docs/src/oss/deepagents/subagents.mdx at 3cd0396268f69b15e210ed249ff516fe91fc6110 · langchain-ai/docs

title	Subagents
description	Learn how to use subagents to delegate work and keep context clean

import SubagentBasicPy from '/snippets/subagent-basic-py.mdx'; import SubagentBasicJs from '/snippets/subagent-basic-js.mdx';

Deep Agents can create subagents to delegate work. You can specify custom subagents in the subagents parameter. Subagents are useful for context quarantine (keeping the main agent's context clean) and for providing specialized instructions.

This page covers synchronous subagents, where the supervisor blocks until the subagent finishes. For long-running tasks, parallel workstreams, or cases where you need mid-flight steering and cancellation, see Async subagents.

graph TB
    Main[Main Agent] --> |task tool| Sub[Subagent]

    Sub --> Research[Research]
    Sub --> Code[Code]
    Sub --> General[General]

    Research --> |isolated work| Result[Final Result]
    Code --> |isolated work| Result
    General --> |isolated work| Result

    Result --> Main

Why use subagents?

Subagents solve the context bloat problem. When agents use tools with large outputs (web search, file reads, database queries), the context window fills up quickly with intermediate results. Subagents isolate this detailed work—the main agent receives only the final result, not the dozens of tool calls that produced it.

When to use subagents:

✅ Multi-step tasks that would clutter the main agent's context
✅ Specialized domains that need custom instructions or tools
✅ Tasks requiring different model capabilities
✅ When you want to keep the main agent focused on high-level coordination

When NOT to use subagents:

❌ Simple, single-step tasks
❌ When you need to maintain intermediate context
❌ When the overhead outweighs benefits

Configuration

subagents should be a list of dictionaries or @[CompiledSubAgent] objects. There are two types:

SubAgent (Dictionary-based)

For most use cases, define subagents as dictionaries matching the @[SubAgent] spec with the following fields:

:::python

Field	Type	Description
`name`	`str`	Required. Unique identifier for the subagent. The main agent uses this name when calling the `task()` tool. The subagent name becomes metadata for `AIMessage`s and for streaming, which helps to differentiate between agents.
`description`	`str`	Required. Description of what this subagent does. Be specific and action-oriented. The main agent uses this to decide when to delegate.
`system_prompt`	`str`	Required. Instructions for the subagent. Custom subagents must define their own. Include tool usage guidance and output format requirements. Does not inherit from main agent.
`tools`	`list[Callable]`	Optional. Tools the subagent can use. Keep this minimal and include only what's needed. Inherits from main agent by default. When specified, overrides the inherited tools entirely.
`model`	`str` \| `BaseChatModel`	Optional. Overrides the main agent's model. Omit to use the main agent's model. Inherits from main agent by default. You can pass either a model identifier string like `'openai:gpt-5.4'` (using the `'provider:model'` format) or a LangChain chat model object (`init_chat_model("gpt-5.4")` or `ChatOpenAI(model="gpt-5.4")`).
`middleware`	`list[Middleware]`	Optional. Additional middleware for custom behavior, logging, or rate limiting. Does not inherit from main agent.
`interrupt_on`	`dict[str, bool]`	Optional. Configure human-in-the-loop for specific tools. Subagent value overrides main agent. Requires checkpointer. Inherits from main agent by default. Subagent value overrides the default.
`skills`	`list[str]`	Optional. Skills source paths. When specified, the subagent will load skills from these directories (e.g., `["/skills/research/", "/skills/web-search/"]`). This allows subagents to have different skill sets than the main agent. Does not inherit from main agent. Only the general-purpose subagent inherits the main agent's skills. When a subagent has skills, it runs its own independent @[`SkillsMiddleware`] instance. Skill state is fully isolated—a subagent's loaded skills are not visible to the parent, and vice versa.
`response_format`	`ResponseFormat`	Optional. Structured output schema for the subagent. When set, the parent receives the subagent's result as JSON instead of free-form text. Accepts Pydantic models, `ToolStrategy(...)`, `ProviderStrategy(...)`, or a raw schema type. See Structured output.
`permissions`	`list[FilesystemPermission]`	Optional. Filesystem permission rules for the subagent. When set, replaces the parent agent's permissions entirely. Inherits from main agent by default.

