Repository Public
1---2title: Get Session3url: https://platform.claude.com/docs/en/api/beta/sessions/retrieve4---56# Get Session78**GET** `/v1/sessions/{session_id}`910Get Session1112## Path parameters1314- `session_id: string`1516## Headers1718- `"anthropic-beta": optional array of AnthropicBeta`1920 Optional header to specify the beta version(s) you want to use.2122 - `string`2324 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`2526 - `"message-batches-2024-09-24"`2728 - `"prompt-caching-2024-07-31"`2930 - `"computer-use-2024-10-22"`3132 - `"computer-use-2025-01-24"`3334 - `"pdfs-2024-09-25"`3536 - `"token-counting-2024-11-01"`3738 - `"token-efficient-tools-2025-02-19"`3940 - `"output-128k-2025-02-19"`4142 - `"files-api-2025-04-14"`4344 - `"mcp-client-2025-04-04"`4546 - `"mcp-client-2025-11-20"`4748 - `"dev-full-thinking-2025-05-14"`4950 - `"interleaved-thinking-2025-05-14"`5152 - `"code-execution-2025-05-22"`5354 - `"extended-cache-ttl-2025-04-11"`5556 - `"context-1m-2025-08-07"`5758 - `"context-management-2025-06-27"`5960 - `"model-context-window-exceeded-2025-08-26"`6162 - `"skills-2025-10-02"`6364 - `"fast-mode-2026-02-01"`6566 - `"output-300k-2026-03-24"`6768 - `"user-profiles-2026-03-24"`6970 - `"user-profiles-2026-08-18"`7172 - `"user-profiles-2026-09-04"`7374 - `"advisor-tool-2026-03-01"`7576 - `"managed-agents-2026-04-01"`7778 - `"cache-diagnosis-2026-04-07"`7980 - `"dreaming-2026-04-21"`8182 - `"thinking-token-count-2026-05-13"`8384 - `"server-side-fallback-2026-06-01"`8586 - `"server-side-fallback-2026-07-01"`8788 - `"fallback-credit-2026-06-01"`8990 - `"fallback-credit-2026-07-01"`9192 - `"agent-memory-2026-07-22"`9394 - `"mid-conversation-tool-changes-2026-07-01"`9596 - `"compact-2026-01-12"`9798 - `"computer-use-2025-11-24"`99100 - `"mcp-tunnels-2026-06-22"`101102 - `"structured-outputs-2025-11-13"`103104 - `"task-budgets-2026-03-13"`105106 - `"thinking-display-updates-2026-08-18"`107108 - `"ce-user-management-2026-07-13"`109110 - `"mid-conversation-output-config-2026-07-01"`111112 - `"thinking-binding-controls-2026-08-01"`113114 - `"mid-conversation-system-clear-at-2026-08-21"`115116 - `"compact-2026-09-04"`117118- `"anthropic-workspace-id": optional string`119120## Returns121122- `BetaManagedAgentsSession object`123124 A Managed Agents `session`.125126 - `type: "session"`127128 - `id: string`129130 - `agent: BetaManagedAgentsSessionAgent`131132 Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time.133134 - `type: "agent"`135136 - `id: string`137138 - `description: string or null`139140 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`141142 - `type: "url"`143144 - `name: string`145146 - `url: string`147148 - `model: BetaManagedAgentsModelConfig`149150 Model identifier and configuration.151152 - `id: BetaManagedAgentsModel`153154 The model that will power your agent.155156 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.157158 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`159160 The model that will power your agent.161162 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.163164 - `"claude-fable-5-1"`165166 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows167168 - `"claude-sonnet-5"`169170 High-performance model for coding and agents171172 - `"claude-fable-5"`173174 Next generation of intelligence for the hardest knowledge work and coding problems175176 - `"claude-opus-5"`177178 Powerful intelligence for long-running agents and coding179180 - `"claude-opus-4-8"`181182 Powerful intelligence for long-running agents and coding183184 - `"claude-opus-4-7"`185186 Powerful intelligence for long-running agents and coding187188 - `"claude-opus-4-6"`189190 Powerful intelligence for long-running agents and coding191192 - `"claude-sonnet-4-6"`193194 Best combination of speed and intelligence195196 - `"claude-haiku-4-5"`197198 Fastest model with near-frontier intelligence199200 - `"claude-haiku-4-5-20251001"`201202 Fastest model with near-frontier intelligence203204 - `"claude-opus-4-5"`205206 Powerful intelligence for long-running agents and coding207208 - `"claude-opus-4-5-20251101"`209210 Powerful intelligence for long-running agents and coding211212 - `"claude-sonnet-4-5"`213214 High-performance model for agents and coding215216 - `"claude-sonnet-4-5-20250929"`217218 High-performance model for agents and coding219220 - `string`221222 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`223224 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.225226 - `BetaManagedAgentsEffortLow object`227228 Low effort. Favors latency over reasoning depth.229230 - `type: "low"`231232 - `BetaManagedAgentsEffortMedium object`233234 Medium effort. Balances latency and reasoning depth.235236 - `type: "medium"`237238 - `BetaManagedAgentsEffortHigh object`239240 High effort. Favors reasoning depth.241242 - `type: "high"`243244 - `BetaManagedAgentsEffortXhigh object`245246 Extra-high effort. Not all models accept this level.247248 - `type: "xhigh"`249250 - `BetaManagedAgentsEffortMax object`251252 Maximum effort. Favors reasoning depth over latency.253254 - `type: "max"`255256 - `inference_geo: optional string`257258 Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.259260 - `speed: optional "standard" or "fast"`261262 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.263264 - `"standard"`265266 - `"fast"`267268 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`269270 Resolved coordinator topology with full agent definitions for each roster member.271272 - `type: "coordinator"`273274 - `agents: array of BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`275276 Full `agent` definitions the coordinator may spawn as session threads.277278 - `BetaManagedAgentsSessionThreadAgent object`279280 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`.281282 - `type: "agent"`283284 - `id: string`285286 - `description: string or null`287288 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`289290 - `type: "url"`291292 - `name: string`293294 - `url: string`295296 - `model: BetaManagedAgentsModelConfig`297298 Model identifier and configuration.299300 - `name: string`301302 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`303304 - `BetaManagedAgentsAnthropicSkill object`305306 A resolved Anthropic-managed skill.307308 - `type: "anthropic"`309310 - `skill_id: string`311312 - `version: string`313314 - `BetaManagedAgentsCustomSkill object`315316 A resolved user-created custom skill.317318 - `type: "custom"`319320 - `skill_id: string`321322 - `version: string`323324 - `system: string or null`325326 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`327328 - `BetaManagedAgentsAgentToolset20260401 object`329330 - `type: "agent_toolset_20260401"`331332 - `configs: array of BetaManagedAgentsAgentToolConfig`333334 - `BetaManagedAgentsBashToolConfig object`335336 Configuration for the bash tool.337338 - `type: "bash"`339340 - `enabled: boolean`341342 - `name: "bash"`343344 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`345346 Permission policy for tool execution.347348 - `BetaManagedAgentsAlwaysAllowPolicy object`349350 Tool calls are automatically approved without user confirmation.351352 - `type: "always_allow"`353354 - `BetaManagedAgentsAlwaysAskPolicy object`355356 Tool calls require user confirmation before execution.357358 - `type: "always_ask"`359360 - `BetaManagedAgentsAutoPolicy object`361362 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.363364 - `type: "auto"`365366 - `BetaManagedAgentsEditToolConfig object`367368 Configuration for the edit tool.369370 - `type: "edit"`371372 - `enabled: boolean`373374 - `name: "edit"`375376 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`377378 Permission policy for tool execution.379380 - `BetaManagedAgentsAlwaysAllowPolicy object`381382 Tool calls are automatically approved without user confirmation.383384 - `BetaManagedAgentsAlwaysAskPolicy object`385386 Tool calls require user confirmation before execution.387388 - `BetaManagedAgentsAutoPolicy object`389390 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.391392 - `BetaManagedAgentsReadToolConfig object`393394 Configuration for the read tool.395396 - `type: "read"`397398 - `enabled: boolean`399400 - `name: "read"`401402 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`403404 Permission policy for tool execution.405406 - `BetaManagedAgentsAlwaysAllowPolicy object`407408 Tool calls are automatically approved without user confirmation.409410 - `BetaManagedAgentsAlwaysAskPolicy object`411412 Tool calls require user confirmation before execution.413414 - `BetaManagedAgentsAutoPolicy object`415416 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.417418 - `BetaManagedAgentsWriteToolConfig object`419420 Configuration for the write tool.421422 - `type: "write"`423424 - `enabled: boolean`425426 - `name: "write"`427428 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`429430 Permission policy for tool execution.431432 - `BetaManagedAgentsAlwaysAllowPolicy object`433434 Tool calls are automatically approved without user confirmation.435436 - `BetaManagedAgentsAlwaysAskPolicy object`437438 Tool calls require user confirmation before execution.439440 - `BetaManagedAgentsAutoPolicy object`441442 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.443444 - `BetaManagedAgentsGlobToolConfig object`445446 Configuration for the glob tool.447448 - `type: "glob"`449450 - `enabled: boolean`451452 - `name: "glob"`453454 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`455456 Permission policy for tool execution.457458 - `BetaManagedAgentsAlwaysAllowPolicy object`459460 Tool calls are automatically approved without user confirmation.461462 - `BetaManagedAgentsAlwaysAskPolicy object`463464 Tool calls require user confirmation before execution.465466 - `BetaManagedAgentsAutoPolicy object`467468 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.469470 - `BetaManagedAgentsGrepToolConfig object`471472 Configuration for the grep tool.473474 - `type: "grep"`475476 - `enabled: boolean`477478 - `name: "grep"`479480 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`481482 Permission policy for tool execution.483484 - `BetaManagedAgentsAlwaysAllowPolicy object`485486 Tool calls are automatically approved without user confirmation.487488 - `BetaManagedAgentsAlwaysAskPolicy object`489490 Tool calls require user confirmation before execution.491492 - `BetaManagedAgentsAutoPolicy object`493494 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.495496 - `BetaManagedAgentsWebFetchToolConfig object`497498 Configuration for the web_fetch tool.499500 - `type: "web_fetch"`501502 - `enabled: boolean`503504 - `name: "web_fetch"`505506 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`507508 Permission policy for tool execution.509510 - `BetaManagedAgentsAlwaysAllowPolicy object`511512 Tool calls are automatically approved without user confirmation.513514 - `BetaManagedAgentsAlwaysAskPolicy object`515516 Tool calls require user confirmation before execution.517518 - `BetaManagedAgentsAutoPolicy object`519520 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.521522 - `allowed_domains: optional array of string`523524 - `blocked_domains: optional array of string`525526 - `max_content_tokens: optional number or null`527528 format: int32529530 - `BetaManagedAgentsWebSearchToolConfig object`531532 Configuration for the web_search tool.533534 - `type: "web_search"`535536 - `enabled: boolean`537538 - `name: "web_search"`539540 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`541542 Permission policy for tool execution.543544 - `BetaManagedAgentsAlwaysAllowPolicy object`545546 Tool calls are automatically approved without user confirmation.547548 - `BetaManagedAgentsAlwaysAskPolicy object`549550 Tool calls require user confirmation before execution.551552 - `BetaManagedAgentsAutoPolicy object`553554 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.555556 - `allowed_domains: optional array of string`557558 - `blocked_domains: optional array of string`559560 - `user_location: optional BetaManagedAgentsUserLocation or null`561562 Approximate user location for search result localization.563564 - `type: "approximate"`565566 Location precision. Only "approximate" is supported.567568 - `city: optional string or null`569570 City name.571572 minLength: 1, maxLength: 255573574 - `country: optional string or null`575576 Two-letter ISO 3166-1 country code, uppercase.577578 - `region: optional string or null`579580 Region or state name.581582 minLength: 1, maxLength: 255583584 - `timezone: optional string or null`585586 IANA timezone identifier, e.g. "America/Los_Angeles".587588 minLength: 1, maxLength: 255589590 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig`591592 Resolved default configuration for agent tools.593594 - `enabled: boolean`595596 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`597598 Permission policy for tool execution.599600 - `BetaManagedAgentsAlwaysAllowPolicy object`601602 Tool calls are automatically