Internal orchestrator-to-subagent communication leaks into final AssistantMessage

[erdem-b]

Description

When using multi-agent orchestration with ClaudeSDKClient, internal communication between the orchestrator and sub-agents (via the Task tool) is included in the final AssistantMessage content, even when include_partial_messages=False (the default).

Expected Behavior

Only the final user-facing response from the orchestrator should be included in AssistantMessage objects yielded by receive_response(). Internal delegation prompts and sub-agent responses should not be visible.

Actual Behavior

The AssistantMessage.content includes internal text like:

• Orchestrator delegation prompts: "Search for marbles matching this profile: elegant white marble with gold veins. This describes a prestigious, luxurious aesthetic..."
• Sub-agent task instructions: "Return the marble IDs found"
• Other internal workflow text

This internal content is concatenated with the actual user-facing response.

Reproduction

from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, AssistantMessage, TextBlock

options = ClaudeAgentOptions(
    agents={
        "ProfileSearcher": {
            "description": "Searches for marbles by profile",
            "prompt": "You search for marbles. Return marble IDs.",
            "tools": ["mcp__tools__search"]
        }
    },
    allowed_tools=["Task", "mcp__tools__search"],
    # include_partial_messages=False  # Default
)

async with ClaudeSDKClient(options) as client:
    await client.query("Find white marbles with gold veins")
    
    async for message in client.receive_response():
        if isinstance(message, AssistantMessage):
            for block in message.content:
                if isinstance(block, TextBlock):
                    print(block.text)  # Contains internal delegation text!

Environment

• claude-agent-sdk version: 0.1.10
• Python version: 3.11
• OS: Linux (Docker container)

Workaround Attempted

We tried using include_partial_messages=True with content filtering patterns, but this is fragile and not a proper solution.

Suggested Fix

The SDK should either:

1. Filter out Task tool delegation content from final messages automatically
2. Provide a message type or flag to distinguish internal vs user-facing content
3. Document the expected behavior for multi-agent message handling

[qing-ant]

Closing as stale. This was filed against SDK v0.1.10 (November 2025), which is significantly outdated — the current version is v0.1.50. The Task tool / subagent system and message streaming pipeline have been substantially reworked since then, including the introduction of TaskStartedMessage, TaskProgressMessage, and TaskNotificationMessage types that provide structured visibility into subagent activity.

If internal orchestrator-to-subagent communication still leaks into AssistantMessage content on the current SDK version, please open a new issue with updated reproduction steps and SDK version.