:::

:::js

Field	Type	Description
`name`	`str`	Required. Unique identifier for the subagent. The main agent uses this name when calling the `task()` tool. The subagent name becomes metadata for `AIMessage`s and for streaming, which helps to differentiate between agents.
`description`	`str`	Required. Description of what this subagent does. Be specific and action-oriented. The main agent uses this to decide when to delegate.
`system_prompt`	`str`	Required. Instructions for the subagent. Custom subagents must define their own. Include tool usage guidance and output format requirements. Does not inherit from main agent.
`tools`	`list[Callable]`	Optional. Tools the subagent can use. Keep this minimal and include only what's needed. Inherits from main agent by default. When specified, overrides the inherited tools entirely.
`model`	`str` \| `BaseChatModel`	Optional. Overrides the main agent's model. Omit to use the main agent's model. Inherits from main agent by default. You can pass either a model identifier string like `'openai:gpt-5.4'` (using the `'provider:model'` format) or a LangChain chat model object (`await initChatModel("gpt-5.4")` or `new ChatOpenAI({ model: "gpt-5.4" })`).
`middleware`	`list[Middleware]`	Optional. Additional middleware for custom behavior, logging, or rate limiting. Does not inherit from main agent.
`interrupt_on`	`dict[str, bool]`	Optional. Configure human-in-the-loop for specific tools. Subagent value overrides main agent. Requires checkpointer. Inherits from main agent by default. Subagent value overrides the default.
`skills`	`list[str]`	Optional. Skills source paths. When specified, the subagent will load skills from these directories (e.g., `["/skills/research/", "/skills/web-search/"]`). This allows subagents to have different skill sets than the main agent. Does not inherit from main agent. Only the general-purpose subagent inherits the main agent's skills. When a subagent has skills, it runs its own independent @[`SkillsMiddleware`] instance. Skill state is fully isolated—a subagent's loaded skills are not visible to the parent, and vice versa.
`responseFormat`	`ResponseFormat`	Optional. Structured output schema for the subagent. When set, the parent receives the subagent's result as JSON instead of free-form text. Accepts Zod schemas, JSON schema objects, `toolStrategy(...)`, or `providerStrategy(...)`. See Structured output.

:::

**CLI users:** You can also define subagents as `AGENTS.md` files on disk instead of in code. The `name`, `description`, and `model` fields map to YAML frontmatter, and the markdown body becomes the `system_prompt`. See [Custom subagents](/oss/deepagents/cli/overview#subagents) for the file format.

**Deploy users:** Define subagents as directories under `subagents/` with their own `deepagents.toml` and `AGENTS.md`. The bundler auto-discovers them. See [Deploy subagents](/oss/deepagents/deploy#subagents) for the full configuration reference.

CompiledSubAgent

For complex workflows, use a prebuilt LangGraph graph as a @[CompiledSubAgent]:

Field	Type	Description
`name`	`str`	Required. Unique identifier for the subagent. The subagent name becomes metadata for `AIMessage`s and for streaming, which helps to differentiate between agents.
`description`	`str`	Required. What this subagent does.
`runnable`	`Runnable`	Required. A compiled LangGraph graph (must call `.compile()` first).

Using SubAgent

:::python :::

:::js :::

Using CompiledSubAgent

For more complex use cases, you can provide your custom subagents with @[CompiledSubAgent]. You can create a custom subagent using LangChain's @[create_agent] or by making a custom LangGraph graph using the graph API.

If you're creating a custom LangGraph graph, make sure that the graph has a state key called "messages":

:::python

from deepagents import create_deep_agent, CompiledSubAgent
from langchain.agents import create_agent

# Create a custom agent graph
custom_graph = create_agent(
    model=your_model,
    tools=specialized_tools,
    prompt="You are a specialized agent for data analysis..."
)

# Use it as a custom subagent
custom_subagent = CompiledSubAgent(
    name="data-analyzer",
    description="Specialized agent for complex data analysis tasks",
    runnable=custom_graph
)

subagents = [custom_subagent]

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    tools=[internet_search],
    system_prompt=research_instructions,
    subagents=subagents
)

:::

