Repository Public
1---2title: List Sessions3url: https://platform.claude.com/docs/en/api/beta/sessions/list4---56# List Sessions78**GET** `/v1/sessions`910List Sessions1112## Query parameters1314- `agent_id: optional string`1516 Filter sessions created with this agent ID.1718- `agent_version: optional number`1920 Filter by agent version. Only applies when `agent_id` is also set.2122 format: int322324- `"created_at[gt]": optional string`2526 Return sessions created after this time (exclusive).2728 format: date-time2930- `"created_at[gte]": optional string`3132 Return sessions created at or after this time (inclusive).3334 format: date-time3536- `"created_at[lt]": optional string`3738 Return sessions created before this time (exclusive).3940 format: date-time4142- `"created_at[lte]": optional string`4344 Return sessions created at or before this time (inclusive).4546 format: date-time4748- `deployment_id: optional string`4950 Filter sessions created by this deployment ID.5152- `include_archived: optional boolean`5354 When true, includes archived sessions. Default: false (exclude archived).5556- `limit: optional number`5758 Maximum number of results to return.5960 format: int326162- `memory_store_id: optional string`6364 Filter sessions whose resources contain a `memory_store` with this memory store ID.6566- `order: optional "asc" or "desc"`6768 Sort direction for results, ordered by `created_at`. Defaults to `desc` (newest first).6970 - `"asc"`7172 - `"desc"`7374- `page: optional string`7576 Opaque pagination cursor from a previous response.7778- `statuses: optional array of "rescheduling" or "running" or "idle" or "terminated"`7980 Filter by session status. Repeat the parameter to match any of multiple statuses.8182 - `"rescheduling"`8384 - `"running"`8586 - `"idle"`8788 - `"terminated"`8990## Headers9192- `"anthropic-beta": optional array of AnthropicBeta`9394 Optional header to specify the beta version(s) you want to use.9596 - `string`9798 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`99100 - `"message-batches-2024-09-24"`101102 - `"prompt-caching-2024-07-31"`103104 - `"computer-use-2024-10-22"`105106 - `"computer-use-2025-01-24"`107108 - `"pdfs-2024-09-25"`109110 - `"token-counting-2024-11-01"`111112 - `"token-efficient-tools-2025-02-19"`113114 - `"output-128k-2025-02-19"`115116 - `"files-api-2025-04-14"`117118 - `"mcp-client-2025-04-04"`119120 - `"mcp-client-2025-11-20"`121122 - `"dev-full-thinking-2025-05-14"`123124 - `"interleaved-thinking-2025-05-14"`125126 - `"code-execution-2025-05-22"`127128 - `"extended-cache-ttl-2025-04-11"`129130 - `"context-1m-2025-08-07"`131132 - `"context-management-2025-06-27"`133134 - `"model-context-window-exceeded-2025-08-26"`135136 - `"skills-2025-10-02"`137138 - `"fast-mode-2026-02-01"`139140 - `"output-300k-2026-03-24"`141142 - `"user-profiles-2026-03-24"`143144 - `"user-profiles-2026-08-18"`145146 - `"user-profiles-2026-09-04"`147148 - `"advisor-tool-2026-03-01"`149150 - `"managed-agents-2026-04-01"`151152 - `"cache-diagnosis-2026-04-07"`153154 - `"dreaming-2026-04-21"`155156 - `"thinking-token-count-2026-05-13"`157158 - `"server-side-fallback-2026-06-01"`159160 - `"server-side-fallback-2026-07-01"`161162 - `"fallback-credit-2026-06-01"`163164 - `"fallback-credit-2026-07-01"`165166 - `"agent-memory-2026-07-22"`167168 - `"mid-conversation-tool-changes-2026-07-01"`169170 - `"compact-2026-01-12"`171172 - `"computer-use-2025-11-24"`173174 - `"mcp-tunnels-2026-06-22"`175176 - `"structured-outputs-2025-11-13"`177178 - `"task-budgets-2026-03-13"`179180 - `"thinking-display-updates-2026-08-18"`181182 - `"ce-user-management-2026-07-13"`183184 - `"mid-conversation-output-config-2026-07-01"`185186 - `"thinking-binding-controls-2026-08-01"`187188 - `"mid-conversation-system-clear-at-2026-08-21"`189190 - `"compact-2026-09-04"`191192- `"anthropic-workspace-id": optional string`193194## Returns195196- `data: optional array of BetaManagedAgentsSession`197198 List of sessions.199200 - `type: "session"`201202 - `id: string`203204 - `agent: BetaManagedAgentsSessionAgent`205206 Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time.207208 - `type: "agent"`209210 - `id: string`211212 - `description: string or null`213214 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`215216 - `type: "url"`217218 - `name: string`219220 - `url: string`221222 - `model: BetaManagedAgentsModelConfig`223224 Model identifier and configuration.225226 - `id: BetaManagedAgentsModel`227228 The model that will power your agent.229230 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.231232 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`233234 The model that will power your agent.235236 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.237238 - `"claude-fable-5-1"`239240 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows241242 - `"claude-sonnet-5"`243244 High-performance model for coding and agents245246 - `"claude-fable-5"`247248 Next generation of intelligence for the hardest knowledge work and coding problems249250 - `"claude-opus-5"`251252 Powerful intelligence for long-running agents and coding253254 - `"claude-opus-4-8"`255256 Powerful intelligence for long-running agents and coding257258 - `"claude-opus-4-7"`259260 Powerful intelligence for long-running agents and coding261262 - `"claude-opus-4-6"`263264 Powerful intelligence for long-running agents and coding265266 - `"claude-sonnet-4-6"`267268 Best combination of speed and intelligence269270 - `"claude-haiku-4-5"`271272 Fastest model with near-frontier intelligence273274 - `"claude-haiku-4-5-20251001"`275276 Fastest model with near-frontier intelligence277278 - `"claude-opus-4-5"`279280 Powerful intelligence for long-running agents and coding281282 - `"claude-opus-4-5-20251101"`283284 Powerful intelligence for long-running agents and coding285286 - `"claude-sonnet-4-5"`287288 High-performance model for agents and coding289290 - `"claude-sonnet-4-5-20250929"`291292 High-performance model for agents and coding293294 - `string`295296 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`297298 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.299300 - `BetaManagedAgentsEffortLow object`301302 Low effort. Favors latency over reasoning depth.303304 - `type: "low"`305306 - `BetaManagedAgentsEffortMedium object`307308 Medium effort. Balances latency and reasoning depth.309310 - `type: "medium"`311312 - `BetaManagedAgentsEffortHigh object`313314 High effort. Favors reasoning depth.315316 - `type: "high"`317318 - `BetaManagedAgentsEffortXhigh object`319320 Extra-high effort. Not all models accept this level.321322 - `type: "xhigh"`323324 - `BetaManagedAgentsEffortMax object`325326 Maximum effort. Favors reasoning depth over latency.327328 - `type: "max"`329330 - `inference_geo: optional string`331332 Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.333334 - `speed: optional "standard" or "fast"`335336 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time.337338 - `"standard"`339340 - `"fast"`341342 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`343344 Resolved coordinator topology with full agent definitions for each roster member.345346 - `type: "coordinator"`347348 - `agents: array of BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`349350 Full `agent` definitions the coordinator may spawn as session threads.351352 - `BetaManagedAgentsSessionThreadAgent object`353354 Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`.355356 - `type: "agent"`357358 - `id: string`359360 - `description: string or null`361362 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`363364 - `type: "url"`365366 - `name: string`367368 - `url: string`369370 - `model: BetaManagedAgentsModelConfig`371372 Model identifier and configuration.373374 - `name: string`375376 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`377378 - `BetaManagedAgentsAnthropicSkill object`379380 A resolved Anthropic-managed skill.381382 - `type: "anthropic"`383384 - `skill_id: string`385386 - `version: string`387388 - `BetaManagedAgentsCustomSkill object`389390 A resolved user-created custom skill.391392 - `type: "custom"`393394 - `skill_id: string`395396 - `version: string`397398 - `system: string or null`399400 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`401402 - `BetaManagedAgentsAgentToolset20260401 object`403404 - `type: "agent_toolset_20260401"`405406 - `configs: array of BetaManagedAgentsAgentToolConfig`407408 - `BetaManagedAgentsBashToolConfig object`409410 Configuration for the bash tool.411412 - `type: "bash"`413414 - `enabled: boolean`415416 - `name: "bash"`417418 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`419420 Permission policy for tool execution.421422 - `BetaManagedAgentsAlwaysAllowPolicy object`423424 Tool calls are automatically approved without user confirmation.425426 - `type: "always_allow"`427428 - `BetaManagedAgentsAlwaysAskPolicy object`429430 Tool calls require user confirmation before execution.431432 - `type: "always_ask"`433434 - `BetaManagedAgentsAutoPolicy object`435436 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.437438 - `type: "auto"`439440 - `BetaManagedAgentsEditToolConfig object`441442 Configuration for the edit tool.443444 - `type: "edit"`445446 - `enabled: boolean`447448 - `name: "edit"`449450 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`451452 Permission policy for tool execution.453454 - `BetaManagedAgentsAlwaysAllowPolicy object`455456 Tool calls are automatically approved without user confirmation.457458 - `BetaManagedAgentsAlwaysAskPolicy object`459460 Tool calls require user confirmation before execution.461462 - `BetaManagedAgentsAutoPolicy object`463464 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.465466 - `BetaManagedAgentsReadToolConfig object`467468 Configuration for the read tool.469470 - `type: "read"`471472 - `enabled: boolean`473474 - `name: "read"`475476 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`477478 Permission policy for tool execution.479480 - `BetaManagedAgentsAlwaysAllowPolicy object`481482 Tool calls are automatically approved without user confirmation.483484 - `BetaManagedAgentsAlwaysAskPolicy object`485486 Tool calls require user confirmation before execution.487488 - `BetaManagedAgentsAutoPolicy object`489490 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.491492 - `BetaManagedAgentsWriteToolConfig object`493494 Configuration for the write tool.495496 - `type: "write"`497498 - `enabled: boolean`499500 - `name: "write"`501502 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`503504 Permission policy for tool execution.505506 - `BetaManagedAgentsAlwaysAllowPolicy object`507508 Tool calls are automatically approved without user confirmation.509510 - `BetaManagedAgentsAlwaysAskPolicy object`511512 Tool calls require user confirmation before execution.513514 - `BetaManagedAgentsAutoPolicy object`515516 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.517518 - `BetaManagedAgentsGlobToolConfig object`519520 Configuration for the glob tool.521522 - `type: "glob"`523524 - `enabled: boolean`525526 - `name: "glob"`527528 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`529530 Permission policy for tool execution.531532 - `BetaManagedAgentsAlwaysAllowPolicy object`533534 Tool calls are automatically approved without user confirmation.535536 - `BetaManagedAgentsAlwaysAskPolicy object`537538 Tool calls require user confirmation before execution.539540 - `BetaManagedAgentsAutoPolicy object`541542 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.543544 - `BetaManagedAgentsGrepToolConfig object`545546 Configuration for the grep tool.547548 - `type: "grep"`549550 - `enabled: boolean`551552 - `name: "grep"`553554 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`555556 Permission policy for tool execution.557558 - `BetaManagedAgentsAlwaysAllowPolicy object`559560 Tool calls are automatically approved without user confirmation.561562 - `BetaManagedAgentsAlwaysAskPolicy object`563564 Tool calls require user confirmation before execution.565566 - `BetaManagedAgentsAutoPolicy object`567568 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.569570 - `BetaManagedAgentsWebFetchToolConfig object`571572 