pydantic-ai-harness
Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- currently Code Mode, which collapses many tool calls into one sandboxed Python execution. Use when the user mentions pydantic-ai-harness, CodeMode, Monty, code mode, or tool sandboxing, when they want an agent to run agent-written Python, or when a Pydantic AI agent would benefit from orchestrating multiple tool calls in a single sandboxed script.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- pydantic-ai-harness
- license
- MIT
- metadata
- { "author": "pydantic", "version": "0.1.0" }
- description
- Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- currently Code Mode, which collapses many tool calls into one sandboxed Python execution. Use when the user mentions pydantic-ai-harness, CodeMode, Monty, code mode, or tool sandboxing, when they want an agent to run agent-written Python, or when a Pydantic AI agent would benefit from orchestrating multiple tool calls in a single sandboxed script.
- compatibility
- Requires Python 3.10+ and pydantic-ai-slim>=1.95.1
02 资源文件 1
- 参考文档references/CODE-MODE.md5.2 KB
03 SKILL.md 正文
Building with Pydantic AI Harness
Pydantic AI Harness is the official capability library for Pydantic AI. Capabilities that need model or
framework support -- and those fundamental to every agent -- live in core pydantic-ai; optional,
batteries-included capabilities live here. Both are composed onto an agent through the same
capabilities=[...] API.
This skill covers the capabilities shipped by pydantic-ai-harness. For the core framework -- agents,
tools, structured output, hooks, and testing -- use the building-pydantic-ai-agents skill instead.
When to Use This Skill
Invoke this skill when:
- The user mentions
pydantic-ai-harness,CodeMode, code mode, or the Monty sandbox - An agent makes many sequential tool calls that could collapse into one sandboxed Python execution
- The user wants the model to write Python that loops, branches, aggregates, or parallelizes tool calls with
asyncio.gather - The user asks to sandbox or constrain the code an agent runs
Do not use this skill for:
- Core Pydantic AI usage -- building agents, adding tools, structured output, streaming, or testing (use
building-pydantic-ai-agents) - Capabilities that ship in core
pydantic-ai, such as web search, tool search, and thinking - The Pydantic validation library on its own (
pydantic/BaseModelwithout agents)
Supported Capabilities
| Capability | Description | Reference |
|---|---|---|
CodeMode |
Wraps eligible tools into a single sandboxed run_code tool so the model orchestrates them in Python |
Code Mode |
More capability areas are tracked in the capability matrix; as they stabilize, this skill grows to cover them.
Install
uv add pydantic-ai-harness
Each capability declares its own extra. Code Mode needs the Monty sandbox:
uv add "pydantic-ai-harness[codemode]" # `code-mode` is also accepted as an alias
Requires Python 3.10+ and pydantic-ai-slim>=1.95.1.
Quick Start
A harness capability is added to the agent like any other. Here CodeMode wraps an MCP server's tools into
a single run_code tool that the model drives with Python.
from pydantic_ai import Agent
from pydantic_ai.capabilities import MCP # MCP ships in core pydantic-ai
from pydantic_ai_harness import CodeMode
agent = Agent(
'anthropic:claude-sonnet-4-6',
capabilities=[
# native=False routes the MCP tools through a local toolset so CodeMode can wrap them.
# Without it, providers with native MCP run the tools server-side and bypass the sandbox.
MCP('https://hn.caseyjhand.com/mcp', native=False),
CodeMode(),
],
)
result = agent.run_sync(
'Across the top and best Hacker News feeds, find the most-discussed story with at '
'least 100 points and summarize its comment thread in one paragraph.'
)
print(result.output)
#> The most-discussed story clearing 100 points is ...
Instead of one model round-trip per tool call, the model writes a single Python script that fetches both
feeds with asyncio.gather, dedupes and ranks them in plain Python, and pulls the winning thread --
collapsing many calls into one run_code.
Key Practices
- Confirm a harness capability is actually needed. If core Pydantic AI tools and capabilities are enough, use the
building-pydantic-ai-agentsskill instead -- don't reach for the harness by default. - Read the reference before writing code. Each capability has its own configuration, constraints, and gotchas -- load the linked reference (e.g. Code Mode) first.
- Install the capability's extra. Importing
CodeModewithoutpydantic-ai-harness[codemode]raises anImportError; the Monty sandbox is an optional dependency.
Common Gotchas
native=Truetools bypassCodeMode. Provider-native MCP servers and web search execute server-side, sorun_codenever sees them. Construct them withnative=Falseto keep them local and wrappable.- The Monty sandbox is a Python subset. No class definitions, no third-party imports, and only a small stdlib allowlist -- read Code Mode before debugging generated code that fails to run.
CodeModeneeds its extra. Installpydantic-ai-harness[codemode], not the bare package.
04 同仓库更多 Skills
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.
motherduck-share-data
Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access/visibility/update modes, GRANT READ ON SHARE, attaching share URLs, UPDATE SHARE, and REFRESH DATABASE.
motherduck-security-governance
Explain MotherDuck security, governance, and access-control patterns. Use for any question about SOC 2, GDPR, compliance, data residency, regions, SSO, service accounts, token handling, tenant isolation, sharing boundaries, snapshots and recovery, or governance posture — including when a security_compliance_owner, technical_owner, or application_builder is evaluating MotherDuck.
motherduck-rest-api
MotherDuck REST API control-plane reference. Use when calling api.motherduck.com to provision service accounts, create, list, rotate, or revoke access tokens, configure Duckling instance sizes and read scaling, inspect active accounts, or mint Dive embed sessions. Not for SQL or data-plane query work.
motherduck-query
Execute DuckDB SQL queries against MotherDuck databases. Use when running analytics, aggregations, transformations, or any SQL operation. Covers query best practices, CTEs, window functions, QUALIFY, and performance optimization.
motherduck-pricing-roi
Explain MotherDuck pricing and ROI tradeoffs. Use for any pricing, cost, billing, plan-comparison, instance-sizing, chargeback, or budget question — when an economic_buyer, technical_owner, or analytics_lead asks about spend, budget guardrails, workload cost drivers, plan fit, vendor cost comparisons, or whether MotherDuck is worth adopting.