:::js

import { createDeepAgent, CompiledSubAgent } from "deepagents";
import { createAgent } from "langchain";

// Create a custom agent graph
const customGraph = createAgent({
  model: yourModel,
  tools: specializedTools,
  prompt: "You are a specialized agent for data analysis...",
});

// Use it as a custom subagent
const customSubagent: CompiledSubAgent = {
  name: "data-analyzer",
  description: "Specialized agent for complex data analysis tasks",
  runnable: customGraph,
};

const subagents = [customSubagent];

const agent = createDeepAgent({
  model: "google_genai:gemini-3.1-pro-preview",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
  subagents: subagents,
});

:::

Streaming

When streaming tracing information agents' names are available as lc_agent_name in metadata. When reviewing tracing information, you can use this metadata to differentiate which agent the data came from.

The following example creates a deep agent with the name main-agent and a subagent with the name research-agent:

import os
from typing import Literal
from tavily import TavilyClient
from deepagents import create_deep_agent

tavily_client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])

def internet_search(
    query: str,
    max_results: int = 5,
    topic: Literal["general", "news", "finance"] = "general",
    include_raw_content: bool = False,
):
    """Run a web search"""
    return tavily_client.search(
        query,
        max_results=max_results,
        include_raw_content=include_raw_content,
        topic=topic,
    )

research_subagent = {
    "name": "research-agent",
    "description": "Used to research more in depth questions",
    "system_prompt": "You are a great researcher",
    "tools": [internet_search],
    "model": "google_genai:gemini-3.1-pro-preview",  # Optional override, defaults to main agent model
}
subagents = [research_subagent]

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    subagents=subagents,
    name="main-agent"
)

As you prompt your deepagents, all agent runs executed by a subagent or deep agent will have the agent name in their metadata. In this case the subagent with the name "research-agent", will have {'lc_agent_name': 'research-agent'} in any associated agent run metadata:

Structured output

Subagents support structured output, so the parent agent receives predictable, parseable JSON instead of free-form text.

:::python Pass response_format on the subagent config. When the subagent finishes, its structured response is JSON-serialized and returned as the ToolMessage content to the parent agent. The schema accepts anything supported by @[create_agent]: Pydantic models, ToolStrategy(...), ProviderStrategy(...), or a raw schema type.

from pydantic import BaseModel, Field

from deepagents import create_deep_agent


class ResearchFindings(BaseModel):
    """Structured findings from a research task."""
    summary: str = Field(description="Summary of findings")
    confidence: float = Field(description="Confidence score from 0 to 1")
    sources: list[str] = Field(description="List of source URLs")

research_subagent = {
    "name": "researcher",
    "description": "Researches topics and returns structured findings",
    "system_prompt": "Research the given topic thoroughly. Return your findings.",
    "tools": [web_search],
    "response_format": ResearchFindings,
}

agent = create_deep_agent(
    model="claude-sonnet-4-6",
    subagents=[research_subagent],
)

result = await agent.ainvoke(
    {"messages": [{"role": "user", "content": "Research recent advances in quantum computing"}]}
)

# The parent's ToolMessage contains JSON-serialized structured data:
# '{"summary": "...", "confidence": 0.87, "sources": ["https://..."]}'

:::

:::js Pass responseFormat on the subagent config. When the subagent finishes, its structured response is JSON-serialized and returned as the ToolMessage content to the parent agent. The schema accepts anything supported by createAgent: Zod schemas, JSON schema objects, toolStrategy(...), or providerStrategy(...).

import { z } from "zod";
import { createDeepAgent } from "deepagents";

const ResearchFindings = z.object({
  summary: z.string().describe("Summary of findings"),
  confidence: z.number().describe("Confidence score from 0 to 1"),
  sources: z.array(z.string()).describe("List of source URLs"),
});

const researchSubagent = {
  name: "researcher",
  description: "Researches topics and returns structured findings",
  systemPrompt: "Research the given topic thoroughly. Return your findings.",
  tools: [webSearch],
  responseFormat: ResearchFindings,
};

const agent = createDeepAgent({
  model: "claude-sonnet-4-6",
  subagents: [researchSubagent],
});

const result = await agent.invoke({
  messages: [{ role: "user", content: "Research recent advances in quantum computing" }],
});

// The parent's ToolMessage contains JSON-serialized structured data:
// '{"summary": "...", "confidence": 0.87, "sources": ["https://..."]}'

:::

Without response_format, the parent receives the subagent's last message text as-is. With it, the parent always gets valid JSON matching the schema, which is useful when the parent needs to process the result programmatically or pass it to downstream tools.