Configuration for the web_fetch tool.573574 - `type: "web_fetch"`575576 - `enabled: boolean`577578 - `name: "web_fetch"`579580 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`581582 Permission policy for tool execution.583584 - `BetaManagedAgentsAlwaysAllowPolicy object`585586 Tool calls are automatically approved without user confirmation.587588 - `BetaManagedAgentsAlwaysAskPolicy object`589590 Tool calls require user confirmation before execution.591592 - `BetaManagedAgentsAutoPolicy object`593594 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.595596 - `allowed_domains: optional array of string`597598 - `blocked_domains: optional array of string`599600 - `max_content_tokens: optional number or null`601602 format: int32603604 - `BetaManagedAgentsWebSearchToolConfig object`605606 Configuration for the web_search tool.607608 - `type: "web_search"`609610 - `enabled: boolean`611612 - `name: "web_search"`613614 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`615616 Permission policy for tool execution.617618 - `BetaManagedAgentsAlwaysAllowPolicy object`619620 Tool calls are automatically approved without user confirmation.621622 - `BetaManagedAgentsAlwaysAskPolicy object`623624 Tool calls require user confirmation before execution.625626 - `BetaManagedAgentsAutoPolicy object`627628 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.629630 - `allowed_domains: optional array of string`631632 - `blocked_domains: optional array of string`633634 - `user_location: optional BetaManagedAgentsUserLocation or null`635636 Approximate user location for search result localization.637638 - `type: "approximate"`639640 Location precision. Only "approximate" is supported.641642 - `city: optional string or null`643644 City name.645646 minLength: 1, maxLength: 255647648 - `country: optional string or null`649650 Two-letter ISO 3166-1 country code, uppercase.651652 - `region: optional string or null`653654 Region or state name.655656 minLength: 1, maxLength: 255657658 - `timezone: optional string or null`659660 IANA timezone identifier, e.g. "America/Los_Angeles".661662 minLength: 1, maxLength: 255663664 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig`665666 Resolved default configuration for agent tools.667668 - `enabled: boolean`669670 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`671672 Permission policy for tool execution.673674 - `BetaManagedAgentsAlwaysAllowPolicy object`675676 Tool calls are automatically approved without user confirmation.677678 - `BetaManagedAgentsAlwaysAskPolicy object`679680 Tool calls require user confirmation before execution.681682 - `BetaManagedAgentsAutoPolicy object`683684 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.685686 - `BetaManagedAgentsMCPToolset object`687688 - `type: "mcp_toolset"`689690 - `configs: array of BetaManagedAgentsMCPToolConfig`691692 - `enabled: boolean`693694 - `name: string`695696 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`697698 Permission policy for tool execution.699700 - `BetaManagedAgentsAlwaysAllowPolicy object`701702 Tool calls are automatically approved without user confirmation.703704 - `BetaManagedAgentsAlwaysAskPolicy object`705706 Tool calls require user confirmation before execution.707708 - `BetaManagedAgentsAutoPolicy object`709710 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.711712 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`713714 Resolved default configuration for all tools from an MCP server.715716 - `enabled: boolean`717718 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`719720 Permission policy for tool execution.721722 - `BetaManagedAgentsAlwaysAllowPolicy object`723724 Tool calls are automatically approved without user confirmation.725726 - `BetaManagedAgentsAlwaysAskPolicy object`727728 Tool calls require user confirmation before execution.729730 - `BetaManagedAgentsAutoPolicy object`731732 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.733734 - `mcp_server_name: string`735736 - `BetaManagedAgentsCustomTool object`737738 A custom tool as returned in API