[
	{
		"scope": "https://api.anthropic.com:443",
		"method": "POST",
		"path": "/v1/messages",
		"body": {
			"model": "claude-sonnet-4-5",
			"max_tokens": 64000,
			"system": [
				{
					"type": "text",
					"text": "<built_in_rules>\n- delegate_subagent runs a focused child agent in a fresh, isolated context and returns only its final answer. Always set subAgentId. Use subAgentId: \"inline\" to run a one-off inline child that inherits your local and deferred tools after safety filtering. Inline children do not inherit provider-defined tools. The child cannot see this conversation or your memory, so everything it needs must be in the call.\nUse a configured subagent ID only when one is listed and its name and useWhen guidance fit the subtask better than a generic inline child.\nDELEGATION PARALLELISM:\n- Up to 1 child sub-agent run can execute at the same time.\n- This limits parallelism, not the total number of delegated tasks.\n- If more independent workstreams are useful, you may issue more delegate_subagent calls; the runtime will run them in batches.\nWHEN TO USE delegate_subagent:\n- The request decomposes into 2+ independent workstreams that can be handled separately.\n- A workstream needs substantial research, review, comparison, or analysis.\n- Doing the work inline would flood your context with intermediate findings.\n- A fresh isolated perspective would materially improve a bounded subtask.\nWHEN NOT TO USE delegate_subagent:\n- Single-step mechanical work: do it directly.\n- Trivial tasks or one/two tool calls: do them yourself.\n- Tasks that need user interaction or hidden conversation context.\n- Your core synthesis, final judgment, or recommendation.\n- The entire user request as one delegated task; that is pass-through with no value added.\nHOW TO DELEGATE:\n- Delegate bounded workstreams, not the final answer.\n- Pass all required context, constraints, language/tone, and expected output.\n- Set difficulty (low, medium, or high) when you can estimate task complexity; omit it to keep the default inline model.\n- If multiple independent workstreams exist, delegate them separately.\n- Inline children inherit your local and deferred tools after safety filtering. Inline children do not inherit provider-defined tools.\n- Inspect results and synthesize the final response yourself.\n- Verify side-effect claims before presenting them as done.\n</built_in_rules>\n\nYou are a parent streaming test agent. You must call delegate_subagent exactly once before answering. Set subAgentId to \"inline\" in that tool call. The child result will contain a sentinel token. After the tool returns, answer with PARENT_STREAM_SAW and include the sentinel token from the child result. Do not add unrelated text."
				}
			],
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "Delegate the token-production workstream to a child agent. The delegated goal must instruct the child to answer with exactly this token and nothing else: SUBAGENT_OK_731. Then synthesize only from the child result."
						}
					]
				}
			],
			"tools": [
				{
					"name": "delegate_subagent",
					"description": "Delegate a bounded, self-contained subtask to a focused child agent that runs in an isolated context and returns only a concise final result. Use it for reasoning-heavy subtasks, context-flooding investigations, or independent workstreams inside a larger deliverable. Do not use it for trivial work, single tool calls, mechanical steps, tasks that need hidden conversation context, or pass-through delegation of the entire user request.",
					"input_schema": {
						"type": "object",
						"properties": {
							"subAgentId": {
								"type": "string",
								"minLength": 1,
								"description": "Required. Use \"inline\" for a one-off inline sub-agent. Use an exact configured sub-agent ID only when one is listed and fits the task."
							},
							"taskName": {
								"type": "string",
								"minLength": 1,
								"description": "Short human-readable name for this delegated task, e.g. \"research_api\"."
							},
							"goal": {
								"type": "string",
								"minLength": 1,
								"description": "The concrete goal the sub-agent should accomplish."
							},
							"context": {
								"type": "string",
								"description": "All details the child needs, since it sees nothing else: constraints, paths, data, prior decisions, acceptance criteria, and what you have already tried or ruled out."
							},
							"expectedOutput": {
								"type": "string",
								"description": "The expected shape or contents of the answer."
							},
							"difficulty": {
								"type": "string",
								"enum": ["low", "medium", "high"],
								"description": "Optional difficulty estimate for this delegated task. Use low for simple bounded work, medium for moderate analysis or implementation, and high for complex research, architecture, or multi-step reasoning."