For full details on schema types and strategies (tool calling vs. provider-native), see Structured output.

The general-purpose subagent

In addition to any user-defined subagents, Deep Agents have access to a general-purpose subagent at all times. This subagent:

Has the same system prompt as the main agent
Has access to all the same tools
Uses the same model (unless overridden)
Inherits skills from the main agent (when skills are configured)

Override the general-purpose subagent

:::python Include a subagent with name="general-purpose" in your subagents list to replace the default. Use this to configure a different model, tools, or system prompt for the general-purpose subagent:

from deepagents import create_deep_agent

# Main agent uses Gemini; general-purpose subagent uses GPT
agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    tools=[internet_search],
    subagents=[
        {
            "name": "general-purpose",
            "description": "General-purpose agent for research and multi-step tasks",
            "system_prompt": "You are a general-purpose assistant.",
            "tools": [internet_search],
            "model": "openai:gpt-5.4",  # Different model for delegated tasks
        },
    ],
)

:::

:::js Include a subagent with name: "general-purpose" in your subagents list to replace the default. Use this to configure a different model, tools, or system prompt for the general-purpose subagent:

import { createDeepAgent } from "deepagents";

// Main agent uses Gemini; general-purpose subagent uses GPT
const agent = await createDeepAgent({
  model: "google_genai:gemini-3.1-pro-preview",
  tools: [internetSearch],
  subagents: [
    {
      name: "general-purpose",
      description: "General-purpose agent for research and multi-step tasks",
      systemPrompt: "You are a general-purpose assistant.",
      tools: [internetSearch],
      model: "openai:gpt-5.4",  // Different model for delegated tasks
    },
  ],
});

:::

When you provide a subagent with the general-purpose name, the default general-purpose subagent is not added. Your spec fully replaces it.

When to use it

The general-purpose subagent is ideal for context isolation without specialized behavior. The main agent can delegate a complex multi-step task to this subagent and get a concise result back without bloat from intermediate tool calls.

Instead of the main agent making 10 web searches and filling its context with results, it delegates to the general-purpose subagent: `task(name="general-purpose", task="Research quantum computing trends")`. The subagent performs all the searches internally and returns only a summary.

Skills inheritance

When configuring skills with create_deep_agent:

General-purpose subagent: Automatically inherits skills from the main agent
Custom subagents: Do NOT inherit skills by default—use the skills parameter to give them their own skills

Only subagents configured with skills get a `SkillsMiddleware` instance—custom subagents without a `skills` parameter do not. When present, skill state is fully isolated in both directions: the parent's skills are not visible to the child, and the child's skills are not propagated back to the parent.

:::python

from deepagents import create_deep_agent

# Research subagent with its own skills
research_subagent = {
    "name": "researcher",
    "description": "Research assistant with specialized skills",
    "system_prompt": "You are a researcher.",
    "tools": [web_search],
    "skills": ["/skills/research/", "/skills/web-search/"],  # Subagent-specific skills
}

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    skills=["/skills/main/"],  # Main agent and GP subagent get these
    subagents=[research_subagent],  # Gets only /skills/research/ and /skills/web-search/
)

:::

:::js

import { createDeepAgent, SubAgent } from "deepagents";

// Research subagent with its own skills
const researchSubagent: SubAgent = {
  name: "researcher",
  description: "Research assistant with specialized skills",
  systemPrompt: "You are a researcher.",
  tools: [webSearch],
  skills: ["/skills/research/", "/skills/web-search/"],  // Subagent-specific skills
};

const agent = createDeepAgent({
  model: "google_genai:gemini-3.1-pro-preview",
  skills: ["/skills/main/"],  // Main agent and GP subagent get these
  subagents: [researchSubagent],  // Gets only /skills/research/ and /skills/web-search/
});

:::

