Threads

List Session Threads

get /v1/sessions/{session_id}/threads

List Session Threads

Path Parameters

• session_id: string

Query Parameters

• limit: optional number

  Maximum results per page. Defaults to 1000.

• page: optional string

  Opaque pagination cursor from a previous response's next_page. Forward-only.

Header Parameters

• "anthropic-beta": optional array of AnthropicBeta

  Optional header to specify the beta version(s) you want to use.

  • string

  • "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 22 more

    • "message-batches-2024-09-24"

    • "prompt-caching-2024-07-31"

    • "computer-use-2024-10-22"

    • "computer-use-2025-01-24"

    • "pdfs-2024-09-25"

    • "token-counting-2024-11-01"

    • "token-efficient-tools-2025-02-19"

    • "output-128k-2025-02-19"

    • "files-api-2025-04-14"

    • "mcp-client-2025-04-04"

    • "mcp-client-2025-11-20"

    • "dev-full-thinking-2025-05-14"

    • "interleaved-thinking-2025-05-14"

    • "code-execution-2025-05-22"

    • "extended-cache-ttl-2025-04-11"

    • "context-1m-2025-08-07"

    • "context-management-2025-06-27"

    • "model-context-window-exceeded-2025-08-26"

    • "skills-2025-10-02"

    • "fast-mode-2026-02-01"

    • "output-300k-2026-03-24"

    • "user-profiles-2026-03-24"

    • "advisor-tool-2026-03-01"

    • "managed-agents-2026-04-01"

    • "cache-diagnosis-2026-04-07"

Returns

• data: optional array of BetaManagedAgentsSessionThread

  Threads in the session, primary first then children in spawn order.

  • id: string

    Unique identifier for this thread.

  • agent: BetaManagedAgentsSessionThreadAgent

    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.

    • id: string

    • description: string

    • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

      • name: string

      • type: "url"

        • "url"

      • url: string

    • model: BetaManagedAgentsModelConfig

      Model identifier and configuration.

      • id: BetaManagedAgentsModel

        The model that will power your agent.

        See models for additional details and options.

        • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7"

            Frontier intelligence for long-running agents and coding

          • "claude-opus-4-6"

            Most intelligent model for building agents and coding

          • "claude-sonnet-4-6"

            Best combination of speed and intelligence

          • "claude-haiku-4-5"

            Fastest model with near-frontier intelligence

          • "claude-haiku-4-5-20251001"

            Fastest model with near-frontier intelligence

          • "claude-opus-4-5"

            Premium model combining maximum intelligence with practical performance

          • "claude-opus-4-5-20251101"

            Premium model combining maximum intelligence with practical performance

          • "claude-sonnet-4-5"

            High-performance model for agents and coding

          • "claude-sonnet-4-5-20250929"

            High-performance model for agents and coding

        • string

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

    • name: string

    • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

      • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

        A resolved Anthropic-managed skill.

        • skill_id: string

        • type: "anthropic"

          • "anthropic"

        • version: string

      • BetaManagedAgentsCustomSkill object { skill_id, type, version }

        A resolved user-created custom skill.

        • skill_id: string

        • type: "custom"

          • "custom"

        • version: string

    • system: string

    • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

      • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • configs: array of BetaManagedAgentsAgentToolConfig

          • enabled: boolean

          • name: "bash" or "edit" or "read" or 5 more

            Built-in agent tool identifier.

            • "bash"

            • "edit"

            • "read"

            • "write"

            • "glob"

            • "grep"

            • "web_fetch"

            • "web_search"

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

              • type: "always_allow"

                • "always_allow"

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

              • type: "always_ask"

                • "always_ask"

        • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

          Resolved default configuration for agent tools.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • type: "agent_toolset_20260401"

          • "agent_toolset_20260401"

      • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • configs: array of BetaManagedAgentsMCPToolConfig

          • enabled: boolean

          • name: string

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

          Resolved default configuration for all tools from an MCP server.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • mcp_server_name: string

        • type: "mcp_toolset"

          • "mcp_toolset"

      • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

        A custom tool as returned in API responses.

        • description: string

        • input_schema: BetaManagedAgentsCustomToolInputSchema

          JSON Schema for custom tool input parameters.

          • properties: optional map[unknown]

            JSON Schema properties defining the tool's input parameters.

          • required: optional array of string

            List of required property names.

          • type: optional "object"

            Must be 'object' for tool input schemas.

            • "object"

        • name: string

        • type: "custom"

          • "custom"

    • type: "agent"

      • "agent"

    • version: number

  • archived_at: string

    A timestamp in RFC 3339 format

  • created_at: string

    A timestamp in RFC 3339 format

  • parent_thread_id: string

    Parent thread that spawned this thread. Null for the primary thread.

  • session_id: string

    The session this thread belongs to.

  • stats: BetaManagedAgentsSessionThreadStats

    Timing statistics for a session thread.

    • active_seconds: optional number

      Cumulative time in seconds the thread spent actively running. Excludes idle time.

    • duration_seconds: optional number

      Elapsed time since thread creation in seconds. For archived threads, frozen at the final update.

    • startup_seconds: optional number

      Time in seconds for the thread to begin running. Zero for child threads, which start immediately.

  • status: BetaManagedAgentsSessionThreadStatus

    SessionThreadStatus enum

    • "running"

    • "idle"

    • "rescheduling"

    • "terminated"

  • type: "session_thread"

    • "session_thread"

  • updated_at: string

    A timestamp in RFC 3339 format

  • usage: BetaManagedAgentsSessionThreadUsage

    Cumulative token usage for a session thread across all turns.

    • cache_creation: optional BetaManagedAgentsCacheCreationUsage

      Prompt-cache creation token usage broken down by cache lifetime.

      • ephemeral_1h_input_tokens: optional number

        Tokens used to create 1-hour ephemeral cache entries.

      • ephemeral_5m_input_tokens: optional number

        Tokens used to create 5-minute ephemeral cache entries.

    • cache_read_input_tokens: optional number

      Total tokens read from prompt cache.

    • input_tokens: optional number

      Total input tokens consumed across all turns.

    • output_tokens: optional number

      Total output tokens generated across all turns.

• next_page: optional string

  Opaque cursor for the next page. Null when no more results.

Example

curl https://api.anthropic.com/v1/sessions/$SESSION_ID/threads \
    -H 'anthropic-version: 2023-06-01' \
    -H 'anthropic-beta: managed-agents-2026-04-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"

Response

{
  "data": [
    {
      "id": "sthr_011CZkZVWa6oIjw0rgXZpnBt",
      "agent": {
        "id": "agent_011CZkYqphY8vELVzwCUpqiQ",
        "description": "A focused research subagent.",
        "mcp_servers": [
          {
            "name": "example-mcp",
            "type": "url",
            "url": "https://example-server.modelcontextprotocol.io/sse"
          }
        ],
        "model": {
          "id": "claude-sonnet-4-6",
          "speed": "standard"
        },
        "name": "Researcher",
        "skills": [
          {
            "skill_id": "xlsx",
            "type": "anthropic",
            "version": "1"
          }
        ],
        "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.",
        "tools": [
          {
            "configs": [
              {
                "enabled": true,
                "name": "bash",
                "permission_policy": {
                  "type": "always_allow"
                }
              }
            ],
            "default_config": {
              "enabled": true,
              "permission_policy": {
                "type": "always_ask"
              }
            },
            "type": "agent_toolset_20260401"
          }
        ],
        "type": "agent",
        "version": 1
      },
      "archived_at": null,
      "created_at": "2026-03-15T10:00:00Z",
      "parent_thread_id": null,
      "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7",
      "stats": {
        "active_seconds": 0,
        "duration_seconds": 0,
        "startup_seconds": 0
      },
      "status": "idle",
      "type": "session_thread",
      "updated_at": "2026-03-15T10:00:00Z",
      "usage": {
        "cache_creation": {
          "ephemeral_1h_input_tokens": 0,
          "ephemeral_5m_input_tokens": 0
        },
        "cache_read_input_tokens": 0,
        "input_tokens": 0,
        "output_tokens": 0
      }
    }
  ],
  "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo="
}

Get Session Thread

get /v1/sessions/{session_id}/threads/{thread_id}

Get Session Thread

Path Parameters

• session_id: string

• thread_id: string

Header Parameters

• "anthropic-beta": optional array of AnthropicBeta

  Optional header to specify the beta version(s) you want to use.

  • string

  • "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 22 more

    • "message-batches-2024-09-24"

    • "prompt-caching-2024-07-31"

    • "computer-use-2024-10-22"

    • "computer-use-2025-01-24"

    • "pdfs-2024-09-25"

    • "token-counting-2024-11-01"

    • "token-efficient-tools-2025-02-19"

    • "output-128k-2025-02-19"

    • "files-api-2025-04-14"

    • "mcp-client-2025-04-04"

    • "mcp-client-2025-11-20"

    • "dev-full-thinking-2025-05-14"

    • "interleaved-thinking-2025-05-14"

    • "code-execution-2025-05-22"

    • "extended-cache-ttl-2025-04-11"

    • "context-1m-2025-08-07"

    • "context-management-2025-06-27"

    • "model-context-window-exceeded-2025-08-26"

    • "skills-2025-10-02"

    • "fast-mode-2026-02-01"

    • "output-300k-2026-03-24"

    • "user-profiles-2026-03-24"

    • "advisor-tool-2026-03-01"

    • "managed-agents-2026-04-01"

    • "cache-diagnosis-2026-04-07"

Returns

• BetaManagedAgentsSessionThread object { id, agent, archived_at, 8 more }

  An execution thread within a session. Each session has one primary thread plus zero or more child threads spawned by the coordinator.

  • id: string

    Unique identifier for this thread.

  • agent: BetaManagedAgentsSessionThreadAgent

    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.

    • id: string

    • description: string

    • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

      • name: string

      • type: "url"

        • "url"

      • url: string

    • model: BetaManagedAgentsModelConfig

      Model identifier and configuration.

      • id: BetaManagedAgentsModel

        The model that will power your agent.

        See models for additional details and options.

        • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7"

            Frontier intelligence for long-running agents and coding

          • "claude-opus-4-6"

            Most intelligent model for building agents and coding

          • "claude-sonnet-4-6"

            Best combination of speed and intelligence

          • "claude-haiku-4-5"

            Fastest model with near-frontier intelligence

          • "claude-haiku-4-5-20251001"

            Fastest model with near-frontier intelligence

          • "claude-opus-4-5"

            Premium model combining maximum intelligence with practical performance

          • "claude-opus-4-5-20251101"

            Premium model combining maximum intelligence with practical performance

          • "claude-sonnet-4-5"

            High-performance model for agents and coding

          • "claude-sonnet-4-5-20250929"

            High-performance model for agents and coding

        • string

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

    • name: string

    • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

      • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

        A resolved Anthropic-managed skill.

        • skill_id: string

        • type: "anthropic"

          • "anthropic"

        • version: string

      • BetaManagedAgentsCustomSkill object { skill_id, type, version }

        A resolved user-created custom skill.

        • skill_id: string

        • type: "custom"

          • "custom"

        • version: string

    • system: string

    • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

      • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • configs: array of BetaManagedAgentsAgentToolConfig

          • enabled: boolean

          • name: "bash" or "edit" or "read" or 5 more

            Built-in agent tool identifier.

            • "bash"

            • "edit"

            • "read"

            • "write"

            • "glob"

            • "grep"

            • "web_fetch"

            • "web_search"

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

              • type: "always_allow"

                • "always_allow"

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

              • type: "always_ask"

                • "always_ask"

        • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

          Resolved default configuration for agent tools.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • type: "agent_toolset_20260401"

          • "agent_toolset_20260401"

      • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • configs: array of BetaManagedAgentsMCPToolConfig

          • enabled: boolean

          • name: string

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

          Resolved default configuration for all tools from an MCP server.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • mcp_server_name: string

        • type: "mcp_toolset"

          • "mcp_toolset"

      • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

        A custom tool as returned in API responses.

        • description: string

        • input_schema: BetaManagedAgentsCustomToolInputSchema

          JSON Schema for custom tool input parameters.

          • properties: optional map[unknown]

            JSON Schema properties defining the tool's input parameters.

          • required: optional array of string

            List of required property names.

          • type: optional "object"

            Must be 'object' for tool input schemas.

            • "object"

        • name: string

        • type: "custom"

          • "custom"

    • type: "agent"

      • "agent"

    • version: number

  • archived_at: string

    A timestamp in RFC 3339 format

  • created_at: string

    A timestamp in RFC 3339 format

  • parent_thread_id: string

    Parent thread that spawned this thread. Null for the primary thread.