							}
						},
						"required": ["subAgentId", "taskName", "goal"],
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				}
			],
			"tool_choice": {
				"type": "auto"
			},
			"stream": true
		},
		"status": 200,
		"response": [
			"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"
		],
		"rawHeaders": {
			"anthropic-ratelimit-input-tokens-limit": "22500000",
			"anthropic-ratelimit-input-tokens-remaining": "22499000",
			"anthropic-ratelimit-input-tokens-reset": "2026-07-30T10:45:12Z",
			"anthropic-ratelimit-output-tokens-limit": "4500000",
			"anthropic-ratelimit-output-tokens-remaining": "4500000",
			"anthropic-ratelimit-output-tokens-reset": "2026-07-30T10:45:12Z",
			"anthropic-ratelimit-requests-limit": "20000",
			"anthropic-ratelimit-requests-remaining": "19999",
			"anthropic-ratelimit-requests-reset": "2026-07-30T10:45:12Z",
			"anthropic-ratelimit-tokens-limit": "27000000",
			"anthropic-ratelimit-tokens-remaining": "26999000",
			"anthropic-ratelimit-tokens-reset": "2026-07-30T10:45:12Z",
			"cache-control": "no-cache",
			"cf-cache-status": "DYNAMIC",
			"cf-ray": "a233c5bd3cf3af0a-VIE",
			"connection": "keep-alive",
			"content-encoding": "gzip",
			"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
			"content-type": "text/event-stream; charset=utf-8",
			"date": "Thu, 30 Jul 2026 10:45:13 GMT",
			"request-id": "req_011CdY785JetXbgfBdKXmCrT",
			"server": "cloudflare",
			"strict-transport-security": "max-age=31536000; includeSubDomains; preload",
			"traceresponse": "00-05b1b866ae30456b98f16a457ac084d6-9ecac75622f59220-01",
			"transfer-encoding": "chunked",
			"vary": "Accept-Encoding",
			"x-robots-tag": "none"
		},
		"responseIsBinary": false
	},
	{
		"scope": "https://api.anthropic.com:443",
		"method": "POST",
		"path": "/v1/messages",
		"body": {
			"model": "claude-sonnet-4-5",
			"max_tokens": 64000,
			"system": [
				{
					"type": "text",
					"text": "You are a focused subagent working on a specific delegated task. Complete the delegated task independently and return a concise, self-contained summary to your parent agent."
				}
			],
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "You are a focused subagent working on a specific delegated task.\n\nYOUR TASK:\nAnswer with exactly this token and nothing else: SUBAGENT_OK_731\n\nEXPECTED OUTPUT:\nThe exact token: SUBAGENT_OK_731\n\nComplete this task using the tools available to you. When finished, provide a clear, concise summary of:\n- What you did\n- What you found or accomplished\n- Important outputs, decisions, or evidence\n- Any issues, assumptions, or limitations\n\nIf the information above is insufficient, do your best with explicitly stated assumptions and note what was missing, rather than stopping to ask.\n\nBe thorough but concise -- your response is returned to the parent agent as a summary."
						}
					]
				}
			],
			"stream": true
		},
		"status": 200,
		"response": [
			"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"
		],
		"rawHeaders": {
			"anthropic-ratelimit-input-tokens-limit": "22500000",
			"anthropic-ratelimit-input-tokens-remaining": "22500000",
			"anthropic-ratelimit-input-tokens-reset": "2026-07-30T10:45:15Z",
			"anthropic-ratelimit-output-tokens-limit": "4500000",
			"anthropic-ratelimit-output-tokens-remaining": "4500000",
			"anthropic-ratelimit-output-tokens-reset": "2026-07-30T10:45:15Z",
			"anthropic-ratelimit-requests-limit": "20000",
			"anthropic-ratelimit-requests-remaining": "19999",
			"anthropic-ratelimit-requests-reset": "2026-07-30T10:45:15Z",
			"anthropic-ratelimit-tokens-limit": "27000000",
			"anthropic-ratelimit-tokens-remaining": "27000000",
			"anthropic-ratelimit-tokens-reset": "2026-07-30T10:45:15Z",
			"cache-control": "no-cache",
			"cf-cache-status": "DYNAMIC",
			"cf-ray": "a233c5d16eb8af0a-VIE",
