete automation aggregate in the paused state after validating the pinned agent version, environment, and every trigger source. - [Get a canonical automation](https://docs.labelbox.com/api-reference/automations/get-a-canonical-automation.md): Returns the complete round-trippable automation aggregate with a strong revision ETag. If-None-Match may answer 304. - [Replace a canonical automation aggregate](https://docs.labelbox.com/api-reference/automations/replace-a-canonical-automation-aggregate.md): Replaces the complete writable aggregate and trigger set while preserving lifecycle state. Requires the latest strong ETag in If-Match. - [Delete a canonical automation](https://docs.labelbox.com/api-reference/automations/delete-a-canonical-automation.md): Soft-deletes the aggregate and its live triggers while preserving admitted run snapshots. Requires the latest strong ETag in If-Match. - [Get automation schedule status](https://docs.labelbox.com/api-reference/automations/get-automation-schedule-status.md): Reads synchronization and bounded live scheduler previews independently of the writable definition. Unavailable state is explicit. - [Run a canonical automation manually](https://docs.labelbox.com/api-reference/automations/run-a-canonical-automation-manually.md): Atomically freezes the automation and optional payload into one pending run. Explicit manual runs remain available while the automation is paused. Within the organization-wide receipt namespace, Idempotency-Key plus the exact HTTP method, escaped path, raw query, and raw body bytes identify the dura… - [Pause canonical automation admission](https://docs.labelbox.com/api-reference/automations/pause-canonical-automation-admission.md): Stops stored triggers from admitting new runs while leaving explicit manual runs available. Requires the latest strong ETag in If-Match. - [Resume canonical automation admission](https://docs.labelbox.com/api-reference/automations/resume-canonical-automation-admission.md): Allows enabled stored triggers to admit new runs. Refuses with 422 automation_reference_invalid when the agent, agent version, or environment is no longer live. Requires the latest strong ETag in If-Match. - [List canonical automation runs](https://docs.labelbox.com/api-reference/automations/list-canonical-automation-runs.md): Returns a consistent page of automation runs, newest first. Filters combine with AND, and a continuation cursor is bound to the organization, filters, and the moment the first page was read. - [Get one canonical automation run](https://docs.labelbox.com/api-reference/automations/get-one-canonical-automation-run.md): Returns one canonical run, including the immutable prompt and context snapshots and its current session-creation outcome. - [Test an AI filter on a sample message](https://docs.labelbox.com/api-reference/automations/test-an-ai-filter-on-a-sample-message.md): Asks the AI filter the given question about a sample message, its text and up to four screenshots, and returns the answer, every answer's probability, and whether the agent would wake. Nothing is saved and no run starts. The model call is billed to the organization like a filter evaluation on a real… - [Get an automation run's result](https://docs.labelbox.com/api-reference/automations/get-an-automation-runs-result.md): Returns where one automation run stands and, once it is finished, its verdict: passed, completed, failed, needs_attention, cancelled or error, with a reason code, the graded outcome, the structured JSON result, the agent's final message and the files its session saved. Pass waitSeconds to hold the r… #### Files - [List files](https://docs.labelbox.com/api-reference/files/list-files.md): Returns the caller organization's files, newest first, one page at a time: up to limit files (default 200, at most 1000) and a next_page_token while more follow. Deleted files are omitted; an expired file stays listed, with expires_at in the past, until it is removed after a grace period, so a clien… - [Upload a file](https://docs.labelbox.com/api-reference/files/upload-a-file.md): Stores a file the organization can attach to any number of sessions. Attaching one mounts it read-only into the session's sandbox under its files directory, and the agent knows where to find it. Send the bytes as the file part of a multipart/form-data body; the part's filename and Content-Type becom… - [Get one file](https://docs.labelbox.com/api-reference/files/get-one-file.md): Returns one file's metadata. A deleted file answers 404, as does a file belonging to another organization; an expired file still answers, with expires_at in the past, until it is removed after a grace period. - [Download a file's bytes](https://docs.labelbox.com/api-reference/files/download-a-files-bytes.md): Returns a file's bytes to its organization as application/octet-stream with a Content-Disposition naming it. The file's recorded media type remains available in its metadata but is not used as the response Content-Type. Responses include nosniff and sandbox content-security headers so uploaded HTML… ## OpenAPI Specs - [openapi](/recursion/openapi.yaml)