approved without user confirmation.603604 - `BetaManagedAgentsAlwaysAskPolicy object`605606 Tool calls require user confirmation before execution.607608 - `BetaManagedAgentsAutoPolicy object`609610 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.611612 - `BetaManagedAgentsMCPToolset object`613614 - `type: "mcp_toolset"`615616 - `configs: array of BetaManagedAgentsMCPToolConfig`617618 - `enabled: boolean`619620 - `name: string`621622 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`623624 Permission policy for tool execution.625626 - `BetaManagedAgentsAlwaysAllowPolicy object`627628 Tool calls are automatically approved without user confirmation.629630 - `BetaManagedAgentsAlwaysAskPolicy object`631632 Tool calls require user confirmation before execution.633634 - `BetaManagedAgentsAutoPolicy object`635636 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.637638 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`639640 Resolved default configuration for all tools from an MCP server.641642 - `enabled: boolean`643644 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`645646 Permission policy for tool execution.647648 - `BetaManagedAgentsAlwaysAllowPolicy object`649650 Tool calls are automatically approved without user confirmation.651652 - `BetaManagedAgentsAlwaysAskPolicy object`653654 Tool calls require user confirmation before execution.655656 - `BetaManagedAgentsAutoPolicy object`657658 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.659660 - `mcp_server_name: string`661662 - `BetaManagedAgentsCustomTool object`663664 A custom tool as returned in API responses.665666 - `type: "custom"`667668 - `description: string`669670 - `input_schema: BetaManagedAgentsCustomToolInputSchema`671672 JSON Schema for custom tool input parameters.673674 - `type: "object"`675676 - `properties: optional map[unknown] or null`677678 - `required: optional array of string or null`679680 - `name: string`681682 - `version: number`683684 format: int32685686 - `BetaManagedAgentsAdvisor object`687688 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.689690 - `type: "advisor"`691692 - `model: string`693694 The advisor model id.695696 - `name: string`697698 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`699700 - `BetaManagedAgentsAnthropicSkill object`701702 A resolved Anthropic-managed skill.703704 - `BetaManagedAgentsCustomSkill object`705706 A resolved user-created custom skill.707708 - `system: string or null`709710 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`711712 - `BetaManagedAgentsAgentToolset20260401 object`713714 - `BetaManagedAgentsMCPToolset object`715716 - `BetaManagedAgentsCustomTool object`717718 A custom tool as returned in API responses.719720 - `version: number`721722 format: int32723724 - `archived_at: string or null`725726 A timestamp in RFC 3339 format727728 format: date-time729730 - `budget: BetaManagedAgentsBudgetLimit or null`731732 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.733734 - `type: "limit"`735736 - `max_list_cost: BetaMonetaryAmount`737738 A monetary amount in a specific currency.739740 - `amount: string`741742 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.743744 - `currency: BetaCurrency`745746 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.747748 - `created_at: string`749750 A timestamp in RFC 3339 format751752 format: date-time753754 - `environment_id: string`755756 - `metadata: map[string]`757758 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`759760 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.761762 - `type: "outcome_evaluation"`763764 - `completed_at: string or null`765766 A timestamp in RFC 3339 format767768 format: date-time769770 - `description: string`771772 What the agent should produce.773774 - `explanation: string or null`775776 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.777778 - `iteration: number`779780 0-indexed revision cycle the outcome is currently on.781782 format: int32783784 - `outcome_id: string`785786 Server-generated outc_ ID for this outcome.787788 - `result: string`789790 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.791792 - `resources: array of BetaManagedAgentsSessionResource`793794 - `BetaManagedAgentsGitHubRepositoryResource object`795796 - `type: "github_repository"`797798 - `id: string`799800 - `created_at: string`801802 A