			"connection": "keep-alive",
			"content-encoding": "gzip",
			"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
			"content-type": "text/event-stream; charset=utf-8",
			"date": "Thu, 30 Jul 2026 10:45:16 GMT",
			"request-id": "req_011CdY78JTg2zufpwvK2Uvbp",
			"server": "cloudflare",
			"strict-transport-security": "max-age=31536000; includeSubDomains; preload",
			"traceresponse": "00-20c5cb3b9b6d07470c38f23d730e5d0a-7ecbe286d9ef4513-01",
			"transfer-encoding": "chunked",
			"vary": "Accept-Encoding",
			"x-robots-tag": "none"
		},
		"responseIsBinary": false
	},
	{
		"scope": "https://api.anthropic.com:443",
		"method": "POST",
		"path": "/v1/messages",
		"body": {
			"model": "claude-sonnet-4-5",
			"max_tokens": 64000,
			"system": [
				{
					"type": "text",
					"text": "<built_in_rules>\n- delegate_subagent runs a focused child agent in a fresh, isolated context and returns only its final answer. Always set subAgentId. Use subAgentId: \"inline\" to run a one-off inline child that inherits your local and deferred tools after safety filtering. Inline children do not inherit provider-defined tools. The child cannot see this conversation or your memory, so everything it needs must be in the call.\nUse a configured subagent ID only when one is listed and its name and useWhen guidance fit the subtask better than a generic inline child.\nDELEGATION PARALLELISM:\n- Up to 1 child sub-agent run can execute at the same time.\n- This limits parallelism, not the total number of delegated tasks.\n- If more independent workstreams are useful, you may issue more delegate_subagent calls; the runtime will run them in batches.\nWHEN TO USE delegate_subagent:\n- The request decomposes into 2+ independent workstreams that can be handled separately.\n- A workstream needs substantial research, review, comparison, or analysis.\n- Doing the work inline would flood your context with intermediate findings.\n- A fresh isolated perspective would materially improve a bounded subtask.\nWHEN NOT TO USE delegate_subagent:\n- Single-step mechanical work: do it directly.\n- Trivial tasks or one/two tool calls: do them yourself.\n- Tasks that need user interaction or hidden conversation context.\n- Your core synthesis, final judgment, or recommendation.\n- The entire user request as one delegated task; that is pass-through with no value added.\nHOW TO DELEGATE:\n- Delegate bounded workstreams, not the final answer.\n- Pass all required context, constraints, language/tone, and expected output.\n- Set difficulty (low, medium, or high) when you can estimate task complexity; omit it to keep the default inline model.\n- If multiple independent workstreams exist, delegate them separately.\n- Inline children inherit your local and deferred tools after safety filtering. Inline children do not inherit provider-defined tools.\n- Inspect results and synthesize the final response yourself.\n- Verify side-effect claims before presenting them as done.\n</built_in_rules>\n\nYou are a parent streaming test agent. You must call delegate_subagent exactly once before answering. Set subAgentId to \"inline\" in that tool call. The child result will contain a sentinel token. After the tool returns, answer with PARENT_STREAM_SAW and include the sentinel token from the child result. Do not add unrelated text."
				}
			],
			"messages": [
				{
					"role": "user",
					"content": [
						{
							"type": "text",
							"text": "Delegate the token-production workstream to a child agent. The delegated goal must instruct the child to answer with exactly this token and nothing else: SUBAGENT_OK_731. Then synthesize only from the child result."
						}
					]
				},
				{
					"role": "assistant",
					"content": [
						{
							"type": "text",
							"text": "I'll delegate the token-production workstream to a child agent now."