Best practices

Write clear descriptions

The main agent uses descriptions to decide which subagent to call. Be specific:

✅ Good: "Analyzes financial data and generates investment insights with confidence scores"

❌ Bad: "Does finance stuff"

Keep system prompts detailed

Include specific guidance on how to use tools and format outputs:

:::python

research_subagent = {
    "name": "research-agent",
    "description": "Conducts in-depth research using web search and synthesizes findings",
    "system_prompt": """You are a thorough researcher. Your job is to:

    1. Break down the research question into searchable queries
    2. Use internet_search to find relevant information
    3. Synthesize findings into a comprehensive but concise summary
    4. Cite sources when making claims

    Output format:
    - Summary (2-3 paragraphs)
    - Key findings (bullet points)
    - Sources (with URLs)

    Keep your response under 500 words to maintain clean context.""",
    "tools": [internet_search],
}

:::

:::js

const researchSubagent = {
  name: "research-agent",
  description: "Conducts in-depth research using web search and synthesizes findings",
  systemPrompt: `You are a thorough researcher. Your job is to:

  1. Break down the research question into searchable queries
  2. Use internet_search to find relevant information
  3. Synthesize findings into a comprehensive but concise summary
  4. Cite sources when making claims

  Output format:
  - Summary (2-3 paragraphs)
  - Key findings (bullet points)
  - Sources (with URLs)

  Keep your response under 500 words to maintain clean context.`,
  tools: [internetSearch],
};

:::

Minimize tool sets

Only give subagents the tools they need. This improves focus and security:

:::python

# ✅ Good: Focused tool set
email_agent = {
    "name": "email-sender",
    "tools": [send_email, validate_email],  # Only email-related
}

# ❌ Bad: Too many tools
email_agent = {
    "name": "email-sender",
    "tools": [send_email, web_search, database_query, file_upload],  # Unfocused
}

:::

:::js

// ✅ Good: Focused tool set
const emailAgent = {
  name: "email-sender",
  tools: [sendEmail, validateEmail],  // Only email-related
};

// ❌ Bad: Too many tools
const emailAgentBad = {
  name: "email-sender",
  tools: [sendEmail, webSearch, databaseQuery, fileUpload],  // Unfocused
};

:::

Choose models by task

Different models excel at different tasks:

:::python

subagents = [
    {
        "name": "contract-reviewer",
        "description": "Reviews legal documents and contracts",
        "system_prompt": "You are an expert legal reviewer...",
        "tools": [read_document, analyze_contract],
        "model": "google_genai:gemini-3.1-pro-preview",  # Large context for long documents
    },
    {
        "name": "financial-analyst",
        "description": "Analyzes financial data and market trends",
        "system_prompt": "You are an expert financial analyst...",
        "tools": [get_stock_price, analyze_fundamentals],
        "model": "openai:gpt-5.4",  # Better for numerical analysis
    },
]

:::

:::js

const subagents = [
  {
    name: "contract-reviewer",
    description: "Reviews legal documents and contracts",
    systemPrompt: "You are an expert legal reviewer...",
    tools: [readDocument, analyzeContract],
    model: "google_genai:gemini-3.1-pro-preview",  // Large context for long documents
  },
  {
    name: "financial-analyst",
    description: "Analyzes financial data and market trends",
    systemPrompt: "You are an expert financial analyst...",
    tools: [getStockPrice, analyzeFundamentals],
    model: "gpt-5.4",  // Better for numerical analysis
  },
];

:::

Return concise results

Instruct subagents to return summaries, not raw data:

:::python

data_analyst = {
    "system_prompt": """Analyze the data and return:
    1. Key insights (3-5 bullet points)
    2. Overall confidence score
    3. Recommended next actions

    Do NOT include:
    - Raw data
    - Intermediate calculations
    - Detailed tool outputs

    Keep response under 300 words."""
}

:::

:::js

const dataAnalyst = {
  systemPrompt: `Analyze the data and return:
  1. Key insights (3-5 bullet points)
  2. Overall confidence score
  3. Recommended next actions

  Do NOT include:
  - Raw data
  - Intermediate calculations
  - Detailed tool outputs

  Keep response under 300 words.`,
};

:::