responses.739740 - `type: "custom"`741742 - `description: string`743744 - `input_schema: BetaManagedAgentsCustomToolInputSchema`745746 JSON Schema for custom tool input parameters.747748 - `type: "object"`749750 - `properties: optional map[unknown] or null`751752 - `required: optional array of string or null`753754 - `name: string`755756 - `version: number`757758 format: int32759760 - `BetaManagedAgentsAdvisor object`761762 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.763764 - `type: "advisor"`765766 - `model: string`767768 The advisor model id.769770 - `name: string`771772 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`773774 - `BetaManagedAgentsAnthropicSkill object`775776 A resolved Anthropic-managed skill.777778 - `BetaManagedAgentsCustomSkill object`779780 A resolved user-created custom skill.781782 - `system: string or null`783784 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`785786 - `BetaManagedAgentsAgentToolset20260401 object`787788 - `BetaManagedAgentsMCPToolset object`789790 - `BetaManagedAgentsCustomTool object`791792 A custom tool as returned in API responses.793794 - `version: number`795796 format: int32797798 - `archived_at: string or null`799800 A timestamp in RFC 3339 format801802 format: date-time803804 - `budget: BetaManagedAgentsBudgetLimit or null`805806 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.807808 - `type: "limit"`809810 - `max_list_cost: BetaMonetaryAmount`811812 A monetary amount in a specific currency.813814 - `amount: string`815816 Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied.817818 - `currency: BetaCurrency`819820 Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced.821822 - `created_at: string`823824 A timestamp in RFC 3339 format825826 format: date-time827828 - `environment_id: string`829830 - `metadata: map[string]`831832 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`833834 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.835836 - `type: "outcome_evaluation"`837838 - `completed_at: string or null`839840 A timestamp in RFC 3339 format841842 format: date-time843844 - `description: string`845846 What the agent should produce.847848 - `explanation: string or null`849850 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.851852 - `iteration: number`853854 0-indexed revision cycle the outcome is currently on.855856 format: int32857858 - `outcome_id: string`859860 Server-generated outc_ ID for this outcome.861862 - `result: string`863864 Current evaluation state. `pending` before the agent begins work; `running` while producing or revising; `evaluating` while the grader scores; `satisfied`/`max_iterations_reached`/`failed`/`interrupted` are terminal.865866 - `resources: array of BetaManagedAgentsSessionResource`867868 - `BetaManagedAgentsGitHubRepositoryResource object`869870 - `type: "github_repository"`871872 - `id: string`873874 - `created_at: string`875876 A timestamp in RFC 3339 format877878 format: date-time879880 - `mount_path: string`881882 - `updated_at: string`883884 A timestamp in RFC 3339 format885886 format: date-time887888 - `url: string`889890 - `checkout: optional BetaManagedAgentsBranchCheckout or BetaManagedAgentsCommitCheckout or null`891892 - `BetaManagedAgentsBranchCheckout object`893894 - `type: "branch"`895896 - `name: string`897898 Branch name to check out.899900 minLength: 1, maxLength: 255901902 - `BetaManagedAgentsCommitCheckout object`903904 - `type: "commit"`905906 - `sha: string`907908 Full commit SHA to check out.909910 minLength: 7, maxLength: 64911912 - `BetaManagedAgentsFileResource object`913914 - `type: "file"`915916 - `id: string`917918 - `created_at: string`919920 A timestamp in RFC 3339 format921922 format: date-time923924 - `file_id: string`925926 - `mount_path: string`927928 - `updated_at: string`929930 A timestamp in RFC 3339 format931932 format: date-time933934 - `BetaManagedAgentsMemoryStoreResource object`935936 A memory store attached to an agent session.937938 - `type: "memory_store"`939940 - `memory_store_id: string`941942 The memory store ID (memstore_...). Must