  • session_id: string

    The session this thread belongs to.

  • stats: BetaManagedAgentsSessionThreadStats

    Timing statistics for a session thread.

    • active_seconds: optional number

      Cumulative time in seconds the thread spent actively running. Excludes idle time.

    • duration_seconds: optional number

      Elapsed time since thread creation in seconds. For archived threads, frozen at the final update.

    • startup_seconds: optional number

      Time in seconds for the thread to begin running. Zero for child threads, which start immediately.

  • status: BetaManagedAgentsSessionThreadStatus

    SessionThreadStatus enum

    • "running"

    • "idle"

    • "rescheduling"

    • "terminated"

  • type: "session_thread"

    • "session_thread"

  • updated_at: string

    A timestamp in RFC 3339 format

  • usage: BetaManagedAgentsSessionThreadUsage

    Cumulative token usage for a session thread across all turns.

    • cache_creation: optional BetaManagedAgentsCacheCreationUsage

      Prompt-cache creation token usage broken down by cache lifetime.

      • ephemeral_1h_input_tokens: optional number

        Tokens used to create 1-hour ephemeral cache entries.

      • ephemeral_5m_input_tokens: optional number

        Tokens used to create 5-minute ephemeral cache entries.

    • cache_read_input_tokens: optional number

      Total tokens read from prompt cache.

    • input_tokens: optional number

      Total input tokens consumed across all turns.

    • output_tokens: optional number

      Total output tokens generated across all turns.

Example

curl https://api.anthropic.com/v1/sessions/$SESSION_ID/threads/$THREAD_ID \
    -H 'anthropic-version: 2023-06-01' \
    -H 'anthropic-beta: managed-agents-2026-04-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"

Response

{
  "id": "sthr_011CZkZVWa6oIjw0rgXZpnBt",
  "agent": {
    "id": "agent_011CZkYqphY8vELVzwCUpqiQ",
    "description": "A focused research subagent.",
    "mcp_servers": [
      {
        "name": "example-mcp",
        "type": "url",
        "url": "https://example-server.modelcontextprotocol.io/sse"
      }
    ],
    "model": {
      "id": "claude-sonnet-4-6",
      "speed": "standard"
    },
    "name": "Researcher",
    "skills": [
      {
        "skill_id": "xlsx",
        "type": "anthropic",
        "version": "1"
      }
    ],
    "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.",
    "tools": [
      {
        "configs": [
          {
            "enabled": true,
            "name": "bash",
            "permission_policy": {
              "type": "always_allow"
            }
          }
        ],
        "default_config": {
          "enabled": true,
          "permission_policy": {
            "type": "always_ask"
          }
        },
        "type": "agent_toolset_20260401"
      }
    ],
    "type": "agent",
    "version": 1
  },
  "archived_at": null,
  "created_at": "2026-03-15T10:00:00Z",
  "parent_thread_id": null,
  "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7",
  "stats": {
    "active_seconds": 0,
    "duration_seconds": 0,
    "startup_seconds": 0
  },
  "status": "idle",
  "type": "session_thread",
  "updated_at": "2026-03-15T10:00:00Z",
  "usage": {
    "cache_creation": {
      "ephemeral_1h_input_tokens": 0,
      "ephemeral_5m_input_tokens": 0
    },
    "cache_read_input_tokens": 0,
    "input_tokens": 0,
    "output_tokens": 0
  }
}

Archive Session Thread

post /v1/sessions/{session_id}/threads/{thread_id}/archive

Archive Session Thread

Path Parameters

• session_id: string

• thread_id: string

Header Parameters

• "anthropic-beta": optional array of AnthropicBeta

  Optional header to specify the beta version(s) you want to use.

  • string

  • "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 22 more

    • "message-batches-2024-09-24"

    • "prompt-caching-2024-07-31"

    • "computer-use-2024-10-22"

    • "computer-use-2025-01-24"

    • "pdfs-2024-09-25"

    • "token-counting-2024-11-01"

    • "token-efficient-tools-2025-02-19"

    • "output-128k-2025-02-19"

    • "files-api-2025-04-14"

    • "mcp-client-2025-04-04"

    • "mcp-client-2025-11-20"

    • "dev-full-thinking-2025-05-14"

    • "interleaved-thinking-2025-05-14"

    • "code-execution-2025-05-22"

    • "extended-cache-ttl-2025-04-11"

    • "context-1m-2025-08-07"

    • "context-management-2025-06-27"

    • "model-context-window-exceeded-2025-08-26"

    • "skills-2025-10-02"

    • "fast-mode-2026-02-01"

    • "output-300k-2026-03-24"

    • "user-profiles-2026-03-24"

    • "advisor-tool-2026-03-01"

    • "managed-agents-2026-04-01"

    • "cache-diagnosis-2026-04-07"

Returns

• BetaManagedAgentsSessionThread object { id, agent, archived_at, 8 more }

  An execution thread within a session. Each session has one primary thread plus zero or more child threads spawned by the coordinator.

  • id: string

    Unique identifier for this thread.

  • agent: BetaManagedAgentsSessionThreadAgent

    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.

    • id: string

    • description: string

    • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

      • name: string

      • type: "url"

        • "url"

      • url: string

    • model: BetaManagedAgentsModelConfig

      Model identifier and configuration.

      • id: BetaManagedAgentsModel

        The model that will power your agent.

        See models for additional details and options.

        • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7"

            Frontier intelligence for long-running agents and coding

          • "claude-opus-4-6"

            Most intelligent model for building agents and coding

          • "claude-sonnet-4-6"

            Best combination of speed and intelligence

          • "claude-haiku-4-5"

            Fastest model with near-frontier intelligence

          • "claude-haiku-4-5-20251001"

            Fastest model with near-frontier intelligence

          • "claude-opus-4-5"

            Premium model combining maximum intelligence with practical performance

          • "claude-opus-4-5-20251101"

            Premium model combining maximum intelligence with practical performance

          • "claude-sonnet-4-5"

            High-performance model for agents and coding

          • "claude-sonnet-4-5-20250929"

            High-performance model for agents and coding

        • string

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

    • name: string

    • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

      • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

        A resolved Anthropic-managed skill.

        • skill_id: string

        • type: "anthropic"

          • "anthropic"

        • version: string

      • BetaManagedAgentsCustomSkill object { skill_id, type, version }

        A resolved user-created custom skill.

        • skill_id: string

        • type: "custom"

          • "custom"

        • version: string

    • system: string

    • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

      • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • configs: array of BetaManagedAgentsAgentToolConfig

          • enabled: boolean

          • name: "bash" or "edit" or "read" or 5 more

            Built-in agent tool identifier.

            • "bash"

            • "edit"

            • "read"

            • "write"

            • "glob"

            • "grep"

            • "web_fetch"

            • "web_search"

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

              • type: "always_allow"

                • "always_allow"

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

              • type: "always_ask"

                • "always_ask"

        • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

          Resolved default configuration for agent tools.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • type: "agent_toolset_20260401"

          • "agent_toolset_20260401"

      • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • configs: array of BetaManagedAgentsMCPToolConfig

          • enabled: boolean

          • name: string

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

          Resolved default configuration for all tools from an MCP server.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • mcp_server_name: string

        • type: "mcp_toolset"

          • "mcp_toolset"

      • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

        A custom tool as returned in API responses.

        • description: string

        • input_schema: BetaManagedAgentsCustomToolInputSchema

          JSON Schema for custom tool input parameters.

          • properties: optional map[unknown]

            JSON Schema properties defining the tool's input parameters.

          • required: optional array of string

            List of required property names.

          • type: optional "object"

            Must be 'object' for tool input schemas.

            • "object"

        • name: string

        • type: "custom"

          • "custom"

    • type: "agent"

      • "agent"

    • version: number

  • archived_at: string

    A timestamp in RFC 3339 format

  • created_at: string

    A timestamp in RFC 3339 format

  • parent_thread_id: string

    Parent thread that spawned this thread. Null for the primary thread.

  • session_id: string

    The session this thread belongs to.

  • stats: BetaManagedAgentsSessionThreadStats

    Timing statistics for a session thread.

    • active_seconds: optional number

      Cumulative time in seconds the thread spent actively running. Excludes idle time.

    • duration_seconds: optional number

      Elapsed time since thread creation in seconds. For archived threads, frozen at the final update.

    • startup_seconds: optional number

      Time in seconds for the thread to begin running. Zero for child threads, which start immediately.

  • status: BetaManagedAgentsSessionThreadStatus

    SessionThreadStatus enum

    • "running"

    • "idle"

    • "rescheduling"

    • "terminated"

  • type: "session_thread"

    • "session_thread"

  • updated_at: string

    A timestamp in RFC 3339 format

  • usage: BetaManagedAgentsSessionThreadUsage

    Cumulative token usage for a session thread across all turns.

    • cache_creation: optional BetaManagedAgentsCacheCreationUsage

      Prompt-cache creation token usage broken down by cache lifetime.

      • ephemeral_1h_input_tokens: optional number

        Tokens used to create 1-hour ephemeral cache entries.

      • ephemeral_5m_input_tokens: optional number

        Tokens used to create 5-minute ephemeral cache entries.

    • cache_read_input_tokens: optional number

      Total tokens read from prompt cache.

    • input_tokens: optional number

      Total input tokens consumed across all turns.

    • output_tokens: optional number

      Total output tokens generated across all turns.

Example

curl https://api.anthropic.com/v1/sessions/$SESSION_ID/threads/$THREAD_ID/archive \
    -X POST \
    -H 'anthropic-version: 2023-06-01' \
    -H 'anthropic-beta: managed-agents-2026-04-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"

Response

{
  "id": "sthr_011CZkZVWa6oIjw0rgXZpnBt",
  "agent": {
    "id": "agent_011CZkYqphY8vELVzwCUpqiQ",
    "description": "A focused research subagent.",
    "mcp_servers": [
      {
        "name": "example-mcp",
        "type": "url",
        "url": "https://example-server.modelcontextprotocol.io/sse"
      }
    ],
    "model": {
      "id": "claude-sonnet-4-6",
      "speed": "standard"
    },
    "name": "Researcher",
    "skills": [
      {
        "skill_id": "xlsx",
        "type": "anthropic",
        "version": "1"
      }
    ],
    "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.",
    "tools": [
      {
        "configs": [
          {
            "enabled": true,
            "name": "bash",
            "permission_policy": {
              "type": "always_allow"
            }
          }
        ],
        "default_config": {
          "enabled": true,
          "permission_policy": {
            "type": "always_ask"
          }
        },
        "type": "agent_toolset_20260401"
      }
    ],
    "type": "agent",
    "version": 1
  },
  "archived_at": null,
  "created_at": "2026-03-15T10:00:00Z",
  "parent_thread_id": null,
  "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7",
  "stats": {
    "active_seconds": 0,
    "duration_seconds": 0,
    "startup_seconds": 0
  },
  "status": "idle",
  "type": "session_thread",
  "updated_at": "2026-03-15T10:00:00Z",
  "usage": {
    "cache_creation": {
      "ephemeral_1h_input_tokens": 0,
      "ephemeral_5m_input_tokens": 0
    },
    "cache_read_input_tokens": 0,
    "input_tokens": 0,
    "output_tokens": 0
  }
}

Domain Types

Beta Managed Agents Session Thread

• BetaManagedAgentsSessionThread object { id, agent, archived_at, 8 more }

  An execution thread within a session. Each session has one primary thread plus zero or more child threads spawned by the coordinator.

  • id: string

    Unique identifier for this thread.

  • agent: BetaManagedAgentsSessionThreadAgent

    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.

    • id: string

    • description: string

    • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

      • name: string

      • type: "url"

        • "url"

      • url: string

    • model: BetaManagedAgentsModelConfig

      Model identifier and configuration.

      • id: BetaManagedAgentsModel

        The model that will power your agent.

        See models for additional details and options.

        • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7"

            Frontier intelligence for long-running agents and coding

          • "claude-opus-4-6"

            Most intelligent model for building agents and coding

          • "claude-sonnet-4-6"

            Best combination of speed and intelligence

          • "claude-haiku-4-5"

            Fastest model with near-frontier intelligence

          • "claude-haiku-4-5-20251001"

            Fastest model with near-frontier intelligence

          • "claude-opus-4-5"

            Premium model combining maximum intelligence with practical performance

          • "claude-opus-4-5-20251101"

            Premium model combining maximum intelligence with practical performance

          • "claude-sonnet-4-5"

            High-performance model for agents and coding

          • "claude-sonnet-4-5-20250929"

            High-performance model for agents and coding

        • string

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

    • name: string

    • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

      • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

        A resolved Anthropic-managed skill.