Common patterns

Multiple specialized subagents

Create specialized subagents for different domains:

:::python

from deepagents import create_deep_agent

subagents = [
    {
        "name": "data-collector",
        "description": "Gathers raw data from various sources",
        "system_prompt": "Collect comprehensive data on the topic",
        "tools": [web_search, api_call, database_query],
    },
    {
        "name": "data-analyzer",
        "description": "Analyzes collected data for insights",
        "system_prompt": "Analyze data and extract key insights",
        "tools": [statistical_analysis],
    },
    {
        "name": "report-writer",
        "description": "Writes polished reports from analysis",
        "system_prompt": "Create professional reports from insights",
        "tools": [format_document],
    },
]

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    system_prompt="You coordinate data analysis and reporting. Use subagents for specialized tasks.",
    subagents=subagents
)

:::

:::js

import { createDeepAgent } from "deepagents";

const subagents = [
  {
    name: "data-collector",
    description: "Gathers raw data from various sources",
    systemPrompt: "Collect comprehensive data on the topic",
    tools: [webSearch, apiCall, databaseQuery],
  },
  {
    name: "data-analyzer",
    description: "Analyzes collected data for insights",
    systemPrompt: "Analyze data and extract key insights",
    tools: [statisticalAnalysis],
  },
  {
    name: "report-writer",
    description: "Writes polished reports from analysis",
    systemPrompt: "Create professional reports from insights",
    tools: [formatDocument],
  },
];

const agent = createDeepAgent({
  model: "google_genai:gemini-3.1-pro-preview",
  systemPrompt: "You coordinate data analysis and reporting. Use subagents for specialized tasks.",
  subagents: subagents,
});

:::

Workflow:

Main agent creates high-level plan
Delegates data collection to data-collector
Passes results to data-analyzer
Sends insights to report-writer
Compiles final output

Each subagent works with clean context focused only on its task.

Context management

When you invoke a parent agent with runtime context, that context automatically propagates to all subagents. Each subagent run receives the same runtime context you passed on the parent invoke / ainvoke call.

This means tools running inside any subagent can access the same context values you provided to the parent:

:::python

from dataclasses import dataclass

from deepagents import create_deep_agent
from langchain.messages import HumanMessage
from langchain.tools import tool, ToolRuntime

@dataclass
class Context:
    user_id: str
    session_id: str

@tool
def get_user_data(query: str, runtime: ToolRuntime[Context]) -> str:
    """Fetch data for the current user."""
    user_id = runtime.context.user_id
    return f"Data for user {user_id}: {query}"

research_subagent = {
    "name": "researcher",
    "description": "Conducts research for the current user",
    "system_prompt": "You are a research assistant.",
    "tools": [get_user_data],
}

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    subagents=[research_subagent],
    context_schema=Context,
)

# Context flows to the researcher subagent and its tools automatically
result = await agent.invoke(
    {"messages": [HumanMessage("Look up my recent activity")]},
    context=Context(user_id="user-123", session_id="abc"),
)

:::

:::js

import { createDeepAgent } from "deepagents";
import { tool } from "langchain";
import type { ToolRuntime } from "@langchain/core/tools";
import { z } from "zod";

const contextSchema = z.object({
  userId: z.string(),
  sessionId: z.string(),
});

const getUserData = tool(
  async (input, runtime: ToolRuntime<unknown, typeof contextSchema>) => {
    const userId = runtime.context?.userId;
    return `Data for user ${userId}: ${input.query}`;
  },
  {
    name: "get_user_data",
    description: "Fetch data for the current user",
    schema: z.object({ query: z.string() }),
  }
);

const researchSubagent = {
  name: "researcher",
  description: "Conducts research for the current user",
  systemPrompt: "You are a research assistant.",
  tools: [getUserData],
};

const agent = createDeepAgent({
  model: "google_genai:gemini-3.1-pro-preview",
  subagents: [researchSubagent],
  contextSchema,
});

// Context flows to the researcher subagent and its tools automatically
const result = await agent.invoke(
  { messages: [new HumanMessage("Look up my recent activity")] },
  { context: { userId: "user-123", sessionId: "abc" } },
);

:::