belong to the caller's organization and workspace.943944 - `access: optional "read_write" or "read_only" or null`945946 Access mode for an attached memory store.947948 - `"read_write"`949950 - `"read_only"`951952 - `description: optional string`953954 Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description.955956 - `instructions: optional string or null`957958 Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars.959960 maxLength: 4096961962 - `mount_path: optional string or null`963964 Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only.965966 - `name: optional string or null`967968 Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource.969970 - `stats: BetaManagedAgentsSessionStats`971972 Timing statistics for a session.973974 - `active_seconds: optional number`975976 Cumulative time in seconds the session spent in `running` status. Excludes idle time.977978 format: double979980 - `duration_seconds: optional number`981982 Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update.983984 format: double985986 - `status: "rescheduling" or "running" or "idle" or "terminated"`987988 SessionStatus enum989990 - `"rescheduling"`991992 - `"running"`993994 - `"idle"`995996 - `"terminated"`997998 - `title: string or null`9991000 - `updated_at: string`10011002 A timestamp in RFC 3339 format10031004 format: date-time10051006 - `usage: BetaManagedAgentsSessionUsage`10071008 Cumulative token usage for a session across all turns.10091010 - `active_seconds: optional number`10111012 Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once, unlike `stats.active_seconds`, which sums each thread's own active time. This is the duration the session's runtime cost is priced on.10131014 format: double10151016 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`10171018 Prompt-cache creation token usage broken down by cache lifetime.10191020 - `ephemeral_1h_input_tokens: optional number`10211022 Tokens used to create 1-hour ephemeral cache entries.10231024 format: int3210251026 - `ephemeral_5m_input_tokens: optional number`10271028 Tokens used to create 5-minute ephemeral cache entries.10291030 format: int3210311032 - `cache_read_input_tokens: optional number`10331034 Total tokens read from prompt cache.10351036 format: int3210371038 - `input_tokens: optional number`10391040 Total input tokens consumed across all turns.10411042 format: int3210431044 - `list_cost: optional BetaMonetaryAmount or null`10451046 A monetary amount in a specific currency.10471048 - `output_tokens: optional number`10491050 Total output tokens generated across all turns.10511052 format: int3210531054 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`10551056 Cumulative count of server-executed tool invocations, broken down by tool.10571058 - `web_fetch_requests: optional number`10591060 Number of server-executed web fetch requests.10611062 format: int3210631064 - `web_search_requests: optional number`10651066 Number of server-executed web search requests.10671068 format: int3210691070 - `vault_ids: array of string`10711072 Vault IDs attached to the session at creation. Empty when no vaults were supplied.10731074 - `deployment_id: optional string or null`10751076 Deployment ID when the session was created from a deployment reference. Null otherwise.10771078- `next_page: optional string or null`10791080 Opaque cursor for the next page. Null when no more results.10811082- `prev_page: optional string or null`10831084 Opaque cursor for the previous page. Null when on the first page. Pass as the `page` parameter to navigate backward.10851086## Example10871088```bash1089curl https://api.anthropic.com/v1/sessions \1090 -H 'anthropic-version: 2023-06-01' \1091 -H 'anthropic-beta: managed-agents-2026-04-01' \1092 -H "X-Api-Key: $ANTHROPIC_API_KEY"1093```10941095### Response (200)10961097```json1098{1099 "data": [1100 {1101 "id": "sesn_011CZkZAtmR3yMPDzynEDxu7",1102 "agent": {1103 "id": "agent_011CZkYpogX7uDKUyvBTophP",1104 "description": "A general-purpose starter agent.",1105 "mcp_servers": [1106 {1107 "name": "example-mcp",1108 "type": "url",1109 "url": "https://example-server.modelcontextprotocol.io/sse"1110 }1111 ],1112 "model": {1113 "id": "claude-opus-5",1114 "effort": {1115 "type": "low"1116 },1117 "inference_geo": "inference_geo",1118 "speed": "standard"1119 },1120 "multiagent": {1121 "agents": [1122 {1123 "id": "agent_011CZkYqphY8vELVzwCUpqiQ",1124 "description": "A focused research subagent.",1125 "mcp_servers": [1126 {1127 "name": "example-mcp",1128 "type": "url",1129 "url": "https://example-server.modelcontextprotocol.io/sse"1130 }1131 ],1132 "model": {1133 "id": "claude-opus-5",1134 "effort": {1135 "type": "low"1136 },1137 "inference_geo": "inference_geo",1138 "speed": "standard"1139 },1140 "name": "Researcher",1141 "skills": [1142 {1143 "skill_id": "xlsx",1144 "type": "anthropic",1145 "version": "1"1146 }1147 ],1148 "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.",1149 "tools": [1150 {1151 "configs": [1152 {1153 "enabled": true,1154 "name": "bash",1155 "permission_policy": {1156 "type": "always_allow"1157 },1158 "type": "bash"1159 }1160 ],1161 "default_config": {1162 "enabled": true,1163 "permission_policy": {1164 "type": "always_ask"1165 }1166 },1167 "type": "agent_toolset_20260401"1168 }1169 ],1170 "type": "agent",1171 "version": 11172 }1173 ],1174 "type": "coordinator"1175 },1176 "name": "My First Agent",1177 "skills": [1178 {1179 "skill_id": "xlsx",1180 "type": "anthropic",1181 "version": "1"1182 },1183 {1184 "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTlx",1185 "type": "custom",1186 "version": "2"1187 }1188 ],1189 "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.",1190 "tools": [1191 {1192 "configs": [1193 {1194 "enabled": true,1195 "name": "bash",1196 "permission_policy": {1197 "type": "always_allow"1198 },1199 "type": "bash"1200 }1201 ],1202 "default_config": {1203 "enabled": true,1204 "permission_policy": {1205 "type": "always_ask"1206 }1207 },1208 "type": "agent_toolset_20260401"1209 }1210 ],1211 "type": "agent",1212 "version": 11213 },1214 "archived_at": null,1215 "budget": {1216 "max_list_cost": {1217 "amount": "2500",1218 "currency": "USD"1219 },1220 "type": "limit"1221 },1222 "created_at": "2026-03-15T10:00:00Z",1223 "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW",1224 "metadata": {},1225 "outcome_evaluations": [1226 {1227 "completed_at": "2026-03-15T10:02:31Z",1228 "description": "Produce a 2-page summary as summary.md",1229 "explanation": "All five sections present with inline citations.",1230 "iteration": 0,1231 "outcome_id": "outc_011CZkZRSw2kEfs6ncTVljxP",1232 "result": "satisfied",1233 "type": "outcome_evaluation"1234 }1235 ],1236 "resources": [1237 {1238 "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht",1239 "created_at": "2026-03-15T10:00:00Z",1240 "file_id": "file_011CNha8iCJcU1wXNR6q4V8w",1241 "mount_path": "/uploads/receipt.pdf",1242 "type": "file",1243 "updated_at": "2026-03-15T10:00:00Z"1244 },1245 {1246 "id": "sesrsc_011CZkZCKr6eXyl0gWMOdQiu",1247 "created_at": "2026-03-15T10:00:00Z",1248 "mount_path": "/workspace/example-repo",1249 "type": "github_repository",1250 "updated_at": "2026-03-15T10:00:00Z",1251 "url": "https://github.com/example-org/example-repo",1252 "checkout": {1253 "name": "main",1254 "type": "branch"1255 }1256 }1257 ],1258 "stats": {1259 "active_seconds": 0,1260 "duration_seconds": 01261 },1262 "status": "idle",1263 "title": "Order #1234 inquiry",1264 "type": "session",1265 "updated_at": "2026-03-15T10:00:00Z",1266 "usage": {1267 "active_seconds": 0,1268 "cache_creation": {1269 "ephemeral_1h_input_tokens": 0,1270 "ephemeral_5m_input_tokens": 01271 },1272 "cache_read_input_tokens": 0,1273 "input_tokens": 0,1274 "list_cost": {1275 "amount": "2500",1276 "currency": "USD"1277 },1278 "output_tokens": 0,1279 "server_tool_use": {1280 "web_fetch_requests": 0,1281 "web_search_requests": 31282 }1283 },1284 "vault_ids": [1285 "vlt_011CZkZDLs7fYzm1hXNPeRjv"1286 ],1287 "deployment_id": "deployment_id"1288 }1289 ],1290 "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=",1291 "prev_page": "page_MjAyNS0wNS0xM1QwMDowMDowMFo="1292}1293```1294