        • skill_id: string

        • type: "anthropic"

          • "anthropic"

        • version: string

      • BetaManagedAgentsCustomSkill object { skill_id, type, version }

        A resolved user-created custom skill.

        • skill_id: string

        • type: "custom"

          • "custom"

        • version: string

    • system: string

    • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

      • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • configs: array of BetaManagedAgentsAgentToolConfig

          • enabled: boolean

          • name: "bash" or "edit" or "read" or 5 more

            Built-in agent tool identifier.

            • "bash"

            • "edit"

            • "read"

            • "write"

            • "glob"

            • "grep"

            • "web_fetch"

            • "web_search"

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

              • type: "always_allow"

                • "always_allow"

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

              • type: "always_ask"

                • "always_ask"

        • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

          Resolved default configuration for agent tools.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • type: "agent_toolset_20260401"

          • "agent_toolset_20260401"

      • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • configs: array of BetaManagedAgentsMCPToolConfig

          • enabled: boolean

          • name: string

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

          Resolved default configuration for all tools from an MCP server.

          • enabled: boolean

          • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

            Permission policy for tool execution.

            • BetaManagedAgentsAlwaysAllowPolicy object { type }

              Tool calls are automatically approved without user confirmation.

            • BetaManagedAgentsAlwaysAskPolicy object { type }

              Tool calls require user confirmation before execution.

        • mcp_server_name: string

        • type: "mcp_toolset"

          • "mcp_toolset"

      • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

        A custom tool as returned in API responses.

        • description: string

        • input_schema: BetaManagedAgentsCustomToolInputSchema

          JSON Schema for custom tool input parameters.

          • properties: optional map[unknown]

            JSON Schema properties defining the tool's input parameters.

          • required: optional array of string

            List of required property names.

          • type: optional "object"

            Must be 'object' for tool input schemas.

            • "object"

        • name: string

        • type: "custom"

          • "custom"

    • type: "agent"

      • "agent"

    • version: number

  • archived_at: string

    A timestamp in RFC 3339 format

  • created_at: string

    A timestamp in RFC 3339 format

  • parent_thread_id: string

    Parent thread that spawned this thread. Null for the primary thread.

  • session_id: string

    The session this thread belongs to.

  • stats: BetaManagedAgentsSessionThreadStats

    Timing statistics for a session thread.

    • active_seconds: optional number

      Cumulative time in seconds the thread spent actively running. Excludes idle time.

    • duration_seconds: optional number

      Elapsed time since thread creation in seconds. For archived threads, frozen at the final update.

    • startup_seconds: optional number

      Time in seconds for the thread to begin running. Zero for child threads, which start immediately.

  • status: BetaManagedAgentsSessionThreadStatus

    SessionThreadStatus enum

    • "running"

    • "idle"

    • "rescheduling"

    • "terminated"

  • type: "session_thread"

    • "session_thread"

  • updated_at: string

    A timestamp in RFC 3339 format

  • usage: BetaManagedAgentsSessionThreadUsage

    Cumulative token usage for a session thread across all turns.

    • cache_creation: optional BetaManagedAgentsCacheCreationUsage

      Prompt-cache creation token usage broken down by cache lifetime.

      • ephemeral_1h_input_tokens: optional number

        Tokens used to create 1-hour ephemeral cache entries.

      • ephemeral_5m_input_tokens: optional number

        Tokens used to create 5-minute ephemeral cache entries.

    • cache_read_input_tokens: optional number

      Total tokens read from prompt cache.

    • input_tokens: optional number

      Total input tokens consumed across all turns.

    • output_tokens: optional number

      Total output tokens generated across all turns.

Beta Managed Agents Session Thread Stats

• BetaManagedAgentsSessionThreadStats object { active_seconds, duration_seconds, startup_seconds }

  Timing statistics for a session thread.

  • active_seconds: optional number

    Cumulative time in seconds the thread spent actively running. Excludes idle time.

  • duration_seconds: optional number

    Elapsed time since thread creation in seconds. For archived threads, frozen at the final update.

  • startup_seconds: optional number

    Time in seconds for the thread to begin running. Zero for child threads, which start immediately.

Beta Managed Agents Session Thread Status

• BetaManagedAgentsSessionThreadStatus = "running" or "idle" or "rescheduling" or "terminated"

  SessionThreadStatus enum

  • "running"

  • "idle"

  • "rescheduling"

  • "terminated"

Beta Managed Agents Session Thread Usage

• BetaManagedAgentsSessionThreadUsage object { cache_creation, cache_read_input_tokens, input_tokens, output_tokens }

  Cumulative token usage for a session thread across all turns.

  • cache_creation: optional BetaManagedAgentsCacheCreationUsage

    Prompt-cache creation token usage broken down by cache lifetime.

    • ephemeral_1h_input_tokens: optional number

      Tokens used to create 1-hour ephemeral cache entries.

    • ephemeral_5m_input_tokens: optional number

      Tokens used to create 5-minute ephemeral cache entries.

  • cache_read_input_tokens: optional number

    Total tokens read from prompt cache.

  • input_tokens: optional number

    Total input tokens consumed across all turns.

  • output_tokens: optional number

    Total output tokens generated across all turns.

Beta Managed Agents Stream Session Thread Events

• BetaManagedAgentsStreamSessionThreadEvents = BetaManagedAgentsUserMessageEvent or BetaManagedAgentsUserInterruptEvent or BetaManagedAgentsUserToolConfirmationEvent or 30 more

  Server-sent event in a single thread's stream.

  • BetaManagedAgentsUserMessageEvent object { id, content, type, processed_at }

    A user message event in the session conversation.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Array of content blocks comprising the user message.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

        • text: string

          The text content.

        • type: "text"

          • "text"

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

        • source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource

          Union type for image source variants.

          • BetaManagedAgentsBase64ImageSource object { data, media_type, type }

            Base64-encoded image data.

            • data: string

              Base64-encoded image data.

            • media_type: string

              MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp").

            • type: "base64"

              • "base64"

          • BetaManagedAgentsURLImageSource object { type, url }

            Image referenced by URL.

            • type: "url"

              • "url"

            • url: string

              URL of the image to fetch.

          • BetaManagedAgentsFileImageSource object { file_id, type }

            Image referenced by file ID.

            • file_id: string

              ID of a previously uploaded file.

            • type: "file"

              • "file"

        • type: "image"

          • "image"

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

        • source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource

          Union type for document source variants.

          • BetaManagedAgentsBase64DocumentSource object { data, media_type, type }

            Base64-encoded document data.

            • data: string

              Base64-encoded document data.

            • media_type: string

              MIME type of the document (e.g., "application/pdf").

            • type: "base64"

              • "base64"

          • BetaManagedAgentsPlainTextDocumentSource object { data, media_type, type }

            Plain text document content.

            • data: string

              The plain text content.

            • media_type: "text/plain"

              MIME type of the text content. Must be "text/plain".

              • "text/plain"

            • type: "text"

              • "text"

          • BetaManagedAgentsURLDocumentSource object { type, url }

            Document referenced by URL.

            • type: "url"

              • "url"

            • url: string

              URL of the document to fetch.

          • BetaManagedAgentsFileDocumentSource object { file_id, type }

            Document referenced by file ID.

            • file_id: string

              ID of a previously uploaded file.

            • type: "file"

              • "file"

        • type: "document"

          • "document"

        • context: optional string

          Additional context about the document for the model.

        • title: optional string

          The title of the document.

    • type: "user.message"

      • "user.message"

    • processed_at: optional string

      A timestamp in RFC 3339 format

  • BetaManagedAgentsUserInterruptEvent object { id, type, processed_at, session_thread_id }

    An interrupt event that pauses agent execution and returns control to the user.

    • id: string

      Unique identifier for this event.

    • type: "user.interrupt"

      • "user.interrupt"

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread.

  • BetaManagedAgentsUserToolConfirmationEvent object { id, result, tool_use_id, 4 more }

    A tool confirmation event that approves or denies a pending tool execution.

    • id: string

      Unique identifier for this event.

    • result: "allow" or "deny"

      UserToolConfirmationResult enum

      • "allow"

      • "deny"

    • tool_use_id: string

      The id of the agent.tool_use or agent.mcp_tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.tool_confirmation"

      • "user.tool_confirmation"

    • deny_message: optional string

      Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      When set, the confirmation routes to this subagent's thread rather than the primary. Echo this from the session_thread_id on the agent.tool_use or agent.mcp_tool_use event that prompted the approval.

  • BetaManagedAgentsUserCustomToolResultEvent object { id, custom_tool_use_id, type, 4 more }

    Event sent by the client providing the result of a custom tool execution.

    • id: string

      Unique identifier for this event.

    • custom_tool_use_id: string

      The id of the agent.custom_tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.custom_tool_result"

      • "user.custom_tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

        • citations: BetaManagedAgentsSearchResultCitations

          Citation settings for a search result.

          • enabled: boolean

            Whether citations are enabled for this search result.

        • content: array of BetaManagedAgentsSearchResultContent

          Array of text content blocks from the search result.

          • text: string

            The text content.

          • type: "text"

            • "text"

        • source: string

          The URL source of the search result.

        • title: string

          The title of the search result.

        • type: "search_result"

          • "search_result"

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      Routes this result to a subagent thread. Copy from the agent.custom_tool_use event's session_thread_id.

  • BetaManagedAgentsAgentCustomToolUseEvent object { id, input, name, 3 more }

    Event emitted when the agent calls a custom tool. The session goes idle until the client sends a user.custom_tool_result event with the result.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • name: string

      Name of the custom tool being called.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.custom_tool_use"

      • "agent.custom_tool_use"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Echo this on a user.custom_tool_result event to route the result back.

  • BetaManagedAgentsAgentMessageEvent object { id, content, processed_at, type }

    An agent response event in the session conversation.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock

      Array of text blocks comprising the agent response.

      • text: string

        The text content.

      • type: "text"

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.message"

      • "agent.message"

  • BetaManagedAgentsAgentThinkingEvent object { id, processed_at, type }

    Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thinking"

      • "agent.thinking"

  • BetaManagedAgentsAgentMCPToolUseEvent object { id, input, mcp_server_name, 5 more }

    Event emitted when the agent invokes a tool provided by an MCP server.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • mcp_server_name: string

      Name of the MCP server providing the tool.

    • name: string

      Name of the MCP tool being used.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.mcp_tool_use"

      • "agent.mcp_tool_use"

    • evaluated_permission: optional "allow" or "ask" or "deny"

      AgentEvaluatedPermission enum

      • "allow"

      • "ask"

      • "deny"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Echo this on a user.tool_confirmation event to route the approval back.

  • BetaManagedAgentsAgentMCPToolResultEvent object { id, mcp_tool_use_id, processed_at, 3 more }

    Event representing the result of an MCP tool execution.

    • id: string

      Unique identifier for this event.

    • mcp_tool_use_id: string

      The id of the agent.mcp_tool_use event this result corresponds to.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.mcp_tool_result"

      • "agent.mcp_tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

  • BetaManagedAgentsAgentToolUseEvent object { id, input, name, 4 more }

    Event emitted when the agent invokes a built-in agent tool.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • name: string

      Name of the agent tool being used.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.tool_use"

      • "agent.tool_use"

    • evaluated_permission: optional "allow" or "ask" or "deny"

      AgentEvaluatedPermission enum

      • "allow"

      • "ask"

      • "deny"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Echo this on a user.tool_confirmation event to route the approval back.

  • BetaManagedAgentsAgentToolResultEvent object { id, processed_at, tool_use_id, 3 more }

    Event representing the result of an agent tool execution.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • tool_use_id: string

      The id of the agent.tool_use event this result corresponds to.

    • type: "agent.tool_result"

      • "agent.tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

  • BetaManagedAgentsAgentThreadMessageReceivedEvent object { id, content, from_session_thread_id, 3 more }

    Delivery event written to the target thread's input stream when an agent-to-agent message arrives.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Message content blocks.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

    • from_session_thread_id: string

      Public sthr_ ID of the thread that sent the message.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thread_message_received"

      • "agent.thread_message_received"

    • from_agent_name: optional string

      Name of the callable agent this message came from. Absent when received from the primary agent.