Per-subagent context

All subagents receive the same parent context. To pass configuration that is specific to a particular subagent, use namespaced keys (prefix keys with the subagent name, for example researcher:max_depth) in a flat context mapping, or model those settings as separate fields on your context type:

:::python

from dataclasses import dataclass

from langchain.messages import HumanMessage
from langchain.tools import tool, ToolRuntime

@dataclass
class Context:
    user_id: str
    researcher_max_depth: int | None = None
    fact_checker_strict_mode: bool | None = None

result = await agent.invoke(
    {"messages": [HumanMessage("Research this and verify the claims")]},
    context=Context(
        user_id="user-123",
        researcher_max_depth=3,
        fact_checker_strict_mode=True,
    ),
)

@tool
def verify_claim(claim: str, runtime: ToolRuntime[Context]) -> str:
    """Verify a factual claim."""
    strict_mode = runtime.context.fact_checker_strict_mode or False
    if strict_mode:
        return strict_verification(claim)
    return basic_verification(claim)

:::

:::js

import { tool } from "langchain";
import type { ToolRuntime } from "@langchain/core/tools";
import { z } from "zod";

const contextSchema = z.object({
  userId: z.string(),
  researcherMaxDepth: z.number().optional(),
  factCheckerStrictMode: z.boolean().optional(),
});

const result = await agent.invoke(
  { messages: [new HumanMessage("Research this and verify the claims")] },
  {
    context: {
      userId: "user-123",                        // shared by all agents
      "researcher:maxDepth": 3,                  // only for researcher
      "fact-checker:strictMode": true,           // only for fact-checker
    },
  },
);

const verifyClaim = tool(
  async (input, runtime: ToolRuntime<unknown, typeof contextSchema>) => {
    const strictMode = runtime.context?.factCheckerStrictMode ?? false;
    if (strictMode) {
      return strictVerification(input.claim);
    }
    return basicVerification(input.claim);
  },
  {
    name: "verify_claim",
    description: "Verify a factual claim",
    schema: z.object({ claim: z.string() }),
  }
);

:::

Identifying which subagent called a tool

When the same tool is shared between the parent and multiple subagents, you can use the lc_agent_name metadata (the same value used in streaming) to determine which agent initiated the call:

:::python

from langchain.tools import tool, ToolRuntime

@tool
def shared_lookup(query: str, runtime: ToolRuntime) -> str:
    """Look up information."""
    agent_name = runtime.config.get("metadata", {}).get("lc_agent_name")
    if agent_name == "fact-checker":
        return strict_lookup(query)
    return general_lookup(query)

:::

:::js

import { tool } from "langchain";
import type { ToolRuntime } from "@langchain/core/tools";

const sharedLookup = tool(
  async (input, runtime: ToolRuntime) => {
    const agentName = runtime.config?.metadata?.lc_agent_name;
    if (agentName === "fact-checker") {
      return strictLookup(input.query);
    }
    return generalLookup(input.query);
  },
  {
    name: "shared_lookup",
    description: "Look up information from various sources",
    schema: z.object({ query: z.string() }),
  }
);

:::

You can combine both patterns—read agent-specific settings from runtime.context and read lc_agent_name from runtime.config metadata when branching tool behavior.

:::python

from langchain.tools import tool, ToolRuntime

@tool
def flexible_search(query: str, runtime: ToolRuntime[Context]) -> str:
    """Search with agent-specific settings."""
    agent_name = runtime.config.get("metadata", {}).get("lc_agent_name", "unknown")
    ctx = runtime.context
    if agent_name == "researcher":
        max_results = ctx.researcher_max_depth or 5
    else:
        max_results = 5
    include_raw = False

    return perform_search(query, max_results=max_results, include_raw=include_raw)

:::

:::js

const flexibleSearch = tool(
  async (input, runtime: ToolRuntime<unknown, typeof contextSchema>) => {
    const agentName = runtime.config?.metadata?.lc_agent_name ?? "unknown";
    const ctx = runtime.context;
    const maxResults =
      agentName === "researcher" ? ctx?.researcherMaxDepth ?? 5 : 5;
    const includeRaw = false;

    return performSearch(input.query, { maxResults, includeRaw });
  },
  {
    name: "flexible_search",
    description: "Search with agent-specific settings",
    schema: z.object({ query: z.string() }),
  }
);

:::

Troubleshooting

Subagent not being called

Problem: Main agent tries to do work itself instead of delegating.