timestamp in RFC 3339 format803804 format: date-time805806 - `mount_path: string`807808 - `updated_at: string`809810 A timestamp in RFC 3339 format811812 format: date-time813814 - `url: string`815816 - `checkout: optional BetaManagedAgentsBranchCheckout or BetaManagedAgentsCommitCheckout or null`817818 - `BetaManagedAgentsBranchCheckout object`819820 - `type: "branch"`821822 - `name: string`823824 Branch name to check out.825826 minLength: 1, maxLength: 255827828 - `BetaManagedAgentsCommitCheckout object`829830 - `type: "commit"`831832 - `sha: string`833834 Full commit SHA to check out.835836 minLength: 7, maxLength: 64837838 - `BetaManagedAgentsFileResource object`839840 - `type: "file"`841842 - `id: string`843844 - `created_at: string`845846 A timestamp in RFC 3339 format847848 format: date-time849850 - `file_id: string`851852 - `mount_path: string`853854 - `updated_at: string`855856 A timestamp in RFC 3339 format857858 format: date-time859860 - `BetaManagedAgentsMemoryStoreResource object`861862 A memory store attached to an agent session.863864 - `type: "memory_store"`865866 - `memory_store_id: string`867868 The memory store ID (memstore_...). Must belong to the caller's organization and workspace.869870 - `access: optional "read_write" or "read_only" or null`871872 Access mode for an attached memory store.873874 - `"read_write"`875876 - `"read_only"`877878 - `description: optional string`879880 Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description.881882 - `instructions: optional string or null`883884 Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars.885886 maxLength: 4096887888 - `mount_path: optional string or null`889890 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.891892 - `name: optional string or null`893894 Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource.895896 - `stats: BetaManagedAgentsSessionStats`897898 Timing statistics for a session.899900 - `active_seconds: optional number`901902 Cumulative time in seconds the session spent in `running` status. Excludes idle time.903904 format: double905906 - `duration_seconds: optional number`907908 Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update.909910 format: double911912 - `status: "rescheduling" or "running" or "idle" or "terminated"`913914 SessionStatus enum915916 - `"rescheduling"`917918 - `"running"`919920 - `"idle"`921922 - `"terminated"`923924 - `title: string or null`925926 - `updated_at: string`927928 A timestamp in RFC 3339 format929930 format: date-time931932 - `usage: BetaManagedAgentsSessionUsage`933934 Cumulative token usage for a session across all turns.935936 - `active_seconds: optional number`937938 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.939940 format: double941942 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`943944 Prompt-cache creation token usage broken down by cache lifetime.945946 - `ephemeral_1h_input_tokens: optional number`947948 Tokens used to create 1-hour ephemeral cache entries.949950 format: int32951952 - `ephemeral_5m_input_tokens: optional number`953954 Tokens used to create 5-minute ephemeral cache entries.955956 format: int32957958 - `cache_read_input_tokens: optional number`959960 Total tokens read from prompt cache.961962 format: int32963964 - `input_tokens: optional number`965966 Total input tokens consumed across all turns.967968 format: int32969970 - `list_cost: optional BetaMonetaryAmount or null`971972 A monetary amount in a specific currency.973974 - `output_tokens: optional number`975976 Total output tokens generated across all turns.977978 format: int32979980 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`981982 Cumulative count of server-executed tool invocations, broken down by tool.983984 - `web_fetch_requests: optional number`985986 Number of server-executed web fetch requests.987988 format: int32989990 - `web_search_requests: optional number`991992 Number of server-executed web search requests.993994 format: int32995996 - `vault_ids: array of string`997998 Vault IDs attached to the session at creation. Empty when no vaults were supplied.9991000 - `deployment_id: optional string or null`10011002 Deployment ID when the session was created from a deployment reference. Null otherwise.10031004## Example10051006```bash1007curl https://api.anthropic.com/v1/sessions/$SESSION_ID \1008 -H 