  • BetaManagedAgentsAgentThreadMessageSentEvent object { id, content, processed_at, 3 more }

    Observability event emitted to the sender's output stream when an agent-to-agent message is sent.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Message content blocks.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

    • processed_at: string

      A timestamp in RFC 3339 format

    • to_session_thread_id: string

      Public sthr_ ID of the thread the message was sent to.

    • type: "agent.thread_message_sent"

      • "agent.thread_message_sent"

    • to_agent_name: optional string

      Name of the callable agent this message was sent to. Absent when sent to the primary agent.

  • BetaManagedAgentsAgentThreadContextCompactedEvent object { id, processed_at, type }

    Indicates that context compaction (summarization) occurred during the session.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thread_context_compacted"

      • "agent.thread_context_compacted"

  • BetaManagedAgentsSessionErrorEvent object { id, error, processed_at, type }

    An error event indicating a problem occurred during session execution.

    • id: string

      Unique identifier for this event.

    • error: BetaManagedAgentsUnknownError or BetaManagedAgentsModelOverloadedError or BetaManagedAgentsModelRateLimitedError or 4 more

      An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on retry_status and message alone.

      • BetaManagedAgentsUnknownError object { message, retry_status, type }

        An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on retry_status and message alone.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

            • type: "retrying"

              • "retrying"

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

            • type: "exhausted"

              • "exhausted"

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

            • type: "terminal"

              • "terminal"

        • type: "unknown_error"

          • "unknown_error"

      • BetaManagedAgentsModelOverloadedError object { message, retry_status, type }

        The model is currently overloaded. Emitted after automatic retries are exhausted.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_overloaded_error"

          • "model_overloaded_error"

      • BetaManagedAgentsModelRateLimitedError object { message, retry_status, type }

        The model request was rate-limited.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_rate_limited_error"

          • "model_rate_limited_error"

      • BetaManagedAgentsModelRequestFailedError object { message, retry_status, type }

        A model request failed for a reason other than overload or rate-limiting.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_request_failed_error"

          • "model_request_failed_error"

      • BetaManagedAgentsMCPConnectionFailedError object { mcp_server_name, message, retry_status, type }

        Failed to connect to an MCP server.

        • mcp_server_name: string

          Name of the MCP server that failed to connect.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "mcp_connection_failed_error"

          • "mcp_connection_failed_error"

      • BetaManagedAgentsMCPAuthenticationFailedError object { mcp_server_name, message, retry_status, type }

        Authentication to an MCP server failed.

        • mcp_server_name: string

          Name of the MCP server that failed authentication.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "mcp_authentication_failed_error"

          • "mcp_authentication_failed_error"

      • BetaManagedAgentsBillingError object { message, retry_status, type }

        The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "billing_error"

          • "billing_error"

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.error"

      • "session.error"

  • BetaManagedAgentsSessionStatusRescheduledEvent object { id, processed_at, type }

    Indicates the session is recovering from an error state and is rescheduled for execution.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_rescheduled"

      • "session.status_rescheduled"

  • BetaManagedAgentsSessionStatusRunningEvent object { id, processed_at, type }

    Indicates the session is actively running and the agent is working.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_running"

      • "session.status_running"

  • BetaManagedAgentsSessionStatusIdleEvent object { id, processed_at, stop_reason, type }

    Indicates the agent has paused and is awaiting user input.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted

      The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionEndTurn object { type }

        The agent completed its turn naturally and is ready for the next user message.

        • type: "end_turn"

          • "end_turn"

      • BetaManagedAgentsSessionRequiresAction object { event_ids, type }

        The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running.

        • event_ids: array of string

          The ids of events the agent is blocked on. Resolving fewer than all re-emits session.status_idle with the remainder.

        • type: "requires_action"

          • "requires_action"

      • BetaManagedAgentsSessionRetriesExhausted object { type }

        The turn ended because the retry budget was exhausted (max_iterations hit or an error escalated to retry_status: 'exhausted').

        • type: "retries_exhausted"

          • "retries_exhausted"

    • type: "session.status_idle"

      • "session.status_idle"

  • BetaManagedAgentsSessionStatusTerminatedEvent object { id, processed_at, type }

    Indicates the session has terminated, either due to an error or completion.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_terminated"

      • "session.status_terminated"

  • BetaManagedAgentsSessionThreadCreatedEvent object { id, agent_name, processed_at, 2 more }

    Emitted when a subagent is spawned as a new thread. Written to the parent thread's output stream so clients observing the session see child creation.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the callable agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the newly created thread.

    • type: "session.thread_created"

      • "session.thread_created"

  • BetaManagedAgentsSpanOutcomeEvaluationStartEvent object { id, iteration, outcome_id, 2 more }

    Emitted when an outcome evaluation cycle begins.

    • id: string

      Unique identifier for this event.

    • iteration: number

      0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.outcome_evaluation_start"

      • "span.outcome_evaluation_start"

  • BetaManagedAgentsSpanOutcomeEvaluationEndEvent object { id, explanation, iteration, 6 more }

    Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of needs_revision means another evaluation cycle follows; satisfied, max_iterations_reached, failed, or interrupted are terminal — no further evaluation cycles follow.

    • id: string

      Unique identifier for this event.

    • explanation: string

      Human-readable explanation of the verdict. For needs_revision, describes which criteria failed and why.

    • iteration: number

      0-indexed revision cycle, matching the corresponding span.outcome_evaluation_start.

    • outcome_evaluation_start_id: string

      The id of the corresponding span.outcome_evaluation_start event.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • result: string

      Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress.

    • type: "span.outcome_evaluation_end"

      • "span.outcome_evaluation_end"

    • usage: BetaManagedAgentsSpanModelUsage

      Token usage for a single model request.

      • cache_creation_input_tokens: number

        Tokens used to create prompt cache in this request.

      • cache_read_input_tokens: number

        Tokens read from prompt cache in this request.

      • input_tokens: number

        Input tokens consumed by this request.

      • output_tokens: number

        Output tokens generated by this request.

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

  • BetaManagedAgentsSpanModelRequestStartEvent object { id, processed_at, type }

    Emitted when a model request is initiated by the agent.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.model_request_start"

      • "span.model_request_start"

  • BetaManagedAgentsSpanModelRequestEndEvent object { id, is_error, model_request_start_id, 3 more }

    Emitted when a model request completes.

    • id: string

      Unique identifier for this event.

    • is_error: boolean

      Whether the model request resulted in an error.

    • model_request_start_id: string

      The id of the corresponding span.model_request_start event.

    • model_usage: BetaManagedAgentsSpanModelUsage

      Token usage for a single model request.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.model_request_end"

      • "span.model_request_end"

  • BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent object { id, iteration, outcome_id, 2 more }

    Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding span.outcome_evaluation_start and span.outcome_evaluation_end events.

    • id: string

      Unique identifier for this event.

    • iteration: number

      0-indexed revision cycle, matching the corresponding span.outcome_evaluation_start.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.outcome_evaluation_ongoing"

      • "span.outcome_evaluation_ongoing"

  • BetaManagedAgentsUserDefineOutcomeEvent object { id, description, max_iterations, 4 more }

    Echo of a user.define_outcome input event. Carries the server-generated outcome_id that subsequent span.outcome_evaluation_* events reference.

    • id: string

      Unique identifier for this event.

    • description: string

      What the agent should produce. Copied from the input event.

    • max_iterations: number

      Evaluate-then-revise cycles before giving up. Default 3, max 20.

    • outcome_id: string

      Server-generated outc_ ID for this outcome. Referenced by span.outcome_evaluation_* events and the session's outcome_evaluations list.

    • processed_at: string

      A timestamp in RFC 3339 format

    • rubric: BetaManagedAgentsFileRubric or BetaManagedAgentsTextRubric

      Rubric for grading the quality of an outcome.

      • BetaManagedAgentsFileRubric object { file_id, type }

        Rubric referenced by a file uploaded via the Files API.

        • file_id: string

          ID of the rubric file.

        • type: "file"

          • "file"

      • BetaManagedAgentsTextRubric object { content, type }

        Rubric content provided inline as text.

        • content: string

          Rubric content. Plain text or markdown — the grader treats it as freeform text.

        • type: "text"

          • "text"

    • type: "user.define_outcome"

      • "user.define_outcome"

  • BetaManagedAgentsSessionDeletedEvent object { id, processed_at, type }

    Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.deleted"

      • "session.deleted"

  • BetaManagedAgentsSessionThreadStatusRunningEvent object { id, agent_name, processed_at, 2 more }

    A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that started running.

    • type: "session.thread_status_running"

      • "session.thread_status_running"

  • BetaManagedAgentsSessionThreadStatusIdleEvent object { id, agent_name, processed_at, 3 more }

    A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that went idle.

    • stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted

      The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionEndTurn object { type }

        The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionRequiresAction object { event_ids, type }

        The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running.

      • BetaManagedAgentsSessionRetriesExhausted object { type }

        The turn ended because the retry budget was exhausted (max_iterations hit or an error escalated to retry_status: 'exhausted').

    • type: "session.thread_status_idle"

      • "session.thread_status_idle"

  • BetaManagedAgentsSessionThreadStatusTerminatedEvent object { id, agent_name, processed_at, 2 more }

    A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that terminated.

    • type: "session.thread_status_terminated"

      • "session.thread_status_terminated"

  • BetaManagedAgentsUserToolResultEvent object { id, tool_use_id, type, 4 more }

    Event sent by the client providing the result of an agent-toolset tool execution. Only valid on self_hosted environments, where sandbox-routed tools are executed by the client rather than the server.

    • id: string

      Unique identifier for this event.

    • tool_use_id: string

      The id of the agent.tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.tool_result"

      • "user.tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      Routes this result to a subagent thread. Copy from the agent.tool_use event's session_thread_id.

  • BetaManagedAgentsSessionThreadStatusRescheduledEvent object { id, agent_name, processed_at, 2 more }

    A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that is retrying.

    • type: "session.thread_status_rescheduled"

      • "session.thread_status_rescheduled"

  • BetaManagedAgentsSessionUpdatedEvent object { id, processed_at, type, 3 more }

    Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.updated"

      • "session.updated"

    • agent: optional BetaManagedAgentsSessionAgent

      Resolved agent definition for a session. Snapshot of the agent at session creation time.

      • id: string

      • description: string

      • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

        • name: string

        • type: "url"

          • "url"

        • url: string

      • model: BetaManagedAgentsModelConfig

        Model identifier and configuration.

        • id: BetaManagedAgentsModel

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

            The model that will power your agent.

            See models for additional details and options.

            • "claude-opus-4-7"

              Frontier intelligence for long-running agents and coding

            • "claude-opus-4-6"

              Most intelligent model for building agents and coding

            • "claude-sonnet-4-6"

              Best combination of speed and intelligence

            • "claude-haiku-4-5"

              Fastest model with near-frontier intelligence

            • "claude-haiku-4-5-20251001"

              Fastest model with near-frontier intelligence

            • "claude-opus-4-5"

              Premium model combining maximum intelligence with practical performance

            • "claude-opus-4-5-20251101"

              Premium model combining maximum intelligence with practical performance

            • "claude-sonnet-4-5"

              High-performance model for agents and coding

            • "claude-sonnet-4-5-20250929"

              High-performance model for agents and coding

          • string

        • speed: optional "standard" or "fast"

          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.

          • "standard"

          • "fast"

      • multiagent: BetaManagedAgentsSessionMultiagentCoordinator

        Resolved coordinator topology with full agent definitions for each roster member.

        • agents: array of BetaManagedAgentsSessionThreadAgent

          Full agent definitions the coordinator may spawn as session threads.

          • id: string

          • description: string

          • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

            • name: string

            • type: "url"

            • url: string

          • model: BetaManagedAgentsModelConfig

            Model identifier and configuration.

          • name: string

          • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

            • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

              A resolved Anthropic-managed skill.

              • skill_id: string

              • type: "anthropic"

                • "anthropic"

              • version: string

            • BetaManagedAgentsCustomSkill object { skill_id, type, version }

              A resolved user-created custom skill.

              • skill_id: string

              • type: "custom"

                • "custom"

              • version: string

          • system: string

          • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

            • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

              • configs: array of BetaManagedAgentsAgentToolConfig

                • enabled: boolean

                • name: "bash" or "edit" or "read" or 5 more

                  Built-in agent tool identifier.

                  • "bash"

                  • "edit"

                  • "read"

                  • "write"

                  • "glob"

                  • "grep"

                  • "web_fetch"

                  • "web_search"

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                    • type: "always_allow"

                      • "always_allow"

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

                    • type: "always_ask"

                      • "always_ask"

              • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

                Resolved default configuration for agent tools.