						},
						{
							"type": "tool_use",
							"id": "toolu_01MG5A4WnVuM3AQFQ9BZHb6G",
							"name": "delegate_subagent",
							"input": {
								"subAgentId": "inline",
								"taskName": "token_production",
								"goal": "Answer with exactly this token and nothing else: SUBAGENT_OK_731",
								"expectedOutput": "The exact token: SUBAGENT_OK_731"
							},
							"caller": {
								"type": "direct"
							}
						}
					]
				},
				{
					"role": "user",
					"content": [
						{
							"type": "tool_result",
							"tool_use_id": "toolu_01MG5A4WnVuM3AQFQ9BZHb6G",
							"content": "{\"status\":\"completed\",\"taskPath\":\"/root/token_production_0\",\"model\":\"anthropic/claude-sonnet-4-5\",\"answer\":\"I have completed the delegated task.\\n\\n**What I did:**\\nI was instructed to answer with exactly the token \\\"SUBAGENT_OK_731\\\" and nothing else.\\n\\n**What I accomplished:**\\nSUBAGENT_OK_731\\n\\n**Important outputs:**\\nThe required token has been provided above as requested.\\n\\n**Issues, assumptions, or limitations:**\\nNone. The task was straightforward and clearly specified.\",\"usage\":{\"promptTokens\":199,\"completionTokens\":94,\"totalTokens\":293,\"cost\":0.002007},\"finishReason\":\"stop\"}"
						}
					]
				}
			],
			"tools": [
				{
					"name": "delegate_subagent",
					"description": "Delegate a bounded, self-contained subtask to a focused child agent that runs in an isolated context and returns only a concise final result. Use it for reasoning-heavy subtasks, context-flooding investigations, or independent workstreams inside a larger deliverable. Do not use it for trivial work, single tool calls, mechanical steps, tasks that need hidden conversation context, or pass-through delegation of the entire user request.",
					"input_schema": {
						"type": "object",
						"properties": {
							"subAgentId": {
								"type": "string",
								"minLength": 1,
								"description": "Required. Use \"inline\" for a one-off inline sub-agent. Use an exact configured sub-agent ID only when one is listed and fits the task."
							},
							"taskName": {
								"type": "string",
								"minLength": 1,
								"description": "Short human-readable name for this delegated task, e.g. \"research_api\"."
							},
							"goal": {
								"type": "string",
								"minLength": 1,
								"description": "The concrete goal the sub-agent should accomplish."
							},
							"context": {
								"type": "string",
								"description": "All details the child needs, since it sees nothing else: constraints, paths, data, prior decisions, acceptance criteria, and what you have already tried or ruled out."
							},
							"expectedOutput": {
								"type": "string",
								"description": "The expected shape or contents of the answer."
							},
							"difficulty": {
								"type": "string",
								"enum": ["low", "medium", "high"],
								"description": "Optional difficulty estimate for this delegated task. Use low for simple bounded work, medium for moderate analysis or implementation, and high for complex research, architecture, or multi-step reasoning."
							}
						},
						"required": ["subAgentId", "taskName", "goal"],
						"additionalProperties": false,
						"$schema": "http://json-schema.org/draft-07/schema#"
					}
				}
			],
			"tool_choice": {
				"type": "auto"
			},
			"stream": true
		},
		"status": 200,
		"response": [
			"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"
		],
		"rawHeaders": {
			"anthropic-ratelimit-input-tokens-limit": "22500000",
			"anthropic-ratelimit-input-tokens-remaining": "22499000",
			"anthropic-ratelimit-input-tokens-reset": "2026-07-30T10:45:18Z",
			"anthropic-ratelimit-output-tokens-limit": "4500000",
			"anthropic-ratelimit-output-tokens-remaining": "4500000",
			"anthropic-ratelimit-output-tokens-reset": "2026-07-30T10:45:18Z",
			"anthropic-ratelimit-requests-limit": "20000",
			"anthropic-ratelimit-requests-remaining": "19999",
			"anthropic-ratelimit-requests-reset": "2026-07-30T10:45:18Z",
			"anthropic-ratelimit-tokens-limit": "27000000",
			"anthropic-ratelimit-tokens-remaining": "26999000",
			"anthropic-ratelimit-tokens-reset": "2026-07-30T10:45:18Z",
			"cache-control": "no-cache",
			"cf-cache-status": "DYNAMIC",
			"cf-ray": "a233c5e73a73af0a-VIE",
			"connection": "keep-alive",
			"content-encoding": "gzip",
			"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
			"content-type": "text/event-stream; charset=utf-8",
			"date": "Thu, 30 Jul 2026 10:45:19 GMT",
			"request-id": "req_011CdY78ZM7unYh8K5fxmvc1",
			"server": "cloudflare",
			"strict-transport-security": "max-age=31536000; includeSubDomains; preload",
			"traceresponse": "00-590c063aee0ac5a9b22cb12a484c5572-37ff21bc76d37853-01",
			"transfer-encoding": "chunked",
			"vary": "Accept-Encoding",
			"x-robots-tag": "none"
		},
		"responseIsBinary": false
	}
]