'anthropic-version: 2023-06-01' \1009 -H 'anthropic-beta: managed-agents-2026-04-01' \1010 -H "X-Api-Key: $ANTHROPIC_API_KEY"1011```10121013### Response (200)10141015```json1016{1017 "id": "sesn_011CZkZAtmR3yMPDzynEDxu7",1018 "agent": {1019 "id": "agent_011CZkYpogX7uDKUyvBTophP",1020 "description": "A general-purpose starter agent.",1021 "mcp_servers": [1022 {1023 "name": "example-mcp",1024 "type": "url",1025 "url": "https://example-server.modelcontextprotocol.io/sse"1026 }1027 ],1028 "model": {1029 "id": "claude-opus-5",1030 "effort": {1031 "type": "low"1032 },1033 "inference_geo": "inference_geo",1034 "speed": "standard"1035 },1036 "multiagent": {1037 "agents": [1038 {1039 "id": "agent_011CZkYqphY8vELVzwCUpqiQ",1040 "description": "A focused research subagent.",1041 "mcp_servers": [1042 {1043 "name": "example-mcp",1044 "type": "url",1045 "url": "https://example-server.modelcontextprotocol.io/sse"1046 }1047 ],1048 "model": {1049 "id": "claude-opus-5",1050 "effort": {1051 "type": "low"1052 },1053 "inference_geo": "inference_geo",1054 "speed": "standard"1055 },1056 "name": "Researcher",1057 "skills": [1058 {1059 "skill_id": "xlsx",1060 "type": "anthropic",1061 "version": "1"1062 }1063 ],1064 "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.",1065 "tools": [1066 {1067 "configs": [1068 {1069 "enabled": true,1070 "name": "bash",1071 "permission_policy": {1072 "type": "always_allow"1073 },1074 "type": "bash"1075 }1076 ],1077 "default_config": {1078 "enabled": true,1079 "permission_policy": {1080 "type": "always_ask"1081 }1082 },1083 "type": "agent_toolset_20260401"1084 }1085 ],1086 "type": "agent",1087 "version": 11088 }1089 ],1090 "type": "coordinator"1091 },1092 "name": "My First Agent",1093 "skills": [1094 {1095 "skill_id": "xlsx",1096 "type": "anthropic",1097 "version": "1"1098 },1099 {1100 "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTlx",1101 "type": "custom",1102 "version": "2"1103 }1104 ],1105 "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.",1106 "tools": [1107 {1108 "configs": [1109 {1110 "enabled": true,1111 "name": "bash",1112 "permission_policy": {1113 "type": "always_allow"1114 },1115 "type": "bash"1116 }1117 ],1118 "default_config": {1119 "enabled": true,1120 "permission_policy": {1121 "type": "always_ask"1122 }1123 },1124 "type": "agent_toolset_20260401"1125 }1126 ],1127 "type": "agent",1128 "version": 11129 },1130 "archived_at": null,1131 "budget": {1132 "max_list_cost": {1133 "amount": "2500",1134 "currency": "USD"1135 },1136 "type": "limit"1137 },1138 "created_at": "2026-03-15T10:00:00Z",1139 "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW",1140 "metadata": {},1141 "outcome_evaluations": [1142 {1143 "completed_at": "2026-03-15T10:02:31Z",1144 "description": "Produce a 2-page summary as summary.md",1145 "explanation": "All five sections present with inline citations.",1146 "iteration": 0,1147 "outcome_id": "outc_011CZkZRSw2kEfs6ncTVljxP",1148 "result": "satisfied",1149 "type": "outcome_evaluation"1150 }1151 ],1152 "resources": [1153 {1154 "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht",1155 "created_at": "2026-03-15T10:00:00Z",1156 "file_id": "file_011CNha8iCJcU1wXNR6q4V8w",1157 "mount_path": "/uploads/receipt.pdf",1158 "type": "file",1159 "updated_at": "2026-03-15T10:00:00Z"1160 },1161 {1162 "id": "sesrsc_011CZkZCKr6eXyl0gWMOdQiu",1163 "created_at": "2026-03-15T10:00:00Z",1164 "mount_path": "/workspace/example-repo",1165 "type": "github_repository",1166 "updated_at": "2026-03-15T10:00:00Z",1167 "url": "https://github.com/example-org/example-repo",1168 "checkout": {1169 "name": "main",1170 "type": "branch"1171 }1172 }1173 ],1174 "stats": {1175 "active_seconds": 0,1176 "duration_seconds": 01177 },1178 "status": "idle",1179 "title": "Order #1234 inquiry",1180 "type": "session",1181 "updated_at": "2026-03-15T10:00:00Z",1182 "usage": {1183 "active_seconds": 0,1184 "cache_creation": {1185 "ephemeral_1h_input_tokens": 0,1186 "ephemeral_5m_input_tokens": 01187 },1188 "cache_read_input_tokens": 0,1189 "input_tokens": 0,1190 "list_cost": {1191 "amount": "2500",1192 "currency": "USD"1193 },1194 "output_tokens": 0,1195 "server_tool_use": {1196 "web_fetch_requests": 0,1197 "web_search_requests": 31198 }1199 },1200 "vault_ids": [1201 "vlt_011CZkZDLs7fYzm1hXNPeRjv"1202 ],1203 "deployment_id": "deployment_id"1204}1205```1206