                • enabled: boolean

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • type: "agent_toolset_20260401"

                • "agent_toolset_20260401"

            • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

              • configs: array of BetaManagedAgentsMCPToolConfig

                • enabled: boolean

                • name: string

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

                Resolved default configuration for all tools from an MCP server.

                • enabled: boolean

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • mcp_server_name: string

              • type: "mcp_toolset"

                • "mcp_toolset"

            • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

              A custom tool as returned in API responses.

              • description: string

              • input_schema: BetaManagedAgentsCustomToolInputSchema

                JSON Schema for custom tool input parameters.

                • properties: optional map[unknown]

                  JSON Schema properties defining the tool's input parameters.

                • required: optional array of string

                  List of required property names.

                • type: optional "object"

                  Must be 'object' for tool input schemas.

                  • "object"

              • name: string

              • type: "custom"

                • "custom"

          • type: "agent"

            • "agent"

          • version: number

        • type: "coordinator"

          • "coordinator"

      • name: string

      • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

        • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

          A resolved Anthropic-managed skill.

        • BetaManagedAgentsCustomSkill object { skill_id, type, version }

          A resolved user-created custom skill.

      • system: string

      • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

        • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

          A custom tool as returned in API responses.

      • type: "agent"

        • "agent"

      • version: number

    • metadata: optional map[string]

      The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty.

    • title: optional string

      The session's new title. Present only when the update changed it.

Events

List Session Thread Events

get /v1/sessions/{session_id}/threads/{thread_id}/events

List Session Thread Events

Path Parameters

• session_id: string

• thread_id: string

Query Parameters

• limit: optional number

  Query parameter for limit

• page: optional string

  Query parameter for page

Header Parameters

• "anthropic-beta": optional array of AnthropicBeta

  Optional header to specify the beta version(s) you want to use.

  • string

  • "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 22 more

    • "message-batches-2024-09-24"

    • "prompt-caching-2024-07-31"

    • "computer-use-2024-10-22"

    • "computer-use-2025-01-24"

    • "pdfs-2024-09-25"

    • "token-counting-2024-11-01"

    • "token-efficient-tools-2025-02-19"

    • "output-128k-2025-02-19"

    • "files-api-2025-04-14"

    • "mcp-client-2025-04-04"

    • "mcp-client-2025-11-20"

    • "dev-full-thinking-2025-05-14"

    • "interleaved-thinking-2025-05-14"

    • "code-execution-2025-05-22"

    • "extended-cache-ttl-2025-04-11"

    • "context-1m-2025-08-07"

    • "context-management-2025-06-27"

    • "model-context-window-exceeded-2025-08-26"

    • "skills-2025-10-02"

    • "fast-mode-2026-02-01"

    • "output-300k-2026-03-24"

    • "user-profiles-2026-03-24"

    • "advisor-tool-2026-03-01"

    • "managed-agents-2026-04-01"

    • "cache-diagnosis-2026-04-07"

Returns

• data: optional array of BetaManagedAgentsSessionEvent

  Events for the thread, ordered by created_at.

  • BetaManagedAgentsUserMessageEvent object { id, content, type, processed_at }

    A user message event in the session conversation.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Array of content blocks comprising the user message.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

        • text: string

          The text content.

        • type: "text"

          • "text"

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

        • source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource

          Union type for image source variants.

          • BetaManagedAgentsBase64ImageSource object { data, media_type, type }

            Base64-encoded image data.

            • data: string

              Base64-encoded image data.

            • media_type: string

              MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp").

            • type: "base64"

              • "base64"

          • BetaManagedAgentsURLImageSource object { type, url }

            Image referenced by URL.

            • type: "url"

              • "url"

            • url: string

              URL of the image to fetch.

          • BetaManagedAgentsFileImageSource object { file_id, type }

            Image referenced by file ID.

            • file_id: string

              ID of a previously uploaded file.

            • type: "file"

              • "file"

        • type: "image"

          • "image"

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

        • source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource

          Union type for document source variants.

          • BetaManagedAgentsBase64DocumentSource object { data, media_type, type }

            Base64-encoded document data.

            • data: string

              Base64-encoded document data.

            • media_type: string

              MIME type of the document (e.g., "application/pdf").

            • type: "base64"

              • "base64"

          • BetaManagedAgentsPlainTextDocumentSource object { data, media_type, type }

            Plain text document content.

            • data: string

              The plain text content.

            • media_type: "text/plain"

              MIME type of the text content. Must be "text/plain".

              • "text/plain"

            • type: "text"

              • "text"

          • BetaManagedAgentsURLDocumentSource object { type, url }

            Document referenced by URL.

            • type: "url"

              • "url"

            • url: string

              URL of the document to fetch.

          • BetaManagedAgentsFileDocumentSource object { file_id, type }

            Document referenced by file ID.

            • file_id: string

              ID of a previously uploaded file.

            • type: "file"

              • "file"

        • type: "document"

          • "document"

        • context: optional string

          Additional context about the document for the model.

        • title: optional string

          The title of the document.

    • type: "user.message"

      • "user.message"

    • processed_at: optional string

      A timestamp in RFC 3339 format

  • BetaManagedAgentsUserInterruptEvent object { id, type, processed_at, session_thread_id }

    An interrupt event that pauses agent execution and returns control to the user.

    • id: string

      Unique identifier for this event.

    • type: "user.interrupt"

      • "user.interrupt"

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread.

  • BetaManagedAgentsUserToolConfirmationEvent object { id, result, tool_use_id, 4 more }

    A tool confirmation event that approves or denies a pending tool execution.

    • id: string

      Unique identifier for this event.

    • result: "allow" or "deny"

      UserToolConfirmationResult enum

      • "allow"

      • "deny"

    • tool_use_id: string

      The id of the agent.tool_use or agent.mcp_tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.tool_confirmation"

      • "user.tool_confirmation"

    • deny_message: optional string

      Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      When set, the confirmation routes to this subagent's thread rather than the primary. Echo this from the session_thread_id on the agent.tool_use or agent.mcp_tool_use event that prompted the approval.

  • BetaManagedAgentsUserCustomToolResultEvent object { id, custom_tool_use_id, type, 4 more }

    Event sent by the client providing the result of a custom tool execution.

    • id: string

      Unique identifier for this event.

    • custom_tool_use_id: string

      The id of the agent.custom_tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.custom_tool_result"

      • "user.custom_tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

        • citations: BetaManagedAgentsSearchResultCitations

          Citation settings for a search result.

          • enabled: boolean

            Whether citations are enabled for this search result.

        • content: array of BetaManagedAgentsSearchResultContent

          Array of text content blocks from the search result.

          • text: string

            The text content.

          • type: "text"

            • "text"

        • source: string

          The URL source of the search result.

        • title: string

          The title of the search result.

        • type: "search_result"

          • "search_result"

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      Routes this result to a subagent thread. Copy from the agent.custom_tool_use event's session_thread_id.

  • BetaManagedAgentsAgentCustomToolUseEvent object { id, input, name, 3 more }

    Event emitted when the agent calls a custom tool. The session goes idle until the client sends a user.custom_tool_result event with the result.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • name: string

      Name of the custom tool being called.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.custom_tool_use"

      • "agent.custom_tool_use"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Echo this on a user.custom_tool_result event to route the result back.

  • BetaManagedAgentsAgentMessageEvent object { id, content, processed_at, type }

    An agent response event in the session conversation.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock

      Array of text blocks comprising the agent response.

      • text: string

        The text content.

      • type: "text"

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.message"

      • "agent.message"

  • BetaManagedAgentsAgentThinkingEvent object { id, processed_at, type }

    Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thinking"

      • "agent.thinking"

  • BetaManagedAgentsAgentMCPToolUseEvent object { id, input, mcp_server_name, 5 more }

    Event emitted when the agent invokes a tool provided by an MCP server.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • mcp_server_name: string

      Name of the MCP server providing the tool.

    • name: string

      Name of the MCP tool being used.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.mcp_tool_use"

      • "agent.mcp_tool_use"

    • evaluated_permission: optional "allow" or "ask" or "deny"

      AgentEvaluatedPermission enum

      • "allow"

      • "ask"

      • "deny"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Echo this on a user.tool_confirmation event to route the approval back.

  • BetaManagedAgentsAgentMCPToolResultEvent object { id, mcp_tool_use_id, processed_at, 3 more }

    Event representing the result of an MCP tool execution.

    • id: string

      Unique identifier for this event.

    • mcp_tool_use_id: string

      The id of the agent.mcp_tool_use event this result corresponds to.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.mcp_tool_result"

      • "agent.mcp_tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

  • BetaManagedAgentsAgentToolUseEvent object { id, input, name, 4 more }

    Event emitted when the agent invokes a built-in agent tool.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • name: string

      Name of the agent tool being used.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.tool_use"

      • "agent.tool_use"

    • evaluated_permission: optional "allow" or "ask" or "deny"

      AgentEvaluatedPermission enum

      • "allow"

      • "ask"

      • "deny"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Echo this on a user.tool_confirmation event to route the approval back.

  • BetaManagedAgentsAgentToolResultEvent object { id, processed_at, tool_use_id, 3 more }

    Event representing the result of an agent tool execution.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • tool_use_id: string

      The id of the agent.tool_use event this result corresponds to.

    • type: "agent.tool_result"

      • "agent.tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

  • BetaManagedAgentsAgentThreadMessageReceivedEvent object { id, content, from_session_thread_id, 3 more }

    Delivery event written to the target thread's input stream when an agent-to-agent message arrives.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Message content blocks.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

    • from_session_thread_id: string

      Public sthr_ ID of the thread that sent the message.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thread_message_received"

      • "agent.thread_message_received"

    • from_agent_name: optional string

      Name of the callable agent this message came from. Absent when received from the primary agent.

  • BetaManagedAgentsAgentThreadMessageSentEvent object { id, content, processed_at, 3 more }

    Observability event emitted to the sender's output stream when an agent-to-agent message is sent.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Message content blocks.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

    • processed_at: string

      A timestamp in RFC 3339 format

    • to_session_thread_id: string

      Public sthr_ ID of the thread the message was sent to.

    • type: "agent.thread_message_sent"

      • "agent.thread_message_sent"

    • to_agent_name: optional string

      Name of the callable agent this message was sent to. Absent when sent to the primary agent.

  • BetaManagedAgentsAgentThreadContextCompactedEvent object { id, processed_at, type }

    Indicates that context compaction (summarization) occurred during the session.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thread_context_compacted"

      • "agent.thread_context_compacted"

  • BetaManagedAgentsSessionErrorEvent object { id, error, processed_at, type }

    An error event indicating a problem occurred during session execution.

    • id: string

      Unique identifier for this event.

    • error: BetaManagedAgentsUnknownError or BetaManagedAgentsModelOverloadedError or BetaManagedAgentsModelRateLimitedError or 4 more

      An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on retry_status and message alone.

      • BetaManagedAgentsUnknownError object { message, retry_status, type }

        An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on retry_status and message alone.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

            • type: "retrying"

              • "retrying"

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

            • type: "exhausted"

              • "exhausted"

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

            • type: "terminal"

              • "terminal"

        • type: "unknown_error"

          • "unknown_error"

      • BetaManagedAgentsModelOverloadedError object { message, retry_status, type }

        The model is currently overloaded. Emitted after automatic retries are exhausted.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_overloaded_error"

          • "model_overloaded_error"

      • BetaManagedAgentsModelRateLimitedError object { message, retry_status, type }

        The model request was rate-limited.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_rate_limited_error"

          • "model_rate_limited_error"

      • BetaManagedAgentsModelRequestFailedError object { message, retry_status, type }

        A model request failed for a reason other than overload or rate-limiting.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_request_failed_error"

          • "model_request_failed_error"

      • BetaManagedAgentsMCPConnectionFailedError object { mcp_server_name, message, retry_status, type }

        Failed to connect to an MCP server.

        • mcp_server_name: string

          Name of the MCP server that failed to connect.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "mcp_connection_failed_error"

          • "mcp_connection_failed_error"

      • BetaManagedAgentsMCPAuthenticationFailedError object { mcp_server_name, message, retry_status, type }

        Authentication to an MCP server failed.