Solutions:

Make descriptions more specific:

:::python

# ✅ Good
{"name": "research-specialist", "description": "Conducts in-depth research on specific topics using web search. Use when you need detailed information that requires multiple searches."}

# ❌ Bad
{"name": "helper", "description": "helps with stuff"}

:::

:::js

// ✅ Good
{ name: "research-specialist", description: "Conducts in-depth research on specific topics using web search. Use when you need detailed information that requires multiple searches." }

// ❌ Bad
{ name: "helper", description: "helps with stuff" }

:::

Instruct main agent to delegate:

:::python

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    system_prompt="""...your instructions...

    IMPORTANT: For complex tasks, delegate to your subagents using the task() tool.
    This keeps your context clean and improves results.""",
    subagents=[...]
)

:::

:::js

const agent = createDeepAgent({
  systemPrompt: `...your instructions...

  IMPORTANT: For complex tasks, delegate to your subagents using the task() tool.
  This keeps your context clean and improves results.`,
  subagents: [...]
});

:::

Context still getting bloated

Problem: Context fills up despite using subagents.

Solutions:

Instruct subagent to return concise results:

:::python

system_prompt="""...

IMPORTANT: Return only the essential summary.
Do NOT include raw data, intermediate search results, or detailed tool outputs.
Your response should be under 500 words."""

:::

:::js

systemPrompt: `...

IMPORTANT: Return only the essential summary.
Do NOT include raw data, intermediate search results, or detailed tool outputs.
Your response should be under 500 words.`

:::

Use filesystem for large data:

:::python

system_prompt="""When you gather large amounts of data:
1. Save raw data to /data/raw_results.txt
2. Process and analyze the data
3. Return only the analysis summary

This keeps context clean."""

:::

:::js

systemPrompt: `When you gather large amounts of data:
1. Save raw data to /data/raw_results.txt
2. Process and analyze the data
3. Return only the analysis summary

This keeps context clean.`

:::

Wrong subagent being selected

Problem: Main agent calls inappropriate subagent for the task.

Solution: Differentiate subagents clearly in descriptions:

:::python

subagents = [
    {
        "name": "quick-researcher",
        "description": "For simple, quick research questions that need 1-2 searches. Use when you need basic facts or definitions.",
    },
    {
        "name": "deep-researcher",
        "description": "For complex, in-depth research requiring multiple searches, synthesis, and analysis. Use for comprehensive reports.",
    }
]

:::

:::js

const subagents = [
  {
    name: "quick-researcher",
    description: "For simple, quick research questions that need 1-2 searches. Use when you need basic facts or definitions.",
  },
  {
    name: "deep-researcher",
    description: "For complex, in-depth research requiring multiple searches, synthesis, and analysis. Use for comprehensive reports.",
  }
];

::: :::

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Why use subagents?

Configuration

SubAgent (Dictionary-based)

CompiledSubAgent

Using SubAgent

Using CompiledSubAgent

Streaming

Structured output

The general-purpose subagent

Override the general-purpose subagent

When to use it

Skills inheritance

Best practices

Write clear descriptions

Keep system prompts detailed

Minimize tool sets

Choose models by task

Return concise results

Common patterns

Multiple specialized subagents

Context management

Per-subagent context

Identifying which subagent called a tool

Troubleshooting

Subagent not being called

Context still getting bloated

Wrong subagent being selected

FilesExpand file tree

subagents.mdx

Latest commit

History

subagents.mdx

File metadata and controls

Why use subagents?

Configuration

SubAgent (Dictionary-based)

CompiledSubAgent

Using SubAgent

Using CompiledSubAgent

Streaming

Structured output

The general-purpose subagent

Override the general-purpose subagent

When to use it

Skills inheritance

Best practices

Write clear descriptions

Keep system prompts detailed

Minimize tool sets

Choose models by task

Return concise results

Common patterns

Multiple specialized subagents

Context management

Per-subagent context

Identifying which subagent called a tool

Troubleshooting

Subagent not being called

Context still getting bloated

Wrong subagent being selected