        • mcp_server_name: string

          Name of the MCP server that failed authentication.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "mcp_authentication_failed_error"

          • "mcp_authentication_failed_error"

      • BetaManagedAgentsBillingError object { message, retry_status, type }

        The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "billing_error"

          • "billing_error"

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.error"

      • "session.error"

  • BetaManagedAgentsSessionStatusRescheduledEvent object { id, processed_at, type }

    Indicates the session is recovering from an error state and is rescheduled for execution.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_rescheduled"

      • "session.status_rescheduled"

  • BetaManagedAgentsSessionStatusRunningEvent object { id, processed_at, type }

    Indicates the session is actively running and the agent is working.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_running"

      • "session.status_running"

  • BetaManagedAgentsSessionStatusIdleEvent object { id, processed_at, stop_reason, type }

    Indicates the agent has paused and is awaiting user input.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted

      The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionEndTurn object { type }

        The agent completed its turn naturally and is ready for the next user message.

        • type: "end_turn"

          • "end_turn"

      • BetaManagedAgentsSessionRequiresAction object { event_ids, type }

        The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running.

        • event_ids: array of string

          The ids of events the agent is blocked on. Resolving fewer than all re-emits session.status_idle with the remainder.

        • type: "requires_action"

          • "requires_action"

      • BetaManagedAgentsSessionRetriesExhausted object { type }

        The turn ended because the retry budget was exhausted (max_iterations hit or an error escalated to retry_status: 'exhausted').

        • type: "retries_exhausted"

          • "retries_exhausted"

    • type: "session.status_idle"

      • "session.status_idle"

  • BetaManagedAgentsSessionStatusTerminatedEvent object { id, processed_at, type }

    Indicates the session has terminated, either due to an error or completion.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_terminated"

      • "session.status_terminated"

  • BetaManagedAgentsSessionThreadCreatedEvent object { id, agent_name, processed_at, 2 more }

    Emitted when a subagent is spawned as a new thread. Written to the parent thread's output stream so clients observing the session see child creation.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the callable agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the newly created thread.

    • type: "session.thread_created"

      • "session.thread_created"

  • BetaManagedAgentsSpanOutcomeEvaluationStartEvent object { id, iteration, outcome_id, 2 more }

    Emitted when an outcome evaluation cycle begins.

    • id: string

      Unique identifier for this event.

    • iteration: number

      0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.outcome_evaluation_start"

      • "span.outcome_evaluation_start"

  • BetaManagedAgentsSpanOutcomeEvaluationEndEvent object { id, explanation, iteration, 6 more }

    Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of needs_revision means another evaluation cycle follows; satisfied, max_iterations_reached, failed, or interrupted are terminal — no further evaluation cycles follow.

    • id: string

      Unique identifier for this event.

    • explanation: string

      Human-readable explanation of the verdict. For needs_revision, describes which criteria failed and why.

    • iteration: number

      0-indexed revision cycle, matching the corresponding span.outcome_evaluation_start.

    • outcome_evaluation_start_id: string

      The id of the corresponding span.outcome_evaluation_start event.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • result: string

      Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress.

    • type: "span.outcome_evaluation_end"

      • "span.outcome_evaluation_end"

    • usage: BetaManagedAgentsSpanModelUsage

      Token usage for a single model request.

      • cache_creation_input_tokens: number

        Tokens used to create prompt cache in this request.

      • cache_read_input_tokens: number

        Tokens read from prompt cache in this request.

      • input_tokens: number

        Input tokens consumed by this request.

      • output_tokens: number

        Output tokens generated by this request.

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

  • BetaManagedAgentsSpanModelRequestStartEvent object { id, processed_at, type }

    Emitted when a model request is initiated by the agent.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.model_request_start"

      • "span.model_request_start"

  • BetaManagedAgentsSpanModelRequestEndEvent object { id, is_error, model_request_start_id, 3 more }

    Emitted when a model request completes.

    • id: string

      Unique identifier for this event.

    • is_error: boolean

      Whether the model request resulted in an error.

    • model_request_start_id: string

      The id of the corresponding span.model_request_start event.

    • model_usage: BetaManagedAgentsSpanModelUsage

      Token usage for a single model request.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.model_request_end"

      • "span.model_request_end"

  • BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent object { id, iteration, outcome_id, 2 more }

    Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding span.outcome_evaluation_start and span.outcome_evaluation_end events.

    • id: string

      Unique identifier for this event.

    • iteration: number

      0-indexed revision cycle, matching the corresponding span.outcome_evaluation_start.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.outcome_evaluation_ongoing"

      • "span.outcome_evaluation_ongoing"

  • BetaManagedAgentsUserDefineOutcomeEvent object { id, description, max_iterations, 4 more }

    Echo of a user.define_outcome input event. Carries the server-generated outcome_id that subsequent span.outcome_evaluation_* events reference.

    • id: string

      Unique identifier for this event.

    • description: string

      What the agent should produce. Copied from the input event.

    • max_iterations: number

      Evaluate-then-revise cycles before giving up. Default 3, max 20.

    • outcome_id: string

      Server-generated outc_ ID for this outcome. Referenced by span.outcome_evaluation_* events and the session's outcome_evaluations list.

    • processed_at: string

      A timestamp in RFC 3339 format

    • rubric: BetaManagedAgentsFileRubric or BetaManagedAgentsTextRubric

      Rubric for grading the quality of an outcome.

      • BetaManagedAgentsFileRubric object { file_id, type }

        Rubric referenced by a file uploaded via the Files API.

        • file_id: string

          ID of the rubric file.

        • type: "file"

          • "file"

      • BetaManagedAgentsTextRubric object { content, type }

        Rubric content provided inline as text.

        • content: string

          Rubric content. Plain text or markdown — the grader treats it as freeform text.

        • type: "text"

          • "text"

    • type: "user.define_outcome"

      • "user.define_outcome"

  • BetaManagedAgentsSessionDeletedEvent object { id, processed_at, type }

    Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.deleted"

      • "session.deleted"

  • BetaManagedAgentsSessionThreadStatusRunningEvent object { id, agent_name, processed_at, 2 more }

    A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that started running.

    • type: "session.thread_status_running"

      • "session.thread_status_running"

  • BetaManagedAgentsSessionThreadStatusIdleEvent object { id, agent_name, processed_at, 3 more }

    A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that went idle.

    • stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted

      The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionEndTurn object { type }

        The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionRequiresAction object { event_ids, type }

        The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running.

      • BetaManagedAgentsSessionRetriesExhausted object { type }

        The turn ended because the retry budget was exhausted (max_iterations hit or an error escalated to retry_status: 'exhausted').

    • type: "session.thread_status_idle"

      • "session.thread_status_idle"

  • BetaManagedAgentsSessionThreadStatusTerminatedEvent object { id, agent_name, processed_at, 2 more }

    A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that terminated.

    • type: "session.thread_status_terminated"

      • "session.thread_status_terminated"

  • BetaManagedAgentsUserToolResultEvent object { id, tool_use_id, type, 4 more }

    Event sent by the client providing the result of an agent-toolset tool execution. Only valid on self_hosted environments, where sandbox-routed tools are executed by the client rather than the server.

    • id: string

      Unique identifier for this event.

    • tool_use_id: string

      The id of the agent.tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.tool_result"

      • "user.tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      Routes this result to a subagent thread. Copy from the agent.tool_use event's session_thread_id.

  • BetaManagedAgentsSessionThreadStatusRescheduledEvent object { id, agent_name, processed_at, 2 more }

    A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that is retrying.

    • type: "session.thread_status_rescheduled"

      • "session.thread_status_rescheduled"

  • BetaManagedAgentsSessionUpdatedEvent object { id, processed_at, type, 3 more }

    Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.updated"

      • "session.updated"

    • agent: optional BetaManagedAgentsSessionAgent

      Resolved agent definition for a session. Snapshot of the agent at session creation time.

      • id: string

      • description: string

      • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

        • name: string

        • type: "url"

          • "url"

        • url: string

      • model: BetaManagedAgentsModelConfig

        Model identifier and configuration.

        • id: BetaManagedAgentsModel

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

            The model that will power your agent.

            See models for additional details and options.

            • "claude-opus-4-7"

              Frontier intelligence for long-running agents and coding

            • "claude-opus-4-6"

              Most intelligent model for building agents and coding

            • "claude-sonnet-4-6"

              Best combination of speed and intelligence

            • "claude-haiku-4-5"

              Fastest model with near-frontier intelligence

            • "claude-haiku-4-5-20251001"

              Fastest model with near-frontier intelligence

            • "claude-opus-4-5"

              Premium model combining maximum intelligence with practical performance

            • "claude-opus-4-5-20251101"

              Premium model combining maximum intelligence with practical performance

            • "claude-sonnet-4-5"

              High-performance model for agents and coding

            • "claude-sonnet-4-5-20250929"

              High-performance model for agents and coding

          • string

        • speed: optional "standard" or "fast"

          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.

          • "standard"

          • "fast"

      • multiagent: BetaManagedAgentsSessionMultiagentCoordinator

        Resolved coordinator topology with full agent definitions for each roster member.

        • agents: array of BetaManagedAgentsSessionThreadAgent

          Full agent definitions the coordinator may spawn as session threads.

          • id: string

          • description: string

          • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

            • name: string

            • type: "url"

            • url: string

          • model: BetaManagedAgentsModelConfig

            Model identifier and configuration.

          • name: string

          • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

            • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

              A resolved Anthropic-managed skill.

              • skill_id: string

              • type: "anthropic"

                • "anthropic"

              • version: string

            • BetaManagedAgentsCustomSkill object { skill_id, type, version }

              A resolved user-created custom skill.

              • skill_id: string

              • type: "custom"

                • "custom"

              • version: string

          • system: string

          • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

            • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

              • configs: array of BetaManagedAgentsAgentToolConfig

                • enabled: boolean

                • name: "bash" or "edit" or "read" or 5 more

                  Built-in agent tool identifier.

                  • "bash"

                  • "edit"

                  • "read"

                  • "write"

                  • "glob"

                  • "grep"

                  • "web_fetch"

                  • "web_search"

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                    • type: "always_allow"

                      • "always_allow"

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

                    • type: "always_ask"

                      • "always_ask"

              • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

                Resolved default configuration for agent tools.

                • enabled: boolean

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • type: "agent_toolset_20260401"

                • "agent_toolset_20260401"

            • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

              • configs: array of BetaManagedAgentsMCPToolConfig

                • enabled: boolean

                • name: string

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

                Resolved default configuration for all tools from an MCP server.

                • enabled: boolean

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • mcp_server_name: string

              • type: "mcp_toolset"

                • "mcp_toolset"

            • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

              A custom tool as returned in API responses.

              • description: string

              • input_schema: BetaManagedAgentsCustomToolInputSchema

                JSON Schema for custom tool input parameters.

                • properties: optional map[unknown]

                  JSON Schema properties defining the tool's input parameters.

                • required: optional array of string

                  List of required property names.

                • type: optional "object"

                  Must be 'object' for tool input schemas.

                  • "object"

              • name: string

              • type: "custom"

                • "custom"

          • type: "agent"

            • "agent"

          • version: number

        • type: "coordinator"

          • "coordinator"

      • name: string

      • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

        • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

          A resolved Anthropic-managed skill.

        • BetaManagedAgentsCustomSkill object { skill_id, type, version }

          A resolved user-created custom skill.

      • system: string

      • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

        • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

          A custom tool as returned in API responses.

      • type: "agent"

        • "agent"

      • version: number

    • metadata: optional map[string]

      The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty.

    • title: optional string

      The session's new title. Present only when the update changed it.

• next_page: optional string

  Opaque cursor for the next page. Null when no more results.

Example

curl https://api.anthropic.com/v1/sessions/$SESSION_ID/threads/$THREAD_ID/events \
    -H 'anthropic-version: 2023-06-01' \
    -H 'anthropic-beta: managed-agents-2026-04-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"

Response

{
  "data": [
    {
      "id": "sevt_011CZkZGOp0iBcp4kaQSihUmy",
      "content": [
        {
          "text": "Where is my order #1234?",
          "type": "text"
        }
      ],
      "type": "user.message",
      "processed_at": "2026-03-15T10:00:00Z"
    }
  ],
  "next_page": "next_page"
}

Stream Session Thread Events

get /v1/sessions/{session_id}/threads/{thread_id}/stream

Stream Session Thread Events

Path Parameters

• session_id: string

• thread_id: string

Header Parameters

• "anthropic-beta": optional array of AnthropicBeta

  Optional header to specify the beta version(s) you want to use.

  • string

  • "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 22 more

    • "message-batches-2024-09-24"

    • "prompt-caching-2024-07-31"

    • "computer-use-2024-10-22"

    • "computer-use-2025-01-24"

    • "pdfs-2024-09-25"

    • "token-counting-2024-11-01"

    • "token-efficient-tools-2025-02-19"

    • "output-128k-2025-02-19"

    • "files-api-2025-04-14"

    • "mcp-client-2025-04-04"

    • "mcp-client-2025-11-20"

    • "dev-full-thinking-2025-05-14"

    • "interleaved-thinking-2025-05-14"

    • "code-execution-2025-05-22"

    • "extended-cache-ttl-2025-04-11"

    • "context-1m-2025-08-07"

    • "context-management-2025-06-27"

    • "model-context-window-exceeded-2025-08-26"

    • "skills-2025-10-02"

    • "fast-mode-2026-02-01"

    • "output-300k-2026-03-24"

    • "user-profiles-2026-03-24"

    • "advisor-tool-2026-03-01"

    • "managed-agents-2026-04-01"

    • "cache-diagnosis-2026-04-07"

Returns

• BetaManagedAgentsStreamSessionThreadEvents = BetaManagedAgentsUserMessageEvent or BetaManagedAgentsUserInterruptEvent or BetaManagedAgentsUserToolConfirmationEvent or 30 more

  Server-sent event in a single thread's stream.

  • BetaManagedAgentsUserMessageEvent object { id, content, type, processed_at }

    A user message event in the session conversation.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Array of content blocks comprising the user message.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

        • text: string

          The text content.

        • type: "text"

          • "text"

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

        • source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource

          Union type for image source variants.

          • BetaManagedAgentsBase64ImageSource object { data, media_type, type }

            Base64-encoded image data.

            • data: string

              Base64-encoded image data.

            • media_type: string

              MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp").

            • type: "base64"

              • "base64"

          • BetaManagedAgentsURLImageSource object { type, url }

            Image referenced by URL.

            • type: "url"

              • "url"

            • url: string

              URL of the image to fetch.

          • BetaManagedAgentsFileImageSource object { file_id, type }

            Image referenced by file ID.

            • file_id: string

              ID of a previously uploaded file.

            • type: "file"

              • "file"

        • type: "image"

          • "image"

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

        • source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource

          Union type for document source variants.

          • BetaManagedAgentsBase64DocumentSource object { data, media_type, type }

            Base64-encoded document data.

            • data: string

              Base64-encoded document data.

            • media_type: string

              MIME type of the document (e.g., "application/pdf").

            • type: "base64"

              • "base64"

          • BetaManagedAgentsPlainTextDocumentSource object { data, media_type, type }

            Plain text document content.

            • data: string

              The plain text content.

            • media_type: "text/plain"

              MIME type of the text content. Must be "text/plain".

              • "text/plain"

            • type: "text"

              • "text"

          • BetaManagedAgentsURLDocumentSource object { type, url }

            Document referenced by URL.

            • type: "url"

              • "url"

            • url: string

              URL of the document to fetch.

          • BetaManagedAgentsFileDocumentSource object { file_id, type }

            Document referenced by file ID.

            • file_id: string

              ID of a previously uploaded file.

            • type: "file"

              • "file"

        • type: "document"

          • "document"

        • context: optional string

          Additional context about the document for the model.

        • title: optional string

          The title of the document.

    • type: "user.message"

      • "user.message"

    • processed_at: optional string

      A timestamp in RFC 3339 format

  • BetaManagedAgentsUserInterruptEvent object { id, type, processed_at, session_thread_id }

    An interrupt event that pauses agent execution and returns control to the user.

    • id: string

      Unique identifier for this event.

    • type: "user.interrupt"

      • "user.interrupt"

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread.

  • BetaManagedAgentsUserToolConfirmationEvent object { id, result, tool_use_id, 4 more }

    A tool confirmation event that approves or denies a pending tool execution.

    • id: string

      Unique identifier for this event.

    • result: "allow" or "deny"

      UserToolConfirmationResult enum

      • "allow"

      • "deny"

    • tool_use_id: string

      The id of the agent.tool_use or agent.mcp_tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.tool_confirmation"

      • "user.tool_confirmation"

    • deny_message: optional string

      Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      When set, the confirmation routes to this subagent's thread rather than the primary. Echo this from the session_thread_id on the agent.tool_use or agent.mcp_tool_use event that prompted the approval.

  • BetaManagedAgentsUserCustomToolResultEvent object { id, custom_tool_use_id, type, 4 more }

    Event sent by the client providing the result of a custom tool execution.

    • id: string

      Unique identifier for this event.

    • custom_tool_use_id: string

      The id of the agent.custom_tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.custom_tool_result"

      • "user.custom_tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

        • citations: BetaManagedAgentsSearchResultCitations

          Citation settings for a search result.

          • enabled: boolean

            Whether citations are enabled for this search result.

        • content: array of BetaManagedAgentsSearchResultContent

          Array of text content blocks from the search result.

          • text: string

            The text content.

          • type: "text"

            • "text"

        • source: string

          The URL source of the search result.

        • title: string

          The title of the search result.

        • type: "search_result"

          • "search_result"

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      Routes this result to a subagent thread. Copy from the agent.custom_tool_use event's session_thread_id.

  • BetaManagedAgentsAgentCustomToolUseEvent object { id, input, name, 3 more }

    Event emitted when the agent calls a custom tool. The session goes idle until the client sends a user.custom_tool_result event with the result.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • name: string

      Name of the custom tool being called.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.custom_tool_use"

      • "agent.custom_tool_use"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Echo this on a user.custom_tool_result event to route the result back.

  • BetaManagedAgentsAgentMessageEvent object { id, content, processed_at, type }

    An agent response event in the session conversation.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock

      Array of text blocks comprising the agent response.

      • text: string

        The text content.

      • type: "text"

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.message"

      • "agent.message"

  • BetaManagedAgentsAgentThinkingEvent object { id, processed_at, type }

    Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thinking"

      • "agent.thinking"

  • BetaManagedAgentsAgentMCPToolUseEvent object { id, input, mcp_server_name, 5 more }

    Event emitted when the agent invokes a tool provided by an MCP server.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • mcp_server_name: string

      Name of the MCP server providing the tool.

    • name: string

      Name of the MCP tool being used.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.mcp_tool_use"

      • "agent.mcp_tool_use"

    • evaluated_permission: optional "allow" or "ask" or "deny"

      AgentEvaluatedPermission enum

      • "allow"

      • "ask"

      • "deny"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Echo this on a user.tool_confirmation event to route the approval back.

  • BetaManagedAgentsAgentMCPToolResultEvent object { id, mcp_tool_use_id, processed_at, 3 more }

    Event representing the result of an MCP tool execution.

    • id: string

      Unique identifier for this event.

    • mcp_tool_use_id: string

      The id of the agent.mcp_tool_use event this result corresponds to.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.mcp_tool_result"

      • "agent.mcp_tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

  • BetaManagedAgentsAgentToolUseEvent object { id, input, name, 4 more }

    Event emitted when the agent invokes a built-in agent tool.

    • id: string

      Unique identifier for this event.

    • input: map[unknown]

      Input parameters for the tool call.

    • name: string

      Name of the agent tool being used.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.tool_use"

      • "agent.tool_use"

    • evaluated_permission: optional "allow" or "ask" or "deny"

      AgentEvaluatedPermission enum

      • "allow"

      • "ask"

      • "deny"

    • session_thread_id: optional string

      When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Echo this on a user.tool_confirmation event to route the approval back.

  • BetaManagedAgentsAgentToolResultEvent object { id, processed_at, tool_use_id, 3 more }

    Event representing the result of an agent tool execution.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • tool_use_id: string

      The id of the agent.tool_use event this result corresponds to.

    • type: "agent.tool_result"

      • "agent.tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

  • BetaManagedAgentsAgentThreadMessageReceivedEvent object { id, content, from_session_thread_id, 3 more }

    Delivery event written to the target thread's input stream when an agent-to-agent message arrives.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Message content blocks.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

    • from_session_thread_id: string

      Public sthr_ ID of the thread that sent the message.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thread_message_received"

      • "agent.thread_message_received"

    • from_agent_name: optional string

      Name of the callable agent this message came from. Absent when received from the primary agent.

  • BetaManagedAgentsAgentThreadMessageSentEvent object { id, content, processed_at, 3 more }

    Observability event emitted to the sender's output stream when an agent-to-agent message is sent.

    • id: string

      Unique identifier for this event.

    • content: array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock

      Message content blocks.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

    • processed_at: string

      A timestamp in RFC 3339 format

    • to_session_thread_id: string

      Public sthr_ ID of the thread the message was sent to.

    • type: "agent.thread_message_sent"

      • "agent.thread_message_sent"

    • to_agent_name: optional string

      Name of the callable agent this message was sent to. Absent when sent to the primary agent.

  • BetaManagedAgentsAgentThreadContextCompactedEvent object { id, processed_at, type }

    Indicates that context compaction (summarization) occurred during the session.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "agent.thread_context_compacted"

      • "agent.thread_context_compacted"

  • BetaManagedAgentsSessionErrorEvent object { id, error, processed_at, type }

    An error event indicating a problem occurred during session execution.

    • id: string

      Unique identifier for this event.

    • error: BetaManagedAgentsUnknownError or BetaManagedAgentsModelOverloadedError or BetaManagedAgentsModelRateLimitedError or 4 more

      An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on retry_status and message alone.

      • BetaManagedAgentsUnknownError object { message, retry_status, type }

        An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on retry_status and message alone.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

            • type: "retrying"

              • "retrying"

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

            • type: "exhausted"

              • "exhausted"

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

            • type: "terminal"

              • "terminal"

        • type: "unknown_error"

          • "unknown_error"

      • BetaManagedAgentsModelOverloadedError object { message, retry_status, type }

        The model is currently overloaded. Emitted after automatic retries are exhausted.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_overloaded_error"

          • "model_overloaded_error"

      • BetaManagedAgentsModelRateLimitedError object { message, retry_status, type }

        The model request was rate-limited.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_rate_limited_error"

          • "model_rate_limited_error"

      • BetaManagedAgentsModelRequestFailedError object { message, retry_status, type }

        A model request failed for a reason other than overload or rate-limiting.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "model_request_failed_error"

          • "model_request_failed_error"

      • BetaManagedAgentsMCPConnectionFailedError object { mcp_server_name, message, retry_status, type }

        Failed to connect to an MCP server.

        • mcp_server_name: string

          Name of the MCP server that failed to connect.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "mcp_connection_failed_error"

          • "mcp_connection_failed_error"

      • BetaManagedAgentsMCPAuthenticationFailedError object { mcp_server_name, message, retry_status, type }

        Authentication to an MCP server failed.

        • mcp_server_name: string

          Name of the MCP server that failed authentication.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "mcp_authentication_failed_error"

          • "mcp_authentication_failed_error"

      • BetaManagedAgentsBillingError object { message, retry_status, type }

        The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state.

        • message: string

          Human-readable error description.

        • retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal

          What the client should do next in response to this error.

          • BetaManagedAgentsRetryStatusRetrying object { type }

            The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out.

          • BetaManagedAgentsRetryStatusExhausted object { type }

            This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt.

          • BetaManagedAgentsRetryStatusTerminal object { type }

            The session encountered a terminal error and will transition to terminated state.

        • type: "billing_error"

          • "billing_error"

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.error"

      • "session.error"

  • BetaManagedAgentsSessionStatusRescheduledEvent object { id, processed_at, type }

    Indicates the session is recovering from an error state and is rescheduled for execution.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_rescheduled"

      • "session.status_rescheduled"

  • BetaManagedAgentsSessionStatusRunningEvent object { id, processed_at, type }

    Indicates the session is actively running and the agent is working.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_running"

      • "session.status_running"

  • BetaManagedAgentsSessionStatusIdleEvent object { id, processed_at, stop_reason, type }

    Indicates the agent has paused and is awaiting user input.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted

      The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionEndTurn object { type }

        The agent completed its turn naturally and is ready for the next user message.

        • type: "end_turn"

          • "end_turn"

      • BetaManagedAgentsSessionRequiresAction object { event_ids, type }

        The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running.

        • event_ids: array of string

          The ids of events the agent is blocked on. Resolving fewer than all re-emits session.status_idle with the remainder.

        • type: "requires_action"

          • "requires_action"

      • BetaManagedAgentsSessionRetriesExhausted object { type }

        The turn ended because the retry budget was exhausted (max_iterations hit or an error escalated to retry_status: 'exhausted').

        • type: "retries_exhausted"

          • "retries_exhausted"

    • type: "session.status_idle"

      • "session.status_idle"

  • BetaManagedAgentsSessionStatusTerminatedEvent object { id, processed_at, type }

    Indicates the session has terminated, either due to an error or completion.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.status_terminated"

      • "session.status_terminated"

  • BetaManagedAgentsSessionThreadCreatedEvent object { id, agent_name, processed_at, 2 more }

    Emitted when a subagent is spawned as a new thread. Written to the parent thread's output stream so clients observing the session see child creation.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the callable agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the newly created thread.

    • type: "session.thread_created"

      • "session.thread_created"

  • BetaManagedAgentsSpanOutcomeEvaluationStartEvent object { id, iteration, outcome_id, 2 more }

    Emitted when an outcome evaluation cycle begins.

    • id: string

      Unique identifier for this event.

    • iteration: number

      0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.outcome_evaluation_start"

      • "span.outcome_evaluation_start"

  • BetaManagedAgentsSpanOutcomeEvaluationEndEvent object { id, explanation, iteration, 6 more }

    Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of needs_revision means another evaluation cycle follows; satisfied, max_iterations_reached, failed, or interrupted are terminal — no further evaluation cycles follow.

    • id: string

      Unique identifier for this event.

    • explanation: string

      Human-readable explanation of the verdict. For needs_revision, describes which criteria failed and why.

    • iteration: number

      0-indexed revision cycle, matching the corresponding span.outcome_evaluation_start.

    • outcome_evaluation_start_id: string

      The id of the corresponding span.outcome_evaluation_start event.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • result: string

      Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress.

    • type: "span.outcome_evaluation_end"

      • "span.outcome_evaluation_end"

    • usage: BetaManagedAgentsSpanModelUsage

      Token usage for a single model request.

      • cache_creation_input_tokens: number

        Tokens used to create prompt cache in this request.

      • cache_read_input_tokens: number

        Tokens read from prompt cache in this request.

      • input_tokens: number

        Input tokens consumed by this request.

      • output_tokens: number

        Output tokens generated by this request.

      • speed: optional "standard" or "fast"

        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.

        • "standard"

        • "fast"

  • BetaManagedAgentsSpanModelRequestStartEvent object { id, processed_at, type }

    Emitted when a model request is initiated by the agent.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.model_request_start"

      • "span.model_request_start"

  • BetaManagedAgentsSpanModelRequestEndEvent object { id, is_error, model_request_start_id, 3 more }

    Emitted when a model request completes.

    • id: string

      Unique identifier for this event.

    • is_error: boolean

      Whether the model request resulted in an error.

    • model_request_start_id: string

      The id of the corresponding span.model_request_start event.

    • model_usage: BetaManagedAgentsSpanModelUsage

      Token usage for a single model request.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.model_request_end"

      • "span.model_request_end"

  • BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent object { id, iteration, outcome_id, 2 more }

    Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding span.outcome_evaluation_start and span.outcome_evaluation_end events.

    • id: string

      Unique identifier for this event.

    • iteration: number

      0-indexed revision cycle, matching the corresponding span.outcome_evaluation_start.

    • outcome_id: string

      The outc_ ID of the outcome being evaluated.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "span.outcome_evaluation_ongoing"

      • "span.outcome_evaluation_ongoing"

  • BetaManagedAgentsUserDefineOutcomeEvent object { id, description, max_iterations, 4 more }

    Echo of a user.define_outcome input event. Carries the server-generated outcome_id that subsequent span.outcome_evaluation_* events reference.

    • id: string

      Unique identifier for this event.

    • description: string

      What the agent should produce. Copied from the input event.

    • max_iterations: number

      Evaluate-then-revise cycles before giving up. Default 3, max 20.

    • outcome_id: string

      Server-generated outc_ ID for this outcome. Referenced by span.outcome_evaluation_* events and the session's outcome_evaluations list.

    • processed_at: string

      A timestamp in RFC 3339 format

    • rubric: BetaManagedAgentsFileRubric or BetaManagedAgentsTextRubric

      Rubric for grading the quality of an outcome.

      • BetaManagedAgentsFileRubric object { file_id, type }

        Rubric referenced by a file uploaded via the Files API.

        • file_id: string

          ID of the rubric file.

        • type: "file"

          • "file"

      • BetaManagedAgentsTextRubric object { content, type }

        Rubric content provided inline as text.

        • content: string

          Rubric content. Plain text or markdown — the grader treats it as freeform text.

        • type: "text"

          • "text"

    • type: "user.define_outcome"

      • "user.define_outcome"

  • BetaManagedAgentsSessionDeletedEvent object { id, processed_at, type }

    Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.deleted"

      • "session.deleted"

  • BetaManagedAgentsSessionThreadStatusRunningEvent object { id, agent_name, processed_at, 2 more }

    A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that started running.

    • type: "session.thread_status_running"

      • "session.thread_status_running"

  • BetaManagedAgentsSessionThreadStatusIdleEvent object { id, agent_name, processed_at, 3 more }

    A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that went idle.

    • stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted

      The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionEndTurn object { type }

        The agent completed its turn naturally and is ready for the next user message.

      • BetaManagedAgentsSessionRequiresAction object { event_ids, type }

        The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running.

      • BetaManagedAgentsSessionRetriesExhausted object { type }

        The turn ended because the retry budget was exhausted (max_iterations hit or an error escalated to retry_status: 'exhausted').

    • type: "session.thread_status_idle"

      • "session.thread_status_idle"

  • BetaManagedAgentsSessionThreadStatusTerminatedEvent object { id, agent_name, processed_at, 2 more }

    A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that terminated.

    • type: "session.thread_status_terminated"

      • "session.thread_status_terminated"

  • BetaManagedAgentsUserToolResultEvent object { id, tool_use_id, type, 4 more }

    Event sent by the client providing the result of an agent-toolset tool execution. Only valid on self_hosted environments, where sandbox-routed tools are executed by the client rather than the server.

    • id: string

      Unique identifier for this event.

    • tool_use_id: string

      The id of the agent.tool_use event this result corresponds to, which can be found in the last session.status_idle event's stop_reason.event_ids field.

    • type: "user.tool_result"

      • "user.tool_result"

    • content: optional array of BetaManagedAgentsTextBlock or BetaManagedAgentsImageBlock or BetaManagedAgentsDocumentBlock or BetaManagedAgentsSearchResultBlock

      The result content returned by the tool.

      • BetaManagedAgentsTextBlock object { text, type }

        Regular text content.

      • BetaManagedAgentsImageBlock object { source, type }

        Image content specified directly as base64 data or as a reference via a URL.

      • BetaManagedAgentsDocumentBlock object { source, type, context, title }

        Document content, either specified directly as base64 data, as text, or as a reference via a URL.

      • BetaManagedAgentsSearchResultBlock object { citations, content, source, 2 more }

        A block containing a web search result.

    • is_error: optional boolean

      Whether the tool execution resulted in an error.

    • processed_at: optional string

      A timestamp in RFC 3339 format

    • session_thread_id: optional string

      Routes this result to a subagent thread. Copy from the agent.tool_use event's session_thread_id.

  • BetaManagedAgentsSessionThreadStatusRescheduledEvent object { id, agent_name, processed_at, 2 more }

    A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads.

    • id: string

      Unique identifier for this event.

    • agent_name: string

      Name of the agent the thread runs.

    • processed_at: string

      A timestamp in RFC 3339 format

    • session_thread_id: string

      Public sthr_ ID of the thread that is retrying.

    • type: "session.thread_status_rescheduled"

      • "session.thread_status_rescheduled"

  • BetaManagedAgentsSessionUpdatedEvent object { id, processed_at, type, 3 more }

    Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn.

    • id: string

      Unique identifier for this event.

    • processed_at: string

      A timestamp in RFC 3339 format

    • type: "session.updated"

      • "session.updated"

    • agent: optional BetaManagedAgentsSessionAgent

      Resolved agent definition for a session. Snapshot of the agent at session creation time.

      • id: string

      • description: string

      • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

        • name: string

        • type: "url"

          • "url"

        • url: string

      • model: BetaManagedAgentsModelConfig

        Model identifier and configuration.

        • id: BetaManagedAgentsModel

          The model that will power your agent.

          See models for additional details and options.

          • "claude-opus-4-7" or "claude-opus-4-6" or "claude-sonnet-4-6" or 6 more

            The model that will power your agent.

            See models for additional details and options.

            • "claude-opus-4-7"

              Frontier intelligence for long-running agents and coding

            • "claude-opus-4-6"

              Most intelligent model for building agents and coding

            • "claude-sonnet-4-6"

              Best combination of speed and intelligence

            • "claude-haiku-4-5"

              Fastest model with near-frontier intelligence

            • "claude-haiku-4-5-20251001"

              Fastest model with near-frontier intelligence

            • "claude-opus-4-5"

              Premium model combining maximum intelligence with practical performance

            • "claude-opus-4-5-20251101"

              Premium model combining maximum intelligence with practical performance

            • "claude-sonnet-4-5"

              High-performance model for agents and coding

            • "claude-sonnet-4-5-20250929"

              High-performance model for agents and coding

          • string

        • speed: optional "standard" or "fast"

          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.

          • "standard"

          • "fast"

      • multiagent: BetaManagedAgentsSessionMultiagentCoordinator

        Resolved coordinator topology with full agent definitions for each roster member.

        • agents: array of BetaManagedAgentsSessionThreadAgent

          Full agent definitions the coordinator may spawn as session threads.

          • id: string

          • description: string

          • mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition

            • name: string

            • type: "url"

            • url: string

          • model: BetaManagedAgentsModelConfig

            Model identifier and configuration.

          • name: string

          • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

            • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

              A resolved Anthropic-managed skill.

              • skill_id: string

              • type: "anthropic"

                • "anthropic"

              • version: string

            • BetaManagedAgentsCustomSkill object { skill_id, type, version }

              A resolved user-created custom skill.

              • skill_id: string

              • type: "custom"

                • "custom"

              • version: string

          • system: string

          • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

            • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

              • configs: array of BetaManagedAgentsAgentToolConfig

                • enabled: boolean

                • name: "bash" or "edit" or "read" or 5 more

                  Built-in agent tool identifier.

                  • "bash"

                  • "edit"

                  • "read"

                  • "write"

                  • "glob"

                  • "grep"

                  • "web_fetch"

                  • "web_search"

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                    • type: "always_allow"

                      • "always_allow"

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

                    • type: "always_ask"

                      • "always_ask"

              • default_config: BetaManagedAgentsAgentToolsetDefaultConfig

                Resolved default configuration for agent tools.

                • enabled: boolean

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • type: "agent_toolset_20260401"

                • "agent_toolset_20260401"

            • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

              • configs: array of BetaManagedAgentsMCPToolConfig

                • enabled: boolean

                • name: string

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • default_config: BetaManagedAgentsMCPToolsetDefaultConfig

                Resolved default configuration for all tools from an MCP server.

                • enabled: boolean

                • permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy

                  Permission policy for tool execution.

                  • BetaManagedAgentsAlwaysAllowPolicy object { type }

                    Tool calls are automatically approved without user confirmation.

                  • BetaManagedAgentsAlwaysAskPolicy object { type }

                    Tool calls require user confirmation before execution.

              • mcp_server_name: string

              • type: "mcp_toolset"

                • "mcp_toolset"

            • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

              A custom tool as returned in API responses.

              • description: string

              • input_schema: BetaManagedAgentsCustomToolInputSchema

                JSON Schema for custom tool input parameters.

                • properties: optional map[unknown]

                  JSON Schema properties defining the tool's input parameters.

                • required: optional array of string

                  List of required property names.

                • type: optional "object"

                  Must be 'object' for tool input schemas.

                  • "object"

              • name: string

              • type: "custom"

                • "custom"

          • type: "agent"

            • "agent"

          • version: number

        • type: "coordinator"

          • "coordinator"

      • name: string

      • skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill

        • BetaManagedAgentsAnthropicSkill object { skill_id, type, version }

          A resolved Anthropic-managed skill.

        • BetaManagedAgentsCustomSkill object { skill_id, type, version }

          A resolved user-created custom skill.

      • system: string

      • tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool

        • BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }

        • BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }

        • BetaManagedAgentsCustomTool object { description, input_schema, name, type }

          A custom tool as returned in API responses.

      • type: "agent"

        • "agent"

      • version: number

    • metadata: optional map[string]

      The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty.

    • title: optional string

      The session's new title. Present only when the update changed it.